The number of compute unit (CU) for a device is used for the gpu cgroup
compute capacity. The gpu cgroup compute allocation limit only applies
to compute workload for the moment (enforced via kfd queue creation.)
Any cu_mask update is validated against the availability of the compute
unit as defined by the drmcg the kfd process belongs to.
Change-Id: I2930e76ef9ac6d36d0feb81f604c89a4208e6614
Signed-off-by: Kenny Ho <Kenny.Ho@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 4 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 29 ++++
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 7 +
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 +
.../amd/amdkfd/kfd_process_queue_manager.c | 153 ++++++++++++++++++
5 files changed, 196 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 0ee8aae6c519..1efbc0d3c03e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -199,6 +199,10 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
valid; \
})
+int amdgpu_amdkfd_update_cu_mask_for_process(struct task_struct *task,
+ struct amdgpu_device *adev, unsigned long *compute_bm,
+ unsigned int compute_bm_size);
+
/* GPUVM API */
int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
void **vm, void **process_info,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 171397708855..595ad852080b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1418,9 +1418,31 @@ amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe,
static void amdgpu_drmcg_custom_init(struct drm_device *dev,
struct drmcg_props *props)
{
+ struct amdgpu_device *adev = dev->dev_private;
+
+ props->compute_capacity = adev->gfx.cu_info.number;
+ bitmap_zero(props->compute_slots, MAX_DRMCG_COMPUTE_CAPACITY);
+ bitmap_fill(props->compute_slots, props->compute_capacity);
+
props->limit_enforced = true;
}
+static void amdgpu_drmcg_limit_updated(struct drm_device *dev,
+ struct task_struct *task, struct drmcg_device_resource *ddr,
+ enum drmcg_res_type res_type)
+{
+ struct amdgpu_device *adev = dev->dev_private;
+
+ switch (res_type) {
+ case DRMCG_TYPE_COMPUTE:
+ amdgpu_amdkfd_update_cu_mask_for_process(task, adev,
+ ddr->compute_eff, dev->drmcg_props.compute_capacity);
+ break;
+ default:
+ break;
+ }
+}
+
#else
static void amdgpu_drmcg_custom_init(struct drm_device *dev,
@@ -1428,6 +1450,12 @@ static void amdgpu_drmcg_custom_init(struct drm_device *dev,
{
}
+static void amdgpu_drmcg_limit_updated(struct drm_device *dev,
+ struct task_struct *task, struct drmcg_device_resource *ddr,
+ enum drmcg_res_type res_type)
+{
+}
+
#endif /* CONFIG_CGROUP_DRM */
static struct drm_driver kms_driver = {
@@ -1462,6 +1490,7 @@ static struct drm_driver kms_driver = {
.gem_prime_mmap = amdgpu_gem_prime_mmap,
.drmcg_custom_init = amdgpu_drmcg_custom_init,
+ .drmcg_limit_updated = amdgpu_drmcg_limit_updated,
.name = DRIVER_NAME,
.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 675735b8243a..a35596f2dc4e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -451,6 +451,13 @@ static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p,
return -EFAULT;
}
+ if (!pqm_drmcg_compute_validate(p, args->queue_id,
+ properties.cu_mask, cu_mask_size)) {
+ pr_debug("CU mask not permitted by DRM Cgroup");
+ kfree(properties.cu_mask);
+ return -EACCES;
+ }
+
mutex_lock(&p->mutex);
retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 063096ec832d..0fb619586e24 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -929,6 +929,9 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
u32 *ctl_stack_used_size,
u32 *save_area_used_size);
+bool pqm_drmcg_compute_validate(struct kfd_process *p, int qid, u32 *cu_mask,
+ unsigned int cu_mask_size);
+
int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
unsigned int fence_value,
unsigned int timeout_ms);
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 cb1ca11b99c3..bd09403e07b5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -23,9 +23,11 @@
#include <linux/slab.h>
#include <linux/list.h>
+#include <linux/cgroup_drm.h>
#include "kfd_device_queue_manager.h"
#include "kfd_priv.h"
#include "kfd_kernel_queue.h"
+#include "amdgpu.h"
#include "amdgpu_amdkfd.h"
static inline struct process_queue_node *get_queue_by_qid(
@@ -167,6 +169,7 @@ static int init_user_queue(struct process_queue_manager *pqm,
struct queue_properties *q_properties,
struct file *f, unsigned int qid)
{
+ struct drmcg *drmcg;
int retval;
/* Doorbell initialized in user space*/
@@ -180,6 +183,37 @@ static int init_user_queue(struct process_queue_manager *pqm,
if (retval != 0)
return retval;
+#ifdef CONFIG_CGROUP_DRM
+ drmcg = drmcg_get(pqm->process->lead_thread);
+ if (drmcg) {
+ struct amdgpu_device *adev;
+ struct drmcg_device_resource *ddr;
+ int mask_size;
+ u32 *mask;
+
+ adev = (struct amdgpu_device *) dev->kgd;
+
+ mask_size = adev->ddev->drmcg_props.compute_capacity;
+ mask = kzalloc(sizeof(u32) * round_up(mask_size, 32),
+ GFP_KERNEL);
+
+ if (!mask) {
+ drmcg_put(drmcg);
+ uninit_queue(*q);
+ return -ENOMEM;
+ }
+
+ ddr = drmcg->dev_resources[adev->ddev->primary->index];
+
+ bitmap_to_arr32(mask, ddr->compute_eff, mask_size);
+
+ (*q)->properties.cu_mask_count = mask_size;
+ (*q)->properties.cu_mask = mask;
+
+ drmcg_put(drmcg);
+ }
+#endif /* CONFIG_CGROUP_DRM */
+
(*q)->device = dev;
(*q)->process = pqm->process;
@@ -510,6 +544,125 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
save_area_used_size);
}
+#ifdef CONFIG_CGROUP_DRM
+
+bool pqm_drmcg_compute_validate(struct kfd_process *p, int qid, u32 *cu_mask,
+ unsigned int cu_mask_size)
+{
+ DECLARE_BITMAP(curr_mask, MAX_DRMCG_COMPUTE_CAPACITY);
+ struct drmcg_device_resource *ddr;
+ struct process_queue_node *pqn;
+ struct amdgpu_device *adev;
+ struct drmcg *drmcg;
+ bool result;
+
+ if (cu_mask_size > MAX_DRMCG_COMPUTE_CAPACITY)
+ return false;
+
+ bitmap_from_arr32(curr_mask, cu_mask, cu_mask_size);
+
+ pqn = get_queue_by_qid(&p->pqm, qid);
+ if (!pqn)
+ return false;
+
+ adev = (struct amdgpu_device *)pqn->q->device->kgd;
+
+ drmcg = drmcg_get(p->lead_thread);
+ ddr = drmcg->dev_resources[adev->ddev->primary->index];
+
+ if (bitmap_subset(curr_mask, ddr->compute_eff,
+ MAX_DRMCG_COMPUTE_CAPACITY))
+ result = true;
+ else
+ result = false;
+
+ drmcg_put(drmcg);
+
+ return result;
+}
+
+#else
+
+bool pqm_drmcg_compute_validate(struct kfd_process *p, int qid, u32 *cu_mask,
+ unsigned int cu_mask_size)
+{
+ return true;
+}
+
+#endif /* CONFIG_CGROUP_DRM */
+
+int amdgpu_amdkfd_update_cu_mask_for_process(struct task_struct *task,
+ struct amdgpu_device *adev, unsigned long *compute_bm,
+ unsigned int compute_bm_size)
+{
+ struct kfd_dev *kdev = adev->kfd.dev;
+ struct process_queue_node *pqn;
+ struct kfd_process *kfdproc;
+ size_t size_in_bytes;
+ u32 *cu_mask;
+ int rc = 0;
+
+ if ((compute_bm_size % 32) != 0) {
+ pr_warn("compute_bm_size %d must be a multiple of 32",
+ compute_bm_size);
+ return -EINVAL;
+ }
+
+ kfdproc = kfd_get_process(task);
+
+ if (IS_ERR(kfdproc))
+ return -ESRCH;
+
+ size_in_bytes = sizeof(u32) * round_up(compute_bm_size, 32);
+
+ mutex_lock(&kfdproc->mutex);
+ list_for_each_entry(pqn, &kfdproc->pqm.queues, process_queue_list) {
+ if (pqn->q && pqn->q->device == kdev) {
+ /* update cu_mask accordingly */
+ cu_mask = kzalloc(size_in_bytes, GFP_KERNEL);
+ if (!cu_mask) {
+ rc = -ENOMEM;
+ break;
+ }
+
+ if (pqn->q->properties.cu_mask) {
+ DECLARE_BITMAP(curr_mask,
+ MAX_DRMCG_COMPUTE_CAPACITY);
+
+ if (pqn->q->properties.cu_mask_count >
+ compute_bm_size) {
+ rc = -EINVAL;
+ kfree(cu_mask);
+ break;
+ }
+
+ bitmap_from_arr32(curr_mask,
+ pqn->q->properties.cu_mask,
+ pqn->q->properties.cu_mask_count);
+
+ bitmap_and(curr_mask, curr_mask, compute_bm,
+ compute_bm_size);
+
+ bitmap_to_arr32(cu_mask, curr_mask,
+ compute_bm_size);
+
+ kfree(curr_mask);
+ } else
+ bitmap_to_arr32(cu_mask, compute_bm,
+ compute_bm_size);
+
+ pqn->q->properties.cu_mask = cu_mask;
+ pqn->q->properties.cu_mask_count = compute_bm_size;
+
+ rc = pqn->q->device->dqm->ops.update_queue(
+ pqn->q->device->dqm, pqn->q);
+ }
+ }
+ mutex_unlock(&kfdproc->mutex);
+
+ return rc;
+}
+
#if defined(CONFIG_DEBUG_FS)
int pqm_debugfs_mqds(struct seq_file *m, void *data)
--
2.25.0
