[Intel-gfx] [PATCH 1/8] drm/i915: Make own struct for execlist items
Mika Kuoppala
mika.kuoppala at linux.intel.com
Wed Sep 20 14:36:58 UTC 2017
Engine's execlist related items have been increasing to
a point where a separate struct is warranted. Carve execlist
specific items to a dedicated struct to add clarity.
v2: add kerneldoc and fix whitespace (Joonas, Chris)
v3: csb_mmio changes, rebase
Suggested-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
drivers/gpu/drm/i915/i915_debugfs.c | 8 +--
drivers/gpu/drm/i915/i915_gem.c | 6 +-
drivers/gpu/drm/i915/i915_gpu_error.c | 4 +-
drivers/gpu/drm/i915/i915_guc_submission.c | 31 +++++----
drivers/gpu/drm/i915/i915_irq.c | 5 +-
drivers/gpu/drm/i915/intel_engine_cs.c | 12 ++--
drivers/gpu/drm/i915/intel_lrc.c | 100 +++++++++++++++--------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 100 +++++++++++++++++++++++------
8 files changed, 167 insertions(+), 99 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ca6fa6d122c6..7648ff207670 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3324,7 +3324,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
read = GEN8_CSB_READ_PTR(ptr);
write = GEN8_CSB_WRITE_PTR(ptr);
seq_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
- read, engine->csb_head,
+ read, engine->execlist.csb_head,
write,
intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
yesno(test_bit(ENGINE_IRQ_EXECLIST,
@@ -3346,10 +3346,10 @@ static int i915_engine_info(struct seq_file *m, void *unused)
}
rcu_read_lock();
- for (idx = 0; idx < ARRAY_SIZE(engine->execlist_port); idx++) {
+ for (idx = 0; idx < ARRAY_SIZE(engine->execlist.port); idx++) {
unsigned int count;
- rq = port_unpack(&engine->execlist_port[idx],
+ rq = port_unpack(&engine->execlist.port[idx],
&count);
if (rq) {
seq_printf(m, "\t\tELSP[%d] count=%d, ",
@@ -3363,7 +3363,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
rcu_read_unlock();
spin_lock_irq(&engine->timeline->lock);
- for (rb = engine->execlist_first; rb; rb = rb_next(rb)){
+ for (rb = engine->execlist.first; rb; rb = rb_next(rb)) {
struct i915_priolist *p =
rb_entry(rb, typeof(*p), node);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c4bf34865fa3..7934bafab081 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2815,8 +2815,8 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
* Turning off the engine->irq_tasklet until the reset is over
* prevents the race.
*/
- tasklet_kill(&engine->irq_tasklet);
- tasklet_disable(&engine->irq_tasklet);
+ tasklet_kill(&engine->execlist.irq_tasklet);
+ tasklet_disable(&engine->execlist.irq_tasklet);
if (engine->irq_seqno_barrier)
engine->irq_seqno_barrier(engine);
@@ -2995,7 +2995,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
{
- tasklet_enable(&engine->irq_tasklet);
+ tasklet_enable(&engine->execlist.irq_tasklet);
kthread_unpark(engine->breadcrumbs.signaler);
}
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0c779671fe2d..8710fbdbbcb1 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1327,10 +1327,10 @@ static void engine_record_requests(struct intel_engine_cs *engine,
static void error_record_engine_execlists(struct intel_engine_cs *engine,
struct drm_i915_error_engine *ee)
{
- const struct execlist_port *port = engine->execlist_port;
+ const struct execlist_port *port = engine->execlist.port;
unsigned int n;
- for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) {
+ for (n = 0; n < ARRAY_SIZE(engine->execlist.port); n++) {
struct drm_i915_gem_request *rq = port_request(&port[n]);
if (!rq)
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index e191d56fc990..e967d266bc3c 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -494,11 +494,12 @@ static void i915_guc_submit(struct intel_engine_cs *engine)
struct drm_i915_private *dev_priv = engine->i915;
struct intel_guc *guc = &dev_priv->guc;
struct i915_guc_client *client = guc->execbuf_client;
- struct execlist_port *port = engine->execlist_port;
- unsigned int engine_id = engine->id;
+ struct intel_engine_execlist * const el = &engine->execlist;
+ struct execlist_port *port = el->port;
+ const unsigned int engine_id = engine->id;
unsigned int n;
- for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) {
+ for (n = 0; n < ARRAY_SIZE(el->port); n++) {
struct drm_i915_gem_request *rq;
unsigned int count;
@@ -558,7 +559,8 @@ static void port_assign(struct execlist_port *port,
static void i915_guc_dequeue(struct intel_engine_cs *engine)
{
- struct execlist_port *port = engine->execlist_port;
+ struct intel_engine_execlist * const el = &engine->execlist;
+ struct execlist_port *port = el->port;
struct drm_i915_gem_request *last = NULL;
bool submit = false;
struct rb_node *rb;
@@ -567,15 +569,15 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
port++;
spin_lock_irq(&engine->timeline->lock);
- rb = engine->execlist_first;
- GEM_BUG_ON(rb_first(&engine->execlist_queue) != rb);
+ rb = el->first;
+ GEM_BUG_ON(rb_first(&el->queue) != rb);
while (rb) {
struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
struct drm_i915_gem_request *rq, *rn;
list_for_each_entry_safe(rq, rn, &p->requests, priotree.link) {
if (last && rq->ctx != last->ctx) {
- if (port != engine->execlist_port) {
+ if (port != el->port) {
__list_del_many(&p->requests,
&rq->priotree.link);
goto done;
@@ -596,13 +598,13 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
}
rb = rb_next(rb);
- rb_erase(&p->node, &engine->execlist_queue);
+ rb_erase(&p->node, &el->queue);
INIT_LIST_HEAD(&p->requests);
if (p->priority != I915_PRIORITY_NORMAL)
kmem_cache_free(engine->i915->priorities, p);
}
done:
- engine->execlist_first = rb;
+ el->first = rb;
if (submit) {
port_assign(port, last);
i915_guc_submit(engine);
@@ -612,8 +614,8 @@ static void i915_guc_dequeue(struct intel_engine_cs *engine)
static void i915_guc_irq_handler(unsigned long data)
{
- struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
- struct execlist_port *port = engine->execlist_port;
+ struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+ struct execlist_port *port = engine->execlist.port;
struct drm_i915_gem_request *rq;
rq = port_request(&port[0]);
@@ -1144,7 +1146,7 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
* and it is guaranteed that it will remove the work item from the
* queue before our request is completed.
*/
- BUILD_BUG_ON(ARRAY_SIZE(engine->execlist_port) *
+ BUILD_BUG_ON(ARRAY_SIZE(engine->execlist.port) *
sizeof(struct guc_wq_item) *
I915_NUM_ENGINES > GUC_WQ_SIZE);
@@ -1175,14 +1177,15 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
guc_interrupts_capture(dev_priv);
for_each_engine(engine, dev_priv, id) {
+ struct intel_engine_execlist * const el = &engine->execlist;
/* The tasklet was initialised by execlists, and may be in
* a state of flux (across a reset) and so we just want to
* take over the callback without changing any other state
* in the tasklet.
*/
- engine->irq_tasklet.func = i915_guc_irq_handler;
+ el->irq_tasklet.func = i915_guc_irq_handler;
clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
- tasklet_schedule(&engine->irq_tasklet);
+ tasklet_schedule(&el->irq_tasklet);
}
return 0;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c23efc4394ce..de703c26e124 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1338,10 +1338,11 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
static void
gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
{
+ struct intel_engine_execlist * const el = &engine->execlist;
bool tasklet = false;
if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift)) {
- if (port_count(&engine->execlist_port[0])) {
+ if (port_count(&el->port[0])) {
__set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
tasklet = true;
}
@@ -1353,7 +1354,7 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
}
if (tasklet)
- tasklet_hi_schedule(&engine->irq_tasklet);
+ tasklet_hi_schedule(&el->irq_tasklet);
}
static irqreturn_t gen8_gt_irq_ack(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 3d135c3cd380..eb6feaf69a3b 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -391,8 +391,8 @@ static void intel_engine_init_timeline(struct intel_engine_cs *engine)
*/
void intel_engine_setup_common(struct intel_engine_cs *engine)
{
- engine->execlist_queue = RB_ROOT;
- engine->execlist_first = NULL;
+ engine->execlist.queue = RB_ROOT;
+ engine->execlist.first = NULL;
intel_engine_init_timeline(engine);
intel_engine_init_hangcheck(engine);
@@ -1473,11 +1473,11 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
return false;
/* Both ports drained, no more ELSP submission? */
- if (port_request(&engine->execlist_port[0]))
+ if (port_request(&engine->execlist.port[0]))
return false;
/* ELSP is empty, but there are ready requests? */
- if (READ_ONCE(engine->execlist_first))
+ if (READ_ONCE(engine->execlist.first))
return false;
/* Ring stopped? */
@@ -1526,8 +1526,8 @@ void intel_engines_mark_idle(struct drm_i915_private *i915)
for_each_engine(engine, i915, id) {
intel_engine_disarm_breadcrumbs(engine);
i915_gem_batch_pool_fini(&engine->batch_pool);
- tasklet_kill(&engine->irq_tasklet);
- engine->no_priolist = false;
+ tasklet_kill(&engine->execlist.irq_tasklet);
+ engine->execlist.no_priolist = false;
}
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 86fed9f1f1ae..5c2fcc4936ba 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -291,17 +291,18 @@ lookup_priolist(struct intel_engine_cs *engine,
struct i915_priotree *pt,
int prio)
{
+ struct intel_engine_execlist * const el = &engine->execlist;
struct i915_priolist *p;
struct rb_node **parent, *rb;
bool first = true;
- if (unlikely(engine->no_priolist))
+ if (unlikely(el->no_priolist))
prio = I915_PRIORITY_NORMAL;
find_priolist:
/* most positive priority is scheduled first, equal priorities fifo */
rb = NULL;
- parent = &engine->execlist_queue.rb_node;
+ parent = &el->queue.rb_node;
while (*parent) {
rb = *parent;
p = rb_entry(rb, typeof(*p), node);
@@ -316,7 +317,7 @@ lookup_priolist(struct intel_engine_cs *engine,
}
if (prio == I915_PRIORITY_NORMAL) {
- p = &engine->default_priolist;
+ p = &el->default_priolist;
} else {
p = kmem_cache_alloc(engine->i915->priorities, GFP_ATOMIC);
/* Convert an allocation failure to a priority bump */
@@ -331,7 +332,7 @@ lookup_priolist(struct intel_engine_cs *engine,
* requests, so if userspace lied about their
* dependencies that reordering may be visible.
*/
- engine->no_priolist = true;
+ el->no_priolist = true;
goto find_priolist;
}
}
@@ -339,10 +340,10 @@ lookup_priolist(struct intel_engine_cs *engine,
p->priority = prio;
INIT_LIST_HEAD(&p->requests);
rb_link_node(&p->node, rb, parent);
- rb_insert_color(&p->node, &engine->execlist_queue);
+ rb_insert_color(&p->node, &el->queue);
if (first)
- engine->execlist_first = &p->node;
+ el->first = &p->node;
return ptr_pack_bits(p, first, 1);
}
@@ -393,12 +394,12 @@ static u64 execlists_update_context(struct drm_i915_gem_request *rq)
static void execlists_submit_ports(struct intel_engine_cs *engine)
{
- struct execlist_port *port = engine->execlist_port;
+ struct execlist_port *port = engine->execlist.port;
u32 __iomem *elsp =
engine->i915->regs + i915_mmio_reg_offset(RING_ELSP(engine));
unsigned int n;
- for (n = ARRAY_SIZE(engine->execlist_port); n--; ) {
+ for (n = ARRAY_SIZE(engine->execlist.port); n--; ) {
struct drm_i915_gem_request *rq;
unsigned int count;
u64 desc;
@@ -453,7 +454,7 @@ static void port_assign(struct execlist_port *port,
static void execlists_dequeue(struct intel_engine_cs *engine)
{
struct drm_i915_gem_request *last;
- struct execlist_port *port = engine->execlist_port;
+ struct execlist_port *port = engine->execlist.port;
struct rb_node *rb;
bool submit = false;
@@ -491,8 +492,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
*/
spin_lock_irq(&engine->timeline->lock);
- rb = engine->execlist_first;
- GEM_BUG_ON(rb_first(&engine->execlist_queue) != rb);
+ rb = engine->execlist.first;
+ GEM_BUG_ON(rb_first(&engine->execlist.queue) != rb);
while (rb) {
struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
struct drm_i915_gem_request *rq, *rn;
@@ -515,7 +516,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* combine this request with the last, then we
* are done.
*/
- if (port != engine->execlist_port) {
+ if (port != engine->execlist.port) {
__list_del_many(&p->requests,
&rq->priotree.link);
goto done;
@@ -552,13 +553,13 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
}
rb = rb_next(rb);
- rb_erase(&p->node, &engine->execlist_queue);
+ rb_erase(&p->node, &engine->execlist.queue);
INIT_LIST_HEAD(&p->requests);
if (p->priority != I915_PRIORITY_NORMAL)
kmem_cache_free(engine->i915->priorities, p);
}
done:
- engine->execlist_first = rb;
+ engine->execlist.first = rb;
if (submit)
port_assign(port, last);
spin_unlock_irq(&engine->timeline->lock);
@@ -569,7 +570,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
static void execlists_cancel_requests(struct intel_engine_cs *engine)
{
- struct execlist_port *port = engine->execlist_port;
+ struct intel_engine_execlist * const el = &engine->execlist;
+ struct execlist_port *port = el->port;
struct drm_i915_gem_request *rq, *rn;
struct rb_node *rb;
unsigned long flags;
@@ -578,9 +580,9 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
spin_lock_irqsave(&engine->timeline->lock, flags);
/* Cancel the requests on the HW and clear the ELSP tracker. */
- for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++)
+ for (n = 0; n < ARRAY_SIZE(el->port); n++)
i915_gem_request_put(port_request(&port[n]));
- memset(engine->execlist_port, 0, sizeof(engine->execlist_port));
+ memset(el->port, 0, sizeof(el->port));
/* Mark all executing requests as skipped. */
list_for_each_entry(rq, &engine->timeline->requests, link) {
@@ -590,7 +592,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
}
/* Flush the queued requests to the timeline list (for retiring). */
- rb = engine->execlist_first;
+ rb = el->first;
while (rb) {
struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
@@ -603,7 +605,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
}
rb = rb_next(rb);
- rb_erase(&p->node, &engine->execlist_queue);
+ rb_erase(&p->node, &el->queue);
INIT_LIST_HEAD(&p->requests);
if (p->priority != I915_PRIORITY_NORMAL)
kmem_cache_free(engine->i915->priorities, p);
@@ -611,8 +613,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
/* Remaining _unready_ requests will be nop'ed when submitted */
- engine->execlist_queue = RB_ROOT;
- engine->execlist_first = NULL;
+ el->queue = RB_ROOT;
+ el->first = NULL;
GEM_BUG_ON(port_isset(&port[0]));
/*
@@ -628,7 +630,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
static bool execlists_elsp_ready(const struct intel_engine_cs *engine)
{
- const struct execlist_port *port = engine->execlist_port;
+ const struct execlist_port *port = engine->execlist.port;
return port_count(&port[0]) + port_count(&port[1]) < 2;
}
@@ -639,8 +641,9 @@ static bool execlists_elsp_ready(const struct intel_engine_cs *engine)
*/
static void intel_lrc_irq_handler(unsigned long data)
{
- struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
- struct execlist_port *port = engine->execlist_port;
+ struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+ struct intel_engine_execlist * const el = &engine->execlist;
+ struct execlist_port *port = el->port;
struct drm_i915_private *dev_priv = engine->i915;
/* We can skip acquiring intel_runtime_pm_get() here as it was taken
@@ -652,7 +655,7 @@ static void intel_lrc_irq_handler(unsigned long data)
*/
GEM_BUG_ON(!dev_priv->gt.awake);
- intel_uncore_forcewake_get(dev_priv, engine->fw_domains);
+ intel_uncore_forcewake_get(dev_priv, el->fw_domains);
/* Prefer doing test_and_clear_bit() as a two stage operation to avoid
* imposing the cost of a locked atomic transaction when submitting a
@@ -665,10 +668,10 @@ static void intel_lrc_irq_handler(unsigned long data)
unsigned int head, tail;
/* However GVT emulation depends upon intercepting CSB mmio */
- if (unlikely(engine->csb_use_mmio)) {
+ if (unlikely(el->csb_use_mmio)) {
buf = (u32 * __force)
(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
- engine->csb_head = -1; /* force mmio read of CSB ptrs */
+ el->csb_head = -1; /* force mmio read of CSB ptrs */
}
/* The write will be ordered by the uncached read (itself
@@ -682,19 +685,20 @@ static void intel_lrc_irq_handler(unsigned long data)
* is set and we do a new loop.
*/
__clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
- if (unlikely(engine->csb_head == -1)) { /* following a reset */
+ if (unlikely(el->csb_head == -1)) { /* following a reset */
head = readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
tail = GEN8_CSB_WRITE_PTR(head);
head = GEN8_CSB_READ_PTR(head);
- engine->csb_head = head;
+ el->csb_head = head;
} else {
const int write_idx =
intel_hws_csb_write_index(dev_priv) -
I915_HWS_CSB_BUF0_INDEX;
- head = engine->csb_head;
+ head = el->csb_head;
tail = READ_ONCE(buf[write_idx]);
}
+
while (head != tail) {
struct drm_i915_gem_request *rq;
unsigned int status;
@@ -748,8 +752,8 @@ static void intel_lrc_irq_handler(unsigned long data)
!(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
}
- if (head != engine->csb_head) {
- engine->csb_head = head;
+ if (head != el->csb_head) {
+ el->csb_head = head;
writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
}
@@ -758,7 +762,7 @@ static void intel_lrc_irq_handler(unsigned long data)
if (execlists_elsp_ready(engine))
execlists_dequeue(engine);
- intel_uncore_forcewake_put(dev_priv, engine->fw_domains);
+ intel_uncore_forcewake_put(dev_priv, el->fw_domains);
}
static void insert_request(struct intel_engine_cs *engine,
@@ -769,7 +773,7 @@ static void insert_request(struct intel_engine_cs *engine,
list_add_tail(&pt->link, &ptr_mask_bits(p, 1)->requests);
if (ptr_unmask_bits(p, 1) && execlists_elsp_ready(engine))
- tasklet_hi_schedule(&engine->irq_tasklet);
+ tasklet_hi_schedule(&engine->execlist.irq_tasklet);
}
static void execlists_submit_request(struct drm_i915_gem_request *request)
@@ -782,7 +786,7 @@ static void execlists_submit_request(struct drm_i915_gem_request *request)
insert_request(engine, &request->priotree, request->priotree.priority);
- GEM_BUG_ON(!engine->execlist_first);
+ GEM_BUG_ON(!engine->execlist.first);
GEM_BUG_ON(list_empty(&request->priotree.link));
spin_unlock_irqrestore(&engine->timeline->lock, flags);
@@ -1289,6 +1293,7 @@ static u8 gtiir[] = {
static int gen8_init_common_ring(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
+ struct intel_engine_execlist * const el = &engine->execlist;
int ret;
ret = intel_mocs_init_engine(engine);
@@ -1321,11 +1326,11 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift);
clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
- engine->csb_head = -1;
+ el->csb_head = -1;
/* After a GPU reset, we may have requests to replay */
- if (!i915.enable_guc_submission && engine->execlist_first)
- tasklet_schedule(&engine->irq_tasklet);
+ if (!i915.enable_guc_submission && el->first)
+ tasklet_schedule(&el->irq_tasklet);
return 0;
}
@@ -1366,7 +1371,8 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine)
static void reset_common_ring(struct intel_engine_cs *engine,
struct drm_i915_gem_request *request)
{
- struct execlist_port *port = engine->execlist_port;
+ struct intel_engine_execlist * const el = &engine->execlist;
+ struct execlist_port *port = el->port;
struct drm_i915_gem_request *rq, *rn;
struct intel_context *ce;
unsigned long flags;
@@ -1383,9 +1389,9 @@ static void reset_common_ring(struct intel_engine_cs *engine,
* guessing the missed context-switch events by looking at what
* requests were completed.
*/
- for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++)
+ for (n = 0; n < ARRAY_SIZE(el->port); n++)
i915_gem_request_put(port_request(&port[n]));
- memset(engine->execlist_port, 0, sizeof(engine->execlist_port));
+ memset(el->port, 0, sizeof(el->port));
/* Push back any incomplete requests for replay after the reset. */
list_for_each_entry_safe_reverse(rq, rn,
@@ -1719,8 +1725,8 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
* Tasklet cannot be active at this point due intel_mark_active/idle
* so this is just for documentation.
*/
- if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->irq_tasklet.state)))
- tasklet_kill(&engine->irq_tasklet);
+ if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->execlist.irq_tasklet.state)))
+ tasklet_kill(&engine->execlist.irq_tasklet);
dev_priv = engine->i915;
@@ -1744,7 +1750,7 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine)
engine->submit_request = execlists_submit_request;
engine->cancel_requests = execlists_cancel_requests;
engine->schedule = execlists_schedule;
- engine->irq_tasklet.func = intel_lrc_irq_handler;
+ engine->execlist.irq_tasklet.func = intel_lrc_irq_handler;
}
static void
@@ -1806,7 +1812,7 @@ logical_ring_setup(struct intel_engine_cs *engine)
/* Intentionally left blank. */
engine->buffer = NULL;
- engine->csb_use_mmio = irq_handler_force_mmio(dev_priv);
+ engine->execlist.csb_use_mmio = irq_handler_force_mmio(dev_priv);
fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
RING_ELSP(engine),
@@ -1820,9 +1826,9 @@ logical_ring_setup(struct intel_engine_cs *engine)
RING_CONTEXT_STATUS_BUF_BASE(engine),
FW_REG_READ);
- engine->fw_domains = fw_domains;
+ engine->execlist.fw_domains = fw_domains;
- tasklet_init(&engine->irq_tasklet,
+ tasklet_init(&engine->execlist.irq_tasklet,
intel_lrc_irq_handler, (unsigned long)engine);
logical_ring_default_vfuncs(engine);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 138116a3b537..9469f314d3fa 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -184,6 +184,84 @@ struct i915_priolist {
int priority;
};
+/**
+ * struct intel_engine_execlist - execlist submission queue and port state
+ *
+ * The struct intel_engine_execlist represents the combined logical state of driver
+ * and the hardware state for execlist mode of submission.
+ */
+struct intel_engine_execlist {
+ /**
+ * @irq_tasklet: softirq tasklet for bottom handler
+ */
+ struct tasklet_struct irq_tasklet;
+
+ /**
+ * @default_priolist: priority list for I915_PRIORITY_NORMAL
+ */
+ struct i915_priolist default_priolist;
+
+ /**
+ * @no_priolist: priority lists disabled
+ */
+ bool no_priolist;
+
+ /**
+ * @port: execlist port states
+ *
+ * For each hardware ELSP (ExecList Submission Port) we keep
+ * track of the last request and the number of times we submitted
+ * that port to hw. We then count the number of times the hw reports
+ * a context completion or preemption. As only one context can
+ * be active on hw, we limit resubmission of context to port[0]. This
+ * is called Lite Restore, of the context.
+ */
+ struct execlist_port {
+ /**
+ * @request_count: combined request and submission count
+ */
+ struct drm_i915_gem_request *request_count;
+#define EXECLIST_COUNT_BITS 2
+#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
+#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
+#define port_set(p, packed) ((p)->request_count = (packed))
+#define port_isset(p) ((p)->request_count)
+#define port_index(p, e) ((p) - (e)->execlist.port)
+
+ /**
+ * @context_id: context ID for port
+ */
+ GEM_DEBUG_DECL(u32 context_id);
+ } port[2];
+
+ /**
+ * @queue: queue of requests, in priority lists
+ */
+ struct rb_root queue;
+
+ /**
+ * @first: leftmost level in priority @queue
+ */
+ struct rb_node *first;
+
+ /**
+ * @fw_domains: forcewake domains for irq tasklet
+ */
+ unsigned int fw_domains;
+
+ /**
+ * @csb_head: context status buffer head
+ */
+ unsigned int csb_head;
+
+ /**
+ * @csb_use_mmio: access csb through mmio, instead of hwsp
+ */
+ bool csb_use_mmio;
+};
+
#define INTEL_ENGINE_CS_MAX_NAME 8
struct intel_engine_cs {
@@ -380,27 +458,7 @@ struct intel_engine_cs {
u32 *(*signal)(struct drm_i915_gem_request *req, u32 *cs);
} semaphore;
- /* Execlists */
- struct tasklet_struct irq_tasklet;
- struct i915_priolist default_priolist;
- bool no_priolist;
- struct execlist_port {
- struct drm_i915_gem_request *request_count;
-#define EXECLIST_COUNT_BITS 2
-#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
-#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
-#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
-#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
-#define port_set(p, packed) ((p)->request_count = (packed))
-#define port_isset(p) ((p)->request_count)
-#define port_index(p, e) ((p) - (e)->execlist_port)
- GEM_DEBUG_DECL(u32 context_id);
- } execlist_port[2];
- struct rb_root execlist_queue;
- struct rb_node *execlist_first;
- unsigned int fw_domains;
- unsigned int csb_head;
- bool csb_use_mmio;
+ struct intel_engine_execlist execlist;
/* Contexts are pinned whilst they are active on the GPU. The last
* context executed remains active whilst the GPU is idle - the
--
2.11.0
More information about the Intel-gfx
mailing list