From: "Kuehling, Felix" <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
To: "Zeng, Oak" <Oak.Zeng-5C7GfCeVMHo@public.gmane.org>,
"amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
<amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Cc: "Keely, Sean" <Sean.Keely-5C7GfCeVMHo@public.gmane.org>
Subject: Re: [PATCH 6/7] drm/amdkfd: New IOCTL to allocate queue GWS
Date: Wed, 22 May 2019 21:49:21 +0000 [thread overview]
Message-ID: <37883f89-b2a0-4d3f-76d8-eb3cf8b9a462@amd.com> (raw)
In-Reply-To: <1558540278-23734-6-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
On 2019-05-22 11:51 a.m., Zeng, Oak wrote:
> Add a new kfd ioctl to allocate queue GWS. Queue
> GWS is released on queue destroy.
>
> Change-Id: I60153c26a577992ad873e4292e759e5c3d5bbd15
> Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 39 ++++++++++++++++++++++++++++++++
> include/uapi/linux/kfd_ioctl.h | 20 +++++++++++++++-
> 2 files changed, 58 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> index 38ae53f..828bd66 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> @@ -1559,6 +1559,43 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
> return err;
> }
>
> +static int kfd_ioctl_alloc_queue_gws(struct file *filep,
> + struct kfd_process *p, void *data)
> +{
> + int retval;
> + struct kfd_ioctl_alloc_queue_gws_args *args = data;
> + struct kfd_dev *dev = NULL;
> + struct kgd_mem *mem;
> +
> + if (args->num_gws == 0)
> + return -EINVAL;
> +
> + if (!hws_gws_support ||
> + dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS)
> + return -EINVAL;
> +
> + dev = kfd_device_by_id(args->gpu_id);
> + if (!dev) {
> + pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
> + return -EINVAL;
> + }
> +
> + retval = amdgpu_amdkfd_add_gws_to_process(p->kgd_process_info,
> + dev->gws, &mem);
Do you want to move this into pqm_set_gws? The corresponding call to
amdgpu_amdkfd_remove_from_gws is handled in pqm (during queue
destruction) too.
Regards,
Felix
> + if (unlikely(retval))
> + return retval;
> +
> + mutex_lock(&p->mutex);
> + retval = pqm_set_gws(&p->pqm, args->queue_id, mem);
> + mutex_unlock(&p->mutex);
> +
> + if (unlikely(retval))
> + amdgpu_amdkfd_remove_gws_from_process(p->kgd_process_info, mem);
> +
> + args->first_gws = 0;
> + return retval;
> +}
> +
> static int kfd_ioctl_get_dmabuf_info(struct file *filep,
> struct kfd_process *p, void *data)
> {
> @@ -1761,6 +1798,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
> AMDKFD_IOCTL_DEF(AMDKFD_IOC_IMPORT_DMABUF,
> kfd_ioctl_import_dmabuf, 0),
>
> + AMDKFD_IOCTL_DEF(AMDKFD_IOC_ALLOC_QUEUE_GWS,
> + kfd_ioctl_alloc_queue_gws, 0),
> };
>
> #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls)
> diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
> index 20917c5..070d1bc 100644
> --- a/include/uapi/linux/kfd_ioctl.h
> +++ b/include/uapi/linux/kfd_ioctl.h
> @@ -410,6 +410,21 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
> __u32 n_success; /* to/from KFD */
> };
>
> +/* Allocate GWS for specific queue
> + *
> + * @gpu_id: device identifier
> + * @queue_id: queue's id that GWS is allocated for
> + * @num_gws: how many GWS to allocate
> + * @first_gws: index of the first GWS allocated.
> + * only support contiguous GWS allocation
> + */
> +struct kfd_ioctl_alloc_queue_gws_args {
> + __u32 gpu_id; /* to KFD */
> + __u32 queue_id; /* to KFD */
> + __u32 num_gws; /* to KFD */
> + __u32 first_gws; /* from KFD */
> +};
> +
> struct kfd_ioctl_get_dmabuf_info_args {
> __u64 size; /* from KFD */
> __u64 metadata_ptr; /* to KFD */
> @@ -529,7 +544,10 @@ enum kfd_mmio_remap {
> #define AMDKFD_IOC_IMPORT_DMABUF \
> AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args)
>
> +#define AMDKFD_IOC_ALLOC_QUEUE_GWS \
> + AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)
> +
> #define AMDKFD_COMMAND_START 0x01
> -#define AMDKFD_COMMAND_END 0x1E
> +#define AMDKFD_COMMAND_END 0x1F
>
> #endif
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
next prev parent reply other threads:[~2019-05-22 21:49 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-22 15:51 [PATCH 1/7] drm/amdkfd: Add gws number to kfd topology node properties Zeng, Oak
[not found] ` <1558540278-23734-1-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-22 15:51 ` [PATCH 2/7] drm/amdgpu: Add interface to alloc gws from amdgpu Zeng, Oak
2019-05-22 15:51 ` [PATCH 3/7] drm/amdkfd: Allocate gws on device initialization Zeng, Oak
2019-05-22 15:51 ` [PATCH 4/7] drm/amdgpu: Add function to add/remove gws to kfd process Zeng, Oak
[not found] ` <1558540278-23734-4-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-22 21:49 ` Kuehling, Felix
2019-05-22 15:51 ` [PATCH 5/7] drm/amdkfd: Add function to set queue gws Zeng, Oak
[not found] ` <1558540278-23734-5-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-22 21:46 ` Kuehling, Felix
2019-05-22 15:51 ` [PATCH 6/7] drm/amdkfd: New IOCTL to allocate queue GWS Zeng, Oak
[not found] ` <1558540278-23734-6-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-22 21:49 ` Kuehling, Felix [this message]
2019-05-22 15:51 ` [PATCH 7/7] drm/amdkfd: PM4 packets change to support GWS Zeng, Oak
-- strict thread matches above, loose matches on Subject: below --
2019-05-23 18:40 [PATCH 1/7] drm/amdkfd: Add gws number to kfd topology node properties Zeng, Oak
[not found] ` <1558636843-9867-1-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-23 18:41 ` [PATCH 6/7] drm/amdkfd: New IOCTL to allocate queue GWS Zeng, Oak
[not found] ` <1558636843-9867-6-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-23 21:44 ` Kuehling, Felix
2019-05-15 20:37 [PATCH 1/7] drm/amdkfd: Add gws number to kfd topology node properties Zeng, Oak
[not found] ` <1557952664-12218-1-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-15 20:37 ` [PATCH 6/7] drm/amdkfd: New IOCTL to allocate queue GWS Zeng, Oak
[not found] ` <1557952664-12218-6-git-send-email-Oak.Zeng-5C7GfCeVMHo@public.gmane.org>
2019-05-21 20:20 ` Kuehling, Felix
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=37883f89-b2a0-4d3f-76d8-eb3cf8b9a462@amd.com \
--to=felix.kuehling-5c7gfcevmho@public.gmane.org \
--cc=Oak.Zeng-5C7GfCeVMHo@public.gmane.org \
--cc=Sean.Keely-5C7GfCeVMHo@public.gmane.org \
--cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox