Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: "Christian König" <christian.koenig@amd.com>
Cc: "Christian König" <ckoenig.leichtzumerken@gmail.com>,
	"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
	"Huang Rui" <ray.huang@amd.com>,
	intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
	matthew.auld@intel.com
Subject: Re: [PATCH v6 2/8] drm/ttm: Add ttm_bo_access
Date: Wed, 6 Nov 2024 09:00:09 -0800	[thread overview]
Message-ID: <ZyugmXt7v+JeKuN9@lstrano-desk.jf.intel.com> (raw)
In-Reply-To: <34d18085-7e23-4632-9287-65eff6651bba@amd.com>

On Wed, Nov 06, 2024 at 04:44:15PM +0100, Christian König wrote:
> Am 06.11.24 um 16:25 schrieb Matthew Brost:
> > [SNIP]
> > > Can you fully describe your use case? In other words what exactly is your
> > > debugger trying to do?
> > See above; I hope I've made this clearer.
> 
> It at least sounds a little bit better.
> 
> > Also, I'm not really an expert on Eudebug, as I haven't been involved in
> > the development aside from reviewing its interaction with the core of
> > Xe. Any further explanation would likely require me to loop in a
> > colleague.
> 
> I think that could help since I don't have a clear picture of your use case.
> 
> 
> > > Well, I think we need to take a step back. The major question is what is
> > > your use case and is that use case valid or causes security concerns.
> > > 
> > > For example userptrs are imported anonymous pages the GPU has a DMA mapping
> > > for. Re-mapping them into an user address space for debugging or even
> > > accessing them through the ptrace interface is strictly forbidden.
> > > 
> > > We already had people trying to do exactly that and it ended not well at
> > > all.
> > > 
> > Again, if we can focus on what this patch is doing—accessing a BO, not a
> > userptr—I think that will help progress here.
> > 
> > To bring things together: "There is a huge push from upstream to avoid
> > using kmap/vmap if possible." How would you suggest accessing a BO then?
> 
> Well that's the whole point: You should *not* access the BO on behalves of
> userspace in a peek/poke like interface.
> 

This is not a generic interface that anyone can freely access. The same
permissions used by ptrace are checked when opening such an interface.
See [1] [2].

[1] https://patchwork.freedesktop.org/patch/617470/?series=136572&rev=2
[2] https://patchwork.freedesktop.org/patch/617471/?series=136572&rev=2

> > kmap/vmap are used everywhere in the DRM subsystem to access BOs, so I’m
> > failing to see the problem with adding a simple helper based on existing
> > code.
> 
> What#s possible and often done is to do kmap/vmap if you need to implement a
> CPU copy for scanout for example or for copying/validating command buffers.
> But that usually requires accessing the whole BO and has separate security
> checks.
> 
> When you want to access only a few bytes of a BO that sounds massively like
> a peek/poke like interface and we have already rejected that more than once.
> There even used to be standardized GEM IOCTLs for that which have been
> removed by now.
> 
> If you need to access BOs which are placed in not CPU accessible memory then
> implement the access callback for ptrace, see amdgpu_ttm_access_memory for
> an example how to do this.
> 

Ptrace access via vm_operations_struct.access → ttm_bo_vm_access.

This series renames ttm_bo_vm_access to ttm_bo_access, with no code changes.

The above function accesses a BO via kmap if it is in SYSTEM / TT,
which is existing code.

This function is only exposed to user space via ptrace permissions.

In this series, we implement a function [3] similar to
amdgpu_ttm_access_memory for the TTM vfunc access_memory. What is
missing is non-visible CPU memory access, similar to
amdgpu_ttm_access_memory_sdma. This will be addressed in a follow-up and
was omitted in this series given its complexity.

So, this looks more or less identical to AMD's ptrace implementation,
but in GPU address space. Again, I fail to see what the problem is here.
What am I missing?

