Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>
To: Matthew Brost <matthew.brost@intel.com>
Cc: <intel-xe@lists.freedesktop.org>,
	<thomas.hellstrom@linux.intel.com>, <oak.zeng@intel.com>
Subject: Re: [RFC 09/29] drm/xe/svm: Allow unaligned addresses and ranges for prefetch
Date: Mon, 7 Apr 2025 11:45:41 +0530	[thread overview]
Message-ID: <c805bb29-ddc8-44a7-900d-48cd557b06b3@intel.com> (raw)
In-Reply-To: <Z+7087lxPgQWSyez@lstrano-desk.jf.intel.com>



On 04-04-2025 02:22, Matthew Brost wrote:
> On Fri, Mar 14, 2025 at 01:32:06PM +0530, Himal Prasad Ghimiray wrote:
>> The SVM prefetch operation can handle unaligned addresses and range sizes.
>> This commit updates the ioctl parameter checks to accommodate unaligned
>> addresses and range sizes for SVM prefetch operations.
>>
> 
> Do we really want to allow unaligned to page size prefetches? That seems
> rather odd use case. Was this a specific request from the UMD team?

Yes, this came as a requirement from UMD team.

> 
> Matt
> 
>> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
>> ---
>>   drivers/gpu/drm/xe/xe_vm.c | 18 ++++++++++++++++--
>>   1 file changed, 16 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
>> index 07cad2804b14..c6343a629c02 100644
>> --- a/drivers/gpu/drm/xe/xe_vm.c
>> +++ b/drivers/gpu/drm/xe/xe_vm.c
>> @@ -3086,6 +3086,16 @@ ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO);
>>   #define XE_64K_PAGE_MASK 0xffffull
>>   #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
>>   
>> +static bool addr_not_in_cpu_addr_vma(struct xe_vm *vm, u64 addr)
>> +{
>> +	struct xe_vma *vma;
>> +
>> +	down_write(&vm->lock);
>> +	vma = xe_vm_find_vma_by_addr(vm, addr);
>> +	up_write(&vm->lock);
>> +	return !xe_vma_is_cpu_addr_mirror(vma);
>> +}
>> +
>>   static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
>>   				    struct drm_xe_vm_bind *args,
>>   				    struct drm_xe_vm_bind_op **bind_ops)
>> @@ -3194,8 +3204,12 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
>>   		}
>>   
>>   		if (XE_IOCTL_DBG(xe, obj_offset & ~PAGE_MASK) ||
>> -		    XE_IOCTL_DBG(xe, addr & ~PAGE_MASK) ||
>> -		    XE_IOCTL_DBG(xe, range & ~PAGE_MASK) ||
>> +		    XE_IOCTL_DBG(xe, (addr & ~PAGE_MASK) &&
>> +				 (addr_not_in_cpu_addr_vma(vm, addr) ||
>> +				 op != DRM_XE_VM_BIND_OP_PREFETCH)) ||
>> +		    XE_IOCTL_DBG(xe, (range & ~PAGE_MASK) &&
>> +				 (addr_not_in_cpu_addr_vma(vm, addr) ||
>> +				 op != DRM_XE_VM_BIND_OP_PREFETCH)) ||
>>   		    XE_IOCTL_DBG(xe, !range &&
>>   				 op != DRM_XE_VM_BIND_OP_UNMAP_ALL)) {
>>   			err = -EINVAL;
>> -- 
>> 2.34.1
>>


  reply	other threads:[~2025-04-07  6:15 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-14  8:01 [RFC 00/29] PREFETCH and MADVISE for SVM ranges Himal Prasad Ghimiray
2025-03-14  8:01 ` [RFC 01/29] drm/xe: Introduce xe_vma_op_prefetch_range struct for prefetch of ranges Himal Prasad Ghimiray
2025-04-03 20:59   ` Matthew Brost
2025-03-14  8:01 ` [RFC 02/29] drm/xe: Make xe_svm_alloc_vram public Himal Prasad Ghimiray
2025-03-27 22:45   ` Matthew Brost
2025-03-28  7:51     ` Ghimiray, Himal Prasad
2025-03-14  8:02 ` [RFC 03/29] drm/xe/svm: Helper to add tile masks to svm ranges Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 04/29] drm/xe/svm: Make to_xe_range a public function Himal Prasad Ghimiray
2025-03-28  2:57   ` Matthew Brost
2025-03-14  8:02 ` [RFC 05/29] drm/xe/svm: Make xe_svm_range_* end/start/size public Himal Prasad Ghimiray
2025-03-27 22:46   ` Matthew Brost
2025-03-14  8:02 ` [RFC 06/29] drm/xe/vm: Update xe_vma_ops_incr_pt_update_ops to take an increment value Himal Prasad Ghimiray
2025-03-28  2:56   ` Matthew Brost
2025-03-28  7:52     ` Ghimiray, Himal Prasad
2025-03-14  8:02 ` [RFC 07/29] drm/xe/vm: Add an identifier in xe_vma_ops for svm prefetch Himal Prasad Ghimiray
2025-03-27 22:49   ` Matthew Brost
2025-03-28  7:53     ` Ghimiray, Himal Prasad
2025-03-14  8:02 ` [RFC 08/29] drm/xe: Rename lookup_vma function to xe_find_vma_by_addr Himal Prasad Ghimiray
2025-04-03 21:02   ` Matthew Brost
2025-04-07  6:16     ` Ghimiray, Himal Prasad
2025-03-14  8:02 ` [RFC 09/29] drm/xe/svm: Allow unaligned addresses and ranges for prefetch Himal Prasad Ghimiray
2025-04-03 20:52   ` Matthew Brost
2025-04-07  6:15     ` Ghimiray, Himal Prasad [this message]
2025-03-14  8:02 ` [RFC 10/29] drm/xe/svm: Refactor usage of drm_gpusvm* function in xe_svm Himal Prasad Ghimiray
2025-04-03 20:54   ` Matthew Brost
2025-04-07  6:15     ` Ghimiray, Himal Prasad
2025-03-14  8:02 ` [RFC 11/29] drm/xe/svm: Implement prefetch support for SVM ranges Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 12/29] drm/xe/vm: Add debug prints for SVM range prefetch Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 13/29] drm/gpuvm: Introduce MADVISE Operations Himal Prasad Ghimiray
2025-03-14  8:46   ` Ghimiray, Himal Prasad
2025-03-17 14:27   ` Danilo Krummrich
2025-03-18 11:58     ` Ghimiray, Himal Prasad
2025-03-14  8:02 ` [RFC 14/29] drm/xe/uapi: Add madvise interface Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 15/29] drm/xe/vm: Add attributes struct as member of vma Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 16/29] drm/xe/vma: Move pat_index to vma attributes Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 17/29] drm/xe/vma: Modify new_vma to accept struct xe_vma_mem_attr as parameter Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 18/29] drm/gpusvm: Make drm_gpusvm_for_each_* macros public Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 19/29] drm/xe/svm: Split system allocator vma incase of madvise call Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 20/29] drm/xe: Implement madvise ioctl for xe Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 21/29] drm/xe: Allow CPU address mirror VMA unbind with gpu bindings for madvise Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 22/29] drm/xe/svm : Add svm ranges migration policy on atomic access Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 23/29] drm/xe/madvise: Update migration policy based on preferred location Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 24/29] drm/xe/svm: Support DRM_XE_SVM_ATTR_PAT memory attribute Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 25/29] drm/xe/uapi: Add flag for consulting madvise hints on svm prefetch Himal Prasad Ghimiray
2025-05-14 19:26   ` Matthew Brost
2025-03-14  8:02 ` [RFC 26/29] drm/xe/svm: Consult madvise preferred location in prefetch Himal Prasad Ghimiray
2025-03-14  8:02 ` [RFC 27/29] drm/xe/uapi: Add uapi for vma count and mem attributes Himal Prasad Ghimiray
2025-05-14 19:39   ` Matthew Brost
2025-03-14  8:02 ` [RFC 28/29] drm/xe/bo: Add attributes field to xe_bo Himal Prasad Ghimiray
2025-05-14 19:35   ` Matthew Brost
2025-03-14  8:02 ` [RFC 29/29] drm/xe/bo : Update atomic_access attribute on madvise Himal Prasad Ghimiray
2025-03-14 15:00 ` ✗ CI.Patch_applied: failure for PREFETCH and MADVISE for SVM ranges (rev2) Patchwork

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=c805bb29-ddc8-44a7-900d-48cd557b06b3@intel.com \
    --to=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=oak.zeng@intel.com \
    --cc=thomas.hellstrom@linux.intel.com \
    /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