* [PATCH] drm/amdkfd: Make all TLB-flushes heavy-weight
@ 2026-04-20 15:58 Felix Kuehling
2026-04-20 21:32 ` Philip Yang
0 siblings, 1 reply; 4+ messages in thread
From: Felix Kuehling @ 2026-04-20 15:58 UTC (permalink / raw)
To: amd-gfx; +Cc: philip.yang, christian.koenig
With only one sequence number we cannot track the need for legacy vs
heavy-weight flushes reliably. Always use heavy-weight.
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++--
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++---
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 6 +++---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 ++--
4 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 16fb39259911..0625104a7693 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1358,7 +1358,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
if (WARN_ON_ONCE(!peer_pdd))
continue;
- kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+ kfd_flush_tlb(peer_pdd);
}
kfree(devices_arr);
@@ -1453,7 +1453,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
if (WARN_ON_ONCE(!peer_pdd))
continue;
if (flush_tlb)
- kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
+ kfd_flush_tlb(peer_pdd);
/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index c1f668f12732..8d9bf4334090 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -595,7 +595,7 @@ static int allocate_vmid(struct device_queue_manager *dqm,
qpd->vmid,
qpd->page_table_base);
/* invalidate the VM context after pasid and vmid mapping is set up */
- kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
+ kfd_flush_tlb(qpd_to_pdd(qpd));
if (dqm->dev->kfd2kgd->set_scratch_backing_va)
dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev,
@@ -633,7 +633,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
if (flush_texture_cache_nocpsch(q->device, qpd))
dev_err(dev, "Failed to flush TC\n");
- kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
+ kfd_flush_tlb(qpd_to_pdd(qpd));
/* Release the vmid mapping */
set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
@@ -1307,7 +1307,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
dqm->dev->adev,
qpd->vmid,
qpd->page_table_base);
- kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
+ kfd_flush_tlb(pdd);
}
/* Take a safe reference to the mm_struct, which may otherwise
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 53c26b1a25ca..dc8787dc399b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1559,13 +1559,13 @@ void kfd_signal_reset_event(struct kfd_node *dev);
void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid);
void kfd_signal_process_terminate_event(struct kfd_process *p);
-static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
- enum TLB_FLUSH_TYPE type)
+static inline void kfd_flush_tlb(struct kfd_process_device *pdd)
{
struct amdgpu_device *adev = pdd->dev->adev;
struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv);
- amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask);
+ amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT,
+ pdd->dev->xcc_mask);
}
static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 015eb61f3440..5090f8c15428 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1418,7 +1418,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
if (r)
break;
}
- kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
+ kfd_flush_tlb(pdd);
}
return r;
@@ -1560,7 +1560,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,
}
}
- kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
+ kfd_flush_tlb(pdd);
}
return r;
--
2.43.0
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH] drm/amdkfd: Make all TLB-flushes heavy-weight
2026-04-20 15:58 [PATCH] drm/amdkfd: Make all TLB-flushes heavy-weight Felix Kuehling
@ 2026-04-20 21:32 ` Philip Yang
2026-04-27 17:48 ` Felix Kuehling
0 siblings, 1 reply; 4+ messages in thread
From: Philip Yang @ 2026-04-20 21:32 UTC (permalink / raw)
To: Felix Kuehling, amd-gfx; +Cc: philip.yang, christian.koenig
[-- Attachment #1: Type: text/plain, Size: 4987 bytes --]
On 2026-04-20 11:58, Felix Kuehling wrote:
> With only one sequence number we cannot track the need for legacy vs
> heavy-weight flushes reliably. Always use heavy-weight.
