Linux-mm Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "David Hildenbrand (Arm)" <david@kernel.org>
To: "Tal Zussman" <tz2294@columbia.edu>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Mike Rapoport" <rppt@kernel.org>, "Peter Xu" <peterx@redhat.com>,
	"James Houghton" <jthoughton@google.com>,
	"Andrea Arcangeli" <aarcange@redhat.com>,
	"Suren Baghdasaryan" <surenb@google.com>,
	"Balbir Singh" <balbirs@nvidia.com>,
	"Liam R. Howlett" <liam@infradead.org>,
	"Lorenzo Stoakes" <ljs@kernel.org>,
	"Vlastimil Babka" <vbabka@kernel.org>,
	"Jann Horn" <jannh@google.com>,
	"Pedro Falcato" <pfalcato@suse.de>,
	"Michal Hocko" <mhocko@suse.com>,
	"Michał Mirosław" <mirq-linux@rere.qmqm.pl>,
	"Andrei Vagin" <avagin@gmail.com>,
	"Muhammad Usama Anjum" <usama.anjum@arm.com>,
	"Stephen Rothwell" <sfr@canb.auug.org.au>,
	"Arnd Bergmann" <arnd@arndb.de>, "Zi Yan" <ziy@nvidia.com>,
	"Matthew Brost" <matthew.brost@intel.com>,
	"Joshua Hahn" <joshua.hahnjy@gmail.com>,
	"Byungchul Park" <byungchul@sk.com>,
	"Gregory Price" <gourry@gourry.net>,
	"Ying Huang" <ying.huang@linux.alibaba.com>,
	"Alistair Popple" <apopple@nvidia.com>,
	"Baolin Wang" <baolin.wang@linux.alibaba.com>,
	"Nico Pache" <nico.pache@linux.dev>,
	"Ryan Roberts" <ryan.roberts@arm.com>,
	"Dev Jain" <dev.jain@arm.com>, "Barry Song" <baohua@kernel.org>,
	"Lance Yang" <lance.yang@linux.dev>,
	"Usama Arif" <usama.arif@linux.dev>,
	"Kiryl Shutsemau" <kas@kernel.org>,
	"Muchun Song" <muchun.song@linux.dev>,
	"Oscar Salvador" <osalvador@suse.de>,
	"Mikołaj Lenczewski" <miko.lenczewski@arm.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH v2 9/9] mm/userfaultfd: check hugetlb end alignment in UFFDIO_UNREGISTER pre-scan
Date: Mon, 16 Nov 2026 21:56:48 +0100	[thread overview]
Message-ID: <2837958f-5a9d-46ad-b6ff-5a922b09e81a@kernel.org> (raw)
In-Reply-To: <20261116-uffd-state-fixes-v2-9-4397a0196479@columbia.edu>

On 11/16/26 21:02, Tal Zussman wrote:
> UFFDIO_REGISTER and UFFDIO_UNREGISTER both scan the VMAs of the range
> before changing anything. For a hugetlb VMA, userfaultfd_register()
> rejects a range whose start or end is not huge page aligned there.
> However, userfaultfd_unregister() only checks the start.
> 
> An unaligned end only fails later, when vma_modify_flags_uffd() cannot
> split the VMA there. At that point, userfaultfd_clear_vma() already
> cleared the WP or RWP protection. The ioctl returns -EINVAL and the VMA
> stays registered, but accesses to its pages are no longer reported. This
> requires a caller passing a misaligned range.
> 
> To fix it, check the end of a registered VMA in the pre-scan as well.
> The ioctl still returns -EINVAL, but no longer unregisters the VMAs
> before the misaligned one first.
> 
> Fixes: cab350afcbc9 ("userfaultfd: hugetlbfs: allow registration of ranges containing huge pages")
> Fixes: f369b07c8614 ("mm/uffd: reset write protection when unregister with wp-mode")
> Signed-off-by: Tal Zussman <tz2294@columbia.edu>

Okay, I assume it's not a stable kernel, so we can fix this in a cleaner way.

> ---
>  mm/userfaultfd.c | 11 +++++++++++
>  1 file changed, 11 insertions(+)
> 
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index bf42fabb5afd..d8abc24353e1 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -3960,6 +3960,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
>  	found = false;
>  	cur = vma;
>  	do {
> +		const struct userfaultfd_ctx *vma_ctx = cur->vm_userfaultfd_ctx.ctx;
> +
>  		cond_resched();
>  
>  		VM_WARN_ON_ONCE(!!cur->vm_userfaultfd_ctx.ctx ^
> @@ -3983,6 +3985,15 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
>  		if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
>  			goto out_unlock;
>  
> +		/* See the check in userfaultfd_register(). */
> +		if (vma_ctx && vma_is_hugetlb(cur) &&

I'm not sure if we really need the vma_ctx. I'd just fail this consistently if
someone passes hugetlb VMAs, independent of if they are registered or not.

