@@ -37,3 +37,9 @@ void rust_helper_mmap_read_unlock(struct mm_struct *mm)
{
mmap_read_unlock(mm);
}
+
+struct vm_area_struct *rust_helper_vma_lookup(struct mm_struct *mm,
+ unsigned long addr)
+{
+ return vma_lookup(mm, addr);
+}
@@ -12,6 +12,8 @@
};
use core::{ops::Deref, ptr::NonNull};
+pub mod virt;
+
/// A wrapper for the kernel's `struct mm_struct`.
///
/// Since `mm_users` may be zero, the associated address space may not exist anymore. You can use
@@ -210,6 +212,25 @@ pub struct MmapReadGuard<'a> {
_nts: NotThreadSafe,
}
+impl<'a> MmapReadGuard<'a> {
+ /// Look up a vma at the given address.
+ #[inline]
+ pub fn vma_lookup(&self, vma_addr: usize) -> Option<&virt::VmAreaRef> {
+ // SAFETY: We hold a reference to the mm, so the pointer must be valid. Any value is okay
+ // for `vma_addr`.
+ let vma = unsafe { bindings::vma_lookup(self.mm.as_raw(), vma_addr as _) };
+
+ if vma.is_null() {
+ None
+ } else {
+ // SAFETY: We just checked that a vma was found, so the pointer is valid. Furthermore,
+ // the returned area will borrow from this read lock guard, so it can only be used
+ // while the mmap read lock is still held.
+ unsafe { Some(virt::VmAreaRef::from_raw(vma)) }
+ }
+ }
+}
+
impl Drop for MmapReadGuard<'_> {
#[inline]
fn drop(&mut self) {
new file mode 100644
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 Google LLC.
+
+//! Virtual memory.
+
+use crate::{bindings, types::Opaque};
+
+/// A wrapper for the kernel's `struct vm_area_struct` with read access.
+///
+/// It represents an area of virtual memory.
+///
+/// # Invariants
+///
+/// The caller must hold the mmap read lock or the vma read lock.
+#[repr(transparent)]
+pub struct VmAreaRef {
+ vma: Opaque<bindings::vm_area_struct>,
+}
+
+// Methods you can call when holding the mmap or vma read lock (or strong). They must be usable no
+// matter what the vma flags are.
+impl VmAreaRef {
+ /// Access a virtual memory area given a raw pointer.
+ ///
+ /// # Safety
+ ///
+ /// Callers must ensure that `vma` is valid for the duration of 'a, and that the mmap or vma
+ /// read lock (or stronger) is held for at least the duration of 'a.
+ #[inline]
+ pub unsafe fn from_raw<'a>(vma: *const bindings::vm_area_struct) -> &'a Self {
+ // SAFETY: The caller ensures that the invariants are satisfied for the duration of 'a.
+ unsafe { &*vma.cast() }
+ }
+
+ /// Returns a raw pointer to this area.
+ #[inline]
+ pub fn as_ptr(&self) -> *mut bindings::vm_area_struct {
+ self.vma.get()
+ }
+
+ /// Returns the flags associated with the virtual memory area.
+ ///
+ /// The possible flags are a combination of the constants in [`flags`].
+ #[inline]
+ pub fn flags(&self) -> vm_flags_t {
+ // SAFETY: By the type invariants, the caller holds at least the mmap read lock, so this
+ // access is not a data race.
+ unsafe { (*self.as_ptr()).__bindgen_anon_2.vm_flags as _ }
+ }
+
+ /// Returns the (inclusive) start address of the virtual memory area.
+ #[inline]
+ pub fn start(&self) -> usize {
+ // SAFETY: By the type invariants, the caller holds at least the mmap read lock, so this
+ // access is not a data race.
+ unsafe { (*self.as_ptr()).__bindgen_anon_1.__bindgen_anon_1.vm_start as _ }
+ }
+
+ /// Returns the (exclusive) end address of the virtual memory area.
+ #[inline]
+ pub fn end(&self) -> usize {
+ // SAFETY: By the type invariants, the caller holds at least the mmap read lock, so this
+ // access is not a data race.
+ unsafe { (*self.as_ptr()).__bindgen_anon_1.__bindgen_anon_1.vm_end as _ }
+ }
+
+ /// Zap pages in the given page range.
+ ///
+ /// This clears page table mappings for the range at the leaf level, leaving all other page
+ /// tables intact, and freeing any memory referenced by the VMA in this range. That is,
+ /// anonymous memory is completely freed, file-backed memory has its reference count on page
+ /// cache folio's dropped, any dirty data will still be written back to disk as usual.
