[Intel-gfx] [PATCH 4/5] drm/i915: Refactor sseu helper functions
Summers, Stuart
stuart.summers at intel.com
Tue May 7 18:21:53 UTC 2019
On Tue, 2019-05-07 at 11:12 -0700, Daniele Ceraolo Spurio wrote:
>
> On 5/3/19 2:30 PM, Stuart Summers wrote:
> > Move functions to intel_sseu.h and remove inline qualifier.
> > Additionally, ensure these are all prefixed with intel_sseu_*
> > to match the convention of other functions in i915.
> >
> > v2: fix spacing from checkpatch warning
> > v3: squash helper function changes into a single patch
> > break 80 character line to fix checkpatch warning
> > move get/set_eus helpers to intel_device_info.c
> >
> > Acked-by: Jani Nikula <jani.nikula at intel.com>
> > Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
> > Signed-off-by: Stuart Summers <stuart.summers at intel.com>
> > ---
> > drivers/gpu/drm/i915/gt/intel_sseu.c | 17 ++++
> > drivers/gpu/drm/i915/gt/intel_sseu.h | 10 +--
> > drivers/gpu/drm/i915/i915_debugfs.c | 4 +-
> > drivers/gpu/drm/i915/i915_drv.c | 2 +-
> > drivers/gpu/drm/i915/intel_device_info.c | 103 ++++++++++++++++
> > -------
> > drivers/gpu/drm/i915/intel_device_info.h | 44 ----------
> > 6 files changed, 97 insertions(+), 83 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c
> > b/drivers/gpu/drm/i915/gt/intel_sseu.c
> > index 7f448f3bea0b..a0756f006f5f 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_sseu.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
> > @@ -8,6 +8,23 @@
> > #include "intel_lrc_reg.h"ther occurrences below a
> > #include "intel_sseu.h"
> >
> > +unsigned int
> > +intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
> > +{
> > + unsigned int i, total = 0;
> > +
> > + for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask); i++)
> > + total += hweight8(sseu->subslice_mask[i]);
> > +
> > + return total;
> > +}
> > +
> > +unsigned int
> > +intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu,
> > u8 slice)
> > +{
> > + return hweight8(sseu->subslice_mask[slice]);
> > +}
> > +
> > u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
> > const struct intel_sseu *req_sseu)
> > {
> > diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h
> > b/drivers/gpu/drm/i915/gt/intel_sseu.h
> > index 9618dff46d83..b50d0401a4e2 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_sseu.h
> > +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
> > @@ -63,11 +63,11 @@ intel_sseu_from_device_info(const struct
> > sseu_dev_info *sseu)
> > return value;
> > }
> >
> > -static inline unsigned int
> > -intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu,
> > u8 slice)
> > -{
> > - return hweight8(sseu->subslice_mask[slice]);
> > -}
> > +unsigned int
> > +intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
> > +
> > +unsigned int
> > +intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu,
> > u8 slice);
> >
> > u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
> > const struct intel_sseu *req_sseu);
> > diff --git a/drivers/gpu/drm/i915/i915_debugfs.c
> > b/drivers/gpu/drm/i915/i915_debugfs.c
