[PATCH alsa-lib v2 2/2] pcm: dmix: Fix semaphore usage with lockless operation

[Takashi Iwai]

As Maarten Baert recently reported, the current dmix code applies the
semaphore unnecessarily around mixing streams even when the lockless
mix operation is used on x86.  This was rather introduced mistakenly
at the commit 267d7c728196 ("Add support of little-endian on
i386/x86_64 dmix") where the generic dmix code was included on x86,
too.

For achieving the original performance back, this patch changes the
semaphore handling to be checked at run time instead of statically at
compile time.

Signed-off-by: Takashi Iwai <tiwai at suse.de>
---
 src/pcm/pcm_direct.h       |  1 +
 src/pcm/pcm_dmix.c         | 18 +++++++++++-------
 src/pcm/pcm_dmix_generic.c |  2 +-
 src/pcm/pcm_dmix_i386.c    |  1 +
 src/pcm/pcm_dmix_x86_64.c  |  1 +
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/src/pcm/pcm_direct.h b/src/pcm/pcm_direct.h
index 8a236970a3a1..2150bce15449 100644
--- a/src/pcm/pcm_direct.h
+++ b/src/pcm/pcm_direct.h
@@ -186,6 +186,7 @@ struct snd_pcm_direct {
 			mix_areas_32_t *remix_areas_32;
 			mix_areas_24_t *remix_areas_24;
 			mix_areas_u8_t *remix_areas_u8;
+			unsigned int use_sem;
 		} dmix;
 		struct {
 			unsigned long long chn_mask;
diff --git a/src/pcm/pcm_dmix.c b/src/pcm/pcm_dmix.c
index 843fa3168756..e9343b19a536 100644
--- a/src/pcm/pcm_dmix.c
+++ b/src/pcm/pcm_dmix.c
@@ -292,13 +292,17 @@ static void remix_areas(snd_pcm_direct_t *dmix,
  * the area via semaphore
  */
 #ifndef DOC_HIDDEN
-#ifdef NO_CONCURRENT_ACCESS
-#define dmix_down_sem(dmix) snd_pcm_direct_semaphore_down(dmix, DIRECT_IPC_SEM_CLIENT)
-#define dmix_up_sem(dmix) snd_pcm_direct_semaphore_up(dmix, DIRECT_IPC_SEM_CLIENT)
-#else
-#define dmix_down_sem(dmix)
-#define dmix_up_sem(dmix)
-#endif
+static void dmix_down_sem(snd_pcm_direct_t *dmix)
+{
+	if (dmix->u.dmix.use_sem)
+		snd_pcm_direct_semaphore_down(dmix, DIRECT_IPC_SEM_CLIENT);
+}
+
+static void dmix_up_sem(snd_pcm_direct_t *dmix)
+{
+	if (dmix->u.dmix.use_sem)
+		snd_pcm_direct_semaphore_up(dmix, DIRECT_IPC_SEM_CLIENT);
+}
 #endif
 
 /*
diff --git a/src/pcm/pcm_dmix_generic.c b/src/pcm/pcm_dmix_generic.c
index 40c08747a74a..8a5b6f148556 100644
--- a/src/pcm/pcm_dmix_generic.c
+++ b/src/pcm/pcm_dmix_generic.c
@@ -43,7 +43,6 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 #ifndef ARCH_ADD
 #define ARCH_ADD(p,a) (*(p) += (a))
 #define ARCH_CMPXCHG(p,a,b) (*(p)) /* fake */
-#define NO_CONCURRENT_ACCESS	/* use semaphore to avoid race */
 #define IS_CONCURRENT	0	/* no race check */
 #endif
 
@@ -530,6 +529,7 @@ static void generic_mix_select_callbacks(snd_pcm_direct_t *dmix)
 	dmix->u.dmix.mix_areas_u8 = generic_mix_areas_u8;
 	dmix->u.dmix.remix_areas_24 = generic_remix_areas_24;
 	dmix->u.dmix.remix_areas_u8 = generic_remix_areas_u8;
+	dmix->u.dmix.use_sem = 1;
 }
 
 #endif
diff --git a/src/pcm/pcm_dmix_i386.c b/src/pcm/pcm_dmix_i386.c
index 1ab983a8a373..82a91c5c2897 100644
--- a/src/pcm/pcm_dmix_i386.c
+++ b/src/pcm/pcm_dmix_i386.c
@@ -135,4 +135,5 @@ static void mix_select_callbacks(snd_pcm_direct_t *dmix)
 		dmix->u.dmix.mix_areas_24 = smp > 1 ? mix_areas_24_smp: mix_areas_24;
 		dmix->u.dmix.remix_areas_24 = smp > 1 ? remix_areas_24_smp: remix_areas_24;
 	}
+	dmix->u.dmix.use_sem = 0;
 }
diff --git a/src/pcm/pcm_dmix_x86_64.c b/src/pcm/pcm_dmix_x86_64.c
index 34c40d4e9d1d..4d882bfd01bf 100644
--- a/src/pcm/pcm_dmix_x86_64.c
+++ b/src/pcm/pcm_dmix_x86_64.c
@@ -102,4 +102,5 @@ static void mix_select_callbacks(snd_pcm_direct_t *dmix)
 	dmix->u.dmix.remix_areas_32 = smp > 1 ? remix_areas_32_smp : remix_areas_32;
 	dmix->u.dmix.mix_areas_24 = smp > 1 ? mix_areas_24_smp : mix_areas_24;
 	dmix->u.dmix.remix_areas_24 = smp > 1 ? remix_areas_24_smp : remix_areas_24;
+	dmix->u.dmix.use_sem = 0;
 }
-- 
2.16.4