diff options
| author | Srinivas Kandagatla <srinivas.kandagatla@linaro.org> | 2014-09-23 11:59:09 +0200 |
|---|---|---|
| committer | Grant Likely <grant.likely@linaro.org> | 2014-09-25 12:55:50 +0200 |
| commit | 9aacd602f0246f1b1f3c4684b2ab13d0772976f7 (patch) | |
| tree | 63b98dd512853323f19b82ec7a67fa2fd266cde1 /drivers/of/fdt.c | |
| parent | of: Fix memory block alignment in early_init_dt_add_memory_arch() (diff) | |
| download | linux-9aacd602f0246f1b1f3c4684b2ab13d0772976f7.tar.xz linux-9aacd602f0246f1b1f3c4684b2ab13d0772976f7.zip | |
of/fdt: fix memory range check
In cases where board has below memory DT node
memory{
device_type = "memory";
reg = <0x80000000 0x80000000>;
};
Check on the memory range in fdt.c will always fail because it is
comparing MAX_PHYS_ADDR with base + size, in fact it should compare
it with base + size - 1.
This issue was originally noticed on Qualcomm IFC6410 board.
Without this patch kernel shows up noticed unnecessary warnings
[ 0.000000] Machine model: Qualcomm APQ8064/IFC6410
[ 0.000000] Ignoring memory range 0xffffffff - 0x100000000
[ 0.000000] cma: Reserved 64 MiB at ab800000
as a result the size get reduced to 0x7fffffff which looks wrong.
This patch fixes the check involved in generating this warning and
as a result it also fixes the wrong size calculation.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
[grant.likely: adjust new size calculation also]
Signed-off-by: Grant Likely <grant.likely@linaro.org>
Diffstat (limited to 'drivers/of/fdt.c')
| -rw-r--r-- | drivers/of/fdt.c | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 2d34afb2647d..d1ffca8b34ea 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -941,10 +941,10 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) return; } - if (base + size > MAX_PHYS_ADDR) { - pr_warning("Ignoring memory range 0x%lx - 0x%llx\n", - ULONG_MAX, base + size); - size = MAX_PHYS_ADDR - base; + if (base + size - 1 > MAX_PHYS_ADDR) { + pr_warning("Ignoring memory range 0x%llx - 0x%llx\n", + ((u64)MAX_PHYS_ADDR) + 1, base + size); + size = MAX_PHYS_ADDR - base + 1; } if (base + size < phys_offset) { |