From: Zhu Lingshan <lingshan.zhu@amd.com>
To: <felix.kuehling@amd.com>, <alexander.deucher@amd.com>
Cc: <ray.huang@amd.com>, <amd-gfx@lists.freedesktop.org>,
Zhu Lingshan <lingshan.zhu@amd.com>
Subject: [PATCH V5 05/18] amdkfd: destroy kfd secondary contexts through fd close
Date: Fri, 17 Oct 2025 16:42:09 +0800 [thread overview]
Message-ID: <20251017084222.54721-6-lingshan.zhu@amd.com> (raw)
In-Reply-To: <20251017084222.54721-1-lingshan.zhu@amd.com>
Life cycle of a KFD secondary context(kfd_process) is tied
to the opened file. Therefore this commit destroy a kfd
secondary context when close the fd it belonging to.
This commit extracts the code removing the kfd_process
from the kfd_process_table to a separate function and
call it in kfd_process_notifier_release_internal unconditionally.
Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 9 ++++--
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 1 +
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 41 +++++++++++++-----------
3 files changed, 31 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 0f0719528bcc..158e75975557 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -164,8 +164,13 @@ static int kfd_release(struct inode *inode, struct file *filep)
{
struct kfd_process *process = filep->private_data;
- if (process)
- kfd_unref_process(process);
+ if (!process)
+ return 0;
+
+ if (process->context_id != KFD_CONTEXT_ID_PRIMARY)
+ kfd_process_notifier_release_internal(process);
+
+ kfd_unref_process(process);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index cfedc0c5892c..919510f18249 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1096,6 +1096,7 @@ bool kfd_process_xnack_mode(struct kfd_process *p, bool supported);
int kfd_reserved_mem_mmap(struct kfd_node *dev, struct kfd_process *process,
struct vm_area_struct *vma);
+void kfd_process_notifier_release_internal(struct kfd_process *p);
/* KFD process API for creating and translating handles */
int kfd_process_device_create_obj_handle(struct kfd_process_device *pdd,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 83fe571b801c..995d27be06e3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1235,10 +1235,30 @@ static void kfd_process_free_notifier(struct mmu_notifier *mn)
kfd_unref_process(container_of(mn, struct kfd_process, mmu_notifier));
}
-static void kfd_process_notifier_release_internal(struct kfd_process *p)
+static void kfd_process_table_remove(struct kfd_process *p)
+{
+ mutex_lock(&kfd_processes_mutex);
+ /*
+ * Do early return if table is empty.
+ *
+ * This could potentially happen if this function is called concurrently
+ * by mmu_notifier and by kfd_cleanup_pocesses.
+ *
+ */
+ if (hash_empty(kfd_processes_table)) {
+ mutex_unlock(&kfd_processes_mutex);
+ return;
+ }
+ hash_del_rcu(&p->kfd_processes);
+ mutex_unlock(&kfd_processes_mutex);
+ synchronize_srcu(&kfd_processes_srcu);
+}
+
+void kfd_process_notifier_release_internal(struct kfd_process *p)
{
int i;
+ kfd_process_table_remove(p);
cancel_delayed_work_sync(&p->eviction_work);
cancel_delayed_work_sync(&p->restore_work);
@@ -1272,7 +1292,8 @@ static void kfd_process_notifier_release_internal(struct kfd_process *p)
srcu_read_unlock(&kfd_processes_srcu, idx);
}
- mmu_notifier_put(&p->mmu_notifier);
+ if (p->context_id == KFD_CONTEXT_ID_PRIMARY)
+ mmu_notifier_put(&p->mmu_notifier);
}
static void kfd_process_notifier_release(struct mmu_notifier *mn,
@@ -1288,22 +1309,6 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
if (WARN_ON(p->mm != mm))
return;
- mutex_lock(&kfd_processes_mutex);
- /*
- * Do early return if table is empty.
- *
- * This could potentially happen if this function is called concurrently
- * by mmu_notifier and by kfd_cleanup_pocesses.
- *
- */
- if (hash_empty(kfd_processes_table)) {
- mutex_unlock(&kfd_processes_mutex);
- return;
- }
- hash_del_rcu(&p->kfd_processes);
- mutex_unlock(&kfd_processes_mutex);
- synchronize_srcu(&kfd_processes_srcu);
-
kfd_process_notifier_release_internal(p);
}
--
2.51.0
next prev parent reply other threads:[~2025-10-17 8:43 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-17 8:42 [PATCH V5 00/18] [PATCH V4 00/18] amdkfd: Implement kfd multiple contexts Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 01/18] amdkfd: enlarge the hashtable of kfd_process Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 02/18] amdkfd: mark the first kfd_process as the primary one Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 03/18] amdkfd: find_process_by_mm always return the primary context Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 04/18] amdkfd: Introduce kfd_create_process_sysfs as a separate function Zhu Lingshan
2025-10-17 8:42 ` Zhu Lingshan [this message]
2025-10-17 8:42 ` [PATCH V5 06/18] amdkfd: process svm ioctl only on the primary kfd process Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 07/18] amdkfd: process USERPTR allocation " Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 08/18] amdkfd: identify a secondary kfd process by its id Zhu Lingshan
2025-10-17 23:16 ` Felix Kuehling
2025-10-22 6:56 ` Zhu, Lingshan
2025-10-17 8:42 ` [PATCH V5 09/18] amdkfd: find kfd_process by filep->private_data in kfd_mmap Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 10/18] amdkfd: remove DIQ support Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 11/18] amdkfd: process pointer of a HIQ should be NULL Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 12/18] amdkfd: remove test_kq Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 13/18] amdkfd: introduce new helper kfd_lookup_process_by_id Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 14/18] amdkfd: record kfd context id into kfd process_info Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 15/18] amdkfd: record kfd context id in amdkfd_fence Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 16/18] amdkfd: fence handler evict and restore a kfd process by its context id Zhu Lingshan
2025-10-17 8:42 ` [PATCH V5 17/18] amdkfd: process debug trap ioctl only on a primary context Zhu Lingshan
2025-10-17 23:32 ` Felix Kuehling
2025-10-22 6:55 ` Zhu, Lingshan
2025-10-17 8:42 ` [PATCH V5 18/18] amdkfd: introduce new ioctl AMDKFD_IOC_CREATE_PROCESS Zhu Lingshan
2025-10-17 23:55 ` Felix Kuehling
2025-10-22 6:59 ` Zhu, Lingshan
2025-10-17 23:58 ` [PATCH V5 00/18] [PATCH V4 00/18] amdkfd: Implement kfd multiple contexts Felix Kuehling
2025-10-22 7:01 ` Zhu, Lingshan
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=20251017084222.54721-6-lingshan.zhu@amd.com \
--to=lingshan.zhu@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=felix.kuehling@amd.com \
--cc=ray.huang@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