Matt

[3] https://patchwork.freedesktop.org/patch/622520/?series=140200&rev=6

> Regards,
> Christian.
> 
> > 
> > Matt
> > 
> > > Regards,
> > > Christian.
> > > 
> > > > With this, I strongly prefer the code as is.
> > > > 
> > > > Matt
> > > > 
> > > > > Regards,
> > > > > Christian.
> > > > > 
> > > > > > Matt
> > > > > > 
> > > > > > > Regards,
> > > > > > > Christian.
> > > > > > > 
> > > > > > > > > Matt
> > > > > > > > > 
> > > > > > > > > > Reported-by: Christoph Manszewski<christoph.manszewski@intel.com>
> > > > > > > > > > Suggested-by: Thomas Hellström<thomas.hellstrom@linux.intel.com>
> > > > > > > > > > Signed-off-by: Matthew Brost<matthew.brost@intel.com>
> > > > > > > > > > Tested-by: Mika Kuoppala<mika.kuoppala@linux.intel.com>
> > > > > > > > > > Reviewed-by: Matthew Auld<matthew.auld@intel.com>
> > > > > > > > > > ---
> > > > > > > > > >      drivers/gpu/drm/ttm/ttm_bo_util.c | 86 +++++++++++++++++++++++++++++++
> > > > > > > > > >      drivers/gpu/drm/ttm/ttm_bo_vm.c   | 65 +----------------------
> > > > > > > > > >      include/drm/ttm/ttm_bo.h          |  2 +
> > > > > > > > > >      3 files changed, 89 insertions(+), 64 deletions(-)
> > > > > > > > > > 
> > > > > > > > > > diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > > > > > > > > index d939925efa81..77e760ea7193 100644
> > > > > > > > > > --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > > > > > > > > +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > > > > > > > > > @@ -919,3 +919,89 @@ s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev,
> > > > > > > > > >      	return progress;
> > > > > > > > > >      }
> > > > > > > > > > +
> > > > > > > > > > +static int ttm_bo_access_kmap(struct ttm_buffer_object *bo,
> > > > > > > > > > +			      unsigned long offset,
> > > > > > > > > > +			      void *buf, int len, int write)
> > > > > > > > > > +{
> > > > > > > > > > +	unsigned long page = offset >> PAGE_SHIFT;
> > > > > > > > > > +	unsigned long bytes_left = len;
> > > > > > > > > > +	int ret;
> > > > > > > > > > +
> > > > > > > > > > +	/* Copy a page at a time, that way no extra virtual address
> > > > > > > > > > +	 * mapping is needed
> > > > > > > > > > +	 */
> > > > > > > > > > +	offset -= page << PAGE_SHIFT;
> > > > > > > > > > +	do {
> > > > > > > > > > +		unsigned long bytes = min(bytes_left, PAGE_SIZE - offset);
> > > > > > > > > > +		struct ttm_bo_kmap_obj map;
> > > > > > > > > > +		void *ptr;
> > > > > > > > > > +		bool is_iomem;
> > > > > > > > > > +
> > > > > > > > > > +		ret = ttm_bo_kmap(bo, page, 1, &map);
> > > > > > > > > > +		if (ret)
> > > > > > > > > > +			return ret;
> > > > > > > > > > +
> > > > > > > > > > +		ptr = (void *)ttm_kmap_obj_virtual(&map, &is_iomem) + offset;
> > > > > > > > > > +		WARN_ON_ONCE(is_iomem);
> > > > > > > > > > +		if (write)
> > > > > > > > > > +			memcpy(ptr, buf, bytes);
> > > > > > > > > > +		else
> > > > > > > > > > +			memcpy(buf, ptr, bytes);
> > > > > > > > > > +		ttm_bo_kunmap(&map);
> > > > > > > > > > +
> > > > > > > > > > +		page++;
> > > > > > > > > > +		buf += bytes;
> > > > > > > > > > +		bytes_left -= bytes;
> > > > > > > > > > +		offset = 0;
> > > > > > > > > > +	} while (bytes_left);
> > > > > > > > > > +
> > > > > > > > > > +	return len;
> > > > > > > > > > +}
> > > > > > > > > > +
> > > > > > > > > > +/**
