[Patch v5 12/24] drm/amdkfd: CRIU checkpoint and restore queue mqds
Rajneesh Bhardwaj
rajneesh.bhardwaj at amd.com
Thu Feb 3 09:09:06 UTC 2022
From: David Yat Sin <david.yatsin at amd.com>
Checkpoint contents of queue MQD's on CRIU dump and restore them during
CRIU restore.
Signed-off-by: David Yat Sin <david.yatsin at amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj at amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c | 2 +-
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 73 +++++++-
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 12 +-
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h | 7 +
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c | 70 ++++++++
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 71 ++++++++
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 71 ++++++++
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c | 72 ++++++++
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 5 +
.../amd/amdkfd/kfd_process_queue_manager.c | 157 ++++++++++++++++--
11 files changed, 516 insertions(+), 26 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index d35911550792..999672602252 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -311,7 +311,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
p->pasid,
dev->id);
- err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL,
+ err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, NULL,
&doorbell_offset_in_process);
if (err != 0)
goto err_create_queue;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 0c50e67e2b51..3a5303ebcabf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -185,7 +185,7 @@ static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev)
properties.type = KFD_QUEUE_TYPE_DIQ;
status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,
- &properties, &qid, NULL, NULL);
+ &properties, &qid, NULL, NULL, NULL);
if (status) {
pr_err("Failed to create DIQ\n");
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 13317d2c8959..42933610d4e1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -322,7 +322,8 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
static int create_queue_nocpsch(struct device_queue_manager *dqm,
struct queue *q,
struct qcm_process_device *qpd,
- const struct kfd_criu_queue_priv_data *qd)
+ const struct kfd_criu_queue_priv_data *qd,
+ const void *restore_mqd)
{
struct mqd_manager *mqd_mgr;
int retval;
@@ -381,8 +382,14 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
retval = -ENOMEM;
goto out_deallocate_doorbell;
}
- mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
- &q->gart_mqd_addr, &q->properties);
+
+ if (qd)
+ mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,
+ &q->properties, restore_mqd);
+ else
+ mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
+ &q->gart_mqd_addr, &q->properties);
+
if (q->properties.is_active) {
if (!dqm->sched_running) {
WARN_ONCE(1, "Load non-HWS mqd while stopped\n");
@@ -1334,7 +1341,8 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
struct qcm_process_device *qpd,
- const struct kfd_criu_queue_priv_data *qd)
+ const struct kfd_criu_queue_priv_data *qd,
+ const void *restore_mqd)
{
int retval;
struct mqd_manager *mqd_mgr;
@@ -1380,8 +1388,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
* updates the is_evicted flag but is a no-op otherwise.
*/
q->properties.is_evicted = !!qpd->evicted;
- mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
- &q->gart_mqd_addr, &q->properties);
+
+ if (qd)
+ mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,
+ &q->properties, restore_mqd);
+ else
+ mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
+ &q->gart_mqd_addr, &q->properties);
list_add(&q->list, &qpd->queues_list);
qpd->queue_count++;
@@ -1784,6 +1797,50 @@ static int get_wave_state(struct device_queue_manager *dqm,
ctl_stack_used_size, save_area_used_size);
}
+static void get_queue_checkpoint_info(struct device_queue_manager *dqm,
+ const struct queue *q,
+ u32 *mqd_size)
+{
+ struct mqd_manager *mqd_mgr;
+ enum KFD_MQD_TYPE mqd_type =
+ get_mqd_type_from_queue_type(q->properties.type);
+
+ dqm_lock(dqm);
+ mqd_mgr = dqm->mqd_mgrs[mqd_type];
+ *mqd_size = mqd_mgr->mqd_size;
+
+ dqm_unlock(dqm);
+}
+
+static int checkpoint_mqd(struct device_queue_manager *dqm,
+ const struct queue *q,
+ void *mqd)
+{
+ struct mqd_manager *mqd_mgr;
+ int r = 0;
+ enum KFD_MQD_TYPE mqd_type =
+ get_mqd_type_from_queue_type(q->properties.type);
+
+ dqm_lock(dqm);
+
+ if (q->properties.is_active || !q->device->cwsr_enabled) {
+ r = -EINVAL;
+ goto dqm_unlock;
+ }
+
+ mqd_mgr = dqm->mqd_mgrs[mqd_type];
+ if (!mqd_mgr->checkpoint_mqd) {
+ r = -EOPNOTSUPP;
+ goto dqm_unlock;
+ }
+
+ mqd_mgr->checkpoint_mqd(mqd_mgr, q->mqd, mqd);
+
+dqm_unlock:
+ dqm_unlock(dqm);
+ return r;
+}
+
static int process_termination_cpsch(struct device_queue_manager *dqm,
struct qcm_process_device *qpd)
{
@@ -1961,6 +2018,8 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
dqm->ops.restore_process_queues = restore_process_queues_cpsch;
dqm->ops.get_wave_state = get_wave_state;
dqm->ops.reset_queues = reset_queues_cpsch;
+ dqm->ops.get_queue_checkpoint_info = get_queue_checkpoint_info;
+ dqm->ops.checkpoint_mqd = checkpoint_mqd;
break;
case KFD_SCHED_POLICY_NO_HWS:
/* initialize dqm for no cp scheduling */
@@ -1980,6 +2039,8 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
dqm->ops.restore_process_queues =
restore_process_queues_nocpsch;
dqm->ops.get_wave_state = get_wave_state;
+ dqm->ops.get_queue_checkpoint_info = get_queue_checkpoint_info;
+ dqm->ops.checkpoint_mqd = checkpoint_mqd;
break;
default:
pr_err("Invalid scheduling policy %d\n", dqm->sched_policy);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 76cc5e2a9733..fb6aa2a1ca0f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -83,13 +83,17 @@ struct device_process_node {
* control stack, if kept in the MQD, to the given userspace address.
*
* @reset_queues: reset queues which consume RAS poison
+ * @get_queue_checkpoint_info: Retrieves queue size information for CRIU checkpoint.
+ *
+ * @checkpoint_mqd: checkpoint queue MQD contents for CRIU.
*/
struct device_queue_manager_ops {
int (*create_queue)(struct device_queue_manager *dqm,
struct queue *q,
struct qcm_process_device *qpd,
- const struct kfd_criu_queue_priv_data *qd);
+ const struct kfd_criu_queue_priv_data *qd,
+ const void *restore_mqd);
int (*destroy_queue)(struct device_queue_manager *dqm,
struct qcm_process_device *qpd,
@@ -140,6 +144,12 @@ struct device_queue_manager_ops {
int (*reset_queues)(struct device_queue_manager *dqm,
uint16_t pasid);
+ void (*get_queue_checkpoint_info)(struct device_queue_manager *dqm,
+ const struct queue *q, u32 *mqd_size);
+
+ int (*checkpoint_mqd)(struct device_queue_manager *dqm,
+ const struct queue *q,
+ void *mqd);
};
struct device_queue_manager_asic_ops {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 965e17c5dbb4..cebb2877a505 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -100,6 +100,13 @@ struct mqd_manager {
u32 *ctl_stack_used_size,
u32 *save_area_used_size);
+ void (*checkpoint_mqd)(struct mqd_manager *mm, void *mqd, void *mqd_dst);
+
+ void (*restore_mqd)(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *p,
+ const void *mqd_src);
+
#if defined(CONFIG_DEBUG_FS)
int (*debugfs_show_mqd)(struct seq_file *m, void *data);
#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index e9a8e21e144e..83117209bc15 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -280,6 +280,72 @@ static int destroy_mqd(struct mqd_manager *mm, void *mqd,
pipe_id, queue_id);
}
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct cik_mqd *m;
+
+ m = get_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct cik_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct cik_mqd *m;
+
+ m = (struct cik_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ m->cp_hqd_pq_doorbell_control = DOORBELL_OFFSET(qp->doorbell_off);
+
+ pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+ m->cp_hqd_pq_doorbell_control);
+
+ qp->is_active = 0;
+}
+
+static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct cik_sdma_rlc_registers *m;
+
+ m = get_sdma_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct cik_sdma_rlc_registers));
+}
+
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct cik_sdma_rlc_registers *m;
+
+ m = (struct cik_sdma_rlc_registers *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ m->sdma_rlc_doorbell =
+ qp->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ qp->is_active = 0;
+}
+
/*
* preempt type here is ignored because there is only one way
* to preempt sdma queue
@@ -394,6 +460,8 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
mqd->update_mqd = update_mqd;
mqd->destroy_mqd = destroy_mqd;
mqd->is_occupied = is_occupied;
+ mqd->checkpoint_mqd = checkpoint_mqd;
+ mqd->restore_mqd = restore_mqd;
mqd->mqd_size = sizeof(struct cik_mqd);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -434,6 +502,8 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
mqd->update_mqd = update_mqd_sdma;
mqd->destroy_mqd = destroy_mqd_sdma;
mqd->is_occupied = is_occupied_sdma;
+ mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+ mqd->restore_mqd = restore_mqd_sdma;
mqd->mqd_size = sizeof(struct cik_sdma_rlc_registers);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index d74d8a6ac27a..4ddf5b45c42a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -285,6 +285,41 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
return 0;
}
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct v10_compute_mqd *m;
+
+ m = get_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct v10_compute_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct v10_compute_mqd *m;
+
+ m = (struct v10_compute_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ m->cp_hqd_pq_doorbell_control =
+ qp->doorbell_off <<
+ CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+ pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+ m->cp_hqd_pq_doorbell_control);
+
+ qp->is_active = 0;
+}
+
static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
struct queue_properties *q)
@@ -373,6 +408,38 @@ static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
}
+static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct v10_sdma_mqd *m;
+
+ m = get_sdma_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct v10_sdma_mqd));
+}
+
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct v10_sdma_mqd *m;
+
+ m = (struct v10_sdma_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ m->sdmax_rlcx_doorbell_offset =
+ qp->doorbell_off << SDMA0_RLC0_DOORBELL_OFFSET__OFFSET__SHIFT;
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ qp->is_active = 0;
+}
+
#if defined(CONFIG_DEBUG_FS)
static int debugfs_show_mqd(struct seq_file *m, void *data)
@@ -417,6 +484,8 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
mqd->is_occupied = is_occupied;
mqd->mqd_size = sizeof(struct v10_compute_mqd);
mqd->get_wave_state = get_wave_state;
+ mqd->checkpoint_mqd = checkpoint_mqd;
+ mqd->restore_mqd = restore_mqd;
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd;
#endif
@@ -460,6 +529,8 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
mqd->update_mqd = update_mqd_sdma;
mqd->destroy_mqd = destroy_mqd_sdma;
mqd->is_occupied = is_occupied_sdma;
+ mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+ mqd->restore_mqd = restore_mqd_sdma;
mqd->mqd_size = sizeof(struct v10_sdma_mqd);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 326eb2285029..18ad7669eedf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -340,6 +340,41 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
return 0;
}
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct v9_mqd *m;
+
+ m = get_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct v9_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct v9_mqd *m;
+
+ m = (struct v9_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ m->cp_hqd_pq_doorbell_control =
+ qp->doorbell_off <<
+ CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+ pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+ m->cp_hqd_pq_doorbell_control);
+
+ qp->is_active = 0;
+}
+
static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
struct queue_properties *q)
@@ -428,6 +463,38 @@ static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
}
+static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct v9_sdma_mqd *m;
+
+ m = get_sdma_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct v9_sdma_mqd));
+}
+
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct v9_sdma_mqd *m;
+
+ m = (struct v9_sdma_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ m->sdmax_rlcx_doorbell_offset =
+ qp->doorbell_off << SDMA0_RLC0_DOORBELL_OFFSET__OFFSET__SHIFT;
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ qp->is_active = 0;
+}
+
#if defined(CONFIG_DEBUG_FS)
static int debugfs_show_mqd(struct seq_file *m, void *data)
@@ -470,6 +537,8 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
mqd->destroy_mqd = destroy_mqd;
mqd->is_occupied = is_occupied;
mqd->get_wave_state = get_wave_state;
+ mqd->checkpoint_mqd = checkpoint_mqd;
+ mqd->restore_mqd = restore_mqd;
mqd->mqd_size = sizeof(struct v9_mqd);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -510,6 +579,8 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
mqd->update_mqd = update_mqd_sdma;
mqd->destroy_mqd = destroy_mqd_sdma;
mqd->is_occupied = is_occupied_sdma;
+ mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+ mqd->restore_mqd = restore_mqd_sdma;
mqd->mqd_size = sizeof(struct v9_sdma_mqd);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index d456e950ce1d..9fdc67b60bb4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -306,6 +306,42 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
return 0;
}
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct vi_mqd *m;
+
+ m = get_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct vi_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct vi_mqd *m;
+
+ m = (struct vi_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ m->cp_hqd_pq_doorbell_control =
+ qp->doorbell_off <<
+ CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+ pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+ m->cp_hqd_pq_doorbell_control);
+
+ qp->is_active = 0;
+}
+
+
static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
struct queue_properties *q)
@@ -399,6 +435,38 @@ static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
}
+static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst)
+{
+ struct vi_sdma_mqd *m;
+
+ m = get_sdma_mqd(mqd);
+
+ memcpy(mqd_dst, m, sizeof(struct vi_sdma_mqd));
+}
+
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+ struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+ struct queue_properties *qp,
+ const void *mqd_src)
+{
+ uint64_t addr;
+ struct vi_sdma_mqd *m;
+
+ m = (struct vi_sdma_mqd *) mqd_mem_obj->cpu_ptr;
+ addr = mqd_mem_obj->gpu_addr;
+
+ memcpy(m, mqd_src, sizeof(*m));
+
+ m->sdmax_rlcx_doorbell =
+ qp->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+ *mqd = m;
+ if (gart_addr)
+ *gart_addr = addr;
+
+ qp->is_active = 0;
+}
+
#if defined(CONFIG_DEBUG_FS)
static int debugfs_show_mqd(struct seq_file *m, void *data)
@@ -441,6 +509,8 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
mqd->destroy_mqd = destroy_mqd;
mqd->is_occupied = is_occupied;
mqd->get_wave_state = get_wave_state;
+ mqd->checkpoint_mqd = checkpoint_mqd;
+ mqd->restore_mqd = restore_mqd;
mqd->mqd_size = sizeof(struct vi_mqd);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -481,6 +551,8 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
mqd->update_mqd = update_mqd_sdma;
mqd->destroy_mqd = destroy_mqd_sdma;
mqd->is_occupied = is_occupied_sdma;
+ mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+ mqd->restore_mqd = restore_mqd_sdma;
mqd->mqd_size = sizeof(struct vi_sdma_mqd);
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 59125d8f16a7..1c62abe0dbd5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1158,6 +1158,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
struct queue_properties *properties,
unsigned int *qid,
const struct kfd_criu_queue_priv_data *q_data,
+ const void *restore_mqd,
uint32_t *p_doorbell_offset_in_process);
int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
