[PATCH 5/9] mm, drm/ttm, drm/vmwgfx: Support huge TTM pagefaults

[Thomas Hellström (VMware)]

On 1/29/20 3:55 PM, Christian König wrote:
> Am 24.01.20 um 10:09 schrieb Thomas Hellström (VMware):
>> From: Thomas Hellstrom <thellstrom at vmware.com>
>>
>> Support huge (PMD-size and PUD-size) page-table entries by providing a
>> huge_fault() callback.
>> We still support private mappings and write-notify by splitting the huge
>> page-table entries on write-access.
>>
>> Note that for huge page-faults to occur, either the kernel needs to be
>> compiled with trans-huge-pages always enabled, or the kernel needs to be
>> compiled with trans-huge-pages enabled using madvise, and the user-space
>> app needs to call madvise() to enable trans-huge pages on a per-mapping
>> basis.
>>
>> Furthermore huge page-faults will not succeed unless buffer objects and
>> user-space addresses are aligned on huge page size boundaries.
>>
>> Cc: Andrew Morton <akpm at linux-foundation.org>
>> Cc: Michal Hocko <mhocko at suse.com>
>> Cc: "Matthew Wilcox (Oracle)" <willy at infradead.org>
>> Cc: "Kirill A. Shutemov" <kirill.shutemov at linux.intel.com>
>> Cc: Ralph Campbell <rcampbell at nvidia.com>
>> Cc: "Jérôme Glisse" <jglisse at redhat.com>
>> Cc: "Christian König" <christian.koenig at amd.com>
>> Cc: Dan Williams <dan.j.williams at intel.com>
>> Signed-off-by: Thomas Hellstrom <thellstrom at vmware.com>
>> Reviewed-by: Roland Scheidegger <sroland at vmware.com>
>> ---
>>   drivers/gpu/drm/ttm/ttm_bo_vm.c            | 145 ++++++++++++++++++++-
>>   drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c |   2 +-
>>   include/drm/ttm/ttm_bo_api.h               |   3 +-
>>   3 files changed, 145 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c 
>> b/drivers/gpu/drm/ttm/ttm_bo_vm.c
>> index 389128b8c4dd..49704261a00d 100644
>> --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
>> +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
>> @@ -156,6 +156,89 @@ vm_fault_t ttm_bo_vm_reserve(struct 
>> ttm_buffer_object *bo,
>>   }
>>   EXPORT_SYMBOL(ttm_bo_vm_reserve);
>>   +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
>> +/**
>> + * ttm_bo_vm_insert_huge - Insert a pfn for PUD or PMD faults
>> + * @vmf: Fault data
>> + * @bo: The buffer object
>> + * @page_offset: Page offset from bo start
>> + * @fault_page_size: The size of the fault in pages.
>> + * @pgprot: The page protections.
>> + * Does additional checking whether it's possible to insert a PUD or 
>> PMD
>> + * pfn and performs the insertion.
>> + *
>> + * Return: VM_FAULT_NOPAGE on successful insertion, 
>> VM_FAULT_FALLBACK if
>> + * a huge fault was not possible, and a VM_FAULT_ERROR code otherwise.
>> + */
>> +static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
>> +                    struct ttm_buffer_object *bo,
>> +                    pgoff_t page_offset,
>> +                    pgoff_t fault_page_size,
>> +                    pgprot_t pgprot)
>> +{
>> +    pgoff_t i;
>> +    vm_fault_t ret;
>> +    unsigned long pfn;
>> +    pfn_t pfnt;
>> +    struct ttm_tt *ttm = bo->ttm;
>> +    bool write = vmf->flags & FAULT_FLAG_WRITE;
>> +
>> +    /* Fault should not cross bo boundary. */
>> +    page_offset &= ~(fault_page_size - 1);
>> +    if (page_offset + fault_page_size > bo->num_pages)
>> +        goto out_fallback;
>> +
>> +    if (bo->mem.bus.is_iomem)
>> +        pfn = ttm_bo_io_mem_pfn(bo, page_offset);
>> +    else
>> +        pfn = page_to_pfn(ttm->pages[page_offset]);
>> +
>> +    /* pfn must be fault_page_size aligned. */
>> +    if ((pfn & (fault_page_size - 1)) != 0)
>> +        goto out_fallback;
>> +
>> +    /* Check that memory is contiguous. */
>> +    if (!bo->mem.bus.is_iomem)
>> +        for (i = 1; i < fault_page_size; ++i) {
>> +            if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i)
>> +                goto out_fallback;
>> +        }
>> +    /* IO mem without the io_mem_pfn callback is always contiguous. */
>> +    else if (bo->bdev->driver->io_mem_pfn)
>> +        for (i = 1; i < fault_page_size; ++i) {
>> +            if (ttm_bo_io_mem_pfn(bo, page_offset + i) != pfn + i)
>> +                goto out_fallback;
>> +        }
>
> Maybe add {} to the if to make clear where things start/end.
>
>> +
>> +    pfnt = __pfn_to_pfn_t(pfn, PFN_DEV);
>> +    if (fault_page_size == (HPAGE_PMD_SIZE >> PAGE_SHIFT))
>> +        ret = vmf_insert_pfn_pmd_prot(vmf, pfnt, pgprot, write);
>> +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
>> +    else if (fault_page_size == (HPAGE_PUD_SIZE >> PAGE_SHIFT))
>> +        ret = vmf_insert_pfn_pud_prot(vmf, pfnt, pgprot, write);
>> +#endif
>> +    else
>> +        WARN_ON_ONCE(ret = VM_FAULT_FALLBACK);
>> +
>> +    if (ret != VM_FAULT_NOPAGE)
>> +        goto out_fallback;
>> +
>> +    return VM_FAULT_NOPAGE;
>> +out_fallback:
>> +    count_vm_event(THP_FAULT_FALLBACK);
>> +    return VM_FAULT_FALLBACK;
>
> This doesn't seem to match the function documentation since we never 
> return ret here as far as I can see.
>
> Apart from those comments it looks like that should work,
> Christian.


Thanks for reviewing, Christian. I'll update the next version with your 
feedback.

/Thomas