linux/drivers/gpu/drm/i915/selftests/i915_random.c
Chris Wilson 4797948071 drm/i915: Squash repeated awaits on the same fence
Track the latest fence waited upon on each context, and only add a new
asynchronous wait if the new fence is more recent than the recorded
fence for that context. This requires us to filter out unordered
timelines, which are noted by DMA_FENCE_NO_CONTEXT. However, in the
absence of a universal identifier, we have to use our own
i915->mm.unordered_timeline token.

v2: Throw around the debug crutches
v3: Inline the likely case of the pre-allocation cache being full.
v4: Drop the pre-allocation support, we can lose the most recent fence
in case of allocation failure -- it just means we may emit more awaits
than strictly necessary but will not break.
v5: Trim allocation size for leaf nodes, they only need an array of u32
not pointers.
v6: Create mock_timeline to tidy selftest writing
v7: s/intel_timeline_sync_get/intel_timeline_sync_is_later/ (Tvrtko)
v8: Prune the stale sync points when we idle.
v9: Include a small benchmark in the kselftests
v10: Separate the idr implementation into its own compartment. (Tvrkto)
v11: Refactor igt_sync kselftests to avoid deep nesting (Tvrkto)
v12: __sync_leaf_idx() to assert that p->height is 0 when checking leaves
v13: kselftests to investigate struct i915_syncmap itself (Tvrtko)
v14: Foray into ascii art graphs
v15: Take into account that the random lookup/insert does 2 prng calls,
not 1, when benchmarking, and use for_each_set_bit() (Tvrtko)
v16: Improved ascii art

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170503093924.5320-4-chris@chris-wilson.co.uk
2017-05-03 11:08:48 +01:00

75 lines
2.1 KiB
C

/*
* Copyright © 2016 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*
*/
#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/types.h>
#include "i915_random.h"
u64 i915_prandom_u64_state(struct rnd_state *rnd)
{
u64 x;
x = prandom_u32_state(rnd);
x <<= 32;
x |= prandom_u32_state(rnd);
return x;
}
static inline u32 i915_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
{
return upper_32_bits((u64)prandom_u32_state(state) * ep_ro);
}
void i915_random_reorder(unsigned int *order, unsigned int count,
struct rnd_state *state)
{
unsigned int i, j;
for (i = 0; i < count; i++) {
BUILD_BUG_ON(sizeof(unsigned int) > sizeof(u32));
j = i915_prandom_u32_max_state(count, state);
swap(order[i], order[j]);
}
}
unsigned int *i915_random_order(unsigned int count, struct rnd_state *state)
{
unsigned int *order, i;
order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY);
if (!order)
return order;
for (i = 0; i < count; i++)
order[i] = i;
i915_random_reorder(order, count, state);
return order;
}