From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: ZhenGuo Yin <zhenguo.yin@amd.com>,
Felix Kuehling <Felix.Kuehling@amd.com>,
Alex Deucher <alexander.deucher@amd.com>,
Sasha Levin <sashal@kernel.org>,
christian.koenig@amd.com, Xinhui.Pan@amd.com, airlied@gmail.com,
daniel@ffwll.ch, amd-gfx@lists.freedesktop.org,
dri-devel@lists.freedesktop.org
Subject: [PATCH AUTOSEL 6.6 27/32] drm/amdkfd: Free gang_ctx_bo and wptr_bo in pqm_uninit
Date: Mon, 4 Dec 2023 15:32:47 -0500 [thread overview]
Message-ID: <20231204203317.2092321-27-sashal@kernel.org> (raw)
In-Reply-To: <20231204203317.2092321-1-sashal@kernel.org>
From: ZhenGuo Yin <zhenguo.yin@amd.com>
[ Upstream commit 72838777aa38352e20301e123b97110c456cd38e ]
[Why]
Memory leaks of gang_ctx_bo and wptr_bo.
[How]
Free gang_ctx_bo and wptr_bo in pqm_uninit.
v2: add a common function pqm_clean_queue_resource to
free queue's resources.
v3: reset pdd->pqd.num_gws when destorying GWS queue.
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: ZhenGuo Yin <zhenguo.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
.../amd/amdkfd/kfd_process_queue_manager.c | 54 +++++++++++--------
1 file changed, 33 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index adb5e4bdc0b20..7d0f887d99558 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -169,16 +169,43 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
return 0;
}
+static void pqm_clean_queue_resource(struct process_queue_manager *pqm,
+ struct process_queue_node *pqn)
+{
+ struct kfd_node *dev;
+ struct kfd_process_device *pdd;
+
+ dev = pqn->q->device;
+
+ pdd = kfd_get_process_device_data(dev, pqm->process);
+ if (!pdd) {
+ pr_err("Process device data doesn't exist\n");
+ return;
+ }
+
+ if (pqn->q->gws) {
+ if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
+ !dev->kfd->shared_resources.enable_mes)
+ amdgpu_amdkfd_remove_gws_from_process(
+ pqm->process->kgd_process_info, pqn->q->gws);
+ pdd->qpd.num_gws = 0;
+ }
+
+ if (dev->kfd->shared_resources.enable_mes) {
+ amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->gang_ctx_bo);
+ if (pqn->q->wptr_bo)
+ amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
+ }
+}
+
void pqm_uninit(struct process_queue_manager *pqm)
{
struct process_queue_node *pqn, *next;
list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) {
- if (pqn->q && pqn->q->gws &&
- KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
- !pqn->q->device->kfd->shared_resources.enable_mes)
- amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
- pqn->q->gws);
+ if (pqn->q)
+ pqm_clean_queue_resource(pqm, pqn);
+
kfd_procfs_del_queue(pqn->q);
uninit_queue(pqn->q);
list_del(&pqn->process_queue_list);
@@ -460,22 +487,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
goto err_destroy_queue;
}
- if (pqn->q->gws) {
- if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
- !dev->kfd->shared_resources.enable_mes)
- amdgpu_amdkfd_remove_gws_from_process(
- pqm->process->kgd_process_info,
- pqn->q->gws);
- pdd->qpd.num_gws = 0;
- }
-
- if (dev->kfd->shared_resources.enable_mes) {
- amdgpu_amdkfd_free_gtt_mem(dev->adev,
- pqn->q->gang_ctx_bo);
- if (pqn->q->wptr_bo)
- amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
-
- }
+ pqm_clean_queue_resource(pqm, pqn);
uninit_queue(pqn->q);
}
--
2.42.0
next prev parent reply other threads:[~2023-12-04 20:34 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-04 20:32 [PATCH AUTOSEL 6.6 01/32] pinctrl: s32cc: Avoid possible string truncation Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 02/32] kunit: Warn if tests are slow Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 03/32] kunit: Reset suite counter right before running tests Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 04/32] pinctrl: lochnagar: Don't build on MIPS Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 05/32] ALSA: hda - Fix speaker and headset mic pin config for CHUWI CoreBook XPro Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 06/32] ksmbd: separately allocate ci per dentry Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 07/32] ksmbd: release interim response after sending status pending response Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 08/32] ksmbd: move setting SMB2_FLAGS_ASYNC_COMMAND and AsyncId Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 09/32] ksmbd: don't update ->op_state as OPLOCK_STATE_NONE on error Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 10/32] mptcp: fix uninit-value in mptcp_incoming_options Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 11/32] wifi: cfg80211: lock wiphy mutex for rfkill poll Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 12/32] wifi: avoid offset calculation on NULL pointer Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 13/32] wifi: mac80211: handle 320 MHz in ieee80211_ht_cap_ie_to_sta_ht_cap Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 14/32] debugfs: fix automount d_fsdata usage Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 15/32] debugfs: annotate debugfs handlers vs. removal with lockdep Sasha Levin
2023-12-04 20:45 ` Johannes Berg
2023-12-05 4:25 ` Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 16/32] debugfs: add API to allow debugfs operations cancellation Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 17/32] wifi: cfg80211: add locked debugfs wrappers Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 18/32] wifi: mac80211: use wiphy locked debugfs helpers for agg_status Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 19/32] ALSA: hda: intel-nhlt: Ignore vbps when looking for DMIC 32 bps format Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 20/32] nvme-core: fix a memory leak in nvme_ns_info_from_identify() Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 21/32] io_uring: use fget/fput consistently Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 22/32] block: warn once for each partition in bio_check_ro() Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 23/32] drm/amdgpu: Do not issue gpu reset from nbio v7_9 bif interrupt Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 24/32] drm/amdkfd: Use common function for IP version check Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 25/32] drm/amd/display: update dcn315 lpddr pstate latency Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 26/32] drm/amdgpu: Fix cat debugfs amdgpu_regs_didt causes kernel null pointer Sasha Levin
2023-12-04 20:32 ` Sasha Levin [this message]
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 28/32] drm/amdgpu: Use another offset for GC 9.4.3 remap Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 29/32] smb: client, common: fix fortify warnings Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 30/32] Revert "drm/prime: Unexport helpers for fd/handle conversion" Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 31/32] blk-mq: don't count completed flush data request as inflight in case of quiesce Sasha Levin
2023-12-04 20:32 ` [PATCH AUTOSEL 6.6 32/32] nvme-core: check for too small lba shift Sasha Levin
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=20231204203317.2092321-27-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=Felix.Kuehling@amd.com \
--cc=Xinhui.Pan@amd.com \
--cc=airlied@gmail.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=zhenguo.yin@amd.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