ALSA: pcm: oss: annotate data-races around runtime->state
PATCH 1/1 ALSA: pcm: oss: annotate data-races around runtime->state
__snd_pcm_set_state() writes runtime->state under the PCM stream lock:
runtime->state = state;
However, the OSS I/O functions snd_pcm_oss_write3(), snd_pcm_oss_read3(), snd_pcm_oss_writev3() and snd_pcm_oss_readv3() read runtime->state without holding the stream lock, only holding oss.params_lock (a different mutex that does not synchronize with the stream lock):
if (runtime->state == SNDRV_PCM_STATE_XRUN || ...)
Since __snd_pcm_set_state() is called from IRQ context (e.g., snd_pcm_period_elapsed -> snd_pcm_update_state -> __snd_pcm_xrun -> snd_pcm_stop -> snd_pcm_post_stop) while the OSS read/write paths run in process context, these are concurrent accesses that constitute a data race.
The code handles stale reads gracefully through its retry loop (re-checking after __snd_pcm_lib_xfer returns -EPIPE), so the race is not harmful under simple interleaving. However, plain C accesses are formally undefined under LKMM, and without READ_ONCE the compiler is free to fuse or cache the loads across loop iterations.
Add WRITE_ONCE() in __snd_pcm_set_state() for the write side and READ_ONCE() on all lockless reads of runtime->state in the four OSS I/O functions.
--- include/sound/pcm.h | 2 +- sound/core/oss/pcm_oss.c | 34 +++++++++++++++++----------------- 2 files changed, 18 insertions(+), 18 deletions(-)
include/sound/pcm.h +1 -1
@@ -725,7 +725,7 @@ static inline int snd_pcm_running(struct snd_pcm_substream *substream)static inline void __snd_pcm_set_state (struct snd_pcm_runtime *runtime,snd_pcm_state_t state) { - runtime->state = state; +WRITE_ONCE (runtime->state, state); runtime->status->state = state;/* copy for mmap */ }
sound/core/oss/pcm_oss.c +17 -17
@@ -1229,12 +1229,12 @@ snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, conststruct snd_pcm_runtime *runtime = substream->runtime;int ret;while (1 ) { -if (runtime->state ==SNDRV_PCM_STATE_XRUN || - runtime->state ==SNDRV_PCM_STATE_SUSPENDED ) { +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN || +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_SUSPENDED ) {#ifdef OSS_DEBUG pcm_dbg (substream->pcm,"pcm_oss: write: recovering from %s\n" , - runtime->state ==SNDRV_PCM_STATE_XRUN ? +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN ?"XRUN" :"SUSPEND" );#endif ret =snd_pcm_oss_prepare (substream);
@@ -1249,7 +1249,7 @@ snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, constbreak ;/* test, if we can't store new data, because the stream */ /* has not been started */ -if (runtime->state ==SNDRV_PCM_STATE_PREPARED ) +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_PREPARED )return -EAGAIN ; }return ret;
@@ -1261,18 +1261,18 @@ snd_pcm_sframes_t snd_pcm_oss_read3(struct snd_pcm_substream *substream, char *psnd_pcm_sframes_t delay;int ret;while (1 ) { -if (runtime->state ==SNDRV_PCM_STATE_XRUN || - runtime->state ==SNDRV_PCM_STATE_SUSPENDED ) { +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN || +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_SUSPENDED ) {#ifdef OSS_DEBUG pcm_dbg (substream->pcm,"pcm_oss: read: recovering from %s\n" , - runtime->state ==SNDRV_PCM_STATE_XRUN ? +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN ?"XRUN" :"SUSPEND" );#endif ret =snd_pcm_kernel_ioctl (substream,SNDRV_PCM_IOCTL_DRAIN ,NULL );if (ret <0 )break ; - }else if (runtime->state ==SNDRV_PCM_STATE_SETUP ) { + }else if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_SETUP ) { ret =snd_pcm_oss_prepare (substream);if (ret <0 )break ;
@@ -1285,7 +1285,7 @@ snd_pcm_sframes_t snd_pcm_oss_read3(struct snd_pcm_substream *substream, char *p frames, in_kernel);mutex_lock (&runtime->oss.params_lock);if (ret == -EPIPE ) { -if (runtime->state ==SNDRV_PCM_STATE_DRAINING ) { +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_DRAINING ) { ret =snd_pcm_kernel_ioctl (substream,SNDRV_PCM_IOCTL_DROP ,NULL );if (ret <0 )break ;