> > index dceb32a16c5c..fce3ccd87f76 100644
> > --- a/drivers/gpu/drm/i915/i915_debugfs.c
> > +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> > @@ -4160,7 +4160,7 @@ static void
> > broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
> > RUNTIME_INFO(dev_priv)-
> > >sseu.subslice_mask[s];
> > }
> > sseu->eu_total = sseu->eu_per_subslice *
> > - sseu_subslice_total(sseu);
> > + intel_sseu_subslice_total(sseu);
> >
> > /* subtract fused off EU(s) from enabled slice(s) */
> > for (s = 0; s < fls(sseu->slice_mask); s++) {
> > @@ -4184,7 +4184,7 @@ static void i915_print_sseu_info(struct
> > seq_file *m, bool is_available_info,
> > seq_printf(m, " %s Slice Total: %u\n", type,
> > hweight8(sseu->slice_mask));
> > seq_printf(m, " %s Subslice Total: %u\n", type,
> > - sseu_subslice_total(sseu));
> > + intel_sseu_subslice_total(sseu));
> > for (s = 0; s < fls(sseu->slice_mask); s++) {
> > seq_printf(m, " %s Slice%i subslices: %u\n", type,
> > s, intel_sseu_subslices_per_slice(sseu, s));
> > diff --git a/drivers/gpu/drm/i915/i915_drv.c
> > b/drivers/gpu/drm/i915/i915_drv.c
> > index dcc872f9c676..c2ea3f0992b2 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.c
> > +++ b/drivers/gpu/drm/i915/i915_drv.c
> > @@ -382,7 +382,7 @@ static int i915_getparam_ioctl(struct
> > drm_device *dev, void *data,
> > value = i915_cmd_parser_get_version(dev_priv);
> > break;
> > case I915_PARAM_SUBSLICE_TOTAL:
> > - value = sseu_subslice_total(sseu);
> > + value = intel_sseu_subslice_total(sseu);
> > if (!value)
> > return -ENODEV;
> > break;
> > diff --git a/drivers/gpu/drm/i915/intel_device_info.c
> > b/drivers/gpu/drm/i915/intel_device_info.c
> > index 9d6b9c45bc5e..689702b28e80 100644
> > --- a/drivers/gpu/drm/i915/intel_device_info.c
> > +++ b/drivers/gpu/drm/i915/intel_device_info.c
> > @@ -90,7 +90,7 @@ static void sseu_dump(const struct sseu_dev_info
> > *sseu, struct drm_printer *p)
> >
> > drm_printf(p, "slice total: %u, mask=%04x\n",
> > hweight8(sseu->slice_mask), sseu->slice_mask);
> > - drm_printf(p, "subslice total: %u\n",
> > sseu_subslice_total(sseu));
> > + drm_printf(p, "subslice total: %u\n",
> > intel_sseu_subslice_total(sseu));
> > for (s = 0; s < sseu->max_slices; s++) {
> > drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
> > s, intel_sseu_subslices_per_slice(sseu, s),
> > @@ -114,6 +114,43 @@ void intel_device_info_dump_runtime(const
> > struct intel_runtime_info *info,
> > info->cs_timestamp_frequency_khz);
> > }
> >
> > +static int intel_sseu_eu_idx(const struct sseu_dev_info *sseu, int
> > slice,
>
> No need for intel_ prefix for these functions if they're static
> (which
> also helps reducing the diff).
>
> > + int subslice)
> > +{
> > + int subslice_stride = DIV_ROUND_UP(sseu->max_eus_per_subslice,
> > + BITS_PER_BYTE);
>
> This was GEN_SSEU_STRIDE in the deleted code (other occurrences below
> as
> well).
>
> With these addressed:
Nice catch, I obviously missed this case. Will address both of these in
the next revision.
Thanks for the review!
-Stuart
>
> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
>
> Daniele
>
> > + int slice_stride = sseu->max_subslices * subslice_stride;
> > +
> > + return slice * slice_stride + subslice * subslice_stride;
> > +}
> > +
> > +static u16 intel_sseu_get_eus(const struct sseu_dev_info *sseu,
> > int slice,
> > + int subslice)
> > +{
> > + int i, offset = intel_sseu_eu_idx(sseu, slice, subslice);
> > + u16 eu_mask = 0;
> > +
> > + for (i = 0;
> > + i < DIV_ROUND_UP(sseu->max_eus_per_subslice,
> > BITS_PER_BYTE); i++) {
> > + eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
> > + (i * BITS_PER_BYTE);
> > + }
> > +
> > + return eu_mask;
> > +}
> > +
> > +static void intel_sseu_set_eus(struct sseu_dev_info *sseu, int
> > slice,
> > + int subslice, u16 eu_mask)
> > +{
> > + int i, offset = intel_sseu_eu_idx(sseu, slice, subslice);
> > +
> > + for (i = 0;
> > + i < DIV_ROUND_UP(sseu->max_eus_per_subslice,
> > BITS_PER_BYTE); i++) {
> > + sseu->eu_mask[offset + i] =
> > + (eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
> > + }
> > +}
> > +
> > void intel_device_info_dump_topology(const struct sseu_dev_info
> > *sseu,
> > struct drm_printer *p)
> > {
> > @@ -130,7 +167,7 @@ void intel_device_info_dump_topology(const
> > struct sseu_dev_info *sseu,
> > sseu->subslice_mask[s]);
> >
> > for (ss = 0; ss < sseu->max_subslices; ss++) {
> > - u16 enabled_eus = sseu_get_eus(sseu, s, ss);
> > + u16 enabled_eus = intel_sseu_get_eus(sseu, s,
> > ss);
> >
> > drm_printf(p, "\tsubslice%d: %u EUs (0x%hx)\n",
> > ss, hweight16(enabled_eus),
> > enabled_eus);
> > @@ -180,7 +217,7 @@ static void gen11_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > sseu->subslice_mask[s] = (ss_en >> ss_idx) &
> > ss_en_mask;
> > for (ss = 0; ss < sseu->max_subslices; ss++) {
> > if (sseu->subslice_mask[s] & BIT(ss))
> > - sseu_set_eus(sseu, s, ss,
> > eu_en);
> > + intel_sseu_set_eus(sseu, s, ss,
> > eu_en);
> > }
> > }
> > }
> > @@ -222,32 +259,32 @@ static void gen10_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > /* Slice0 */
> > eu_en = ~I915_READ(GEN8_EU_DISABLE0);
> > for (ss = 0; ss < sseu->max_subslices; ss++)
> > - sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) &
> > eu_mask);
> > + intel_sseu_set_eus(sseu, 0, ss, (eu_en >> (8 * ss)) &
> > eu_mask);
> > /* Slice1 */
> > - sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
> > + intel_sseu_set_eus(sseu, 1, 0, (eu_en >> 24) & eu_mask);
> > eu_en = ~I915_READ(GEN8_EU_DISABLE1);
> > - sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
> > + intel_sseu_set_eus(sseu, 1, 1, eu_en & eu_mask);
> > /* Slice2 */
> > - sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
> > - sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
> > + intel_sseu_set_eus(sseu, 2, 0, (eu_en >> 8) & eu_mask);
> > + intel_sseu_set_eus(sseu, 2, 1, (eu_en >> 16) & eu_mask);
> > /* Slice3 */
> > - sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
> > + intel_sseu_set_eus(sseu, 3, 0, (eu_en >> 24) & eu_mask);
> > eu_en = ~I915_READ(GEN8_EU_DISABLE2);
> > - sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
> > + intel_sseu_set_eus(sseu, 3, 1, eu_en & eu_mask);
> > /* Slice4 */
> > - sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
> > - sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
> > + intel_sseu_set_eus(sseu, 4, 0, (eu_en >> 8) & eu_mask);
> > + intel_sseu_set_eus(sseu, 4, 1, (eu_en >> 16) & eu_mask);
> > /* Slice5 */
> > - sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
> > + intel_sseu_set_eus(sseu, 5, 0, (eu_en >> 24) & eu_mask);
> > eu_en = ~I915_READ(GEN10_EU_DISABLE3);
> > - sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
> > + intel_sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
> >
> > /* Do a second pass where we mark the subslices disabled if all
> > their
> > * eus are off.
