266 files changed, 4819 insertions, 2810 deletions

diff --git a/src/android/app/build.gradle.kts b/src/android/app/build.gradle.kts
index bab4f4d0f..9a47e2bd8 100644
--- a/src/android/app/build.gradle.kts
+++ b/src/android/app/build.gradle.kts
@@ -26,7 +26,7 @@ val autoVersion = (((System.currentTimeMillis() / 1000) - 1451606400) / 10).toIn
 android {
     namespace = "org.yuzu.yuzu_emu"
 
-    compileSdkVersion = "android-33"
+    compileSdkVersion = "android-34"
     ndkVersion = "25.2.9519653"
 
     buildFeatures {
@@ -51,7 +51,7 @@ android {
         // TODO If this is ever modified, change application_id in strings.xml
         applicationId = "org.yuzu.yuzu_emu"
         minSdk = 30
-        targetSdk = 33
+        targetSdk = 34
         versionName = getGitVersion()
 
         // If you want to use autoVersion for the versionCode, create a property in local.properties
diff --git a/src/android/app/src/main/AndroidManifest.xml b/src/android/app/src/main/AndroidManifest.xml
index e31ad69e2..51d949d65 100644
--- a/src/android/app/src/main/AndroidManifest.xml
+++ b/src/android/app/src/main/AndroidManifest.xml
@@ -13,6 +13,7 @@ SPDX-License-Identifier: GPL-3.0-or-later
 
     <uses-permission android:name="android.permission.INTERNET" />
     <uses-permission android:name="android.permission.FOREGROUND_SERVICE" />
+    <uses-permission android:name="android.permission.FOREGROUND_SERVICE_SPECIAL_USE" />
     <uses-permission android:name="android.permission.NFC" />
     <uses-permission android:name="android.permission.POST_NOTIFICATIONS" />
 
@@ -69,7 +70,9 @@ SPDX-License-Identifier: GPL-3.0-or-later
                 android:resource="@xml/nfc_tech_filter" />
         </activity>
 
-        <service android:name="org.yuzu.yuzu_emu.utils.ForegroundService"/>
+        <service android:name="org.yuzu.yuzu_emu.utils.ForegroundService" android:foregroundServiceType="specialUse">
+            <property android:name="android.app.PROPERTY_SPECIAL_USE_FGS_SUBTYPE" android:value="Keep emulation running in background"/>
+        </service>
 
         <provider
             android:name=".features.DocumentProvider"
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/NativeLibrary.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/NativeLibrary.kt
index f860cdd4b..9c32e044c 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/NativeLibrary.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/NativeLibrary.kt
@@ -286,7 +286,7 @@ object NativeLibrary {
     /**
      * Unpauses emulation from a paused state.
      */
-    external fun unPauseEmulation()
+    external fun unpauseEmulation()
 
     /**
      * Pauses emulation.
@@ -314,6 +314,21 @@ object NativeLibrary {
     external fun isPaused(): Boolean
 
     /**
+     * Mutes emulation sound
+     */
+    external fun muteAudio(): Boolean
+
+    /**
+     * Unmutes emulation sound
+     */
+    external fun unmuteAudio(): Boolean
+
+    /**
+     * Returns true if emulation audio is muted.
+     */
+    external fun isMuted(): Boolean
+
+    /**
      * Returns the performance stats for the current game
      */
     external fun getPerfStats(): DoubleArray
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/activities/EmulationActivity.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/activities/EmulationActivity.kt
index f0a6753a9..ae665ed2e 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/activities/EmulationActivity.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/activities/EmulationActivity.kt
@@ -27,13 +27,13 @@ import android.view.MotionEvent
 import android.view.Surface
 import android.view.View
 import android.view.inputmethod.InputMethodManager
+import android.widget.Toast
 import androidx.activity.viewModels
 import androidx.appcompat.app.AppCompatActivity
 import androidx.core.view.WindowCompat
 import androidx.core.view.WindowInsetsCompat
 import androidx.core.view.WindowInsetsControllerCompat
 import androidx.navigation.fragment.NavHostFragment
-import kotlin.math.roundToInt
 import org.yuzu.yuzu_emu.NativeLibrary
 import org.yuzu.yuzu_emu.R
 import org.yuzu.yuzu_emu.databinding.ActivityEmulationBinding
@@ -44,8 +44,10 @@ import org.yuzu.yuzu_emu.model.Game
 import org.yuzu.yuzu_emu.utils.ControllerMappingHelper
 import org.yuzu.yuzu_emu.utils.ForegroundService
 import org.yuzu.yuzu_emu.utils.InputHandler
+import org.yuzu.yuzu_emu.utils.MemoryUtil
 import org.yuzu.yuzu_emu.utils.NfcReader
 import org.yuzu.yuzu_emu.utils.ThemeHelper
+import kotlin.math.roundToInt
 
 class EmulationActivity : AppCompatActivity(), SensorEventListener {
     private lateinit var binding: ActivityEmulationBinding
@@ -63,6 +65,8 @@ class EmulationActivity : AppCompatActivity(), SensorEventListener {
 
     private val actionPause = "ACTION_EMULATOR_PAUSE"
     private val actionPlay = "ACTION_EMULATOR_PLAY"
+    private val actionMute = "ACTION_EMULATOR_MUTE"
+    private val actionUnmute = "ACTION_EMULATOR_UNMUTE"
 
     private val settingsViewModel: SettingsViewModel by viewModels()
 
@@ -102,6 +106,19 @@ class EmulationActivity : AppCompatActivity(), SensorEventListener {
         inputHandler = InputHandler()
         inputHandler.initialize()
 
+        val memoryUtil = MemoryUtil(this)
+        if (memoryUtil.isLessThan(8, MemoryUtil.Gb)) {
+            Toast.makeText(
+                this,
+                getString(
+                    R.string.device_memory_inadequate,
+                    memoryUtil.getDeviceRAM(),
+                    "8 ${getString(R.string.memory_gigabyte)}"
+                ),
+                Toast.LENGTH_LONG
+            ).show()
+        }
+
         // Start a foreground service to prevent the app from getting killed in the background
         val startIntent = Intent(this, ForegroundService::class.java)
         startForegroundService(startIntent)
@@ -305,6 +322,41 @@ class EmulationActivity : AppCompatActivity(), SensorEventListener {
             pictureInPictureActions.add(pauseRemoteAction)
         }
 
+        if (NativeLibrary.isMuted()) {
+            val unmuteIcon = Icon.createWithResource(
+                this@EmulationActivity,
+                R.drawable.ic_pip_unmute
+            )
+            val unmutePendingIntent = PendingIntent.getBroadcast(
+                this@EmulationActivity,
+                R.drawable.ic_pip_unmute,
+                Intent(actionUnmute),
+                pendingFlags
+            )
+            val unmuteRemoteAction = RemoteAction(
+                unmuteIcon,
+                getString(R.string.unmute),
+                getString(R.string.unmute),
+                unmutePendingIntent
+            )
+            pictureInPictureActions.add(unmuteRemoteAction)
+        } else {
+            val muteIcon = Icon.createWithResource(this@EmulationActivity, R.drawable.ic_pip_mute)
+            val mutePendingIntent = PendingIntent.getBroadcast(
+                this@EmulationActivity,
+                R.drawable.ic_pip_mute,
+                Intent(actionMute),
+                pendingFlags
+            )
+            val muteRemoteAction = RemoteAction(
+                muteIcon,
+                getString(R.string.mute),
+                getString(R.string.mute),
+                mutePendingIntent
+            )
+            pictureInPictureActions.add(muteRemoteAction)
+        }
+
         return this.apply { setActions(pictureInPictureActions) }
     }
 
@@ -322,10 +374,15 @@ class EmulationActivity : AppCompatActivity(), SensorEventListener {
     private var pictureInPictureReceiver = object : BroadcastReceiver() {
         override fun onReceive(context: Context?, intent: Intent) {
             if (intent.action == actionPlay) {
-                if (NativeLibrary.isPaused()) NativeLibrary.unPauseEmulation()
+                if (NativeLibrary.isPaused()) NativeLibrary.unpauseEmulation()
             } else if (intent.action == actionPause) {
                 if (!NativeLibrary.isPaused()) NativeLibrary.pauseEmulation()
             }
+            if (intent.action == actionUnmute) {
+                if (NativeLibrary.isMuted()) NativeLibrary.unmuteAudio()
+            } else if (intent.action == actionMute) {
+                if (!NativeLibrary.isMuted()) NativeLibrary.muteAudio()
+            }
             buildPictureInPictureParams()
         }
     }
@@ -339,6 +396,8 @@ class EmulationActivity : AppCompatActivity(), SensorEventListener {
             IntentFilter().apply {
                 addAction(actionPause)
                 addAction(actionPlay)
+                addAction(actionMute)
+                addAction(actionUnmute)
             }.also {
                 registerReceiver(pictureInPictureReceiver, it)
             }
@@ -347,6 +406,8 @@ class EmulationActivity : AppCompatActivity(), SensorEventListener {
                 unregisterReceiver(pictureInPictureReceiver)
             } catch (ignored: Exception) {
             }
+            // Always resume audio, since there is no UI button
+            if (NativeLibrary.isMuted()) NativeLibrary.unmuteAudio()
         }
     }
 
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/EmulationFragment.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/EmulationFragment.kt
index 4643418c1..09976db62 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/EmulationFragment.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/EmulationFragment.kt
@@ -714,7 +714,7 @@ class EmulationFragment : Fragment(), SurfaceHolder.Callback {
                 State.PAUSED -> {
                     Log.debug("[EmulationFragment] Resuming emulation.")
                     NativeLibrary.surfaceChanged(surface)
-                    NativeLibrary.unPauseEmulation()
+                    NativeLibrary.unpauseEmulation()
                 }
 
                 else -> Log.debug("[EmulationFragment] Bug, run called while already running.")
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/HomeSettingsFragment.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/HomeSettingsFragment.kt
index 6f8adbba5..5a36ffad4 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/HomeSettingsFragment.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/HomeSettingsFragment.kt
@@ -68,79 +68,109 @@ class HomeSettingsFragment : Fragment() {
     override fun onViewCreated(view: View, savedInstanceState: Bundle?) {
         mainActivity = requireActivity() as MainActivity
 
-        val optionsList: MutableList<HomeSetting> = mutableListOf(
-            HomeSetting(
-                R.string.advanced_settings,
-                R.string.settings_description,
-                R.drawable.ic_settings
-            ) { SettingsActivity.launch(requireContext(), SettingsFile.FILE_NAME_CONFIG, "") },
-            HomeSetting(
-                R.string.open_user_folder,
-                R.string.open_user_folder_description,
-                R.drawable.ic_folder_open
-            ) { openFileManager() },
-            HomeSetting(
-                R.string.preferences_theme,
-                R.string.theme_and_color_description,
-                R.drawable.ic_palette
-            ) { SettingsActivity.launch(requireContext(), Settings.SECTION_THEME, "") },
-            HomeSetting(
-                R.string.install_gpu_driver,
-                R.string.install_gpu_driver_description,
-                R.drawable.ic_exit
-            ) { driverInstaller() },
-            HomeSetting(
-                R.string.install_amiibo_keys,
-                R.string.install_amiibo_keys_description,
-                R.drawable.ic_nfc
-            ) { mainActivity.getAmiiboKey.launch(arrayOf("*/*")) },
-            HomeSetting(
-                R.string.install_game_content,
-                R.string.install_game_content_description,
-                R.drawable.ic_system_update_alt
-            ) { mainActivity.installGameUpdate.launch(arrayOf("*/*")) },
-            HomeSetting(
-                R.string.select_games_folder,
-                R.string.select_games_folder_description,
-                R.drawable.ic_add
-            ) {
-                mainActivity.getGamesDirectory.launch(Intent(Intent.ACTION_OPEN_DOCUMENT_TREE).data)
-            },
-            HomeSetting(
-                R.string.manage_save_data,
-                R.string.import_export_saves_description,
-                R.drawable.ic_save
-            ) {
-                ImportExportSavesFragment().show(
-                    parentFragmentManager,
-                    ImportExportSavesFragment.TAG
+        val optionsList: MutableList<HomeSetting> = mutableListOf<HomeSetting>().apply {
+            add(
+                HomeSetting(
+                    R.string.advanced_settings,
+                    R.string.settings_description,
+                    R.drawable.ic_settings
+                ) { SettingsActivity.launch(requireContext(), SettingsFile.FILE_NAME_CONFIG, "") }
+            )
+            add(
+                HomeSetting(
+                    R.string.open_user_folder,
+                    R.string.open_user_folder_description,
+                    R.drawable.ic_folder_open
+                ) { openFileManager() }
+            )
+            add(
+                HomeSetting(
+                    R.string.preferences_theme,
+                    R.string.theme_and_color_description,
+                    R.drawable.ic_palette
+                ) { SettingsActivity.launch(requireContext(), Settings.SECTION_THEME, "") }
+            )
+
+            if (GpuDriverHelper.supportsCustomDriverLoading()) {
+                add(
+                    HomeSetting(
+                        R.string.install_gpu_driver,
+                        R.string.install_gpu_driver_description,
+                        R.drawable.ic_exit
+                    ) { driverInstaller() }
                 )
-            },
-            HomeSetting(
-                R.string.install_prod_keys,
-                R.string.install_prod_keys_description,
-                R.drawable.ic_unlock
-            ) { mainActivity.getProdKey.launch(arrayOf("*/*")) },
-            HomeSetting(
-                R.string.install_firmware,
-                R.string.install_firmware_description,
-                R.drawable.ic_firmware
-            ) { mainActivity.getFirmware.launch(arrayOf("application/zip")) },
-            HomeSetting(
-                R.string.share_log,
-                R.string.share_log_description,
-                R.drawable.ic_log
-            ) { shareLog() },
-            HomeSetting(
-                R.string.about,
-                R.string.about_description,
-                R.drawable.ic_info_outline
-            ) {
-                exitTransition = MaterialSharedAxis(MaterialSharedAxis.X, true)
-                parentFragmentManager.primaryNavigationFragment?.findNavController()
-                    ?.navigate(R.id.action_homeSettingsFragment_to_aboutFragment)
             }
-        )
+
+            add(
+                HomeSetting(
+                    R.string.install_amiibo_keys,
+                    R.string.install_amiibo_keys_description,
+                    R.drawable.ic_nfc
+                ) { mainActivity.getAmiiboKey.launch(arrayOf("*/*")) }
+            )
+            add(
+                HomeSetting(
+                    R.string.install_game_content,
+                    R.string.install_game_content_description,
+                    R.drawable.ic_system_update_alt
+                ) { mainActivity.installGameUpdate.launch(arrayOf("*/*")) }
+            )
+            add(
+                HomeSetting(
+                    R.string.select_games_folder,
+                    R.string.select_games_folder_description,
+                    R.drawable.ic_add
+                ) {
+                    mainActivity.getGamesDirectory.launch(
+                        Intent(Intent.ACTION_OPEN_DOCUMENT_TREE).data
+                    )
+                }
+            )
+            add(
+                HomeSetting(
+                    R.string.manage_save_data,
+                    R.string.import_export_saves_description,
+                    R.drawable.ic_save
+                ) {
+                    ImportExportSavesFragment().show(
+                        parentFragmentManager,
+                        ImportExportSavesFragment.TAG
+                    )
+                }
+            )
+            add(
+                HomeSetting(
+                    R.string.install_prod_keys,
+                    R.string.install_prod_keys_description,
+                    R.drawable.ic_unlock
+                ) { mainActivity.getProdKey.launch(arrayOf("*/*")) }
+            )
+            add(
+                HomeSetting(
+                    R.string.install_firmware,
+                    R.string.install_firmware_description,
+                    R.drawable.ic_firmware
+                ) { mainActivity.getFirmware.launch(arrayOf("application/zip")) }
+            )
+            add(
+                HomeSetting(
+                    R.string.share_log,
+                    R.string.share_log_description,
+                    R.drawable.ic_log
+                ) { shareLog() }
+            )
+            add(
+                HomeSetting(
+                    R.string.about,
+                    R.string.about_description,
+                    R.drawable.ic_info_outline
+                ) {
+                    exitTransition = MaterialSharedAxis(MaterialSharedAxis.X, true)
+                    parentFragmentManager.primaryNavigationFragment?.findNavController()
+                        ?.navigate(R.id.action_homeSettingsFragment_to_aboutFragment)
+                }
+            )
+        }
 
         if (!BuildConfig.PREMIUM) {
             optionsList.add(
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/LongMessageDialogFragment.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/LongMessageDialogFragment.kt
new file mode 100644
index 000000000..b29b627e9
--- /dev/null
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/LongMessageDialogFragment.kt
@@ -0,0 +1,62 @@
+// SPDX-FileCopyrightText: 2023 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+package org.yuzu.yuzu_emu.fragments
+
+import android.app.Dialog
+import android.content.Intent
+import android.net.Uri
+import android.os.Bundle
+import androidx.fragment.app.DialogFragment
+import com.google.android.material.dialog.MaterialAlertDialogBuilder
+import org.yuzu.yuzu_emu.R
+
+class LongMessageDialogFragment : DialogFragment() {
+    override fun onCreateDialog(savedInstanceState: Bundle?): Dialog {
+        val titleId = requireArguments().getInt(TITLE)
+        val description = requireArguments().getString(DESCRIPTION)
+        val helpLinkId = requireArguments().getInt(HELP_LINK)
+
+        val dialog = MaterialAlertDialogBuilder(requireContext())
+            .setPositiveButton(R.string.close, null)
+            .setTitle(titleId)
+            .setMessage(description)
+
+        if (helpLinkId != 0) {
+            dialog.setNeutralButton(R.string.learn_more) { _, _ ->
+                openLink(getString(helpLinkId))
+            }
+        }
+
+        return dialog.show()
+    }
+
+    private fun openLink(link: String) {
+        val intent = Intent(Intent.ACTION_VIEW, Uri.parse(link))
+        startActivity(intent)
+    }
+
+    companion object {
+        const val TAG = "LongMessageDialogFragment"
+
+        private const val TITLE = "Title"
+        private const val DESCRIPTION = "Description"
+        private const val HELP_LINK = "Link"
+
+        fun newInstance(
+            titleId: Int,
+            description: String,
+            helpLinkId: Int = 0
+        ): LongMessageDialogFragment {
+            val dialog = LongMessageDialogFragment()
+            val bundle = Bundle()
+            bundle.apply {
+                putInt(TITLE, titleId)
+                putString(DESCRIPTION, description)
+                putInt(HELP_LINK, helpLinkId)
+            }
+            dialog.arguments = bundle
+            return dialog
+        }
+    }
+}
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/SearchFragment.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/SearchFragment.kt
index dd6c895fd..f54dccc69 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/SearchFragment.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/fragments/SearchFragment.kt
@@ -29,7 +29,6 @@ import org.yuzu.yuzu_emu.layout.AutofitGridLayoutManager
 import org.yuzu.yuzu_emu.model.Game
 import org.yuzu.yuzu_emu.model.GamesViewModel
 import org.yuzu.yuzu_emu.model.HomeViewModel
-import org.yuzu.yuzu_emu.utils.FileUtil
 
 class SearchFragment : Fragment() {
     private var _binding: FragmentSearchBinding? = null
@@ -128,10 +127,7 @@ class SearchFragment : Fragment() {
 
             R.id.chip_homebrew -> baseList.filter { it.isHomebrew }
 
-            R.id.chip_retail -> baseList.filter {
-                FileUtil.hasExtension(it.path, "xci") ||
-                    FileUtil.hasExtension(it.path, "nsp")
-            }
+            R.id.chip_retail -> baseList.filter { !it.isHomebrew }
 
             else -> baseList
         }
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/model/Game.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/model/Game.kt
index 6a048e39f..6527c64ab 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/model/Game.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/model/Game.kt
@@ -43,7 +43,7 @@ class Game(
 
     companion object {
         val extensions: Set<String> = HashSet(
-            listOf(".xci", ".nsp", ".nca", ".nro")
+            listOf("xci", "nsp", "nca", "nro")
         )
     }
 }
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/ui/main/MainActivity.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/ui/main/MainActivity.kt
index cc1d87f1b..f7d7aed1e 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/ui/main/MainActivity.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/ui/main/MainActivity.kt
@@ -4,6 +4,7 @@
 package org.yuzu.yuzu_emu.ui.main
 
 import android.content.Intent
+import android.net.Uri
 import android.os.Bundle
 import android.view.View
 import android.view.ViewGroup.MarginLayoutParams
@@ -42,6 +43,7 @@ import org.yuzu.yuzu_emu.features.settings.model.SettingsViewModel
 import org.yuzu.yuzu_emu.features.settings.ui.SettingsActivity
 import org.yuzu.yuzu_emu.features.settings.utils.SettingsFile
 import org.yuzu.yuzu_emu.fragments.IndeterminateProgressDialogFragment
+import org.yuzu.yuzu_emu.fragments.LongMessageDialogFragment
 import org.yuzu.yuzu_emu.fragments.MessageDialogFragment
 import org.yuzu.yuzu_emu.model.GamesViewModel
 import org.yuzu.yuzu_emu.model.HomeViewModel
@@ -294,7 +296,7 @@ class MainActivity : AppCompatActivity(), ThemeProvider {
                 return@registerForActivityResult
             }
 
-            if (!FileUtil.hasExtension(result, "keys")) {
+            if (FileUtil.getExtension(result) != "keys") {
                 MessageDialogFragment.newInstance(
                     R.string.reading_keys_failure,
                     R.string.install_prod_keys_failure_extension_description
@@ -391,7 +393,7 @@ class MainActivity : AppCompatActivity(), ThemeProvider {
                 return@registerForActivityResult
             }
 
-            if (!FileUtil.hasExtension(result, "bin")) {
+            if (FileUtil.getExtension(result) != "bin") {
                 MessageDialogFragment.newInstance(
                     R.string.reading_keys_failure,
                     R.string.install_amiibo_keys_failure_extension_description
@@ -481,62 +483,110 @@ class MainActivity : AppCompatActivity(), ThemeProvider {
             }
         }
 
-    val installGameUpdate =
-        registerForActivityResult(ActivityResultContracts.OpenDocument()) {
-            if (it == null) {
-                return@registerForActivityResult
-            }
-
+    val installGameUpdate = registerForActivityResult(
+        ActivityResultContracts.OpenMultipleDocuments()
+    ) { documents: List<Uri> ->
+        if (documents.isNotEmpty()) {
             IndeterminateProgressDialogFragment.newInstance(
                 this@MainActivity,
                 R.string.install_game_content
             ) {
-                val result = NativeLibrary.installFileToNand(it.toString())
+                var installSuccess = 0
+                var installOverwrite = 0
+                var errorBaseGame = 0
+                var errorExtension = 0
+                var errorOther = 0
+                var errorTotal = 0
                 lifecycleScope.launch {
-                    withContext(Dispatchers.Main) {
-                        when (result) {
+                    documents.forEach {
+                        when (NativeLibrary.installFileToNand(it.toString())) {
                             NativeLibrary.InstallFileToNandResult.Success -> {
-                                Toast.makeText(
-                                    applicationContext,
-                                    R.string.install_game_content_success,
-                                    Toast.LENGTH_SHORT
-                                ).show()
+                                installSuccess += 1
                             }
 
                             NativeLibrary.InstallFileToNandResult.SuccessFileOverwritten -> {
-                                Toast.makeText(
-                                    applicationContext,
-                                    R.string.install_game_content_success_overwrite,
-                                    Toast.LENGTH_SHORT
-                                ).show()
+                                installOverwrite += 1
                             }
 
                             NativeLibrary.InstallFileToNandResult.ErrorBaseGame -> {
-                                MessageDialogFragment.newInstance(
-                                    R.string.install_game_content_failure,
-                                    R.string.install_game_content_failure_base
-                                ).show(supportFragmentManager, MessageDialogFragment.TAG)
+                                errorBaseGame += 1
                             }
 
                             NativeLibrary.InstallFileToNandResult.ErrorFilenameExtension -> {
-                                MessageDialogFragment.newInstance(
-                                    R.string.install_game_content_failure,
-                                    R.string.install_game_content_failure_file_extension,
-                                    R.string.install_game_content_help_link
-                                ).show(supportFragmentManager, MessageDialogFragment.TAG)
+                                errorExtension += 1
                             }
 
                             else -> {
-                                MessageDialogFragment.newInstance(
-                                    R.string.install_game_content_failure,
-                                    R.string.install_game_content_failure_description,
-                                    R.string.install_game_content_help_link
-                                ).show(supportFragmentManager, MessageDialogFragment.TAG)
+                                errorOther += 1
                             }
                         }
                     }
+                    withContext(Dispatchers.Main) {
+                        val separator = System.getProperty("line.separator") ?: "\n"
+                        val installResult = StringBuilder()
+                        if (installSuccess > 0) {
+                            installResult.append(
+                                getString(
+                                    R.string.install_game_content_success_install,
+                                    installSuccess
+                                )
+                            )
+                            installResult.append(separator)
+                        }
+                        if (installOverwrite > 0) {
+                            installResult.append(
+                                getString(
+                                    R.string.install_game_content_success_overwrite,
+                                    installOverwrite
+                                )
+                            )
+                            installResult.append(separator)
+                        }
+                        errorTotal = errorBaseGame + errorExtension + errorOther
+                        if (errorTotal > 0) {
+                            installResult.append(separator)
+                            installResult.append(
+                                getString(
+                                    R.string.install_game_content_failed_count,
+                                    errorTotal
+                                )
+                            )
+                            installResult.append(separator)
+                            if (errorBaseGame > 0) {
+                                installResult.append(separator)
+                                installResult.append(
+                                    getString(R.string.install_game_content_failure_base)
+                                )
+                                installResult.append(separator)
+                            }
+                            if (errorExtension > 0) {
+                                installResult.append(separator)
+                                installResult.append(
+                                    getString(R.string.install_game_content_failure_file_extension)
+                                )
+                                installResult.append(separator)
+                            }
+                            if (errorOther > 0) {
+                                installResult.append(
+                                    getString(R.string.install_game_content_failure_description)
+                                )
+                                installResult.append(separator)
+                            }
+                            LongMessageDialogFragment.newInstance(
+                                R.string.install_game_content_failure,
+                                installResult.toString().trim(),
+                                R.string.install_game_content_help_link
+                            ).show(supportFragmentManager, LongMessageDialogFragment.TAG)
+                        } else {
+                            LongMessageDialogFragment.newInstance(
+                                R.string.install_game_content_success,
+                                installResult.toString().trim()
+                            ).show(supportFragmentManager, LongMessageDialogFragment.TAG)
+                        }
+                    }
                 }
-                return@newInstance result
+                return@newInstance installSuccess + installOverwrite + errorTotal
             }.show(supportFragmentManager, IndeterminateProgressDialogFragment.TAG)
         }
+    }
 }
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/FileUtil.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/FileUtil.kt
index 9f3bbe56f..142af5f26 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/FileUtil.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/FileUtil.kt
@@ -7,7 +7,6 @@ import android.content.Context
 import android.database.Cursor
 import android.net.Uri
 import android.provider.DocumentsContract
-import android.provider.OpenableColumns
 import androidx.documentfile.provider.DocumentFile
 import java.io.BufferedInputStream
 import java.io.File
@@ -185,19 +184,18 @@ object FileUtil {
 
     /**
      * Get file display name from given path
-     * @param path content uri path
+     * @param uri content uri
      * @return String display name
      */
-    fun getFilename(context: Context, path: String): String {
-        val resolver = context.contentResolver
+    fun getFilename(uri: Uri): String {
+        val resolver = YuzuApplication.appContext.contentResolver
         val columns = arrayOf(
             DocumentsContract.Document.COLUMN_DISPLAY_NAME
         )
         var filename = ""
         var c: Cursor? = null
         try {
-            val mUri = Uri.parse(path)
-            c = resolver.query(mUri, columns, null, null, null)
+            c = resolver.query(uri, columns, null, null, null)
             c!!.moveToNext()
             filename = c.getString(0)
         } catch (e: Exception) {
@@ -326,25 +324,9 @@ object FileUtil {
         }
     }
 
-    fun hasExtension(path: String, extension: String): Boolean =
-        path.substring(path.lastIndexOf(".") + 1).contains(extension)
-
-    fun hasExtension(uri: Uri, extension: String): Boolean {
-        val fileName: String?
-        val cursor = YuzuApplication.appContext.contentResolver.query(uri, null, null, null, null)
-        val nameIndex = cursor?.getColumnIndex(OpenableColumns.DISPLAY_NAME)
-        cursor?.moveToFirst()
-
-        if (nameIndex == null) {
-            return false
-        }
-
-        fileName = cursor.getString(nameIndex)
-        cursor.close()
-
-        if (fileName == null) {
-            return false
-        }
-        return fileName.substring(fileName.lastIndexOf(".") + 1).contains(extension)
+    fun getExtension(uri: Uri): String {
+        val fileName = getFilename(uri)
+        return fileName.substring(fileName.lastIndexOf(".") + 1)
+            .lowercase()
     }
 }
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GameHelper.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GameHelper.kt
index ee9f3e570..f8e7eeca7 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GameHelper.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GameHelper.kt
@@ -6,7 +6,6 @@ package org.yuzu.yuzu_emu.utils
 import android.content.SharedPreferences
 import android.net.Uri
 import androidx.preference.PreferenceManager
-import java.util.*
 import kotlinx.serialization.encodeToString
 import kotlinx.serialization.json.Json
 import org.yuzu.yuzu_emu.NativeLibrary
@@ -33,15 +32,9 @@ object GameHelper {
         val children = FileUtil.listFiles(context, gamesUri)
         for (file in children) {
             if (!file.isDirectory) {
-                val filename = file.uri.toString()
-                val extensionStart = filename.lastIndexOf('.')
-                if (extensionStart > 0) {
-                    val fileExtension = filename.substring(extensionStart)
-
-                    // Check that the file has an extension we care about before trying to read out of it.
-                    if (Game.extensions.contains(fileExtension.lowercase(Locale.getDefault()))) {
-                        games.add(getGame(filename))
-                    }
+                // Check that the file has an extension we care about before trying to read out of it.
+                if (Game.extensions.contains(FileUtil.getExtension(file.uri))) {
+                    games.add(getGame(file.uri))
                 }
             }
         }
@@ -59,21 +52,19 @@ object GameHelper {
         return games.toList()
     }
 
-    private fun getGame(filePath: String): Game {
+    private fun getGame(uri: Uri): Game {
+        val filePath = uri.toString()
         var name = NativeLibrary.getTitle(filePath)
 
         // If the game's title field is empty, use the filename.
         if (name.isEmpty()) {
-            name = filePath.substring(filePath.lastIndexOf("/") + 1)
+            name = FileUtil.getFilename(uri)
         }
         var gameId = NativeLibrary.getGameId(filePath)
 
         // If the game's ID field is empty, use the filename without extension.
         if (gameId.isEmpty()) {
-            gameId = filePath.substring(
-                filePath.lastIndexOf("/") + 1,
-                filePath.lastIndexOf(".")
-            )
+            gameId = name.substring(0, name.lastIndexOf("."))
         }
 
         val newGame = Game(
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GpuDriverHelper.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GpuDriverHelper.kt
index dad159481..1d4695a2a 100644
--- a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GpuDriverHelper.kt
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/GpuDriverHelper.kt
@@ -113,6 +113,8 @@ object GpuDriverHelper {
         initializeDriverParameters(context)
     }
 
+    external fun supportsCustomDriverLoading(): Boolean
+
     // Parse the custom driver metadata to retrieve the name.
     val customDriverName: String?
         get() {
diff --git a/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/MemoryUtil.kt b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/MemoryUtil.kt
new file mode 100644
index 000000000..18e5fa0b0
--- /dev/null
+++ b/src/android/app/src/main/java/org/yuzu/yuzu_emu/utils/MemoryUtil.kt
@@ -0,0 +1,59 @@
+// SPDX-FileCopyrightText: 2023 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+package org.yuzu.yuzu_emu.utils
+
+import android.app.ActivityManager
+import android.content.Context
+import org.yuzu.yuzu_emu.R
+import java.util.Locale
+
+class MemoryUtil(val context: Context) {
+
+    private val Long.floatForm: String
+        get() = String.format(Locale.ROOT, "%.2f", this.toDouble())
+
+    private fun bytesToSizeUnit(size: Long): String {
+        return when {
+            size < Kb -> "${size.floatForm} ${context.getString(R.string.memory_byte)}"
+            size < Mb -> "${(size / Kb).floatForm} ${context.getString(R.string.memory_kilobyte)}"
+            size < Gb -> "${(size / Mb).floatForm} ${context.getString(R.string.memory_megabyte)}"
+            size < Tb -> "${(size / Gb).floatForm} ${context.getString(R.string.memory_gigabyte)}"
+            size < Pb -> "${(size / Tb).floatForm} ${context.getString(R.string.memory_terabyte)}"
+            size < Eb -> "${(size / Pb).floatForm} ${context.getString(R.string.memory_petabyte)}"
+            else -> "${(size / Eb).floatForm} ${context.getString(R.string.memory_exabyte)}"
+        }
+    }
+
+    private val totalMemory =
+        with(context.getSystemService(Context.ACTIVITY_SERVICE) as ActivityManager) {
+            val memInfo = ActivityManager.MemoryInfo()
+            getMemoryInfo(memInfo)
+            memInfo.totalMem
+        }
+
+    fun isLessThan(minimum: Int, size: Long): Boolean {
+        return when (size) {
+            Kb -> totalMemory < Mb && totalMemory < minimum
+            Mb -> totalMemory < Gb && (totalMemory / Mb) < minimum
+            Gb -> totalMemory < Tb && (totalMemory / Gb) < minimum
+            Tb -> totalMemory < Pb && (totalMemory / Tb) < minimum
+            Pb -> totalMemory < Eb && (totalMemory / Pb) < minimum
+            Eb -> totalMemory / Eb < minimum
+            else -> totalMemory < Kb && totalMemory < minimum
+        }
+    }
+
+    fun getDeviceRAM(): String {
+        return bytesToSizeUnit(totalMemory)
+    }
+
+    companion object {
+        const val Kb: Long = 1024
+        const val Mb = Kb * 1024
+        const val Gb = Mb * 1024
+        const val Tb = Gb * 1024
+        const val Pb = Tb * 1024
+        const val Eb = Pb * 1024
+    }
+}
diff --git a/src/android/app/src/main/jni/CMakeLists.txt b/src/android/app/src/main/jni/CMakeLists.txt
index 041781577..e2ed08e9f 100644
--- a/src/android/app/src/main/jni/CMakeLists.txt
+++ b/src/android/app/src/main/jni/CMakeLists.txt
@@ -14,7 +14,6 @@ add_library(yuzu-android SHARED
     id_cache.cpp
     id_cache.h
     native.cpp
-    native.h
 )
 
 set_property(TARGET yuzu-android PROPERTY IMPORTED_LOCATION ${FFmpeg_LIBRARY_DIR})
diff --git a/src/android/app/src/main/jni/native.cpp b/src/android/app/src/main/jni/native.cpp
index f9617202b..8bc6a4a04 100644
--- a/src/android/app/src/main/jni/native.cpp
+++ b/src/android/app/src/main/jni/native.cpp
@@ -14,6 +14,7 @@
 #include <android/api-level.h>
 #include <android/native_window_jni.h>
 #include <core/loader/nro.h>
+#include <jni.h>
 
 #include "common/detached_tasks.h"
 #include "common/dynamic_library.h"
@@ -59,6 +60,9 @@
 #include "video_core/rasterizer_interface.h"
 #include "video_core/renderer_base.h"
 
+#define jconst [[maybe_unused]] const auto
+#define jauto [[maybe_unused]] auto
+
 namespace {
 
 class EmulationSession final {
@@ -98,8 +102,8 @@ public:
     }
 
     int InstallFileToNand(std::string filename) {
-        const auto copy_func = [](const FileSys::VirtualFile& src, const FileSys::VirtualFile& dest,
-                                  std::size_t block_size) {
+        jconst copy_func = [](const FileSys::VirtualFile& src, const FileSys::VirtualFile& dest,
+                              std::size_t block_size) {
             if (src == nullptr || dest == nullptr) {
                 return false;
             }
@@ -108,10 +112,10 @@ public:
             }
 
             using namespace Common::Literals;
-            std::vector<u8> buffer(1_MiB);
+            [[maybe_unused]] std::vector<u8> buffer(1_MiB);
 
             for (std::size_t i = 0; i < src->GetSize(); i += buffer.size()) {
-                const auto read = src->Read(buffer.data(), buffer.size(), i);
+                jconst read = src->Read(buffer.data(), buffer.size(), i);
                 dest->Write(buffer.data(), read, i);
             }
             return true;
@@ -128,14 +132,14 @@ public:
         m_system.SetContentProvider(std::make_unique<FileSys::ContentProviderUnion>());
         m_system.GetFileSystemController().CreateFactories(*m_vfs);
 
-        std::shared_ptr<FileSys::NSP> nsp;
+        [[maybe_unused]] std::shared_ptr<FileSys::NSP> nsp;
         if (filename.ends_with("nsp")) {
             nsp = std::make_shared<FileSys::NSP>(m_vfs->OpenFile(filename, FileSys::Mode::Read));
             if (nsp->IsExtractedType()) {
                 return InstallError;
             }
         } else if (filename.ends_with("xci")) {
-            const auto xci =
+            jconst xci =
                 std::make_shared<FileSys::XCI>(m_vfs->OpenFile(filename, FileSys::Mode::Read));
             nsp = xci->GetSecurePartitionNSP();
         } else {
@@ -150,7 +154,7 @@ public:
             return InstallError;
         }
 
-        const auto res = m_system.GetFileSystemController().GetUserNANDContents()->InstallEntry(
+        jconst res = m_system.GetFileSystemController().GetUserNANDContents()->InstallEntry(
             *nsp, true, copy_func);
 
         switch (res) {
@@ -233,10 +237,11 @@ public:
         m_system.SetFilesystem(m_vfs);
 
         // Initialize system.
-        auto android_keyboard = std::make_unique<SoftwareKeyboard::AndroidKeyboard>();
+        jauto android_keyboard = std::make_unique<SoftwareKeyboard::AndroidKeyboard>();
         m_software_keyboard = android_keyboard.get();
         m_system.SetShuttingDown(false);
         m_system.ApplySettings();
+        Settings::LogSettings();
         m_system.HIDCore().ReloadInputDevices();
         m_system.SetAppletFrontendSet({
             nullptr,                     // Amiibo Settings
@@ -330,7 +335,7 @@ public:
 
         while (true) {
             {
-                std::unique_lock lock(m_mutex);
+                [[maybe_unused]] std::unique_lock lock(m_mutex);
                 if (m_cv.wait_for(lock, std::chrono::milliseconds(800),
                                   [&]() { return !m_is_running; })) {
                     // Emulation halted.
@@ -362,7 +367,7 @@ public:
     }
 
     bool IsHandheldOnly() {
-        const auto npad_style_set = m_system.HIDCore().GetSupportedStyleTag();
+        jconst npad_style_set = m_system.HIDCore().GetSupportedStyleTag();
 
         if (npad_style_set.fullkey == 1) {
             return false;
@@ -375,17 +380,17 @@ public:
         return !Settings::values.use_docked_mode.GetValue();
     }
 
-    void SetDeviceType(int index, int type) {
-        auto controller = m_system.HIDCore().GetEmulatedControllerByIndex(index);
+    void SetDeviceType([[maybe_unused]] int index, int type) {
+        jauto controller = m_system.HIDCore().GetEmulatedControllerByIndex(index);
         controller->SetNpadStyleIndex(static_cast<Core::HID::NpadStyleIndex>(type));
     }
 
-    void OnGamepadConnectEvent(int index) {
-        auto controller = m_system.HIDCore().GetEmulatedControllerByIndex(index);
+    void OnGamepadConnectEvent([[maybe_unused]] int index) {
+        jauto controller = m_system.HIDCore().GetEmulatedControllerByIndex(index);
 
         // Ensure that player1 is configured correctly and handheld disconnected
         if (controller->GetNpadIdType() == Core::HID::NpadIdType::Player1) {
-            auto handheld =
+            jauto handheld =
                 m_system.HIDCore().GetEmulatedController(Core::HID::NpadIdType::Handheld);
 
             if (controller->GetNpadStyleIndex() == Core::HID::NpadStyleIndex::Handheld) {
@@ -397,7 +402,8 @@ public:
 
         // Ensure that handheld is configured correctly and player 1 disconnected
         if (controller->GetNpadIdType() == Core::HID::NpadIdType::Handheld) {
-            auto player1 = m_system.HIDCore().GetEmulatedController(Core::HID::NpadIdType::Player1);
+            jauto player1 =
+                m_system.HIDCore().GetEmulatedController(Core::HID::NpadIdType::Player1);
 
             if (controller->GetNpadStyleIndex() != Core::HID::NpadStyleIndex::Handheld) {
                 player1->SetNpadStyleIndex(Core::HID::NpadStyleIndex::Handheld);
@@ -411,8 +417,8 @@ public:
         }
     }
 
-    void OnGamepadDisconnectEvent(int index) {
-        auto controller = m_system.HIDCore().GetEmulatedControllerByIndex(index);
+    void OnGamepadDisconnectEvent([[maybe_unused]] int index) {
+        jauto controller = m_system.HIDCore().GetEmulatedControllerByIndex(index);
         controller->Disconnect();
     }
 
@@ -428,7 +434,7 @@ private:
     };
 
     RomMetadata GetRomMetadata(const std::string& path) {
-        if (auto search = m_rom_metadata_cache.find(path); search != m_rom_metadata_cache.end()) {
+        if (jauto search = m_rom_metadata_cache.find(path); search != m_rom_metadata_cache.end()) {
             return search->second;
         }
 
@@ -436,14 +442,14 @@ private:
     }
 
     RomMetadata CacheRomMetadata(const std::string& path) {
-        const auto file = Core::GetGameFileFromPath(m_vfs, path);
-        auto loader = Loader::GetLoader(EmulationSession::GetInstance().System(), file, 0, 0);
+        jconst file = Core::GetGameFileFromPath(m_vfs, path);
+        jauto loader = Loader::GetLoader(EmulationSession::GetInstance().System(), file, 0, 0);
 
         RomMetadata entry;
         loader->ReadTitle(entry.title);
         loader->ReadIcon(entry.icon);
         if (loader->GetFileType() == Loader::FileType::NRO) {
-            auto loader_nro = dynamic_cast<Loader::AppLoader_NRO*>(loader.get());
+            jauto loader_nro = dynamic_cast<Loader::AppLoader_NRO*>(loader.get());
             entry.isHomebrew = loader_nro->IsHomebrew();
         } else {
             entry.isHomebrew = false;
@@ -514,7 +520,7 @@ static Core::SystemResultStatus RunEmulation(const std::string& filepath) {
 
     SCOPE_EXIT({ EmulationSession::GetInstance().ShutdownEmulation(); });
 
-    const auto result = EmulationSession::GetInstance().InitializeEmulation(filepath);
+    jconst result = EmulationSession::GetInstance().InitializeEmulation(filepath);
     if (result != Core::SystemResultStatus::Success) {
         return result;
     }
@@ -526,83 +532,104 @@ static Core::SystemResultStatus RunEmulation(const std::string& filepath) {
 
 extern "C" {
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_surfaceChanged(JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz,
-                                                          jobject surf) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_surfaceChanged(JNIEnv* env, jobject instance,
+                                                          [[maybe_unused]] jobject surf) {
     EmulationSession::GetInstance().SetNativeWindow(ANativeWindow_fromSurface(env, surf));
     EmulationSession::GetInstance().SurfaceChanged();
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_surfaceDestroyed(JNIEnv* env,
-                                                            [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_surfaceDestroyed(JNIEnv* env, jobject instance) {
     ANativeWindow_release(EmulationSession::GetInstance().NativeWindow());
     EmulationSession::GetInstance().SetNativeWindow(nullptr);
     EmulationSession::GetInstance().SurfaceChanged();
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_setAppDirectory(JNIEnv* env,
-                                                           [[maybe_unused]] jclass clazz,
-                                                           jstring j_directory) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_setAppDirectory(JNIEnv* env, jobject instance,
+                                                           [[maybe_unused]] jstring j_directory) {
     Common::FS::SetAppDirectory(GetJString(env, j_directory));
 }
 
-int Java_org_yuzu_yuzu_1emu_NativeLibrary_installFileToNand(JNIEnv* env,
-                                                            [[maybe_unused]] jclass clazz,
-                                                            jstring j_file) {
+int Java_org_yuzu_yuzu_1emu_NativeLibrary_installFileToNand(JNIEnv* env, jobject instance,
+                                                            [[maybe_unused]] jstring j_file) {
     return EmulationSession::GetInstance().InstallFileToNand(GetJString(env, j_file));
 }
 
-void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_initializeGpuDriver(
-    JNIEnv* env, [[maybe_unused]] jclass clazz, jstring hook_lib_dir, jstring custom_driver_dir,
-    jstring custom_driver_name, jstring file_redirect_dir) {
+void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_initializeGpuDriver(JNIEnv* env, jclass clazz,
+                                                                       jstring hook_lib_dir,
+                                                                       jstring custom_driver_dir,
+                                                                       jstring custom_driver_name,
+                                                                       jstring file_redirect_dir) {
     EmulationSession::GetInstance().InitializeGpuDriver(
         GetJString(env, hook_lib_dir), GetJString(env, custom_driver_dir),
         GetJString(env, custom_driver_name), GetJString(env, file_redirect_dir));
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_reloadKeys(JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz) {
+[[maybe_unused]] static bool CheckKgslPresent() {
+    constexpr auto KgslPath{"/dev/kgsl-3d0"};
+
+    return access(KgslPath, F_OK) == 0;
+}
+
+[[maybe_unused]] bool SupportsCustomDriver() {
+    return android_get_device_api_level() >= 28 && CheckKgslPresent();
+}
+
+jboolean JNICALL Java_org_yuzu_yuzu_1emu_utils_GpuDriverHelper_supportsCustomDriverLoading(
+    JNIEnv* env, jobject instance) {
+#ifdef ARCHITECTURE_arm64
+    // If the KGSL device exists custom drivers can be loaded using adrenotools
+    return SupportsCustomDriver();
+#else
+    return false;
+#endif
+}
+
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_reloadKeys(JNIEnv* env, jclass clazz) {
     Core::Crypto::KeyManager::Instance().ReloadKeys();
     return static_cast<jboolean>(Core::Crypto::KeyManager::Instance().AreKeysLoaded());
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_unPauseEmulation([[maybe_unused]] JNIEnv* env,
-                                                            [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_unpauseEmulation(JNIEnv* env, jclass clazz) {
     EmulationSession::GetInstance().UnPauseEmulation();
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_pauseEmulation([[maybe_unused]] JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_pauseEmulation(JNIEnv* env, jclass clazz) {
     EmulationSession::GetInstance().PauseEmulation();
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_stopEmulation([[maybe_unused]] JNIEnv* env,
-                                                         [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_stopEmulation(JNIEnv* env, jclass clazz) {
     EmulationSession::GetInstance().HaltEmulation();
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_resetRomMetadata([[maybe_unused]] JNIEnv* env,
-                                                            [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_resetRomMetadata(JNIEnv* env, jclass clazz) {
     EmulationSession::GetInstance().ResetRomMetadata();
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isRunning([[maybe_unused]] JNIEnv* env,
-                                                         [[maybe_unused]] jclass clazz) {
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isRunning(JNIEnv* env, jclass clazz) {
     return static_cast<jboolean>(EmulationSession::GetInstance().IsRunning());
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isPaused([[maybe_unused]] JNIEnv* env,
-                                                        [[maybe_unused]] jclass clazz) {
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isPaused(JNIEnv* env, jclass clazz) {
     return static_cast<jboolean>(EmulationSession::GetInstance().IsPaused());
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isHandheldOnly([[maybe_unused]] JNIEnv* env,
-                                                              [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_muteAduio(JNIEnv* env, jclass clazz) {
+    Settings::values.audio_muted = true;
+}
+
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_unmuteAudio(JNIEnv* env, jclass clazz) {
+    Settings::values.audio_muted = false;
+}
+
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isMuted(JNIEnv* env, jclass clazz) {
+    return static_cast<jboolean>(Settings::values.audio_muted.GetValue());
+}
+
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isHandheldOnly(JNIEnv* env, jclass clazz) {
     return EmulationSession::GetInstance().IsHandheldOnly();
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_setDeviceType([[maybe_unused]] JNIEnv* env,
-                                                             [[maybe_unused]] jclass clazz,
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_setDeviceType(JNIEnv* env, jclass clazz,
                                                              jint j_device, jint j_type) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().SetDeviceType(j_device, j_type);
@@ -610,8 +637,7 @@ jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_setDeviceType([[maybe_unused]] JN
     return static_cast<jboolean>(true);
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadConnectEvent([[maybe_unused]] JNIEnv* env,
-                                                                     [[maybe_unused]] jclass clazz,
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadConnectEvent(JNIEnv* env, jclass clazz,
                                                                      jint j_device) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().OnGamepadConnectEvent(j_device);
@@ -619,17 +645,16 @@ jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadConnectEvent([[maybe_unu
     return static_cast<jboolean>(true);
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadDisconnectEvent(
-    [[maybe_unused]] JNIEnv* env, [[maybe_unused]] jclass clazz, jint j_device) {
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadDisconnectEvent(JNIEnv* env, jclass clazz,
+                                                                        jint j_device) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().OnGamepadDisconnectEvent(j_device);
     }
     return static_cast<jboolean>(true);
 }
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadButtonEvent([[maybe_unused]] JNIEnv* env,
-                                                                    [[maybe_unused]] jclass clazz,
-                                                                    [[maybe_unused]] jint j_device,
-                                                                    jint j_button, jint action) {
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadButtonEvent(JNIEnv* env, jclass clazz,
+                                                                    jint j_device, jint j_button,
+                                                                    jint action) {
     if (EmulationSession::GetInstance().IsRunning()) {
         // Ensure gamepad is connected
         EmulationSession::GetInstance().OnGamepadConnectEvent(j_device);
@@ -639,8 +664,7 @@ jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadButtonEvent([[maybe_unus
     return static_cast<jboolean>(true);
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadJoystickEvent([[maybe_unused]] JNIEnv* env,
-                                                                      [[maybe_unused]] jclass clazz,
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadJoystickEvent(JNIEnv* env, jclass clazz,
                                                                       jint j_device, jint stick_id,
                                                                       jfloat x, jfloat y) {
     if (EmulationSession::GetInstance().IsRunning()) {
@@ -650,9 +674,8 @@ jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadJoystickEvent([[maybe_un
 }
 
 jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadMotionEvent(
-    [[maybe_unused]] JNIEnv* env, [[maybe_unused]] jclass clazz, jint j_device,
-    jlong delta_timestamp, jfloat gyro_x, jfloat gyro_y, jfloat gyro_z, jfloat accel_x,
-    jfloat accel_y, jfloat accel_z) {
+    JNIEnv* env, jclass clazz, jint j_device, jlong delta_timestamp, jfloat gyro_x, jfloat gyro_y,
+    jfloat gyro_z, jfloat accel_x, jfloat accel_y, jfloat accel_z) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().Window().OnGamepadMotionEvent(
             j_device, delta_timestamp, gyro_x, gyro_y, gyro_z, accel_x, accel_y, accel_z);
@@ -660,8 +683,7 @@ jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadMotionEvent(
     return static_cast<jboolean>(true);
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onReadNfcTag([[maybe_unused]] JNIEnv* env,
-                                                            [[maybe_unused]] jclass clazz,
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onReadNfcTag(JNIEnv* env, jclass clazz,
                                                             jbyteArray j_data) {
     jboolean isCopy{false};
     std::span<u8> data(reinterpret_cast<u8*>(env->GetByteArrayElements(j_data, &isCopy)),
@@ -673,108 +695,92 @@ jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onReadNfcTag([[maybe_unused]] JNI
     return static_cast<jboolean>(true);
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onRemoveNfcTag([[maybe_unused]] JNIEnv* env,
-                                                              [[maybe_unused]] jclass clazz) {
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_onRemoveNfcTag(JNIEnv* env, jclass clazz) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().Window().OnRemoveNfcTag();
     }
     return static_cast<jboolean>(true);
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchPressed([[maybe_unused]] JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz, jint id,
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchPressed(JNIEnv* env, jclass clazz, jint id,
                                                           jfloat x, jfloat y) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().Window().OnTouchPressed(id, x, y);
     }
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchMoved([[maybe_unused]] JNIEnv* env,
-                                                        [[maybe_unused]] jclass clazz, jint id,
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchMoved(JNIEnv* env, jclass clazz, jint id,
                                                         jfloat x, jfloat y) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().Window().OnTouchMoved(id, x, y);
     }
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchReleased([[maybe_unused]] JNIEnv* env,
-                                                           [[maybe_unused]] jclass clazz, jint id) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchReleased(JNIEnv* env, jclass clazz, jint id) {
     if (EmulationSession::GetInstance().IsRunning()) {
         EmulationSession::GetInstance().Window().OnTouchReleased(id);
     }
 }
 
-jbyteArray Java_org_yuzu_yuzu_1emu_NativeLibrary_getIcon([[maybe_unused]] JNIEnv* env,
-                                                         [[maybe_unused]] jclass clazz,
-                                                         [[maybe_unused]] jstring j_filename) {
-    auto icon_data = EmulationSession::GetInstance().GetRomIcon(GetJString(env, j_filename));
+jbyteArray Java_org_yuzu_yuzu_1emu_NativeLibrary_getIcon(JNIEnv* env, jclass clazz,
+                                                         jstring j_filename) {
+    jauto icon_data = EmulationSession::GetInstance().GetRomIcon(GetJString(env, j_filename));
     jbyteArray icon = env->NewByteArray(static_cast<jsize>(icon_data.size()));
     env->SetByteArrayRegion(icon, 0, env->GetArrayLength(icon),
                             reinterpret_cast<jbyte*>(icon_data.data()));
     return icon;
 }
 
-jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getTitle([[maybe_unused]] JNIEnv* env,
-                                                       [[maybe_unused]] jclass clazz,
-                                                       [[maybe_unused]] jstring j_filename) {
-    auto title = EmulationSession::GetInstance().GetRomTitle(GetJString(env, j_filename));
+jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getTitle(JNIEnv* env, jclass clazz,
+                                                       jstring j_filename) {
+    jauto title = EmulationSession::GetInstance().GetRomTitle(GetJString(env, j_filename));
     return env->NewStringUTF(title.c_str());
 }
 
-jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getDescription([[maybe_unused]] JNIEnv* env,
-                                                             [[maybe_unused]] jclass clazz,
+jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getDescription(JNIEnv* env, jclass clazz,
                                                              jstring j_filename) {
     return j_filename;
 }
 
-jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getGameId([[maybe_unused]] JNIEnv* env,
-                                                        [[maybe_unused]] jclass clazz,
+jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getGameId(JNIEnv* env, jclass clazz,
                                                         jstring j_filename) {
     return j_filename;
 }
 
-jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getRegions([[maybe_unused]] JNIEnv* env,
-                                                         [[maybe_unused]] jclass clazz,
-                                                         [[maybe_unused]] jstring j_filename) {
+jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getRegions(JNIEnv* env, jclass clazz,
+                                                         jstring j_filename) {
     return env->NewStringUTF("");
 }
 
-jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getCompany([[maybe_unused]] JNIEnv* env,
-                                                         [[maybe_unused]] jclass clazz,
-                                                         [[maybe_unused]] jstring j_filename) {
+jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getCompany(JNIEnv* env, jclass clazz,
+                                                         jstring j_filename) {
     return env->NewStringUTF("");
 }
 
-jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isHomebrew([[maybe_unused]] JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz,
-                                                          [[maybe_unused]] jstring j_filename) {
+jboolean Java_org_yuzu_yuzu_1emu_NativeLibrary_isHomebrew(JNIEnv* env, jclass clazz,
+                                                          jstring j_filename) {
     return EmulationSession::GetInstance().GetIsHomebrew(GetJString(env, j_filename));
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_initializeEmulation
-    [[maybe_unused]] (JNIEnv* env, [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_initializeEmulation(JNIEnv* env, jclass clazz) {
     // Create the default config.ini.
     Config{};
     // Initialize the emulated system.
     EmulationSession::GetInstance().System().Initialize();
 }
 
-jint Java_org_yuzu_yuzu_1emu_NativeLibrary_defaultCPUCore([[maybe_unused]] JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz) {
+jint Java_org_yuzu_yuzu_1emu_NativeLibrary_defaultCPUCore(JNIEnv* env, jclass clazz) {
     return {};
 }
 
 void Java_org_yuzu_yuzu_1emu_NativeLibrary_run__Ljava_lang_String_2Ljava_lang_String_2Z(
-    [[maybe_unused]] JNIEnv* env, [[maybe_unused]] jclass clazz, [[maybe_unused]] jstring j_file,
-    [[maybe_unused]] jstring j_savestate, [[maybe_unused]] jboolean j_delete_savestate) {}
+    JNIEnv* env, jclass clazz, jstring j_file, jstring j_savestate, jboolean j_delete_savestate) {}
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_reloadSettings([[maybe_unused]] JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_reloadSettings(JNIEnv* env, jclass clazz) {
     Config{};
 }
 
-jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getUserSetting([[maybe_unused]] JNIEnv* env,
-                                                             [[maybe_unused]] jclass clazz,
+jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getUserSetting(JNIEnv* env, jclass clazz,
                                                              jstring j_game_id, jstring j_section,
                                                              jstring j_key) {
     std::string_view game_id = env->GetStringUTFChars(j_game_id, 0);
@@ -788,8 +794,7 @@ jstring Java_org_yuzu_yuzu_1emu_NativeLibrary_getUserSetting([[maybe_unused]] JN
     return env->NewStringUTF("");
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_setUserSetting([[maybe_unused]] JNIEnv* env,
-                                                          [[maybe_unused]] jclass clazz,
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_setUserSetting(JNIEnv* env, jclass clazz,
                                                           jstring j_game_id, jstring j_section,
                                                           jstring j_key, jstring j_value) {
     std::string_view game_id = env->GetStringUTFChars(j_game_id, 0);
@@ -803,20 +808,18 @@ void Java_org_yuzu_yuzu_1emu_NativeLibrary_setUserSetting([[maybe_unused]] JNIEn
     env->ReleaseStringUTFChars(j_value, value.data());
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_initGameIni([[maybe_unused]] JNIEnv* env,
-                                                       [[maybe_unused]] jclass clazz,
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_initGameIni(JNIEnv* env, jclass clazz,
                                                        jstring j_game_id) {
     std::string_view game_id = env->GetStringUTFChars(j_game_id, 0);
 
     env->ReleaseStringUTFChars(j_game_id, game_id.data());
 }
 
-jdoubleArray Java_org_yuzu_yuzu_1emu_NativeLibrary_getPerfStats([[maybe_unused]] JNIEnv* env,
-                                                                [[maybe_unused]] jclass clazz) {
+jdoubleArray Java_org_yuzu_yuzu_1emu_NativeLibrary_getPerfStats(JNIEnv* env, jclass clazz) {
     jdoubleArray j_stats = env->NewDoubleArray(4);
 
     if (EmulationSession::GetInstance().IsRunning()) {
-        const auto results = EmulationSession::GetInstance().PerfStats();
+        jconst results = EmulationSession::GetInstance().PerfStats();
 
         // Converting the structure into an array makes it easier to pass it to the frontend
         double stats[4] = {results.system_fps, results.average_game_fps, results.frametime,
@@ -828,11 +831,11 @@ jdoubleArray Java_org_yuzu_yuzu_1emu_NativeLibrary_getPerfStats([[maybe_unused]]
     return j_stats;
 }
 
-void Java_org_yuzu_yuzu_1emu_utils_DirectoryInitialization_setSysDirectory(
-    [[maybe_unused]] JNIEnv* env, [[maybe_unused]] jclass clazz, jstring j_path) {}
+void Java_org_yuzu_yuzu_1emu_utils_DirectoryInitialization_setSysDirectory(JNIEnv* env,
+                                                                           jclass clazz,
+                                                                           jstring j_path) {}
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_run__Ljava_lang_String_2([[maybe_unused]] JNIEnv* env,
-                                                                    [[maybe_unused]] jclass clazz,
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_run__Ljava_lang_String_2(JNIEnv* env, jclass clazz,
                                                                     jstring j_path) {
     const std::string path = GetJString(env, j_path);
 
@@ -843,8 +846,7 @@ void Java_org_yuzu_yuzu_1emu_NativeLibrary_run__Ljava_lang_String_2([[maybe_unus
     }
 }
 
-void Java_org_yuzu_yuzu_1emu_NativeLibrary_logDeviceInfo([[maybe_unused]] JNIEnv* env,
-                                                         [[maybe_unused]] jclass clazz) {
+void Java_org_yuzu_yuzu_1emu_NativeLibrary_logDeviceInfo(JNIEnv* env, jclass clazz) {
     LOG_INFO(Frontend, "yuzu Version: {}-{}", Common::g_scm_branch, Common::g_scm_desc);
     LOG_INFO(Frontend, "Host OS: Android API level {}", android_get_device_api_level());
 }
diff --git a/src/android/app/src/main/jni/native.h b/src/android/app/src/main/jni/native.h
deleted file mode 100644
index 24dcbbcb8..000000000
--- a/src/android/app/src/main/jni/native.h
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-#pragma once
-
-#include <jni.h>
-
-// Function calls from the Java side
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_UnPauseEmulation(JNIEnv* env,
-                                                                              jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_PauseEmulation(JNIEnv* env,
-                                                                            jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_StopEmulation(JNIEnv* env,
-                                                                           jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_ResetRomMetadata(JNIEnv* env,
-                                                                              jclass clazz);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_IsRunning(JNIEnv* env,
-                                                                           jclass clazz);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_isHandheldOnly(JNIEnv* env,
-                                                                                jclass clazz);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_setDeviceType(JNIEnv* env,
-                                                                               jclass clazz,
-                                                                               jstring j_device,
-                                                                               jstring j_type);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadConnectEvent(
-    JNIEnv* env, jclass clazz, jstring j_device);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadDisconnectEvent(
-    JNIEnv* env, jclass clazz, jstring j_device);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadEvent(
-    JNIEnv* env, jclass clazz, jstring j_device, jint j_button, jint action);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadMoveEvent(
-    JNIEnv* env, jclass clazz, jstring j_device, jint axis, jfloat x, jfloat y);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onGamePadAxisEvent(
-    JNIEnv* env, jclass clazz, jstring j_device, jint axis_id, jfloat axis_val);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onReadNfcTag(JNIEnv* env,
-                                                                              jclass clazz,
-                                                                              jbyteArray j_data);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onRemoveNfcTag(JNIEnv* env,
-                                                                                jclass clazz);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchEvent(JNIEnv* env,
-                                                                              jclass clazz,
-                                                                              jfloat x, jfloat y,
-                                                                              jboolean pressed);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_onTouchMoved(JNIEnv* env, jclass clazz,
-                                                                          jfloat x, jfloat y);
-
-JNIEXPORT jbyteArray JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetIcon(JNIEnv* env,
-                                                                           jclass clazz,
-                                                                           jstring j_file);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetTitle(JNIEnv* env, jclass clazz,
-                                                                         jstring j_filename);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetDescription(JNIEnv* env,
-                                                                               jclass clazz,
-                                                                               jstring j_filename);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetGameId(JNIEnv* env, jclass clazz,
-                                                                          jstring j_filename);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetRegions(JNIEnv* env,
-                                                                           jclass clazz,
-                                                                           jstring j_filename);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetCompany(JNIEnv* env,
-                                                                           jclass clazz,
-                                                                           jstring j_filename);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetGitRevision(JNIEnv* env,
-                                                                               jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SetAppDirectory(JNIEnv* env,
-                                                                             jclass clazz,
-                                                                             jstring j_directory);
-
-JNIEXPORT void JNICALL
-Java_org_yuzu_yuzu_1emu_NativeLibrary_Java_org_yuzu_yuzu_1emu_NativeLibrary_InitializeGpuDriver(
-    JNIEnv* env, jclass clazz, jstring hook_lib_dir, jstring custom_driver_dir,
-    jstring custom_driver_name, jstring file_redirect_dir);
-
-JNIEXPORT jboolean JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_ReloadKeys(JNIEnv* env,
-                                                                            jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_utils_DirectoryInitialization_SetSysDirectory(
-    JNIEnv* env, jclass clazz, jstring path_);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SetSysDirectory(JNIEnv* env,
-                                                                             jclass clazz,
-                                                                             jstring path);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_InitializeEmulation(JNIEnv* env,
-                                                                                 jclass clazz);
-
-JNIEXPORT jint JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_DefaultCPUCore(JNIEnv* env,
-                                                                            jclass clazz);
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SetProfiling(JNIEnv* env, jclass clazz,
-                                                                          jboolean enable);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_WriteProfileResults(JNIEnv* env,
-                                                                                 jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_NotifyOrientationChange(
-    JNIEnv* env, jclass clazz, jint layout_option, jint rotation);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_Run__Ljava_lang_String_2(
-    JNIEnv* env, jclass clazz, jstring j_path);
-
-JNIEXPORT void JNICALL
-Java_org_yuzu_yuzu_1emu_NativeLibrary_Run__Ljava_lang_String_2Ljava_lang_String_2Z(
-    JNIEnv* env, jclass clazz, jstring j_file, jstring j_savestate, jboolean j_delete_savestate);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SurfaceChanged(JNIEnv* env,
-                                                                            jclass clazz,
-                                                                            jobject surf);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SurfaceDestroyed(JNIEnv* env,
-                                                                              jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_InitGameIni(JNIEnv* env, jclass clazz,
-                                                                         jstring j_game_id);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_ReloadSettings(JNIEnv* env,
-                                                                            jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SetUserSetting(
-    JNIEnv* env, jclass clazz, jstring j_game_id, jstring j_section, jstring j_key,
-    jstring j_value);
-
-JNIEXPORT jstring JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetUserSetting(
-    JNIEnv* env, jclass clazz, jstring game_id, jstring section, jstring key);
-
-JNIEXPORT jdoubleArray JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_GetPerfStats(JNIEnv* env,
-                                                                                  jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_LogDeviceInfo(JNIEnv* env,
-                                                                           jclass clazz);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SubmitInlineKeyboardText(
-    JNIEnv* env, jclass clazz, jstring j_text);
-
-JNIEXPORT void JNICALL Java_org_yuzu_yuzu_1emu_NativeLibrary_SubmitInlineKeyboardInput(
-    JNIEnv* env, jclass clazz, jint j_key_code);
-
-#ifdef __cplusplus
-}
-#endif
diff --git a/src/android/app/src/main/res/drawable/ic_pip_mute.xml b/src/android/app/src/main/res/drawable/ic_pip_mute.xml
new file mode 100644
index 000000000..a271c5fe8
--- /dev/null
+++ b/src/android/app/src/main/res/drawable/ic_pip_mute.xml
@@ -0,0 +1,9 @@
+<vector xmlns:android="http://schemas.android.com/apk/res/android"
+    android:width="24dp"
+    android:height="24dp"
+    android:viewportHeight="24"
+    android:viewportWidth="24">
+    <path
+        android:fillColor="@android:color/white"
+        android:pathData="M7,9v6h4l5,5V4l-5,5H7z" />
+</vector>
diff --git a/src/android/app/src/main/res/drawable/ic_pip_unmute.xml b/src/android/app/src/main/res/drawable/ic_pip_unmute.xml
new file mode 100644
index 000000000..f7ed0862e
--- /dev/null
+++ b/src/android/app/src/main/res/drawable/ic_pip_unmute.xml
@@ -0,0 +1,9 @@
+<vector xmlns:android="http://schemas.android.com/apk/res/android"
+    android:width="24dp"
+    android:height="24dp"
+    android:viewportHeight="24"
+    android:viewportWidth="24">
+    <path
+        android:fillColor="@android:color/white"
+        android:pathData="M3,9v6h4l5,5L12,4L7,9L3,9zM16.5,12c0,-1.77 -1.02,-3.29 -2.5,-4.03v8.05c1.48,-0.73 2.5,-2.25 2.5,-4.02zM14,3.23v2.06c2.89,0.86 5,3.54 5,6.71s-2.11,5.85 -5,6.71v2.06c4.01,-0.91 7,-4.49 7,-8.77s-2.99,-7.86 -7,-8.77z" />
+</vector>
diff --git a/src/android/app/src/main/res/values/strings.xml b/src/android/app/src/main/res/values/strings.xml
index cc1d8c39d..af7450619 100644
--- a/src/android/app/src/main/res/values/strings.xml
+++ b/src/android/app/src/main/res/values/strings.xml
@@ -104,12 +104,14 @@
     <string name="share_log_missing">No log file found</string>
     <string name="install_game_content">Install game content</string>
     <string name="install_game_content_description">Install game updates or DLC</string>
-    <string name="install_game_content_failure">Error installing file to NAND</string>
-    <string name="install_game_content_failure_description">Game content installation failed. Please ensure content is valid and that the prod.keys file is installed.</string>
-    <string name="install_game_content_failure_base">Installation of base games isn\'t permitted in order to avoid possible conflicts. Please select an update or DLC instead.</string>
-    <string name="install_game_content_failure_file_extension">The selected file type is not supported. Only NSP and XCI content is supported for this action. Please verify the game content is valid.</string>
-    <string name="install_game_content_success">Game content installed successfully</string>
-    <string name="install_game_content_success_overwrite">Game content was overwritten successfully</string>
+    <string name="install_game_content_failure">Error installing file(s) to NAND</string>
+    <string name="install_game_content_failure_description">Please ensure content(s) are valid and that the prod.keys file is installed.</string>
+    <string name="install_game_content_failure_base">Installation of base games isn\'t permitted in order to avoid possible conflicts.</string>
+    <string name="install_game_content_failure_file_extension">Only NSP and XCI content is supported. Please verify the game content(s) are valid.</string>
+    <string name="install_game_content_failed_count">%1$d installation error(s)</string>
+    <string name="install_game_content_success">Game content(s) installed successfully</string>
+    <string name="install_game_content_success_install">%1$d installed successfully</string>
+    <string name="install_game_content_success_overwrite">%1$d overwritten successfully</string>
     <string name="install_game_content_help_link">https://yuzu-emu.org/help/quickstart/#dumping-installed-updates</string>
 
     <!-- About screen strings -->
@@ -270,6 +272,7 @@
     <string name="fatal_error">Fatal Error</string>
     <string name="fatal_error_message">A fatal error occurred. Check the log for details.\nContinuing emulation may result in crashes and bugs.</string>
     <string name="performance_warning">Turning off this setting will significantly reduce emulation performance! For the best experience, it is recommended that you leave this setting enabled.</string>
+    <string name="device_memory_inadequate">Device RAM: %1$s\nRecommended: %2$s</string>
 
     <!-- Region Names -->
     <string name="region_japan">Japan</string>
@@ -300,6 +303,15 @@
     <string name="language_traditional_chinese">Traditional Chinese (正體中文)</string>
     <string name="language_brazilian_portuguese">Brazilian Portuguese (Português do Brasil)</string>
 
+    <!-- Memory Sizes -->
+    <string name="memory_byte">Byte</string>
+    <string name="memory_kilobyte">KB</string>
+    <string name="memory_megabyte">MB</string>
+    <string name="memory_gigabyte">GB</string>
+    <string name="memory_terabyte">TB</string>
+    <string name="memory_petabyte">PB</string>
+    <string name="memory_exabyte">EB</string>
+
     <!-- Renderer APIs -->
     <string name="renderer_vulkan">Vulkan</string>
     <string name="renderer_none">None</string>
@@ -387,6 +399,8 @@
     <string name="picture_in_picture_description">Minimize window when placed in the background</string>
     <string name="pause">Pause</string>
     <string name="play">Play</string>
+    <string name="mute">Mute</string>
+    <string name="unmute">Unmute</string>
 
     <!-- Licenses screen strings -->
     <string name="licenses">Licenses</string>
diff --git a/src/android/gradle.properties b/src/android/gradle.properties
index e2f278f33..4fca1b576 100644
--- a/src/android/gradle.properties
+++ b/src/android/gradle.properties
@@ -15,3 +15,6 @@ android.useAndroidX=true
 kotlin.code.style=official
 kotlin.parallel.tasks.in.project=true
 android.defaults.buildfeatures.buildconfig=true
+
+# Android Gradle plugin 8.0.2
+android.suppressUnsupportedCompileSdk=34
diff --git a/src/audio_core/device/audio_buffers.h b/src/audio_core/device/audio_buffers.h
index 15082f6c6..5d8ed0ef7 100644
--- a/src/audio_core/device/audio_buffers.h
+++ b/src/audio_core/device/audio_buffers.h
@@ -7,6 +7,7 @@
 #include <mutex>
 #include <span>
 #include <vector>
+#include <boost/container/static_vector.hpp>
 
 #include "audio_buffer.h"
 #include "audio_core/device/device_session.h"
@@ -48,7 +49,7 @@ public:
      *
      * @param out_buffers - The buffers which were registered.
      */
-    void RegisterBuffers(std::vector<AudioBuffer>& out_buffers) {
+    void RegisterBuffers(boost::container::static_vector<AudioBuffer, N>& out_buffers) {
         std::scoped_lock l{lock};
         const s32 to_register{std::min(std::min(appended_count, BufferAppendLimit),
                                        BufferAppendLimit - registered_count)};
@@ -162,7 +163,8 @@ public:
      * @param max_buffers     - Maximum number of buffers to released.
      * @return The number of buffers released.
      */
-    u32 GetRegisteredAppendedBuffers(std::vector<AudioBuffer>& buffers_flushed, u32 max_buffers) {
+    u32 GetRegisteredAppendedBuffers(
+        boost::container::static_vector<AudioBuffer, N>& buffers_flushed, u32 max_buffers) {
         std::scoped_lock l{lock};
         if (registered_count + appended_count == 0) {
             return 0;
@@ -270,7 +272,7 @@ public:
      */
     bool FlushBuffers(u32& buffers_released) {
         std::scoped_lock l{lock};
-        std::vector<AudioBuffer> buffers_flushed{};
+        boost::container::static_vector<AudioBuffer, N> buffers_flushed{};
 
         buffers_released = GetRegisteredAppendedBuffers(buffers_flushed, append_limit);
 
diff --git a/src/audio_core/device/device_session.cpp b/src/audio_core/device/device_session.cpp
index b5c0ef0e6..86811fcb8 100644
--- a/src/audio_core/device/device_session.cpp
+++ b/src/audio_core/device/device_session.cpp
@@ -79,7 +79,7 @@ void DeviceSession::ClearBuffers() {
     }
 }
 
-void DeviceSession::AppendBuffers(std::span<const AudioBuffer> buffers) const {
+void DeviceSession::AppendBuffers(std::span<const AudioBuffer> buffers) {
     for (const auto& buffer : buffers) {
         Sink::SinkBuffer new_buffer{
             .frames = buffer.size / (channel_count * sizeof(s16)),
@@ -88,13 +88,13 @@ void DeviceSession::AppendBuffers(std::span<const AudioBuffer> buffers) const {
             .consumed = false,
         };
 
+        tmp_samples.resize_destructive(buffer.size / sizeof(s16));
         if (type == Sink::StreamType::In) {
-            std::vector<s16> samples{};
-            stream->AppendBuffer(new_buffer, samples);
+            stream->AppendBuffer(new_buffer, tmp_samples);
         } else {
-            std::vector<s16> samples(buffer.size / sizeof(s16));
-            system.ApplicationMemory().ReadBlockUnsafe(buffer.samples, samples.data(), buffer.size);
-            stream->AppendBuffer(new_buffer, samples);
+            system.ApplicationMemory().ReadBlockUnsafe(buffer.samples, tmp_samples.data(),
+                                                       buffer.size);
+            stream->AppendBuffer(new_buffer, tmp_samples);
         }
     }
 }
diff --git a/src/audio_core/device/device_session.h b/src/audio_core/device/device_session.h
index 75f766c68..7d52f362d 100644
--- a/src/audio_core/device/device_session.h
+++ b/src/audio_core/device/device_session.h
@@ -10,6 +10,7 @@
 
 #include "audio_core/common/common.h"
 #include "audio_core/sink/sink.h"
+#include "common/scratch_buffer.h"
 #include "core/hle/service/audio/errors.h"
 
 namespace Core {
@@ -62,7 +63,7 @@ public:
      *
      * @param buffers - The buffers to play.
      */
-    void AppendBuffers(std::span<const AudioBuffer> buffers) const;
+    void AppendBuffers(std::span<const AudioBuffer> buffers);
 
     /**
      * (Audio In only) Pop samples from the backend, and write them back to this buffer's address.
@@ -146,8 +147,8 @@ private:
     std::shared_ptr<Core::Timing::EventType> thread_event;
     /// Is this session initialised?
     bool initialized{};
-    /// Buffer queue
-    std::vector<AudioBuffer> buffer_queue{};
+    /// Temporary sample buffer
+    Common::ScratchBuffer<s16> tmp_samples{};
 };
 
 } // namespace AudioCore
diff --git a/src/audio_core/in/audio_in_system.cpp b/src/audio_core/in/audio_in_system.cpp
index e23e51758..579129121 100644
--- a/src/audio_core/in/audio_in_system.cpp
+++ b/src/audio_core/in/audio_in_system.cpp
@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <mutex>
+
 #include "audio_core/audio_event.h"
 #include "audio_core/audio_manager.h"
 #include "audio_core/in/audio_in_system.h"
@@ -89,7 +90,7 @@ Result System::Start() {
     session->Start();
     state = State::Started;
 
-    std::vector<AudioBuffer> buffers_to_flush{};
+    boost::container::static_vector<AudioBuffer, BufferCount> buffers_to_flush{};
     buffers.RegisterBuffers(buffers_to_flush);
     session->AppendBuffers(buffers_to_flush);
     session->SetRingSize(static_cast<u32>(buffers_to_flush.size()));
@@ -134,7 +135,7 @@ bool System::AppendBuffer(const AudioInBuffer& buffer, const u64 tag) {
 
 void System::RegisterBuffers() {
     if (state == State::Started) {
-        std::vector<AudioBuffer> registered_buffers{};
+        boost::container::static_vector<AudioBuffer, BufferCount> registered_buffers{};
         buffers.RegisterBuffers(registered_buffers);
         session->AppendBuffers(registered_buffers);
     }
diff --git a/src/audio_core/out/audio_out_system.cpp b/src/audio_core/out/audio_out_system.cpp
index bd13f7219..0adf64bd3 100644
--- a/src/audio_core/out/audio_out_system.cpp
+++ b/src/audio_core/out/audio_out_system.cpp
@@ -89,7 +89,7 @@ Result System::Start() {
     session->Start();
     state = State::Started;
 
-    std::vector<AudioBuffer> buffers_to_flush{};
+    boost::container::static_vector<AudioBuffer, BufferCount> buffers_to_flush{};
     buffers.RegisterBuffers(buffers_to_flush);
     session->AppendBuffers(buffers_to_flush);
     session->SetRingSize(static_cast<u32>(buffers_to_flush.size()));
@@ -134,7 +134,7 @@ bool System::AppendBuffer(const AudioOutBuffer& buffer, u64 tag) {
 
 void System::RegisterBuffers() {
     if (state == State::Started) {
-        std::vector<AudioBuffer> registered_buffers{};
+        boost::container::static_vector<AudioBuffer, BufferCount> registered_buffers{};
         buffers.RegisterBuffers(registered_buffers);
         session->AppendBuffers(registered_buffers);
     }
diff --git a/src/audio_core/renderer/adsp/adsp.cpp b/src/audio_core/renderer/adsp/adsp.cpp
index 74772fc50..b1db31e93 100644
--- a/src/audio_core/renderer/adsp/adsp.cpp
+++ b/src/audio_core/renderer/adsp/adsp.cpp
@@ -7,7 +7,6 @@
 #include "common/logging/log.h"
 #include "core/core.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 #include "core/memory.h"
 
 namespace AudioCore::AudioRenderer::ADSP {
diff --git a/src/audio_core/renderer/adsp/audio_renderer.cpp b/src/audio_core/renderer/adsp/audio_renderer.cpp
index 8bc39f9f9..9ca716b60 100644
--- a/src/audio_core/renderer/adsp/audio_renderer.cpp
+++ b/src/audio_core/renderer/adsp/audio_renderer.cpp
@@ -13,7 +13,6 @@
 #include "common/thread.h"
 #include "core/core.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 
 MICROPROFILE_DEFINE(Audio_Renderer, "Audio", "DSP", MP_RGB(60, 19, 97));
 
@@ -144,6 +143,7 @@ void AudioRenderer::ThreadFunc(std::stop_token stop_token) {
 
     mailbox->ADSPSendMessage(RenderMessage::AudioRenderer_InitializeOK);
 
+    // 0.12 seconds (2304000 / 19200000)
     constexpr u64 max_process_time{2'304'000ULL};
 
     while (!stop_token.stop_requested()) {
@@ -184,8 +184,7 @@ void AudioRenderer::ThreadFunc(std::stop_token stop_token) {
                     u64 max_time{max_process_time};
                     if (index == 1 && command_buffer.applet_resource_user_id ==
                                           mailbox->GetCommandBuffer(0).applet_resource_user_id) {
-                        max_time = max_process_time -
-                                   Core::Timing::CyclesToNs(render_times_taken[0]).count();
+                        max_time = max_process_time - render_times_taken[0];
                         if (render_times_taken[0] > max_process_time) {
                             max_time = 0;
                         }
diff --git a/src/audio_core/renderer/adsp/command_list_processor.cpp b/src/audio_core/renderer/adsp/command_list_processor.cpp
index 7a300d216..3a0f1ae38 100644
--- a/src/audio_core/renderer/adsp/command_list_processor.cpp
+++ b/src/audio_core/renderer/adsp/command_list_processor.cpp
@@ -9,7 +9,6 @@
 #include "common/settings.h"
 #include "core/core.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 #include "core/memory.h"
 
 namespace AudioCore::AudioRenderer::ADSP {
diff --git a/src/audio_core/renderer/command/data_source/decode.cpp b/src/audio_core/renderer/command/data_source/decode.cpp
index ff5d31bd6..f45933203 100644
--- a/src/audio_core/renderer/command/data_source/decode.cpp
+++ b/src/audio_core/renderer/command/data_source/decode.cpp
@@ -8,6 +8,7 @@
 #include "audio_core/renderer/command/resample/resample.h"
 #include "common/fixed_point.h"
 #include "common/logging/log.h"
+#include "common/scratch_buffer.h"
 #include "core/memory.h"
 
 namespace AudioCore::AudioRenderer {
@@ -27,6 +28,7 @@ constexpr std::array<u8, 3> PitchBySrcQuality = {4, 8, 4};
 template <typename T>
 static u32 DecodePcm(Core::Memory::Memory& memory, std::span<s16> out_buffer,
                      const DecodeArg& req) {
+    std::array<T, TempBufferSize> tmp_samples{};
     constexpr s32 min{std::numeric_limits<s16>::min()};
     constexpr s32 max{std::numeric_limits<s16>::max()};
 
@@ -49,18 +51,17 @@ static u32 DecodePcm(Core::Memory::Memory& memory, std::span<s16> out_buffer,
         const u64 size{channel_count * samples_to_decode};
         const u64 size_bytes{size * sizeof(T)};
 
-        std::vector<T> samples(size);
-        memory.ReadBlockUnsafe(source, samples.data(), size_bytes);
+        memory.ReadBlockUnsafe(source, tmp_samples.data(), size_bytes);
 
         if constexpr (std::is_floating_point_v<T>) {
             for (u32 i = 0; i < samples_to_decode; i++) {
-                auto sample{static_cast<s32>(samples[i * channel_count + req.target_channel] *
+                auto sample{static_cast<s32>(tmp_samples[i * channel_count + req.target_channel] *
                                              std::numeric_limits<s16>::max())};
                 out_buffer[i] = static_cast<s16>(std::clamp(sample, min, max));
             }
         } else {
             for (u32 i = 0; i < samples_to_decode; i++) {
-                out_buffer[i] = samples[i * channel_count + req.target_channel];
+                out_buffer[i] = tmp_samples[i * channel_count + req.target_channel];
             }
         }
     } break;
@@ -73,17 +74,16 @@ static u32 DecodePcm(Core::Memory::Memory& memory, std::span<s16> out_buffer,
         }
 
         const VAddr source{req.buffer + ((req.start_offset + req.offset) * sizeof(T))};
-        std::vector<T> samples(samples_to_decode);
-        memory.ReadBlockUnsafe(source, samples.data(), samples_to_decode * sizeof(T));
+        memory.ReadBlockUnsafe(source, tmp_samples.data(), samples_to_decode * sizeof(T));
 
         if constexpr (std::is_floating_point_v<T>) {
             for (u32 i = 0; i < samples_to_decode; i++) {
-                auto sample{static_cast<s32>(samples[i * channel_count + req.target_channel] *
+                auto sample{static_cast<s32>(tmp_samples[i * channel_count + req.target_channel] *
                                              std::numeric_limits<s16>::max())};
                 out_buffer[i] = static_cast<s16>(std::clamp(sample, min, max));
             }
         } else {
-            std::memcpy(out_buffer.data(), samples.data(), samples_to_decode * sizeof(s16));
+            std::memcpy(out_buffer.data(), tmp_samples.data(), samples_to_decode * sizeof(s16));
         }
         break;
     }
@@ -101,6 +101,7 @@ static u32 DecodePcm(Core::Memory::Memory& memory, std::span<s16> out_buffer,
  */
 static u32 DecodeAdpcm(Core::Memory::Memory& memory, std::span<s16> out_buffer,
                        const DecodeArg& req) {
+    std::array<u8, TempBufferSize> wavebuffer{};
     constexpr u32 SamplesPerFrame{14};
     constexpr u32 NibblesPerFrame{16};
 
@@ -138,9 +139,7 @@ static u32 DecodeAdpcm(Core::Memory::Memory& memory, std::span<s16> out_buffer,
     }
 
     const auto size{std::max((samples_to_process / 8U) * SamplesPerFrame, 8U)};
-    std::vector<u8> wavebuffer(size);
-    memory.ReadBlockUnsafe(req.buffer + position_in_frame / 2, wavebuffer.data(),
-                           wavebuffer.size());
+    memory.ReadBlockUnsafe(req.buffer + position_in_frame / 2, wavebuffer.data(), size);
 
     auto context{req.adpcm_context};
     auto header{context->header};
@@ -258,7 +257,7 @@ void DecodeFromWaveBuffers(Core::Memory::Memory& memory, const DecodeFromWaveBuf
     u32 offset{voice_state.offset};
 
     auto output_buffer{args.output};
-    std::vector<s16> temp_buffer(TempBufferSize, 0);
+    std::array<s16, TempBufferSize> temp_buffer{};
 
     while (remaining_sample_count > 0) {
         const auto samples_to_write{std::min(remaining_sample_count, max_remaining_sample_count)};
diff --git a/src/audio_core/renderer/command/effect/compressor.cpp b/src/audio_core/renderer/command/effect/compressor.cpp
index 7229618e8..ee9b68d5b 100644
--- a/src/audio_core/renderer/command/effect/compressor.cpp
+++ b/src/audio_core/renderer/command/effect/compressor.cpp
@@ -44,8 +44,8 @@ static void InitializeCompressorEffect(const CompressorInfo::ParameterVersion2&
 
 static void ApplyCompressorEffect(const CompressorInfo::ParameterVersion2& params,
                                   CompressorInfo::State& state, bool enabled,
-                                  std::vector<std::span<const s32>> input_buffers,
-                                  std::vector<std::span<s32>> output_buffers, u32 sample_count) {
+                                  std::span<std::span<const s32>> input_buffers,
+                                  std::span<std::span<s32>> output_buffers, u32 sample_count) {
     if (enabled) {
         auto state_00{state.unk_00};
         auto state_04{state.unk_04};
@@ -124,8 +124,8 @@ void CompressorCommand::Dump([[maybe_unused]] const ADSP::CommandListProcessor&
 }
 
 void CompressorCommand::Process(const ADSP::CommandListProcessor& processor) {
-    std::vector<std::span<const s32>> input_buffers(parameter.channel_count);
-    std::vector<std::span<s32>> output_buffers(parameter.channel_count);
+    std::array<std::span<const s32>, MaxChannels> input_buffers{};
+    std::array<std::span<s32>, MaxChannels> output_buffers{};
 
     for (s16 i = 0; i < parameter.channel_count; i++) {
         input_buffers[i] = processor.mix_buffers.subspan(inputs[i] * processor.sample_count,
diff --git a/src/audio_core/renderer/command/effect/delay.cpp b/src/audio_core/renderer/command/effect/delay.cpp
index a4e408d40..e536cbb1e 100644
--- a/src/audio_core/renderer/command/effect/delay.cpp
+++ b/src/audio_core/renderer/command/effect/delay.cpp
@@ -51,7 +51,7 @@ static void InitializeDelayEffect(const DelayInfo::ParameterVersion1& params,
         state.delay_lines[channel].sample_count_max = sample_count_max.to_int_floor();
         state.delay_lines[channel].sample_count = sample_count.to_int_floor();
         state.delay_lines[channel].buffer.resize(state.delay_lines[channel].sample_count, 0);
-        if (state.delay_lines[channel].buffer.size() == 0) {
+        if (state.delay_lines[channel].sample_count == 0) {
             state.delay_lines[channel].buffer.push_back(0);
         }
         state.delay_lines[channel].buffer_pos = 0;
@@ -74,8 +74,8 @@ static void InitializeDelayEffect(const DelayInfo::ParameterVersion1& params,
  */
 template <size_t NumChannels>
 static void ApplyDelay(const DelayInfo::ParameterVersion1& params, DelayInfo::State& state,
-                       std::vector<std::span<const s32>>& inputs,
-                       std::vector<std::span<s32>>& outputs, const u32 sample_count) {
+                       std::span<std::span<const s32>> inputs, std::span<std::span<s32>> outputs,
+                       const u32 sample_count) {
     for (u32 sample_index = 0; sample_index < sample_count; sample_index++) {
         std::array<Common::FixedPoint<50, 14>, NumChannels> input_samples{};
         for (u32 channel = 0; channel < NumChannels; channel++) {
@@ -153,8 +153,8 @@ static void ApplyDelay(const DelayInfo::ParameterVersion1& params, DelayInfo::St
  * @param sample_count - Number of samples to process.
  */
 static void ApplyDelayEffect(const DelayInfo::ParameterVersion1& params, DelayInfo::State& state,
-                             const bool enabled, std::vector<std::span<const s32>>& inputs,
-                             std::vector<std::span<s32>>& outputs, const u32 sample_count) {
+                             const bool enabled, std::span<std::span<const s32>> inputs,
+                             std::span<std::span<s32>> outputs, const u32 sample_count) {
 
     if (!IsChannelCountValid(params.channel_count)) {
         LOG_ERROR(Service_Audio, "Invalid delay channels {}", params.channel_count);
@@ -208,8 +208,8 @@ void DelayCommand::Dump([[maybe_unused]] const ADSP::CommandListProcessor& proce
 }
 
 void DelayCommand::Process(const ADSP::CommandListProcessor& processor) {
-    std::vector<std::span<const s32>> input_buffers(parameter.channel_count);
-    std::vector<std::span<s32>> output_buffers(parameter.channel_count);
+    std::array<std::span<const s32>, MaxChannels> input_buffers{};
+    std::array<std::span<s32>, MaxChannels> output_buffers{};
 
     for (s16 i = 0; i < parameter.channel_count; i++) {
         input_buffers[i] = processor.mix_buffers.subspan(inputs[i] * processor.sample_count,
diff --git a/src/audio_core/renderer/command/effect/i3dl2_reverb.cpp b/src/audio_core/renderer/command/effect/i3dl2_reverb.cpp
index 27d8b9844..d2bfb67cc 100644
--- a/src/audio_core/renderer/command/effect/i3dl2_reverb.cpp
+++ b/src/audio_core/renderer/command/effect/i3dl2_reverb.cpp
@@ -408,8 +408,8 @@ void I3dl2ReverbCommand::Dump([[maybe_unused]] const ADSP::CommandListProcessor&
 }
 
 void I3dl2ReverbCommand::Process(const ADSP::CommandListProcessor& processor) {
-    std::vector<std::span<const s32>> input_buffers(parameter.channel_count);
-    std::vector<std::span<s32>> output_buffers(parameter.channel_count);
+    std::array<std::span<const s32>, MaxChannels> input_buffers{};
+    std::array<std::span<s32>, MaxChannels> output_buffers{};
 
     for (u32 i = 0; i < parameter.channel_count; i++) {
         input_buffers[i] = processor.mix_buffers.subspan(inputs[i] * processor.sample_count,
diff --git a/src/audio_core/renderer/command/effect/light_limiter.cpp b/src/audio_core/renderer/command/effect/light_limiter.cpp
index e8fb0e2fc..4161a9821 100644
--- a/src/audio_core/renderer/command/effect/light_limiter.cpp
+++ b/src/audio_core/renderer/command/effect/light_limiter.cpp
@@ -47,8 +47,8 @@ static void InitializeLightLimiterEffect(const LightLimiterInfo::ParameterVersio
  */
 static void ApplyLightLimiterEffect(const LightLimiterInfo::ParameterVersion2& params,
                                     LightLimiterInfo::State& state, const bool enabled,
-                                    std::vector<std::span<const s32>>& inputs,
-                                    std::vector<std::span<s32>>& outputs, const u32 sample_count,
+                                    std::span<std::span<const s32>> inputs,
+                                    std::span<std::span<s32>> outputs, const u32 sample_count,
                                     LightLimiterInfo::StatisticsInternal* statistics) {
     constexpr s64 min{std::numeric_limits<s32>::min()};
     constexpr s64 max{std::numeric_limits<s32>::max()};
@@ -147,8 +147,8 @@ void LightLimiterVersion1Command::Dump([[maybe_unused]] const ADSP::CommandListP
 }
 
 void LightLimiterVersion1Command::Process(const ADSP::CommandListProcessor& processor) {
-    std::vector<std::span<const s32>> input_buffers(parameter.channel_count);
-    std::vector<std::span<s32>> output_buffers(parameter.channel_count);
+    std::array<std::span<const s32>, MaxChannels> input_buffers{};
+    std::array<std::span<s32>, MaxChannels> output_buffers{};
 
     for (u32 i = 0; i < parameter.channel_count; i++) {
         input_buffers[i] = processor.mix_buffers.subspan(inputs[i] * processor.sample_count,
@@ -190,8 +190,8 @@ void LightLimiterVersion2Command::Dump([[maybe_unused]] const ADSP::CommandListP
 }
 
 void LightLimiterVersion2Command::Process(const ADSP::CommandListProcessor& processor) {
-    std::vector<std::span<const s32>> input_buffers(parameter.channel_count);
-    std::vector<std::span<s32>> output_buffers(parameter.channel_count);
+    std::array<std::span<const s32>, MaxChannels> input_buffers{};
+    std::array<std::span<s32>, MaxChannels> output_buffers{};
 
     for (u32 i = 0; i < parameter.channel_count; i++) {
         input_buffers[i] = processor.mix_buffers.subspan(inputs[i] * processor.sample_count,
diff --git a/src/audio_core/renderer/command/effect/reverb.cpp b/src/audio_core/renderer/command/effect/reverb.cpp
index 8b9b65214..fc2f15a5e 100644
--- a/src/audio_core/renderer/command/effect/reverb.cpp
+++ b/src/audio_core/renderer/command/effect/reverb.cpp
@@ -250,8 +250,8 @@ static Common::FixedPoint<50, 14> Axfx2AllPassTick(ReverbInfo::ReverbDelayLine&
  */
 template <size_t NumChannels>
 static void ApplyReverbEffect(const ReverbInfo::ParameterVersion2& params, ReverbInfo::State& state,
-                              std::vector<std::span<const s32>>& inputs,
-                              std::vector<std::span<s32>>& outputs, const u32 sample_count) {
+                              std::span<std::span<const s32>> inputs,
+                              std::span<std::span<s32>> outputs, const u32 sample_count) {
     static constexpr std::array<u8, ReverbInfo::MaxDelayTaps> OutTapIndexes1Ch{
         0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
     };
@@ -369,8 +369,8 @@ static void ApplyReverbEffect(const ReverbInfo::ParameterVersion2& params, Rever
  * @param sample_count - Number of samples to process.
  */
 static void ApplyReverbEffect(const ReverbInfo::ParameterVersion2& params, ReverbInfo::State& state,
-                              const bool enabled, std::vector<std::span<const s32>>& inputs,
-                              std::vector<std::span<s32>>& outputs, const u32 sample_count) {
+                              const bool enabled, std::span<std::span<const s32>> inputs,
+                              std::span<std::span<s32>> outputs, const u32 sample_count) {
     if (enabled) {
         switch (params.channel_count) {
         case 0:
@@ -412,8 +412,8 @@ void ReverbCommand::Dump([[maybe_unused]] const ADSP::CommandListProcessor& proc
 }
 
 void ReverbCommand::Process(const ADSP::CommandListProcessor& processor) {
-    std::vector<std::span<const s32>> input_buffers(parameter.channel_count);
-    std::vector<std::span<s32>> output_buffers(parameter.channel_count);
+    std::array<std::span<const s32>, MaxChannels> input_buffers{};
+    std::array<std::span<s32>, MaxChannels> output_buffers{};
 
     for (u32 i = 0; i < parameter.channel_count; i++) {
         input_buffers[i] = processor.mix_buffers.subspan(inputs[i] * processor.sample_count,
diff --git a/src/audio_core/renderer/command/performance/performance.cpp b/src/audio_core/renderer/command/performance/performance.cpp
index 985958b03..4a881547f 100644
--- a/src/audio_core/renderer/command/performance/performance.cpp
+++ b/src/audio_core/renderer/command/performance/performance.cpp
@@ -5,7 +5,6 @@
 #include "audio_core/renderer/command/performance/performance.h"
 #include "core/core.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 
 namespace AudioCore::AudioRenderer {
 
@@ -18,20 +17,18 @@ void PerformanceCommand::Process(const ADSP::CommandListProcessor& processor) {
     auto base{entry_address.translated_address};
     if (state == PerformanceState::Start) {
         auto start_time_ptr{reinterpret_cast<u32*>(base + entry_address.entry_start_time_offset)};
-        *start_time_ptr = static_cast<u32>(
-            Core::Timing::CyclesToUs(processor.system->CoreTiming().GetClockTicks() -
-                                     processor.start_time - processor.current_processing_time)
-                .count());
+        *start_time_ptr =
+            static_cast<u32>(processor.system->CoreTiming().GetClockTicks() - processor.start_time -
+                             processor.current_processing_time);
     } else if (state == PerformanceState::Stop) {
         auto processed_time_ptr{
             reinterpret_cast<u32*>(base + entry_address.entry_processed_time_offset)};
         auto entry_count_ptr{
             reinterpret_cast<u32*>(base + entry_address.header_entry_count_offset)};
 
-        *processed_time_ptr = static_cast<u32>(
-            Core::Timing::CyclesToUs(processor.system->CoreTiming().GetClockTicks() -
-                                     processor.start_time - processor.current_processing_time)
-                .count());
+        *processed_time_ptr =
+            static_cast<u32>(processor.system->CoreTiming().GetClockTicks() - processor.start_time -
+                             processor.current_processing_time);
         (*entry_count_ptr)++;
     }
 }
diff --git a/src/audio_core/renderer/command/sink/circular_buffer.cpp b/src/audio_core/renderer/command/sink/circular_buffer.cpp
index ded5afc94..e2ce59792 100644
--- a/src/audio_core/renderer/command/sink/circular_buffer.cpp
+++ b/src/audio_core/renderer/command/sink/circular_buffer.cpp
@@ -24,7 +24,7 @@ void CircularBufferSinkCommand::Process(const ADSP::CommandListProcessor& proces
     constexpr s32 min{std::numeric_limits<s16>::min()};
     constexpr s32 max{std::numeric_limits<s16>::max()};
 
-    std::vector<s16> output(processor.sample_count);
+    std::array<s16, TargetSampleCount * MaxChannels> output{};
     for (u32 channel = 0; channel < input_count; channel++) {
         auto input{processor.mix_buffers.subspan(inputs[channel] * processor.sample_count,
                                                  processor.sample_count)};
@@ -33,7 +33,7 @@ void CircularBufferSinkCommand::Process(const ADSP::CommandListProcessor& proces
         }
 
         processor.memory->WriteBlockUnsafe(address + pos, output.data(),
-                                           output.size() * sizeof(s16));
+                                           processor.sample_count * sizeof(s16));
         pos += static_cast<u32>(processor.sample_count * sizeof(s16));
         if (pos >= size) {
             pos = 0;
diff --git a/src/audio_core/renderer/command/sink/device.cpp b/src/audio_core/renderer/command/sink/device.cpp
index e88372a75..5f74dd7ad 100644
--- a/src/audio_core/renderer/command/sink/device.cpp
+++ b/src/audio_core/renderer/command/sink/device.cpp
@@ -33,8 +33,7 @@ void DeviceSinkCommand::Process(const ADSP::CommandListProcessor& processor) {
         .consumed{false},
     };
 
-    std::vector<s16> samples(out_buffer.frames * input_count);
-
+    std::array<s16, TargetSampleCount * MaxChannels> samples{};
     for (u32 channel = 0; channel < input_count; channel++) {
         const auto offset{inputs[channel] * out_buffer.frames};
 
@@ -45,7 +44,7 @@ void DeviceSinkCommand::Process(const ADSP::CommandListProcessor& processor) {
     }
 
     out_buffer.tag = reinterpret_cast<u64>(samples.data());
-    stream->AppendBuffer(out_buffer, samples);
+    stream->AppendBuffer(out_buffer, {samples.data(), out_buffer.frames * input_count});
 
     if (stream->IsPaused()) {
         stream->Start();
diff --git a/src/audio_core/renderer/mix/mix_context.cpp b/src/audio_core/renderer/mix/mix_context.cpp
index 35b748ede..3a18ae7c2 100644
--- a/src/audio_core/renderer/mix/mix_context.cpp
+++ b/src/audio_core/renderer/mix/mix_context.cpp
@@ -125,10 +125,10 @@ bool MixContext::TSortInfo(const SplitterContext& splitter_context) {
         return false;
     }
 
-    std::vector<s32> sorted_results{node_states.GetSortedResuls()};
-    const auto result_size{std::min(count, static_cast<s32>(sorted_results.size()))};
+    auto sorted_results{node_states.GetSortedResuls()};
+    const auto result_size{std::min(count, static_cast<s32>(sorted_results.second))};
     for (s32 i = 0; i < result_size; i++) {
-        sorted_mix_infos[i] = &mix_infos[sorted_results[i]];
+        sorted_mix_infos[i] = &mix_infos[sorted_results.first[i]];
     }
 
     CalcMixBufferOffset();
diff --git a/src/audio_core/renderer/nodes/node_states.cpp b/src/audio_core/renderer/nodes/node_states.cpp
index 1821a51e6..b7a44a54c 100644
--- a/src/audio_core/renderer/nodes/node_states.cpp
+++ b/src/audio_core/renderer/nodes/node_states.cpp
@@ -134,8 +134,8 @@ u32 NodeStates::GetNodeCount() const {
     return node_count;
 }
 
-std::vector<s32> NodeStates::GetSortedResuls() const {
-    return {results.rbegin(), results.rbegin() + result_pos};
+std::pair<std::span<u32>::reverse_iterator, size_t> NodeStates::GetSortedResuls() const {
+    return {results.rbegin(), result_pos};
 }
 
 } // namespace AudioCore::AudioRenderer
diff --git a/src/audio_core/renderer/nodes/node_states.h b/src/audio_core/renderer/nodes/node_states.h
index 94b1d1254..e768cd4b5 100644
--- a/src/audio_core/renderer/nodes/node_states.h
+++ b/src/audio_core/renderer/nodes/node_states.h
@@ -175,7 +175,7 @@ public:
      *
      * @return Vector of nodes in reverse order.
      */
-    std::vector<s32> GetSortedResuls() const;
+    std::pair<std::span<u32>::reverse_iterator, size_t> GetSortedResuls() const;
 
 private:
     /// Number of nodes in the graph
diff --git a/src/audio_core/renderer/system.cpp b/src/audio_core/renderer/system.cpp
index 53b258c4f..a23627472 100644
--- a/src/audio_core/renderer/system.cpp
+++ b/src/audio_core/renderer/system.cpp
@@ -444,6 +444,7 @@ Result System::Update(std::span<const u8> input, std::span<u8> performance, std:
     std::scoped_lock l{lock};
 
     const auto start_time{core.CoreTiming().GetClockTicks()};
+    std::memset(output.data(), 0, output.size());
 
     InfoUpdater info_updater(input, output, process_handle, behavior);
 
diff --git a/src/audio_core/sink/null_sink.h b/src/audio_core/sink/null_sink.h
index 1215d3cd2..b6b43c93e 100644
--- a/src/audio_core/sink/null_sink.h
+++ b/src/audio_core/sink/null_sink.h
@@ -20,7 +20,7 @@ public:
     explicit NullSinkStreamImpl(Core::System& system_, StreamType type_)
         : SinkStream{system_, type_} {}
     ~NullSinkStreamImpl() override {}
-    void AppendBuffer(SinkBuffer&, std::vector<s16>&) override {}
+    void AppendBuffer(SinkBuffer&, std::span<s16>) override {}
     std::vector<s16> ReleaseBuffer(u64) override {
         return {};
     }
diff --git a/src/audio_core/sink/sink_stream.cpp b/src/audio_core/sink/sink_stream.cpp
index f44fedfd5..404dcd0e9 100644
--- a/src/audio_core/sink/sink_stream.cpp
+++ b/src/audio_core/sink/sink_stream.cpp
@@ -15,11 +15,10 @@
 #include "common/settings.h"
 #include "core/core.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 
 namespace AudioCore::Sink {
 
-void SinkStream::AppendBuffer(SinkBuffer& buffer, std::vector<s16>& samples) {
+void SinkStream::AppendBuffer(SinkBuffer& buffer, std::span<s16> samples) {
     if (type == StreamType::In) {
         queue.enqueue(buffer);
         queued_buffers++;
@@ -67,15 +66,16 @@ void SinkStream::AppendBuffer(SinkBuffer& buffer, std::vector<s16>& samples) {
                 static_cast<s16>(std::clamp(right_sample, min, max));
         }
 
-        samples.resize(samples.size() / system_channels * device_channels);
+        samples = samples.subspan(0, samples.size() / system_channels * device_channels);
 
     } else if (system_channels == 2 && device_channels == 6) {
         // We need moar samples! Not all games will provide 6 channel audio.
         // TODO: Implement some upmixing here. Currently just passthrough, with other
         // channels left as silence.
-        std::vector<s16> new_samples(samples.size() / system_channels * device_channels, 0);
+        auto new_size = samples.size() / system_channels * device_channels;
+        tmp_samples.resize_destructive(new_size);
 
-        for (u32 read_index = 0, write_index = 0; read_index < samples.size();
+        for (u32 read_index = 0, write_index = 0; read_index < new_size;
              read_index += system_channels, write_index += device_channels) {
             const auto left_sample{static_cast<s16>(std::clamp(
                 static_cast<s32>(
@@ -83,7 +83,7 @@ void SinkStream::AppendBuffer(SinkBuffer& buffer, std::vector<s16>& samples) {
                     volume),
                 min, max))};
 
-            new_samples[write_index + static_cast<u32>(Channels::FrontLeft)] = left_sample;
+            tmp_samples[write_index + static_cast<u32>(Channels::FrontLeft)] = left_sample;
 
             const auto right_sample{static_cast<s16>(std::clamp(
                 static_cast<s32>(
@@ -91,9 +91,9 @@ void SinkStream::AppendBuffer(SinkBuffer& buffer, std::vector<s16>& samples) {
                     volume),
                 min, max))};
 
-            new_samples[write_index + static_cast<u32>(Channels::FrontRight)] = right_sample;
+            tmp_samples[write_index + static_cast<u32>(Channels::FrontRight)] = right_sample;
         }
-        samples = std::move(new_samples);
+        samples = std::span<s16>(tmp_samples);
 
     } else if (volume != 1.0f) {
         for (u32 i = 0; i < samples.size(); i++) {
diff --git a/src/audio_core/sink/sink_stream.h b/src/audio_core/sink/sink_stream.h
index 41cbadc9c..98d72ace1 100644
--- a/src/audio_core/sink/sink_stream.h
+++ b/src/audio_core/sink/sink_stream.h
@@ -16,6 +16,7 @@
 #include "common/polyfill_thread.h"
 #include "common/reader_writer_queue.h"
 #include "common/ring_buffer.h"
+#include "common/scratch_buffer.h"
 #include "common/thread.h"
 
 namespace Core {
@@ -170,7 +171,7 @@ public:
      * @param buffer  - Audio buffer information to be queued.
      * @param samples - The s16 samples to be queue for playback.
      */
-    virtual void AppendBuffer(SinkBuffer& buffer, std::vector<s16>& samples);
+    virtual void AppendBuffer(SinkBuffer& buffer, std::span<s16> samples);
 
     /**
      * Release a buffer. Audio In only, will fill a buffer with recorded samples.
@@ -255,6 +256,8 @@ private:
     /// Signalled when ring buffer entries are consumed
     std::condition_variable_any release_cv;
     std::mutex release_mutex;
+    /// Temporary buffer for appending samples when upmixing
+    Common::ScratchBuffer<s16> tmp_samples{};
 };
 
 using SinkStreamPtr = std::unique_ptr<SinkStream>;
diff --git a/src/common/CMakeLists.txt b/src/common/CMakeLists.txt
index efc4a9fe9..3adf13a3f 100644
--- a/src/common/CMakeLists.txt
+++ b/src/common/CMakeLists.txt
@@ -172,6 +172,8 @@ if(ARCHITECTURE_x86_64)
             x64/cpu_wait.h
             x64/native_clock.cpp
             x64/native_clock.h
+            x64/rdtsc.cpp
+            x64/rdtsc.h
             x64/xbyak_abi.h
             x64/xbyak_util.h
     )
diff --git a/src/common/fs/fs.cpp b/src/common/fs/fs.cpp
index 6d66c926d..36e67c145 100644
--- a/src/common/fs/fs.cpp
+++ b/src/common/fs/fs.cpp
@@ -436,7 +436,7 @@ void IterateDirEntries(const std::filesystem::path& path, const DirEntryCallable
 
         if (True(filter & DirEntryFilter::File) &&
             entry.status().type() == fs::file_type::regular) {
-            if (!callback(entry.path())) {
+            if (!callback(entry)) {
                 callback_error = true;
                 break;
             }
@@ -444,7 +444,7 @@ void IterateDirEntries(const std::filesystem::path& path, const DirEntryCallable
 
         if (True(filter & DirEntryFilter::Directory) &&
             entry.status().type() == fs::file_type::directory) {
-            if (!callback(entry.path())) {
+            if (!callback(entry)) {
                 callback_error = true;
                 break;
             }
@@ -493,7 +493,7 @@ void IterateDirEntriesRecursively(const std::filesystem::path& path,
 
         if (True(filter & DirEntryFilter::File) &&
             entry.status().type() == fs::file_type::regular) {
-            if (!callback(entry.path())) {
+            if (!callback(entry)) {
                 callback_error = true;
                 break;
             }
@@ -501,7 +501,7 @@ void IterateDirEntriesRecursively(const std::filesystem::path& path,
 
         if (True(filter & DirEntryFilter::Directory) &&
             entry.status().type() == fs::file_type::directory) {
-            if (!callback(entry.path())) {
+            if (!callback(entry)) {
                 callback_error = true;
                 break;
             }
@@ -605,6 +605,12 @@ fs::file_type GetEntryType(const fs::path& path) {
 }
 
 u64 GetSize(const fs::path& path) {
+#ifdef ANDROID
+    if (Android::IsContentUri(path)) {
+        return Android::GetSize(path);
+    }
+#endif
+
     std::error_code ec;
 
     const auto file_size = fs::file_size(path, ec);
diff --git a/src/common/fs/fs_types.h b/src/common/fs/fs_types.h
index 5a4090c19..900f85d24 100644
--- a/src/common/fs/fs_types.h
+++ b/src/common/fs/fs_types.h
@@ -66,6 +66,6 @@ DECLARE_ENUM_FLAG_OPERATORS(DirEntryFilter);
  * @returns A boolean value.
  *          Return true to indicate whether the callback is successful, false otherwise.
  */
-using DirEntryCallable = std::function<bool(const std::filesystem::path& path)>;
+using DirEntryCallable = std::function<bool(const std::filesystem::directory_entry& entry)>;
 
 } // namespace Common::FS
diff --git a/src/common/input.h b/src/common/input.h
index 66fb15f0a..2c4ccea22 100644
--- a/src/common/input.h
+++ b/src/common/input.h
@@ -75,8 +75,10 @@ enum class DriverResult {
     ErrorWritingData,
     NoDeviceDetected,
     InvalidHandle,
+    InvalidParameters,
     NotSupported,
     Disabled,
+    Delayed,
     Unknown,
 };
 
@@ -86,7 +88,7 @@ enum class NfcState {
     NewAmiibo,
     WaitingForAmiibo,
     AmiiboRemoved,
-    NotAnAmiibo,
+    InvalidTagType,
     NotSupported,
     WrongDeviceState,
     WriteFailed,
@@ -218,8 +220,22 @@ struct CameraStatus {
 };
 
 struct NfcStatus {
-    NfcState state{};
-    std::vector<u8> data{};
+    NfcState state{NfcState::Unknown};
+    u8 uuid_length;
+    u8 protocol;
+    u8 tag_type;
+    std::array<u8, 10> uuid;
+};
+
+struct MifareData {
+    u8 command;
+    u8 sector;
+    std::array<u8, 0x6> key;
+    std::array<u8, 0x10> data;
+};
+
+struct MifareRequest {
+    std::array<MifareData, 0x10> data;
 };
 
 // List of buttons to be passed to Qt that can be translated
@@ -294,7 +310,7 @@ struct CallbackStatus {
     BatteryStatus battery_status{};
     VibrationStatus vibration_status{};
     CameraFormat camera_status{CameraFormat::None};
-    NfcState nfc_status{NfcState::Unknown};
+    NfcStatus nfc_status{};
     std::vector<u8> raw_data{};
 };
 
@@ -356,9 +372,30 @@ public:
         return NfcState::NotSupported;
     }
 
+    virtual NfcState StartNfcPolling() {
+        return NfcState::NotSupported;
+    }
+
+    virtual NfcState StopNfcPolling() {
+        return NfcState::NotSupported;
+    }
+
+    virtual NfcState ReadAmiiboData([[maybe_unused]] std::vector<u8>& out_data) {
+        return NfcState::NotSupported;
+    }
+
     virtual NfcState WriteNfcData([[maybe_unused]] const std::vector<u8>& data) {
         return NfcState::NotSupported;
     }
+
+    virtual NfcState ReadMifareData([[maybe_unused]] const MifareRequest& request,
+                                    [[maybe_unused]] MifareRequest& out_data) {
+        return NfcState::NotSupported;
+    }
+
+    virtual NfcState WriteMifareData([[maybe_unused]] const MifareRequest& request) {
+        return NfcState::NotSupported;
+    }
 };
 
 /// An abstract class template for a factory that can create input devices.
diff --git a/src/common/ring_buffer.h b/src/common/ring_buffer.h
index 4c328ab44..416680d44 100644
--- a/src/common/ring_buffer.h
+++ b/src/common/ring_buffer.h
@@ -9,6 +9,7 @@
 #include <cstddef>
 #include <cstring>
 #include <new>
+#include <span>
 #include <type_traits>
 #include <vector>
 
@@ -53,7 +54,7 @@ public:
         return push_count;
     }
 
-    std::size_t Push(const std::vector<T>& input) {
+    std::size_t Push(const std::span<T> input) {
         return Push(input.data(), input.size());
     }
 
diff --git a/src/common/scratch_buffer.h b/src/common/scratch_buffer.h
index a69a5a7af..6fe907953 100644
--- a/src/common/scratch_buffer.h
+++ b/src/common/scratch_buffer.h
@@ -3,6 +3,9 @@
 
 #pragma once
 
+#include <iterator>
+
+#include "common/concepts.h"
 #include "common/make_unique_for_overwrite.h"
 
 namespace Common {
@@ -16,6 +19,12 @@ namespace Common {
 template <typename T>
 class ScratchBuffer {
 public:
+    using iterator = T*;
+    using const_iterator = const T*;
+    using value_type = T;
+    using element_type = T;
+    using iterator_category = std::contiguous_iterator_tag;
+
     ScratchBuffer() = default;
 
     explicit ScratchBuffer(size_t initial_capacity)
diff --git a/src/common/settings.cpp b/src/common/settings.cpp
index 66dffc9bf..6cbbea1b2 100644
--- a/src/common/settings.cpp
+++ b/src/common/settings.cpp
@@ -1,8 +1,11 @@
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <version>
 #if __cpp_lib_chrono >= 201907L
 #include <chrono>
+#include <exception>
+#include <stdexcept>
 #endif
 #include <string_view>
 
@@ -25,9 +28,19 @@ std::string GetTimeZoneString() {
     if (time_zone_index == 0) { // Auto
 #if __cpp_lib_chrono >= 201907L
         const struct std::chrono::tzdb& time_zone_data = std::chrono::get_tzdb();
-        const std::chrono::time_zone* current_zone = time_zone_data.current_zone();
-        std::string_view current_zone_name = current_zone->name();
-        location_name = current_zone_name;
+        try {
+            const std::chrono::time_zone* current_zone = time_zone_data.current_zone();
+            std::string_view current_zone_name = current_zone->name();
+            location_name = current_zone_name;
+        } catch (std::runtime_error& runtime_error) {
+            // VCRUNTIME will throw a runtime_error if the operating system's selected time zone
+            // cannot be found
+            location_name = Common::TimeZone::FindSystemTimeZone();
+            LOG_WARNING(Common,
+                        "Error occurred when trying to determine system time zone:\n{}\nFalling "
+                        "back to hour offset \"{}\"",
+                        runtime_error.what(), location_name);
+        }
 #else
         location_name = Common::TimeZone::FindSystemTimeZone();
 #endif
diff --git a/src/common/settings.h b/src/common/settings.h
index 9682281b0..ae5ed93d8 100644
--- a/src/common/settings.h
+++ b/src/common/settings.h
@@ -483,6 +483,7 @@ struct Values {
         AstcRecompression::Uncompressed, AstcRecompression::Uncompressed, AstcRecompression::Bc3,
         "astc_recompression"};
     SwitchableSetting<bool> use_video_framerate{false, "use_video_framerate"};
+    SwitchableSetting<bool> barrier_feedback_loops{true, "barrier_feedback_loops"};
 
     SwitchableSetting<u8> bg_red{0, "bg_red"};
     SwitchableSetting<u8> bg_green{0, "bg_green"};
@@ -524,9 +525,16 @@ struct Values {
     Setting<bool> tas_loop{false, "tas_loop"};
 
     Setting<bool> mouse_panning{false, "mouse_panning"};
-    Setting<u8, true> mouse_panning_sensitivity{50, 1, 100, "mouse_panning_sensitivity"};
-    Setting<bool> mouse_enabled{false, "mouse_enabled"};
+    Setting<u8, true> mouse_panning_x_sensitivity{50, 1, 100, "mouse_panning_x_sensitivity"};
+    Setting<u8, true> mouse_panning_y_sensitivity{50, 1, 100, "mouse_panning_y_sensitivity"};
+    Setting<u8, true> mouse_panning_deadzone_x_counterweight{
+        0, 0, 100, "mouse_panning_deadzone_x_counterweight"};
+    Setting<u8, true> mouse_panning_deadzone_y_counterweight{
+        0, 0, 100, "mouse_panning_deadzone_y_counterweight"};
+    Setting<u8, true> mouse_panning_decay_strength{22, 0, 100, "mouse_panning_decay_strength"};
+    Setting<u8, true> mouse_panning_min_decay{5, 0, 100, "mouse_panning_min_decay"};
 
+    Setting<bool> mouse_enabled{false, "mouse_enabled"};
     Setting<bool> emulate_analog_keyboard{false, "emulate_analog_keyboard"};
     Setting<bool> keyboard_enabled{false, "keyboard_enabled"};
 
diff --git a/src/common/steady_clock.cpp b/src/common/steady_clock.cpp
index 782859196..9415eed29 100644
--- a/src/common/steady_clock.cpp
+++ b/src/common/steady_clock.cpp
@@ -28,13 +28,12 @@ static s64 GetSystemTimeNS() {
     // GetSystemTimePreciseAsFileTime returns the file time in 100ns units.
     static constexpr s64 Multiplier = 100;
     // Convert Windows epoch to Unix epoch.
-    static constexpr s64 WindowsEpochToUnixEpochNS = 0x19DB1DED53E8000LL;
+    static constexpr s64 WindowsEpochToUnixEpoch = 0x19DB1DED53E8000LL;
 
     FILETIME filetime;
     GetSystemTimePreciseAsFileTime(&filetime);
     return Multiplier * ((static_cast<s64>(filetime.dwHighDateTime) << 32) +
-                         static_cast<s64>(filetime.dwLowDateTime)) -
-           WindowsEpochToUnixEpochNS;
+                         static_cast<s64>(filetime.dwLowDateTime) - WindowsEpochToUnixEpoch);
 }
 #endif
 
diff --git a/src/common/telemetry.cpp b/src/common/telemetry.cpp
index 91352912d..929ed67e4 100644
--- a/src/common/telemetry.cpp
+++ b/src/common/telemetry.cpp
@@ -93,6 +93,7 @@ void AppendCPUInfo(FieldCollection& fc) {
     add_field("CPU_Extension_x64_GFNI", caps.gfni);
     add_field("CPU_Extension_x64_INVARIANT_TSC", caps.invariant_tsc);
     add_field("CPU_Extension_x64_LZCNT", caps.lzcnt);
+    add_field("CPU_Extension_x64_MONITORX", caps.monitorx);
     add_field("CPU_Extension_x64_MOVBE", caps.movbe);
     add_field("CPU_Extension_x64_PCLMULQDQ", caps.pclmulqdq);
     add_field("CPU_Extension_x64_POPCNT", caps.popcnt);
diff --git a/src/common/thread.h b/src/common/thread.h
index 8ae169b4e..c6976fb6c 100644
--- a/src/common/thread.h
+++ b/src/common/thread.h
@@ -55,7 +55,7 @@ public:
         is_set = false;
     }
 
-    [[nodiscard]] bool IsSet() {
+    [[nodiscard]] bool IsSet() const {
         return is_set;
     }
 
diff --git a/src/common/wall_clock.cpp b/src/common/wall_clock.cpp
index 817e71d52..dc0dcbd68 100644
--- a/src/common/wall_clock.cpp
+++ b/src/common/wall_clock.cpp
@@ -2,88 +2,75 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include "common/steady_clock.h"
-#include "common/uint128.h"
 #include "common/wall_clock.h"
 
 #ifdef ARCHITECTURE_x86_64
 #include "common/x64/cpu_detect.h"
 #include "common/x64/native_clock.h"
+#include "common/x64/rdtsc.h"
 #endif
 
 namespace Common {
 
 class StandardWallClock final : public WallClock {
 public:
-    explicit StandardWallClock(u64 emulated_cpu_frequency_, u64 emulated_clock_frequency_)
-        : WallClock{emulated_cpu_frequency_, emulated_clock_frequency_, false},
-          start_time{SteadyClock::Now()} {}
+    explicit StandardWallClock() : start_time{SteadyClock::Now()} {}
 
-    std::chrono::nanoseconds GetTimeNS() override {
+    std::chrono::nanoseconds GetTimeNS() const override {
         return SteadyClock::Now() - start_time;
     }
 
-    std::chrono::microseconds GetTimeUS() override {
-        return std::chrono::duration_cast<std::chrono::microseconds>(GetTimeNS());
+    std::chrono::microseconds GetTimeUS() const override {
+        return static_cast<std::chrono::microseconds>(GetHostTicksElapsed() / NsToUsRatio::den);
     }
 
-    std::chrono::milliseconds GetTimeMS() override {
-        return std::chrono::duration_cast<std::chrono::milliseconds>(GetTimeNS());
+    std::chrono::milliseconds GetTimeMS() const override {
+        return static_cast<std::chrono::milliseconds>(GetHostTicksElapsed() / NsToMsRatio::den);
     }
 
-    u64 GetClockCycles() override {
-        const u128 temp = Common::Multiply64Into128(GetTimeNS().count(), emulated_clock_frequency);
-        return Common::Divide128On32(temp, NS_RATIO).first;
+    u64 GetCNTPCT() const override {
+        return GetHostTicksElapsed() * NsToCNTPCTRatio::num / NsToCNTPCTRatio::den;
     }
 
-    u64 GetCPUCycles() override {
-        const u128 temp = Common::Multiply64Into128(GetTimeNS().count(), emulated_cpu_frequency);
-        return Common::Divide128On32(temp, NS_RATIO).first;
+    u64 GetGPUTick() const override {
+        return GetHostTicksElapsed() * NsToGPUTickRatio::num / NsToGPUTickRatio::den;
     }
 
-    void Pause([[maybe_unused]] bool is_paused) override {
-        // Do nothing in this clock type.
+    u64 GetHostTicksNow() const override {
+        return static_cast<u64>(SteadyClock::Now().time_since_epoch().count());
+    }
+
+    u64 GetHostTicksElapsed() const override {
+        return static_cast<u64>(GetTimeNS().count());
+    }
+
+    bool IsNative() const override {
+        return false;
     }
 
 private:
     SteadyClock::time_point start_time;
 };
 
+std::unique_ptr<WallClock> CreateOptimalClock() {
 #ifdef ARCHITECTURE_x86_64
-
-std::unique_ptr<WallClock> CreateBestMatchingClock(u64 emulated_cpu_frequency,
-                                                   u64 emulated_clock_frequency) {
     const auto& caps = GetCPUCaps();
-    u64 rtsc_frequency = 0;
-    if (caps.invariant_tsc) {
-        rtsc_frequency = caps.tsc_frequency ? caps.tsc_frequency : EstimateRDTSCFrequency();
-    }
 
-    // Fallback to StandardWallClock if the hardware TSC does not have the precision greater than:
-    // - A nanosecond
-    // - The emulated CPU frequency
-    // - The emulated clock counter frequency (CNTFRQ)
-    if (rtsc_frequency <= WallClock::NS_RATIO || rtsc_frequency <= emulated_cpu_frequency ||
-        rtsc_frequency <= emulated_clock_frequency) {
-        return std::make_unique<StandardWallClock>(emulated_cpu_frequency,
-                                                   emulated_clock_frequency);
+    if (caps.invariant_tsc && caps.tsc_frequency >= WallClock::GPUTickFreq) {
+        return std::make_unique<X64::NativeClock>(caps.tsc_frequency);
     } else {
-        return std::make_unique<X64::NativeClock>(emulated_cpu_frequency, emulated_clock_frequency,
-                                                  rtsc_frequency);
+        // Fallback to StandardWallClock if the hardware TSC
+        // - Is not invariant
+        // - Is not more precise than GPUTickFreq
+        return std::make_unique<StandardWallClock>();
     }
-}
-
 #else
-
-std::unique_ptr<WallClock> CreateBestMatchingClock(u64 emulated_cpu_frequency,
-                                                   u64 emulated_clock_frequency) {
-    return std::make_unique<StandardWallClock>(emulated_cpu_frequency, emulated_clock_frequency);
-}
-
+    return std::make_unique<StandardWallClock>();
 #endif
+}
 
-std::unique_ptr<WallClock> CreateStandardWallClock(u64 emulated_cpu_frequency,
-                                                   u64 emulated_clock_frequency) {
-    return std::make_unique<StandardWallClock>(emulated_cpu_frequency, emulated_clock_frequency);
+std::unique_ptr<WallClock> CreateStandardWallClock() {
+    return std::make_unique<StandardWallClock>();
 }
 
 } // namespace Common
diff --git a/src/common/wall_clock.h b/src/common/wall_clock.h
index 157ec5eae..f45d3d8c5 100644
--- a/src/common/wall_clock.h
+++ b/src/common/wall_clock.h
@@ -5,6 +5,7 @@
 
 #include <chrono>
 #include <memory>
+#include <ratio>
 
 #include "common/common_types.h"
 
@@ -12,50 +13,82 @@ namespace Common {
 
 class WallClock {
 public:
-    static constexpr u64 NS_RATIO = 1'000'000'000;
-    static constexpr u64 US_RATIO = 1'000'000;
-    static constexpr u64 MS_RATIO = 1'000;
+    static constexpr u64 CNTFRQ = 19'200'000;         // CNTPCT_EL0 Frequency = 19.2 MHz
+    static constexpr u64 GPUTickFreq = 614'400'000;   // GM20B GPU Tick Frequency = 614.4 MHz
+    static constexpr u64 CPUTickFreq = 1'020'000'000; // T210/4 A57 CPU Tick Frequency = 1020.0 MHz
 
     virtual ~WallClock() = default;
 
-    /// Returns current wall time in nanoseconds
-    [[nodiscard]] virtual std::chrono::nanoseconds GetTimeNS() = 0;
+    /// @returns The time in nanoseconds since the construction of this clock.
+    virtual std::chrono::nanoseconds GetTimeNS() const = 0;
 
-    /// Returns current wall time in microseconds
-    [[nodiscard]] virtual std::chrono::microseconds GetTimeUS() = 0;
+    /// @returns The time in microseconds since the construction of this clock.
+    virtual std::chrono::microseconds GetTimeUS() const = 0;
 
-    /// Returns current wall time in milliseconds
-    [[nodiscard]] virtual std::chrono::milliseconds GetTimeMS() = 0;
+    /// @returns The time in milliseconds since the construction of this clock.
+    virtual std::chrono::milliseconds GetTimeMS() const = 0;
 
-    /// Returns current wall time in emulated clock cycles
-    [[nodiscard]] virtual u64 GetClockCycles() = 0;
+    /// @returns The guest CNTPCT ticks since the construction of this clock.
+    virtual u64 GetCNTPCT() const = 0;
 
-    /// Returns current wall time in emulated cpu cycles
-    [[nodiscard]] virtual u64 GetCPUCycles() = 0;
+    /// @returns The guest GPU ticks since the construction of this clock.
+    virtual u64 GetGPUTick() const = 0;
 
-    virtual void Pause(bool is_paused) = 0;
+    /// @returns The raw host timer ticks since an indeterminate epoch.
+    virtual u64 GetHostTicksNow() const = 0;
 
-    /// Tells if the wall clock, uses the host CPU's hardware clock
-    [[nodiscard]] bool IsNative() const {
-        return is_native;
+    /// @returns The raw host timer ticks since the construction of this clock.
+    virtual u64 GetHostTicksElapsed() const = 0;
+
+    /// @returns Whether the clock directly uses the host's hardware clock.
+    virtual bool IsNative() const = 0;
+
+    static inline u64 NSToCNTPCT(u64 ns) {
+        return ns * NsToCNTPCTRatio::num / NsToCNTPCTRatio::den;
+    }
+
+    static inline u64 NSToGPUTick(u64 ns) {
+        return ns * NsToGPUTickRatio::num / NsToGPUTickRatio::den;
+    }
+
+    // Cycle Timing
+
+    static inline u64 CPUTickToNS(u64 cpu_tick) {
+        return cpu_tick * CPUTickToNsRatio::num / CPUTickToNsRatio::den;
+    }
+
+    static inline u64 CPUTickToUS(u64 cpu_tick) {
+        return cpu_tick * CPUTickToUsRatio::num / CPUTickToUsRatio::den;
+    }
+
+    static inline u64 CPUTickToCNTPCT(u64 cpu_tick) {
+        return cpu_tick * CPUTickToCNTPCTRatio::num / CPUTickToCNTPCTRatio::den;
+    }
+
+    static inline u64 CPUTickToGPUTick(u64 cpu_tick) {
+        return cpu_tick * CPUTickToGPUTickRatio::num / CPUTickToGPUTickRatio::den;
     }
 
 protected:
-    explicit WallClock(u64 emulated_cpu_frequency_, u64 emulated_clock_frequency_, bool is_native_)
-        : emulated_cpu_frequency{emulated_cpu_frequency_},
-          emulated_clock_frequency{emulated_clock_frequency_}, is_native{is_native_} {}
+    using NsRatio = std::nano;
+    using UsRatio = std::micro;
+    using MsRatio = std::milli;
+
+    using NsToUsRatio = std::ratio_divide<std::nano, std::micro>;
+    using NsToMsRatio = std::ratio_divide<std::nano, std::milli>;
+    using NsToCNTPCTRatio = std::ratio<CNTFRQ, std::nano::den>;
+    using NsToGPUTickRatio = std::ratio<GPUTickFreq, std::nano::den>;
 
-    u64 emulated_cpu_frequency;
-    u64 emulated_clock_frequency;
+    // Cycle Timing
 
-private:
-    bool is_native;
+    using CPUTickToNsRatio = std::ratio<std::nano::den, CPUTickFreq>;
+    using CPUTickToUsRatio = std::ratio<std::micro::den, CPUTickFreq>;
+    using CPUTickToCNTPCTRatio = std::ratio<CNTFRQ, CPUTickFreq>;
+    using CPUTickToGPUTickRatio = std::ratio<GPUTickFreq, CPUTickFreq>;
 };
 
-[[nodiscard]] std::unique_ptr<WallClock> CreateBestMatchingClock(u64 emulated_cpu_frequency,
-                                                                 u64 emulated_clock_frequency);
+std::unique_ptr<WallClock> CreateOptimalClock();
 
-[[nodiscard]] std::unique_ptr<WallClock> CreateStandardWallClock(u64 emulated_cpu_frequency,
-                                                                 u64 emulated_clock_frequency);
+std::unique_ptr<WallClock> CreateStandardWallClock();
 
 } // namespace Common
diff --git a/src/common/x64/cpu_detect.cpp b/src/common/x64/cpu_detect.cpp
index 72ed6e96c..780120a5b 100644
--- a/src/common/x64/cpu_detect.cpp
+++ b/src/common/x64/cpu_detect.cpp
@@ -14,6 +14,7 @@
 #include "common/common_types.h"
 #include "common/logging/log.h"
 #include "common/x64/cpu_detect.h"
+#include "common/x64/rdtsc.h"
 
 #ifdef _WIN32
 #include <windows.h>
@@ -167,6 +168,7 @@ static CPUCaps Detect() {
         __cpuid(cpu_id, 0x80000001);
         caps.lzcnt = Common::Bit<5>(cpu_id[2]);
         caps.fma4 = Common::Bit<16>(cpu_id[2]);
+        caps.monitorx = Common::Bit<29>(cpu_id[2]);
     }
 
     if (max_ex_fn >= 0x80000007) {
@@ -187,6 +189,8 @@ static CPUCaps Detect() {
             caps.tsc_frequency = static_cast<u64>(caps.crystal_frequency) *
                                  caps.tsc_crystal_ratio_numerator /
                                  caps.tsc_crystal_ratio_denominator;
+        } else {
+            caps.tsc_frequency = X64::EstimateRDTSCFrequency();
         }
     }
 
diff --git a/src/common/x64/cpu_detect.h b/src/common/x64/cpu_detect.h
index 8253944d6..756459417 100644
--- a/src/common/x64/cpu_detect.h
+++ b/src/common/x64/cpu_detect.h
@@ -63,6 +63,7 @@ struct CPUCaps {
     bool gfni : 1;
     bool invariant_tsc : 1;
     bool lzcnt : 1;
+    bool monitorx : 1;
     bool movbe : 1;
     bool pclmulqdq : 1;
     bool popcnt : 1;
diff --git a/src/common/x64/cpu_wait.cpp b/src/common/x64/cpu_wait.cpp
index cfeef6a3d..41d385f59 100644
--- a/src/common/x64/cpu_wait.cpp
+++ b/src/common/x64/cpu_wait.cpp
@@ -9,58 +9,64 @@
 
 #include "common/x64/cpu_detect.h"
 #include "common/x64/cpu_wait.h"
+#include "common/x64/rdtsc.h"
 
 namespace Common::X64 {
 
+namespace {
+
+// 100,000 cycles is a reasonable amount of time to wait to save on CPU resources.
+// For reference:
+// At 1 GHz, 100K cycles is 100us
+// At 2 GHz, 100K cycles is 50us
+// At 4 GHz, 100K cycles is 25us
+constexpr auto PauseCycles = 100'000U;
+
+} // Anonymous namespace
+
 #ifdef _MSC_VER
-__forceinline static u64 FencedRDTSC() {
-    _mm_lfence();
-    _ReadWriteBarrier();
-    const u64 result = __rdtsc();
-    _mm_lfence();
-    _ReadWriteBarrier();
-    return result;
+__forceinline static void TPAUSE() {
+    static constexpr auto RequestC02State = 0U;
+    _tpause(RequestC02State, FencedRDTSC() + PauseCycles);
 }
 
-__forceinline static void TPAUSE() {
-    // 100,000 cycles is a reasonable amount of time to wait to save on CPU resources.
-    // For reference:
-    // At 1 GHz, 100K cycles is 100us
-    // At 2 GHz, 100K cycles is 50us
-    // At 4 GHz, 100K cycles is 25us
-    static constexpr auto PauseCycles = 100'000;
-    _tpause(0, FencedRDTSC() + PauseCycles);
+__forceinline static void MWAITX() {
+    static constexpr auto EnableWaitTimeFlag = 1U << 1;
+    static constexpr auto RequestC1State = 0U;
+
+    // monitor_var should be aligned to a cache line.
+    alignas(64) u64 monitor_var{};
+    _mm_monitorx(&monitor_var, 0, 0);
+    _mm_mwaitx(EnableWaitTimeFlag, RequestC1State, PauseCycles);
 }
 #else
-static u64 FencedRDTSC() {
-    u64 eax;
-    u64 edx;
-    asm volatile("lfence\n\t"
-                 "rdtsc\n\t"
-                 "lfence\n\t"
-                 : "=a"(eax), "=d"(edx));
-    return (edx << 32) | eax;
-}
-
 static void TPAUSE() {
-    // 100,000 cycles is a reasonable amount of time to wait to save on CPU resources.
-    // For reference:
-    // At 1 GHz, 100K cycles is 100us
-    // At 2 GHz, 100K cycles is 50us
-    // At 4 GHz, 100K cycles is 25us
-    static constexpr auto PauseCycles = 100'000;
+    static constexpr auto RequestC02State = 0U;
     const auto tsc = FencedRDTSC() + PauseCycles;
     const auto eax = static_cast<u32>(tsc & 0xFFFFFFFF);
     const auto edx = static_cast<u32>(tsc >> 32);
-    asm volatile("tpause %0" : : "r"(0), "d"(edx), "a"(eax));
+    asm volatile("tpause %0" : : "r"(RequestC02State), "d"(edx), "a"(eax));
+}
+
+static void MWAITX() {
+    static constexpr auto EnableWaitTimeFlag = 1U << 1;
+    static constexpr auto RequestC1State = 0U;
+
+    // monitor_var should be aligned to a cache line.
+    alignas(64) u64 monitor_var{};
+    asm volatile("monitorx" : : "a"(&monitor_var), "c"(0), "d"(0));
+    asm volatile("mwaitx" : : "a"(RequestC1State), "b"(PauseCycles), "c"(EnableWaitTimeFlag));
 }
 #endif
 
 void MicroSleep() {
     static const bool has_waitpkg = GetCPUCaps().waitpkg;
+    static const bool has_monitorx = GetCPUCaps().monitorx;
 
     if (has_waitpkg) {
         TPAUSE();
+    } else if (has_monitorx) {
+        MWAITX();
     } else {
         std::this_thread::yield();
     }
diff --git a/src/common/x64/native_clock.cpp b/src/common/x64/native_clock.cpp
index 277b00662..7d2a26bd9 100644
--- a/src/common/x64/native_clock.cpp
+++ b/src/common/x64/native_clock.cpp
@@ -1,164 +1,50 @@
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <array>
-#include <chrono>
-#include <thread>
-
-#include "common/atomic_ops.h"
-#include "common/steady_clock.h"
 #include "common/uint128.h"
 #include "common/x64/native_clock.h"
+#include "common/x64/rdtsc.h"
 
-#ifdef _MSC_VER
-#include <intrin.h>
-#endif
-
-namespace Common {
+namespace Common::X64 {
 
-#ifdef _MSC_VER
-__forceinline static u64 FencedRDTSC() {
-    _mm_lfence();
-    _ReadWriteBarrier();
-    const u64 result = __rdtsc();
-    _mm_lfence();
-    _ReadWriteBarrier();
-    return result;
-}
-#else
-static u64 FencedRDTSC() {
-    u64 eax;
-    u64 edx;
-    asm volatile("lfence\n\t"
-                 "rdtsc\n\t"
-                 "lfence\n\t"
-                 : "=a"(eax), "=d"(edx));
-    return (edx << 32) | eax;
-}
-#endif
+NativeClock::NativeClock(u64 rdtsc_frequency_)
+    : start_ticks{FencedRDTSC()}, rdtsc_frequency{rdtsc_frequency_},
+      ns_rdtsc_factor{GetFixedPoint64Factor(NsRatio::den, rdtsc_frequency)},
+      us_rdtsc_factor{GetFixedPoint64Factor(UsRatio::den, rdtsc_frequency)},
+      ms_rdtsc_factor{GetFixedPoint64Factor(MsRatio::den, rdtsc_frequency)},
+      cntpct_rdtsc_factor{GetFixedPoint64Factor(CNTFRQ, rdtsc_frequency)},
+      gputick_rdtsc_factor{GetFixedPoint64Factor(GPUTickFreq, rdtsc_frequency)} {}
 
-template <u64 Nearest>
-static u64 RoundToNearest(u64 value) {
-    const auto mod = value % Nearest;
-    return mod >= (Nearest / 2) ? (value - mod + Nearest) : (value - mod);
+std::chrono::nanoseconds NativeClock::GetTimeNS() const {
+    return std::chrono::nanoseconds{MultiplyHigh(GetHostTicksElapsed(), ns_rdtsc_factor)};
 }
 
-u64 EstimateRDTSCFrequency() {
-    // Discard the first result measuring the rdtsc.
-    FencedRDTSC();
-    std::this_thread::sleep_for(std::chrono::milliseconds{1});
-    FencedRDTSC();
-
-    // Get the current time.
-    const auto start_time = Common::RealTimeClock::Now();
-    const u64 tsc_start = FencedRDTSC();
-    // Wait for 250 milliseconds.
-    std::this_thread::sleep_for(std::chrono::milliseconds{250});
-    const auto end_time = Common::RealTimeClock::Now();
-    const u64 tsc_end = FencedRDTSC();
-    // Calculate differences.
-    const u64 timer_diff = static_cast<u64>(
-        std::chrono::duration_cast<std::chrono::nanoseconds>(end_time - start_time).count());
-    const u64 tsc_diff = tsc_end - tsc_start;
-    const u64 tsc_freq = MultiplyAndDivide64(tsc_diff, 1000000000ULL, timer_diff);
-    return RoundToNearest<1000>(tsc_freq);
+std::chrono::microseconds NativeClock::GetTimeUS() const {
+    return std::chrono::microseconds{MultiplyHigh(GetHostTicksElapsed(), us_rdtsc_factor)};
 }
 
-namespace X64 {
-NativeClock::NativeClock(u64 emulated_cpu_frequency_, u64 emulated_clock_frequency_,
-                         u64 rtsc_frequency_)
-    : WallClock(emulated_cpu_frequency_, emulated_clock_frequency_, true), rtsc_frequency{
-                                                                               rtsc_frequency_} {
-    // Thread to re-adjust the RDTSC frequency after 10 seconds has elapsed.
-    time_sync_thread = std::jthread{[this](std::stop_token token) {
-        // Get the current time.
-        const auto start_time = Common::RealTimeClock::Now();
-        const u64 tsc_start = FencedRDTSC();
-        // Wait for 10 seconds.
-        if (!Common::StoppableTimedWait(token, std::chrono::seconds{10})) {
-            return;
-        }
-        const auto end_time = Common::RealTimeClock::Now();
-        const u64 tsc_end = FencedRDTSC();
-        // Calculate differences.
-        const u64 timer_diff = static_cast<u64>(
-            std::chrono::duration_cast<std::chrono::nanoseconds>(end_time - start_time).count());
-        const u64 tsc_diff = tsc_end - tsc_start;
-        const u64 tsc_freq = MultiplyAndDivide64(tsc_diff, 1000000000ULL, timer_diff);
-        rtsc_frequency = tsc_freq;
-        CalculateAndSetFactors();
-    }};
-
-    time_point.inner.last_measure = FencedRDTSC();
-    time_point.inner.accumulated_ticks = 0U;
-    CalculateAndSetFactors();
+std::chrono::milliseconds NativeClock::GetTimeMS() const {
+    return std::chrono::milliseconds{MultiplyHigh(GetHostTicksElapsed(), ms_rdtsc_factor)};
 }
 
-u64 NativeClock::GetRTSC() {
-    TimePoint new_time_point{};
-    TimePoint current_time_point{};
-
-    current_time_point.pack = Common::AtomicLoad128(time_point.pack.data());
-    do {
-        const u64 current_measure = FencedRDTSC();
-        u64 diff = current_measure - current_time_point.inner.last_measure;
-        diff = diff & ~static_cast<u64>(static_cast<s64>(diff) >> 63); // max(diff, 0)
-        new_time_point.inner.last_measure = current_measure > current_time_point.inner.last_measure
-                                                ? current_measure
-                                                : current_time_point.inner.last_measure;
-        new_time_point.inner.accumulated_ticks = current_time_point.inner.accumulated_ticks + diff;
-    } while (!Common::AtomicCompareAndSwap(time_point.pack.data(), new_time_point.pack,
-                                           current_time_point.pack, current_time_point.pack));
-    return new_time_point.inner.accumulated_ticks;
+u64 NativeClock::GetCNTPCT() const {
+    return MultiplyHigh(GetHostTicksElapsed(), cntpct_rdtsc_factor);
 }
 
-void NativeClock::Pause(bool is_paused) {
-    if (!is_paused) {
-        TimePoint current_time_point{};
-        TimePoint new_time_point{};
-
-        current_time_point.pack = Common::AtomicLoad128(time_point.pack.data());
-        do {
-            new_time_point.pack = current_time_point.pack;
-            new_time_point.inner.last_measure = FencedRDTSC();
-        } while (!Common::AtomicCompareAndSwap(time_point.pack.data(), new_time_point.pack,
-                                               current_time_point.pack, current_time_point.pack));
-    }
+u64 NativeClock::GetGPUTick() const {
+    return MultiplyHigh(GetHostTicksElapsed(), gputick_rdtsc_factor);
 }
 
-std::chrono::nanoseconds NativeClock::GetTimeNS() {
-    const u64 rtsc_value = GetRTSC();
-    return std::chrono::nanoseconds{MultiplyHigh(rtsc_value, ns_rtsc_factor)};
+u64 NativeClock::GetHostTicksNow() const {
+    return FencedRDTSC();
 }
 
-std::chrono::microseconds NativeClock::GetTimeUS() {
-    const u64 rtsc_value = GetRTSC();
-    return std::chrono::microseconds{MultiplyHigh(rtsc_value, us_rtsc_factor)};
+u64 NativeClock::GetHostTicksElapsed() const {
+    return FencedRDTSC() - start_ticks;
 }
 
-std::chrono::milliseconds NativeClock::GetTimeMS() {
-    const u64 rtsc_value = GetRTSC();
-    return std::chrono::milliseconds{MultiplyHigh(rtsc_value, ms_rtsc_factor)};
+bool NativeClock::IsNative() const {
+    return true;
 }
 
-u64 NativeClock::GetClockCycles() {
-    const u64 rtsc_value = GetRTSC();
-    return MultiplyHigh(rtsc_value, clock_rtsc_factor);
-}
-
-u64 NativeClock::GetCPUCycles() {
-    const u64 rtsc_value = GetRTSC();
-    return MultiplyHigh(rtsc_value, cpu_rtsc_factor);
-}
-
-void NativeClock::CalculateAndSetFactors() {
-    ns_rtsc_factor = GetFixedPoint64Factor(NS_RATIO, rtsc_frequency);
-    us_rtsc_factor = GetFixedPoint64Factor(US_RATIO, rtsc_frequency);
-    ms_rtsc_factor = GetFixedPoint64Factor(MS_RATIO, rtsc_frequency);
-    clock_rtsc_factor = GetFixedPoint64Factor(emulated_clock_frequency, rtsc_frequency);
-    cpu_rtsc_factor = GetFixedPoint64Factor(emulated_cpu_frequency, rtsc_frequency);
-}
-
-} // namespace X64
-
-} // namespace Common
+} // namespace Common::X64
diff --git a/src/common/x64/native_clock.h b/src/common/x64/native_clock.h
index 03ca291d8..334415eff 100644
--- a/src/common/x64/native_clock.h
+++ b/src/common/x64/native_clock.h
@@ -3,58 +3,39 @@
 
 #pragma once
 
-#include "common/polyfill_thread.h"
 #include "common/wall_clock.h"
 
-namespace Common {
+namespace Common::X64 {
 
-namespace X64 {
 class NativeClock final : public WallClock {
 public:
-    explicit NativeClock(u64 emulated_cpu_frequency_, u64 emulated_clock_frequency_,
-                         u64 rtsc_frequency_);
+    explicit NativeClock(u64 rdtsc_frequency_);
 
-    std::chrono::nanoseconds GetTimeNS() override;
+    std::chrono::nanoseconds GetTimeNS() const override;
 
-    std::chrono::microseconds GetTimeUS() override;
+    std::chrono::microseconds GetTimeUS() const override;
 
-    std::chrono::milliseconds GetTimeMS() override;
+    std::chrono::milliseconds GetTimeMS() const override;
 
-    u64 GetClockCycles() override;
+    u64 GetCNTPCT() const override;
 
-    u64 GetCPUCycles() override;
+    u64 GetGPUTick() const override;
 
-    void Pause(bool is_paused) override;
+    u64 GetHostTicksNow() const override;
 
-private:
-    u64 GetRTSC();
-
-    void CalculateAndSetFactors();
-
-    union alignas(16) TimePoint {
-        TimePoint() : pack{} {}
-        u128 pack{};
-        struct Inner {
-            u64 last_measure{};
-            u64 accumulated_ticks{};
-        } inner;
-    };
-
-    TimePoint time_point;
+    u64 GetHostTicksElapsed() const override;
 
-    // factors
-    u64 clock_rtsc_factor{};
-    u64 cpu_rtsc_factor{};
-    u64 ns_rtsc_factor{};
-    u64 us_rtsc_factor{};
-    u64 ms_rtsc_factor{};
+    bool IsNative() const override;
 
-    u64 rtsc_frequency;
-
-    std::jthread time_sync_thread;
+private:
+    u64 start_ticks;
+    u64 rdtsc_frequency;
+
+    u64 ns_rdtsc_factor;
+    u64 us_rdtsc_factor;
+    u64 ms_rdtsc_factor;
+    u64 cntpct_rdtsc_factor;
+    u64 gputick_rdtsc_factor;
 };
-} // namespace X64
-
-u64 EstimateRDTSCFrequency();
 
-} // namespace Common
+} // namespace Common::X64
diff --git a/src/common/x64/rdtsc.cpp b/src/common/x64/rdtsc.cpp
new file mode 100644
index 000000000..9273274a3
--- /dev/null
+++ b/src/common/x64/rdtsc.cpp
@@ -0,0 +1,39 @@
+// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <thread>
+
+#include "common/steady_clock.h"
+#include "common/uint128.h"
+#include "common/x64/rdtsc.h"
+
+namespace Common::X64 {
+
+template <u64 Nearest>
+static u64 RoundToNearest(u64 value) {
+    const auto mod = value % Nearest;
+    return mod >= (Nearest / 2) ? (value - mod + Nearest) : (value - mod);
+}
+
+u64 EstimateRDTSCFrequency() {
+    // Discard the first result measuring the rdtsc.
+    FencedRDTSC();
+    std::this_thread::sleep_for(std::chrono::milliseconds{1});
+    FencedRDTSC();
+
+    // Get the current time.
+    const auto start_time = RealTimeClock::Now();
+    const u64 tsc_start = FencedRDTSC();
+    // Wait for 100 milliseconds.
+    std::this_thread::sleep_for(std::chrono::milliseconds{100});
+    const auto end_time = RealTimeClock::Now();
+    const u64 tsc_end = FencedRDTSC();
+    // Calculate differences.
+    const u64 timer_diff = static_cast<u64>(
+        std::chrono::duration_cast<std::chrono::nanoseconds>(end_time - start_time).count());
+    const u64 tsc_diff = tsc_end - tsc_start;
+    const u64 tsc_freq = MultiplyAndDivide64(tsc_diff, 1000000000ULL, timer_diff);
+    return RoundToNearest<100'000>(tsc_freq);
+}
+
+} // namespace Common::X64
diff --git a/src/common/x64/rdtsc.h b/src/common/x64/rdtsc.h
new file mode 100644
index 000000000..0ec4f52f9
--- /dev/null
+++ b/src/common/x64/rdtsc.h
@@ -0,0 +1,37 @@
+// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#ifdef _MSC_VER
+#include <intrin.h>
+#endif
+
+#include "common/common_types.h"
+
+namespace Common::X64 {
+
+#ifdef _MSC_VER
+__forceinline static u64 FencedRDTSC() {
+    _mm_lfence();
+    _ReadWriteBarrier();
+    const u64 result = __rdtsc();
+    _mm_lfence();
+    _ReadWriteBarrier();
+    return result;
+}
+#else
+static inline u64 FencedRDTSC() {
+    u64 eax;
+    u64 edx;
+    asm volatile("lfence\n\t"
+                 "rdtsc\n\t"
+                 "lfence\n\t"
+                 : "=a"(eax), "=d"(edx));
+    return (edx << 32) | eax;
+}
+#endif
+
+u64 EstimateRDTSCFrequency();
+
+} // namespace Common::X64
diff --git a/src/core/CMakeLists.txt b/src/core/CMakeLists.txt
index 4c53aed72..dd2c053d0 100644
--- a/src/core/CMakeLists.txt
+++ b/src/core/CMakeLists.txt
@@ -14,7 +14,6 @@ add_library(core STATIC
     core.h
     core_timing.cpp
     core_timing.h
-    core_timing_util.h
     cpu_manager.cpp
     cpu_manager.h
     crypto/aes_util.cpp
diff --git a/src/core/arm/dynarmic/arm_dynarmic_32.cpp b/src/core/arm/dynarmic/arm_dynarmic_32.cpp
index 5acf9008d..3b82fb73c 100644
--- a/src/core/arm/dynarmic/arm_dynarmic_32.cpp
+++ b/src/core/arm/dynarmic/arm_dynarmic_32.cpp
@@ -322,11 +322,6 @@ std::shared_ptr<Dynarmic::A32::Jit> ARM_Dynarmic_32::MakeJit(Common::PageTable*
         }
     }
 
-#ifdef ARCHITECTURE_arm64
-    // TODO: remove when fixed in dynarmic
-    config.optimizations &= ~Dynarmic::OptimizationFlag::BlockLinking;
-#endif
-
     return std::make_unique<Dynarmic::A32::Jit>(config);
 }
 
diff --git a/src/core/core_timing.cpp b/src/core/core_timing.cpp
index 4f2692b05..4f0a3f8ea 100644
--- a/src/core/core_timing.cpp
+++ b/src/core/core_timing.cpp
@@ -16,12 +16,11 @@
 
 #include "common/microprofile.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 #include "core/hardware_properties.h"
 
 namespace Core::Timing {
 
-constexpr s64 MAX_SLICE_LENGTH = 4000;
+constexpr s64 MAX_SLICE_LENGTH = 10000;
 
 std::shared_ptr<EventType> CreateEvent(std::string name, TimedCallback&& callback) {
     return std::make_shared<EventType>(std::move(callback), std::move(name));
@@ -45,9 +44,7 @@ struct CoreTiming::Event {
     }
 };
 
-CoreTiming::CoreTiming()
-    : cpu_clock{Common::CreateBestMatchingClock(Hardware::BASE_CLOCK_RATE, Hardware::CNTFREQ)},
-      event_clock{Common::CreateStandardWallClock(Hardware::BASE_CLOCK_RATE, Hardware::CNTFREQ)} {}
+CoreTiming::CoreTiming() : clock{Common::CreateOptimalClock()} {}
 
 CoreTiming::~CoreTiming() {
     Reset();
@@ -68,7 +65,7 @@ void CoreTiming::Initialize(std::function<void()>&& on_thread_init_) {
     on_thread_init = std::move(on_thread_init_);
     event_fifo_id = 0;
     shutting_down = false;
-    ticks = 0;
+    cpu_ticks = 0;
     const auto empty_timed_callback = [](std::uintptr_t, u64, std::chrono::nanoseconds)
         -> std::optional<std::chrono::nanoseconds> { return std::nullopt; };
     ev_lost = CreateEvent("_lost_event", empty_timed_callback);
@@ -173,38 +170,30 @@ void CoreTiming::UnscheduleEvent(const std::shared_ptr<EventType>& event_type,
 }
 
 void CoreTiming::AddTicks(u64 ticks_to_add) {
-    ticks += ticks_to_add;
-    downcount -= static_cast<s64>(ticks);
+    cpu_ticks += ticks_to_add;
+    downcount -= static_cast<s64>(cpu_ticks);
 }
 
 void CoreTiming::Idle() {
-    if (!event_queue.empty()) {
-        const u64 next_event_time = event_queue.front().time;
-        const u64 next_ticks = nsToCycles(std::chrono::nanoseconds(next_event_time)) + 10U;
-        if (next_ticks > ticks) {
-            ticks = next_ticks;
-        }
-        return;
-    }
-    ticks += 1000U;
+    cpu_ticks += 1000U;
 }
 
 void CoreTiming::ResetTicks() {
     downcount = MAX_SLICE_LENGTH;
 }
 
-u64 CoreTiming::GetCPUTicks() const {
+u64 CoreTiming::GetClockTicks() const {
     if (is_multicore) [[likely]] {
-        return cpu_clock->GetCPUCycles();
+        return clock->GetCNTPCT();
     }
-    return ticks;
+    return Common::WallClock::CPUTickToCNTPCT(cpu_ticks);
 }
 
-u64 CoreTiming::GetClockTicks() const {
+u64 CoreTiming::GetGPUTicks() const {
     if (is_multicore) [[likely]] {
-        return cpu_clock->GetClockCycles();
+        return clock->GetGPUTick();
     }
-    return CpuCyclesToClockCycles(ticks);
+    return Common::WallClock::CPUTickToGPUTick(cpu_ticks);
 }
 
 std::optional<s64> CoreTiming::Advance() {
@@ -297,9 +286,7 @@ void CoreTiming::ThreadLoop() {
         }
 
         paused_set = true;
-        event_clock->Pause(true);
         pause_event.Wait();
-        event_clock->Pause(false);
     }
 }
 
@@ -315,25 +302,18 @@ void CoreTiming::Reset() {
     has_started = false;
 }
 
-std::chrono::nanoseconds CoreTiming::GetCPUTimeNs() const {
-    if (is_multicore) [[likely]] {
-        return cpu_clock->GetTimeNS();
-    }
-    return CyclesToNs(ticks);
-}
-
 std::chrono::nanoseconds CoreTiming::GetGlobalTimeNs() const {
     if (is_multicore) [[likely]] {
-        return event_clock->GetTimeNS();
+        return clock->GetTimeNS();
     }
-    return CyclesToNs(ticks);
+    return std::chrono::nanoseconds{Common::WallClock::CPUTickToNS(cpu_ticks)};
 }
 
 std::chrono::microseconds CoreTiming::GetGlobalTimeUs() const {
     if (is_multicore) [[likely]] {
-        return event_clock->GetTimeUS();
+        return clock->GetTimeUS();
     }
-    return CyclesToUs(ticks);
+    return std::chrono::microseconds{Common::WallClock::CPUTickToUS(cpu_ticks)};
 }
 
 } // namespace Core::Timing
diff --git a/src/core/core_timing.h b/src/core/core_timing.h
index e7c4a949f..10db1de55 100644
--- a/src/core/core_timing.h
+++ b/src/core/core_timing.h
@@ -116,14 +116,11 @@ public:
         return downcount;
     }
 
-    /// Returns current time in emulated CPU cycles
-    u64 GetCPUTicks() const;
-
-    /// Returns current time in emulated in Clock cycles
+    /// Returns the current CNTPCT tick value.
     u64 GetClockTicks() const;
 
-    /// Returns current time in nanoseconds.
-    std::chrono::nanoseconds GetCPUTimeNs() const;
+    /// Returns the current GPU tick value.
+    u64 GetGPUTicks() const;
 
     /// Returns current time in microseconds.
     std::chrono::microseconds GetGlobalTimeUs() const;
@@ -142,8 +139,7 @@ private:
 
     void Reset();
 
-    std::unique_ptr<Common::WallClock> cpu_clock;
-    std::unique_ptr<Common::WallClock> event_clock;
+    std::unique_ptr<Common::WallClock> clock;
 
     s64 global_timer = 0;
 
@@ -171,7 +167,7 @@ private:
     s64 pause_end_time{};
 
     /// Cycle timing
-    u64 ticks{};
+    u64 cpu_ticks{};
     s64 downcount{};
 };
 
diff --git a/src/core/core_timing_util.h b/src/core/core_timing_util.h
deleted file mode 100644
index fe5aaefc7..000000000
--- a/src/core/core_timing_util.h
+++ /dev/null
@@ -1,58 +0,0 @@
-// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-#pragma once
-
-#include <chrono>
-
-#include "common/common_types.h"
-#include "core/hardware_properties.h"
-
-namespace Core::Timing {
-
-namespace detail {
-constexpr u64 CNTFREQ_ADJUSTED = Hardware::CNTFREQ / 1000;
-constexpr u64 BASE_CLOCK_RATE_ADJUSTED = Hardware::BASE_CLOCK_RATE / 1000;
-} // namespace detail
-
-[[nodiscard]] constexpr s64 msToCycles(std::chrono::milliseconds ms) {
-    return ms.count() * detail::BASE_CLOCK_RATE_ADJUSTED;
-}
-
-[[nodiscard]] constexpr s64 usToCycles(std::chrono::microseconds us) {
-    return us.count() * detail::BASE_CLOCK_RATE_ADJUSTED / 1000;
-}
-
-[[nodiscard]] constexpr s64 nsToCycles(std::chrono::nanoseconds ns) {
-    return ns.count() * detail::BASE_CLOCK_RATE_ADJUSTED / 1000000;
-}
-
-[[nodiscard]] constexpr u64 msToClockCycles(std::chrono::milliseconds ms) {
-    return static_cast<u64>(ms.count()) * detail::CNTFREQ_ADJUSTED;
-}
-
-[[nodiscard]] constexpr u64 usToClockCycles(std::chrono::microseconds us) {
-    return us.count() * detail::CNTFREQ_ADJUSTED / 1000;
-}
-
-[[nodiscard]] constexpr u64 nsToClockCycles(std::chrono::nanoseconds ns) {
-    return ns.count() * detail::CNTFREQ_ADJUSTED / 1000000;
-}
-
-[[nodiscard]] constexpr u64 CpuCyclesToClockCycles(u64 ticks) {
-    return ticks * detail::CNTFREQ_ADJUSTED / detail::BASE_CLOCK_RATE_ADJUSTED;
-}
-
-[[nodiscard]] constexpr std::chrono::milliseconds CyclesToMs(s64 cycles) {
-    return std::chrono::milliseconds(cycles / detail::BASE_CLOCK_RATE_ADJUSTED);
-}
-
-[[nodiscard]] constexpr std::chrono::nanoseconds CyclesToNs(s64 cycles) {
-    return std::chrono::nanoseconds(cycles * 1000000 / detail::BASE_CLOCK_RATE_ADJUSTED);
-}
-
-[[nodiscard]] constexpr std::chrono::microseconds CyclesToUs(s64 cycles) {
-    return std::chrono::microseconds(cycles * 1000 / detail::BASE_CLOCK_RATE_ADJUSTED);
-}
-
-} // namespace Core::Timing
diff --git a/src/core/file_sys/patch_manager.cpp b/src/core/file_sys/patch_manager.cpp
index 4e61d4335..d3286b352 100644
--- a/src/core/file_sys/patch_manager.cpp
+++ b/src/core/file_sys/patch_manager.cpp
@@ -153,7 +153,7 @@ VirtualDir PatchManager::PatchExeFS(VirtualDir exefs) const {
     const auto sdmc_load_dir = fs_controller.GetSDMCModificationLoadRoot(title_id);
 
     std::vector<VirtualDir> patch_dirs = {sdmc_load_dir};
-    if (load_dir != nullptr && load_dir->GetSize() > 0) {
+    if (load_dir != nullptr) {
         const auto load_patch_dirs = load_dir->GetSubdirectories();
         patch_dirs.insert(patch_dirs.end(), load_patch_dirs.begin(), load_patch_dirs.end());
     }
@@ -354,8 +354,7 @@ static void ApplyLayeredFS(VirtualFile& romfs, u64 title_id, ContentRecordType t
     const auto load_dir = fs_controller.GetModificationLoadRoot(title_id);
     const auto sdmc_load_dir = fs_controller.GetSDMCModificationLoadRoot(title_id);
     if ((type != ContentRecordType::Program && type != ContentRecordType::Data) ||
-        ((load_dir == nullptr || load_dir->GetSize() <= 0) &&
-         (sdmc_load_dir == nullptr || sdmc_load_dir->GetSize() <= 0))) {
+        (load_dir == nullptr && sdmc_load_dir == nullptr)) {
         return;
     }
 
@@ -496,7 +495,7 @@ PatchManager::PatchVersionNames PatchManager::GetPatchVersionNames(VirtualFile u
 
     // General Mods (LayeredFS and IPS)
     const auto mod_dir = fs_controller.GetModificationLoadRoot(title_id);
-    if (mod_dir != nullptr && mod_dir->GetSize() > 0) {
+    if (mod_dir != nullptr) {
         for (const auto& mod : mod_dir->GetSubdirectories()) {
             std::string types;
 
@@ -540,7 +539,7 @@ PatchManager::PatchVersionNames PatchManager::GetPatchVersionNames(VirtualFile u
 
     // SDMC mod directory (RomFS LayeredFS)
     const auto sdmc_mod_dir = fs_controller.GetSDMCModificationLoadRoot(title_id);
-    if (sdmc_mod_dir != nullptr && sdmc_mod_dir->GetSize() > 0) {
+    if (sdmc_mod_dir != nullptr) {
         std::string types;
         if (IsDirValidAndNonEmpty(FindSubdirectoryCaseless(sdmc_mod_dir, "exefs"))) {
             AppendCommaIfNotEmpty(types, "LayeredExeFS");
diff --git a/src/core/file_sys/vfs_concat.cpp b/src/core/file_sys/vfs_concat.cpp
index 853b893a1..311a59e5f 100644
--- a/src/core/file_sys/vfs_concat.cpp
+++ b/src/core/file_sys/vfs_concat.cpp
@@ -150,23 +150,29 @@ std::size_t ConcatenatedVfsFile::Read(u8* data, std::size_t length, std::size_t
     while (cur_length > 0 && it != concatenation_map.end()) {
         // Check if we can read the file at this position.
         const auto& file = it->file;
-        const u64 file_offset = it->offset;
+        const u64 map_offset = it->offset;
         const u64 file_size = file->GetSize();
 
-        if (cur_offset >= file_offset + file_size) {
+        if (cur_offset > map_offset + file_size) {
             // Entirely out of bounds read.
             break;
         }
 
         // Read the file at this position.
-        const u64 intended_read_size = std::min<u64>(cur_length, file_size);
+        const u64 file_seek = cur_offset - map_offset;
+        const u64 intended_read_size = std::min<u64>(cur_length, file_size - file_seek);
         const u64 actual_read_size =
-            file->Read(data + (cur_offset - offset), intended_read_size, cur_offset - file_offset);
+            file->Read(data + (cur_offset - offset), intended_read_size, file_seek);
 
         // Update tracking.
         cur_offset += actual_read_size;
         cur_length -= actual_read_size;
         it++;
+
+        // If we encountered a short read, we're done.
+        if (actual_read_size < intended_read_size) {
+            break;
+        }
     }
 
     return cur_offset - offset;
diff --git a/src/core/file_sys/vfs_real.cpp b/src/core/file_sys/vfs_real.cpp
index 7a15d8438..b0515ec05 100644
--- a/src/core/file_sys/vfs_real.cpp
+++ b/src/core/file_sys/vfs_real.cpp
@@ -10,6 +10,7 @@
 #include "common/fs/fs.h"
 #include "common/fs/path_util.h"
 #include "common/logging/log.h"
+#include "core/file_sys/vfs.h"
 #include "core/file_sys/vfs_real.h"
 
 // For FileTimeStampRaw
@@ -72,8 +73,10 @@ VfsEntryType RealVfsFilesystem::GetEntryType(std::string_view path_) const {
     return VfsEntryType::File;
 }
 
-VirtualFile RealVfsFilesystem::OpenFile(std::string_view path_, Mode perms) {
+VirtualFile RealVfsFilesystem::OpenFileFromEntry(std::string_view path_, std::optional<u64> size,
+                                                 Mode perms) {
     const auto path = FS::SanitizePath(path_, FS::DirectorySeparator::PlatformDefault);
+    std::scoped_lock lk{list_lock};
 
     if (auto it = cache.find(path); it != cache.end()) {
         if (auto file = it->second.lock(); file) {
@@ -81,23 +84,30 @@ VirtualFile RealVfsFilesystem::OpenFile(std::string_view path_, Mode perms) {
         }
     }
 
-    if (!FS::Exists(path) || !FS::IsFile(path)) {
+    if (!size && !FS::IsFile(path)) {
         return nullptr;
     }
 
     auto reference = std::make_unique<FileReference>();
-    this->InsertReferenceIntoList(*reference);
+    this->InsertReferenceIntoListLocked(*reference);
 
-    auto file =
-        std::shared_ptr<RealVfsFile>(new RealVfsFile(*this, std::move(reference), path, perms));
+    auto file = std::shared_ptr<RealVfsFile>(
+        new RealVfsFile(*this, std::move(reference), path, perms, size));
     cache[path] = file;
 
     return file;
 }
 
+VirtualFile RealVfsFilesystem::OpenFile(std::string_view path_, Mode perms) {
+    return OpenFileFromEntry(path_, {}, perms);
+}
+
 VirtualFile RealVfsFilesystem::CreateFile(std::string_view path_, Mode perms) {
     const auto path = FS::SanitizePath(path_, FS::DirectorySeparator::PlatformDefault);
-    cache.erase(path);
+    {
+        std::scoped_lock lk{list_lock};
+        cache.erase(path);
+    }
 
     // Current usages of CreateFile expect to delete the contents of an existing file.
     if (FS::IsFile(path)) {
@@ -127,8 +137,11 @@ VirtualFile RealVfsFilesystem::CopyFile(std::string_view old_path_, std::string_
 VirtualFile RealVfsFilesystem::MoveFile(std::string_view old_path_, std::string_view new_path_) {
     const auto old_path = FS::SanitizePath(old_path_, FS::DirectorySeparator::PlatformDefault);
     const auto new_path = FS::SanitizePath(new_path_, FS::DirectorySeparator::PlatformDefault);
-    cache.erase(old_path);
-    cache.erase(new_path);
+    {
+        std::scoped_lock lk{list_lock};
+        cache.erase(old_path);
+        cache.erase(new_path);
+    }
     if (!FS::RenameFile(old_path, new_path)) {
         return nullptr;
     }
@@ -137,7 +150,10 @@ VirtualFile RealVfsFilesystem::MoveFile(std::string_view old_path_, std::string_
 
 bool RealVfsFilesystem::DeleteFile(std::string_view path_) {
     const auto path = FS::SanitizePath(path_, FS::DirectorySeparator::PlatformDefault);
-    cache.erase(path);
+    {
+        std::scoped_lock lk{list_lock};
+        cache.erase(path);
+    }
     return FS::RemoveFile(path);
 }
 
@@ -176,14 +192,17 @@ bool RealVfsFilesystem::DeleteDirectory(std::string_view path_) {
     return FS::RemoveDirRecursively(path);
 }
 
-void RealVfsFilesystem::RefreshReference(const std::string& path, Mode perms,
-                                         FileReference& reference) {
+std::unique_lock<std::mutex> RealVfsFilesystem::RefreshReference(const std::string& path,
+                                                                 Mode perms,
+                                                                 FileReference& reference) {
+    std::unique_lock lk{list_lock};
+
     // Temporarily remove from list.
-    this->RemoveReferenceFromList(reference);
+    this->RemoveReferenceFromListLocked(reference);
 
     // Restore file if needed.
     if (!reference.file) {
-        this->EvictSingleReference();
+        this->EvictSingleReferenceLocked();
 
         reference.file =
             FS::FileOpen(path, ModeFlagsToFileAccessMode(perms), FS::FileType::BinaryFile);
@@ -193,12 +212,16 @@ void RealVfsFilesystem::RefreshReference(const std::string& path, Mode perms,
     }
 
     // Reinsert into list.
-    this->InsertReferenceIntoList(reference);
+    this->InsertReferenceIntoListLocked(reference);
+
+    return lk;
 }
 
 void RealVfsFilesystem::DropReference(std::unique_ptr<FileReference>&& reference) {
+    std::scoped_lock lk{list_lock};
+
     // Remove from list.
-    this->RemoveReferenceFromList(*reference);
+    this->RemoveReferenceFromListLocked(*reference);
 
     // Close the file.
     if (reference->file) {
@@ -207,14 +230,14 @@ void RealVfsFilesystem::DropReference(std::unique_ptr<FileReference>&& reference
     }
 }
 
-void RealVfsFilesystem::EvictSingleReference() {
+void RealVfsFilesystem::EvictSingleReferenceLocked() {
     if (num_open_files < MaxOpenFiles || open_references.empty()) {
         return;
     }
 
     // Get and remove from list.
     auto& reference = open_references.back();
-    this->RemoveReferenceFromList(reference);
+    this->RemoveReferenceFromListLocked(reference);
 
     // Close the file.
     if (reference.file) {
@@ -223,10 +246,10 @@ void RealVfsFilesystem::EvictSingleReference() {
     }
 
     // Reinsert into closed list.
-    this->InsertReferenceIntoList(reference);
+    this->InsertReferenceIntoListLocked(reference);
 }
 
-void RealVfsFilesystem::InsertReferenceIntoList(FileReference& reference) {
+void RealVfsFilesystem::InsertReferenceIntoListLocked(FileReference& reference) {
     if (reference.file) {
         open_references.push_front(reference);
     } else {
@@ -234,7 +257,7 @@ void RealVfsFilesystem::InsertReferenceIntoList(FileReference& reference) {
     }
 }
 
-void RealVfsFilesystem::RemoveReferenceFromList(FileReference& reference) {
+void RealVfsFilesystem::RemoveReferenceFromListLocked(FileReference& reference) {
     if (reference.file) {
         open_references.erase(open_references.iterator_to(reference));
     } else {
@@ -243,10 +266,10 @@ void RealVfsFilesystem::RemoveReferenceFromList(FileReference& reference) {
 }
 
 RealVfsFile::RealVfsFile(RealVfsFilesystem& base_, std::unique_ptr<FileReference> reference_,
-                         const std::string& path_, Mode perms_)
+                         const std::string& path_, Mode perms_, std::optional<u64> size_)
     : base(base_), reference(std::move(reference_)), path(path_),
       parent_path(FS::GetParentPath(path_)), path_components(FS::SplitPathComponents(path_)),
-      perms(perms_) {}
+      size(size_), perms(perms_) {}
 
 RealVfsFile::~RealVfsFile() {
     base.DropReference(std::move(reference));
@@ -257,12 +280,15 @@ std::string RealVfsFile::GetName() const {
 }
 
 std::size_t RealVfsFile::GetSize() const {
-    base.RefreshReference(path, perms, *reference);
-    return reference->file ? reference->file->GetSize() : 0;
+    if (size) {
+        return *size;
+    }
+    return FS::GetSize(path);
 }
 
 bool RealVfsFile::Resize(std::size_t new_size) {
-    base.RefreshReference(path, perms, *reference);
+    size.reset();
+    auto lk = base.RefreshReference(path, perms, *reference);
     return reference->file ? reference->file->SetSize(new_size) : false;
 }
 
@@ -279,7 +305,7 @@ bool RealVfsFile::IsReadable() const {
 }
 
 std::size_t RealVfsFile::Read(u8* data, std::size_t length, std::size_t offset) const {
-    base.RefreshReference(path, perms, *reference);
+    auto lk = base.RefreshReference(path, perms, *reference);
     if (!reference->file || !reference->file->Seek(static_cast<s64>(offset))) {
         return 0;
     }
@@ -287,7 +313,8 @@ std::size_t RealVfsFile::Read(u8* data, std::size_t length, std::size_t offset)
 }
 
 std::size_t RealVfsFile::Write(const u8* data, std::size_t length, std::size_t offset) {
-    base.RefreshReference(path, perms, *reference);
+    size.reset();
+    auto lk = base.RefreshReference(path, perms, *reference);
     if (!reference->file || !reference->file->Seek(static_cast<s64>(offset))) {
         return 0;
     }
@@ -309,10 +336,11 @@ std::vector<VirtualFile> RealVfsDirectory::IterateEntries<RealVfsFile, VfsFile>(
 
     std::vector<VirtualFile> out;
 
-    const FS::DirEntryCallable callback = [this, &out](const std::filesystem::path& full_path) {
-        const auto full_path_string = FS::PathToUTF8String(full_path);
+    const FS::DirEntryCallable callback = [this,
+                                           &out](const std::filesystem::directory_entry& entry) {
+        const auto full_path_string = FS::PathToUTF8String(entry.path());
 
-        out.emplace_back(base.OpenFile(full_path_string, perms));
+        out.emplace_back(base.OpenFileFromEntry(full_path_string, entry.file_size(), perms));
 
         return true;
     };
@@ -330,8 +358,9 @@ std::vector<VirtualDir> RealVfsDirectory::IterateEntries<RealVfsDirectory, VfsDi
 
     std::vector<VirtualDir> out;
 
-    const FS::DirEntryCallable callback = [this, &out](const std::filesystem::path& full_path) {
-        const auto full_path_string = FS::PathToUTF8String(full_path);
+    const FS::DirEntryCallable callback = [this,
+                                           &out](const std::filesystem::directory_entry& entry) {
+        const auto full_path_string = FS::PathToUTF8String(entry.path());
 
         out.emplace_back(base.OpenDirectory(full_path_string, perms));
 
@@ -483,12 +512,10 @@ std::map<std::string, VfsEntryType, std::less<>> RealVfsDirectory::GetEntries()
 
     std::map<std::string, VfsEntryType, std::less<>> out;
 
-    const FS::DirEntryCallable callback = [&out](const std::filesystem::path& full_path) {
-        const auto filename = FS::PathToUTF8String(full_path.filename());
-
+    const FS::DirEntryCallable callback = [&out](const std::filesystem::directory_entry& entry) {
+        const auto filename = FS::PathToUTF8String(entry.path().filename());
         out.insert_or_assign(filename,
-                             FS::IsDir(full_path) ? VfsEntryType::Directory : VfsEntryType::File);
-
+                             entry.is_directory() ? VfsEntryType::Directory : VfsEntryType::File);
         return true;
     };
 
diff --git a/src/core/file_sys/vfs_real.h b/src/core/file_sys/vfs_real.h
index d8c900e33..26ea7df62 100644
--- a/src/core/file_sys/vfs_real.h
+++ b/src/core/file_sys/vfs_real.h
@@ -4,6 +4,8 @@
 #pragma once
 
 #include <map>
+#include <mutex>
+#include <optional>
 #include <string_view>
 #include "common/intrusive_list.h"
 #include "core/file_sys/mode.h"
@@ -20,6 +22,8 @@ struct FileReference : public Common::IntrusiveListBaseNode<FileReference> {
 };
 
 class RealVfsFile;
+class RealVfsDirectory;
+
 class RealVfsFilesystem : public VfsFilesystem {
 public:
     RealVfsFilesystem();
@@ -45,17 +49,24 @@ private:
     std::map<std::string, std::weak_ptr<VfsFile>, std::less<>> cache;
     ReferenceListType open_references;
     ReferenceListType closed_references;
+    std::mutex list_lock;
     size_t num_open_files{};
 
 private:
     friend class RealVfsFile;
-    void RefreshReference(const std::string& path, Mode perms, FileReference& reference);
+    std::unique_lock<std::mutex> RefreshReference(const std::string& path, Mode perms,
+                                                  FileReference& reference);
     void DropReference(std::unique_ptr<FileReference>&& reference);
-    void EvictSingleReference();
 
 private:
-    void InsertReferenceIntoList(FileReference& reference);
-    void RemoveReferenceFromList(FileReference& reference);
+    friend class RealVfsDirectory;
+    VirtualFile OpenFileFromEntry(std::string_view path, std::optional<u64> size,
+                                  Mode perms = Mode::Read);
+
+private:
+    void EvictSingleReferenceLocked();
+    void InsertReferenceIntoListLocked(FileReference& reference);
+    void RemoveReferenceFromListLocked(FileReference& reference);
 };
 
 // An implementation of VfsFile that represents a file on the user's computer.
@@ -78,13 +89,14 @@ public:
 
 private:
     RealVfsFile(RealVfsFilesystem& base, std::unique_ptr<FileReference> reference,
-                const std::string& path, Mode perms = Mode::Read);
+                const std::string& path, Mode perms = Mode::Read, std::optional<u64> size = {});
 
     RealVfsFilesystem& base;
     std::unique_ptr<FileReference> reference;
     std::string path;
     std::string parent_path;
     std::vector<std::string> path_components;
+    std::optional<u64> size;
     Mode perms;
 };
 
diff --git a/src/core/hid/emulated_controller.cpp b/src/core/hid/emulated_controller.cpp
index 0a7777732..1ebc32c1e 100644
--- a/src/core/hid/emulated_controller.cpp
+++ b/src/core/hid/emulated_controller.cpp
@@ -149,12 +149,16 @@ void EmulatedController::LoadDevices() {
 
     camera_params[0] = right_joycon;
     camera_params[0].Set("camera", true);
-    camera_params[1] = Common::ParamPackage{"engine:camera,camera:1"};
-    ring_params[1] = Common::ParamPackage{"engine:joycon,axis_x:100,axis_y:101"};
-    nfc_params[0] = Common::ParamPackage{"engine:virtual_amiibo,nfc:1"};
     nfc_params[1] = right_joycon;
     nfc_params[1].Set("nfc", true);
 
+    // Only map virtual devices to the first controller
+    if (npad_id_type == NpadIdType::Player1 || npad_id_type == NpadIdType::Handheld) {
+        camera_params[1] = Common::ParamPackage{"engine:camera,camera:1"};
+        ring_params[1] = Common::ParamPackage{"engine:joycon,axis_x:100,axis_y:101"};
+        nfc_params[0] = Common::ParamPackage{"engine:virtual_amiibo,nfc:1"};
+    }
+
     output_params[LeftIndex] = left_joycon;
     output_params[RightIndex] = right_joycon;
     output_params[2] = camera_params[1];
@@ -1176,10 +1180,7 @@ void EmulatedController::SetNfc(const Common::Input::CallbackStatus& callback) {
         return;
     }
 
-    controller.nfc_state = {
-        controller.nfc_values.state,
-        controller.nfc_values.data,
-    };
+    controller.nfc_state = controller.nfc_values;
 }
 
 bool EmulatedController::SetVibration(std::size_t device_index, VibrationValue vibration) {
@@ -1249,6 +1250,11 @@ Common::Input::DriverResult EmulatedController::SetPollingMode(
         const auto virtual_nfc_result = nfc_output_device->SetPollingMode(polling_mode);
         const auto mapped_nfc_result = right_output_device->SetPollingMode(polling_mode);
 
+        // Restore previous state
+        if (mapped_nfc_result != Common::Input::DriverResult::Success) {
+            right_output_device->SetPollingMode(Common::Input::PollingMode::Active);
+        }
+
         if (virtual_nfc_result == Common::Input::DriverResult::Success) {
             return virtual_nfc_result;
         }
@@ -1308,6 +1314,79 @@ bool EmulatedController::HasNfc() const {
     return is_connected && (has_virtual_nfc && is_virtual_nfc_supported);
 }
 
+bool EmulatedController::AddNfcHandle() {
+    nfc_handles++;
+    return SetPollingMode(EmulatedDeviceIndex::RightIndex, Common::Input::PollingMode::NFC) ==
+           Common::Input::DriverResult::Success;
+}
+
+bool EmulatedController::RemoveNfcHandle() {
+    nfc_handles--;
+    if (nfc_handles <= 0) {
+        return SetPollingMode(EmulatedDeviceIndex::RightIndex,
+                              Common::Input::PollingMode::Active) ==
+               Common::Input::DriverResult::Success;
+    }
+    return true;
+}
+
+bool EmulatedController::StartNfcPolling() {
+    auto& nfc_output_device = output_devices[static_cast<std::size_t>(DeviceIndex::Right)];
+    auto& nfc_virtual_output_device = output_devices[3];
+
+    const auto device_result = nfc_output_device->StartNfcPolling();
+    const auto virtual_device_result = nfc_virtual_output_device->StartNfcPolling();
+
+    return device_result == Common::Input::NfcState::Success ||
+           virtual_device_result == Common::Input::NfcState::Success;
+}
+
+bool EmulatedController::StopNfcPolling() {
+    auto& nfc_output_device = output_devices[static_cast<std::size_t>(DeviceIndex::Right)];
+    auto& nfc_virtual_output_device = output_devices[3];
+
+    const auto device_result = nfc_output_device->StopNfcPolling();
+    const auto virtual_device_result = nfc_virtual_output_device->StopNfcPolling();
+
+    return device_result == Common::Input::NfcState::Success ||
+           virtual_device_result == Common::Input::NfcState::Success;
+}
+
+bool EmulatedController::ReadAmiiboData(std::vector<u8>& data) {
+    auto& nfc_output_device = output_devices[static_cast<std::size_t>(DeviceIndex::Right)];
+    auto& nfc_virtual_output_device = output_devices[3];
+
+    if (nfc_output_device->ReadAmiiboData(data) == Common::Input::NfcState::Success) {
+        return true;
+    }
+
+    return nfc_virtual_output_device->ReadAmiiboData(data) == Common::Input::NfcState::Success;
+}
+
+bool EmulatedController::ReadMifareData(const Common::Input::MifareRequest& request,
+                                        Common::Input::MifareRequest& out_data) {
+    auto& nfc_output_device = output_devices[static_cast<std::size_t>(DeviceIndex::Right)];
+    auto& nfc_virtual_output_device = output_devices[3];
+
+    if (nfc_output_device->ReadMifareData(request, out_data) == Common::Input::NfcState::Success) {
+        return true;
+    }
+
+    return nfc_virtual_output_device->ReadMifareData(request, out_data) ==
+           Common::Input::NfcState::Success;
+}
+
+bool EmulatedController::WriteMifareData(const Common::Input::MifareRequest& request) {
+    auto& nfc_output_device = output_devices[static_cast<std::size_t>(DeviceIndex::Right)];
+    auto& nfc_virtual_output_device = output_devices[3];
+
+    if (nfc_output_device->WriteMifareData(request) == Common::Input::NfcState::Success) {
+        return true;
+    }
+
+    return nfc_virtual_output_device->WriteMifareData(request) == Common::Input::NfcState::Success;
+}
+
 bool EmulatedController::WriteNfc(const std::vector<u8>& data) {
     auto& nfc_output_device = output_devices[static_cast<std::size_t>(DeviceIndex::Right)];
     auto& nfc_virtual_output_device = output_devices[3];
diff --git a/src/core/hid/emulated_controller.h b/src/core/hid/emulated_controller.h
index 09fe1a0ab..d511e5fac 100644
--- a/src/core/hid/emulated_controller.h
+++ b/src/core/hid/emulated_controller.h
@@ -97,10 +97,7 @@ struct RingSensorForce {
     f32 force;
 };
 
-struct NfcState {
-    Common::Input::NfcState state{};
-    std::vector<u8> data{};
-};
+using NfcState = Common::Input::NfcStatus;
 
 struct ControllerMotion {
     Common::Vec3f accel{};
@@ -393,9 +390,31 @@ public:
     /// Returns true if the device has nfc support
     bool HasNfc() const;
 
+    /// Sets the joycon in nfc mode and increments the handle count
+    bool AddNfcHandle();
+
+    /// Decrements the handle count if zero sets the joycon in active mode
+    bool RemoveNfcHandle();
+
+    /// Start searching for nfc tags
+    bool StartNfcPolling();
+
+    /// Stop searching for nfc tags
+    bool StopNfcPolling();
+
+    /// Returns true if the nfc tag was readable
+    bool ReadAmiiboData(std::vector<u8>& data);
+
     /// Returns true if the nfc tag was written
     bool WriteNfc(const std::vector<u8>& data);
 
+    /// Returns true if the nfc tag was readable
+    bool ReadMifareData(const Common::Input::MifareRequest& request,
+                        Common::Input::MifareRequest& out_data);
+
+    /// Returns true if the nfc tag was written
+    bool WriteMifareData(const Common::Input::MifareRequest& request);
+
     /// Returns the led pattern corresponding to this emulated controller
     LedPattern GetLedPattern() const;
 
@@ -532,6 +551,7 @@ private:
     bool system_buttons_enabled{true};
     f32 motion_sensitivity{Core::HID::MotionInput::IsAtRestStandard};
     u32 turbo_button_state{0};
+    std::size_t nfc_handles{0};
 
     // Temporary values to avoid doing changes while the controller is in configuring mode
     NpadStyleIndex tmp_npad_type{NpadStyleIndex::None};
diff --git a/src/core/hid/input_converter.cpp b/src/core/hid/input_converter.cpp
index 4ccb1c596..a05716fd8 100644
--- a/src/core/hid/input_converter.cpp
+++ b/src/core/hid/input_converter.cpp
@@ -299,11 +299,7 @@ Common::Input::NfcStatus TransformToNfc(const Common::Input::CallbackStatus& cal
     Common::Input::NfcStatus nfc{};
     switch (callback.type) {
     case Common::Input::InputType::Nfc:
-        nfc = {
-            .state = callback.nfc_status,
-            .data = callback.raw_data,
-        };
-        break;
+        return callback.nfc_status;
     default:
         LOG_ERROR(Input, "Conversion from type {} to NFC not implemented", callback.type);
         break;
diff --git a/src/core/hle/kernel/k_scheduler.cpp b/src/core/hle/kernel/k_scheduler.cpp
index faa12b4f0..75ce5a23c 100644
--- a/src/core/hle/kernel/k_scheduler.cpp
+++ b/src/core/hle/kernel/k_scheduler.cpp
@@ -184,7 +184,8 @@ u64 KScheduler::UpdateHighestPriorityThread(KThread* highest_thread) {
         prev_highest_thread != highest_thread) [[likely]] {
         if (prev_highest_thread != nullptr) [[likely]] {
             IncrementScheduledCount(prev_highest_thread);
-            prev_highest_thread->SetLastScheduledTick(m_kernel.System().CoreTiming().GetCPUTicks());
+            prev_highest_thread->SetLastScheduledTick(
+                m_kernel.System().CoreTiming().GetClockTicks());
         }
         if (m_state.should_count_idle) {
             if (highest_thread != nullptr) [[likely]] {
@@ -351,7 +352,7 @@ void KScheduler::SwitchThread(KThread* next_thread) {
 
     // Update the CPU time tracking variables.
     const s64 prev_tick = m_last_context_switch_time;
-    const s64 cur_tick = m_kernel.System().CoreTiming().GetCPUTicks();
+    const s64 cur_tick = m_kernel.System().CoreTiming().GetClockTicks();
     const s64 tick_diff = cur_tick - prev_tick;
     cur_thread->AddCpuTime(m_core_id, tick_diff);
     if (cur_process != nullptr) {
diff --git a/src/core/hle/kernel/k_synchronization_object.cpp b/src/core/hle/kernel/k_synchronization_object.cpp
index b7da3eee7..3e5b735b1 100644
--- a/src/core/hle/kernel/k_synchronization_object.cpp
+++ b/src/core/hle/kernel/k_synchronization_object.cpp
@@ -3,6 +3,7 @@
 
 #include "common/assert.h"
 #include "common/common_types.h"
+#include "common/scratch_buffer.h"
 #include "core/hle/kernel/k_scheduler.h"
 #include "core/hle/kernel/k_scoped_scheduler_lock_and_sleep.h"
 #include "core/hle/kernel/k_synchronization_object.h"
@@ -75,7 +76,7 @@ Result KSynchronizationObject::Wait(KernelCore& kernel, s32* out_index,
                                     KSynchronizationObject** objects, const s32 num_objects,
                                     s64 timeout) {
     // Allocate space on stack for thread nodes.
-    std::vector<ThreadListNode> thread_nodes(num_objects);
+    std::array<ThreadListNode, Svc::ArgumentHandleCountMax> thread_nodes;
 
     // Prepare for wait.
     KThread* thread = GetCurrentThreadPointer(kernel);
diff --git a/src/core/hle/kernel/k_thread.cpp b/src/core/hle/kernel/k_thread.cpp
index 908811e2c..adb6ec581 100644
--- a/src/core/hle/kernel/k_thread.cpp
+++ b/src/core/hle/kernel/k_thread.cpp
@@ -909,7 +909,7 @@ Result KThread::SetActivity(Svc::ThreadActivity activity) {
     R_SUCCEED();
 }
 
-Result KThread::GetThreadContext3(std::vector<u8>& out) {
+Result KThread::GetThreadContext3(Common::ScratchBuffer<u8>& out) {
     // Lock ourselves.
     KScopedLightLock lk{m_activity_pause_lock};
 
@@ -927,15 +927,13 @@ Result KThread::GetThreadContext3(std::vector<u8>& out) {
                 // Mask away mode bits, interrupt bits, IL bit, and other reserved bits.
                 auto context = GetContext64();
                 context.pstate &= 0xFF0FFE20;
-
-                out.resize(sizeof(context));
+                out.resize_destructive(sizeof(context));
                 std::memcpy(out.data(), std::addressof(context), sizeof(context));
             } else {
                 // Mask away mode bits, interrupt bits, IL bit, and other reserved bits.
                 auto context = GetContext32();
                 context.cpsr &= 0xFF0FFE20;
-
-                out.resize(sizeof(context));
+                out.resize_destructive(sizeof(context));
                 std::memcpy(out.data(), std::addressof(context), sizeof(context));
             }
         }
diff --git a/src/core/hle/kernel/k_thread.h b/src/core/hle/kernel/k_thread.h
index 37fe5db77..dd662b3f8 100644
--- a/src/core/hle/kernel/k_thread.h
+++ b/src/core/hle/kernel/k_thread.h
@@ -15,6 +15,7 @@
 #include "common/intrusive_list.h"
 
 #include "common/intrusive_red_black_tree.h"
+#include "common/scratch_buffer.h"
 #include "common/spin_lock.h"
 #include "core/arm/arm_interface.h"
 #include "core/hle/kernel/k_affinity_mask.h"
@@ -567,7 +568,7 @@ public:
 
     void RemoveWaiter(KThread* thread);
 
-    Result GetThreadContext3(std::vector<u8>& out);
+    Result GetThreadContext3(Common::ScratchBuffer<u8>& out);
 
     KThread* RemoveUserWaiterByKey(bool* out_has_waiters, KProcessAddress key) {
         return this->RemoveWaiterByKey(out_has_waiters, key, false);
diff --git a/src/core/hle/kernel/svc/svc_info.cpp b/src/core/hle/kernel/svc/svc_info.cpp
index 2b2c878b5..445cdd87b 100644
--- a/src/core/hle/kernel/svc/svc_info.cpp
+++ b/src/core/hle/kernel/svc/svc_info.cpp
@@ -199,9 +199,9 @@ Result GetInfo(Core::System& system, u64* result, InfoType info_id_type, Handle
         if (same_thread && info_sub_id == 0xFFFFFFFFFFFFFFFF) {
             const u64 thread_ticks = current_thread->GetCpuTime();
 
-            out_ticks = thread_ticks + (core_timing.GetCPUTicks() - prev_ctx_ticks);
+            out_ticks = thread_ticks + (core_timing.GetClockTicks() - prev_ctx_ticks);
         } else if (same_thread && info_sub_id == system.Kernel().CurrentPhysicalCoreIndex()) {
-            out_ticks = core_timing.GetCPUTicks() - prev_ctx_ticks;
+            out_ticks = core_timing.GetClockTicks() - prev_ctx_ticks;
         }
 
         *result = out_ticks;
diff --git a/src/core/hle/kernel/svc/svc_ipc.cpp b/src/core/hle/kernel/svc/svc_ipc.cpp
index ea03068aa..60247df2e 100644
--- a/src/core/hle/kernel/svc/svc_ipc.cpp
+++ b/src/core/hle/kernel/svc/svc_ipc.cpp
@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include "common/scope_exit.h"
+#include "common/scratch_buffer.h"
 #include "core/core.h"
 #include "core/hle/kernel/k_client_session.h"
 #include "core/hle/kernel/k_process.h"
@@ -45,11 +46,11 @@ Result ReplyAndReceive(Core::System& system, s32* out_index, uint64_t handles_ad
                  handles_addr, static_cast<u64>(sizeof(Handle) * num_handles)),
              ResultInvalidPointer);
 
-    std::vector<Handle> handles(num_handles);
+    std::array<Handle, Svc::ArgumentHandleCountMax> handles;
     GetCurrentMemory(kernel).ReadBlock(handles_addr, handles.data(), sizeof(Handle) * num_handles);
 
     // Convert handle list to object table.
-    std::vector<KSynchronizationObject*> objs(num_handles);
+    std::array<KSynchronizationObject*, Svc::ArgumentHandleCountMax> objs;
     R_UNLESS(handle_table.GetMultipleObjects<KSynchronizationObject>(objs.data(), handles.data(),
                                                                      num_handles),
              ResultInvalidHandle);
@@ -80,7 +81,7 @@ Result ReplyAndReceive(Core::System& system, s32* out_index, uint64_t handles_ad
         // Wait for an object.
         s32 index;
         Result result = KSynchronizationObject::Wait(kernel, std::addressof(index), objs.data(),
-                                                     static_cast<s32>(objs.size()), timeout_ns);
+                                                     num_handles, timeout_ns);
         if (result == ResultTimedOut) {
             R_RETURN(result);
         }
diff --git a/src/core/hle/kernel/svc/svc_synchronization.cpp b/src/core/hle/kernel/svc/svc_synchronization.cpp
index 04d65f0bd..53df5bcd8 100644
--- a/src/core/hle/kernel/svc/svc_synchronization.cpp
+++ b/src/core/hle/kernel/svc/svc_synchronization.cpp
@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include "common/scope_exit.h"
+#include "common/scratch_buffer.h"
 #include "core/core.h"
 #include "core/hle/kernel/k_process.h"
 #include "core/hle/kernel/k_readable_event.h"
@@ -54,7 +55,7 @@ static Result WaitSynchronization(Core::System& system, int32_t* out_index, cons
     // Get the synchronization context.
     auto& kernel = system.Kernel();
     auto& handle_table = GetCurrentProcess(kernel).GetHandleTable();
-    std::vector<KSynchronizationObject*> objs(num_handles);
+    std::array<KSynchronizationObject*, Svc::ArgumentHandleCountMax> objs;
 
     // Copy user handles.
     if (num_handles > 0) {
@@ -72,8 +73,8 @@ static Result WaitSynchronization(Core::System& system, int32_t* out_index, cons
     });
 
     // Wait on the objects.
-    Result res = KSynchronizationObject::Wait(kernel, out_index, objs.data(),
-                                              static_cast<s32>(objs.size()), timeout_ns);
+    Result res =
+        KSynchronizationObject::Wait(kernel, out_index, objs.data(), num_handles, timeout_ns);
 
     R_SUCCEED_IF(res == ResultSessionClosed);
     R_RETURN(res);
@@ -87,8 +88,7 @@ Result WaitSynchronization(Core::System& system, int32_t* out_index, u64 user_ha
 
     // Ensure number of handles is valid.
     R_UNLESS(0 <= num_handles && num_handles <= Svc::ArgumentHandleCountMax, ResultOutOfRange);
-
-    std::vector<Handle> handles(num_handles);
+    std::array<Handle, Svc::ArgumentHandleCountMax> handles;
     if (num_handles > 0) {
         GetCurrentMemory(system.Kernel())
             .ReadBlock(user_handles, handles.data(), num_handles * sizeof(Handle));
diff --git a/src/core/hle/kernel/svc/svc_thread.cpp b/src/core/hle/kernel/svc/svc_thread.cpp
index 37b54079c..36b94e6bf 100644
--- a/src/core/hle/kernel/svc/svc_thread.cpp
+++ b/src/core/hle/kernel/svc/svc_thread.cpp
@@ -174,7 +174,7 @@ Result GetThreadContext3(Core::System& system, u64 out_context, Handle thread_ha
         }
 
         // Get the thread context.
-        std::vector<u8> context;
+        static thread_local Common::ScratchBuffer<u8> context;
         R_TRY(thread->GetThreadContext3(context));
 
         // Copy the thread context to user space.
diff --git a/src/core/hle/kernel/svc/svc_tick.cpp b/src/core/hle/kernel/svc/svc_tick.cpp
index 561336482..7dd7c6e51 100644
--- a/src/core/hle/kernel/svc/svc_tick.cpp
+++ b/src/core/hle/kernel/svc/svc_tick.cpp
@@ -12,16 +12,8 @@ namespace Kernel::Svc {
 int64_t GetSystemTick(Core::System& system) {
     LOG_TRACE(Kernel_SVC, "called");
 
-    auto& core_timing = system.CoreTiming();
-
     // Returns the value of cntpct_el0 (https://switchbrew.org/wiki/SVC#svcGetSystemTick)
-    const u64 result{core_timing.GetClockTicks()};
-
-    if (!system.Kernel().IsMulticore()) {
-        core_timing.AddTicks(400U);
-    }
-
-    return static_cast<int64_t>(result);
+    return static_cast<int64_t>(system.CoreTiming().GetClockTicks());
 }
 
 int64_t GetSystemTick64(Core::System& system) {
diff --git a/src/core/hle/service/am/applets/applet_cabinet.cpp b/src/core/hle/service/am/applets/applet_cabinet.cpp
index 8b754e9d4..19ed184e8 100644
--- a/src/core/hle/service/am/applets/applet_cabinet.cpp
+++ b/src/core/hle/service/am/applets/applet_cabinet.cpp
@@ -141,7 +141,7 @@ void Cabinet::DisplayCompleted(bool apply_changes, std::string_view amiibo_name)
     applet_output.device_handle = applet_input_common.device_handle;
     applet_output.result = CabinetResult::Cancel;
     const auto reg_result = nfp_device->GetRegisterInfo(applet_output.register_info);
-    const auto tag_result = nfp_device->GetTagInfo(applet_output.tag_info, false);
+    const auto tag_result = nfp_device->GetTagInfo(applet_output.tag_info);
     nfp_device->Finalize();
 
     if (reg_result.IsSuccess()) {
diff --git a/src/core/hle/service/audio/audin_u.cpp b/src/core/hle/service/audio/audin_u.cpp
index f0640c64f..c8d574993 100644
--- a/src/core/hle/service/audio/audin_u.cpp
+++ b/src/core/hle/service/audio/audin_u.cpp
@@ -5,6 +5,7 @@
 #include "audio_core/renderer/audio_device.h"
 #include "common/common_funcs.h"
 #include "common/logging/log.h"
+#include "common/settings.h"
 #include "common/string_util.h"
 #include "core/core.h"
 #include "core/hle/kernel/k_event.h"
@@ -123,19 +124,13 @@ private:
 
     void GetReleasedAudioInBuffer(HLERequestContext& ctx) {
         const auto write_buffer_size = ctx.GetWriteBufferNumElements<u64>();
-        std::vector<u64> released_buffers(write_buffer_size);
+        tmp_buffer.resize_destructive(write_buffer_size);
+        tmp_buffer[0] = 0;
 
-        const auto count = impl->GetReleasedBuffers(released_buffers);
+        const auto count = impl->GetReleasedBuffers(tmp_buffer);
 
-        [[maybe_unused]] std::string tags{};
-        for (u32 i = 0; i < count; i++) {
-            tags += fmt::format("{:08X}, ", released_buffers[i]);
-        }
-        [[maybe_unused]] auto sessionid{impl->GetSystem().GetSessionId()};
-        LOG_TRACE(Service_Audio, "called. Session {} released {} buffers: {}", sessionid, count,
-                  tags);
+        ctx.WriteBuffer(tmp_buffer);
 
-        ctx.WriteBuffer(released_buffers);
         IPC::ResponseBuilder rb{ctx, 3};
         rb.Push(ResultSuccess);
         rb.Push(count);
@@ -200,6 +195,7 @@ private:
     KernelHelpers::ServiceContext service_context;
     Kernel::KEvent* event;
     std::shared_ptr<AudioCore::AudioIn::In> impl;
+    Common::ScratchBuffer<u64> tmp_buffer;
 };
 
 AudInU::AudInU(Core::System& system_)
diff --git a/src/core/hle/service/audio/audout_u.cpp b/src/core/hle/service/audio/audout_u.cpp
index 3e62fa4fc..032c8c11f 100644
--- a/src/core/hle/service/audio/audout_u.cpp
+++ b/src/core/hle/service/audio/audout_u.cpp
@@ -123,19 +123,13 @@ private:
 
     void GetReleasedAudioOutBuffers(HLERequestContext& ctx) {
         const auto write_buffer_size = ctx.GetWriteBufferNumElements<u64>();
-        std::vector<u64> released_buffers(write_buffer_size);
+        tmp_buffer.resize_destructive(write_buffer_size);
+        tmp_buffer[0] = 0;
 
-        const auto count = impl->GetReleasedBuffers(released_buffers);
+        const auto count = impl->GetReleasedBuffers(tmp_buffer);
 
-        [[maybe_unused]] std::string tags{};
-        for (u32 i = 0; i < count; i++) {
-            tags += fmt::format("{:08X}, ", released_buffers[i]);
-        }
-        [[maybe_unused]] const auto sessionid{impl->GetSystem().GetSessionId()};
-        LOG_TRACE(Service_Audio, "called. Session {} released {} buffers: {}", sessionid, count,
-                  tags);
+        ctx.WriteBuffer(tmp_buffer);
 
-        ctx.WriteBuffer(released_buffers);
         IPC::ResponseBuilder rb{ctx, 3};
         rb.Push(ResultSuccess);
         rb.Push(count);
@@ -211,6 +205,7 @@ private:
     KernelHelpers::ServiceContext service_context;
     Kernel::KEvent* event;
     std::shared_ptr<AudioCore::AudioOut::Out> impl;
+    Common::ScratchBuffer<u64> tmp_buffer;
 };
 
 AudOutU::AudOutU(Core::System& system_)
diff --git a/src/core/hle/service/audio/audren_u.cpp b/src/core/hle/service/audio/audren_u.cpp
index 7086d4750..12845c23a 100644
--- a/src/core/hle/service/audio/audren_u.cpp
+++ b/src/core/hle/service/audio/audren_u.cpp
@@ -116,28 +116,26 @@ private:
         // These buffers are written manually to avoid an issue with WriteBuffer throwing errors for
         // checking size 0. Performance size is 0 for most games.
 
-        std::vector<u8> output{};
-        std::vector<u8> performance{};
         auto is_buffer_b{ctx.BufferDescriptorB()[0].Size() != 0};
         if (is_buffer_b) {
             const auto buffersB{ctx.BufferDescriptorB()};
-            output.resize(buffersB[0].Size(), 0);
-            performance.resize(buffersB[1].Size(), 0);
+            tmp_output.resize_destructive(buffersB[0].Size());
+            tmp_performance.resize_destructive(buffersB[1].Size());
         } else {
             const auto buffersC{ctx.BufferDescriptorC()};
-            output.resize(buffersC[0].Size(), 0);
-            performance.resize(buffersC[1].Size(), 0);
+            tmp_output.resize_destructive(buffersC[0].Size());
+            tmp_performance.resize_destructive(buffersC[1].Size());
         }
 
-        auto result = impl->RequestUpdate(input, performance, output);
+        auto result = impl->RequestUpdate(input, tmp_performance, tmp_output);
 
         if (result.IsSuccess()) {
             if (is_buffer_b) {
-                ctx.WriteBufferB(output.data(), output.size(), 0);
-                ctx.WriteBufferB(performance.data(), performance.size(), 1);
+                ctx.WriteBufferB(tmp_output.data(), tmp_output.size(), 0);
+                ctx.WriteBufferB(tmp_performance.data(), tmp_performance.size(), 1);
             } else {
-                ctx.WriteBufferC(output.data(), output.size(), 0);
-                ctx.WriteBufferC(performance.data(), performance.size(), 1);
+                ctx.WriteBufferC(tmp_output.data(), tmp_output.size(), 0);
+                ctx.WriteBufferC(tmp_performance.data(), tmp_performance.size(), 1);
             }
         } else {
             LOG_ERROR(Service_Audio, "RequestUpdate failed error 0x{:02X}!", result.description);
@@ -235,6 +233,8 @@ private:
     Kernel::KEvent* rendered_event;
     Manager& manager;
     std::unique_ptr<Renderer> impl;
+    Common::ScratchBuffer<u8> tmp_output;
+    Common::ScratchBuffer<u8> tmp_performance;
 };
 
 class IAudioDevice final : public ServiceFramework<IAudioDevice> {
diff --git a/src/core/hle/service/audio/audren_u.h b/src/core/hle/service/audio/audren_u.h
index 24ce37e87..d8e9c8719 100644
--- a/src/core/hle/service/audio/audren_u.h
+++ b/src/core/hle/service/audio/audren_u.h
@@ -4,6 +4,7 @@
 #pragma once
 
 #include "audio_core/audio_render_manager.h"
+#include "common/scratch_buffer.h"
 #include "core/hle/service/kernel_helpers.h"
 #include "core/hle/service/service.h"
 
diff --git a/src/core/hle/service/audio/hwopus.cpp b/src/core/hle/service/audio/hwopus.cpp
index 451ac224a..c835f6cb7 100644
--- a/src/core/hle/service/audio/hwopus.cpp
+++ b/src/core/hle/service/audio/hwopus.cpp
@@ -68,13 +68,13 @@ private:
                                  ExtraBehavior extra_behavior) {
         u32 consumed = 0;
         u32 sample_count = 0;
-        std::vector<opus_int16> samples(ctx.GetWriteBufferNumElements<opus_int16>());
+        tmp_samples.resize_destructive(ctx.GetWriteBufferNumElements<opus_int16>());
 
         if (extra_behavior == ExtraBehavior::ResetContext) {
             ResetDecoderContext();
         }
 
-        if (!DecodeOpusData(consumed, sample_count, ctx.ReadBuffer(), samples, performance)) {
+        if (!DecodeOpusData(consumed, sample_count, ctx.ReadBuffer(), tmp_samples, performance)) {
             LOG_ERROR(Audio, "Failed to decode opus data");
             IPC::ResponseBuilder rb{ctx, 2};
             // TODO(ogniK): Use correct error code
@@ -90,11 +90,11 @@ private:
         if (performance) {
             rb.Push<u64>(*performance);
         }
-        ctx.WriteBuffer(samples);
+        ctx.WriteBuffer(tmp_samples);
     }
 
     bool DecodeOpusData(u32& consumed, u32& sample_count, std::span<const u8> input,
-                        std::vector<opus_int16>& output, u64* out_performance_time) const {
+                        std::span<opus_int16> output, u64* out_performance_time) const {
         const auto start_time = std::chrono::steady_clock::now();
         const std::size_t raw_output_sz = output.size() * sizeof(opus_int16);
         if (sizeof(OpusPacketHeader) > input.size()) {
@@ -154,6 +154,7 @@ private:
     OpusDecoderPtr decoder;
     u32 sample_rate;
     u32 channel_count;
+    Common::ScratchBuffer<opus_int16> tmp_samples;
 };
 
 class IHardwareOpusDecoderManager final : public ServiceFramework<IHardwareOpusDecoderManager> {
diff --git a/src/core/hle/service/hid/hidbus.cpp b/src/core/hle/service/hid/hidbus.cpp
index 5604a6fda..80aac221b 100644
--- a/src/core/hle/service/hid/hidbus.cpp
+++ b/src/core/hle/service/hid/hidbus.cpp
@@ -5,7 +5,6 @@
 #include "common/settings.h"
 #include "core/core.h"
 #include "core/core_timing.h"
-#include "core/core_timing_util.h"
 #include "core/hid/hid_types.h"
 #include "core/hle/kernel/k_event.h"
 #include "core/hle/kernel/k_readable_event.h"
diff --git a/src/core/hle/service/nfc/common/device.cpp b/src/core/hle/service/nfc/common/device.cpp
index f4b180b06..5bf289818 100644
--- a/src/core/hle/service/nfc/common/device.cpp
+++ b/src/core/hle/service/nfc/common/device.cpp
@@ -93,7 +93,8 @@ void NfcDevice::NpadUpdate(Core::HID::ControllerTriggerType type) {
     const auto nfc_status = npad_device->GetNfc();
     switch (nfc_status.state) {
     case Common::Input::NfcState::NewAmiibo:
-        LoadNfcTag(nfc_status.data);
+        LoadNfcTag(nfc_status.protocol, nfc_status.tag_type, nfc_status.uuid_length,
+                   nfc_status.uuid);
         break;
     case Common::Input::NfcState::AmiiboRemoved:
         if (device_state == DeviceState::Initialized || device_state == DeviceState::TagRemoved) {
@@ -108,28 +109,46 @@ void NfcDevice::NpadUpdate(Core::HID::ControllerTriggerType type) {
     }
 }
 
-bool NfcDevice::LoadNfcTag(std::span<const u8> data) {
+bool NfcDevice::LoadNfcTag(u8 protocol, u8 tag_type, u8 uuid_length, UniqueSerialNumber uuid) {
     if (device_state != DeviceState::SearchingForTag) {
         LOG_ERROR(Service_NFC, "Game is not looking for nfc tag, current state {}", device_state);
         return false;
     }
 
+    if ((protocol & static_cast<u8>(allowed_protocols)) == 0) {
+        LOG_ERROR(Service_NFC, "Protocol not supported {}", protocol);
+        return false;
+    }
+
+    real_tag_info = {
+        .uuid = uuid,
+        .uuid_length = uuid_length,
+        .protocol = static_cast<NfcProtocol>(protocol),
+        .tag_type = static_cast<TagType>(tag_type),
+    };
+
+    device_state = DeviceState::TagFound;
+    deactivate_event->GetReadableEvent().Clear();
+    activate_event->Signal();
+    return true;
+}
+
+bool NfcDevice::LoadAmiiboData() {
+    std::vector<u8> data{};
+
+    if (!npad_device->ReadAmiiboData(data)) {
+        return false;
+    }
+
     if (data.size() < sizeof(NFP::EncryptedNTAG215File)) {
         LOG_ERROR(Service_NFC, "Not an amiibo, size={}", data.size());
         return false;
     }
 
-    mifare_data.resize(data.size());
-    memcpy(mifare_data.data(), data.data(), data.size());
-
     memcpy(&tag_data, data.data(), sizeof(NFP::EncryptedNTAG215File));
     is_plain_amiibo = NFP::AmiiboCrypto::IsAmiiboValid(tag_data);
     is_write_protected = false;
 
-    device_state = DeviceState::TagFound;
-    deactivate_event->GetReadableEvent().Clear();
-    activate_event->Signal();
-
     // Fallback for plain amiibos
     if (is_plain_amiibo) {
         LOG_INFO(Service_NFP, "Using plain amiibo");
@@ -147,6 +166,7 @@ bool NfcDevice::LoadNfcTag(std::span<const u8> data) {
         return true;
     }
 
+    LOG_INFO(Service_NFP, "Using encrypted amiibo");
     tag_data = {};
     memcpy(&encrypted_tag_data, data.data(), sizeof(NFP::EncryptedNTAG215File));
     return true;
@@ -162,7 +182,6 @@ void NfcDevice::CloseNfcTag() {
     device_state = DeviceState::TagRemoved;
     encrypted_tag_data = {};
     tag_data = {};
-    mifare_data = {};
     activate_event->GetReadableEvent().Clear();
     deactivate_event->Signal();
 }
@@ -179,8 +198,12 @@ void NfcDevice::Initialize() {
     device_state = npad_device->HasNfc() ? DeviceState::Initialized : DeviceState::Unavailable;
     encrypted_tag_data = {};
     tag_data = {};
-    mifare_data = {};
-    is_initalized = true;
+
+    if (device_state != DeviceState::Initialized) {
+        return;
+    }
+
+    is_initalized = npad_device->AddNfcHandle();
 }
 
 void NfcDevice::Finalize() {
@@ -190,6 +213,11 @@ void NfcDevice::Finalize() {
     if (device_state == DeviceState::SearchingForTag || device_state == DeviceState::TagRemoved) {
         StopDetection();
     }
+
+    if (device_state != DeviceState::Unavailable) {
+        npad_device->RemoveNfcHandle();
+    }
+
     device_state = DeviceState::Unavailable;
     is_initalized = false;
 }
@@ -200,10 +228,8 @@ Result NfcDevice::StartDetection(NfcProtocol allowed_protocol) {
         return ResultWrongDeviceState;
     }
 
-    if (npad_device->SetPollingMode(Core::HID::EmulatedDeviceIndex::RightIndex,
-                                    Common::Input::PollingMode::NFC) !=
-        Common::Input::DriverResult::Success) {
-        LOG_ERROR(Service_NFC, "Nfc not supported");
+    if (!npad_device->StartNfcPolling()) {
+        LOG_ERROR(Service_NFC, "Nfc polling not supported");
         return ResultNfcDisabled;
     }
 
@@ -213,9 +239,6 @@ Result NfcDevice::StartDetection(NfcProtocol allowed_protocol) {
 }
 
 Result NfcDevice::StopDetection() {
-    npad_device->SetPollingMode(Core::HID::EmulatedDeviceIndex::RightIndex,
-                                Common::Input::PollingMode::Active);
-
     if (device_state == DeviceState::Initialized) {
         return ResultSuccess;
     }
@@ -225,6 +248,7 @@ Result NfcDevice::StopDetection() {
     }
 
     if (device_state == DeviceState::SearchingForTag || device_state == DeviceState::TagRemoved) {
+        npad_device->StopNfcPolling();
         device_state = DeviceState::Initialized;
         return ResultSuccess;
     }
@@ -233,7 +257,7 @@ Result NfcDevice::StopDetection() {
     return ResultWrongDeviceState;
 }
 
-Result NfcDevice::GetTagInfo(NFP::TagInfo& tag_info, bool is_mifare) const {
+Result NfcDevice::GetTagInfo(NFP::TagInfo& tag_info) const {
     if (device_state != DeviceState::TagFound && device_state != DeviceState::TagMounted) {
         LOG_ERROR(Service_NFC, "Wrong device state {}", device_state);
         if (device_state == DeviceState::TagRemoved) {
@@ -242,41 +266,15 @@ Result NfcDevice::GetTagInfo(NFP::TagInfo& tag_info, bool is_mifare) const {
         return ResultWrongDeviceState;
     }
 
-    UniqueSerialNumber uuid{};
-    u8 uuid_length{};
-    NfcProtocol protocol{NfcProtocol::TypeA};
-    TagType tag_type{TagType::Type2};
-
-    if (is_mifare) {
-        tag_type = TagType::Mifare;
-        uuid_length = sizeof(NFP::NtagTagUuid);
-        memcpy(uuid.data(), mifare_data.data(), uuid_length);
-    } else {
-        tag_type = TagType::Type2;
-        uuid_length = sizeof(NFP::NtagTagUuid);
-        NFP::NtagTagUuid nUuid{
-            .part1 = encrypted_tag_data.uuid.part1,
-            .part2 = encrypted_tag_data.uuid.part2,
-            .nintendo_id = encrypted_tag_data.uuid.nintendo_id,
-        };
-        memcpy(uuid.data(), &nUuid, uuid_length);
+    tag_info = real_tag_info;
 
-        // Generate random UUID to bypass amiibo load limits
-        if (Settings::values.random_amiibo_id) {
-            Common::TinyMT rng{};
-            rng.Initialize(static_cast<u32>(GetCurrentPosixTime()));
-            rng.GenerateRandomBytes(uuid.data(), uuid_length);
-        }
+    // Generate random UUID to bypass amiibo load limits
+    if (real_tag_info.tag_type == TagType::Type2 && Settings::values.random_amiibo_id) {
+        Common::TinyMT rng{};
+        rng.Initialize(static_cast<u32>(GetCurrentPosixTime()));
+        rng.GenerateRandomBytes(tag_info.uuid.data(), tag_info.uuid_length);
     }
 
-    // Protocol and tag type may change here
-    tag_info = {
-        .uuid = uuid,
-        .uuid_length = uuid_length,
-        .protocol = protocol,
-        .tag_type = tag_type,
-    };
-
     return ResultSuccess;
 }
 
@@ -293,7 +291,7 @@ Result NfcDevice::ReadMifare(std::span<const MifareReadBlockParameter> parameter
     Result result = ResultSuccess;
 
     TagInfo tag_info{};
-    result = GetTagInfo(tag_info, true);
+    result = GetTagInfo(tag_info);
 
     if (result.IsError()) {
         return result;
@@ -307,6 +305,8 @@ Result NfcDevice::ReadMifare(std::span<const MifareReadBlockParameter> parameter
         return ResultInvalidArgument;
     }
 
+    Common::Input::MifareRequest request{};
+    Common::Input::MifareRequest out_data{};
     const auto unknown = parameters[0].sector_key.unknown;
     for (std::size_t i = 0; i < parameters.size(); i++) {
         if (unknown != parameters[i].sector_key.unknown) {
@@ -315,25 +315,29 @@ Result NfcDevice::ReadMifare(std::span<const MifareReadBlockParameter> parameter
     }
 
     for (std::size_t i = 0; i < parameters.size(); i++) {
-        result = ReadMifare(parameters[i], read_block_data[i]);
-        if (result.IsError()) {
-            break;
+        if (parameters[i].sector_key.command == MifareCmd::None) {
+            continue;
         }
+        request.data[i].command = static_cast<u8>(parameters[i].sector_key.command);
+        request.data[i].sector = parameters[i].sector_number;
+        memcpy(request.data[i].key.data(), parameters[i].sector_key.sector_key.data(),
+               sizeof(KeyData));
     }
 
-    return result;
-}
-
-Result NfcDevice::ReadMifare(const MifareReadBlockParameter& parameter,
-                             MifareReadBlockData& read_block_data) const {
-    const std::size_t sector_index = parameter.sector_number * sizeof(DataBlock);
-    read_block_data.sector_number = parameter.sector_number;
-    if (mifare_data.size() < sector_index + sizeof(DataBlock)) {
+    if (!npad_device->ReadMifareData(request, out_data)) {
         return ResultMifareError288;
     }
 
-    // TODO: Use parameter.sector_key to read encrypted data
-    memcpy(read_block_data.data.data(), mifare_data.data() + sector_index, sizeof(DataBlock));
+    for (std::size_t i = 0; i < read_block_data.size(); i++) {
+        if (static_cast<MifareCmd>(out_data.data[i].command) == MifareCmd::None) {
+            continue;
+        }
+
+        read_block_data[i] = {
+            .data = out_data.data[i].data,
+            .sector_number = out_data.data[i].sector,
+        };
+    }
 
     return ResultSuccess;
 }
@@ -342,7 +346,7 @@ Result NfcDevice::WriteMifare(std::span<const MifareWriteBlockParameter> paramet
     Result result = ResultSuccess;
 
     TagInfo tag_info{};
-    result = GetTagInfo(tag_info, true);
+    result = GetTagInfo(tag_info);
 
     if (result.IsError()) {
         return result;
@@ -363,42 +367,25 @@ Result NfcDevice::WriteMifare(std::span<const MifareWriteBlockParameter> paramet
         }
     }
 
+    Common::Input::MifareRequest request{};
     for (std::size_t i = 0; i < parameters.size(); i++) {
-        result = WriteMifare(parameters[i]);
-        if (result.IsError()) {
-            break;
+        if (parameters[i].sector_key.command == MifareCmd::None) {
+            continue;
         }
+        request.data[i].command = static_cast<u8>(parameters[i].sector_key.command);
+        request.data[i].sector = parameters[i].sector_number;
+        memcpy(request.data[i].key.data(), parameters[i].sector_key.sector_key.data(),
+               sizeof(KeyData));
+        memcpy(request.data[i].data.data(), parameters[i].data.data(), sizeof(KeyData));
     }
 
-    if (!npad_device->WriteNfc(mifare_data)) {
-        LOG_ERROR(Service_NFP, "Error writing to file");
+    if (!npad_device->WriteMifareData(request)) {
         return ResultMifareError288;
     }
 
     return result;
 }
 
-Result NfcDevice::WriteMifare(const MifareWriteBlockParameter& parameter) {
-    const std::size_t sector_index = parameter.sector_number * sizeof(DataBlock);
-
-    if (device_state != DeviceState::TagFound && device_state != DeviceState::TagMounted) {
-        LOG_ERROR(Service_NFC, "Wrong device state {}", device_state);
-        if (device_state == DeviceState::TagRemoved) {
-            return ResultTagRemoved;
-        }
-        return ResultWrongDeviceState;
-    }
-
-    if (mifare_data.size() < sector_index + sizeof(DataBlock)) {
-        return ResultMifareError288;
-    }
-
-    // TODO: Use parameter.sector_key to encrypt the data
-    memcpy(mifare_data.data() + sector_index, parameter.data.data(), sizeof(DataBlock));
-
-    return ResultSuccess;
-}
-
 Result NfcDevice::SendCommandByPassThrough(const Time::Clock::TimeSpanType& timeout,
                                            std::span<const u8> command_data,
                                            std::span<u8> out_data) {
@@ -412,6 +399,11 @@ Result NfcDevice::Mount(NFP::ModelType model_type, NFP::MountTarget mount_target
         return ResultWrongDeviceState;
     }
 
+    if (!LoadAmiiboData()) {
+        LOG_ERROR(Service_NFP, "Not an amiibo");
+        return ResultInvalidTagType;
+    }
+
     if (!NFP::AmiiboCrypto::IsAmiiboValid(encrypted_tag_data)) {
         LOG_ERROR(Service_NFP, "Not an amiibo");
         return ResultInvalidTagType;
@@ -562,7 +554,7 @@ Result NfcDevice::Restore() {
 
     NFC::TagInfo tag_info{};
     std::array<u8, sizeof(NFP::EncryptedNTAG215File)> data{};
-    Result result = GetTagInfo(tag_info, false);
+    Result result = GetTagInfo(tag_info);
 
     if (result.IsError()) {
         return result;
@@ -635,7 +627,7 @@ Result NfcDevice::GetCommonInfo(NFP::CommonInfo& common_info) const {
     // TODO: Validate this data
     common_info = {
         .last_write_date = settings.write_date.GetWriteDate(),
-        .write_counter = tag_data.write_counter,
+        .write_counter = tag_data.application_write_counter,
         .version = tag_data.amiibo_version,
         .application_area_size = sizeof(NFP::ApplicationArea),
     };
diff --git a/src/core/hle/service/nfc/common/device.h b/src/core/hle/service/nfc/common/device.h
index 7560210d6..0ed1ff34c 100644
--- a/src/core/hle/service/nfc/common/device.h
+++ b/src/core/hle/service/nfc/common/device.h
@@ -42,15 +42,12 @@ public:
     Result StartDetection(NfcProtocol allowed_protocol);
     Result StopDetection();
 
-    Result GetTagInfo(TagInfo& tag_info, bool is_mifare) const;
+    Result GetTagInfo(TagInfo& tag_info) const;
 
     Result ReadMifare(std::span<const MifareReadBlockParameter> parameters,
                       std::span<MifareReadBlockData> read_block_data) const;
-    Result ReadMifare(const MifareReadBlockParameter& parameter,
-                      MifareReadBlockData& read_block_data) const;
 
     Result WriteMifare(std::span<const MifareWriteBlockParameter> parameters);
-    Result WriteMifare(const MifareWriteBlockParameter& parameter);
 
     Result SendCommandByPassThrough(const Time::Clock::TimeSpanType& timeout,
                                     std::span<const u8> command_data, std::span<u8> out_data);
@@ -105,7 +102,8 @@ public:
 
 private:
     void NpadUpdate(Core::HID::ControllerTriggerType type);
-    bool LoadNfcTag(std::span<const u8> data);
+    bool LoadNfcTag(u8 protocol, u8 tag_type, u8 uuid_length, UniqueSerialNumber uuid);
+    bool LoadAmiiboData();
     void CloseNfcTag();
 
     NFP::AmiiboName GetAmiiboName(const NFP::AmiiboSettings& settings) const;
@@ -140,8 +138,8 @@ private:
     bool is_write_protected{};
     NFP::MountTarget mount_target{NFP::MountTarget::None};
 
+    TagInfo real_tag_info{};
     NFP::NTAG215File tag_data{};
-    std::vector<u8> mifare_data{};
     NFP::EncryptedNTAG215File encrypted_tag_data{};
 };
 
diff --git a/src/core/hle/service/nfc/common/device_manager.cpp b/src/core/hle/service/nfc/common/device_manager.cpp
index b0456508e..562f3a28e 100644
--- a/src/core/hle/service/nfc/common/device_manager.cpp
+++ b/src/core/hle/service/nfc/common/device_manager.cpp
@@ -29,6 +29,9 @@ DeviceManager::DeviceManager(Core::System& system_, KernelHelpers::ServiceContex
 }
 
 DeviceManager ::~DeviceManager() {
+    if (is_initialized) {
+        Finalize();
+    }
     service_context.CloseEvent(availability_change_event);
 }
 
@@ -125,14 +128,14 @@ Result DeviceManager::StopDetection(u64 device_handle) {
     return result;
 }
 
-Result DeviceManager::GetTagInfo(u64 device_handle, TagInfo& tag_info, bool is_mifare) const {
+Result DeviceManager::GetTagInfo(u64 device_handle, TagInfo& tag_info) const {
     std::scoped_lock lock{mutex};
 
     std::shared_ptr<NfcDevice> device = nullptr;
     auto result = GetDeviceHandle(device_handle, device);
 
     if (result.IsSuccess()) {
-        result = device->GetTagInfo(tag_info, is_mifare);
+        result = device->GetTagInfo(tag_info);
         result = VerifyDeviceResult(device, result);
     }
 
@@ -546,7 +549,7 @@ Result DeviceManager::ReadBackupData(u64 device_handle, std::span<u8> data) cons
     NFC::TagInfo tag_info{};
 
     if (result.IsSuccess()) {
-        result = device->GetTagInfo(tag_info, false);
+        result = device->GetTagInfo(tag_info);
     }
 
     if (result.IsSuccess()) {
@@ -565,7 +568,7 @@ Result DeviceManager::WriteBackupData(u64 device_handle, std::span<const u8> dat
     NFC::TagInfo tag_info{};
 
     if (result.IsSuccess()) {
-        result = device->GetTagInfo(tag_info, false);
+        result = device->GetTagInfo(tag_info);
     }
 
     if (result.IsSuccess()) {
diff --git a/src/core/hle/service/nfc/common/device_manager.h b/src/core/hle/service/nfc/common/device_manager.h
index 2971e280f..c61ba0cf3 100644
--- a/src/core/hle/service/nfc/common/device_manager.h
+++ b/src/core/hle/service/nfc/common/device_manager.h
@@ -33,7 +33,7 @@ public:
     Kernel::KReadableEvent& AttachAvailabilityChangeEvent() const;
     Result StartDetection(u64 device_handle, NfcProtocol tag_protocol);
     Result StopDetection(u64 device_handle);
-    Result GetTagInfo(u64 device_handle, NFP::TagInfo& tag_info, bool is_mifare) const;
+    Result GetTagInfo(u64 device_handle, NFP::TagInfo& tag_info) const;
     Kernel::KReadableEvent& AttachActivateEvent(u64 device_handle) const;
     Kernel::KReadableEvent& AttachDeactivateEvent(u64 device_handle) const;
     Result ReadMifare(u64 device_handle,
diff --git a/src/core/hle/service/nfc/mifare_types.h b/src/core/hle/service/nfc/mifare_types.h
index 75b59f021..467937399 100644
--- a/src/core/hle/service/nfc/mifare_types.h
+++ b/src/core/hle/service/nfc/mifare_types.h
@@ -11,9 +11,10 @@
 namespace Service::NFC {
 
 enum class MifareCmd : u8 {
+    None = 0x00,
+    Read = 0x30,
     AuthA = 0x60,
     AuthB = 0x61,
-    Read = 0x30,
     Write = 0xA0,
     Transfer = 0xB0,
     Decrement = 0xC0,
@@ -35,17 +36,17 @@ static_assert(sizeof(SectorKey) == 0x10, "SectorKey is an invalid size");
 
 // This is nn::nfc::MifareReadBlockParameter
 struct MifareReadBlockParameter {
-    u8 sector_number;
+    u8 sector_number{};
     INSERT_PADDING_BYTES(0x7);
-    SectorKey sector_key;
+    SectorKey sector_key{};
 };
 static_assert(sizeof(MifareReadBlockParameter) == 0x18,
               "MifareReadBlockParameter is an invalid size");
 
 // This is nn::nfc::MifareReadBlockData
 struct MifareReadBlockData {
-    DataBlock data;
-    u8 sector_number;
+    DataBlock data{};
+    u8 sector_number{};
     INSERT_PADDING_BYTES(0x7);
 };
 static_assert(sizeof(MifareReadBlockData) == 0x18, "MifareReadBlockData is an invalid size");
diff --git a/src/core/hle/service/nfc/nfc_interface.cpp b/src/core/hle/service/nfc/nfc_interface.cpp
index 130fb7f78..e7ca7582e 100644
--- a/src/core/hle/service/nfc/nfc_interface.cpp
+++ b/src/core/hle/service/nfc/nfc_interface.cpp
@@ -174,8 +174,7 @@ void NfcInterface::GetTagInfo(HLERequestContext& ctx) {
     LOG_INFO(Service_NFC, "called, device_handle={}", device_handle);
 
     TagInfo tag_info{};
-    auto result =
-        GetManager()->GetTagInfo(device_handle, tag_info, backend_type == BackendType::Mifare);
+    auto result = GetManager()->GetTagInfo(device_handle, tag_info);
     result = TranslateResultToServiceError(result);
 
     if (result.IsSuccess()) {
@@ -216,8 +215,8 @@ void NfcInterface::ReadMifare(HLERequestContext& ctx) {
     memcpy(read_commands.data(), buffer.data(),
            number_of_commands * sizeof(MifareReadBlockParameter));
 
-    LOG_INFO(Service_NFC, "(STUBBED) called, device_handle={}, read_commands_size={}",
-             device_handle, number_of_commands);
+    LOG_INFO(Service_NFC, "called, device_handle={}, read_commands_size={}", device_handle,
+             number_of_commands);
 
     std::vector<MifareReadBlockData> out_data(number_of_commands);
     auto result = GetManager()->ReadMifare(device_handle, read_commands, out_data);
diff --git a/src/core/hle/service/nvdrv/devices/nvdevice.h b/src/core/hle/service/nvdrv/devices/nvdevice.h
index ab1f30f9e..a04538d5d 100644
--- a/src/core/hle/service/nvdrv/devices/nvdevice.h
+++ b/src/core/hle/service/nvdrv/devices/nvdevice.h
@@ -34,7 +34,7 @@ public:
      * @returns The result code of the ioctl.
      */
     virtual NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::vector<u8>& output) = 0;
+                            std::span<u8> output) = 0;
 
     /**
      * Handles an ioctl2 request.
@@ -45,7 +45,7 @@ public:
      * @returns The result code of the ioctl.
      */
     virtual NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::span<const u8> inline_input, std::vector<u8>& output) = 0;
+                            std::span<const u8> inline_input, std::span<u8> output) = 0;
 
     /**
      * Handles an ioctl3 request.
@@ -56,7 +56,7 @@ public:
      * @returns The result code of the ioctl.
      */
     virtual NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::vector<u8>& output, std::vector<u8>& inline_output) = 0;
+                            std::span<u8> output, std::span<u8> inline_output) = 0;
 
     /**
      * Called once a device is opened
diff --git a/src/core/hle/service/nvdrv/devices/nvdisp_disp0.cpp b/src/core/hle/service/nvdrv/devices/nvdisp_disp0.cpp
index 5a5b2e305..05a43d8dc 100644
--- a/src/core/hle/service/nvdrv/devices/nvdisp_disp0.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvdisp_disp0.cpp
@@ -18,19 +18,19 @@ nvdisp_disp0::nvdisp_disp0(Core::System& system_, NvCore::Container& core)
 nvdisp_disp0::~nvdisp_disp0() = default;
 
 NvResult nvdisp_disp0::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::vector<u8>& output) {
+                              std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvdisp_disp0::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::span<const u8> inline_input, std::vector<u8>& output) {
+                              std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvdisp_disp0::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::vector<u8>& output, std::vector<u8>& inline_output) {
+                              std::span<u8> output, std::span<u8> inline_output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
@@ -51,8 +51,8 @@ void nvdisp_disp0::flip(u32 buffer_handle, u32 offset, android::PixelFormat form
                                                stride, format, transform, crop_rect};
 
     system.GPU().RequestSwapBuffers(&framebuffer, fences, num_fences);
-    system.GetPerfStats().EndSystemFrame();
     system.SpeedLimiter().DoSpeedLimiting(system.CoreTiming().GetGlobalTimeUs());
+    system.GetPerfStats().EndSystemFrame();
     system.GetPerfStats().BeginSystemFrame();
 }
 
diff --git a/src/core/hle/service/nvdrv/devices/nvdisp_disp0.h b/src/core/hle/service/nvdrv/devices/nvdisp_disp0.h
index bcd0e3ed5..daee05fe8 100644
--- a/src/core/hle/service/nvdrv/devices/nvdisp_disp0.h
+++ b/src/core/hle/service/nvdrv/devices/nvdisp_disp0.h
@@ -26,11 +26,11 @@ public:
     ~nvdisp_disp0() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.cpp b/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.cpp
index 681bd0867..07e570a9f 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.cpp
@@ -28,7 +28,7 @@ nvhost_as_gpu::nvhost_as_gpu(Core::System& system_, Module& module_, NvCore::Con
 nvhost_as_gpu::~nvhost_as_gpu() = default;
 
 NvResult nvhost_as_gpu::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                               std::vector<u8>& output) {
+                               std::span<u8> output) {
     switch (command.group) {
     case 'A':
         switch (command.cmd) {
@@ -61,13 +61,13 @@ NvResult nvhost_as_gpu::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> i
 }
 
 NvResult nvhost_as_gpu::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                               std::span<const u8> inline_input, std::vector<u8>& output) {
+                               std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvhost_as_gpu::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                               std::vector<u8>& output, std::vector<u8>& inline_output) {
+                               std::span<u8> output, std::span<u8> inline_output) {
     switch (command.group) {
     case 'A':
         switch (command.cmd) {
@@ -87,7 +87,7 @@ NvResult nvhost_as_gpu::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> i
 void nvhost_as_gpu::OnOpen(DeviceFD fd) {}
 void nvhost_as_gpu::OnClose(DeviceFD fd) {}
 
-NvResult nvhost_as_gpu::AllocAsEx(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::AllocAsEx(std::span<const u8> input, std::span<u8> output) {
     IoctlAllocAsEx params{};
     std::memcpy(&params, input.data(), input.size());
 
@@ -141,7 +141,7 @@ NvResult nvhost_as_gpu::AllocAsEx(std::span<const u8> input, std::vector<u8>& ou
     return NvResult::Success;
 }
 
-NvResult nvhost_as_gpu::AllocateSpace(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::AllocateSpace(std::span<const u8> input, std::span<u8> output) {
     IoctlAllocSpace params{};
     std::memcpy(&params, input.data(), input.size());
 
@@ -220,7 +220,7 @@ void nvhost_as_gpu::FreeMappingLocked(u64 offset) {
     mapping_map.erase(offset);
 }
 
-NvResult nvhost_as_gpu::FreeSpace(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::FreeSpace(std::span<const u8> input, std::span<u8> output) {
     IoctlFreeSpace params{};
     std::memcpy(&params, input.data(), input.size());
 
@@ -266,15 +266,14 @@ NvResult nvhost_as_gpu::FreeSpace(std::span<const u8> input, std::vector<u8>& ou
     return NvResult::Success;
 }
 
-NvResult nvhost_as_gpu::Remap(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::Remap(std::span<const u8> input, std::span<u8> output) {
     const auto num_entries = input.size() / sizeof(IoctlRemapEntry);
 
     LOG_DEBUG(Service_NVDRV, "called, num_entries=0x{:X}", num_entries);
 
-    std::vector<IoctlRemapEntry> entries(num_entries);
-    std::memcpy(entries.data(), input.data(), input.size());
-
     std::scoped_lock lock(mutex);
+    entries.resize_destructive(num_entries);
+    std::memcpy(entries.data(), input.data(), input.size());
 
     if (!vm.initialised) {
         return NvResult::BadValue;
@@ -320,7 +319,7 @@ NvResult nvhost_as_gpu::Remap(std::span<const u8> input, std::vector<u8>& output
     return NvResult::Success;
 }
 
-NvResult nvhost_as_gpu::MapBufferEx(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::MapBufferEx(std::span<const u8> input, std::span<u8> output) {
     IoctlMapBufferEx params{};
     std::memcpy(&params, input.data(), input.size());
 
@@ -424,7 +423,7 @@ NvResult nvhost_as_gpu::MapBufferEx(std::span<const u8> input, std::vector<u8>&
     return NvResult::Success;
 }
 
-NvResult nvhost_as_gpu::UnmapBuffer(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::UnmapBuffer(std::span<const u8> input, std::span<u8> output) {
     IoctlUnmapBuffer params{};
     std::memcpy(&params, input.data(), input.size());
 
@@ -463,7 +462,7 @@ NvResult nvhost_as_gpu::UnmapBuffer(std::span<const u8> input, std::vector<u8>&
     return NvResult::Success;
 }
 
-NvResult nvhost_as_gpu::BindChannel(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::BindChannel(std::span<const u8> input, std::span<u8> output) {
     IoctlBindChannel params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "called, fd={:X}", params.fd);
@@ -492,7 +491,7 @@ void nvhost_as_gpu::GetVARegionsImpl(IoctlGetVaRegions& params) {
     };
 }
 
-NvResult nvhost_as_gpu::GetVARegions(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_as_gpu::GetVARegions(std::span<const u8> input, std::span<u8> output) {
     IoctlGetVaRegions params{};
     std::memcpy(&params, input.data(), input.size());
 
@@ -511,8 +510,8 @@ NvResult nvhost_as_gpu::GetVARegions(std::span<const u8> input, std::vector<u8>&
     return NvResult::Success;
 }
 
-NvResult nvhost_as_gpu::GetVARegions(std::span<const u8> input, std::vector<u8>& output,
-                                     std::vector<u8>& inline_output) {
+NvResult nvhost_as_gpu::GetVARegions(std::span<const u8> input, std::span<u8> output,
+                                     std::span<u8> inline_output) {
     IoctlGetVaRegions params{};
     std::memcpy(&params, input.data(), input.size());
 
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.h b/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.h
index 1aba8d579..2af3e1260 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_as_gpu.h
@@ -15,6 +15,7 @@
 #include "common/address_space.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
+#include "common/scratch_buffer.h"
 #include "common/swap.h"
 #include "core/hle/service/nvdrv/core/nvmap.h"
 #include "core/hle/service/nvdrv/devices/nvdevice.h"
@@ -48,11 +49,11 @@ public:
     ~nvhost_as_gpu() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
@@ -138,18 +139,18 @@ private:
     static_assert(sizeof(IoctlGetVaRegions) == 16 + sizeof(VaRegion) * 2,
                   "IoctlGetVaRegions is incorrect size");
 
-    NvResult AllocAsEx(std::span<const u8> input, std::vector<u8>& output);
-    NvResult AllocateSpace(std::span<const u8> input, std::vector<u8>& output);
-    NvResult Remap(std::span<const u8> input, std::vector<u8>& output);
-    NvResult MapBufferEx(std::span<const u8> input, std::vector<u8>& output);
-    NvResult UnmapBuffer(std::span<const u8> input, std::vector<u8>& output);
-    NvResult FreeSpace(std::span<const u8> input, std::vector<u8>& output);
-    NvResult BindChannel(std::span<const u8> input, std::vector<u8>& output);
+    NvResult AllocAsEx(std::span<const u8> input, std::span<u8> output);
+    NvResult AllocateSpace(std::span<const u8> input, std::span<u8> output);
+    NvResult Remap(std::span<const u8> input, std::span<u8> output);
+    NvResult MapBufferEx(std::span<const u8> input, std::span<u8> output);
+    NvResult UnmapBuffer(std::span<const u8> input, std::span<u8> output);
+    NvResult FreeSpace(std::span<const u8> input, std::span<u8> output);
+    NvResult BindChannel(std::span<const u8> input, std::span<u8> output);
 
     void GetVARegionsImpl(IoctlGetVaRegions& params);
-    NvResult GetVARegions(std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetVARegions(std::span<const u8> input, std::vector<u8>& output,
-                          std::vector<u8>& inline_output);
+    NvResult GetVARegions(std::span<const u8> input, std::span<u8> output);
+    NvResult GetVARegions(std::span<const u8> input, std::span<u8> output,
+                          std::span<u8> inline_output);
 
     void FreeMappingLocked(u64 offset);
 
@@ -212,6 +213,7 @@ private:
         bool initialised{};
     } vm;
     std::shared_ptr<Tegra::MemoryManager> gmmu;
+    Common::ScratchBuffer<IoctlRemapEntry> entries;
 
     // s32 channel{};
     // u32 big_page_size{VM::DEFAULT_BIG_PAGE_SIZE};
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_ctrl.cpp b/src/core/hle/service/nvdrv/devices/nvhost_ctrl.cpp
index e12025560..4d55554b4 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_ctrl.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_ctrl.cpp
@@ -35,7 +35,7 @@ nvhost_ctrl::~nvhost_ctrl() {
 }
 
 NvResult nvhost_ctrl::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                             std::vector<u8>& output) {
+                             std::span<u8> output) {
     switch (command.group) {
     case 0x0:
         switch (command.cmd) {
@@ -64,13 +64,13 @@ NvResult nvhost_ctrl::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> inp
 }
 
 NvResult nvhost_ctrl::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                             std::span<const u8> inline_input, std::vector<u8>& output) {
+                             std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvhost_ctrl::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                             std::vector<u8>& output, std::vector<u8>& inline_outpu) {
+                             std::span<u8> output, std::span<u8> inline_outpu) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
@@ -79,7 +79,7 @@ void nvhost_ctrl::OnOpen(DeviceFD fd) {}
 
 void nvhost_ctrl::OnClose(DeviceFD fd) {}
 
-NvResult nvhost_ctrl::NvOsGetConfigU32(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl::NvOsGetConfigU32(std::span<const u8> input, std::span<u8> output) {
     IocGetConfigParams params{};
     std::memcpy(&params, input.data(), sizeof(params));
     LOG_TRACE(Service_NVDRV, "called, setting={}!{}", params.domain_str.data(),
@@ -87,7 +87,7 @@ NvResult nvhost_ctrl::NvOsGetConfigU32(std::span<const u8> input, std::vector<u8
     return NvResult::ConfigVarNotFound; // Returns error on production mode
 }
 
-NvResult nvhost_ctrl::IocCtrlEventWait(std::span<const u8> input, std::vector<u8>& output,
+NvResult nvhost_ctrl::IocCtrlEventWait(std::span<const u8> input, std::span<u8> output,
                                        bool is_allocation) {
     IocCtrlEventWaitParams params{};
     std::memcpy(&params, input.data(), sizeof(params));
@@ -231,7 +231,7 @@ NvResult nvhost_ctrl::FreeEvent(u32 slot) {
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl::IocCtrlEventRegister(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl::IocCtrlEventRegister(std::span<const u8> input, std::span<u8> output) {
     IocCtrlEventRegisterParams params{};
     std::memcpy(&params, input.data(), sizeof(params));
     const u32 event_id = params.user_event_id;
@@ -252,7 +252,7 @@ NvResult nvhost_ctrl::IocCtrlEventRegister(std::span<const u8> input, std::vecto
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl::IocCtrlEventUnregister(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl::IocCtrlEventUnregister(std::span<const u8> input, std::span<u8> output) {
     IocCtrlEventUnregisterParams params{};
     std::memcpy(&params, input.data(), sizeof(params));
     const u32 event_id = params.user_event_id & 0x00FF;
@@ -262,8 +262,7 @@ NvResult nvhost_ctrl::IocCtrlEventUnregister(std::span<const u8> input, std::vec
     return FreeEvent(event_id);
 }
 
-NvResult nvhost_ctrl::IocCtrlEventUnregisterBatch(std::span<const u8> input,
-                                                  std::vector<u8>& output) {
+NvResult nvhost_ctrl::IocCtrlEventUnregisterBatch(std::span<const u8> input, std::span<u8> output) {
     IocCtrlEventUnregisterBatchParams params{};
     std::memcpy(&params, input.data(), sizeof(params));
     u64 event_mask = params.user_events;
@@ -281,7 +280,7 @@ NvResult nvhost_ctrl::IocCtrlEventUnregisterBatch(std::span<const u8> input,
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl::IocCtrlClearEventWait(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl::IocCtrlClearEventWait(std::span<const u8> input, std::span<u8> output) {
     IocCtrlEventClearParams params{};
     std::memcpy(&params, input.data(), sizeof(params));
 
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_ctrl.h b/src/core/hle/service/nvdrv/devices/nvhost_ctrl.h
index dd2e7888a..2efed4862 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_ctrl.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_ctrl.h
@@ -26,11 +26,11 @@ public:
     ~nvhost_ctrl() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
@@ -186,13 +186,12 @@ private:
     static_assert(sizeof(IocCtrlEventUnregisterBatchParams) == 8,
                   "IocCtrlEventKill is incorrect size");
 
-    NvResult NvOsGetConfigU32(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocCtrlEventWait(std::span<const u8> input, std::vector<u8>& output,
-                              bool is_allocation);
-    NvResult IocCtrlEventRegister(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocCtrlEventUnregister(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocCtrlEventUnregisterBatch(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocCtrlClearEventWait(std::span<const u8> input, std::vector<u8>& output);
+    NvResult NvOsGetConfigU32(std::span<const u8> input, std::span<u8> output);
+    NvResult IocCtrlEventWait(std::span<const u8> input, std::span<u8> output, bool is_allocation);
+    NvResult IocCtrlEventRegister(std::span<const u8> input, std::span<u8> output);
+    NvResult IocCtrlEventUnregister(std::span<const u8> input, std::span<u8> output);
+    NvResult IocCtrlEventUnregisterBatch(std::span<const u8> input, std::span<u8> output);
+    NvResult IocCtrlClearEventWait(std::span<const u8> input, std::span<u8> output);
 
     NvResult FreeEvent(u32 slot);
 
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.cpp b/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.cpp
index be3c083db..6081d92e9 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.cpp
@@ -22,7 +22,7 @@ nvhost_ctrl_gpu::~nvhost_ctrl_gpu() {
 }
 
 NvResult nvhost_ctrl_gpu::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                                 std::vector<u8>& output) {
+                                 std::span<u8> output) {
     switch (command.group) {
     case 'G':
         switch (command.cmd) {
@@ -54,13 +54,13 @@ NvResult nvhost_ctrl_gpu::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8>
 }
 
 NvResult nvhost_ctrl_gpu::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                                 std::span<const u8> inline_input, std::vector<u8>& output) {
+                                 std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvhost_ctrl_gpu::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                                 std::vector<u8>& output, std::vector<u8>& inline_output) {
+                                 std::span<u8> output, std::span<u8> inline_output) {
     switch (command.group) {
     case 'G':
         switch (command.cmd) {
@@ -82,7 +82,7 @@ NvResult nvhost_ctrl_gpu::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8>
 void nvhost_ctrl_gpu::OnOpen(DeviceFD fd) {}
 void nvhost_ctrl_gpu::OnClose(DeviceFD fd) {}
 
-NvResult nvhost_ctrl_gpu::GetCharacteristics(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::GetCharacteristics(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
     IoctlCharacteristics params{};
     std::memcpy(&params, input.data(), input.size());
@@ -127,8 +127,8 @@ NvResult nvhost_ctrl_gpu::GetCharacteristics(std::span<const u8> input, std::vec
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::GetCharacteristics(std::span<const u8> input, std::vector<u8>& output,
-                                             std::vector<u8>& inline_output) {
+NvResult nvhost_ctrl_gpu::GetCharacteristics(std::span<const u8> input, std::span<u8> output,
+                                             std::span<u8> inline_output) {
     LOG_DEBUG(Service_NVDRV, "called");
     IoctlCharacteristics params{};
     std::memcpy(&params, input.data(), input.size());
@@ -175,7 +175,7 @@ NvResult nvhost_ctrl_gpu::GetCharacteristics(std::span<const u8> input, std::vec
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::GetTPCMasks(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::GetTPCMasks(std::span<const u8> input, std::span<u8> output) {
     IoctlGpuGetTpcMasksArgs params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "called, mask_buffer_size=0x{:X}", params.mask_buffer_size);
@@ -186,8 +186,8 @@ NvResult nvhost_ctrl_gpu::GetTPCMasks(std::span<const u8> input, std::vector<u8>
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::GetTPCMasks(std::span<const u8> input, std::vector<u8>& output,
-                                      std::vector<u8>& inline_output) {
+NvResult nvhost_ctrl_gpu::GetTPCMasks(std::span<const u8> input, std::span<u8> output,
+                                      std::span<u8> inline_output) {
     IoctlGpuGetTpcMasksArgs params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "called, mask_buffer_size=0x{:X}", params.mask_buffer_size);
@@ -199,7 +199,7 @@ NvResult nvhost_ctrl_gpu::GetTPCMasks(std::span<const u8> input, std::vector<u8>
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::GetActiveSlotMask(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::GetActiveSlotMask(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
 
     IoctlActiveSlotMask params{};
@@ -212,7 +212,7 @@ NvResult nvhost_ctrl_gpu::GetActiveSlotMask(std::span<const u8> input, std::vect
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::ZCullGetCtxSize(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::ZCullGetCtxSize(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
 
     IoctlZcullGetCtxSize params{};
@@ -224,7 +224,7 @@ NvResult nvhost_ctrl_gpu::ZCullGetCtxSize(std::span<const u8> input, std::vector
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::ZCullGetInfo(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::ZCullGetInfo(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
 
     IoctlNvgpuGpuZcullGetInfoArgs params{};
@@ -247,7 +247,7 @@ NvResult nvhost_ctrl_gpu::ZCullGetInfo(std::span<const u8> input, std::vector<u8
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::ZBCSetTable(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::ZBCSetTable(std::span<const u8> input, std::span<u8> output) {
     LOG_WARNING(Service_NVDRV, "(STUBBED) called");
 
     IoctlZbcSetTable params{};
@@ -263,7 +263,7 @@ NvResult nvhost_ctrl_gpu::ZBCSetTable(std::span<const u8> input, std::vector<u8>
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::ZBCQueryTable(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::ZBCQueryTable(std::span<const u8> input, std::span<u8> output) {
     LOG_WARNING(Service_NVDRV, "(STUBBED) called");
 
     IoctlZbcQueryTable params{};
@@ -273,7 +273,7 @@ NvResult nvhost_ctrl_gpu::ZBCQueryTable(std::span<const u8> input, std::vector<u
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::FlushL2(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::FlushL2(std::span<const u8> input, std::span<u8> output) {
     LOG_WARNING(Service_NVDRV, "(STUBBED) called");
 
     IoctlFlushL2 params{};
@@ -283,7 +283,7 @@ NvResult nvhost_ctrl_gpu::FlushL2(std::span<const u8> input, std::vector<u8>& ou
     return NvResult::Success;
 }
 
-NvResult nvhost_ctrl_gpu::GetGpuTime(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_ctrl_gpu::GetGpuTime(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
 
     IoctlGetGpuTime params{};
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.h b/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.h
index b9333d9d3..97995551c 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_ctrl_gpu.h
@@ -22,11 +22,11 @@ public:
     ~nvhost_ctrl_gpu() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
@@ -151,21 +151,21 @@ private:
     };
     static_assert(sizeof(IoctlGetGpuTime) == 0x10, "IoctlGetGpuTime is incorrect size");
 
-    NvResult GetCharacteristics(std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetCharacteristics(std::span<const u8> input, std::vector<u8>& output,
-                                std::vector<u8>& inline_output);
-
-    NvResult GetTPCMasks(std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetTPCMasks(std::span<const u8> input, std::vector<u8>& output,
-                         std::vector<u8>& inline_output);
-
-    NvResult GetActiveSlotMask(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ZCullGetCtxSize(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ZCullGetInfo(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ZBCSetTable(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ZBCQueryTable(std::span<const u8> input, std::vector<u8>& output);
-    NvResult FlushL2(std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetGpuTime(std::span<const u8> input, std::vector<u8>& output);
+    NvResult GetCharacteristics(std::span<const u8> input, std::span<u8> output);
+    NvResult GetCharacteristics(std::span<const u8> input, std::span<u8> output,
+                                std::span<u8> inline_output);
+
+    NvResult GetTPCMasks(std::span<const u8> input, std::span<u8> output);
+    NvResult GetTPCMasks(std::span<const u8> input, std::span<u8> output,
+                         std::span<u8> inline_output);
+
+    NvResult GetActiveSlotMask(std::span<const u8> input, std::span<u8> output);
+    NvResult ZCullGetCtxSize(std::span<const u8> input, std::span<u8> output);
+    NvResult ZCullGetInfo(std::span<const u8> input, std::span<u8> output);
+    NvResult ZBCSetTable(std::span<const u8> input, std::span<u8> output);
+    NvResult ZBCQueryTable(std::span<const u8> input, std::span<u8> output);
+    NvResult FlushL2(std::span<const u8> input, std::span<u8> output);
+    NvResult GetGpuTime(std::span<const u8> input, std::span<u8> output);
 
     EventInterface& events_interface;
 
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_gpu.cpp b/src/core/hle/service/nvdrv/devices/nvhost_gpu.cpp
index 453a965dc..46a25fcab 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_gpu.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_gpu.cpp
@@ -47,7 +47,7 @@ nvhost_gpu::~nvhost_gpu() {
 }
 
 NvResult nvhost_gpu::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::vector<u8>& output) {
+                            std::span<u8> output) {
     switch (command.group) {
     case 0x0:
         switch (command.cmd) {
@@ -99,7 +99,7 @@ NvResult nvhost_gpu::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> inpu
 };
 
 NvResult nvhost_gpu::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::span<const u8> inline_input, std::vector<u8>& output) {
+                            std::span<const u8> inline_input, std::span<u8> output) {
     switch (command.group) {
     case 'H':
         switch (command.cmd) {
@@ -113,7 +113,7 @@ NvResult nvhost_gpu::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> inpu
 }
 
 NvResult nvhost_gpu::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::vector<u8>& output, std::vector<u8>& inline_output) {
+                            std::span<u8> output, std::span<u8> inline_output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
@@ -121,7 +121,7 @@ NvResult nvhost_gpu::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> inpu
 void nvhost_gpu::OnOpen(DeviceFD fd) {}
 void nvhost_gpu::OnClose(DeviceFD fd) {}
 
-NvResult nvhost_gpu::SetNVMAPfd(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::SetNVMAPfd(std::span<const u8> input, std::span<u8> output) {
     IoctlSetNvmapFD params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "called, fd={}", params.nvmap_fd);
@@ -130,7 +130,7 @@ NvResult nvhost_gpu::SetNVMAPfd(std::span<const u8> input, std::vector<u8>& outp
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::SetClientData(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::SetClientData(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
 
     IoctlClientData params{};
@@ -139,7 +139,7 @@ NvResult nvhost_gpu::SetClientData(std::span<const u8> input, std::vector<u8>& o
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::GetClientData(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::GetClientData(std::span<const u8> input, std::span<u8> output) {
     LOG_DEBUG(Service_NVDRV, "called");
 
     IoctlClientData params{};
@@ -149,7 +149,7 @@ NvResult nvhost_gpu::GetClientData(std::span<const u8> input, std::vector<u8>& o
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::ZCullBind(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::ZCullBind(std::span<const u8> input, std::span<u8> output) {
     std::memcpy(&zcull_params, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "called, gpu_va={:X}, mode={:X}", zcull_params.gpu_va,
               zcull_params.mode);
@@ -158,7 +158,7 @@ NvResult nvhost_gpu::ZCullBind(std::span<const u8> input, std::vector<u8>& outpu
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::SetErrorNotifier(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::SetErrorNotifier(std::span<const u8> input, std::span<u8> output) {
     IoctlSetErrorNotifier params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_WARNING(Service_NVDRV, "(STUBBED) called, offset={:X}, size={:X}, mem={:X}", params.offset,
@@ -168,14 +168,14 @@ NvResult nvhost_gpu::SetErrorNotifier(std::span<const u8> input, std::vector<u8>
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::SetChannelPriority(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::SetChannelPriority(std::span<const u8> input, std::span<u8> output) {
     std::memcpy(&channel_priority, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "(STUBBED) called, priority={:X}", channel_priority);
 
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::AllocGPFIFOEx2(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::AllocGPFIFOEx2(std::span<const u8> input, std::span<u8> output) {
     IoctlAllocGpfifoEx2 params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_WARNING(Service_NVDRV,
@@ -197,7 +197,7 @@ NvResult nvhost_gpu::AllocGPFIFOEx2(std::span<const u8> input, std::vector<u8>&
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::AllocateObjectContext(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::AllocateObjectContext(std::span<const u8> input, std::span<u8> output) {
     IoctlAllocObjCtx params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_WARNING(Service_NVDRV, "(STUBBED) called, class_num={:X}, flags={:X}", params.class_num,
@@ -208,7 +208,8 @@ NvResult nvhost_gpu::AllocateObjectContext(std::span<const u8> input, std::vecto
     return NvResult::Success;
 }
 
-static std::vector<Tegra::CommandHeader> BuildWaitCommandList(NvFence fence) {
+static boost::container::small_vector<Tegra::CommandHeader, 512> BuildWaitCommandList(
+    NvFence fence) {
     return {
         Tegra::BuildCommandHeader(Tegra::BufferMethods::SyncpointPayload, 1,
                                   Tegra::SubmissionMode::Increasing),
@@ -219,35 +220,35 @@ static std::vector<Tegra::CommandHeader> BuildWaitCommandList(NvFence fence) {
     };
 }
 
-static std::vector<Tegra::CommandHeader> BuildIncrementCommandList(NvFence fence) {
-    std::vector<Tegra::CommandHeader> result{
+static boost::container::small_vector<Tegra::CommandHeader, 512> BuildIncrementCommandList(
+    NvFence fence) {
+    boost::container::small_vector<Tegra::CommandHeader, 512> result{
         Tegra::BuildCommandHeader(Tegra::BufferMethods::SyncpointPayload, 1,
                                   Tegra::SubmissionMode::Increasing),
         {}};
 
     for (u32 count = 0; count < 2; ++count) {
-        result.emplace_back(Tegra::BuildCommandHeader(Tegra::BufferMethods::SyncpointOperation, 1,
-                                                      Tegra::SubmissionMode::Increasing));
-        result.emplace_back(
+        result.push_back(Tegra::BuildCommandHeader(Tegra::BufferMethods::SyncpointOperation, 1,
+                                                   Tegra::SubmissionMode::Increasing));
+        result.push_back(
             BuildFenceAction(Tegra::Engines::Puller::FenceOperation::Increment, fence.id));
     }
 
     return result;
 }
 
-static std::vector<Tegra::CommandHeader> BuildIncrementWithWfiCommandList(NvFence fence) {
-    std::vector<Tegra::CommandHeader> result{
+static boost::container::small_vector<Tegra::CommandHeader, 512> BuildIncrementWithWfiCommandList(
+    NvFence fence) {
+    boost::container::small_vector<Tegra::CommandHeader, 512> result{
         Tegra::BuildCommandHeader(Tegra::BufferMethods::WaitForIdle, 1,
                                   Tegra::SubmissionMode::Increasing),
         {}};
-    const std::vector<Tegra::CommandHeader> increment{BuildIncrementCommandList(fence)};
-
-    result.insert(result.end(), increment.begin(), increment.end());
-
+    auto increment_list{BuildIncrementCommandList(fence)};
+    result.insert(result.end(), increment_list.begin(), increment_list.end());
     return result;
 }
 
-NvResult nvhost_gpu::SubmitGPFIFOImpl(IoctlSubmitGpfifo& params, std::vector<u8>& output,
+NvResult nvhost_gpu::SubmitGPFIFOImpl(IoctlSubmitGpfifo& params, std::span<u8> output,
                                       Tegra::CommandList&& entries) {
     LOG_TRACE(Service_NVDRV, "called, gpfifo={:X}, num_entries={:X}, flags={:X}", params.address,
               params.num_entries, params.flags.raw);
@@ -293,7 +294,7 @@ NvResult nvhost_gpu::SubmitGPFIFOImpl(IoctlSubmitGpfifo& params, std::vector<u8>
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::SubmitGPFIFOBase(std::span<const u8> input, std::vector<u8>& output,
+NvResult nvhost_gpu::SubmitGPFIFOBase(std::span<const u8> input, std::span<u8> output,
                                       bool kickoff) {
     if (input.size() < sizeof(IoctlSubmitGpfifo)) {
         UNIMPLEMENTED();
@@ -315,7 +316,7 @@ NvResult nvhost_gpu::SubmitGPFIFOBase(std::span<const u8> input, std::vector<u8>
 }
 
 NvResult nvhost_gpu::SubmitGPFIFOBase(std::span<const u8> input, std::span<const u8> input_inline,
-                                      std::vector<u8>& output) {
+                                      std::span<u8> output) {
     if (input.size() < sizeof(IoctlSubmitGpfifo)) {
         UNIMPLEMENTED();
         return NvResult::InvalidSize;
@@ -327,7 +328,7 @@ NvResult nvhost_gpu::SubmitGPFIFOBase(std::span<const u8> input, std::span<const
     return SubmitGPFIFOImpl(params, output, std::move(entries));
 }
 
-NvResult nvhost_gpu::GetWaitbase(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::GetWaitbase(std::span<const u8> input, std::span<u8> output) {
     IoctlGetWaitbase params{};
     std::memcpy(&params, input.data(), sizeof(IoctlGetWaitbase));
     LOG_INFO(Service_NVDRV, "called, unknown=0x{:X}", params.unknown);
@@ -337,7 +338,7 @@ NvResult nvhost_gpu::GetWaitbase(std::span<const u8> input, std::vector<u8>& out
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::ChannelSetTimeout(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::ChannelSetTimeout(std::span<const u8> input, std::span<u8> output) {
     IoctlChannelSetTimeout params{};
     std::memcpy(&params, input.data(), sizeof(IoctlChannelSetTimeout));
     LOG_INFO(Service_NVDRV, "called, timeout=0x{:X}", params.timeout);
@@ -345,7 +346,7 @@ NvResult nvhost_gpu::ChannelSetTimeout(std::span<const u8> input, std::vector<u8
     return NvResult::Success;
 }
 
-NvResult nvhost_gpu::ChannelSetTimeslice(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_gpu::ChannelSetTimeslice(std::span<const u8> input, std::span<u8> output) {
     IoctlSetTimeslice params{};
     std::memcpy(&params, input.data(), sizeof(IoctlSetTimeslice));
     LOG_INFO(Service_NVDRV, "called, timeslice=0x{:X}", params.timeslice);
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_gpu.h b/src/core/hle/service/nvdrv/devices/nvhost_gpu.h
index 3ca58202d..529c20526 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_gpu.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_gpu.h
@@ -41,11 +41,11 @@ public:
     ~nvhost_gpu() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
@@ -186,23 +186,23 @@ private:
     u32_le channel_priority{};
     u32_le channel_timeslice{};
 
-    NvResult SetNVMAPfd(std::span<const u8> input, std::vector<u8>& output);
-    NvResult SetClientData(std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetClientData(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ZCullBind(std::span<const u8> input, std::vector<u8>& output);
-    NvResult SetErrorNotifier(std::span<const u8> input, std::vector<u8>& output);
-    NvResult SetChannelPriority(std::span<const u8> input, std::vector<u8>& output);
-    NvResult AllocGPFIFOEx2(std::span<const u8> input, std::vector<u8>& output);
-    NvResult AllocateObjectContext(std::span<const u8> input, std::vector<u8>& output);
-    NvResult SubmitGPFIFOImpl(IoctlSubmitGpfifo& params, std::vector<u8>& output,
+    NvResult SetNVMAPfd(std::span<const u8> input, std::span<u8> output);
+    NvResult SetClientData(std::span<const u8> input, std::span<u8> output);
+    NvResult GetClientData(std::span<const u8> input, std::span<u8> output);
+    NvResult ZCullBind(std::span<const u8> input, std::span<u8> output);
+    NvResult SetErrorNotifier(std::span<const u8> input, std::span<u8> output);
+    NvResult SetChannelPriority(std::span<const u8> input, std::span<u8> output);
+    NvResult AllocGPFIFOEx2(std::span<const u8> input, std::span<u8> output);
+    NvResult AllocateObjectContext(std::span<const u8> input, std::span<u8> output);
+    NvResult SubmitGPFIFOImpl(IoctlSubmitGpfifo& params, std::span<u8> output,
                               Tegra::CommandList&& entries);
-    NvResult SubmitGPFIFOBase(std::span<const u8> input, std::vector<u8>& output,
+    NvResult SubmitGPFIFOBase(std::span<const u8> input, std::span<u8> output,
                               bool kickoff = false);
     NvResult SubmitGPFIFOBase(std::span<const u8> input, std::span<const u8> input_inline,
-                              std::vector<u8>& output);
-    NvResult GetWaitbase(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ChannelSetTimeout(std::span<const u8> input, std::vector<u8>& output);
-    NvResult ChannelSetTimeslice(std::span<const u8> input, std::vector<u8>& output);
+                              std::span<u8> output);
+    NvResult GetWaitbase(std::span<const u8> input, std::span<u8> output);
+    NvResult ChannelSetTimeout(std::span<const u8> input, std::span<u8> output);
+    NvResult ChannelSetTimeslice(std::span<const u8> input, std::span<u8> output);
 
     EventInterface& events_interface;
     NvCore::Container& core;
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_nvdec.cpp b/src/core/hle/service/nvdrv/devices/nvhost_nvdec.cpp
index dc45169ad..a174442a6 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_nvdec.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_nvdec.cpp
@@ -16,7 +16,7 @@ nvhost_nvdec::nvhost_nvdec(Core::System& system_, NvCore::Container& core_)
 nvhost_nvdec::~nvhost_nvdec() = default;
 
 NvResult nvhost_nvdec::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::vector<u8>& output) {
+                              std::span<u8> output) {
     switch (command.group) {
     case 0x0:
         switch (command.cmd) {
@@ -56,13 +56,13 @@ NvResult nvhost_nvdec::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> in
 }
 
 NvResult nvhost_nvdec::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::span<const u8> inline_input, std::vector<u8>& output) {
+                              std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvhost_nvdec::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::vector<u8>& output, std::vector<u8>& inline_output) {
+                              std::span<u8> output, std::span<u8> inline_output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_nvdec.h b/src/core/hle/service/nvdrv/devices/nvhost_nvdec.h
index 0d615bbcb..ad2233c49 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_nvdec.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_nvdec.h
@@ -14,11 +14,11 @@ public:
     ~nvhost_nvdec() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.cpp b/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.cpp
index 1ab51f10b..61649aa4a 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.cpp
@@ -36,7 +36,7 @@ std::size_t SliceVectors(std::span<const u8> input, std::vector<T>& dst, std::si
 // Writes the data in src to an offset into the dst vector. The offset is specified in bytes
 // Returns the number of bytes written into dst.
 template <typename T>
-std::size_t WriteVectors(std::vector<u8>& dst, const std::vector<T>& src, std::size_t offset) {
+std::size_t WriteVectors(std::span<u8> dst, const std::vector<T>& src, std::size_t offset) {
     if (src.empty()) {
         return 0;
     }
@@ -72,8 +72,7 @@ NvResult nvhost_nvdec_common::SetNVMAPfd(std::span<const u8> input) {
     return NvResult::Success;
 }
 
-NvResult nvhost_nvdec_common::Submit(DeviceFD fd, std::span<const u8> input,
-                                     std::vector<u8>& output) {
+NvResult nvhost_nvdec_common::Submit(DeviceFD fd, std::span<const u8> input, std::span<u8> output) {
     IoctlSubmit params{};
     std::memcpy(&params, input.data(), sizeof(IoctlSubmit));
     LOG_DEBUG(Service_NVDRV, "called NVDEC Submit, cmd_buffer_count={}", params.cmd_buffer_count);
@@ -121,7 +120,7 @@ NvResult nvhost_nvdec_common::Submit(DeviceFD fd, std::span<const u8> input,
     return NvResult::Success;
 }
 
-NvResult nvhost_nvdec_common::GetSyncpoint(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_nvdec_common::GetSyncpoint(std::span<const u8> input, std::span<u8> output) {
     IoctlGetSyncpoint params{};
     std::memcpy(&params, input.data(), sizeof(IoctlGetSyncpoint));
     LOG_DEBUG(Service_NVDRV, "called GetSyncpoint, id={}", params.param);
@@ -133,7 +132,7 @@ NvResult nvhost_nvdec_common::GetSyncpoint(std::span<const u8> input, std::vecto
     return NvResult::Success;
 }
 
-NvResult nvhost_nvdec_common::GetWaitbase(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_nvdec_common::GetWaitbase(std::span<const u8> input, std::span<u8> output) {
     IoctlGetWaitbase params{};
     LOG_CRITICAL(Service_NVDRV, "called WAITBASE");
     std::memcpy(&params, input.data(), sizeof(IoctlGetWaitbase));
@@ -142,7 +141,7 @@ NvResult nvhost_nvdec_common::GetWaitbase(std::span<const u8> input, std::vector
     return NvResult::Success;
 }
 
-NvResult nvhost_nvdec_common::MapBuffer(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_nvdec_common::MapBuffer(std::span<const u8> input, std::span<u8> output) {
     IoctlMapBuffer params{};
     std::memcpy(&params, input.data(), sizeof(IoctlMapBuffer));
     std::vector<MapBufferEntry> cmd_buffer_handles(params.num_entries);
@@ -159,7 +158,7 @@ NvResult nvhost_nvdec_common::MapBuffer(std::span<const u8> input, std::vector<u
     return NvResult::Success;
 }
 
-NvResult nvhost_nvdec_common::UnmapBuffer(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_nvdec_common::UnmapBuffer(std::span<const u8> input, std::span<u8> output) {
     IoctlMapBuffer params{};
     std::memcpy(&params, input.data(), sizeof(IoctlMapBuffer));
     std::vector<MapBufferEntry> cmd_buffer_handles(params.num_entries);
@@ -173,7 +172,7 @@ NvResult nvhost_nvdec_common::UnmapBuffer(std::span<const u8> input, std::vector
     return NvResult::Success;
 }
 
-NvResult nvhost_nvdec_common::SetSubmitTimeout(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_nvdec_common::SetSubmitTimeout(std::span<const u8> input, std::span<u8> output) {
     std::memcpy(&submit_timeout, input.data(), input.size());
     LOG_WARNING(Service_NVDRV, "(STUBBED) called");
     return NvResult::Success;
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.h b/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.h
index 5af26a26f..9bb573bfe 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_nvdec_common.h
@@ -108,12 +108,12 @@ protected:
 
     /// Ioctl command implementations
     NvResult SetNVMAPfd(std::span<const u8> input);
-    NvResult Submit(DeviceFD fd, std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetSyncpoint(std::span<const u8> input, std::vector<u8>& output);
-    NvResult GetWaitbase(std::span<const u8> input, std::vector<u8>& output);
-    NvResult MapBuffer(std::span<const u8> input, std::vector<u8>& output);
-    NvResult UnmapBuffer(std::span<const u8> input, std::vector<u8>& output);
-    NvResult SetSubmitTimeout(std::span<const u8> input, std::vector<u8>& output);
+    NvResult Submit(DeviceFD fd, std::span<const u8> input, std::span<u8> output);
+    NvResult GetSyncpoint(std::span<const u8> input, std::span<u8> output);
+    NvResult GetWaitbase(std::span<const u8> input, std::span<u8> output);
+    NvResult MapBuffer(std::span<const u8> input, std::span<u8> output);
+    NvResult UnmapBuffer(std::span<const u8> input, std::span<u8> output);
+    NvResult SetSubmitTimeout(std::span<const u8> input, std::span<u8> output);
 
     Kernel::KEvent* QueryEvent(u32 event_id) override;
 
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.cpp b/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.cpp
index 39f30e7c8..a05c8cdae 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.cpp
@@ -13,7 +13,7 @@ nvhost_nvjpg::nvhost_nvjpg(Core::System& system_) : nvdevice{system_} {}
 nvhost_nvjpg::~nvhost_nvjpg() = default;
 
 NvResult nvhost_nvjpg::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::vector<u8>& output) {
+                              std::span<u8> output) {
     switch (command.group) {
     case 'H':
         switch (command.cmd) {
@@ -32,13 +32,13 @@ NvResult nvhost_nvjpg::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> in
 }
 
 NvResult nvhost_nvjpg::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::span<const u8> inline_input, std::vector<u8>& output) {
+                              std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvhost_nvjpg::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                              std::vector<u8>& output, std::vector<u8>& inline_output) {
+                              std::span<u8> output, std::span<u8> inline_output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
@@ -46,7 +46,7 @@ NvResult nvhost_nvjpg::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> in
 void nvhost_nvjpg::OnOpen(DeviceFD fd) {}
 void nvhost_nvjpg::OnClose(DeviceFD fd) {}
 
-NvResult nvhost_nvjpg::SetNVMAPfd(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvhost_nvjpg::SetNVMAPfd(std::span<const u8> input, std::span<u8> output) {
     IoctlSetNvmapFD params{};
     std::memcpy(&params, input.data(), input.size());
     LOG_DEBUG(Service_NVDRV, "called, fd={}", params.nvmap_fd);
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.h b/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.h
index 41b57e872..5623e0d47 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_nvjpg.h
@@ -16,11 +16,11 @@ public:
     ~nvhost_nvjpg() override;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
@@ -33,7 +33,7 @@ private:
 
     s32_le nvmap_fd{};
 
-    NvResult SetNVMAPfd(std::span<const u8> input, std::vector<u8>& output);
+    NvResult SetNVMAPfd(std::span<const u8> input, std::span<u8> output);
 };
 
 } // namespace Service::Nvidia::Devices
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_vic.cpp b/src/core/hle/service/nvdrv/devices/nvhost_vic.cpp
index b0ea402a7..c0b8684c3 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_vic.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvhost_vic.cpp
@@ -16,7 +16,7 @@ nvhost_vic::nvhost_vic(Core::System& system_, NvCore::Container& core_)
 nvhost_vic::~nvhost_vic() = default;
 
 NvResult nvhost_vic::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::vector<u8>& output) {
+                            std::span<u8> output) {
     switch (command.group) {
     case 0x0:
         switch (command.cmd) {
@@ -56,13 +56,13 @@ NvResult nvhost_vic::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> inpu
 }
 
 NvResult nvhost_vic::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::span<const u8> inline_input, std::vector<u8>& output) {
+                            std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
 NvResult nvhost_vic::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                            std::vector<u8>& output, std::vector<u8>& inline_output) {
+                            std::span<u8> output, std::span<u8> inline_output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
diff --git a/src/core/hle/service/nvdrv/devices/nvhost_vic.h b/src/core/hle/service/nvdrv/devices/nvhost_vic.h
index b5e350a83..cadbcb0a5 100644
--- a/src/core/hle/service/nvdrv/devices/nvhost_vic.h
+++ b/src/core/hle/service/nvdrv/devices/nvhost_vic.h
@@ -13,11 +13,11 @@ public:
     ~nvhost_vic();
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
diff --git a/src/core/hle/service/nvdrv/devices/nvmap.cpp b/src/core/hle/service/nvdrv/devices/nvmap.cpp
index 07417f045..e7f7e273b 100644
--- a/src/core/hle/service/nvdrv/devices/nvmap.cpp
+++ b/src/core/hle/service/nvdrv/devices/nvmap.cpp
@@ -26,7 +26,7 @@ nvmap::nvmap(Core::System& system_, NvCore::Container& container_)
 nvmap::~nvmap() = default;
 
 NvResult nvmap::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                       std::vector<u8>& output) {
+                       std::span<u8> output) {
     switch (command.group) {
     case 0x1:
         switch (command.cmd) {
@@ -55,13 +55,13 @@ NvResult nvmap::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
 }
 
 NvResult nvmap::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                       std::span<const u8> inline_input, std::vector<u8>& output) {
+                       std::span<const u8> inline_input, std::span<u8> output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
 
-NvResult nvmap::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                       std::vector<u8>& output, std::vector<u8>& inline_output) {
+NvResult nvmap::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                       std::span<u8> inline_output) {
     UNIMPLEMENTED_MSG("Unimplemented ioctl={:08X}", command.raw);
     return NvResult::NotImplemented;
 }
@@ -69,7 +69,7 @@ NvResult nvmap::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
 void nvmap::OnOpen(DeviceFD fd) {}
 void nvmap::OnClose(DeviceFD fd) {}
 
-NvResult nvmap::IocCreate(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvmap::IocCreate(std::span<const u8> input, std::span<u8> output) {
     IocCreateParams params;
     std::memcpy(&params, input.data(), sizeof(params));
     LOG_DEBUG(Service_NVDRV, "called, size=0x{:08X}", params.size);
@@ -89,7 +89,7 @@ NvResult nvmap::IocCreate(std::span<const u8> input, std::vector<u8>& output) {
     return NvResult::Success;
 }
 
-NvResult nvmap::IocAlloc(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvmap::IocAlloc(std::span<const u8> input, std::span<u8> output) {
     IocAllocParams params;
     std::memcpy(&params, input.data(), sizeof(params));
     LOG_DEBUG(Service_NVDRV, "called, addr={:X}", params.address);
@@ -137,7 +137,7 @@ NvResult nvmap::IocAlloc(std::span<const u8> input, std::vector<u8>& output) {
     return result;
 }
 
-NvResult nvmap::IocGetId(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvmap::IocGetId(std::span<const u8> input, std::span<u8> output) {
     IocGetIdParams params;
     std::memcpy(&params, input.data(), sizeof(params));
 
@@ -161,7 +161,7 @@ NvResult nvmap::IocGetId(std::span<const u8> input, std::vector<u8>& output) {
     return NvResult::Success;
 }
 
-NvResult nvmap::IocFromId(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvmap::IocFromId(std::span<const u8> input, std::span<u8> output) {
     IocFromIdParams params;
     std::memcpy(&params, input.data(), sizeof(params));
 
@@ -192,7 +192,7 @@ NvResult nvmap::IocFromId(std::span<const u8> input, std::vector<u8>& output) {
     return NvResult::Success;
 }
 
-NvResult nvmap::IocParam(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvmap::IocParam(std::span<const u8> input, std::span<u8> output) {
     enum class ParamTypes { Size = 1, Alignment = 2, Base = 3, Heap = 4, Kind = 5, Compr = 6 };
 
     IocParamParams params;
@@ -241,7 +241,7 @@ NvResult nvmap::IocParam(std::span<const u8> input, std::vector<u8>& output) {
     return NvResult::Success;
 }
 
-NvResult nvmap::IocFree(std::span<const u8> input, std::vector<u8>& output) {
+NvResult nvmap::IocFree(std::span<const u8> input, std::span<u8> output) {
     IocFreeParams params;
     std::memcpy(&params, input.data(), sizeof(params));
 
diff --git a/src/core/hle/service/nvdrv/devices/nvmap.h b/src/core/hle/service/nvdrv/devices/nvmap.h
index 82bd3b118..40c65b430 100644
--- a/src/core/hle/service/nvdrv/devices/nvmap.h
+++ b/src/core/hle/service/nvdrv/devices/nvmap.h
@@ -27,11 +27,11 @@ public:
     nvmap& operator=(const nvmap&) = delete;
 
     NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::vector<u8>& output) override;
+                    std::span<u8> output) override;
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output) override;
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output) override;
+                    std::span<const u8> inline_input, std::span<u8> output) override;
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output) override;
 
     void OnOpen(DeviceFD fd) override;
     void OnClose(DeviceFD fd) override;
@@ -106,12 +106,12 @@ private:
     };
     static_assert(sizeof(IocGetIdParams) == 8, "IocGetIdParams has wrong size");
 
-    NvResult IocCreate(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocAlloc(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocGetId(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocFromId(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocParam(std::span<const u8> input, std::vector<u8>& output);
-    NvResult IocFree(std::span<const u8> input, std::vector<u8>& output);
+    NvResult IocCreate(std::span<const u8> input, std::span<u8> output);
+    NvResult IocAlloc(std::span<const u8> input, std::span<u8> output);
+    NvResult IocGetId(std::span<const u8> input, std::span<u8> output);
+    NvResult IocFromId(std::span<const u8> input, std::span<u8> output);
+    NvResult IocParam(std::span<const u8> input, std::span<u8> output);
+    NvResult IocFree(std::span<const u8> input, std::span<u8> output);
 
     NvCore::Container& container;
     NvCore::NvMap& file;
diff --git a/src/core/hle/service/nvdrv/nvdrv.cpp b/src/core/hle/service/nvdrv/nvdrv.cpp
index 3d774eec4..9e46ee8dd 100644
--- a/src/core/hle/service/nvdrv/nvdrv.cpp
+++ b/src/core/hle/service/nvdrv/nvdrv.cpp
@@ -130,7 +130,7 @@ DeviceFD Module::Open(const std::string& device_name) {
 }
 
 NvResult Module::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                        std::vector<u8>& output) {
+                        std::span<u8> output) {
     if (fd < 0) {
         LOG_ERROR(Service_NVDRV, "Invalid DeviceFD={}!", fd);
         return NvResult::InvalidState;
@@ -147,7 +147,7 @@ NvResult Module::Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input,
 }
 
 NvResult Module::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                        std::span<const u8> inline_input, std::vector<u8>& output) {
+                        std::span<const u8> inline_input, std::span<u8> output) {
     if (fd < 0) {
         LOG_ERROR(Service_NVDRV, "Invalid DeviceFD={}!", fd);
         return NvResult::InvalidState;
@@ -163,8 +163,8 @@ NvResult Module::Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
     return itr->second->Ioctl2(fd, command, input, inline_input, output);
 }
 
-NvResult Module::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                        std::vector<u8>& output, std::vector<u8>& inline_output) {
+NvResult Module::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                        std::span<u8> inline_output) {
     if (fd < 0) {
         LOG_ERROR(Service_NVDRV, "Invalid DeviceFD={}!", fd);
         return NvResult::InvalidState;
diff --git a/src/core/hle/service/nvdrv/nvdrv.h b/src/core/hle/service/nvdrv/nvdrv.h
index 668be742b..d8622b3ca 100644
--- a/src/core/hle/service/nvdrv/nvdrv.h
+++ b/src/core/hle/service/nvdrv/nvdrv.h
@@ -80,13 +80,13 @@ public:
     DeviceFD Open(const std::string& device_name);
 
     /// Sends an ioctl command to the specified file descriptor.
-    NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output);
+    NvResult Ioctl1(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output);
 
     NvResult Ioctl2(DeviceFD fd, Ioctl command, std::span<const u8> input,
-                    std::span<const u8> inline_input, std::vector<u8>& output);
+                    std::span<const u8> inline_input, std::span<u8> output);
 
-    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::vector<u8>& output,
-                    std::vector<u8>& inline_output);
+    NvResult Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> input, std::span<u8> output,
+                    std::span<u8> inline_output);
 
     /// Closes a device file descriptor and returns operation success.
     NvResult Close(DeviceFD fd);
diff --git a/src/core/hle/service/nvdrv/nvdrv_interface.cpp b/src/core/hle/service/nvdrv/nvdrv_interface.cpp
index d010a1e03..348207e25 100644
--- a/src/core/hle/service/nvdrv/nvdrv_interface.cpp
+++ b/src/core/hle/service/nvdrv/nvdrv_interface.cpp
@@ -63,12 +63,12 @@ void NVDRV::Ioctl1(HLERequestContext& ctx) {
     }
 
     // Check device
-    std::vector<u8> output_buffer(ctx.GetWriteBufferSize(0));
+    tmp_output.resize_destructive(ctx.GetWriteBufferSize(0));
     const auto input_buffer = ctx.ReadBuffer(0);
 
-    const auto nv_result = nvdrv->Ioctl1(fd, command, input_buffer, output_buffer);
+    const auto nv_result = nvdrv->Ioctl1(fd, command, input_buffer, tmp_output);
     if (command.is_out != 0) {
-        ctx.WriteBuffer(output_buffer);
+        ctx.WriteBuffer(tmp_output);
     }
 
     IPC::ResponseBuilder rb{ctx, 3};
@@ -90,12 +90,12 @@ void NVDRV::Ioctl2(HLERequestContext& ctx) {
 
     const auto input_buffer = ctx.ReadBuffer(0);
     const auto input_inlined_buffer = ctx.ReadBuffer(1);
-    std::vector<u8> output_buffer(ctx.GetWriteBufferSize(0));
+    tmp_output.resize_destructive(ctx.GetWriteBufferSize(0));
 
     const auto nv_result =
-        nvdrv->Ioctl2(fd, command, input_buffer, input_inlined_buffer, output_buffer);
+        nvdrv->Ioctl2(fd, command, input_buffer, input_inlined_buffer, tmp_output);
     if (command.is_out != 0) {
-        ctx.WriteBuffer(output_buffer);
+        ctx.WriteBuffer(tmp_output);
     }
 
     IPC::ResponseBuilder rb{ctx, 3};
@@ -116,14 +116,12 @@ void NVDRV::Ioctl3(HLERequestContext& ctx) {
     }
 
     const auto input_buffer = ctx.ReadBuffer(0);
-    std::vector<u8> output_buffer(ctx.GetWriteBufferSize(0));
-    std::vector<u8> output_buffer_inline(ctx.GetWriteBufferSize(1));
-
-    const auto nv_result =
-        nvdrv->Ioctl3(fd, command, input_buffer, output_buffer, output_buffer_inline);
+    tmp_output.resize_destructive(ctx.GetWriteBufferSize(0));
+    tmp_output_inline.resize_destructive(ctx.GetWriteBufferSize(1));
+    const auto nv_result = nvdrv->Ioctl3(fd, command, input_buffer, tmp_output, tmp_output_inline);
     if (command.is_out != 0) {
-        ctx.WriteBuffer(output_buffer, 0);
-        ctx.WriteBuffer(output_buffer_inline, 1);
+        ctx.WriteBuffer(tmp_output, 0);
+        ctx.WriteBuffer(tmp_output_inline, 1);
     }
 
     IPC::ResponseBuilder rb{ctx, 3};
diff --git a/src/core/hle/service/nvdrv/nvdrv_interface.h b/src/core/hle/service/nvdrv/nvdrv_interface.h
index 881ea1a6b..4b593ff90 100644
--- a/src/core/hle/service/nvdrv/nvdrv_interface.h
+++ b/src/core/hle/service/nvdrv/nvdrv_interface.h
@@ -4,6 +4,7 @@
 #pragma once
 
 #include <memory>
+#include "common/scratch_buffer.h"
 #include "core/hle/service/nvdrv/nvdrv.h"
 #include "core/hle/service/service.h"
 
@@ -33,6 +34,8 @@ private:
 
     u64 pid{};
     bool is_initialized{};
+    Common::ScratchBuffer<u8> tmp_output;
+    Common::ScratchBuffer<u8> tmp_output_inline;
 };
 
 } // namespace Service::Nvidia
diff --git a/src/core/hle/service/nvnflinger/nvnflinger.cpp b/src/core/hle/service/nvnflinger/nvnflinger.cpp
index da2d5890f..5f55cd31e 100644
--- a/src/core/hle/service/nvnflinger/nvnflinger.cpp
+++ b/src/core/hle/service/nvnflinger/nvnflinger.cpp
@@ -43,14 +43,10 @@ void Nvnflinger::SplitVSync(std::stop_token stop_token) {
     Common::SetCurrentThreadPriority(Common::ThreadPriority::High);
 
     while (!stop_token.stop_requested()) {
-        vsync_signal.wait(false);
-        vsync_signal.store(false);
-
-        guard->lock();
+        vsync_signal.Wait();
 
+        const auto lock_guard = Lock();
         Compose();
-
-        guard->unlock();
     }
 }
 
@@ -69,8 +65,8 @@ Nvnflinger::Nvnflinger(Core::System& system_, HosBinderDriverServer& hos_binder_
         "ScreenComposition",
         [this](std::uintptr_t, s64 time,
                std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
-            vsync_signal.store(true);
-            vsync_signal.notify_all();
+            { const auto lock_guard = Lock(); }
+            vsync_signal.Set();
             return std::chrono::nanoseconds(GetNextTicks());
         });
 
@@ -96,8 +92,7 @@ Nvnflinger::~Nvnflinger() {
     if (system.IsMulticore()) {
         system.CoreTiming().UnscheduleEvent(multi_composition_event, {});
         vsync_thread.request_stop();
-        vsync_signal.store(true);
-        vsync_signal.notify_all();
+        vsync_signal.Set();
     } else {
         system.CoreTiming().UnscheduleEvent(single_composition_event, {});
     }
diff --git a/src/core/hle/service/nvnflinger/nvnflinger.h b/src/core/hle/service/nvnflinger/nvnflinger.h
index a043cceb2..ef236303a 100644
--- a/src/core/hle/service/nvnflinger/nvnflinger.h
+++ b/src/core/hle/service/nvnflinger/nvnflinger.h
@@ -12,6 +12,7 @@
 
 #include "common/common_types.h"
 #include "common/polyfill_thread.h"
+#include "common/thread.h"
 #include "core/hle/result.h"
 #include "core/hle/service/kernel_helpers.h"
 
@@ -143,7 +144,7 @@ private:
 
     Core::System& system;
 
-    std::atomic<bool> vsync_signal;
+    Common::Event vsync_signal;
 
     std::jthread vsync_thread;
 
diff --git a/src/core/hle/service/nvnflinger/parcel.h b/src/core/hle/service/nvnflinger/parcel.h
index fb56d75d7..23ba315a0 100644
--- a/src/core/hle/service/nvnflinger/parcel.h
+++ b/src/core/hle/service/nvnflinger/parcel.h
@@ -6,6 +6,7 @@
 #include <memory>
 #include <span>
 #include <vector>
+#include <boost/container/small_vector.hpp>
 
 #include "common/alignment.h"
 #include "common/assert.h"
@@ -167,7 +168,7 @@ public:
 private:
     template <typename T>
         requires(std::is_trivially_copyable_v<T>)
-    void WriteImpl(const T& val, std::vector<u8>& buffer) {
+    void WriteImpl(const T& val, boost::container::small_vector<u8, 0x200>& buffer) {
         const size_t aligned_size = Common::AlignUp(sizeof(T), 4);
         const size_t old_size = buffer.size();
         buffer.resize(old_size + aligned_size);
@@ -176,8 +177,8 @@ private:
     }
 
 private:
-    std::vector<u8> m_data_buffer;
-    std::vector<u8> m_object_buffer;
+    boost::container::small_vector<u8, 0x200> m_data_buffer;
+    boost::container::small_vector<u8, 0x200> m_object_buffer;
 };
 
 } // namespace Service::android
diff --git a/src/core/hle/service/server_manager.cpp b/src/core/hle/service/server_manager.cpp
index 156bc27d8..d1e99b184 100644
--- a/src/core/hle/service/server_manager.cpp
+++ b/src/core/hle/service/server_manager.cpp
@@ -44,7 +44,7 @@ ServerManager::~ServerManager() {
     m_event->Signal();
 
     // Wait for processing to stop.
-    m_stopped.wait(false);
+    m_stopped.Wait();
     m_threads.clear();
 
     // Clean up ports.
@@ -182,10 +182,7 @@ void ServerManager::StartAdditionalHostThreads(const char* name, size_t num_thre
 }
 
 Result ServerManager::LoopProcess() {
-    SCOPE_EXIT({
-        m_stopped.store(true);
-        m_stopped.notify_all();
-    });
+    SCOPE_EXIT({ m_stopped.Set(); });
 
     R_RETURN(this->LoopProcessImpl());
 }
diff --git a/src/core/hle/service/server_manager.h b/src/core/hle/service/server_manager.h
index fdb8af2ff..58b0a0832 100644
--- a/src/core/hle/service/server_manager.h
+++ b/src/core/hle/service/server_manager.h
@@ -3,7 +3,6 @@
 
 #pragma once
 
-#include <atomic>
 #include <functional>
 #include <list>
 #include <map>
@@ -12,6 +11,7 @@
 #include <vector>
 
 #include "common/polyfill_thread.h"
+#include "common/thread.h"
 #include "core/hle/result.h"
 #include "core/hle/service/mutex.h"
 
@@ -82,7 +82,7 @@ private:
     std::list<RequestState> m_deferrals{};
 
     // Host state tracking
-    std::atomic<bool> m_stopped{};
+    Common::Event m_stopped{};
     std::vector<std::jthread> m_threads{};
     std::stop_source m_stop_source{};
 };
diff --git a/src/core/hle/service/time/clock_types.h b/src/core/hle/service/time/clock_types.h
index e6293ffb9..9fc01ea90 100644
--- a/src/core/hle/service/time/clock_types.h
+++ b/src/core/hle/service/time/clock_types.h
@@ -3,6 +3,8 @@
 
 #pragma once
 
+#include <ratio>
+
 #include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "common/uuid.h"
@@ -74,18 +76,19 @@ static_assert(std::is_trivially_copyable_v<ContinuousAdjustmentTimePoint>,
 /// https://switchbrew.org/wiki/Glue_services#TimeSpanType
 struct TimeSpanType {
     s64 nanoseconds{};
-    static constexpr s64 ns_per_second{1000000000ULL};
 
     s64 ToSeconds() const {
-        return nanoseconds / ns_per_second;
+        return nanoseconds / std::nano::den;
     }
 
     static TimeSpanType FromSeconds(s64 seconds) {
-        return {seconds * ns_per_second};
+        return {seconds * std::nano::den};
     }
 
-    static TimeSpanType FromTicks(u64 ticks, u64 frequency) {
-        return FromSeconds(static_cast<s64>(ticks) / static_cast<s64>(frequency));
+    template <u64 Frequency>
+    static TimeSpanType FromTicks(u64 ticks) {
+        using TicksToNSRatio = std::ratio<std::nano::den, Frequency>;
+        return {static_cast<s64>(ticks * TicksToNSRatio::num / TicksToNSRatio::den)};
     }
 };
 static_assert(sizeof(TimeSpanType) == 8, "TimeSpanType is incorrect size");
diff --git a/src/core/hle/service/time/standard_steady_clock_core.cpp b/src/core/hle/service/time/standard_steady_clock_core.cpp
index 3dbbb9850..5627b7003 100644
--- a/src/core/hle/service/time/standard_steady_clock_core.cpp
+++ b/src/core/hle/service/time/standard_steady_clock_core.cpp
@@ -10,7 +10,7 @@ namespace Service::Time::Clock {
 
 TimeSpanType StandardSteadyClockCore::GetCurrentRawTimePoint(Core::System& system) {
     const TimeSpanType ticks_time_span{
-        TimeSpanType::FromTicks(system.CoreTiming().GetClockTicks(), Core::Hardware::CNTFREQ)};
+        TimeSpanType::FromTicks<Core::Hardware::CNTFREQ>(system.CoreTiming().GetClockTicks())};
     TimeSpanType raw_time_point{setup_value.nanoseconds + ticks_time_span.nanoseconds};
 
     if (raw_time_point.nanoseconds < cached_raw_time_point.nanoseconds) {
diff --git a/src/core/hle/service/time/tick_based_steady_clock_core.cpp b/src/core/hle/service/time/tick_based_steady_clock_core.cpp
index 27600413e..0d9fb3143 100644
--- a/src/core/hle/service/time/tick_based_steady_clock_core.cpp
+++ b/src/core/hle/service/time/tick_based_steady_clock_core.cpp
@@ -10,7 +10,7 @@ namespace Service::Time::Clock {
 
 SteadyClockTimePoint TickBasedSteadyClockCore::GetTimePoint(Core::System& system) {
     const TimeSpanType ticks_time_span{
-        TimeSpanType::FromTicks(system.CoreTiming().GetClockTicks(), Core::Hardware::CNTFREQ)};
+        TimeSpanType::FromTicks<Core::Hardware::CNTFREQ>(system.CoreTiming().GetClockTicks())};
 
     return {ticks_time_span.ToSeconds(), GetClockSourceId()};
 }
diff --git a/src/core/hle/service/time/time.cpp b/src/core/hle/service/time/time.cpp
index 868be60c5..7197ca30f 100644
--- a/src/core/hle/service/time/time.cpp
+++ b/src/core/hle/service/time/time.cpp
@@ -240,8 +240,8 @@ void Module::Interface::CalculateMonotonicSystemClockBaseTimePoint(HLERequestCon
     const auto current_time_point{steady_clock_core.GetCurrentTimePoint(system)};
 
     if (current_time_point.clock_source_id == context.steady_time_point.clock_source_id) {
-        const auto ticks{Clock::TimeSpanType::FromTicks(system.CoreTiming().GetClockTicks(),
-                                                        Core::Hardware::CNTFREQ)};
+        const auto ticks{Clock::TimeSpanType::FromTicks<Core::Hardware::CNTFREQ>(
+            system.CoreTiming().GetClockTicks())};
         const s64 base_time_point{context.offset + current_time_point.time_point -
                                   ticks.ToSeconds()};
         IPC::ResponseBuilder rb{ctx, (sizeof(s64) / 4) + 2};
diff --git a/src/core/hle/service/time/time_sharedmemory.cpp b/src/core/hle/service/time/time_sharedmemory.cpp
index ce1c85bcc..a00676669 100644
--- a/src/core/hle/service/time/time_sharedmemory.cpp
+++ b/src/core/hle/service/time/time_sharedmemory.cpp
@@ -21,8 +21,9 @@ SharedMemory::~SharedMemory() = default;
 
 void SharedMemory::SetupStandardSteadyClock(const Common::UUID& clock_source_id,
                                             Clock::TimeSpanType current_time_point) {
-    const Clock::TimeSpanType ticks_time_span{Clock::TimeSpanType::FromTicks(
-        system.CoreTiming().GetClockTicks(), Core::Hardware::CNTFREQ)};
+    const Clock::TimeSpanType ticks_time_span{
+        Clock::TimeSpanType::FromTicks<Core::Hardware::CNTFREQ>(
+            system.CoreTiming().GetClockTicks())};
     const Clock::SteadyClockContext context{
         static_cast<u64>(current_time_point.nanoseconds - ticks_time_span.nanoseconds),
         clock_source_id};
diff --git a/src/core/hle/service/time/time_zone_manager.cpp b/src/core/hle/service/time/time_zone_manager.cpp
index 63aacd19f..205371a26 100644
--- a/src/core/hle/service/time/time_zone_manager.cpp
+++ b/src/core/hle/service/time/time_zone_manager.cpp
@@ -911,9 +911,13 @@ static Result ToCalendarTimeInternal(const TimeZoneRule& rules, s64 time,
 
     calendar_additional_info.is_dst = rules.ttis[tti_index].is_dst;
     const char* time_zone{&rules.chars[rules.ttis[tti_index].abbreviation_list_index]};
-    for (int index{}; time_zone[index] != '\0'; ++index) {
+    u32 index;
+    for (index = 0; time_zone[index] != '\0' && time_zone[index] != ',' &&
+                    index < calendar_additional_info.timezone_name.size() - 1;
+         ++index) {
         calendar_additional_info.timezone_name[index] = time_zone[index];
     }
+    calendar_additional_info.timezone_name[index] = '\0';
     return ResultSuccess;
 }
 
diff --git a/src/input_common/drivers/joycon.cpp b/src/input_common/drivers/joycon.cpp
index b2b5677c8..0aca5a3a3 100644
--- a/src/input_common/drivers/joycon.cpp
+++ b/src/input_common/drivers/joycon.cpp
@@ -102,12 +102,12 @@ bool Joycons::IsDeviceNew(SDL_hid_device_info* device_info) const {
     Joycon::SerialNumber serial_number{};
 
     const auto result = Joycon::JoyconDriver::GetDeviceType(device_info, type);
-    if (result != Joycon::DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return false;
     }
 
     const auto result2 = Joycon::JoyconDriver::GetSerialNumber(device_info, serial_number);
-    if (result2 != Joycon::DriverResult::Success) {
+    if (result2 != Common::Input::DriverResult::Success) {
         return false;
     }
 
@@ -171,10 +171,10 @@ void Joycons::RegisterNewDevice(SDL_hid_device_info* device_info) {
         LOG_WARNING(Input, "No free handles available");
         return;
     }
-    if (result == Joycon::DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = handle->RequestDeviceAccess(device_info);
     }
-    if (result == Joycon::DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         LOG_WARNING(Input, "Initialize device");
 
         const std::size_t port = handle->GetDevicePort();
@@ -195,8 +195,8 @@ void Joycons::RegisterNewDevice(SDL_hid_device_info* device_info) {
                 OnMotionUpdate(port, type, id, value);
             }},
             .on_ring_data = {[this](f32 ring_data) { OnRingConUpdate(ring_data); }},
-            .on_amiibo_data = {[this, port, type](const std::vector<u8>& amiibo_data) {
-                OnAmiiboUpdate(port, type, amiibo_data);
+            .on_amiibo_data = {[this, port, type](const Joycon::TagInfo& tag_info) {
+                OnAmiiboUpdate(port, type, tag_info);
             }},
             .on_camera_data = {[this, port](const std::vector<u8>& camera_data,
                                             Joycon::IrsResolution format) {
@@ -273,8 +273,7 @@ Common::Input::DriverResult Joycons::SetLeds(const PadIdentifier& identifier,
     led_config += led_status.led_3 ? 4 : 0;
     led_config += led_status.led_4 ? 8 : 0;
 
-    return static_cast<Common::Input::DriverResult>(
-        handle->SetLedConfig(static_cast<u8>(led_config)));
+    return handle->SetLedConfig(static_cast<u8>(led_config));
 }
 
 Common::Input::DriverResult Joycons::SetCameraFormat(const PadIdentifier& identifier,
@@ -283,21 +282,113 @@ Common::Input::DriverResult Joycons::SetCameraFormat(const PadIdentifier& identi
     if (handle == nullptr) {
         return Common::Input::DriverResult::InvalidHandle;
     }
-    return static_cast<Common::Input::DriverResult>(handle->SetIrsConfig(
-        Joycon::IrsMode::ImageTransfer, static_cast<Joycon::IrsResolution>(camera_format)));
+    return handle->SetIrsConfig(Joycon::IrsMode::ImageTransfer,
+                                static_cast<Joycon::IrsResolution>(camera_format));
 };
 
 Common::Input::NfcState Joycons::SupportsNfc(const PadIdentifier& identifier_) const {
     return Common::Input::NfcState::Success;
 };
 
+Common::Input::NfcState Joycons::StartNfcPolling(const PadIdentifier& identifier) {
+    auto handle = GetHandle(identifier);
+    if (handle == nullptr) {
+        return Common::Input::NfcState::Unknown;
+    }
+    return TranslateDriverResult(handle->StartNfcPolling());
+};
+
+Common::Input::NfcState Joycons::StopNfcPolling(const PadIdentifier& identifier) {
+    auto handle = GetHandle(identifier);
+    if (handle == nullptr) {
+        return Common::Input::NfcState::Unknown;
+    }
+    return TranslateDriverResult(handle->StopNfcPolling());
+};
+
+Common::Input::NfcState Joycons::ReadAmiiboData(const PadIdentifier& identifier,
+                                                std::vector<u8>& out_data) {
+    auto handle = GetHandle(identifier);
+    if (handle == nullptr) {
+        return Common::Input::NfcState::Unknown;
+    }
+    return TranslateDriverResult(handle->ReadAmiiboData(out_data));
+}
+
 Common::Input::NfcState Joycons::WriteNfcData(const PadIdentifier& identifier,
                                               const std::vector<u8>& data) {
     auto handle = GetHandle(identifier);
-    if (handle->WriteNfcData(data) != Joycon::DriverResult::Success) {
-        return Common::Input::NfcState::WriteFailed;
+    if (handle == nullptr) {
+        return Common::Input::NfcState::Unknown;
     }
-    return Common::Input::NfcState::Success;
+    return TranslateDriverResult(handle->WriteNfcData(data));
+};
+
+Common::Input::NfcState Joycons::ReadMifareData(const PadIdentifier& identifier,
+                                                const Common::Input::MifareRequest& request,
+                                                Common::Input::MifareRequest& data) {
+    auto handle = GetHandle(identifier);
+    if (handle == nullptr) {
+        return Common::Input::NfcState::Unknown;
+    }
+
+    const auto command = static_cast<Joycon::MifareCmd>(request.data[0].command);
+    std::vector<Joycon::MifareReadChunk> read_request{};
+    for (const auto& request_data : request.data) {
+        if (request_data.command == 0) {
+            continue;
+        }
+        Joycon::MifareReadChunk chunk = {
+            .command = command,
+            .sector_key = {},
+            .sector = request_data.sector,
+        };
+        memcpy(chunk.sector_key.data(), request_data.key.data(),
+               sizeof(Joycon::MifareReadChunk::sector_key));
+        read_request.emplace_back(chunk);
+    }
+
+    std::vector<Joycon::MifareReadData> read_data(read_request.size());
+    const auto result = handle->ReadMifareData(read_request, read_data);
+    if (result == Common::Input::DriverResult::Success) {
+        for (std::size_t i = 0; i < read_request.size(); i++) {
+            data.data[i] = {
+                .command = static_cast<u8>(command),
+                .sector = read_data[i].sector,
+                .key = {},
+                .data = read_data[i].data,
+            };
+        }
+    }
+    return TranslateDriverResult(result);
+};
+
+Common::Input::NfcState Joycons::WriteMifareData(const PadIdentifier& identifier,
+                                                 const Common::Input::MifareRequest& request) {
+    auto handle = GetHandle(identifier);
+    if (handle == nullptr) {
+        return Common::Input::NfcState::Unknown;
+    }
+
+    const auto command = static_cast<Joycon::MifareCmd>(request.data[0].command);
+    std::vector<Joycon::MifareWriteChunk> write_request{};
+    for (const auto& request_data : request.data) {
+        if (request_data.command == 0) {
+            continue;
+        }
+        Joycon::MifareWriteChunk chunk = {
+            .command = command,
+            .sector_key = {},
+            .sector = request_data.sector,
+            .data = {},
+        };
+        memcpy(chunk.sector_key.data(), request_data.key.data(),
+               sizeof(Joycon::MifareReadChunk::sector_key));
+        memcpy(chunk.data.data(), request_data.data.data(), sizeof(Joycon::MifareWriteChunk::data));
+        write_request.emplace_back(chunk);
+    }
+
+    return TranslateDriverResult(handle->WriteMifareData(write_request));
 };
 
 Common::Input::DriverResult Joycons::SetPollingMode(const PadIdentifier& identifier,
@@ -310,15 +401,15 @@ Common::Input::DriverResult Joycons::SetPollingMode(const PadIdentifier& identif
 
     switch (polling_mode) {
     case Common::Input::PollingMode::Active:
-        return static_cast<Common::Input::DriverResult>(handle->SetActiveMode());
+        return handle->SetActiveMode();
     case Common::Input::PollingMode::Passive:
-        return static_cast<Common::Input::DriverResult>(handle->SetPassiveMode());
+        return handle->SetPassiveMode();
     case Common::Input::PollingMode::IR:
-        return static_cast<Common::Input::DriverResult>(handle->SetIrMode());
+        return handle->SetIrMode();
     case Common::Input::PollingMode::NFC:
-        return static_cast<Common::Input::DriverResult>(handle->SetNfcMode());
+        return handle->SetNfcMode();
     case Common::Input::PollingMode::Ring:
-        return static_cast<Common::Input::DriverResult>(handle->SetRingConMode());
+        return handle->SetRingConMode();
     default:
         return Common::Input::DriverResult::NotSupported;
     }
@@ -403,11 +494,20 @@ void Joycons::OnRingConUpdate(f32 ring_data) {
 }
 
 void Joycons::OnAmiiboUpdate(std::size_t port, Joycon::ControllerType type,
-                             const std::vector<u8>& amiibo_data) {
+                             const Joycon::TagInfo& tag_info) {
     const auto identifier = GetIdentifier(port, type);
-    const auto nfc_state = amiibo_data.empty() ? Common::Input::NfcState::AmiiboRemoved
-                                               : Common::Input::NfcState::NewAmiibo;
-    SetNfc(identifier, {nfc_state, amiibo_data});
+    const auto nfc_state = tag_info.uuid_length == 0 ? Common::Input::NfcState::AmiiboRemoved
+                                                     : Common::Input::NfcState::NewAmiibo;
+
+    const Common::Input::NfcStatus nfc_status{
+        .state = nfc_state,
+        .uuid_length = tag_info.uuid_length,
+        .protocol = tag_info.protocol,
+        .tag_type = tag_info.tag_type,
+        .uuid = tag_info.uuid,
+    };
+
+    SetNfc(identifier, nfc_status);
 }
 
 void Joycons::OnCameraUpdate(std::size_t port, const std::vector<u8>& camera_data,
@@ -726,4 +826,18 @@ std::string Joycons::JoyconName(Joycon::ControllerType type) const {
         return "Unknown Switch Controller";
     }
 }
+
+Common::Input::NfcState Joycons::TranslateDriverResult(Common::Input::DriverResult result) const {
+    switch (result) {
+    case Common::Input::DriverResult::Success:
+        return Common::Input::NfcState::Success;
+    case Common::Input::DriverResult::Disabled:
+        return Common::Input::NfcState::WrongDeviceState;
+    case Common::Input::DriverResult::NotSupported:
+        return Common::Input::NfcState::NotSupported;
+    default:
+        return Common::Input::NfcState::Unknown;
+    }
+}
+
 } // namespace InputCommon
diff --git a/src/input_common/drivers/joycon.h b/src/input_common/drivers/joycon.h
index e3f0ad78f..112e970e1 100644
--- a/src/input_common/drivers/joycon.h
+++ b/src/input_common/drivers/joycon.h
@@ -15,8 +15,8 @@ using SerialNumber = std::array<u8, 15>;
 struct Battery;
 struct Color;
 struct MotionData;
+struct TagInfo;
 enum class ControllerType : u8;
-enum class DriverResult;
 enum class IrsResolution;
 class JoyconDriver;
 } // namespace InputCommon::Joycon
@@ -39,9 +39,18 @@ public:
     Common::Input::DriverResult SetCameraFormat(const PadIdentifier& identifier,
                                                 Common::Input::CameraFormat camera_format) override;
 
-    Common::Input::NfcState SupportsNfc(const PadIdentifier& identifier_) const override;
-    Common::Input::NfcState WriteNfcData(const PadIdentifier& identifier_,
+    Common::Input::NfcState SupportsNfc(const PadIdentifier& identifier) const override;
+    Common::Input::NfcState StartNfcPolling(const PadIdentifier& identifier) override;
+    Common::Input::NfcState StopNfcPolling(const PadIdentifier& identifier) override;
+    Common::Input::NfcState ReadAmiiboData(const PadIdentifier& identifier,
+                                           std::vector<u8>& out_data) override;
+    Common::Input::NfcState WriteNfcData(const PadIdentifier& identifier,
                                          const std::vector<u8>& data) override;
+    Common::Input::NfcState ReadMifareData(const PadIdentifier& identifier,
+                                           const Common::Input::MifareRequest& request,
+                                           Common::Input::MifareRequest& out_data) override;
+    Common::Input::NfcState WriteMifareData(const PadIdentifier& identifier,
+                                            const Common::Input::MifareRequest& request) override;
 
     Common::Input::DriverResult SetPollingMode(
         const PadIdentifier& identifier, const Common::Input::PollingMode polling_mode) override;
@@ -82,7 +91,7 @@ private:
                         const Joycon::MotionData& value);
     void OnRingConUpdate(f32 ring_data);
     void OnAmiiboUpdate(std::size_t port, Joycon::ControllerType type,
-                        const std::vector<u8>& amiibo_data);
+                        const Joycon::TagInfo& amiibo_data);
     void OnCameraUpdate(std::size_t port, const std::vector<u8>& camera_data,
                         Joycon::IrsResolution format);
 
@@ -102,6 +111,8 @@ private:
     /// Returns the name of the device in text format
     std::string JoyconName(Joycon::ControllerType type) const;
 
+    Common::Input::NfcState TranslateDriverResult(Common::Input::DriverResult result) const;
+
     std::jthread scan_thread;
 
     // Joycon types are split by type to ease supporting dualjoycon configurations
diff --git a/src/input_common/drivers/mouse.cpp b/src/input_common/drivers/mouse.cpp
index 0c9f642bb..f07cf8a0e 100644
--- a/src/input_common/drivers/mouse.cpp
+++ b/src/input_common/drivers/mouse.cpp
@@ -76,9 +76,6 @@ void Mouse::UpdateThread(std::stop_token stop_token) {
         UpdateStickInput();
         UpdateMotionInput();
 
-        if (mouse_panning_timeout++ > 20) {
-            StopPanning();
-        }
         std::this_thread::sleep_for(std::chrono::milliseconds(update_time));
     }
 }
@@ -88,18 +85,45 @@ void Mouse::UpdateStickInput() {
         return;
     }
 
-    const float sensitivity =
-        Settings::values.mouse_panning_sensitivity.GetValue() * default_stick_sensitivity;
+    const float length = last_mouse_change.Length();
 
-    // Slow movement by 4%
-    last_mouse_change *= 0.96f;
-    SetAxis(identifier, mouse_axis_x, last_mouse_change.x * sensitivity);
-    SetAxis(identifier, mouse_axis_y, -last_mouse_change.y * sensitivity);
+    // Prevent input from exceeding the max range (1.0f) too much,
+    // but allow some room to make it easier to sustain
+    if (length > 1.2f) {
+        last_mouse_change /= length;
+        last_mouse_change *= 1.2f;
+    }
+
+    auto mouse_change = last_mouse_change;
+
+    // Bind the mouse change to [0 <= deadzone_counterweight <= 1,1]
+    if (length < 1.0f) {
+        const float deadzone_h_counterweight =
+            Settings::values.mouse_panning_deadzone_x_counterweight.GetValue();
+        const float deadzone_v_counterweight =
+            Settings::values.mouse_panning_deadzone_y_counterweight.GetValue();
+        mouse_change /= length;
+        mouse_change.x *= length + (1 - length) * deadzone_h_counterweight * 0.01f;
+        mouse_change.y *= length + (1 - length) * deadzone_v_counterweight * 0.01f;
+    }
+
+    SetAxis(identifier, mouse_axis_x, mouse_change.x);
+    SetAxis(identifier, mouse_axis_y, -mouse_change.y);
+
+    // Decay input over time
+    const float clamped_length = std::min(1.0f, length);
+    const float decay_strength = Settings::values.mouse_panning_decay_strength.GetValue();
+    const float decay = 1 - clamped_length * clamped_length * decay_strength * 0.01f;
+    const float min_decay = Settings::values.mouse_panning_min_decay.GetValue();
+    const float clamped_decay = std::min(1 - min_decay / 100.0f, decay);
+    last_mouse_change *= clamped_decay;
 }
 
 void Mouse::UpdateMotionInput() {
-    const float sensitivity =
-        Settings::values.mouse_panning_sensitivity.GetValue() * default_motion_sensitivity;
+    // This may need its own sensitivity instead of using the average
+    const float sensitivity = (Settings::values.mouse_panning_x_sensitivity.GetValue() +
+                               Settings::values.mouse_panning_y_sensitivity.GetValue()) /
+                              2.0f * default_motion_sensitivity;
 
     const float rotation_velocity = std::sqrt(last_motion_change.x * last_motion_change.x +
                                               last_motion_change.y * last_motion_change.y);
@@ -131,49 +155,28 @@ void Mouse::UpdateMotionInput() {
 
 void Mouse::Move(int x, int y, int center_x, int center_y) {
     if (Settings::values.mouse_panning) {
-        mouse_panning_timeout = 0;
-
-        auto mouse_change =
+        const auto mouse_change =
             (Common::MakeVec(x, y) - Common::MakeVec(center_x, center_y)).Cast<float>();
-        last_motion_change += {-mouse_change.y, -mouse_change.x, 0};
-
-        const auto move_distance = mouse_change.Length();
-        if (move_distance == 0) {
-            return;
-        }
+        const float x_sensitivity =
+            Settings::values.mouse_panning_x_sensitivity.GetValue() * default_stick_sensitivity;
+        const float y_sensitivity =
+            Settings::values.mouse_panning_y_sensitivity.GetValue() * default_stick_sensitivity;
 
-        // Make slow movements at least 3 units on length
-        if (move_distance < 3.0f) {
-            // Normalize value
-            mouse_change /= move_distance;
-            mouse_change *= 3.0f;
-        }
-
-        // Average mouse movements
-        last_mouse_change = (last_mouse_change * 0.91f) + (mouse_change * 0.09f);
-
-        const auto last_move_distance = last_mouse_change.Length();
-
-        // Make fast movements clamp to 8 units on length
-        if (last_move_distance > 8.0f) {
-            // Normalize value
-            last_mouse_change /= last_move_distance;
-            last_mouse_change *= 8.0f;
-        }
-
-        // Ignore average if it's less than 1 unit and use current movement value
-        if (last_move_distance < 1.0f) {
-            last_mouse_change = mouse_change / mouse_change.Length();
-        }
+        last_motion_change += {-mouse_change.y, -mouse_change.x, 0};
+        last_mouse_change.x += mouse_change.x * x_sensitivity * 0.09f;
+        last_mouse_change.y += mouse_change.y * y_sensitivity * 0.09f;
 
         return;
     }
 
     if (button_pressed) {
         const auto mouse_move = Common::MakeVec<int>(x, y) - mouse_origin;
-        const float sensitivity = Settings::values.mouse_panning_sensitivity.GetValue() * 0.0012f;
-        SetAxis(identifier, mouse_axis_x, static_cast<float>(mouse_move.x) * sensitivity);
-        SetAxis(identifier, mouse_axis_y, static_cast<float>(-mouse_move.y) * sensitivity);
+        const float x_sensitivity = Settings::values.mouse_panning_x_sensitivity.GetValue();
+        const float y_sensitivity = Settings::values.mouse_panning_y_sensitivity.GetValue();
+        SetAxis(identifier, mouse_axis_x,
+                static_cast<float>(mouse_move.x) * x_sensitivity * 0.0012f);
+        SetAxis(identifier, mouse_axis_y,
+                static_cast<float>(-mouse_move.y) * y_sensitivity * 0.0012f);
 
         last_motion_change = {
             static_cast<float>(-mouse_move.y) / 50.0f,
@@ -241,10 +244,6 @@ void Mouse::ReleaseAllButtons() {
     button_pressed = false;
 }
 
-void Mouse::StopPanning() {
-    last_mouse_change = {};
-}
-
 std::vector<Common::ParamPackage> Mouse::GetInputDevices() const {
     std::vector<Common::ParamPackage> devices;
     devices.emplace_back(Common::ParamPackage{
diff --git a/src/input_common/drivers/mouse.h b/src/input_common/drivers/mouse.h
index b872c7a0f..0e8edcce1 100644
--- a/src/input_common/drivers/mouse.h
+++ b/src/input_common/drivers/mouse.h
@@ -98,7 +98,6 @@ private:
     void UpdateThread(std::stop_token stop_token);
     void UpdateStickInput();
     void UpdateMotionInput();
-    void StopPanning();
 
     Common::Input::ButtonNames GetUIButtonName(const Common::ParamPackage& params) const;
 
@@ -108,7 +107,6 @@ private:
     Common::Vec3<float> last_motion_change;
     Common::Vec2<int> wheel_position;
     bool button_pressed;
-    int mouse_panning_timeout{};
     std::jthread update_thread;
 };
 
diff --git a/src/input_common/drivers/sdl_driver.cpp b/src/input_common/drivers/sdl_driver.cpp
index 9a0439bb5..9f26392b1 100644
--- a/src/input_common/drivers/sdl_driver.cpp
+++ b/src/input_common/drivers/sdl_driver.cpp
@@ -150,6 +150,8 @@ public:
         if (sdl_controller) {
             const auto type = SDL_GameControllerGetType(sdl_controller.get());
             return (type == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_PRO) ||
+                   (type == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_JOYCON_LEFT) ||
+                   (type == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_JOYCON_RIGHT) ||
                    (type == SDL_CONTROLLER_TYPE_PS5);
         }
         return false;
@@ -228,9 +230,8 @@ public:
         return false;
     }
 
-    Common::Input::BatteryLevel GetBatteryLevel() {
-        const auto level = SDL_JoystickCurrentPowerLevel(sdl_joystick.get());
-        switch (level) {
+    Common::Input::BatteryLevel GetBatteryLevel(SDL_JoystickPowerLevel battery_level) {
+        switch (battery_level) {
         case SDL_JOYSTICK_POWER_EMPTY:
             return Common::Input::BatteryLevel::Empty;
         case SDL_JOYSTICK_POWER_LOW:
@@ -378,7 +379,6 @@ void SDLDriver::InitJoystick(int joystick_index) {
     if (joystick_map.find(guid) == joystick_map.end()) {
         auto joystick = std::make_shared<SDLJoystick>(guid, 0, sdl_joystick, sdl_gamecontroller);
         PreSetController(joystick->GetPadIdentifier());
-        SetBattery(joystick->GetPadIdentifier(), joystick->GetBatteryLevel());
         joystick->EnableMotion();
         joystick_map[guid].emplace_back(std::move(joystick));
         return;
@@ -398,7 +398,6 @@ void SDLDriver::InitJoystick(int joystick_index) {
     const int port = static_cast<int>(joystick_guid_list.size());
     auto joystick = std::make_shared<SDLJoystick>(guid, port, sdl_joystick, sdl_gamecontroller);
     PreSetController(joystick->GetPadIdentifier());
-    SetBattery(joystick->GetPadIdentifier(), joystick->GetBatteryLevel());
     joystick->EnableMotion();
     joystick_guid_list.emplace_back(std::move(joystick));
 }
@@ -438,8 +437,6 @@ void SDLDriver::HandleGameControllerEvent(const SDL_Event& event) {
         if (const auto joystick = GetSDLJoystickBySDLID(event.jbutton.which)) {
             const PadIdentifier identifier = joystick->GetPadIdentifier();
             SetButton(identifier, event.jbutton.button, true);
-            // Battery doesn't trigger an event so just update every button press
-            SetBattery(identifier, joystick->GetBatteryLevel());
         }
         break;
     }
@@ -466,6 +463,13 @@ void SDLDriver::HandleGameControllerEvent(const SDL_Event& event) {
         }
         break;
     }
+    case SDL_JOYBATTERYUPDATED: {
+        if (auto joystick = GetSDLJoystickBySDLID(event.jbattery.which)) {
+            const PadIdentifier identifier = joystick->GetPadIdentifier();
+            SetBattery(identifier, joystick->GetBatteryLevel(event.jbattery.level));
+        }
+        break;
+    }
     case SDL_JOYDEVICEREMOVED:
         LOG_DEBUG(Input, "Controller removed with Instance_ID {}", event.jdevice.which);
         CloseJoystick(SDL_JoystickFromInstanceID(event.jdevice.which));
@@ -483,6 +487,10 @@ void SDLDriver::CloseJoysticks() {
 }
 
 SDLDriver::SDLDriver(std::string input_engine_) : InputEngine(std::move(input_engine_)) {
+    // Set our application name. Currently passed to DBus by SDL and visible to the user through
+    // their desktop environment.
+    SDL_SetHint(SDL_HINT_APP_NAME, "yuzu");
+
     if (!Settings::values.enable_raw_input) {
         // Disable raw input. When enabled this setting causes SDL to die when a web applet opens
         SDL_SetHint(SDL_HINT_JOYSTICK_RAWINPUT, "0");
@@ -501,6 +509,9 @@ SDLDriver::SDLDriver(std::string input_engine_) : InputEngine(std::move(input_en
         SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_JOY_CONS, "0");
     } else {
         SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_JOY_CONS, "1");
+        SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_JOYCON_HOME_LED, "0");
+        SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_COMBINE_JOY_CONS, "0");
+        SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_VERTICAL_JOY_CONS, "1");
     }
 
     // Disable hidapi drivers for pro controllers when the custom joycon driver is enabled
@@ -508,8 +519,11 @@ SDLDriver::SDLDriver(std::string input_engine_) : InputEngine(std::move(input_en
         SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_SWITCH, "0");
     } else {
         SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_SWITCH, "1");
+        SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_SWITCH_HOME_LED, "0");
     }
 
+    SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_SWITCH_PLAYER_LED, "1");
+
     // Disable hidapi driver for xbox. Already default on Windows, this causes conflict with native
     // driver on Linux.
     SDL_SetHint(SDL_HINT_JOYSTICK_HIDAPI_XBOX, "0");
@@ -789,7 +803,9 @@ ButtonMapping SDLDriver::GetButtonMappingForDevice(const Common::ParamPackage& p
     // This list also excludes Screenshot since there's not really a mapping for that
     ButtonBindings switch_to_sdl_button;
 
-    if (SDL_GameControllerGetType(controller) == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_PRO) {
+    if (SDL_GameControllerGetType(controller) == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_PRO ||
+        SDL_GameControllerGetType(controller) == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_JOYCON_LEFT ||
+        SDL_GameControllerGetType(controller) == SDL_CONTROLLER_TYPE_NINTENDO_SWITCH_JOYCON_RIGHT) {
         switch_to_sdl_button = GetNintendoButtonBinding(joystick);
     } else {
         switch_to_sdl_button = GetDefaultButtonBinding();
diff --git a/src/input_common/drivers/virtual_amiibo.cpp b/src/input_common/drivers/virtual_amiibo.cpp
index 6435b8af8..180eb53ef 100644
--- a/src/input_common/drivers/virtual_amiibo.cpp
+++ b/src/input_common/drivers/virtual_amiibo.cpp
@@ -29,14 +29,13 @@ Common::Input::DriverResult VirtualAmiibo::SetPollingMode(
 
     switch (polling_mode) {
     case Common::Input::PollingMode::NFC:
-        if (state == State::Initialized) {
-            state = State::WaitingForAmiibo;
-        }
+        state = State::Initialized;
         return Common::Input::DriverResult::Success;
     default:
-        if (state == State::AmiiboIsOpen) {
+        if (state == State::TagNearby) {
             CloseAmiibo();
         }
+        state = State::Disabled;
         return Common::Input::DriverResult::NotSupported;
     }
 }
@@ -45,6 +44,39 @@ Common::Input::NfcState VirtualAmiibo::SupportsNfc(
     [[maybe_unused]] const PadIdentifier& identifier_) const {
     return Common::Input::NfcState::Success;
 }
+Common::Input::NfcState VirtualAmiibo::StartNfcPolling(const PadIdentifier& identifier_) {
+    if (state != State::Initialized) {
+        return Common::Input::NfcState::WrongDeviceState;
+    }
+    state = State::WaitingForAmiibo;
+    return Common::Input::NfcState::Success;
+}
+
+Common::Input::NfcState VirtualAmiibo::StopNfcPolling(const PadIdentifier& identifier_) {
+    if (state == State::Disabled) {
+        return Common::Input::NfcState::WrongDeviceState;
+    }
+    if (state == State::TagNearby) {
+        CloseAmiibo();
+    }
+    state = State::Initialized;
+    return Common::Input::NfcState::Success;
+}
+
+Common::Input::NfcState VirtualAmiibo::ReadAmiiboData(const PadIdentifier& identifier_,
+                                                      std::vector<u8>& out_data) {
+    if (state != State::TagNearby) {
+        return Common::Input::NfcState::WrongDeviceState;
+    }
+
+    if (status.tag_type != 1U << 1) {
+        return Common::Input::NfcState::InvalidTagType;
+    }
+
+    out_data.resize(nfc_data.size());
+    memcpy(out_data.data(), nfc_data.data(), nfc_data.size());
+    return Common::Input::NfcState::Success;
+}
 
 Common::Input::NfcState VirtualAmiibo::WriteNfcData(
     [[maybe_unused]] const PadIdentifier& identifier_, const std::vector<u8>& data) {
@@ -66,6 +98,69 @@ Common::Input::NfcState VirtualAmiibo::WriteNfcData(
     return Common::Input::NfcState::Success;
 }
 
+Common::Input::NfcState VirtualAmiibo::ReadMifareData(const PadIdentifier& identifier_,
+                                                      const Common::Input::MifareRequest& request,
+                                                      Common::Input::MifareRequest& out_data) {
+    if (state != State::TagNearby) {
+        return Common::Input::NfcState::WrongDeviceState;
+    }
+
+    if (status.tag_type != 1U << 6) {
+        return Common::Input::NfcState::InvalidTagType;
+    }
+
+    for (std::size_t i = 0; i < request.data.size(); i++) {
+        if (request.data[i].command == 0) {
+            continue;
+        }
+        out_data.data[i].command = request.data[i].command;
+        out_data.data[i].sector = request.data[i].sector;
+
+        const std::size_t sector_index =
+            request.data[i].sector * sizeof(Common::Input::MifareData::data);
+
+        if (nfc_data.size() < sector_index + sizeof(Common::Input::MifareData::data)) {
+            return Common::Input::NfcState::WriteFailed;
+        }
+
+        // Ignore the sector key as we don't support it
+        memcpy(out_data.data[i].data.data(), nfc_data.data() + sector_index,
+               sizeof(Common::Input::MifareData::data));
+    }
+
+    return Common::Input::NfcState::Success;
+}
+
+Common::Input::NfcState VirtualAmiibo::WriteMifareData(
+    const PadIdentifier& identifier_, const Common::Input::MifareRequest& request) {
+    if (state != State::TagNearby) {
+        return Common::Input::NfcState::WrongDeviceState;
+    }
+
+    if (status.tag_type != 1U << 6) {
+        return Common::Input::NfcState::InvalidTagType;
+    }
+
+    for (std::size_t i = 0; i < request.data.size(); i++) {
+        if (request.data[i].command == 0) {
+            continue;
+        }
+
+        const std::size_t sector_index =
+            request.data[i].sector * sizeof(Common::Input::MifareData::data);
+
+        if (nfc_data.size() < sector_index + sizeof(Common::Input::MifareData::data)) {
+            return Common::Input::NfcState::WriteFailed;
+        }
+
+        // Ignore the sector key as we don't support it
+        memcpy(nfc_data.data() + sector_index, request.data[i].data.data(),
+               sizeof(Common::Input::MifareData::data));
+    }
+
+    return Common::Input::NfcState::Success;
+}
+
 VirtualAmiibo::State VirtualAmiibo::GetCurrentState() const {
     return state;
 }
@@ -112,23 +207,31 @@ VirtualAmiibo::Info VirtualAmiibo::LoadAmiibo(std::span<u8> data) {
     case AmiiboSizeWithoutPassword:
     case AmiiboSizeWithSignature:
         nfc_data.resize(AmiiboSize);
+        status.tag_type = 1U << 1;
+        status.uuid_length = 7;
         break;
     case MifareSize:
         nfc_data.resize(MifareSize);
+        status.tag_type = 1U << 6;
+        status.uuid_length = 4;
         break;
     default:
         return Info::NotAnAmiibo;
     }
 
-    state = State::AmiiboIsOpen;
+    status.uuid = {};
+    status.protocol = 1;
+    state = State::TagNearby;
+    status.state = Common::Input::NfcState::NewAmiibo,
     memcpy(nfc_data.data(), data.data(), data.size_bytes());
-    SetNfc(identifier, {Common::Input::NfcState::NewAmiibo, nfc_data});
+    memcpy(status.uuid.data(), nfc_data.data(), status.uuid_length);
+    SetNfc(identifier, status);
     return Info::Success;
 }
 
 VirtualAmiibo::Info VirtualAmiibo::ReloadAmiibo() {
-    if (state == State::AmiiboIsOpen) {
-        SetNfc(identifier, {Common::Input::NfcState::NewAmiibo, nfc_data});
+    if (state == State::TagNearby) {
+        SetNfc(identifier, status);
         return Info::Success;
     }
 
@@ -136,9 +239,14 @@ VirtualAmiibo::Info VirtualAmiibo::ReloadAmiibo() {
 }
 
 VirtualAmiibo::Info VirtualAmiibo::CloseAmiibo() {
-    state = polling_mode == Common::Input::PollingMode::NFC ? State::WaitingForAmiibo
-                                                            : State::Initialized;
-    SetNfc(identifier, {Common::Input::NfcState::AmiiboRemoved, {}});
+    if (state != State::TagNearby) {
+        return Info::Success;
+    }
+
+    state = State::WaitingForAmiibo;
+    status.state = Common::Input::NfcState::AmiiboRemoved;
+    SetNfc(identifier, status);
+    status.tag_type = 0;
     return Info::Success;
 }
 
diff --git a/src/input_common/drivers/virtual_amiibo.h b/src/input_common/drivers/virtual_amiibo.h
index 09ca09e68..490f38e05 100644
--- a/src/input_common/drivers/virtual_amiibo.h
+++ b/src/input_common/drivers/virtual_amiibo.h
@@ -20,9 +20,10 @@ namespace InputCommon {
 class VirtualAmiibo final : public InputEngine {
 public:
     enum class State {
+        Disabled,
         Initialized,
         WaitingForAmiibo,
-        AmiiboIsOpen,
+        TagNearby,
     };
 
     enum class Info {
@@ -41,9 +42,17 @@ public:
         const PadIdentifier& identifier_, const Common::Input::PollingMode polling_mode_) override;
 
     Common::Input::NfcState SupportsNfc(const PadIdentifier& identifier_) const override;
-
+    Common::Input::NfcState StartNfcPolling(const PadIdentifier& identifier_) override;
+    Common::Input::NfcState StopNfcPolling(const PadIdentifier& identifier_) override;
+    Common::Input::NfcState ReadAmiiboData(const PadIdentifier& identifier_,
+                                           std::vector<u8>& out_data) override;
     Common::Input::NfcState WriteNfcData(const PadIdentifier& identifier_,
                                          const std::vector<u8>& data) override;
+    Common::Input::NfcState ReadMifareData(const PadIdentifier& identifier_,
+                                           const Common::Input::MifareRequest& data,
+                                           Common::Input::MifareRequest& out_data) override;
+    Common::Input::NfcState WriteMifareData(const PadIdentifier& identifier_,
+                                            const Common::Input::MifareRequest& data) override;
 
     State GetCurrentState() const;
 
@@ -61,8 +70,9 @@ private:
     static constexpr std::size_t MifareSize = 0x400;
 
     std::string file_path{};
-    State state{State::Initialized};
+    State state{State::Disabled};
     std::vector<u8> nfc_data;
+    Common::Input::NfcStatus status;
     Common::Input::PollingMode polling_mode{Common::Input::PollingMode::Passive};
 };
 } // namespace InputCommon
diff --git a/src/input_common/helpers/joycon_driver.cpp b/src/input_common/helpers/joycon_driver.cpp
index 95106f16d..cf51f3481 100644
--- a/src/input_common/helpers/joycon_driver.cpp
+++ b/src/input_common/helpers/joycon_driver.cpp
@@ -1,7 +1,9 @@
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "common/input.h"
 #include "common/logging/log.h"
+#include "common/scope_exit.h"
 #include "common/swap.h"
 #include "common/thread.h"
 #include "input_common/helpers/joycon_driver.h"
@@ -27,13 +29,13 @@ void JoyconDriver::Stop() {
     input_thread = {};
 }
 
-DriverResult JoyconDriver::RequestDeviceAccess(SDL_hid_device_info* device_info) {
+Common::Input::DriverResult JoyconDriver::RequestDeviceAccess(SDL_hid_device_info* device_info) {
     std::scoped_lock lock{mutex};
 
     handle_device_type = ControllerType::None;
     GetDeviceType(device_info, handle_device_type);
     if (handle_device_type == ControllerType::None) {
-        return DriverResult::UnsupportedControllerType;
+        return Common::Input::DriverResult::UnsupportedControllerType;
     }
 
     hidapi_handle->handle =
@@ -42,15 +44,15 @@ DriverResult JoyconDriver::RequestDeviceAccess(SDL_hid_device_info* device_info)
     if (!hidapi_handle->handle) {
         LOG_ERROR(Input, "Yuzu can't gain access to this device: ID {:04X}:{:04X}.",
                   device_info->vendor_id, device_info->product_id);
-        return DriverResult::HandleInUse;
+        return Common::Input::DriverResult::HandleInUse;
     }
     SDL_hid_set_nonblocking(hidapi_handle->handle, 1);
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconDriver::InitializeDevice() {
+Common::Input::DriverResult JoyconDriver::InitializeDevice() {
     if (!hidapi_handle->handle) {
-        return DriverResult::InvalidHandle;
+        return Common::Input::DriverResult::InvalidHandle;
     }
     std::scoped_lock lock{mutex};
     disable_input_thread = true;
@@ -71,6 +73,7 @@ DriverResult JoyconDriver::InitializeDevice() {
     nfc_enabled = false;
     passive_enabled = false;
     irs_enabled = false;
+    input_only_device = false;
     gyro_sensitivity = Joycon::GyroSensitivity::DPS2000;
     gyro_performance = Joycon::GyroPerformance::HZ833;
     accelerometer_sensitivity = Joycon::AccelerometerSensitivity::G8;
@@ -85,16 +88,23 @@ DriverResult JoyconDriver::InitializeDevice() {
     rumble_protocol = std::make_unique<RumbleProtocol>(hidapi_handle);
 
     // Get fixed joycon info
-    generic_protocol->GetVersionNumber(version);
-    generic_protocol->SetLowPowerMode(false);
-    generic_protocol->GetColor(color);
-    if (handle_device_type == ControllerType::Pro) {
-        // Some 3rd party controllers aren't pro controllers
-        generic_protocol->GetControllerType(device_type);
-    } else {
-        device_type = handle_device_type;
+    if (generic_protocol->GetVersionNumber(version) != Common::Input::DriverResult::Success) {
+        // If this command fails the device doesn't accept configuration commands
+        input_only_device = true;
+    }
+
+    if (!input_only_device) {
+        generic_protocol->SetLowPowerMode(false);
+        generic_protocol->GetColor(color);
+        if (handle_device_type == ControllerType::Pro) {
+            // Some 3rd party controllers aren't pro controllers
+            generic_protocol->GetControllerType(device_type);
+        } else {
+            device_type = handle_device_type;
+        }
+        generic_protocol->GetSerialNumber(serial_number);
     }
-    generic_protocol->GetSerialNumber(serial_number);
+
     supported_features = GetSupportedFeatures();
 
     // Get Calibration data
@@ -112,7 +122,7 @@ DriverResult JoyconDriver::InitializeDevice() {
     joycon_poller = std::make_unique<JoyconPoller>(device_type, left_stick_calibration,
                                                    right_stick_calibration, motion_calibration);
 
-    // Start pooling for data
+    // Start polling for data
     is_connected = true;
     if (!input_thread_running) {
         input_thread =
@@ -120,7 +130,7 @@ DriverResult JoyconDriver::InitializeDevice() {
     }
 
     disable_input_thread = false;
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
 void JoyconDriver::InputThread(std::stop_token stop_token) {
@@ -208,7 +218,7 @@ void JoyconDriver::OnNewData(std::span<u8> buffer) {
         joycon_poller->UpdateCamera(irs_protocol->GetImage(), irs_protocol->GetIrsFormat());
     }
 
-    if (nfc_protocol->IsEnabled()) {
+    if (nfc_protocol->IsPolling()) {
         if (amiibo_detected) {
             if (!nfc_protocol->HasAmiibo()) {
                 joycon_poller->UpdateAmiibo({});
@@ -218,10 +228,10 @@ void JoyconDriver::OnNewData(std::span<u8> buffer) {
         }
 
         if (!amiibo_detected) {
-            std::vector<u8> data(0x21C);
-            const auto result = nfc_protocol->ScanAmiibo(data);
-            if (result == DriverResult::Success) {
-                joycon_poller->UpdateAmiibo(data);
+            Joycon::TagInfo tag_info;
+            const auto result = nfc_protocol->GetTagInfo(tag_info);
+            if (result == Common::Input::DriverResult::Success) {
+                joycon_poller->UpdateAmiibo(tag_info);
                 amiibo_detected = true;
             }
         }
@@ -246,7 +256,8 @@ void JoyconDriver::OnNewData(std::span<u8> buffer) {
     }
 }
 
-DriverResult JoyconDriver::SetPollingMode() {
+Common::Input::DriverResult JoyconDriver::SetPollingMode() {
+    SCOPE_EXIT({ disable_input_thread = false; });
     disable_input_thread = true;
 
     rumble_protocol->EnableRumble(vibration_enabled && supported_features.vibration);
@@ -259,6 +270,10 @@ DriverResult JoyconDriver::SetPollingMode() {
         generic_protocol->EnableImu(false);
     }
 
+    if (input_only_device) {
+        return Common::Input::DriverResult::NotSupported;
+    }
+
     if (irs_protocol->IsEnabled()) {
         irs_protocol->DisableIrs();
     }
@@ -275,46 +290,42 @@ DriverResult JoyconDriver::SetPollingMode() {
 
     if (irs_enabled && supported_features.irs) {
         auto result = irs_protocol->EnableIrs();
-        if (result == DriverResult::Success) {
-            disable_input_thread = false;
+        if (result == Common::Input::DriverResult::Success) {
             return result;
         }
         irs_protocol->DisableIrs();
         LOG_ERROR(Input, "Error enabling IRS");
+        return result;
     }
 
     if (nfc_enabled && supported_features.nfc) {
         auto result = nfc_protocol->EnableNfc();
-        if (result == DriverResult::Success) {
-            result = nfc_protocol->StartNFCPollingMode();
-        }
-        if (result == DriverResult::Success) {
-            disable_input_thread = false;
+        if (result == Common::Input::DriverResult::Success) {
             return result;
         }
         nfc_protocol->DisableNfc();
         LOG_ERROR(Input, "Error enabling NFC");
+        return result;
     }
 
     if (hidbus_enabled && supported_features.hidbus) {
         auto result = ring_protocol->EnableRingCon();
-        if (result == DriverResult::Success) {
+        if (result == Common::Input::DriverResult::Success) {
             result = ring_protocol->StartRingconPolling();
         }
-        if (result == DriverResult::Success) {
+        if (result == Common::Input::DriverResult::Success) {
             ring_connected = true;
-            disable_input_thread = false;
             return result;
         }
         ring_connected = false;
         ring_protocol->DisableRingCon();
         LOG_ERROR(Input, "Error enabling Ringcon");
+        return result;
     }
 
     if (passive_enabled && supported_features.passive) {
         const auto result = generic_protocol->EnablePassiveMode();
-        if (result == DriverResult::Success) {
-            disable_input_thread = false;
+        if (result == Common::Input::DriverResult::Success) {
             return result;
         }
         LOG_ERROR(Input, "Error enabling passive mode");
@@ -322,13 +333,12 @@ DriverResult JoyconDriver::SetPollingMode() {
 
     // Default Mode
     const auto result = generic_protocol->EnableActiveMode();
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         LOG_ERROR(Input, "Error enabling active mode");
     }
     // Switch calls this function after enabling active mode
     generic_protocol->TriggersElapsed();
 
-    disable_input_thread = false;
     return result;
 }
 
@@ -339,6 +349,10 @@ JoyconDriver::SupportedFeatures JoyconDriver::GetSupportedFeatures() {
         .vibration = true,
     };
 
+    if (input_only_device) {
+        return features;
+    }
+
     if (device_type == ControllerType::Right) {
         features.nfc = true;
         features.irs = true;
@@ -383,26 +397,26 @@ bool JoyconDriver::IsPayloadCorrect(int status, std::span<const u8> buffer) {
     return true;
 }
 
-DriverResult JoyconDriver::SetVibration(const VibrationValue& vibration) {
+Common::Input::DriverResult JoyconDriver::SetVibration(const VibrationValue& vibration) {
     std::scoped_lock lock{mutex};
     if (disable_input_thread) {
-        return DriverResult::HandleInUse;
+        return Common::Input::DriverResult::HandleInUse;
     }
     return rumble_protocol->SendVibration(vibration);
 }
 
-DriverResult JoyconDriver::SetLedConfig(u8 led_pattern) {
+Common::Input::DriverResult JoyconDriver::SetLedConfig(u8 led_pattern) {
     std::scoped_lock lock{mutex};
     if (disable_input_thread) {
-        return DriverResult::HandleInUse;
+        return Common::Input::DriverResult::HandleInUse;
     }
     return generic_protocol->SetLedPattern(led_pattern);
 }
 
-DriverResult JoyconDriver::SetIrsConfig(IrsMode mode_, IrsResolution format_) {
+Common::Input::DriverResult JoyconDriver::SetIrsConfig(IrsMode mode_, IrsResolution format_) {
     std::scoped_lock lock{mutex};
     if (disable_input_thread) {
-        return DriverResult::HandleInUse;
+        return Common::Input::DriverResult::HandleInUse;
     }
     disable_input_thread = true;
     const auto result = irs_protocol->SetIrsConfig(mode_, format_);
@@ -410,7 +424,7 @@ DriverResult JoyconDriver::SetIrsConfig(IrsMode mode_, IrsResolution format_) {
     return result;
 }
 
-DriverResult JoyconDriver::SetPassiveMode() {
+Common::Input::DriverResult JoyconDriver::SetPassiveMode() {
     std::scoped_lock lock{mutex};
     motion_enabled = false;
     hidbus_enabled = false;
@@ -420,7 +434,7 @@ DriverResult JoyconDriver::SetPassiveMode() {
     return SetPollingMode();
 }
 
-DriverResult JoyconDriver::SetActiveMode() {
+Common::Input::DriverResult JoyconDriver::SetActiveMode() {
     if (is_ring_disabled_by_irs) {
         is_ring_disabled_by_irs = false;
         SetActiveMode();
@@ -436,11 +450,11 @@ DriverResult JoyconDriver::SetActiveMode() {
     return SetPollingMode();
 }
 
-DriverResult JoyconDriver::SetIrMode() {
+Common::Input::DriverResult JoyconDriver::SetIrMode() {
     std::scoped_lock lock{mutex};
 
     if (!supported_features.irs) {
-        return DriverResult::NotSupported;
+        return Common::Input::DriverResult::NotSupported;
     }
 
     if (ring_connected) {
@@ -455,11 +469,11 @@ DriverResult JoyconDriver::SetIrMode() {
     return SetPollingMode();
 }
 
-DriverResult JoyconDriver::SetNfcMode() {
+Common::Input::DriverResult JoyconDriver::SetNfcMode() {
     std::scoped_lock lock{mutex};
 
     if (!supported_features.nfc) {
-        return DriverResult::NotSupported;
+        return Common::Input::DriverResult::NotSupported;
     }
 
     motion_enabled = true;
@@ -470,11 +484,11 @@ DriverResult JoyconDriver::SetNfcMode() {
     return SetPollingMode();
 }
 
-DriverResult JoyconDriver::SetRingConMode() {
+Common::Input::DriverResult JoyconDriver::SetRingConMode() {
     std::scoped_lock lock{mutex};
 
     if (!supported_features.hidbus) {
-        return DriverResult::NotSupported;
+        return Common::Input::DriverResult::NotSupported;
     }
 
     motion_enabled = true;
@@ -486,29 +500,130 @@ DriverResult JoyconDriver::SetRingConMode() {
     const auto result = SetPollingMode();
 
     if (!ring_connected) {
-        return DriverResult::NoDeviceDetected;
+        return Common::Input::DriverResult::NoDeviceDetected;
+    }
+
+    return result;
+}
+
+Common::Input::DriverResult JoyconDriver::StartNfcPolling() {
+    std::scoped_lock lock{mutex};
+
+    if (!supported_features.nfc) {
+        return Common::Input::DriverResult::NotSupported;
+    }
+    if (!nfc_protocol->IsEnabled()) {
+        return Common::Input::DriverResult::Disabled;
     }
 