>
> Signed-off-by: Felix Kuehling<felix.kuehling@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++--
> drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++---
> drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 6 +++---
> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 ++--
> 4 files changed, 10 insertions(+), 10 deletions(-)
Probably change to heavy-weight flush in this path, other changes look
good to me.
amdgpu_gem_va_update_vm()
{
....
if (vm->is_compute_context) {
.....
r = amdgpu_vm_flush_compute_tlb(adev, vm,
TLB_FLUSH_LEGACY,
xcc_mask);
}
Regards,
Philip
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> index 16fb39259911..0625104a7693 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> @@ -1358,7 +1358,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
> peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
> if (WARN_ON_ONCE(!peer_pdd))
> continue;
> - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
> + kfd_flush_tlb(peer_pdd);
> }
> kfree(devices_arr);
>
> @@ -1453,7 +1453,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
> if (WARN_ON_ONCE(!peer_pdd))
> continue;
> if (flush_tlb)
> - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
> + kfd_flush_tlb(peer_pdd);
>
> /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
> err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> index c1f668f12732..8d9bf4334090 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> @@ -595,7 +595,7 @@ static int allocate_vmid(struct device_queue_manager *dqm,
> qpd->vmid,
> qpd->page_table_base);
> /* invalidate the VM context after pasid and vmid mapping is set up */
> - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
> + kfd_flush_tlb(qpd_to_pdd(qpd));
>
> if (dqm->dev->kfd2kgd->set_scratch_backing_va)
> dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev,
> @@ -633,7 +633,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
> if (flush_texture_cache_nocpsch(q->device, qpd))
> dev_err(dev, "Failed to flush TC\n");
>
> - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
> + kfd_flush_tlb(qpd_to_pdd(qpd));
>
> /* Release the vmid mapping */
> set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
> @@ -1307,7 +1307,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
> dqm->dev->adev,
> qpd->vmid,
> qpd->page_table_base);
> - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
> + kfd_flush_tlb(pdd);
> }
>
> /* Take a safe reference to the mm_struct, which may otherwise
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> index 53c26b1a25ca..dc8787dc399b 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> @@ -1559,13 +1559,13 @@ void kfd_signal_reset_event(struct kfd_node *dev);
> void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid);
> void kfd_signal_process_terminate_event(struct kfd_process *p);
>
> -static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
> - enum TLB_FLUSH_TYPE type)
> +static inline void kfd_flush_tlb(struct kfd_process_device *pdd)
> {
> struct amdgpu_device *adev = pdd->dev->adev;
> struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv);
>
> - amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask);
> + amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT,
> + pdd->dev->xcc_mask);
> }
>
> static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index 015eb61f3440..5090f8c15428 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -1418,7 +1418,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
> if (r)
> break;
> }
> - kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
> + kfd_flush_tlb(pdd);
> }
>
> return r;
> @@ -1560,7 +1560,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,
> }
> }
>
> - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
> + kfd_flush_tlb(pdd);
> }
>
> return r;
[-- Attachment #2: Type: text/html, Size: 5773 bytes --]
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] drm/amdkfd: Make all TLB-flushes heavy-weight
2026-04-20 21:32 ` Philip Yang
@ 2026-04-27 17:48 ` Felix Kuehling
2026-04-27 20:53 ` Philip Yang
0 siblings, 1 reply; 4+ messages in thread
From: Felix Kuehling @ 2026-04-27 17:48 UTC (permalink / raw)
To: Philip Yang, amd-gfx; +Cc: philip.yang, christian.koenig
On 2026-04-20 17:32, Philip Yang wrote:
>
>
> On 2026-04-20 11:58, Felix Kuehling wrote:
>> With only one sequence number we cannot track the need for legacy vs
>> heavy-weight flushes reliably. Always use heavy-weight.
>>
>> Signed-off-by: Felix Kuehling<felix.kuehling@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++--
>> drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++---
>> drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 6 +++---
>> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 ++--
>> 4 files changed, 10 insertions(+), 10 deletions(-)
> Probably change to heavy-weight flush in this path, other changes look
> good to me.
>
> amdgpu_gem_va_update_vm()
> {
> ....
> if (vm->is_compute_context) {
> .....
> r = amdgpu_vm_flush_compute_tlb(adev, vm,
> TLB_FLUSH_LEGACY,
> xcc_mask);
This code doesn't exist on the amd-staging-drm-next branch that this
patch is intended for. I'll need to make a separate patch for the DKMS
branch that includes this one.
Can I get your R-b for this patch?
