On 2/19/19 6:01 PM, Arnd Bergmann wrote:
> Clang-9 makes some different inlining decisions compared to gcc, which
> leads to a warning about a possible stack overflow problem when building
> with CONFIG_KASAN, including when setting asan-stack=0, which avoids
> most other frame overflow warnings:
>
> drivers/media/platform/vicodec/codec-fwht.c:673:12: error: stack frame size
> of 2224 bytes in function 'encode_plane'
>
> Manually adding noinline_for_stack annotations in those functions
> called by encode_plane() or decode_plane() that require a significant
> amount of kernel stack makes this impossible to happen with any
> compiler.
>
> Signed-off-by: Arnd Bergmann <a...@arndb.de>
> ---
> drivers/media/platform/vicodec/codec-fwht.c | 18 ++++++++++--------
> 1 file changed, 10 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/media/platform/vicodec/codec-fwht.c
> b/drivers/media/platform/vicodec/codec-fwht.c
> index d1d6085da9f1..135d56bcc2c5 100644
> --- a/drivers/media/platform/vicodec/codec-fwht.c
> +++ b/drivers/media/platform/vicodec/codec-fwht.c
> @@ -47,7 +47,7 @@ static const uint8_t zigzag[64] = {
> };
>
>
> -static int rlc(const s16 *in, __be16 *output, int blocktype)
> +static int noinline_for_stack rlc(const s16 *in, __be16 *output, int
> blocktype)
> {
> s16 block[8 * 8];
> s16 *wp = block;
> @@ -106,8 +106,8 @@ static int rlc(const s16 *in, __be16 *output, int
> blocktype)
> * This function will worst-case increase rlc_in by 65*2 bytes:
> * one s16 value for the header and 8 * 8 coefficients of type s16.
> */
> -static u16 derlc(const __be16 **rlc_in, s16 *dwht_out,
> - const __be16 *end_of_input)
> +static noinline_for_stack u16
> +derlc(const __be16 **rlc_in, s16 *dwht_out, const __be16 *end_of_input)
> {
> /* header */
> const __be16 *input = *rlc_in;
> @@ -373,7 +373,8 @@ static void fwht(const u8 *block, s16 *output_block,
> unsigned int stride,
> * Furthermore values can be negative... This is just a version that
> * works with 16 signed data
> */
> -static void fwht16(const s16 *block, s16 *output_block, int stride, int
> intra)
> +static void noinline_for_stack
> +fwht16(const s16 *block, s16 *output_block, int stride, int intra)
> {
> /* we'll need more than 8 bits for the transformed coefficients */
> s32 workspace1[8], workspace2[8];
> @@ -456,7 +457,8 @@ static void fwht16(const s16 *block, s16 *output_block,
> int stride, int intra)
> }
> }
>
> -static void ifwht(const s16 *block, s16 *output_block, int intra)
> +static noinline_for_stack void
> +ifwht(const s16 *block, s16 *output_block, int intra)
> {
Please add it for fwht as well. It makes no sense to have it for fwht16, ifwht
but not the fwht function.
Got to say this is all very magic...
I think it would be good to perhaps have a comment at the start of the source
that explains why noinline_for_stack is added to selected functions.
Patches 1 & 3 are fine, BTW.
Regards,
Hans
> /*
> * we'll need more than 8 bits for the transformed coefficients
> @@ -604,9 +606,9 @@ static int var_inter(const s16 *old, const s16 *new)
> return ret;
> }
>
> -static int decide_blocktype(const u8 *cur, const u8 *reference,
> - s16 *deltablock, unsigned int stride,
> - unsigned int input_step)
> +static noinline_for_stack int
> +decide_blocktype(const u8 *cur, const u8 *reference, s16 *deltablock,
> + unsigned int stride, unsigned int input_step)
> {
> s16 tmp[64];
> s16 old[64];
>
