amdkfd: introduce new ioctl AMDKFD_IOC_CREATE_PROCESS

This commit implemetns a new ioctl AMDKFD_IOC_CREATE_PROCESS
that creates a new secondary kfd_progress on the FD.

To keep backward compatibility, userspace programs need to invoke
this ioctl explicitly on a FD to create a secondary
kfd_process which replacing its primary kfd_process.

This commit bumps ioctl minor version.

Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 092a2b8aaea141deed0eeb87be73d91e944c2a39..041237861107f457b9519f5f48e14340096fc01a 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -3150,6 +3150,48 @@ out:
        return r;
 }
 
+/* userspace programs need to invoke this ioctl explicitly on a FD to
+ * create a secondary kfd_process which replacing its primary kfd_process
+ */
+static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, void *data)
+{
+       struct kfd_process *process;
+       int ret;
+
+       /* Each FD owns only one kfd_process */
+       if (p->context_id != KFD_CONTEXT_ID_PRIMARY)
+               return -EINVAL;
+
+       if (!filep->private_data || !p)
+               return -EINVAL;
+
+       mutex_lock(&kfd_processes_mutex);
+       if (p != filep->private_data) {
+               mutex_unlock(&kfd_processes_mutex);
+               return -EINVAL;
+       }
+
+       process = create_process(current, false);
+       if (IS_ERR(process)) {
+               mutex_unlock(&kfd_processes_mutex);
+               return PTR_ERR(process);
+       }
+
+       filep->private_data = process;
+       mutex_unlock(&kfd_processes_mutex);
+
+       ret = kfd_create_process_sysfs(process);
+       if (ret)
+               pr_warn("Failed to create sysfs entry for the kfd_process");
+
+       /* Each open() increases kref of the primary kfd_process,
+        * so we need to reduce it here when we create a new secondary process replacing it
+        */
+       kfd_unref_process(p);
+
+       return 0;
+}
+
 #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
        [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \
                            .cmd_drv = 0, .name = #ioctl}
@@ -3268,6 +3310,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 
        AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_TRAP,
                        kfd_ioctl_set_debug_trap, 0),
+
+       AMDKFD_IOCTL_DEF(AMDKFD_IOC_CREATE_PROCESS,
+                       kfd_ioctl_create_process, 0),
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT        ARRAY_SIZE(amdkfd_ioctls)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 399f32689678f1290d97dd8c9dd57e2bfcf71f15..12f640a9370ad403667578b0a7cd6c8e63953e80 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1053,6 +1053,7 @@ struct amdkfd_ioctl_desc {
 };
 bool kfd_dev_is_large_bar(struct kfd_node *dev);
 
+struct kfd_process *create_process(const struct task_struct *thread, bool primary);
 int kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 void kfd_cleanup_processes(void);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index c52e56aa93166d49fc12e93e36670b72a8a99560..b4982da9234b23d80c0821c0d17d53c1e1e9092b 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -68,7 +68,6 @@ static struct workqueue_struct *kfd_restore_wq;
 static struct kfd_process *find_process(const struct task_struct *thread,
                                        bool ref);
 static void kfd_process_ref_release(struct kref *ref);
-static struct kfd_process *create_process(const struct task_struct *thread, bool primary);
 
 static void evict_process_worker(struct work_struct *work);
 static void restore_process_worker(struct work_struct *work);
@@ -1582,7 +1581,7 @@ void kfd_process_set_trap_debug_flag(struct qcm_process_device *qpd,
  * On return the kfd_process is fully operational and will be freed when the
  * mm is released
  */
-static struct kfd_process *create_process(const struct task_struct *thread, bool primary)
+struct kfd_process *create_process(const struct task_struct *thread, bool primary)
 {
        struct kfd_process *process;
        struct mmu_notifier *mn;

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 5d1727a6d040535d123f47d7850ec99c79a79f4c..84aa24c02715abd593d9c1f2992c0a9ec8eebd84 100644 (file)
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -44,9 +44,10 @@
  * - 1.16 - Add contiguous VRAM allocation flag
  * - 1.17 - Add SDMA queue creation with target SDMA engine ID
  * - 1.18 - Rename pad in set_memory_policy_args to misc_process_flag
+ * - 1.19 - Add a new ioctl to craete secondary kfd processes
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 18
+#define KFD_IOCTL_MINOR_VERSION 19
 
 struct kfd_ioctl_get_version_args {
        __u32 major_version;    /* from KFD */
@@ -1671,7 +1672,10 @@ struct kfd_ioctl_dbg_trap_args {
 #define AMDKFD_IOC_DBG_TRAP                    \
                AMDKFD_IOWR(0x26, struct kfd_ioctl_dbg_trap_args)
 
+#define AMDKFD_IOC_CREATE_PROCESS              \
+               AMDKFD_IO(0x27)
+
 #define AMDKFD_COMMAND_START           0x01
-#define AMDKFD_COMMAND_END             0x27
+#define AMDKFD_COMMAND_END             0x28
 
 #endif