On Wed, Feb 11, 2026 at 07:48:59PM +0100, Thomas Hellström wrote:
> On Wed, 2026-02-11 at 07:37 -0800, Matthew Brost wrote:
> > On Wed, Feb 11, 2026 at 12:34:12PM +0100, Thomas Hellström wrote:
> > > On Wed, 2026-02-04 at 20:19 -0800, Matthew Brost wrote:
> > > > The dma-map IOVA alloc, link, and sync APIs perform significantly
> > > > better
> > > > than dma-map / dma-unmap, as they avoid costly IOMMU
> > > > synchronizations.
> > > > This difference is especially noticeable when mapping a 2MB
> > > > region in
> > > > 4KB pages.
> > > >
> > > > Use the IOVA alloc, link, and sync APIs for DRM pagemap, which
> > > > create
> > > > DMA
> > > > mappings between the CPU and GPU for copying data.
> > > >
> > > > Signed-off-by: Matthew Brost <[email protected]>
> > > > ---
> > > > v4:
> > > > - Pack IOVA and drop dummy page (Jason)
> > > >
> > > > drivers/gpu/drm/drm_pagemap.c | 84
> > > > +++++++++++++++++++++++++++++----
> > > > --
> > > > 1 file changed, 70 insertions(+), 14 deletions(-)
> > > >
> > > > diff --git a/drivers/gpu/drm/drm_pagemap.c
> > > > b/drivers/gpu/drm/drm_pagemap.c
> > > > index 29677b19bb69..52a196bc8459 100644
> > > > --- a/drivers/gpu/drm/drm_pagemap.c
> > > > +++ b/drivers/gpu/drm/drm_pagemap.c
> > > > @@ -280,6 +280,20 @@ drm_pagemap_migrate_map_device_pages(struct
> > > > device *dev,
> > > > return 0;
> > > > }
> > > >
> > > > +/**
> > > > + * struct drm_pagemap_iova_state - DRM pagemap IOVA state
> > > > + *
> > >
> > > No newline
> > >
> >
> > +1
> >
> > > > + * @dma_state: DMA IOVA state.
> > > > + * @offset: Current offset in IOVA.
> > > > + *
> > > > + * This structure acts as an iterator for packing all IOVA
> > > > addresses
> > > > within a
> > > > + * contiguous range.
> > > > + */
> > > > +struct drm_pagemap_iova_state {
> > > > + struct dma_iova_state dma_state;
> > > > + unsigned long offset;
> > > > +};
> > > > +
> > > > /**
> > > > * drm_pagemap_migrate_map_system_pages() - Map system migration
> > > > pages for GPU SVM migration
> > > > * @dev: The device performing the migration.
> > > > @@ -287,6 +301,7 @@ drm_pagemap_migrate_map_device_pages(struct
> > > > device *dev,
> > > > * @migrate_pfn: Array of page frame numbers of system pages or
> > > > peer
> > > > pages to map.
> > > > * @npages: Number of system pages or peer pages to map.
> > > > * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
> > > > + * @state: DMA IOVA state for mapping.
> > > > *
> > > > * This function maps pages of memory for migration usage in GPU
> > > > SVM. It
> > > > * iterates over each page frame number provided in
> > > > @migrate_pfn,
> > > > maps the
> > > > @@ -300,9 +315,11 @@ drm_pagemap_migrate_map_system_pages(struct
> > > > device *dev,
> > > > struct drm_pagemap_addr
> > > > *pagemap_addr,
> > > > unsigned long *migrate_pfn,
> > > > unsigned long npages,
> > > > - enum dma_data_direction
> > > > dir)
> > > > + enum dma_data_direction
> > > > dir,
> > > > + struct
> > > > drm_pagemap_iova_state
> > > > *state)
> > > > {
> > > > unsigned long i;
> > > > + bool try_alloc = false;
> > > >
> > > > for (i = 0; i < npages;) {
> > > > struct page *page =
> > > > migrate_pfn_to_page(migrate_pfn[i]);
> > > > @@ -317,9 +334,31 @@ drm_pagemap_migrate_map_system_pages(struct
> > > > device *dev,
> > > > folio = page_folio(page);
> > > > order = folio_order(folio);
> > > >
> > > > - dma_addr = dma_map_page(dev, page, 0,
> > > > page_size(page), dir);
> > > > - if (dma_mapping_error(dev, dma_addr))
> > > > - return -EFAULT;
> > > > + if (!try_alloc) {
> > > > + dma_iova_try_alloc(dev, &state-
> > > > >dma_state,
> > > > + npages * PAGE_SIZE >=
> > > > + HPAGE_PMD_SIZE ?
