dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org,
	dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: [PATCH 6/7] drm/amdgpu: always reserve one more shared slot for pipelines BO moves
Date: Mon, 24 Sep 2018 13:58:18 +0200	[thread overview]
Message-ID: <20180924115819.2116-7-christian.koenig@amd.com> (raw)
In-Reply-To: <20180924115819.2116-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>

This allows us to drop the extra reserve in TTM.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index cda8cf90777c..3e31561d141b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -50,7 +50,7 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 	bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
 	p->uf_entry.priority = 0;
 	p->uf_entry.tv.bo = &bo->tbo;
-	p->uf_entry.tv.shared = 1;
+	p->uf_entry.tv.shared = 2;
 	p->uf_entry.user_pages = NULL;
 
 	drm_gem_object_put_unlocked(gobj);
@@ -599,7 +599,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	}
 
 	amdgpu_bo_list_for_each_entry(e, p->bo_list)
-		e->tv.shared = 1;
+		e->tv.shared = 2;
 
 	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 	if (p->bo_list->first_userptr != p->bo_list->num_entries)
@@ -723,7 +723,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
 
-		e->tv.shared = bo->prime_shared_count ? 1 : 0;
+		e->tv.shared = bo->prime_shared_count ? 2 : 0;
 		e->bo_va = amdgpu_vm_bo_find(vm, bo);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 353367382874..96fcb33774b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -616,7 +616,7 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 {
 	entry->priority = 0;
 	entry->tv.bo = &vm->root.base.bo->tbo;
-	entry->tv.shared = 2;
+	entry->tv.shared = 3;
 	entry->user_pages = NULL;
 	list_add(&entry->tv.head, validated);
 }
-- 
2.14.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  parent reply	other threads:[~2018-09-24 11:58 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-24 11:58 Improve reservation object shared slot function Christian König
     [not found] ` <20180924115819.2116-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-24 11:58   ` [PATCH 1/7] dma-buf: remove shared fence staging in reservation object Christian König
2018-09-24 11:58   ` [PATCH 2/7] dma-buf: allow reserving more than one shared fence slot Christian König
2018-09-24 11:58   ` [PATCH 3/7] drm/ttm: allow reserve more than one shared slot Christian König
2018-09-24 14:11     ` Michel Dänzer
2018-09-24 11:58   ` [PATCH 4/7] drm/amdgpu: fix using shared fence for exported BOs Christian König
2018-09-24 11:58   ` Christian König [this message]
2018-09-24 11:58   ` [PATCH 7/7] drm/ttm: drop the extra reservation for pipelines BO moves Christian König
2018-09-24 11:58 ` [PATCH 5/7] drm/amdgpu: always reserve two slots for the VM Christian König
     [not found]   ` <20180924115819.2116-6-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-24 14:14     ` Michel Dänzer
2018-09-24 15:03 ` Improve reservation object shared slot function Daniel Vetter
     [not found]   ` <20180924150319.GV11082-dv86pmgwkMBes7Z6vYuT8azUEOm+Xw19@public.gmane.org>
2018-09-24 15:16     ` Christian König
     [not found]       ` <b84dbae6-12ce-5632-d80f-567cb7fe678b-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-09-24 15:43         ` Daniel Vetter

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=20180924115819.2116-7-christian.koenig@amd.com \
    --to=ckoenig.leichtzumerken-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
    --cc=dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.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