[PATCH resend-for-CI 1/3] drm/i915: Extract knowledge of register forcewake domains

[PATCH resend-for-CI 1/3] drm/i915: Extract knowledge of register forcewake domains

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Knowledge of which register per platform belonds in which
forcewake domain was embedded in the MMIO accessors themselves.

Extract it into standalone macros so they can be used from
new code in the following patches.

This causes GCC to compile some of the MMIO accessors slightly
differently and grows the code a tiny amount. But none of the
growth is on the fast-path so it does not matter hugely.

Affected sizes before:

00000000000026f0 00000000000001a5 t gen6_read16
0000000000002390 00000000000001a5 t gen6_read32
00000000000028a0 00000000000001a5 t gen6_read64

00000000000061d0 000000000000019e t gen8_write16
0000000000006510 000000000000019d t gen8_write32
0000000000006370 000000000000019d t gen8_write64
00000000000021f0 000000000000019d t gen8_write8

Affected sizes after:

0000000000002840 00000000000001aa t gen6_read16
00000000000024e0 00000000000001a9 t gen6_read32
00000000000029f0 00000000000001a9 t gen6_read64

0000000000004f20 00000000000001b5 t gen8_write16
0000000000004ba0 00000000000001b4 t gen8_write32
00000000000050e0 00000000000001b4 t gen8_write64
0000000000004d60 00000000000001b4 t gen8_write8

Other MMIO accessors are not affected in size.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_uncore.c | 255 ++++++++++++++++++++++--------------
 1 file changed, 155 insertions(+), 100 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index dcf38bb5a097..6b98b8a6d64a 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -552,6 +552,16 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
 /* We give fast paths for the really cool registers */
 #define NEEDS_FORCE_WAKE(reg) ((reg) < 0x40000)
 
+#define __gen6_reg_read_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd; \
+	if (NEEDS_FORCE_WAKE(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else \
+		__fwd = 0; \
+	__fwd; \
+})
+
 #define REG_RANGE(reg, start, end) ((reg) >= (start) && (reg) < (end))
 
 #define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
@@ -565,6 +575,49 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
 	 REG_RANGE((reg), 0x22000, 0x24000) || \
 	 REG_RANGE((reg), 0x30000, 0x40000))
 
+#define __vlv_reg_read_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd = 0; \
+	if (!NEEDS_FORCE_WAKE(offset)) \
+		__fwd = 0; \
+	else if (FORCEWAKE_VLV_RENDER_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else if (FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_MEDIA; \
+	__fwd; \
+})
+
+static const i915_reg_t gen8_shadowed_regs[] = {
+	FORCEWAKE_MT,
+	GEN6_RPNSWREQ,
+	GEN6_RC_VIDEO_FREQ,
+	RING_TAIL(RENDER_RING_BASE),
+	RING_TAIL(GEN6_BSD_RING_BASE),
+	RING_TAIL(VEBOX_RING_BASE),
+	RING_TAIL(BLT_RING_BASE),
+	/* TODO: Other registers are not yet used */
+};
+
+static bool is_gen8_shadowed(u32 offset)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(gen8_shadowed_regs); i++)
+		if (offset == gen8_shadowed_regs[i].reg)
+			return true;
+
+	return false;
+}
+
+#define __gen8_reg_write_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd; \
+	if (NEEDS_FORCE_WAKE(offset) && !is_gen8_shadowed(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else \
+		__fwd = 0; \
+	__fwd; \
+})
+
 #define FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg) \
 	(REG_RANGE((reg), 0x2000, 0x4000) || \
 	 REG_RANGE((reg), 0x5200, 0x8000) || \
@@ -587,6 +640,34 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
 	 REG_RANGE((reg), 0x9000, 0xB000) || \
 	 REG_RANGE((reg), 0xF000, 0x10000))
 