+ #[inline]
+ pub fn zap_page_range_single(&self, address: usize, size: usize) {
+ let (end, did_overflow) = address.overflowing_add(size);
+ if did_overflow || address < self.start() || self.end() < end {
+ // TODO: call WARN_ONCE once Rust version of it is added
+ return;
+ }
+
+ // SAFETY: By the type invariants, the caller has read access to this VMA, which is
+ // sufficient for this method call. This method has no requirements on the vma flags. The
+ // address range is checked to be within the vma.
+ unsafe {
+ bindings::zap_page_range_single(
+ self.as_ptr(),
+ address as _,
+ size as _,
+ core::ptr::null_mut(),
+ )
+ };
+ }
+}
+
+/// The integer type used for vma flags.
+#[doc(inline)]
+pub use bindings::vm_flags_t;
+
+/// All possible flags for [`VmAreaRef`].
+pub mod flags {
+ use super::vm_flags_t;
+ use crate::bindings;
+
+ /// No flags are set.
+ pub const NONE: vm_flags_t = bindings::VM_NONE as _;
+
+ /// Mapping allows reads.
+ pub const READ: vm_flags_t = bindings::VM_READ as _;
+
+ /// Mapping allows writes.
+ pub const WRITE: vm_flags_t = bindings::VM_WRITE as _;
+
+ /// Mapping allows execution.
+ pub const EXEC: vm_flags_t = bindings::VM_EXEC as _;
+
+ /// Mapping is shared.
+ pub const SHARED: vm_flags_t = bindings::VM_SHARED as _;
+
+ /// Mapping may be updated to allow reads.
+ pub const MAYREAD: vm_flags_t = bindings::VM_MAYREAD as _;
+
+ /// Mapping may be updated to allow writes.
+ pub const MAYWRITE: vm_flags_t = bindings::VM_MAYWRITE as _;
+
+ /// Mapping may be updated to allow execution.
+ pub const MAYEXEC: vm_flags_t = bindings::VM_MAYEXEC as _;
+
+ /// Mapping may be updated to be shared.
+ pub const MAYSHARE: vm_flags_t = bindings::VM_MAYSHARE as _;
+
+ /// Page-ranges managed without `struct page`, just pure PFN.
+ pub const PFNMAP: vm_flags_t = bindings::VM_PFNMAP as _;
+
+ /// Memory mapped I/O or similar.
+ pub const IO: vm_flags_t = bindings::VM_IO as _;
+
+ /// Do not copy this vma on fork.
+ pub const DONTCOPY: vm_flags_t = bindings::VM_DONTCOPY as _;
+
+ /// Cannot expand with mremap().
+ pub const DONTEXPAND: vm_flags_t = bindings::VM_DONTEXPAND as _;
+
+ /// Lock the pages covered when they are faulted in.
+ pub const LOCKONFAULT: vm_flags_t = bindings::VM_LOCKONFAULT as _;
+
+ /// Is a VM accounted object.
+ pub const ACCOUNT: vm_flags_t = bindings::VM_ACCOUNT as _;
+
+ /// Should the VM suppress accounting.
+ pub const NORESERVE: vm_flags_t = bindings::VM_NORESERVE as _;
+
+ /// Huge TLB Page VM.
+ pub const HUGETLB: vm_flags_t = bindings::VM_HUGETLB as _;
+
+ /// Synchronous page faults. (DAX-specific)
+ pub const SYNC: vm_flags_t = bindings::VM_SYNC as _;
+
+ /// Architecture-specific flag.
+ pub const ARCH_1: vm_flags_t = bindings::VM_ARCH_1 as _;
+
+ /// Wipe VMA contents in child on fork.
+ pub const WIPEONFORK: vm_flags_t = bindings::VM_WIPEONFORK as _;
+
+ /// Do not include in the core dump.
+ pub const DONTDUMP: vm_flags_t = bindings::VM_DONTDUMP as _;
+
+ /// Not soft dirty clean area.
+ pub const SOFTDIRTY: vm_flags_t = bindings::VM_SOFTDIRTY as _;
+
+ /// Can contain `struct page` and pure PFN pages.
+ pub const MIXEDMAP: vm_flags_t = bindings::VM_MIXEDMAP as _;
+
+ /// MADV_HUGEPAGE marked this vma.
+ pub const HUGEPAGE: vm_flags_t = bindings::VM_HUGEPAGE as _;
+
+ /// MADV_NOHUGEPAGE marked this vma.
+ pub const NOHUGEPAGE: vm_flags_t = bindings::VM_NOHUGEPAGE as _;
+
+ /// KSM may merge identical pages.
+ pub const MERGEABLE: vm_flags_t = bindings::VM_MERGEABLE as _;
+}