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>
This commit is contained in:
parent
304a48400d
commit
52b53a0bf8
@ -468,27 +468,42 @@ set_default_state(struct radeon_device *rdev)
|
|||||||
radeon_ring_write(ring, sq_stack_resource_mgmt_2);
|
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)
|
static uint32_t i2f(uint32_t input)
|
||||||
{
|
{
|
||||||
u32 result, i, exponent, fraction;
|
u32 result, i, exponent, fraction;
|
||||||
|
|
||||||
if ((input & 0x3fff) == 0)
|
WARN_ON_ONCE(input > I2F_MAX_INPUT);
|
||||||
result = 0; /* 0 is a special case */
|
|
||||||
|
if ((input & I2F_MAX_INPUT) == 0)
|
||||||
|
result = 0;
|
||||||
else {
|
else {
|
||||||
exponent = 140; /* exponent biased by 127; */
|
exponent = 126 + I2F_MAX_BITS;
|
||||||
fraction = (input & 0x3fff) << 10; /* cheat and only
|
fraction = (input & I2F_MAX_INPUT) << I2F_SHIFT;
|
||||||
handle numbers below 2^^15 */
|
|
||||||
for (i = 0; i < 14; i++) {
|
for (i = 0; i < I2F_MAX_BITS; i++) {
|
||||||
if (fraction & 0x800000)
|
if (fraction & 0x800000)
|
||||||
break;
|
break;
|
||||||
else {
|
else {
|
||||||
fraction = fraction << 1; /* keep
|
fraction = fraction << 1;
|
||||||
shifting left until top bit = 1 */
|
|
||||||
exponent = exponent - 1;
|
exponent = exponent - 1;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
result = exponent << 23 | (fraction & 0x7fffff); /* mask
|
result = exponent << 23 | (fraction & 0x7fffff);
|
||||||
off top bit; assumed 1 */
|
|
||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user