return -EBUSY;
return -ENOENT;
} else if (is_pte_marker_entry(entry)) {
- /*
- * We're copying the pgtable should only because dst_vma has
- * uffd-wp enabled, do sanity check.
- */
- WARN_ON_ONCE(!userfaultfd_wp(dst_vma));
- set_pte_at(dst_mm, addr, dst_pte, pte);
+ if (userfaultfd_wp(dst_vma))
+ set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
if (!userfaultfd_wp(dst_vma))
return ret;
}
-/*
- * Parameter block passed down to zap_pte_range in exceptional cases.
- */
-struct zap_details {
- struct folio *single_folio; /* Locked folio to be unmapped */
- bool even_cows; /* Zap COWed private pages too? */
- zap_flags_t zap_flags; /* Extra flags for zapping */
-};
-
/* Whether we should zap all COWed (private) pages too */
static inline bool should_zap_cows(struct zap_details *details)
{
{
struct mmu_notifier_range range;
struct zap_details details = {
- .zap_flags = ZAP_FLAG_DROP_MARKER,
+ .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP,
/* Careful - we need to zap private pages too! */
.even_cows = true,
};
*
* The range must fit into one VMA.
*/
-static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details)
{
+ const unsigned long end = address + size;
struct mmu_notifier_range range;
struct mmu_gather tlb;
lru_add_drain();
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
- address, address + size);
+ address, end);
+ if (is_vm_hugetlb_page(vma))
+ adjust_range_if_pmd_sharing_possible(vma, &range.start,
+ &range.end);
tlb_gather_mmu(&tlb, vma->vm_mm);
update_hiwater_rss(vma->vm_mm);
mmu_notifier_invalidate_range_start(&range);
- unmap_single_vma(&tlb, vma, address, range.end, details);
+ /*
+ * unmap 'address-end' not 'range.start-range.end' as range
+ * could have been expanded for hugetlb pmd sharing.
+ */
+ unmap_single_vma(&tlb, vma, address, end, details);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
return same;
}
-static inline bool __wp_page_copy_user(struct page *dst, struct page *src,
- struct vm_fault *vmf)
+/*
+ * Return:
+ * 0: copied succeeded
+ * -EHWPOISON: copy failed due to hwpoison in source page
+ * -EAGAIN: copied failed (some other reason)
+ */
+static inline int __wp_page_copy_user(struct page *dst, struct page *src,
+ struct vm_fault *vmf)
{
- bool ret;
+ int ret;
void *kaddr;
void __user *uaddr;
bool locked = false;
unsigned long addr = vmf->address;
if (likely(src)) {
- copy_user_highpage(dst, src, addr, vma);
- return true;
+ if (copy_mc_user_highpage(dst, src, addr, vma)) {
+ memory_failure_queue(page_to_pfn(src), 0);
+ return -EHWPOISON;
+ }
+ return 0;
}
/*
* and update local tlb only
*/
update_mmu_tlb(vma, addr, vmf->pte);
- ret = false;
+ ret = -EAGAIN;
goto pte_unlock;
}
if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
/* The PTE changed under us, update local tlb */
update_mmu_tlb(vma, addr, vmf->pte);
- ret = false;
+ ret = -EAGAIN;
goto pte_unlock;
}
}
}
- ret = true;
+ ret = 0;
pte_unlock:
if (locked)
pte_t entry;
int page_copied = 0;
struct mmu_notifier_range range;
+ int ret;
delayacct_wpcopy_start();
if (!new_page)
goto oom;
- if (!__wp_page_copy_user(new_page, old_page, vmf)) {
+ ret = __wp_page_copy_user(new_page, old_page, vmf);
+ if (ret) {
/*
* COW failed, if the fault was solved by other,
* it's fine. If not, userspace would re-fault on
* the same address and we will handle the fault
* from the second attempt.
+ * The -EHWPOISON case will not be retried.
*/
put_page(new_page);
if (old_page)
put_page(old_page);
delayacct_wpcopy_end();
- return 0;
+ return ret == -EHWPOISON ? VM_FAULT_HWPOISON : 0;
}
kmsan_copy_page_meta(new_page, old_page);
}
struct vm_area_struct *vma = vmf->vma;
struct mmu_notifier_range range;
- if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags))
+ /*
+ * We need a reference to lock the folio because we don't hold
+ * the PTL so a racing thread can remove the device-exclusive
+ * entry and unmap it. If the folio is free the entry must
+ * have been removed already. If it happens to have already
+ * been re-allocated after being freed all we do is lock and
+ * unlock it.
