mm, hugepages: add mremap() support for hugepage backed vma

Support mremap() for hugepage backed vma segment by simply repositioning
page table entries.  The page table entries are repositioned to the new
virtual address on mremap().

Hugetlb mremap() support is of course generic; my motivating use case is
a library (hugepage_text), which reloads the ELF text of executables in
hugepages.  This significantly increases the execution performance of
said executables.

Restrict the mremap operation on hugepages to up to the size of the
original mapping as the underlying hugetlb reservation is not yet
capable of handling remapping to a larger size.

During the mremap() operation we detect pmd_share'd mappings and we
unshare those during the mremap().  On access and fault the sharing is
established again.

Link: https://lkml.kernel.org/r/20211013195825.3058275-1-almasrymina@google.com
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Ken Chen <kenchen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Kirill Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 33 insertions, 3 deletions

diff --git a/mm/mremap.c b/mm/mremap.c
index c0b6c41b7b78..002eec83e91e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -489,6 +489,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 	old_end = old_addr + len;
 	flush_cache_range(vma, old_addr, old_end);
 
+	if (is_vm_hugetlb_page(vma))
+		return move_hugetlb_page_tables(vma, new_vma, old_addr,
+						new_addr, len);
+
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
 				old_addr, old_end);
 	mmu_notifier_invalidate_range_start(&range);
@@ -646,6 +650,10 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		mremap_userfaultfd_prep(new_vma, uf);
 	}
 
+	if (is_vm_hugetlb_page(vma)) {
+		clear_vma_resv_huge_pages(vma);
+	}
+
 	/* Conceal VM_ACCOUNT so old reservation is not undone */
 	if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) {
 		vma->vm_flags &= ~VM_ACCOUNT;
@@ -739,9 +747,6 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 			(vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)))
 		return ERR_PTR(-EINVAL);
 
-	if (is_vm_hugetlb_page(vma))
-		return ERR_PTR(-EINVAL);
-
 	/* We can't remap across vm area boundaries */
 	if (old_len > vma->vm_end - addr)
 		return ERR_PTR(-EFAULT);
@@ -937,6 +942,31 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 
 	if (mmap_write_lock_killable(current->mm))
 		return -EINTR;
+	vma = find_vma(mm, addr);
+	if (!vma || vma->vm_start > addr) {
+		ret = EFAULT;
+		goto out;
+	}
+
+	if (is_vm_hugetlb_page(vma)) {
+		struct hstate *h __maybe_unused = hstate_vma(vma);
+
+		old_len = ALIGN(old_len, huge_page_size(h));
+		new_len = ALIGN(new_len, huge_page_size(h));
+
+		/* addrs must be huge page aligned */
+		if (addr & ~huge_page_mask(h))
+			goto out;
+		if (new_addr & ~huge_page_mask(h))
+			goto out;
+
+		/*
+		 * Don't allow remap expansion, because the underlying hugetlb
+		 * reservation is not yet capable to handle split reservation.
+		 */
+		if (new_len > old_len)
+			goto out;
+	}
 
 	if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,