From: Rodrigo Vivi <rodrigo.vivi@intel.com>
To: <intel-xe@lists.freedesktop.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Subject: [RFC 08/20] drm/xe: Runtime PM wake on every exec
Date: Wed, 27 Dec 2023 21:12:20 -0500 [thread overview]
Message-ID: <20231228021232.2366249-9-rodrigo.vivi@intel.com> (raw)
In-Reply-To: <20231228021232.2366249-1-rodrigo.vivi@intel.com>
Let's ensure our PCI device is awaken on every GT execution to
the end of the execution.
Let's increase the runtime_pm protection and start moving
that to the outer bounds.
Let's also remove the unnecessary mem_access get/put.
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/xe/xe_sched_job.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad8..0b30ec77fc5ad 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -15,6 +15,7 @@
#include "xe_hw_fence.h"
#include "xe_lrc.h"
#include "xe_macros.h"
+#include "xe_pm.h"
#include "xe_trace.h"
#include "xe_vm.h"
@@ -67,6 +68,8 @@ static void job_free(struct xe_sched_job *job)
struct xe_exec_queue *q = job->q;
bool is_migration = xe_sched_job_is_migration(q);
+ xe_pm_runtime_put(gt_to_xe(q->gt));
+
kmem_cache_free(xe_exec_queue_is_parallel(job->q) || is_migration ?
xe_sched_job_parallel_slab : xe_sched_job_slab, job);
}
@@ -86,6 +89,8 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
int i, j;
u32 width;
+ xe_pm_runtime_get(gt_to_xe(q->gt));
+
/* only a kernel context can submit a vm-less job */
XE_WARN_ON(!q->vm && !(q->flags & EXEC_QUEUE_FLAG_KERNEL));
@@ -155,9 +160,6 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
for (i = 0; i < width; ++i)
job->batch_addr[i] = batch_addr[i];
- /* All other jobs require a VM to be open which has a ref */
- if (unlikely(q->flags & EXEC_QUEUE_FLAG_KERNEL))
- xe_device_mem_access_get(job_to_xe(job));
xe_device_assert_mem_access(job_to_xe(job));
trace_xe_sched_job_create(job);
@@ -189,8 +191,6 @@ void xe_sched_job_destroy(struct kref *ref)
struct xe_sched_job *job =
container_of(ref, struct xe_sched_job, refcount);
- if (unlikely(job->q->flags & EXEC_QUEUE_FLAG_KERNEL))
- xe_device_mem_access_put(job_to_xe(job));
xe_exec_queue_put(job->q);
dma_fence_put(job->fence);
drm_sched_job_cleanup(&job->drm);
--
2.43.0
next prev parent reply other threads:[~2023-12-28 2:13 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-28 2:12 [RFC 00/20] First attempt to kill mem_access Rodrigo Vivi
2023-12-28 2:12 ` [RFC 01/20] drm/xe: Document Xe PM component Rodrigo Vivi
2023-12-28 2:12 ` [RFC 02/20] drm/xe: Fix display runtime_pm handling Rodrigo Vivi
2023-12-28 2:12 ` [RFC 03/20] drm/xe: Create a xe_pm_runtime_resume_and_get variant for display Rodrigo Vivi
2023-12-28 2:12 ` [RFC 04/20] drm/xe: Convert xe_pm_runtime_{get, put} to void and protect from recursion Rodrigo Vivi
2023-12-28 2:12 ` [RFC 05/20] drm/xe: Prepare display for D3Cold Rodrigo Vivi
2023-12-28 2:12 ` [RFC 06/20] drm/xe: Convert mem_access assertion towards the runtime_pm state Rodrigo Vivi
2024-01-09 11:06 ` Matthew Auld
2024-01-09 17:50 ` Rodrigo Vivi
2023-12-28 2:12 ` [RFC 07/20] drm/xe: Runtime PM wake on every IOCTL Rodrigo Vivi
2024-01-02 11:30 ` Gupta, Anshuman
2024-01-09 17:57 ` Rodrigo Vivi
2023-12-28 2:12 ` Rodrigo Vivi [this message]
2024-01-09 11:24 ` [RFC 08/20] drm/xe: Runtime PM wake on every exec Matthew Auld
2024-01-09 17:41 ` Rodrigo Vivi
2024-01-09 18:40 ` Matthew Auld
2023-12-28 2:12 ` [RFC 09/20] drm/xe: Runtime PM wake on every sysfs call Rodrigo Vivi
2023-12-28 2:12 ` [RFC 10/20] drm/xe: Sort some xe_pm_runtime related functions Rodrigo Vivi
2024-01-09 11:26 ` Matthew Auld
2023-12-28 2:12 ` [RFC 11/20] drm/xe: Ensure device is awake before removing it Rodrigo Vivi
2023-12-28 2:12 ` [RFC 12/20] drm/xe: Remove mem_access from guc_pc calls Rodrigo Vivi
2023-12-28 2:12 ` [RFC 13/20] drm/xe: Runtime PM wake on every debugfs call Rodrigo Vivi
2023-12-28 2:12 ` [RFC 14/20] drm/xe: Replace dma_buf mem_access per direct xe_pm_runtime calls Rodrigo Vivi
2023-12-28 2:12 ` [RFC 15/20] drm/xe: Allow GuC CT fast path and worker regardless of runtime_pm Rodrigo Vivi
2024-01-09 12:09 ` Matthew Auld
2023-12-28 2:12 ` [RFC 16/20] drm/xe: Remove mem_access calls from migration Rodrigo Vivi
2024-01-09 12:33 ` Matthew Auld
2024-01-09 17:58 ` Rodrigo Vivi
2024-01-09 18:49 ` Matthew Auld
2024-01-09 22:40 ` Rodrigo Vivi
2024-01-11 14:17 ` Matthew Brost
2023-12-28 2:12 ` [RFC 17/20] drm/xe: Removing extra mem_access protection from runtime pm Rodrigo Vivi
2023-12-28 2:12 ` [RFC 18/20] drm/xe: Convert hwmon from mem_access to xe_pm_runtime calls Rodrigo Vivi
2023-12-28 2:12 ` [RFC 19/20] drm/xe: Remove unused runtime pm helper Rodrigo Vivi
2023-12-28 2:12 ` [RFC 20/20] drm/xe: Mega Kill of mem_access Rodrigo Vivi
2024-01-09 11:41 ` Matthew Auld
2024-01-09 17:39 ` Rodrigo Vivi
2024-01-09 18:27 ` Matthew Auld
2024-01-09 22:34 ` Rodrigo Vivi
2024-01-04 5:40 ` ✓ CI.Patch_applied: success for First attempt to kill mem_access Patchwork
2024-01-04 5:40 ` ✗ CI.checkpatch: warning " Patchwork
2024-01-04 5:41 ` ✗ CI.KUnit: failure " Patchwork
2024-01-10 5:21 ` [RFC 00/20] " Matthew Brost
2024-01-10 14:06 ` Rodrigo Vivi
2024-01-10 14:08 ` Vivi, Rodrigo
2024-01-10 14:33 ` 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=20231228021232.2366249-9-rodrigo.vivi@intel.com \
--to=rodrigo.vivi@intel.com \
--cc=intel-xe@lists.freedesktop.org \
/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