From: Vince Hsu <vinc...@nvidia.com>
commit e2127ae7a5e80eb53ad431c39145767391da40cd upstream.
Tegra124 was accidentally left out when the number of TLB lines was
parameterized in commit 11cec15bf3fb ("iommu/tegra-smmu: Parameterize
number of TLB lines"). Fortunately this doesn't cause any noticeable
regressions upstream, presumably because there aren't any use-cases
that exercise enough pressure on the SMMU. But it is a regression
nonetheless, so let's fix it.
Fixes: 11cec15bf3fb ("iommu/tegra-smmu: Parameterize number of TLB lines")
Signed-off-by: Vince Hsu <vinc...@nvidia.com>
Signed-off-by: Tomasz Figa <tf...@chromium.org>
[tred...@nvidia.com: extract from unrelated patch]
Signed-off-by: Thierry Reding <tred...@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
drivers/memory/tegra/tegra124.c | 1 +
1 file changed, 1 insertion(+)
--- a/drivers/memory/tegra/tegra124.c
+++ b/drivers/memory/tegra/tegra124.c
@@ -1007,6 +1007,7 @@ static const struct tegra_smmu_soc tegra
.num_swgroups = ARRAY_SIZE(tegra124_swgroups),
.supports_round_robin_arbitration = true,
.supports_request_limit = true,
+ .num_tlb_lines = 32,
.num_asids = 128,
};