+#define __chv_reg_read_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd = 0; \
+	if (!NEEDS_FORCE_WAKE(offset)) \
+		__fwd = 0; \
+	else if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_MEDIA; \
+	else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
+	__fwd; \
+})
+
+#define __chv_reg_write_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd = 0; \
+	if (!NEEDS_FORCE_WAKE(offset) || is_gen8_shadowed(offset)) \
+		__fwd = 0; \
+	else if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_MEDIA; \
+	else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
+	__fwd; \
+})
+
 #define FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg) \
 	REG_RANGE((reg), 0xB00,  0x2000)
 
@@ -619,6 +700,64 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
 	 !FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg) && \
 	 !FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg))
 
+#define SKL_NEEDS_FORCE_WAKE(reg) \
+	((reg) < 0x40000 && !FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg))
+
+#define __gen9_reg_read_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd; \
+	if (!SKL_NEEDS_FORCE_WAKE(offset)) \
+		__fwd = 0; \
+	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_MEDIA; \
+	else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
+	else \
+		__fwd = FORCEWAKE_BLITTER; \
+	__fwd; \
+})
+
+static const i915_reg_t 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(u32 offset)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(gen9_shadowed_regs); i++)
+		if (offset == gen9_shadowed_regs[i].reg)
+			return true;
+
+	return false;
+}
+
+#define __gen9_reg_write_fw_domains(offset) \
+({ \
+	enum forcewake_domains __fwd; \
+	if (!SKL_NEEDS_FORCE_WAKE(offset) || is_gen9_shadowed(offset)) \
+		__fwd = 0; \
+	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER; \
+	else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_MEDIA; \
+	else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(offset)) \
+		__fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
+	else \
+		__fwd = FORCEWAKE_BLITTER; \
+	__fwd; \
+})
+
 static void
 ilk_dummy_write(struct drm_i915_private *dev_priv)
 {
@@ -742,9 +881,11 @@ static inline void __force_wake_auto(struct drm_i915_private *dev_priv,
 #define __gen6_read(x) \
 static u##x \
 gen6_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
+	enum forcewake_domains fw_engine; \
 	GEN6_READ_HEADER(x); \
-	if (NEEDS_FORCE_WAKE(offset)) \
-		__force_wake_auto(dev_priv, FORCEWAKE_RENDER); \
+	fw_engine = __gen6_reg_read_fw_domains(offset); \
+	if (fw_engine) \
+		__force_wake_auto(dev_priv, fw_engine); \
 	val = __raw_i915_read##x(dev_priv, reg); \
 	GEN6_READ_FOOTER; \
 }
@@ -752,14 +893,9 @@ gen6_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
 #define __vlv_read(x) \
 static u##x \
 vlv_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
-	enum forcewake_domains fw_engine = 0; \
+	enum forcewake_domains fw_engine; \
 	GEN6_READ_HEADER(x); \
-	if (!NEEDS_FORCE_WAKE(offset)) \
-		fw_engine = 0; \
-	else if (FORCEWAKE_VLV_RENDER_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER; \
-	else if (FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_MEDIA; \
+	fw_engine = __vlv_reg_read_fw_domains(offset); \
 	if (fw_engine) \
 		__force_wake_auto(dev_priv, fw_engine); \
 	val = __raw_i915_read##x(dev_priv, reg); \
@@ -769,40 +905,21 @@ vlv_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
 #define __chv_read(x) \
 static u##x \
 chv_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \
-	enum forcewake_domains fw_engine = 0; \
+	enum forcewake_domains fw_engine; \
 	GEN6_READ_HEADER(x); \
-	if (!NEEDS_FORCE_WAKE(offset)) \
-		fw_engine = 0; \
-	else if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER; \
-	else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_MEDIA; \
-	else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
+	fw_engine = __chv_reg_read_fw_domains(offset); \
 	if (fw_engine) \
 		__force_wake_auto(dev_priv, fw_engine); \
 	val = __raw_i915_read##x(dev_priv, reg); \
 	GEN6_READ_FOOTER; \
 }
 