+    disable_input_thread = true;
+    const auto result = nfc_protocol->StartNFCPollingMode();
+    disable_input_thread = false;
+
     return result;
 }
 
-DriverResult JoyconDriver::WriteNfcData(std::span<const u8> data) {
+Common::Input::DriverResult JoyconDriver::StopNfcPolling() {
     std::scoped_lock lock{mutex};
+
+    if (!supported_features.nfc) {
+        return Common::Input::DriverResult::NotSupported;
+    }
+    if (!nfc_protocol->IsEnabled()) {
+        return Common::Input::DriverResult::Disabled;
+    }
+
     disable_input_thread = true;
+    const auto result = nfc_protocol->StopNFCPollingMode();
+    disable_input_thread = false;
+
+    if (amiibo_detected) {
+        amiibo_detected = false;
+        joycon_poller->UpdateAmiibo({});
+    }
+
+    return result;
+}
+
+Common::Input::DriverResult JoyconDriver::ReadAmiiboData(std::vector<u8>& out_data) {
+    std::scoped_lock lock{mutex};
 
     if (!supported_features.nfc) {
-        return DriverResult::NotSupported;
+        return Common::Input::DriverResult::NotSupported;
     }
     if (!nfc_protocol->IsEnabled()) {
-        return DriverResult::Disabled;
+        return Common::Input::DriverResult::Disabled;
     }
     if (!amiibo_detected) {
-        return DriverResult::ErrorWritingData;
+        return Common::Input::DriverResult::ErrorWritingData;
     }
 
+    out_data.resize(0x21C);
+    disable_input_thread = true;
+    const auto result = nfc_protocol->ReadAmiibo(out_data);
+    disable_input_thread = false;
+
+    return result;
+}
+
+Common::Input::DriverResult JoyconDriver::WriteNfcData(std::span<const u8> data) {
+    std::scoped_lock lock{mutex};
+
+    if (!supported_features.nfc) {
+        return Common::Input::DriverResult::NotSupported;
+    }
+    if (!nfc_protocol->IsEnabled()) {
+        return Common::Input::DriverResult::Disabled;
+    }
+    if (!amiibo_detected) {
+        return Common::Input::DriverResult::ErrorWritingData;
+    }
+
+    disable_input_thread = true;
     const auto result = nfc_protocol->WriteAmiibo(data);
+    disable_input_thread = false;
+
+    return result;
+}
 
+Common::Input::DriverResult JoyconDriver::ReadMifareData(std::span<const MifareReadChunk> data,
+                                                         std::span<MifareReadData> out_data) {
+    std::scoped_lock lock{mutex};
+
+    if (!supported_features.nfc) {
+        return Common::Input::DriverResult::NotSupported;
+    }
+    if (!nfc_protocol->IsEnabled()) {
+        return Common::Input::DriverResult::Disabled;
+    }
+    if (!amiibo_detected) {
+        return Common::Input::DriverResult::ErrorWritingData;
+    }
+
+    disable_input_thread = true;
+    const auto result = nfc_protocol->ReadMifare(data, out_data);
     disable_input_thread = false;
+
+    return result;
+}
+
+Common::Input::DriverResult JoyconDriver::WriteMifareData(std::span<const MifareWriteChunk> data) {
+    std::scoped_lock lock{mutex};
+
+    if (!supported_features.nfc) {
+        return Common::Input::DriverResult::NotSupported;
+    }
+    if (!nfc_protocol->IsEnabled()) {
+        return Common::Input::DriverResult::Disabled;
+    }
+    if (!amiibo_detected) {
+        return Common::Input::DriverResult::ErrorWritingData;
+    }
+
+    disable_input_thread = true;
+    const auto result = nfc_protocol->WriteMifare(data);
+    disable_input_thread = false;
+
     return result;
 }
 
@@ -561,8 +676,8 @@ void JoyconDriver::SetCallbacks(const JoyconCallbacks& callbacks) {
     joycon_poller->SetCallbacks(callbacks);
 }
 
-DriverResult JoyconDriver::GetDeviceType(SDL_hid_device_info* device_info,
-                                         ControllerType& controller_type) {
+Common::Input::DriverResult JoyconDriver::GetDeviceType(SDL_hid_device_info* device_info,
+                                                        ControllerType& controller_type) {
     static constexpr std::array<std::pair<u32, ControllerType>, 6> supported_devices{
         std::pair<u32, ControllerType>{0x2006, ControllerType::Left},
         {0x2007, ControllerType::Right},
@@ -572,25 +687,25 @@ DriverResult JoyconDriver::GetDeviceType(SDL_hid_device_info* device_info,
 
     controller_type = ControllerType::None;
     if (device_info->vendor_id != nintendo_vendor_id) {
-        return DriverResult::UnsupportedControllerType;
+        return Common::Input::DriverResult::UnsupportedControllerType;
     }
 
     for (const auto& [product_id, type] : supported_devices) {
         if (device_info->product_id == static_cast<u16>(product_id)) {
             controller_type = type;
-            return Joycon::DriverResult::Success;
+            return Common::Input::DriverResult::Success;
         }
     }
-    return Joycon::DriverResult::UnsupportedControllerType;
+    return Common::Input::DriverResult::UnsupportedControllerType;
 }
 
-DriverResult JoyconDriver::GetSerialNumber(SDL_hid_device_info* device_info,
-                                           SerialNumber& serial_number) {
+Common::Input::DriverResult JoyconDriver::GetSerialNumber(SDL_hid_device_info* device_info,
+                                                          SerialNumber& serial_number) {
     if (device_info->serial_number == nullptr) {
-        return DriverResult::Unknown;
+        return Common::Input::DriverResult::Unknown;
     }
     std::memcpy(&serial_number, device_info->serial_number, 15);
-    return Joycon::DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
 } // namespace InputCommon::Joycon
diff --git a/src/input_common/helpers/joycon_driver.h b/src/input_common/helpers/joycon_driver.h
index e9b2fccbb..335e12cc3 100644
--- a/src/input_common/helpers/joycon_driver.h
+++ b/src/input_common/helpers/joycon_driver.h
@@ -11,6 +11,10 @@
 
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
+namespace Common::Input {
+enum class DriverResult;
+}
+
 namespace InputCommon::Joycon {
 class CalibrationProtocol;
 class GenericProtocol;
@@ -26,8 +30,8 @@ public:
 
     ~JoyconDriver();
 
-    DriverResult RequestDeviceAccess(SDL_hid_device_info* device_info);
-    DriverResult InitializeDevice();
+    Common::Input::DriverResult RequestDeviceAccess(SDL_hid_device_info* device_info);
+    Common::Input::DriverResult InitializeDevice();
     void Stop();
 
     bool IsConnected() const;
@@ -41,25 +45,31 @@ public:
     SerialNumber GetSerialNumber() const;
     SerialNumber GetHandleSerialNumber() const;
 
-    DriverResult SetVibration(const VibrationValue& vibration);
-    DriverResult SetLedConfig(u8 led_pattern);
-    DriverResult SetIrsConfig(IrsMode mode_, IrsResolution format_);
-    DriverResult SetPassiveMode();
-    DriverResult SetActiveMode();
-    DriverResult SetIrMode();
-    DriverResult SetNfcMode();
-    DriverResult SetRingConMode();
-    DriverResult WriteNfcData(std::span<const u8> data);
+    Common::Input::DriverResult SetVibration(const VibrationValue& vibration);
+    Common::Input::DriverResult SetLedConfig(u8 led_pattern);
+    Common::Input::DriverResult SetIrsConfig(IrsMode mode_, IrsResolution format_);
+    Common::Input::DriverResult SetPassiveMode();
+    Common::Input::DriverResult SetActiveMode();
+    Common::Input::DriverResult SetIrMode();
+    Common::Input::DriverResult SetNfcMode();
+    Common::Input::DriverResult SetRingConMode();
+    Common::Input::DriverResult StartNfcPolling();
+    Common::Input::DriverResult StopNfcPolling();
+    Common::Input::DriverResult ReadAmiiboData(std::vector<u8>& out_data);
+    Common::Input::DriverResult WriteNfcData(std::span<const u8> data);
+    Common::Input::DriverResult ReadMifareData(std::span<const MifareReadChunk> request,
+                                               std::span<MifareReadData> out_data);
+    Common::Input::DriverResult WriteMifareData(std::span<const MifareWriteChunk> request);
 
     void SetCallbacks(const JoyconCallbacks& callbacks);
 
     // Returns device type from hidapi handle
-    static DriverResult GetDeviceType(SDL_hid_device_info* device_info,
-                                      ControllerType& controller_type);
+    static Common::Input::DriverResult GetDeviceType(SDL_hid_device_info* device_info,
+                                                     ControllerType& controller_type);
 
     // Returns serial number from hidapi handle
-    static DriverResult GetSerialNumber(SDL_hid_device_info* device_info,
-                                        SerialNumber& serial_number);
+    static Common::Input::DriverResult GetSerialNumber(SDL_hid_device_info* device_info,
+                                                       SerialNumber& serial_number);
 
 private:
     struct SupportedFeatures {
@@ -78,7 +88,7 @@ private:
     void OnNewData(std::span<u8> buffer);
 
     /// Updates device configuration to enable or disable features
-    DriverResult SetPollingMode();
+    Common::Input::DriverResult SetPollingMode();
 
     /// Returns true if input thread is valid and doesn't need to be stopped
     bool IsInputThreadValid() const;
@@ -114,6 +124,7 @@ private:
     // Hardware configuration
     u8 leds{};
     ReportMode mode{};
+    bool input_only_device{};
     bool passive_enabled{};   // Low power mode, Ideal for multiple controllers at the same time
     bool hidbus_enabled{};    // External device support
     bool irs_enabled{};       // Infrared camera input
diff --git a/src/input_common/helpers/joycon_protocol/calibration.cpp b/src/input_common/helpers/joycon_protocol/calibration.cpp
index d8f040f75..1300ecaf5 100644
--- a/src/input_common/helpers/joycon_protocol/calibration.cpp
+++ b/src/input_common/helpers/joycon_protocol/calibration.cpp
@@ -3,6 +3,7 @@
 
 #include <cstring>
 
+#include "common/input.h"
 #include "input_common/helpers/joycon_protocol/calibration.h"
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
@@ -11,28 +12,29 @@ namespace InputCommon::Joycon {
 CalibrationProtocol::CalibrationProtocol(std::shared_ptr<JoyconHandle> handle)
     : JoyconCommonProtocol(std::move(handle)) {}
 
-DriverResult CalibrationProtocol::GetLeftJoyStickCalibration(JoyStickCalibration& calibration) {
+Common::Input::DriverResult CalibrationProtocol::GetLeftJoyStickCalibration(
+    JoyStickCalibration& calibration) {
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     JoystickLeftSpiCalibration spi_calibration{};
     bool has_user_calibration = false;
     calibration = {};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = HasUserCalibration(SpiAddress::USER_LEFT_MAGIC, has_user_calibration);
     }
 
     // Read User defined calibration
-    if (result == DriverResult::Success && has_user_calibration) {
+    if (result == Common::Input::DriverResult::Success && has_user_calibration) {
         result = ReadSPI(SpiAddress::USER_LEFT_DATA, spi_calibration);
     }
 
     // Read Factory calibration
-    if (result == DriverResult::Success && !has_user_calibration) {
+    if (result == Common::Input::DriverResult::Success && !has_user_calibration) {
         result = ReadSPI(SpiAddress::FACT_LEFT_DATA, spi_calibration);
     }
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         calibration.x.center = GetXAxisCalibrationValue(spi_calibration.center);
         calibration.y.center = GetYAxisCalibrationValue(spi_calibration.center);
         calibration.x.min = GetXAxisCalibrationValue(spi_calibration.min);
@@ -47,28 +49,29 @@ DriverResult CalibrationProtocol::GetLeftJoyStickCalibration(JoyStickCalibration
     return result;
 }
 
-DriverResult CalibrationProtocol::GetRightJoyStickCalibration(JoyStickCalibration& calibration) {
+Common::Input::DriverResult CalibrationProtocol::GetRightJoyStickCalibration(
+    JoyStickCalibration& calibration) {
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     JoystickRightSpiCalibration spi_calibration{};
     bool has_user_calibration = false;
     calibration = {};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = HasUserCalibration(SpiAddress::USER_RIGHT_MAGIC, has_user_calibration);
     }
 
     // Read User defined calibration
-    if (result == DriverResult::Success && has_user_calibration) {
+    if (result == Common::Input::DriverResult::Success && has_user_calibration) {
         result = ReadSPI(SpiAddress::USER_RIGHT_DATA, spi_calibration);
     }
 
     // Read Factory calibration
-    if (result == DriverResult::Success && !has_user_calibration) {
+    if (result == Common::Input::DriverResult::Success && !has_user_calibration) {
         result = ReadSPI(SpiAddress::FACT_RIGHT_DATA, spi_calibration);
     }
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         calibration.x.center = GetXAxisCalibrationValue(spi_calibration.center);
         calibration.y.center = GetYAxisCalibrationValue(spi_calibration.center);
         calibration.x.min = GetXAxisCalibrationValue(spi_calibration.min);
@@ -83,28 +86,28 @@ DriverResult CalibrationProtocol::GetRightJoyStickCalibration(JoyStickCalibratio
     return result;
 }
 
-DriverResult CalibrationProtocol::GetImuCalibration(MotionCalibration& calibration) {
+Common::Input::DriverResult CalibrationProtocol::GetImuCalibration(MotionCalibration& calibration) {
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     ImuSpiCalibration spi_calibration{};
     bool has_user_calibration = false;
     calibration = {};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = HasUserCalibration(SpiAddress::USER_IMU_MAGIC, has_user_calibration);
     }
 
     // Read User defined calibration
-    if (result == DriverResult::Success && has_user_calibration) {
+    if (result == Common::Input::DriverResult::Success && has_user_calibration) {
         result = ReadSPI(SpiAddress::USER_IMU_DATA, spi_calibration);
     }
 
     // Read Factory calibration
-    if (result == DriverResult::Success && !has_user_calibration) {
+    if (result == Common::Input::DriverResult::Success && !has_user_calibration) {
         result = ReadSPI(SpiAddress::FACT_IMU_DATA, spi_calibration);
     }
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         calibration.accelerometer[0].offset = spi_calibration.accelerometer_offset[0];
         calibration.accelerometer[1].offset = spi_calibration.accelerometer_offset[1];
         calibration.accelerometer[2].offset = spi_calibration.accelerometer_offset[2];
@@ -127,8 +130,8 @@ DriverResult CalibrationProtocol::GetImuCalibration(MotionCalibration& calibrati
     return result;
 }
 
-DriverResult CalibrationProtocol::GetRingCalibration(RingCalibration& calibration,
-                                                     s16 current_value) {
+Common::Input::DriverResult CalibrationProtocol::GetRingCalibration(RingCalibration& calibration,
+                                                                    s16 current_value) {
     constexpr s16 DefaultRingRange{800};
 
     // TODO: Get default calibration form ring itself
@@ -144,15 +147,15 @@ DriverResult CalibrationProtocol::GetRingCalibration(RingCalibration& calibratio
         .max_value = ring_data_max,
         .min_value = ring_data_min,
     };
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult CalibrationProtocol::HasUserCalibration(SpiAddress address,
-                                                     bool& has_user_calibration) {
+Common::Input::DriverResult CalibrationProtocol::HasUserCalibration(SpiAddress address,
+                                                                    bool& has_user_calibration) {
     MagicSpiCalibration spi_magic{};
-    const DriverResult result{ReadSPI(address, spi_magic)};
+    const Common::Input::DriverResult result{ReadSPI(address, spi_magic)};
     has_user_calibration = false;
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         has_user_calibration = spi_magic.first == CalibrationMagic::USR_MAGIC_0 &&
                                spi_magic.second == CalibrationMagic::USR_MAGIC_1;
     }
diff --git a/src/input_common/helpers/joycon_protocol/calibration.h b/src/input_common/helpers/joycon_protocol/calibration.h
index c6fd0f729..82d94b366 100644
--- a/src/input_common/helpers/joycon_protocol/calibration.h
+++ b/src/input_common/helpers/joycon_protocol/calibration.h
@@ -12,8 +12,11 @@
 
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 
-namespace InputCommon::Joycon {
+namespace Common::Input {
 enum class DriverResult;
+}
+
+namespace InputCommon::Joycon {
 struct JoyStickCalibration;
 struct IMUCalibration;
 struct JoyconHandle;
@@ -31,30 +34,30 @@ public:
      * @param is_factory_calibration if true factory values will be returned
      * @returns JoyStickCalibration of the left joystick
      */
-    DriverResult GetLeftJoyStickCalibration(JoyStickCalibration& calibration);
+    Common::Input::DriverResult GetLeftJoyStickCalibration(JoyStickCalibration& calibration);
 
     /**
      * Sends a request to obtain the right stick calibration from memory
      * @param is_factory_calibration if true factory values will be returned
      * @returns JoyStickCalibration of the right joystick
      */
-    DriverResult GetRightJoyStickCalibration(JoyStickCalibration& calibration);
+    Common::Input::DriverResult GetRightJoyStickCalibration(JoyStickCalibration& calibration);
 
     /**
      * Sends a request to obtain the motion calibration from memory
      * @returns ImuCalibration of the motion sensor
      */
-    DriverResult GetImuCalibration(MotionCalibration& calibration);
+    Common::Input::DriverResult GetImuCalibration(MotionCalibration& calibration);
 
     /**
      * Calculates on run time the proper calibration of the ring controller
      * @returns RingCalibration of the ring sensor
      */
-    DriverResult GetRingCalibration(RingCalibration& calibration, s16 current_value);
+    Common::Input::DriverResult GetRingCalibration(RingCalibration& calibration, s16 current_value);
 
 private:
     /// Returns true if the specified address corresponds to the magic value of user calibration
-    DriverResult HasUserCalibration(SpiAddress address, bool& has_user_calibration);
+    Common::Input::DriverResult HasUserCalibration(SpiAddress address, bool& has_user_calibration);
 
     /// Converts a raw calibration block to an u16 value containing the x axis value
     u16 GetXAxisCalibrationValue(std::span<u8> block) const;
diff --git a/src/input_common/helpers/joycon_protocol/common_protocol.cpp b/src/input_common/helpers/joycon_protocol/common_protocol.cpp
index 51669261a..a6eecf980 100644
--- a/src/input_common/helpers/joycon_protocol/common_protocol.cpp
+++ b/src/input_common/helpers/joycon_protocol/common_protocol.cpp
@@ -1,6 +1,7 @@
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "common/input.h"
 #include "common/logging/log.h"
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 
@@ -21,10 +22,10 @@ void JoyconCommonProtocol::SetNonBlocking() {
     SDL_hid_set_nonblocking(hidapi_handle->handle, 1);
 }
 
-DriverResult JoyconCommonProtocol::GetDeviceType(ControllerType& controller_type) {
+Common::Input::DriverResult JoyconCommonProtocol::GetDeviceType(ControllerType& controller_type) {
     const auto result = ReadSPI(SpiAddress::DEVICE_TYPE, controller_type);
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         // Fallback to 3rd party pro controllers
         if (controller_type == ControllerType::None) {
             controller_type = ControllerType::Pro;
@@ -34,12 +35,13 @@ DriverResult JoyconCommonProtocol::GetDeviceType(ControllerType& controller_type
     return result;
 }
 
-DriverResult JoyconCommonProtocol::CheckDeviceAccess(SDL_hid_device_info* device_info) {
+Common::Input::DriverResult JoyconCommonProtocol::CheckDeviceAccess(
+    SDL_hid_device_info* device_info) {
     ControllerType controller_type{ControllerType::None};
     const auto result = GetDeviceType(controller_type);
 
-    if (result != DriverResult::Success || controller_type == ControllerType::None) {
-        return DriverResult::UnsupportedControllerType;
+    if (result != Common::Input::DriverResult::Success || controller_type == ControllerType::None) {
+        return Common::Input::DriverResult::UnsupportedControllerType;
     }
 
     hidapi_handle->handle =
@@ -48,32 +50,32 @@ DriverResult JoyconCommonProtocol::CheckDeviceAccess(SDL_hid_device_info* device
     if (!hidapi_handle->handle) {
         LOG_ERROR(Input, "Yuzu can't gain access to this device: ID {:04X}:{:04X}.",
                   device_info->vendor_id, device_info->product_id);
-        return DriverResult::HandleInUse;
+        return Common::Input::DriverResult::HandleInUse;
     }
 
     SetNonBlocking();
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconCommonProtocol::SetReportMode(ReportMode report_mode) {
+Common::Input::DriverResult JoyconCommonProtocol::SetReportMode(ReportMode report_mode) {
     const std::array<u8, 1> buffer{static_cast<u8>(report_mode)};
     return SendSubCommand(SubCommand::SET_REPORT_MODE, buffer);
 }
 
-DriverResult JoyconCommonProtocol::SendRawData(std::span<const u8> buffer) {
+Common::Input::DriverResult JoyconCommonProtocol::SendRawData(std::span<const u8> buffer) {
     const auto result = SDL_hid_write(hidapi_handle->handle, buffer.data(), buffer.size());
 
     if (result == -1) {
-        return DriverResult::ErrorWritingData;
+        return Common::Input::DriverResult::ErrorWritingData;
     }
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconCommonProtocol::GetSubCommandResponse(SubCommand sc,
-                                                         SubCommandResponse& output) {
+Common::Input::DriverResult JoyconCommonProtocol::GetSubCommandResponse(
+    SubCommand sc, SubCommandResponse& output) {
     constexpr int timeout_mili = 66;
-    constexpr int MaxTries = 15;
+    constexpr int MaxTries = 10;
     int tries = 0;
 
     do {
@@ -84,16 +86,17 @@ DriverResult JoyconCommonProtocol::GetSubCommandResponse(SubCommand sc,
             LOG_ERROR(Input, "No response from joycon");
         }
         if (tries++ > MaxTries) {
-            return DriverResult::Timeout;
+            return Common::Input::DriverResult::Timeout;
         }
     } while (output.input_report.report_mode != ReportMode::SUBCMD_REPLY &&
              output.sub_command != sc);
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconCommonProtocol::SendSubCommand(SubCommand sc, std::span<const u8> buffer,
-                                                  SubCommandResponse& output) {
+Common::Input::DriverResult JoyconCommonProtocol::SendSubCommand(SubCommand sc,
+                                                                 std::span<const u8> buffer,
+                                                                 SubCommandResponse& output) {
     SubCommandPacket packet{
         .output_report = OutputReport::RUMBLE_AND_SUBCMD,
         .packet_counter = GetCounter(),
@@ -102,28 +105,28 @@ DriverResult JoyconCommonProtocol::SendSubCommand(SubCommand sc, std::span<const
     };
 
     if (buffer.size() > packet.command_data.size()) {
-        return DriverResult::InvalidParameters;
+        return Common::Input::DriverResult::InvalidParameters;
     }
 
     memcpy(packet.command_data.data(), buffer.data(), buffer.size());
 
     auto result = SendData(packet);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return result;
     }
 
-    result = GetSubCommandResponse(sc, output);
-
-    return DriverResult::Success;
+    return GetSubCommandResponse(sc, output);
 }
 
-DriverResult JoyconCommonProtocol::SendSubCommand(SubCommand sc, std::span<const u8> buffer) {
+Common::Input::DriverResult JoyconCommonProtocol::SendSubCommand(SubCommand sc,
+                                                                 std::span<const u8> buffer) {
     SubCommandResponse output{};
     return SendSubCommand(sc, buffer, output);
 }
 
-DriverResult JoyconCommonProtocol::SendMCUCommand(SubCommand sc, std::span<const u8> buffer) {
+Common::Input::DriverResult JoyconCommonProtocol::SendMCUCommand(SubCommand sc,
+                                                                 std::span<const u8> buffer) {
     SubCommandPacket packet{
         .output_report = OutputReport::MCU_DATA,
         .packet_counter = GetCounter(),
@@ -132,7 +135,7 @@ DriverResult JoyconCommonProtocol::SendMCUCommand(SubCommand sc, std::span<const
     };
 
     if (buffer.size() > packet.command_data.size()) {
-        return DriverResult::InvalidParameters;
+        return Common::Input::DriverResult::InvalidParameters;
     }
 
     memcpy(packet.command_data.data(), buffer.data(), buffer.size());
@@ -140,7 +143,7 @@ DriverResult JoyconCommonProtocol::SendMCUCommand(SubCommand sc, std::span<const
     return SendData(packet);
 }
 
-DriverResult JoyconCommonProtocol::SendVibrationReport(std::span<const u8> buffer) {
+Common::Input::DriverResult JoyconCommonProtocol::SendVibrationReport(std::span<const u8> buffer) {
     VibrationPacket packet{
         .output_report = OutputReport::RUMBLE_ONLY,
         .packet_counter = GetCounter(),
@@ -148,7 +151,7 @@ DriverResult JoyconCommonProtocol::SendVibrationReport(std::span<const u8> buffe
     };
 
     if (buffer.size() > packet.vibration_data.size()) {
-        return DriverResult::InvalidParameters;
+        return Common::Input::DriverResult::InvalidParameters;
     }
 
     memcpy(packet.vibration_data.data(), buffer.data(), buffer.size());
@@ -156,9 +159,10 @@ DriverResult JoyconCommonProtocol::SendVibrationReport(std::span<const u8> buffe
     return SendData(packet);
 }
 
-DriverResult JoyconCommonProtocol::ReadRawSPI(SpiAddress addr, std::span<u8> output) {
+Common::Input::DriverResult JoyconCommonProtocol::ReadRawSPI(SpiAddress addr,
+                                                             std::span<u8> output) {
     constexpr std::size_t HeaderSize = 5;
-    constexpr std::size_t MaxTries = 10;
+    constexpr std::size_t MaxTries = 5;
     std::size_t tries = 0;
     SubCommandResponse response{};
     std::array<u8, sizeof(ReadSpiPacket)> buffer{};
@@ -170,36 +174,36 @@ DriverResult JoyconCommonProtocol::ReadRawSPI(SpiAddress addr, std::span<u8> out
     memcpy(buffer.data(), &packet_data, sizeof(ReadSpiPacket));
     do {
         const auto result = SendSubCommand(SubCommand::SPI_FLASH_READ, buffer, response);
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
 
         if (tries++ > MaxTries) {
-            return DriverResult::Timeout;
+            return Common::Input::DriverResult::Timeout;
         }
     } while (response.spi_address != addr);
 
     if (response.command_data.size() < packet_data.size + HeaderSize) {
-        return DriverResult::WrongReply;
+        return Common::Input::DriverResult::WrongReply;
     }
 
     // Remove header from output
     memcpy(output.data(), response.command_data.data() + HeaderSize, packet_data.size);
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconCommonProtocol::EnableMCU(bool enable) {
+Common::Input::DriverResult JoyconCommonProtocol::EnableMCU(bool enable) {
     const std::array<u8, 1> mcu_state{static_cast<u8>(enable ? 1 : 0)};
     const auto result = SendSubCommand(SubCommand::SET_MCU_STATE, mcu_state);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         LOG_ERROR(Input, "Failed with error {}", result);
     }
 
     return result;
 }
 
-DriverResult JoyconCommonProtocol::ConfigureMCU(const MCUConfig& config) {
+Common::Input::DriverResult JoyconCommonProtocol::ConfigureMCU(const MCUConfig& config) {
     LOG_DEBUG(Input, "ConfigureMCU");
     std::array<u8, sizeof(MCUConfig)> config_buffer;
     memcpy(config_buffer.data(), &config, sizeof(MCUConfig));
@@ -207,15 +211,15 @@ DriverResult JoyconCommonProtocol::ConfigureMCU(const MCUConfig& config) {
 
     const auto result = SendSubCommand(SubCommand::SET_MCU_CONFIG, config_buffer);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         LOG_ERROR(Input, "Failed with error {}", result);
     }
 
     return result;
 }
 
-DriverResult JoyconCommonProtocol::GetMCUDataResponse(ReportMode report_mode,
-                                                      MCUCommandResponse& output) {
+Common::Input::DriverResult JoyconCommonProtocol::GetMCUDataResponse(ReportMode report_mode,
+                                                                     MCUCommandResponse& output) {
     constexpr int TimeoutMili = 200;
     constexpr int MaxTries = 9;
     int tries = 0;
@@ -228,17 +232,18 @@ DriverResult JoyconCommonProtocol::GetMCUDataResponse(ReportMode report_mode,
             LOG_ERROR(Input, "No response from joycon attempt {}", tries);
         }
         if (tries++ > MaxTries) {
-            return DriverResult::Timeout;
+            return Common::Input::DriverResult::Timeout;
         }
     } while (output.input_report.report_mode != report_mode ||
              output.mcu_report == MCUReport::EmptyAwaitingCmd);
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconCommonProtocol::SendMCUData(ReportMode report_mode, MCUSubCommand sc,
-                                               std::span<const u8> buffer,
-                                               MCUCommandResponse& output) {
+Common::Input::DriverResult JoyconCommonProtocol::SendMCUData(ReportMode report_mode,
+                                                              MCUSubCommand sc,
+                                                              std::span<const u8> buffer,
+                                                              MCUCommandResponse& output) {
     SubCommandPacket packet{
         .output_report = OutputReport::MCU_DATA,
         .packet_counter = GetCounter(),
@@ -247,23 +252,24 @@ DriverResult JoyconCommonProtocol::SendMCUData(ReportMode report_mode, MCUSubCom
     };
 
     if (buffer.size() > packet.command_data.size()) {
-        return DriverResult::InvalidParameters;
+        return Common::Input::DriverResult::InvalidParameters;
     }
 
     memcpy(packet.command_data.data(), buffer.data(), buffer.size());
 
     auto result = SendData(packet);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return result;
     }
 
     result = GetMCUDataResponse(report_mode, output);
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult JoyconCommonProtocol::WaitSetMCUMode(ReportMode report_mode, MCUMode mode) {
+Common::Input::DriverResult JoyconCommonProtocol::WaitSetMCUMode(ReportMode report_mode,
+                                                                 MCUMode mode) {
     MCUCommandResponse output{};
     constexpr std::size_t MaxTries{16};
     std::size_t tries{};
@@ -271,17 +277,17 @@ DriverResult JoyconCommonProtocol::WaitSetMCUMode(ReportMode report_mode, MCUMod
     do {
         const auto result = SendMCUData(report_mode, MCUSubCommand::SetDeviceMode, {}, output);
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
 
         if (tries++ > MaxTries) {
-            return DriverResult::WrongReply;
+            return Common::Input::DriverResult::WrongReply;
         }
     } while (output.mcu_report != MCUReport::StateReport ||
              output.mcu_data[6] != static_cast<u8>(mode));
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
 // crc-8-ccitt / polynomial 0x07 look up table
diff --git a/src/input_common/helpers/joycon_protocol/common_protocol.h b/src/input_common/helpers/joycon_protocol/common_protocol.h
index 411ec018a..dd667ca2b 100644
--- a/src/input_common/helpers/joycon_protocol/common_protocol.h
+++ b/src/input_common/helpers/joycon_protocol/common_protocol.h
@@ -38,30 +38,30 @@ public:
      * Sends a request to obtain the joycon type from device
      * @returns controller type of the joycon
      */
-    DriverResult GetDeviceType(ControllerType& controller_type);
+    Common::Input::DriverResult GetDeviceType(ControllerType& controller_type);
 
     /**
      * Verifies and sets the joycon_handle if device is valid
      * @param device info from the driver
      * @returns success if the device is valid
      */
-    DriverResult CheckDeviceAccess(SDL_hid_device_info* device);
+    Common::Input::DriverResult CheckDeviceAccess(SDL_hid_device_info* device);
 
     /**
      * Sends a request to set the polling mode of the joycon
      * @param report_mode polling mode to be set
      */
-    DriverResult SetReportMode(Joycon::ReportMode report_mode);
+    Common::Input::DriverResult SetReportMode(Joycon::ReportMode report_mode);
 
     /**
      * Sends data to the joycon device
      * @param buffer data to be send
      */
-    DriverResult SendRawData(std::span<const u8> buffer);
+    Common::Input::DriverResult SendRawData(std::span<const u8> buffer);
 
     template <typename Output>
         requires std::is_trivially_copyable_v<Output>
-    DriverResult SendData(const Output& output) {
+    Common::Input::DriverResult SendData(const Output& output) {
         std::array<u8, sizeof(Output)> buffer;
         std::memcpy(buffer.data(), &output, sizeof(Output));
         return SendRawData(buffer);
@@ -72,7 +72,8 @@ public:
      * @param sub_command type of data to be returned
      * @returns a buffer containing the response
      */
-    DriverResult GetSubCommandResponse(SubCommand sub_command, SubCommandResponse& output);
+    Common::Input::DriverResult GetSubCommandResponse(SubCommand sub_command,
+                                                      SubCommandResponse& output);
 
     /**
      * Sends a sub command to the device and waits for it's reply
@@ -80,35 +81,35 @@ public:
      * @param buffer data to be send
      * @returns output buffer containing the response
      */
-    DriverResult SendSubCommand(SubCommand sc, std::span<const u8> buffer,
-                                SubCommandResponse& output);
+    Common::Input::DriverResult SendSubCommand(SubCommand sc, std::span<const u8> buffer,
+                                               SubCommandResponse& output);
 
     /**
      * Sends a sub command to the device and waits for it's reply and ignores the output
      * @param sc sub command to be send
      * @param buffer data to be send
      */
-    DriverResult SendSubCommand(SubCommand sc, std::span<const u8> buffer);
+    Common::Input::DriverResult SendSubCommand(SubCommand sc, std::span<const u8> buffer);
 
     /**
      * Sends a mcu command to the device
      * @param sc sub command to be send
      * @param buffer data to be send
      */
-    DriverResult SendMCUCommand(SubCommand sc, std::span<const u8> buffer);
+    Common::Input::DriverResult SendMCUCommand(SubCommand sc, std::span<const u8> buffer);
 
     /**
      * Sends vibration data to the joycon
      * @param buffer data to be send
      */
-    DriverResult SendVibrationReport(std::span<const u8> buffer);
+    Common::Input::DriverResult SendVibrationReport(std::span<const u8> buffer);
 
     /**
      * Reads the SPI memory stored on the joycon
      * @param Initial address location
      * @returns output buffer containing the response
      */
-    DriverResult ReadRawSPI(SpiAddress addr, std::span<u8> output);
+    Common::Input::DriverResult ReadRawSPI(SpiAddress addr, std::span<u8> output);
 
     /**
      * Reads the SPI memory stored on the joycon
@@ -117,37 +118,38 @@ public:
      */
     template <typename Output>
         requires std::is_trivially_copyable_v<Output>
-    DriverResult ReadSPI(SpiAddress addr, Output& output) {
+    Common::Input::DriverResult ReadSPI(SpiAddress addr, Output& output) {
         std::array<u8, sizeof(Output)> buffer;
         output = {};
 
         const auto result = ReadRawSPI(addr, buffer);
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
 
         std::memcpy(&output, buffer.data(), sizeof(Output));
-        return DriverResult::Success;
+        return Common::Input::DriverResult::Success;
     }
 
     /**
      * Enables MCU chip on the joycon
      * @param enable if true the chip will be enabled
      */
-    DriverResult EnableMCU(bool enable);
+    Common::Input::DriverResult EnableMCU(bool enable);
 
     /**
      * Configures the MCU to the corresponding mode
      * @param MCUConfig configuration
      */
-    DriverResult ConfigureMCU(const MCUConfig& config);
+    Common::Input::DriverResult ConfigureMCU(const MCUConfig& config);
 
     /**
      * Waits until there's MCU data available. On timeout returns error
      * @param report mode of the expected reply
      * @returns a buffer containing the response
      */
-    DriverResult GetMCUDataResponse(ReportMode report_mode_, MCUCommandResponse& output);
+    Common::Input::DriverResult GetMCUDataResponse(ReportMode report_mode_,
+                                                   MCUCommandResponse& output);
 
     /**
      * Sends data to the MCU chip and waits for it's reply
@@ -156,15 +158,15 @@ public:
      * @param buffer data to be send
      * @returns output buffer containing the response
      */
-    DriverResult SendMCUData(ReportMode report_mode, MCUSubCommand sc, std::span<const u8> buffer,
-                             MCUCommandResponse& output);
+    Common::Input::DriverResult SendMCUData(ReportMode report_mode, MCUSubCommand sc,
+                                            std::span<const u8> buffer, MCUCommandResponse& output);
 
     /**
      * Wait's until the MCU chip is on the specified mode
      * @param report mode of the expected reply
      * @param MCUMode configuration
      */
-    DriverResult WaitSetMCUMode(ReportMode report_mode, MCUMode mode);
+    Common::Input::DriverResult WaitSetMCUMode(ReportMode report_mode, MCUMode mode);
 
     /**
      * Calculates the checksum from the MCU data
diff --git a/src/input_common/helpers/joycon_protocol/generic_functions.cpp b/src/input_common/helpers/joycon_protocol/generic_functions.cpp
index 548a4b9e3..e9a056448 100644
--- a/src/input_common/helpers/joycon_protocol/generic_functions.cpp
+++ b/src/input_common/helpers/joycon_protocol/generic_functions.cpp
@@ -1,6 +1,7 @@
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "common/input.h"
 #include "common/logging/log.h"
 #include "input_common/helpers/joycon_protocol/generic_functions.h"
 
@@ -9,73 +10,74 @@ namespace InputCommon::Joycon {
 GenericProtocol::GenericProtocol(std::shared_ptr<JoyconHandle> handle)
     : JoyconCommonProtocol(std::move(handle)) {}
 
-DriverResult GenericProtocol::EnablePassiveMode() {
+Common::Input::DriverResult GenericProtocol::EnablePassiveMode() {
     ScopedSetBlocking sb(this);
     return SetReportMode(ReportMode::SIMPLE_HID_MODE);
 }
 
-DriverResult GenericProtocol::EnableActiveMode() {
+Common::Input::DriverResult GenericProtocol::EnableActiveMode() {
     ScopedSetBlocking sb(this);
     return SetReportMode(ReportMode::STANDARD_FULL_60HZ);
 }
 
-DriverResult GenericProtocol::SetLowPowerMode(bool enable) {
+Common::Input::DriverResult GenericProtocol::SetLowPowerMode(bool enable) {
     ScopedSetBlocking sb(this);
     const std::array<u8, 1> buffer{static_cast<u8>(enable ? 1 : 0)};
     return SendSubCommand(SubCommand::LOW_POWER_MODE, buffer);
 }
 
-DriverResult GenericProtocol::TriggersElapsed() {
+Common::Input::DriverResult GenericProtocol::TriggersElapsed() {
     ScopedSetBlocking sb(this);
     return SendSubCommand(SubCommand::TRIGGERS_ELAPSED, {});
 }
 
-DriverResult GenericProtocol::GetDeviceInfo(DeviceInfo& device_info) {
+Common::Input::DriverResult GenericProtocol::GetDeviceInfo(DeviceInfo& device_info) {
     ScopedSetBlocking sb(this);
     SubCommandResponse output{};
 
     const auto result = SendSubCommand(SubCommand::REQ_DEV_INFO, {}, output);
 
     device_info = {};
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         device_info = output.device_info;
     }
 
     return result;
 }
 
-DriverResult GenericProtocol::GetControllerType(ControllerType& controller_type) {
+Common::Input::DriverResult GenericProtocol::GetControllerType(ControllerType& controller_type) {
     return GetDeviceType(controller_type);
 }
 
-DriverResult GenericProtocol::EnableImu(bool enable) {
+Common::Input::DriverResult GenericProtocol::EnableImu(bool enable) {
     ScopedSetBlocking sb(this);
     const std::array<u8, 1> buffer{static_cast<u8>(enable ? 1 : 0)};
     return SendSubCommand(SubCommand::ENABLE_IMU, buffer);
 }
 
-DriverResult GenericProtocol::SetImuConfig(GyroSensitivity gsen, GyroPerformance gfrec,
-                                           AccelerometerSensitivity asen,
-                                           AccelerometerPerformance afrec) {
+Common::Input::DriverResult GenericProtocol::SetImuConfig(GyroSensitivity gsen,
+                                                          GyroPerformance gfrec,
+                                                          AccelerometerSensitivity asen,
+                                                          AccelerometerPerformance afrec) {
     ScopedSetBlocking sb(this);
     const std::array<u8, 4> buffer{static_cast<u8>(gsen), static_cast<u8>(asen),
                                    static_cast<u8>(gfrec), static_cast<u8>(afrec)};
     return SendSubCommand(SubCommand::SET_IMU_SENSITIVITY, buffer);
 }
 
-DriverResult GenericProtocol::GetBattery(u32& battery_level) {
+Common::Input::DriverResult GenericProtocol::GetBattery(u32& battery_level) {
     // This function is meant to request the high resolution battery status
     battery_level = 0;
-    return DriverResult::NotSupported;
+    return Common::Input::DriverResult::NotSupported;
 }
 
-DriverResult GenericProtocol::GetColor(Color& color) {
+Common::Input::DriverResult GenericProtocol::GetColor(Color& color) {
     ScopedSetBlocking sb(this);
     std::array<u8, 12> buffer{};
     const auto result = ReadRawSPI(SpiAddress::COLOR_DATA, buffer);
 
     color = {};
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         color.body = static_cast<u32>((buffer[0] << 16) | (buffer[1] << 8) | buffer[2]);
         color.buttons = static_cast<u32>((buffer[3] << 16) | (buffer[4] << 8) | buffer[5]);
         color.left_grip = static_cast<u32>((buffer[6] << 16) | (buffer[7] << 8) | buffer[8]);
@@ -85,26 +87,26 @@ DriverResult GenericProtocol::GetColor(Color& color) {
     return result;
 }
 
-DriverResult GenericProtocol::GetSerialNumber(SerialNumber& serial_number) {
+Common::Input::DriverResult GenericProtocol::GetSerialNumber(SerialNumber& serial_number) {
     ScopedSetBlocking sb(this);
     std::array<u8, 16> buffer{};
     const auto result = ReadRawSPI(SpiAddress::SERIAL_NUMBER, buffer);
 
     serial_number = {};
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         memcpy(serial_number.data(), buffer.data() + 1, sizeof(SerialNumber));
     }
 
     return result;
 }
 
-DriverResult GenericProtocol::GetTemperature(u32& temperature) {
+Common::Input::DriverResult GenericProtocol::GetTemperature(u32& temperature) {
     // Not all devices have temperature sensor
     temperature = 25;
-    return DriverResult::NotSupported;
+    return Common::Input::DriverResult::NotSupported;
 }
 
-DriverResult GenericProtocol::GetVersionNumber(FirmwareVersion& version) {
+Common::Input::DriverResult GenericProtocol::GetVersionNumber(FirmwareVersion& version) {
     DeviceInfo device_info{};
 
     const auto result = GetDeviceInfo(device_info);
@@ -113,23 +115,23 @@ DriverResult GenericProtocol::GetVersionNumber(FirmwareVersion& version) {
     return result;
 }
 
-DriverResult GenericProtocol::SetHomeLight() {
+Common::Input::DriverResult GenericProtocol::SetHomeLight() {
     ScopedSetBlocking sb(this);
     static constexpr std::array<u8, 3> buffer{0x0f, 0xf0, 0x00};
     return SendSubCommand(SubCommand::SET_HOME_LIGHT, buffer);
 }
 
-DriverResult GenericProtocol::SetLedBusy() {
-    return DriverResult::NotSupported;
+Common::Input::DriverResult GenericProtocol::SetLedBusy() {
+    return Common::Input::DriverResult::NotSupported;
 }
 
-DriverResult GenericProtocol::SetLedPattern(u8 leds) {
+Common::Input::DriverResult GenericProtocol::SetLedPattern(u8 leds) {
     ScopedSetBlocking sb(this);
     const std::array<u8, 1> buffer{leds};
     return SendSubCommand(SubCommand::SET_PLAYER_LIGHTS, buffer);
 }
 
-DriverResult GenericProtocol::SetLedBlinkPattern(u8 leds) {
+Common::Input::DriverResult GenericProtocol::SetLedBlinkPattern(u8 leds) {
     return SetLedPattern(static_cast<u8>(leds << 4));
 }
 
diff --git a/src/input_common/helpers/joycon_protocol/generic_functions.h b/src/input_common/helpers/joycon_protocol/generic_functions.h
index 424831e81..90fcd17f6 100644
--- a/src/input_common/helpers/joycon_protocol/generic_functions.h
+++ b/src/input_common/helpers/joycon_protocol/generic_functions.h
@@ -11,6 +11,10 @@
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
+namespace Common::Input {
+enum class DriverResult;
+}
+
 namespace InputCommon::Joycon {
 
 /// Joycon driver functions that easily implemented
@@ -20,34 +24,34 @@ public:
 
     /// Enables passive mode. This mode only sends button data on change. Sticks will return digital
     /// data instead of analog. Motion will be disabled
-    DriverResult EnablePassiveMode();
+    Common::Input::DriverResult EnablePassiveMode();
 
     /// Enables active mode. This mode will return the current status every 5-15ms
-    DriverResult EnableActiveMode();
+    Common::Input::DriverResult EnableActiveMode();
 
     /// Enables or disables the low power mode
-    DriverResult SetLowPowerMode(bool enable);
+    Common::Input::DriverResult SetLowPowerMode(bool enable);
 
     /// Unknown function used by the switch
-    DriverResult TriggersElapsed();
+    Common::Input::DriverResult TriggersElapsed();
 
     /**
      * Sends a request to obtain the joycon firmware and mac from handle
      * @returns controller device info
      */
-    DriverResult GetDeviceInfo(DeviceInfo& controller_type);
+    Common::Input::DriverResult GetDeviceInfo(DeviceInfo& controller_type);
 
     /**
      * Sends a request to obtain the joycon type from handle
      * @returns controller type of the joycon
      */
-    DriverResult GetControllerType(ControllerType& controller_type);
+    Common::Input::DriverResult GetControllerType(ControllerType& controller_type);
 
     /**
      * Enables motion input
      * @param enable if true motion data will be enabled
      */
-    DriverResult EnableImu(bool enable);
+    Common::Input::DriverResult EnableImu(bool enable);
 
     /**
      * Configures the motion sensor with the specified parameters
@@ -56,59 +60,60 @@ public:
      * @param asen accelerometer sensitivity in G force
      * @param afrec accelerometer frequency in hertz
      */
-    DriverResult SetImuConfig(GyroSensitivity gsen, GyroPerformance gfrec,
-                              AccelerometerSensitivity asen, AccelerometerPerformance afrec);
+    Common::Input::DriverResult SetImuConfig(GyroSensitivity gsen, GyroPerformance gfrec,
+                                             AccelerometerSensitivity asen,
+                                             AccelerometerPerformance afrec);
 
     /**
      * Request battery level from the device
      * @returns battery level
      */
-    DriverResult GetBattery(u32& battery_level);
+    Common::Input::DriverResult GetBattery(u32& battery_level);
 
     /**
      * Request joycon colors from the device
      * @returns colors of the body and buttons
      */
-    DriverResult GetColor(Color& color);
+    Common::Input::DriverResult GetColor(Color& color);
 
     /**
      * Request joycon serial number from the device
      * @returns 16 byte serial number
      */
-    DriverResult GetSerialNumber(SerialNumber& serial_number);
+    Common::Input::DriverResult GetSerialNumber(SerialNumber& serial_number);
 
     /**
      * Request joycon serial number from the device
      * @returns 16 byte serial number
      */
-    DriverResult GetTemperature(u32& temperature);
+    Common::Input::DriverResult GetTemperature(u32& temperature);
 
     /**
      * Request joycon serial number from the device
      * @returns 16 byte serial number
      */
-    DriverResult GetVersionNumber(FirmwareVersion& version);
+    Common::Input::DriverResult GetVersionNumber(FirmwareVersion& version);
 
     /**
      * Sets home led behaviour
      */
-    DriverResult SetHomeLight();
+    Common::Input::DriverResult SetHomeLight();
 
     /**
      * Sets home led into a slow breathing state
      */
-    DriverResult SetLedBusy();
+    Common::Input::DriverResult SetLedBusy();
 
     /**
      * Sets the 4 player leds on the joycon on a solid state
      * @params bit flag containing the led state
      */
-    DriverResult SetLedPattern(u8 leds);
+    Common::Input::DriverResult SetLedPattern(u8 leds);
 
     /**
      * Sets the 4 player leds on the joycon on a blinking state
      * @returns bit flag containing the led state
      */
-    DriverResult SetLedBlinkPattern(u8 leds);
+    Common::Input::DriverResult SetLedBlinkPattern(u8 leds);
 };
 } // namespace InputCommon::Joycon
diff --git a/src/input_common/helpers/joycon_protocol/irs.cpp b/src/input_common/helpers/joycon_protocol/irs.cpp
index 731fd5981..68b0589e3 100644
--- a/src/input_common/helpers/joycon_protocol/irs.cpp
+++ b/src/input_common/helpers/joycon_protocol/irs.cpp
@@ -1,7 +1,7 @@
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <thread>
+#include "common/input.h"
 #include "common/logging/log.h"
 #include "input_common/helpers/joycon_protocol/irs.h"
 
@@ -10,21 +10,21 @@ namespace InputCommon::Joycon {
 IrsProtocol::IrsProtocol(std::shared_ptr<JoyconHandle> handle)
     : JoyconCommonProtocol(std::move(handle)) {}
 
-DriverResult IrsProtocol::EnableIrs() {
+Common::Input::DriverResult IrsProtocol::EnableIrs() {
     LOG_INFO(Input, "Enable IRS");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = SetReportMode(ReportMode::NFC_IR_MODE_60HZ);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = EnableMCU(true);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitSetMCUMode(ReportMode::NFC_IR_MODE_60HZ, MCUMode::Standby);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         const MCUConfig config{
             .command = MCUCommand::ConfigureMCU,
             .sub_command = MCUSubCommand::SetMCUMode,
@@ -34,16 +34,16 @@ DriverResult IrsProtocol::EnableIrs() {
 
         result = ConfigureMCU(config);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitSetMCUMode(ReportMode::NFC_IR_MODE_60HZ, MCUMode::IR);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = ConfigureIrs();
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WriteRegistersStep1();
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WriteRegistersStep2();
     }
 
@@ -52,12 +52,12 @@ DriverResult IrsProtocol::EnableIrs() {
     return result;
 }
 
-DriverResult IrsProtocol::DisableIrs() {
+Common::Input::DriverResult IrsProtocol::DisableIrs() {
     LOG_DEBUG(Input, "Disable IRS");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = EnableMCU(false);
     }
 
@@ -66,7 +66,7 @@ DriverResult IrsProtocol::DisableIrs() {
     return result;
 }
 
-DriverResult IrsProtocol::SetIrsConfig(IrsMode mode, IrsResolution format) {
+Common::Input::DriverResult IrsProtocol::SetIrsConfig(IrsMode mode, IrsResolution format) {
     irs_mode = mode;
     switch (format) {
     case IrsResolution::Size320x240:
@@ -103,10 +103,10 @@ DriverResult IrsProtocol::SetIrsConfig(IrsMode mode, IrsResolution format) {
         return EnableIrs();
     }
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult IrsProtocol::RequestImage(std::span<u8> buffer) {
+Common::Input::DriverResult IrsProtocol::RequestImage(std::span<u8> buffer) {
     const u8 next_packet_fragment =
         static_cast<u8>((packet_fragment + 1) % (static_cast<u8>(fragments) + 1));
 
@@ -129,7 +129,7 @@ DriverResult IrsProtocol::RequestImage(std::span<u8> buffer) {
     return RequestFrame(packet_fragment);
 }
 
-DriverResult IrsProtocol::ConfigureIrs() {
+Common::Input::DriverResult IrsProtocol::ConfigureIrs() {
     LOG_DEBUG(Input, "Configure IRS");
     constexpr std::size_t max_tries = 28;
     SubCommandResponse output{};
@@ -152,20 +152,20 @@ DriverResult IrsProtocol::ConfigureIrs() {
     do {
         const auto result = SendSubCommand(SubCommand::SET_MCU_CONFIG, request_data, output);
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
         if (tries++ >= max_tries) {
-            return DriverResult::WrongReply;
+            return Common::Input::DriverResult::WrongReply;
         }
     } while (output.command_data[0] != 0x0b);
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult IrsProtocol::WriteRegistersStep1() {
+Common::Input::DriverResult IrsProtocol::WriteRegistersStep1() {
     LOG_DEBUG(Input, "WriteRegistersStep1");
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     constexpr std::size_t max_tries = 28;
     SubCommandResponse output{};
     std::size_t tries = 0;
@@ -197,7 +197,7 @@ DriverResult IrsProtocol::WriteRegistersStep1() {
     mcu_request[36] = CalculateMCU_CRC8(mcu_request.data(), 36);
     mcu_request[37] = 0xFF;
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return result;
     }
 
@@ -205,26 +205,26 @@ DriverResult IrsProtocol::WriteRegistersStep1() {
         result = SendSubCommand(SubCommand::SET_MCU_CONFIG, request_data, output);
 
         // First time we need to set the report mode
-        if (result == DriverResult::Success && tries == 0) {
+        if (result == Common::Input::DriverResult::Success && tries == 0) {
             result = SendMCUCommand(SubCommand::SET_REPORT_MODE, mcu_request);
         }
-        if (result == DriverResult::Success && tries == 0) {
+        if (result == Common::Input::DriverResult::Success && tries == 0) {
             GetSubCommandResponse(SubCommand::SET_MCU_CONFIG, output);
         }
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
         if (tries++ >= max_tries) {
-            return DriverResult::WrongReply;
+            return Common::Input::DriverResult::WrongReply;
         }
     } while (!(output.command_data[0] == 0x13 && output.command_data[2] == 0x07) &&
              output.command_data[0] != 0x23);
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult IrsProtocol::WriteRegistersStep2() {
+Common::Input::DriverResult IrsProtocol::WriteRegistersStep2() {
     LOG_DEBUG(Input, "WriteRegistersStep2");
     constexpr std::size_t max_tries = 28;
     SubCommandResponse output{};
@@ -255,18 +255,18 @@ DriverResult IrsProtocol::WriteRegistersStep2() {
     do {
         const auto result = SendSubCommand(SubCommand::SET_MCU_CONFIG, request_data, output);
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
         if (tries++ >= max_tries) {
-            return DriverResult::WrongReply;
+            return Common::Input::DriverResult::WrongReply;
         }
     } while (output.command_data[0] != 0x13 && output.command_data[0] != 0x23);
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult IrsProtocol::RequestFrame(u8 frame) {
+Common::Input::DriverResult IrsProtocol::RequestFrame(u8 frame) {
     std::array<u8, 38> mcu_request{};
     mcu_request[3] = frame;
     mcu_request[36] = CalculateMCU_CRC8(mcu_request.data(), 36);
@@ -274,7 +274,7 @@ DriverResult IrsProtocol::RequestFrame(u8 frame) {
     return SendMCUCommand(SubCommand::SET_REPORT_MODE, mcu_request);
 }
 
-DriverResult IrsProtocol::ResendFrame(u8 frame) {
+Common::Input::DriverResult IrsProtocol::ResendFrame(u8 frame) {
     std::array<u8, 38> mcu_request{};
     mcu_request[1] = 0x1;
     mcu_request[2] = frame;
diff --git a/src/input_common/helpers/joycon_protocol/irs.h b/src/input_common/helpers/joycon_protocol/irs.h
index 76dfa02ea..714cbb6b2 100644
--- a/src/input_common/helpers/joycon_protocol/irs.h
+++ b/src/input_common/helpers/joycon_protocol/irs.h
@@ -13,19 +13,23 @@
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
+namespace Common::Input {
+enum class DriverResult;
+}
+
 namespace InputCommon::Joycon {
 
 class IrsProtocol final : private JoyconCommonProtocol {
 public:
     explicit IrsProtocol(std::shared_ptr<JoyconHandle> handle);
 
-    DriverResult EnableIrs();
+    Common::Input::DriverResult EnableIrs();
 
-    DriverResult DisableIrs();
+    Common::Input::DriverResult DisableIrs();
 
-    DriverResult SetIrsConfig(IrsMode mode, IrsResolution format);
+    Common::Input::DriverResult SetIrsConfig(IrsMode mode, IrsResolution format);
 
-    DriverResult RequestImage(std::span<u8> buffer);
+    Common::Input::DriverResult RequestImage(std::span<u8> buffer);
 
     std::vector<u8> GetImage() const;
 
@@ -34,13 +38,13 @@ public:
     bool IsEnabled() const;
 
 private:
-    DriverResult ConfigureIrs();
+    Common::Input::DriverResult ConfigureIrs();
 
-    DriverResult WriteRegistersStep1();
-    DriverResult WriteRegistersStep2();
+    Common::Input::DriverResult WriteRegistersStep1();
+    Common::Input::DriverResult WriteRegistersStep2();
 
-    DriverResult RequestFrame(u8 frame);
-    DriverResult ResendFrame(u8 frame);
+    Common::Input::DriverResult RequestFrame(u8 frame);
+    Common::Input::DriverResult ResendFrame(u8 frame);
 
     IrsMode irs_mode{IrsMode::ImageTransfer};
     IrsResolution resolution{IrsResolution::Size40x30};
diff --git a/src/input_common/helpers/joycon_protocol/joycon_types.h b/src/input_common/helpers/joycon_protocol/joycon_types.h
index 5007b0e18..77a43c67a 100644
--- a/src/input_common/helpers/joycon_protocol/joycon_types.h
+++ b/src/input_common/helpers/joycon_protocol/joycon_types.h
@@ -24,6 +24,7 @@ constexpr std::array<u8, 8> DefaultVibrationBuffer{0x0, 0x1, 0x40, 0x40, 0x0, 0x
 using MacAddress = std::array<u8, 6>;
 using SerialNumber = std::array<u8, 15>;
 using TagUUID = std::array<u8, 7>;
+using MifareUUID = std::array<u8, 4>;
 
 enum class ControllerType : u8 {
     None = 0x00,
@@ -307,6 +308,19 @@ enum class NFCStatus : u8 {
     WriteDone = 0x05,
     TagLost = 0x07,
     WriteReady = 0x09,
+    MifareDone = 0x10,
+};
+
+enum class MifareCmd : u8 {
+    None = 0x00,
+    Read = 0x30,
+    AuthA = 0x60,
+    AuthB = 0x61,
+    Write = 0xA0,
+    Transfer = 0xB0,
+    Decrement = 0xC0,
+    Increment = 0xC1,
+    Store = 0xC2
 };
 
 enum class IrsMode : u8 {
@@ -388,23 +402,6 @@ enum class ExternalDeviceId : u16 {
     Starlink = 0x2800,
 };
 
-enum class DriverResult {
-    Success,
-    WrongReply,
-    Timeout,
-    InvalidParameters,
-    UnsupportedControllerType,
-    HandleInUse,
-    ErrorReadingData,
-    ErrorWritingData,
-    NoDeviceDetected,
-    InvalidHandle,
-    NotSupported,
-    Disabled,
-    Delayed,
-    Unknown,
-};
-
 struct MotionSensorCalibration {
     s16 offset;
     s16 scale;
@@ -592,6 +589,14 @@ struct NFCWriteCommandData {
 static_assert(sizeof(NFCWriteCommandData) == 0x15, "NFCWriteCommandData is an invalid size");
 #pragma pack(pop)
 
+struct MifareCommandData {
+    u8 unknown1;
+    u8 unknown2;
+    u8 number_of_short_bytes;
+    MifareUUID uid;
+};
+static_assert(sizeof(MifareCommandData) == 0x7, "MifareCommandData is an invalid size");
+
 struct NFCPollingCommandData {
     u8 enable_mifare;
     u8 unknown_1;
@@ -629,6 +634,41 @@ struct NFCWritePackage {
     std::array<NFCDataChunk, 4> data_chunks;
 };
 
+struct MifareReadChunk {
+    MifareCmd command;
+    std::array<u8, 0x6> sector_key;
+    u8 sector;
+};
+
+struct MifareWriteChunk {
+    MifareCmd command;
+    std::array<u8, 0x6> sector_key;
+    u8 sector;
+    std::array<u8, 0x10> data;
+};
+
+struct MifareReadData {
+    u8 sector;
+    std::array<u8, 0x10> data;
+};
+
+struct MifareReadPackage {
+    MifareCommandData command_data;
+    std::array<MifareReadChunk, 0x10> data_chunks;
+};
+
+struct MifareWritePackage {
+    MifareCommandData command_data;
+    std::array<MifareWriteChunk, 0x10> data_chunks;
+};
+
+struct TagInfo {
+    u8 uuid_length;
+    u8 protocol;
+    u8 tag_type;
+    std::array<u8, 10> uuid;
+};
+
 struct IrsConfigure {
     MCUCommand command;
     MCUSubCommand sub_command;
@@ -744,7 +784,7 @@ struct JoyconCallbacks {
     std::function<void(int, f32)> on_stick_data;
     std::function<void(int, const MotionData&)> on_motion_data;
     std::function<void(f32)> on_ring_data;
-    std::function<void(const std::vector<u8>&)> on_amiibo_data;
+    std::function<void(const Joycon::TagInfo&)> on_amiibo_data;
     std::function<void(const std::vector<u8>&, IrsResolution)> on_camera_data;
 };
 
diff --git a/src/input_common/helpers/joycon_protocol/nfc.cpp b/src/input_common/helpers/joycon_protocol/nfc.cpp
index f7058c4a7..09953394b 100644
--- a/src/input_common/helpers/joycon_protocol/nfc.cpp
+++ b/src/input_common/helpers/joycon_protocol/nfc.cpp
@@ -1,7 +1,7 @@
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <thread>
+#include "common/input.h"
 #include "common/logging/log.h"
 #include "input_common/helpers/joycon_protocol/nfc.h"
 
@@ -10,21 +10,21 @@ namespace InputCommon::Joycon {
 NfcProtocol::NfcProtocol(std::shared_ptr<JoyconHandle> handle)
     : JoyconCommonProtocol(std::move(handle)) {}
 
-DriverResult NfcProtocol::EnableNfc() {
+Common::Input::DriverResult NfcProtocol::EnableNfc() {
     LOG_INFO(Input, "Enable NFC");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = SetReportMode(ReportMode::NFC_IR_MODE_60HZ);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = EnableMCU(true);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitSetMCUMode(ReportMode::NFC_IR_MODE_60HZ, MCUMode::Standby);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         const MCUConfig config{
             .command = MCUCommand::ConfigureMCU,
             .sub_command = MCUSubCommand::SetMCUMode,
@@ -34,123 +34,240 @@ DriverResult NfcProtocol::EnableNfc() {
 
         result = ConfigureMCU(config);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitSetMCUMode(ReportMode::NFC_IR_MODE_60HZ, MCUMode::NFC);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitUntilNfcIs(NFCStatus::Ready);
     }
+    if (result == Common::Input::DriverResult::Success) {
+        MCUCommandResponse output{};
+        result = SendStopPollingRequest(output);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::Ready);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        is_enabled = true;
+    }
 
     return result;
 }
 
-DriverResult NfcProtocol::DisableNfc() {
+Common::Input::DriverResult NfcProtocol::DisableNfc() {
     LOG_DEBUG(Input, "Disable NFC");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = EnableMCU(false);
     }
 
     is_enabled = false;
+    is_polling = false;
 
     return result;
 }
 
-DriverResult NfcProtocol::StartNFCPollingMode() {
-    LOG_DEBUG(Input, "Start NFC pooling Mode");
+Common::Input::DriverResult NfcProtocol::StartNFCPollingMode() {
+    LOG_DEBUG(Input, "Start NFC polling Mode");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         MCUCommandResponse output{};
-        result = SendStopPollingRequest(output);
+        result = SendStartPollingRequest(output);
     }
-    if (result == DriverResult::Success) {
-        result = WaitUntilNfcIs(NFCStatus::Ready);
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::Polling);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        is_polling = true;
     }
-    if (result == DriverResult::Success) {
+
+    return result;
+}
+
+Common::Input::DriverResult NfcProtocol::StopNFCPollingMode() {
+    LOG_DEBUG(Input, "Stop NFC polling Mode");
+    ScopedSetBlocking sb(this);
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
+
+    if (result == Common::Input::DriverResult::Success) {
         MCUCommandResponse output{};
-        result = SendStartPollingRequest(output);
+        result = SendStopPollingRequest(output);
     }
-    if (result == DriverResult::Success) {
-        result = WaitUntilNfcIs(NFCStatus::Polling);
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::WriteReady);
     }
-    if (result == DriverResult::Success) {
-        is_enabled = true;
+    if (result == Common::Input::DriverResult::Success) {
+        is_polling = false;
     }
 
     return result;
 }
 
-DriverResult NfcProtocol::ScanAmiibo(std::vector<u8>& data) {
+Common::Input::DriverResult NfcProtocol::GetTagInfo(Joycon::TagInfo& tag_info) {
     if (update_counter++ < AMIIBO_UPDATE_DELAY) {
-        return DriverResult::Delayed;
+        return Common::Input::DriverResult::Delayed;
     }
     update_counter = 0;
 
     LOG_DEBUG(Input, "Scan for amiibos");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     TagFoundData tag_data{};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = IsTagInRange(tag_data);
     }
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
+        tag_info = {
+            .uuid_length = tag_data.uuid_size,
+            .protocol = 1,
+            .tag_type = tag_data.type,
+            .uuid = {},
+        };
+
+        memcpy(tag_info.uuid.data(), tag_data.uuid.data(), tag_data.uuid_size);
+
+        // Investigate why mifare type is not correct
+        if (tag_info.tag_type == 144) {
+            tag_info.tag_type = 1U << 6;
+        }
+
         std::string uuid_string;
         for (auto& content : tag_data.uuid) {
             uuid_string += fmt::format(" {:02x}", content);
         }
         LOG_INFO(Input, "Tag detected, type={}, uuid={}", tag_data.type, uuid_string);
+    }
+
+    return result;
+}
+
+Common::Input::DriverResult NfcProtocol::ReadAmiibo(std::vector<u8>& data) {
+    LOG_DEBUG(Input, "Scan for amiibos");
+    ScopedSetBlocking sb(this);
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
+    TagFoundData tag_data{};
+
+    if (result == Common::Input::DriverResult::Success) {
+        result = IsTagInRange(tag_data, 7);
+    }
+
+    if (result == Common::Input::DriverResult::Success) {
         result = GetAmiiboData(data);
     }
 
     return result;
 }
 
-DriverResult NfcProtocol::WriteAmiibo(std::span<const u8> data) {
+Common::Input::DriverResult NfcProtocol::WriteAmiibo(std::span<const u8> data) {
     LOG_DEBUG(Input, "Write amiibo");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     TagUUID tag_uuid = GetTagUUID(data);
     TagFoundData tag_data{};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = IsTagInRange(tag_data, 7);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         if (tag_data.uuid != tag_uuid) {
-            result = DriverResult::InvalidParameters;
+            result = Common::Input::DriverResult::InvalidParameters;
         }
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         MCUCommandResponse output{};
         result = SendStopPollingRequest(output);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitUntilNfcIs(NFCStatus::Ready);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         MCUCommandResponse output{};
         result = SendStartPollingRequest(output, true);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitUntilNfcIs(NFCStatus::WriteReady);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WriteAmiiboData(tag_uuid, data);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = WaitUntilNfcIs(NFCStatus::WriteDone);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
+        MCUCommandResponse output{};
+        result = SendStopPollingRequest(output);
+    }
+
+    return result;
+}
+
+Common::Input::DriverResult NfcProtocol::ReadMifare(std::span<const MifareReadChunk> read_request,
+                                                    std::span<MifareReadData> out_data) {
+    LOG_DEBUG(Input, "Read mifare");
+    ScopedSetBlocking sb(this);
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
+    TagFoundData tag_data{};
+    MifareUUID tag_uuid{};
+
+    if (result == Common::Input::DriverResult::Success) {
+        result = IsTagInRange(tag_data, 7);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        memcpy(tag_uuid.data(), tag_data.uuid.data(), sizeof(MifareUUID));
+        result = GetMifareData(tag_uuid, read_request, out_data);
+    }
+    if (result == Common::Input::DriverResult::Success) {
         MCUCommandResponse output{};
         result = SendStopPollingRequest(output);
     }
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::Ready);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        MCUCommandResponse output{};
+        result = SendStartPollingRequest(output, true);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::WriteReady);
+    }
+    return result;
+}
+
+Common::Input::DriverResult NfcProtocol::WriteMifare(
+    std::span<const MifareWriteChunk> write_request) {
+    LOG_DEBUG(Input, "Write mifare");
+    ScopedSetBlocking sb(this);
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
+    TagFoundData tag_data{};
+    MifareUUID tag_uuid{};
 
+    if (result == Common::Input::DriverResult::Success) {
+        result = IsTagInRange(tag_data, 7);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        memcpy(tag_uuid.data(), tag_data.uuid.data(), sizeof(MifareUUID));
+        result = WriteMifareData(tag_uuid, write_request);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        MCUCommandResponse output{};
+        result = SendStopPollingRequest(output);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::Ready);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        MCUCommandResponse output{};
+        result = SendStartPollingRequest(output, true);
+    }
+    if (result == Common::Input::DriverResult::Success) {
+        result = WaitUntilNfcIs(NFCStatus::WriteReady);
+    }
     return result;
 }
 
@@ -161,17 +278,17 @@ bool NfcProtocol::HasAmiibo() {
     update_counter = 0;
 
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     TagFoundData tag_data{};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = IsTagInRange(tag_data, 7);
     }
 
-    return result == DriverResult::Success;
+    return result == Common::Input::DriverResult::Success;
 }
 
-DriverResult NfcProtocol::WaitUntilNfcIs(NFCStatus status) {
+Common::Input::DriverResult NfcProtocol::WaitUntilNfcIs(NFCStatus status) {
     constexpr std::size_t timeout_limit = 10;
     MCUCommandResponse output{};
     std::size_t tries = 0;
@@ -179,30 +296,31 @@ DriverResult NfcProtocol::WaitUntilNfcIs(NFCStatus status) {
     do {
         auto result = SendNextPackageRequest(output, {});
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
         if (tries++ > timeout_limit) {
-            return DriverResult::Timeout;
+            return Common::Input::DriverResult::Timeout;
         }
     } while (output.mcu_report != MCUReport::NFCState ||
              (output.mcu_data[1] << 8) + output.mcu_data[0] != 0x0500 ||
              output.mcu_data[5] != 0x31 || output.mcu_data[6] != static_cast<u8>(status));
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult NfcProtocol::IsTagInRange(TagFoundData& data, std::size_t timeout_limit) {
+Common::Input::DriverResult NfcProtocol::IsTagInRange(TagFoundData& data,
+                                                      std::size_t timeout_limit) {
     MCUCommandResponse output{};
     std::size_t tries = 0;
 
     do {
         const auto result = SendNextPackageRequest(output, {});
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
         if (tries++ > timeout_limit) {
-            return DriverResult::Timeout;
+            return Common::Input::DriverResult::Timeout;
         }
     } while (output.mcu_report != MCUReport::NFCState ||
              (output.mcu_data[1] << 8) + output.mcu_data[0] != 0x0500 ||
@@ -212,10 +330,10 @@ DriverResult NfcProtocol::IsTagInRange(TagFoundData& data, std::size_t timeout_l
     data.uuid_size = std::min(output.mcu_data[14], static_cast<u8>(sizeof(TagUUID)));
     memcpy(data.uuid.data(), output.mcu_data.data() + 15, data.uuid.size());
 
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult NfcProtocol::GetAmiiboData(std::vector<u8>& ntag_data) {
+Common::Input::DriverResult NfcProtocol::GetAmiiboData(std::vector<u8>& ntag_data) {
     constexpr std::size_t timeout_limit = 60;
     MCUCommandResponse output{};
     std::size_t tries = 0;
@@ -224,7 +342,7 @@ DriverResult NfcProtocol::GetAmiiboData(std::vector<u8>& ntag_data) {
     std::size_t ntag_buffer_pos = 0;
     auto result = SendReadAmiiboRequest(output, NFCPages::Block135);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return result;
     }
 
@@ -233,14 +351,14 @@ DriverResult NfcProtocol::GetAmiiboData(std::vector<u8>& ntag_data) {
         result = SendNextPackageRequest(output, package_index);
         const auto nfc_status = static_cast<NFCStatus>(output.mcu_data[6]);
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
 
         if ((output.mcu_report == MCUReport::NFCReadData ||
              output.mcu_report == MCUReport::NFCState) &&
             nfc_status == NFCStatus::TagLost) {
-            return DriverResult::ErrorReadingData;
+            return Common::Input::DriverResult::ErrorReadingData;
         }
 
         if (output.mcu_report == MCUReport::NFCReadData && output.mcu_data[1] == 0x07) {
@@ -259,14 +377,15 @@ DriverResult NfcProtocol::GetAmiiboData(std::vector<u8>& ntag_data) {
 
         if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::LastPackage) {
             LOG_INFO(Input, "Finished reading amiibo");
-            return DriverResult::Success;
+            return Common::Input::DriverResult::Success;
         }
     }
 
-    return DriverResult::Timeout;
+    return Common::Input::DriverResult::Timeout;
 }
 
-DriverResult NfcProtocol::WriteAmiiboData(const TagUUID& tag_uuid, std::span<const u8> data) {
+Common::Input::DriverResult NfcProtocol::WriteAmiiboData(const TagUUID& tag_uuid,
+                                                         std::span<const u8> data) {
     constexpr std::size_t timeout_limit = 60;
     const auto nfc_data = MakeAmiiboWritePackage(tag_uuid, data);
     const std::vector<u8> nfc_buffer_data = SerializeWritePackage(nfc_data);
@@ -281,7 +400,7 @@ DriverResult NfcProtocol::WriteAmiiboData(const TagUUID& tag_uuid, std::span<con
 
     auto result = SendWriteAmiiboRequest(output, tag_uuid);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return result;
     }
 
@@ -290,14 +409,14 @@ DriverResult NfcProtocol::WriteAmiiboData(const TagUUID& tag_uuid, std::span<con
         result = SendNextPackageRequest(output, package_index);
         const auto nfc_status = static_cast<NFCStatus>(output.mcu_data[6]);
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success) {
             return result;
         }
 
         if ((output.mcu_report == MCUReport::NFCReadData ||
              output.mcu_report == MCUReport::NFCState) &&
             nfc_status == NFCStatus::TagLost) {
-            return DriverResult::ErrorReadingData;
+            return Common::Input::DriverResult::ErrorReadingData;
         }
 
         if (output.mcu_report == MCUReport::NFCReadData && output.mcu_data[1] == 0x07) {
@@ -326,7 +445,131 @@ DriverResult NfcProtocol::WriteAmiiboData(const TagUUID& tag_uuid, std::span<con
         if ((output.mcu_report == MCUReport::NFCReadData ||
              output.mcu_report == MCUReport::NFCState) &&
             nfc_status == NFCStatus::TagLost) {
-            return DriverResult::ErrorReadingData;
+            return Common::Input::DriverResult::ErrorReadingData;
+        }
+
+        // Increase position when data is confirmed by the joycon
+        if (output.mcu_report == MCUReport::NFCState &&
+            (output.mcu_data[1] << 8) + output.mcu_data[0] == 0x0500 &&
+            output.mcu_data[3] == block_id) {
+            block_id++;
+            current_position = next_position;
+        }
+    }
+
+    return result;
+}
+
+Common::Input::DriverResult NfcProtocol::GetMifareData(
+    const MifareUUID& tag_uuid, std::span<const MifareReadChunk> read_request,
+    std::span<MifareReadData> out_data) {
+    constexpr std::size_t timeout_limit = 60;
+    const auto nfc_data = MakeMifareReadPackage(tag_uuid, read_request);
+    const std::vector<u8> nfc_buffer_data = SerializeMifareReadPackage(nfc_data);
+    std::span<const u8> buffer(nfc_buffer_data);
+    Common::Input::DriverResult result = Common::Input::DriverResult::Success;
+    MCUCommandResponse output{};
+    u8 block_id = 1;
+    u8 package_index = 0;
+    std::size_t tries = 0;
+    std::size_t current_position = 0;
+
+    LOG_INFO(Input, "Reading Mifare data");
+
+    // Send data request. Nfc buffer size is 31, Send the data in smaller packages
+    while (current_position < buffer.size() && tries++ < timeout_limit) {
+        const std::size_t next_position =
+            std::min(current_position + sizeof(NFCRequestState::raw_data), buffer.size());
+        const std::size_t block_size = next_position - current_position;
+        const bool is_last_packet = block_size < sizeof(NFCRequestState::raw_data);
+
+        SendReadDataMifareRequest(output, block_id, is_last_packet,
+                                  buffer.subspan(current_position, block_size));
+
+        const auto nfc_status = static_cast<NFCStatus>(output.mcu_data[6]);
+
+        if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::TagLost) {
+            return Common::Input::DriverResult::ErrorReadingData;
+        }
+
+        // Increase position when data is confirmed by the joycon
+        if (output.mcu_report == MCUReport::NFCState &&
+            (output.mcu_data[1] << 8) + output.mcu_data[0] == 0x0500 &&
+            output.mcu_data[3] == block_id) {
+            block_id++;
+            current_position = next_position;
+        }
+    }
+
+    if (result != Common::Input::DriverResult::Success) {
+        return result;
+    }
+
+    // Wait for reply and save the output data
+    while (tries++ < timeout_limit) {
+        result = SendNextPackageRequest(output, package_index);
+        const auto nfc_status = static_cast<NFCStatus>(output.mcu_data[6]);
+
+        if (result != Common::Input::DriverResult::Success) {
+            return result;
+        }
+
+        if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::TagLost) {
+            return Common::Input::DriverResult::ErrorReadingData;
+        }
+
+        if (output.mcu_report == MCUReport::NFCState && output.mcu_data[1] == 0x10) {
+            constexpr std::size_t DATA_LENGHT = 0x10 + 1;
+            constexpr std::size_t DATA_START = 11;
+            const u8 number_of_elements = output.mcu_data[10];
+            for (std::size_t i = 0; i < number_of_elements; i++) {
+                out_data[i].sector = output.mcu_data[DATA_START + (i * DATA_LENGHT)];
+                memcpy(out_data[i].data.data(),
+                       output.mcu_data.data() + DATA_START + 1 + (i * DATA_LENGHT),
+                       sizeof(MifareReadData::data));
+            }
+            package_index++;
+            continue;
+        }
+
+        if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::MifareDone) {
+            LOG_INFO(Input, "Finished reading mifare");
+            break;
+        }
+    }
+
+    return result;
+}
+
+Common::Input::DriverResult NfcProtocol::WriteMifareData(
+    const MifareUUID& tag_uuid, std::span<const MifareWriteChunk> write_request) {
+    constexpr std::size_t timeout_limit = 60;
+    const auto nfc_data = MakeMifareWritePackage(tag_uuid, write_request);
+    const std::vector<u8> nfc_buffer_data = SerializeMifareWritePackage(nfc_data);
+    std::span<const u8> buffer(nfc_buffer_data);
+    Common::Input::DriverResult result = Common::Input::DriverResult::Success;
+    MCUCommandResponse output{};
+    u8 block_id = 1;
+    u8 package_index = 0;
+    std::size_t tries = 0;
+    std::size_t current_position = 0;
+
+    LOG_INFO(Input, "Writing Mifare data");
+
+    // Send data request. Nfc buffer size is 31, Send the data in smaller packages
+    while (current_position < buffer.size() && tries++ < timeout_limit) {
+        const std::size_t next_position =
+            std::min(current_position + sizeof(NFCRequestState::raw_data), buffer.size());
+        const std::size_t block_size = next_position - current_position;
+        const bool is_last_packet = block_size < sizeof(NFCRequestState::raw_data);
+
+        SendReadDataMifareRequest(output, block_id, is_last_packet,
+                                  buffer.subspan(current_position, block_size));
+
+        const auto nfc_status = static_cast<NFCStatus>(output.mcu_data[6]);
+
+        if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::TagLost) {
+            return Common::Input::DriverResult::ErrorReadingData;
         }
 
         // Increase position when data is confirmed by the joycon
@@ -338,11 +581,39 @@ DriverResult NfcProtocol::WriteAmiiboData(const TagUUID& tag_uuid, std::span<con
         }
     }
 
+    if (result != Common::Input::DriverResult::Success) {
+        return result;
+    }
+
+    // Wait for reply and ignore the output data
+    while (tries++ < timeout_limit) {
+        result = SendNextPackageRequest(output, package_index);
+        const auto nfc_status = static_cast<NFCStatus>(output.mcu_data[6]);
+
+        if (result != Common::Input::DriverResult::Success) {
+            return result;
+        }
+
+        if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::TagLost) {
+            return Common::Input::DriverResult::ErrorReadingData;
+        }
+
+        if (output.mcu_report == MCUReport::NFCState && output.mcu_data[1] == 0x10) {
+            package_index++;
+            continue;
+        }
+
+        if (output.mcu_report == MCUReport::NFCState && nfc_status == NFCStatus::MifareDone) {
+            LOG_INFO(Input, "Finished writing mifare");
+            break;
+        }
+    }
+
     return result;
 }
 
-DriverResult NfcProtocol::SendStartPollingRequest(MCUCommandResponse& output,
-                                                  bool is_second_attempt) {
+Common::Input::DriverResult NfcProtocol::SendStartPollingRequest(MCUCommandResponse& output,
+                                                                 bool is_second_attempt) {
     NFCRequestState request{
         .command_argument = NFCCommand::StartPolling,
         .block_id = {},
@@ -367,7 +638,7 @@ DriverResult NfcProtocol::SendStartPollingRequest(MCUCommandResponse& output,
                        output);
 }
 
-DriverResult NfcProtocol::SendStopPollingRequest(MCUCommandResponse& output) {
+Common::Input::DriverResult NfcProtocol::SendStopPollingRequest(MCUCommandResponse& output) {
     NFCRequestState request{
         .command_argument = NFCCommand::StopPolling,
         .block_id = {},
@@ -385,7 +656,8 @@ DriverResult NfcProtocol::SendStopPollingRequest(MCUCommandResponse& output) {
                        output);
 }
 
-DriverResult NfcProtocol::SendNextPackageRequest(MCUCommandResponse& output, u8 packet_id) {
+Common::Input::DriverResult NfcProtocol::SendNextPackageRequest(MCUCommandResponse& output,
+                                                                u8 packet_id) {
     NFCRequestState request{
         .command_argument = NFCCommand::StartWaitingRecieve,
         .block_id = {},
@@ -403,7 +675,8 @@ DriverResult NfcProtocol::SendNextPackageRequest(MCUCommandResponse& output, u8
                        output);
 }
 
-DriverResult NfcProtocol::SendReadAmiiboRequest(MCUCommandResponse& output, NFCPages ntag_pages) {
+Common::Input::DriverResult NfcProtocol::SendReadAmiiboRequest(MCUCommandResponse& output,
+                                                               NFCPages ntag_pages) {
     NFCRequestState request{
         .command_argument = NFCCommand::ReadNtag,
         .block_id = {},
@@ -428,8 +701,8 @@ DriverResult NfcProtocol::SendReadAmiiboRequest(MCUCommandResponse& output, NFCP
                        output);
 }
 
-DriverResult NfcProtocol::SendWriteAmiiboRequest(MCUCommandResponse& output,
-                                                 const TagUUID& tag_uuid) {
+Common::Input::DriverResult NfcProtocol::SendWriteAmiiboRequest(MCUCommandResponse& output,
+                                                                const TagUUID& tag_uuid) {
     NFCRequestState request{
         .command_argument = NFCCommand::ReadNtag,
         .block_id = {},
@@ -454,9 +727,10 @@ DriverResult NfcProtocol::SendWriteAmiiboRequest(MCUCommandResponse& output,
                        output);
 }
 
-DriverResult NfcProtocol::SendWriteDataAmiiboRequest(MCUCommandResponse& output, u8 block_id,
-                                                     bool is_last_packet,
-                                                     std::span<const u8> data) {
+Common::Input::DriverResult NfcProtocol::SendWriteDataAmiiboRequest(MCUCommandResponse& output,
+                                                                    u8 block_id,
+                                                                    bool is_last_packet,
+                                                                    std::span<const u8> data) {
     const auto data_size = std::min(data.size(), sizeof(NFCRequestState::raw_data));
     NFCRequestState request{
         .command_argument = NFCCommand::WriteNtag,
@@ -477,6 +751,29 @@ DriverResult NfcProtocol::SendWriteDataAmiiboRequest(MCUCommandResponse& output,
                        output);
 }
 
+Common::Input::DriverResult NfcProtocol::SendReadDataMifareRequest(MCUCommandResponse& output,
+                                                                   u8 block_id, bool is_last_packet,
+                                                                   std::span<const u8> data) {
+    const auto data_size = std::min(data.size(), sizeof(NFCRequestState::raw_data));
+    NFCRequestState request{
+        .command_argument = NFCCommand::Mifare,
+        .block_id = block_id,
+        .packet_id = {},
+        .packet_flag =
+            is_last_packet ? MCUPacketFlag::LastCommandPacket : MCUPacketFlag::MorePacketsRemaining,
+        .data_length = static_cast<u8>(data_size),
+        .raw_data = {},
+        .crc = {},
+    };
+    memcpy(request.raw_data.data(), data.data(), data_size);
+
+    std::array<u8, sizeof(NFCRequestState)> request_data{};
+    memcpy(request_data.data(), &request, sizeof(NFCRequestState));
+    request_data[36] = CalculateMCU_CRC8(request_data.data(), 36);
+    return SendMCUData(ReportMode::NFC_IR_MODE_60HZ, MCUSubCommand::ReadDeviceMode, request_data,
+                       output);
+}
+
 std::vector<u8> NfcProtocol::SerializeWritePackage(const NFCWritePackage& package) const {
     const std::size_t header_size =
         sizeof(NFCWriteCommandData) + sizeof(NFCWritePackage::number_of_chunks);
@@ -498,6 +795,48 @@ std::vector<u8> NfcProtocol::SerializeWritePackage(const NFCWritePackage& packag
     return serialized_data;
 }
 
+std::vector<u8> NfcProtocol::SerializeMifareReadPackage(const MifareReadPackage& package) const {
+    const std::size_t header_size = sizeof(MifareCommandData);
+    std::vector<u8> serialized_data(header_size);
+    std::size_t start_index = 0;
+
+    memcpy(serialized_data.data(), &package, header_size);
+    start_index += header_size;
+
+    for (const auto& data_chunk : package.data_chunks) {
+        const std::size_t chunk_size = sizeof(MifareReadChunk);
+        if (data_chunk.command == MifareCmd::None) {
+            continue;
+        }
+        serialized_data.resize(start_index + chunk_size);
+        memcpy(serialized_data.data() + start_index, &data_chunk, chunk_size);
+        start_index += chunk_size;
+    }
+
+    return serialized_data;
+}
+
+std::vector<u8> NfcProtocol::SerializeMifareWritePackage(const MifareWritePackage& package) const {
+    const std::size_t header_size = sizeof(MifareCommandData);
+    std::vector<u8> serialized_data(header_size);
+    std::size_t start_index = 0;
+
+    memcpy(serialized_data.data(), &package, header_size);
+    start_index += header_size;
+
+    for (const auto& data_chunk : package.data_chunks) {
+        const std::size_t chunk_size = sizeof(MifareWriteChunk);
+        if (data_chunk.command == MifareCmd::None) {
+            continue;
+        }
+        serialized_data.resize(start_index + chunk_size);
+        memcpy(serialized_data.data() + start_index, &data_chunk, chunk_size);
+        start_index += chunk_size;
+    }
+
+    return serialized_data;
+}
+
 NFCWritePackage NfcProtocol::MakeAmiiboWritePackage(const TagUUID& tag_uuid,
                                                     std::span<const u8> data) const {
     return {
@@ -527,6 +866,46 @@ NFCWritePackage NfcProtocol::MakeAmiiboWritePackage(const TagUUID& tag_uuid,
     };
 }
 
