On 2023-10-18 21:56, Jesse Zhang wrote:
[ 567.613292] shift exponent 255 is too large for 64-bit type 'long unsigned int'
[ 567.614498] CPU: 5 PID: 238 Comm: kworker/5:1 Tainted: G OE 6.2.0-34-generic #34~22.04.1-Ubuntu
[ 567.614502] Hardware
[AMD Official Use Only - General]
I think it is better to separate it to two patches since it addresses different
issues. With or without the change, this patch is
Reviewed-by: Yifan Zhang
-Original Message-
From: Jesse Zhang
Sent: Thursday, October 19, 2023 9:56 AM
To:
/amdkfd: Fix shift out-of-bounds issue
On 10/18/2023 9:53 AM, Philip Yang wrote:
>
>
> Caution: This message originated from an External Source. Use proper
> caution when opening attachments, clicking links, or responding.
>
>
> The 255 granularity is from recent Thunk change
On 10/18/2023 9:53 AM, Philip Yang wrote:
Caution: This message originated from an External Source. Use proper
caution when opening attachments, clicking links, or responding.
The 255 granularity is from recent Thunk change to increase CWSR area
granularity.
I think we also
The 255 granularity is from recent Thunk change to increase CWSR
area granularity.
Thanks for catching this with kernel debug option
CC_HAS_UBSAN_ARRAY_BOUNDS enabled. Because
1
[AMD Official Use Only - General]
Hi Jesse,
This patch is only a WA for the error log. How is this issue reproduced ? 255
looks like an invalid value for a prange->granularity, it is better to root
cause who set it in the first place.
BRs,
Yifan
-Original Message-
From: Jesse Zhang