Thank you for your contribution! Sashiko AI review found 2 potential
issues to consider:
- [Medium] accel/amd-ai-engine: aiemlv2_set_part_clocks() clobbers
  tiles_inuse bitmap
- [Low] accel/amd-ai-engine: % 2 discards mask bit 1 in
  aiemlv2_scan_part_clocks()
--

commit 31b6ed2773ef86bbc6d6e5049ee938eccc623dd5
Author: Gregory Williams <[email protected]>

accel/amd-ai-engine: Add support to enable/disable tile clocks

This commit adds partition clock scanning and tile clock enable/disable
operations for requesting and releasing AI Engine tiles.

> diff --git a/drivers/accel/amd-ai-engine/ai-engine-aiemlv2.c 
> b/drivers/accel/amd-ai-engine/ai-engine-aiemlv2.c
> index 0c9c7ccdd54e0..26dd1d726bfad 100644
> --- a/drivers/accel/amd-ai-engine/ai-engine-aiemlv2.c
> +++ b/drivers/accel/amd-ai-engine/ai-engine-aiemlv2.c
> @@ -13,6 +13,16 @@
>  #define AIEMLV2_COL_SHIFT            25U
>  #define AIEMLV2_ROW_SHIFT            20U
>  
> +/*
> + * Register offsets
> + */
> +#define AIEMLV2_SHIMPL_COLCLOCK_CTRL_REGOFF          0x0007FF20U
> +
> +/*
> + * Register masks
> + */
> +#define AIEMLV2_SHIMPL_COLCLOCK_CTRL_MASK            GENMASK(1, 0)
> +
>  static u32 aiemlv2_get_tile_type(struct aie_device *adev, struct 
> aie_location *loc)
>  {
>       u8 num_mem_rows = adev->ttype_attr[AIE_TILE_TYPE_MEMORY].num_rows;
> @@ -25,8 +35,148 @@ static u32 aiemlv2_get_tile_type(struct aie_device *adev, 
> struct aie_location *l
>       return AIE_TILE_TYPE_SHIMNOC;
>  }
>  
> +static int aiemlv2_scan_part_clocks(struct aie_partition *apart)
> +{
> +     struct aie_range *range = &apart->range;
> +     struct aie_device *adev = apart->adev;
> +     struct aie_location loc;
> +
> +     /* Clear the bitmap of cores and memories clock state */
> +     aie_resource_put_region(&apart->cores_clk_state, 0,
> +                             apart->cores_clk_state.total);
> +
> +     /*
> +      * If the clock buffer on shim tile is enabled, then all tiles above in
> +      * the same column are also enabled.
> +      */
> +
> +     loc.row = 0;
> +     for (loc.col = range->start.col;
> +          loc.col < range->start.col + range->size.col;
> +          loc.col++) {
> +             void __iomem *va;
> +             u32 val, nbitpos;
> +
> +             nbitpos = (loc.col - range->start.col) * (range->size.row - 1) 
> + loc.row;
> +
> +             va = adev->base +
> +                  aie_cal_regoff(adev, loc,
> +                                 AIEMLV2_SHIMPL_COLCLOCK_CTRL_REGOFF);
> +             val = readl(va);
> +
> +             if (!((val & AIEMLV2_SHIMPL_COLCLOCK_CTRL_MASK) % 2))
> +                     continue;

[Severity: Low]
Does applying "% 2" after masking with AIEMLV2_SHIMPL_COLCLOCK_CTRL_MASK
(GENMASK(1, 0)) unintentionally discard bit 1?  Since (val & 0x3) % 2 only
tests bit 0, a column with bit 1 set and bit 0 clear will be treated as
clocked off during aie_part_create() -> aie_part_scan_clk_state().

> +
> +             aie_resource_set(&apart->cores_clk_state, nbitpos,
> +                              range->size.row - 1);
> +     }
> +     /*
> +      * Set the tiles in use bitmap.
> +      * In case of scanning, tiles which are powered on are considered as
> +      * tiles in use.
> +      */
> +     bitmap_copy(apart->tiles_inuse.bitmap, apart->cores_clk_state.bitmap,
> +                 apart->tiles_inuse.total);
> +
> +     return 0;
> +}
> +
> +static int aiemlv2_set_part_clocks(struct aie_partition *apart)
> +{
> +     struct aie_range *range = &apart->range;
> +     struct aie_range prev_range = {};
> +     struct aie_location loc;
> +     int ret = -EINVAL;
> +     u32 prev_ops = 0;
> +
> +     for (loc.col = 0; loc.col < range->size.col; loc.col++) {
> +             u32 startbit, col_inuse = 0;
> +
> +             startbit = loc.col * (range->size.row - 1);
> +
> +             for (loc.row = range->start.row + 1;
> +                  loc.row < range->start.row + range->size.row;
> +                  loc.row++) {
> +                     u32 nbitpos = startbit + loc.row - 1;
> +
> +                     if (aie_resource_testbit(&apart->tiles_inuse, nbitpos)) 
> {
> +                             col_inuse = 1;
> +                             break;
> +                     }
> +             }
> +
> +             if (col_inuse) {
> +                     struct aie_range op_range = {
> +                             .start.col = loc.col + range->start.col,
> +                             .size.col = 1,
> +                     };
> +
> +                     ret = aie_resource_set(&apart->tiles_inuse, startbit,
> +                                            apart->range.size.row - 1);
> +                     if (ret)
> +                             return ret;
> +                     ret = aie_resource_set(&apart->cores_clk_state, 
> startbit,
> +                                            apart->range.size.row - 1);

[Severity: Medium]
Should aiemlv2_set_part_clocks() avoid setting the entire column in
apart->tiles_inuse when col_inuse is true?

When aie_part_request_tiles() requests a subset of tiles in a column, it
sets only those tile bits in apart->tiles_inuse, but this call marks every
row in the column as in use.  If the caller later releases the requested
tiles via aie_part_release_tiles(), only the specified tile bits are
cleared in apart->tiles_inuse, so aiemlv2_set_part_clocks() sees the remaining
row bits still set, re-sets the released bits in apart->tiles_inuse, and
never disables the column clock buffer.

-- 
Sashiko AI review ยท 
https://sashiko.dev/#/patchset/[email protected]?part=14

Reply via email to