+MifareReadPackage NfcProtocol::MakeMifareReadPackage(
+    const MifareUUID& tag_uuid, std::span<const MifareReadChunk> read_request) const {
+    MifareReadPackage package{
+        .command_data{
+            .unknown1 = 0xd0,
+            .unknown2 = 0x07,
+            .number_of_short_bytes = static_cast<u8>(
+                ((read_request.size() * sizeof(MifareReadChunk)) + sizeof(MifareUUID)) / 2),
+            .uid = tag_uuid,
+        },
+        .data_chunks = {},
+    };
+
+    for (std::size_t i = 0; i < read_request.size() && i < package.data_chunks.size(); ++i) {
+        package.data_chunks[i] = read_request[i];
+    }
+
+    return package;
+}
+
+MifareWritePackage NfcProtocol::MakeMifareWritePackage(
+    const MifareUUID& tag_uuid, std::span<const MifareWriteChunk> read_request) const {
+    MifareWritePackage package{
+        .command_data{
+            .unknown1 = 0xd0,
+            .unknown2 = 0x07,
+            .number_of_short_bytes = static_cast<u8>(
+                ((read_request.size() * sizeof(MifareReadChunk)) + sizeof(MifareUUID) + 2) / 2),
+            .uid = tag_uuid,
+        },
+        .data_chunks = {},
+    };
+
+    for (std::size_t i = 0; i < read_request.size() && i < package.data_chunks.size(); ++i) {
+        package.data_chunks[i] = read_request[i];
+    }
+
+    return package;
+}
+
 NFCDataChunk NfcProtocol::MakeAmiiboChunk(u8 page, u8 size, std::span<const u8> data) const {
     constexpr u8 NFC_PAGE_SIZE = 4;
 
@@ -606,4 +985,8 @@ bool NfcProtocol::IsEnabled() const {
     return is_enabled;
 }
 
+bool NfcProtocol::IsPolling() const {
+    return is_polling;
+}
+
 } // namespace InputCommon::Joycon
diff --git a/src/input_common/helpers/joycon_protocol/nfc.h b/src/input_common/helpers/joycon_protocol/nfc.h
index eb58c427d..22db95170 100644
--- a/src/input_common/helpers/joycon_protocol/nfc.h
+++ b/src/input_common/helpers/joycon_protocol/nfc.h
@@ -13,26 +13,41 @@
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
+namespace Common::Input {
+enum class DriverResult;
+}
+
 namespace InputCommon::Joycon {
 
 class NfcProtocol final : private JoyconCommonProtocol {
 public:
     explicit NfcProtocol(std::shared_ptr<JoyconHandle> handle);
 
-    DriverResult EnableNfc();
+    Common::Input::DriverResult EnableNfc();
+
+    Common::Input::DriverResult DisableNfc();
+
+    Common::Input::DriverResult StartNFCPollingMode();
+
+    Common::Input::DriverResult StopNFCPollingMode();
 
-    DriverResult DisableNfc();
+    Common::Input::DriverResult GetTagInfo(Joycon::TagInfo& tag_info);
 
-    DriverResult StartNFCPollingMode();
+    Common::Input::DriverResult ReadAmiibo(std::vector<u8>& data);
 
-    DriverResult ScanAmiibo(std::vector<u8>& data);
+    Common::Input::DriverResult WriteAmiibo(std::span<const u8> data);
 
-    DriverResult WriteAmiibo(std::span<const u8> data);
+    Common::Input::DriverResult ReadMifare(std::span<const MifareReadChunk> read_request,
+                                           std::span<MifareReadData> out_data);
+
+    Common::Input::DriverResult WriteMifare(std::span<const MifareWriteChunk> write_request);
 
     bool HasAmiibo();
 
     bool IsEnabled() const;
 
+    bool IsPolling() const;
+
 private:
     // Number of times the function will be delayed until it outputs valid data
     static constexpr std::size_t AMIIBO_UPDATE_DELAY = 15;
@@ -43,39 +58,64 @@ private:
         TagUUID uuid;
     };
 
-    DriverResult WaitUntilNfcIs(NFCStatus status);
+    Common::Input::DriverResult WaitUntilNfcIs(NFCStatus status);
+
+    Common::Input::DriverResult IsTagInRange(TagFoundData& data, std::size_t timeout_limit = 1);
 
-    DriverResult IsTagInRange(TagFoundData& data, std::size_t timeout_limit = 1);
+    Common::Input::DriverResult GetAmiiboData(std::vector<u8>& data);
 
-    DriverResult GetAmiiboData(std::vector<u8>& data);
+    Common::Input::DriverResult WriteAmiiboData(const TagUUID& tag_uuid, std::span<const u8> data);
 
-    DriverResult WriteAmiiboData(const TagUUID& tag_uuid, std::span<const u8> data);
+    Common::Input::DriverResult GetMifareData(const MifareUUID& tag_uuid,
+                                              std::span<const MifareReadChunk> read_request,
+                                              std::span<MifareReadData> out_data);
 
-    DriverResult SendStartPollingRequest(MCUCommandResponse& output,
-                                         bool is_second_attempt = false);
+    Common::Input::DriverResult WriteMifareData(const MifareUUID& tag_uuid,
+                                                std::span<const MifareWriteChunk> write_request);
 
-    DriverResult SendStopPollingRequest(MCUCommandResponse& output);
+    Common::Input::DriverResult SendStartPollingRequest(MCUCommandResponse& output,
+                                                        bool is_second_attempt = false);
 
-    DriverResult SendNextPackageRequest(MCUCommandResponse& output, u8 packet_id);
+    Common::Input::DriverResult SendStopPollingRequest(MCUCommandResponse& output);
 
-    DriverResult SendReadAmiiboRequest(MCUCommandResponse& output, NFCPages ntag_pages);
+    Common::Input::DriverResult SendNextPackageRequest(MCUCommandResponse& output, u8 packet_id);
 
-    DriverResult SendWriteAmiiboRequest(MCUCommandResponse& output, const TagUUID& tag_uuid);
+    Common::Input::DriverResult SendReadAmiiboRequest(MCUCommandResponse& output,
+                                                      NFCPages ntag_pages);
 
-    DriverResult SendWriteDataAmiiboRequest(MCUCommandResponse& output, u8 block_id,
-                                            bool is_last_packet, std::span<const u8> data);
+    Common::Input::DriverResult SendWriteAmiiboRequest(MCUCommandResponse& output,
+                                                       const TagUUID& tag_uuid);
+
+    Common::Input::DriverResult SendWriteDataAmiiboRequest(MCUCommandResponse& output, u8 block_id,
+                                                           bool is_last_packet,
+                                                           std::span<const u8> data);
+
+    Common::Input::DriverResult SendReadDataMifareRequest(MCUCommandResponse& output, u8 block_id,
+                                                          bool is_last_packet,
+                                                          std::span<const u8> data);
 
     std::vector<u8> SerializeWritePackage(const NFCWritePackage& package) const;
 
+    std::vector<u8> SerializeMifareReadPackage(const MifareReadPackage& package) const;
+
+    std::vector<u8> SerializeMifareWritePackage(const MifareWritePackage& package) const;
+
     NFCWritePackage MakeAmiiboWritePackage(const TagUUID& tag_uuid, std::span<const u8> data) const;
 
     NFCDataChunk MakeAmiiboChunk(u8 page, u8 size, std::span<const u8> data) const;
 
+    MifareReadPackage MakeMifareReadPackage(const MifareUUID& tag_uuid,
+                                            std::span<const MifareReadChunk> read_request) const;
+
+    MifareWritePackage MakeMifareWritePackage(const MifareUUID& tag_uuid,
+                                              std::span<const MifareWriteChunk> read_request) const;
+
     NFCReadBlockCommand GetReadBlockCommand(NFCPages pages) const;
 
     TagUUID GetTagUUID(std::span<const u8> data) const;
 
     bool is_enabled{};
+    bool is_polling{};
     std::size_t update_counter{};
 };
 
diff --git a/src/input_common/helpers/joycon_protocol/poller.cpp b/src/input_common/helpers/joycon_protocol/poller.cpp
index dca797f7a..1aab9e12a 100644
--- a/src/input_common/helpers/joycon_protocol/poller.cpp
+++ b/src/input_common/helpers/joycon_protocol/poller.cpp
@@ -70,8 +70,8 @@ void JoyconPoller::UpdateColor(const Color& color) {
     callbacks.on_color_data(color);
 }
 
-void JoyconPoller::UpdateAmiibo(const std::vector<u8>& amiibo_data) {
-    callbacks.on_amiibo_data(amiibo_data);
+void JoyconPoller::UpdateAmiibo(const Joycon::TagInfo& tag_info) {
+    callbacks.on_amiibo_data(tag_info);
 }
 
 void JoyconPoller::UpdateCamera(const std::vector<u8>& camera_data, IrsResolution format) {
diff --git a/src/input_common/helpers/joycon_protocol/poller.h b/src/input_common/helpers/joycon_protocol/poller.h
index 0fa72c6db..3746abe5d 100644
--- a/src/input_common/helpers/joycon_protocol/poller.h
+++ b/src/input_common/helpers/joycon_protocol/poller.h
@@ -36,8 +36,8 @@ public:
 
     void UpdateColor(const Color& color);
     void UpdateRing(s16 value, const RingStatus& ring_status);
-    void UpdateAmiibo(const std::vector<u8>& amiibo_data);
-    void UpdateCamera(const std::vector<u8>& amiibo_data, IrsResolution format);
+    void UpdateAmiibo(const Joycon::TagInfo& tag_info);
+    void UpdateCamera(const std::vector<u8>& camera_data, IrsResolution format);
 
 private:
     void UpdateActiveLeftPadInput(const InputReportActive& input,
diff --git a/src/input_common/helpers/joycon_protocol/ringcon.cpp b/src/input_common/helpers/joycon_protocol/ringcon.cpp
index 190cef812..96414fb67 100644
--- a/src/input_common/helpers/joycon_protocol/ringcon.cpp
+++ b/src/input_common/helpers/joycon_protocol/ringcon.cpp
@@ -1,6 +1,7 @@
 // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "common/input.h"
 #include "common/logging/log.h"
 #include "input_common/helpers/joycon_protocol/ringcon.h"
 
@@ -9,18 +10,18 @@ namespace InputCommon::Joycon {
 RingConProtocol::RingConProtocol(std::shared_ptr<JoyconHandle> handle)
     : JoyconCommonProtocol(std::move(handle)) {}
 
-DriverResult RingConProtocol::EnableRingCon() {
+Common::Input::DriverResult RingConProtocol::EnableRingCon() {
     LOG_DEBUG(Input, "Enable Ringcon");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = SetReportMode(ReportMode::STANDARD_FULL_60HZ);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = EnableMCU(true);
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         const MCUConfig config{
             .command = MCUCommand::ConfigureMCU,
             .sub_command = MCUSubCommand::SetDeviceMode,
@@ -33,12 +34,12 @@ DriverResult RingConProtocol::EnableRingCon() {
     return result;
 }
 
-DriverResult RingConProtocol::DisableRingCon() {
+Common::Input::DriverResult RingConProtocol::DisableRingCon() {
     LOG_DEBUG(Input, "Disable RingCon");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = EnableMCU(false);
     }
 
@@ -47,29 +48,29 @@ DriverResult RingConProtocol::DisableRingCon() {
     return result;
 }
 
-DriverResult RingConProtocol::StartRingconPolling() {
+Common::Input::DriverResult RingConProtocol::StartRingconPolling() {
     LOG_DEBUG(Input, "Enable Ringcon");
     ScopedSetBlocking sb(this);
-    DriverResult result{DriverResult::Success};
+    Common::Input::DriverResult result{Common::Input::DriverResult::Success};
     bool is_connected = false;
 
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         result = IsRingConnected(is_connected);
     }
-    if (result == DriverResult::Success && is_connected) {
+    if (result == Common::Input::DriverResult::Success && is_connected) {
         LOG_INFO(Input, "Ringcon detected");
         result = ConfigureRing();
     }
-    if (result == DriverResult::Success) {
+    if (result == Common::Input::DriverResult::Success) {
         is_enabled = true;
     }
 
     return result;
 }
 
-DriverResult RingConProtocol::IsRingConnected(bool& is_connected) {
+Common::Input::DriverResult RingConProtocol::IsRingConnected(bool& is_connected) {
     LOG_DEBUG(Input, "IsRingConnected");
-    constexpr std::size_t max_tries = 28;
+    constexpr std::size_t max_tries = 42;
     SubCommandResponse output{};
     std::size_t tries = 0;
     is_connected = false;
@@ -77,20 +78,21 @@ DriverResult RingConProtocol::IsRingConnected(bool& is_connected) {
     do {
         const auto result = SendSubCommand(SubCommand::GET_EXTERNAL_DEVICE_INFO, {}, output);
 
-        if (result != DriverResult::Success) {
+        if (result != Common::Input::DriverResult::Success &&
+            result != Common::Input::DriverResult::Timeout) {
             return result;
         }
 
         if (tries++ >= max_tries) {
-            return DriverResult::NoDeviceDetected;
+            return Common::Input::DriverResult::NoDeviceDetected;
         }
     } while (output.external_device_id != ExternalDeviceId::RingController);
 
     is_connected = true;
-    return DriverResult::Success;
+    return Common::Input::DriverResult::Success;
 }
 
-DriverResult RingConProtocol::ConfigureRing() {
+Common::Input::DriverResult RingConProtocol::ConfigureRing() {
     LOG_DEBUG(Input, "ConfigureRing");
 
     static constexpr std::array<u8, 37> ring_config{
@@ -98,9 +100,10 @@ DriverResult RingConProtocol::ConfigureRing() {
         0x00, 0x00, 0x00, 0x0A, 0x64, 0x0B, 0xE6, 0xA9, 0x22, 0x00, 0x00, 0x04, 0x00,
         0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x90, 0xA8, 0xE1, 0x34, 0x36};
 
-    const DriverResult result = SendSubCommand(SubCommand::SET_EXTERNAL_FORMAT_CONFIG, ring_config);
+    const Common::Input::DriverResult result =
+        SendSubCommand(SubCommand::SET_EXTERNAL_FORMAT_CONFIG, ring_config);
 
-    if (result != DriverResult::Success) {
+    if (result != Common::Input::DriverResult::Success) {
         return result;
     }
 
diff --git a/src/input_common/helpers/joycon_protocol/ringcon.h b/src/input_common/helpers/joycon_protocol/ringcon.h
index 6e858f3fc..9f0888de3 100644
--- a/src/input_common/helpers/joycon_protocol/ringcon.h
+++ b/src/input_common/helpers/joycon_protocol/ringcon.h
@@ -13,24 +13,28 @@
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
+namespace Common::Input {
+enum class DriverResult;
+}
+
 namespace InputCommon::Joycon {
 
 class RingConProtocol final : private JoyconCommonProtocol {
 public:
     explicit RingConProtocol(std::shared_ptr<JoyconHandle> handle);
 
-    DriverResult EnableRingCon();
+    Common::Input::DriverResult EnableRingCon();
 
-    DriverResult DisableRingCon();
+    Common::Input::DriverResult DisableRingCon();
 
-    DriverResult StartRingconPolling();
+    Common::Input::DriverResult StartRingconPolling();
 
     bool IsEnabled() const;
 
 private:
-    DriverResult IsRingConnected(bool& is_connected);
+    Common::Input::DriverResult IsRingConnected(bool& is_connected);
 
-    DriverResult ConfigureRing();
+    Common::Input::DriverResult ConfigureRing();
 
     bool is_enabled{};
 };
diff --git a/src/input_common/helpers/joycon_protocol/rumble.cpp b/src/input_common/helpers/joycon_protocol/rumble.cpp
index 63b60c946..7647f505e 100644
--- a/src/input_common/helpers/joycon_protocol/rumble.cpp
+++ b/src/input_common/helpers/joycon_protocol/rumble.cpp
@@ -4,6 +4,7 @@
 #include <algorithm>
 #include <cmath>
 
+#include "common/input.h"
 #include "common/logging/log.h"
 #include "input_common/helpers/joycon_protocol/rumble.h"
 
@@ -12,14 +13,14 @@ namespace InputCommon::Joycon {
 RumbleProtocol::RumbleProtocol(std::shared_ptr<JoyconHandle> handle)
     : JoyconCommonProtocol(std::move(handle)) {}
 
-DriverResult RumbleProtocol::EnableRumble(bool is_enabled) {
+Common::Input::DriverResult RumbleProtocol::EnableRumble(bool is_enabled) {
     LOG_DEBUG(Input, "Enable Rumble");
     ScopedSetBlocking sb(this);
     const std::array<u8, 1> buffer{static_cast<u8>(is_enabled ? 1 : 0)};
     return SendSubCommand(SubCommand::ENABLE_VIBRATION, buffer);
 }
 
-DriverResult RumbleProtocol::SendVibration(const VibrationValue& vibration) {
+Common::Input::DriverResult RumbleProtocol::SendVibration(const VibrationValue& vibration) {
     std::array<u8, sizeof(DefaultVibrationBuffer)> buffer{};
 
     if (vibration.high_amplitude <= 0.0f && vibration.low_amplitude <= 0.0f) {
diff --git a/src/input_common/helpers/joycon_protocol/rumble.h b/src/input_common/helpers/joycon_protocol/rumble.h
index 6c12b7925..5e50e531a 100644
--- a/src/input_common/helpers/joycon_protocol/rumble.h
+++ b/src/input_common/helpers/joycon_protocol/rumble.h
@@ -13,15 +13,19 @@
 #include "input_common/helpers/joycon_protocol/common_protocol.h"
 #include "input_common/helpers/joycon_protocol/joycon_types.h"
 
+namespace Common::Input {
+enum class DriverResult;
+}
+
 namespace InputCommon::Joycon {
 
 class RumbleProtocol final : private JoyconCommonProtocol {
 public:
     explicit RumbleProtocol(std::shared_ptr<JoyconHandle> handle);
 
-    DriverResult EnableRumble(bool is_enabled);
+    Common::Input::DriverResult EnableRumble(bool is_enabled);
 
-    DriverResult SendVibration(const VibrationValue& vibration);
+    Common::Input::DriverResult SendVibration(const VibrationValue& vibration);
 
 private:
     u16 EncodeHighFrequency(f32 frequency) const;
diff --git a/src/input_common/input_engine.h b/src/input_common/input_engine.h
index 50b5a3dc8..c2d0cbb34 100644
--- a/src/input_common/input_engine.h
+++ b/src/input_common/input_engine.h
@@ -143,12 +143,46 @@ public:
         return Common::Input::NfcState::NotSupported;
     }
 
+    // Start scanning for nfc tags
+    virtual Common::Input::NfcState StartNfcPolling(
+        [[maybe_unused]] const PadIdentifier& identifier_) {
+        return Common::Input::NfcState::NotSupported;
+    }
+
+    // Start scanning for nfc tags
+    virtual Common::Input::NfcState StopNfcPolling(
+        [[maybe_unused]] const PadIdentifier& identifier_) {
+        return Common::Input::NfcState::NotSupported;
+    }
+
+    // Reads data from amiibo tag
+    virtual Common::Input::NfcState ReadAmiiboData(
+        [[maybe_unused]] const PadIdentifier& identifier_,
+        [[maybe_unused]] std::vector<u8>& out_data) {
+        return Common::Input::NfcState::NotSupported;
+    }
+
     // Writes data to an nfc tag
     virtual Common::Input::NfcState WriteNfcData([[maybe_unused]] const PadIdentifier& identifier,
                                                  [[maybe_unused]] const std::vector<u8>& data) {
         return Common::Input::NfcState::NotSupported;
     }
 
+    // Reads data from mifare tag
+    virtual Common::Input::NfcState ReadMifareData(
+        [[maybe_unused]] const PadIdentifier& identifier_,
+        [[maybe_unused]] const Common::Input::MifareRequest& request,
+        [[maybe_unused]] Common::Input::MifareRequest& out_data) {
+        return Common::Input::NfcState::NotSupported;
+    }
+
+    // Write data to mifare tag
+    virtual Common::Input::NfcState WriteMifareData(
+        [[maybe_unused]] const PadIdentifier& identifier_,
+        [[maybe_unused]] const Common::Input::MifareRequest& request) {
+        return Common::Input::NfcState::NotSupported;
+    }
+
     // Returns the engine name
     [[nodiscard]] const std::string& GetEngineName() const;
 
diff --git a/src/input_common/input_poller.cpp b/src/input_common/input_poller.cpp
index 380a01542..870e76ab0 100644
--- a/src/input_common/input_poller.cpp
+++ b/src/input_common/input_poller.cpp
@@ -792,8 +792,7 @@ public:
 
         const Common::Input::CallbackStatus status{
             .type = Common::Input::InputType::Nfc,
-            .nfc_status = nfc_status.state,
-            .raw_data = nfc_status.data,
+            .nfc_status = nfc_status,
         };
 
         TriggerOnChange(status);
@@ -836,10 +835,31 @@ public:
         return input_engine->SupportsNfc(identifier);
     }
 
+    Common::Input::NfcState StartNfcPolling() {
+        return input_engine->StartNfcPolling(identifier);
+    }
+
+    Common::Input::NfcState StopNfcPolling() {
+        return input_engine->StopNfcPolling(identifier);
+    }
+
+    Common::Input::NfcState ReadAmiiboData(std::vector<u8>& out_data) {
+        return input_engine->ReadAmiiboData(identifier, out_data);
+    }
+
     Common::Input::NfcState WriteNfcData(const std::vector<u8>& data) override {
         return input_engine->WriteNfcData(identifier, data);
     }
 
+    Common::Input::NfcState ReadMifareData(const Common::Input::MifareRequest& request,
+                                           Common::Input::MifareRequest& out_data) {
+        return input_engine->ReadMifareData(identifier, request, out_data);
+    }
+
+    Common::Input::NfcState WriteMifareData(const Common::Input::MifareRequest& request) {
+        return input_engine->WriteMifareData(identifier, request);
+    }
+
 private:
     const PadIdentifier identifier;
     InputEngine* input_engine;
diff --git a/src/shader_recompiler/backend/glasm/emit_glasm.cpp b/src/shader_recompiler/backend/glasm/emit_glasm.cpp
index fd4a61a4d..b795c0179 100644
--- a/src/shader_recompiler/backend/glasm/emit_glasm.cpp
+++ b/src/shader_recompiler/backend/glasm/emit_glasm.cpp
@@ -461,7 +461,7 @@ std::string EmitGLASM(const Profile& profile, const RuntimeInfo& runtime_info, I
         header += fmt::format("R{},", index);
     }
     if (program.local_memory_size > 0) {
-        header += fmt::format("lmem[{}],", program.local_memory_size);
+        header += fmt::format("lmem[{}],", Common::DivCeil(program.local_memory_size, 4U));
     }
     if (program.info.uses_fswzadd) {
         header += "FSWZA[4],FSWZB[4],";
diff --git a/src/shader_recompiler/backend/glsl/glsl_emit_context.cpp b/src/shader_recompiler/backend/glsl/glsl_emit_context.cpp
index c3c2281bb..9ff4028c2 100644
--- a/src/shader_recompiler/backend/glsl/glsl_emit_context.cpp
+++ b/src/shader_recompiler/backend/glsl/glsl_emit_context.cpp
@@ -479,7 +479,7 @@ void EmitContext::DefineGenericOutput(size_t index, u32 invocations) {
         const u32 remainder{4 - element};
         const TransformFeedbackVarying* xfb_varying{};
         const size_t xfb_varying_index{base_index + element};
-        if (xfb_varying_index < runtime_info.xfb_varyings.size()) {
+        if (xfb_varying_index < runtime_info.xfb_count) {
             xfb_varying = &runtime_info.xfb_varyings[xfb_varying_index];
             xfb_varying = xfb_varying->components > 0 ? xfb_varying : nullptr;
         }
diff --git a/src/shader_recompiler/backend/spirv/emit_spirv.cpp b/src/shader_recompiler/backend/spirv/emit_spirv.cpp
index 0f86a8004..34592a01f 100644
--- a/src/shader_recompiler/backend/spirv/emit_spirv.cpp
+++ b/src/shader_recompiler/backend/spirv/emit_spirv.cpp
@@ -387,7 +387,7 @@ void SetupSignedNanCapabilities(const Profile& profile, const IR::Program& progr
 }
 
 void SetupTransformFeedbackCapabilities(EmitContext& ctx, Id main_func) {
-    if (ctx.runtime_info.xfb_varyings.empty()) {
+    if (ctx.runtime_info.xfb_count == 0) {
         return;
     }
     ctx.AddCapability(spv::Capability::TransformFeedback);
diff --git a/src/shader_recompiler/backend/spirv/spirv_emit_context.cpp b/src/shader_recompiler/backend/spirv/spirv_emit_context.cpp
index fd15f47ea..bec5db173 100644
--- a/src/shader_recompiler/backend/spirv/spirv_emit_context.cpp
+++ b/src/shader_recompiler/backend/spirv/spirv_emit_context.cpp
@@ -160,7 +160,7 @@ void DefineGenericOutput(EmitContext& ctx, size_t index, std::optional<u32> invo
         const u32 remainder{4 - element};
         const TransformFeedbackVarying* xfb_varying{};
         const size_t xfb_varying_index{base_attr_index + element};
-        if (xfb_varying_index < ctx.runtime_info.xfb_varyings.size()) {
+        if (xfb_varying_index < ctx.runtime_info.xfb_count) {
             xfb_varying = &ctx.runtime_info.xfb_varyings[xfb_varying_index];
             xfb_varying = xfb_varying->components > 0 ? xfb_varying : nullptr;
         }
diff --git a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
index 5a4195217..70292686f 100644
--- a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
+++ b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
@@ -424,6 +424,10 @@ void VisitUsages(Info& info, IR::Inst& inst) {
         info.used_constant_buffer_types |= IR::Type::U32 | IR::Type::U32x2;
         info.used_storage_buffer_types |= IR::Type::U32 | IR::Type::U32x2 | IR::Type::U32x4;
         break;
+    case IR::Opcode::LoadLocal:
+    case IR::Opcode::WriteLocal:
+        info.uses_local_memory = true;
+        break;
     default:
         break;
     }
diff --git a/src/shader_recompiler/runtime_info.h b/src/shader_recompiler/runtime_info.h
index 3b63c249f..619c0b138 100644
--- a/src/shader_recompiler/runtime_info.h
+++ b/src/shader_recompiler/runtime_info.h
@@ -84,7 +84,8 @@ struct RuntimeInfo {
     bool glasm_use_storage_buffers{};
 
     /// Transform feedback state for each varying
-    std::vector<TransformFeedbackVarying> xfb_varyings;
+    std::array<TransformFeedbackVarying, 256> xfb_varyings{};
+    u32 xfb_count{0};
 };
 
 } // namespace Shader
diff --git a/src/shader_recompiler/shader_info.h b/src/shader_recompiler/shader_info.h
index d308db942..b4b4afd37 100644
--- a/src/shader_recompiler/shader_info.h
+++ b/src/shader_recompiler/shader_info.h
@@ -172,6 +172,7 @@ struct Info {
     bool stores_indexed_attributes{};
 
     bool stores_global_memory{};
+    bool uses_local_memory{};
 
     bool uses_fp16{};
     bool uses_fp64{};
diff --git a/src/video_core/CMakeLists.txt b/src/video_core/CMakeLists.txt
index bf6439530..3b2fe01da 100644
--- a/src/video_core/CMakeLists.txt
+++ b/src/video_core/CMakeLists.txt
@@ -220,8 +220,8 @@ add_library(video_core STATIC
     surface.h
     texture_cache/accelerated_swizzle.cpp
     texture_cache/accelerated_swizzle.h
-    texture_cache/decode_bc4.cpp
-    texture_cache/decode_bc4.h
+    texture_cache/decode_bc.cpp
+    texture_cache/decode_bc.h
     texture_cache/descriptor_table.h
     texture_cache/formatter.cpp
     texture_cache/formatter.h
@@ -279,7 +279,7 @@ add_library(video_core STATIC
 create_target_directory_groups(video_core)
 
 target_link_libraries(video_core PUBLIC common core)
-target_link_libraries(video_core PUBLIC glad shader_recompiler stb)
+target_link_libraries(video_core PUBLIC glad shader_recompiler stb bc_decoder)
 
 if (YUZU_USE_BUNDLED_FFMPEG AND NOT (WIN32 OR ANDROID))
     add_dependencies(video_core ffmpeg-build)
@@ -291,7 +291,7 @@ target_link_options(video_core PRIVATE ${FFmpeg_LDFLAGS})
 
 add_dependencies(video_core host_shaders)
 target_include_directories(video_core PRIVATE ${HOST_SHADERS_INCLUDE})
-target_link_libraries(video_core PRIVATE sirit Vulkan::Headers)
+target_link_libraries(video_core PRIVATE sirit Vulkan::Headers vma)
 
 if (ENABLE_NSIGHT_AFTERMATH)
     if (NOT DEFINED ENV{NSIGHT_AFTERMATH_SDK})
diff --git a/src/video_core/buffer_cache/buffer_cache.h b/src/video_core/buffer_cache/buffer_cache.h
index 45977d578..58a45ab67 100644
--- a/src/video_core/buffer_cache/buffer_cache.h
+++ b/src/video_core/buffer_cache/buffer_cache.h
@@ -207,7 +207,7 @@ bool BufferCache<P>::DMACopy(GPUVAddr src_address, GPUVAddr dest_address, u64 am
     if (has_new_downloads) {
         memory_tracker.MarkRegionAsGpuModified(*cpu_dest_address, amount);
     }
-    tmp_buffer.resize(amount);
+    tmp_buffer.resize_destructive(amount);
     cpu_memory.ReadBlockUnsafe(*cpu_src_address, tmp_buffer.data(), amount);
     cpu_memory.WriteBlockUnsafe(*cpu_dest_address, tmp_buffer.data(), amount);
     return true;
@@ -1279,7 +1279,7 @@ template <class P>
 typename BufferCache<P>::OverlapResult BufferCache<P>::ResolveOverlaps(VAddr cpu_addr,
                                                                        u32 wanted_size) {
     static constexpr int STREAM_LEAP_THRESHOLD = 16;
-    std::vector<BufferId> overlap_ids;
+    boost::container::small_vector<BufferId, 16> overlap_ids;
     VAddr begin = cpu_addr;
     VAddr end = cpu_addr + wanted_size;
     int stream_score = 0;
diff --git a/src/video_core/buffer_cache/buffer_cache_base.h b/src/video_core/buffer_cache/buffer_cache_base.h
index 63a120f7a..fe6068cfe 100644
--- a/src/video_core/buffer_cache/buffer_cache_base.h
+++ b/src/video_core/buffer_cache/buffer_cache_base.h
@@ -229,7 +229,7 @@ class BufferCache : public VideoCommon::ChannelSetupCaches<BufferCacheChannelInf
     using OverlapCounter = boost::icl::split_interval_map<VAddr, int>;
 
     struct OverlapResult {
-        std::vector<BufferId> ids;
+        boost::container::small_vector<BufferId, 16> ids;
         VAddr begin;
         VAddr end;
         bool has_stream_leap = false;
@@ -582,7 +582,7 @@ private:
     BufferId inline_buffer_id;
 
     std::array<BufferId, ((1ULL << 39) >> CACHING_PAGEBITS)> page_table;
-    std::vector<u8> tmp_buffer;
+    Common::ScratchBuffer<u8> tmp_buffer;
 };
 
 } // namespace VideoCommon
diff --git a/src/video_core/cdma_pusher.h b/src/video_core/cdma_pusher.h
index 83112dfce..7d660af47 100644
--- a/src/video_core/cdma_pusher.h
+++ b/src/video_core/cdma_pusher.h
@@ -63,7 +63,6 @@ struct ChCommand {
 };
 
 using ChCommandHeaderList = std::vector<ChCommandHeader>;
-using ChCommandList = std::vector<ChCommand>;
 
 struct ThiRegisters {
     u32_le increment_syncpt{};
diff --git a/src/video_core/dma_pusher.h b/src/video_core/dma_pusher.h
index 1cdb690ed..8a2784cdc 100644
--- a/src/video_core/dma_pusher.h
+++ b/src/video_core/dma_pusher.h
@@ -6,6 +6,7 @@
 #include <array>
 #include <span>
 #include <vector>
+#include <boost/container/small_vector.hpp>
 #include <queue>
 
 #include "common/bit_field.h"
@@ -102,11 +103,12 @@ inline CommandHeader BuildCommandHeader(BufferMethods method, u32 arg_count, Sub
 struct CommandList final {
     CommandList() = default;
     explicit CommandList(std::size_t size) : command_lists(size) {}
-    explicit CommandList(std::vector<CommandHeader>&& prefetch_command_list_)
+    explicit CommandList(
+        boost::container::small_vector<CommandHeader, 512>&& prefetch_command_list_)
         : prefetch_command_list{std::move(prefetch_command_list_)} {}
 
-    std::vector<CommandListHeader> command_lists;
-    std::vector<CommandHeader> prefetch_command_list;
+    boost::container::small_vector<CommandListHeader, 512> command_lists;
+    boost::container::small_vector<CommandHeader, 512> prefetch_command_list;
 };
 
 /**
diff --git a/src/video_core/engines/maxwell_dma.cpp b/src/video_core/engines/maxwell_dma.cpp
index ebe5536de..a290d6ea7 100644
--- a/src/video_core/engines/maxwell_dma.cpp
+++ b/src/video_core/engines/maxwell_dma.cpp
@@ -108,9 +108,11 @@ void MaxwellDMA::Launch() {
         if (regs.launch_dma.remap_enable != 0 && is_const_a_dst) {
             ASSERT(regs.remap_const.component_size_minus_one == 3);
             accelerate.BufferClear(regs.offset_out, regs.line_length_in, regs.remap_consta_value);
-            std::vector<u32> tmp_buffer(regs.line_length_in, regs.remap_consta_value);
+            read_buffer.resize_destructive(regs.line_length_in * sizeof(u32));
+            std::span<u32> span(reinterpret_cast<u32*>(read_buffer.data()), regs.line_length_in);
+            std::ranges::fill(span, regs.remap_consta_value);
             memory_manager.WriteBlockUnsafe(regs.offset_out,
-                                            reinterpret_cast<u8*>(tmp_buffer.data()),
+                                            reinterpret_cast<u8*>(read_buffer.data()),
                                             regs.line_length_in * sizeof(u32));
         } else {
             memory_manager.FlushCaching();
@@ -126,32 +128,33 @@ void MaxwellDMA::Launch() {
                 UNIMPLEMENTED_IF(regs.line_length_in % 16 != 0);
                 UNIMPLEMENTED_IF(regs.offset_in % 16 != 0);
                 UNIMPLEMENTED_IF(regs.offset_out % 16 != 0);
-                std::vector<u8> tmp_buffer(16);
+                read_buffer.resize_destructive(16);
                 for (u32 offset = 0; offset < regs.line_length_in; offset += 16) {
-                    memory_manager.ReadBlockUnsafe(
+                    memory_manager.ReadBlock(
                         convert_linear_2_blocklinear_addr(regs.offset_in + offset),
-                        tmp_buffer.data(), tmp_buffer.size());
-                    memory_manager.WriteBlockCached(regs.offset_out + offset, tmp_buffer.data(),
-                                                    tmp_buffer.size());
+                        read_buffer.data(), read_buffer.size());
+                    memory_manager.WriteBlockCached(regs.offset_out + offset, read_buffer.data(),
+                                                    read_buffer.size());
                 }
             } else if (is_src_pitch && !is_dst_pitch) {
                 UNIMPLEMENTED_IF(regs.line_length_in % 16 != 0);
                 UNIMPLEMENTED_IF(regs.offset_in % 16 != 0);
                 UNIMPLEMENTED_IF(regs.offset_out % 16 != 0);
-                std::vector<u8> tmp_buffer(16);
+                read_buffer.resize_destructive(16);
                 for (u32 offset = 0; offset < regs.line_length_in; offset += 16) {
-                    memory_manager.ReadBlockUnsafe(regs.offset_in + offset, tmp_buffer.data(),
-                                                   tmp_buffer.size());
+                    memory_manager.ReadBlock(regs.offset_in + offset, read_buffer.data(),
+                                             read_buffer.size());
                     memory_manager.WriteBlockCached(
                         convert_linear_2_blocklinear_addr(regs.offset_out + offset),
-                        tmp_buffer.data(), tmp_buffer.size());
+                        read_buffer.data(), read_buffer.size());
                 }
             } else {
                 if (!accelerate.BufferCopy(regs.offset_in, regs.offset_out, regs.line_length_in)) {
-                    std::vector<u8> tmp_buffer(regs.line_length_in);
-                    memory_manager.ReadBlockUnsafe(regs.offset_in, tmp_buffer.data(),
-                                                   regs.line_length_in);
-                    memory_manager.WriteBlockCached(regs.offset_out, tmp_buffer.data(),
+                    read_buffer.resize_destructive(regs.line_length_in);
+                    memory_manager.ReadBlock(regs.offset_in, read_buffer.data(),
+                                             regs.line_length_in,
+                                             VideoCommon::CacheType::NoBufferCache);
+                    memory_manager.WriteBlockCached(regs.offset_out, read_buffer.data(),
                                                     regs.line_length_in);
                 }
             }
@@ -171,7 +174,8 @@ void MaxwellDMA::CopyBlockLinearToPitch() {
     src_operand.address = regs.offset_in;
 
     DMA::BufferOperand dst_operand;
-    dst_operand.pitch = regs.pitch_out;
+    u32 abs_pitch_out = std::abs(static_cast<s32>(regs.pitch_out));
+    dst_operand.pitch = abs_pitch_out;
     dst_operand.width = regs.line_length_in;
     dst_operand.height = regs.line_count;
     dst_operand.address = regs.offset_out;
@@ -218,7 +222,7 @@ void MaxwellDMA::CopyBlockLinearToPitch() {
     const size_t src_size =
         CalculateSize(true, bytes_per_pixel, width, height, depth, block_height, block_depth);
 
-    const size_t dst_size = static_cast<size_t>(regs.pitch_out) * regs.line_count;
+    const size_t dst_size = static_cast<size_t>(abs_pitch_out) * regs.line_count;
     read_buffer.resize_destructive(src_size);
     write_buffer.resize_destructive(dst_size);
 
@@ -227,7 +231,7 @@ void MaxwellDMA::CopyBlockLinearToPitch() {
 
     UnswizzleSubrect(write_buffer, read_buffer, bytes_per_pixel, width, height, depth, x_offset,
                      src_params.origin.y, x_elements, regs.line_count, block_height, block_depth,
-                     regs.pitch_out);
+                     abs_pitch_out);
 
     memory_manager.WriteBlockCached(regs.offset_out, write_buffer.data(), dst_size);
 }
diff --git a/src/video_core/gpu.cpp b/src/video_core/gpu.cpp
index 456f733cf..db385076d 100644
--- a/src/video_core/gpu.cpp
+++ b/src/video_core/gpu.cpp
@@ -193,18 +193,13 @@ struct GPU::Impl {
     }
 
     [[nodiscard]] u64 GetTicks() const {
-        // This values were reversed engineered by fincs from NVN
-        // The gpu clock is reported in units of 385/625 nanoseconds
-        constexpr u64 gpu_ticks_num = 384;
-        constexpr u64 gpu_ticks_den = 625;
+        u64 gpu_tick = system.CoreTiming().GetGPUTicks();
 
-        u64 nanoseconds = system.CoreTiming().GetCPUTimeNs().count();
         if (Settings::values.use_fast_gpu_time.GetValue()) {
-            nanoseconds /= 256;
+            gpu_tick /= 256;
         }
-        const u64 nanoseconds_num = nanoseconds / gpu_ticks_den;
-        const u64 nanoseconds_rem = nanoseconds % gpu_ticks_den;
-        return nanoseconds_num * gpu_ticks_num + (nanoseconds_rem * gpu_ticks_num) / gpu_ticks_den;
+
+        return gpu_tick;
     }
 
     [[nodiscard]] bool IsAsync() const {
diff --git a/src/video_core/host1x/codecs/h264.cpp b/src/video_core/host1x/codecs/h264.cpp
index 6ce179167..ce827eb6c 100644
--- a/src/video_core/host1x/codecs/h264.cpp
+++ b/src/video_core/host1x/codecs/h264.cpp
@@ -4,6 +4,7 @@
 #include <array>
 #include <bit>
 
+#include "common/scratch_buffer.h"
 #include "common/settings.h"
 #include "video_core/host1x/codecs/h264.h"
 #include "video_core/host1x/host1x.h"
@@ -188,7 +189,8 @@ void H264BitWriter::WriteBit(bool state) {
 }
 
 void H264BitWriter::WriteScalingList(std::span<const u8> list, s32 start, s32 count) {
-    std::vector<u8> scan(count);
+    static Common::ScratchBuffer<u8> scan{};
+    scan.resize_destructive(count);
     if (count == 16) {
         std::memcpy(scan.data(), zig_zag_scan.data(), scan.size());
     } else {
diff --git a/src/video_core/host_shaders/CMakeLists.txt b/src/video_core/host_shaders/CMakeLists.txt
index 2442c3c29..e61d9af80 100644
--- a/src/video_core/host_shaders/CMakeLists.txt
+++ b/src/video_core/host_shaders/CMakeLists.txt
@@ -33,6 +33,7 @@ set(SHADER_FILES
     opengl_fidelityfx_fsr.frag
     opengl_fidelityfx_fsr_easu.frag
     opengl_fidelityfx_fsr_rcas.frag
+    opengl_lmem_warmup.comp
     opengl_present.frag
     opengl_present.vert
     opengl_present_scaleforce.frag
diff --git a/src/video_core/host_shaders/opengl_lmem_warmup.comp b/src/video_core/host_shaders/opengl_lmem_warmup.comp
new file mode 100644
index 000000000..518268477
--- /dev/null
+++ b/src/video_core/host_shaders/opengl_lmem_warmup.comp
@@ -0,0 +1,47 @@
+// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+// This shader is a workaround for a quirk in NVIDIA OpenGL drivers
+// Shaders using local memory see a great performance benefit if a shader that was dispatched
+// before it had more local memory allocated.
+// This shader allocates the maximum local memory allowed on NVIDIA drivers to ensure that
+// subsequent shaders see the performance boost.
+
+// NOTE: This shader does no actual meaningful work and returns immediately,
+// it is simply a means to have the driver expect a shader using lots of local memory.
+
+#version 450
+
+layout(local_size_x = 1, local_size_y = 1, local_size_z = 1) in;
+
+layout(location = 0) uniform uint uniform_data;
+
+layout(binding = 0, rgba8) uniform writeonly restrict image2DArray dest_image;
+
+#define MAX_LMEM_SIZE 4080 // Size chosen to avoid errors in Nvidia's GLSL compiler
+#define NUM_LMEM_CONSTANTS 1
+#define ARRAY_SIZE MAX_LMEM_SIZE - NUM_LMEM_CONSTANTS
+
+uint lmem_0[ARRAY_SIZE];
+const uvec4 constant_values[NUM_LMEM_CONSTANTS] = uvec4[](uvec4(0));
+
+void main() {
+    const uint global_id = gl_GlobalInvocationID.x;
+    if (global_id <= 128) {
+        // Since the shader is called with a dispatch of 1x1x1
+        // This should always be the case, and this shader will not actually execute
+        return;
+    }
+    for (uint t = 0; t < uniform_data; t++) {
+        const uint offset = (t * uniform_data);
+        lmem_0[offset] = t;
+    }
+    const uint offset = (gl_GlobalInvocationID.y * uniform_data + gl_GlobalInvocationID.x);
+    const uint value = lmem_0[offset];
+    const uint const_value = constant_values[offset / 4][offset % 4];
+    const uvec4 color = uvec4(value + const_value);
+
+    // A "side-effect" is needed so the variables don't get optimized out,
+    // but this should never execute so there should be no clobbering of previously bound state.
+    imageStore(dest_image, ivec3(gl_GlobalInvocationID), color);
+}
diff --git a/src/video_core/memory_manager.cpp b/src/video_core/memory_manager.cpp
index 7b2cde7a7..45141e488 100644
--- a/src/video_core/memory_manager.cpp
+++ b/src/video_core/memory_manager.cpp
@@ -111,7 +111,7 @@ GPUVAddr MemoryManager::PageTableOp(GPUVAddr gpu_addr, [[maybe_unused]] VAddr cp
         [[maybe_unused]] const auto current_entry_type = GetEntry<false>(current_gpu_addr);
         SetEntry<false>(current_gpu_addr, entry_type);
         if (current_entry_type != entry_type) {
-            rasterizer->ModifyGPUMemory(unique_identifier, gpu_addr, page_size);
+            rasterizer->ModifyGPUMemory(unique_identifier, current_gpu_addr, page_size);
         }
         if constexpr (entry_type == EntryType::Mapped) {
             const VAddr current_cpu_addr = cpu_addr + offset;
@@ -134,7 +134,7 @@ GPUVAddr MemoryManager::BigPageTableOp(GPUVAddr gpu_addr, [[maybe_unused]] VAddr
         [[maybe_unused]] const auto current_entry_type = GetEntry<true>(current_gpu_addr);
         SetEntry<true>(current_gpu_addr, entry_type);
         if (current_entry_type != entry_type) {
-            rasterizer->ModifyGPUMemory(unique_identifier, gpu_addr, big_page_size);
+            rasterizer->ModifyGPUMemory(unique_identifier, current_gpu_addr, big_page_size);
         }
         if constexpr (entry_type == EntryType::Mapped) {
             const VAddr current_cpu_addr = cpu_addr + offset;
@@ -587,7 +587,7 @@ void MemoryManager::InvalidateRegion(GPUVAddr gpu_addr, size_t size,
 
 void MemoryManager::CopyBlock(GPUVAddr gpu_dest_addr, GPUVAddr gpu_src_addr, std::size_t size,
                               VideoCommon::CacheType which) {
-    std::vector<u8> tmp_buffer(size);
+    tmp_buffer.resize_destructive(size);
     ReadBlock(gpu_src_addr, tmp_buffer.data(), size, which);
 
     // The output block must be flushed in case it has data modified from the GPU.
@@ -670,9 +670,9 @@ bool MemoryManager::IsFullyMappedRange(GPUVAddr gpu_addr, std::size_t size) cons
     return result;
 }
 
-std::vector<std::pair<GPUVAddr, std::size_t>> MemoryManager::GetSubmappedRange(
-    GPUVAddr gpu_addr, std::size_t size) const {
-    std::vector<std::pair<GPUVAddr, std::size_t>> result{};
+boost::container::small_vector<std::pair<GPUVAddr, std::size_t>, 32>
+MemoryManager::GetSubmappedRange(GPUVAddr gpu_addr, std::size_t size) const {
+    boost::container::small_vector<std::pair<GPUVAddr, std::size_t>, 32> result{};
     GetSubmappedRangeImpl<true>(gpu_addr, size, result);
     return result;
 }
@@ -680,8 +680,9 @@ std::vector<std::pair<GPUVAddr, std::size_t>> MemoryManager::GetSubmappedRange(
 template <bool is_gpu_address>
 void MemoryManager::GetSubmappedRangeImpl(
     GPUVAddr gpu_addr, std::size_t size,
-    std::vector<std::pair<std::conditional_t<is_gpu_address, GPUVAddr, VAddr>, std::size_t>>&
-        result) const {
+    boost::container::small_vector<
+        std::pair<std::conditional_t<is_gpu_address, GPUVAddr, VAddr>, std::size_t>, 32>& result)
+    const {
     std::optional<std::pair<std::conditional_t<is_gpu_address, GPUVAddr, VAddr>, std::size_t>>
         last_segment{};
     std::optional<VAddr> old_page_addr{};
diff --git a/src/video_core/memory_manager.h b/src/video_core/memory_manager.h
index 794535122..4202c26ff 100644
--- a/src/video_core/memory_manager.h
+++ b/src/video_core/memory_manager.h
@@ -8,10 +8,12 @@
 #include <mutex>
 #include <optional>
 #include <vector>
+#include <boost/container/small_vector.hpp>
 
 #include "common/common_types.h"
 #include "common/multi_level_page_table.h"
 #include "common/range_map.h"
+#include "common/scratch_buffer.h"
 #include "common/virtual_buffer.h"
 #include "video_core/cache_types.h"
 #include "video_core/pte_kind.h"
@@ -107,8 +109,8 @@ public:
      * if the region is continuous, a single pair will be returned. If it's unmapped, an empty
      * vector will be returned;
      */
-    std::vector<std::pair<GPUVAddr, std::size_t>> GetSubmappedRange(GPUVAddr gpu_addr,
-                                                                    std::size_t size) const;
+    boost::container::small_vector<std::pair<GPUVAddr, std::size_t>, 32> GetSubmappedRange(
+        GPUVAddr gpu_addr, std::size_t size) const;
 
     GPUVAddr Map(GPUVAddr gpu_addr, VAddr cpu_addr, std::size_t size,
                  PTEKind kind = PTEKind::INVALID, bool is_big_pages = true);
@@ -165,7 +167,8 @@ private:
     template <bool is_gpu_address>
     void GetSubmappedRangeImpl(
         GPUVAddr gpu_addr, std::size_t size,
-        std::vector<std::pair<std::conditional_t<is_gpu_address, GPUVAddr, VAddr>, std::size_t>>&
+        boost::container::small_vector<
+            std::pair<std::conditional_t<is_gpu_address, GPUVAddr, VAddr>, std::size_t>, 32>&
             result) const;
 
     Core::System& system;
@@ -215,8 +218,8 @@ private:
     Common::VirtualBuffer<u32> big_page_table_cpu;
 
     std::vector<u64> big_page_continuous;
-    std::vector<std::pair<VAddr, std::size_t>> page_stash{};
-    std::vector<std::pair<VAddr, std::size_t>> page_stash2{};
+    boost::container::small_vector<std::pair<VAddr, std::size_t>, 32> page_stash{};
+    boost::container::small_vector<std::pair<VAddr, std::size_t>, 32> page_stash2{};
 
     mutable std::mutex guard;
 
@@ -226,6 +229,8 @@ private:
     std::unique_ptr<VideoCommon::InvalidationAccumulator> accumulator;
 
     static std::atomic<size_t> unique_identifier_generator;
+
+    Common::ScratchBuffer<u8> tmp_buffer;
 };
 
 } // namespace Tegra
diff --git a/src/video_core/renderer_opengl/gl_compute_pipeline.cpp b/src/video_core/renderer_opengl/gl_compute_pipeline.cpp
index 3151c0db8..f9ca55c36 100644
--- a/src/video_core/renderer_opengl/gl_compute_pipeline.cpp
+++ b/src/video_core/renderer_opengl/gl_compute_pipeline.cpp
@@ -63,6 +63,7 @@ ComputePipeline::ComputePipeline(const Device& device, TextureCache& texture_cac
     writes_global_memory = !use_storage_buffers &&
                            std::ranges::any_of(info.storage_buffers_descriptors,
                                                [](const auto& desc) { return desc.is_written; });
+    uses_local_memory = info.uses_local_memory;
     if (force_context_flush) {
         std::scoped_lock lock{built_mutex};
         built_fence.Create();
diff --git a/src/video_core/renderer_opengl/gl_compute_pipeline.h b/src/video_core/renderer_opengl/gl_compute_pipeline.h
index 9bcc72b59..c26b4fa5e 100644
--- a/src/video_core/renderer_opengl/gl_compute_pipeline.h
+++ b/src/video_core/renderer_opengl/gl_compute_pipeline.h
@@ -59,6 +59,10 @@ public:
         return writes_global_memory;
     }
 
+    [[nodiscard]] bool UsesLocalMemory() const noexcept {
+        return uses_local_memory;
+    }
+
     void SetEngine(Tegra::Engines::KeplerCompute* kepler_compute_,
                    Tegra::MemoryManager* gpu_memory_) {
         kepler_compute = kepler_compute_;
@@ -84,6 +88,7 @@ private:
 
     bool use_storage_buffers{};
     bool writes_global_memory{};
+    bool uses_local_memory{};
 
     std::mutex built_mutex;
     std::condition_variable built_condvar;
diff --git a/src/video_core/renderer_opengl/gl_device.cpp b/src/video_core/renderer_opengl/gl_device.cpp
index 03d234f2f..33e63c17d 100644
--- a/src/video_core/renderer_opengl/gl_device.cpp
+++ b/src/video_core/renderer_opengl/gl_device.cpp
@@ -194,6 +194,7 @@ Device::Device(Core::Frontend::EmuWindow& emu_window) {
             has_bool_ref_bug = true;
         }
     }
+    has_lmem_perf_bug = is_nvidia;
 
     strict_context_required = emu_window.StrictContextRequired();
     // Blocks AMD and Intel OpenGL drivers on Windows from using asynchronous shader compilation.
diff --git a/src/video_core/renderer_opengl/gl_device.h b/src/video_core/renderer_opengl/gl_device.h
index ad27264e5..a5a6bbbba 100644
--- a/src/video_core/renderer_opengl/gl_device.h
+++ b/src/video_core/renderer_opengl/gl_device.h
@@ -192,6 +192,10 @@ public:
         return supports_conditional_barriers;
     }
 
+    bool HasLmemPerfBug() const {
+        return has_lmem_perf_bug;
+    }
+
 private:
     static bool TestVariableAoffi();
     static bool TestPreciseBug();
@@ -238,6 +242,7 @@ private:
     bool can_report_memory{};
     bool strict_context_required{};
     bool supports_conditional_barriers{};
+    bool has_lmem_perf_bug{};
 
     std::string vendor_name;
 };
diff --git a/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp b/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp
index c58f760b8..23a48c6fe 100644
--- a/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp
+++ b/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp
@@ -215,6 +215,7 @@ GraphicsPipeline::GraphicsPipeline(const Device& device, TextureCache& texture_c
 
         writes_global_memory |= std::ranges::any_of(
             info.storage_buffers_descriptors, [](const auto& desc) { return desc.is_written; });
+        uses_local_memory |= info.uses_local_memory;
     }
     ASSERT(num_textures <= MAX_TEXTURES);
     ASSERT(num_images <= MAX_IMAGES);
diff --git a/src/video_core/renderer_opengl/gl_graphics_pipeline.h b/src/video_core/renderer_opengl/gl_graphics_pipeline.h
index 7bab3be0a..7b3d7eae8 100644
--- a/src/video_core/renderer_opengl/gl_graphics_pipeline.h
+++ b/src/video_core/renderer_opengl/gl_graphics_pipeline.h
@@ -98,6 +98,10 @@ public:
         return writes_global_memory;
     }
 
+    [[nodiscard]] bool UsesLocalMemory() const noexcept {
+        return uses_local_memory;
+    }
+
     [[nodiscard]] bool IsBuilt() noexcept;
 
     template <typename Spec>
@@ -146,6 +150,7 @@ private:
 
     bool use_storage_buffers{};
     bool writes_global_memory{};
+    bool uses_local_memory{};
 
     static constexpr std::size_t XFB_ENTRY_STRIDE = 3;
     GLsizei num_xfb_attribs{};
diff --git a/src/video_core/renderer_opengl/gl_rasterizer.cpp b/src/video_core/renderer_opengl/gl_rasterizer.cpp
index fc711c44a..edf527f2d 100644
--- a/src/video_core/renderer_opengl/gl_rasterizer.cpp
+++ b/src/video_core/renderer_opengl/gl_rasterizer.cpp
@@ -222,6 +222,9 @@ void RasterizerOpenGL::PrepareDraw(bool is_indexed, Func&& draw_func) {
     gpu.TickWork();
 
     std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
+    if (pipeline->UsesLocalMemory()) {
+        program_manager.LocalMemoryWarmup();
+    }
     pipeline->SetEngine(maxwell3d, gpu_memory);
     pipeline->Configure(is_indexed);
 
@@ -371,6 +374,9 @@ void RasterizerOpenGL::DispatchCompute() {
     if (!pipeline) {
         return;
     }
+    if (pipeline->UsesLocalMemory()) {
+        program_manager.LocalMemoryWarmup();
+    }
     pipeline->SetEngine(kepler_compute, gpu_memory);
     pipeline->Configure();
     const auto& qmd{kepler_compute->launch_description};
diff --git a/src/video_core/renderer_opengl/gl_shader_cache.cpp b/src/video_core/renderer_opengl/gl_shader_cache.cpp
index 3f077311e..0329ed820 100644
--- a/src/video_core/renderer_opengl/gl_shader_cache.cpp
+++ b/src/video_core/renderer_opengl/gl_shader_cache.cpp
@@ -85,7 +85,9 @@ Shader::RuntimeInfo MakeRuntimeInfo(const GraphicsPipelineKey& key,
     case Shader::Stage::VertexB:
     case Shader::Stage::Geometry:
         if (!use_assembly_shaders && key.xfb_enabled != 0) {
-            info.xfb_varyings = VideoCommon::MakeTransformFeedbackVaryings(key.xfb_state);
+            auto [varyings, count] = VideoCommon::MakeTransformFeedbackVaryings(key.xfb_state);
+            info.xfb_varyings = varyings;
+            info.xfb_count = count;
         }
         break;
     case Shader::Stage::TessellationEval:
diff --git a/src/video_core/renderer_opengl/gl_shader_manager.cpp b/src/video_core/renderer_opengl/gl_shader_manager.cpp
index 98841ae65..03d4b9d06 100644
--- a/src/video_core/renderer_opengl/gl_shader_manager.cpp
+++ b/src/video_core/renderer_opengl/gl_shader_manager.cpp
@@ -3,7 +3,9 @@
 
 #include <glad/glad.h>
 
+#include "video_core/host_shaders/opengl_lmem_warmup_comp.h"
 #include "video_core/renderer_opengl/gl_shader_manager.h"
+#include "video_core/renderer_opengl/gl_shader_util.h"
 
 namespace OpenGL {
 
@@ -17,6 +19,10 @@ ProgramManager::ProgramManager(const Device& device) {
     if (device.UseAssemblyShaders()) {
         glEnable(GL_COMPUTE_PROGRAM_NV);
     }
+    if (device.HasLmemPerfBug()) {
+        lmem_warmup_program =
+            CreateProgram(HostShaders::OPENGL_LMEM_WARMUP_COMP, GL_COMPUTE_SHADER);
+    }
 }
 
 void ProgramManager::BindComputeProgram(GLuint program) {
@@ -98,6 +104,13 @@ void ProgramManager::BindAssemblyPrograms(std::span<const OGLAssemblyProgram, NU
 
 void ProgramManager::RestoreGuestCompute() {}
 
+void ProgramManager::LocalMemoryWarmup() {
+    if (lmem_warmup_program.handle != 0) {
+        BindComputeProgram(lmem_warmup_program.handle);
+        glDispatchCompute(1, 1, 1);
+    }
+}
+
 void ProgramManager::BindPipeline() {
     if (!is_pipeline_bound) {
         is_pipeline_bound = true;
diff --git a/src/video_core/renderer_opengl/gl_shader_manager.h b/src/video_core/renderer_opengl/gl_shader_manager.h
index 07ffab77f..852d8c88e 100644
--- a/src/video_core/renderer_opengl/gl_shader_manager.h
+++ b/src/video_core/renderer_opengl/gl_shader_manager.h
@@ -30,6 +30,8 @@ public:
 
     void RestoreGuestCompute();
 
+    void LocalMemoryWarmup();
+
 private:
     void BindPipeline();
 
@@ -44,6 +46,7 @@ private:
     u32 current_stage_mask = 0;
     std::array<GLuint, NUM_STAGES> current_programs{};
     GLuint current_assembly_compute_program = 0;
+    OGLProgram lmem_warmup_program;
 };
 
 } // namespace OpenGL
diff --git a/src/video_core/renderer_vulkan/blit_image.cpp b/src/video_core/renderer_vulkan/blit_image.cpp
index cf2964a3f..28d4b15a0 100644
--- a/src/video_core/renderer_vulkan/blit_image.cpp
+++ b/src/video_core/renderer_vulkan/blit_image.cpp
@@ -495,6 +495,9 @@ void BlitImageHelper::BlitDepthStencil(const Framebuffer* dst_framebuffer,
                                        const Region2D& dst_region, const Region2D& src_region,
                                        Tegra::Engines::Fermi2D::Filter filter,
                                        Tegra::Engines::Fermi2D::Operation operation) {
+    if (!device.IsExtShaderStencilExportSupported()) {
+        return;
+    }
     ASSERT(filter == Tegra::Engines::Fermi2D::Filter::Point);
     ASSERT(operation == Tegra::Engines::Fermi2D::Operation::SrcCopy);
     const BlitImagePipelineKey key{
diff --git a/src/video_core/renderer_vulkan/maxwell_to_vk.cpp b/src/video_core/renderer_vulkan/maxwell_to_vk.cpp
index 9a0b10568..a8540339d 100644
--- a/src/video_core/renderer_vulkan/maxwell_to_vk.cpp
+++ b/src/video_core/renderer_vulkan/maxwell_to_vk.cpp
@@ -259,6 +259,26 @@ FormatInfo SurfaceFormat(const Device& device, FormatType format_type, bool with
             break;
         }
     }
+    // Transcode on hardware that doesn't support BCn natively
+    if (!device.IsOptimalBcnSupported() && VideoCore::Surface::IsPixelFormatBCn(pixel_format)) {
+        const bool is_srgb = with_srgb && VideoCore::Surface::IsPixelFormatSRGB(pixel_format);
+        if (pixel_format == PixelFormat::BC4_SNORM) {
+            tuple.format = VK_FORMAT_R8_SNORM;
+        } else if (pixel_format == PixelFormat::BC4_UNORM) {
+            tuple.format = VK_FORMAT_R8_UNORM;
+        } else if (pixel_format == PixelFormat::BC5_SNORM) {
+            tuple.format = VK_FORMAT_R8G8_SNORM;
+        } else if (pixel_format == PixelFormat::BC5_UNORM) {
+            tuple.format = VK_FORMAT_R8G8_UNORM;
+        } else if (pixel_format == PixelFormat::BC6H_SFLOAT ||
+                   pixel_format == PixelFormat::BC6H_UFLOAT) {
+            tuple.format = VK_FORMAT_R16G16B16A16_SFLOAT;
+        } else if (is_srgb) {
+            tuple.format = VK_FORMAT_A8B8G8R8_SRGB_PACK32;
+        } else {
+            tuple.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
+        }
+    }
     const bool attachable = (tuple.usage & Attachable) != 0;
     const bool storage = (tuple.usage & Storage) != 0;
 
diff --git a/src/video_core/renderer_vulkan/renderer_vulkan.cpp b/src/video_core/renderer_vulkan/renderer_vulkan.cpp
index 77128c6e2..454bb66a4 100644
--- a/src/video_core/renderer_vulkan/renderer_vulkan.cpp
+++ b/src/video_core/renderer_vulkan/renderer_vulkan.cpp
@@ -12,6 +12,7 @@
 #include <fmt/format.h>
 
 #include "common/logging/log.h"
+#include "common/polyfill_ranges.h"
 #include "common/scope_exit.h"
 #include "common/settings.h"
 #include "common/telemetry.h"
@@ -65,6 +66,21 @@ std::string BuildCommaSeparatedExtensions(
     return fmt::format("{}", fmt::join(available_extensions, ","));
 }
 
+DebugCallback MakeDebugCallback(const vk::Instance& instance, const vk::InstanceDispatch& dld) {
+    if (!Settings::values.renderer_debug) {
+        return DebugCallback{};
+    }
+    const std::optional properties = vk::EnumerateInstanceExtensionProperties(dld);
+    const auto it = std::ranges::find_if(*properties, [](const auto& prop) {
+        return std::strcmp(VK_EXT_DEBUG_UTILS_EXTENSION_NAME, prop.extensionName) == 0;
+    });
+    if (it != properties->end()) {
+        return CreateDebugUtilsCallback(instance);
+    } else {
+        return CreateDebugReportCallback(instance);
+    }
+}
+
 } // Anonymous namespace
 
 Device CreateDevice(const vk::Instance& instance, const vk::InstanceDispatch& dld,
@@ -87,10 +103,10 @@ RendererVulkan::RendererVulkan(Core::TelemetrySession& telemetry_session_,
       cpu_memory(cpu_memory_), gpu(gpu_), library(OpenLibrary(context.get())),
       instance(CreateInstance(*library, dld, VK_API_VERSION_1_1, render_window.GetWindowInfo().type,
                               Settings::values.renderer_debug.GetValue())),
-      debug_callback(Settings::values.renderer_debug ? CreateDebugCallback(instance) : nullptr),
+      debug_callback(MakeDebugCallback(instance, dld)),
       surface(CreateSurface(instance, render_window.GetWindowInfo())),
-      device(CreateDevice(instance, dld, *surface)), memory_allocator(device, false),
-      state_tracker(), scheduler(device, state_tracker),
+      device(CreateDevice(instance, dld, *surface)), memory_allocator(device), state_tracker(),
+      scheduler(device, state_tracker),
       swapchain(*surface, device, scheduler, render_window.GetFramebufferLayout().width,
                 render_window.GetFramebufferLayout().height, false),
       present_manager(instance, render_window, device, memory_allocator, scheduler, swapchain,
@@ -173,7 +189,7 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr
         return;
     }
     const Layout::FramebufferLayout layout{renderer_settings.screenshot_framebuffer_layout};
-    vk::Image staging_image = device.GetLogical().CreateImage(VkImageCreateInfo{
+    vk::Image staging_image = memory_allocator.CreateImage(VkImageCreateInfo{
         .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
         .pNext = nullptr,
         .flags = VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT,
@@ -196,7 +212,6 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr
         .pQueueFamilyIndices = nullptr,
         .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
     });
-    const auto image_commit = memory_allocator.Commit(staging_image, MemoryUsage::DeviceLocal);
 
     const vk::ImageView dst_view = device.GetLogical().CreateImageView(VkImageViewCreateInfo{
         .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
@@ -234,8 +249,8 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
     };
-    const vk::Buffer dst_buffer = device.GetLogical().CreateBuffer(dst_buffer_info);
-    MemoryCommit dst_buffer_memory = memory_allocator.Commit(dst_buffer, MemoryUsage::Download);
+    const vk::Buffer dst_buffer =
+        memory_allocator.CreateBuffer(dst_buffer_info, MemoryUsage::Download);
 
     scheduler.RequestOutsideRenderPassOperationContext();
     scheduler.Record([&](vk::CommandBuffer cmdbuf) {
@@ -309,8 +324,9 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr
     scheduler.Finish();
 
     // Copy backing image data to the QImage screenshot buffer
-    const auto dst_memory_map = dst_buffer_memory.Map();
-    std::memcpy(renderer_settings.screenshot_bits, dst_memory_map.data(), dst_memory_map.size());
+    dst_buffer.Invalidate();
+    std::memcpy(renderer_settings.screenshot_bits, dst_buffer.Mapped().data(),
+                dst_buffer.Mapped().size());
     renderer_settings.screenshot_complete_callback(false);
     renderer_settings.screenshot_requested = false;
 }
diff --git a/src/video_core/renderer_vulkan/renderer_vulkan.h b/src/video_core/renderer_vulkan/renderer_vulkan.h
index b2e8cbd1b..ca22c0baa 100644
--- a/src/video_core/renderer_vulkan/renderer_vulkan.h
+++ b/src/video_core/renderer_vulkan/renderer_vulkan.h
@@ -5,6 +5,7 @@
 
 #include <memory>
 #include <string>
+#include <variant>
 
 #include "common/dynamic_library.h"
 #include "video_core/renderer_base.h"
@@ -33,6 +34,8 @@ class GPU;
 
 namespace Vulkan {
 
+using DebugCallback = std::variant<vk::DebugUtilsMessenger, vk::DebugReportCallback>;
+
 Device CreateDevice(const vk::Instance& instance, const vk::InstanceDispatch& dld,
                     VkSurfaceKHR surface);
 
@@ -71,7 +74,7 @@ private:
     vk::InstanceDispatch dld;
 
     vk::Instance instance;
-    vk::DebugUtilsMessenger debug_callback;
+    DebugCallback debug_callback;
     vk::SurfaceKHR surface;
 
     ScreenInfo screen_info;
diff --git a/src/video_core/renderer_vulkan/vk_blit_screen.cpp b/src/video_core/renderer_vulkan/vk_blit_screen.cpp
index acb143fc7..ad3b29f0e 100644
--- a/src/video_core/renderer_vulkan/vk_blit_screen.cpp
+++ b/src/video_core/renderer_vulkan/vk_blit_screen.cpp
@@ -162,7 +162,7 @@ void BlitScreen::Draw(const Tegra::FramebufferConfig& framebuffer,
     SetUniformData(data, layout);
     SetVertexData(data, framebuffer, layout);
 
-    const std::span<u8> mapped_span = buffer_commit.Map();
+    const std::span<u8> mapped_span = buffer.Mapped();
     std::memcpy(mapped_span.data(), &data, sizeof(data));
 
     if (!use_accelerated) {
@@ -1071,14 +1071,9 @@ void BlitScreen::ReleaseRawImages() {
         scheduler.Wait(tick);
     }
     raw_images.clear();
-    raw_buffer_commits.clear();
-
     aa_image_view.reset();
     aa_image.reset();
-    aa_commit = MemoryCommit{};
-
     buffer.reset();
-    buffer_commit = MemoryCommit{};
 }
 
 void BlitScreen::CreateStagingBuffer(const Tegra::FramebufferConfig& framebuffer) {
@@ -1094,20 +1089,18 @@ void BlitScreen::CreateStagingBuffer(const Tegra::FramebufferConfig& framebuffer
         .pQueueFamilyIndices = nullptr,
     };
 
-    buffer = device.GetLogical().CreateBuffer(ci);
-    buffer_commit = memory_allocator.Commit(buffer, MemoryUsage::Upload);
+    buffer = memory_allocator.CreateBuffer(ci, MemoryUsage::Upload);
 }
 
 void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) {
     raw_images.resize(image_count);
     raw_image_views.resize(image_count);
-    raw_buffer_commits.resize(image_count);
 
     const auto create_image = [&](bool used_on_framebuffer = false, u32 up_scale = 1,
                                   u32 down_shift = 0) {
         u32 extra_usages = used_on_framebuffer ? VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT
                                                : VK_IMAGE_USAGE_TRANSFER_DST_BIT;
-        return device.GetLogical().CreateImage(VkImageCreateInfo{
+        return memory_allocator.CreateImage(VkImageCreateInfo{
             .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
             .pNext = nullptr,
             .flags = 0,
@@ -1130,9 +1123,6 @@ void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) {
             .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
         });
     };
-    const auto create_commit = [&](vk::Image& image) {
-        return memory_allocator.Commit(image, MemoryUsage::DeviceLocal);
-    };
     const auto create_image_view = [&](vk::Image& image, bool used_on_framebuffer = false) {
         return device.GetLogical().CreateImageView(VkImageViewCreateInfo{
             .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
@@ -1161,7 +1151,6 @@ void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) {
 
     for (size_t i = 0; i < image_count; ++i) {
         raw_images[i] = create_image();
-        raw_buffer_commits[i] = create_commit(raw_images[i]);
         raw_image_views[i] = create_image_view(raw_images[i]);
     }
 
@@ -1169,7 +1158,6 @@ void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) {
     const u32 up_scale = Settings::values.resolution_info.up_scale;
     const u32 down_shift = Settings::values.resolution_info.down_shift;
     aa_image = create_image(true, up_scale, down_shift);
-    aa_commit = create_commit(aa_image);
     aa_image_view = create_image_view(aa_image, true);
     VkExtent2D size{
         .width = (up_scale * framebuffer.width) >> down_shift,
diff --git a/src/video_core/renderer_vulkan/vk_blit_screen.h b/src/video_core/renderer_vulkan/vk_blit_screen.h
index 68ec20253..8365b5668 100644
--- a/src/video_core/renderer_vulkan/vk_blit_screen.h
+++ b/src/video_core/renderer_vulkan/vk_blit_screen.h
@@ -142,13 +142,11 @@ private:
     vk::Sampler sampler;
 
     vk::Buffer buffer;
-    MemoryCommit buffer_commit;
 
     std::vector<u64> resource_ticks;
 
     std::vector<vk::Image> raw_images;
     std::vector<vk::ImageView> raw_image_views;
-    std::vector<MemoryCommit> raw_buffer_commits;
 
     vk::DescriptorPool aa_descriptor_pool;
     vk::DescriptorSetLayout aa_descriptor_set_layout;
@@ -159,7 +157,6 @@ private:
     vk::DescriptorSets aa_descriptor_sets;
     vk::Image aa_image;
     vk::ImageView aa_image_view;
-    MemoryCommit aa_commit;
 
     u32 raw_width = 0;
     u32 raw_height = 0;
diff --git a/src/video_core/renderer_vulkan/vk_buffer_cache.cpp b/src/video_core/renderer_vulkan/vk_buffer_cache.cpp
index e30fcb1ed..b72f95235 100644
--- a/src/video_core/renderer_vulkan/vk_buffer_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_buffer_cache.cpp
@@ -50,7 +50,7 @@ size_t BytesPerIndex(VkIndexType index_type) {
     }
 }
 
-vk::Buffer CreateBuffer(const Device& device, u64 size) {
+vk::Buffer CreateBuffer(const Device& device, const MemoryAllocator& memory_allocator, u64 size) {
     VkBufferUsageFlags flags =
         VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT |
         VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_TEXEL_BUFFER_BIT |
@@ -60,7 +60,7 @@ vk::Buffer CreateBuffer(const Device& device, u64 size) {
     if (device.IsExtTransformFeedbackSupported()) {
         flags |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
     }
-    return device.GetLogical().CreateBuffer({
+    const VkBufferCreateInfo buffer_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
@@ -69,7 +69,8 @@ vk::Buffer CreateBuffer(const Device& device, u64 size) {
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
-    });
+    };
+    return memory_allocator.CreateBuffer(buffer_ci, MemoryUsage::DeviceLocal);
 }
 } // Anonymous namespace
 
@@ -79,8 +80,8 @@ Buffer::Buffer(BufferCacheRuntime&, VideoCommon::NullBufferParams null_params)
 Buffer::Buffer(BufferCacheRuntime& runtime, VideoCore::RasterizerInterface& rasterizer_,
                VAddr cpu_addr_, u64 size_bytes_)
     : VideoCommon::BufferBase<VideoCore::RasterizerInterface>(rasterizer_, cpu_addr_, size_bytes_),
-      device{&runtime.device}, buffer{CreateBuffer(*device, SizeBytes())},
-      commit{runtime.memory_allocator.Commit(buffer, MemoryUsage::DeviceLocal)} {
+      device{&runtime.device}, buffer{
+                                   CreateBuffer(*device, runtime.memory_allocator, SizeBytes())} {
     if (runtime.device.HasDebuggingToolAttached()) {
         buffer.SetObjectNameEXT(fmt::format("Buffer 0x{:x}", CpuAddr()).c_str());
     }
@@ -138,7 +139,7 @@ public:
         const u32 num_first_offset_copies = 4;
         const size_t bytes_per_index = BytesPerIndex(index_type);
         const size_t size_bytes = num_triangle_indices * bytes_per_index * num_first_offset_copies;
-        buffer = device.GetLogical().CreateBuffer(VkBufferCreateInfo{
+        const VkBufferCreateInfo buffer_ci = {
             .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
             .pNext = nullptr,
             .flags = 0,
@@ -147,14 +148,21 @@ public:
             .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
             .queueFamilyIndexCount = 0,
             .pQueueFamilyIndices = nullptr,
-        });
+        };
+        buffer = memory_allocator.CreateBuffer(buffer_ci, MemoryUsage::DeviceLocal);
         if (device.HasDebuggingToolAttached()) {
             buffer.SetObjectNameEXT("Quad LUT");
         }
-        memory_commit = memory_allocator.Commit(buffer, MemoryUsage::DeviceLocal);
 
-        const StagingBufferRef staging = staging_pool.Request(size_bytes, MemoryUsage::Upload);
-        u8* staging_data = staging.mapped_span.data();
+        const bool host_visible = buffer.IsHostVisible();
+        const StagingBufferRef staging = [&] {
+            if (host_visible) {
+                return StagingBufferRef{};
+            }
+            return staging_pool.Request(size_bytes, MemoryUsage::Upload);
+        }();
+
+        u8* staging_data = host_visible ? buffer.Mapped().data() : staging.mapped_span.data();
         const size_t quad_size = bytes_per_index * 6;
 
         for (u32 first = 0; first < num_first_offset_copies; ++first) {
@@ -164,29 +172,33 @@ public:
             }
         }
 
-        scheduler.RequestOutsideRenderPassOperationContext();
-        scheduler.Record([src_buffer = staging.buffer, src_offset = staging.offset,
-                          dst_buffer = *buffer, size_bytes](vk::CommandBuffer cmdbuf) {
-            const VkBufferCopy copy{
-                .srcOffset = src_offset,
-                .dstOffset = 0,
-                .size = size_bytes,
-            };
-            const VkBufferMemoryBarrier write_barrier{
-                .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
-                .pNext = nullptr,
-                .srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT,
-                .dstAccessMask = VK_ACCESS_INDEX_READ_BIT,
-                .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-                .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-                .buffer = dst_buffer,
-                .offset = 0,
-                .size = size_bytes,
-            };
-            cmdbuf.CopyBuffer(src_buffer, dst_buffer, copy);
-            cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT,
-                                   VK_PIPELINE_STAGE_VERTEX_INPUT_BIT, 0, write_barrier);
-        });
+        if (!host_visible) {
+            scheduler.RequestOutsideRenderPassOperationContext();
+            scheduler.Record([src_buffer = staging.buffer, src_offset = staging.offset,
+                              dst_buffer = *buffer, size_bytes](vk::CommandBuffer cmdbuf) {
+                const VkBufferCopy copy{
+                    .srcOffset = src_offset,
+                    .dstOffset = 0,
+                    .size = size_bytes,
+                };
+                const VkBufferMemoryBarrier write_barrier{
+                    .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
+                    .pNext = nullptr,
+                    .srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT,
+                    .dstAccessMask = VK_ACCESS_INDEX_READ_BIT,
+                    .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+                    .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+                    .buffer = dst_buffer,
+                    .offset = 0,
+                    .size = size_bytes,
+                };
+                cmdbuf.CopyBuffer(src_buffer, dst_buffer, copy);
+                cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT,
+                                       VK_PIPELINE_STAGE_VERTEX_INPUT_BIT, 0, write_barrier);
+            });
+        } else {
+            buffer.Flush();
+        }
     }
 
     void BindBuffer(u32 first) {
@@ -361,7 +373,7 @@ void BufferCacheRuntime::CopyBuffer(VkBuffer dst_buffer, VkBuffer src_buffer,
         .dstAccessMask = VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT,
     };
     // Measuring a popular game, this number never exceeds the specified size once data is warmed up
-    boost::container::small_vector<VkBufferCopy, 3> vk_copies(copies.size());
+    boost::container::small_vector<VkBufferCopy, 8> vk_copies(copies.size());
     std::ranges::transform(copies, vk_copies.begin(), MakeBufferCopy);
     scheduler.RequestOutsideRenderPassOperationContext();
     scheduler.Record([src_buffer, dst_buffer, vk_copies, barrier](vk::CommandBuffer cmdbuf) {
@@ -578,7 +590,8 @@ void BufferCacheRuntime::ReserveNullBuffer() {
         .pNext = nullptr,
         .flags = 0,
         .size = 4,
-        .usage = VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT,
+        .usage = VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT |
+                 VK_BUFFER_USAGE_TRANSFER_DST_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
@@ -587,11 +600,10 @@ void BufferCacheRuntime::ReserveNullBuffer() {
         create_info.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
     }
     create_info.usage |= VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT;
-    null_buffer = device.GetLogical().CreateBuffer(create_info);
+    null_buffer = memory_allocator.CreateBuffer(create_info, MemoryUsage::DeviceLocal);
     if (device.HasDebuggingToolAttached()) {
         null_buffer.SetObjectNameEXT("Null buffer");
     }
-    null_buffer_commit = memory_allocator.Commit(null_buffer, MemoryUsage::DeviceLocal);
 
     scheduler.RequestOutsideRenderPassOperationContext();
     scheduler.Record([buffer = *null_buffer](vk::CommandBuffer cmdbuf) {
diff --git a/src/video_core/renderer_vulkan/vk_buffer_cache.h b/src/video_core/renderer_vulkan/vk_buffer_cache.h
index cdeef8846..95446c732 100644
--- a/src/video_core/renderer_vulkan/vk_buffer_cache.h
+++ b/src/video_core/renderer_vulkan/vk_buffer_cache.h
@@ -48,7 +48,6 @@ private:
 
     const Device* device{};
     vk::Buffer buffer;
-    MemoryCommit commit;
     std::vector<BufferView> views;
 };
 
@@ -142,7 +141,6 @@ private:
     std::shared_ptr<QuadStripIndexBuffer> quad_strip_index_buffer;
 
     vk::Buffer null_buffer;
-    MemoryCommit null_buffer_commit;
 
     std::unique_ptr<Uint8Pass> uint8_pass;
     QuadIndexedPass quad_index_pass;
diff --git a/src/video_core/renderer_vulkan/vk_fsr.cpp b/src/video_core/renderer_vulkan/vk_fsr.cpp
index df972cd54..9bcdca2fb 100644
--- a/src/video_core/renderer_vulkan/vk_fsr.cpp
+++ b/src/video_core/renderer_vulkan/vk_fsr.cpp
@@ -205,10 +205,9 @@ void FSR::CreateDescriptorSets() {
 void FSR::CreateImages() {
     images.resize(image_count * 2);
     image_views.resize(image_count * 2);
-    buffer_commits.resize(image_count * 2);
 
     for (size_t i = 0; i < image_count * 2; ++i) {
-        images[i] = device.GetLogical().CreateImage(VkImageCreateInfo{
+        images[i] = memory_allocator.CreateImage(VkImageCreateInfo{
             .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
             .pNext = nullptr,
             .flags = 0,
@@ -231,7 +230,6 @@ void FSR::CreateImages() {
             .pQueueFamilyIndices = nullptr,
             .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
         });
-        buffer_commits[i] = memory_allocator.Commit(images[i], MemoryUsage::DeviceLocal);
         image_views[i] = device.GetLogical().CreateImageView(VkImageViewCreateInfo{
             .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
             .pNext = nullptr,
diff --git a/src/video_core/renderer_vulkan/vk_fsr.h b/src/video_core/renderer_vulkan/vk_fsr.h
index 5d872861f..8bb9fc23a 100644
--- a/src/video_core/renderer_vulkan/vk_fsr.h
+++ b/src/video_core/renderer_vulkan/vk_fsr.h
@@ -47,7 +47,6 @@ private:
     vk::Sampler sampler;
     std::vector<vk::Image> images;
     std::vector<vk::ImageView> image_views;
-    std::vector<MemoryCommit> buffer_commits;
 };
 
 } // namespace Vulkan
diff --git a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
index c1595642e..ad35cacac 100644
--- a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
+++ b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
@@ -652,13 +652,14 @@ void GraphicsPipeline::MakePipeline(VkRenderPass render_pass) {
         .pNext = nullptr,
         .negativeOneToOne = key.state.ndc_minus_one_to_one.Value() != 0 ? VK_TRUE : VK_FALSE,
     };
+    const u32 num_viewports = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports);
     VkPipelineViewportStateCreateInfo viewport_ci{
         .sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
-        .viewportCount = Maxwell::NumViewports,
+        .viewportCount = num_viewports,
         .pViewports = nullptr,
-        .scissorCount = Maxwell::NumViewports,
+        .scissorCount = num_viewports,
         .pScissors = nullptr,
     };
     if (device.IsNvViewportSwizzleSupported()) {
diff --git a/src/video_core/renderer_vulkan/vk_master_semaphore.cpp b/src/video_core/renderer_vulkan/vk_master_semaphore.cpp
index 5eeda08d2..6b288b994 100644
--- a/src/video_core/renderer_vulkan/vk_master_semaphore.cpp
+++ b/src/video_core/renderer_vulkan/vk_master_semaphore.cpp
@@ -75,15 +75,9 @@ void MasterSemaphore::Refresh() {
 
 void MasterSemaphore::Wait(u64 tick) {
     if (!semaphore) {
-        // If we don't support timeline semaphores, use an atomic wait
-        while (true) {
-            u64 current_value = gpu_tick.load(std::memory_order_relaxed);
-            if (current_value >= tick) {
-                return;
-            }
-            gpu_tick.wait(current_value);
-        }
-
+        // If we don't support timeline semaphores, wait for the value normally
+        std::unique_lock lk{free_mutex};
+        free_cv.wait(lk, [&] { return gpu_tick.load(std::memory_order_relaxed) >= tick; });
         return;
     }
 
@@ -198,11 +192,13 @@ void MasterSemaphore::WaitThread(std::stop_token token) {
 
         fence.Wait();
         fence.Reset();
-        gpu_tick.store(host_tick);
-        gpu_tick.notify_all();
 
-        std::scoped_lock lock{free_mutex};
-        free_queue.push_front(std::move(fence));
+        {
+            std::scoped_lock lock{free_mutex};
+            free_queue.push_front(std::move(fence));
+            gpu_tick.store(host_tick);
+        }
+        free_cv.notify_one();
     }
 }
 
diff --git a/src/video_core/renderer_vulkan/vk_master_semaphore.h b/src/video_core/renderer_vulkan/vk_master_semaphore.h
index 1e7c90215..3f599d7bd 100644
--- a/src/video_core/renderer_vulkan/vk_master_semaphore.h
+++ b/src/video_core/renderer_vulkan/vk_master_semaphore.h
@@ -72,6 +72,7 @@ private:
     std::atomic<u64> current_tick{1}; ///< Current logical tick.
     std::mutex wait_mutex;
     std::mutex free_mutex;
+    std::condition_variable free_cv;
     std::condition_variable_any wait_cv;
     std::queue<Waitable> wait_queue;  ///< Queue for the fences to be waited on by the wait thread.
     std::deque<vk::Fence> free_queue; ///< Holds available fences for submission.
diff --git a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
index 18e040a1b..d600c4e61 100644
--- a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
@@ -167,7 +167,10 @@ Shader::RuntimeInfo MakeRuntimeInfo(std::span<const Shader::IR::Program> program
                 info.fixed_state_point_size = point_size;
             }
             if (key.state.xfb_enabled) {
-                info.xfb_varyings = VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state);
+                auto [varyings, count] =
+                    VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state);
+                info.xfb_varyings = varyings;
+                info.xfb_count = count;
             }
             info.convert_depth_mode = gl_ndc;
         }
@@ -214,7 +217,10 @@ Shader::RuntimeInfo MakeRuntimeInfo(std::span<const Shader::IR::Program> program
             info.fixed_state_point_size = point_size;
         }
         if (key.state.xfb_enabled != 0) {
-            info.xfb_varyings = VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state);
+            auto [varyings, count] =
+                VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state);
+            info.xfb_varyings = varyings;
+            info.xfb_count = count;
         }
         info.convert_depth_mode = gl_ndc;
         break;
@@ -303,7 +309,7 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device
         .support_int16 = device.IsShaderInt16Supported(),
         .support_int64 = device.IsShaderInt64Supported(),
         .support_vertex_instance_id = false,
-        .support_float_controls = true,
+        .support_float_controls = device.IsKhrShaderFloatControlsSupported(),
         .support_separate_denorm_behavior =
             float_control.denormBehaviorIndependence == VK_SHADER_FLOAT_CONTROLS_INDEPENDENCE_ALL,
         .support_separate_rounding_mode =
@@ -319,12 +325,13 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device
         .support_fp64_signed_zero_nan_preserve =
             float_control.shaderSignedZeroInfNanPreserveFloat64 != VK_FALSE,
         .support_explicit_workgroup_layout = device.IsKhrWorkgroupMemoryExplicitLayoutSupported(),
-        .support_vote = true,
+        .support_vote = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_VOTE_BIT),
         .support_viewport_index_layer_non_geometry =
             device.IsExtShaderViewportIndexLayerSupported(),
         .support_viewport_mask = device.IsNvViewportArray2Supported(),
         .support_typeless_image_loads = device.IsFormatlessImageLoadSupported(),
-        .support_demote_to_helper_invocation = true,
+        .support_demote_to_helper_invocation =
+            device.IsExtShaderDemoteToHelperInvocationSupported(),
         .support_int64_atomics = device.IsExtShaderAtomicInt64Supported(),
         .support_derivative_control = true,
         .support_geometry_shader_passthrough = device.IsNvGeometryShaderPassthroughSupported(),
@@ -705,10 +712,7 @@ std::unique_ptr<ComputePipeline> PipelineCache::CreateComputePipeline(
 std::unique_ptr<ComputePipeline> PipelineCache::CreateComputePipeline(
     ShaderPools& pools, const ComputePipelineCacheKey& key, Shader::Environment& env,
     PipelineStatistics* statistics, bool build_in_parallel) try {
-    // TODO: Remove this when Intel fixes their shader compiler.
-    //       https://github.com/IGCIT/Intel-GPU-Community-Issue-Tracker-IGCIT/issues/159
-    if (device.GetDriverID() == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS &&
-        !Settings::values.enable_compute_pipelines.GetValue()) {
+    if (device.HasBrokenCompute()) {
         LOG_ERROR(Render_Vulkan, "Skipping 0x{:016x}", key.Hash());
         return nullptr;
     }
diff --git a/src/video_core/renderer_vulkan/vk_present_manager.cpp b/src/video_core/renderer_vulkan/vk_present_manager.cpp
index 10ace0420..d681bd22a 100644
--- a/src/video_core/renderer_vulkan/vk_present_manager.cpp
+++ b/src/video_core/renderer_vulkan/vk_present_manager.cpp
@@ -181,7 +181,7 @@ void PresentManager::RecreateFrame(Frame* frame, u32 width, u32 height, bool is_
     frame->height = height;
     frame->is_srgb = is_srgb;
 
-    frame->image = dld.CreateImage({
+    frame->image = memory_allocator.CreateImage({
         .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
         .pNext = nullptr,
         .flags = VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT,
@@ -204,8 +204,6 @@ void PresentManager::RecreateFrame(Frame* frame, u32 width, u32 height, bool is_
         .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
     });
 
-    frame->image_commit = memory_allocator.Commit(frame->image, MemoryUsage::DeviceLocal);
-
     frame->image_view = dld.CreateImageView({
         .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
         .pNext = nullptr,
diff --git a/src/video_core/renderer_vulkan/vk_present_manager.h b/src/video_core/renderer_vulkan/vk_present_manager.h
index 4ac2e2395..83e859416 100644
--- a/src/video_core/renderer_vulkan/vk_present_manager.h
+++ b/src/video_core/renderer_vulkan/vk_present_manager.h
@@ -29,7 +29,6 @@ struct Frame {
     vk::Image image;
     vk::ImageView image_view;
     vk::Framebuffer framebuffer;
-    MemoryCommit image_commit;
     vk::CommandBuffer cmdbuf;
     vk::Semaphore render_ready;
     vk::Fence present_done;
diff --git a/src/video_core/renderer_vulkan/vk_rasterizer.cpp b/src/video_core/renderer_vulkan/vk_rasterizer.cpp
index 84e3a30cc..f7c0d939a 100644
--- a/src/video_core/renderer_vulkan/vk_rasterizer.cpp
+++ b/src/video_core/renderer_vulkan/vk_rasterizer.cpp
@@ -315,7 +315,14 @@ void RasterizerVulkan::Clear(u32 layer_count) {
     FlushWork();
     gpu_memory->FlushCaching();
 
+#if ANDROID
+    if (Settings::IsGPULevelHigh()) {
+        // This is problematic on Android, disable on GPU Normal.
+        query_cache.UpdateCounters();
+    }
+#else
     query_cache.UpdateCounters();
+#endif
 
     auto& regs = maxwell3d->regs;
     const bool use_color = regs.clear_surface.R || regs.clear_surface.G || regs.clear_surface.B ||
@@ -925,7 +932,7 @@ void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& reg
     }
     const bool is_rescaling{texture_cache.IsRescaling()};
     const float scale = is_rescaling ? Settings::values.resolution_info.up_factor : 1.0f;
-    const std::array viewports{
+    const std::array viewport_list{
         GetViewportState(device, regs, 0, scale),  GetViewportState(device, regs, 1, scale),
         GetViewportState(device, regs, 2, scale),  GetViewportState(device, regs, 3, scale),
         GetViewportState(device, regs, 4, scale),  GetViewportState(device, regs, 5, scale),
@@ -935,7 +942,11 @@ void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& reg
         GetViewportState(device, regs, 12, scale), GetViewportState(device, regs, 13, scale),
         GetViewportState(device, regs, 14, scale), GetViewportState(device, regs, 15, scale),
     };
-    scheduler.Record([viewports](vk::CommandBuffer cmdbuf) { cmdbuf.SetViewport(0, viewports); });
+    scheduler.Record([this, viewport_list](vk::CommandBuffer cmdbuf) {
+        const u32 num_viewports = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports);
+        const vk::Span<VkViewport> viewports(viewport_list.data(), num_viewports);
+        cmdbuf.SetViewport(0, viewports);
+    });
 }
 
 void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs) {
@@ -948,7 +959,7 @@ void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs
         up_scale = Settings::values.resolution_info.up_scale;
         down_shift = Settings::values.resolution_info.down_shift;
     }
-    const std::array scissors{
+    const std::array scissor_list{
         GetScissorState(regs, 0, up_scale, down_shift),
         GetScissorState(regs, 1, up_scale, down_shift),
         GetScissorState(regs, 2, up_scale, down_shift),
@@ -966,7 +977,11 @@ void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs
         GetScissorState(regs, 14, up_scale, down_shift),
         GetScissorState(regs, 15, up_scale, down_shift),
     };
-    scheduler.Record([scissors](vk::CommandBuffer cmdbuf) { cmdbuf.SetScissor(0, scissors); });
+    scheduler.Record([this, scissor_list](vk::CommandBuffer cmdbuf) {
+        const u32 num_scissors = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports);
+        const vk::Span<VkRect2D> scissors(scissor_list.data(), num_scissors);
+        cmdbuf.SetScissor(0, scissors);
+    });
 }
 
 void RasterizerVulkan::UpdateDepthBias(Tegra::Engines::Maxwell3D::Regs& regs) {
diff --git a/src/video_core/renderer_vulkan/vk_smaa.cpp b/src/video_core/renderer_vulkan/vk_smaa.cpp
index f8735189d..5efd7d66e 100644
--- a/src/video_core/renderer_vulkan/vk_smaa.cpp
+++ b/src/video_core/renderer_vulkan/vk_smaa.cpp
@@ -25,9 +25,7 @@ namespace {
 
 #define ARRAY_TO_SPAN(a) std::span(a, (sizeof(a) / sizeof(a[0])))
 
-std::pair<vk::Image, MemoryCommit> CreateWrappedImage(const Device& device,
-                                                      MemoryAllocator& allocator,
-                                                      VkExtent2D dimensions, VkFormat format) {
+vk::Image CreateWrappedImage(MemoryAllocator& allocator, VkExtent2D dimensions, VkFormat format) {
     const VkImageCreateInfo image_ci{
         .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
         .pNext = nullptr,
@@ -46,11 +44,7 @@ std::pair<vk::Image, MemoryCommit> CreateWrappedImage(const Device& device,
         .pQueueFamilyIndices = nullptr,
         .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
     };
-
-    auto image = device.GetLogical().CreateImage(image_ci);
-    auto commit = allocator.Commit(image, Vulkan::MemoryUsage::DeviceLocal);
-
-    return std::make_pair(std::move(image), std::move(commit));
+    return allocator.CreateImage(image_ci);
 }
 
 void TransitionImageLayout(vk::CommandBuffer& cmdbuf, VkImage image, VkImageLayout target_layout,
@@ -82,7 +76,7 @@ void TransitionImageLayout(vk::CommandBuffer& cmdbuf, VkImage image, VkImageLayo
 void UploadImage(const Device& device, MemoryAllocator& allocator, Scheduler& scheduler,
                  vk::Image& image, VkExtent2D dimensions, VkFormat format,
                  std::span<const u8> initial_contents = {}) {
-    auto upload_buffer = device.GetLogical().CreateBuffer(VkBufferCreateInfo{
+    const VkBufferCreateInfo upload_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
@@ -91,9 +85,10 @@ void UploadImage(const Device& device, MemoryAllocator& allocator, Scheduler& sc
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
-    });
-    auto upload_commit = allocator.Commit(upload_buffer, MemoryUsage::Upload);
-    std::ranges::copy(initial_contents, upload_commit.Map().begin());
+    };
+    auto upload_buffer = allocator.CreateBuffer(upload_ci, MemoryUsage::Upload);
+    std::ranges::copy(initial_contents, upload_buffer.Mapped().begin());
+    upload_buffer.Flush();
 
     const std::array<VkBufferImageCopy, 1> regions{{{
         .bufferOffset = 0,
@@ -117,9 +112,6 @@ void UploadImage(const Device& device, MemoryAllocator& allocator, Scheduler& sc
                               VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL);
     });
     scheduler.Finish();
-
-    // This should go out of scope before the commit
-    auto upload_buffer2 = std::move(upload_buffer);
 }
 
 vk::ImageView CreateWrappedImageView(const Device& device, vk::Image& image, VkFormat format) {
@@ -531,10 +523,8 @@ void SMAA::CreateImages() {
     static constexpr VkExtent2D area_extent{AREATEX_WIDTH, AREATEX_HEIGHT};
     static constexpr VkExtent2D search_extent{SEARCHTEX_WIDTH, SEARCHTEX_HEIGHT};
 
-    std::tie(m_static_images[Area], m_static_buffer_commits[Area]) =
-        CreateWrappedImage(m_device, m_allocator, area_extent, VK_FORMAT_R8G8_UNORM);
-    std::tie(m_static_images[Search], m_static_buffer_commits[Search]) =
-        CreateWrappedImage(m_device, m_allocator, search_extent, VK_FORMAT_R8_UNORM);
+    m_static_images[Area] = CreateWrappedImage(m_allocator, area_extent, VK_FORMAT_R8G8_UNORM);
+    m_static_images[Search] = CreateWrappedImage(m_allocator, search_extent, VK_FORMAT_R8_UNORM);
 
     m_static_image_views[Area] =
         CreateWrappedImageView(m_device, m_static_images[Area], VK_FORMAT_R8G8_UNORM);
@@ -544,12 +534,11 @@ void SMAA::CreateImages() {
     for (u32 i = 0; i < m_image_count; i++) {
         Images& images = m_dynamic_images.emplace_back();
 
-        std::tie(images.images[Blend], images.buffer_commits[Blend]) =
-            CreateWrappedImage(m_device, m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT);
-        std::tie(images.images[Edges], images.buffer_commits[Edges]) =
-            CreateWrappedImage(m_device, m_allocator, m_extent, VK_FORMAT_R16G16_SFLOAT);
-        std::tie(images.images[Output], images.buffer_commits[Output]) =
-            CreateWrappedImage(m_device, m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT);
+        images.images[Blend] =
+            CreateWrappedImage(m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT);
+        images.images[Edges] = CreateWrappedImage(m_allocator, m_extent, VK_FORMAT_R16G16_SFLOAT);
+        images.images[Output] =
+            CreateWrappedImage(m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT);
 
         images.image_views[Blend] =
             CreateWrappedImageView(m_device, images.images[Blend], VK_FORMAT_R16G16B16A16_SFLOAT);
diff --git a/src/video_core/renderer_vulkan/vk_smaa.h b/src/video_core/renderer_vulkan/vk_smaa.h
index 99a369148..0e214258a 100644
--- a/src/video_core/renderer_vulkan/vk_smaa.h
+++ b/src/video_core/renderer_vulkan/vk_smaa.h
@@ -66,13 +66,11 @@ private:
     std::array<vk::Pipeline, MaxSMAAStage> m_pipelines{};
     std::array<vk::RenderPass, MaxSMAAStage> m_renderpasses{};
 
-    std::array<MemoryCommit, MaxStaticImage> m_static_buffer_commits;
     std::array<vk::Image, MaxStaticImage> m_static_images{};
     std::array<vk::ImageView, MaxStaticImage> m_static_image_views{};
 
     struct Images {
         vk::DescriptorSets descriptor_sets{};
-        std::array<MemoryCommit, MaxDynamicImage> buffer_commits;
         std::array<vk::Image, MaxDynamicImage> images{};
         std::array<vk::ImageView, MaxDynamicImage> image_views{};
         std::array<vk::Framebuffer, MaxSMAAStage> framebuffers{};
diff --git a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp
index 74ca77216..ce92f66ab 100644
--- a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp
+++ b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp
@@ -30,55 +30,6 @@ constexpr VkDeviceSize MAX_STREAM_BUFFER_REQUEST_SIZE = 8_MiB;
 constexpr VkDeviceSize STREAM_BUFFER_SIZE = 128_MiB;
 constexpr VkDeviceSize REGION_SIZE = STREAM_BUFFER_SIZE / StagingBufferPool::NUM_SYNCS;
 
-constexpr VkMemoryPropertyFlags HOST_FLAGS =
-    VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
-constexpr VkMemoryPropertyFlags STREAM_FLAGS = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT | HOST_FLAGS;
-
-bool IsStreamHeap(VkMemoryHeap heap) noexcept {
-    return STREAM_BUFFER_SIZE < (heap.size * 2) / 3;
-}
-
-std::optional<u32> FindMemoryTypeIndex(const VkPhysicalDeviceMemoryProperties& props, u32 type_mask,
-                                       VkMemoryPropertyFlags flags) noexcept {
-    for (u32 type_index = 0; type_index < props.memoryTypeCount; ++type_index) {
-        if (((type_mask >> type_index) & 1) == 0) {
-            // Memory type is incompatible
-            continue;
-        }
-        const VkMemoryType& memory_type = props.memoryTypes[type_index];
-        if ((memory_type.propertyFlags & flags) != flags) {
-            // Memory type doesn't have the flags we want
-            continue;
-        }
-        if (!IsStreamHeap(props.memoryHeaps[memory_type.heapIndex])) {
-            // Memory heap is not suitable for streaming
-            continue;
-        }
-        // Success!
-        return type_index;
-    }
-    return std::nullopt;
-}
-
-u32 FindMemoryTypeIndex(const VkPhysicalDeviceMemoryProperties& props, u32 type_mask,
-                        bool try_device_local) {
-    std::optional<u32> type;
-    if (try_device_local) {
-        // Try to find a DEVICE_LOCAL_BIT type, Nvidia and AMD have a dedicated heap for this
-        type = FindMemoryTypeIndex(props, type_mask, STREAM_FLAGS);
-        if (type) {
-            return *type;
-        }
-    }
-    // Otherwise try without the DEVICE_LOCAL_BIT
-    type = FindMemoryTypeIndex(props, type_mask, HOST_FLAGS);
-    if (type) {
-        return *type;
-    }
-    // This should never happen, and in case it does, signal it as an out of memory situation
-    throw vk::Exception(VK_ERROR_OUT_OF_DEVICE_MEMORY);
-}
-
 size_t Region(size_t iterator) noexcept {
     return iterator / REGION_SIZE;
 }
@@ -87,58 +38,26 @@ size_t Region(size_t iterator) noexcept {
 StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& memory_allocator_,
                                      Scheduler& scheduler_)
     : device{device_}, memory_allocator{memory_allocator_}, scheduler{scheduler_} {
-    const vk::Device& dev = device.GetLogical();
-    stream_buffer = dev.CreateBuffer(VkBufferCreateInfo{
+    VkBufferCreateInfo stream_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
         .size = STREAM_BUFFER_SIZE,
         .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT |
-                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
-                 VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT,
+                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
-    });
-    if (device.HasDebuggingToolAttached()) {
-        stream_buffer.SetObjectNameEXT("Stream Buffer");
-    }
-    VkMemoryDedicatedRequirements dedicated_reqs{
-        .sType = VK_STRUCTURE_TYPE_MEMORY_DEDICATED_REQUIREMENTS,
-        .pNext = nullptr,
-        .prefersDedicatedAllocation = VK_FALSE,
-        .requiresDedicatedAllocation = VK_FALSE,
-    };
-    const auto requirements = dev.GetBufferMemoryRequirements(*stream_buffer, &dedicated_reqs);
-    const bool make_dedicated = dedicated_reqs.prefersDedicatedAllocation == VK_TRUE ||
-                                dedicated_reqs.requiresDedicatedAllocation == VK_TRUE;
-    const VkMemoryDedicatedAllocateInfo dedicated_info{
-        .sType = VK_STRUCTURE_TYPE_MEMORY_DEDICATED_ALLOCATE_INFO,
-        .pNext = nullptr,
-        .image = nullptr,
-        .buffer = *stream_buffer,
     };
-    const auto memory_properties = device.GetPhysical().GetMemoryProperties().memoryProperties;
-    VkMemoryAllocateInfo stream_memory_info{
-        .sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO,
-        .pNext = make_dedicated ? &dedicated_info : nullptr,
-        .allocationSize = requirements.size,
-        .memoryTypeIndex =
-            FindMemoryTypeIndex(memory_properties, requirements.memoryTypeBits, true),
-    };
-    stream_memory = dev.TryAllocateMemory(stream_memory_info);
-    if (!stream_memory) {
-        LOG_INFO(Render_Vulkan, "Dynamic memory allocation failed, trying with system memory");
-        stream_memory_info.memoryTypeIndex =
-            FindMemoryTypeIndex(memory_properties, requirements.memoryTypeBits, false);
-        stream_memory = dev.AllocateMemory(stream_memory_info);
+    if (device.IsExtTransformFeedbackSupported()) {
+        stream_ci.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
     }
-
+    stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream);
     if (device.HasDebuggingToolAttached()) {
-        stream_memory.SetObjectNameEXT("Stream Buffer Memory");
+        stream_buffer.SetObjectNameEXT("Stream Buffer");
     }
-    stream_buffer.BindMemory(*stream_memory, 0);
-    stream_pointer = stream_memory.Map(0, STREAM_BUFFER_SIZE);
+    stream_pointer = stream_buffer.Mapped();
+    ASSERT_MSG(!stream_pointer.empty(), "Stream buffer must be host visible!");
 }
 
 StagingBufferPool::~StagingBufferPool() = default;
@@ -199,7 +118,7 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) {
     return StagingBufferRef{
         .buffer = *stream_buffer,
         .offset = static_cast<VkDeviceSize>(offset),
-        .mapped_span = std::span<u8>(stream_pointer + offset, size),
+        .mapped_span = stream_pointer.subspan(offset, size),
         .usage{},
         .log2_level{},
         .index{},
@@ -247,29 +166,29 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s
 StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage,
                                                         bool deferred) {
     const u32 log2 = Common::Log2Ceil64(size);
-    vk::Buffer buffer = device.GetLogical().CreateBuffer({
+    VkBufferCreateInfo buffer_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
         .size = 1ULL << log2,
         .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT |
                  VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
-                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT |
-                 VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT,
+                 VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT,
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
-    });
+    };
+    if (device.IsExtTransformFeedbackSupported()) {
+        buffer_ci.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
+    }
+    vk::Buffer buffer = memory_allocator.CreateBuffer(buffer_ci, usage);
     if (device.HasDebuggingToolAttached()) {
         ++buffer_index;
         buffer.SetObjectNameEXT(fmt::format("Staging Buffer {}", buffer_index).c_str());
     }
-    MemoryCommit commit = memory_allocator.Commit(buffer, usage);
-    const std::span<u8> mapped_span = IsHostVisible(usage) ? commit.Map() : std::span<u8>{};
-
+    const std::span<u8> mapped_span = buffer.Mapped();
     StagingBuffer& entry = GetCache(usage)[log2].entries.emplace_back(StagingBuffer{
         .buffer = std::move(buffer),
-        .commit = std::move(commit),
         .mapped_span = mapped_span,
         .usage = usage,
         .log2_level = log2,
diff --git a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h
index 4fd15f11a..5f69f08b1 100644
--- a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h
+++ b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h
@@ -46,7 +46,6 @@ private:
 
     struct StagingBuffer {
         vk::Buffer buffer;
-        MemoryCommit commit;
         std::span<u8> mapped_span;
         MemoryUsage usage;
         u32 log2_level;
@@ -97,8 +96,7 @@ private:
     Scheduler& scheduler;
 
     vk::Buffer stream_buffer;
-    vk::DeviceMemory stream_memory;
-    u8* stream_pointer = nullptr;
+    std::span<u8> stream_pointer;
 
     size_t iterator = 0;
     size_t used_iterator = 0;
diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.cpp b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
index f025f618b..8385b5509 100644
--- a/src/video_core/renderer_vulkan/vk_texture_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
@@ -15,7 +15,6 @@
 #include "video_core/renderer_vulkan/blit_image.h"
 #include "video_core/renderer_vulkan/maxwell_to_vk.h"
 #include "video_core/renderer_vulkan/vk_compute_pass.h"
-#include "video_core/renderer_vulkan/vk_rasterizer.h"
 #include "video_core/renderer_vulkan/vk_render_pass_cache.h"
 #include "video_core/renderer_vulkan/vk_scheduler.h"
 #include "video_core/renderer_vulkan/vk_staging_buffer_pool.h"
@@ -163,11 +162,12 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
     };
 }
 
-[[nodiscard]] vk::Image MakeImage(const Device& device, const ImageInfo& info) {
+[[nodiscard]] vk::Image MakeImage(const Device& device, const MemoryAllocator& allocator,
+                                  const ImageInfo& info) {
     if (info.type == ImageType::Buffer) {
         return vk::Image{};
     }
-    return device.GetLogical().CreateImage(MakeImageCreateInfo(device, info));
+    return allocator.CreateImage(MakeImageCreateInfo(device, info));
 }
 
 [[nodiscard]] VkImageAspectFlags ImageAspectMask(PixelFormat format) {
@@ -330,9 +330,9 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
     };
 }
 
-[[maybe_unused]] [[nodiscard]] std::vector<VkBufferCopy> TransformBufferCopies(
-    std::span<const VideoCommon::BufferCopy> copies, size_t buffer_offset) {
-    std::vector<VkBufferCopy> result(copies.size());
+[[maybe_unused]] [[nodiscard]] boost::container::small_vector<VkBufferCopy, 16>
+TransformBufferCopies(std::span<const VideoCommon::BufferCopy> copies, size_t buffer_offset) {
+    boost::container::small_vector<VkBufferCopy, 16> result(copies.size());
     std::ranges::transform(
         copies, result.begin(), [buffer_offset](const VideoCommon::BufferCopy& copy) {
             return VkBufferCopy{
@@ -344,7 +344,7 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
     return result;
 }
 
-[[nodiscard]] std::vector<VkBufferImageCopy> TransformBufferImageCopies(
+[[nodiscard]] boost::container::small_vector<VkBufferImageCopy, 16> TransformBufferImageCopies(
     std::span<const BufferImageCopy> copies, size_t buffer_offset, VkImageAspectFlags aspect_mask) {
     struct Maker {
         VkBufferImageCopy operator()(const BufferImageCopy& copy) const {
@@ -377,14 +377,14 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
         VkImageAspectFlags aspect_mask;
     };
     if (aspect_mask == (VK_IMAGE_ASPECT_DEPTH_BIT | VK_IMAGE_ASPECT_STENCIL_BIT)) {
-        std::vector<VkBufferImageCopy> result(copies.size() * 2);
+        boost::container::small_vector<VkBufferImageCopy, 16> result(copies.size() * 2);
         std::ranges::transform(copies, result.begin(),
                                Maker{buffer_offset, VK_IMAGE_ASPECT_DEPTH_BIT});
         std::ranges::transform(copies, result.begin() + copies.size(),
                                Maker{buffer_offset, VK_IMAGE_ASPECT_STENCIL_BIT});
         return result;
     } else {
-        std::vector<VkBufferImageCopy> result(copies.size());
+        boost::container::small_vector<VkBufferImageCopy, 16> result(copies.size());
         std::ranges::transform(copies, result.begin(), Maker{buffer_offset, aspect_mask});
         return result;
     }
@@ -839,14 +839,14 @@ bool TextureCacheRuntime::ShouldReinterpret(Image& dst, Image& src) {
 
 VkBuffer TextureCacheRuntime::GetTemporaryBuffer(size_t needed_size) {
     const auto level = (8 * sizeof(size_t)) - std::countl_zero(needed_size - 1ULL);
-    if (buffer_commits[level]) {
+    if (buffers[level]) {
         return *buffers[level];
     }
     const auto new_size = Common::NextPow2(needed_size);
     static constexpr VkBufferUsageFlags flags =
         VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT |
         VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_TEXEL_BUFFER_BIT;
-    buffers[level] = device.GetLogical().CreateBuffer({
+    const VkBufferCreateInfo temp_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
@@ -855,9 +855,8 @@ VkBuffer TextureCacheRuntime::GetTemporaryBuffer(size_t needed_size) {
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
-    });
-    buffer_commits[level] = std::make_unique<MemoryCommit>(
-        memory_allocator.Commit(buffers[level], MemoryUsage::DeviceLocal));
+    };
+    buffers[level] = memory_allocator.CreateBuffer(temp_ci, MemoryUsage::DeviceLocal);
     return *buffers[level];
 }
 
@@ -867,8 +866,8 @@ void TextureCacheRuntime::BarrierFeedbackLoop() {
 
 void TextureCacheRuntime::ReinterpretImage(Image& dst, Image& src,
                                            std::span<const VideoCommon::ImageCopy> copies) {
-    std::vector<VkBufferImageCopy> vk_in_copies(copies.size());
-    std::vector<VkBufferImageCopy> vk_out_copies(copies.size());
+    boost::container::small_vector<VkBufferImageCopy, 16> vk_in_copies(copies.size());
+    boost::container::small_vector<VkBufferImageCopy, 16> vk_out_copies(copies.size());
     const VkImageAspectFlags src_aspect_mask = src.AspectMask();
     const VkImageAspectFlags dst_aspect_mask = dst.AspectMask();
 
@@ -1157,7 +1156,7 @@ void TextureCacheRuntime::ConvertImage(Framebuffer* dst, ImageView& dst_view, Im
 
 void TextureCacheRuntime::CopyImage(Image& dst, Image& src,
                                     std::span<const VideoCommon::ImageCopy> copies) {
-    std::vector<VkImageCopy> vk_copies(copies.size());
+    boost::container::small_vector<VkImageCopy, 16> vk_copies(copies.size());
     const VkImageAspectFlags aspect_mask = dst.AspectMask();
     ASSERT(aspect_mask == src.AspectMask());
 
@@ -1266,8 +1265,8 @@ void TextureCacheRuntime::TickFrame() {}
 Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu_addr_,
              VAddr cpu_addr_)
     : VideoCommon::ImageBase(info_, gpu_addr_, cpu_addr_), scheduler{&runtime_.scheduler},
-      runtime{&runtime_}, original_image(MakeImage(runtime_.device, info)),
-      commit(runtime_.memory_allocator.Commit(original_image, MemoryUsage::DeviceLocal)),
+      runtime{&runtime_},
+      original_image(MakeImage(runtime_.device, runtime_.memory_allocator, info)),
       aspect_mask(ImageAspectMask(info.format)) {
     if (IsPixelFormatASTC(info.format) && !runtime->device.IsOptimalAstcSupported()) {
         if (Settings::values.async_astc.GetValue()) {
@@ -1280,6 +1279,10 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
         flags |= VideoCommon::ImageFlagBits::Converted;
         flags |= VideoCommon::ImageFlagBits::CostlyLoad;
     }
+    if (IsPixelFormatBCn(info.format) && !runtime->device.IsOptimalBcnSupported()) {
+        flags |= VideoCommon::ImageFlagBits::Converted;
+        flags |= VideoCommon::ImageFlagBits::CostlyLoad;
+    }
     if (runtime->device.HasDebuggingToolAttached()) {
         original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str());
     }
@@ -1332,7 +1335,7 @@ void Image::UploadMemory(VkBuffer buffer, VkDeviceSize offset,
         ScaleDown(true);
     }
     scheduler->RequestOutsideRenderPassOperationContext();
-    std::vector vk_copies = TransformBufferImageCopies(copies, offset, aspect_mask);
+    auto vk_copies = TransformBufferImageCopies(copies, offset, aspect_mask);
     const VkBuffer src_buffer = buffer;
     const VkImage vk_image = *original_image;
     const VkImageAspectFlags vk_aspect_mask = aspect_mask;
@@ -1367,8 +1370,9 @@ void Image::DownloadMemory(std::span<VkBuffer> buffers_span, std::span<VkDeviceS
     if (is_rescaled) {
         ScaleDown();
     }
-    boost::container::small_vector<VkBuffer, 1> buffers_vector{};
-    boost::container::small_vector<std::vector<VkBufferImageCopy>, 1> vk_copies;
+    boost::container::small_vector<VkBuffer, 8> buffers_vector{};
+    boost::container::small_vector<boost::container::small_vector<VkBufferImageCopy, 16>, 8>
+        vk_copies;
     for (size_t index = 0; index < buffers_span.size(); index++) {
         buffers_vector.emplace_back(buffers_span[index]);
         vk_copies.emplace_back(
@@ -1467,9 +1471,7 @@ bool Image::ScaleUp(bool ignore) {
         auto scaled_info = info;
         scaled_info.size.width = scaled_width;
         scaled_info.size.height = scaled_height;
-        scaled_image = MakeImage(runtime->device, scaled_info);
-        auto& allocator = runtime->memory_allocator;
-        scaled_commit = MemoryCommit(allocator.Commit(scaled_image, MemoryUsage::DeviceLocal));
+        scaled_image = MakeImage(runtime->device, runtime->memory_allocator, scaled_info);
         ignore = false;
     }
     current_image = *scaled_image;
@@ -1858,7 +1860,7 @@ Framebuffer::~Framebuffer() = default;
 void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
                                     std::span<ImageView*, NUM_RT> color_buffers,
                                     ImageView* depth_buffer, bool is_rescaled) {
-    std::vector<VkImageView> attachments;
+    boost::container::small_vector<VkImageView, NUM_RT + 1> attachments;
     RenderPassKey renderpass_key{};
     s32 num_layers = 1;
 
diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.h b/src/video_core/renderer_vulkan/vk_texture_cache.h
index f14525dcb..220943116 100644
--- a/src/video_core/renderer_vulkan/vk_texture_cache.h
+++ b/src/video_core/renderer_vulkan/vk_texture_cache.h
@@ -116,7 +116,6 @@ public:
 
     static constexpr size_t indexing_slots = 8 * sizeof(size_t);
     std::array<vk::Buffer, indexing_slots> buffers{};
-    std::array<std::unique_ptr<MemoryCommit>, indexing_slots> buffer_commits{};
 };
 
 class Image : public VideoCommon::ImageBase {
@@ -180,12 +179,10 @@ private:
     TextureCacheRuntime* runtime{};
 
     vk::Image original_image;
-    MemoryCommit commit;
     std::vector<vk::ImageView> storage_image_views;
     VkImageAspectFlags aspect_mask = 0;
     bool initialized = false;
     vk::Image scaled_image{};
-    MemoryCommit scaled_commit{};
     VkImage current_image{};
 
     std::unique_ptr<Framebuffer> scale_framebuffer;
diff --git a/src/video_core/renderer_vulkan/vk_turbo_mode.cpp b/src/video_core/renderer_vulkan/vk_turbo_mode.cpp
index a802d3c49..460d8d59d 100644
--- a/src/video_core/renderer_vulkan/vk_turbo_mode.cpp
+++ b/src/video_core/renderer_vulkan/vk_turbo_mode.cpp
@@ -18,7 +18,7 @@ using namespace Common::Literals;
 
 TurboMode::TurboMode(const vk::Instance& instance, const vk::InstanceDispatch& dld)
 #ifndef ANDROID
-    : m_device{CreateDevice(instance, dld, VK_NULL_HANDLE)}, m_allocator{m_device, false}
+    : m_device{CreateDevice(instance, dld, VK_NULL_HANDLE)}, m_allocator{m_device}
 #endif
 {
     {
@@ -41,7 +41,7 @@ void TurboMode::Run(std::stop_token stop_token) {
     auto& dld = m_device.GetLogical();
 
     // Allocate buffer. 2MiB should be sufficient.
-    auto buffer = dld.CreateBuffer(VkBufferCreateInfo{
+    const VkBufferCreateInfo buffer_ci = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
         .pNext = nullptr,
         .flags = 0,
@@ -50,10 +50,8 @@ void TurboMode::Run(std::stop_token stop_token) {
         .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
         .queueFamilyIndexCount = 0,
         .pQueueFamilyIndices = nullptr,
-    });
-
-    // Commit some device local memory for the buffer.
-    auto commit = m_allocator.Commit(buffer, MemoryUsage::DeviceLocal);
+    };
+    vk::Buffer buffer = m_allocator.CreateBuffer(buffer_ci, MemoryUsage::DeviceLocal);
 
     // Create the descriptor pool to contain our descriptor.
     static constexpr VkDescriptorPoolSize pool_size{
diff --git a/src/video_core/shader_cache.cpp b/src/video_core/shader_cache.cpp
index c5213875b..4db948b6d 100644
--- a/src/video_core/shader_cache.cpp
+++ b/src/video_core/shader_cache.cpp
@@ -151,11 +151,9 @@ void ShaderCache::RemovePendingShaders() {
     marked_for_removal.erase(std::unique(marked_for_removal.begin(), marked_for_removal.end()),
                              marked_for_removal.end());
 
-    std::vector<ShaderInfo*> removed_shaders;
-    removed_shaders.reserve(marked_for_removal.size());
+    boost::container::small_vector<ShaderInfo*, 16> removed_shaders;
 
     std::scoped_lock lock{lookup_mutex};
-
     for (Entry* const entry : marked_for_removal) {
         removed_shaders.push_back(entry->data);
 
diff --git a/src/video_core/surface.cpp b/src/video_core/surface.cpp
index cb51529e4..e16cd5e73 100644
--- a/src/video_core/surface.cpp
+++ b/src/video_core/surface.cpp
@@ -269,6 +269,28 @@ bool IsPixelFormatASTC(PixelFormat format) {
     }
 }
 
+bool IsPixelFormatBCn(PixelFormat format) {
+    switch (format) {
+    case PixelFormat::BC1_RGBA_UNORM:
+    case PixelFormat::BC2_UNORM:
+    case PixelFormat::BC3_UNORM:
+    case PixelFormat::BC4_UNORM:
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC5_UNORM:
+    case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC1_RGBA_SRGB:
+    case PixelFormat::BC2_SRGB:
+    case PixelFormat::BC3_SRGB:
+    case PixelFormat::BC7_UNORM:
+    case PixelFormat::BC6H_UFLOAT:
+    case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC7_SRGB:
+        return true;
+    default:
+        return false;
+    }
+}
+
 bool IsPixelFormatSRGB(PixelFormat format) {
     switch (format) {
     case PixelFormat::A8B8G8R8_SRGB:
diff --git a/src/video_core/surface.h b/src/video_core/surface.h
index 0225d3287..9b9c4d9bc 100644
--- a/src/video_core/surface.h
+++ b/src/video_core/surface.h
@@ -501,6 +501,8 @@ SurfaceType GetFormatType(PixelFormat pixel_format);
 
 bool IsPixelFormatASTC(PixelFormat format);
 
+bool IsPixelFormatBCn(PixelFormat format);
+
 bool IsPixelFormatSRGB(PixelFormat format);
 
 bool IsPixelFormatInteger(PixelFormat format);
diff --git a/src/video_core/texture_cache/decode_bc.cpp b/src/video_core/texture_cache/decode_bc.cpp
new file mode 100644
index 000000000..3e26474a3
--- /dev/null
+++ b/src/video_core/texture_cache/decode_bc.cpp
@@ -0,0 +1,129 @@
+// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <algorithm>
+#include <array>
+#include <span>
+#include <bc_decoder.h>
+
+#include "common/common_types.h"
+#include "video_core/texture_cache/decode_bc.h"
+
+namespace VideoCommon {
+
+namespace {
+constexpr u32 BLOCK_SIZE = 4;
+
+using VideoCore::Surface::PixelFormat;
+
+constexpr bool IsSigned(PixelFormat pixel_format) {
+    switch (pixel_format) {
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC4_UNORM:
+    case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC5_UNORM:
+    case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC6H_UFLOAT:
+        return true;
+    default:
+        return false;
+    }
+}
+
+constexpr u32 BlockSize(PixelFormat pixel_format) {
+    switch (pixel_format) {
+    case PixelFormat::BC1_RGBA_SRGB:
+    case PixelFormat::BC1_RGBA_UNORM:
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC4_UNORM:
+        return 8;
+    default:
+        return 16;
+    }
+}
+} // Anonymous namespace
+
+u32 ConvertedBytesPerBlock(VideoCore::Surface::PixelFormat pixel_format) {
+    switch (pixel_format) {
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC4_UNORM:
+        return 1;
+    case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC5_UNORM:
+        return 2;
+    case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC6H_UFLOAT:
+        return 8;
+    default:
+        return 4;
+    }
+}
+
+template <auto decompress, PixelFormat pixel_format>
+void DecompressBlocks(std::span<const u8> input, std::span<u8> output, Extent3D extent,
+                      bool is_signed = false) {
+    const u32 out_bpp = ConvertedBytesPerBlock(pixel_format);
+    const u32 block_width = std::min(extent.width, BLOCK_SIZE);
+    const u32 block_height = std::min(extent.height, BLOCK_SIZE);
+    const u32 pitch = extent.width * out_bpp;
+    size_t input_offset = 0;
+    size_t output_offset = 0;
+    for (u32 slice = 0; slice < extent.depth; ++slice) {
+        for (u32 y = 0; y < extent.height; y += block_height) {
+            size_t row_offset = 0;
+            for (u32 x = 0; x < extent.width;
+                 x += block_width, row_offset += block_width * out_bpp) {
+                const u8* src = input.data() + input_offset;
+                u8* const dst = output.data() + output_offset + row_offset;
+                if constexpr (IsSigned(pixel_format)) {
+                    decompress(src, dst, x, y, extent.width, extent.height, is_signed);
+                } else {
+                    decompress(src, dst, x, y, extent.width, extent.height);
+                }
+                input_offset += BlockSize(pixel_format);
+            }
+            output_offset += block_height * pitch;
+        }
+    }
+}
+
+void DecompressBCn(std::span<const u8> input, std::span<u8> output, Extent3D extent,
+                   VideoCore::Surface::PixelFormat pixel_format) {
+    switch (pixel_format) {
+    case PixelFormat::BC1_RGBA_UNORM:
+    case PixelFormat::BC1_RGBA_SRGB:
+        DecompressBlocks<bcn::DecodeBc1, PixelFormat::BC1_RGBA_UNORM>(input, output, extent);
+        break;
+    case PixelFormat::BC2_UNORM:
+    case PixelFormat::BC2_SRGB:
+        DecompressBlocks<bcn::DecodeBc2, PixelFormat::BC2_UNORM>(input, output, extent);
+        break;
+    case PixelFormat::BC3_UNORM:
+    case PixelFormat::BC3_SRGB:
+        DecompressBlocks<bcn::DecodeBc3, PixelFormat::BC3_UNORM>(input, output, extent);
+        break;
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC4_UNORM:
+        DecompressBlocks<bcn::DecodeBc4, PixelFormat::BC4_UNORM>(
+            input, output, extent, pixel_format == PixelFormat::BC4_SNORM);
+        break;
+    case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC5_UNORM:
+        DecompressBlocks<bcn::DecodeBc5, PixelFormat::BC5_UNORM>(
+            input, output, extent, pixel_format == PixelFormat::BC5_SNORM);
+        break;
+    case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC6H_UFLOAT:
+        DecompressBlocks<bcn::DecodeBc6, PixelFormat::BC6H_UFLOAT>(
+            input, output, extent, pixel_format == PixelFormat::BC6H_SFLOAT);
+        break;
+    case PixelFormat::BC7_SRGB:
+    case PixelFormat::BC7_UNORM:
+        DecompressBlocks<bcn::DecodeBc7, PixelFormat::BC7_UNORM>(input, output, extent);
+        break;
+    default:
+        LOG_WARNING(HW_GPU, "Unimplemented BCn decompression {}", pixel_format);
+    }
+}
+
+} // namespace VideoCommon
diff --git a/src/video_core/texture_cache/decode_bc4.h b/src/video_core/texture_cache/decode_bc.h
index ab2f735be..41d1ec0a3 100644
--- a/src/video_core/texture_cache/decode_bc4.h
+++ b/src/video_core/texture_cache/decode_bc.h
@@ -6,10 +6,14 @@
 #include <span>
 
 #include "common/common_types.h"
+#include "video_core/surface.h"
 #include "video_core/texture_cache/types.h"
 
 namespace VideoCommon {
 
-void DecompressBC4(std::span<const u8> data, Extent3D extent, std::span<u8> output);
+[[nodiscard]] u32 ConvertedBytesPerBlock(VideoCore::Surface::PixelFormat pixel_format);
+
+void DecompressBCn(std::span<const u8> input, std::span<u8> output, Extent3D extent,
+                   VideoCore::Surface::PixelFormat pixel_format);
 
 } // namespace VideoCommon
diff --git a/src/video_core/texture_cache/decode_bc4.cpp b/src/video_core/texture_cache/decode_bc4.cpp
deleted file mode 100644
index ef98afdca..000000000
--- a/src/video_core/texture_cache/decode_bc4.cpp
+++ /dev/null
@@ -1,96 +0,0 @@
-// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-#include <algorithm>
-#include <array>
-#include <span>
-
-#include "common/assert.h"
-#include "common/common_types.h"
-#include "video_core/texture_cache/decode_bc4.h"
-#include "video_core/texture_cache/types.h"
-
-namespace VideoCommon {
-
-// https://www.khronos.org/registry/OpenGL/extensions/ARB/ARB_texture_compression_rgtc.txt
-[[nodiscard]] constexpr u32 DecompressBlock(u64 bits, u32 x, u32 y) {
-    const u32 code_offset = 16 + 3 * (4 * y + x);
-    const u32 code = (bits >> code_offset) & 7;
-    const u32 red0 = (bits >> 0) & 0xff;
-    const u32 red1 = (bits >> 8) & 0xff;
-    if (red0 > red1) {
-        switch (code) {
-        case 0:
-            return red0;
-        case 1:
-            return red1;
-        case 2:
-            return (6 * red0 + 1 * red1) / 7;
-        case 3:
-            return (5 * red0 + 2 * red1) / 7;
-        case 4:
-            return (4 * red0 + 3 * red1) / 7;
-        case 5:
-            return (3 * red0 + 4 * red1) / 7;
-        case 6:
-            return (2 * red0 + 5 * red1) / 7;
-        case 7:
-            return (1 * red0 + 6 * red1) / 7;
-        }
-    } else {
-        switch (code) {
-        case 0:
-            return red0;
-        case 1:
-            return red1;
-        case 2:
-            return (4 * red0 + 1 * red1) / 5;
-        case 3:
-            return (3 * red0 + 2 * red1) / 5;
-        case 4:
-            return (2 * red0 + 3 * red1) / 5;
-        case 5:
-            return (1 * red0 + 4 * red1) / 5;
-        case 6:
-            return 0;
-        case 7:
-            return 0xff;
-        }
-    }
-    return 0;
-}
-
-void DecompressBC4(std::span<const u8> input, Extent3D extent, std::span<u8> output) {
-    UNIMPLEMENTED_IF_MSG(extent.width % 4 != 0, "Unaligned width={}", extent.width);
-    UNIMPLEMENTED_IF_MSG(extent.height % 4 != 0, "Unaligned height={}", extent.height);
-    static constexpr u32 BLOCK_SIZE = 4;
-    size_t input_offset = 0;
-    for (u32 slice = 0; slice < extent.depth; ++slice) {
-        for (u32 block_y = 0; block_y < extent.height / 4; ++block_y) {
-            for (u32 block_x = 0; block_x < extent.width / 4; ++block_x) {
-                u64 bits;
-                std::memcpy(&bits, &input[input_offset], sizeof(bits));
-                input_offset += sizeof(bits);
-
-                for (u32 y = 0; y < BLOCK_SIZE; ++y) {
-                    for (u32 x = 0; x < BLOCK_SIZE; ++x) {
-                        const u32 linear_z = slice;
-                        const u32 linear_y = block_y * BLOCK_SIZE + y;
-                        const u32 linear_x = block_x * BLOCK_SIZE + x;
-                        const u32 offset_z = linear_z * extent.width * extent.height;
-                        const u32 offset_y = linear_y * extent.width;
-                        const u32 offset_x = linear_x;
-                        const u32 output_offset = (offset_z + offset_y + offset_x) * 4ULL;
-                        const u32 color = DecompressBlock(bits, x, y);
-                        output[output_offset + 0] = static_cast<u8>(color);
-                        output[output_offset + 1] = 0;
-                        output[output_offset + 2] = 0;
-                        output[output_offset + 3] = 0xff;
-                    }
-                }
-            }
-        }
-    }
-}
-
-} // namespace VideoCommon
diff --git a/src/video_core/texture_cache/image_base.h b/src/video_core/texture_cache/image_base.h
index 1b8a17ee8..55d49d017 100644
--- a/src/video_core/texture_cache/image_base.h
+++ b/src/video_core/texture_cache/image_base.h
@@ -6,6 +6,7 @@
 #include <array>
 #include <optional>
 #include <vector>
+#include <boost/container/small_vector.hpp>
 
 #include "common/common_funcs.h"
 #include "common/common_types.h"
@@ -108,8 +109,8 @@ struct ImageBase {
     std::vector<ImageViewInfo> image_view_infos;
     std::vector<ImageViewId> image_view_ids;
 
-    std::vector<u32> slice_offsets;
-    std::vector<SubresourceBase> slice_subresources;
+    boost::container::small_vector<u32, 16> slice_offsets;
+    boost::container::small_vector<SubresourceBase, 16> slice_subresources;
 
     std::vector<AliasedImage> aliased_images;
     std::vector<ImageId> overlapping_images;
diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index 4027d860b..8190f3ba1 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -186,6 +186,10 @@ void TextureCache<P>::FillComputeImageViews(std::span<ImageViewInOut> views) {
 
 template <class P>
 void TextureCache<P>::CheckFeedbackLoop(std::span<const ImageViewInOut> views) {
+    if (!Settings::values.barrier_feedback_loops.GetValue()) {
+        return;
+    }
+
     const bool requires_barrier = [&] {
         for (const auto& view : views) {
             if (!view.id) {
@@ -300,7 +304,7 @@ void TextureCache<P>::SynchronizeComputeDescriptors() {
 }
 
 template <class P>
-bool TextureCache<P>::RescaleRenderTargets(bool is_clear) {
+bool TextureCache<P>::RescaleRenderTargets() {
     auto& flags = maxwell3d->dirty.flags;
     u32 scale_rating = 0;
     bool rescaled = false;
@@ -338,13 +342,13 @@ bool TextureCache<P>::RescaleRenderTargets(bool is_clear) {
             ImageViewId& color_buffer_id = render_targets.color_buffer_ids[index];
             if (flags[Dirty::ColorBuffer0 + index] || force) {
                 flags[Dirty::ColorBuffer0 + index] = false;
-                BindRenderTarget(&color_buffer_id, FindColorBuffer(index, is_clear));
+                BindRenderTarget(&color_buffer_id, FindColorBuffer(index));
             }
             check_rescale(color_buffer_id, tmp_color_images[index]);
         }
         if (flags[Dirty::ZetaBuffer] || force) {
             flags[Dirty::ZetaBuffer] = false;
-            BindRenderTarget(&render_targets.depth_buffer_id, FindDepthBuffer(is_clear));
+            BindRenderTarget(&render_targets.depth_buffer_id, FindDepthBuffer());
         }
         check_rescale(render_targets.depth_buffer_id, tmp_depth_image);
 
@@ -409,7 +413,7 @@ void TextureCache<P>::UpdateRenderTargets(bool is_clear) {
         return;
     }
 
-    const bool rescaled = RescaleRenderTargets(is_clear);
+    const bool rescaled = RescaleRenderTargets();
     if (is_rescaling != rescaled) {
         flags[Dirty::RescaleViewports] = true;
         flags[Dirty::RescaleScissors] = true;
@@ -522,7 +526,7 @@ void TextureCache<P>::WriteMemory(VAddr cpu_addr, size_t size) {
 
 template <class P>
 void TextureCache<P>::DownloadMemory(VAddr cpu_addr, size_t size) {
-    std::vector<ImageId> images;
+    boost::container::small_vector<ImageId, 16> images;
     ForEachImageInRegion(cpu_addr, size, [&images](ImageId image_id, ImageBase& image) {
         if (!image.IsSafeDownload()) {
             return;
@@ -575,7 +579,7 @@ std::optional<VideoCore::RasterizerDownloadArea> TextureCache<P>::GetFlushArea(V
 
 template <class P>
 void TextureCache<P>::UnmapMemory(VAddr cpu_addr, size_t size) {
-    std::vector<ImageId> deleted_images;
+    boost::container::small_vector<ImageId, 16> deleted_images;
     ForEachImageInRegion(cpu_addr, size, [&](ImageId id, Image&) { deleted_images.push_back(id); });
     for (const ImageId id : deleted_images) {
         Image& image = slot_images[id];
@@ -589,19 +593,11 @@ void TextureCache<P>::UnmapMemory(VAddr cpu_addr, size_t size) {
 
 template <class P>
 void TextureCache<P>::UnmapGPUMemory(size_t as_id, GPUVAddr gpu_addr, size_t size) {
-    std::vector<ImageId> deleted_images;
+    boost::container::small_vector<ImageId, 16> deleted_images;
     ForEachImageInRegionGPU(as_id, gpu_addr, size,
                             [&](ImageId id, Image&) { deleted_images.push_back(id); });
     for (const ImageId id : deleted_images) {
         Image& image = slot_images[id];
-        if (True(image.flags & ImageFlagBits::CpuModified)) {
-            return;
-        }
-        image.flags |= ImageFlagBits::CpuModified;
-        if (True(image.flags & ImageFlagBits::Tracked)) {
-            UntrackImage(image, id);
-        }
-        /*
         if (True(image.flags & ImageFlagBits::Remapped)) {
             continue;
         }
@@ -609,7 +605,6 @@ void TextureCache<P>::UnmapGPUMemory(size_t as_id, GPUVAddr gpu_addr, size_t siz
         if (True(image.flags & ImageFlagBits::Tracked)) {
             UntrackImage(image, id);
         }
-        */
     }
 }
 
@@ -875,6 +870,10 @@ ImageId TextureCache<P>::DmaImageId(const Tegra::DMA::ImageOperand& operand, boo
         return NULL_IMAGE_ID;
     }
     auto& image = slot_images[image_id];
+    if (image.info.type == ImageType::e3D) {
+        // Don't accelerate 3D images.
+        return NULL_IMAGE_ID;
+    }
     if (!is_upload && !image.info.dma_downloaded) {
         // Force a full sync.
         image.info.dma_downloaded = true;
@@ -1097,7 +1096,7 @@ ImageId TextureCache<P>::FindImage(const ImageInfo& info, GPUVAddr gpu_addr,
     const bool native_bgr = runtime.HasNativeBgr();
     const bool flexible_formats = True(options & RelaxedOptions::Format);
     ImageId image_id{};
-    boost::container::small_vector<ImageId, 1> image_ids;
+    boost::container::small_vector<ImageId, 8> image_ids;
     const auto lambda = [&](ImageId existing_image_id, ImageBase& existing_image) {
         if (True(existing_image.flags & ImageFlagBits::Remapped)) {
             return false;
@@ -1618,7 +1617,7 @@ ImageId TextureCache<P>::FindDMAImage(const ImageInfo& info, GPUVAddr gpu_addr)
         }
     }
     ImageId image_id{};
-    boost::container::small_vector<ImageId, 1> image_ids;
+    boost::container::small_vector<ImageId, 8> image_ids;
     const auto lambda = [&](ImageId existing_image_id, ImageBase& existing_image) {
         if (True(existing_image.flags & ImageFlagBits::Remapped)) {
             return false;
@@ -1678,7 +1677,7 @@ SamplerId TextureCache<P>::FindSampler(const TSCEntry& config) {
 }
 
 template <class P>
-ImageViewId TextureCache<P>::FindColorBuffer(size_t index, bool is_clear) {
+ImageViewId TextureCache<P>::FindColorBuffer(size_t index) {
     const auto& regs = maxwell3d->regs;
     if (index >= regs.rt_control.count) {
         return ImageViewId{};
@@ -1692,11 +1691,11 @@ ImageViewId TextureCache<P>::FindColorBuffer(size_t index, bool is_clear) {
         return ImageViewId{};
     }
     const ImageInfo info(regs.rt[index], regs.anti_alias_samples_mode);
-    return FindRenderTargetView(info, gpu_addr, is_clear);
+    return FindRenderTargetView(info, gpu_addr);
 }
 
 template <class P>
-ImageViewId TextureCache<P>::FindDepthBuffer(bool is_clear) {
+ImageViewId TextureCache<P>::FindDepthBuffer() {
     const auto& regs = maxwell3d->regs;
     if (!regs.zeta_enable) {
         return ImageViewId{};
@@ -1706,18 +1705,16 @@ ImageViewId TextureCache<P>::FindDepthBuffer(bool is_clear) {
         return ImageViewId{};
     }
     const ImageInfo info(regs.zeta, regs.zeta_size, regs.anti_alias_samples_mode);
-    return FindRenderTargetView(info, gpu_addr, is_clear);
+    return FindRenderTargetView(info, gpu_addr);
 }
 
 template <class P>
-ImageViewId TextureCache<P>::FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr,
-                                                  bool is_clear) {
-    const auto options = is_clear ? RelaxedOptions::Samples : RelaxedOptions{};
+ImageViewId TextureCache<P>::FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr) {
     ImageId image_id{};
     bool delete_state = has_deleted_images;
     do {
         has_deleted_images = false;
-        image_id = FindOrInsertImage(info, gpu_addr, options);
+        image_id = FindOrInsertImage(info, gpu_addr);
         delete_state |= has_deleted_images;
     } while (has_deleted_images);
     has_deleted_images = delete_state;
@@ -1940,7 +1937,7 @@ void TextureCache<P>::RegisterImage(ImageId image_id) {
         image.map_view_id = map_id;
         return;
     }
-    std::vector<ImageViewId> sparse_maps{};
+    boost::container::small_vector<ImageViewId, 16> sparse_maps;
     ForEachSparseSegment(
         image, [this, image_id, &sparse_maps](GPUVAddr gpu_addr, VAddr cpu_addr, size_t size) {
             auto map_id = slot_map_views.insert(gpu_addr, cpu_addr, size, image_id);
@@ -2215,7 +2212,7 @@ void TextureCache<P>::MarkModification(ImageBase& image) noexcept {
 
 template <class P>
 void TextureCache<P>::SynchronizeAliases(ImageId image_id) {
-    boost::container::small_vector<const AliasedImage*, 1> aliased_images;
+    boost::container::small_vector<const AliasedImage*, 8> aliased_images;
     Image& image = slot_images[image_id];
     bool any_rescaled = True(image.flags & ImageFlagBits::Rescaled);
     bool any_modified = True(image.flags & ImageFlagBits::GpuModified);
diff --git a/src/video_core/texture_cache/texture_cache_base.h b/src/video_core/texture_cache/texture_cache_base.h
index d96ddea9d..e9ec91265 100644
--- a/src/video_core/texture_cache/texture_cache_base.h
+++ b/src/video_core/texture_cache/texture_cache_base.h
@@ -56,7 +56,7 @@ struct ImageViewInOut {
 struct AsyncDecodeContext {
     ImageId image_id;
     Common::ScratchBuffer<u8> decoded_data;
-    std::vector<BufferImageCopy> copies;
+    boost::container::small_vector<BufferImageCopy, 16> copies;
     std::mutex mutex;
     std::atomic_bool complete;
 };
@@ -178,9 +178,8 @@ public:
     void SynchronizeComputeDescriptors();
 
     /// Updates the Render Targets if they can be rescaled
-    /// @param is_clear True when the render targets are being used for clears
     /// @retval True if the Render Targets have been rescaled.
-    bool RescaleRenderTargets(bool is_clear);
+    bool RescaleRenderTargets();
 
     /// Update bound render targets and upload memory if necessary
     /// @param is_clear True when the render targets are being used for clears
@@ -336,14 +335,13 @@ private:
     [[nodiscard]] SamplerId FindSampler(const TSCEntry& config);
 
     /// Find or create an image view for the given color buffer index
-    [[nodiscard]] ImageViewId FindColorBuffer(size_t index, bool is_clear);
+    [[nodiscard]] ImageViewId FindColorBuffer(size_t index);
 
     /// Find or create an image view for the depth buffer
-    [[nodiscard]] ImageViewId FindDepthBuffer(bool is_clear);
+    [[nodiscard]] ImageViewId FindDepthBuffer();
 
     /// Find or create a view for a render target with the given image parameters
-    [[nodiscard]] ImageViewId FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr,
-                                                   bool is_clear);
+    [[nodiscard]] ImageViewId FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr);
 
     /// Iterates over all the images in a region calling func
     template <typename Func>
@@ -431,7 +429,7 @@ private:
 
     std::unordered_map<u64, std::vector<ImageMapId>, Common::IdentityHash<u64>> page_table;
     std::unordered_map<u64, std::vector<ImageId>, Common::IdentityHash<u64>> sparse_page_table;
-    std::unordered_map<ImageId, std::vector<ImageViewId>> sparse_views;
+    std::unordered_map<ImageId, boost::container::small_vector<ImageViewId, 16>> sparse_views;
 
     VAddr virtual_invalid_space{};
 
diff --git a/src/video_core/texture_cache/util.cpp b/src/video_core/texture_cache/util.cpp
index 95a5b47d8..9a618a57a 100644
--- a/src/video_core/texture_cache/util.cpp
+++ b/src/video_core/texture_cache/util.cpp
@@ -24,7 +24,7 @@
 #include "video_core/engines/maxwell_3d.h"
 #include "video_core/memory_manager.h"
 #include "video_core/surface.h"
-#include "video_core/texture_cache/decode_bc4.h"
+#include "video_core/texture_cache/decode_bc.h"
 #include "video_core/texture_cache/format_lookup_table.h"
 #include "video_core/texture_cache/formatter.h"
 #include "video_core/texture_cache/samples_helper.h"
@@ -61,8 +61,6 @@ using VideoCore::Surface::PixelFormatFromDepthFormat;
 using VideoCore::Surface::PixelFormatFromRenderTargetFormat;
 using VideoCore::Surface::SurfaceType;
 
-constexpr u32 CONVERTED_BYTES_PER_BLOCK = BytesPerBlock(PixelFormat::A8B8G8R8_UNORM);
-
 struct LevelInfo {
     Extent3D size;
     Extent3D block;
@@ -329,13 +327,13 @@ template <u32 GOB_EXTENT>
 
 [[nodiscard]] std::optional<SubresourceExtent> ResolveOverlapRightAddress3D(
     const ImageInfo& new_info, GPUVAddr gpu_addr, const ImageBase& overlap, bool strict_size) {
-    const std::vector<u32> slice_offsets = CalculateSliceOffsets(new_info);
+    const auto slice_offsets = CalculateSliceOffsets(new_info);
     const u32 diff = static_cast<u32>(overlap.gpu_addr - gpu_addr);
     const auto it = std::ranges::find(slice_offsets, diff);
     if (it == slice_offsets.end()) {
         return std::nullopt;
     }
-    const std::vector subresources = CalculateSliceSubresources(new_info);
+    const auto subresources = CalculateSliceSubresources(new_info);
     const SubresourceBase base = subresources[std::distance(slice_offsets.begin(), it)];
     const ImageInfo& info = overlap.info;
     if (!IsBlockLinearSizeCompatible(new_info, info, base.level, 0, strict_size)) {
@@ -612,7 +610,8 @@ u32 CalculateConvertedSizeBytes(const ImageInfo& info) noexcept {
         }
         return output_size;
     }
-    return NumBlocksPerLayer(info, TILE_SIZE) * info.resources.layers * CONVERTED_BYTES_PER_BLOCK;
+    return NumBlocksPerLayer(info, TILE_SIZE) * info.resources.layers *
+           ConvertedBytesPerBlock(info.format);
 }
 
 u32 CalculateLayerStride(const ImageInfo& info) noexcept {
@@ -655,9 +654,9 @@ LevelArray CalculateMipLevelSizes(const ImageInfo& info) noexcept {
     return sizes;
 }
 
-std::vector<u32> CalculateSliceOffsets(const ImageInfo& info) {
+boost::container::small_vector<u32, 16> CalculateSliceOffsets(const ImageInfo& info) {
     ASSERT(info.type == ImageType::e3D);
-    std::vector<u32> offsets;
+    boost::container::small_vector<u32, 16> offsets;
     offsets.reserve(NumSlices(info));
 
     const LevelInfo level_info = MakeLevelInfo(info);
@@ -679,9 +678,10 @@ std::vector<u32> CalculateSliceOffsets(const ImageInfo& info) {
     return offsets;
 }
 
-std::vector<SubresourceBase> CalculateSliceSubresources(const ImageInfo& info) {
+boost::container::small_vector<SubresourceBase, 16> CalculateSliceSubresources(
+    const ImageInfo& info) {
     ASSERT(info.type == ImageType::e3D);
-    std::vector<SubresourceBase> subresources;
+    boost::container::small_vector<SubresourceBase, 16> subresources;
     subresources.reserve(NumSlices(info));
     for (s32 level = 0; level < info.resources.levels; ++level) {
         const s32 depth = AdjustMipSize(info.size.depth, level);
@@ -723,8 +723,10 @@ ImageViewType RenderTargetImageViewType(const ImageInfo& info) noexcept {
     }
 }
 
-std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst, const ImageInfo& src,
-                                             SubresourceBase base, u32 up_scale, u32 down_shift) {
+boost::container::small_vector<ImageCopy, 16> MakeShrinkImageCopies(const ImageInfo& dst,
+                                                                    const ImageInfo& src,
+                                                                    SubresourceBase base,
+                                                                    u32 up_scale, u32 down_shift) {
     ASSERT(dst.resources.levels >= src.resources.levels);
 
     const bool is_dst_3d = dst.type == ImageType::e3D;
@@ -733,7 +735,7 @@ std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst, const ImageIn
         ASSERT(src.resources.levels == 1);
     }
     const bool both_2d{src.type == ImageType::e2D && dst.type == ImageType::e2D};
-    std::vector<ImageCopy> copies;
+    boost::container::small_vector<ImageCopy, 16> copies;
     copies.reserve(src.resources.levels);
     for (s32 level = 0; level < src.resources.levels; ++level) {
         ImageCopy& copy = copies.emplace_back();
@@ -770,9 +772,10 @@ std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst, const ImageIn
     return copies;
 }
 
-std::vector<ImageCopy> MakeReinterpretImageCopies(const ImageInfo& src, u32 up_scale,
-                                                  u32 down_shift) {
-    std::vector<ImageCopy> copies;
+boost::container::small_vector<ImageCopy, 16> MakeReinterpretImageCopies(const ImageInfo& src,
+                                                                         u32 up_scale,
+                                                                         u32 down_shift) {
+    boost::container::small_vector<ImageCopy, 16> copies;
     copies.reserve(src.resources.levels);
     const bool is_3d = src.type == ImageType::e3D;
     for (s32 level = 0; level < src.resources.levels; ++level) {
@@ -824,9 +827,11 @@ bool IsValidEntry(const Tegra::MemoryManager& gpu_memory, const TICEntry& config
     return gpu_memory.GpuToCpuAddress(address, guest_size_bytes).has_value();
 }
 
-std::vector<BufferImageCopy> UnswizzleImage(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr,
-                                            const ImageInfo& info, std::span<const u8> input,
-                                            std::span<u8> output) {
+boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(Tegra::MemoryManager& gpu_memory,
+                                                                   GPUVAddr gpu_addr,
+                                                                   const ImageInfo& info,
+                                                                   std::span<const u8> input,
+                                                                   std::span<u8> output) {
     const size_t guest_size_bytes = input.size_bytes();
     const u32 bpp_log2 = BytesPerBlockLog2(info.format);
     const Extent3D size = info.size;
@@ -861,7 +866,7 @@ std::vector<BufferImageCopy> UnswizzleImage(Tegra::MemoryManager& gpu_memory, GP
                                             info.tile_width_spacing);
     size_t guest_offset = 0;
     u32 host_offset = 0;
-    std::vector<BufferImageCopy> copies(num_levels);
+    boost::container::small_vector<BufferImageCopy, 16> copies(num_levels);
 
     for (s32 level = 0; level < num_levels; ++level) {
         const Extent3D level_size = AdjustMipSize(size, level);
@@ -939,7 +944,8 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
                 tile_size.height, output.subspan(output_offset));
 
             output_offset += copy.image_extent.width * copy.image_extent.height *
-                             copy.image_subresource.num_layers * CONVERTED_BYTES_PER_BLOCK;
+                             copy.image_subresource.num_layers *
+                             BytesPerBlock(PixelFormat::A8B8G8R8_UNORM);
         } else if (astc) {
             // BC1 uses 0.5 bytes per texel
             // BC3 uses 1 byte per texel
@@ -950,7 +956,8 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
 
             const u32 plane_dim = copy.image_extent.width * copy.image_extent.height;
             const u32 level_size = plane_dim * copy.image_extent.depth *
-                                   copy.image_subresource.num_layers * CONVERTED_BYTES_PER_BLOCK;
+                                   copy.image_subresource.num_layers *
+                                   BytesPerBlock(PixelFormat::A8B8G8R8_UNORM);
             decode_scratch.resize_destructive(level_size);
 
             Tegra::Texture::ASTC::Decompress(
@@ -970,15 +977,20 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
                 bpp_div;
             output_offset += static_cast<u32>(copy.buffer_size);
         } else {
-            DecompressBC4(input_offset, copy.image_extent, output.subspan(output_offset));
-
+            const Extent3D image_extent{
+                .width = copy.image_extent.width,
+                .height = copy.image_extent.height * copy.image_subresource.num_layers,
+                .depth = copy.image_extent.depth,
+            };
+            DecompressBCn(input_offset, output.subspan(output_offset), image_extent, info.format);
             output_offset += copy.image_extent.width * copy.image_extent.height *
-                             copy.image_subresource.num_layers * CONVERTED_BYTES_PER_BLOCK;
+                             copy.image_subresource.num_layers *
+                             ConvertedBytesPerBlock(info.format);
         }
     }
 }
 
-std::vector<BufferImageCopy> FullDownloadCopies(const ImageInfo& info) {
+boost::container::small_vector<BufferImageCopy, 16> FullDownloadCopies(const ImageInfo& info) {
     const Extent3D size = info.size;
     const u32 bytes_per_block = BytesPerBlock(info.format);
     if (info.type == ImageType::Linear) {
@@ -1006,7 +1018,7 @@ std::vector<BufferImageCopy> FullDownloadCopies(const ImageInfo& info) {
 
     u32 host_offset = 0;
 
-    std::vector<BufferImageCopy> copies(num_levels);
+    boost::container::small_vector<BufferImageCopy, 16> copies(num_levels);
     for (s32 level = 0; level < num_levels; ++level) {
         const Extent3D level_size = AdjustMipSize(size, level);
         const u32 num_blocks_per_layer = NumBlocks(level_size, tile_size);
@@ -1042,10 +1054,10 @@ Extent3D MipBlockSize(const ImageInfo& info, u32 level) {
     return AdjustMipBlockSize(num_tiles, level_info.block, level);
 }
 
-std::vector<SwizzleParameters> FullUploadSwizzles(const ImageInfo& info) {
+boost::container::small_vector<SwizzleParameters, 16> FullUploadSwizzles(const ImageInfo& info) {
     const Extent2D tile_size = DefaultBlockSize(info.format);
     if (info.type == ImageType::Linear) {
-        return std::vector{SwizzleParameters{
+        return {SwizzleParameters{
             .num_tiles = AdjustTileSize(info.size, tile_size),
             .block = {},
             .buffer_offset = 0,
@@ -1057,7 +1069,7 @@ std::vector<SwizzleParameters> FullUploadSwizzles(const ImageInfo& info) {
     const s32 num_levels = info.resources.levels;
 
     u32 guest_offset = 0;
-    std::vector<SwizzleParameters> params(num_levels);
+    boost::container::small_vector<SwizzleParameters, 16> params(num_levels);
     for (s32 level = 0; level < num_levels; ++level) {
         const Extent3D level_size = AdjustMipSize(size, level);
         const Extent3D num_tiles = AdjustTileSize(level_size, tile_size);
diff --git a/src/video_core/texture_cache/util.h b/src/video_core/texture_cache/util.h
index 84aa6880d..ab45a43c4 100644
--- a/src/video_core/texture_cache/util.h
+++ b/src/video_core/texture_cache/util.h
@@ -5,6 +5,7 @@
 
 #include <optional>
 #include <span>
+#include <boost/container/small_vector.hpp>
 
 #include "common/common_types.h"
 #include "common/scratch_buffer.h"
@@ -40,9 +41,10 @@ struct OverlapResult {
 
 [[nodiscard]] LevelArray CalculateMipLevelSizes(const ImageInfo& info) noexcept;
 
-[[nodiscard]] std::vector<u32> CalculateSliceOffsets(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<u32, 16> CalculateSliceOffsets(const ImageInfo& info);
 
-[[nodiscard]] std::vector<SubresourceBase> CalculateSliceSubresources(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<SubresourceBase, 16> CalculateSliceSubresources(
+    const ImageInfo& info);
 
 [[nodiscard]] u32 CalculateLevelStrideAlignment(const ImageInfo& info, u32 level);
 
@@ -51,21 +53,18 @@ struct OverlapResult {
 
 [[nodiscard]] ImageViewType RenderTargetImageViewType(const ImageInfo& info) noexcept;
 
-[[nodiscard]] std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst,
-                                                           const ImageInfo& src,
-                                                           SubresourceBase base, u32 up_scale = 1,
-                                                           u32 down_shift = 0);
+[[nodiscard]] boost::container::small_vector<ImageCopy, 16> MakeShrinkImageCopies(
+    const ImageInfo& dst, const ImageInfo& src, SubresourceBase base, u32 up_scale = 1,
+    u32 down_shift = 0);
 
-[[nodiscard]] std::vector<ImageCopy> MakeReinterpretImageCopies(const ImageInfo& src,
-                                                                u32 up_scale = 1,
-                                                                u32 down_shift = 0);
+[[nodiscard]] boost::container::small_vector<ImageCopy, 16> MakeReinterpretImageCopies(
+    const ImageInfo& src, u32 up_scale = 1, u32 down_shift = 0);
 
 [[nodiscard]] bool IsValidEntry(const Tegra::MemoryManager& gpu_memory, const TICEntry& config);
 
-[[nodiscard]] std::vector<BufferImageCopy> UnswizzleImage(Tegra::MemoryManager& gpu_memory,
-                                                          GPUVAddr gpu_addr, const ImageInfo& info,
-                                                          std::span<const u8> input,
-                                                          std::span<u8> output);
+[[nodiscard]] boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(
+    Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr, const ImageInfo& info,
+    std::span<const u8> input, std::span<u8> output);
 
 [[nodiscard]] BufferCopy UploadBufferCopy(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr,
                                           const ImageBase& image, std::span<u8> output);
@@ -73,13 +72,15 @@ struct OverlapResult {
 void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8> output,
                   std::span<BufferImageCopy> copies);
 
-[[nodiscard]] std::vector<BufferImageCopy> FullDownloadCopies(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<BufferImageCopy, 16> FullDownloadCopies(
+    const ImageInfo& info);
 
 [[nodiscard]] Extent3D MipSize(Extent3D size, u32 level);
 
 [[nodiscard]] Extent3D MipBlockSize(const ImageInfo& info, u32 level);
 
-[[nodiscard]] std::vector<SwizzleParameters> FullUploadSwizzles(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<SwizzleParameters, 16> FullUploadSwizzles(
+    const ImageInfo& info);
 
 void SwizzleImage(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr, const ImageInfo& info,
                   std::span<const BufferImageCopy> copies, std::span<const u8> memory,
diff --git a/src/video_core/textures/bcn.cpp b/src/video_core/textures/bcn.cpp
index 671212a49..16ddbe320 100644
--- a/src/video_core/textures/bcn.cpp
+++ b/src/video_core/textures/bcn.cpp
@@ -3,7 +3,6 @@
 
 #include <stb_dxt.h>
 #include <string.h>
-
 #include "common/alignment.h"
 #include "video_core/textures/bcn.h"
 #include "video_core/textures/workers.h"
diff --git a/src/video_core/textures/bcn.h b/src/video_core/textures/bcn.h
index 6464af885..d5d2a16c9 100644
--- a/src/video_core/textures/bcn.h
+++ b/src/video_core/textures/bcn.h
@@ -4,14 +4,13 @@
 #pragma once
 
 #include <span>
-#include <stdint.h>
+
+#include "common/common_types.h"
 
 namespace Tegra::Texture::BCN {
 
-void CompressBC1(std::span<const uint8_t> data, uint32_t width, uint32_t height, uint32_t depth,
-                 std::span<uint8_t> output);
+void CompressBC1(std::span<const u8> data, u32 width, u32 height, u32 depth, std::span<u8> output);
 
-void CompressBC3(std::span<const uint8_t> data, uint32_t width, uint32_t height, uint32_t depth,
-                 std::span<uint8_t> output);
+void CompressBC3(std::span<const u8> data, u32 width, u32 height, u32 depth, std::span<u8> output);
 
 } // namespace Tegra::Texture::BCN
diff --git a/src/video_core/transform_feedback.cpp b/src/video_core/transform_feedback.cpp
index 155599316..1f353d2df 100644
--- a/src/video_core/transform_feedback.cpp
+++ b/src/video_core/transform_feedback.cpp
@@ -13,7 +13,7 @@
 
 namespace VideoCommon {
 
-std::vector<Shader::TransformFeedbackVarying> MakeTransformFeedbackVaryings(
+std::pair<std::array<Shader::TransformFeedbackVarying, 256>, u32> MakeTransformFeedbackVaryings(
     const TransformFeedbackState& state) {
     static constexpr std::array VECTORS{
         28U,  // gl_Position
@@ -62,7 +62,8 @@ std::vector<Shader::TransformFeedbackVarying> MakeTransformFeedbackVaryings(
         216U, // gl_TexCoord[6]
         220U, // gl_TexCoord[7]
     };
-    std::vector<Shader::TransformFeedbackVarying> xfb(256);
+    std::array<Shader::TransformFeedbackVarying, 256> xfb{};
+    u32 count{0};
     for (size_t buffer = 0; buffer < state.layouts.size(); ++buffer) {
         const auto& locations = state.varyings[buffer];
         const auto& layout = state.layouts[buffer];
@@ -103,11 +104,12 @@ std::vector<Shader::TransformFeedbackVarying> MakeTransformFeedbackVaryings(
                 }
             }
             xfb[attribute] = varying;
+            count = std::max(count, attribute);
             highest = std::max(highest, (base_offset + varying.components) * 4);
         }
         UNIMPLEMENTED_IF(highest != layout.stride);
     }
-    return xfb;
+    return {xfb, count + 1};
 }
 
 } // namespace VideoCommon
diff --git a/src/video_core/transform_feedback.h b/src/video_core/transform_feedback.h
index d13eb16c3..401b1352a 100644
--- a/src/video_core/transform_feedback.h
+++ b/src/video_core/transform_feedback.h
@@ -24,7 +24,7 @@ struct TransformFeedbackState {
         varyings;
 };
 
-std::vector<Shader::TransformFeedbackVarying> MakeTransformFeedbackVaryings(
+std::pair<std::array<Shader::TransformFeedbackVarying, 256>, u32> MakeTransformFeedbackVaryings(
     const TransformFeedbackState& state);
 
 } // namespace VideoCommon
diff --git a/src/video_core/vulkan_common/vulkan_debug_callback.cpp b/src/video_core/vulkan_common/vulkan_debug_callback.cpp
index 9de484c29..67e8065a4 100644
--- a/src/video_core/vulkan_common/vulkan_debug_callback.cpp
+++ b/src/video_core/vulkan_common/vulkan_debug_callback.cpp
@@ -7,10 +7,10 @@
 
 namespace Vulkan {
 namespace {
-VkBool32 Callback(VkDebugUtilsMessageSeverityFlagBitsEXT severity,
-                  VkDebugUtilsMessageTypeFlagsEXT type,
-                  const VkDebugUtilsMessengerCallbackDataEXT* data,
-                  [[maybe_unused]] void* user_data) {
+VkBool32 DebugUtilCallback(VkDebugUtilsMessageSeverityFlagBitsEXT severity,
+                           VkDebugUtilsMessageTypeFlagsEXT type,
+                           const VkDebugUtilsMessengerCallbackDataEXT* data,
+                           [[maybe_unused]] void* user_data) {
     // Skip logging known false-positive validation errors
     switch (static_cast<u32>(data->messageIdNumber)) {
 #ifdef ANDROID
@@ -62,9 +62,26 @@ VkBool32 Callback(VkDebugUtilsMessageSeverityFlagBitsEXT severity,
     }
     return VK_FALSE;
 }
+
+VkBool32 DebugReportCallback(VkDebugReportFlagsEXT flags, VkDebugReportObjectTypeEXT objectType,
+                             uint64_t object, size_t location, int32_t messageCode,
+                             const char* pLayerPrefix, const char* pMessage, void* pUserData) {
+    const VkDebugReportFlagBitsEXT severity = static_cast<VkDebugReportFlagBitsEXT>(flags);
+    const std::string_view message{pMessage};
+    if (severity & VK_DEBUG_REPORT_ERROR_BIT_EXT) {
+        LOG_CRITICAL(Render_Vulkan, "{}", message);
+    } else if (severity & VK_DEBUG_REPORT_WARNING_BIT_EXT) {
+        LOG_WARNING(Render_Vulkan, "{}", message);
+    } else if (severity & VK_DEBUG_REPORT_INFORMATION_BIT_EXT) {
+        LOG_INFO(Render_Vulkan, "{}", message);
+    } else if (severity & VK_DEBUG_REPORT_DEBUG_BIT_EXT) {
+        LOG_DEBUG(Render_Vulkan, "{}", message);
+    }
+    return VK_FALSE;
+}
 } // Anonymous namespace
 
-vk::DebugUtilsMessenger CreateDebugCallback(const vk::Instance& instance) {
+vk::DebugUtilsMessenger CreateDebugUtilsCallback(const vk::Instance& instance) {
     return instance.CreateDebugUtilsMessenger(VkDebugUtilsMessengerCreateInfoEXT{
         .sType = VK_STRUCTURE_TYPE_DEBUG_UTILS_MESSENGER_CREATE_INFO_EXT,
         .pNext = nullptr,
@@ -76,7 +93,18 @@ vk::DebugUtilsMessenger CreateDebugCallback(const vk::Instance& instance) {
         .messageType = VK_DEBUG_UTILS_MESSAGE_TYPE_GENERAL_BIT_EXT |
                        VK_DEBUG_UTILS_MESSAGE_TYPE_VALIDATION_BIT_EXT |
                        VK_DEBUG_UTILS_MESSAGE_TYPE_PERFORMANCE_BIT_EXT,
-        .pfnUserCallback = Callback,
+        .pfnUserCallback = DebugUtilCallback,
+        .pUserData = nullptr,
+    });
+}
+
+vk::DebugReportCallback CreateDebugReportCallback(const vk::Instance& instance) {
+    return instance.CreateDebugReportCallback({
+        .sType = VK_STRUCTURE_TYPE_DEBUG_REPORT_CALLBACK_CREATE_INFO_EXT,
+        .pNext = nullptr,
+        .flags = VK_DEBUG_REPORT_DEBUG_BIT_EXT | VK_DEBUG_REPORT_INFORMATION_BIT_EXT |
+                 VK_DEBUG_REPORT_ERROR_BIT_EXT | VK_DEBUG_REPORT_WARNING_BIT_EXT,
+        .pfnCallback = DebugReportCallback,
         .pUserData = nullptr,
     });
 }
diff --git a/src/video_core/vulkan_common/vulkan_debug_callback.h b/src/video_core/vulkan_common/vulkan_debug_callback.h
index 71b1f69ec..a8af7b406 100644
--- a/src/video_core/vulkan_common/vulkan_debug_callback.h
+++ b/src/video_core/vulkan_common/vulkan_debug_callback.h
@@ -7,6 +7,8 @@
 
 namespace Vulkan {
 
-vk::DebugUtilsMessenger CreateDebugCallback(const vk::Instance& instance);
+vk::DebugUtilsMessenger CreateDebugUtilsCallback(const vk::Instance& instance);
+
+vk::DebugReportCallback CreateDebugReportCallback(const vk::Instance& instance);
 
 } // namespace Vulkan
diff --git a/src/video_core/vulkan_common/vulkan_device.cpp b/src/video_core/vulkan_common/vulkan_device.cpp
index dcedf4425..421e71e5a 100644
--- a/src/video_core/vulkan_common/vulkan_device.cpp
+++ b/src/video_core/vulkan_common/vulkan_device.cpp
@@ -22,6 +22,8 @@
 #include <adrenotools/bcenabler.h>
 #endif
 
+#include <vk_mem_alloc.h>
+
 namespace Vulkan {
 using namespace Common::Literals;
 namespace {
@@ -316,6 +318,7 @@ NvidiaArchitecture GetNvidiaArchitecture(vk::PhysicalDevice physical,
 std::vector<const char*> ExtensionListForVulkan(
     const std::set<std::string, std::less<>>& extensions) {
     std::vector<const char*> output;
+    output.reserve(extensions.size());
     for (const auto& extension : extensions) {
         output.push_back(extension.c_str());
     }
@@ -346,7 +349,7 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
     const bool is_s8gen2 = device_id == 0x43050a01;
     const bool is_arm = driver_id == VK_DRIVER_ID_ARM_PROPRIETARY;
 
-    if ((is_mvk || is_qualcomm || is_turnip) && !is_suitable) {
+    if ((is_mvk || is_qualcomm || is_turnip || is_arm) && !is_suitable) {
         LOG_WARNING(Render_Vulkan, "Unsuitable driver, continuing anyway");
     } else if (!is_suitable) {
         throw vk::Exception(VK_ERROR_INCOMPATIBLE_DRIVER);
@@ -525,6 +528,14 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
     }
 
     sets_per_pool = 64;
+    if (extensions.extended_dynamic_state3 && is_amd_driver &&
+        properties.properties.driverVersion >= VK_MAKE_API_VERSION(0, 2, 0, 270)) {
+        LOG_WARNING(Render_Vulkan,
+                    "AMD drivers after 23.5.2 have broken extendedDynamicState3ColorBlendEquation");
+        features.extended_dynamic_state3.extendedDynamicState3ColorBlendEnable = false;
+        features.extended_dynamic_state3.extendedDynamicState3ColorBlendEquation = false;
+        dynamic_state3_blending = false;
+    }
     if (is_amd_driver) {
         // AMD drivers need a higher amount of Sets per Pool in certain circumstances like in XC2.
         sets_per_pool = 96;
@@ -562,6 +573,9 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
         LOG_WARNING(Render_Vulkan, "Intel proprietary drivers do not support MSAA image blits");
         cant_blit_msaa = true;
     }
+    has_broken_compute =
+        CheckBrokenCompute(properties.driver.driverID, properties.properties.driverVersion) &&
+        !Settings::values.enable_compute_pipelines.GetValue();
     if (is_intel_anv || (is_qualcomm && !is_s8gen2)) {
         LOG_WARNING(Render_Vulkan, "Driver does not support native BGR format");
         must_emulate_bgr565 = true;
@@ -592,9 +606,31 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
 
     graphics_queue = logical.GetQueue(graphics_family);
     present_queue = logical.GetQueue(present_family);
+
+    VmaVulkanFunctions functions{};
+    functions.vkGetInstanceProcAddr = dld.vkGetInstanceProcAddr;
+    functions.vkGetDeviceProcAddr = dld.vkGetDeviceProcAddr;
+
+    const VmaAllocatorCreateInfo allocator_info = {
+        .flags = VMA_ALLOCATOR_CREATE_EXTERNALLY_SYNCHRONIZED_BIT,
+        .physicalDevice = physical,
+        .device = *logical,
+        .preferredLargeHeapBlockSize = 0,
+        .pAllocationCallbacks = nullptr,
+        .pDeviceMemoryCallbacks = nullptr,
+        .pHeapSizeLimit = nullptr,
+        .pVulkanFunctions = &functions,
+        .instance = instance,
+        .vulkanApiVersion = VK_API_VERSION_1_1,
+        .pTypeExternalMemoryHandleTypes = nullptr,
+    };
+
+    vk::Check(vmaCreateAllocator(&allocator_info, &allocator));
 }
 
-Device::~Device() = default;
+Device::~Device() {
+    vmaDestroyAllocator(allocator);
+}
 
 VkFormat Device::GetSupportedFormat(VkFormat wanted_format, VkFormatFeatureFlags wanted_usage,
                                     FormatType format_type) const {
@@ -877,6 +913,10 @@ bool Device::GetSuitability(bool requires_swapchain) {
     properties.driver.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_DRIVER_PROPERTIES;
     SetNext(next, properties.driver);
 
+    // Retrieve subgroup properties.
+    properties.subgroup_properties.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_SUBGROUP_PROPERTIES;
+    SetNext(next, properties.subgroup_properties);
+
     // Retrieve relevant extension properties.
     if (extensions.shader_float_controls) {
         properties.float_controls.sType =
diff --git a/src/video_core/vulkan_common/vulkan_device.h b/src/video_core/vulkan_common/vulkan_device.h
index 8c7e44fcb..1f17265d5 100644
--- a/src/video_core/vulkan_common/vulkan_device.h
+++ b/src/video_core/vulkan_common/vulkan_device.h
@@ -10,9 +10,12 @@
 #include <vector>
 
 #include "common/common_types.h"
+#include "common/logging/log.h"
 #include "common/settings.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+VK_DEFINE_HANDLE(VmaAllocator)
+
 // Define all features which may be used by the implementation here.
 // Vulkan version in the macro describes the minimum version required for feature availability.
 // If the Vulkan version is lower than the required version, the named extension is required.
@@ -198,6 +201,11 @@ public:
         return dld;
     }
 
+    /// Returns the VMA allocator.
+    VmaAllocator GetAllocator() const {
+        return allocator;
+    }
+
     /// Returns the logical device.
     const vk::Device& GetLogical() const {
         return logical;
@@ -285,6 +293,11 @@ public:
         return features.features.textureCompressionASTC_LDR;
     }
 
+    /// Returns true if BCn is natively supported.
+    bool IsOptimalBcnSupported() const {
+        return features.features.textureCompressionBC;
+    }
+
     /// Returns true if descriptor aliasing is natively supported.
     bool IsDescriptorAliasingSupported() const {
         return GetDriverID() != VK_DRIVER_ID_QUALCOMM_PROPRIETARY;
@@ -315,6 +328,11 @@ public:
         return properties.subgroup_size_control.requiredSubgroupSizeStages & stage;
     }
 
+    /// Returns true if the device supports the provided subgroup feature.
+    bool IsSubgroupFeatureSupported(VkSubgroupFeatureFlagBits feature) const {
+        return properties.subgroup_properties.supportedOperations & feature;
+    }
+
     /// Returns the maximum number of push descriptors.
     u32 MaxPushDescriptors() const {
         return properties.push_descriptor.maxPushDescriptors;
@@ -380,6 +398,11 @@ public:
         return extensions.swapchain_mutable_format;
     }
 
+    /// Returns true if VK_KHR_shader_float_controls is enabled.
+    bool IsKhrShaderFloatControlsSupported() const {
+        return extensions.shader_float_controls;
+    }
+
     /// Returns true if the device supports VK_KHR_workgroup_memory_explicit_layout.
     bool IsKhrWorkgroupMemoryExplicitLayoutSupported() const {
         return extensions.workgroup_memory_explicit_layout;
@@ -405,6 +428,11 @@ public:
         return extensions.sampler_filter_minmax;
     }
 
+    /// Returns true if the device supports VK_EXT_shader_stencil_export.
+    bool IsExtShaderStencilExportSupported() const {
+        return extensions.shader_stencil_export;
+    }
+
     /// Returns true if the device supports VK_EXT_depth_range_unrestricted.
     bool IsExtDepthRangeUnrestrictedSupported() const {
         return extensions.depth_range_unrestricted;
@@ -474,9 +502,9 @@ public:
         return extensions.vertex_input_dynamic_state;
     }
 
-    /// Returns true if the device supports VK_EXT_shader_stencil_export.
-    bool IsExtShaderStencilExportSupported() const {
-        return extensions.shader_stencil_export;
+    /// Returns true if the device supports VK_EXT_shader_demote_to_helper_invocation
+    bool IsExtShaderDemoteToHelperInvocationSupported() const {
+        return extensions.shader_demote_to_helper_invocation;
     }
 
