* [PATCH] drm/amdkfd: disable SVM for GC 10.1.3/4
@ 2023-09-07 12:08 Lang Yu
2023-09-07 20:03 ` Felix Kuehling
0 siblings, 1 reply; 3+ messages in thread
From: Lang Yu @ 2023-09-07 12:08 UTC (permalink / raw)
To: amd-gfx; +Cc: Philip Yang, Felix Kuehling, Lang Yu
GC 10.1.3/4 have problems with TLB_FLUSH_HEAVYWEIGHT
which is used by SVM in svm_range_unmap_from_gpus().
This causes problems on GC 10.1.3/4.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 22 +++++++++++++++++-----
1 file changed, 17 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 7d82c7da223a..dd3db3d88d59 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -992,6 +992,22 @@ static const struct dev_pagemap_ops svm_migrate_pgmap_ops = {
/* Each VRAM page uses sizeof(struct page) on system memory */
#define SVM_HMM_PAGE_STRUCT_SIZE(size) ((size)/PAGE_SIZE * sizeof(struct page))
+static inline bool is_zone_device_needed(struct amdgpu_device *adev)
+{
+ /* Page migration works on gfx9 or newer */
+ if (adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 1))
+ return false;
+
+ if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 3) ||
+ adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 4))
+ return false;
+
+ if (adev->gmc.is_app_apu)
+ return false;
+
+ return true;
+}
+
int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
{
struct amdgpu_kfd_dev *kfddev = &adev->kfd;
@@ -1000,11 +1016,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
unsigned long size;
void *r;
- /* Page migration works on gfx9 or newer */
- if (adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 1))
- return -EINVAL;
-
- if (adev->gmc.is_app_apu)
+ if (!is_zone_device_needed(adev))
return 0;
pgmap = &kfddev->pgmap;
--
2.25.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/amdkfd: disable SVM for GC 10.1.3/4
2023-09-07 12:08 [PATCH] drm/amdkfd: disable SVM for GC 10.1.3/4 Lang Yu
@ 2023-09-07 20:03 ` Felix Kuehling
2023-09-08 2:27 ` Lang Yu
0 siblings, 1 reply; 3+ messages in thread
From: Felix Kuehling @ 2023-09-07 20:03 UTC (permalink / raw)
To: Lang Yu, amd-gfx; +Cc: Philip Yang
We need heavy-weight flushes not just for SVM. If this is broken it will
affect ROCm either way.
Regards,
Felix
On 2023-09-07 08:08, Lang Yu wrote:
> GC 10.1.3/4 have problems with TLB_FLUSH_HEAVYWEIGHT
> which is used by SVM in svm_range_unmap_from_gpus().
> This causes problems on GC 10.1.3/4.
>
> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 22 +++++++++++++++++-----
> 1 file changed, 17 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 7d82c7da223a..dd3db3d88d59 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -992,6 +992,22 @@ static const struct dev_pagemap_ops svm_migrate_pgmap_ops = {
> /* Each VRAM page uses sizeof(struct page) on system memory */
> #define SVM_HMM_PAGE_STRUCT_SIZE(size) ((size)/PAGE_SIZE * sizeof(struct page))
>
> +static inline bool is_zone_device_needed(struct amdgpu_device *adev)
> +{
> + /* Page migration works on gfx9 or newer */
> + if (adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 1))
> + return false;
> +
> + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 3) ||
> + adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 4))
> + return false;
> +
> + if (adev->gmc.is_app_apu)
> + return false;
> +
> + return true;
> +}
> +
> int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
> {
> struct amdgpu_kfd_dev *kfddev = &adev->kfd;
> @@ -1000,11 +1016,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
> unsigned long size;
> void *r;
>
> - /* Page migration works on gfx9 or newer */
> - if (adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 1))
> - return -EINVAL;
> -
> - if (adev->gmc.is_app_apu)
> + if (!is_zone_device_needed(adev))
> return 0;
>
> pgmap = &kfddev->pgmap;
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/amdkfd: disable SVM for GC 10.1.3/4
2023-09-07 20:03 ` Felix Kuehling
@ 2023-09-08 2:27 ` Lang Yu
0 siblings, 0 replies; 3+ messages in thread
From: Lang Yu @ 2023-09-08 2:27 UTC (permalink / raw)
To: Felix Kuehling; +Cc: Philip Yang, amd-gfx
On 09/07/ , Felix Kuehling wrote:
> We need heavy-weight flushes not just for SVM. If this is broken it will
> affect ROCm either way.
Currently, TLB_FLUSH_HEAVYWEIGHT is called in 2 places,
1, kfd_ioctl_unmap_memory_from_gpu()
Under following conditions.
KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3) ||
KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
(KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
2, svm_range_unmap_from_gpus()
Unconditional.
That means TLB_FLUSH_HEAVYWEIGHT defect won't affect ROCm if
we don't use SVM for ASICs except MI series.
Regards,
Lang
> Regards,
> Felix
>
>
> On 2023-09-07 08:08, Lang Yu wrote:
> > GC 10.1.3/4 have problems with TLB_FLUSH_HEAVYWEIGHT
> > which is used by SVM in svm_range_unmap_from_gpus().
> > This causes problems on GC 10.1.3/4.
> >
> > Signed-off-by: Lang Yu <Lang.Yu@amd.com>
> > ---
> > drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 22 +++++++++++++++++-----
> > 1 file changed, 17 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> > index 7d82c7da223a..dd3db3d88d59 100644
> > --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> > +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> > @@ -992,6 +992,22 @@ static const struct dev_pagemap_ops svm_migrate_pgmap_ops = {
> > /* Each VRAM page uses sizeof(struct page) on system memory */
> > #define SVM_HMM_PAGE_STRUCT_SIZE(size) ((size)/PAGE_SIZE * sizeof(struct page))
> > +static inline bool is_zone_device_needed(struct amdgpu_device *adev)
> > +{
> > + /* Page migration works on gfx9 or newer */
> > + if (adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 1))
> > + return false;
> > +
> > + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 3) ||
> > + adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 4))
> > + return false;
> > +
> > + if (adev->gmc.is_app_apu)
> > + return false;
> > +
> > + return true;
> > +}
> > +
> > int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
> > {
> > struct amdgpu_kfd_dev *kfddev = &adev->kfd;
> > @@ -1000,11 +1016,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
> > unsigned long size;
> > void *r;
> > - /* Page migration works on gfx9 or newer */
> > - if (adev->ip_versions[GC_HWIP][0] < IP_VERSION(9, 0, 1))
> > - return -EINVAL;
> > -
> > - if (adev->gmc.is_app_apu)
> > + if (!is_zone_device_needed(adev))
> > return 0;
> > pgmap = &kfddev->pgmap;
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2023-09-08 2:27 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2023-09-07 12:08 [PATCH] drm/amdkfd: disable SVM for GC 10.1.3/4 Lang Yu
2023-09-07 20:03 ` Felix Kuehling
2023-09-08 2:27 ` Lang Yu
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.