int pqm_update_queue_properties(struct process_queue_manager *pqm, unsigned int qid,
@@ -1180,6 +1181,10 @@ int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
uint64_t fence_value,
unsigned int timeout_ms);
+int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm,
+ unsigned int qid,
+ u32 *mqd_size);
+
/* Packet Manager */
#define KFD_FENCE_COMPLETED (100)
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 8afe6879b861..844917c1c346 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -208,6 +208,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
struct queue_properties *properties,
unsigned int *qid,
const struct kfd_criu_queue_priv_data *q_data,
+ const void *restore_mqd,
uint32_t *p_doorbell_offset_in_process)
{
int retval;
@@ -272,7 +273,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
goto err_create_queue;
pqn->q = q;
pqn->kq = NULL;
- retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data);
+ retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data, restore_mqd);
print_queue(q);
break;
@@ -292,7 +293,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
goto err_create_queue;
pqn->q = q;
pqn->kq = NULL;
- retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data);
+ retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data, restore_mqd);
print_queue(q);
break;
case KFD_QUEUE_TYPE_DIQ:
@@ -517,12 +518,25 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
save_area_used_size);
}
+static int get_queue_data_sizes(struct kfd_process_device *pdd, struct queue *q, uint32_t *mqd_size)
+{
+ int ret;
+
+ ret = pqm_get_queue_checkpoint_info(&pdd->process->pqm, q->properties.queue_id, mqd_size);
+ if (ret)
+ pr_err("Failed to get queue dump info (%d)\n", ret);
+
+ return ret;
+}
+
int kfd_process_get_queue_info(struct kfd_process *p,
uint32_t *num_queues,
uint64_t *priv_data_sizes)
{
+ uint32_t extra_data_sizes = 0;
struct queue *q;
int i;
+ int ret;
*num_queues = 0;
@@ -534,23 +548,53 @@ int kfd_process_get_queue_info(struct kfd_process *p,
if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
q->properties.type == KFD_QUEUE_TYPE_SDMA ||
q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
-
+ uint32_t mqd_size;
*num_queues = *num_queues + 1;
+
+ ret = get_queue_data_sizes(pdd, q, &mqd_size);
+ if (ret)
+ return ret;
+
+ extra_data_sizes += mqd_size;
} else {
pr_err("Unsupported queue type (%d)\n", q->properties.type);
return -EOPNOTSUPP;
}
}
}
- *priv_data_sizes = *num_queues * sizeof(struct kfd_criu_queue_priv_data);
+ *priv_data_sizes = extra_data_sizes +
+ (*num_queues * sizeof(struct kfd_criu_queue_priv_data));
return 0;
}
-static void criu_checkpoint_queue(struct kfd_process_device *pdd,
+static int pqm_checkpoint_mqd(struct process_queue_manager *pqm, unsigned int qid, void *mqd)
+{
+ struct process_queue_node *pqn;
+
+ pqn = get_queue_by_qid(pqm, qid);
+ if (!pqn) {
+ pr_debug("amdkfd: No queue %d exists for operation\n", qid);
+ return -EFAULT;
+ }
+
+ if (!pqn->q->device->dqm->ops.checkpoint_mqd) {
+ pr_err("amdkfd: queue dumping not supported on this device\n");
+ return -EOPNOTSUPP;
+ }
+
+ return pqn->q->device->dqm->ops.checkpoint_mqd(pqn->q->device->dqm, pqn->q, mqd);
+}
+
+static int criu_checkpoint_queue(struct kfd_process_device *pdd,
struct queue *q,
struct kfd_criu_queue_priv_data *q_data)
{
+ uint8_t *mqd;
+ int ret;
+
+ mqd = (void *)(q_data + 1);
+
q_data->gpu_id = pdd->dev->id;
q_data->type = q->properties.type;
q_data->format = q->properties.format;
@@ -576,7 +620,14 @@ static void criu_checkpoint_queue(struct kfd_process_device *pdd,
q_data->ctx_save_restore_area_size =
q->properties.ctx_save_restore_area_size;
+ ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd);
+ if (ret) {
+ pr_err("Failed checkpoint queue_mqd (%d)\n", ret);
+ return ret;
+ }
+
pr_debug("Dumping Queue: gpu_id:%x queue_id:%u\n", q_data->gpu_id, q_data->q_id);
+ return ret;
}
static int criu_checkpoint_queues_device(struct kfd_process_device *pdd,
@@ -584,15 +635,16 @@ static int criu_checkpoint_queues_device(struct kfd_process_device *pdd,
unsigned int *q_index,
uint64_t *queues_priv_data_offset)
{
- struct kfd_criu_queue_priv_data *q_data;
+ unsigned int q_private_data_size = 0;
+ uint8_t *q_private_data = NULL; /* Local buffer to store individual queue private data */
struct queue *q;
int ret = 0;
- q_data = kzalloc(sizeof(*q_data), GFP_KERNEL);
- if (!q_data)
- return -ENOMEM;
-
list_for_each_entry(q, &pdd->qpd.queues_list, list) {
+ struct kfd_criu_queue_priv_data *q_data;
+ uint64_t q_data_size;
+ uint32_t mqd_size;
+
if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE &&
q->properties.type != KFD_QUEUE_TYPE_SDMA &&
q->properties.type != KFD_QUEUE_TYPE_SDMA_XGMI) {
@@ -602,19 +654,46 @@ static int criu_checkpoint_queues_device(struct kfd_process_device *pdd,
break;
}
- criu_checkpoint_queue(pdd, q, q_data);
+ ret = get_queue_data_sizes(pdd, q, &mqd_size);
+ if (ret)
+ break;
+
+ q_data_size = sizeof(*q_data) + mqd_size;
+
+ /* Increase local buffer space if needed */
+ if (q_private_data_size < q_data_size) {
+ kfree(q_private_data);
+
+ q_private_data = kzalloc(q_data_size, GFP_KERNEL);
+ if (!q_private_data) {
+ ret = -ENOMEM;
+ break;
+ }
+ q_private_data_size = q_data_size;
+ }
+
+ q_data = (struct kfd_criu_queue_priv_data *)q_private_data;
+
+ /* data stored in this order: priv_data, mqd */
+ q_data->mqd_size = mqd_size;
+
+ ret = criu_checkpoint_queue(pdd, q, q_data);
+ if (ret)
+ break;
+
q_data->object_type = KFD_CRIU_OBJECT_TYPE_QUEUE;
- ret = copy_to_user(user_priv + *queues_priv_data_offset, q_data, sizeof(*q_data));
+ ret = copy_to_user(user_priv + *queues_priv_data_offset,
+ q_data, q_data_size);
if (ret) {
ret = -EFAULT;
break;
}
- *queues_priv_data_offset += sizeof(*q_data);
+ *queues_priv_data_offset += q_data_size;
*q_index = *q_index + 1;
}
- kfree(q_data);
+ kfree(q_private_data);
return ret;
}
@@ -668,11 +747,12 @@ int kfd_criu_restore_queue(struct kfd_process *p,
uint64_t max_priv_data_size)
{
struct kfd_criu_queue_priv_data *q_data;
+ uint8_t *mqd, *q_extra_data = NULL;
struct kfd_process_device *pdd;
- struct kfd_dev *dev;
+ uint64_t q_extra_data_size;
struct queue_properties qp;
unsigned int queue_id;
-
+ struct kfd_dev *dev;
int ret = 0;
if (*priv_data_offset + sizeof(*q_data) > max_priv_data_size)
@@ -689,6 +769,26 @@ int kfd_criu_restore_queue(struct kfd_process *p,
}
*priv_data_offset += sizeof(*q_data);
+ q_extra_data_size = q_data->mqd_size;
+
+ if (*priv_data_offset + q_extra_data_size > max_priv_data_size) {
+ ret = -EINVAL;
+ goto exit;
+ }
+
+ q_extra_data = kmalloc(q_extra_data_size, GFP_KERNEL);
+ if (!q_extra_data) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
+ ret = copy_from_user(q_extra_data, user_priv_ptr + *priv_data_offset, q_extra_data_size);
+ if (ret) {
+ ret = -EFAULT;
+ goto exit;
+ }
+
+ *priv_data_offset += q_extra_data_size;
dev = kfd_device_by_id(q_data->gpu_id);
if (!dev) {
@@ -705,13 +805,15 @@ int kfd_criu_restore_queue(struct kfd_process *p,
ret = -EFAULT;
return ret;
}
+ /* data stored in this order: mqd */
+ mqd = q_extra_data;
memset(&qp, 0, sizeof(qp));
set_queue_properties_from_criu(&qp, q_data);
print_queue_properties(&qp);
- ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, q_data, NULL);
+ ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, q_data, mqd, NULL);
if (ret) {
pr_err("Failed to create new queue err:%d\n", ret);
ret = -EINVAL;
@@ -728,6 +830,27 @@ int kfd_criu_restore_queue(struct kfd_process *p,
return ret;
}
+int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm,
+ unsigned int qid,
+ uint32_t *mqd_size)
+{
+ struct process_queue_node *pqn;
+
+ pqn = get_queue_by_qid(pqm, qid);
+ if (!pqn) {
+ pr_debug("amdkfd: No queue %d exists for operation\n", qid);
+ return -EFAULT;
+ }
+
+ if (!pqn->q->device->dqm->ops.get_queue_checkpoint_info) {
+ pr_err("amdkfd: queue dumping not supported on this device\n");
+ return -EOPNOTSUPP;
+ }
+
+ pqn->q->device->dqm->ops.get_queue_checkpoint_info(pqn->q->device->dqm, pqn->q, mqd_size);
+ return 0;
+}
+
#if defined(CONFIG_DEBUG_FS)
int pqm_debugfs_mqds(struct seq_file *m, void *data)
--
2.17.1
More information about the amd-gfx
mailing list