Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm merge (part 1) from Dave Airlie:
 "So first of all my tree and uapi stuff has a conflict mess, its my
  fault as the nouveau stuff didn't hit -next as were trying to rebase
  regressions out of it before we merged.

  Highlights:
   - SH mobile modesetting driver and associated helpers
   - some DRM core documentation
   - i915 modesetting rework, haswell hdmi, haswell and vlv fixes, write
     combined pte writing, ilk rc6 support,
   - nouveau: major driver rework into a hw core driver, makes features
     like SLI a lot saner to implement,
   - psb: add eDP/DP support for Cedarview
   - radeon: 2 layer page tables, async VM pte updates, better PLL
     selection for > 2 screens, better ACPI interactions

  The rest is general grab bag of fixes.

  So why part 1? well I have the exynos pull req which came in a bit
  late but was waiting for me to do something they shouldn't have and it
  looks fairly safe, and David Howells has some more header cleanups
  he'd like me to pull, that seem like a good idea, but I'd like to get
  this merge out of the way so -next dosen't get blocked."

Tons of conflicts mostly due to silly include line changes, but mostly
mindless.  A few other small semantic conflicts too, noted from Dave's
pre-merged branch.

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (447 commits)
  drm/nv98/crypt: fix fuc build with latest envyas
  drm/nouveau/devinit: fixup various issues with subdev ctor/init ordering
  drm/nv41/vm: fix and enable use of "real" pciegart
  drm/nv44/vm: fix and enable use of "real" pciegart
  drm/nv04/dmaobj: fixup vm target handling in preparation for nv4x pcie
  drm/nouveau: store supported dma mask in vmmgr
  drm/nvc0/ibus: initial implementation of subdev
  drm/nouveau/therm: add support for fan-control modes
  drm/nouveau/hwmon: rename pwm0* to pmw1* to follow hwmon's rules
  drm/nouveau/therm: calculate the pwm divisor on nv50+
  drm/nouveau/fan: rewrite the fan tachometer driver to get more precision, faster
  drm/nouveau/therm: move thermal-related functions to the therm subdev
  drm/nouveau/bios: parse the pwm divisor from the perf table
  drm/nouveau/therm: use the EXTDEV table to detect i2c monitoring devices
  drm/nouveau/therm: rework thermal table parsing
  drm/nouveau/gpio: expose the PWM/TOGGLE parameter found in the gpio vbios table
  drm/nouveau: fix pm initialization order
  drm/nouveau/bios: check that fixed tvdac gpio data is valid before using it
  drm/nouveau: log channel debug/error messages from client object rather than drm client
  drm/nouveau: have drm debugging macros build on top of core macros
  ...

1 files changed, 60 insertions, 55 deletions

diff --git a/drivers/gpu/drm/radeon/r600_blit.c b/drivers/gpu/drm/radeon/r600_blit.c
index 26ace5623dc7..77da1f9c0b8e 100644
--- a/drivers/gpu/drm/radeon/r600_blit.c
+++ b/drivers/gpu/drm/radeon/r600_blit.c
@@ -488,31 +488,36 @@ set_default_state(drm_radeon_private_t *dev_priv)
         ADVANCE_RING();
 }
 
-static uint32_t i2f(uint32_t input)
+/* 23 bits of float fractional data */
+#define I2F_FRAC_BITS  23
+#define I2F_MASK ((1 << I2F_FRAC_BITS) - 1)
+
+/*
+ * Converts unsigned integer into 32-bit IEEE floating point representation.
+ * Will be exact from 0 to 2^24.  Above that, we round towards zero
+ * as the fractional bits will not fit in a float.  (It would be better to
+ * round towards even as the fpu does, but that is slower.)
+ */
+__pure uint32_t int2float(uint32_t x)
 {
-        u32 result, i, exponent, fraction;
-
-        if ((input & 0x3fff) == 0)
-                result = 0; /* 0 is a special case */
-        else {
-                exponent = 140; /* exponent biased by 127; */
-                fraction = (input & 0x3fff) << 10; /* cheat and only
-                                                      handle numbers below 2^^15 */
-                for (i = 0; i < 14; i++) {
-                        if (fraction & 0x800000)
-                                break;
-                        else {
-                                fraction = fraction << 1; /* keep
-                                                             shifting left until top bit = 1 */
-                                exponent = exponent - 1;
-                        }
-                }
-                result = exponent << 23 | (fraction & 0x7fffff); /* mask
-                                                                    off top bit; assumed 1 */
-        }
-        return result;
-}
+        uint32_t msb, exponent, fraction;
+
+        /* Zero is special */
+        if (!x) return 0;
+
+        /* Get location of the most significant bit */
+        msb = __fls(x);
 
+        /*
+         * Use a rotate instead of a shift because that works both leftwards
+         * and rightwards due to the mod(32) behaviour.  This means we don't
+         * need to check to see if we are above 2^24 or not.
+         */
+        fraction = ror32(x, (msb - I2F_FRAC_BITS) & 0x1f) & I2F_MASK;
+        exponent = (127 + msb) << I2F_FRAC_BITS;
+
+        return fraction + exponent;
+}
 
 static int r600_nomm_get_vb(struct drm_device *dev)
 {
@@ -631,20 +636,20 @@ r600_blit_copy(struct drm_device *dev,
                                 vb = r600_nomm_get_vb_ptr(dev);
                         }
 
-                        vb[0] = i2f(dst_x);
+                        vb[0] = int2float(dst_x);
                         vb[1] = 0;
-                        vb[2] = i2f(src_x);
+                        vb[2] = int2float(src_x);
                         vb[3] = 0;
 
-                        vb[4] = i2f(dst_x);
-                        vb[5] = i2f(h);
-                        vb[6] = i2f(src_x);
-                        vb[7] = i2f(h);
+                        vb[4] = int2float(dst_x);
+                        vb[5] = int2float(h);
+                        vb[6] = int2float(src_x);
+                        vb[7] = int2float(h);
 
-                        vb[8] = i2f(dst_x + cur_size);
-                        vb[9] = i2f(h);
-                        vb[10] = i2f(src_x + cur_size);
-                        vb[11] = i2f(h);
+                        vb[8] = int2float(dst_x + cur_size);
+                        vb[9] = int2float(h);
+                        vb[10] = int2float(src_x + cur_size);
+                        vb[11] = int2float(h);
 
                         /* src */
                         set_tex_resource(dev_priv, FMT_8,
@@ -720,20 +725,20 @@ r600_blit_copy(struct drm_device *dev,
                                 vb = r600_nomm_get_vb_ptr(dev);
                         }
 
-                        vb[0] = i2f(dst_x / 4);
+                        vb[0] = int2float(dst_x / 4);
                         vb[1] = 0;
-                        vb[2] = i2f(src_x / 4);
+                        vb[2] = int2float(src_x / 4);
                         vb[3] = 0;
 
-                        vb[4] = i2f(dst_x / 4);
-                        vb[5] = i2f(h);
-                        vb[6] = i2f(src_x / 4);
-                        vb[7] = i2f(h);
+                        vb[4] = int2float(dst_x / 4);
+                        vb[5] = int2float(h);
+                        vb[6] = int2float(src_x / 4);
+                        vb[7] = int2float(h);
 
-                        vb[8] = i2f((dst_x + cur_size) / 4);
-                        vb[9] = i2f(h);
-                        vb[10] = i2f((src_x + cur_size) / 4);
-                        vb[11] = i2f(h);
+                        vb[8] = int2float((dst_x + cur_size) / 4);
+                        vb[9] = int2float(h);
+                        vb[10] = int2float((src_x + cur_size) / 4);
+                        vb[11] = int2float(h);
 
                         /* src */
                         set_tex_resource(dev_priv, FMT_8_8_8_8,
@@ -803,20 +808,20 @@ r600_blit_swap(struct drm_device *dev,
         dx2 = dx + w;
         dy2 = dy + h;
 
-        vb[0] = i2f(dx);
-        vb[1] = i2f(dy);
-        vb[2] = i2f(sx);
-        vb[3] = i2f(sy);
+        vb[0] = int2float(dx);
+        vb[1] = int2float(dy);
+        vb[2] = int2float(sx);
+        vb[3] = int2float(sy);
 
-        vb[4] = i2f(dx);
-        vb[5] = i2f(dy2);
-        vb[6] = i2f(sx);
-        vb[7] = i2f(sy2);
+        vb[4] = int2float(dx);
+        vb[5] = int2float(dy2);
+        vb[6] = int2float(sx);
+        vb[7] = int2float(sy2);
 
-        vb[8] = i2f(dx2);
-        vb[9] = i2f(dy2);
-        vb[10] = i2f(sx2);
-        vb[11] = i2f(sy2);
+        vb[8] = int2float(dx2);
+        vb[9] = int2float(dy2);
+        vb[10] = int2float(sx2);
+        vb[11] = int2float(sy2);
 
         switch(cpp) {
         case 4: