From: Santosh Shilimkar <[email protected]>

Fix the possible race condition in omap_free_dma(). Function omap_free_dma()
sets the dev_id = -1 and then accesses the channel afterwards to clear it.
But setting the dev_id=-1 makes the channel available for allocation again.
So it is possible someone else can grab it and results are unpredictable.
To avod this DMA channle is cleared first and then the dev_id = -1 is set.

Thanks to McNeil, Sean <[email protected]> for ointing out this issue.

Signed-off-by: Santosh Shilimkar <[email protected]>
Signed-off-by: Tony Lindgren <[email protected]>
---
 arch/arm/plat-omap/dma.c |   13 ++++++-------
 1 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 21cc014..7fc8c04 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -760,19 +760,12 @@ void omap_free_dma(int lch)
 {
        unsigned long flags;
 
-       spin_lock_irqsave(&dma_chan_lock, flags);
        if (dma_chan[lch].dev_id == -1) {
                pr_err("omap_dma: trying to free unallocated DMA channel %d\n",
                       lch);
-               spin_unlock_irqrestore(&dma_chan_lock, flags);
                return;
        }
 
-       dma_chan[lch].dev_id = -1;
-       dma_chan[lch].next_lch = -1;
-       dma_chan[lch].callback = NULL;
-       spin_unlock_irqrestore(&dma_chan_lock, flags);
-
        if (cpu_class_is_omap1()) {
                /* Disable all DMA interrupts for the channel. */
                dma_write(0, CICR(lch));
@@ -798,6 +791,12 @@ void omap_free_dma(int lch)
                dma_write(0, CCR(lch));
                omap_clear_dma(lch);
        }
+
+       spin_lock_irqsave(&dma_chan_lock, flags);
+       dma_chan[lch].dev_id = -1;
+       dma_chan[lch].next_lch = -1;
+       dma_chan[lch].callback = NULL;
+       spin_unlock_irqrestore(&dma_chan_lock, flags);
 }
 EXPORT_SYMBOL(omap_free_dma);
 

--
To unsubscribe from this list: send the line "unsubscribe linux-omap" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to