-#define SKL_NEEDS_FORCE_WAKE(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, i915_reg_t reg, bool trace) { \
 	enum forcewake_domains fw_engine; \
 	GEN6_READ_HEADER(x); \
-	if (!SKL_NEEDS_FORCE_WAKE(offset)) \
-		fw_engine = 0; \
-	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER; \
-	else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_MEDIA; \
-	else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
-	else \
-		fw_engine = FORCEWAKE_BLITTER; \
+	fw_engine = __gen9_reg_read_fw_domains(offset); \
 	if (fw_engine) \
 		__force_wake_auto(dev_priv, fw_engine); \
 	val = __raw_i915_read##x(dev_priv, reg); \
@@ -941,34 +1058,14 @@ hsw_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool t
 	GEN6_WRITE_FOOTER; \
 }
 
-static const i915_reg_t gen8_shadowed_regs[] = {
-	FORCEWAKE_MT,
-	GEN6_RPNSWREQ,
-	GEN6_RC_VIDEO_FREQ,
-	RING_TAIL(RENDER_RING_BASE),
-	RING_TAIL(GEN6_BSD_RING_BASE),
-	RING_TAIL(VEBOX_RING_BASE),
-	RING_TAIL(BLT_RING_BASE),
-	/* TODO: Other registers are not yet used */
-};
-
-static bool is_gen8_shadowed(struct drm_i915_private *dev_priv,
-			     i915_reg_t reg)
-{
-	int i;
-	for (i = 0; i < ARRAY_SIZE(gen8_shadowed_regs); i++)
-		if (i915_mmio_reg_equal(reg, gen8_shadowed_regs[i]))
-			return true;
-
-	return false;
-}
-
 #define __gen8_write(x) \
 static void \
 gen8_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \
+	enum forcewake_domains fw_engine; \
 	GEN6_WRITE_HEADER; \
-	if (NEEDS_FORCE_WAKE(offset) && !is_gen8_shadowed(dev_priv, reg)) \
-		__force_wake_auto(dev_priv, FORCEWAKE_RENDER); \
+	fw_engine = __gen8_reg_write_fw_domains(offset); \
+	if (fw_engine) \
+		__force_wake_auto(dev_priv, fw_engine); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	GEN6_WRITE_FOOTER; \
 }
@@ -976,64 +1073,22 @@ gen8_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool
 #define __chv_write(x) \
 static void \
 chv_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \
-	enum forcewake_domains fw_engine = 0; \
+	enum forcewake_domains fw_engine; \
 	GEN6_WRITE_HEADER; \
-	if (!NEEDS_FORCE_WAKE(offset) || \
-	    is_gen8_shadowed(dev_priv, reg)) \
-		fw_engine = 0; \
-	else if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER; \
-	else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_MEDIA; \
-	else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
+	fw_engine = __chv_reg_write_fw_domains(offset); \
 	if (fw_engine) \
 		__force_wake_auto(dev_priv, fw_engine); \
 	__raw_i915_write##x(dev_priv, reg, val); \
 	GEN6_WRITE_FOOTER; \
 }
 
-static const i915_reg_t 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,
-			     i915_reg_t reg)
-{
-	int i;
-	for (i = 0; i < ARRAY_SIZE(gen9_shadowed_regs); i++)
-		if (i915_mmio_reg_equal(reg, gen9_shadowed_regs[i]))
-			return true;
-
-	return false;
-}
-
 #define __gen9_write(x) \
 static void \
 gen9_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, \
 		bool trace) { \
 	enum forcewake_domains fw_engine; \
 	GEN6_WRITE_HEADER; \
-	if (!SKL_NEEDS_FORCE_WAKE(offset) || \
-	    is_gen9_shadowed(dev_priv, reg)) \
-		fw_engine = 0; \
-	else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER; \
-	else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_MEDIA; \
-	else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(offset)) \
-		fw_engine = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \
-	else \
-		fw_engine = FORCEWAKE_BLITTER; \
+	fw_engine = __gen9_reg_write_fw_domains(offset); \
 	if (fw_engine) \
 		__force_wake_auto(dev_priv, fw_engine); \
 	__raw_i915_write##x(dev_priv, reg, val); \
-- 
1.9.1