@@ -1304,12 +1304,12 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, voidstruct snd_pcm_runtime *runtime = substream->runtime;int ret;while (1 ) { -if (runtime->state ==SNDRV_PCM_STATE_XRUN || - runtime->state ==SNDRV_PCM_STATE_SUSPENDED ) { +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN || +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_SUSPENDED ) {#ifdef OSS_DEBUG pcm_dbg (substream->pcm,"pcm_oss: writev: recovering from %s\n" , - runtime->state ==SNDRV_PCM_STATE_XRUN ? +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN ?"XRUN" :"SUSPEND" );#endif ret =snd_pcm_oss_prepare (substream);
@@ -1322,7 +1322,7 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, void/* test, if we can't store new data, because the stream */ /* has not been started */ -if (runtime->state ==SNDRV_PCM_STATE_PREPARED ) +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_PREPARED )return -EAGAIN ; }return ret;
@@ -1333,18 +1333,18 @@ snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void *struct snd_pcm_runtime *runtime = substream->runtime;int ret;while (1 ) { -if (runtime->state ==SNDRV_PCM_STATE_XRUN || - runtime->state ==SNDRV_PCM_STATE_SUSPENDED ) { +if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN || +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_SUSPENDED ) {#ifdef OSS_DEBUG pcm_dbg (substream->pcm,"pcm_oss: readv: recovering from %s\n" , - runtime->state ==SNDRV_PCM_STATE_XRUN ? +READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_XRUN ?"XRUN" :"SUSPEND" );#endif ret =snd_pcm_kernel_ioctl (substream,SNDRV_PCM_IOCTL_DRAIN ,NULL );if (ret <0 )break ; - }else if (runtime->state ==SNDRV_PCM_STATE_SETUP ) { + }else if (READ_ONCE (runtime->state) ==SNDRV_PCM_STATE_SETUP ) { ret =snd_pcm_oss_prepare (substream);if (ret <0 )break ;
Signature · 1 line
2.34.1
Quoted 24 lines · Cen Zhang
__snd_pcm_set_state()writesruntime->stateunder the PCM stream lock:runtime->state = state;However, the OSS I/O functions
snd_pcm_oss_write3(),snd_pcm_oss_read3(),snd_pcm_oss_writev3()andsnd_pcm_oss_readv3()readruntime->statewithout holding the stream lock, only holding oss.params_lock (a different mutex that does not synchronize with the stream lock):if (runtime->state == SNDRV_PCM_STATE_XRUN || ...)Since
__snd_pcm_set_state()is called from IRQ context (e.g.,snd_pcm_period_elapsed->snd_pcm_update_state->__snd_pcm_xrun->snd_pcm_stop->snd_pcm_post_stop) while the OSS read/write paths run in process context, these are concurrent accesses that constitute a data race.The code handles stale reads gracefully through its retry loop (re-checking after
__snd_pcm_lib_xferreturns-EPIPE), so the race is not harmful under simple interleaving. However, plain C accesses are formally undefined under LKMM, and withoutREAD_ONCEthe compiler is free to fuse or cache the loads across loop iterations.
Quoted 5 lines
Add
WRITE_ONCE()in__snd_pcm_set_state()for the write side andREAD_ONCE()on all lockless reads ofruntime->statein the four OSS I/O functions.Signed-off-by Cen Zhang <[email protected]>
Thanks for the patch.
I believe it's better not to go with barriers but rather taking the proper spinlock, as it's only for this OSS layer, and other places are already doing so.
That said,
- Export snd_pcm_set_state() in pcm_native.c
- Introduce snd_pcm_get_state() helper just to call like
snd_pcm_state_t snd_pcm_get_state(struct snd_pcm_substream *substream)
{
guard(pcm_stream_lock_irqsave)(substream);
return substream->runtime->state;
}- Use those for setting the state in pcm_oss.c appropriately; some places are already in the lock, and they don't use the above. Also avoid calling snd_pcm_get_state() repeatedly if not needed.
Care to revise the patch and resubmit?
thanks,
Takashi
Quoted 10 lines
I believe it's better not to go with barriers but rather taking the proper spinlock, as it's only for this OSS layer, and other places are already doing so.
That said,
- Export
snd_pcm_set_state()inpcm_native.c
- Introducesnd_pcm_get_state()helper just to call like
...
Care to revise the patch and resubmit?
Thank you for the review. That makes sense — using the proper stream lock is indeed cleaner than barriers for this layer.
I've sent the v2 following your suggestions. Please take a look.
Best regards,
Cen Zhang