[Intel-gfx] [PATCH i-g-t 11/21] gem_wsim: Engine map support
Tvrtko Ursulin
tvrtko.ursulin at linux.intel.com
Wed May 8 12:10:48 UTC 2019
From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Support new i915 uAPI for configuring contexts with engine maps.
Please refer to the README file for more detailed explanation.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
benchmarks/gem_wsim.c | 212 ++++++++++++++++++++++++++++++++++-------
benchmarks/wsim/README | 17 +++-
2 files changed, 192 insertions(+), 37 deletions(-)
diff --git a/benchmarks/gem_wsim.c b/benchmarks/gem_wsim.c
index f654decb24cc..e6b7b8f5335d 100644
--- a/benchmarks/gem_wsim.c
+++ b/benchmarks/gem_wsim.c
@@ -57,6 +57,7 @@
#include "ewma.h"
enum intel_engine_id {
+ DEFAULT,
RCS,
BCS,
VCS,
@@ -81,7 +82,8 @@ enum w_type
SW_FENCE,
SW_FENCE_SIGNAL,
CTX_PRIORITY,
- PREEMPTION
+ PREEMPTION,
+ ENGINE_MAP
};
struct deps
@@ -115,6 +117,10 @@ struct w_step
int throttle;
int fence_signal;
int priority;
+ struct {
+ unsigned int engine_map_count;
+ enum intel_engine_id *engine_map;
+ };
};
/* Implementation details */
@@ -142,6 +148,8 @@ DECLARE_EWMA(uint64_t, rt, 4, 2)
struct ctx {
uint32_t id;
int priority;
+ unsigned int engine_map_count;
+ enum intel_engine_id *engine_map;
bool targets_instance;
bool wants_balance;
unsigned int static_vcs;
@@ -200,10 +208,10 @@ struct workload
int fd;
bool first;
unsigned int num_engines;
- unsigned int engine_map[5];
+ unsigned int engine_map[NUM_ENGINES];
uint64_t t_prev;
- uint64_t prev[5];
- double busy[5];
+ uint64_t prev[NUM_ENGINES];
+ double busy[NUM_ENGINES];
} busy_balancer;
};
@@ -234,6 +242,7 @@ static int fd;
#define REG(x) (volatile uint32_t *)((volatile char *)igt_global_mmio + x)
static const char *ring_str_map[NUM_ENGINES] = {
+ [DEFAULT] = "DEFAULT",
[RCS] = "RCS",
[BCS] = "BCS",
[VCS] = "VCS",
@@ -330,6 +339,37 @@ static int str_to_engine(const char *str)
return -1;
}
+static int parse_engine_map(struct w_step *step, const char *_str)
+{
+ char *token, *tctx = NULL, *tstart = (char *)_str;
+
+ while ((token = strtok_r(tstart, "|", &tctx))) {
+ enum intel_engine_id engine;
+
+ tstart = NULL;
+
+ if (!strcmp(token, "DEFAULT"))
+ return -1;
+ else if (!strcmp(token, "VCS"))
+ return -1;
+
+ engine = str_to_engine(token);
+ if ((int)engine < 0)
+ return -1;
+
+ if (engine != VCS1 && engine != VCS2)
+ return -1; /* TODO */
+
+ step->engine_map_count++;
+ step->engine_map = realloc(step->engine_map,
+ step->engine_map_count *
+ sizeof(step->engine_map[0]));
+ step->engine_map[step->engine_map_count - 1] = engine;
+ }
+
+ return 0;
+}
+
static struct workload *
parse_workload(struct w_arg *arg, unsigned int flags, struct workload *app_w)
{
@@ -448,6 +488,33 @@ parse_workload(struct w_arg *arg, unsigned int flags, struct workload *app_w)
} else if (!strcmp(field, "f")) {
step.type = SW_FENCE;
goto add_step;
+ } else if (!strcmp(field, "M")) {
+ unsigned int nr = 0;
+ while ((field = strtok_r(fstart, ".", &fctx)) !=
+ NULL) {
+ tmp = atoi(field);
+ check_arg(nr == 0 && tmp <= 0,
+ "Invalid context at step %u!\n",
+ nr_steps);
+ check_arg(nr > 1,
+ "Invalid engine map format at step %u!\n",
+ nr_steps);
+
+ if (nr == 0) {
+ step.context = tmp;
+ } else {
+ tmp = parse_engine_map(&step,
+ field);
+ check_arg(tmp < 0,
+ "Invalid engine map list at step %u!\n",
+ nr_steps);
+ }
+
+ nr++;
+ }
+
+ step.type = ENGINE_MAP;
+ goto add_step;
} else if (!strcmp(field, "X")) {
unsigned int nr = 0;
while ((field = strtok_r(fstart, ".", &fctx)) !=
@@ -497,9 +564,7 @@ parse_workload(struct w_arg *arg, unsigned int flags, struct workload *app_w)
i = str_to_engine(field);
check_arg(i < 0,
"Invalid engine id at step %u!\n", nr_steps);
- if (i >= 0)
- valid++;
-
+ valid++;
step.engine = i;
if (step.engine == BCS)
@@ -774,6 +839,7 @@ terminate_bb(struct w_step *w, unsigned int flags)
}
static const unsigned int eb_engine_map[NUM_ENGINES] = {
+ [DEFAULT] = I915_EXEC_DEFAULT,
[RCS] = I915_EXEC_RENDER,
[BCS] = I915_EXEC_BLT,
[VCS] = I915_EXEC_BSD,
@@ -790,18 +856,42 @@ eb_set_engine(struct drm_i915_gem_execbuffer2 *eb,
if (engine == VCS2 && (flags & VCS2REMAP))
engine = BCS;
- if ((flags & I915) && engine == VCS) {
+ if ((flags & I915) && engine == VCS)
eb->flags = 0;
- } else {
+ else
eb->flags = eb_engine_map[engine];
+}
+
+static unsigned int
+find_engine_in_map(struct ctx *ctx, enum intel_engine_id engine)
+{
+ unsigned int i;
+
+ for (i = 0; i < ctx->engine_map_count; i++) {
+ if (ctx->engine_map[i] == engine)
+ return i + 1;
}
+
+ igt_assert(0);
+ return 0;
+}
+
+static struct ctx *
+__get_ctx(struct workload *wrk, struct w_step *w)
+{
+ return &wrk->ctx_list[w->context * 2];
}
static void
-eb_update_flags(struct w_step *w, enum intel_engine_id engine,
- unsigned int flags)
+eb_update_flags(struct workload *wrk, struct w_step *w,
+ enum intel_engine_id engine, unsigned int flags)
{
- eb_set_engine(&w->eb, engine, flags);
+ struct ctx *ctx = __get_ctx(wrk, w);
+
+ if (ctx->engine_map)
+ w->eb.flags = find_engine_in_map(ctx, engine);
+ else
+ eb_set_engine(&w->eb, engine, flags);
w->eb.flags |= I915_EXEC_HANDLE_LUT;
w->eb.flags |= I915_EXEC_NO_RELOC;
@@ -820,12 +910,6 @@ get_status_objects(struct workload *wrk)
return wrk->status_object;
}
-static struct ctx *
-__get_ctx(struct workload *wrk, struct w_step *w)
-{
- return &wrk->ctx_list[w->context * 2];
-}
-
static uint32_t
get_ctxid(struct workload *wrk, struct w_step *w)
{
@@ -895,7 +979,7 @@ alloc_step_batch(struct workload *wrk, struct w_step *w, unsigned int flags)
engine = VCS2;
else if (flags & SWAPVCS && engine == VCS2)
engine = VCS1;
- eb_update_flags(w, engine, flags);
+ eb_update_flags(wrk, w, engine, flags);
#ifdef DEBUG
printf("%u: %u:|", w->idx, w->eb.buffer_count);
for (i = 0; i <= j; i++)
@@ -918,7 +1002,7 @@ static void __ctx_set_prio(uint32_t ctx_id, unsigned int prio)
gem_context_set_param(fd, ¶m);
}
-static void
+static int
prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
{
unsigned int ctx_vcs = 0;
@@ -979,30 +1063,53 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
/*
* Identify if contexts target specific engine instances and if they
* want to be balanced.
+ *
+ * Transfer over engine map configuration from the workload step.
*/
for (j = 0; j < wrk->nr_ctxs; j += 2) {
bool targets = false;
bool balance = false;
for (i = 0, w = wrk->steps; i < wrk->nr_steps; i++, w++) {
- if (w->type != BATCH)
- continue;
-
if (w->context != (j / 2))
continue;
- if (w->engine == VCS)
- balance = true;
- else
- targets = true;
+ if (w->type == BATCH) {
+ if (w->engine == VCS)
+ balance = true;
+ else
+ targets = true;
+ } else if (w->type == ENGINE_MAP) {
+ wrk->ctx_list[j].engine_map = w->engine_map;
+ wrk->ctx_list[j].engine_map_count =
+ w->engine_map_count;
+ }
}
- if (flags & I915) {
- wrk->ctx_list[j].targets_instance = targets;
+ wrk->ctx_list[j].targets_instance = targets;
+ if (flags & I915)
wrk->ctx_list[j].wants_balance = balance;
+ }
+
+ /*
+ * Ensure VCS is not allowed with engine map contexts.
+ */
+ for (j = 0; j < wrk->nr_ctxs; j += 2) {
+ for (i = 0, w = wrk->steps; i < wrk->nr_steps; i++, w++) {
+ if (w->context != (j / 2))
+ continue;
+
+ if (w->type != BATCH)
+ continue;
+
+ if (wrk->ctx_list[j].engine_map && w->engine == VCS) {
+ wsim_err("Batches targetting engine maps must use explicit engines!\n");
+ return -1;
+ }
}
}
+
/*
* Create and configure contexts.
*/
@@ -1013,7 +1120,7 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
if (ctx->id)
continue;
- if (flags & I915) {
+ if ((flags & I915) || ctx->engine_map) {
struct drm_i915_gem_context_create_ext_setparam ext = {
.base.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
.param.param = I915_CONTEXT_PARAM_VM,
@@ -1043,7 +1150,7 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
break;
}
- if (!ctx->targets_instance)
+ if (!ctx->engine_map && !ctx->targets_instance)
args.flags |=
I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE;
@@ -1076,7 +1183,7 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
* both want to target specific engines and be balanced by i915?
*/
if ((flags & I915) && ctx->wants_balance &&
- ctx->targets_instance) {
+ ctx->targets_instance && !ctx->engine_map) {
struct drm_i915_gem_context_create_ext_setparam ext = {
.base.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
.param.param = I915_CONTEXT_PARAM_VM,
@@ -1101,7 +1208,33 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
__ctx_set_prio(ctx_id, wrk->prio);
}
- if (ctx->wants_balance) {
+ if (ctx->engine_map) {
+ I915_DEFINE_CONTEXT_PARAM_ENGINES(set_engines,
+ ctx->engine_map_count + 1);
+ struct drm_i915_gem_context_param param = {
+ .ctx_id = ctx_id,
+ .param = I915_CONTEXT_PARAM_ENGINES,
+ .size = sizeof(set_engines),
+ .value = to_user_pointer(&set_engines),
+ };
+
+ set_engines.extensions = 0;
+
+ /* Reserve slot for virtual engine. */
+ set_engines.engines[0].engine_class =
+ I915_ENGINE_CLASS_INVALID;
+ set_engines.engines[0].engine_instance =
+ I915_ENGINE_CLASS_INVALID_NONE;
+
+ for (j = 1; j <= ctx->engine_map_count; j++) {
+ set_engines.engines[j].engine_class =
+ I915_ENGINE_CLASS_VIDEO; /* FIXME */
+ set_engines.engines[j].engine_instance =
+ ctx->engine_map[j - 1] - VCS1; /* FIXME */
+ }
+
+ gem_context_set_param(fd, ¶m);
+ } else if (ctx->wants_balance) {
I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(load_balance, 2) = {
.base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
.num_siblings = 2,
@@ -1181,6 +1314,8 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
alloc_step_batch(wrk, w, _flags);
}
+
+ return 0;
}
static double elapsed(const struct timespec *start, const struct timespec *end)
@@ -1918,7 +2053,7 @@ do_eb(struct workload *wrk, struct w_step *w, enum intel_engine_id engine,
uint32_t seqno = new_seqno(wrk, engine);
unsigned int i;
- eb_update_flags(w, engine, flags);
+ eb_update_flags(wrk, w, engine, flags);
if (flags & SEQNO)
update_bb_seqno(w, engine, seqno);
@@ -2067,7 +2202,8 @@ static void *run_workload(void *data)
w->priority;
}
continue;
- } else if (w->type == PREEMPTION) {
+ } else if (w->type == PREEMPTION ||
+ w->type == ENGINE_MAP) {
continue;
}
@@ -2625,7 +2761,11 @@ int main(int argc, char **argv)
w[i]->print_stats = verbose > 1 ||
(verbose > 0 && master_workload == i);
- prepare_workload(i, w[i], flags_);
+ if (prepare_workload(i, w[i], flags_)) {
+ wsim_err("Failed to prepare workload %u!\n", i);
+ return 1;
+ }
+
if (balancer && balancer->init) {
int ret = balancer->init(balancer, w[i]);
diff --git a/benchmarks/wsim/README b/benchmarks/wsim/README
index 4786f116b4ac..4b14aa28bfa7 100644
--- a/benchmarks/wsim/README
+++ b/benchmarks/wsim/README
@@ -3,6 +3,7 @@ Workload descriptor format
ctx.engine.duration_us.dependency.wait,...
<uint>.<str>.<uint>[-<uint>].<int <= 0>[/<int <= 0>][...].<0|1>,...
+M.<uint>.<str>[|<str>]...
P|X.<uint>.<int>
d|p|s|t|q|a.<int>,...
f
@@ -23,10 +24,11 @@ Additional workload steps are also supported:
'q' - Throttle to n max queue depth.
'f' - Create a sync fence.
'a' - Advance the previously created sync fence.
+ 'M' - Set up engine map.
'P' - Context priority.
'X' - Context preemption control.
-Engine ids: RCS, BCS, VCS, VCS1, VCS2, VECS
+Engine ids: DEFAULT, RCS, BCS, VCS, VCS1, VCS2, VECS
Example (leading spaces must not be present in the actual file):
----------------------------------------------------------------
@@ -161,3 +163,16 @@ The same context is then marked to have batches which can be preempted every
Same as with context priority, context preemption commands are valid until
optionally overriden by another preemption control change on the same context.
+
+Engine maps
+-----------
+
+Engine maps are a per context feature which changes the way engine selection is
+done in the driver.
+
+Example:
+
+ M.1.VCS1|VCS2
+
+This sets up context 1 with an engine map containing VCS1 and VCS2 engine.
+Submission to this context can now only reference these two engines.
--
2.19.1
More information about the Intel-gfx
mailing list