lkml.org 
[lkml]   [2019]   [Apr]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [PATCH v2 11/11] mm/hmm: add an helper function that fault pages and map them to a device v2
On Mon, Mar 25, 2019 at 8:11 PM <jglisse@redhat.com> wrote:
>
> From: Jérôme Glisse <jglisse@redhat.com>
>
> This is a all in one helper that fault pages in a range and map them to
> a device so that every single device driver do not have to re-implement
> this common pattern.
>
> This is taken from ODP RDMA in preparation of ODP RDMA convertion. It
> will be use by nouveau and other drivers.
>
> Changes since v1:
> - improved commit message
>
> Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Ralph Campbell <rcampbell@nvidia.com>
> Cc: John Hubbard <jhubbard@nvidia.com>
> Cc: Dan Williams <dan.j.williams@intel.com>
> ---
> include/linux/hmm.h | 9 +++
> mm/hmm.c | 152 ++++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 161 insertions(+)
>
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index 5f9deaeb9d77..7aadf18b29cb 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -568,6 +568,15 @@ int hmm_range_register(struct hmm_range *range,
> void hmm_range_unregister(struct hmm_range *range);
> long hmm_range_snapshot(struct hmm_range *range);
> long hmm_range_fault(struct hmm_range *range, bool block);
> +long hmm_range_dma_map(struct hmm_range *range,
> + struct device *device,
> + dma_addr_t *daddrs,
> + bool block);
> +long hmm_range_dma_unmap(struct hmm_range *range,
> + struct vm_area_struct *vma,
> + struct device *device,
> + dma_addr_t *daddrs,
> + bool dirty);
>
> /*
> * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
> diff --git a/mm/hmm.c b/mm/hmm.c
> index ce33151c6832..fd143251b157 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -30,6 +30,7 @@
> #include <linux/hugetlb.h>
> #include <linux/memremap.h>
> #include <linux/jump_label.h>
> +#include <linux/dma-mapping.h>
> #include <linux/mmu_notifier.h>
> #include <linux/memory_hotplug.h>
>
> @@ -1163,6 +1164,157 @@ long hmm_range_fault(struct hmm_range *range, bool block)
> return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
> }
> EXPORT_SYMBOL(hmm_range_fault);
> +
> +/*

Adding extra * might be helpful here for documentation.

> + * hmm_range_dma_map() - hmm_range_fault() and dma map page all in one.
> + * @range: range being faulted
> + * @device: device against to dma map page to
> + * @daddrs: dma address of mapped pages
> + * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
> + * Returns: number of pages mapped on success, -EAGAIN if mmap_sem have been
> + * drop and you need to try again, some other error value otherwise
> + *
> + * Note same usage pattern as hmm_range_fault().
> + */
> +long hmm_range_dma_map(struct hmm_range *range,
> + struct device *device,
> + dma_addr_t *daddrs,
> + bool block)
> +{
> + unsigned long i, npages, mapped;
> + long ret;
> +
> + ret = hmm_range_fault(range, block);
> + if (ret <= 0)
> + return ret ? ret : -EBUSY;
> +
> + npages = (range->end - range->start) >> PAGE_SHIFT;
> + for (i = 0, mapped = 0; i < npages; ++i) {
> + enum dma_data_direction dir = DMA_FROM_DEVICE;
> + struct page *page;
> +
> + /*
> + * FIXME need to update DMA API to provide invalid DMA address
> + * value instead of a function to test dma address value. This
> + * would remove lot of dumb code duplicated accross many arch.
> + *
> + * For now setting it to 0 here is good enough as the pfns[]
> + * value is what is use to check what is valid and what isn't.
> + */
> + daddrs[i] = 0;
> +
> + page = hmm_pfn_to_page(range, range->pfns[i]);
> + if (page == NULL)
> + continue;
> +
> + /* Check if range is being invalidated */
> + if (!range->valid) {
> + ret = -EBUSY;
> + goto unmap;
> + }
> +
> + /* If it is read and write than map bi-directional. */
> + if (range->pfns[i] & range->values[HMM_PFN_WRITE])
> + dir = DMA_BIDIRECTIONAL;
> +
> + daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
> + if (dma_mapping_error(device, daddrs[i])) {
> + ret = -EFAULT;
> + goto unmap;
> + }
> +
> + mapped++;
> + }
> +
> + return mapped;
> +
> +unmap:
> + for (npages = i, i = 0; (i < npages) && mapped; ++i) {
> + enum dma_data_direction dir = DMA_FROM_DEVICE;
> + struct page *page;
> +
> + page = hmm_pfn_to_page(range, range->pfns[i]);
> + if (page == NULL)
> + continue;
> +
> + if (dma_mapping_error(device, daddrs[i]))
> + continue;
> +
> + /* If it is read and write than map bi-directional. */
> + if (range->pfns[i] & range->values[HMM_PFN_WRITE])
> + dir = DMA_BIDIRECTIONAL;
> +
> + dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
> + mapped--;
> + }
> +
> + return ret;
> +}
> +EXPORT_SYMBOL(hmm_range_dma_map);
> +
> +/*

Same here.

> + * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
> + * @range: range being unmapped
> + * @vma: the vma against which the range (optional)
> + * @device: device against which dma map was done
> + * @daddrs: dma address of mapped pages
> + * @dirty: dirty page if it had the write flag set
> + * Returns: number of page unmapped on success, -EINVAL otherwise
> + *
> + * Note that caller MUST abide by mmu notifier or use HMM mirror and abide
> + * to the sync_cpu_device_pagetables() callback so that it is safe here to
> + * call set_page_dirty(). Caller must also take appropriate locks to avoid
> + * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress.
> + */
> +long hmm_range_dma_unmap(struct hmm_range *range,
> + struct vm_area_struct *vma,
> + struct device *device,
> + dma_addr_t *daddrs,
> + bool dirty)
> +{
> + unsigned long i, npages;
> + long cpages = 0;
> +
> + /* Sanity check. */
> + if (range->end <= range->start)
> + return -EINVAL;
> + if (!daddrs)
> + return -EINVAL;
> + if (!range->pfns)
> + return -EINVAL;
> +
> + npages = (range->end - range->start) >> PAGE_SHIFT;
> + for (i = 0; i < npages; ++i) {
> + enum dma_data_direction dir = DMA_FROM_DEVICE;
> + struct page *page;
> +
> + page = hmm_pfn_to_page(range, range->pfns[i]);
> + if (page == NULL)
> + continue;
> +
> + /* If it is read and write than map bi-directional. */
> + if (range->pfns[i] & range->values[HMM_PFN_WRITE]) {
> + dir = DMA_BIDIRECTIONAL;
> +
> + /*
> + * See comments in function description on why it is
> + * safe here to call set_page_dirty()
> + */
> + if (dirty)
> + set_page_dirty(page);
> + }
> +
> + /* Unmap and clear pfns/dma address */
> + dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
> + range->pfns[i] = range->values[HMM_PFN_NONE];
> + /* FIXME see comments in hmm_vma_dma_map() */
> + daddrs[i] = 0;
> + cpages++;
> + }
> +
> + return cpages;
> +}
> +EXPORT_SYMBOL(hmm_range_dma_unmap);
> #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
>
>
> --
> 2.17.2
>

\
 
 \ /
  Last update: 2019-04-01 14:00    [W:0.088 / U:2.608 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site