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_events.c | 61 +++++++++++++++++++-----------
1 files changed, 38 insertions(+), 23 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/kernel/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index e9f0e0a..2c19b37 100644
--- a/kernel/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/kernel/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -187,7 +187,7 @@
if (p->signal_mapped_size &&
p->signal_event_count == p->signal_mapped_size / 8) {
if (!p->signal_event_limit_reached) {
- pr_warn("Signal event wasn't created because limit was reached\n");
+ pr_debug("Signal event wasn't created because limit was reached\n");
p->signal_event_limit_reached = true;
}
return -ENOSPC;
@@ -346,7 +346,6 @@
ret = create_signal_event(devkfd, p, ev);
if (!ret) {
*event_page_offset = KFD_MMAP_TYPE_EVENTS;
- *event_page_offset <<= PAGE_SHIFT;
*event_slot_index = ev->event_id;
}
break;
@@ -461,7 +460,7 @@
}
}
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
uint32_t valid_id_bits)
{
struct kfd_event *ev = NULL;
@@ -529,14 +528,13 @@
struct kfd_event_waiter *event_waiters;
uint32_t i;
- event_waiters = kmalloc_array(num_events,
- sizeof(struct kfd_event_waiter),
- GFP_KERNEL);
+ event_waiters = kcalloc(num_events, sizeof(struct kfd_event_waiter),
+ GFP_KERNEL);
+ if (!event_waiters)
+ return NULL;
- for (i = 0; (event_waiters) && (i < num_events) ; i++) {
+ for (i = 0; i < num_events; i++)
init_wait(&event_waiters[i].wait);
- event_waiters[i].activated = false;
- }
return event_waiters;
}
@@ -852,8 +850,8 @@
if (type == KFD_EVENT_TYPE_MEMORY) {
dev_warn(kfd_device,
- "Sending SIGSEGV to HSA Process with PID %d ",
- p->lead_thread->pid);
+ "Sending SIGSEGV to process %d (pasid 0x%x)",
+ p->lead_thread->pid, p->pasid);
send_sig(SIGSEGV, p->lead_thread, 0);
}
@@ -861,19 +859,19 @@
if (send_signal) {
if (send_sigterm) {
dev_warn(kfd_device,
- "Sending SIGTERM to HSA Process with PID %d ",
- p->lead_thread->pid);
+ "Sending SIGTERM to process %d (pasid 0x%x)",
+ p->lead_thread->pid, p->pasid);
send_sig(SIGTERM, p->lead_thread, 0);
} else {
dev_err(kfd_device,
- "HSA Process (PID %d) got unhandled exception",
- p->lead_thread->pid);
+ "Process %d (pasid 0x%x) got unhandled exception",
+ p->lead_thread->pid, p->pasid);
}
}
}
#ifdef KFD_SUPPORT_IOMMU_V2
-void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
unsigned long address, bool is_write_requested,
bool is_execute_requested)
{
@@ -902,7 +900,7 @@
memset(&memory_exception_data, 0, sizeof(memory_exception_data));
- down_read(&mm->mmap_sem);
+ mmap_read_lock(mm);
vma = find_vma(mm, address);
memory_exception_data.gpu_id = dev->id;
@@ -925,7 +923,7 @@
memory_exception_data.failure.NoExecute = 0;
}
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
pr_debug("notpresent %d, noexecute %d, readonly %d\n",
@@ -936,7 +934,8 @@
/* Workaround on Raven to not kill the process when memory is freed
* before IOMMU is able to finish processing all the excessive PPRs
*/
- if (dev->device_info->asic_family != CHIP_RAVEN) {
+ if (dev->device_info->asic_family != CHIP_RAVEN &&
+ dev->device_info->asic_family != CHIP_RENOIR) {
mutex_lock(&p->event_mutex);
/* Lookup events by type and signal them */
@@ -950,7 +949,7 @@
}
#endif /* KFD_SUPPORT_IOMMU_V2 */
-void kfd_signal_hw_exception_event(unsigned int pasid)
+void kfd_signal_hw_exception_event(u32 pasid)
{
/*
* Because we are called from arbitrary context (workqueue) as opposed
@@ -971,7 +970,7 @@
kfd_unref_process(p);
}
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
struct kfd_vm_fault_info *info)
{
struct kfd_event *ev;
@@ -983,7 +982,7 @@
return; /* Presumably process exited. */
memset(&memory_exception_data, 0, sizeof(memory_exception_data));
memory_exception_data.gpu_id = dev->id;
- memory_exception_data.failure.imprecise = 1;
+ memory_exception_data.failure.imprecise = true;
/* Set failure reason */
if (info) {
memory_exception_data.va = (info->page_addr) << PAGE_SHIFT;
@@ -1011,25 +1010,41 @@
void kfd_signal_reset_event(struct kfd_dev *dev)
{
struct kfd_hsa_hw_exception_data hw_exception_data;
+ struct kfd_hsa_memory_exception_data memory_exception_data;
struct kfd_process *p;
struct kfd_event *ev;
unsigned int temp;
uint32_t id, idx;
+ int reset_cause = atomic_read(&dev->sram_ecc_flag) ?
+ KFD_HW_EXCEPTION_ECC :
+ KFD_HW_EXCEPTION_GPU_HANG;
/* Whole gpu reset caused by GPU hang and memory is lost */
memset(&hw_exception_data, 0, sizeof(hw_exception_data));
hw_exception_data.gpu_id = dev->id;
hw_exception_data.memory_lost = 1;
+ hw_exception_data.reset_cause = reset_cause;
+
+ memset(&memory_exception_data, 0, sizeof(memory_exception_data));
+ memory_exception_data.ErrorType = KFD_MEM_ERR_SRAM_ECC;
+ memory_exception_data.gpu_id = dev->id;
+ memory_exception_data.failure.imprecise = true;
idx = srcu_read_lock(&kfd_processes_srcu);
hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
mutex_lock(&p->event_mutex);
id = KFD_FIRST_NONSIGNAL_EVENT_ID;
- idr_for_each_entry_continue(&p->event_idr, ev, id)
+ idr_for_each_entry_continue(&p->event_idr, ev, id) {
if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
ev->hw_exception_data = hw_exception_data;
set_event(ev);
}
+ if (ev->type == KFD_EVENT_TYPE_MEMORY &&
+ reset_cause == KFD_HW_EXCEPTION_ECC) {
+ ev->memory_exception_data = memory_exception_data;
+ set_event(ev);
+ }
+ }
mutex_unlock(&p->event_mutex);
}
srcu_read_unlock(&kfd_processes_srcu, idx);
--
Gitblit v1.6.2