[PATCH 1/2] drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

[PATCH 1/2] drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

[Chris Wilson]

As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x). This catches a
couple of instances in the display code using (u64)x * (u32)y.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_display.c | 2 +-
 drivers/gpu/drm/i915/intel_tv.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8bd8ed362e1a..c66749e8f75e 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10022,7 +10022,7 @@ int intel_dotclock_calculate(int link_freq,
 	if (!m_n->link_n)
 		return 0;
 
-	return div_u64((u64)m_n->link_m * link_freq, m_n->link_n);
+	return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n);
 }
 
 static void ironlake_pch_clock_get(struct intel_crtc *crtc,
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 784df024e230..38087d0a4465 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1385,7 +1385,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 			mode_ptr->vsync_end = mode_ptr->vsync_start  + 1;
 		mode_ptr->vtotal = vactive_s + 33;
 
-		tmp = (u64) tv_mode->refresh * mode_ptr->vtotal;
+		tmp = mul_u32_u32(tv_mode->refresh, mode_ptr->vtotal);
 		tmp *= mode_ptr->htotal;
 		tmp = div_u64(tmp, 1000000);
 		mode_ptr->clock = (int) tmp;
-- 
2.13.3

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/2] drm/i915/selftests: Use mul_u32_u32() for 32b x 32b -> 64b result

[Chris Wilson]

As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/selftests/i915_gem_timeline.c | 2 +-
 drivers/gpu/drm/i915/selftests/i915_random.c       | 5 -----
 drivers/gpu/drm/i915/selftests/i915_random.h       | 5 +++++
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
index 7a44dab631b8..4795877abe56 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
@@ -121,7 +121,7 @@ static int igt_sync(void *arg)
 
 static unsigned int random_engine(struct rnd_state *rnd)
 {
-	return ((u64)prandom_u32_state(rnd) * I915_NUM_ENGINES) >> 32;
+	return i915_prandom_u32_max_state(I915_NUM_ENGINES, rnd);
 }
 
 static int bench_sync(void *arg)
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c
index d044bf9a6feb..ea0f5dbc0eb7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.c
+++ b/drivers/gpu/drm/i915/selftests/i915_random.c
@@ -41,11 +41,6 @@ u64 i915_prandom_u64_state(struct rnd_state *rnd)
 	return x;
 }
 
-static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
-{
-	return upper_32_bits((u64)prandom_u32_state(state) * ep_ro);
-}
-
 void i915_random_reorder(unsigned int *order, unsigned int count,
 			 struct rnd_state *state)
 {
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 6c9379871384..7dffedc501ca 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -43,6 +43,11 @@
 
 u64 i915_prandom_u64_state(struct rnd_state *rnd);
 
+static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
+{
+	return upper_32_bits(mul_u32_u32(prandom_u32_state(state), ep_ro));
+}
+
 unsigned int *i915_random_order(unsigned int count,
 				struct rnd_state *state);
 void i915_random_reorder(unsigned int *order,
-- 
2.13.3

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

[Patchwork]

== Series Details ==

Series: series starting with [1/2] drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result
URL   : https://patchwork.freedesktop.org/series/27629/
State : success

== Summary ==

Series 27629v1 Series without cover letter
https://patchwork.freedesktop.org/api/1.0/series/27629/revisions/1/mbox/

Test kms_cursor_legacy:
        Subgroup basic-busy-flip-before-cursor-atomic:
                fail       -> PASS       (fi-snb-2600) fdo#100215
Test kms_pipe_crc_basic:
        Subgroup suspend-read-crc-pipe-b:
                dmesg-warn -> PASS       (fi-byt-j1900) fdo#101705

fdo#100215 https://bugs.freedesktop.org/show_bug.cgi?id=100215
fdo#101705 https://bugs.freedesktop.org/show_bug.cgi?id=101705

