[PATCH 0/2] SKL stage 1 part 4

[PATCH 0/2] SKL stage 1 part 4

[Damien Lespiau]

A couple more patches around gen9 forcewake have just been r-bed by Mika. The
changes are fairly contained and shouldn't affect other platforms, a nice
property this late in the cycle (I won't be able to say the same for AUX power
well, so well ahem 3.20 for them maybe, ...)

This also means current work to simplify fw handling will need to be rebased on
top.

-- 
Damien

Zhe Wang (2):
  drm/i915/skl: Gen9 multi-engine forcewake
  drm/i915: Gen9 shadowed registers

 drivers/gpu/drm/i915/intel_uncore.c | 139 ++++++++++++++++++++++++++++++++++++
 1 file changed, 139 insertions(+)

-- 
1.8.3.1

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

[PATCH 1/2] drm/i915/skl: Gen9 multi-engine forcewake

[Damien Lespiau]

From: Zhe Wang <zhe1.wang@intel.com>

Enable multi-engine forcewake for Gen9.

v2: (Damien)
- Rebase on top of nightly
- Move the register range definitions to intel_uncore.c
- Whitespace fixes

v3: (Addressing Mika's comment, done by Damien)
- Use REG_RANGE() (introduced after the patch was written)
- Add a SKL_NEEDS_FORCE_WAKE() macro that gets rid of a useless
  comparison to FORCEWAKE (reg 0xa18c is not used on SKL)

v4: (Damien)
- Use newly introduced ASSIGN_READ/WRITE_MMIO_VFUNCS() macros

Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Zhe Wang <zhe1.wang@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
---
 drivers/gpu/drm/i915/intel_uncore.c | 115 ++++++++++++++++++++++++++++++++++++
 1 file changed, 115 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index c98421d..4c10faa 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -670,6 +670,34 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
 	 REG_RANGE((reg), 0x14000, 0x14400) || \
 	 REG_RANGE((reg), 0x22000, 0x24000))
 
+#define FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg) \
+	REG_RANGE((reg), 0xC00,  0x2000)
+
+#define FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x2000, 0x4000) || \
+	 REG_RANGE((reg), 0x5200, 0x8000) || \
+	 REG_RANGE((reg), 0x8300, 0x8500) || \
+	 REG_RANGE((reg), 0x8C00, 0x8D00) || \
+	 REG_RANGE((reg), 0xB000, 0xB480) || \
+	 REG_RANGE((reg), 0xE000, 0xE800))
+
+#define FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x8800, 0x8A00) || \
+	 REG_RANGE((reg), 0xD000, 0xD800) || \
+	 REG_RANGE((reg), 0x12000, 0x14000) || \
+	 REG_RANGE((reg), 0x1A000, 0x1EA00) || \
+	 REG_RANGE((reg), 0x30000, 0x40000))
+
+#define FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg) \
+	REG_RANGE((reg), 0x9400, 0x9800)
+
+#define FORCEWAKE_GEN9_BLITTER_RANGE_OFFSET(reg) \
+	((reg) < 0x40000 &&\
+	 !FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg) && \
+	 !FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg) && \
+	 !FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg) && \
+	 !FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg))
+
 static void
 ilk_dummy_write(struct drm_i915_private *dev_priv)
 {
@@ -800,6 +828,45 @@ chv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	REG_READ_FOOTER; \
 }
 
+#define SKL_NEEDS_FORCE_WAKE(dev_priv, reg)	\
+	 ((reg) < 0x40000 && !FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg))
+
+#define __gen9_read(x) \
+static u##x \
+gen9_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
+	REG_READ_HEADER(x); \
+	if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		val = __raw_i915_read##x(dev_priv, reg); \
+	} else { \
+		unsigned fwengine = 0; \
+		if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_rendercount == 0) \
+				fwengine = FORCEWAKE_RENDER; \
+		} else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_mediacount == 0) \
+				fwengine = FORCEWAKE_MEDIA; \
+		} else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_rendercount == 0) \
+				fwengine |= FORCEWAKE_RENDER; \
+			if (dev_priv->uncore.fw_mediacount == 0) \
+				fwengine |= FORCEWAKE_MEDIA; \
+		} else { \
+			if (dev_priv->uncore.fw_blittercount == 0) \
+				fwengine = FORCEWAKE_BLITTER; \
+		} \
+		if (fwengine) \
+			dev_priv->uncore.funcs.force_wake_get(dev_priv, fwengine); \
+		val = __raw_i915_read##x(dev_priv, reg); \
+		if (fwengine) \
+			dev_priv->uncore.funcs.force_wake_put(dev_priv, fwengine); \
+	} \
+	REG_READ_FOOTER; \
+}
+
+__gen9_read(8)
+__gen9_read(16)
+__gen9_read(32)
+__gen9_read(64)
 __chv_read(8)
 __chv_read(16)
 __chv_read(32)
@@ -821,6 +888,7 @@ __gen4_read(16)
 __gen4_read(32)
 __gen4_read(64)
 
+#undef __gen9_read
 #undef __chv_read
 #undef __vlv_read
 #undef __gen6_read
@@ -958,6 +1026,45 @@ chv_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace)
 	REG_WRITE_FOOTER; \
 }
 
+#define __gen9_write(x) \
+static void \
+gen9_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, \
+		bool trace) { \
+	REG_WRITE_HEADER; \
+	if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		__raw_i915_write##x(dev_priv, reg, val); \
+	} else { \
+		unsigned fwengine = 0; \
+		if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_rendercount == 0) \
+				fwengine = FORCEWAKE_RENDER; \
+		} else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_mediacount == 0) \
+				fwengine = FORCEWAKE_MEDIA; \
+		} else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_rendercount == 0) \
+				fwengine |= FORCEWAKE_RENDER; \
+			if (dev_priv->uncore.fw_mediacount == 0) \
+				fwengine |= FORCEWAKE_MEDIA; \
+		} else { \
+			if (dev_priv->uncore.fw_blittercount == 0) \
+				fwengine = FORCEWAKE_BLITTER; \
+		} \
+		if (fwengine) \
+			dev_priv->uncore.funcs.force_wake_get(dev_priv, \
+					fwengine); \
+		__raw_i915_write##x(dev_priv, reg, val); \
+		if (fwengine) \
+			dev_priv->uncore.funcs.force_wake_put(dev_priv, \
+					fwengine); \
+	} \
+	REG_WRITE_FOOTER; \
+}
+
+__gen9_write(8)
+__gen9_write(16)
+__gen9_write(32)
+__gen9_write(64)
 __chv_write(8)
 __chv_write(16)
 __chv_write(32)
@@ -983,6 +1090,7 @@ __gen4_write(16)
 __gen4_write(32)
 __gen4_write(64)
 
+#undef __gen9_write
 #undef __chv_write
 #undef __gen8_write
 #undef __hsw_write
@@ -1066,6 +1174,13 @@ void intel_uncore_init(struct drm_device *dev)
 
 	switch (INTEL_INFO(dev)->gen) {
 	default:
+		WARN_ON(1);
+		return;
+	case 9:
+		ASSIGN_WRITE_MMIO_VFUNCS(gen9);
+		ASSIGN_READ_MMIO_VFUNCS(gen9);
+		break;
+	case 8:
 		if (IS_CHERRYVIEW(dev)) {
 			ASSIGN_WRITE_MMIO_VFUNCS(chv);
 			ASSIGN_READ_MMIO_VFUNCS(chv);
-- 
1.8.3.1

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

[PATCH 2/2] drm/i915: Gen9 shadowed registers

[Damien Lespiau]

From: Zhe Wang <zhe1.wang@intel.com>

For MMIO registers which are shadowed, force wake is not needed to
write to these registers.

v2: Rebase on top of nightly (Damien)

v3: Rebase on top of "Gen9 multiple-engine forcewake" changes

v4: (Mika, Bob, done by Damien)
- Reorder the shadowed registers by popularity

Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Zhe Wang <zhe1.wang@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
---
 drivers/gpu/drm/i915/intel_uncore.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 4c10faa..1a3e485 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1026,12 +1026,36 @@ chv_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace)
 	REG_WRITE_FOOTER; \
 }
 
+static const u32 gen9_shadowed_regs[] = {
+	RING_TAIL(RENDER_RING_BASE),
+	RING_TAIL(GEN6_BSD_RING_BASE),
+	RING_TAIL(VEBOX_RING_BASE),
+	RING_TAIL(BLT_RING_BASE),
+	FORCEWAKE_BLITTER_GEN9,
+	FORCEWAKE_RENDER_GEN9,
+	FORCEWAKE_MEDIA_GEN9,
+	GEN6_RPNSWREQ,
+	GEN6_RC_VIDEO_FREQ,
+	/* TODO: Other registers are not yet used */
+};
+
+static bool is_gen9_shadowed(struct drm_i915_private *dev_priv, u32 reg)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(gen9_shadowed_regs); i++)
+		if (reg == gen9_shadowed_regs[i])
+			return true;
+
+	return false;
+}
+
 #define __gen9_write(x) \
 static void \
 gen9_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, \
 		bool trace) { \
 	REG_WRITE_HEADER; \
-	if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+	if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg)) || \
+			is_gen9_shadowed(dev_priv, reg)) { \
 		__raw_i915_write##x(dev_priv, reg, val); \
 	} else { \
 		unsigned fwengine = 0; \
-- 
1.8.3.1

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

Re: [PATCH 2/2] drm/i915: Gen9 shadowed registers

[shuang.he]

Tested-By: PRC QA PRTS (Patch Regression Test System Contact: shuang.he@intel.com)
-------------------------------------Summary-------------------------------------
Platform          Delta          drm-intel-nightly          Series Applied
PNV                                  367/367              367/367
ILK              +2                 373/375              375/375
SNB                                  450/450              450/450
IVB                 -2              503/503              501/503
BYT                                  289/289              289/289
HSW                 -3              567/567              564/567
BDW                                  417/417              417/417
-------------------------------------Detailed-------------------------------------
Platform  Test                                drm-intel-nightly          Series Applied
ILK  igt_kms_flip_flip-vs-panning      NSPT(1, M26)      PASS(2, M37)
ILK  igt_kms_flip_nonexisting-fb      DMESG_WARN(1, M26)      PASS(2, M37)
IVB  igt_gem_bad_reloc_negative-reloc      PASS(1, M21)      NSPT(2, M34)
IVB  igt_gem_bad_reloc_negative-reloc-lut      PASS(1, M21)      NSPT(1, M34)PASS(1, M34)
HSW  igt_gem_bad_reloc_negative-reloc-lut      PASS(1, M19)      NSPT(2, M40)
HSW  igt_kms_rotation_crc_primary-rotation      PASS(1, M19)      DMESG_WARN(1, M40)PASS(1, M40)
HSW  igt_pm_rc6_residency_rc6-accuracy      PASS(1, M19)      FAIL(1, M40)PASS(1, M40)
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 0/2] SKL stage 1 part 4

[Daniel Vetter]

On Thu, Nov 20, 2014 at 01:42:54PM +0000, Damien Lespiau wrote:
> A couple more patches around gen9 forcewake have just been r-bed by Mika. The
> changes are fairly contained and shouldn't affect other platforms, a nice
> property this late in the cycle (I won't be able to say the same for AUX power
> well, so well ahem 3.20 for them maybe, ...)
> 
> This also means current work to simplify fw handling will need to be rebased on
> top.

Both merged to dinq, thanks.
-Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx