Merge remote-tracking branch 'remotes/kraxel/tags/audio-20210115-pull-request' into staging

audio: improvements for sdl, pulse, fsound.
audio: cleanups & codestyle fixes.

# gpg: Signature made Fri 15 Jan 2021 13:20:56 GMT
# gpg:                using RSA key A0328CFFB93A17A79901FE7D4CB6D8EED3E87138
# gpg: Good signature from "Gerd Hoffmann (work) <kraxel@redhat.com>" [full]
# gpg:                 aka "Gerd Hoffmann <gerd@kraxel.org>" [full]
# gpg:                 aka "Gerd Hoffmann (private) <kraxel@gmail.com>" [full]
# Primary key fingerprint: A032 8CFF B93A 17A7 9901  FE7D 4CB6 D8EE D3E8 7138

* remotes/kraxel/tags/audio-20210115-pull-request: (30 commits)
  audio: space prohibited between function name and parenthesis'('
  audio: Suspect code indent for conditional statements
  audio: Don't use '%#' in format strings
  audio: Fix lines over 90 characters
  audio: foo* bar" should be "foo *bar".
  audio: Add spaces around operator/delete redundant spaces
  audio: Add braces for statements/fix braces' position
  dsoundaudio: fix log message
  dsoundaudio: enable f32 audio sample format
  dsoundaudio: rename dsound_open()
  dsoundaudio: replace GetForegroundWindow()
  paaudio: send recorded data in smaller chunks
  paaudio: limit minreq to 75% of audio timer_rate
  paaudio: comment bugs in functions qpa_init_*
  paaudio: remove unneeded code
  paaudio: wait until the playback stream is ready
  paaudio: wait for PA_STREAM_READY in qpa_write()
  paaudio: avoid to clip samples multiple times
  audio: remove remaining unused plive code
  sdlaudio: enable (in|out).mixing-engine=off
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

17 files changed, 472 insertions, 236 deletions

diff --git a/audio/alsaaudio.c b/audio/alsaaudio.c
index a8e62542f9..fcc2f62864 100644
--- a/audio/alsaaudio.c
+++ b/audio/alsaaudio.c
@@ -278,32 +278,28 @@ static snd_pcm_format_t aud_to_alsafmt (AudioFormat fmt, int endianness)
     case AUDIO_FORMAT_S16:
         if (endianness) {
             return SND_PCM_FORMAT_S16_BE;
-        }
-        else {
+        } else {
             return SND_PCM_FORMAT_S16_LE;
         }
 
     case AUDIO_FORMAT_U16:
         if (endianness) {
             return SND_PCM_FORMAT_U16_BE;
-        }
-        else {
+        } else {
             return SND_PCM_FORMAT_U16_LE;
         }
 
     case AUDIO_FORMAT_S32:
         if (endianness) {
             return SND_PCM_FORMAT_S32_BE;
-        }
-        else {
+        } else {
             return SND_PCM_FORMAT_S32_LE;
         }
 
     case AUDIO_FORMAT_U32:
         if (endianness) {
             return SND_PCM_FORMAT_U32_BE;
-        }
-        else {
+        } else {
             return SND_PCM_FORMAT_U32_LE;
         }
 
@@ -599,7 +595,7 @@ static int alsa_open(bool in, struct alsa_params_req *req,
     }
 
 #ifdef DEBUG
-    alsa_dump_info(req, obt, obtfmt, pdo);
+    alsa_dump_info(req, obt, obtfmt, apdo);
 #endif
     return 0;
 
@@ -722,8 +718,7 @@ static int alsa_voice_ctl (snd_pcm_t *handle, const char *typ, int ctl)
             alsa_logerr (err, "Could not stop %s\n", typ);
             return -1;
         }
-    }
-    else {
+    } else {
         err = snd_pcm_prepare (handle);
         if (err < 0) {
             alsa_logerr (err, "Could not prepare handle for %s\n", typ);
@@ -929,6 +924,7 @@ static struct audio_pcm_ops alsa_pcm_ops = {
     .init_in  = alsa_init_in,
     .fini_in  = alsa_fini_in,
     .read     = alsa_read,
+    .run_buffer_in = audio_generic_run_buffer_in,
     .enable_in = alsa_enable_in,
 };
 
diff --git a/audio/audio.c b/audio/audio.c
index b48471bb3f..6734c8af70 100644
--- a/audio/audio.c
+++ b/audio/audio.c
@@ -344,8 +344,7 @@ void audio_pcm_info_clear_buf (struct audio_pcm_info *info, void *buf, int len)
 
     if (info->is_signed || info->is_float) {
         memset(buf, 0x00, len * info->bytes_per_frame);
-    }
-    else {
+    } else {
         switch (info->bits) {
         case 8:
             memset(buf, 0x80, len * info->bytes_per_frame);
@@ -584,8 +583,7 @@ static size_t audio_pcm_sw_get_rpos_in(SWVoiceIn *sw)
     rpos = hw->conv_buf->pos - live;
     if (rpos >= 0) {
         return rpos;
-    }
-    else {
+    } else {
         return hw->conv_buf->size + rpos;
     }
 }
@@ -788,10 +786,14 @@ static int audio_is_timer_needed(AudioState *s)
     HWVoiceOut *hwo = NULL;
 
     while ((hwo = audio_pcm_hw_find_any_enabled_out(s, hwo))) {
-        if (!hwo->poll_mode) return 1;
+        if (!hwo->poll_mode) {
+            return 1;
+        }
     }
     while ((hwi = audio_pcm_hw_find_any_enabled_in(s, hwi))) {
-        if (!hwi->poll_mode) return 1;
+        if (!hwi->poll_mode) {
+            return 1;
+        }
     }
     return 0;
 }
@@ -908,8 +910,7 @@ void AUD_set_active_out (SWVoiceOut *sw, int on)
                     audio_reset_timer (s);
                 }
             }
-        }
-        else {
+        } else {
             if (hw->enabled) {
                 int nb_active = 0;
 
@@ -956,8 +957,7 @@ void AUD_set_active_in (SWVoiceIn *sw, int on)
                 }
             }
             sw->total_hw_samples_acquired = hw->total_samples_captured;
-        }
-        else {
+        } else {
             if (hw->enabled) {
                 int nb_active = 0;
 
@@ -1132,7 +1132,7 @@ static void audio_run_out (AudioState *s)
 
     while ((hw = audio_pcm_hw_find_any_enabled_out(s, hw))) {
         size_t played, live, prev_rpos, free;
-        int nb_live, cleanup_required;
+        int nb_live;
 
         live = audio_pcm_hw_get_live_out (hw, &nb_live);
         if (!nb_live) {
@@ -1194,7 +1194,6 @@ static void audio_run_out (AudioState *s)
             audio_capture_mix_and_clear (hw, prev_rpos, played);
         }
 
-        cleanup_required = 0;
         for (sw = hw->sw_head.lh_first; sw; sw = sw->entries.le_next) {
             if (!sw->active && sw->empty) {
                 continue;
@@ -1210,7 +1209,6 @@ static void audio_run_out (AudioState *s)
 
             if (!sw->total_hw_samples_mixed) {
                 sw->empty = 1;
-                cleanup_required |= !sw->active && !sw->callback.fn;
             }
 
             if (sw->active) {
@@ -1220,19 +1218,6 @@ static void audio_run_out (AudioState *s)
                 }
             }
         }
-
-        if (cleanup_required) {
-            SWVoiceOut *sw1;
-
-            sw = hw->sw_head.lh_first;
-            while (sw) {
-                sw1 = sw->entries.le_next;
-                if (!sw->active && !sw->callback.fn) {
-                    audio_close_out (sw);
-                }
-                sw = sw1;
-            }
-        }
     }
 }
 