fi-bdw-5557u     total:279  pass:268  dwarn:0   dfail:0   fail:0   skip:11  time:444s
fi-bdw-gvtdvm    total:279  pass:265  dwarn:0   dfail:0   fail:0   skip:14  time:431s
fi-blb-e6850     total:279  pass:224  dwarn:1   dfail:0   fail:0   skip:54  time:360s
fi-bsw-n3050     total:279  pass:243  dwarn:0   dfail:0   fail:0   skip:36  time:537s
fi-bxt-j4205     total:279  pass:260  dwarn:0   dfail:0   fail:0   skip:19  time:516s
fi-byt-j1900     total:279  pass:255  dwarn:0   dfail:0   fail:0   skip:24  time:489s
fi-byt-n2820     total:279  pass:250  dwarn:1   dfail:0   fail:0   skip:28  time:492s
fi-glk-2a        total:279  pass:260  dwarn:0   dfail:0   fail:0   skip:19  time:598s
fi-hsw-4770      total:279  pass:263  dwarn:0   dfail:0   fail:0   skip:16  time:437s
fi-hsw-4770r     total:279  pass:263  dwarn:0   dfail:0   fail:0   skip:16  time:414s
fi-ilk-650       total:279  pass:229  dwarn:0   dfail:0   fail:0   skip:50  time:417s
fi-ivb-3520m     total:279  pass:261  dwarn:0   dfail:0   fail:0   skip:18  time:512s
fi-ivb-3770      total:279  pass:261  dwarn:0   dfail:0   fail:0   skip:18  time:494s
fi-kbl-7500u     total:279  pass:261  dwarn:0   dfail:0   fail:0   skip:18  time:468s
fi-kbl-7560u     total:279  pass:269  dwarn:0   dfail:0   fail:0   skip:10  time:573s
fi-kbl-r         total:279  pass:261  dwarn:0   dfail:0   fail:0   skip:18  time:581s
fi-pnv-d510      total:279  pass:222  dwarn:2   dfail:0   fail:0   skip:55  time:559s
fi-skl-6260u     total:279  pass:269  dwarn:0   dfail:0   fail:0   skip:10  time:469s
fi-skl-6700hq    total:279  pass:262  dwarn:0   dfail:0   fail:0   skip:17  time:587s
fi-skl-6700k     total:279  pass:261  dwarn:0   dfail:0   fail:0   skip:18  time:471s
fi-skl-6770hq    total:279  pass:269  dwarn:0   dfail:0   fail:0   skip:10  time:473s
fi-skl-gvtdvm    total:279  pass:266  dwarn:0   dfail:0   fail:0   skip:13  time:434s
fi-skl-x1585l    total:279  pass:269  dwarn:0   dfail:0   fail:0   skip:10  time:496s
fi-snb-2520m     total:279  pass:251  dwarn:0   dfail:0   fail:0   skip:28  time:550s
fi-snb-2600      total:279  pass:250  dwarn:0   dfail:0   fail:0   skip:29  time:404s

948c3bddb3333e7245970c684749ba5d72370cd2 drm-tip: 2017y-07m-20d-10h-52m-43s UTC integration manifest
8ac809d drm/i915/selftests: Use mul_u32_u32() for 32b x 32b -> 64b result
f61b3c6 drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_5245/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 1/2] drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

[Chris Wilson]

As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x). This catches a
couple of instances in the display code using (u64)x * (u32)y.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_display.c | 2 +-
 drivers/gpu/drm/i915/intel_tv.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 6b3de6ad86d3..8f19d0b3512e 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10223,7 +10223,7 @@ int intel_dotclock_calculate(int link_freq,
 	if (!m_n->link_n)
 		return 0;
 
-	return div_u64((u64)m_n->link_m * link_freq, m_n->link_n);
+	return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n);
 }
 
 static void ironlake_pch_clock_get(struct intel_crtc *crtc,
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 0cc999fa09c5..a79a7591b2cf 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1385,7 +1385,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 			mode_ptr->vsync_end = mode_ptr->vsync_start  + 1;
 		mode_ptr->vtotal = vactive_s + 33;
 
-		tmp = (u64) tv_mode->refresh * mode_ptr->vtotal;
+		tmp = mul_u32_u32(tv_mode->refresh, mode_ptr->vtotal);
 		tmp *= mode_ptr->htotal;
 		tmp = div_u64(tmp, 1000000);
 		mode_ptr->clock = (int) tmp;
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 2/2] drm/i915/selftests: Use mul_u32_u32() for 32b x 32b -> 64b result

[Chris Wilson]

As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/selftests/i915_gem_timeline.c | 2 +-
 drivers/gpu/drm/i915/selftests/i915_random.c       | 5 -----
 drivers/gpu/drm/i915/selftests/i915_random.h       | 5 +++++
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
index 7a44dab631b8..4795877abe56 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
@@ -121,7 +121,7 @@ static int igt_sync(void *arg)
 
 static unsigned int random_engine(struct rnd_state *rnd)
 {
-	return ((u64)prandom_u32_state(rnd) * I915_NUM_ENGINES) >> 32;
+	return i915_prandom_u32_max_state(I915_NUM_ENGINES, rnd);
 }
 
 static int bench_sync(void *arg)
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c
index d044bf9a6feb..ea0f5dbc0eb7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.c
+++ b/drivers/gpu/drm/i915/selftests/i915_random.c
@@ -41,11 +41,6 @@ u64 i915_prandom_u64_state(struct rnd_state *rnd)
 	return x;
 }
 
-static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
-{
-	return upper_32_bits((u64)prandom_u32_state(state) * ep_ro);
-}
-
 void i915_random_reorder(unsigned int *order, unsigned int count,
 			 struct rnd_state *state)
 {
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 6c9379871384..7dffedc501ca 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -43,6 +43,11 @@
 
 u64 i915_prandom_u64_state(struct rnd_state *rnd);
 
+static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
+{
+	return upper_32_bits(mul_u32_u32(prandom_u32_state(state), ep_ro));
+}
+
 unsigned int *i915_random_order(unsigned int count,
 				struct rnd_state *state);
 void i915_random_reorder(unsigned int *order,
-- 
2.14.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 2/2] drm/i915/selftests: Use mul_u32_u32() for 32b x 32b -> 64b result

[Ville Syrjälä]

On Wed, Sep 13, 2017 at 11:51:54AM +0100, Chris Wilson wrote:
> As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
> mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
> for performing a 32b x 32b multiply returning a 64b result (i.e. where
> we idiomatically use u64 result = (u64)x * (u32)x).
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/selftests/i915_gem_timeline.c | 2 +-
>  drivers/gpu/drm/i915/selftests/i915_random.c       | 5 -----
>  drivers/gpu/drm/i915/selftests/i915_random.h       | 5 +++++
>  3 files changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
> index 7a44dab631b8..4795877abe56 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_gem_timeline.c
> @@ -121,7 +121,7 @@ static int igt_sync(void *arg)
>  
>  static unsigned int random_engine(struct rnd_state *rnd)
>  {
> -	return ((u64)prandom_u32_state(rnd) * I915_NUM_ENGINES) >> 32;
> +	return i915_prandom_u32_max_state(I915_NUM_ENGINES, rnd);
>  }
>  
>  static int bench_sync(void *arg)
> diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c
> index d044bf9a6feb..ea0f5dbc0eb7 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_random.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_random.c
> @@ -41,11 +41,6 @@ u64 i915_prandom_u64_state(struct rnd_state *rnd)
>  	return x;
>  }
>  
> -static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
> -{
> -	return upper_32_bits((u64)prandom_u32_state(state) * ep_ro);
> -}
> -
>  void i915_random_reorder(unsigned int *order, unsigned int count,
>  			 struct rnd_state *state)
>  {
> diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
> index 6c9379871384..7dffedc501ca 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_random.h
> +++ b/drivers/gpu/drm/i915/selftests/i915_random.h
> @@ -43,6 +43,11 @@
>  
>  u64 i915_prandom_u64_state(struct rnd_state *rnd);
>  
> +static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
> +{
> +	return upper_32_bits(mul_u32_u32(prandom_u32_state(state), ep_ro));
> +}
> +
>  unsigned int *i915_random_order(unsigned int count,
>  				struct rnd_state *state);
>  void i915_random_reorder(unsigned int *order,
> -- 
> 2.14.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx