[v7,14/21] mm: introduce FOLL_PCI_P2PDMA to gate getting PCI P2PDMA pages

Commit Message

Logan Gunthorpe June 15, 2022, 4:12 p.m. UTC

GUP Callers that expect PCI P2PDMA pages can now set FOLL_PCI_P2PDMA to
allow obtaining P2PDMA pages. If GUP is called without the flag and a
P2PDMA page is found, it will return an error.

FOLL_PCI_P2PDMA cannot be set if FOLL_LONGTERM is set.

Signed-off-by: Logan Gunthorpe <[e-mail]>
---
 include/linux/mm.h |  1 +
 mm/gup.c           | 22 +++++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

Comments

Christoph Hellwig June 29, 2022, 6:45 a.m. UTC | #1

On Wed, Jun 15, 2022 at 10:12:26AM -0600, Logan Gunthorpe wrote:
> GUP Callers that expect PCI P2PDMA pages can now set FOLL_PCI_P2PDMA to
> allow obtaining P2PDMA pages. If GUP is called without the flag and a
> P2PDMA page is found, it will return an error.
> 
> FOLL_PCI_P2PDMA cannot be set if FOLL_LONGTERM is set.

Looks good:

Reviewed-by: Christoph Hellwig <[e-mail]>

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index bc8f326be0ce..0bcb54ea503c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2941,6 +2941,7 @@  struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 #define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
 #define FOLL_FAST_ONLY	0x80000	/* gup_fast: prevent fall-back to slow gup */
+#define FOLL_PCI_P2PDMA	0x100000 /* allow returning PCI P2PDMA pages */
 
 /*
  * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
diff --git a/mm/gup.c b/mm/gup.c
index 551264407624..f15f01d06a09 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -564,6 +564,12 @@  static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto out;
 	}
 
+	if (unlikely(!(flags & FOLL_PCI_P2PDMA) &&
+		     is_pci_p2pdma_page(page))) {
+		page = ERR_PTR(-EREMOTEIO);
+		goto out;
+	}
+
 	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
 		       !PageAnonExclusive(page), page);
 
@@ -994,6 +1000,9 @@  static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
 		return -EOPNOTSUPP;
 
+	if ((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))
+		return -EOPNOTSUPP;
+
 	if (vma_is_secretmem(vma))
 		return -EFAULT;
 
@@ -2289,6 +2298,10 @@  static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
+		if (unlikely(!(flags & FOLL_PCI_P2PDMA) &&
+			     is_pci_p2pdma_page(page)))
+			goto pte_unmap;
+
 		folio = try_grab_folio(page, 1, flags);
 		if (!folio)
 			goto pte_unmap;
@@ -2368,6 +2381,12 @@  static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 			undo_dev_pagemap(nr, nr_start, flags, pages);
 			break;
 		}
+
+		if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) {
+			undo_dev_pagemap(nr, nr_start, flags, pages);
+			break;
+		}
+
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		if (unlikely(!try_grab_page(page, flags))) {
@@ -2856,7 +2875,8 @@  static int internal_get_user_pages_fast(unsigned long start,
 
 	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
 				       FOLL_FORCE | FOLL_PIN | FOLL_GET |
-				       FOLL_FAST_ONLY | FOLL_NOFAULT)))
+				       FOLL_FAST_ONLY | FOLL_NOFAULT |
+				       FOLL_PCI_P2PDMA)))
 		return -EINVAL;
 
 	if (gup_flags & FOLL_PIN)