@@ -1241,6 +1226,10 @@ static size_t audio_pcm_hw_run_in(HWVoiceIn *hw, size_t samples)
     size_t conv = 0;
     STSampleBuffer *conv_buf = hw->conv_buf;
 
+    if (hw->pcm_ops->run_buffer_in) {
+        hw->pcm_ops->run_buffer_in(hw);
+    }
+
     while (samples) {
         size_t proc;
         size_t size = samples * hw->info.bytes_per_frame;
@@ -1381,14 +1370,11 @@ void audio_run(AudioState *s, const char *msg)
 #endif
 }
 
-void *audio_generic_get_buffer_in(HWVoiceIn *hw, size_t *size)
+void audio_generic_run_buffer_in(HWVoiceIn *hw)
 {
-    ssize_t start;
-
     if (unlikely(!hw->buf_emul)) {
-        size_t calc_size = hw->conv_buf->size * hw->info.bytes_per_frame;
-        hw->buf_emul = g_malloc(calc_size);
-        hw->size_emul = calc_size;
+        hw->size_emul = hw->samples * hw->info.bytes_per_frame;
+        hw->buf_emul = g_malloc(hw->size_emul);
         hw->pos_emul = hw->pending_emul = 0;
     }
 
@@ -1403,8 +1389,12 @@ void *audio_generic_get_buffer_in(HWVoiceIn *hw, size_t *size)
             break;
         }
     }
+}
+
+void *audio_generic_get_buffer_in(HWVoiceIn *hw, size_t *size)
+{
+    ssize_t start = (ssize_t)hw->pos_emul - hw->pending_emul;
 
-    start = ((ssize_t) hw->pos_emul) - hw->pending_emul;
     if (start < 0) {
         start += hw->size_emul;
     }
@@ -1446,10 +1436,8 @@ void audio_generic_run_buffer_out(HWVoiceOut *hw)
 void *audio_generic_get_buffer_out(HWVoiceOut *hw, size_t *size)
 {
     if (unlikely(!hw->buf_emul)) {
-        size_t calc_size = hw->mix_buf->size * hw->info.bytes_per_frame;
-
-        hw->buf_emul = g_malloc(calc_size);
-        hw->size_emul = calc_size;
+        hw->size_emul = hw->samples * hw->info.bytes_per_frame;
+        hw->buf_emul = g_malloc(hw->size_emul);
         hw->pos_emul = hw->pending_emul = 0;
     }
 
@@ -1505,6 +1493,10 @@ size_t audio_generic_read(HWVoiceIn *hw, void *buf, size_t size)
 {
     size_t total = 0;
 
+    if (hw->pcm_ops->run_buffer_in) {
+        hw->pcm_ops->run_buffer_in(hw);
+    }
+
     while (total < size) {
         size_t src_size = size - total;
         void *src = hw->pcm_ops->get_buffer_in(hw, &src_size);
@@ -1540,8 +1532,7 @@ static int audio_driver_init(AudioState *s, struct audio_driver *drv,
         audio_init_nb_voices_in(s, drv);
         s->drv = drv;
         return 0;
-    }
-    else {
+    } else {
         if (msg) {
             dolog("Could not init `%s' audio driver\n", drv->name);
         }
@@ -1856,8 +1847,7 @@ CaptureVoiceOut *AUD_add_capture(
     if (cap) {
         QLIST_INSERT_HEAD (&cap->cb_head, cb, entries);
         return cap;
-    }
-    else {
+    } else {
         HWVoiceOut *hw;
         CaptureVoiceOut *cap;
 
@@ -2003,7 +1993,7 @@ void audio_create_pdos(Audiodev *dev)
         CASE(JACK, jack, Jack);
         CASE(OSS, oss, Oss);
         CASE(PA, pa, Pa);
-        CASE(SDL, sdl, );
+        CASE(SDL, sdl, Sdl);
         CASE(SPICE, spice, );
         CASE(WAV, wav, );
 
diff --git a/audio/audio_int.h b/audio/audio_int.h
index 4775857bf2..06f0913835 100644
--- a/audio/audio_int.h
+++ b/audio/audio_int.h
@@ -172,12 +172,14 @@ struct audio_pcm_ops {
     int    (*init_in) (HWVoiceIn *hw, audsettings *as, void *drv_opaque);
     void   (*fini_in) (HWVoiceIn *hw);
     size_t (*read)    (HWVoiceIn *hw, void *buf, size_t size);
+    void   (*run_buffer_in)(HWVoiceIn *hw);
     void  *(*get_buffer_in)(HWVoiceIn *hw, size_t *size);
     void   (*put_buffer_in)(HWVoiceIn *hw, void *buf, size_t size);
     void   (*enable_in)(HWVoiceIn *hw, bool enable);
     void   (*volume_in)(HWVoiceIn *hw, Volume *vol);
 };
 
+void audio_generic_run_buffer_in(HWVoiceIn *hw);
 void *audio_generic_get_buffer_in(HWVoiceIn *hw, size_t *size);
 void audio_generic_put_buffer_in(HWVoiceIn *hw, void *buf, size_t size);
 void audio_generic_run_buffer_out(HWVoiceOut *hw);
diff --git a/audio/audio_legacy.c b/audio/audio_legacy.c
index ffdbd0bcce..0fe827b057 100644
--- a/audio/audio_legacy.c
+++ b/audio/audio_legacy.c
@@ -286,7 +286,8 @@ static void handle_sdl(Audiodev *dev)
 {
     /* SDL is output only */
     get_samples_to_usecs("QEMU_SDL_SAMPLES", &dev->u.sdl.out->buffer_length,
-                         &dev->u.sdl.out->has_buffer_length, dev->u.sdl.out);
+        &dev->u.sdl.out->has_buffer_length,
+        qapi_AudiodevSdlPerDirectionOptions_base(dev->u.sdl.out));
 }
 
 /* wav */
diff --git a/audio/audio_template.h b/audio/audio_template.h
index 8dd48ce14e..c6714946aa 100644
--- a/audio/audio_template.h
+++ b/audio/audio_template.h
@@ -47,8 +47,7 @@ static void glue(audio_init_nb_voices_, TYPE)(AudioState *s,
 #ifdef DAC
             dolog ("Driver `%s' does not support " NAME "\n", drv->name);
 #endif
-        }
-        else {
+        } else {
             dolog ("Driver `%s' does not support %d " NAME " voices, max %d\n",
                    drv->name,
                    glue (s->nb_hw_voices_, TYPE),
@@ -204,13 +203,13 @@ static void glue (audio_pcm_hw_gc_, TYPE) (HW **hwp)
 
     if (!hw->sw_head.lh_first) {
 #ifdef DAC
-        audio_detach_capture (hw);
+        audio_detach_capture(hw);
 #endif
-        QLIST_REMOVE (hw, entries);
-        glue (hw->pcm_ops->fini_, TYPE) (hw);
-        glue (s->nb_hw_voices_, TYPE) += 1;
-        glue (audio_pcm_hw_free_resources_ ,TYPE) (hw);
-        g_free (hw);
+        QLIST_REMOVE(hw, entries);
+        glue(hw->pcm_ops->fini_, TYPE) (hw);
+        glue(s->nb_hw_voices_, TYPE) += 1;
+        glue(audio_pcm_hw_free_resources_ , TYPE) (hw);
+        g_free(hw);
         *hwp = NULL;
     }
 }
@@ -337,7 +336,7 @@ AudiodevPerDirectionOptions *glue(audio_get_pdo_, TYPE)(Audiodev *dev)
     case AUDIODEV_DRIVER_PA:
         return qapi_AudiodevPaPerDirectionOptions_base(dev->u.pa.TYPE);
     case AUDIODEV_DRIVER_SDL:
-        return dev->u.sdl.TYPE;
+        return qapi_AudiodevSdlPerDirectionOptions_base(dev->u.sdl.TYPE);
     case AUDIODEV_DRIVER_SPICE:
         return dev->u.spice.TYPE;
     case AUDIODEV_DRIVER_WAV:
@@ -387,8 +386,7 @@ static SW *glue(audio_pcm_create_voice_pair_, TYPE)(
 
     if (pdo->fixed_settings) {
         hw_as = audiodev_to_audsettings(pdo);
-    }
-    else {
+    } else {
         hw_as = *as;
     }
 
@@ -498,8 +496,7 @@ SW *glue (AUD_open_, TYPE) (
         if (glue (audio_pcm_sw_init_, TYPE) (sw, hw, name, as)) {
             goto fail;
         }
-    }
-    else {
+    } else {
         sw = glue(audio_pcm_create_voice_pair_, TYPE)(s, name, as);
         if (!sw) {
             dolog ("Failed to create voice `%s'\n", name);
@@ -553,8 +550,7 @@ uint64_t glue (AUD_get_elapsed_usec_, TYPE) (SW *sw, QEMUAudioTimeStamp *ts)
 
     if (cur_ts >= old_ts) {
         delta = cur_ts - old_ts;
-    }
-    else {
+    } else {
         delta = UINT64_MAX - old_ts + cur_ts;
     }
 
diff --git a/audio/audio_win_int.c b/audio/audio_win_int.c
index b938fd667b..5ea8157dfc 100644
--- a/audio/audio_win_int.c
+++ b/audio/audio_win_int.c
@@ -5,6 +5,7 @@
 
 #define AUDIO_CAP "win-int"
 #include <windows.h>
+#include <mmreg.h>
 #include <mmsystem.h>
 
 #include "audio.h"
@@ -16,7 +17,6 @@ int waveformat_from_audio_settings (WAVEFORMATEX *wfx,
 {
     memset (wfx, 0, sizeof (*wfx));
 
-    wfx->wFormatTag = WAVE_FORMAT_PCM;
     wfx->nChannels = as->nchannels;
     wfx->nSamplesPerSec = as->freq;
     wfx->nAvgBytesPerSec = as->freq << (as->nchannels == 2);
@@ -26,11 +26,13 @@ int waveformat_from_audio_settings (WAVEFORMATEX *wfx,
     switch (as->fmt) {
     case AUDIO_FORMAT_S8:
     case AUDIO_FORMAT_U8:
+        wfx->wFormatTag = WAVE_FORMAT_PCM;
         wfx->wBitsPerSample = 8;
         break;
 
     case AUDIO_FORMAT_S16:
     case AUDIO_FORMAT_U16:
+        wfx->wFormatTag = WAVE_FORMAT_PCM;
         wfx->wBitsPerSample = 16;
         wfx->nAvgBytesPerSec <<= 1;
         wfx->nBlockAlign <<= 1;
@@ -38,13 +40,21 @@ int waveformat_from_audio_settings (WAVEFORMATEX *wfx,
 
     case AUDIO_FORMAT_S32:
     case AUDIO_FORMAT_U32:
+        wfx->wFormatTag = WAVE_FORMAT_PCM;
+        wfx->wBitsPerSample = 32;
+        wfx->nAvgBytesPerSec <<= 2;
+        wfx->nBlockAlign <<= 2;
+        break;
+
+    case AUDIO_FORMAT_F32:
+        wfx->wFormatTag = WAVE_FORMAT_IEEE_FLOAT;
         wfx->wBitsPerSample = 32;
         wfx->nAvgBytesPerSec <<= 2;
         wfx->nBlockAlign <<= 2;
         break;
 
     default:
-        dolog ("Internal logic error: Bad audio format %d\n", as->freq);
+        dolog("Internal logic error: Bad audio format %d\n", as->fmt);
         return -1;
     }
 
@@ -54,12 +64,6 @@ int waveformat_from_audio_settings (WAVEFORMATEX *wfx,
 int waveformat_to_audio_settings (WAVEFORMATEX *wfx,
                                   struct audsettings *as)
 {
-    if (wfx->wFormatTag != WAVE_FORMAT_PCM) {
-        dolog ("Invalid wave format, tag is not PCM, but %d\n",
-               wfx->wFormatTag);
-        return -1;
-    }
-
     if (!wfx->nSamplesPerSec) {
         dolog ("Invalid wave format, frequency is zero\n");
         return -1;
@@ -83,23 +87,42 @@ int waveformat_to_audio_settings (WAVEFORMATEX *wfx,
         return -1;
     }
 
-    switch (wfx->wBitsPerSample) {
-    case 8:
-        as->fmt = AUDIO_FORMAT_U8;
-        break;
-
-    case 16:
-        as->fmt = AUDIO_FORMAT_S16;
-        break;
-
-    case 32:
-        as->fmt = AUDIO_FORMAT_S32;
-        break;
-
-    default:
-        dolog ("Invalid wave format, bits per sample is not "
-               "8, 16 or 32, but %d\n",
-               wfx->wBitsPerSample);
+    if (wfx->wFormatTag == WAVE_FORMAT_PCM) {
+        switch (wfx->wBitsPerSample) {
+        case 8:
+            as->fmt = AUDIO_FORMAT_U8;
+            break;
+
+        case 16:
+            as->fmt = AUDIO_FORMAT_S16;
+            break;
+
+        case 32:
+            as->fmt = AUDIO_FORMAT_S32;
+            break;
+
+        default:
+            dolog("Invalid PCM wave format, bits per sample is not "
+                  "8, 16 or 32, but %d\n",
+                  wfx->wBitsPerSample);
+            return -1;
+        }
+    } else if (wfx->wFormatTag == WAVE_FORMAT_IEEE_FLOAT) {
+        switch (wfx->wBitsPerSample) {
+        case 32:
+            as->fmt = AUDIO_FORMAT_F32;
+            break;
+
+        default:
+            dolog("Invalid IEEE_FLOAT wave format, bits per sample is not "
+                  "32, but %d\n",
+                  wfx->wBitsPerSample);
+            return -1;
+        }
+    } else {
+        dolog("Invalid wave format, tag is not PCM and not IEEE_FLOAT, "
+              "but %d\n",
+              wfx->wFormatTag);
         return -1;
     }
 
diff --git a/audio/coreaudio.c b/audio/coreaudio.c
index 79a9d40bf8..b7c02e0e51 100644
--- a/audio/coreaudio.c
+++ b/audio/coreaudio.c
@@ -270,7 +270,7 @@ static void coreaudio_logstatus (OSStatus status)
 {
     const char *str = "BUG";
 
