From: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
commit 17457784004c84178798432a029ab20e14f728b1 upstream.
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 2e1c0170771e ("fs/proc/kcore: avoid
bounce buffer for ktext data"), reinstating the bounce buffer, but adapts
the code to continue to use an iterator.
[lstoakes@xxxxxxxxx: correct comment to be strictly correct about reasoning]
Link: https://lkml.kernel.org/r/525a3f14-74fa-4c22-9fca-9dab4de8a0c3@lucifer.local
Link: https://lkml.kernel.org/r/20230731215021.70911-1-lstoakes@xxxxxxxxx
Fixes: 2e1c0170771e ("fs/proc/kcore: avoid bounce buffer for ktext data")
Signed-off-by: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Reported-by: Jiri Olsa <olsajiri@xxxxxxxxx>
Closes: https://lore.kernel.org/all/ZHc2fm+9daF6cgCE@krava
Tested-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Tested-by: Will Deacon <will@xxxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Ard Biesheuvel <ardb@xxxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Liu Shixin <liushixin2@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Thorsten Leemhuis <regressions@xxxxxxxxxxxxx>
Cc: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/proc/kcore.c | 30 +++++++++++++++++++++++++++---
1 file changed, 27 insertions(+), 3 deletions(-)
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 9cb32e1a78a0..23fc24d16b31 100644
--- a/fs/proc/kcore.c
+++ b/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,
};
--
2.41.0
