github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-11-13 05:04:29 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/xe: Track parallel page fault activity in GT stats

Browse Source 
Add a new GT statistic, PARALLEL_PAGEFAULT_COUNT, to record when
multiple page fault workers are active concurrently.

When a worker dequeues a fault, scan peer workers for an active
cache entry and increment the counter if another fault is already
in flight. This provides basic visibility into parallel fault
handling behavior for performance analysis and tuning.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
Link: https://patch.msgid.link/20260806185202.3922432-13-matthew.brost@intel.com
This commit is contained in:
Matthew Brost 2026-08-06 11:52:02 -07:00
parent d4a7e16117
commit aa8216142a
3 changed files with 21 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
drivers/gpu/drm/xe/xe_gt_stats.c
View File

@ -99,6 +99,7 @@ static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = {
DEF_STAT_STR(CHAIN_IRQ_PAGEFAULT_COUNT, "chain_irq_pagefault_count"),
DEF_STAT_STR(CHAIN_DRAIN_IRQ_PAGEFAULT_COUNT, "chain_drain_irq_pagefault_count"),
DEF_STAT_STR(CHAIN_MISMATCH_PAGEFAULT_COUNT, "chain_mismatch_pagefault_count"),
DEF_STAT_STR(PARALLEL_PAGEFAULT_COUNT, "parallel_pagefault_count"),
DEF_STAT_STR(LAST_PAGEFAULT_COUNT, "last_pagefault_count"),
DEF_STAT_STR(SVM_PAGEFAULT_COUNT, "svm_pagefault_count"),
DEF_STAT_STR(TLB_INVAL, "tlb_inval_count"),

3
drivers/gpu/drm/xe/xe_gt_stats_types.h
View File

@ -18,6 +18,8 @@
* that also drained the fault queue.
* @XE_GT_STATS_ID_CHAIN_MISMATCH_PAGEFAULT_COUNT: Chained faults requeued
* because their fault range did not match the fault they were chained onto.
* @XE_GT_STATS_ID_PARALLEL_PAGEFAULT_COUNT: Faults dequeued while another page
* fault worker was already handling a fault concurrently.
* @XE_GT_STATS_ID_LAST_PAGEFAULT_COUNT: Faults whose range matched the last
* serviced range, allowing an immediate ack.
*
@ -144,6 +146,7 @@ enum xe_gt_stats_id {
XE_GT_STATS_ID_CHAIN_IRQ_PAGEFAULT_COUNT,
XE_GT_STATS_ID_CHAIN_DRAIN_IRQ_PAGEFAULT_COUNT,
XE_GT_STATS_ID_CHAIN_MISMATCH_PAGEFAULT_COUNT,
XE_GT_STATS_ID_PARALLEL_PAGEFAULT_COUNT,
XE_GT_STATS_ID_LAST_PAGEFAULT_COUNT,
XE_GT_STATS_ID_SVM_PAGEFAULT_COUNT,
XE_GT_STATS_ID_TLB_INVAL,

18
drivers/gpu/drm/xe/xe_pagefault.c
View File

@ -460,9 +460,10 @@ static bool xe_pagefault_queue_pop(struct xe_pagefault_queue *pf_queue,
{
struct xe_device *xe = container_of(pf_queue, typeof(*xe),
usm.pf_queue);
struct xe_pagefault_work *pf_work;
struct xe_pagefault_work *pf_work, *__pf_work;
struct xe_pagefault *lpf;
size_t align = SZ_2M;
int i;
guard(spinlock_irq)(&pf_queue->lock);
@ -499,6 +500,21 @@ static bool xe_pagefault_queue_pop(struct xe_pagefault_queue *pf_queue,
pf_work->cache.pf = lpf;
lpf->consumer.alloc_state = XE_PAGEFAULT_ALLOC_STATE_ACTIVE;
for (i = 0, __pf_work = xe->usm.pf_workers;
i < xe->info.num_pf_work; ++i, ++__pf_work) {
u64 cache_start = __pf_work->cache.start;
if (__pf_work == pf_work)
continue;
if (cache_start != XE_PAGEFAULT_CACHE_START_INVALID) {
xe_gt_stats_incr(xe_root_mmio_gt(xe),
XE_GT_STATS_ID_PARALLEL_PAGEFAULT_COUNT,
1);
break;
}
}
/* Drain queue until empty or new fault found */
while (1) {
if (xe_pagefault_queue_empty(pf_queue))