-    switch(status) {
+    switch (status) {
     case kAudioHardwareNoError:
         str = "kAudioHardwareNoError";
         break;
@@ -421,12 +421,12 @@ COREAUDIO_WRAPPER_FUNC(write, size_t, (HWVoiceOut *hw, void *buf, size_t size),
 /* callback to feed audiooutput buffer */
 static OSStatus audioDeviceIOProc(
     AudioDeviceID inDevice,
-    const AudioTimeStamp* inNow,
-    const AudioBufferList* inInputData,
-    const AudioTimeStamp* inInputTime,
-    AudioBufferList* outOutputData,
-    const AudioTimeStamp* inOutputTime,
-    void* hwptr)
+    const AudioTimeStamp *inNow,
+    const AudioBufferList *inInputData,
+    const AudioTimeStamp *inInputTime,
+    AudioBufferList *outOutputData,
+    const AudioTimeStamp *inOutputTime,
+    void *hwptr)
 {
     UInt32 frameCount, pending_frames;
     void *out = outOutputData->mBuffers[0].mData;
@@ -524,8 +524,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     } else if (frameRange.mMaximum < frames) {
         core->audioDevicePropertyBufferFrameSize = (UInt32) frameRange.mMaximum;
         dolog ("warning: Downsizing Buffer Frames to %f\n", frameRange.mMaximum);
-    }
-    else {
+    } else {
         core->audioDevicePropertyBufferFrameSize = frames;
     }
 
diff --git a/audio/dsound_template.h b/audio/dsound_template.h
index 9c5ce625ab..0678f2de38 100644
--- a/audio/dsound_template.h
+++ b/audio/dsound_template.h
@@ -205,7 +205,7 @@ static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
         NULL
         );
 #else
-    bd.dwFlags = DSBCAPS_STICKYFOCUS | DSBCAPS_GETCURRENTPOSITION2;
+    bd.dwFlags = DSBCAPS_GLOBALFOCUS | DSBCAPS_GETCURRENTPOSITION2;
     hr = IDirectSound_CreateSoundBuffer (
         s->dsound,
         &bd,
diff --git a/audio/dsoundaudio.c b/audio/dsoundaudio.c
index 4cdf19ab67..cfc79c129e 100644
--- a/audio/dsoundaudio.c
+++ b/audio/dsoundaudio.c
@@ -89,7 +89,9 @@ static void dsound_log_hresult (HRESULT hr)
 #endif
 #ifdef DSERR_ALLOCATED
     case DSERR_ALLOCATED:
-        str = "The request failed because resources, such as a priority level, were already in use by another caller";
+        str = "The request failed because resources, "
+              "such as a priority level, were already in use "
+              "by another caller";
         break;
 #endif
 #ifdef DSERR_ALREADYINITIALIZED
@@ -104,7 +106,8 @@ static void dsound_log_hresult (HRESULT hr)
 #endif
 #ifdef DSERR_BADSENDBUFFERGUID
     case DSERR_BADSENDBUFFERGUID:
-        str = "The GUID specified in an audiopath file does not match a valid mix-in buffer";
+        str = "The GUID specified in an audiopath file "
+              "does not match a valid mix-in buffer";
         break;
 #endif
 #ifdef DSERR_BUFFERLOST
@@ -114,26 +117,35 @@ static void dsound_log_hresult (HRESULT hr)
 #endif
 #ifdef DSERR_BUFFERTOOSMALL
     case DSERR_BUFFERTOOSMALL:
-        str = "The buffer size is not great enough to enable effects processing";
+        str = "The buffer size is not great enough to "
+              "enable effects processing";
         break;
 #endif
 #ifdef DSERR_CONTROLUNAVAIL
     case DSERR_CONTROLUNAVAIL:
-        str = "The buffer control (volume, pan, and so on) requested by the caller is not available. Controls must be specified when the buffer is created, using the dwFlags member of DSBUFFERDESC";
+        str = "The buffer control (volume, pan, and so on) "
+              "requested by the caller is not available. "
+              "Controls must be specified when the buffer is created, "
+              "using the dwFlags member of DSBUFFERDESC";
         break;
 #endif
 #ifdef DSERR_DS8_REQUIRED
     case DSERR_DS8_REQUIRED:
-        str = "A DirectSound object of class CLSID_DirectSound8 or later is required for the requested functionality. For more information, see IDirectSound8 Interface";
+        str = "A DirectSound object of class CLSID_DirectSound8 or later "
+              "is required for the requested functionality. "
+              "For more information, see IDirectSound8 Interface";
         break;
 #endif
 #ifdef DSERR_FXUNAVAILABLE
     case DSERR_FXUNAVAILABLE:
-        str = "The effects requested could not be found on the system, or they are in the wrong order or in the wrong location; for example, an effect expected in hardware was found in software";
+        str = "The effects requested could not be found on the system, "
+              "or they are in the wrong order or in the wrong location; "
+              "for example, an effect expected in hardware "
+              "was found in software";
         break;
 #endif
 #ifdef DSERR_GENERIC
-    case DSERR_GENERIC :
+    case DSERR_GENERIC:
         str = "An undetermined error occurred inside the DirectSound subsystem";
         break;
 #endif
@@ -154,7 +166,8 @@ static void dsound_log_hresult (HRESULT hr)
 #endif
 #ifdef DSERR_NODRIVER
     case DSERR_NODRIVER:
-        str = "No sound driver is available for use, or the given GUID is not a valid DirectSound device ID";
+        str = "No sound driver is available for use, "
+              "or the given GUID is not a valid DirectSound device ID";
         break;
 #endif
 #ifdef DSERR_NOINTERFACE
@@ -169,12 +182,14 @@ static void dsound_log_hresult (HRESULT hr)
 #endif
 #ifdef DSERR_OTHERAPPHASPRIO
     case DSERR_OTHERAPPHASPRIO:
-        str = "Another application has a higher priority level, preventing this call from succeeding";
+        str = "Another application has a higher priority level, "
+              "preventing this call from succeeding";
         break;
 #endif
 #ifdef DSERR_OUTOFMEMORY
     case DSERR_OUTOFMEMORY:
-        str = "The DirectSound subsystem could not allocate sufficient memory to complete the caller's request";
+        str = "The DirectSound subsystem could not allocate "
+               "sufficient memory to complete the caller's request";
         break;
 #endif
 #ifdef DSERR_PRIOLEVELNEEDED
@@ -189,7 +204,9 @@ static void dsound_log_hresult (HRESULT hr)
 #endif
 #ifdef DSERR_UNINITIALIZED
     case DSERR_UNINITIALIZED:
-        str = "The Initialize method has not been called or has not been called successfully before other methods were called";
+        str = "The Initialize method has not been called "
+              "or has not been called successfully "
+              "before other methods were called";
         break;
 #endif
 #ifdef DSERR_UNSUPPORTED
@@ -198,7 +215,7 @@ static void dsound_log_hresult (HRESULT hr)
         break;
 #endif
     default:
-        AUD_log (AUDIO_CAP, "Reason: Unknown (HRESULT %#lx)\n", hr);
+        AUD_log (AUDIO_CAP, "Reason: Unknown (HRESULT 0x%lx)\n", hr);
         return;
     }
 
@@ -342,12 +359,12 @@ static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
     dsound_unlock_out (dsb, p1, p2, blen1, blen2);
 }
 
-static int dsound_open (dsound *s)
+static int dsound_set_cooperative_level(dsound *s)
 {
     HRESULT hr;
     HWND hwnd;
 
-    hwnd = GetForegroundWindow ();
+    hwnd = GetDesktopWindow();
     hr = IDirectSound_SetCooperativeLevel (
         s->dsound,
         hwnd,
@@ -404,8 +421,7 @@ static void dsound_enable_out(HWVoiceOut *hw, bool enable)
                 dsound_logerr (hr, "Could not stop playing buffer\n");
                 return;
             }
-        }
-        else {
+        } else {
             dolog ("warning: Voice is not playing\n");
         }
     }
@@ -509,8 +525,7 @@ static void dsound_enable_in(HWVoiceIn *hw, bool enable)
                 dsound_logerr (hr, "Could not stop capturing\n");
                 return;
             }
-        }
-        else {
+        } else {
             dolog ("warning: Voice is not capturing\n");
         }
     }
@@ -659,8 +674,7 @@ static void *dsound_audio_init(Audiodev *dev)
         );
     if (FAILED (hr)) {
         dsound_logerr (hr, "Could not create DirectSoundCapture instance\n");
-    }
-    else {
+    } else {
         hr = IDirectSoundCapture_Initialize (s->dsound_capture, NULL);
         if (FAILED (hr)) {
             dsound_logerr (hr, "Could not initialize DirectSoundCapture\n");
@@ -673,7 +687,7 @@ static void *dsound_audio_init(Audiodev *dev)
         }
     }
 
