| Message ID | 1428689711-3541-2-git-send-email-rodrigo.vivi@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
>-----Original Message----- >From: Vivi, Rodrigo >Sent: Friday, April 10, 2015 11:45 PM >To: intel-gfx@lists.freedesktop.org >Cc: Vivi, Rodrigo; R, Durgadoss; Runyan, Arthur J >Subject: [PATCH 2/5] drm/i915: PSR: Fix DP_PSR_NO_TRAIN_ON_EXIT logic > >Since the beginning there is a missunderstanding on the meaning of this >dpcd bit. >This bit shouldn't indicate whether to use link standby or not, but just >be used to configure TP1, TP2 and TP3 times and tell hw aux should be skiped >since HW is the responsible one. > >Even with help of frontbuffer tracking, HW is still fully responsible for >PSR exit logic with/without DP training. > >DP_PSR_NO_TRAIN_ON_EXIT means the source doesn't need to do the training, but >it doesn't tell to avoid TP patterns, so we will send minimal TP1 and avoid >TP2. It also means that sink itself can take up to 5 idle frames for training. >6 in our case since we might be off by 1. So we also increment idle_frames by 4 >here. > >v2: Fix and improve commit message (Durga). >v3: Use minimal TP1 time avoiding TP2 and increase idle frame. > >Cc: Durgadoss R <durgadoss.r@intel.com> >Cc: Arthur Runyan <arthur.j.runyan@intel.com> >Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> >--- > drivers/gpu/drm/i915/intel_psr.c | 13 +++++++++---- > 1 file changed, 9 insertions(+), 4 deletions(-) > >diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c >index db95b39..0e3b652 100644 >--- a/drivers/gpu/drm/i915/intel_psr.c >+++ b/drivers/gpu/drm/i915/intel_psr.c >@@ -264,11 +264,17 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp) > uint32_t val = 0x0; > const uint32_t link_entry_time = EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES; > >- if (dev_priv->psr.link_standby) { >+ if (dev_priv->psr.link_standby) > val |= EDP_PSR_LINK_STANDBY; >+ >+ if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) { >+ /* It doesn't mean we shouldn't send TPS patters, so let's >+ send the minimal TP1 possible and skip TP2. */ We can fix the multi-line comment style though, Reviewed-by: Durgadoss R <durgadoss.r@intel.com> Thanks, Durga >+ val |= EDP_PSR_TP1_TIME_100us; > val |= EDP_PSR_TP2_TP3_TIME_0us; >- val |= EDP_PSR_TP1_TIME_0us; > val |= EDP_PSR_SKIP_AUX_EXIT; >+ /* Sink should be able to train with the 5 or 6 idle patterns */ >+ idle_frames += 4; > } > > I915_WRITE(EDP_PSR_CTL(dev), val | >@@ -381,8 +387,7 @@ void intel_psr_enable(struct intel_dp *intel_dp) > /* First we check VBT, but we must respect sink and source > * known restrictions */ > dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link; >- if ((intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) || >- (IS_BROADWELL(dev) && intel_dig_port->port != PORT_A)) >+ if (IS_BROADWELL(dev) && intel_dig_port->port != PORT_A) > dev_priv->psr.link_standby = true; > > dev_priv->psr.busy_frontbuffer_bits = 0; >-- >2.1.0
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index db95b39..0e3b652 100644 --- a/drivers/gpu/drm/i915/intel_psr.c +++ b/drivers/gpu/drm/i915/intel_psr.c @@ -264,11 +264,17 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp) uint32_t val = 0x0; const uint32_t link_entry_time = EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES; - if (dev_priv->psr.link_standby) { + if (dev_priv->psr.link_standby) val |= EDP_PSR_LINK_STANDBY; + + if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) { + /* It doesn't mean we shouldn't send TPS patters, so let's + send the minimal TP1 possible and skip TP2. */ + val |= EDP_PSR_TP1_TIME_100us; val |= EDP_PSR_TP2_TP3_TIME_0us; - val |= EDP_PSR_TP1_TIME_0us; val |= EDP_PSR_SKIP_AUX_EXIT; + /* Sink should be able to train with the 5 or 6 idle patterns */ + idle_frames += 4; } I915_WRITE(EDP_PSR_CTL(dev), val | @@ -381,8 +387,7 @@ void intel_psr_enable(struct intel_dp *intel_dp) /* First we check VBT, but we must respect sink and source * known restrictions */ dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link; - if ((intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) || - (IS_BROADWELL(dev) && intel_dig_port->port != PORT_A)) + if (IS_BROADWELL(dev) && intel_dig_port->port != PORT_A) dev_priv->psr.link_standby = true; dev_priv->psr.busy_frontbuffer_bits = 0;
Since the beginning there is a missunderstanding on the meaning of this dpcd bit. This bit shouldn't indicate whether to use link standby or not, but just be used to configure TP1, TP2 and TP3 times and tell hw aux should be skiped since HW is the responsible one. Even with help of frontbuffer tracking, HW is still fully responsible for PSR exit logic with/without DP training. DP_PSR_NO_TRAIN_ON_EXIT means the source doesn't need to do the training, but it doesn't tell to avoid TP patterns, so we will send minimal TP1 and avoid TP2. It also means that sink itself can take up to 5 idle frames for training. 6 in our case since we might be off by 1. So we also increment idle_frames by 4 here. v2: Fix and improve commit message (Durga). v3: Use minimal TP1 time avoiding TP2 and increase idle frame. Cc: Durgadoss R <durgadoss.r@intel.com> Cc: Arthur Runyan <arthur.j.runyan@intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> --- drivers/gpu/drm/i915/intel_psr.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)