[PATCH] of: fdt: fix memory range check

[PATCH] of: fdt: fix memory range check

[Srinivas Kandagatla]

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-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
---
 drivers/of/fdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 79cb831..3f5736c 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -937,7 +937,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 		return;
 	}
 
-	if (base + size > MAX_PHYS_ADDR) {
+	if (base + size - 1 > MAX_PHYS_ADDR) {
 		pr_warning("Ignoring memory range 0x%lx - 0x%llx\n",
 				ULONG_MAX, base + size);
 		size = MAX_PHYS_ADDR - base;
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] of: fdt: fix memory range check

[Grant Likely]

On Tue, 23 Sep 2014 10:59:09 +0100, Srinivas Kandagatla <srinivas.kandagatla@linaro.org> wrote:
> 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>
> ---
>  drivers/of/fdt.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
> index 79cb831..3f5736c 100644
> --- a/drivers/of/fdt.c
> +++ b/drivers/of/fdt.c
> @@ -937,7 +937,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
>  		return;
>  	}
>  
> -	if (base + size > MAX_PHYS_ADDR) {
> +	if (base + size - 1 > MAX_PHYS_ADDR) {
>  		pr_warning("Ignoring memory range 0x%lx - 0x%llx\n",
>  				ULONG_MAX, base + size);
>  		size = MAX_PHYS_ADDR - base;

By that logic, the above two lines need to be repaired also:

		pr_warning("Ignoring memory range 0x%lx - 0x%llx\n",
				MAX_PHYS_ADDR + 1, base + size);
		size = MAX_PHYS_ADDR - base + 1;

I've fixed it up and applied, thanks.

g.

Re: [PATCH] of: fdt: fix memory range check

[Srinivas Kandagatla]

On 24/09/14 15:38, Grant Likely wrote:
>> --- a/drivers/of/fdt.c
>> >+++ b/drivers/of/fdt.c
>> >@@ -937,7 +937,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
>> >  		return;
>> >  	}
>> >
>> >-	if (base + size > MAX_PHYS_ADDR) {
>> >+	if (base + size - 1 > MAX_PHYS_ADDR) {
>> >  		pr_warning("Ignoring memory range 0x%lx - 0x%llx\n",
>> >  				ULONG_MAX, base + size);
>> >  		size = MAX_PHYS_ADDR - base;
> By that logic, the above two lines need to be repaired also:
Thanks for fixing this too.
>
> 		pr_warning("Ignoring memory range 0x%lx - 0x%llx\n",
> 				MAX_PHYS_ADDR + 1, base + size);

I think the first argument should be printed in 0x%llx format as there 
would be a 32bit overflow for MAX_PHYS_ADDR + 1.

> 		size = MAX_PHYS_ADDR - base + 1;
>
> I've fixed it up and applied, thanks.

--srini