Thanks,
Felix
> }
>
> Regards,
> Philip
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>> index 16fb39259911..0625104a7693 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>> @@ -1358,7 +1358,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
>> peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
>> if (WARN_ON_ONCE(!peer_pdd))
>> continue;
>> - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
>> + kfd_flush_tlb(peer_pdd);
>> }
>> kfree(devices_arr);
>>
>> @@ -1453,7 +1453,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
>> if (WARN_ON_ONCE(!peer_pdd))
>> continue;
>> if (flush_tlb)
>> - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
>> + kfd_flush_tlb(peer_pdd);
>>
>> /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
>> err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> index c1f668f12732..8d9bf4334090 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> @@ -595,7 +595,7 @@ static int allocate_vmid(struct device_queue_manager *dqm,
>> qpd->vmid,
>> qpd->page_table_base);
>> /* invalidate the VM context after pasid and vmid mapping is set up */
>> - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
>> + kfd_flush_tlb(qpd_to_pdd(qpd));
>>
>> if (dqm->dev->kfd2kgd->set_scratch_backing_va)
>> dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev,
>> @@ -633,7 +633,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
>> if (flush_texture_cache_nocpsch(q->device, qpd))
>> dev_err(dev, "Failed to flush TC\n");
>>
>> - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
>> + kfd_flush_tlb(qpd_to_pdd(qpd));
>>
>> /* Release the vmid mapping */
>> set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
>> @@ -1307,7 +1307,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
>> dqm->dev->adev,
>> qpd->vmid,
>> qpd->page_table_base);
>> - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
>> + kfd_flush_tlb(pdd);
>> }
>>
>> /* Take a safe reference to the mm_struct, which may otherwise
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>> index 53c26b1a25ca..dc8787dc399b 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>> @@ -1559,13 +1559,13 @@ void kfd_signal_reset_event(struct kfd_node *dev);
>> void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid);
>> void kfd_signal_process_terminate_event(struct kfd_process *p);
>>
>> -static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
>> - enum TLB_FLUSH_TYPE type)
>> +static inline void kfd_flush_tlb(struct kfd_process_device *pdd)
>> {
>> struct amdgpu_device *adev = pdd->dev->adev;
>> struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv);
>>
>> - amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask);
>> + amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT,
>> + pdd->dev->xcc_mask);
>> }
>>
>> static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>> index 015eb61f3440..5090f8c15428 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>> @@ -1418,7 +1418,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
>> if (r)
>> break;
>> }
>> - kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
>> + kfd_flush_tlb(pdd);
>> }
>>
>> return r;
>> @@ -1560,7 +1560,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,
>> }
>> }
>>
>> - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
>> + kfd_flush_tlb(pdd);
>> }
>>
>> return r;
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] drm/amdkfd: Make all TLB-flushes heavy-weight
2026-04-27 17:48 ` Felix Kuehling
@ 2026-04-27 20:53 ` Philip Yang
0 siblings, 0 replies; 4+ messages in thread
From: Philip Yang @ 2026-04-27 20:53 UTC (permalink / raw)
To: Felix Kuehling, amd-gfx; +Cc: philip.yang, christian.koenig
[-- Attachment #1: Type: text/plain, Size: 6569 bytes --]
On 2026-04-27 13:48, Felix Kuehling wrote:
> On 2026-04-20 17:32, Philip Yang wrote:
>>
>>
>> On 2026-04-20 11:58, Felix Kuehling wrote:
>>> With only one sequence number we cannot track the need for legacy vs
>>> heavy-weight flushes reliably. Always use heavy-weight.
>>>
>>> Signed-off-by: Felix Kuehling<felix.kuehling@amd.com>
>>> ---
>>> drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++--
>>> drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++---
>>> drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 6 +++---
>>> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 ++--
>>> 4 files changed, 10 insertions(+), 10 deletions(-)
>> Probably change to heavy-weight flush in this path, other changes
>> look good to me.
>>
>> amdgpu_gem_va_update_vm()
>> {
>> ....
>> if (vm->is_compute_context) {
>> .....
>> r = amdgpu_vm_flush_compute_tlb(adev, vm,
>> TLB_FLUSH_LEGACY,
>> xcc_mask);
>
> This code doesn't exist on the amd-staging-drm-next branch that this
> patch is intended for. I'll need to make a separate patch for the DKMS
> branch that includes this one.
>
> Can I get your R-b for this patch?
ohh, I checked the DKMS branch as I am working on it. For
amd-staging-drm-next branch, this patch is
Reviewed-by: Philip Yang <philip.yang@amd.com>
>
> Thanks,
> Felix
>
>
>> }
>>
>> Regards,
>> Philip
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> index 16fb39259911..0625104a7693 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> @@ -1358,7 +1358,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct
>>> file *filep,
>>> peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
>>> if (WARN_ON_ONCE(!peer_pdd))
>>> continue;
>>> - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
>>> + kfd_flush_tlb(peer_pdd);
>>> }
>>> kfree(devices_arr);
>>> @@ -1453,7 +1453,7 @@ static int
>>> kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
>>> if (WARN_ON_ONCE(!peer_pdd))
>>> continue;
>>> if (flush_tlb)
>>> - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
>>> + kfd_flush_tlb(peer_pdd);
>>> /* Remove dma mapping after tlb flush to avoid
>>> IO_PAGE_FAULT */
>>> err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem,
>>> peer_pdd->drm_priv);
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>>> b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>>> index c1f668f12732..8d9bf4334090 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>>> @@ -595,7 +595,7 @@ static int allocate_vmid(struct
>>> device_queue_manager *dqm,
>>> qpd->vmid,
>>> qpd->page_table_base);
>>> /* invalidate the VM context after pasid and vmid mapping is
>>> set up */
>>> - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
>>> + kfd_flush_tlb(qpd_to_pdd(qpd));
>>> if (dqm->dev->kfd2kgd->set_scratch_backing_va)
>>> dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev,
>>> @@ -633,7 +633,7 @@ static void deallocate_vmid(struct
>>> device_queue_manager *dqm,
>>> if (flush_texture_cache_nocpsch(q->device, qpd))
>>> dev_err(dev, "Failed to flush TC\n");
>>> - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY);
>>> + kfd_flush_tlb(qpd_to_pdd(qpd));
>>> /* Release the vmid mapping */
>>> set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
>>> @@ -1307,7 +1307,7 @@ static int
>>> restore_process_queues_nocpsch(struct device_queue_manager *dqm,
>>> dqm->dev->adev,
>>> qpd->vmid,
>>> qpd->page_table_base);
>>> - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
>>> + kfd_flush_tlb(pdd);
>>> }
>>> /* Take a safe reference to the mm_struct, which may otherwise
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> index 53c26b1a25ca..dc8787dc399b 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> @@ -1559,13 +1559,13 @@ void kfd_signal_reset_event(struct kfd_node
>>> *dev);
>>> void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32
>>> pasid);
>>> void kfd_signal_process_terminate_event(struct kfd_process *p);
>>> -static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
>>> - enum TLB_FLUSH_TYPE type)
>>> +static inline void kfd_flush_tlb(struct kfd_process_device *pdd)
>>> {
>>> struct amdgpu_device *adev = pdd->dev->adev;
>>> struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv);
>>> - amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask);
>>> + amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT,
>>> + pdd->dev->xcc_mask);
>>> }
>>> static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> index 015eb61f3440..5090f8c15428 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> @@ -1418,7 +1418,7 @@ svm_range_unmap_from_gpus(struct svm_range
>>> *prange, unsigned long start,
>>> if (r)
>>> break;
>>> }
>>> - kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
>>> + kfd_flush_tlb(pdd);
>>> }
>>> return r;
>>> @@ -1560,7 +1560,7 @@ svm_range_map_to_gpus(struct svm_range
>>> *prange, unsigned long offset,
>>> }
>>> }
>>> - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
>>> + kfd_flush_tlb(pdd);
>>> }
>>> return r;
>>
[-- Attachment #2: Type: text/html, Size: 12426 bytes --]
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-04-27 20:53 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-04-20 15:58 [PATCH] drm/amdkfd: Make all TLB-flushes heavy-weight Felix Kuehling
2026-04-20 21:32 ` Philip Yang
2026-04-27 17:48 ` Felix Kuehling
2026-04-27 20:53 ` Philip Yang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox