[PATCH 4/4] drm/intel: Push get_scanout_position() timestamping into kms driver.
Move the ktime_get() clock readouts and potential preempt_disable() calls from drm core into kms driver to make it compatible with the api changes in the drm core. The intel-kms driver needs to take the uncore.lock inside i915_get_crtc_scanoutpos() and intel_pipe_in_vblank(). This is incompatible with the preempt_disable() on a PREEMPT_RT patched kernel, as regular spin locks must not be taken within a preempt_disable'd section. Lock contention on the uncore.lock also introduced too much uncertainty in vblank timestamps. Push the ktime_get() timestamping for scanoutpos queries and potential preempt_disable_rt() into i915_get_crtc_scanoutpos(), so these problems can be avoided: 1. First lock the uncore.lock (might sleep on a PREEMPT_RT kernel). 2. preempt_disable_rt() (will be added by the rt-linux folks). 3. ktime_get() a timestamp before scanout pos query. 4. Do all mmio reads as fast as possible without grabbing any new locks! 5. ktime_get() a post-query timestamp. 6. preempt_enable_rt() 7. Unlock the uncore.lock. This reduces timestamp uncertainty on a low-end HP Atom Mini netbook with Intel GMA-950 nicely: Before: 3-8 usecs with spikes > 20 usecs, triggering query retries. After : Typically 1 usec (98% of all samples), occassionally 2 usecs (2% of all samples), with maximum of 3 usecs (a handful). v2: Fix formatting of new multi-line code comments. Signed-off-by: Mario Kleiner Reviewed-by: Ville Syrj?l? Reviewed-by: Alex Deucher --- drivers/gpu/drm/i915/i915_irq.c | 54 +++ 1 file changed, 43 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 156a1a4..7cafe64 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -599,35 +599,40 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) return I915_READ(reg); } -static bool intel_pipe_in_vblank(struct drm_device *dev, enum pipe pipe) +/* raw reads, only for fast reads of display block, no need for forcewake etc. */ +#define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__)) +#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__)) + +static bool intel_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe) { struct drm_i915_private *dev_priv = dev->dev_private; uint32_t status; + int reg; if (IS_VALLEYVIEW(dev)) { status = pipe == PIPE_A ? I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT : I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT; - return I915_READ(VLV_ISR) & status; + reg = VLV_ISR; } else if (IS_GEN2(dev)) { status = pipe == PIPE_A ? I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT : I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT; - return I915_READ16(ISR) & status; + reg = ISR; } else if (INTEL_INFO(dev)->gen < 5) { status = pipe == PIPE_A ? I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT : I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT; - return I915_READ(ISR) & status; + reg = ISR; } else if (INTEL_INFO(dev)->gen < 7) { status = pipe == PIPE_A ? DE_PIPEA_VBLANK : DE_PIPEB_VBLANK; - return I915_READ(DEISR) & status; + reg = DEISR; } else { switch (pipe) { default: @@ -642,12 +647,17 @@ static bool intel_pipe_in_vblank(struct drm_device *dev, enum pipe pipe) break; } - return I915_READ(DEISR) & status; + reg = DEISR; } + + if (IS_GEN2(dev)) + return __raw_i915_read16(dev_priv, reg) & status; + else + return __raw_i915_read32(dev_priv, reg) & status; } static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, -int *vpos, int *hpos) +int *vpos, int *hpos, ktime_t *stime, ktime_t *etime) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; @@ -657,6 +667,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, int vbl_start, vbl_end, htotal, vtotal; bool in_vbl = true; int ret = 0; + unsigned long irqflags; if (!intel_crtc->active) { DRM_DEBUG_DRIVER("trying to get scanoutpos for disabled " @@ -671,14 +682,27 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, ret |= DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE; + /* +* Lock uncore.lock, as we will do multiple timing critical raw +* register reads, potentially with preemption
[PATCH 4/4] drm/intel: Push get_scanout_position() timestamping into kms driver.
Move the ktime_get() clock readouts and potential preempt_disable() calls from drm core into kms driver to make it compatible with the api changes in the drm core. The intel-kms driver needs to take the uncore.lock inside i915_get_crtc_scanoutpos() and intel_pipe_in_vblank(). This is incompatible with the preempt_disable() on a PREEMPT_RT patched kernel, as regular spin locks must not be taken within a preempt_disable'd section. Lock contention on the uncore.lock also introduced too much uncertainty in vblank timestamps. Push the ktime_get() timestamping for scanoutpos queries and potential preempt_disable_rt() into i915_get_crtc_scanoutpos(), so these problems can be avoided: 1. First lock the uncore.lock (might sleep on a PREEMPT_RT kernel). 2. preempt_disable_rt() (will be added by the rt-linux folks). 3. ktime_get() a timestamp before scanout pos query. 4. Do all mmio reads as fast as possible without grabbing any new locks! 5. ktime_get() a post-query timestamp. 6. preempt_enable_rt() 7. Unlock the uncore.lock. This reduces timestamp uncertainty on a low-end HP Atom Mini netbook with Intel GMA-950 nicely: Before: 3-8 usecs with spikes > 20 usecs, triggering query retries. After : Typically 1 usec (98% of all samples), occassionally 2 usecs (2% of all samples), with maximum of 3 usecs (a handful). Signed-off-by: Mario Kleiner --- drivers/gpu/drm/i915/i915_irq.c | 53 +++ 1 file changed, 42 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 156a1a4..a3e41d3 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -599,35 +599,40 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) return I915_READ(reg); } -static bool intel_pipe_in_vblank(struct drm_device *dev, enum pipe pipe) +/* raw reads, only for fast reads of display block, no need for forcewake etc. */ +#define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__)) +#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__)) + +static bool intel_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe) { struct drm_i915_private *dev_priv = dev->dev_private; uint32_t status; + int reg; if (IS_VALLEYVIEW(dev)) { status = pipe == PIPE_A ? I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT : I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT; - return I915_READ(VLV_ISR) & status; + reg = VLV_ISR; } else if (IS_GEN2(dev)) { status = pipe == PIPE_A ? I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT : I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT; - return I915_READ16(ISR) & status; + reg = ISR; } else if (INTEL_INFO(dev)->gen < 5) { status = pipe == PIPE_A ? I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT : I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT; - return I915_READ(ISR) & status; + reg = ISR; } else if (INTEL_INFO(dev)->gen < 7) { status = pipe == PIPE_A ? DE_PIPEA_VBLANK : DE_PIPEB_VBLANK; - return I915_READ(DEISR) & status; + reg = DEISR; } else { switch (pipe) { default: @@ -642,12 +647,17 @@ static bool intel_pipe_in_vblank(struct drm_device *dev, enum pipe pipe) break; } - return I915_READ(DEISR) & status; + reg = DEISR; } + + if (IS_GEN2(dev)) + return __raw_i915_read16(dev_priv, reg) & status; + else + return __raw_i915_read32(dev_priv, reg) & status; } static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, -int *vpos, int *hpos) +int *vpos, int *hpos, ktime_t *stime, ktime_t *etime) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; @@ -657,6 +667,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, int vbl_start, vbl_end, htotal, vtotal; bool in_vbl = true; int ret = 0; + unsigned long irqflags; if (!intel_crtc->active) { DRM_DEBUG_DRIVER("trying to get scanoutpos for disabled " @@ -671,14 +682,26 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, ret |= DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE; + /* Lock uncore.lock, as we will do multiple timing critical raw +* register reads, potentially with preemption disabled, so the +* following code must not block on uncore.lock. +*/ +