iommu_alloc_ctx() finds a zero bit in iommu->ctx_bitmap. It starts
searching from iommu->ctx_lowest_free to the end of the bitmap.
But the size argument to find_next_zero_bit() in iommu_alloc_ctx()
is wrong. It should be the bitmap size, not the maximum size to
search from the offset argument.
Fortunately iommu->ctx_lowest_free is almost unused and it will not
be more than 1. So the bug wasted only 1-bit at the end of
iommu->ctx_bitmap.
Signed-off-by: Akinobu Mita <akinobu.mita@xxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: sparclinux@xxxxxxxxxxxxxxx
---
arch/sparc/kernel/iommu.c | 5 ++---
1 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 47977a7..72509d0 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -255,10 +255,9 @@ static inline iopte_t *alloc_npages(struct device *dev, struct iommu *iommu,
static int iommu_alloc_ctx(struct iommu *iommu)
{
int lowest = iommu->ctx_lowest_free;
- int sz = IOMMU_NUM_CTXS - lowest;
- int n = find_next_zero_bit(iommu->ctx_bitmap, sz, lowest);
+ int n = find_next_zero_bit(iommu->ctx_bitmap, IOMMU_NUM_CTXS, lowest);
- if (unlikely(n == sz)) {
+ if (unlikely(n == IOMMU_NUM_CTXS)) {
n = find_next_zero_bit(iommu->ctx_bitmap, lowest, 1);
if (unlikely(n == lowest)) {
printk(KERN_WARNING "IOMMU: Ran out of contexts.\n");
--
1.7.4
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
