aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu
diff options
context:
space:
mode:
authorIlija Hadzic <ihadzic@research.bell-labs.com>2012-02-02 10:26:24 -0500
committerDave Airlie <airlied@redhat.com>2012-02-02 15:54:48 +0000
commit52b53a0bf8026a322cfa6cfec6a10dd31fef8752 (patch)
treed2247328b87baf65a3245be2ea7e430f14b2be95 /drivers/gpu
parent304a48400d9718f74ec35ae46f30868a5f4c4516 (diff)
drm/radeon/kms/blit: fix blit copy for very large buffers
Evergreen and NI blit copy was broken if the buffer maps to a rectangle whose one dimension is 16384 (max dimension allowed by these chips). In the mainline kernel, the problem is exposed only when buffers are very large (1G), but it's still a problem. The problem could be exposed for smaller buffers if anyone modifies the algorithm for rectangle construction in r600_blit_create_rect() (the reason why someone would modify that algorithm is to tune the performance of buffer moves). The root cause was in i2f() function which only operated on range between 0 and 16383. Fix this by extending the range of i2f() function to 0 to 32767. While at it improve the function so that the range can be easily extended in the future (if it becomes necessary), cleanup lines over 80 characters, and replace in-line comments with one strategic comment that explains the crux of the function. Credits to michel@daenzer.net for pointing out the root cause of the bug. v2: Fix I2F_MAX_INPUT constant definition goof and warn only once if input argument is out of range. Edit the comment a little bit to avoid some linguistic confusion and make it look better in general. Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Michel Dänzer <michel@daenzer.net> Signed-off-by: Dave Airlie <airlied@redhat.com>
Diffstat (limited to 'drivers/gpu')
-rw-r--r--drivers/gpu/drm/radeon/r600_blit_kms.c35
1 files changed, 25 insertions, 10 deletions
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index d996f438113..accc032c103 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -468,27 +468,42 @@ set_default_state(struct radeon_device *rdev)
radeon_ring_write(ring, sq_stack_resource_mgmt_2);
}
+#define I2F_MAX_BITS 15
+#define I2F_MAX_INPUT ((1 << I2F_MAX_BITS) - 1)
+#define I2F_SHIFT (24 - I2F_MAX_BITS)
+
+/*
+ * Converts unsigned integer into 32-bit IEEE floating point representation.
+ * Conversion is not universal and only works for the range from 0
+ * to 2^I2F_MAX_BITS-1. Currently we only use it with inputs between
+ * 0 and 16384 (inclusive), so I2F_MAX_BITS=15 is enough. If necessary,
+ * I2F_MAX_BITS can be increased, but that will add to the loop iterations
+ * and slow us down. Conversion is done by shifting the input and counting
+ * down until the first 1 reaches bit position 23. The resulting counter
+ * and the shifted input are, respectively, the exponent and the fraction.
+ * The sign is always zero.
+ */
static uint32_t i2f(uint32_t input)
{
u32 result, i, exponent, fraction;
- if ((input & 0x3fff) == 0)
- result = 0; /* 0 is a special case */
+ WARN_ON_ONCE(input > I2F_MAX_INPUT);
+
+ if ((input & I2F_MAX_INPUT) == 0)
+ result = 0;
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++) {
+ exponent = 126 + I2F_MAX_BITS;
+ fraction = (input & I2F_MAX_INPUT) << I2F_SHIFT;
+
+ for (i = 0; i < I2F_MAX_BITS; i++) {
if (fraction & 0x800000)
break;
else {
- fraction = fraction << 1; /* keep
- shifting left until top bit = 1 */
+ fraction = fraction << 1;
exponent = exponent - 1;
}
}
- result = exponent << 23 | (fraction & 0x7fffff); /* mask
- off top bit; assumed 1 */
+ result = exponent << 23 | (fraction & 0x7fffff);
}
return result;
}