> > */
> > for (s = 0; s < sseu->max_slices; s++) {
> > for (ss = 0; ss < sseu->max_subslices; ss++) {
> > - if (sseu_get_eus(sseu, s, ss) == 0)
> > + if (intel_sseu_get_eus(sseu, s, ss) == 0)
> > sseu->subslice_mask[s] &= ~BIT(ss);
> > }
> > }
> > @@ -260,9 +297,10 @@ static void gen10_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > * EU in any one subslice may be fused off for die
> > * recovery.
> > */
> > - sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
> > + sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
> > DIV_ROUND_UP(sseu->eu_total,
> > - sseu_subslice_total(sseu))
> > : 0;
> > + intel_sseu_subslice_total(
> > sseu)) :
> > + 0;
> >
> > /* No restrictions on Power Gating */
> > sseu->has_slice_pg = 1;
> > @@ -290,7 +328,7 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
> >
> > sseu->subslice_mask[0] |= BIT(0);
> > - sseu_set_eus(sseu, 0, 0, ~disabled_mask);
> > + intel_sseu_set_eus(sseu, 0, 0, ~disabled_mask);
> > }
> >
> > if (!(fuse & CHV_FGT_DISABLE_SS1)) {
> > @@ -301,7 +339,7 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
> >
> > sseu->subslice_mask[0] |= BIT(1);
> > - sseu_set_eus(sseu, 0, 1, ~disabled_mask);
> > + intel_sseu_set_eus(sseu, 0, 1, ~disabled_mask);
> > }
> >
> > sseu->eu_total = compute_eu_total(sseu);
> > @@ -310,8 +348,9 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > * CHV expected to always have a uniform distribution of EU
> > * across subslices.
> > */
> > - sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
> > - sseu->eu_total /
> > sseu_subslice_total(sseu) :
> > + sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
> > + sseu->eu_total /
> > + intel_sseu_subslice_total(sseu)
> > :
> > 0;
> > /*
> > * CHV supports subslice power gating on devices with more than
> > @@ -319,7 +358,7 @@ static void cherryview_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > * more than one EU pair per subslice.
> > */
> > sseu->has_slice_pg = 0;
> > - sseu->has_subslice_pg = sseu_subslice_total(sseu) > 1;
> > + sseu->has_subslice_pg = intel_sseu_subslice_total(sseu) > 1;
> > sseu->has_eu_pg = (sseu->eu_per_subslice > 2);
> > }
> >
> > @@ -369,7 +408,7 @@ static void gen9_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >
> > eu_disabled_mask = (eu_disable >> (ss * 8)) &
> > eu_mask;
> >
> > - sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
> > + intel_sseu_set_eus(sseu, s, ss,
> > ~eu_disabled_mask);
> >
> > eu_per_ss = sseu->max_eus_per_subslice -
> > hweight8(eu_disabled_mask);
> > @@ -393,9 +432,10 @@ static void gen9_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > * recovery. BXT is expected to be perfectly uniform in EU
> > * distribution.
> > */
> > - sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
> > + sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
> > DIV_ROUND_UP(sseu->eu_total,
> > - sseu_subslice_total(sseu))
> > : 0;
> > + intel_sseu_subslice_total(
> > sseu)) :
> > + 0;
> > /*
> > * SKL+ supports slice power gating on devices with more than
> > * one slice, and supports EU power gating on devices with
> > @@ -407,7 +447,7 @@ static void gen9_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > sseu->has_slice_pg =
> > !IS_GEN9_LP(dev_priv) && hweight8(sseu->slice_mask) >
> > 1;
> > sseu->has_subslice_pg =
> > - IS_GEN9_LP(dev_priv) && sseu_subslice_total(sseu) > 1;
> > + IS_GEN9_LP(dev_priv) && intel_sseu_subslice_total(sseu)
> > > 1;
> > sseu->has_eu_pg = sseu->eu_per_subslice > 2;
> >
> > if (IS_GEN9_LP(dev_priv)) {
> > @@ -477,7 +517,7 @@ static void broadwell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > eu_disabled_mask =
> > eu_disable[s] >> (ss * sseu-
> > >max_eus_per_subslice);
> >
> > - sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
> > + intel_sseu_set_eus(sseu, s, ss,
> > ~eu_disabled_mask);
> >
> > n_disabled = hweight8(eu_disabled_mask);
> >
> > @@ -496,9 +536,10 @@ static void broadwell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> > * subslices with the exception that any one EU in any one
> > subslice may
> > * be fused off for die recovery.
