amd-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Sasha Levin <sashal@kernel.org>, Yong Zhao <Yong.Zhao@amd.com>,
	Felix Kuehling <Felix.Kuehling@amd.com>,
	dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org,
	Alex Deucher <alexander.deucher@amd.com>
Subject: [PATCH AUTOSEL 5.5 131/542] drm/amdkfd: Fix a bug in SDMA RLC queue counting under HWS mode
Date: Fri, 14 Feb 2020 10:42:03 -0500	[thread overview]
Message-ID: <20200214154854.6746-131-sashal@kernel.org> (raw)
In-Reply-To: <20200214154854.6746-1-sashal@kernel.org>

From: Yong Zhao <Yong.Zhao@amd.com>

[ Upstream commit f38abc15d157b7b31fa7f651dc8bf92858c963f8 ]

The sdma_queue_count increment should be done before
execute_queues_cpsch(), which calls pm_calc_rlib_size() where
sdma_queue_count is used to calculate whether over_subscription is
triggered.

With the previous code, when a SDMA queue is created,
compute_queue_count in pm_calc_rlib_size() is one more than the
actual compute queue number, because the queue_count has been
incremented while sdma_queue_count has not. This patch fixes that.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 984c2f2b24b60..d128a8bbe19d0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1225,16 +1225,18 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	list_add(&q->list, &qpd->queues_list);
 	qpd->queue_count++;
+
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
+		dqm->sdma_queue_count++;
+	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
+		dqm->xgmi_sdma_queue_count++;
+
 	if (q->properties.is_active) {
 		dqm->queue_count++;
 		retval = execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
-		dqm->sdma_queue_count++;
-	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
-		dqm->xgmi_sdma_queue_count++;
 	/*
 	 * Unconditionally increment this counter, regardless of the queue's
 	 * type or whether the queue is active.
-- 
2.20.1

