From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c | 63 ++++++++++++++++++++-----------
1 files changed, 40 insertions(+), 23 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/kernel/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 1092631..c85e4f9 100644
--- a/kernel/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/kernel/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -41,14 +41,15 @@
unsigned int *rlib_size,
bool *over_subscription)
{
- unsigned int process_count, queue_count, compute_queue_count;
+ unsigned int process_count, queue_count, compute_queue_count, gws_queue_count;
unsigned int map_queue_size;
unsigned int max_proc_per_quantum = 1;
struct kfd_dev *dev = pm->dqm->dev;
process_count = pm->dqm->processes_count;
- queue_count = pm->dqm->queue_count;
- compute_queue_count = queue_count - pm->dqm->sdma_queue_count;
+ queue_count = pm->dqm->active_queue_count;
+ compute_queue_count = pm->dqm->active_cp_queue_count;
+ gws_queue_count = pm->dqm->gws_queue_count;
/* check if there is over subscription
* Note: the arbitration between the number of VMIDs and
@@ -61,7 +62,8 @@
max_proc_per_quantum = dev->max_proc_per_quantum;
if ((process_count > max_proc_per_quantum) ||
- compute_queue_count > get_queues_num(pm->dqm)) {
+ compute_queue_count > get_cp_queues_num(pm->dqm) ||
+ gws_queue_count > 1) {
*over_subscription = true;
pr_debug("Over subscribed runlist\n");
}
@@ -140,7 +142,7 @@
pm->ib_size_bytes = alloc_size_bytes;
pr_debug("Building runlist ib process count: %d queues count %d\n",
- pm->dqm->processes_count, pm->dqm->queue_count);
+ pm->dqm->processes_count, pm->dqm->active_queue_count);
/* build the run list ib packet */
list_for_each_entry(cur, queues, list) {
@@ -202,11 +204,15 @@
pr_debug("Finished map process and queues to runlist\n");
- if (is_over_subscription)
+ if (is_over_subscription) {
+ if (!pm->is_over_subscription)
+ pr_warn("Runlist is getting oversubscribed. Expect reduced ROCm performance.\n");
retval = pm->pmf->runlist(pm, &rl_buffer[rl_wptr],
*rl_gpu_addr,
alloc_size_bytes / sizeof(uint32_t),
true);
+ }
+ pm->is_over_subscription = is_over_subscription;
for (i = 0; i < alloc_size_bytes / sizeof(uint32_t); i++)
pr_debug("0x%2X ", rl_buffer[i]);
@@ -226,10 +232,21 @@
case CHIP_FIJI:
case CHIP_POLARIS10:
case CHIP_POLARIS11:
+ case CHIP_POLARIS12:
+ case CHIP_VEGAM:
pm->pmf = &kfd_vi_pm_funcs;
break;
case CHIP_VEGA10:
+ case CHIP_VEGA12:
+ case CHIP_VEGA20:
case CHIP_RAVEN:
+ case CHIP_RENOIR:
+ case CHIP_ARCTURUS:
+ case CHIP_NAVI10:
+ case CHIP_NAVI12:
+ case CHIP_NAVI14:
+ case CHIP_SIENNA_CICHLID:
+ case CHIP_NAVY_FLOUNDER:
pm->pmf = &kfd_v9_pm_funcs;
break;
default:
@@ -250,10 +267,10 @@
return 0;
}
-void pm_uninit(struct packet_manager *pm)
+void pm_uninit(struct packet_manager *pm, bool hanging)
{
mutex_destroy(&pm->lock);
- kernel_queue_uninit(pm->priv_queue);
+ kernel_queue_uninit(pm->priv_queue, hanging);
}
int pm_send_set_resources(struct packet_manager *pm,
@@ -264,7 +281,7 @@
size = pm->pmf->set_resources_size;
mutex_lock(&pm->lock);
- pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+ kq_acquire_packet_buffer(pm->priv_queue,
size / sizeof(uint32_t),
(unsigned int **)&buffer);
if (!buffer) {
@@ -275,9 +292,9 @@
retval = pm->pmf->set_resources(pm, buffer, res);
if (!retval)
- pm->priv_queue->ops.submit_packet(pm->priv_queue);
+ kq_submit_packet(pm->priv_queue);
else
- pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+ kq_rollback_packet(pm->priv_queue);
out:
mutex_unlock(&pm->lock);
@@ -302,7 +319,7 @@
packet_size_dwords = pm->pmf->runlist_size / sizeof(uint32_t);
mutex_lock(&pm->lock);
- retval = pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+ retval = kq_acquire_packet_buffer(pm->priv_queue,
packet_size_dwords, &rl_buffer);
if (retval)
goto fail_acquire_packet_buffer;
@@ -312,14 +329,14 @@
if (retval)
goto fail_create_runlist;
- pm->priv_queue->ops.submit_packet(pm->priv_queue);
+ kq_submit_packet(pm->priv_queue);
mutex_unlock(&pm->lock);
return retval;
fail_create_runlist:
- pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+ kq_rollback_packet(pm->priv_queue);
fail_acquire_packet_buffer:
mutex_unlock(&pm->lock);
fail_create_runlist_ib:
@@ -328,7 +345,7 @@
}
int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
- uint32_t fence_value)
+ uint64_t fence_value)
{
uint32_t *buffer, size;
int retval = 0;
@@ -338,7 +355,7 @@
size = pm->pmf->query_status_size;
mutex_lock(&pm->lock);
- pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+ kq_acquire_packet_buffer(pm->priv_queue,
size / sizeof(uint32_t), (unsigned int **)&buffer);
if (!buffer) {
pr_err("Failed to allocate buffer on kernel queue\n");
@@ -348,9 +365,9 @@
retval = pm->pmf->query_status(pm, buffer, fence_address, fence_value);
if (!retval)
- pm->priv_queue->ops.submit_packet(pm->priv_queue);
+ kq_submit_packet(pm->priv_queue);
else
- pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+ kq_rollback_packet(pm->priv_queue);
out:
mutex_unlock(&pm->lock);
@@ -367,7 +384,7 @@
size = pm->pmf->unmap_queues_size;
mutex_lock(&pm->lock);
- pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+ kq_acquire_packet_buffer(pm->priv_queue,
size / sizeof(uint32_t), (unsigned int **)&buffer);
if (!buffer) {
pr_err("Failed to allocate buffer on kernel queue\n");
@@ -378,9 +395,9 @@
retval = pm->pmf->unmap_queues(pm, buffer, type, filter, filter_param,
reset, sdma_engine);
if (!retval)
- pm->priv_queue->ops.submit_packet(pm->priv_queue);
+ kq_submit_packet(pm->priv_queue);
else
- pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+ kq_rollback_packet(pm->priv_queue);
out:
mutex_unlock(&pm->lock);
@@ -425,7 +442,7 @@
size = pm->pmf->query_status_size;
mutex_lock(&pm->lock);
- pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+ kq_acquire_packet_buffer(pm->priv_queue,
size / sizeof(uint32_t), (unsigned int **)&buffer);
if (!buffer) {
pr_err("Failed to allocate buffer on kernel queue\n");
@@ -433,7 +450,7 @@
goto out;
}
memset(buffer, 0x55, size);
- pm->priv_queue->ops.submit_packet(pm->priv_queue);
+ kq_submit_packet(pm->priv_queue);
pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
buffer[0], buffer[1], buffer[2], buffer[3],
--
Gitblit v1.6.2