linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Xu <peterx@redhat.com>,
	David Hildenbrand <david@kernel.org>,
	Lorenzo Stoakes <ljs@kernel.org>, Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@kernel.org>,
	"Liam R . Howlett" <Liam.Howlett@oracle.com>,
	Zi Yan <ziy@nvidia.com>, Jonathan Corbet <corbet@lwn.net>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Sean Christopherson <seanjc@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org,
	kvm@vger.kernel.org, "Kiryl Shutsemau (Meta)" <kas@kernel.org>
Subject: [RFC, PATCH 02/12] userfaultfd: add UFFD_FEATURE_MINOR_ANON registration support
Date: Tue, 14 Apr 2026 15:23:36 +0100	[thread overview]
Message-ID: <20260414142354.1465950-3-kas@kernel.org> (raw)
In-Reply-To: <20260414142354.1465950-1-kas@kernel.org>

Allow UFFDIO_REGISTER_MODE_MINOR on anonymous VMAs when the
UFFD_FEATURE_MINOR_ANON feature is enabled.

Replace the bool wp_async parameter in vma_can_userfault() and
userfaultfd_register_range() with an extensible ctx_flags bitmap.
Add UFFD_CTX_WP_ASYNC and UFFD_CTX_MINOR_ANON flags, and
userfaultfd_ctx_flags() to build the bitmap from ctx->features.

Add userfaultfd_minor_async() helper for checking async minor mode
from the fault path.

Gate UFFD_FEATURE_MINOR_ANON and UFFD_FEATURE_MINOR_ASYNC on
CONFIG_HAVE_ARCH_USERFAULTFD_MINOR. Validate that MINOR_ASYNC
requires at least one minor feature.

Not yet visible to userspace (not in UFFD_API_FEATURES).

Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Assisted-by: Claude:claude-opus-4-6
---
 fs/userfaultfd.c              | 49 ++++++++++++++++++++++++++++++-----
 include/linux/userfaultfd_k.h | 19 +++++++++++---
 mm/userfaultfd.c              |  4 +--
 3 files changed, 59 insertions(+), 13 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index bdc84e5219cd..8d508ad19e89 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -89,6 +89,27 @@ static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx)
 	return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC);
 }
 
+static bool userfaultfd_minor_anon_ctx(struct userfaultfd_ctx *ctx)
+{
+	return ctx && (ctx->features & UFFD_FEATURE_MINOR_ANON);
+}
+
+static bool userfaultfd_minor_async_ctx(struct userfaultfd_ctx *ctx)
+{
+	return ctx && (ctx->features & UFFD_FEATURE_MINOR_ASYNC);
+}
+
+static unsigned int userfaultfd_ctx_flags(struct userfaultfd_ctx *ctx)
+{
+	unsigned int flags = 0;
+
+	if (userfaultfd_wp_async_ctx(ctx))
+		flags |= UFFD_CTX_WP_ASYNC;
+	if (userfaultfd_minor_anon_ctx(ctx))
+		flags |= UFFD_CTX_MINOR_ANON;
+	return flags;
+}
+
 /*
  * Whether WP_UNPOPULATED is enabled on the uffd context.  It is only
  * meaningful when userfaultfd_wp()==true on the vma and when it's
@@ -1271,7 +1292,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	bool basic_ioctls;
 	unsigned long start, end;
 	struct vma_iterator vmi;
-	bool wp_async = userfaultfd_wp_async_ctx(ctx);
+	unsigned int ctx_flags = userfaultfd_ctx_flags(ctx);
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
 
@@ -1345,7 +1366,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 
 		/* check not compatible vmas */
 		ret = -EINVAL;
-		if (!vma_can_userfault(cur, vm_flags, wp_async))
+		if (!vma_can_userfault(cur, vm_flags, ctx_flags))
 			goto out_unlock;
 
 		/*
@@ -1398,7 +1419,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	VM_WARN_ON_ONCE(!found);
 
 	ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end,
-					 wp_async);
+					 ctx_flags);
 
 out_unlock:
 	mmap_write_unlock(mm);
@@ -1443,7 +1464,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	unsigned long start, end, vma_end;
 	const void __user *buf = (void __user *)arg;
 	struct vma_iterator vmi;
-	bool wp_async = userfaultfd_wp_async_ctx(ctx);
+	unsigned int ctx_flags = userfaultfd_ctx_flags(ctx);
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
@@ -1505,7 +1526,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * provides for more strict behavior to notice
 		 * unregistration errors.
 		 */
-		if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
+		if (!vma_can_userfault(cur, cur->vm_flags, ctx_flags))
 			goto out_unlock;
 
 		found = true;
@@ -1526,7 +1547,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			goto skip;
 
 		VM_WARN_ON_ONCE(vma->vm_userfaultfd_ctx.ctx != ctx);
-		VM_WARN_ON_ONCE(!vma_can_userfault(vma, vma->vm_flags, wp_async));
+		VM_WARN_ON_ONCE(!vma_can_userfault(vma, vma->vm_flags, ctx_flags));
 		VM_WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE));
 
 		if (vma->vm_start > start)
@@ -1890,6 +1911,11 @@ bool userfaultfd_wp_async(struct vm_area_struct *vma)
 	return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx);
 }
 
+bool userfaultfd_minor_async(struct vm_area_struct *vma)
+{
+	return userfaultfd_minor_async_ctx(vma->vm_userfaultfd_ctx.ctx);
+}
+
 static inline unsigned int uffd_ctx_features(__u64 user_features)
 {
 	/*
@@ -1993,11 +2019,20 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	if (features & UFFD_FEATURE_WP_ASYNC)
 		features |= UFFD_FEATURE_WP_UNPOPULATED;
 
+	ret = -EINVAL;
+	/* MINOR_ASYNC requires at least one minor feature */
+	if ((features & UFFD_FEATURE_MINOR_ASYNC) &&
+	    !(features & (UFFD_FEATURE_MINOR_ANON |
+			  UFFD_FEATURE_MINOR_HUGETLBFS |
+			  UFFD_FEATURE_MINOR_SHMEM)))
+		goto err_out;
+
 	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
 	uffdio_api.features &=
-		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
+		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM |
+		  UFFD_FEATURE_MINOR_ANON | UFFD_FEATURE_MINOR_ASYNC);
 #endif
 	if (!pgtable_supports_uffd_wp())
 		uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index fd5f42765497..d1d4ed4a08b0 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -208,9 +208,13 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return vma->vm_flags & __VM_UFFD_FLAGS;
 }
 
+/* Flags for vma_can_userfault() describing uffd context capabilities */
+#define UFFD_CTX_WP_ASYNC	(1 << 0)
+#define UFFD_CTX_MINOR_ANON	(1 << 1)
+
 static inline bool vma_can_userfault(struct vm_area_struct *vma,
 				     vm_flags_t vm_flags,
-				     bool wp_async)
+				     unsigned int ctx_flags)
 {
 	vm_flags &= __VM_UFFD_FLAGS;
 
@@ -218,14 +222,15 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 		return false;
 
 	if ((vm_flags & VM_UFFD_MINOR) &&
-	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
+	    !is_vm_hugetlb_page(vma) && !vma_is_shmem(vma) &&
+	    !(vma_is_anonymous(vma) && (ctx_flags & UFFD_CTX_MINOR_ANON)))
 		return false;
 
 	/*
 	 * If wp async enabled, and WP is the only mode enabled, allow any
 	 * memory type.
 	 */
-	if (wp_async && (vm_flags == VM_UFFD_WP))
+	if ((ctx_flags & UFFD_CTX_WP_ASYNC) && (vm_flags == VM_UFFD_WP))
 		return true;
 
 	/*
@@ -270,6 +275,7 @@ extern void userfaultfd_unmap_complete(struct mm_struct *mm,
 				       struct list_head *uf);
 extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma);
 extern bool userfaultfd_wp_async(struct vm_area_struct *vma);
+extern bool userfaultfd_minor_async(struct vm_area_struct *vma);
 
 void userfaultfd_reset_ctx(struct vm_area_struct *vma);
 
@@ -283,7 +289,7 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 			       struct vm_area_struct *vma,
 			       vm_flags_t vm_flags,
 			       unsigned long start, unsigned long end,
-			       bool wp_async);
+			       unsigned int ctx_flags);
 
 void userfaultfd_release_new(struct userfaultfd_ctx *ctx);
 
@@ -446,6 +452,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline bool userfaultfd_minor_async(struct vm_area_struct *vma)
+{
+	return false;
+}
+
 static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma)
 {
 	return false;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 927086bb4a3c..dba1ea26fdfe 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -2008,7 +2008,7 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 			       struct vm_area_struct *vma,
 			       vm_flags_t vm_flags,
 			       unsigned long start, unsigned long end,
-			       bool wp_async)
+			       unsigned int ctx_flags)
 {
 	VMA_ITERATOR(vmi, ctx->mm, start);
 	struct vm_area_struct *prev = vma_prev(&vmi);
@@ -2021,7 +2021,7 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 	for_each_vma_range(vmi, vma, end) {
 		cond_resched();
 
-		VM_WARN_ON_ONCE(!vma_can_userfault(vma, vm_flags, wp_async));
+		VM_WARN_ON_ONCE(!vma_can_userfault(vma, vm_flags, ctx_flags));
 		VM_WARN_ON_ONCE(vma->vm_userfaultfd_ctx.ctx &&
 				vma->vm_userfaultfd_ctx.ctx != ctx);
 		VM_WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE));
-- 
2.51.2



  parent reply	other threads:[~2026-04-14 14:24 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-14 14:23 [RFC, PATCH 00/12] userfaultfd: working set tracking for VM guest memory Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 01/12] userfaultfd: define UAPI constants for anonymous minor faults Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` Kiryl Shutsemau (Meta) [this message]
2026-04-14 14:23 ` [RFC, PATCH 03/12] userfaultfd: implement UFFDIO_DEACTIVATE ioctl Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 04/12] userfaultfd: UFFDIO_CONTINUE for anonymous memory Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 05/12] mm: intercept protnone faults on VM_UFFD_MINOR anonymous VMAs Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 06/12] userfaultfd: auto-resolve shmem and hugetlbfs minor faults in async mode Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 07/12] sched/numa: skip scanning anonymous VM_UFFD_MINOR VMAs Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 08/12] userfaultfd: enable UFFD_FEATURE_MINOR_ANON Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 09/12] mm/pagemap: add PAGE_IS_UFFD_DEACTIVATED to PAGEMAP_SCAN Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 10/12] userfaultfd: add UFFDIO_SET_MODE for runtime sync/async toggle Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 11/12] selftests/mm: add userfaultfd anonymous minor fault tests Kiryl Shutsemau (Meta)
2026-04-14 14:23 ` [RFC, PATCH 12/12] Documentation/userfaultfd: document working set tracking Kiryl Shutsemau (Meta)
2026-04-14 15:28 ` [RFC, PATCH 00/12] userfaultfd: working set tracking for VM guest memory Peter Xu
2026-04-14 17:08   ` Kiryl Shutsemau
2026-04-14 17:45     ` Peter Xu
2026-04-14 15:37 ` David Hildenbrand (Arm)
2026-04-14 17:10   ` Kiryl Shutsemau

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=20260414142354.1465950-3-kas@kernel.org \
    --to=kas@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=corbet@lwn.net \
    --cc=david@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=rppt@kernel.org \
    --cc=seanjc@google.com \
    --cc=skhan@linuxfoundation.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    --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