From 056ae103a161b2543db8e1f8a47324907edc1912 Mon Sep 17 00:00:00 2001
From: David Yat Sin <david.yatsin@amd.com>
Date: Mon, 25 Jan 2021 11:29:30 -0500
Subject: drm/amdkfd: CRIU restore sdma id for queues
Git-commit: 2485c12c980a36bb9e23ababb07d73c4ac6a45af
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
When re-creating queues during CRIU restore, restore the queue with the
same sdma id value used during CRIU dump.
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 48 ++++++++++++++-----
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-
.../amd/amdkfd/kfd_process_queue_manager.c | 4 +-
3 files changed, 40 insertions(+), 15 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 4b6814949aad..15fa2dc6dcba 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -58,7 +58,7 @@ static inline void deallocate_hqd(struct device_queue_manager *dqm,
struct queue *q);
static int allocate_hqd(struct device_queue_manager *dqm, struct queue *q);
static int allocate_sdma_queue(struct device_queue_manager *dqm,
- struct queue *q);
+ struct queue *q, const uint32_t *restore_sdma_id);
static void kfd_process_hw_exception(struct work_struct *work);
static inline
@@ -299,7 +299,8 @@ 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)
+ struct qcm_process_device *qpd,
+ const struct kfd_criu_queue_priv_data *qd)
{
struct mqd_manager *mqd_mgr;
int retval;
@@ -339,7 +340,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
q->pipe, q->queue);
} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
- retval = allocate_sdma_queue(dqm, q);
+ retval = allocate_sdma_queue(dqm, q, qd ? &qd->sdma_id : NULL);
if (retval)
goto deallocate_vmid;
dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
@@ -1034,7 +1035,7 @@ static void pre_reset(struct device_queue_manager *dqm)
}
static int allocate_sdma_queue(struct device_queue_manager *dqm,
- struct queue *q)
+ struct queue *q, const uint32_t *restore_sdma_id)
{
int bit;
@@ -1044,9 +1045,21 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
return -ENOMEM;
}
- bit = __ffs64(dqm->sdma_bitmap);
- dqm->sdma_bitmap &= ~(1ULL << bit);
- q->sdma_id = bit;
+ if (restore_sdma_id) {
+ /* Re-use existing sdma_id */
+ if (!(dqm->sdma_bitmap & (1ULL << *restore_sdma_id))) {
+ pr_err("SDMA queue already in use\n");
+ return -EBUSY;
+ }
+ dqm->sdma_bitmap &= ~(1ULL << *restore_sdma_id);
+ q->sdma_id = *restore_sdma_id;
+ } else {
+ /* Find first available sdma_id */
+ bit = __ffs64(dqm->sdma_bitmap);
+ dqm->sdma_bitmap &= ~(1ULL << bit);
+ q->sdma_id = bit;
+ }
+
q->properties.sdma_engine_id = q->sdma_id %
kfd_get_num_sdma_engines(dqm->dev);
q->properties.sdma_queue_id = q->sdma_id /
@@ -1056,9 +1069,19 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
pr_err("No more XGMI SDMA queue to allocate\n");
return -ENOMEM;
}
- bit = __ffs64(dqm->xgmi_sdma_bitmap);
- dqm->xgmi_sdma_bitmap &= ~(1ULL << bit);
- q->sdma_id = bit;
+ if (restore_sdma_id) {
+ /* Re-use existing sdma_id */
+ if (!(dqm->xgmi_sdma_bitmap & (1ULL << *restore_sdma_id))) {
+ pr_err("SDMA queue already in use\n");
+ return -EBUSY;
+ }
+ dqm->xgmi_sdma_bitmap &= ~(1ULL << *restore_sdma_id);
+ q->sdma_id = *restore_sdma_id;
+ } else {
+ bit = __ffs64(dqm->xgmi_sdma_bitmap);
+ dqm->xgmi_sdma_bitmap &= ~(1ULL << bit);
+ q->sdma_id = bit;
+ }
/* sdma_engine_id is sdma id including
* both PCIe-optimized SDMAs and XGMI-
* optimized SDMAs. The calculation below
@@ -1288,7 +1311,8 @@ 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)
+ struct qcm_process_device *qpd,
+ const struct kfd_criu_queue_priv_data *qd)
{
int retval;
struct mqd_manager *mqd_mgr;
@@ -1303,7 +1327,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
dqm_lock(dqm);
- retval = allocate_sdma_queue(dqm, q);
+ retval = allocate_sdma_queue(dqm, q, qd ? &qd->sdma_id : NULL);
dqm_unlock(dqm);
if (retval)
goto out;
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 e145e4deb53a..76cc5e2a9733 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -88,7 +88,8 @@ struct device_process_node {
struct device_queue_manager_ops {
int (*create_queue)(struct device_queue_manager *dqm,
struct queue *q,
- struct qcm_process_device *qpd);
+ struct qcm_process_device *qpd,
+ const struct kfd_criu_queue_priv_data *qd);
int (*destroy_queue)(struct device_queue_manager *dqm,
struct qcm_process_device *qpd,
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 75bad4381421..8afe6879b861 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -272,7 +272,7 @@ 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);
+ retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data);
print_queue(q);
break;
@@ -292,7 +292,7 @@ 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);
+ retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data);
print_queue(q);
break;
case KFD_QUEUE_TYPE_DIQ:
--
2.38.1