userfaultfd: UFFD_FEATURE_WP_ASYNC

Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.

*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.

This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.

CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.

Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.

*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically

So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.

At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)

All the different masks were added on the request of CRIU devs to create
interface more generic and better.

[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/[e-mail]
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/[e-mail]
[6] https://lore.kernel.org/all/[e-mail]/
[7] https://lore.kernel.org/all/[e-mail]
[8] https://lore.kernel.org/all/[e-mail]
[9] https://lore.kernel.org/all/[e-mail]
[10] https://lore.kernel.org/all/[e-mail]


This patch (of 6):

Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.

It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).

Several goals of such a dirty tracking interface:

1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.

2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.

3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.

One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:

1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.

2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).

3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.

We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.

This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.

vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).

One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.

The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.

Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Peter Xu <[e-mail]>
Co-developed-by: Muhammad Usama Anjum <[e-mail]>
Signed-off-by: Muhammad Usama Anjum <[e-mail]>
Cc: Alex Sierra <[e-mail]>
Cc: Al Viro <[e-mail]>
Cc: Andrei Vagin <[e-mail]>
Cc: Axel Rasmussen <[e-mail]>
Cc: Christian Brauner <[e-mail]>
Cc: Cyrill Gorcunov <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: David Hildenbrand <[e-mail]>
Cc: Greg Kroah-Hartman <[e-mail]>
Cc: Gustavo A. R. Silva <[e-mail]>
Cc: "Liam R. Howlett" <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Cc: Michal Miroslaw <[e-mail]>
Cc: Mike Rapoport (IBM) <[e-mail]>
Cc: Nadav Amit <[e-mail]>
Cc: Pasha Tatashin <[e-mail]>
Cc: Paul Gofman <[e-mail]>
Cc: Shuah Khan <[e-mail]>
Cc: Suren Baghdasaryan <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Cc: Yang Shi <[e-mail]>
Cc: Yun Zhou <[e-mail]>
Cc: Michał Mirosław <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

Documentation/admin-guide/mm/userfaultfd.rst

···
 support a mode flag (``UFFDIO_COPY_MODE_WP`` or ``UFFDIO_CONTINUE_MODE_WP``
 respectively) to configure the mapping this way.
 
+If the userfaultfd context has ``UFFD_FEATURE_WP_ASYNC`` feature bit set,
+any vma registered with write-protection will work in async mode rather
+than the default sync mode.
+
+In async mode, there will be no message generated when a write operation
+happens, meanwhile the write-protection will be resolved automatically by
+the kernel.  It can be seen as a more accurate version of soft-dirty
+tracking and it can be different in a few ways:
+
+  - The dirty result will not be affected by vma changes (e.g. vma
+    merging) because the dirty is only tracked by the pte.
+
+  - It supports range operations by default, so one can enable tracking on
+    any range of memory as long as page aligned.
+
+  - Dirty information will not get lost if the pte was zapped due to
+    various reasons (e.g. during split of a shmem transparent huge page).
+
+  - Due to a reverted meaning of soft-dirty (page clean when uffd-wp bit
+    set; dirty when uffd-wp bit cleared), it has different semantics on
+    some of the memory operations.  For example: ``MADV_DONTNEED`` on
+    anonymous (or ``MADV_REMOVE`` on a file mapping) will be treated as
+    dirtying of memory by dropping uffd-wp bit during the procedure.
+
+The user app can collect the "written/dirty" status by looking up the
+uffd-wp bit for the pages being interested in /proc/pagemap.
+
+The page will not be under track of uffd-wp async mode until the page is
+explicitly write-protected by ``ioctl(UFFDIO_WRITEPROTECT)`` with the mode
+flag ``UFFDIO_WRITEPROTECT_MODE_WP`` set.  Trying to resolve a page fault
+that was tracked by async mode userfaultfd-wp is invalid.
+
+When userfaultfd-wp async mode is used alone, it can be applied to all
+kinds of memory.
+
 Memory Poisioning Emulation
 ---------------------------
 

fs/userfaultfd.c

···
 	return ctx->features & UFFD_FEATURE_INITIALIZED;
 }
 
+static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx)
+{
+	return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC);
+}
+
 /*
  * Whether WP_UNPOPULATED is enabled on the uffd context.  It is only
  * meaningful when userfaultfd_wp()==true on the vma and when it's
···
 	bool basic_ioctls;
 	unsigned long start, end, vma_end;
 	struct vma_iterator vmi;
+	bool wp_async = userfaultfd_wp_async_ctx(ctx);
 	pgoff_t pgoff;
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
···
 
 		/* check not compatible vmas */
 		ret = -EINVAL;
-		if (!vma_can_userfault(cur, vm_flags))
+		if (!vma_can_userfault(cur, vm_flags, wp_async))
 			goto out_unlock;
 
 		/*
···
 	for_each_vma_range(vmi, vma, end) {
 		cond_resched();
 
-		BUG_ON(!vma_can_userfault(vma, vm_flags));
+		BUG_ON(!vma_can_userfault(vma, vm_flags, wp_async));
 		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
 		       vma->vm_userfaultfd_ctx.ctx != ctx);
 		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
···
 	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);
 	pgoff_t pgoff;
 
 	ret = -EFAULT;
···
 		 * provides for more strict behavior to notice
 		 * unregistration errors.
 		 */
-		if (!vma_can_userfault(cur, cur->vm_flags))
+		if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
 			goto out_unlock;
 
 		found = true;
···
 	for_each_vma_range(vmi, vma, end) {
 		cond_resched();
 
-		BUG_ON(!vma_can_userfault(vma, vma->vm_flags));
+		BUG_ON(!vma_can_userfault(vma, vma->vm_flags, wp_async));
 
 		/*
 		 * Nothing to do: this vma is already registered into this
···
 	return ret;
 }
 
+bool userfaultfd_wp_async(struct vm_area_struct *vma)
+{
+	return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx);
+}
+
 static inline unsigned int uffd_ctx_features(__u64 user_features)
 {
 	/*
···
 	ret = -EPERM;
 	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
 		goto err_out;
+
+	/* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */
+	if (features & UFFD_FEATURE_WP_ASYNC)
+		features |= UFFD_FEATURE_WP_UNPOPULATED;
+
 	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
···
 #ifndef CONFIG_PTE_MARKER_UFFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
 	uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
+	uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
 #endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;

include/linux/userfaultfd_k.h

···
 }
 
 static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags)
+				     unsigned long vm_flags,
+				     bool wp_async)
 {
+	vm_flags &= __VM_UFFD_FLAGS;
+
 	if ((vm_flags & VM_UFFD_MINOR) &&
 	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
 		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))
+		return true;
+
 #ifndef CONFIG_PTE_MARKER_UFFD_WP
 	/*
 	 * If user requested uffd-wp but not enabled pte markers for
···
 	if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma))
 		return false;
 #endif
+
+	/* By default, allow any of anon|shmem|hugetlb */
 	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
 	    vma_is_shmem(vma);
 }
···
 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);
 
 #else /* CONFIG_USERFAULTFD */
 
···
 }
 
 static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
+{
+	return false;
+}
+
+static inline bool userfaultfd_wp_async(struct vm_area_struct *vma)
 {
 	return false;
 }

include/uapi/linux/userfaultfd.h

···
 			   UFFD_FEATURE_EXACT_ADDRESS |		\
 			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM |	\
 			   UFFD_FEATURE_WP_UNPOPULATED |	\
-			   UFFD_FEATURE_POISON)
+			   UFFD_FEATURE_POISON |		\
+			   UFFD_FEATURE_WP_ASYNC)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
···
 	 * (i.e. empty ptes).  This will be the default behavior for shmem
 	 * & hugetlbfs, so this flag only affects anonymous memory behavior
 	 * when userfault write-protection mode is registered.
+	 *
+	 * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection
+	 * asynchronous mode is supported in which the write fault is
+	 * automatically resolved and write-protection is un-set.
+	 * It implies UFFD_FEATURE_WP_UNPOPULATED.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
···
 #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM		(1<<12)
 #define UFFD_FEATURE_WP_UNPOPULATED		(1<<13)
 #define UFFD_FEATURE_POISON			(1<<14)
+#define UFFD_FEATURE_WP_ASYNC			(1<<15)
 	__u64 features;
 
 	__u64 ioctls;

mm/hugetlb.c

···
 	/* Handle userfault-wp first, before trying to lock more pages */
 	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) &&
 	    (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
-		struct vm_fault vmf = {
-			.vma = vma,
-			.address = haddr,
-			.real_address = address,
-			.flags = flags,
-		};
+		if (!userfaultfd_wp_async(vma)) {
+			struct vm_fault vmf = {
+				.vma = vma,
+				.address = haddr,
+				.real_address = address,
+				.flags = flags,
+			};
 
-		spin_unlock(ptl);
-		if (pagecache_folio) {
-			folio_unlock(pagecache_folio);
-			folio_put(pagecache_folio);
+			spin_unlock(ptl);
+			if (pagecache_folio) {
+				folio_unlock(pagecache_folio);
+				folio_put(pagecache_folio);
+			}
+			hugetlb_vma_unlock_read(vma);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			return handle_userfault(&vmf, VM_UFFD_WP);
 		}
-		hugetlb_vma_unlock_read(vma);
-		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-		return handle_userfault(&vmf, VM_UFFD_WP);
+
+		entry = huge_pte_clear_uffd_wp(entry);
+		set_huge_pte_at(mm, haddr, ptep, entry);
+		/* Fallthrough to CoW */
 	}
 
 	/*

mm/memory.c

···
+
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/mm/memory.c
···
 	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	struct vm_area_struct *vma = vmf->vma;
 	struct folio *folio = NULL;
+	pte_t pte;
 
 	if (likely(!unshare)) {
 		if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) {
-			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			return handle_userfault(vmf, VM_UFFD_WP);
+			if (!userfaultfd_wp_async(vma)) {
+				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				return handle_userfault(vmf, VM_UFFD_WP);
+			}
+
+			/*
+			 * Nothing needed (cache flush, TLB invalidations,
+			 * etc.) because we're only removing the uffd-wp bit,
+			 * which is completely invisible to the user.
+			 */
+			pte = pte_clear_uffd_wp(ptep_get(vmf->pte));
+
+			set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
+			/*
+			 * Update this to be prepared for following up CoW
+			 * handling
+			 */
+			vmf->orig_pte = pte;
 		}
 
 		/*
···
 
 	if (vma_is_anonymous(vma)) {
 		if (likely(!unshare) &&
-		    userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd))
+		    userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) {
+			if (userfaultfd_wp_async(vmf->vma))
+				goto split;
 			return handle_userfault(vmf, VM_UFFD_WP);
+		}
 		return do_huge_pmd_wp_page(vmf);
 	}
 
···
 		}
 	}
 
+split:
 	/* COW or write-notify handled on pte level: split pmd. */
 	__split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);