Commit 211b9a39 authored by Loïc Molinari's avatar Loïc Molinari Committed by Boris Brezillon
Browse files

drm/shmem-helper: Map huge pages in fault handler 



Attempt a PMD sized PFN insertion into the VMA if the faulty address
of the fault handler is part of a huge page.

On builds with CONFIG_TRANSPARENT_HUGEPAGE enabled, if the mmap() user
address is PMD size aligned, if the GEM object is backed by shmem
buffers on mountpoints setting the 'huge=' option and if the shmem
backing store manages to allocate a huge folio, CPU mapping would then
benefit from significantly increased memcpy() performance. When these
conditions are met on a system with 2 MiB huge pages, an aligned copy
of 2 MiB would raise a single page fault instead of 4096.

v4:
- implement map_pages instead of huge_fault

v6:
- get rid of map_pages handler for now (keep it for another series
  along with arm64 contpte support)

v11:
- remove page fault validity check helper
- rename drm_gem_shmem_map_pmd() to drm_gem_shmem_try_map_pmd()
- add Boris R-b

v12:
- move up ret var decl in fault handler to minimize diff

Signed-off-by: default avatarLoïc Molinari <loic.molinari@collabora.com>
Reviewed-by: default avatarBoris Brezillon <boris.brezillon@collabora.com>
Link: https://patch.msgid.link/20251205182231.194072-3-loic.molinari@collabora.com


Signed-off-by: default avatarBoris Brezillon <boris.brezillon@collabora.com>
parent 9d2d4902

drivers/gpu/drm/drm_gem_shmem_helper.c

+31 −4
Original line number Diff line number Diff line
@@ -567,6 +567,26 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev, 
}

EXPORT_SYMBOL_GPL(drm_gem_shmem_dumb_create);



static bool drm_gem_shmem_try_map_pmd(struct vm_fault *vmf, unsigned long addr,

				      struct page *page)

{

#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP

	unsigned long pfn = page_to_pfn(page);

	unsigned long paddr = pfn << PAGE_SHIFT;

	bool aligned = (addr & ~PMD_MASK) == (paddr & ~PMD_MASK);



	if (aligned &&

	    pmd_none(*vmf->pmd) &&

	    folio_test_pmd_mappable(page_folio(page))) {

		pfn &= PMD_MASK >> PAGE_SHIFT;

		if (vmf_insert_pfn_pmd(vmf, pfn, false) == VM_FAULT_NOPAGE)

			return true;

	}

#endif



	return false;

}



static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf)

{

	struct vm_area_struct *vma = vmf->vma;
@@ -574,8 +594,9 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) 
	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);

	loff_t num_pages = obj->size >> PAGE_SHIFT;

	vm_fault_t ret;

	struct page *page;

	struct page **pages = shmem->pages;

	pgoff_t page_offset;

	unsigned long pfn;



	/* Offset to faulty address in the VMA. */

	page_offset = vmf->pgoff - vma->vm_pgoff;
@@ -586,12 +607,18 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) 
	    drm_WARN_ON_ONCE(obj->dev, !shmem->pages) ||

	    shmem->madv < 0) {

		ret = VM_FAULT_SIGBUS;

	} else {

		page = shmem->pages[page_offset];

		goto out;

	}



		ret = vmf_insert_pfn(vma, vmf->address, page_to_pfn(page));

	if (drm_gem_shmem_try_map_pmd(vmf, vmf->address, pages[page_offset])) {

		ret = VM_FAULT_NOPAGE;

		goto out;

	}



	pfn = page_to_pfn(pages[page_offset]);

	ret = vmf_insert_pfn(vma, vmf->address, pfn);



 out:

	dma_resv_unlock(shmem->base.resv);



	return ret;