mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY

On UFFDIO_COPY, if we fail to copy the page contents while holding the
hugetlb_fault_mutex, we will drop the mutex and return to the caller after
allocating a page that consumed a reservation.  In this case there may be
a fault that double consumes the reservation.  To handle this, we free the
allocated page, fix the reservations, and allocate a temporary hugetlb
page and return that to the caller.  When the caller does the copy outside
of the lock, we again check the cache, and allocate a page consuming the
reservation, and copy over the contents.

Test:
Hacked the code locally such that resv_huge_pages underflows produce
a warning and the copy_huge_page_from_user() always fails, then:

./tools/testing/selftests/vm/userfaultfd hugetlb_shared 10
        2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success
./tools/testing/selftests/vm/userfaultfd hugetlb 10
	2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success

Both tests succeed and produce no warnings. After the
test runs number of free/resv hugepages is correct.

[yuehaibing@huawei.com: remove set but not used variable 'vm_alloc_shared']
  Link: https://lkml.kernel.org/r/20210601141610.28332-1-yuehaibing@huawei.com
[almasrymina@google.com: fix allocation error check and copy func name]
  Link: https://lkml.kernel.org/r/20210605010626.1459873-1-almasrymina@google.com

Link: https://lkml.kernel.org/r/20210528005029.88088-1-almasrymina@google.com
Signed-off-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 39 insertions, 9 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 88f2178ad7c9..b14f4d1749b2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -30,6 +30,7 @@
 #include <linux/numa.h>
 #include <linux/llist.h>
 #include <linux/cma.h>
+#include <linux/migrate.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -5076,20 +5077,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    struct page **pagep)
 {
 	bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE);
-	struct address_space *mapping;
-	pgoff_t idx;
+	struct hstate *h = hstate_vma(dst_vma);
+	struct address_space *mapping = dst_vma->vm_file->f_mapping;
+	pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr);
 	unsigned long size;
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
-	struct hstate *h = hstate_vma(dst_vma);
 	pte_t _dst_pte;
 	spinlock_t *ptl;
-	int ret;
+	int ret = -ENOMEM;
 	struct page *page;
 	int writable;
 
-	mapping = dst_vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, dst_vma, dst_addr);
-
 	if (is_continue) {
 		ret = -EFAULT;
 		page = find_lock_page(mapping, idx);
@@ -5118,12 +5116,44 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		/* fallback to copy_from_user outside mmap_lock */
 		if (unlikely(ret)) {
 			ret = -ENOENT;
+			/* Free the allocated page which may have
+			 * consumed a reservation.
+			 */
+			restore_reserve_on_error(h, dst_vma, dst_addr, page);
+			put_page(page);
+
+			/* Allocate a temporary page to hold the copied
+			 * contents.
+			 */
+			page = alloc_huge_page_vma(h, dst_vma, dst_addr);
+			if (!page) {
+				ret = -ENOMEM;
+				goto out;
+			}
 			*pagep = page;
-			/* don't free the page */
+			/* Set the outparam pagep and return to the caller to
+			 * copy the contents outside the lock. Don't free the
+			 * page.
+			 */
 			goto out;
 		}
 	} else {
-		page = *pagep;
+		if (vm_shared &&
+		    hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) {
+			put_page(*pagep);
+			ret = -EEXIST;
+			*pagep = NULL;
+			goto out;
+		}
+
+		page = alloc_huge_page(dst_vma, dst_addr, 0);
+		if (IS_ERR(page)) {
+			ret = -ENOMEM;
+			*pagep = NULL;
+			goto out;
+		}
+		copy_huge_page(page, *pagep);
+		put_page(*pagep);
 		*pagep = NULL;
 	}