Commit da1b94e6 authored by Santosh Shilimkar's avatar Santosh Shilimkar Committed by Tony Lindgren

ARM: OMAP: Fix for possible race condition in omap_free_dma()

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 <sean.mcneil@ti.com> for ointing out this issue.
Signed-off-by: default avatarSantosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: default avatarTony Lindgren <tony@atomide.com>
parent 09106974
......@@ -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);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment