From: Matthew Brost <matthew.brost@intel.com>
To: <intel-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>
Cc: <john.c.harrison@intel.com>, <daniele.ceraolospurio@intel.com>
Subject: [Intel-gfx] [PATCH 03/26] drm/i915/guc: Take engine PM when a context is pinned with GuC submission
Date: Mon, 4 Oct 2021 15:06:14 -0700 [thread overview]
Message-ID: <20211004220637.14746-4-matthew.brost@intel.com> (raw)
In-Reply-To: <20211004220637.14746-1-matthew.brost@intel.com>
Taking a PM reference to prevent intel_gt_wait_for_idle from short
circuiting while a scheduling of user context could be enabled.
Returning GT idle when it is not can cause all sorts of issues
throughout the stack.
v2:
(Daniel Vetter)
- Add might_lock annotations to pin / unpin function
v3:
(CI)
- Drop intel_engine_pm_might_put from unpin path as an async put is
used
v4:
(John Harrison)
- Make intel_engine_pm_might_get/put work with GuC virtual engines
- Update commit message
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/i915/gt/intel_context.c | 2 ++
drivers/gpu/drm/i915/gt/intel_engine_pm.h | 32 +++++++++++++++++
drivers/gpu/drm/i915/gt/intel_gt_pm.h | 10 ++++++
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 36 +++++++++++++++++--
drivers/gpu/drm/i915/intel_wakeref.h | 12 +++++++
5 files changed, 89 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 1076066f41e0..f601323b939f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -240,6 +240,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce,
if (err)
goto err_post_unpin;
+ intel_engine_pm_might_get(ce->engine);
+
if (unlikely(intel_context_is_closed(ce))) {
err = -ENOENT;
goto err_unlock;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index 6fdeae668e6e..d68675925b79 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -6,9 +6,11 @@
#ifndef INTEL_ENGINE_PM_H
#define INTEL_ENGINE_PM_H
+#include "i915_drv.h"
#include "i915_request.h"
#include "intel_engine_types.h"
#include "intel_wakeref.h"
+#include "intel_gt_pm.h"
static inline bool
intel_engine_pm_is_awake(const struct intel_engine_cs *engine)
@@ -31,6 +33,21 @@ static inline bool intel_engine_pm_get_if_awake(struct intel_engine_cs *engine)
return intel_wakeref_get_if_active(&engine->wakeref);
}
+static inline void intel_engine_pm_might_get(struct intel_engine_cs *engine)
+{
+ if (!intel_engine_is_virtual(engine)) {
+ intel_wakeref_might_get(&engine->wakeref);
+ } else {
+ struct intel_gt *gt = engine->gt;
+ struct intel_engine_cs *tengine;
+ intel_engine_mask_t tmp, mask = engine->mask;
+
+ for_each_engine_masked(tengine, gt, mask, tmp)
+ intel_wakeref_might_get(&tengine->wakeref);
+ }
+ intel_gt_pm_might_get(engine->gt);
+}
+
static inline void intel_engine_pm_put(struct intel_engine_cs *engine)
{
intel_wakeref_put(&engine->wakeref);
@@ -52,6 +69,21 @@ static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
intel_wakeref_unlock_wait(&engine->wakeref);
}
+static inline void intel_engine_pm_might_put(struct intel_engine_cs *engine)
+{
+ if (!intel_engine_is_virtual(engine)) {
+ intel_wakeref_might_put(&engine->wakeref);
+ } else {
+ struct intel_gt *gt = engine->gt;
+ struct intel_engine_cs *tengine;
+ intel_engine_mask_t tmp, mask = engine->mask;
+
+ for_each_engine_masked(tengine, gt, mask, tmp)
+ intel_wakeref_might_put(&tengine->wakeref);
+ }
+ intel_gt_pm_might_put(engine->gt);
+}
+
static inline struct i915_request *
intel_engine_create_kernel_request(struct intel_engine_cs *engine)
{
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index 05de6c1af25b..bc898df7a48c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -31,6 +31,11 @@ static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt)
return intel_wakeref_get_if_active(>->wakeref);
}
+static inline void intel_gt_pm_might_get(struct intel_gt *gt)
+{
+ intel_wakeref_might_get(>->wakeref);
+}
+
static inline void intel_gt_pm_put(struct intel_gt *gt)
{
intel_wakeref_put(>->wakeref);
@@ -41,6 +46,11 @@ static inline void intel_gt_pm_put_async(struct intel_gt *gt)
intel_wakeref_put_async(>->wakeref);
}
+static inline void intel_gt_pm_might_put(struct intel_gt *gt)
+{
+ intel_wakeref_might_put(>->wakeref);
+}
+
#define with_intel_gt_pm(gt, tmp) \
for (tmp = 1, intel_gt_pm_get(gt); tmp; \
intel_gt_pm_put(gt), tmp = 0)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 17da2fea1bff..8b82da50c2bc 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1571,7 +1571,12 @@ static int guc_context_pre_pin(struct intel_context *ce,
static int guc_context_pin(struct intel_context *ce, void *vaddr)
{
- return __guc_context_pin(ce, ce->engine, vaddr);
+ int ret = __guc_context_pin(ce, ce->engine, vaddr);
+
+ if (likely(!ret && !intel_context_is_barrier(ce)))
+ intel_engine_pm_get(ce->engine);
+
+ return ret;
}
static void guc_context_unpin(struct intel_context *ce)
@@ -1580,6 +1585,9 @@ static void guc_context_unpin(struct intel_context *ce)
unpin_guc_id(guc, ce);
lrc_unpin(ce);
+
+ if (likely(!intel_context_is_barrier(ce)))
+ intel_engine_pm_put_async(ce->engine);
}
static void guc_context_post_unpin(struct intel_context *ce)
@@ -2341,8 +2349,30 @@ static int guc_virtual_context_pre_pin(struct intel_context *ce,
static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr)
{
struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0);
+ int ret = __guc_context_pin(ce, engine, vaddr);
+ intel_engine_mask_t tmp, mask = ce->engine->mask;
+
+ if (likely(!ret))
+ for_each_engine_masked(engine, ce->engine->gt, mask, tmp)
+ intel_engine_pm_get(engine);
- return __guc_context_pin(ce, engine, vaddr);
+ return ret;
+}
+
+static void guc_virtual_context_unpin(struct intel_context *ce)
+{
+ intel_engine_mask_t tmp, mask = ce->engine->mask;
+ struct intel_engine_cs *engine;
+ struct intel_guc *guc = ce_to_guc(ce);
+
+ GEM_BUG_ON(context_enabled(ce));
+ GEM_BUG_ON(intel_context_is_barrier(ce));
+
+ unpin_guc_id(guc, ce);
+ lrc_unpin(ce);
+
+ for_each_engine_masked(engine, ce->engine->gt, mask, tmp)
+ intel_engine_pm_put_async(engine);
}
static void guc_virtual_context_enter(struct intel_context *ce)
@@ -2379,7 +2409,7 @@ static const struct intel_context_ops virtual_guc_context_ops = {
.pre_pin = guc_virtual_context_pre_pin,
.pin = guc_virtual_context_pin,
- .unpin = guc_context_unpin,
+ .unpin = guc_virtual_context_unpin,
.post_unpin = guc_context_post_unpin,
.ban = guc_context_ban,
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index 545c8f277c46..4f4c2e15e736 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -123,6 +123,12 @@ enum {
__INTEL_WAKEREF_PUT_LAST_BIT__
};
+static inline void
+intel_wakeref_might_get(struct intel_wakeref *wf)
+{
+ might_lock(&wf->mutex);
+}
+
/**
* intel_wakeref_put_flags: Release the wakeref
* @wf: the wakeref
@@ -170,6 +176,12 @@ intel_wakeref_put_delay(struct intel_wakeref *wf, unsigned long delay)
FIELD_PREP(INTEL_WAKEREF_PUT_DELAY, delay));
}
+static inline void
+intel_wakeref_might_put(struct intel_wakeref *wf)
+{
+ might_lock(&wf->mutex);
+}
+
/**
* intel_wakeref_lock: Lock the wakeref (mutex)
* @wf: the wakeref
--
2.32.0
next prev parent reply other threads:[~2021-10-04 22:12 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-04 22:06 [Intel-gfx] [PATCH 00/26] Parallel submission aka multi-bb execbuf Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 01/26] drm/i915/guc: Move GuC guc_id allocation under submission state sub-struct Matthew Brost
2021-10-07 3:06 ` John Harrison
2021-10-07 15:05 ` Matthew Brost
2021-10-07 18:13 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 02/26] drm/i915/guc: Take GT PM ref when deregistering context Matthew Brost
2021-10-07 3:37 ` John Harrison
2021-10-08 1:28 ` Matthew Brost
2021-10-08 18:23 ` Matthew Brost
2021-10-04 22:06 ` Matthew Brost [this message]
2021-10-07 3:45 ` [Intel-gfx] [PATCH 03/26] drm/i915/guc: Take engine PM when a context is pinned with GuC submission John Harrison
2021-10-07 15:19 ` Matthew Brost
2021-10-07 18:15 ` John Harrison
2021-10-08 1:23 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 04/26] drm/i915/guc: Don't call switch_to_kernel_context " Matthew Brost
2021-10-07 3:49 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 05/26] drm/i915: Add logical engine mapping Matthew Brost
2021-10-07 19:03 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 06/26] drm/i915: Expose logical engine instance to user Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 07/26] drm/i915/guc: Introduce context parent-child relationship Matthew Brost
2021-10-07 19:35 ` John Harrison
2021-10-08 18:33 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 08/26] drm/i915/guc: Add multi-lrc context registration Matthew Brost
2021-10-07 19:50 ` John Harrison
2021-10-08 1:31 ` Matthew Brost
2021-10-08 17:20 ` John Harrison
2021-10-08 17:29 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 09/26] drm/i915/guc: Ensure GuC schedule operations do not operate on child contexts Matthew Brost
2021-10-07 20:23 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 10/26] drm/i915/guc: Assign contexts in parent-child relationship consecutive guc_ids Matthew Brost
2021-10-07 22:03 ` John Harrison
2021-10-08 1:21 ` Matthew Brost
2021-10-08 16:40 ` John Harrison
2021-10-13 18:03 ` Matthew Brost
2021-10-13 19:11 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 11/26] drm/i915/guc: Implement parallel context pin / unpin functions Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 12/26] drm/i915/guc: Implement multi-lrc submission Matthew Brost
2021-10-05 7:55 ` kernel test robot
2021-10-05 10:37 ` kernel test robot
2021-10-08 17:20 ` John Harrison
2021-10-13 18:24 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 13/26] drm/i915/guc: Insert submit fences between requests in parent-child relationship Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 14/26] drm/i915/guc: Implement multi-lrc reset Matthew Brost
2021-10-08 17:39 ` John Harrison
2021-10-08 17:56 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 15/26] drm/i915/guc: Update debugfs for GuC multi-lrc Matthew Brost
2021-10-08 17:46 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 16/26] drm/i915: Fix bug in user proto-context creation that leaked contexts Matthew Brost
2021-10-08 17:49 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 17/26] drm/i915/guc: Connect UAPI to GuC multi-lrc interface Matthew Brost
2021-10-11 22:09 ` John Harrison
2021-10-11 22:59 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 18/26] drm/i915/doc: Update parallel submit doc to point to i915_drm.h Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 19/26] drm/i915/guc: Add basic GuC multi-lrc selftest Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 20/26] drm/i915/guc: Implement no mid batch preemption for multi-lrc Matthew Brost
2021-10-11 23:32 ` John Harrison
2021-10-13 1:52 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 21/26] drm/i915: Multi-BB execbuf Matthew Brost
2021-10-05 8:31 ` kernel test robot
2021-10-05 17:02 ` Matthew Brost
2021-10-06 20:46 ` Matthew Brost
2021-10-12 21:22 ` John Harrison
2021-10-13 0:37 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 22/26] drm/i915/guc: Handle errors in multi-lrc requests Matthew Brost
2021-10-12 21:56 ` John Harrison
2021-10-13 0:18 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 23/26] drm/i915: Make request conflict tracking understand parallel submits Matthew Brost
2021-10-12 22:08 ` John Harrison
2021-10-13 0:32 ` Matthew Brost
2021-10-13 19:35 ` John Harrison
2021-10-13 17:51 ` Matthew Brost
2021-10-13 19:25 ` John Harrison
2021-10-04 22:06 ` [Intel-gfx] [PATCH 24/26] drm/i915: Update I915_GEM_BUSY IOCTL to understand composite fences Matthew Brost
2021-10-11 22:15 ` Daniele Ceraolo Spurio
2021-10-12 7:53 ` Tvrtko Ursulin
2021-10-12 18:31 ` Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 25/26] drm/i915: Enable multi-bb execbuf Matthew Brost
2021-10-04 22:06 ` [Intel-gfx] [PATCH 26/26] drm/i915/execlists: Weak parallel submission support for execlists Matthew Brost
2021-10-04 22:21 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Parallel submission aka multi-bb execbuf (rev4) Patchwork
2021-10-12 22:15 ` John Harrison
2021-10-13 0:15 ` Matthew Brost
2021-10-13 19:24 ` John Harrison
2021-10-04 22:23 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-10-04 22:26 ` [Intel-gfx] ✗ Fi.CI.DOCS: " Patchwork
2021-10-12 22:15 ` John Harrison
2021-10-13 0:12 ` Matthew Brost
2021-10-04 22:54 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2021-10-05 1:49 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Parallel submission aka multi-bb execbuf (rev5) Patchwork
2021-10-05 1:51 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-10-05 1:54 ` [Intel-gfx] ✗ Fi.CI.DOCS: " Patchwork
2021-10-05 2:21 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2021-10-12 18:11 ` [Intel-gfx] [PATCH 02/26] drm/i915/guc: Take GT PM ref when deregistering context Matthew Brost
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211004220637.14746-4-matthew.brost@intel.com \
--to=matthew.brost@intel.com \
--cc=daniele.ceraolospurio@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=john.c.harrison@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox