[v5,13/24] drm/amdkfd: CRIU checkpoint and restore queue control stack

Message ID	20220203090918.11520-14-rajneesh.bhardwaj@amd.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <dri-devel-bounces@lists.freedesktop.org> Received-SPF: Pass (protection.outlook.com: domain of amd.com designates 165.204.84.17 as permitted sender) receiver=protection.outlook.com; client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com> To: <amd-gfx@lists.freedesktop.org> Subject: [Patch v5 13/24] drm/amdkfd: CRIU checkpoint and restore queue control stack Date: Thu, 3 Feb 2022 04:09:07 -0500 Message-ID: <20220203090918.11520-14-rajneesh.bhardwaj@amd.com> In-Reply-To: <20220203090918.11520-1-rajneesh.bhardwaj@amd.com> References: <20220203090918.11520-1-rajneesh.bhardwaj@amd.com> MIME-Version: 1.0 Content-Type: text/plain Precedence: list Cc: alexander.deucher@amd.com, felix.kuehling@amd.com, david.yatsin@amd.com, Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>, dri-devel@lists.freedesktop.org Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" <dri-devel-bounces@lists.freedesktop.org>
Series	CHECKPOINT RESTORE WITH ROCm \| expand [v5,00/24] CHECKPOINT RESTORE WITH ROCm [v5,01/24] x86/configs: CRIU update debug rock defconfig [v5,02/24] drm/amdkfd: CRIU Introduce Checkpoint-Restore APIs [v5,03/24] drm/amdkfd: CRIU Implement KFD process_info ioctl [v5,04/24] drm/amdkfd: CRIU Implement KFD checkpoint ioctl [v5,05/24] drm/amdkfd: CRIU Implement KFD restore ioctl [v5,06/24] drm/amdkfd: CRIU Implement KFD resume ioctl [v5,07/24] drm/amdkfd: CRIU Implement KFD unpause operation [v5,08/24] drm/amdkfd: CRIU add queues support [v5,09/24] drm/amdkfd: CRIU restore queue ids [v5,10/24] drm/amdkfd: CRIU restore sdma id for queues [v5,11/24] drm/amdkfd: CRIU restore queue doorbell id [v5,12/24] drm/amdkfd: CRIU checkpoint and restore queue mqds [v5,13/24] drm/amdkfd: CRIU checkpoint and restore queue control stack [v5,14/24] drm/amdkfd: CRIU checkpoint and restore events [v5,15/24] drm/amdkfd: CRIU implement gpu_id remapping [v5,16/24] drm/amdkfd: CRIU export BOs as prime dmabuf objects [v5,17/24] drm/amdkfd: CRIU checkpoint and restore xnack mode [v5,18/24] drm/amdkfd: CRIU allow external mm for svm ranges [v5,19/24] drm/amdkfd: use user_gpu_id for svm ranges [v5,20/24] drm/amdkfd: CRIU Discover svm ranges [v5,21/24] drm/amdkfd: CRIU Save Shared Virtual Memory ranges [v5,22/24] drm/amdkfd: CRIU prepare for svm resume [v5,23/24] drm/amdkfd: CRIU resume shared virtual memory ranges [v5,24/24] drm/amdkfd: Bump up KFD API version for CRIU

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 999672602252..608214ea634d 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, NULL, + err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, 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 3a5303ebcabf..8eca9ed3ab36 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, NULL); + &properties, &qid, NULL, 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 42933610d4e1..63b3c7af681b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -323,7 +323,7 @@ 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 void *restore_mqd) + const void *restore_mqd, const void *restore_ctl_stack) { struct mqd_manager *mqd_mgr; int retval; @@ -385,7 +385,8 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, if (qd) mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr, - &q->properties, restore_mqd); + &q->properties, restore_mqd, restore_ctl_stack, + qd->ctl_stack_size); else mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); @@ -1342,7 +1343,7 @@ 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 void *restore_mqd) + const void *restore_mqd, const void *restore_ctl_stack) { int retval; struct mqd_manager *mqd_mgr; @@ -1391,7 +1392,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (qd) mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr, - &q->properties, restore_mqd); + &q->properties, restore_mqd, restore_ctl_stack, + qd->ctl_stack_size); else mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); @@ -1799,7 +1801,8 @@ static int get_wave_state(struct device_queue_manager *dqm, static void get_queue_checkpoint_info(struct device_queue_manager *dqm, const struct queue *q, - u32 *mqd_size) + u32 *mqd_size, + u32 *ctl_stack_size) { struct mqd_manager *mqd_mgr; enum KFD_MQD_TYPE mqd_type = @@ -1808,13 +1811,18 @@ static void get_queue_checkpoint_info(struct device_queue_manager *dqm, dqm_lock(dqm); mqd_mgr = dqm->mqd_mgrs[mqd_type]; *mqd_size = mqd_mgr->mqd_size; + *ctl_stack_size = 0; + + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE && mqd_mgr->get_checkpoint_info) + mqd_mgr->get_checkpoint_info(mqd_mgr, q->mqd, ctl_stack_size); dqm_unlock(dqm); } static int checkpoint_mqd(struct device_queue_manager *dqm, const struct queue *q, - void *mqd) + void *mqd, + void *ctl_stack) { struct mqd_manager *mqd_mgr; int r = 0; @@ -1834,7 +1842,7 @@ static int checkpoint_mqd(struct device_queue_manager *dqm, goto dqm_unlock; } - mqd_mgr->checkpoint_mqd(mqd_mgr, q->mqd, mqd); + mqd_mgr->checkpoint_mqd(mqd_mgr, q->mqd, mqd, ctl_stack); dqm_unlock: dqm_unlock(dqm); 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 fb6aa2a1ca0f..a7d2e3323977 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -93,7 +93,8 @@ struct device_queue_manager_ops { struct queue *q, struct qcm_process_device *qpd, const struct kfd_criu_queue_priv_data *qd, - const void *restore_mqd); + const void *restore_mqd, + const void *restore_ctl_stack); int (*destroy_queue)(struct device_queue_manager *dqm, struct qcm_process_device *qpd, @@ -145,11 +146,13 @@ 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); + const struct queue *q, u32 *mqd_size, + u32 *ctl_stack_size); int (*checkpoint_mqd)(struct device_queue_manager *dqm, const struct queue *q, - void *mqd); + void *mqd, + void *ctl_stack); }; 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 cebb2877a505..23486a23df84 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h @@ -100,12 +100,19 @@ 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 (*get_checkpoint_info)(struct mqd_manager *mm, void *mqd, uint32_t *ctl_stack_size); + + void (*checkpoint_mqd)(struct mqd_manager *mm, + void *mqd, + void *mqd_dst, + void *ctl_stack_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); + const void *mqd_src, + const void *ctl_stack_src, + const u32 ctl_stack_size); #if defined(CONFIG_DEBUG_FS) int (*debugfs_show_mqd)(struct seq_file *m, void *data); 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 83117209bc15..96e3303fa27c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c @@ -280,7 +280,7 @@ 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) +static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst) { struct cik_mqd *m; @@ -292,7 +292,8 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst) 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) + const void *mqd_src, + const void *ctl_stack_src, const u32 ctl_stack_size) { uint64_t addr; struct cik_mqd *m; @@ -314,7 +315,10 @@ static void restore_mqd(struct mqd_manager *mm, void **mqd, qp->is_active = 0; } -static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst) +static void checkpoint_mqd_sdma(struct mqd_manager *mm, + void *mqd, + void *mqd_dst, + void *ctl_stack_dst) { struct cik_sdma_rlc_registers *m; @@ -326,7 +330,8 @@ static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst 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) + const void *mqd_src, + const void *ctl_stack_src, const u32 ctl_stack_size) { uint64_t addr; struct cik_sdma_rlc_registers *m; 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 4ddf5b45c42a..0cc8679c24fa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -285,7 +285,7 @@ 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) +static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst) { struct v10_compute_mqd *m; @@ -297,7 +297,8 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst) 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) + const void *mqd_src, + const void *ctl_stack_src, const u32 ctl_stack_size) { uint64_t addr; struct v10_compute_mqd *m; @@ -408,7 +409,10 @@ 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) +static void checkpoint_mqd_sdma(struct mqd_manager *mm, + void *mqd, + void *mqd_dst, + void *ctl_stack_dst) { struct v10_sdma_mqd *m; @@ -420,7 +424,9 @@ static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst 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) + const void *mqd_src, + const void *ctl_stack_src, + const u32 ctl_stack_size) { uint64_t addr; struct v10_sdma_mqd *m; 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 18ad7669eedf..87da4329dbf2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -340,22 +340,34 @@ 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) +static void get_checkpoint_info(struct mqd_manager *mm, void *mqd, u32 *ctl_stack_size) +{ + struct v9_mqd *m = get_mqd(mqd); + + *ctl_stack_size = m->cp_hqd_cntl_stack_size; +} + +static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst) { struct v9_mqd *m; + /* Control stack is located one page after MQD. */ + void *ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE); m = get_mqd(mqd); memcpy(mqd_dst, m, sizeof(struct v9_mqd)); + memcpy(ctl_stack_dst, ctl_stack, m->cp_hqd_cntl_stack_size); } 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) + const void *mqd_src, + const void *ctl_stack_src, u32 ctl_stack_size) { uint64_t addr; struct v9_mqd *m; + void *ctl_stack; m = (struct v9_mqd *) mqd_mem_obj->cpu_ptr; addr = mqd_mem_obj->gpu_addr; @@ -366,6 +378,10 @@ static void restore_mqd(struct mqd_manager *mm, void **mqd, if (gart_addr) *gart_addr = addr; + /* Control stack is located one page after MQD. */ + ctl_stack = (void *)((uintptr_t)*mqd + PAGE_SIZE); + memcpy(ctl_stack, ctl_stack_src, ctl_stack_size); + m->cp_hqd_pq_doorbell_control = qp->doorbell_off << CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT; @@ -463,7 +479,10 @@ 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) +static void checkpoint_mqd_sdma(struct mqd_manager *mm, + void *mqd, + void *mqd_dst, + void *ctl_stack_dst) { struct v9_sdma_mqd *m; @@ -475,7 +494,8 @@ static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst 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) + const void *mqd_src, + const void *ctl_stack_src, const u32 ctl_stack_size) { uint64_t addr; struct v9_sdma_mqd *m; @@ -537,6 +557,7 @@ 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->get_checkpoint_info = get_checkpoint_info; mqd->checkpoint_mqd = checkpoint_mqd; mqd->restore_mqd = restore_mqd; mqd->mqd_size = sizeof(struct v9_mqd); 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 9fdc67b60bb4..137b208135a0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c @@ -306,7 +306,13 @@ 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) +static void get_checkpoint_info(struct mqd_manager *mm, void *mqd, u32 *ctl_stack_size) +{ + /* Control stack is stored in user mode */ + *ctl_stack_size = 0; +} + +static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst) { struct vi_mqd *m; @@ -318,7 +324,8 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst) 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) + const void *mqd_src, + const void *ctl_stack_src, const u32 ctl_stack_size) { uint64_t addr; struct vi_mqd *m; @@ -341,7 +348,6 @@ static void restore_mqd(struct mqd_manager *mm, void **mqd, 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) @@ -435,7 +441,10 @@ 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) +static void checkpoint_mqd_sdma(struct mqd_manager *mm, + void *mqd, + void *mqd_dst, + void *ctl_stack_dst) { struct vi_sdma_mqd *m; @@ -447,7 +456,8 @@ static void checkpoint_mqd_sdma(struct mqd_manager *mm, void *mqd, void *mqd_dst 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) + const void *mqd_src, + const void *ctl_stack_src, const u32 ctl_stack_size) { uint64_t addr; struct vi_sdma_mqd *m; @@ -469,6 +479,7 @@ static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd, #if defined(CONFIG_DEBUG_FS) + static int debugfs_show_mqd(struct seq_file *m, void *data) { seq_hex_dump(m, " ", DUMP_PREFIX_OFFSET, 32, 4, @@ -509,6 +520,7 @@ 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->get_checkpoint_info = get_checkpoint_info; mqd->checkpoint_mqd = checkpoint_mqd; mqd->restore_mqd = restore_mqd; mqd->mqd_size = sizeof(struct vi_mqd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 1c62abe0dbd5..03242975078a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1159,6 +1159,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, unsigned int *qid, const struct kfd_criu_queue_priv_data *q_data, const void *restore_mqd, + const void *restore_ctl_stack, 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, @@ -1183,8 +1184,8 @@ int amdkfd_fence_wait_timeout(uint64_t *fence_addr, int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm, unsigned int qid, - u32 *mqd_size); - + u32 *mqd_size, + u32 *ctl_stack_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 844917c1c346..bd89dd0ca83e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -209,6 +209,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, unsigned int *qid, const struct kfd_criu_queue_priv_data *q_data, const void *restore_mqd, + const void *restore_ctl_stack, uint32_t *p_doorbell_offset_in_process) { int retval; @@ -273,7 +274,8 @@ 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, restore_mqd); + retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data, + restore_mqd, restore_ctl_stack); print_queue(q); break; @@ -293,7 +295,8 @@ 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, restore_mqd); + retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data, + restore_mqd, restore_ctl_stack); print_queue(q); break; case KFD_QUEUE_TYPE_DIQ: @@ -518,11 +521,17 @@ 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) +static int get_queue_data_sizes(struct kfd_process_device *pdd, + struct queue *q, + uint32_t *mqd_size, + uint32_t *ctl_stack_size) { int ret; - ret = pqm_get_queue_checkpoint_info(&pdd->process->pqm, q->properties.queue_id, mqd_size); + ret = pqm_get_queue_checkpoint_info(&pdd->process->pqm, + q->properties.queue_id, + mqd_size, + ctl_stack_size); if (ret) pr_err("Failed to get queue dump info (%d)\n", ret); @@ -548,14 +557,15 @@ 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; + uint32_t mqd_size, ctl_stack_size; + *num_queues = *num_queues + 1; - ret = get_queue_data_sizes(pdd, q, &mqd_size); + ret = get_queue_data_sizes(pdd, q, &mqd_size, &ctl_stack_size); if (ret) return ret; - extra_data_sizes += mqd_size; + extra_data_sizes += mqd_size + ctl_stack_size; } else { pr_err("Unsupported queue type (%d)\n", q->properties.type); return -EOPNOTSUPP; @@ -568,7 +578,10 @@ int kfd_process_get_queue_info(struct kfd_process *p, return 0; } -static int pqm_checkpoint_mqd(struct process_queue_manager *pqm, unsigned int qid, void *mqd) +static int pqm_checkpoint_mqd(struct process_queue_manager *pqm, + unsigned int qid, + void *mqd, + void *ctl_stack) { struct process_queue_node *pqn; @@ -583,17 +596,19 @@ static int pqm_checkpoint_mqd(struct process_queue_manager *pqm, unsigned int qi return -EOPNOTSUPP; } - return pqn->q->device->dqm->ops.checkpoint_mqd(pqn->q->device->dqm, pqn->q, mqd); + return pqn->q->device->dqm->ops.checkpoint_mqd(pqn->q->device->dqm, + pqn->q, mqd, ctl_stack); } static int criu_checkpoint_queue(struct kfd_process_device *pdd, struct queue *q, struct kfd_criu_queue_priv_data *q_data) { - uint8_t *mqd; + uint8_t *mqd, *ctl_stack; int ret; mqd = (void *)(q_data + 1); + ctl_stack = mqd + q_data->mqd_size; q_data->gpu_id = pdd->dev->id; q_data->type = q->properties.type; @@ -620,7 +635,7 @@ static int 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); + ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack); if (ret) { pr_err("Failed checkpoint queue_mqd (%d)\n", ret); return ret; @@ -644,6 +659,7 @@ static int criu_checkpoint_queues_device(struct kfd_process_device *pdd, struct kfd_criu_queue_priv_data *q_data; uint64_t q_data_size; uint32_t mqd_size; + uint32_t ctl_stack_size; if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE && q->properties.type != KFD_QUEUE_TYPE_SDMA && @@ -654,11 +670,11 @@ static int criu_checkpoint_queues_device(struct kfd_process_device *pdd, break; } - ret = get_queue_data_sizes(pdd, q, &mqd_size); + ret = get_queue_data_sizes(pdd, q, &mqd_size, &ctl_stack_size); if (ret) break; - q_data_size = sizeof(*q_data) + mqd_size; + q_data_size = sizeof(*q_data) + mqd_size + ctl_stack_size; /* Increase local buffer space if needed */ if (q_private_data_size < q_data_size) { @@ -674,8 +690,9 @@ static int criu_checkpoint_queues_device(struct kfd_process_device *pdd, q_data = (struct kfd_criu_queue_priv_data *)q_private_data; - /* data stored in this order: priv_data, mqd */ + /* data stored in this order: priv_data, mqd, ctl_stack */ q_data->mqd_size = mqd_size; + q_data->ctl_stack_size = ctl_stack_size; ret = criu_checkpoint_queue(pdd, q, q_data); if (ret) @@ -746,8 +763,8 @@ int kfd_criu_restore_queue(struct kfd_process *p, uint64_t *priv_data_offset, uint64_t max_priv_data_size) { + uint8_t *mqd, *ctl_stack, *q_extra_data = NULL; struct kfd_criu_queue_priv_data *q_data; - uint8_t *mqd, *q_extra_data = NULL; struct kfd_process_device *pdd; uint64_t q_extra_data_size; struct queue_properties qp; @@ -769,7 +786,7 @@ int kfd_criu_restore_queue(struct kfd_process *p, } *priv_data_offset += sizeof(*q_data); - q_extra_data_size = q_data->mqd_size; + q_extra_data_size = q_data->ctl_stack_size + q_data->mqd_size; if (*priv_data_offset + q_extra_data_size > max_priv_data_size) { ret = -EINVAL; @@ -805,15 +822,17 @@ int kfd_criu_restore_queue(struct kfd_process *p, ret = -EFAULT; return ret; } - /* data stored in this order: mqd */ + /* data stored in this order: mqd, ctl_stack */ mqd = q_extra_data; + ctl_stack = mqd + q_data->mqd_size; 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, mqd, NULL); + ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, q_data, mqd, ctl_stack, + NULL); if (ret) { pr_err("Failed to create new queue err:%d\n", ret); ret = -EINVAL; @@ -832,7 +851,8 @@ int kfd_criu_restore_queue(struct kfd_process *p, int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm, unsigned int qid, - uint32_t *mqd_size) + uint32_t *mqd_size, + uint32_t *ctl_stack_size) { struct process_queue_node *pqn; @@ -847,7 +867,9 @@ int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm, return -EOPNOTSUPP; } - pqn->q->device->dqm->ops.get_queue_checkpoint_info(pqn->q->device->dqm, pqn->q, mqd_size); + pqn->q->device->dqm->ops.get_queue_checkpoint_info(pqn->q->device->dqm, + pqn->q, mqd_size, + ctl_stack_size); return 0; }

[v5,13/24] drm/amdkfd: CRIU checkpoint and restore queue control stack

Commit Message

Patch