Merge tag 'v3.14-rc5' into patchwork

Linux 3.14-rc5

* tag 'v3.14-rc5': (1117 commits)
  Linux 3.14-rc5
  drm/vmwgfx: avoid null pointer dereference at failure paths
  drm/vmwgfx: Make sure backing mobs are cleared when allocated. Update driver date.
  drm/vmwgfx: Remove some unused surface formats
  MAINTAINERS: add maintainer entry for Armada DRM driver
  arm64: Fix !CONFIG_SMP kernel build
  arm64: mm: Add double logical invert to pte accessors
  dm cache: fix truncation bug when mapping I/O to >2TB fast device
  perf tools: Fix strict alias issue for find_first_bit
  powerpc/powernv: Fix indirect XSCOM unmangling
  powerpc/powernv: Fix opal_xscom_{read,write} prototype
  powerpc/powernv: Refactor PHB diag-data dump
  powerpc/powernv: Dump PHB diag-data immediately
  powerpc: Increase stack redzone for 64-bit userspace to 512 bytes
  powerpc/ftrace: bugfix for test_24bit_addr
  powerpc/crashdump : Fix page frame number check in copy_oldmem_page
  powerpc/le: Ensure that the 'stop-self' RTAS token is handled correctly
  kvm, vmx: Really fix lazy FPU on nested guest
  perf tools: fix BFD detection on opensuse
  drm/radeon: enable speaker allocation setup on dce3.2
  ...

9 files changed, 75 insertions, 24 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a2bf8e3f739..df77e20e3c3d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1831,6 +1831,14 @@ struct drm_i915_file_private {
 
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev)		(IS_I830(dev) || IS_845G(dev))
+/*
+ * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
+ * even when in MSI mode. This results in spurious interrupt warnings if the
+ * legacy irq no. is shared with another device. The kernel then disables that
+ * interrupt source and so prevents the other device from working properly.
+ */
+#define HAS_AUX_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
+#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
 
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index d7fd2fd2f0a5..990cf8f43efd 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -146,7 +146,10 @@ static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
 		va_list tmp;
 
 		va_copy(tmp, args);
-		if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
+		len = vsnprintf(NULL, 0, f, tmp);
+		va_end(tmp);
+
+		if (!__i915_error_seek(e, len))
 			return;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 17d8fcb1b6f7..9fec71175571 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -567,8 +567,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe)
 
 		vbl_start = mode->crtc_vblank_start * mode->crtc_htotal;
 	} else {
-		enum transcoder cpu_transcoder =
-			intel_pipe_to_cpu_transcoder(dev_priv, pipe);
+		enum transcoder cpu_transcoder = (enum transcoder) pipe;
 		u32 htotal;
 
 		htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9fa24347963a..4c1672809493 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8586,6 +8586,20 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 	if (ring->id == RCS)
 		len += 6;
 
+	/*
+	 * BSpec MI_DISPLAY_FLIP for IVB:
+	 * "The full packet must be contained within the same cache line."
+	 *
+	 * Currently the LRI+SRM+MI_DISPLAY_FLIP all fit within the same
+	 * cacheline, if we ever start emitting more commands before
+	 * the MI_DISPLAY_FLIP we may need to first emit everything else,
+	 * then do the cacheline alignment, and finally emit the
+	 * MI_DISPLAY_FLIP.
+	 */
+	ret = intel_ring_cacheline_align(ring);
+	if (ret)
+		goto err_unpin;
+
 	ret = intel_ring_begin(ring, len);
 	if (ret)
 		goto err_unpin;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 5ede4e8e290d..57552eb386b0 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -404,7 +404,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	int i, ret, recv_bytes;
 	uint32_t status;
 	int try, precharge, clock = 0;
-	bool has_aux_irq = true;
+	bool has_aux_irq = HAS_AUX_IRQ(dev);
 	uint32_t timeout;
 
 	/* dp aux is extremely sensitive to irq latency, hence request the
@@ -537,6 +537,7 @@ intel_dp_aux_native_write(struct intel_dp *intel_dp,
 	uint8_t	msg[20];
 	int msg_bytes;
 	uint8_t	ack;
+	int retry;
 
 	if (WARN_ON(send_bytes > 16))
 		return -E2BIG;
@@ -548,19 +549,21 @@ intel_dp_aux_native_write(struct intel_dp *intel_dp,
 	msg[3] = send_bytes - 1;
 	memcpy(&msg[4], send, send_bytes);
 	msg_bytes = send_bytes + 4;
-	for (;;) {
+	for (retry = 0; retry < 7; retry++) {
 		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1);
 		if (ret < 0)
 			return ret;
 		ack >>= 4;
 		if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK)
-			break;
+			return send_bytes;
 		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
-			udelay(100);
+			usleep_range(400, 500);
 		else
 			return -EIO;
 	}
-	return send_bytes;
+
+	DRM_ERROR("too many retries, giving up\n");
+	return -EIO;
 }
 
 /* Write a single byte to the aux channel in native mode */
@@ -582,6 +585,7 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp,
 	int reply_bytes;
 	uint8_t ack;
 	int ret;
+	int retry;
 
 	if (WARN_ON(recv_bytes > 19))
 		return -E2BIG;
@@ -595,7 +599,7 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp,
 	msg_bytes = 4;
 	reply_bytes = recv_bytes + 1;
 
-	for (;;) {
+	for (retry = 0; retry < 7; retry++) {
 		ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes,
 				      reply, reply_bytes);
 		if (ret == 0)
@@ -608,10 +612,13 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp,
 			return ret - 1;
 		}
 		else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
-			udelay(100);
+			usleep_range(400, 500);
 		else
 			return -EIO;
 	}
+
+	DRM_ERROR("too many retries, giving up\n");
+	return -EIO;
 }
 
 static int
@@ -1869,10 +1876,12 @@ static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 
 	mutex_unlock(&dev_priv->dpio_lock);
 
-	/* init power sequencer on this pipe and port */
-	intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
-						      &power_seq);
+	if (is_edp(intel_dp)) {
+		/* init power sequencer on this pipe and port */
+		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+							      &power_seq);
+	}
 
 	intel_enable_dp(encoder);
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index b1dc33f47899..d33b61d0dd33 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -258,13 +258,6 @@ intel_gpio_setup(struct intel_gmbus *bus, u32 pin)
 	algo->data = bus;
 }
 
-/*
- * gmbus on gen4 seems to be able to generate legacy interrupts even when in MSI
- * mode. This results in spurious interrupt warnings if the legacy irq no. is
- * shared with another device. The kernel then disables that interrupt source
- * and so prevents the other device from working properly.
- */
-#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
 static int
 gmbus_wait_hw_status(struct drm_i915_private *dev_priv,
 		     u32 gmbus2_status,
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 4e960ec7419f..acde2945eb8a 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -226,6 +226,8 @@ struct opregion_asle {
 #define ACPI_DIGITAL_OUTPUT (3<<8)
 #define ACPI_LVDS_OUTPUT (4<<8)
 
+#define MAX_DSLP	1500
+
 #ifdef CONFIG_ACPI
 static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 {
@@ -260,10 +262,11 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 		/* The spec says 2ms should be the default, but it's too small
 		 * for some machines. */
 		dslp = 50;
-	} else if (dslp > 500) {
+	} else if (dslp > MAX_DSLP) {
 		/* Hey bios, trust must be earned. */
-		WARN_ONCE(1, "excessive driver sleep timeout (DSPL) %u\n", dslp);
-		dslp = 500;
+		DRM_INFO_ONCE("ACPI BIOS requests an excessive sleep of %u ms, "
+			      "using %u ms instead\n", dslp, MAX_DSLP);
+		dslp = MAX_DSLP;
 	}
 
 	/* The spec tells us to do this, but we are the only user... */
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b7f1742caf87..31b36c5ac894 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1653,6 +1653,27 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+/* Align the ring tail to a cacheline boundary */
+int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
+{
+	int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t);
+	int ret;
+
+	if (num_dwords == 0)
+		return 0;
+
+	ret = intel_ring_begin(ring, num_dwords);
+	if (ret)
+		return ret;
+
+	while (num_dwords--)
+		intel_ring_emit(ring, MI_NOOP);
+
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
 void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 71a73f4fe252..0b243ce33714 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -233,6 +233,7 @@ intel_write_status_page(struct intel_ring_buffer *ring,
 void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
 
 int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
+int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring);
 static inline void intel_ring_emit(struct intel_ring_buffer *ring,
 				   u32 data)
 {