diff mbox series

[v4,15/23] mm: introduce FOLL_PCI_P2PDMA to gate getting PCI P2PDMA pages

Message ID 20211117215410.3695-16-logang@deltatee.com (mailing list archive)
State New
Headers show
Series Userspace P2PDMA with O_DIRECT NVMe devices | expand

Commit Message

Logan Gunthorpe Nov. 17, 2021, 9:54 p.m. UTC
Callers that expect PCI P2PDMA pages can now set FOLL_PCI_P2PDMA to
allow obtaining P2PDMA pages. If a caller does not set this flag
and tries to map P2PDMA pages it will fail.

This is implemented by checking failing if PCI p2pdma pages are
found when FOLL_PCI_P2PDMA is set. This is only done if pte_devmap()
is set.

FOLL_PCI_P2PDMA cannot be set if FOLL_LONGTERM is set.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
---
 include/linux/mm.h |  1 +
 mm/gup.c           | 22 +++++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index a7e4a9e7d807..65cb27cebbab 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2971,6 +2971,7 @@  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 2c51e9748a6a..c31461c3d256 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -527,6 +527,12 @@  static struct page *follow_page_pte(struct vm_area_struct *vma,
 			page = pte_page(pte);
 		else
 			goto no_page;
+
+		if (unlikely(!(flags & FOLL_PCI_P2PDMA) &&
+			     is_pci_p2pdma_page(page))) {
+			page = ERR_PTR(-EREMOTEIO);
+			goto out;
+		}
 	} else if (unlikely(!page)) {
 		if (flags & FOLL_DUMP) {
 			/* Avoid special (like zero) pages in core dumps */
@@ -980,6 +986,9 @@  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;
 
@@ -2297,6 +2306,10 @@  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(pte_devmap(pte) && !(flags & FOLL_PCI_P2PDMA) &&
+			     is_pci_p2pdma_page(page)))
+			goto pte_unmap;
+
 		head = try_grab_compound_head(page, 1, flags);
 		if (!head)
 			goto pte_unmap;
@@ -2374,6 +2387,12 @@  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))) {
@@ -2842,7 +2861,8 @@  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)