> > */
> > - sseu->eu_per_subslice = sseu_subslice_total(sseu) ?
> > + sseu->eu_per_subslice = intel_sseu_subslice_total(sseu) ?
> > DIV_ROUND_UP(sseu->eu_total,
> > - sseu_subslice_total(sseu))
> > : 0;
> > + intel_sseu_subslice_total(
> > sseu)) :
> > + 0;
> >
> > /*
> > * BDW supports slice power gating on devices with more than
> > @@ -561,8 +602,8 @@ static void haswell_sseu_info_init(struct
> > drm_i915_private *dev_priv)
> >
> > for (s = 0; s < sseu->max_slices; s++) {
> > for (ss = 0; ss < sseu->max_subslices; ss++) {
> > - sseu_set_eus(sseu, s, ss,
> > - (1UL << sseu->eu_per_subslice) -
> > 1);
> > + intel_sseu_set_eus(sseu, s, ss,
> > + (1UL << sseu-
> > >eu_per_subslice) - 1);
> > }
> > }
> >
> > diff --git a/drivers/gpu/drm/i915/intel_device_info.h
> > b/drivers/gpu/drm/i915/intel_device_info.h
> > index 9d43f7edfd63..6412a9c72898 100644
> > --- a/drivers/gpu/drm/i915/intel_device_info.h
> > +++ b/drivers/gpu/drm/i915/intel_device_info.h
> > @@ -218,50 +218,6 @@ struct intel_driver_caps {
> > bool has_logical_contexts:1;
> > };
> >
> > -static inline unsigned int sseu_subslice_total(const struct
> > sseu_dev_info *sseu)
> > -{
> > - unsigned int i, total = 0;
> > -
> > - for (i = 0; i < ARRAY_SIZE(sseu->subslice_mask); i++)
> > - total += hweight8(sseu->subslice_mask[i]);
> > -
> > - return total;
> > -}
> > -
> > -static inline int sseu_eu_idx(const struct sseu_dev_info *sseu,
> > - int slice, int subslice)
> > -{
> > - int subslice_stride = GEN_SSEU_STRIDE(sseu-
> > >max_eus_per_subslice);
> > - int slice_stride = sseu->max_subslices * subslice_stride;
> > -
> > - return slice * slice_stride + subslice * subslice_stride;
> > -}
> > -
> > -static inline u16 sseu_get_eus(const struct sseu_dev_info *sseu,
> > - int slice, int subslice)
> > -{
> > - int i, offset = sseu_eu_idx(sseu, slice, subslice);
> > - u16 eu_mask = 0;
> > -
> > - for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
> > i++) {
> > - eu_mask |= ((u16) sseu->eu_mask[offset + i]) <<
> > - (i * BITS_PER_BYTE);
> > - }
> > -
> > - return eu_mask;
> > -}
> > -
> > -static inline void sseu_set_eus(struct sseu_dev_info *sseu,
> > - int slice, int subslice, u16 eu_mask)
> > -{
> > - int i, offset = sseu_eu_idx(sseu, slice, subslice);
> > -
> > - for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
> > i++) {
> > - sseu->eu_mask[offset + i] =
> > - (eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
> > - }
> > -}
> > -
> > const char *intel_platform_name(enum intel_platform platform);
> >
> > void intel_device_info_subplatform_init(struct drm_i915_private
> > *dev_priv);
> >
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 3270 bytes
Desc: not available
URL: <https://lists.freedesktop.org/archives/intel-gfx/attachments/20190507/784c65ea/attachment.bin>
More information about the Intel-gfx
mailing list