     /// Returns true if the device supports VK_EXT_conservative_rasterization.
@@ -510,12 +538,17 @@ public:
         if (extensions.spirv_1_4) {
             return 0x00010400U;
         }
-        return 0x00010000U;
+        return 0x00010300U;
     }
 
     /// Returns true when a known debugging tool is attached.
     bool HasDebuggingToolAttached() const {
-        return has_renderdoc || has_nsight_graphics || Settings::values.renderer_debug.GetValue();
+        return has_renderdoc || has_nsight_graphics;
+    }
+
+    /// @returns True if compute pipelines can cause crashing.
+    bool HasBrokenCompute() const {
+        return has_broken_compute;
     }
 
     /// Returns true when the device does not properly support cube compatibility.
@@ -575,10 +608,30 @@ public:
         return properties.properties.limits.maxVertexInputBindings;
     }
 
+    u32 GetMaxViewports() const {
+        return properties.properties.limits.maxViewports;
+    }
+
     bool SupportsConditionalBarriers() const {
         return supports_conditional_barriers;
     }
 
+    [[nodiscard]] static constexpr bool CheckBrokenCompute(VkDriverId driver_id,
+                                                           u32 driver_version) {
+        if (driver_id == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS) {
+            const u32 major = VK_API_VERSION_MAJOR(driver_version);
+            const u32 minor = VK_API_VERSION_MINOR(driver_version);
+            const u32 patch = VK_API_VERSION_PATCH(driver_version);
+            if (major == 0 && minor == 405 && patch < 286) {
+                LOG_WARNING(
+                    Render_Vulkan,
+                    "Intel proprietary drivers 0.405.0 until 0.405.286 have broken compute");
+                return true;
+            }
+        }
+        return false;
+    }
+
 private:
     /// Checks if the physical device is suitable and configures the object state
     /// with all necessary info about its properties.
@@ -608,6 +661,7 @@ private:
 
 private:
     VkInstance instance;         ///< Vulkan instance.
+    VmaAllocator allocator;      ///< VMA allocator.
     vk::DeviceDispatch dld;      ///< Device function pointers.
     vk::PhysicalDevice physical; ///< Physical device.
     vk::Device logical;          ///< Logical device.
@@ -650,6 +704,7 @@ private:
 
     struct Properties {
         VkPhysicalDeviceDriverProperties driver{};
+        VkPhysicalDeviceSubgroupProperties subgroup_properties{};
         VkPhysicalDeviceFloatControlsProperties float_controls{};
         VkPhysicalDevicePushDescriptorPropertiesKHR push_descriptor{};
         VkPhysicalDeviceSubgroupSizeControlProperties subgroup_size_control{};
@@ -672,6 +727,7 @@ private:
     bool is_integrated{};                   ///< Is GPU an iGPU.
     bool is_virtual{};                      ///< Is GPU a virtual GPU.
     bool is_non_gpu{};                      ///< Is SoftwareRasterizer, FPGA, non-GPU device.
+    bool has_broken_compute{};              ///< Compute shaders can cause crashes
     bool has_broken_cube_compatibility{};   ///< Has broken cube compatibility bit
     bool has_renderdoc{};                   ///< Has RenderDoc attached
     bool has_nsight_graphics{};             ///< Has Nsight Graphics attached
diff --git a/src/video_core/vulkan_common/vulkan_instance.cpp b/src/video_core/vulkan_common/vulkan_instance.cpp
index b6d83e446..7624a9b32 100644
--- a/src/video_core/vulkan_common/vulkan_instance.cpp
+++ b/src/video_core/vulkan_common/vulkan_instance.cpp
@@ -31,10 +31,34 @@
 
 namespace Vulkan {
 namespace {
+
+[[nodiscard]] bool AreExtensionsSupported(const vk::InstanceDispatch& dld,
+                                          std::span<const char* const> extensions) {
+    const std::optional properties = vk::EnumerateInstanceExtensionProperties(dld);
+    if (!properties) {
+        LOG_ERROR(Render_Vulkan, "Failed to query extension properties");
+        return false;
+    }
+    for (const char* extension : extensions) {
+        const auto it = std::ranges::find_if(*properties, [extension](const auto& prop) {
+            return std::strcmp(extension, prop.extensionName) == 0;
+        });
+        if (it == properties->end()) {
+            LOG_ERROR(Render_Vulkan, "Required instance extension {} is not available", extension);
+            return false;
+        }
+    }
+    return true;
+}
+
 [[nodiscard]] std::vector<const char*> RequiredExtensions(
-    Core::Frontend::WindowSystemType window_type, bool enable_validation) {
+    const vk::InstanceDispatch& dld, Core::Frontend::WindowSystemType window_type,
+    bool enable_validation) {
     std::vector<const char*> extensions;
     extensions.reserve(6);
+#ifdef __APPLE__
+    extensions.push_back(VK_KHR_PORTABILITY_ENUMERATION_EXTENSION_NAME);
+#endif
     switch (window_type) {
     case Core::Frontend::WindowSystemType::Headless:
         break;
@@ -66,35 +90,14 @@ namespace {
         extensions.push_back(VK_KHR_SURFACE_EXTENSION_NAME);
     }
     if (enable_validation) {
-        extensions.push_back(VK_EXT_DEBUG_UTILS_EXTENSION_NAME);
+        const bool debug_utils =
+            AreExtensionsSupported(dld, std::array{VK_EXT_DEBUG_UTILS_EXTENSION_NAME});
+        extensions.push_back(debug_utils ? VK_EXT_DEBUG_UTILS_EXTENSION_NAME
+                                         : VK_EXT_DEBUG_REPORT_EXTENSION_NAME);
     }
-    extensions.push_back(VK_KHR_GET_PHYSICAL_DEVICE_PROPERTIES_2_EXTENSION_NAME);
-
-#ifdef __APPLE__
-    extensions.push_back(VK_KHR_PORTABILITY_ENUMERATION_EXTENSION_NAME);
-#endif
     return extensions;
 }
 
-[[nodiscard]] bool AreExtensionsSupported(const vk::InstanceDispatch& dld,
-                                          std::span<const char* const> extensions) {
-    const std::optional properties = vk::EnumerateInstanceExtensionProperties(dld);
-    if (!properties) {
-        LOG_ERROR(Render_Vulkan, "Failed to query extension properties");
-        return false;
-    }
-    for (const char* extension : extensions) {
-        const auto it = std::ranges::find_if(*properties, [extension](const auto& prop) {
-            return std::strcmp(extension, prop.extensionName) == 0;
-        });
-        if (it == properties->end()) {
-            LOG_ERROR(Render_Vulkan, "Required instance extension {} is not available", extension);
-            return false;
-        }
-    }
-    return true;
-}
-
 [[nodiscard]] std::vector<const char*> Layers(bool enable_validation) {
     std::vector<const char*> layers;
     if (enable_validation) {
@@ -138,7 +141,8 @@ vk::Instance CreateInstance(const Common::DynamicLibrary& library, vk::InstanceD
         LOG_ERROR(Render_Vulkan, "Failed to load Vulkan function pointers");
         throw vk::Exception(VK_ERROR_INITIALIZATION_FAILED);
     }
-    const std::vector<const char*> extensions = RequiredExtensions(window_type, enable_validation);
+    const std::vector<const char*> extensions =
+        RequiredExtensions(dld, window_type, enable_validation);
     if (!AreExtensionsSupported(dld, extensions)) {
         throw vk::Exception(VK_ERROR_EXTENSION_NOT_PRESENT);
     }
diff --git a/src/video_core/vulkan_common/vulkan_memory_allocator.cpp b/src/video_core/vulkan_common/vulkan_memory_allocator.cpp
index e28a556f8..a2ef0efa4 100644
--- a/src/video_core/vulkan_common/vulkan_memory_allocator.cpp
+++ b/src/video_core/vulkan_common/vulkan_memory_allocator.cpp
@@ -6,8 +6,6 @@
 #include <optional>
 #include <vector>
 
-#include <glad/glad.h>
-
 #include "common/alignment.h"
 #include "common/assert.h"
 #include "common/common_types.h"
@@ -17,6 +15,8 @@
 #include "video_core/vulkan_common/vulkan_memory_allocator.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+#include <vk_mem_alloc.h>
+
 namespace Vulkan {
 namespace {
 struct Range {
@@ -49,22 +49,45 @@ struct Range {
     case MemoryUsage::Download:
         return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
                VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
+    case MemoryUsage::Stream:
+        return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT | VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
+               VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
     }
     ASSERT_MSG(false, "Invalid memory usage={}", usage);
     return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
 }
 
-constexpr VkExportMemoryAllocateInfo EXPORT_ALLOCATE_INFO{
-    .sType = VK_STRUCTURE_TYPE_EXPORT_MEMORY_ALLOCATE_INFO,
-    .pNext = nullptr,
-#ifdef _WIN32
-    .handleTypes = VK_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_BIT,
-#elif __unix__
-    .handleTypes = VK_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD_BIT,
-#else
-    .handleTypes = 0,
-#endif
-};
+[[nodiscard]] VkMemoryPropertyFlags MemoryUsagePreferedVmaFlags(MemoryUsage usage) {
+    return usage != MemoryUsage::DeviceLocal ? VK_MEMORY_PROPERTY_HOST_COHERENT_BIT
+                                             : VkMemoryPropertyFlagBits{};
+}
+
+[[nodiscard]] VmaAllocationCreateFlags MemoryUsageVmaFlags(MemoryUsage usage) {
+    switch (usage) {
+    case MemoryUsage::Upload:
+    case MemoryUsage::Stream:
+        return VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
+    case MemoryUsage::Download:
+        return VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
+    case MemoryUsage::DeviceLocal:
+        return VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT |
+               VMA_ALLOCATION_CREATE_HOST_ACCESS_ALLOW_TRANSFER_INSTEAD_BIT;
+    }
+    return {};
+}
+
+[[nodiscard]] VmaMemoryUsage MemoryUsageVma(MemoryUsage usage) {
+    switch (usage) {
+    case MemoryUsage::DeviceLocal:
+    case MemoryUsage::Stream:
+        return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+    case MemoryUsage::Upload:
+    case MemoryUsage::Download:
+        return VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
+    }
+    return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+}
+
 } // Anonymous namespace
 
 class MemoryAllocation {
@@ -74,14 +97,6 @@ public:
         : allocator{allocator_}, memory{std::move(memory_)}, allocation_size{allocation_size_},
           property_flags{properties}, shifted_memory_type{1U << type} {}
 
-#if defined(_WIN32) || defined(__unix__)
-    ~MemoryAllocation() {
-        if (owning_opengl_handle != 0) {
-            glDeleteMemoryObjectsEXT(1, &owning_opengl_handle);
-        }
-    }
-#endif
-
     MemoryAllocation& operator=(const MemoryAllocation&) = delete;
     MemoryAllocation(const MemoryAllocation&) = delete;
 
@@ -120,31 +135,6 @@ public:
         return memory_mapped_span;
     }
 
-#ifdef _WIN32
-    [[nodiscard]] u32 ExportOpenGLHandle() {
-        if (!owning_opengl_handle) {
-            glCreateMemoryObjectsEXT(1, &owning_opengl_handle);
-            glImportMemoryWin32HandleEXT(owning_opengl_handle, allocation_size,
-                                         GL_HANDLE_TYPE_OPAQUE_WIN32_EXT,
-                                         memory.GetMemoryWin32HandleKHR());
-        }
-        return owning_opengl_handle;
-    }
-#elif __unix__
-    [[nodiscard]] u32 ExportOpenGLHandle() {
-        if (!owning_opengl_handle) {
-            glCreateMemoryObjectsEXT(1, &owning_opengl_handle);
-            glImportMemoryFdEXT(owning_opengl_handle, allocation_size, GL_HANDLE_TYPE_OPAQUE_FD_EXT,
-                                memory.GetMemoryFdKHR());
-        }
-        return owning_opengl_handle;
-    }
-#else
-    [[nodiscard]] u32 ExportOpenGLHandle() {
-        return 0;
-    }
-#endif
-
     /// Returns whether this allocation is compatible with the arguments.
     [[nodiscard]] bool IsCompatible(VkMemoryPropertyFlags flags, u32 type_mask) const {
         return (flags & property_flags) == flags && (type_mask & shifted_memory_type) != 0;
@@ -182,9 +172,6 @@ private:
     const u32 shifted_memory_type;              ///< Shifted Vulkan memory type.
     std::vector<Range> commits;                 ///< All commit ranges done from this allocation.
     std::span<u8> memory_mapped_span; ///< Memory mapped span. Empty if not queried before.
-#if defined(_WIN32) || defined(__unix__)
-    u32 owning_opengl_handle{}; ///< Owning OpenGL memory object handle.
-#endif
 };
 
 MemoryCommit::MemoryCommit(MemoryAllocation* allocation_, VkDeviceMemory memory_, u64 begin_,
@@ -216,24 +203,70 @@ std::span<u8> MemoryCommit::Map() {
     return span;
 }
 
-u32 MemoryCommit::ExportOpenGLHandle() const {
-    return allocation->ExportOpenGLHandle();
-}
-
 void MemoryCommit::Release() {
     if (allocation) {
         allocation->Free(begin);
     }
 }
 
-MemoryAllocator::MemoryAllocator(const Device& device_, bool export_allocations_)
-    : device{device_}, properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
-      export_allocations{export_allocations_},
+MemoryAllocator::MemoryAllocator(const Device& device_)
+    : device{device_}, allocator{device.GetAllocator()},
+      properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
       buffer_image_granularity{
           device_.GetPhysical().GetProperties().limits.bufferImageGranularity} {}
 
 MemoryAllocator::~MemoryAllocator() = default;
 
+vk::Image MemoryAllocator::CreateImage(const VkImageCreateInfo& ci) const {
+    const VmaAllocationCreateInfo alloc_ci = {
+        .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT,
+        .usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE,
+        .requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
+        .preferredFlags = 0,
+        .memoryTypeBits = 0,
+        .pool = VK_NULL_HANDLE,
+        .pUserData = nullptr,
+        .priority = 0.f,
+    };
+
+    VkImage handle{};
+    VmaAllocation allocation{};
+
+    vk::Check(vmaCreateImage(allocator, &ci, &alloc_ci, &handle, &allocation, nullptr));
+
+    return vk::Image(handle, *device.GetLogical(), allocator, allocation,
+                     device.GetDispatchLoader());
+}
+
+vk::Buffer MemoryAllocator::CreateBuffer(const VkBufferCreateInfo& ci, MemoryUsage usage) const {
+    const VmaAllocationCreateInfo alloc_ci = {
+        .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT |
+                 MemoryUsageVmaFlags(usage),
+        .usage = MemoryUsageVma(usage),
+        .requiredFlags = 0,
+        .preferredFlags = MemoryUsagePreferedVmaFlags(usage),
+        .memoryTypeBits = 0,
+        .pool = VK_NULL_HANDLE,
+        .pUserData = nullptr,
+        .priority = 0.f,
+    };
+
+    VkBuffer handle{};
+    VmaAllocationInfo alloc_info{};
+    VmaAllocation allocation{};
+    VkMemoryPropertyFlags property_flags{};
+
+    vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
+    vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags);
+
+    u8* data = reinterpret_cast<u8*>(alloc_info.pMappedData);
+    const std::span<u8> mapped_data = data ? std::span<u8>{data, ci.size} : std::span<u8>{};
+    const bool is_coherent = property_flags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+
+    return vk::Buffer(handle, *device.GetLogical(), allocator, allocation, mapped_data, is_coherent,
+                      device.GetDispatchLoader());
+}
+
 MemoryCommit MemoryAllocator::Commit(const VkMemoryRequirements& requirements, MemoryUsage usage) {
     // Find the fastest memory flags we can afford with the current requirements
     const u32 type_mask = requirements.memoryTypeBits;
@@ -253,25 +286,11 @@ MemoryCommit MemoryAllocator::Commit(const VkMemoryRequirements& requirements, M
     return TryCommit(requirements, flags).value();
 }
 
-MemoryCommit MemoryAllocator::Commit(const vk::Buffer& buffer, MemoryUsage usage) {
-    auto commit = Commit(device.GetLogical().GetBufferMemoryRequirements(*buffer), usage);
-    buffer.BindMemory(commit.Memory(), commit.Offset());
-    return commit;
-}
-
-MemoryCommit MemoryAllocator::Commit(const vk::Image& image, MemoryUsage usage) {
-    VkMemoryRequirements requirements = device.GetLogical().GetImageMemoryRequirements(*image);
-    requirements.size = Common::AlignUp(requirements.size, buffer_image_granularity);
-    auto commit = Commit(requirements, usage);
-    image.BindMemory(commit.Memory(), commit.Offset());
-    return commit;
-}
-
 bool MemoryAllocator::TryAllocMemory(VkMemoryPropertyFlags flags, u32 type_mask, u64 size) {
     const u32 type = FindType(flags, type_mask).value();
     vk::DeviceMemory memory = device.GetLogical().TryAllocateMemory({
         .sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO,
-        .pNext = export_allocations ? &EXPORT_ALLOCATE_INFO : nullptr,
+        .pNext = nullptr,
         .allocationSize = size,
         .memoryTypeIndex = type,
     });
@@ -342,16 +361,4 @@ std::optional<u32> MemoryAllocator::FindType(VkMemoryPropertyFlags flags, u32 ty
     return std::nullopt;
 }
 
-bool IsHostVisible(MemoryUsage usage) noexcept {
-    switch (usage) {
-    case MemoryUsage::DeviceLocal:
-        return false;
-    case MemoryUsage::Upload:
-    case MemoryUsage::Download:
-        return true;
-    }
-    ASSERT_MSG(false, "Invalid memory usage={}", usage);
-    return false;
-}
-
 } // namespace Vulkan
diff --git a/src/video_core/vulkan_common/vulkan_memory_allocator.h b/src/video_core/vulkan_common/vulkan_memory_allocator.h
index a5bff03fe..f449bc8d0 100644
--- a/src/video_core/vulkan_common/vulkan_memory_allocator.h
+++ b/src/video_core/vulkan_common/vulkan_memory_allocator.h
@@ -9,6 +9,8 @@
 #include "common/common_types.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+VK_DEFINE_HANDLE(VmaAllocator)
+
 namespace Vulkan {
 
 class Device;
@@ -17,9 +19,11 @@ class MemoryAllocation;
 
 /// Hints and requirements for the backing memory type of a commit
 enum class MemoryUsage {
-    DeviceLocal, ///< Hints device local usages, fastest memory type to read and write from the GPU
+    DeviceLocal, ///< Requests device local host visible buffer, falling back to device local
+                 ///< memory.
     Upload,      ///< Requires a host visible memory type optimized for CPU to GPU uploads
     Download,    ///< Requires a host visible memory type optimized for GPU to CPU readbacks
+    Stream,      ///< Requests device local host visible buffer, falling back host memory.
 };
 
 /// Ownership handle of a memory commitment.
@@ -41,9 +45,6 @@ public:
     /// It will map the backing allocation if it hasn't been mapped before.
     std::span<u8> Map();
 
-    /// Returns an non-owning OpenGL handle, creating one if it doesn't exist.
-    u32 ExportOpenGLHandle() const;
-
     /// Returns the Vulkan memory handler.
     VkDeviceMemory Memory() const {
         return memory;
@@ -74,16 +75,19 @@ public:
      * Construct memory allocator
      *
      * @param device_             Device to allocate from
-     * @param export_allocations_ True when allocations have to be exported
      *
      * @throw vk::Exception on failure
      */
-    explicit MemoryAllocator(const Device& device_, bool export_allocations_);
+    explicit MemoryAllocator(const Device& device_);
     ~MemoryAllocator();
 
     MemoryAllocator& operator=(const MemoryAllocator&) = delete;
     MemoryAllocator(const MemoryAllocator&) = delete;
 
+    vk::Image CreateImage(const VkImageCreateInfo& ci) const;
+
+    vk::Buffer CreateBuffer(const VkBufferCreateInfo& ci, MemoryUsage usage) const;
+
     /**
      * Commits a memory with the specified requirements.
      *
@@ -97,9 +101,6 @@ public:
     /// Commits memory required by the buffer and binds it.
     MemoryCommit Commit(const vk::Buffer& buffer, MemoryUsage usage);
 
-    /// Commits memory required by the image and binds it.
-    MemoryCommit Commit(const vk::Image& image, MemoryUsage usage);
-
 private:
     /// Tries to allocate a chunk of memory.
     bool TryAllocMemory(VkMemoryPropertyFlags flags, u32 type_mask, u64 size);
@@ -117,15 +118,12 @@ private:
     /// Returns index to the fastest memory type compatible with the passed requirements.
     std::optional<u32> FindType(VkMemoryPropertyFlags flags, u32 type_mask) const;
 
-    const Device& device;                              ///< Device handle.
-    const VkPhysicalDeviceMemoryProperties properties; ///< Physical device properties.
-    const bool export_allocations; ///< True when memory allocations have to be exported.
+    const Device& device;                                       ///< Device handle.
+    VmaAllocator allocator;                                     ///< Vma allocator.
+    const VkPhysicalDeviceMemoryProperties properties;          ///< Physical device properties.
     std::vector<std::unique_ptr<MemoryAllocation>> allocations; ///< Current allocations.
     VkDeviceSize buffer_image_granularity; // The granularity for adjacent offsets between buffers
                                            // and optimal images
 };
 
-/// Returns true when a memory usage is guaranteed to be host visible.
-bool IsHostVisible(MemoryUsage usage) noexcept;
-
 } // namespace Vulkan
diff --git a/src/video_core/vulkan_common/vulkan_wrapper.cpp b/src/video_core/vulkan_common/vulkan_wrapper.cpp
index 336f53700..2fa29793a 100644
--- a/src/video_core/vulkan_common/vulkan_wrapper.cpp
+++ b/src/video_core/vulkan_common/vulkan_wrapper.cpp
@@ -12,6 +12,8 @@
 
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+#include <vk_mem_alloc.h>
+
 namespace Vulkan::vk {
 
 namespace {
@@ -257,7 +259,9 @@ bool Load(VkInstance instance, InstanceDispatch& dld) noexcept {
     // These functions may fail to load depending on the enabled extensions.
     // Don't return a failure on these.
     X(vkCreateDebugUtilsMessengerEXT);
+    X(vkCreateDebugReportCallbackEXT);
     X(vkDestroyDebugUtilsMessengerEXT);
+    X(vkDestroyDebugReportCallbackEXT);
     X(vkDestroySurfaceKHR);
     X(vkGetPhysicalDeviceFeatures2);
     X(vkGetPhysicalDeviceProperties2);
@@ -479,6 +483,11 @@ void Destroy(VkInstance instance, VkDebugUtilsMessengerEXT handle,
     dld.vkDestroyDebugUtilsMessengerEXT(instance, handle, nullptr);
 }
 
+void Destroy(VkInstance instance, VkDebugReportCallbackEXT handle,
+             const InstanceDispatch& dld) noexcept {
+    dld.vkDestroyDebugReportCallbackEXT(instance, handle, nullptr);
+}
+
 void Destroy(VkInstance instance, VkSurfaceKHR handle, const InstanceDispatch& dld) noexcept {
     dld.vkDestroySurfaceKHR(instance, handle, nullptr);
 }
@@ -547,24 +556,47 @@ DebugUtilsMessenger Instance::CreateDebugUtilsMessenger(
     return DebugUtilsMessenger(object, handle, *dld);
 }
 
-void Buffer::BindMemory(VkDeviceMemory memory, VkDeviceSize offset) const {
-    Check(dld->vkBindBufferMemory(owner, handle, memory, offset));
+DebugReportCallback Instance::CreateDebugReportCallback(
+    const VkDebugReportCallbackCreateInfoEXT& create_info) const {
+    VkDebugReportCallbackEXT object;
+    Check(dld->vkCreateDebugReportCallbackEXT(handle, &create_info, nullptr, &object));
+    return DebugReportCallback(object, handle, *dld);
 }
 
-void Buffer::SetObjectNameEXT(const char* name) const {
-    SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_BUFFER, name);
+void Image::SetObjectNameEXT(const char* name) const {
+    SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_IMAGE, name);
 }
 
-void BufferView::SetObjectNameEXT(const char* name) const {
-    SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_BUFFER_VIEW, name);
+void Image::Release() const noexcept {
+    if (handle) {
+        vmaDestroyImage(allocator, handle, allocation);
+    }
 }
 
-void Image::BindMemory(VkDeviceMemory memory, VkDeviceSize offset) const {
-    Check(dld->vkBindImageMemory(owner, handle, memory, offset));
+void Buffer::Flush() const {
+    if (!is_coherent) {
+        vmaFlushAllocation(allocator, allocation, 0, VK_WHOLE_SIZE);
+    }
 }
 
-void Image::SetObjectNameEXT(const char* name) const {
-    SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_IMAGE, name);
+void Buffer::Invalidate() const {
+    if (!is_coherent) {
+        vmaInvalidateAllocation(allocator, allocation, 0, VK_WHOLE_SIZE);
+    }
+}
+
+void Buffer::SetObjectNameEXT(const char* name) const {
+    SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_BUFFER, name);
+}
+
+void Buffer::Release() const noexcept {
+    if (handle) {
+        vmaDestroyBuffer(allocator, handle, allocation);
+    }
+}
+
+void BufferView::SetObjectNameEXT(const char* name) const {
+    SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_BUFFER_VIEW, name);
 }
 
 void ImageView::SetObjectNameEXT(const char* name) const {
@@ -701,24 +733,12 @@ Queue Device::GetQueue(u32 family_index) const noexcept {
     return Queue(queue, *dld);
 }
 
-Buffer Device::CreateBuffer(const VkBufferCreateInfo& ci) const {
-    VkBuffer object;
-    Check(dld->vkCreateBuffer(handle, &ci, nullptr, &object));
-    return Buffer(object, handle, *dld);
-}
-
 BufferView Device::CreateBufferView(const VkBufferViewCreateInfo& ci) const {
     VkBufferView object;
     Check(dld->vkCreateBufferView(handle, &ci, nullptr, &object));
     return BufferView(object, handle, *dld);
 }
 
-Image Device::CreateImage(const VkImageCreateInfo& ci) const {
-    VkImage object;
-    Check(dld->vkCreateImage(handle, &ci, nullptr, &object));
-    return Image(object, handle, *dld);
-}
-
 ImageView Device::CreateImageView(const VkImageViewCreateInfo& ci) const {
     VkImageView object;
     Check(dld->vkCreateImageView(handle, &ci, nullptr, &object));
diff --git a/src/video_core/vulkan_common/vulkan_wrapper.h b/src/video_core/vulkan_common/vulkan_wrapper.h
index 4ff328a21..b5e70fcd4 100644
--- a/src/video_core/vulkan_common/vulkan_wrapper.h
+++ b/src/video_core/vulkan_common/vulkan_wrapper.h
@@ -32,6 +32,9 @@
 #pragma warning(disable : 26812) // Disable prefer enum class over enum
 #endif
 
+VK_DEFINE_HANDLE(VmaAllocator)
+VK_DEFINE_HANDLE(VmaAllocation)
+
 namespace Vulkan::vk {
 
 /**
@@ -161,8 +164,10 @@ struct InstanceDispatch {
     PFN_vkEnumerateInstanceLayerProperties vkEnumerateInstanceLayerProperties{};
 
     PFN_vkCreateDebugUtilsMessengerEXT vkCreateDebugUtilsMessengerEXT{};
+    PFN_vkCreateDebugReportCallbackEXT vkCreateDebugReportCallbackEXT{};
     PFN_vkCreateDevice vkCreateDevice{};
     PFN_vkDestroyDebugUtilsMessengerEXT vkDestroyDebugUtilsMessengerEXT{};
+    PFN_vkDestroyDebugReportCallbackEXT vkDestroyDebugReportCallbackEXT{};
     PFN_vkDestroyDevice vkDestroyDevice{};
     PFN_vkDestroySurfaceKHR vkDestroySurfaceKHR{};
     PFN_vkEnumerateDeviceExtensionProperties vkEnumerateDeviceExtensionProperties{};
@@ -363,6 +368,7 @@ void Destroy(VkDevice, VkSwapchainKHR, const DeviceDispatch&) noexcept;
 void Destroy(VkDevice, VkSemaphore, const DeviceDispatch&) noexcept;
 void Destroy(VkDevice, VkShaderModule, const DeviceDispatch&) noexcept;
 void Destroy(VkInstance, VkDebugUtilsMessengerEXT, const InstanceDispatch&) noexcept;
+void Destroy(VkInstance, VkDebugReportCallbackEXT, const InstanceDispatch&) noexcept;
 void Destroy(VkInstance, VkSurfaceKHR, const InstanceDispatch&) noexcept;
 
 VkResult Free(VkDevice, VkDescriptorPool, Span<VkDescriptorSet>, const DeviceDispatch&) noexcept;
@@ -578,6 +584,7 @@ private:
 };
 
 using DebugUtilsMessenger = Handle<VkDebugUtilsMessengerEXT, VkInstance, InstanceDispatch>;
+using DebugReportCallback = Handle<VkDebugReportCallbackEXT, VkInstance, InstanceDispatch>;
 using DescriptorSetLayout = Handle<VkDescriptorSetLayout, VkDevice, DeviceDispatch>;
 using DescriptorUpdateTemplate = Handle<VkDescriptorUpdateTemplate, VkDevice, DeviceDispatch>;
 using Pipeline = Handle<VkPipeline, VkDevice, DeviceDispatch>;
@@ -610,12 +617,149 @@ public:
     DebugUtilsMessenger CreateDebugUtilsMessenger(
         const VkDebugUtilsMessengerCreateInfoEXT& create_info) const;
 
+    /// Creates a debug report callback.
+    /// @throw Exception on creation failure.
+    DebugReportCallback CreateDebugReportCallback(
+        const VkDebugReportCallbackCreateInfoEXT& create_info) const;
+
     /// Returns dispatch table.
     const InstanceDispatch& Dispatch() const noexcept {
         return *dld;
     }
 };
 
+class Image {
+public:
+    explicit Image(VkImage handle_, VkDevice owner_, VmaAllocator allocator_,
+                   VmaAllocation allocation_, const DeviceDispatch& dld_) noexcept
+        : handle{handle_}, owner{owner_}, allocator{allocator_},
+          allocation{allocation_}, dld{&dld_} {}
+    Image() = default;
+
+    Image(const Image&) = delete;
+    Image& operator=(const Image&) = delete;
+
+    Image(Image&& rhs) noexcept
+        : handle{std::exchange(rhs.handle, nullptr)}, owner{rhs.owner}, allocator{rhs.allocator},
+          allocation{rhs.allocation}, dld{rhs.dld} {}
+
+    Image& operator=(Image&& rhs) noexcept {
+        Release();
+        handle = std::exchange(rhs.handle, nullptr);
+        owner = rhs.owner;
+        allocator = rhs.allocator;
+        allocation = rhs.allocation;
+        dld = rhs.dld;
+        return *this;
+    }
+
+    ~Image() noexcept {
+        Release();
+    }
+
+    VkImage operator*() const noexcept {
+        return handle;
+    }
+
+    void reset() noexcept {
+        Release();
+        handle = nullptr;
+    }
+
+    explicit operator bool() const noexcept {
+        return handle != nullptr;
+    }
+
+    void SetObjectNameEXT(const char* name) const;
+
+private:
+    void Release() const noexcept;
+
+    VkImage handle = nullptr;
+    VkDevice owner = nullptr;
+    VmaAllocator allocator = nullptr;
+    VmaAllocation allocation = nullptr;
+    const DeviceDispatch* dld = nullptr;
+};
+
+class Buffer {
+public:
+    explicit Buffer(VkBuffer handle_, VkDevice owner_, VmaAllocator allocator_,
+                    VmaAllocation allocation_, std::span<u8> mapped_, bool is_coherent_,
+                    const DeviceDispatch& dld_) noexcept
+        : handle{handle_}, owner{owner_}, allocator{allocator_},
+          allocation{allocation_}, mapped{mapped_}, is_coherent{is_coherent_}, dld{&dld_} {}
+    Buffer() = default;
+
+    Buffer(const Buffer&) = delete;
+    Buffer& operator=(const Buffer&) = delete;
+
+    Buffer(Buffer&& rhs) noexcept
+        : handle{std::exchange(rhs.handle, nullptr)}, owner{rhs.owner}, allocator{rhs.allocator},
+          allocation{rhs.allocation}, mapped{rhs.mapped},
+          is_coherent{rhs.is_coherent}, dld{rhs.dld} {}
+
+    Buffer& operator=(Buffer&& rhs) noexcept {
+        Release();
+        handle = std::exchange(rhs.handle, nullptr);
+        owner = rhs.owner;
+        allocator = rhs.allocator;
+        allocation = rhs.allocation;
+        mapped = rhs.mapped;
+        is_coherent = rhs.is_coherent;
+        dld = rhs.dld;
+        return *this;
+    }
+
+    ~Buffer() noexcept {
+        Release();
+    }
+
+    VkBuffer operator*() const noexcept {
+        return handle;
+    }
+
+    void reset() noexcept {
+        Release();
+        handle = nullptr;
+    }
+
+    explicit operator bool() const noexcept {
+        return handle != nullptr;
+    }
+
+    /// Returns the host mapped memory, an empty span otherwise.
+    std::span<u8> Mapped() noexcept {
+        return mapped;
+    }
+
+    std::span<const u8> Mapped() const noexcept {
+        return mapped;
+    }
+
+    /// Returns true if the buffer is mapped to the host.
+    bool IsHostVisible() const noexcept {
+        return !mapped.empty();
+    }
+
+    void Flush() const;
+
+    void Invalidate() const;
+
+    void SetObjectNameEXT(const char* name) const;
+
+private:
+    void Release() const noexcept;
+
+    VkBuffer handle = nullptr;
+    VkDevice owner = nullptr;
+    VmaAllocator allocator = nullptr;
+    VmaAllocation allocation = nullptr;
+    std::span<u8> mapped = {};
+    bool is_coherent = false;
+    const DeviceDispatch* dld = nullptr;
+};
+
 class Queue {
 public:
     /// Construct an empty queue handle.
@@ -639,17 +783,6 @@ private:
     const DeviceDispatch* dld = nullptr;
 };
 
-class Buffer : public Handle<VkBuffer, VkDevice, DeviceDispatch> {
-    using Handle<VkBuffer, VkDevice, DeviceDispatch>::Handle;
-
-public:
-    /// Attaches a memory allocation.
-    void BindMemory(VkDeviceMemory memory, VkDeviceSize offset) const;
-
-    /// Set object name.
-    void SetObjectNameEXT(const char* name) const;
-};
-
 class BufferView : public Handle<VkBufferView, VkDevice, DeviceDispatch> {
     using Handle<VkBufferView, VkDevice, DeviceDispatch>::Handle;
 
@@ -658,17 +791,6 @@ public:
     void SetObjectNameEXT(const char* name) const;
 };
 
-class Image : public Handle<VkImage, VkDevice, DeviceDispatch> {
-    using Handle<VkImage, VkDevice, DeviceDispatch>::Handle;
-
-public:
-    /// Attaches a memory allocation.
-    void BindMemory(VkDeviceMemory memory, VkDeviceSize offset) const;
-
-    /// Set object name.
-    void SetObjectNameEXT(const char* name) const;
-};
-
 class ImageView : public Handle<VkImageView, VkDevice, DeviceDispatch> {
     using Handle<VkImageView, VkDevice, DeviceDispatch>::Handle;
 
@@ -840,12 +962,8 @@ public:
 
     Queue GetQueue(u32 family_index) const noexcept;
 
-    Buffer CreateBuffer(const VkBufferCreateInfo& ci) const;
-
     BufferView CreateBufferView(const VkBufferViewCreateInfo& ci) const;
 
-    Image CreateImage(const VkImageCreateInfo& ci) const;
-
     ImageView CreateImageView(const VkImageViewCreateInfo& ci) const;
 
     Semaphore CreateSemaphore() const;
diff --git a/src/yuzu/CMakeLists.txt b/src/yuzu/CMakeLists.txt
index 733c296e4..fe98e3605 100644
--- a/src/yuzu/CMakeLists.txt
+++ b/src/yuzu/CMakeLists.txt
@@ -98,6 +98,9 @@ add_executable(yuzu
     configuration/configure_input_profile_dialog.cpp
     configuration/configure_input_profile_dialog.h
     configuration/configure_input_profile_dialog.ui
+    configuration/configure_mouse_panning.cpp
+    configuration/configure_mouse_panning.h
+    configuration/configure_mouse_panning.ui
     configuration/configure_motion_touch.cpp
     configuration/configure_motion_touch.h
     configuration/configure_motion_touch.ui
diff --git a/src/yuzu/bootmanager.cpp b/src/yuzu/bootmanager.cpp
index cc6b6a25a..bdd1497b5 100644
--- a/src/yuzu/bootmanager.cpp
+++ b/src/yuzu/bootmanager.cpp
@@ -105,14 +105,12 @@ void EmuThread::run() {
         std::unique_lock lk{m_should_run_mutex};
         if (m_should_run) {
             m_system.Run();
-            m_is_running.store(true);
-            m_is_running.notify_all();
+            m_stopped.Reset();
 
             Common::CondvarWait(m_should_run_cv, lk, stop_token, [&] { return !m_should_run; });
         } else {
             m_system.Pause();
-            m_is_running.store(false);
-            m_is_running.notify_all();
+            m_stopped.Set();
 
             EmulationPaused(lk);
             Common::CondvarWait(m_should_run_cv, lk, stop_token, [&] { return m_should_run; });
diff --git a/src/yuzu/bootmanager.h b/src/yuzu/bootmanager.h
index b7b9d4141..87b23df12 100644
--- a/src/yuzu/bootmanager.h
+++ b/src/yuzu/bootmanager.h
@@ -3,7 +3,6 @@
 
 #pragma once
 
-#include <atomic>
 #include <condition_variable>
 #include <cstddef>
 #include <memory>
@@ -88,7 +87,7 @@ public:
 
         // Wait until paused, if pausing.
         if (!should_run) {
-            m_is_running.wait(true);
+            m_stopped.Wait();
         }
     }
 
@@ -97,7 +96,7 @@ public:
      * @return True if the emulation thread is running, otherwise false
      */
     bool IsRunning() const {
-        return m_is_running.load() || m_should_run;
+        return m_should_run;
     }
 
     /**
@@ -118,7 +117,7 @@ private:
     std::stop_source m_stop_source;
     std::mutex m_should_run_mutex;
     std::condition_variable_any m_should_run_cv;
-    std::atomic<bool> m_is_running{false};
+    Common::Event m_stopped;
     bool m_should_run{true};
 
 signals:
diff --git a/src/yuzu/configuration/config.cpp b/src/yuzu/configuration/config.cpp
index bac9dff90..29467d380 100644
--- a/src/yuzu/configuration/config.cpp
+++ b/src/yuzu/configuration/config.cpp
@@ -351,6 +351,10 @@ void Config::ReadPlayerValue(std::size_t player_index) {
             player_motions = default_param;
         }
     }
+
+    if (player_index == 0) {
+        ReadMousePanningValues();
+    }
 }
 
 void Config::ReadDebugValues() {
@@ -471,6 +475,7 @@ void Config::ReadControlValues() {
     ReadKeyboardValues();
     ReadMouseValues();
     ReadTouchscreenValues();
+    ReadMousePanningValues();
     ReadMotionTouchValues();
     ReadHidbusValues();
     ReadIrCameraValues();
@@ -481,8 +486,6 @@ void Config::ReadControlValues() {
     Settings::values.enable_raw_input = false;
 #endif
     ReadBasicSetting(Settings::values.emulate_analog_keyboard);
-    Settings::values.mouse_panning = false;
-    ReadBasicSetting(Settings::values.mouse_panning_sensitivity);
     ReadBasicSetting(Settings::values.enable_joycon_driver);
     ReadBasicSetting(Settings::values.enable_procon_driver);
     ReadBasicSetting(Settings::values.random_amiibo_id);
@@ -496,6 +499,16 @@ void Config::ReadControlValues() {
     qt_config->endGroup();
 }
 
+void Config::ReadMousePanningValues() {
+    ReadBasicSetting(Settings::values.mouse_panning);
+    ReadBasicSetting(Settings::values.mouse_panning_x_sensitivity);
+    ReadBasicSetting(Settings::values.mouse_panning_y_sensitivity);
+    ReadBasicSetting(Settings::values.mouse_panning_deadzone_x_counterweight);
+    ReadBasicSetting(Settings::values.mouse_panning_deadzone_y_counterweight);
+    ReadBasicSetting(Settings::values.mouse_panning_decay_strength);
+    ReadBasicSetting(Settings::values.mouse_panning_min_decay);
+}
+
 void Config::ReadMotionTouchValues() {
     int num_touch_from_button_maps =
         qt_config->beginReadArray(QStringLiteral("touch_from_button_maps"));
@@ -761,6 +774,7 @@ void Config::ReadRendererValues() {
     ReadGlobalSetting(Settings::values.use_vulkan_driver_pipeline_cache);
     ReadGlobalSetting(Settings::values.enable_compute_pipelines);
     ReadGlobalSetting(Settings::values.use_video_framerate);
+    ReadGlobalSetting(Settings::values.barrier_feedback_loops);
     ReadGlobalSetting(Settings::values.bg_red);
     ReadGlobalSetting(Settings::values.bg_green);
     ReadGlobalSetting(Settings::values.bg_blue);
@@ -890,6 +904,7 @@ void Config::ReadUIValues() {
     ReadBasicSetting(UISettings::values.pause_when_in_background);
     ReadBasicSetting(UISettings::values.mute_when_in_background);
     ReadBasicSetting(UISettings::values.hide_mouse);
+    ReadBasicSetting(UISettings::values.controller_applet_disabled);
     ReadBasicSetting(UISettings::values.disable_web_applet);
 
     qt_config->endGroup();
@@ -1063,6 +1078,10 @@ void Config::SavePlayerValue(std::size_t player_index) {
                      QString::fromStdString(player.motions[i]),
                      QString::fromStdString(default_param));
     }
+
+    if (player_index == 0) {
+        SaveMousePanningValues();
+    }
 }
 
 void Config::SaveDebugValues() {
@@ -1099,6 +1118,16 @@ void Config::SaveTouchscreenValues() {
     WriteSetting(QStringLiteral("touchscreen_diameter_y"), touchscreen.diameter_y, 15);
 }
 
+void Config::SaveMousePanningValues() {
+    // Don't overwrite values.mouse_panning
+    WriteBasicSetting(Settings::values.mouse_panning_x_sensitivity);
+    WriteBasicSetting(Settings::values.mouse_panning_y_sensitivity);
+    WriteBasicSetting(Settings::values.mouse_panning_deadzone_x_counterweight);
+    WriteBasicSetting(Settings::values.mouse_panning_deadzone_y_counterweight);
+    WriteBasicSetting(Settings::values.mouse_panning_decay_strength);
+    WriteBasicSetting(Settings::values.mouse_panning_min_decay);
+}
+
 void Config::SaveMotionTouchValues() {
     WriteBasicSetting(Settings::values.touch_device);
     WriteBasicSetting(Settings::values.touch_from_button_map_index);
@@ -1185,6 +1214,7 @@ void Config::SaveControlValues() {
     SaveDebugValues();
     SaveMouseValues();
     SaveTouchscreenValues();
+    SaveMousePanningValues();
     SaveMotionTouchValues();
     SaveHidbusValues();
     SaveIrCameraValues();
@@ -1199,7 +1229,6 @@ void Config::SaveControlValues() {
     WriteBasicSetting(Settings::values.random_amiibo_id);
     WriteBasicSetting(Settings::values.keyboard_enabled);
     WriteBasicSetting(Settings::values.emulate_analog_keyboard);
-    WriteBasicSetting(Settings::values.mouse_panning_sensitivity);
     WriteBasicSetting(Settings::values.controller_navigation);
 
     WriteBasicSetting(Settings::values.tas_enable);
@@ -1417,6 +1446,7 @@ void Config::SaveRendererValues() {
     WriteGlobalSetting(Settings::values.use_vulkan_driver_pipeline_cache);
     WriteGlobalSetting(Settings::values.enable_compute_pipelines);
     WriteGlobalSetting(Settings::values.use_video_framerate);
+    WriteGlobalSetting(Settings::values.barrier_feedback_loops);
     WriteGlobalSetting(Settings::values.bg_red);
     WriteGlobalSetting(Settings::values.bg_green);
     WriteGlobalSetting(Settings::values.bg_blue);
@@ -1522,6 +1552,7 @@ void Config::SaveUIValues() {
     WriteBasicSetting(UISettings::values.pause_when_in_background);
     WriteBasicSetting(UISettings::values.mute_when_in_background);
     WriteBasicSetting(UISettings::values.hide_mouse);
+    WriteBasicSetting(UISettings::values.controller_applet_disabled);
     WriteBasicSetting(UISettings::values.disable_web_applet);
 
     qt_config->endGroup();
diff --git a/src/yuzu/configuration/config.h b/src/yuzu/configuration/config.h
index 0fd4baf6b..1211389d2 100644
--- a/src/yuzu/configuration/config.h
+++ b/src/yuzu/configuration/config.h
@@ -74,6 +74,7 @@ private:
     void ReadKeyboardValues();
     void ReadMouseValues();
     void ReadTouchscreenValues();
+    void ReadMousePanningValues();
     void ReadMotionTouchValues();
     void ReadHidbusValues();
     void ReadIrCameraValues();
@@ -104,6 +105,7 @@ private:
     void SaveDebugValues();
     void SaveMouseValues();
     void SaveTouchscreenValues();
+    void SaveMousePanningValues();
     void SaveMotionTouchValues();
     void SaveHidbusValues();
     void SaveIrCameraValues();
diff --git a/src/yuzu/configuration/configure_general.cpp b/src/yuzu/configuration/configure_general.cpp
index 26258d744..2f55159f5 100644
--- a/src/yuzu/configuration/configure_general.cpp
+++ b/src/yuzu/configuration/configure_general.cpp
@@ -40,6 +40,9 @@ void ConfigureGeneral::SetConfiguration() {
     ui->toggle_user_on_boot->setChecked(UISettings::values.select_user_on_boot.GetValue());
     ui->toggle_background_pause->setChecked(UISettings::values.pause_when_in_background.GetValue());
     ui->toggle_hide_mouse->setChecked(UISettings::values.hide_mouse.GetValue());
+    ui->toggle_controller_applet_disabled->setEnabled(runtime_lock);
+    ui->toggle_controller_applet_disabled->setChecked(
+        UISettings::values.controller_applet_disabled.GetValue());
 
     ui->toggle_speed_limit->setChecked(Settings::values.use_speed_limit.GetValue());
     ui->speed_limit->setValue(Settings::values.speed_limit.GetValue());
@@ -82,6 +85,8 @@ void ConfigureGeneral::ApplyConfiguration() {
         UISettings::values.select_user_on_boot = ui->toggle_user_on_boot->isChecked();
         UISettings::values.pause_when_in_background = ui->toggle_background_pause->isChecked();
         UISettings::values.hide_mouse = ui->toggle_hide_mouse->isChecked();
+        UISettings::values.controller_applet_disabled =
+            ui->toggle_controller_applet_disabled->isChecked();
 
         // Guard if during game and set to game-specific value
         if (Settings::values.use_speed_limit.UsingGlobal()) {
@@ -128,6 +133,7 @@ void ConfigureGeneral::SetupPerGameUI() {
     ui->toggle_user_on_boot->setVisible(false);
     ui->toggle_background_pause->setVisible(false);
     ui->toggle_hide_mouse->setVisible(false);
+    ui->toggle_controller_applet_disabled->setVisible(false);
 
     ui->button_reset_defaults->setVisible(false);
 
diff --git a/src/yuzu/configuration/configure_general.ui b/src/yuzu/configuration/configure_general.ui
index 986a1625b..fe757d011 100644
--- a/src/yuzu/configuration/configure_general.ui
+++ b/src/yuzu/configuration/configure_general.ui
@@ -89,6 +89,13 @@
             </property>
            </widget>
           </item>
+          <item>
+           <widget class="QCheckBox" name="toggle_controller_applet_disabled">
+            <property name="text">
+             <string>Disable controller applet</string>
+            </property>
+           </widget>
+          </item>
          </layout>
         </item>
        </layout>
diff --git a/src/yuzu/configuration/configure_graphics.cpp b/src/yuzu/configuration/configure_graphics.cpp
index 78b487494..a4965524a 100644
--- a/src/yuzu/configuration/configure_graphics.cpp
+++ b/src/yuzu/configuration/configure_graphics.cpp
@@ -508,7 +508,7 @@ void ConfigureGraphics::RetrieveVulkanDevices() {
         vulkan_devices.push_back(QString::fromStdString(record.name));
         device_present_modes.push_back(record.vsync_support);
 
-        if (record.is_intel_proprietary) {
+        if (record.has_broken_compute) {
             expose_compute_option();
         }
     }
diff --git a/src/yuzu/configuration/configure_graphics_advanced.cpp b/src/yuzu/configuration/configure_graphics_advanced.cpp
index 0463ac8b9..c0a044767 100644
--- a/src/yuzu/configuration/configure_graphics_advanced.cpp
+++ b/src/yuzu/configuration/configure_graphics_advanced.cpp
@@ -43,6 +43,8 @@ void ConfigureGraphicsAdvanced::SetConfiguration() {
     ui->enable_compute_pipelines_checkbox->setChecked(
         Settings::values.enable_compute_pipelines.GetValue());
     ui->use_video_framerate_checkbox->setChecked(Settings::values.use_video_framerate.GetValue());
+    ui->barrier_feedback_loops_checkbox->setChecked(
+        Settings::values.barrier_feedback_loops.GetValue());
 
     if (Settings::IsConfiguringGlobal()) {
         ui->gpu_accuracy->setCurrentIndex(
@@ -94,6 +96,9 @@ void ConfigureGraphicsAdvanced::ApplyConfiguration() {
                                              enable_compute_pipelines);
     ConfigurationShared::ApplyPerGameSetting(&Settings::values.use_video_framerate,
                                              ui->use_video_framerate_checkbox, use_video_framerate);
+    ConfigurationShared::ApplyPerGameSetting(&Settings::values.barrier_feedback_loops,
+                                             ui->barrier_feedback_loops_checkbox,
+                                             barrier_feedback_loops);
 }
 
 void ConfigureGraphicsAdvanced::changeEvent(QEvent* event) {
@@ -130,6 +135,8 @@ void ConfigureGraphicsAdvanced::SetupPerGameUI() {
             Settings::values.enable_compute_pipelines.UsingGlobal());
         ui->use_video_framerate_checkbox->setEnabled(
             Settings::values.use_video_framerate.UsingGlobal());
+        ui->barrier_feedback_loops_checkbox->setEnabled(
+            Settings::values.barrier_feedback_loops.UsingGlobal());
 
         return;
     }
@@ -157,6 +164,9 @@ void ConfigureGraphicsAdvanced::SetupPerGameUI() {
     ConfigurationShared::SetColoredTristate(ui->use_video_framerate_checkbox,
                                             Settings::values.use_video_framerate,
                                             use_video_framerate);
+    ConfigurationShared::SetColoredTristate(ui->barrier_feedback_loops_checkbox,
+                                            Settings::values.barrier_feedback_loops,
+                                            barrier_feedback_loops);
     ConfigurationShared::SetColoredComboBox(
         ui->gpu_accuracy, ui->label_gpu_accuracy,
         static_cast<int>(Settings::values.gpu_accuracy.GetValue(true)));
diff --git a/src/yuzu/configuration/configure_graphics_advanced.h b/src/yuzu/configuration/configure_graphics_advanced.h
index a4dc8ceb0..369a7c83e 100644
--- a/src/yuzu/configuration/configure_graphics_advanced.h
+++ b/src/yuzu/configuration/configure_graphics_advanced.h
@@ -48,6 +48,7 @@ private:
     ConfigurationShared::CheckState use_vulkan_driver_pipeline_cache;
     ConfigurationShared::CheckState enable_compute_pipelines;
     ConfigurationShared::CheckState use_video_framerate;
+    ConfigurationShared::CheckState barrier_feedback_loops;
 
     const Core::System& system;
 };
diff --git a/src/yuzu/configuration/configure_graphics_advanced.ui b/src/yuzu/configuration/configure_graphics_advanced.ui
index e7f0ef6be..d527a6f38 100644
--- a/src/yuzu/configuration/configure_graphics_advanced.ui
+++ b/src/yuzu/configuration/configure_graphics_advanced.ui
@@ -202,6 +202,16 @@ Compute pipelines are always enabled on all other drivers.</string>
          </widget>
         </item>
         <item>
+         <widget class="QCheckBox" name="barrier_feedback_loops_checkbox">
+          <property name="toolTip">
+           <string>Improves rendering of transparency effects in specific games.</string>
+          </property>
+          <property name="text">
+           <string>Barrier feedback loops</string>
+          </property>
+         </widget>
+        </item>
+        <item>
          <widget class="QWidget" name="af_layout" native="true">
           <layout class="QHBoxLayout" name="horizontalLayout_1">
            <property name="leftMargin">
diff --git a/src/yuzu/configuration/configure_input_advanced.cpp b/src/yuzu/configuration/configure_input_advanced.cpp
index f13156434..3cfd5d439 100644
--- a/src/yuzu/configuration/configure_input_advanced.cpp
+++ b/src/yuzu/configuration/configure_input_advanced.cpp
@@ -129,9 +129,6 @@ void ConfigureInputAdvanced::ApplyConfiguration() {
     Settings::values.mouse_enabled = ui->mouse_enabled->isChecked();
     Settings::values.keyboard_enabled = ui->keyboard_enabled->isChecked();
     Settings::values.emulate_analog_keyboard = ui->emulate_analog_keyboard->isChecked();
-    Settings::values.mouse_panning = ui->mouse_panning->isChecked();
-    Settings::values.mouse_panning_sensitivity =
-        static_cast<float>(ui->mouse_panning_sensitivity->value());
     Settings::values.touchscreen.enabled = ui->touchscreen_enabled->isChecked();
     Settings::values.enable_raw_input = ui->enable_raw_input->isChecked();
     Settings::values.enable_udp_controller = ui->enable_udp_controller->isChecked();
@@ -167,8 +164,6 @@ void ConfigureInputAdvanced::LoadConfiguration() {
     ui->mouse_enabled->setChecked(Settings::values.mouse_enabled.GetValue());
     ui->keyboard_enabled->setChecked(Settings::values.keyboard_enabled.GetValue());
     ui->emulate_analog_keyboard->setChecked(Settings::values.emulate_analog_keyboard.GetValue());
-    ui->mouse_panning->setChecked(Settings::values.mouse_panning.GetValue());
-    ui->mouse_panning_sensitivity->setValue(Settings::values.mouse_panning_sensitivity.GetValue());
     ui->touchscreen_enabled->setChecked(Settings::values.touchscreen.enabled);
     ui->enable_raw_input->setChecked(Settings::values.enable_raw_input.GetValue());
     ui->enable_udp_controller->setChecked(Settings::values.enable_udp_controller.GetValue());
@@ -197,8 +192,6 @@ void ConfigureInputAdvanced::RetranslateUI() {
 void ConfigureInputAdvanced::UpdateUIEnabled() {
     ui->debug_configure->setEnabled(ui->debug_enabled->isChecked());
     ui->touchscreen_advanced->setEnabled(ui->touchscreen_enabled->isChecked());
-    ui->mouse_panning->setEnabled(!ui->mouse_enabled->isChecked());
-    ui->mouse_panning_sensitivity->setEnabled(!ui->mouse_enabled->isChecked());
     ui->ring_controller_configure->setEnabled(ui->enable_ring_controller->isChecked());
 #if QT_VERSION > QT_VERSION_CHECK(6, 0, 0) || !defined(YUZU_USE_QT_MULTIMEDIA)
     ui->enable_ir_sensor->setEnabled(false);
diff --git a/src/yuzu/configuration/configure_input_advanced.ui b/src/yuzu/configuration/configure_input_advanced.ui
index 2e8b13660..2994d0ab4 100644
--- a/src/yuzu/configuration/configure_input_advanced.ui
+++ b/src/yuzu/configuration/configure_input_advanced.ui
@@ -2744,48 +2744,13 @@
                      </widget>
                    </item>
                    <item row="8" column="0">
-                     <widget class="QCheckBox" name="mouse_panning">
-                       <property name="minimumSize">
-                         <size>
-                           <width>0</width>
-                           <height>23</height>
-                         </size>
-                       </property>
-                       <property name="text">
-                         <string>Enable mouse panning</string>
-                       </property>
-                     </widget>
-                   </item>
-                   <item row="8" column="2">
-                     <widget class="QSpinBox" name="mouse_panning_sensitivity">
-                       <property name="toolTip">
-                         <string>Mouse sensitivity</string>
-                       </property>
-                       <property name="alignment">
-                         <set>Qt::AlignCenter</set>
-                       </property>
-                       <property name="suffix">
-                         <string>%</string>
-                       </property>
-                       <property name="minimum">
-                         <number>1</number>
-                       </property>
-                       <property name="maximum">
-                         <number>100</number>
-                       </property>
-                       <property name="value">
-                         <number>100</number>
-                       </property>
-                     </widget>
-                   </item>
-                   <item row="9" column="0">
                      <widget class="QLabel" name="motion_touch">
                        <property name="text">
                          <string>Motion / Touch</string>
                        </property>
                      </widget>
                    </item>
-                   <item row="9" column="2">
+                   <item row="8" column="2">
                      <widget class="QPushButton" name="buttonMotionTouch">
                        <property name="text">
                          <string>Configure</string>
diff --git a/src/yuzu/configuration/configure_input_player.cpp b/src/yuzu/configuration/configure_input_player.cpp
index 2c2e7e47b..576f5b571 100644
--- a/src/yuzu/configuration/configure_input_player.cpp
+++ b/src/yuzu/configuration/configure_input_player.cpp
@@ -23,6 +23,7 @@
 #include "yuzu/configuration/config.h"
 #include "yuzu/configuration/configure_input_player.h"
 #include "yuzu/configuration/configure_input_player_widget.h"
+#include "yuzu/configuration/configure_mouse_panning.h"
 #include "yuzu/configuration/input_profiles.h"
 #include "yuzu/util/limitable_input_dialog.h"
 
@@ -711,6 +712,21 @@ ConfigureInputPlayer::ConfigureInputPlayer(QWidget* parent, std::size_t player_i
         });
     }
 
+    if (player_index_ == 0) {
+        connect(ui->mousePanningButton, &QPushButton::clicked, [this, input_subsystem_] {
+            const auto right_stick_param =
+                emulated_controller->GetStickParam(Settings::NativeAnalog::RStick);
+            ConfigureMousePanning dialog(this, input_subsystem_,
+                                         right_stick_param.Get("deadzone", 0.0f),
+                                         right_stick_param.Get("range", 1.0f));
+            if (dialog.exec() == QDialog::Accepted) {
+                dialog.ApplyConfiguration();
+            }
+        });
+    } else {
+        ui->mousePanningWidget->hide();
+    }
+
     // Player Connected checkbox
     connect(ui->groupConnectedController, &QGroupBox::toggled,
             [this](bool checked) { emit Connected(checked); });
diff --git a/src/yuzu/configuration/configure_input_player.ui b/src/yuzu/configuration/configure_input_player.ui
index a9567c6ee..43f6c7b50 100644
--- a/src/yuzu/configuration/configure_input_player.ui
+++ b/src/yuzu/configuration/configure_input_player.ui
@@ -3048,6 +3048,102 @@
                 </item>
                </layout>
               </item>
+              <item>
+               <widget class="QWidget" name="mousePanningWidget" native="true">
+                <layout class="QHBoxLayout" name="mousePanningHorizontalLayout">
+                 <property name="spacing">
+                  <number>0</number>
+                 </property>
+                 <property name="leftMargin">
+                  <number>0</number>
+                 </property>
+                 <property name="topMargin">
+                  <number>0</number>
+                 </property>
+                 <property name="rightMargin">
+                  <number>0</number>
+                 </property>
+                 <property name="bottomMargin">
+                  <number>3</number>
+                 </property>
+                 <item>
+                  <spacer name="mousePanningHorizontalSpacerLeft">
+                   <property name="orientation">
+                    <enum>Qt::Horizontal</enum>
+                   </property>
+                   <property name="sizeHint" stdset="0">
+                    <size>
+                     <width>20</width>
+                     <height>20</height>
+                    </size>
+                   </property>
+                  </spacer>
+                 </item>
+                 <item>
+                  <widget class="QGroupBox" name="mousePanningGroup">
+                   <property name="title">
+                    <string>Mouse panning</string>
+                   </property>
+                   <property name="alignment">
+                    <set>Qt::AlignCenter</set>
+                   </property>
+                   <layout class="QVBoxLayout" name="mousePanningVerticalLayout">
+                    <property name="spacing">
+                     <number>3</number>
+                    </property>
+                    <property name="leftMargin">
+                     <number>3</number>
+                    </property>
+                    <property name="topMargin">
+                     <number>3</number>
+                    </property>
+                    <property name="rightMargin">
+                     <number>3</number>
+                    </property>
+                    <property name="bottomMargin">
+                     <number>3</number>
+                    </property>
+                    <item>
+                     <widget class="QPushButton" name="mousePanningButton">
+                      <property name="minimumSize">
+                       <size>
+                        <width>68</width>
+                        <height>0</height>
+                       </size>
+                      </property>
+                      <property name="maximumSize">
+                       <size>
+                        <width>68</width>
+                        <height>16777215</height>
+                       </size>
+                      </property>
+                      <property name="styleSheet">
+                       <string notr="true">min-width: 68px;</string>
+                      </property>
+                      <property name="text">
+                       <string>Configure</string>
+                      </property>
+                     </widget>
+                    </item>
+                   </layout>
+                  </widget>
+                 </item>
+                 <item>
+                  <spacer name="mousePanningHorizontalSpacerRight">
+                   <property name="orientation">
+                    <enum>Qt::Horizontal</enum>
+                   </property>
+                   <property name="sizeHint" stdset="0">
+                    <size>
+                     <width>20</width>
+                     <height>20</height>
+                    </size>
+                   </property>
+                  </spacer>
+                 </item>
+                </layout>
+               </widget>
+              </item>
              </layout>
             </widget>
            </item>
diff --git a/src/yuzu/configuration/configure_mouse_panning.cpp b/src/yuzu/configuration/configure_mouse_panning.cpp
new file mode 100644
index 000000000..f183d2740
--- /dev/null
+++ b/src/yuzu/configuration/configure_mouse_panning.cpp
@@ -0,0 +1,79 @@
+// SPDX-FileCopyrightText: 2023 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <QCloseEvent>
+
+#include "common/settings.h"
+#include "ui_configure_mouse_panning.h"
+#include "yuzu/configuration/configure_mouse_panning.h"
+
+ConfigureMousePanning::ConfigureMousePanning(QWidget* parent,
+                                             InputCommon::InputSubsystem* input_subsystem_,
+                                             float right_stick_deadzone, float right_stick_range)
+    : QDialog(parent), input_subsystem{input_subsystem_},
+      ui(std::make_unique<Ui::ConfigureMousePanning>()) {
+    ui->setupUi(this);
+    SetConfiguration(right_stick_deadzone, right_stick_range);
+    ConnectEvents();
+}
+
+ConfigureMousePanning::~ConfigureMousePanning() = default;
+
+void ConfigureMousePanning::closeEvent(QCloseEvent* event) {
+    event->accept();
+}
+
+void ConfigureMousePanning::SetConfiguration(float right_stick_deadzone, float right_stick_range) {
+    ui->enable->setChecked(Settings::values.mouse_panning.GetValue());
+    ui->x_sensitivity->setValue(Settings::values.mouse_panning_x_sensitivity.GetValue());
+    ui->y_sensitivity->setValue(Settings::values.mouse_panning_y_sensitivity.GetValue());
+    ui->deadzone_x_counterweight->setValue(
+        Settings::values.mouse_panning_deadzone_x_counterweight.GetValue());
+    ui->deadzone_y_counterweight->setValue(
+        Settings::values.mouse_panning_deadzone_y_counterweight.GetValue());
+    ui->decay_strength->setValue(Settings::values.mouse_panning_decay_strength.GetValue());
+    ui->min_decay->setValue(Settings::values.mouse_panning_min_decay.GetValue());
+
+    if (right_stick_deadzone > 0.0f || right_stick_range != 1.0f) {
+        ui->warning_label->setText(QString::fromStdString(
+            "Mouse panning works better with a deadzone of 0% and a range of 100%.\n"
+            "Current values are " +
+            std::to_string(static_cast<int>(right_stick_deadzone * 100.0f)) + "% and " +
+            std::to_string(static_cast<int>(right_stick_range * 100.0f)) + "% respectively."));
+    } else {
+        ui->warning_label->hide();
+    }
+}
+
+void ConfigureMousePanning::SetDefaultConfiguration() {
+    ui->x_sensitivity->setValue(Settings::values.mouse_panning_x_sensitivity.GetDefault());
+    ui->y_sensitivity->setValue(Settings::values.mouse_panning_y_sensitivity.GetDefault());
+    ui->deadzone_x_counterweight->setValue(
+        Settings::values.mouse_panning_deadzone_x_counterweight.GetDefault());
+    ui->deadzone_y_counterweight->setValue(
+        Settings::values.mouse_panning_deadzone_y_counterweight.GetDefault());
+    ui->decay_strength->setValue(Settings::values.mouse_panning_decay_strength.GetDefault());
+    ui->min_decay->setValue(Settings::values.mouse_panning_min_decay.GetDefault());
+}
+
+void ConfigureMousePanning::ConnectEvents() {
+    connect(ui->default_button, &QPushButton::clicked, this,
+            &ConfigureMousePanning::SetDefaultConfiguration);
+    connect(ui->button_box, &QDialogButtonBox::accepted, this,
+            &ConfigureMousePanning::ApplyConfiguration);
+    connect(ui->button_box, &QDialogButtonBox::rejected, this, [this] { reject(); });
+}
+
+void ConfigureMousePanning::ApplyConfiguration() {
+    Settings::values.mouse_panning = ui->enable->isChecked();
+    Settings::values.mouse_panning_x_sensitivity = static_cast<float>(ui->x_sensitivity->value());
+    Settings::values.mouse_panning_y_sensitivity = static_cast<float>(ui->y_sensitivity->value());
+    Settings::values.mouse_panning_deadzone_x_counterweight =
+        static_cast<float>(ui->deadzone_x_counterweight->value());
+    Settings::values.mouse_panning_deadzone_y_counterweight =
+        static_cast<float>(ui->deadzone_y_counterweight->value());
+    Settings::values.mouse_panning_decay_strength = static_cast<float>(ui->decay_strength->value());
+    Settings::values.mouse_panning_min_decay = static_cast<float>(ui->min_decay->value());
+
+    accept();
+}
diff --git a/src/yuzu/configuration/configure_mouse_panning.h b/src/yuzu/configuration/configure_mouse_panning.h
new file mode 100644
index 000000000..08c6e1f62
--- /dev/null
+++ b/src/yuzu/configuration/configure_mouse_panning.h
@@ -0,0 +1,35 @@
+// SPDX-FileCopyrightText: 2023 yuzu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#include <memory>
+#include <QDialog>
+
+namespace InputCommon {
+class InputSubsystem;
+}
+
+namespace Ui {
+class ConfigureMousePanning;
+}
+
+class ConfigureMousePanning : public QDialog {
+    Q_OBJECT
+public:
+    explicit ConfigureMousePanning(QWidget* parent, InputCommon::InputSubsystem* input_subsystem_,
+                                   float right_stick_deadzone, float right_stick_range);
+    ~ConfigureMousePanning() override;
+
+public slots:
+    void ApplyConfiguration();
+
+private:
+    void closeEvent(QCloseEvent* event) override;
+    void SetConfiguration(float right_stick_deadzone, float right_stick_range);
+    void SetDefaultConfiguration();
+    void ConnectEvents();
+
+    InputCommon::InputSubsystem* input_subsystem;
+    std::unique_ptr<Ui::ConfigureMousePanning> ui;
+};
diff --git a/src/yuzu/configuration/configure_mouse_panning.ui b/src/yuzu/configuration/configure_mouse_panning.ui
new file mode 100644
index 000000000..75795b727
--- /dev/null
+++ b/src/yuzu/configuration/configure_mouse_panning.ui
@@ -0,0 +1,238 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>ConfigureMousePanning</class>
+ <widget class="QDialog" name="configure_mouse_panning">
+  <property name="windowTitle">
+   <string>Configure mouse panning</string>
+  </property>
+  <layout class="QVBoxLayout">
+   <item>
+    <widget class="QCheckBox" name="enable">
+     <property name="text">
+      <string>Enable</string>
+     </property>
+     <property name="toolTip">
+      <string>Can be toggled via a hotkey</string>
+     </property>
+    </widget>
+   </item>
+   <item>
+    <layout class="QHBoxLayout">
+     <item>
+      <widget class="QGroupBox" name="sensitivity_box">
+       <property name="title">
+        <string>Sensitivity</string>
+       </property>
+       <layout class="QGridLayout">
+        <item row="0" column="0">
+         <widget class="QLabel" name="x_sensitivity_label">
+          <property name="text">
+           <string>Horizontal</string>
+          </property>
+         </widget>
+        </item>
+        <item row="0" column="1">
+         <widget class="QSpinBox" name="x_sensitivity">
+          <property name="alignment">
+           <set>Qt::AlignCenter</set>
+          </property>
+          <property name="suffix">
+           <string>%</string>
+          </property>
+          <property name="minimum">
+           <number>1</number>
+          </property>
+          <property name="maximum">
+           <number>100</number>
+          </property>
+          <property name="value">
+           <number>50</number>
+          </property>
+         </widget>
+        </item>
+        <item row="1" column="0">
+         <widget class="QLabel" name="y_sensitivity_label">
+          <property name="text">
+           <string>Vertical</string>
+          </property>
+         </widget>
+        </item>
+        <item row="1" column="1">
+         <widget class="QSpinBox" name="y_sensitivity">
+          <property name="alignment">
+           <set>Qt::AlignCenter</set>
+          </property>
+          <property name="suffix">
+           <string>%</string>
+          </property>
+          <property name="minimum">
+           <number>1</number>
+          </property>
+          <property name="maximum">
+           <number>100</number>
+          </property>
+          <property name="value">
+           <number>50</number>
+          </property>
+         </widget>
+        </item>
+       </layout>
+      </widget>
+     </item>
+     <item>
+      <widget class="QGroupBox" name="deadzone_counterweight_box">
+       <property name="title">
+        <string>Deadzone counterweight</string>
+       </property>
+       <property name="toolTip">
+        <string>Counteracts a game's built-in deadzone</string>
+       </property>
+       <layout class="QGridLayout">
+        <item row="0" column="0">
+         <widget class="QLabel" name="deadzone_x_counterweight_label">
+          <property name="text">
+           <string>Horizontal</string>
+          </property>
+         </widget>
+        </item>
+        <item row="0" column="1">
+         <widget class="QSpinBox" name="deadzone_x_counterweight">
+          <property name="alignment">
+           <set>Qt::AlignCenter</set>
+          </property>
+          <property name="suffix">
+           <string>%</string>
+          </property>
+          <property name="minimum">
+           <number>0</number>
+          </property>
+          <property name="maximum">
+           <number>100</number>
+          </property>
+          <property name="value">
+           <number>0</number>
+          </property>
+         </widget>
+        </item>
+        <item row="1" column="0">
+         <widget class="QLabel" name="deadzone_y_counterweight_label">
+          <property name="text">
+           <string>Vertical</string>
+          </property>
+         </widget>
+        </item>
+        <item row="1" column="1">
+         <widget class="QSpinBox" name="deadzone_y_counterweight">
+          <property name="alignment">
+           <set>Qt::AlignCenter</set>
+          </property>
+          <property name="suffix">
+           <string>%</string>
+          </property>
+          <property name="minimum">
+           <number>0</number>
+          </property>
+          <property name="maximum">
+           <number>100</number>
+          </property>
+          <property name="value">
+           <number>0</number>
+          </property>
+         </widget>
+        </item>
+       </layout>
+      </widget>
+     </item>
+     <item>
+      <widget class="QGroupBox" name="decay_box">
+       <property name="title">
+        <string>Stick decay</string>
+       </property>
+       <layout class="QGridLayout">
+        <item row="0" column="0">
+         <widget class="QLabel" name="decay_strength_label">
+          <property name="text">
+           <string>Strength</string>
+          </property>
+         </widget>
+        </item>
+        <item row="0" column="1">
+         <widget class="QSpinBox" name="decay_strength">
+          <property name="alignment">
+           <set>Qt::AlignCenter</set>
+          </property>
+          <property name="suffix">
+           <string>%</string>
+          </property>
+          <property name="minimum">
+           <number>0</number>
+          </property>
+          <property name="maximum">
+           <number>100</number>
+          </property>
+          <property name="value">
+           <number>22</number>
+          </property>
+         </widget>
+        </item>
+        <item row="1" column="0">
+         <widget class="QLabel" name="min_decay_label">
+          <property name="text">
+           <string>Minimum</string>
+          </property>
+         </widget>
+        </item>
+        <item row="1" column="1">
+         <widget class="QSpinBox" name="min_decay">
+          <property name="alignment">
+           <set>Qt::AlignCenter</set>
+          </property>
+          <property name="suffix">
+           <string>%</string>
+          </property>
+          <property name="minimum">
+           <number>0</number>
+          </property>
+          <property name="maximum">
+           <number>100</number>
+          </property>
+          <property name="value">
+           <number>5</number>
+          </property>
+         </widget>
+        </item>
+       </layout>
+      </widget>
+     </item>
+    </layout>
+   </item>
+   <item>
+    <widget class="QLabel" name="warning_label">
+     <property name="text">
+      <string/>
+     </property>
+    </widget>
+   </item>
+   <item>
+    <layout class="QHBoxLayout">
+     <item>
+      <widget class="QPushButton" name="default_button">
+       <property name="text">
+        <string>Default</string>
+       </property>
+      </widget>
+     </item>
+     <item>
+      <widget class="QDialogButtonBox" name="button_box">
+       <property name="standardButtons">
+        <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+       </property>
+      </widget>
+     </item>
+    </layout>
+   </item>
+  </layout>
+ </widget>
+ <resources/>
+ <connections/>
+</ui>
diff --git a/src/yuzu/configuration/configure_ringcon.cpp b/src/yuzu/configuration/configure_ringcon.cpp
index 71afbc423..f83705544 100644
--- a/src/yuzu/configuration/configure_ringcon.cpp
+++ b/src/yuzu/configuration/configure_ringcon.cpp
@@ -305,6 +305,9 @@ void ConfigureRingController::EnableRingController() {
         QMessageBox::warning(this, dialog_title,
                              tr("The current mapped device doesn't have a ring attached"));
         break;
+    case Common::Input::DriverResult::InvalidHandle:
+        QMessageBox::warning(this, dialog_title, tr("The current mapped device is not connected"));
+        break;
     default:
         QMessageBox::warning(this, dialog_title,
                              tr("Unexpected driver result %1").arg(static_cast<int>(result)));
diff --git a/src/yuzu/configuration/configure_ringcon.ui b/src/yuzu/configuration/configure_ringcon.ui
index 514dff372..38ecccc3d 100644
--- a/src/yuzu/configuration/configure_ringcon.ui
+++ b/src/yuzu/configuration/configure_ringcon.ui
@@ -23,7 +23,7 @@
       </size>
      </property>
      <property name="text">
-      <string>If you want to use this controller configure player 1 as right controller and player 2 as dual joycon before starting the game to allow this controller to be detected properly.</string>
+      <string>To use Ring-Con, configure player 1 as right Joy-Con (both physical and emulated), and player 2 as left Joy-Con (left physical and dual emulated) before starting the game.</string>
      </property>
      <property name="wordWrap">
       <bool>true</bool>
diff --git a/src/yuzu/main.cpp b/src/yuzu/main.cpp
index 8768a7c3c..e8418b302 100644
--- a/src/yuzu/main.cpp
+++ b/src/yuzu/main.cpp
@@ -447,6 +447,14 @@ GMainWindow::GMainWindow(std::unique_ptr<Config> config_, bool has_broken_vulkan
 
 #if defined(HAVE_SDL2) && !defined(_WIN32)
     SDL_InitSubSystem(SDL_INIT_VIDEO);
+
+    // Set a screensaver inhibition reason string. Currently passed to DBus by SDL and visible to
+    // the user through their desktop environment.
+    //: TRANSLATORS: This string is shown to the user to explain why yuzu needs to prevent the
+    //: computer from sleeping
+    QByteArray wakelock_reason = tr("Running a game").toLatin1();
+    SDL_SetHint(SDL_HINT_SCREENSAVER_INHIBIT_ACTIVITY_NAME, wakelock_reason.data());
+
     // SDL disables the screen saver by default, and setting the hint
     // SDL_HINT_VIDEO_ALLOW_SCREENSAVER doesn't seem to work, so we just enable the screen saver
     // for now.
@@ -1623,45 +1631,6 @@ void GMainWindow::OnPrepareForSleep(bool prepare_sleep) {
 }
 
 #ifdef __unix__
-static std::optional<QDBusObjectPath> HoldWakeLockLinux(u32 window_id = 0) {
-    if (!QDBusConnection::sessionBus().isConnected()) {
-        return {};
-    }
-    // reference: https://flatpak.github.io/xdg-desktop-portal/#gdbus-org.freedesktop.portal.Inhibit
-    QDBusInterface xdp(QString::fromLatin1("org.freedesktop.portal.Desktop"),
-                       QString::fromLatin1("/org/freedesktop/portal/desktop"),
-                       QString::fromLatin1("org.freedesktop.portal.Inhibit"));
-    if (!xdp.isValid()) {
-        LOG_WARNING(Frontend, "Couldn't connect to XDP D-Bus endpoint");
-        return {};
-    }
-    QVariantMap options = {};
-    //: TRANSLATORS: This string is shown to the user to explain why yuzu needs to prevent the
-    //: computer from sleeping
-    options.insert(QString::fromLatin1("reason"),
-                   QCoreApplication::translate("GMainWindow", "yuzu is running a game"));
-    // 0x4: Suspend lock; 0x8: Idle lock
-    QDBusReply<QDBusObjectPath> reply =
-        xdp.call(QString::fromLatin1("Inhibit"),
-                 QString::fromLatin1("x11:") + QString::number(window_id, 16), 12U, options);
-
-    if (reply.isValid()) {
-        return reply.value();
-    }
-    LOG_WARNING(Frontend, "Couldn't read Inhibit reply from XDP: {}",
-                reply.error().message().toStdString());
-    return {};
-}
-
-static void ReleaseWakeLockLinux(QDBusObjectPath lock) {
-    if (!QDBusConnection::sessionBus().isConnected()) {
-        return;
-    }
-    QDBusInterface unlocker(QString::fromLatin1("org.freedesktop.portal.Desktop"), lock.path(),
-                            QString::fromLatin1("org.freedesktop.portal.Request"));
-    unlocker.call(QString::fromLatin1("Close"));
-}
-
 std::array<int, 3> GMainWindow::sig_interrupt_fds{0, 0, 0};
 
 void GMainWindow::SetupSigInterrupts() {
@@ -1714,12 +1683,6 @@ void GMainWindow::PreventOSSleep() {
     SetThreadExecutionState(ES_CONTINUOUS | ES_SYSTEM_REQUIRED | ES_DISPLAY_REQUIRED);
 #elif defined(HAVE_SDL2)
     SDL_DisableScreenSaver();
-#ifdef __unix__
-    auto reply = HoldWakeLockLinux(winId());
-    if (reply) {
-        wake_lock = std::move(reply.value());
-    }
-#endif
 #endif
 }
 
@@ -1728,11 +1691,6 @@ void GMainWindow::AllowOSSleep() {
     SetThreadExecutionState(ES_CONTINUOUS);
 #elif defined(HAVE_SDL2)
     SDL_EnableScreenSaver();
-#ifdef __unix__
-    if (!wake_lock.path().isEmpty()) {
-        ReleaseWakeLockLinux(wake_lock);
-    }
-#endif
 #endif
 }
 
@@ -1749,15 +1707,17 @@ bool GMainWindow::LoadROM(const QString& filename, u64 program_id, std::size_t p
     system->SetFilesystem(vfs);
 
     system->SetAppletFrontendSet({
-        std::make_unique<QtAmiiboSettings>(*this),     // Amiibo Settings
-        std::make_unique<QtControllerSelector>(*this), // Controller Selector
-        std::make_unique<QtErrorDisplay>(*this),       // Error Display
-        nullptr,                                       // Mii Editor
-        nullptr,                                       // Parental Controls
-        nullptr,                                       // Photo Viewer
-        std::make_unique<QtProfileSelector>(*this),    // Profile Selector
-        std::make_unique<QtSoftwareKeyboard>(*this),   // Software Keyboard
-        std::make_unique<QtWebBrowser>(*this),         // Web Browser
+        std::make_unique<QtAmiiboSettings>(*this), // Amiibo Settings
+        (UISettings::values.controller_applet_disabled.GetValue() == true)
+            ? nullptr
+            : std::make_unique<QtControllerSelector>(*this), // Controller Selector
+        std::make_unique<QtErrorDisplay>(*this),             // Error Display
+        nullptr,                                             // Mii Editor
+        nullptr,                                             // Parental Controls
+        nullptr,                                             // Photo Viewer
+        std::make_unique<QtProfileSelector>(*this),          // Profile Selector
+        std::make_unique<QtSoftwareKeyboard>(*this),         // Software Keyboard
+        std::make_unique<QtWebBrowser>(*this),               // Web Browser
     });
 
     const Core::SystemResultStatus result{
@@ -3840,7 +3800,7 @@ void GMainWindow::OnLoadAmiibo() {
     auto* virtual_amiibo = input_subsystem->GetVirtualAmiibo();
 
     // Remove amiibo if one is connected
-    if (virtual_amiibo->GetCurrentState() == InputCommon::VirtualAmiibo::State::AmiiboIsOpen) {
+    if (virtual_amiibo->GetCurrentState() == InputCommon::VirtualAmiibo::State::TagNearby) {
         virtual_amiibo->CloseAmiibo();
         QMessageBox::warning(this, tr("Amiibo"), tr("The current amiibo has been removed"));
         return;
@@ -3868,7 +3828,7 @@ void GMainWindow::LoadAmiibo(const QString& filename) {
     auto* virtual_amiibo = input_subsystem->GetVirtualAmiibo();
     const QString title = tr("Error loading Amiibo data");
     // Remove amiibo if one is connected
-    if (virtual_amiibo->GetCurrentState() == InputCommon::VirtualAmiibo::State::AmiiboIsOpen) {
+    if (virtual_amiibo->GetCurrentState() == InputCommon::VirtualAmiibo::State::TagNearby) {
         virtual_amiibo->CloseAmiibo();
         QMessageBox::warning(this, tr("Amiibo"), tr("The current amiibo has been removed"));
         return;
diff --git a/src/yuzu/main.h b/src/yuzu/main.h
index e0e775d87..2cfb96257 100644
--- a/src/yuzu/main.h
+++ b/src/yuzu/main.h
@@ -504,8 +504,6 @@ private:
 #ifdef __unix__
     QSocketNotifier* sig_interrupt_notifier;
     static std::array<int, 3> sig_interrupt_fds;
-
-    QDBusObjectPath wake_lock{};
 #endif
 
 protected:
diff --git a/src/yuzu/uisettings.h b/src/yuzu/uisettings.h
index db43b7033..20a517d34 100644
--- a/src/yuzu/uisettings.h
+++ b/src/yuzu/uisettings.h
@@ -77,6 +77,8 @@ struct Values {
     Settings::Setting<bool> pause_when_in_background{false, "pauseWhenInBackground"};
     Settings::Setting<bool> mute_when_in_background{false, "muteWhenInBackground"};
     Settings::Setting<bool> hide_mouse{true, "hideInactiveMouse"};
+    Settings::Setting<bool> controller_applet_disabled{false, "disableControllerApplet"};
+
     // Set when Vulkan is known to crash the application
     bool has_broken_vulkan = false;
 
diff --git a/src/yuzu/vk_device_info.cpp b/src/yuzu/vk_device_info.cpp
index 9bd1ec686..7c26a3dc7 100644
--- a/src/yuzu/vk_device_info.cpp
+++ b/src/yuzu/vk_device_info.cpp
@@ -5,10 +5,12 @@
 #include <vector>
 #include "common/dynamic_library.h"
 #include "common/logging/log.h"
+#include "video_core/vulkan_common/vulkan_device.h"
 #include "video_core/vulkan_common/vulkan_instance.h"
 #include "video_core/vulkan_common/vulkan_library.h"
 #include "video_core/vulkan_common/vulkan_surface.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
+#include "vulkan/vulkan_core.h"
 #include "yuzu/qt_common.h"
 #include "yuzu/vk_device_info.h"
 
@@ -16,8 +18,8 @@ class QWindow;
 
 namespace VkDeviceInfo {
 Record::Record(std::string_view name_, const std::vector<VkPresentModeKHR>& vsync_modes_,
-               bool is_intel_proprietary_)
-    : name{name_}, vsync_support{vsync_modes_}, is_intel_proprietary{is_intel_proprietary_} {}
+               bool has_broken_compute_)
+    : name{name_}, vsync_support{vsync_modes_}, has_broken_compute{has_broken_compute_} {}
 
 Record::~Record() = default;
 
@@ -48,9 +50,10 @@ void PopulateRecords(std::vector<Record>& records, QWindow* window) try {
         properties.pNext = &driver_properties;
         dld.vkGetPhysicalDeviceProperties2(physical_device, &properties);
 
-        records.push_back(VkDeviceInfo::Record(name, present_modes,
-                                               driver_properties.driverID ==
-                                                   VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS));
+        bool has_broken_compute{Vulkan::Device::CheckBrokenCompute(
+            driver_properties.driverID, properties.properties.driverVersion)};
+
+        records.push_back(VkDeviceInfo::Record(name, present_modes, has_broken_compute));
     }
 } catch (const Vulkan::vk::Exception& exception) {
     LOG_ERROR(Frontend, "Failed to enumerate devices with error: {}", exception.what());
diff --git a/src/yuzu/vk_device_info.h b/src/yuzu/vk_device_info.h
index 5a6c64416..bda8262f4 100644
--- a/src/yuzu/vk_device_info.h
+++ b/src/yuzu/vk_device_info.h
@@ -24,12 +24,12 @@ namespace VkDeviceInfo {
 class Record {
 public:
     explicit Record(std::string_view name, const std::vector<VkPresentModeKHR>& vsync_modes,
-                    bool is_intel_proprietary);
+                    bool has_broken_compute);
     ~Record();
 
     const std::string name;
     const std::vector<VkPresentModeKHR> vsync_support;
-    const bool is_intel_proprietary;
+    const bool has_broken_compute;
 };
 
 void PopulateRecords(std::vector<Record>& records, QWindow* window);
diff --git a/src/yuzu_cmd/default_ini.h b/src/yuzu_cmd/default_ini.h
index 911d461e4..119e22183 100644
--- a/src/yuzu_cmd/default_ini.h
+++ b/src/yuzu_cmd/default_ini.h
@@ -140,9 +140,29 @@ udp_input_servers =
 # 0 (default): Off, 1: On
 mouse_panning =
 
-# Set mouse sensitivity.
-# Default: 1.0
-mouse_panning_sensitivity =
+# Set mouse panning horizontal sensitivity.
+# Default: 50.0
+mouse_panning_x_sensitivity =
+
+# Set mouse panning vertical sensitivity.
+# Default: 50.0
+mouse_panning_y_sensitivity =
+
+# Set mouse panning deadzone horizontal counterweight.
+# Default: 0.0
+mouse_panning_deadzone_x_counterweight =
+
+# Set mouse panning deadzone vertical counterweight.
+# Default: 0.0
+mouse_panning_deadzone_y_counterweight =
+
+# Set mouse panning stick decay strength.
+# Default: 22.0
+mouse_panning_decay_strength =
+
+# Set mouse panning stick minimum decay.
+# Default: 5.0
+mouse_panning_minimum_decay =
 
 # Emulate an analog control stick from keyboard inputs.
 # 0 (default): Disabled, 1: Enabled