-    err = dsound_open (s);
+    err = dsound_set_cooperative_level(s);
     if (err) {
         dsound_audio_fini (s);
         return NULL;
diff --git a/audio/jackaudio.c b/audio/jackaudio.c
index 3b7c18443d..3031c4e29b 100644
--- a/audio/jackaudio.c
+++ b/audio/jackaudio.c
@@ -277,7 +277,7 @@ static int qjack_process(jack_nframes_t nframes, void *arg)
         if (likely(c->enabled)) {
             qjack_buffer_read_l(&c->fifo, buffers, nframes);
         } else {
-            for(int i = 0; i < c->nchannels; ++i) {
+            for (int i = 0; i < c->nchannels; ++i) {
                 memset(buffers[i], 0, nframes * sizeof(float));
             }
         }
@@ -657,6 +657,7 @@ static struct audio_pcm_ops jack_pcm_ops = {
     .init_in        = qjack_init_in,
     .fini_in        = qjack_fini_in,
     .read           = qjack_read,
+    .run_buffer_in  = audio_generic_run_buffer_in,
     .enable_in      = qjack_enable_in
 };
 
diff --git a/audio/noaudio.c b/audio/noaudio.c
index 05798ea210..aac87dbc93 100644
--- a/audio/noaudio.c
+++ b/audio/noaudio.c
@@ -124,6 +124,7 @@ static struct audio_pcm_ops no_pcm_ops = {
     .init_in  = no_init_in,
     .fini_in  = no_fini_in,
     .read     = no_read,
+    .run_buffer_in = audio_generic_run_buffer_in,
     .enable_in = no_enable_in
 };
 
diff --git a/audio/ossaudio.c b/audio/ossaudio.c
index a7dcaa31ad..60eff66424 100644
--- a/audio/ossaudio.c
+++ b/audio/ossaudio.c
@@ -142,16 +142,14 @@ static int aud_to_ossfmt (AudioFormat fmt, int endianness)
     case AUDIO_FORMAT_S16:
         if (endianness) {
             return AFMT_S16_BE;
-        }
-        else {
+        } else {
             return AFMT_S16_LE;
         }
 
     case AUDIO_FORMAT_U16:
         if (endianness) {
             return AFMT_U16_BE;
-        }
-        else {
+        } else {
             return AFMT_U16_LE;
         }
 
@@ -542,16 +540,14 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
             int trig = 0;
             if (ioctl (fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
                 oss_logerr (errno, "SNDCTL_DSP_SETTRIGGER 0 failed\n");
-            }
-            else {
+            } else {
                 trig = PCM_ENABLE_OUTPUT;
                 if (ioctl (fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
                     oss_logerr (
                         errno,
                         "SNDCTL_DSP_SETTRIGGER PCM_ENABLE_OUTPUT failed\n"
                         );
-                }
-                else {
+                } else {
                     oss->mmapped = 1;
                 }
             }
@@ -762,6 +758,7 @@ static struct audio_pcm_ops oss_pcm_ops = {
     .init_in  = oss_init_in,
     .fini_in  = oss_fini_in,
     .read     = oss_read,
+    .run_buffer_in = audio_generic_run_buffer_in,
     .enable_in = oss_enable_in
 };
 
diff --git a/audio/paaudio.c b/audio/paaudio.c
index b052084698..c97b22e970 100644
--- a/audio/paaudio.c
+++ b/audio/paaudio.c
@@ -207,19 +207,34 @@ static void *qpa_get_buffer_out(HWVoiceOut *hw, size_t *size)
     PAVoiceOut *p = (PAVoiceOut *) hw;
     PAConnection *c = p->g->conn;
     void *ret;
+    size_t l;
     int r;
 
     pa_threaded_mainloop_lock(c->mainloop);
 
     CHECK_DEAD_GOTO(c, p->stream, unlock_and_fail,
                     "pa_threaded_mainloop_lock failed\n");
+    if (pa_stream_get_state(p->stream) != PA_STREAM_READY) {
+        /* wait for stream to become ready */
+        l = 0;
+        ret = NULL;
+        goto unlock;
+    }
+
+    l = pa_stream_writable_size(p->stream);
+    CHECK_SUCCESS_GOTO(c, l != (size_t) -1, unlock_and_fail,
+                       "pa_stream_writable_size failed\n");
 
     *size = -1;
     r = pa_stream_begin_write(p->stream, &ret, size);
     CHECK_SUCCESS_GOTO(c, r >= 0, unlock_and_fail,
                        "pa_stream_begin_write failed\n");
 
+unlock:
     pa_threaded_mainloop_unlock(c->mainloop);
+    if (*size > l) {
+        *size = l;
+    }
     return ret;
 
 unlock_and_fail:
@@ -228,6 +243,28 @@ unlock_and_fail:
     return NULL;
 }
 
+static size_t qpa_put_buffer_out(HWVoiceOut *hw, void *data, size_t length)
+{
+    PAVoiceOut *p = (PAVoiceOut *)hw;
+    PAConnection *c = p->g->conn;
+    int r;
+
+    pa_threaded_mainloop_lock(c->mainloop);
+
+    CHECK_DEAD_GOTO(c, p->stream, unlock_and_fail,
+                    "pa_threaded_mainloop_lock failed\n");
+
+    r = pa_stream_write(p->stream, data, length, NULL, 0LL, PA_SEEK_RELATIVE);
+    CHECK_SUCCESS_GOTO(c, r >= 0, unlock_and_fail, "pa_stream_write failed\n");
+
+    pa_threaded_mainloop_unlock(c->mainloop);
+    return length;
+
+unlock_and_fail:
+    pa_threaded_mainloop_unlock(c->mainloop);
+    return 0;
+}
+
 static size_t qpa_write(HWVoiceOut *hw, void *data, size_t length)
 {
     PAVoiceOut *p = (PAVoiceOut *) hw;
@@ -239,6 +276,11 @@ static size_t qpa_write(HWVoiceOut *hw, void *data, size_t length)
 
     CHECK_DEAD_GOTO(c, p->stream, unlock_and_fail,
                     "pa_threaded_mainloop_lock failed\n");
+    if (pa_stream_get_state(p->stream) != PA_STREAM_READY) {
+        /* wait for stream to become ready */
+        l = 0;
+        goto unlock;
+    }
 
     l = pa_stream_writable_size(p->stream);
 
@@ -252,6 +294,7 @@ static size_t qpa_write(HWVoiceOut *hw, void *data, size_t length)
     r = pa_stream_write(p->stream, data, l, NULL, 0LL, PA_SEEK_RELATIVE);
     CHECK_SUCCESS_GOTO(c, r >= 0, unlock_and_fail, "pa_stream_write failed\n");
 
+unlock:
     pa_threaded_mainloop_unlock(c->mainloop);
     return l;
 
@@ -437,7 +480,7 @@ static pa_stream *qpa_simple_new (
     }
 
     if (r < 0) {
-      goto fail;
+        goto fail;
     }
 
     pa_threaded_mainloop_unlock(c->mainloop);
@@ -474,7 +517,8 @@ static int qpa_init_out(HWVoiceOut *hw, struct audsettings *as,
     ss.rate = as->freq;
 
     ba.tlength = pa_usec_to_bytes(ppdo->latency, &ss);
-    ba.minreq = -1;
+    ba.minreq = pa_usec_to_bytes(MIN(ppdo->latency >> 2,
+                                     (g->dev->timer_period >> 2) * 3), &ss);
     ba.maxlength = -1;
     ba.prebuf = -1;
 