> +		    end <= cur->vm_end && end > cur->vm_start) {
> +			const unsigned long vma_hpagesize = vma_kernel_pagesize(cur);

vma_kernel_pagesize(), yuk. :)

> +
> +			if (!IS_ALIGNED(end, vma_hpagesize))
> +				goto out_unlock;
> +		}
> +
>  		found = true;
>  	} for_each_vma_range(vmi, cur, end);
>  	VM_WARN_ON_ONCE(!found);


Can we clean all this up into something simple like:

--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -3669,6 +3669,19 @@ static __always_inline int validate_range(struct
mm_struct *mm,
 	return validate_unaligned_range(mm, start, len);
 }

+static bool vma_uffd_range_aligned(struct vm_area_struct *vma,
+	unsigned long start, unsigned long end)
+{
+	unsigned long size;
+
+	if (!vma_is_hugetlb(vma))
+		return true;
+
+	size = huge_page_size(hstate_vma(vma));
+	return IS_ALIGNED(max(start, vma->vm_start), size) &&
+	       IS_ALIGNED(min(end, vma->vm_end), size);
+}
+
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
@@ -3747,17 +3760,6 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	if (!vma)
 		goto out_unlock;

-	/*
-	 * If the first vma contains huge pages, make sure start address
-	 * is aligned to huge page size.
-	 */
-	if (vma_is_hugetlb(vma)) {
-		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
-
-		if (start & (vma_hpagesize - 1))
-			goto out_unlock;
-	}
-
 	/*
 	 * Search for not compatible vmas.
 	 */
@@ -3774,6 +3776,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		ret = -EINVAL;
 		if (!vma_can_userfault(cur, vm_flags, wp_async))
 			goto out_unlock;
+		if (!vma_uffd_range_aligned(cur, start, end))
+			goto out_unlock;

 		/*
 		 * RWP uses protnone as an access-tracking marker. PROT_NONE
@@ -3797,20 +3801,6 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		ret = -EPERM;
 		if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
 			goto out_unlock;
-
-		/*
-		 * If this vma contains ending address, and huge pages
-		 * check alignment.
-		 */
-		if (vma_is_hugetlb(cur) && end <= cur->vm_end &&
-		    end > cur->vm_start) {
-			unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
-
-			ret = -EINVAL;
-
-			if (end & (vma_hpagesize - 1))
-				goto out_unlock;
-		}
 		if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
 			goto out_unlock;

@@ -3920,17 +3910,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx
*ctx,
 	if (!vma)
 		goto out_unlock;

-	/*
-	 * If the first vma contains huge pages, make sure start address
-	 * is aligned to huge page size.
-	 */
-	if (vma_is_hugetlb(vma)) {
-		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
-
-		if (start & (vma_hpagesize - 1))
-			goto out_unlock;
-	}
-
 	/*
 	 * Search for not compatible vmas.
 	 */
@@ -3959,6 +3938,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 */
 		if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
 			goto out_unlock;
+		if (!vma_uffd_range_aligned(cur, start, end))
+			goto out_unlock;

 		found = true;
 	} for_each_vma_range(vmi, cur, end);

-- 
Cheers,

David


      reply	other threads:[~2026-11-16 20:57 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-16 20:02 [PATCH v2 0/9] userfaultfd: assorted fixes (part 1) Tal Zussman
2026-11-16 20:02 ` [PATCH v2 1/9] userfaultfd: use anonymous memory for UFFDIO_ZEROPAGE on private file mappings Tal Zussman
2026-11-16 20:15   ` David Hildenbrand (Arm)
2026-11-16 20:16   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 2/9] userfaultfd: refuse UFFDIO_MOVE into a non-present huge destination PMD Tal Zussman
2026-11-16 20:18   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 3/9] fs/proc/task_mmu: downgrade writable migration entries in PAGEMAP_SCAN write-protect Tal Zussman
2026-11-16 20:21   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 4/9] mm/migrate: keep the uffd bit when restoring a writable migration entry Tal Zussman
2026-11-16 20:23   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 5/9] fs/proc/task_mmu: write-protect device-private THPs in PAGEMAP_SCAN Tal Zussman
2026-11-16 20:26   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 6/9] mm/huge_memory: build the moved huge zero PMD from the destination VMA Tal Zussman
2026-11-16 20:32   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 7/9] mm/mremap: resolve uffd state when the context is dropped, not during the move Tal Zussman
2026-11-16 20:41   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 8/9] mm/migrate_device: do not migrate a uffd-protected zero page Tal Zussman
2026-11-16 20:45   ` David Hildenbrand (Arm)
2026-11-16 20:02 ` [PATCH v2 9/9] mm/userfaultfd: check hugetlb end alignment in UFFDIO_UNREGISTER pre-scan Tal Zussman
2026-11-16 20:56   ` David Hildenbrand (Arm) [this message]

Reply instructions:

You may reply publicly 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=2837958f-5a9d-46ad-b6ff-5a922b09e81a@kernel.org \
    --to=david@kernel.org \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=arnd@arndb.de \
    --cc=avagin@gmail.com \
    --cc=balbirs@nvidia.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=byungchul@sk.com \
    --cc=dev.jain@arm.com \
    --cc=gourry@gourry.net \
    --cc=jannh@google.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=jthoughton@google.com \
    --cc=kas@kernel.org \
    --cc=lance.yang@linux.dev \
    --cc=liam@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=matthew.brost@intel.com \
    --cc=mhocko@suse.com \
    --cc=miko.lenczewski@arm.com \
    --cc=mirq-linux@rere.qmqm.pl \
    --cc=muchun.song@linux.dev \
    --cc=nico.pache@linux.dev \
    --cc=osalvador@suse.de \
    --cc=peterx@redhat.com \
    --cc=pfalcato@suse.de \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=sfr@canb.auug.org.au \
    --cc=surenb@google.com \
    --cc=tz2294@columbia.edu \
    --cc=usama.anjum@arm.com \
    --cc=usama.arif@linux.dev \
    --cc=vbabka@kernel.org \
    --cc=ying.huang@linux.alibaba.com \
    --cc=ziy@nvidia.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox