[PATCH v2] ath10k: fix pointer arithmetic error in trace call

Kalle Valo kvalo at kernel.org
Thu Feb 24 01:05:47 PST 2022

Francesco Magliocca <franciman12 at gmail.com> wrote:

> Reading through the commit history, it looks like
> there is no special need why we must skip the first 4 bytes
> in this trace call:
> trace_ath10k_htt_rx_desc(ar, (void*)rx_desc + sizeof(u32),
>                          hw->rx_desc_ops->rx_desc_size - sizeof(u32));
> found in the function ath10k_htt_rx_amsdu_pop in the file htt_rx.c
> i think the original author
> (who is also the one who added rx_desc tracing capabilities
> in a0883cf7e75a) just wanted to trace the rx_desc contents,
> ignoring the fw_rx_desc_base info field
> (which is the part being skipped over).
> But the trace_ath10k_htt_rx_desc later added
> don't care about skipping it, so it may be good
> to uniform this call to the others in the file.
> But this would change the output of the trace and
> thus it may be a problem for tools that rely on it.
> Therefore I propose until further discussion
> to just keep it as it is and just fix the pointer arithmetic bug.
> Add missing void* cast to rx descriptor pointer in order to
> properly skip the initial 4 bytes of the rx descriptor
> when passing it to trace_ath10k_htt_rx_desc trace function.
> This fixes the pointer arithmetic error detected
> by Dan Carpenter's static analysis tool.
> Fixes: 6bae9de622d3 ("ath10k: abstract htt_rx_desc structure")
> Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00157-QCARMSWPZ-1
> Signed-off-by: Francesco Magliocca <franciman12 at gmail.com>
> Link: https://lore.kernel.org/ath10k/20220201130900.GD22458@kili/
> Signed-off-by: Kalle Valo <quic_kvalo at quicinc.com>

Patch applied to ath-next branch of ath.git, thanks.

49ffac5907a8 ath10k: fix pointer arithmetic error in trace call



More information about the ath10k mailing list