@@ -244,6 +244,41 @@ write-protected (so future writes will also result in a WP fault). These ioctls
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
---------------------------
@@ -123,6 +123,11 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
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
@@ -1318,6 +1323,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
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;
@@ -1392,7 +1398,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
/* 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;
/*
@@ -1453,7 +1459,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
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));
@@ -1553,6 +1559,7 @@ 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);
pgoff_t pgoff;
ret = -EFAULT;
@@ -1607,7 +1614,7 @@ 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))
+ if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
goto out_unlock;
found = true;
@@ -1623,7 +1630,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
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
@@ -2005,6 +2012,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
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)
{
/*
@@ -2038,6 +2050,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
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
@@ -2050,6 +2067,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
#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;
@@ -161,11 +161,22 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
}
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
@@ -175,6 +186,8 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
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);
}
@@ -197,6 +210,7 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *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 */
@@ -297,6 +311,11 @@ 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;
+}
+
#endif /* CONFIG_USERFAULTFD */
static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
@@ -40,7 +40,8 @@
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 | \
@@ -216,6 +217,11 @@ struct uffdio_api {
* (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)
@@ -232,6 +238,7 @@ struct uffdio_api {
#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;
@@ -6165,21 +6165,27 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
/* 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 */
}
/*
@@ -3352,11 +3352,28 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
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;
}
/*
@@ -4851,8 +4868,11 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
if (vma_is_anonymous(vmf->vma)) {
if (likely(!unshare) &&
- userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
+ userfaultfd_huge_pmd_wp(vmf->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);
}
@@ -4864,6 +4884,7 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
}
}
+split:
/* COW or write-notify handled on pte level: split pmd. */
__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);