BPF Archive on lore.kernel.org
 help / color / Atom feed
From: John Hubbard <jhubbard@nvidia.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Al Viro" <viro@zeniv.linux.org.uk>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Dan Williams" <dan.j.williams@intel.com>,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Dave Chinner" <david@fromorbit.com>,
	"David Airlie" <airlied@linux.ie>,
	"David S . Miller" <davem@davemloft.net>,
	"Ira Weiny" <ira.weiny@intel.com>, "Jan Kara" <jack@suse.cz>,
	"Jason Gunthorpe" <jgg@ziepe.ca>, "Jens Axboe" <axboe@kernel.dk>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Mauro Carvalho Chehab" <mchehab@kernel.org>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Michal Hocko" <mhocko@suse.com>,
	"Mike Kravetz" <mike.kravetz@oracle.com>,
	"Paul Mackerras" <paulus@samba.org>,
	"Shuah Khan" <shuah@kernel.org>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	bpf@vger.kernel.org, dri-devel@lists.freedesktop.org,
	kvm@vger.kernel.org, linux-block@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, linux-media@vger.kernel.org,
	linux-rdma@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	netdev@vger.kernel.org, linux-mm@kvack.org,
	LKML <linux-kernel@vger.kernel.org>,
	"John Hubbard" <jhubbard@nvidia.com>,
	"Jason Gunthorpe" <jgg@mellanox.com>
Subject: [PATCH v7 09/24] vfio, mm: fix get_user_pages_remote() and FOLL_LONGTERM
Date: Wed, 20 Nov 2019 23:13:39 -0800
Message-ID: <20191121071354.456618-10-jhubbard@nvidia.com> (raw)
In-Reply-To: <20191121071354.456618-1-jhubbard@nvidia.com>

As it says in the updated comment in gup.c: current FOLL_LONGTERM
behavior is incompatible with FAULT_FLAG_ALLOW_RETRY because of the
FS DAX check requirement on vmas.

However, the corresponding restriction in get_user_pages_remote() was
slightly stricter than is actually required: it forbade all
FOLL_LONGTERM callers, but we can actually allow FOLL_LONGTERM callers
that do not set the "locked" arg.

Update the code and comments accordingly, and update the VFIO caller
to take advantage of this, fixing a bug as a result: the VFIO caller
is logically a FOLL_LONGTERM user.

Also, remove an unnessary pair of calls that were releasing and
reacquiring the mmap_sem. There is no need to avoid holding mmap_sem
just in order to call page_to_pfn().

Also, move the DAX check ("if a VMA is DAX, don't allow long term
pinning") from the VFIO call site, all the way into the internals
of get_user_pages_remote() and __gup_longterm_locked(). That is:
get_user_pages_remote() calls __gup_longterm_locked(), which in turn
calls check_dax_vmas(). It's lightly explained in the comments as well.

Thanks to Jason Gunthorpe for pointing out a clean way to fix this,
and to Dan Williams for helping clarify the DAX refactoring.

Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/vfio/vfio_iommu_type1.c | 30 +++++-------------------------
 mm/gup.c                        | 27 ++++++++++++++++++++++-----
 2 files changed, 27 insertions(+), 30 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index d864277ea16f..c7a111ad9975 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -340,7 +340,6 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 {
 	struct page *page[1];
 	struct vm_area_struct *vma;
-	struct vm_area_struct *vmas[1];
 	unsigned int flags = 0;
 	int ret;
 
@@ -348,33 +347,14 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		flags |= FOLL_WRITE;
 
 	down_read(&mm->mmap_sem);
-	if (mm == current->mm) {
-		ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
-				     vmas);
-	} else {
-		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
-					    vmas, NULL);
-		/*
-		 * The lifetime of a vaddr_get_pfn() page pin is
-		 * userspace-controlled. In the fs-dax case this could
-		 * lead to indefinite stalls in filesystem operations.
-		 * Disallow attempts to pin fs-dax pages via this
-		 * interface.
-		 */
-		if (ret > 0 && vma_is_fsdax(vmas[0])) {
-			ret = -EOPNOTSUPP;
-			put_page(page[0]);
-		}
-	}
-	up_read(&mm->mmap_sem);
-
+	ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+				    page, NULL, NULL);
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
-		return 0;
+		ret = 0;
+		goto done;
 	}
 
-	down_read(&mm->mmap_sem);
-
 	vaddr = untagged_addr(vaddr);
 
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
@@ -384,7 +364,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		if (is_invalid_reserved_pfn(*pfn))
 			ret = 0;
 	}
-
+done:
 	up_read(&mm->mmap_sem);
 	return ret;
 }
diff --git a/mm/gup.c b/mm/gup.c
index 14fcdc502166..cce2c9676853 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,6 +29,13 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
+						  struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long nr_pages,
+						  struct page **pages,
+						  struct vm_area_struct **vmas,
+						  unsigned int flags);
 /*
  * Return the compound head page with ref appropriately incremented,
  * or NULL if that failed.
@@ -1167,13 +1174,23 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 		struct vm_area_struct **vmas, int *locked)
 {
 	/*
-	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+	 * Parts of FOLL_LONGTERM behavior are incompatible with
 	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas.  As there are no users of this flag in this call we simply
-	 * disallow this option for now.
+	 * vmas. However, this only comes up if locked is set, and there are
+	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
+	 * allow what we can.
 	 */
-	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
-		return -EINVAL;
+	if (gup_flags & FOLL_LONGTERM) {
+		if (WARN_ON_ONCE(locked))
+			return -EINVAL;
+		/*
+		 * This will check the vmas (even if our vmas arg is NULL)
+		 * and return -ENOTSUPP if DAX isn't allowed in this case:
+		 */
+		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+					     vmas, gup_flags | FOLL_TOUCH |
+					     FOLL_REMOTE);
+	}
 
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
 				       locked,
-- 
2.24.0


  parent reply index

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-21  7:13 [PATCH v7 00/24] mm/gup: track dma-pinned pages: FOLL_PIN John Hubbard
2019-11-21  7:13 ` [PATCH v7 01/24] mm/gup: pass flags arg to __gup_device_* functions John Hubbard
2019-11-21  8:06   ` Christoph Hellwig
2019-11-21  8:25     ` John Hubbard
2019-11-21  7:13 ` [PATCH v7 02/24] mm/gup: factor out duplicate code from four routines John Hubbard
2019-11-21  8:03   ` Christoph Hellwig
2019-11-21  8:29     ` John Hubbard
2019-11-21  9:49       ` Jan Kara
2019-11-21 21:47         ` John Hubbard
2019-11-21  9:54       ` Jan Kara
2019-11-22  2:54         ` John Hubbard
2019-11-22 11:15           ` Jan Kara
2019-11-21  7:13 ` [PATCH v7 03/24] mm/gup: move try_get_compound_head() to top, fix minor issues John Hubbard
2019-11-21  8:07   ` Christoph Hellwig
2019-11-21  7:13 ` [PATCH v7 04/24] mm: Cleanup __put_devmap_managed_page() vs ->page_free() John Hubbard
2019-11-21  8:04   ` Christoph Hellwig
2019-11-21  7:13 ` [PATCH v7 05/24] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages John Hubbard
2019-11-21  8:05   ` Christoph Hellwig
2019-11-21  8:54     ` John Hubbard
2019-11-21 16:59       ` Dan Williams
2019-11-21 22:22         ` John Hubbard
2019-11-21  7:13 ` [PATCH v7 06/24] goldish_pipe: rename local pin_user_pages() routine John Hubbard
2019-11-21  8:08   ` Christoph Hellwig
2019-11-21  8:36     ` John Hubbard
2019-11-21  7:13 ` [PATCH v7 07/24] IB/umem: use get_user_pages_fast() to pin DMA pages John Hubbard
2019-11-21  8:07   ` Christoph Hellwig
2019-11-21 14:36     ` Jason Gunthorpe
2019-11-24  6:14       ` John Hubbard
2019-11-24 10:07       ` Leon Romanovsky
2019-11-25  0:05         ` John Hubbard
2019-11-25  0:53           ` Jason Gunthorpe
2019-11-21  7:13 ` [PATCH v7 08/24] media/v4l2-core: set pages dirty upon releasing DMA buffers John Hubbard
2019-11-21  8:09   ` Christoph Hellwig
2019-11-21  7:13 ` John Hubbard [this message]
2019-11-21  8:10   ` [PATCH v7 09/24] vfio, mm: fix get_user_pages_remote() and FOLL_LONGTERM Christoph Hellwig
2019-11-21  8:48     ` John Hubbard
2019-11-21 21:35   ` Alex Williamson
2019-11-21 21:49     ` John Hubbard
2019-11-21  7:13 ` [PATCH v7 10/24] mm/gup: introduce pin_user_pages*() and FOLL_PIN John Hubbard
2019-11-21  7:13 ` [PATCH v7 11/24] goldish_pipe: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-21  7:13 ` [PATCH v7 12/24] IB/{core,hw,umem}: set FOLL_PIN via pin_user_pages*(), fix up ODP John Hubbard
2019-11-21  7:13 ` [PATCH v7 13/24] mm/process_vm_access: set FOLL_PIN via pin_user_pages_remote() John Hubbard
2019-11-21  7:13 ` [PATCH v7 14/24] drm/via: set FOLL_PIN via pin_user_pages_fast() John Hubbard
2019-11-21  7:13 ` [PATCH v7 15/24] fs/io_uring: set FOLL_PIN via pin_user_pages() John Hubbard
2019-11-21  7:13 ` [PATCH v7 16/24] net/xdp: " John Hubbard
2019-11-21  7:13 ` [PATCH v7 17/24] mm/gup: track FOLL_PIN pages John Hubbard
2019-11-21  9:39   ` Jan Kara
2019-11-30 18:59   ` kbuild test robot
2019-11-21  7:13 ` [PATCH v7 18/24] media/v4l2-core: pin_user_pages (FOLL_PIN) and put_user_page() conversion John Hubbard
2019-11-21  7:13 ` [PATCH v7 19/24] vfio, mm: " John Hubbard
2019-11-21  7:13 ` [PATCH v7 20/24] powerpc: book3s64: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-21  7:13 ` [PATCH v7 21/24] mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1" John Hubbard
2019-11-21  7:13 ` [PATCH v7 22/24] mm/gup_benchmark: support pin_user_pages() and related calls John Hubbard
2019-11-21  7:13 ` [PATCH v7 23/24] selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage John Hubbard
2019-11-21  7:13 ` [PATCH v7 24/24] mm, tree-wide: rename put_user_page*() to unpin_user_page*() John Hubbard

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191121071354.456618-10-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=airlied@linux.ie \
    --cc=akpm@linux-foundation.org \
    --cc=alex.williamson@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=benh@kernel.crashing.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=daniel@ffwll.ch \
    --cc=davem@davemloft.net \
    --cc=david@fromorbit.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@infradead.org \
    --cc=ira.weiny@intel.com \
    --cc=jack@suse.cz \
    --cc=jgg@mellanox.com \
    --cc=jgg@ziepe.ca \
    --cc=jglisse@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=magnus.karlsson@intel.com \
    --cc=mchehab@kernel.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=mpe@ellerman.id.au \
    --cc=netdev@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=shuah@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git