Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Logan Gunthorpe <logang@deltatee.com>
To:     linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
        linux-block@vger.kernel.org, linux-pci@vger.kernel.org,
        linux-mm@kvack.org
Cc:     Christoph Hellwig <hch@lst.de>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Dan Williams <dan.j.williams@intel.com>,
        Jason Gunthorpe <jgg@ziepe.ca>,
        =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>,
        John Hubbard <jhubbard@nvidia.com>,
        Don Dutile <ddutile@redhat.com>,
        Matthew Wilcox <willy@infradead.org>,
        Daniel Vetter <daniel.vetter@ffwll.ch>,
        Minturn Dave B <dave.b.minturn@intel.com>,
        Jason Ekstrand <jason@jlekstrand.net>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Xiong Jianxin <jianxin.xiong@intel.com>,
        Bjorn Helgaas <helgaas@kernel.org>,
        Ira Weiny <ira.weiny@intel.com>,
        Robin Murphy <robin.murphy@arm.com>,
        Martin Oliveira <martin.oliveira@eideticom.com>,
        Chaitanya Kulkarni <ckulkarnilinux@gmail.com>,
        Ralph Campbell <rcampbell@nvidia.com>,
        Stephen Bates <sbates@raithlin.com>,
        Logan Gunthorpe <logang@deltatee.com>
Date:   Thu, 22 Sep 2022 10:39:19 -0600
Message-Id: <20220922163926.7077-2-logang@deltatee.com>
In-Reply-To: <20220922163926.7077-1-logang@deltatee.com>
References: <20220922163926.7077-1-logang@deltatee.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Subject: [PATCH v10 1/8] mm: introduce FOLL_PCI_P2PDMA to gate getting PCI P2PDMA pages
Precedence: bulk

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 <logang@deltatee.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
---
 include/linux/mm.h |  1 +
 mm/gup.c           | 22 +++++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 21f8b27bd9fd..3cea77c8a9ea 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2897,6 +2897,7 @@ 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 5abdaf487460..108848b67f6f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -601,6 +601,12 @@ 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);
 
@@ -1039,6 +1045,9 @@ 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;
 
@@ -2383,6 +2392,10 @@ 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;
@@ -2462,6 +2475,12 @@ 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))) {
@@ -2950,7 +2969,8 @@ 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)
-- 
2.30.2