Merge tag 'drm-intel-fixes-2021-03-18' of...

Merge tag 'drm-intel-fixes-2021-03-18' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes

drm/i915 fixes for v5.12-rc4:
- Workaround async flip + VT-d frame corruption on HSW/BDW
- Fix NMI watchdog crash due to uninitialized OA buffer use on gen12+
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/87blbg8y5t.fsf@intel.com

drivers/gpu/drm/i915/i915_perf.c

@@ -603,7 +603,6 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 {
 	int report_size = stream->oa_buffer.format_size;
 	struct drm_i915_perf_record_header header;
-	u32 sample_flags = stream->sample_flags;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
 	header.pad = 0;
@@ -617,10 +616,8 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 		return -EFAULT;
 	buf += sizeof(header);
 
-	if (sample_flags & SAMPLE_OA_REPORT) {
 	if (copy_to_user(buf, report, report_size))
 		return -EFAULT;
-	}
 
 	(*offset) += header.size;
 
@@ -2682,7 +2679,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 
 	stream->perf->ops.oa_enable(stream);
 
-	if (stream->periodic)
+	if (stream->sample_flags & SAMPLE_OA_REPORT)
 		hrtimer_start(&stream->poll_check_timer,
 			      ns_to_ktime(stream->poll_oa_period),
 			      HRTIMER_MODE_REL_PINNED);
@@ -2745,7 +2742,7 @@ static void i915_oa_stream_disable(struct i915_perf_stream *stream)
 {
 	stream->perf->ops.oa_disable(stream);
 
-	if (stream->periodic)
+	if (stream->sample_flags & SAMPLE_OA_REPORT)
 		hrtimer_cancel(&stream->poll_check_timer);
 }
 
@@ -3028,7 +3025,7 @@ static ssize_t i915_perf_read(struct file *file,
 	 * disabled stream as an error. In particular it might otherwise lead
 	 * to a deadlock for blocking file descriptors...
 	 */
-	if (!stream->enabled)
+	if (!stream->enabled || !(stream->sample_flags & SAMPLE_OA_REPORT))
 		return -EIO;
 
 	if (!(file->f_flags & O_NONBLOCK)) {

drivers/gpu/drm/i915/i915_reg.h

@@ -3316,7 +3316,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define ILK_DISPLAY_CHICKEN1	_MMIO(0x42000)
 #define   ILK_FBCQ_DIS		(1 << 22)
-#define	  ILK_PABSTRETCH_DIS	(1 << 21)
+#define   ILK_PABSTRETCH_DIS	REG_BIT(21)
+#define   ILK_SABSTRETCH_DIS	REG_BIT(20)
+#define   IVB_PRI_STRETCH_MAX_MASK	REG_GENMASK(21, 20)
+#define   IVB_PRI_STRETCH_MAX_X8	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 0)
+#define   IVB_PRI_STRETCH_MAX_X4	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 1)
+#define   IVB_PRI_STRETCH_MAX_X2	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 2)
+#define   IVB_PRI_STRETCH_MAX_X1	REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 3)
+#define   IVB_SPR_STRETCH_MAX_MASK	REG_GENMASK(19, 18)
+#define   IVB_SPR_STRETCH_MAX_X8	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 0)
+#define   IVB_SPR_STRETCH_MAX_X4	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 1)
+#define   IVB_SPR_STRETCH_MAX_X2	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 2)
+#define   IVB_SPR_STRETCH_MAX_X1	REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 3)
 
 
 /*
@@ -8039,6 +8050,16 @@ enum {
 
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
+#define  HSW_PRI_STRETCH_MAX_MASK	REG_GENMASK(28, 27)
+#define  HSW_PRI_STRETCH_MAX_X8		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 0)
+#define  HSW_PRI_STRETCH_MAX_X4		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 1)
+#define  HSW_PRI_STRETCH_MAX_X2		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 2)
+#define  HSW_PRI_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 3)
+#define  HSW_SPR_STRETCH_MAX_MASK	REG_GENMASK(26, 25)
+#define  HSW_SPR_STRETCH_MAX_X8		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 0)
+#define  HSW_SPR_STRETCH_MAX_X4		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 1)
+#define  HSW_SPR_STRETCH_MAX_X2		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 2)
+#define  HSW_SPR_STRETCH_MAX_X1		REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3)
 #define  HSW_FBCQ_DIS			(1 << 22)
 #define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)

drivers/gpu/drm/i915/intel_pm.c

@@ -7245,11 +7245,16 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
-	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 	for_each_pipe(dev_priv, pipe) {
+		/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 		intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
 			   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) |
 			   BDW_DPRS_MASK_VBLANK_SRD);
+
+		/* Undocumented but fixes async flip + VT-d corruption */
+		if (intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
 	}
 
 	/* WaVSRefCountFullforceMissDisable:bdw */
@@ -7285,11 +7290,20 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
+	enum pipe pipe;
+
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
 	intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A),
 		   intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) |
 		   HSW_FBCQ_DIS);
 
+	for_each_pipe(dev_priv, pipe) {
+		/* Undocumented but fixes async flip + VT-d corruption */
+		if (intel_vtd_active())
+			intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+					 HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
+	}
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 		   intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |