fs/proc/kcore: reinstate bounce buffer for KCORE_TEXT regions

Some architectures do not populate the entire range categorised by
KCORE_TEXT, so we must ensure that the kernel address we read from is
valid.

Unfortunately there is no solution currently available to do so with a
purely iterator solution so reinstate the bounce buffer in this instance
so we can use copy_from_kernel_nofault() in order to avoid page faults
when regions are unmapped.

This change partly reverts commit 2e1c017 ("fs/proc/kcore: avoid
bounce buffer for ktext data"), reinstating the bounce buffer, but adapts
the code to continue to use an iterator.

[[email protected]: correct comment to be strictly correct about reasoning]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 2e1c017 ("fs/proc/kcore: avoid bounce buffer for ktext data")
Signed-off-by: Lorenzo Stoakes <[email protected]>
Reported-by: Jiri Olsa <[email protected]>
Closes: https://lore.kernel.org/all/ZHc2fm+9daF6cgCE@krava
Tested-by: Jiri Olsa <[email protected]>
Tested-by: Will Deacon <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Baoquan He <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Kefeng Wang <[email protected]>
Cc: Liu Shixin <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Thorsten Leemhuis <[email protected]>
Cc: Uladzislau Rezki (Sony) <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: lorenzo-stoakes

fs/proc/kcore.c

@@ -309,6 +309,8 @@ static void append_kcore_note(char *notes, size_t *i, const char *name,
 
 static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
+	struct file *file = iocb->ki_filp;
+	char *buf = file->private_data;
 	loff_t *fpos = &iocb->ki_pos;
 	size_t phdrs_offset, notes_offset, data_offset;
 	size_t page_offline_frozen = 1;
@@ -555,10 +557,21 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 		case KCORE_VMEMMAP:
 		case KCORE_TEXT:
 			/*
-			 * We use _copy_to_iter() to bypass usermode hardening
-			 * which would otherwise prevent this operation.
+			 * Sadly we must use a bounce buffer here to be able to
+			 * make use of copy_from_kernel_nofault(), as these
+			 * memory regions might not always be mapped on all
+			 * architectures.
 			 */
-			if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
+			if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
+				if (iov_iter_zero(tsz, iter) != tsz) {
+					ret = -EFAULT;
+					goto out;
+				}
+			/*
+			 * We know the bounce buffer is safe to copy from, so
+			 * use _copy_to_iter() directly.
+			 */
+			} else if (_copy_to_iter(buf, tsz, iter) != tsz) {
 				ret = -EFAULT;
 				goto out;
 			}
@@ -595,6 +608,10 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
+	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!filp->private_data)
+		return -ENOMEM;
+
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {
@@ -605,9 +622,16 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int release_kcore(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
 static const struct proc_ops kcore_proc_ops = {
 	.proc_read_iter	= read_kcore_iter,
 	.proc_open	= open_kcore,
+	.proc_release	= release_kcore,
 	.proc_lseek	= default_llseek,
 };