@@ -495,9 +539,12 @@ static int qpa_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     audio_pcm_init_info (&hw->info, &obt_as);
+    /*
+     * This is wrong. hw->samples counts in frames. hw->samples will be
+     * number of channels times larger than expected.
+     */
     hw->samples = audio_buffer_samples(
-        qapi_AudiodevPaPerDirectionOptions_base(ppdo),
-        &obt_as, ppdo->buffer_length);
+        qapi_AudiodevPaPerDirectionOptions_base(ppdo), &obt_as, 46440);
 
     return 0;
 
@@ -521,8 +568,9 @@ static int qpa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
     ss.channels = as->nchannels;
     ss.rate = as->freq;
 
-    ba.fragsize = pa_usec_to_bytes(ppdo->latency, &ss);
-    ba.maxlength = pa_usec_to_bytes(ppdo->latency * 2, &ss);
+    ba.fragsize = pa_usec_to_bytes((g->dev->timer_period >> 1) * 3, &ss);
+    ba.maxlength = pa_usec_to_bytes(
+        MAX(ppdo->latency, g->dev->timer_period * 3), &ss);
     ba.minreq = -1;
     ba.prebuf = -1;
 
@@ -543,9 +591,12 @@ static int qpa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
     }
 
     audio_pcm_init_info (&hw->info, &obt_as);
+    /*
+     * This is wrong. hw->samples counts in frames. hw->samples will be
+     * number of channels times larger than expected.
+     */
     hw->samples = audio_buffer_samples(
-        qapi_AudiodevPaPerDirectionOptions_base(ppdo),
-        &obt_as, ppdo->buffer_length);
+        qapi_AudiodevPaPerDirectionOptions_base(ppdo), &obt_as, 46440);
 
     return 0;
 
@@ -695,10 +746,6 @@ static void qpa_volume_in(HWVoiceIn *hw, Volume *vol)
 static int qpa_validate_per_direction_opts(Audiodev *dev,
                                            AudiodevPaPerDirectionOptions *pdo)
 {
-    if (!pdo->has_buffer_length) {
-        pdo->has_buffer_length = true;
-        pdo->buffer_length = 46440;
-    }
     if (!pdo->has_latency) {
         pdo->has_latency = true;
         pdo->latency = 15000;
@@ -861,7 +908,7 @@ static struct audio_pcm_ops qpa_pcm_ops = {
     .fini_out = qpa_fini_out,
     .write    = qpa_write,
     .get_buffer_out = qpa_get_buffer_out,
-    .put_buffer_out = qpa_write, /* pa handles it */
+    .put_buffer_out = qpa_put_buffer_out,
     .volume_out = qpa_volume_out,
 
     .init_in  = qpa_init_in,
diff --git a/audio/sdlaudio.c b/audio/sdlaudio.c
index 21b7a0484b..c68c62a3e4 100644
--- a/audio/sdlaudio.c
+++ b/audio/sdlaudio.c
@@ -41,15 +41,19 @@
 
 typedef struct SDLVoiceOut {
     HWVoiceOut hw;
+    int exit;
+    int initialized;
+    Audiodev *dev;
+    SDL_AudioDeviceID devid;
 } SDLVoiceOut;
 
-static struct SDLAudioState {
+typedef struct SDLVoiceIn {
+    HWVoiceIn hw;
     int exit;
     int initialized;
-    bool driver_created;
     Audiodev *dev;
-} glob_sdl;
-typedef struct SDLAudioState SDLAudioState;
+    SDL_AudioDeviceID devid;
+} SDLVoiceIn;
 
 static void GCC_FMT_ATTR (1, 2) sdl_logerr (const char *fmt, ...)
 {
@@ -155,9 +159,10 @@ static int sdl_to_audfmt(int sdlfmt, AudioFormat *fmt, int *endianness)
     return 0;
 }
 
-static int sdl_open (SDL_AudioSpec *req, SDL_AudioSpec *obt)
+static SDL_AudioDeviceID sdl_open(SDL_AudioSpec *req, SDL_AudioSpec *obt,
+                                  int rec)
 {
-    int status;
+    SDL_AudioDeviceID devid;
 #ifndef _WIN32
     int err;
     sigset_t new, old;
@@ -166,18 +171,19 @@ static int sdl_open (SDL_AudioSpec *req, SDL_AudioSpec *obt)
     err = sigfillset (&new);
     if (err) {
         dolog ("sdl_open: sigfillset failed: %s\n", strerror (errno));
-        return -1;
+        return 0;
     }
     err = pthread_sigmask (SIG_BLOCK, &new, &old);
     if (err) {
         dolog ("sdl_open: pthread_sigmask failed: %s\n", strerror (err));
-        return -1;
+        return 0;
     }
 #endif
 
-    status = SDL_OpenAudio (req, obt);
-    if (status) {
-        sdl_logerr ("SDL_OpenAudio failed\n");
+    devid = SDL_OpenAudioDevice(NULL, rec, req, obt, 0);
+    if (!devid) {
+        sdl_logerr("SDL_OpenAudioDevice for %s failed\n",
+                   rec ? "recording" : "playback");
     }
 
 #ifndef _WIN32
@@ -190,112 +196,175 @@ static int sdl_open (SDL_AudioSpec *req, SDL_AudioSpec *obt)
         exit (EXIT_FAILURE);
     }
 #endif
-    return status;
+    return devid;
 }
 
-static void sdl_close (SDLAudioState *s)
+static void sdl_close_out(SDLVoiceOut *sdl)
 {
-    if (s->initialized) {
-        SDL_LockAudio();
-        s->exit = 1;
-        SDL_UnlockAudio();
-        SDL_PauseAudio (1);
-        SDL_CloseAudio ();
-        s->initialized = 0;
+    if (sdl->initialized) {
+        SDL_LockAudioDevice(sdl->devid);
+        sdl->exit = 1;
+        SDL_UnlockAudioDevice(sdl->devid);
+        SDL_PauseAudioDevice(sdl->devid, 1);
+        sdl->initialized = 0;
+    }
+    if (sdl->devid) {
+        SDL_CloseAudioDevice(sdl->devid);
+        sdl->devid = 0;
     }
 }
 
-static void sdl_callback (void *opaque, Uint8 *buf, int len)
+static void sdl_callback_out(void *opaque, Uint8 *buf, int len)
 {
     SDLVoiceOut *sdl = opaque;
-    SDLAudioState *s = &glob_sdl;
     HWVoiceOut *hw = &sdl->hw;
 
-    if (s->exit) {
-        return;
-    }
+    if (!sdl->exit) {
 
-    /* dolog ("in callback samples=%zu live=%zu\n", samples, sdl->live); */
+        /* dolog("callback_out: len=%d avail=%zu\n", len, hw->pending_emul); */
 
-    while (hw->pending_emul && len) {
-        size_t write_len;
-        ssize_t start = ((ssize_t) hw->pos_emul) - hw->pending_emul;
-        if (start < 0) {
-            start += hw->size_emul;
-        }
-        assert(start >= 0 && start < hw->size_emul);
+        while (hw->pending_emul && len) {
+            size_t write_len;
+            ssize_t start = (ssize_t)hw->pos_emul - hw->pending_emul;
+            if (start < 0) {
+                start += hw->size_emul;
+            }
+            assert(start >= 0 && start < hw->size_emul);
 
-        write_len = MIN(MIN(hw->pending_emul, len),
-                        hw->size_emul - start);
+            write_len = MIN(MIN(hw->pending_emul, len),
+                            hw->size_emul - start);
 
