summaryrefslogtreecommitdiff
path: root/arch/arm/mach-bcm2708
diff options
context:
space:
mode:
authorpopcornmix <popcornmix@gmail.com>2013-05-01 19:55:09 +0100
committerpopcornmix <popcornmix@gmail.com>2015-05-18 14:10:20 +0100
commit07b4138b653ecfd4d3711e0301db90863444fa92 (patch)
treed5f2f03bafc42e331a25e7b612f59b5696fec9a6 /arch/arm/mach-bcm2708
parent5690b77f889d1a6651b51f144b44ee785a7e0ab2 (diff)
downloadlinux-07b4138b653ecfd4d3711e0301db90863444fa92.tar.gz
bcm2708 framebuffer driver
Signed-off-by: popcornmix <popcornmix@gmail.com> bcm2708_fb : Implement blanking support using the mailbox property interface bcm2708_fb: Add pan and vsync controls bcm2708_fb: DMA acceleration for fb_copyarea Based on http://www.raspberrypi.org/phpBB3/viewtopic.php?p=62425#p62425 Also used Simon's dmaer_master module as a reference for tweaking DMA settings for better performance. For now busylooping only. IRQ support might be added later. With non-overclocked Raspberry Pi, the performance is ~360 MB/s for simple copy or ~260 MB/s for two-pass copy (used when dragging windows to the right). In the case of using DMA channel 0, the performance improves to ~440 MB/s. For comparison, VFP optimized CPU copy can only do ~114 MB/s in the same conditions (hindered by reading uncached source buffer). Signed-off-by: Siarhei Siamashka <siarhei.siamashka@gmail.com> bcm2708_fb: report number of dma copies Add a counter (exported via debugfs) reporting the number of dma copies that the framebuffer driver has done, in order to help evaluate different optimization strategies. Signed-off-by: Luke Diamand <luked@broadcom.com> bcm2708_fb: use IRQ for DMA copies The copyarea ioctl() uses DMA to speed things along. This was busy-waiting for completion. This change supports using an interrupt instead for larger transfers. For small transfers, busy-waiting is still likely to be faster. Signed-off-by: Luke Diamand <luke@diamand.org> bcm2708: Make ioctl logging quieter
Diffstat (limited to 'arch/arm/mach-bcm2708')
-rw-r--r--arch/arm/mach-bcm2708/dma.c8
-rw-r--r--arch/arm/mach-bcm2708/include/mach/dma.h2
2 files changed, 10 insertions, 0 deletions
diff --git a/arch/arm/mach-bcm2708/dma.c b/arch/arm/mach-bcm2708/dma.c
index 51d147a8e227..1da2413360ca 100644
--- a/arch/arm/mach-bcm2708/dma.c
+++ b/arch/arm/mach-bcm2708/dma.c
@@ -83,6 +83,14 @@ extern void bcm_dma_wait_idle(void __iomem *dma_chan_base)
EXPORT_SYMBOL_GPL(bcm_dma_start);
+extern bool bcm_dma_is_busy(void __iomem *dma_chan_base)
+{
+ dsb();
+
+ return readl(dma_chan_base + BCM2708_DMA_CS) & BCM2708_DMA_ACTIVE;
+}
+EXPORT_SYMBOL_GPL(bcm_dma_is_busy);
+
/* Complete an ongoing DMA (assuming its results are to be ignored)
Does nothing if there is no DMA in progress.
This routine waits for the current AXI transfer to complete before
diff --git a/arch/arm/mach-bcm2708/include/mach/dma.h b/arch/arm/mach-bcm2708/include/mach/dma.h
index f2568d4ef607..a4aac4cbdd07 100644
--- a/arch/arm/mach-bcm2708/include/mach/dma.h
+++ b/arch/arm/mach-bcm2708/include/mach/dma.h
@@ -64,11 +64,13 @@ struct bcm2708_dma_cb {
unsigned long next;
unsigned long pad[2];
};
+struct scatterlist;
extern int bcm_sg_suitable_for_dma(struct scatterlist *sg_ptr, int sg_len);
extern void bcm_dma_start(void __iomem *dma_chan_base,
dma_addr_t control_block);
extern void bcm_dma_wait_idle(void __iomem *dma_chan_base);
+extern bool bcm_dma_is_busy(void __iomem *dma_chan_base);
extern int /*rc*/ bcm_dma_abort(void __iomem *dma_chan_base);
/* When listing features we can ask for when allocating DMA channels give