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

[PATCH resend-for-CI 2/3] drm/i915: Remove forcewake request registers from the shadowed table

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Chris Wilson points out that we can remove them from the array
since they are always written to with raw accessors.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_uncore.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 6b98b8a6d64a..41dd30f6ddbb 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -588,7 +588,6 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv)
 })
 
 static const i915_reg_t gen8_shadowed_regs[] = {
-	FORCEWAKE_MT,
 	GEN6_RPNSWREQ,
 	GEN6_RC_VIDEO_FREQ,
 	RING_TAIL(RENDER_RING_BASE),
@@ -724,9 +723,6 @@ static const i915_reg_t gen9_shadowed_regs[] = {
 	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 */
-- 
1.9.1

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

[PATCH resend-for-CI 3/3] drm/i915: Only grab correct forcewake for the engine with execlists

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Rather than blindly waking up all forcewake domains on command
submission, we can teach each engine what is (or are) the correct
one to take.

On platforms with multiple forcewake domains like VLV, CHV, SKL
and BXT, this has the potential of lowering the GPU and CPU
power use and submission latency.

To implement it we add a function named
intel_uncore_forcewake_for_reg whose purpose is to query which
forcewake domains need to be taken to read or write a specific
register with raw mmio accessors.

These enables the execlists engine setup  to query which
forcewake domains are relevant per engine on the currently
running platform.

v2:
  * Kerneldoc.
  * Split from intel_uncore.c macro extraction, WARN_ON,
    no warns on old platforms. (Chris Wilson)

v3:
  * Single domain per engine, mention all registers,
    bi-directional function and a new name, fix handling
    of gen6 and gen7 writes. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h         |   7 +++
 drivers/gpu/drm/i915/intel_lrc.c        |  27 ++++++--
 drivers/gpu/drm/i915/intel_lrc.h        |   1 +
 drivers/gpu/drm/i915/intel_ringbuffer.h |   1 +
 drivers/gpu/drm/i915/intel_uncore.c     | 108 ++++++++++++++++++++++++++++++++
 5 files changed, 139 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1e15c21257ea..f5c91b01194f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -634,6 +634,13 @@ enum forcewake_domains {
 			 FORCEWAKE_MEDIA)
 };
 
+#define FW_REG_READ  (1)
+#define FW_REG_WRITE (2)
+
+enum forcewake_domains
+intel_uncore_forcewake_for_reg(struct drm_i915_private *dev_priv,
+			       i915_reg_t reg, unsigned int op);
+
 struct intel_uncore_funcs {
 	void (*force_wake_get)(struct drm_i915_private *dev_priv,
 							enum forcewake_domains domains);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0d6dc5ec4a46..e6e69c2f2386 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -418,6 +418,7 @@ static void execlists_submit_requests(struct drm_i915_gem_request *rq0,
 				      struct drm_i915_gem_request *rq1)
 {
 	struct drm_i915_private *dev_priv = rq0->i915;
+	unsigned int fw_domains = rq0->engine->fw_domains;
 
 	execlists_update_context(rq0);
 
@@ -425,11 +426,11 @@ static void execlists_submit_requests(struct drm_i915_gem_request *rq0,
 		execlists_update_context(rq1);
 
 	spin_lock_irq(&dev_priv->uncore.lock);
-	intel_uncore_forcewake_get__locked(dev_priv, FORCEWAKE_ALL);
+	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
 
 	execlists_elsp_write(rq0, rq1);
 
-	intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL);
+	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
 	spin_unlock_irq(&dev_priv->uncore.lock);
 }
 
@@ -552,7 +553,7 @@ static void intel_lrc_irq_handler(unsigned long data)
 	unsigned int csb_read = 0, i;
 	unsigned int submit_contexts = 0;
 
-	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+	intel_uncore_forcewake_get(dev_priv, engine->fw_domains);
 
 	status_pointer = I915_READ_FW(RING_CONTEXT_STATUS_PTR(engine));
 