> > > > > > > > > > + * ttm_bo_access - Helper to access a buffer object
> > > > > > > > > > + *
> > > > > > > > > > + * @bo: ttm buffer object
> > > > > > > > > > + * @offset: access offset into buffer object
> > > > > > > > > > + * @buf: pointer to caller memory to read into or write from
> > > > > > > > > > + * @len: length of access
> > > > > > > > > > + * @write: write access
> > > > > > > > > > + *
> > > > > > > > > > + * Utility function to access a buffer object. Useful when buffer object cannot
> > > > > > > > > > + * be easily mapped (non-contiguous, non-visible, etc...).
> > > > > > > > > > + *
> > > > > > > > > > + * Returns:
> > > > > > > > > > + * @len if successful, negative error code on failure.
> > > > > > > > > > + */
> > > > > > > > > > +int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset,
> > > > > > > > > > +		  void *buf, int len, int write)
> > > > > > > > > > +{
> > > > > > > > > > +	int ret;
> > > > > > > > > > +
> > > > > > > > > > +	if (len < 1 || (offset + len) > bo->base.size)
> > > > > > > > > > +		return -EIO;
> > > > > > > > > > +
> > > > > > > > > > +	ret = ttm_bo_reserve(bo, true, false, NULL);
> > > > > > > > > > +	if (ret)
> > > > > > > > > > +		return ret;
> > > > > > > > > > +
> > > > > > > > > > +	switch (bo->resource->mem_type) {
> > > > > > > > > > +	case TTM_PL_SYSTEM:
> > > > > > > > > > +		fallthrough;
> > > > > > > > > > +	case TTM_PL_TT:
> > > > > > > > > > +		ret = ttm_bo_access_kmap(bo, offset, buf, len, write);
> > > > > > > > > > +		break;
> > > > > > > > > > +	default:
> > > > > > > > > > +		if (bo->bdev->funcs->access_memory)
> > > > > > > > > > +			ret = bo->bdev->funcs->access_memory
> > > > > > > > > > +				(bo, offset, buf, len, write);
> > > > > > > > > > +		else
> > > > > > > > > > +			ret = -EIO;
> > > > > > > > > > +	}
> > > > > > > > > > +
> > > > > > > > > > +	ttm_bo_unreserve(bo);
> > > > > > > > > > +
> > > > > > > > > > +	return ret;
> > > > > > > > > > +}
> > > > > > > > > > +EXPORT_SYMBOL(ttm_bo_access);
> > > > > > > > > > diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
> > > > > > > > > > index 2c699ed1963a..20b1e5f78684 100644
> > > > > > > > > > --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
> > > > > > > > > > +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
> > > > > > > > > > @@ -366,45 +366,6 @@ void ttm_bo_vm_close(struct vm_area_struct *vma)
> > > > > > > > > >      }
> > > > > > > > > >      EXPORT_SYMBOL(ttm_bo_vm_close);
> > > > > > > > > > -static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
> > > > > > > > > > -				 unsigned long offset,
> > > > > > > > > > -				 uint8_t *buf, int len, int write)
> > > > > > > > > > -{
> > > > > > > > > > -	unsigned long page = offset >> PAGE_SHIFT;
> > > > > > > > > > -	unsigned long bytes_left = len;
> > > > > > > > > > -	int ret;
> > > > > > > > > > -
> > > > > > > > > > -	/* Copy a page at a time, that way no extra virtual address
> > > > > > > > > > -	 * mapping is needed
> > > > > > > > > > -	 */
> > > > > > > > > > -	offset -= page << PAGE_SHIFT;
> > > > > > > > > > -	do {
> > > > > > > > > > -		unsigned long bytes = min(bytes_left, PAGE_SIZE - offset);
> > > > > > > > > > -		struct ttm_bo_kmap_obj map;
> > > > > > > > > > -		void *ptr;
> > > > > > > > > > -		bool is_iomem;
> > > > > > > > > > -
> > > > > > > > > > -		ret = ttm_bo_kmap(bo, page, 1, &map);
> > > > > > > > > > -		if (ret)
> > > > > > > > > > -			return ret;
> > > > > > > > > > -
> > > > > > > > > > -		ptr = (uint8_t *)ttm_kmap_obj_virtual(&map, &is_iomem) + offset;
> > > > > > > > > > -		WARN_ON_ONCE(is_iomem);
> > > > > > > > > > -		if (write)
> > > > > > > > > > -			memcpy(ptr, buf, bytes);
> > > > > > > > > > -		else
> > > > > > > > > > -			memcpy(buf, ptr, bytes);
> > > > > > > > > > -		ttm_bo_kunmap(&map);
> > > > > > > > > > -
> > > > > > > > > > -		page++;
> > > > > > > > > > -		buf += bytes;
> > > > > > > > > > -		bytes_left -= bytes;
> > > > > > > > > > -		offset = 0;
> > > > > > > > > > -	} while (bytes_left);
> > > > > > > > > > -
> > > > > > > > > > -	return len;
> > > > > > > > > > -}
> > > > > > > > > > -
> > > > > > > > > >      int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
> > > > > > > > > >      		     void *buf, int len, int write)
> > > > > > > > > >      {
> > > > > > > > > > @@ -412,32 +373,8 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
> > > > > > > > > >      	unsigned long offset = (addr) - vma->vm_start +
> > > > > > > > > >      		((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node))
> > > > > > > > > >      		 << PAGE_SHIFT);
> > > > > > > > > > -	int ret;
> > > > > > > > > > -
> > > > > > > > > > -	if (len < 1 || (offset + len) > bo->base.size)
> > > > > > > > > > -		return -EIO;
> > > > > > > > > > -	ret = ttm_bo_reserve(bo, true, false, NULL);
> > > > > > > > > > -	if (ret)
> > > > > > > > > > -		return ret;
> > > > > > > > > > -
> > > > > > > > > > -	switch (bo->resource->mem_type) {
> > > > > > > > > > -	case TTM_PL_SYSTEM:
> > > > > > > > > > -		fallthrough;
> > > > > > > > > > -	case TTM_PL_TT:
> > > > > > > > > > -		ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write);
> > > > > > > > > > -		break;
> > > > > > > > > > -	default:
> > > > > > > > > > -		if (bo->bdev->funcs->access_memory)
> > > > > > > > > > -			ret = bo->bdev->funcs->access_memory(
> > > > > > > > > > -				bo, offset, buf, len, write);
> > > > > > > > > > -		else
> > > > > > > > > > -			ret = -EIO;
> > > > > > > > > > -	}
> > > > > > > > > > -
> > > > > > > > > > -	ttm_bo_unreserve(bo);
> > > > > > > > > > -
> > > > > > > > > > -	return ret;
> > > > > > > > > > +	return ttm_bo_access(bo, offset, buf, len, write);
> > > > > > > > > >      }
> > > > > > > > > >      EXPORT_SYMBOL(ttm_bo_vm_access);
> > > > > > > > > > diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h
> > > > > > > > > > index 5804408815be..8ea11cd8df39 100644
> > > > > > > > > > --- a/include/drm/ttm/ttm_bo.h
> > > > > > > > > > +++ b/include/drm/ttm/ttm_bo.h
> > > > > > > > > > @@ -421,6 +421,8 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo);
> > > > > > > > > >      int ttm_bo_evict_first(struct ttm_device *bdev,
> > > > > > > > > >      		       struct ttm_resource_manager *man,
> > > > > > > > > >      		       struct ttm_operation_ctx *ctx);
> > > > > > > > > > +int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset,
> > > > > > > > > > +		  void *buf, int len, int write);
> > > > > > > > > >      vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
> > > > > > > > > >      			     struct vm_fault *vmf);
> > > > > > > > > >      vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
> > > > > > > > > > -- 
> > > > > > > > > > 2.34.1
> > > > > > > > > > 

  reply	other threads:[~2024-11-06 16:59 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-31 18:10 [PATCH v6 0/8] Fix non-contiguous VRAM BO access in Xe Matthew Brost
2024-10-31 18:10 ` [PATCH v6 1/8] drm/xe: Add xe_bo_vm_access Matthew Brost
2024-10-31 18:10 ` [PATCH v6 2/8] drm/ttm: Add ttm_bo_access Matthew Brost
2024-10-31 23:43   ` Matthew Brost
2024-11-04 17:34     ` Rodrigo Vivi
2024-11-04 19:28       ` Christian König
2024-11-04 21:49         ` Matthew Brost
2024-11-05  7:41           ` Christian König
2024-11-05 18:35             ` Matthew Brost
2024-11-06  9:48               ` Christian König
2024-11-06 15:25                 ` Matthew Brost
2024-11-06 15:44                   ` Christian König
2024-11-06 17:00                     ` Matthew Brost [this message]
2024-11-07  9:44                       ` Christian König
2024-11-11  8:00                         ` Joonas Lahtinen
2024-11-11 10:10                           ` Simona Vetter
2024-11-11 11:34                             ` Christian König
2024-11-11 14:00                               ` Joonas Lahtinen
2024-11-11 15:54                                 ` Christian König
2024-11-11 22:45                                   ` Matthew Brost
2024-11-12  9:23                                     ` Christian König
2024-11-12 13:41                                       ` Joonas Lahtinen
2024-11-12 16:22                                         ` Thomas Hellström
2024-11-12 16:25                                           ` Christian König
2024-11-12 16:33                                             ` Thomas Hellström
2024-11-13  8:37                                               ` Christian König
2024-11-13 10:44                                                 ` Thomas Hellström
2024-11-13 11:42                                                   ` Christian König
2024-11-15 18:27                                                     ` Matthew Brost
2024-11-25 15:29                                                       ` Matthew Brost
2024-11-25 16:19                                                         ` Christian König
2024-11-25 17:27                                                           ` Matthew Brost
2024-11-26  8:19                                                             ` Christian König
2024-11-26 17:49                                                               ` Matthew Brost
2024-11-27 13:21                                                                 ` Christian König
2024-11-12  8:28                                 ` Simona Vetter
2024-11-12  8:58                                   ` Christian König
2024-11-12 13:30                                     ` Joonas Lahtinen
2024-11-11 11:27                           ` Christian König
2024-11-04 19:47     ` Christian König
2024-11-04 21:30       ` Matthew Brost
2024-11-04 22:26         ` Rodrigo Vivi
2024-10-31 18:10 ` [PATCH v6 3/8] drm/xe: Add xe_ttm_access_memory Matthew Brost
2024-10-31 18:10 ` [PATCH v6 4/8] drm/xe: Take PM ref in delayed snapshot capture worker Matthew Brost
2024-10-31 18:10 ` [PATCH v6 5/8] drm/xe/display: Update intel_bo_read_from_page to use ttm_bo_access Matthew Brost
2024-10-31 18:10 ` [PATCH v6 6/8] drm/xe: Use ttm_bo_access in xe_vm_snapshot_capture_delayed Matthew Brost
2024-10-31 18:10 ` [PATCH v6 7/8] drm/xe: Set XE_BO_FLAG_PINNED in migrate selftest BOs Matthew Brost
2024-10-31 18:10 ` [PATCH v6 8/8] drm/xe: Only allow contiguous BOs to use xe_bo_vmap Matthew Brost
2024-10-31 18:15 ` ✓ CI.Patch_applied: success for Fix non-contiguous VRAM BO access in Xe (rev6) Patchwork
2024-10-31 18:15 ` ✗ CI.checkpatch: warning " Patchwork
2024-10-31 18:17 ` ✓ CI.KUnit: success " Patchwork
2024-10-31 18:28 ` ✓ CI.Build: " Patchwork
2024-10-31 18:31 ` ✓ CI.Hooks: " Patchwork
2024-10-31 18:32 ` ✗ CI.checksparse: warning " Patchwork
2024-10-31 18:57 ` ✓ CI.BAT: success " Patchwork
2024-10-31 21:27 ` ✗ CI.FULL: failure " 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=ZyugmXt7v+JeKuN9@lstrano-desk.jf.intel.com \
    --to=matthew.brost@intel.com \
    --cc=christian.koenig@amd.com \
    --cc=ckoenig.leichtzumerken@gmail.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.auld@intel.com \
    --cc=ray.huang@amd.com \
    --cc=rodrigo.vivi@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