-        memcpy(buf, hw->buf_emul + start, write_len);
-        hw->pending_emul -= write_len;
-        len -= write_len;
-        buf += write_len;
+            memcpy(buf, hw->buf_emul + start, write_len);
+            hw->pending_emul -= write_len;
+            len -= write_len;
+            buf += write_len;
+        }
     }
 
     /* clear remaining buffer that we couldn't fill with data */
     if (len) {
-        memset(buf, 0, len);
+        audio_pcm_info_clear_buf(&hw->info, buf,
+                                 len / hw->info.bytes_per_frame);
+    }
+}
+
+static void sdl_close_in(SDLVoiceIn *sdl)
+{
+    if (sdl->initialized) {
+        SDL_LockAudioDevice(sdl->devid);
+        sdl->exit = 1;
+        SDL_UnlockAudioDevice(sdl->devid);
+        SDL_PauseAudioDevice(sdl->devid, 1);
+        sdl->initialized = 0;
+    }
+    if (sdl->devid) {
+        SDL_CloseAudioDevice(sdl->devid);
+        sdl->devid = 0;
+    }
+}
+
+static void sdl_callback_in(void *opaque, Uint8 *buf, int len)
+{
+    SDLVoiceIn *sdl = opaque;
+    HWVoiceIn *hw = &sdl->hw;
+
+    if (sdl->exit) {
+        return;
+    }
+
+    /* dolog("callback_in: len=%d pending=%zu\n", len, hw->pending_emul); */
+
+    while (hw->pending_emul < hw->size_emul && len) {
+        size_t read_len = MIN(len, MIN(hw->size_emul - hw->pos_emul,
+                                       hw->size_emul - hw->pending_emul));
+
+        memcpy(hw->buf_emul + hw->pos_emul, buf, read_len);
+
+        hw->pending_emul += read_len;
+        hw->pos_emul = (hw->pos_emul + read_len) % hw->size_emul;
+        len -= read_len;
+        buf += read_len;
     }
 }
 
-#define SDL_WRAPPER_FUNC(name, ret_type, args_decl, args, fail, unlock) \
-    static ret_type glue(sdl_, name)args_decl                           \
-    {                                                                   \
-        ret_type ret;                                                   \
-                                                                        \
-        SDL_LockAudio();                                                \
-                                                                        \
-        ret = glue(audio_generic_, name)args;                           \
-                                                                        \
-        SDL_UnlockAudio();                                              \
-        return ret;                                                     \
+#define SDL_WRAPPER_FUNC(name, ret_type, args_decl, args, dir) \
+    static ret_type glue(sdl_, name)args_decl                  \
+    {                                                          \
+        ret_type ret;                                          \
+        glue(SDLVoice, dir) *sdl = (glue(SDLVoice, dir) *)hw;  \
+                                                               \
+        SDL_LockAudioDevice(sdl->devid);                       \
+        ret = glue(audio_generic_, name)args;                  \
+        SDL_UnlockAudioDevice(sdl->devid);                     \
+                                                               \
+        return ret;                                            \
+    }
+
+#define SDL_WRAPPER_VOID_FUNC(name, args_decl, args, dir)      \
+    static void glue(sdl_, name)args_decl                      \
+    {                                                          \
+        glue(SDLVoice, dir) *sdl = (glue(SDLVoice, dir) *)hw;  \
+                                                               \
+        SDL_LockAudioDevice(sdl->devid);                       \
+        glue(audio_generic_, name)args;                        \
+        SDL_UnlockAudioDevice(sdl->devid);                     \
     }
 
 SDL_WRAPPER_FUNC(get_buffer_out, void *, (HWVoiceOut *hw, size_t *size),
-                 (hw, size), *size = 0, sdl_unlock)
+                 (hw, size), Out)
 SDL_WRAPPER_FUNC(put_buffer_out, size_t,
-                 (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size),
-                 /*nothing*/, sdl_unlock_and_post)
+                 (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size), Out)
 SDL_WRAPPER_FUNC(write, size_t,
-                 (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size),
-                 /*nothing*/, sdl_unlock_and_post)
-
+                 (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size), Out)
+SDL_WRAPPER_FUNC(read, size_t, (HWVoiceIn *hw, void *buf, size_t size),
+                 (hw, buf, size), In)
+SDL_WRAPPER_FUNC(get_buffer_in, void *, (HWVoiceIn *hw, size_t *size),
+                 (hw, size), In)
+SDL_WRAPPER_VOID_FUNC(put_buffer_in, (HWVoiceIn *hw, void *buf, size_t size),
+                      (hw, buf, size), In)
 #undef SDL_WRAPPER_FUNC
+#undef SDL_WRAPPER_VOID_FUNC
 
-static void sdl_fini_out (HWVoiceOut *hw)
+static void sdl_fini_out(HWVoiceOut *hw)
 {
-    (void) hw;
+    SDLVoiceOut *sdl = (SDLVoiceOut *)hw;
 
-    sdl_close (&glob_sdl);
+    sdl_close_out(sdl);
 }
 
 static int sdl_init_out(HWVoiceOut *hw, struct audsettings *as,
                         void *drv_opaque)
 {
-    SDLVoiceOut *sdl = (SDLVoiceOut *) hw;
-    SDLAudioState *s = &glob_sdl;
+    SDLVoiceOut *sdl = (SDLVoiceOut *)hw;
     SDL_AudioSpec req, obt;
     int endianness;
     int err;
     AudioFormat effective_fmt;
+    Audiodev *dev = drv_opaque;
+    AudiodevSdlPerDirectionOptions *spdo = dev->u.sdl.out;
     struct audsettings obt_as;
 
     req.freq = as->freq;
     req.format = aud_to_sdlfmt (as->fmt);
     req.channels = as->nchannels;
-    req.samples = audio_buffer_samples(s->dev->u.sdl.out, as, 11610);
-    req.callback = sdl_callback;
+    /*
+     * This is wrong. SDL samples are QEMU frames. The buffer size will be
+     * the requested buffer size multiplied by the number of channels.
+     */
+    req.samples = audio_buffer_samples(
+        qapi_AudiodevSdlPerDirectionOptions_base(spdo), as, 11610);
+    req.callback = sdl_callback_out;
     req.userdata = sdl;
 
-    if (sdl_open (&req, &obt)) {
+    sdl->dev = dev;
+    sdl->devid = sdl_open(&req, &obt, 0);
+    if (!sdl->devid) {
         return -1;
     }
 
     err = sdl_to_audfmt(obt.format, &effective_fmt, &endianness);
     if (err) {
-        sdl_close (s);
+        sdl_close_out(sdl);
         return -1;
     }
 
@@ -305,44 +374,97 @@ static int sdl_init_out(HWVoiceOut *hw, struct audsettings *as,
     obt_as.endianness = endianness;
 
     audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = obt.samples;
+    hw->samples = (spdo->has_buffer_count ? spdo->buffer_count : 4) *
+        obt.samples;
 
-    s->initialized = 1;
-    s->exit = 0;
-    SDL_PauseAudio (0);
+    sdl->initialized = 1;
+    sdl->exit = 0;
     return 0;
 }
 
 static void sdl_enable_out(HWVoiceOut *hw, bool enable)
 {
-    SDL_PauseAudio(!enable);
+    SDLVoiceOut *sdl = (SDLVoiceOut *)hw;
+
+    SDL_PauseAudioDevice(sdl->devid, !enable);
 }
 
-static void *sdl_audio_init(Audiodev *dev)
+static void sdl_fini_in(HWVoiceIn *hw)
 {
-    SDLAudioState *s = &glob_sdl;
-    if (s->driver_created) {
-        sdl_logerr("Can't create multiple sdl backends\n");
-        return NULL;
+    SDLVoiceIn *sdl = (SDLVoiceIn *)hw;
+
+    sdl_close_in(sdl);
+}
+
+static int sdl_init_in(HWVoiceIn *hw, audsettings *as, void *drv_opaque)
+{
+    SDLVoiceIn *sdl = (SDLVoiceIn *)hw;
+    SDL_AudioSpec req, obt;
+    int endianness;
+    int err;
+    AudioFormat effective_fmt;
+    Audiodev *dev = drv_opaque;
+    AudiodevSdlPerDirectionOptions *spdo = dev->u.sdl.in;
+    struct audsettings obt_as;
+
+    req.freq = as->freq;
+    req.format = aud_to_sdlfmt(as->fmt);
+    req.channels = as->nchannels;
+    /* SDL samples are QEMU frames */
+    req.samples = audio_buffer_frames(
+        qapi_AudiodevSdlPerDirectionOptions_base(spdo), as, 11610);
+    req.callback = sdl_callback_in;
+    req.userdata = sdl;
+
+    sdl->dev = dev;
+    sdl->devid = sdl_open(&req, &obt, 1);
+    if (!sdl->devid) {
+        return -1;
     }
 
+    err = sdl_to_audfmt(obt.format, &effective_fmt, &endianness);
+    if (err) {
+        sdl_close_in(sdl);
+        return -1;
+    }
+
+    obt_as.freq = obt.freq;
+    obt_as.nchannels = obt.channels;
+    obt_as.fmt = effective_fmt;
+    obt_as.endianness = endianness;
+
+    audio_pcm_init_info(&hw->info, &obt_as);
+    hw->samples = (spdo->has_buffer_count ? spdo->buffer_count : 4) *
+        obt.samples;
+    hw->size_emul = hw->samples * hw->info.bytes_per_frame;
+    hw->buf_emul = g_malloc(hw->size_emul);
+    hw->pos_emul = hw->pending_emul = 0;
+
+    sdl->initialized = 1;
+    sdl->exit = 0;
+    return 0;
+}
+
+static void sdl_enable_in(HWVoiceIn *hw, bool enable)
+{
+    SDLVoiceIn *sdl = (SDLVoiceIn *)hw;
+
+    SDL_PauseAudioDevice(sdl->devid, !enable);
+}
+
+static void *sdl_audio_init(Audiodev *dev)
+{
     if (SDL_InitSubSystem (SDL_INIT_AUDIO)) {
         sdl_logerr ("SDL failed to initialize audio subsystem\n");
         return NULL;
     }
 
-    s->driver_created = true;
-    s->dev = dev;
-    return s;
+    return dev;
 }
 
 static void sdl_audio_fini (void *opaque)
 {
-    SDLAudioState *s = opaque;
-    sdl_close (s);
     SDL_QuitSubSystem (SDL_INIT_AUDIO);
-    s->driver_created = false;
-    s->dev = NULL;
 }
 
 static struct audio_pcm_ops sdl_pcm_ops = {
@@ -355,6 +477,15 @@ static struct audio_pcm_ops sdl_pcm_ops = {
   /* wrapper for audio_generic_put_buffer_out */
     .put_buffer_out = sdl_put_buffer_out,
     .enable_out = sdl_enable_out,
+    .init_in = sdl_init_in,
+    .fini_in = sdl_fini_in,
+  /* wrapper for audio_generic_read */
+    .read = sdl_read,
+  /* wrapper for audio_generic_get_buffer_in */
+    .get_buffer_in = sdl_get_buffer_in,
+  /* wrapper for audio_generic_put_buffer_in */
+    .put_buffer_in = sdl_put_buffer_in,
+    .enable_in = sdl_enable_in,
 };
 
 static struct audio_driver sdl_audio_driver = {
@@ -364,10 +495,10 @@ static struct audio_driver sdl_audio_driver = {
     .fini           = sdl_audio_fini,
     .pcm_ops        = &sdl_pcm_ops,
     .can_be_default = 1,
-    .max_voices_out = 1,
-    .max_voices_in  = 0,
-    .voice_size_out = sizeof (SDLVoiceOut),
-    .voice_size_in  = 0
+    .max_voices_out = INT_MAX,
+    .max_voices_in  = INT_MAX,
+    .voice_size_out = sizeof(SDLVoiceOut),
+    .voice_size_in  = sizeof(SDLVoiceIn),
 };
 
 static void register_audio_sdl(void)
diff --git a/audio/spiceaudio.c b/audio/spiceaudio.c
index 8967cca129..999bfbde47 100644
--- a/audio/spiceaudio.c
+++ b/audio/spiceaudio.c
@@ -293,6 +293,7 @@ static struct audio_pcm_ops audio_callbacks = {
     .init_in  = line_in_init,
     .fini_in  = line_in_fini,
     .read     = line_in_read,
+    .run_buffer_in = audio_generic_run_buffer_in,
     .enable_in = line_in_enable,
 #if ((SPICE_INTERFACE_RECORD_MAJOR >= 2) && (SPICE_INTERFACE_RECORD_MINOR >= 2))
     .volume_in = line_in_volume,
diff --git a/qapi/audio.json b/qapi/audio.json
index 072ed79def..9cba0df8a4 100644
--- a/qapi/audio.json
+++ b/qapi/audio.json
@@ -302,6 +302,37 @@
     '*server': 'str' } }
 
 ##
+# @AudiodevSdlPerDirectionOptions:
+#
+# Options of the SDL audio backend that are used for both playback and
+# recording.
+#
+# @buffer-count: number of buffers (default 4)
+#
+# Since: 6.0
+##
+{ 'struct': 'AudiodevSdlPerDirectionOptions',
+  'base': 'AudiodevPerDirectionOptions',
+  'data': {
+    '*buffer-count': 'uint32' } }
+
+##
+# @AudiodevSdlOptions:
+#
+# Options of the SDL audio backend.
+#
+# @in: options of the recording stream
+#
+# @out: options of the playback stream
+#
+# Since: 6.0
+##
+{ 'struct': 'AudiodevSdlOptions',
+  'data': {
+    '*in':  'AudiodevSdlPerDirectionOptions',
+    '*out': 'AudiodevSdlPerDirectionOptions' } }
+
+##
 # @AudiodevWavOptions:
 #
 # Options of the wav audio backend.
@@ -385,6 +416,6 @@
     'jack':      'AudiodevJackOptions',
     'oss':       'AudiodevOssOptions',
     'pa':        'AudiodevPaOptions',
-    'sdl':       'AudiodevGenericOptions',
+    'sdl':       'AudiodevSdlOptions',
     'spice':     'AudiodevGenericOptions',
     'wav':       'AudiodevWavOptions' } }
diff --git a/qemu-options.hx b/qemu-options.hx
index 05fe35ceb6..9dc90ffbfb 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -588,6 +588,7 @@ DEF("audiodev", HAS_ARG, QEMU_OPTION_audiodev,
 #endif
 #ifdef CONFIG_AUDIO_SDL
     "-audiodev sdl,id=id[,prop[=value][,...]]\n"
+    "                in|out.buffer-count= number of buffers\n"
 #endif
 #ifdef CONFIG_SPICE
     "-audiodev spice,id=id[,prop[=value][,...]]\n"
@@ -745,7 +746,12 @@ SRST
 ``-audiodev sdl,id=id[,prop[=value][,...]]``
     Creates a backend using SDL. This backend is available on most
     systems, but you should use your platform's native backend if
-    possible. This backend has no backend specific properties.
+    possible.
+
+    SDL specific options are:
+
+    ``in|out.buffer-count=count``
+        Sets the count of the buffers.
 
 ``-audiodev spice,id=id[,prop[=value][,...]]``
     Creates a backend that sends audio through SPICE. This backend