From: John Brooks <john@fastquake.com>
To: amd-gfx@lists.freedesktop.org,
"Michel Dänzer" <michel@daenzer.net>,
"Marek Olšák" <maraeo@gmail.com>
Cc: dri-devel@lists.freedesktop.org
Subject: [PATCH 5/9] drm/amdgpu: Track time of last page fault and last CS move in struct amdgpu_bo
Date: Fri, 23 Jun 2017 13:39:36 -0400 [thread overview]
Message-ID: <1498239580-17360-6-git-send-email-john@fastquake.com> (raw)
In-Reply-To: <1498239580-17360-1-git-send-email-john@fastquake.com>
Signed-off-by: John Brooks <john@fastquake.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 ++
3 files changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index fe73633..245234e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -429,6 +429,9 @@ struct amdgpu_bo {
void *metadata;
u32 metadata_size;
unsigned prime_shared_count;
+ unsigned long last_page_fault_jiffies;
+ unsigned long last_cs_move_jiffies;
+
/* list of all virtual address to which this bo
* is associated to
*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index aeee684..2fad8bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -306,6 +306,7 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
u64 initial_bytes_moved;
uint32_t domain;
+ uint32_t old_mem;
int r;
if (bo->pin_count)
@@ -322,6 +323,7 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
retry:
amdgpu_ttm_placement_from_domain(bo, domain);
initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
+ old_mem = bo->tbo.mem.mem_type;
r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
p->bytes_moved += atomic64_read(&adev->num_bytes_moved) -
initial_bytes_moved;
@@ -331,6 +333,9 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
goto retry;
}
+ if (bo->tbo.mem.mem_type != old_mem)
+ bo->last_cs_move_jiffies = jiffies;
+
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 0ff555a..31d1f21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -977,6 +977,8 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
if (bo->mem.mem_type != TTM_PL_VRAM)
return 0;
+ abo->last_page_fault_jiffies = jiffies;
+
size = bo->mem.num_pages << PAGE_SHIFT;
offset = bo->mem.start << PAGE_SHIFT;
/* TODO: figure out how to map scattered VRAM to the CPU */
--
2.7.4
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2017-06-23 17:39 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-23 17:39 [PATCH 0/9] Visible VRAM Management Improvements John Brooks
2017-06-23 17:39 ` [PATCH 3/9] drm/amdgpu: Don't force BOs into visible VRAM for page faults John Brooks
[not found] ` <1498239580-17360-4-git-send-email-john-xq/Ko7C6e2Bl57MIdRCFDg@public.gmane.org>
2017-06-26 9:38 ` Michel Dänzer
[not found] ` <f399c192-d90d-9f43-9b8a-820fa51a7715-otUistvHUpPR7s880joybQ@public.gmane.org>
2017-06-27 3:25 ` John Brooks
2017-06-23 17:39 ` John Brooks [this message]
[not found] ` <1498239580-17360-1-git-send-email-john-xq/Ko7C6e2Bl57MIdRCFDg@public.gmane.org>
2017-06-23 17:39 ` [PATCH 1/9] drm/amdgpu: Separate placements and busy placements John Brooks
2017-06-23 17:39 ` [PATCH 2/9] drm/amdgpu: Add vis_vramlimit module parameter John Brooks
2017-06-26 9:48 ` Michel Dänzer
2017-06-26 9:57 ` Christian König
2017-06-23 17:39 ` [PATCH 4/9] drm/amdgpu: Don't force BOs into visible VRAM if they can go to GTT instead John Brooks
[not found] ` <1498239580-17360-5-git-send-email-john-xq/Ko7C6e2Bl57MIdRCFDg@public.gmane.org>
2017-06-24 18:09 ` Christian König
[not found] ` <0c5064f9-5b84-8833-b410-055b5e2064bf-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2017-06-24 18:37 ` John Brooks
2017-06-23 17:39 ` [PATCH 6/9] drm/amdgpu: Set/clear CPU_ACCESS_REQUIRED flag on page fault and CS John Brooks
[not found] ` <1498239580-17360-7-git-send-email-john-xq/Ko7C6e2Bl57MIdRCFDg@public.gmane.org>
2017-06-24 18:00 ` Christian König
2017-06-25 1:57 ` John Brooks
[not found] ` <55ea5e84-0791-5a70-6278-ade83c343a3b-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2017-06-26 9:27 ` Michel Dänzer
[not found] ` <6c6fca21-df95-a413-d5eb-c05f1913787b-otUistvHUpPR7s880joybQ@public.gmane.org>
2017-06-26 23:25 ` Marek Olšák
2017-06-23 17:39 ` [PATCH 7/9] drm/amdgpu: Throttle visible VRAM moves separately John Brooks
[not found] ` <1498239580-17360-8-git-send-email-john-xq/Ko7C6e2Bl57MIdRCFDg@public.gmane.org>
2017-06-26 9:44 ` Michel Dänzer
[not found] ` <c132d211-bb7c-1e7d-617a-6f128343a581-otUistvHUpPR7s880joybQ@public.gmane.org>
2017-06-26 22:29 ` John Brooks
2017-06-27 8:25 ` Michel Dänzer
2017-06-23 17:39 ` [PATCH 8/9] drm/amdgpu: Asynchronously move BOs to visible VRAM John Brooks
2017-06-23 21:02 ` [PATCH 0/9] Visible VRAM Management Improvements Felix Kuehling
[not found] ` <82339d2d-481c-ab3f-1590-ab22f0eac371-5C7GfCeVMHo@public.gmane.org>
2017-06-23 23:16 ` John Brooks
2017-06-24 18:20 ` Christian König
[not found] ` <644cf9b4-e22b-eab1-a505-b0e1f9850f82-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2017-06-24 21:50 ` John Brooks
2017-06-25 11:54 ` Christian König
2017-06-24 18:07 ` Christian König
[not found] ` <3cd916a7-6734-5eff-b645-66f3ee83f13a-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2017-06-24 18:36 ` John Brooks
2017-06-25 11:31 ` Christian König
2017-06-23 17:39 ` [PATCH 9/9] drm/amdgpu: Reduce lock contention when evicting from visible VRAM John Brooks
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=1498239580-17360-6-git-send-email-john@fastquake.com \
--to=john@fastquake.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=maraeo@gmail.com \
--cc=michel@daenzer.net \
/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;
as well as URLs for NNTP newsgroup(s).