From: "Christian König" <christian.koenig@amd.com> To: Jason Gunthorpe <jgg@mellanox.com>, Dave Airlie <airlied@gmail.com>, Christoph Hellwig <hch@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org>, Daniel Vetter <daniel.vetter@ffwll.ch>, dri-devel <dri-devel@lists.freedesktop.org>, LKML <linux-kernel@vger.kernel.org>, Logan Gunthorpe <logang@deltatee.com> Subject: Re: [git pull] drm for 5.8-rc1 Date: Thu, 4 Jun 2020 10:10:21 +0200 [thread overview] Message-ID: <1d1ad025-e215-da23-5282-bbaf154fa979@amd.com> (raw) In-Reply-To: <20200603201337.GA225528@ziepe.ca> Am 03.06.20 um 22:13 schrieb Jason Gunthorpe: > On Tue, Jun 02, 2020 at 04:06:32PM +1000, Dave Airlie wrote: >> Hi Linus, >> >> This is the main drm pull request for 5.8-rc1. >> >> Highlights: >> Core DRM had a lot of refactoring around managed drm resources to make >> drivers simpler. >> Intel Tigerlake support is on by default >> amdgpu now support p2p PCI buffer sharing and encrypted GPU memory > Christoph Hellwig basically NAK'd this approach, why is it getting > merged all of a sudden?? Dave and Daniel explicitly said they want to have this and it is ok as long as I open code it in the driver and keep it AMD internal. We have that in discussion for years now and constructing/using the sg table is actually only the very minor piece of it. On the other hand there is a lot of work underway to get rid of abusing the sg tables as well. > > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.kernel.org%2Fintel-gfx%2F20200311152838.GA24280%40infradead.org%2F&data=02%7C01%7Cchristian.koenig%40amd.com%7C55b238b9104d4a8d4feb08d807faa11c%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637268120315706063&sdata=AgVJ45%2Ft%2FVYkyIGIGgMrop69XLQReLDpF0ahL5rjEjo%3D&reserved=0 > > Are we now OK with this same approach open coded in a driver? Intel is apparently doing this as well for years, see the i915 driver internals. > This wasn't Cc'd to the usual people doing work in this PCI P2P area?? I certainly prefer a common framework for this, but when my upstream maintainer says he wants to take this who am I to object? Christian. > > See > > commit f44ffd677fb3562ac0a1ff9c8ae52672be741f00 > Author: Christian König <christian.koenig@amd.com> > Date: Fri Mar 23 16:56:37 2018 +0100 > > drm/amdgpu: add support for exporting VRAM using DMA-buf v3 > > We should be able to do this now after checking all the prerequisites. > > v2: fix entrie count in the sgt > v3: manually construct the sg > > Signed-off-by: Christian König <christian.koenig@amd.com> > Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> > Acked-by: Sumit Semwal <sumit.semwal@linaro.org> > Link: https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpatchwork.freedesktop.org%2Fpatch%2F359295&data=02%7C01%7Cchristian.koenig%40amd.com%7C55b238b9104d4a8d4feb08d807faa11c%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637268120315706063&sdata=YzNvxBVOf5hcUm5KjOzzV%2FcHG5jdGEYmrI76PQN9v3U%3D&reserved=0 > > [..] > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c > index 82a3299e53c042..128a667ed8fa0d 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c > @@ -22,6 +22,7 @@ > * Authors: Christian König > */ > > +#include <linux/dma-mapping.h> > #include "amdgpu.h" > #include "amdgpu_vm.h" > #include "amdgpu_atomfirmware.h" > @@ -458,6 +459,104 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man, > mem->mm_node = NULL; > } > > +/** > + * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table > + * > + * @adev: amdgpu device pointer > + * @mem: TTM memory object > + * @dev: the other device > + * @dir: dma direction > + * @sgt: resulting sg table > + * > + * Allocate and fill a sg table from a VRAM allocation. > + */ > +int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, > + struct ttm_mem_reg *mem, > + struct device *dev, > + enum dma_data_direction dir, > + struct sg_table **sgt) > +{ > + struct drm_mm_node *node; > + struct scatterlist *sg; > + int num_entries = 0; > + unsigned int pages; > + int i, r; > + > + *sgt = kmalloc(sizeof(*sg), GFP_KERNEL); > + if (!*sgt) > + return -ENOMEM; > + > + for (pages = mem->num_pages, node = mem->mm_node; > + pages; pages -= node->size, ++node) > + ++num_entries; > + > + r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL); > + if (r) > + goto error_free; > + > + for_each_sg((*sgt)->sgl, sg, num_entries, i) > + sg->length = 0; > + > + node = mem->mm_node; > + for_each_sg((*sgt)->sgl, sg, num_entries, i) { > + phys_addr_t phys = (node->start << PAGE_SHIFT) + > + adev->gmc.aper_base; > + size_t size = node->size << PAGE_SHIFT; > + dma_addr_t addr; > + > + ++node; > + addr = dma_map_resource(dev, phys, size, dir, > + DMA_ATTR_SKIP_CPU_SYNC); > + r = dma_mapping_error(dev, addr); > + if (r) > + goto error_unmap; > + > + sg_set_page(sg, NULL, size, 0); > + sg_dma_address(sg) = addr; > + sg_dma_len(sg) = size; > ^^^^^^^^^^^^^^ > > Jason
WARNING: multiple messages have this Message-ID (diff)
From: "Christian König" <christian.koenig@amd.com> To: Jason Gunthorpe <jgg@mellanox.com>, Dave Airlie <airlied@gmail.com>, Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>, Logan Gunthorpe <logang@deltatee.com>, Linus Torvalds <torvalds@linux-foundation.org>, LKML <linux-kernel@vger.kernel.org>, dri-devel <dri-devel@lists.freedesktop.org> Subject: Re: [git pull] drm for 5.8-rc1 Date: Thu, 4 Jun 2020 10:10:21 +0200 [thread overview] Message-ID: <1d1ad025-e215-da23-5282-bbaf154fa979@amd.com> (raw) In-Reply-To: <20200603201337.GA225528@ziepe.ca> Am 03.06.20 um 22:13 schrieb Jason Gunthorpe: > On Tue, Jun 02, 2020 at 04:06:32PM +1000, Dave Airlie wrote: >> Hi Linus, >> >> This is the main drm pull request for 5.8-rc1. >> >> Highlights: >> Core DRM had a lot of refactoring around managed drm resources to make >> drivers simpler. >> Intel Tigerlake support is on by default >> amdgpu now support p2p PCI buffer sharing and encrypted GPU memory > Christoph Hellwig basically NAK'd this approach, why is it getting > merged all of a sudden?? Dave and Daniel explicitly said they want to have this and it is ok as long as I open code it in the driver and keep it AMD internal. We have that in discussion for years now and constructing/using the sg table is actually only the very minor piece of it. On the other hand there is a lot of work underway to get rid of abusing the sg tables as well. > > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.kernel.org%2Fintel-gfx%2F20200311152838.GA24280%40infradead.org%2F&data=02%7C01%7Cchristian.koenig%40amd.com%7C55b238b9104d4a8d4feb08d807faa11c%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637268120315706063&sdata=AgVJ45%2Ft%2FVYkyIGIGgMrop69XLQReLDpF0ahL5rjEjo%3D&reserved=0 > > Are we now OK with this same approach open coded in a driver? Intel is apparently doing this as well for years, see the i915 driver internals. > This wasn't Cc'd to the usual people doing work in this PCI P2P area?? I certainly prefer a common framework for