@@ -577,7 +578,7 @@ static void intel_lrc_irq_handler(unsigned long data)
 		      _MASKED_FIELD(GEN8_CSB_READ_PTR_MASK,
 				    engine->next_context_status_buffer << 8));
 
-	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+	intel_uncore_forcewake_put(dev_priv, engine->fw_domains);
 
 	spin_lock(&engine->execlist_lock);
 
@@ -2089,7 +2090,9 @@ logical_ring_default_irqs(struct intel_engine_cs *engine, unsigned shift)
 static int
 logical_ring_init(struct drm_device *dev, struct intel_engine_cs *engine)
 {
-	struct intel_context *dctx = to_i915(dev)->kernel_context;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_context *dctx = dev_priv->kernel_context;
+	enum forcewake_domains fw_domains;
 	int ret;
 
 	/* Intentionally left blank. */
@@ -2111,6 +2114,20 @@ logical_ring_init(struct drm_device *dev, struct intel_engine_cs *engine)
 
 	logical_ring_init_platform_invariants(engine);
 
+	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
+						    RING_ELSP(engine),
+						    FW_REG_WRITE);
+
+	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
+						     RING_CONTEXT_STATUS_PTR(engine),
+						     FW_REG_READ | FW_REG_WRITE);
+
+	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
+						     RING_CONTEXT_STATUS_BUF_BASE(engine),
+						     FW_REG_READ);
+
+	engine->fw_domains = fw_domains;
+
 	ret = i915_cmd_parser_init_ring(engine);
 	if (ret)
 		goto error;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 0b0853eee91e..8de1ea536ad4 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -34,6 +34,7 @@
 #define	  CTX_CTRL_INHIBIT_SYN_CTX_SWITCH	(1 << 3)
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
 #define   CTX_CTRL_RS_CTX_ENABLE                (1 << 1)
+#define RING_CONTEXT_STATUS_BUF_BASE(ring)	_MMIO((ring)->mmio_base + 0x370)
 #define RING_CONTEXT_STATUS_BUF_LO(ring, i)	_MMIO((ring)->mmio_base + 0x370 + (i) * 8)
 #define RING_CONTEXT_STATUS_BUF_HI(ring, i)	_MMIO((ring)->mmio_base + 0x370 + (i) * 8 + 4)
 #define RING_CONTEXT_STATUS_PTR(ring)		_MMIO((ring)->mmio_base + 0x3a0)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 78dc46864a10..2ade194bbea9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -270,6 +270,7 @@ struct  intel_engine_cs {
 	spinlock_t execlist_lock; /* used inside tasklet, use spin_lock_bh */
 	struct list_head execlist_queue;
 	struct list_head execlist_retired_req_list;
+	unsigned int fw_domains;
 	unsigned int next_context_status_buffer;
 	unsigned int idle_lite_restore_wa;
 	bool disable_lite_restore_wa;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 41dd30f6ddbb..24b0a9ae3df3 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1772,3 +1772,111 @@ intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv)
 
 	return false;
 }
+
+static enum forcewake_domains
+intel_uncore_forcewake_for_read(struct drm_i915_private *dev_priv,
+				i915_reg_t reg)
+{
+	enum forcewake_domains fw_domains;
+
+	if (intel_vgpu_active(dev_priv->dev))
+		return 0;
+
+	switch (INTEL_INFO(dev_priv)->gen) {
+	case 9:
+		fw_domains = __gen9_reg_read_fw_domains(i915_mmio_reg_offset(reg));
+		break;
+	case 8:
+		if (IS_CHERRYVIEW(dev_priv))
+			fw_domains = __chv_reg_read_fw_domains(i915_mmio_reg_offset(reg));
+		else
+			fw_domains = __gen6_reg_read_fw_domains(i915_mmio_reg_offset(reg));
+		break;
+	case 7:
+	case 6:
+		if (IS_VALLEYVIEW(dev_priv))
+			fw_domains = __vlv_reg_read_fw_domains(i915_mmio_reg_offset(reg));
+		else
+			fw_domains = __gen6_reg_read_fw_domains(i915_mmio_reg_offset(reg));
+		break;
+	default:
+		MISSING_CASE(INTEL_INFO(dev_priv)->gen);
+	case 5: /* forcewake was introduced with gen6 */
+	case 4:
+	case 3:
+	case 2:
+		return 0;
+	}
+
+	WARN_ON(fw_domains & ~dev_priv->uncore.fw_domains);
+
+	return fw_domains;
+}
+
+static enum forcewake_domains
+intel_uncore_forcewake_for_write(struct drm_i915_private *dev_priv,
+				 i915_reg_t reg)
+{
+	enum forcewake_domains fw_domains;
+
+	if (intel_vgpu_active(dev_priv->dev))
+		return 0;
+
+	switch (INTEL_INFO(dev_priv)->gen) {
+	case 9:
+		fw_domains = __gen9_reg_write_fw_domains(i915_mmio_reg_offset(reg));
+		break;
+	case 8:
+		if (IS_CHERRYVIEW(dev_priv))
+			fw_domains = __chv_reg_write_fw_domains(i915_mmio_reg_offset(reg));
+		else
+			fw_domains = __gen8_reg_write_fw_domains(i915_mmio_reg_offset(reg));
+		break;
+	case 7:
+	case 6:
+		fw_domains = FORCEWAKE_RENDER;
+		break;
+	default:
+		MISSING_CASE(INTEL_INFO(dev_priv)->gen);
+	case 5:
+	case 4:
+	case 3:
+	case 2:
+		return 0;
+	}
+
+	WARN_ON(fw_domains & ~dev_priv->uncore.fw_domains);
+
+	return fw_domains;
+}
+
+/**
+ * intel_uncore_forcewake_for_reg - which forcewake domains are needed to access
+ * 				    a register
+ * @dev_priv: pointer to struct drm_i915_private
+ * @reg: register in question
+ * @op: operation bitmask of FW_REG_READ and/or FW_REG_WRITE
+ *
+ * Returns a set of forcewake domains required to be taken with for example
+ * intel_uncore_forcewake_get for the specified register to be accessible in the
+ * specified mode (read, write or read/write) with raw mmio accessors.
+ *
+ * NOTE: On Gen6 and Gen7 write forcewake domain (FORCEWAKE_RENDER) requires the
+ * callers to do FIFO management on their own or risk losing writes.
+ */
+enum forcewake_domains
+intel_uncore_forcewake_for_reg(struct drm_i915_private *dev_priv,
+			       i915_reg_t reg, unsigned int op)
+{
+	enum forcewake_domains fw_domains = 0;
+
+	WARN_ON(!op);
+
+	if (op & FW_REG_READ)
+		fw_domains = intel_uncore_forcewake_for_read(dev_priv, reg);
+
+	if (op & FW_REG_WRITE)
+		fw_domains |= intel_uncore_forcewake_for_write(dev_priv, reg);
+
+	return fw_domains;
+}
-- 
1.9.1

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

✗ Fi.CI.BAT: failure for series starting with [resend-for-CI,1/3] drm/i915: Extract knowledge of register forcewake domains

[Patchwork]

== Series Details ==

Series: series starting with [resend-for-CI,1/3] drm/i915: Extract knowledge of register forcewake domains
URL   : https://patchwork.freedesktop.org/series/5593/
State : failure

== Summary ==

Series 5593v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/5593/revisions/1/mbox/

Test drv_hangman:
        Subgroup error-state-basic:
                fail       -> PASS       (ilk-hp8440p)
Test kms_flip:
        Subgroup basic-flip-vs-modeset:
                pass       -> DMESG-WARN (ilk-hp8440p) UNSTABLE
Test pm_rpm:
        Subgroup basic-rte:
                dmesg-warn -> PASS       (bsw-nuc-2)

bdw-nuci7        total:203  pass:191  dwarn:0   dfail:0   fail:0   skip:12 
bdw-ultra        total:203  pass:180  dwarn:0   dfail:0   fail:0   skip:23 
bsw-nuc-2        total:202  pass:163  dwarn:0   dfail:0   fail:0   skip:39 
byt-nuc          total:202  pass:164  dwarn:0   dfail:0   fail:0   skip:38 
hsw-gt2          total:203  pass:184  dwarn:0   dfail:0   fail:0   skip:19 
ilk-hp8440p      total:203  pass:134  dwarn:1   dfail:0   fail:0   skip:68 
skl-i7k-2        total:203  pass:178  dwarn:0   dfail:0   fail:0   skip:25 
skl-nuci5        total:203  pass:192  dwarn:0   dfail:0   fail:0   skip:11 
snb-x220t        total:203  pass:165  dwarn:0   dfail:0   fail:1   skip:37 
BOOT FAILED for snb-dellxps

Results at /archive/results/CI_IGT_test/Patchwork_1871/

d89f227a17b175fce74e11b2d5fa2a41f86fc489 drm-intel-nightly: 2016y-04m-12d-13h-31m-26s UTC integration manifest
9bd8d7e drm/i915: Only grab correct forcewake for the engine with execlists
9c6a1ec drm/i915: Remove forcewake request registers from the shadowed table
c6211b2 drm/i915: Extract knowledge of register forcewake domains

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

Re: ✗ Fi.CI.BAT: failure for series starting with [resend-for-CI,1/3] drm/i915: Extract knowledge of register forcewake domains

[Tvrtko Ursulin]

On 12/04/16 15:29, Patchwork wrote:
> == Series Details ==
>
> Series: series starting with [resend-for-CI,1/3] drm/i915: Extract knowledge of register forcewake domains
> URL   : https://patchwork.freedesktop.org/series/5593/
> State : failure
>
> == Summary ==
>
> Series 5593v1 Series without cover letter
> http://patchwork.freedesktop.org/api/1.0/series/5593/revisions/1/mbox/
>
> Test drv_hangman:
>          Subgroup error-state-basic:
>                  fail       -> PASS       (ilk-hp8440p)
> Test kms_flip:
>          Subgroup basic-flip-vs-modeset:
>                  pass       -> DMESG-WARN (ilk-hp8440p) UNSTABLE

Sporadic ILK fifo underruns: 
https://bugs.freedesktop.org/show_bug.cgi?id=93787

> Test pm_rpm:
>          Subgroup basic-rte:
>                  dmesg-warn -> PASS       (bsw-nuc-2)
>
> bdw-nuci7        total:203  pass:191  dwarn:0   dfail:0   fail:0   skip:12
> bdw-ultra        total:203  pass:180  dwarn:0   dfail:0   fail:0   skip:23
> bsw-nuc-2        total:202  pass:163  dwarn:0   dfail:0   fail:0   skip:39
> byt-nuc          total:202  pass:164  dwarn:0   dfail:0   fail:0   skip:38
> hsw-gt2          total:203  pass:184  dwarn:0   dfail:0   fail:0   skip:19
> ilk-hp8440p      total:203  pass:134  dwarn:1   dfail:0   fail:0   skip:68
> skl-i7k-2        total:203  pass:178  dwarn:0   dfail:0   fail:0   skip:25
> skl-nuci5        total:203  pass:192  dwarn:0   dfail:0   fail:0   skip:11
> snb-x220t        total:203  pass:165  dwarn:0   dfail:0   fail:1   skip:37
> BOOT FAILED for snb-dellxps
>
> Results at /archive/results/CI_IGT_test/Patchwork_1871/
>
> d89f227a17b175fce74e11b2d5fa2a41f86fc489 drm-intel-nightly: 2016y-04m-12d-13h-31m-26s UTC integration manifest
> 9bd8d7e drm/i915: Only grab correct forcewake for the engine with execlists
> 9c6a1ec drm/i915: Remove forcewake request registers from the shadowed table
> c6211b2 drm/i915: Extract knowledge of register forcewake domains

Squeaky clean - merged. Thanks for the review.

Hope this makes a difference on some platform.

Regards,

Tvrtko

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