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

  parent reply	other threads:[~2020-02-14 15:51 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-14 15:39 [PATCH AUTOSEL 5.5 001/542] drm/amdgpu: remove set but not used variable 'mc_shared_chmap' from 'gfx_v6_0.c' and 'gfx_v7_0.c' Sasha Levin
2020-02-14 15:40 ` [PATCH AUTOSEL 5.5 029/542] drm/amd/display: Map ODM memory correctly when doing ODM combine Sasha Levin
2020-02-14 15:41 ` [PATCH AUTOSEL 5.5 070/542] drm/amdgpu/sriov: workaround on rev_id for Navi12 under sriov Sasha Levin
2020-02-14 15:41 ` [PATCH AUTOSEL 5.5 080/542] drm/amd/display: Clear state after exiting fixed active VRR state Sasha Levin
2020-02-14 15:41 ` [PATCH AUTOSEL 5.5 117/542] drm/amd/display: Retrain dongles when SINK_COUNT becomes non-zero Sasha Levin
2020-02-14 15:42 ` Sasha Levin [this message]
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 138/542] drm/amd/display: Renoir chroma viewport WA Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 139/542] drm/amdgpu: remove 4 set but not used variable in amdgpu_atombios_get_connector_info_from_object_table Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 140/542] drm/amdgpu: remove set but not used variable 'dig_connector' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 141/542] drm/amdgpu: remove set but not used variable 'dig' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 142/542] drm/amdgpu: remove always false comparison in 'amdgpu_atombios_i2c_process_i2c_ch' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 143/542] drm/amdgpu: remove set but not used variable 'mc_shared_chmap' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 144/542] drm/amd/powerplay: remove set but not used variable 'vbios_version', 'data' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 145/542] drm/amd/powerplay: remove set but not used variable 'data' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 146/542] drm/amd/powerplay: remove set but not used variable 'threshold', 'state' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 147/542] drm/amdgpu: remove set but not used variable 'amdgpu_connector' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 148/542] drm/amdgpu: remove set but not used variable 'count' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 149/542] drm/amdgpu: remove set but not used variable 'invalid' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 150/542] drm/amd/powerplay: remove set but not used variable 'us_mvdd' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 155/542] drm/amdkfd: remove set but not used variable 'top_dev' Sasha Levin
2020-02-14 21:44   ` Greg KH
2020-02-14 23:59     ` Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 156/542] drm/amd/display: remove set but not used variable 'old_plane_crtc' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 157/542] drm/amd/display: remove set but not used variable 'bp' in bios_parser2.c Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 158/542] drm/amd/display: remove set but not used variable 'bp' in bios_parser.c Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 159/542] drm/amd/display: remove set but not used variable 'min_content' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 160/542] drm/amdgpu/dm: Do not throw an error for a display with no audio Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 161/542] drm/radeon: remove set but not used variable 'size', 'relocs_chunk' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 162/542] drm/radeon: remove set but not used variable 'backbias_response_time' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 163/542] drm/radeon: remove set but not used variable 'dig_connector' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 164/542] drm/radeon: remove set but not used variable 'radeon_connector' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 165/542] drm/radeon: remove set but not used variable 'blocks' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 166/542] drm/radeon: remove set but not used variable 'tv_pll_cntl1' Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 168/542] drm/amdgpu: Ensure ret is always initialized when using SOC15_WAIT_ON_RREG Sasha Levin
2020-02-14 15:42 ` [PATCH AUTOSEL 5.5 179/542] Revert "drm/amdgpu: enable VCN DPG on Raven and Raven2" Sasha Levin
2020-02-14 15:43 ` [PATCH AUTOSEL 5.5 232/542] drm/amd/display: Fix update_bw_bounding_box Calcs Sasha Levin
2020-02-14 15:43 ` [PATCH AUTOSEL 5.5 233/542] drm/amd/display: Lower DPP DTO only when safe Sasha Levin
2020-02-14 15:43 ` [PATCH AUTOSEL 5.5 234/542] drm/amdgpu: fix double gpu_recovery for NV of SRIOV Sasha Levin
2020-02-14 15:43 ` [PATCH AUTOSEL 5.5 235/542] drm/amdgpu: fix KIQ ring test fail in TDR " Sasha Levin
2020-02-14 15:44 ` [PATCH AUTOSEL 5.5 293/542] drm/amdkfd: Fix permissions of hang_hws Sasha Levin
2020-02-14 15:46 ` [PATCH AUTOSEL 5.5 390/542] drm/amd/display: fixup DML dependencies Sasha Levin
2020-02-14 15:46 ` [PATCH AUTOSEL 5.5 408/542] drm/amdgpu: add the lost mutex_init back Sasha Levin
2020-02-14 16:22   ` Alex Deucher
2020-02-20 17:36     ` Sasha Levin
2020-02-14 15:48 ` [PATCH AUTOSEL 5.5 491/542] drm/amd/display: do not allocate display_mode_lib unnecessarily Sasha Levin
2020-02-14 15:48 ` [PATCH AUTOSEL 5.5 499/542] radeon: insert 10ms sleep in dce5_crtc_load_lut Sasha Levin
2020-02-14 15:48 ` [PATCH AUTOSEL 5.5 529/542] drm/amdgpu/smu10: fix smu10_get_clock_by_type_with_latency Sasha Levin
2020-02-14 15:48 ` [PATCH AUTOSEL 5.5 530/542] drm/amdgpu/smu10: fix smu10_get_clock_by_type_with_voltage Sasha Levin
2020-02-14 16:31   ` Alex Deucher
2020-02-20 19:26     ` Sasha Levin
2020-02-20 20:08       ` Alex Deucher
2020-02-14 16:08 ` [PATCH AUTOSEL 5.5 001/542] drm/amdgpu: remove set but not used variable 'mc_shared_chmap' from 'gfx_v6_0.c' and 'gfx_v7_0.c' Alex Deucher

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=20200214154854.6746-131-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=Felix.Kuehling@amd.com \
    --cc=Yong.Zhao@amd.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.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;
as well as URLs for NNTP newsgroup(s).