+ */
+ if (!folio_try_get(folio))
+ return 0;
+
+ if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) {
+ folio_put(folio);
return VM_FAULT_RETRY;
+ }
mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
vma->vm_mm, vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
pte_unmap_unlock(vmf->pte, vmf->ptl);
folio_unlock(folio);
+ folio_put(folio);
mmu_notifier_invalidate_range_end(&range);
return 0;
}
/*
+ * Some architectures may have to restore extra metadata to the page
+ * when reading from swap. This metadata may be indexed by swap entry
+ * so this must be called before swap_free().
+ */
+ arch_swap_restore(entry, folio);
+
+ /*
* Remove the swap entry and conditionally try to free up the swapcache.
* We're already holding a reference on the page but haven't mapped it
* yet.
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
+#ifdef CONFIG_LOCK_MM_AND_FIND_VMA
+#include <linux/extable.h>
+
+static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs)
+{
+ /* Even if this succeeds, make it clear we *might* have slept */
+ if (likely(mmap_read_trylock(mm))) {
+ might_sleep();
+ return true;
+ }
+
+ if (regs && !user_mode(regs)) {
+ unsigned long ip = instruction_pointer(regs);
+ if (!search_exception_tables(ip))
+ return false;
+ }
+
+ return !mmap_read_lock_killable(mm);
+}
+
+static inline bool mmap_upgrade_trylock(struct mm_struct *mm)
+{
+ /*
+ * We don't have this operation yet.
+ *
+ * It should be easy enough to do: it's basically a
+ * atomic_long_try_cmpxchg_acquire()
+ * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but
+ * it also needs the proper lockdep magic etc.
+ */
+ return false;
+}
+
+static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs)
+{
+ mmap_read_unlock(mm);
+ if (regs && !user_mode(regs)) {
+ unsigned long ip = instruction_pointer(regs);
+ if (!search_exception_tables(ip))
+ return false;
+ }
+ return !mmap_write_lock_killable(mm);
+}
+
+/*
+ * Helper for page fault handling.
+ *
+ * This is kind of equivalend to "mmap_read_lock()" followed
+ * by "find_extend_vma()", except it's a lot more careful about
+ * the locking (and will drop the lock on failure).
+ *
+ * For example, if we have a kernel bug that causes a page
+ * fault, we don't want to just use mmap_read_lock() to get
+ * the mm lock, because that would deadlock if the bug were
+ * to happen while we're holding the mm lock for writing.
+ *
+ * So this checks the exception tables on kernel faults in
+ * order to only do this all for instructions that are actually
+ * expected to fault.
+ *
+ * We can also actually take the mm lock for writing if we
+ * need to extend the vma, which helps the VM layer a lot.
+ */
+struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
+ unsigned long addr, struct pt_regs *regs)
+{
+ struct vm_area_struct *vma;
+
+ if (!get_mmap_lock_carefully(mm, regs))
+ return NULL;
+
+ vma = find_vma(mm, addr);
+ if (likely(vma && (vma->vm_start <= addr)))
+ return vma;
+
+ /*
+ * Well, dang. We might still be successful, but only
+ * if we can extend a vma to do so.
+ */
+ if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) {
+ mmap_read_unlock(mm);
+ return NULL;
+ }
+
+ /*
+ * We can try to upgrade the mmap lock atomically,
+ * in which case we can continue to use the vma
+ * we already looked up.
+ *
+ * Otherwise we'll have to drop the mmap lock and
+ * re-take it, and also look up the vma again,
+ * re-checking it.
+ */
+ if (!mmap_upgrade_trylock(mm)) {
+ if (!upgrade_mmap_lock_carefully(mm, regs))
+ return NULL;
+
+ vma = find_vma(mm, addr);
+ if (!vma)
+ goto fail;
+ if (vma->vm_start <= addr)
+ goto success;
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto fail;
+ }
+
+ if (expand_stack_locked(vma, addr))
+ goto fail;
+
+success:
+ mmap_write_downgrade(mm);
+ return vma;
+
+fail:
+ mmap_write_unlock(mm);
+ return NULL;
+}
+#endif
+
#ifndef __PAGETABLE_P4D_FOLDED
/*
* Allocate p4d page table.
if (mmap_read_lock_killable(mm))
return 0;
+ /* We might need to expand the stack to access it */
+ vma = vma_lookup(mm, addr);
+ if (!vma) {
+ vma = expand_stack(mm, addr);
+ if (!vma)
+ return 0;
+ }
+
/* ignore errors, just check how much was successfully transferred */
while (len) {
int bytes, ret, offset;