this, but when my upstream maintainer says he wants to take this who am I to object? Christian. > > See > > commit f44ffd677fb3562ac0a1ff9c8ae52672be741f00 > Author: Christian König <christian.koenig@amd.com> > Date: Fri Mar 23 16:56:37 2018 +0100 > > drm/amdgpu: add support for exporting VRAM using DMA-buf v3 > > We should be able to do this now after checking all the prerequisites. > > v2: fix entrie count in the sgt > v3: manually construct the sg > > Signed-off-by: Christian König <christian.koenig@amd.com> > Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> > Acked-by: Sumit Semwal <sumit.semwal@linaro.org> > Link: https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpatchwork.freedesktop.org%2Fpatch%2F359295&data=02%7C01%7Cchristian.koenig%40amd.com%7C55b238b9104d4a8d4feb08d807faa11c%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637268120315706063&sdata=YzNvxBVOf5hcUm5KjOzzV%2FcHG5jdGEYmrI76PQN9v3U%3D&reserved=0 > > [..] > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c > index 82a3299e53c042..128a667ed8fa0d 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c > @@ -22,6 +22,7 @@ > * Authors: Christian König > */ > > +#include <linux/dma-mapping.h> > #include "amdgpu.h" > #include "amdgpu_vm.h" > #include "amdgpu_atomfirmware.h" > @@ -458,6 +459,104 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man, > mem->mm_node = NULL; > } > > +/** > + * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table > + * > + * @adev: amdgpu device pointer > + * @mem: TTM memory object > + * @dev: the other device > + * @dir: dma direction > + * @sgt: resulting sg table > + * > + * Allocate and fill a sg table from a VRAM allocation. > + */ > +int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, > + struct ttm_mem_reg *mem, > + struct device *dev, > + enum dma_data_direction dir, > + struct sg_table **sgt) > +{ > + struct drm_mm_node *node; > + struct scatterlist *sg; > + int num_entries = 0; > + unsigned int pages; > + int i, r; > + > + *sgt = kmalloc(sizeof(*sg), GFP_KERNEL); > + if (!*sgt) > + return -ENOMEM; > + > + for (pages = mem->num_pages, node = mem->mm_node; > + pages; pages -= node->size, ++node) > + ++num_entries; > + > + r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL); > + if (r) > + goto error_free; > + > + for_each_sg((*sgt)->sgl, sg, num_entries, i) > + sg->length = 0; > + > + node = mem->mm_node; > + for_each_sg((*sgt)->sgl, sg, num_entries, i) { > + phys_addr_t phys = (node->start << PAGE_SHIFT) + > + adev->gmc.aper_base; > + size_t size = node->size << PAGE_SHIFT; > + dma_addr_t addr; > + > + ++node; > + addr = dma_map_resource(dev, phys, size, dir, > + DMA_ATTR_SKIP_CPU_SYNC); > + r = dma_mapping_error(dev, addr); > + if (r) > + goto error_unmap; > + > + sg_set_page(sg, NULL, size, 0); > + sg_dma_address(sg) = addr; > + sg_dma_len(sg) = size; > ^^^^^^^^^^^^^^ > > Jason _______________________________________________ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2020-06-04 8:10 UTC|newest] Thread overview: 103+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-06-02 6:06 [git pull] drm for 5.8-rc1 Dave Airlie 2020-06-02 6:06 ` Dave Airlie 2020-06-02 21:21 ` Linus Torvalds 2020-06-02 21:21 ` Linus Torvalds 2020-06-02 21:22 ` Linus Torvalds 2020-06-02 21:22 ` Linus Torvalds 2020-06-02 21:56 ` Linus Torvalds 2020-06-02 21:56 ` Linus Torvalds 2020-06-03 7:18 ` Thomas Zimmermann 2020-06-03 7:18 ` Thomas Zimmermann 2020-06-03 7:43 ` Daniel Vetter 2020-06-03 7:43 ` Daniel Vetter 2020-06-02 22:14 ` Linus Torvalds 2020-06-02 22:14 ` Linus Torvalds 2020-06-02 23:03 ` Dave Airlie 2020-06-02 23:03 ` Dave Airlie 2020-06-02 22:20 ` pr-tracker-bot 2020-06-02 22:20 ` pr-tracker-bot 2020-06-03 20:13 ` Jason Gunthorpe 2020-06-03 20:13 ` Jason Gunthorpe 2020-06-04 8:10 ` Christian König [this message] 2020-06-04 8:10 ` Christian König 2020-06-04 8:13 ` Christoph Hellwig 2020-06-30 23:08 ` Kirill A. Shutemov 2020-06-30 23:08 ` Kirill A. Shutemov 2020-07-01 4:40 ` James Jones 2020-07-01 4:40 ` James Jones 2020-07-01 7:57 ` Kirill A. Shutemov 2020-07-01 7:57 ` Kirill A. Shutemov 2020-07-01 7:59 ` Kirill A. Shutemov 2020-07-01 7:59 ` Kirill A. Shutemov 2020-07-01 19:45 ` James Jones 2020-07-01 19:45 ` James Jones 2020-07-02 7:36 ` Daniel Vetter 2020-07-02 7:36 ` Daniel Vetter 2020-07-02 7:59 ` Pekka Paalanen 2020-07-02 7:59 ` Pekka Paalanen 2020-07-02 8:22 ` Daniel Stone 2020-07-02 8:22 ` Daniel Stone 2020-07-02 21:14 ` James Jones 2020-07-02 21:14 ` James Jones 2020-07-03 6:01 ` James Jones 2020-07-03 6:01 ` James Jones 2020-07-03 7:16 ` Daniel Vetter 2020-07-03 7:16 ` Daniel Vetter 2020-07-13 1:37 ` Dave Airlie 2020-07-14 14:31 ` James Jones 2020-08-04 8:58 ` Karol Herbst 2020-08-12 0:19 ` James Jones 2020-08-12 10:27 ` Karol Herbst 2020-08-12 10:43 ` Karol Herbst 2020-08-12 12:24 ` Karol Herbst 2020-08-12 12:37 ` Ilia Mirkin 2020-08-12 17:03 ` James Jones 2020-08-12 17:10 ` Karol Herbst 2020-08-12 17:19 ` James Jones 2020-08-12 17:40 ` Alyssa Rosenzweig 2020-08-12 18:24 ` James Jones 2020-08-12 18:51 ` Karol Herbst 2020-08-13 13:00 ` Karol Herbst 2020-08-13 15:39 ` Karol Herbst 2020-08-13 17:19 ` Karol Herbst 2020-08-13 17:45 ` James Jones 2020-08-13 17:48 ` Karol Herbst 2020-08-14 13:57 ` Thierry Reding 2020-08-14 13:59 ` Karol Herbst 2020-08-14 14:10 ` Thierry Reding 2020-08-14 14:05 ` Thierry Reding 2020-08-14 14:44 ` Karol Herbst 2020-08-14 15:34 ` Thierry Reding 2020-08-14 15:40 ` Karol Herbst 2020-08-14 16:06 ` Thierry Reding 2020-08-14 16:12 ` Karol Herbst 2020-08-14 16:22 ` Thierry Reding 2020-08-14 17:17 ` Daniel Stone 2020-08-14 17:25 ` Daniel Vetter 2020-08-18 14:37 ` Thierry Reding 2020-09-01 7:13 ` Daniel Vetter 2020-09-01 10:42 ` Daniel Stone 2020-09-01 10:59 ` Karol Herbst 2020-09-01 14:42 ` James Jones 2020-08-14 14:08 ` Thierry Reding 2020-08-14 14:45 ` Karol Herbst 2020-08-14 15:24 ` Thierry Reding 2020-08-14 15:43 ` Karol Herbst 2020-08-14 13:54 ` Thierry Reding 2020-08-14 13:40 ` Thierry Reding 2020-08-14 13:56 ` Karol Herbst 2020-08-12 15:05 ` Thierry Reding 2020-08-12 15:20 ` Karol Herbst 2020-08-12 15:49 ` Karol Herbst 2020-07-01 11:24 ` Karol Herbst 2020-07-01 11:24 ` Karol Herbst 2020-07-01 15:51 ` James Jones 2020-07-01 15:51 ` James Jones 2020-07-01 16:01 ` Daniel Vetter 2020-07-01 16:01 ` Daniel Vetter 2020-07-01 17:04 ` Karol Herbst 2020-07-01 17:04 ` Karol Herbst 2020-07-01 17:37 ` James Jones 2020-07-01 17:37 ` James Jones 2020-07-01 18:08 ` Karol Herbst 2020-07-01 18:08 ` Karol Herbst
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=1d1ad025-e215-da23-5282-bbaf154fa979@amd.com \ --to=christian.koenig@amd.com \ --cc=airlied@gmail.com \ --cc=daniel.vetter@ffwll.ch \ --cc=dri-devel@lists.freedesktop.org \ --cc=hch@infradead.org \ --cc=jgg@mellanox.com \ --cc=linux-kernel@vger.kernel.org \ --cc=logang@deltatee.com \ --cc=torvalds@linux-foundation.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
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.