Commit e0f1e65b authored by Philip Yang's avatar Philip Yang Committed by Alex Deucher
Browse files

drm/amdkfd: Add GPU recoverable fault SMI event 



Use ktime_get_boottime_ns() as timestamp to correlate with other
APIs. Output timestamp when GPU recoverable fault starts and ends to
recover the fault, if migration happened or only GPU page table is
updated to recover, fault address, if read or write fault.

Signed-off-by: default avatarPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: default avatarFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 163a5a58

drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c

+17 −0
Original line number Diff line number Diff line
@@ -244,6 +244,23 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) 
			  task_info.pid, task_info.task_name);

}



void kfd_smi_event_page_fault_start(struct kfd_dev *dev, pid_t pid,

				    unsigned long address, bool write_fault,

				    ktime_t ts)

{

	kfd_smi_event_add(pid, dev, KFD_SMI_EVENT_PAGE_FAULT_START,

			  "%lld -%d @%lx(%x) %c\n", ktime_to_ns(ts), pid,

			  address, dev->id, write_fault ? 'W' : 'R');

}



void kfd_smi_event_page_fault_end(struct kfd_dev *dev, pid_t pid,

				  unsigned long address, bool migration)

{

	kfd_smi_event_add(pid, dev, KFD_SMI_EVENT_PAGE_FAULT_END,

			  "%lld -%d @%lx(%x) %c\n", ktime_get_boottime_ns(),

			  pid, address, dev->id, migration ? 'M' : 'U');

}



int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)

{

	struct kfd_smi_client *client;

drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h

+5 −1
Original line number Diff line number Diff line
@@ -29,5 +29,9 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid); 
void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,

					     uint64_t throttle_bitmask);

void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset);



void kfd_smi_event_page_fault_start(struct kfd_dev *dev, pid_t pid,

				    unsigned long address, bool write_fault,

				    ktime_t ts);

void kfd_smi_event_page_fault_end(struct kfd_dev *dev, pid_t pid,

				  unsigned long address, bool migration);

#endif

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

+14 −5
Original line number Diff line number Diff line
@@ -32,6 +32,7 @@ 
#include "kfd_priv.h"

#include "kfd_svm.h"

#include "kfd_migrate.h"

#include "kfd_smi_events.h"



#ifdef dev_fmt

#undef dev_fmt
@@ -43,7 +44,7 @@ 
/* Long enough to ensure no retry fault comes after svm range is restored and

 * page table is updated.

 */

#define AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING	2000

#define AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING	(2UL * NSEC_PER_MSEC)



struct criu_svm_metadata {

	struct list_head list;
@@ -1617,7 +1618,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm, 
	svm_range_unreserve_bos(&ctx);



	if (!r)

		prange->validate_timestamp = ktime_to_us(ktime_get());

		prange->validate_timestamp = ktime_get_boottime();



	return r;

}
@@ -2694,11 +2695,12 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, 
	struct svm_range_list *svms;

	struct svm_range *prange;

	struct kfd_process *p;

	uint64_t timestamp;

	ktime_t timestamp = ktime_get_boottime();

	int32_t best_loc;

	int32_t gpuidx = MAX_GPU_INSTANCE;

	bool write_locked = false;

	struct vm_area_struct *vma;

	bool migration = false;

	int r = 0;



	if (!KFD_IS_SVM_API_SUPPORTED(adev->kfd.dev)) {
@@ -2775,9 +2777,9 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, 
		goto out_unlock_range;

	}



	timestamp = ktime_to_us(ktime_get()) - prange->validate_timestamp;

	/* skip duplicate vm fault on different pages of same range */

	if (timestamp < AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING) {

	if (ktime_before(timestamp, ktime_add_ns(prange->validate_timestamp,

				AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING))) {

		pr_debug("svms 0x%p [0x%lx %lx] already restored\n",

			 svms, prange->start, prange->last);

		r = 0;
@@ -2813,7 +2815,11 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, 
		 svms, prange->start, prange->last, best_loc,

		 prange->actual_loc);



	kfd_smi_event_page_fault_start(adev->kfd.dev, p->lead_thread->pid, addr,

				       write_fault, timestamp);



	if (prange->actual_loc != best_loc) {

		migration = true;

		if (best_loc) {

			r = svm_migrate_to_vram(prange, best_loc, mm);

			if (r) {
@@ -2842,6 +2848,9 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, 
		pr_debug("failed %d to map svms 0x%p [0x%lx 0x%lx] to gpus\n",

			 r, svms, prange->start, prange->last);



	kfd_smi_event_page_fault_end(adev->kfd.dev, p->lead_thread->pid, addr,

				     migration);



out_unlock_range:

	mutex_unlock(&prange->migrate_mutex);

out_unlock_svms:

drivers/gpu/drm/amd/amdkfd/kfd_svm.h

+1 −1
Original line number Diff line number Diff line
@@ -125,7 +125,7 @@ struct svm_range { 
	uint32_t			actual_loc;

	uint8_t				granularity;

	atomic_t			invalid;

	uint64_t			validate_timestamp;

	ktime_t				validate_timestamp;

	struct mmu_interval_notifier	notifier;

	struct svm_work_list_item	work_item;

	struct list_head		deferred_list;