> > > > + HPAGE_PMD_SIZE : 0,
> > > > + npages * PAGE_SIZE);
> > > > + try_alloc = true;
> > > > + }
> > >
> > > What happens if dma_iova_try_alloc() fails for all i < some value x
> > > and
> > > then suddenly succeeds for i == x? While the below code looks
> > > correct,
> >
> > We only try to alloc on the first valid page - 'i' may be any value
> > based on the first page found or we may never alloc if the number of
> > pages found == 0 (possible, hence why it is inside the loop). This
> > step
> > is done at most once. If the allocation fails, we use the map_page
> > path
> > for the remaining loop iterations.
> >
> > > I figure we'd allocate a too large IOVA region and possibly get the
> > > alignment wrong?
> >
> > The first and only IOVA allocation attempts an aligned allocation.
> > What
> > can happen is only a subset of the IOVA is used for the copy but we
> > pack
> > in the pages starting at IOVA[0] and end at IOVA[number valid pages -
> > 1].
> >
> > Matt
>
> So to be a little nicer on the IOVA allocator we could use the below?
>
> dma_iova_try_alloc(dev, &state->dma_state,
> (npages - i) * PAGE_SIZE >=
> HPAGE_PMD_SIZE ?
> HPAGE_PMD_SIZE : 0,
> (npages - i) * PAGE_SIZE);
>
Yes, we can do that. No reason to force alignment if our copy code isn't
going to try to use 2M GPU pages.
Matt
> Thanks,
> Thomas
>
> >
> > >
> > > Otherwise LGTM.
> > >
> > >
> > > > +
> > > > + if (dma_use_iova(&state->dma_state)) {
> > > > + int err = dma_iova_link(dev, &state-
> > > > > dma_state,
> > > > + page_to_phys(pag
> > > > e),
> > > > + state->offset,
> > > > page_size(page),
> > > > + dir, 0);
> > > > + if (err)
> > > > + return err;
> > > > +
> > > > + dma_addr = state->dma_state.addr +
> > > > state-
> > > > > offset;
> > > > + state->offset += page_size(page);
> > > > + } else {
> > > > + dma_addr = dma_map_page(dev, page, 0,
> > > > page_size(page),
> > > > + dir);
> > > > + if (dma_mapping_error(dev, dma_addr))
> > > > + return -EFAULT;
> > > > + }
> > > >
> > > > pagemap_addr[i] =
> > > > drm_pagemap_addr_encode(dma_addr,
> > > > @@ -330,6 +369,9 @@ drm_pagemap_migrate_map_system_pages(struct
> > > > device *dev,
> > > > i += NR_PAGES(order);
> > > > }
> > > >
> > > > + if (dma_use_iova(&state->dma_state))
> > > > + return dma_iova_sync(dev, &state->dma_state, 0,
> > > > state->offset);
> > > > +
> > > > return 0;
> > > > }
> > > >
> > > > @@ -341,6 +383,7 @@ drm_pagemap_migrate_map_system_pages(struct
> > > > device *dev,
> > > > * @pagemap_addr: Array of DMA information corresponding to
> > > > mapped
> > > > pages
> > > > * @npages: Number of pages to unmap
> > > > * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
> > > > + * @state: DMA IOVA state for mapping.
> > > > *
> > > > * This function unmaps previously mapped pages of memory for
> > > > GPU
> > > > Shared Virtual
> > > > * Memory (SVM). It iterates over each DMA address provided in
> > > > @dma_addr, checks
> > > > @@ -350,10 +393,17 @@ static void
> > > > drm_pagemap_migrate_unmap_pages(struct device *dev,
> > > > struct
> > > > drm_pagemap_addr
> > > > *pagemap_addr,
> > > > unsigned long
> > > > *migrate_pfn,
> > > > unsigned long
> > > > npages,
> > > > - enum
> > > > dma_data_direction
> > > > dir)
> > > > + enum
> > > > dma_data_direction
> > > > dir,
> > > > + struct
> > > > drm_pagemap_iova_state *state)
> > > > {
> > > > unsigned long i;
> > > >
> > > > + if (state && dma_use_iova(&state->dma_state)) {
> > > > + dma_iova_unlink(dev, &state->dma_state, 0,
> > > > state-
> > > > > offset, dir, 0);
> > > > + dma_iova_free(dev, &state->dma_state);
> > > > + return;
> > > > + }
> > > > +
> > > > for (i = 0; i < npages;) {
> > > > struct page *page =
> > > > migrate_pfn_to_page(migrate_pfn[i]);
> > > >
> > > > @@ -406,7 +456,7 @@ drm_pagemap_migrate_remote_to_local(struct
> > > > drm_pagemap_devmem *devmem,
> > > > devmem->pre_migrate_fence);
> > > > out:
> > > > drm_pagemap_migrate_unmap_pages(remote_device,
> > > > pagemap_addr,
> > > > local_pfns,
> > > > - npages,
> > > > DMA_FROM_DEVICE);
> > > > + npages, DMA_FROM_DEVICE,
> > > > NULL);
> > > > return err;
> > > > }
> > > >
> > > > @@ -416,11 +466,13 @@ drm_pagemap_migrate_sys_to_dev(struct
> > > > drm_pagemap_devmem *devmem,
> > > > struct page *local_pages[],
> > > > struct drm_pagemap_addr
> > > > pagemap_addr[],
> > > > unsigned long npages,
> > > > - const struct
> > > > drm_pagemap_devmem_ops
> > > > *ops)
> > > > + const struct
> > > > drm_pagemap_devmem_ops
> > > > *ops,
> > > > + struct drm_pagemap_iova_state
> > > > *state)
> > > > {
> > > > int err = drm_pagemap_migrate_map_system_pages(devmem-
> > > > >dev,
> > > >
> > > > pagemap_addr,
> > > > sys_pfns,
> > > > - npages,
> > > > DMA_TO_DEVICE);
> > > > + npages,
> > > > DMA_TO_DEVICE,
> > > > + state);
> > > >
> > > > if (err)
> > > > goto out;
> > > > @@ -429,7 +481,7 @@ drm_pagemap_migrate_sys_to_dev(struct
> > > > drm_pagemap_devmem *devmem,
> > > > devmem->pre_migrate_fence);
> > > > out:
> > > > drm_pagemap_migrate_unmap_pages(devmem->dev,
> > > > pagemap_addr,
> > > > sys_pfns, npages,
> > > > - DMA_TO_DEVICE);
> > > > + DMA_TO_DEVICE, state);
> > > > return err;
> > > > }
> > > >
> > > > @@ -457,6 +509,7 @@ static int drm_pagemap_migrate_range(struct
> > > > drm_pagemap_devmem *devmem,
> > > > const struct
> > > > migrate_range_loc
> > > > *cur,
> > > > const struct
> > > > drm_pagemap_migrate_details *mdetails)
> > > > {
> > > > + struct drm_pagemap_iova_state state = {};
> > > > int ret = 0;
> > > >
> > > > if (cur->start == 0)
> > > > @@ -484,7 +537,7 @@ static int drm_pagemap_migrate_range(struct
> > > > drm_pagemap_devmem *devmem,
> > > >
> > > > &pages[last-
> > > > > start],
> > > >
> > > > &pagemap_addr[last->start],
> > > > cur->start
> > > > -
> > > > last->start,
> > > > - last->ops);
> > > > + last->ops,
> > > > &state);
> > > >
> > > > out:
> > > > *last = *cur;
> > > > @@ -1001,6 +1054,7 @@ EXPORT_SYMBOL(drm_pagemap_put);
> > > > int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem
> > > > *devmem_allocation)
> > > > {
> > > > const struct drm_pagemap_devmem_ops *ops =
> > > > devmem_allocation->ops;
> > > > + struct drm_pagemap_iova_state state = {};
> > > > unsigned long npages, mpages = 0;
> > > > struct page **pages;
> > > > unsigned long *src, *dst;
> > > > @@ -1042,7 +1096,7 @@ int drm_pagemap_evict_to_ram(struct
> > > > drm_pagemap_devmem *devmem_allocation)
> > > > err =
> > > > drm_pagemap_migrate_map_system_pages(devmem_allocation->dev,
> > > > pagemap_addr,
> > > > dst, npages,
> > > > -
> > > > DMA_FROM_DEVICE);
> > > > +
> > > > DMA_FROM_DEVICE,
> > > > &state);
> > > > if (err)
> > > > goto err_finalize;
> > > >
> > > > @@ -1059,7 +1113,7 @@ int drm_pagemap_evict_to_ram(struct
> > > > drm_pagemap_devmem *devmem_allocation)
> > > > migrate_device_pages(src, dst, npages);
> > > > migrate_device_finalize(src, dst, npages);
> > > > drm_pagemap_migrate_unmap_pages(devmem_allocation->dev,
> > > > pagemap_addr, dst, npages,
> > > > - DMA_FROM_DEVICE);
> > > > + DMA_FROM_DEVICE,
> > > > &state);
> > > >
> > > > err_free:
> > > > kvfree(buf);
> > > > @@ -1103,6 +1157,7 @@ static int
> > > > __drm_pagemap_migrate_to_ram(struct
> > > > vm_area_struct *vas,
> > > > MIGRATE_VMA_SELECT_DEVICE_COHERENT,
> > > > .fault_page = page,
> > > > };
> > > > + struct drm_pagemap_iova_state state = {};
> > > > struct drm_pagemap_zdd *zdd;
> > > > const struct drm_pagemap_devmem_ops *ops;
> > > > struct device *dev = NULL;
> > > > @@ -1162,7 +1217,7 @@ static int
> > > > __drm_pagemap_migrate_to_ram(struct
> > > > vm_area_struct *vas,
> > > >
> > > > err = drm_pagemap_migrate_map_system_pages(dev,
> > > > pagemap_addr,
> > > > migrate.dst,
> > > > npages,
> > > > -
> > > > DMA_FROM_DEVICE);
> > > > +
> > > > DMA_FROM_DEVICE,
> > > > &state);
> > > > if (err)
> > > > goto err_finalize;
> > > >
> > > > @@ -1180,7 +1235,8 @@ static int
> > > > __drm_pagemap_migrate_to_ram(struct
> > > > vm_area_struct *vas,
> > > > migrate_vma_finalize(&migrate);
> > > > if (dev)
> > > > drm_pagemap_migrate_unmap_pages(dev,
> > > > pagemap_addr,
> > > > migrate.dst,
> > > > - npages,
> > > > DMA_FROM_DEVICE);
> > > > + npages,
> > > > DMA_FROM_DEVICE,
> > > > + &state);
> > > > err_free:
> > > > kvfree(buf);
> > > > err_out:
