mm/slab_common.c: fix possible spectre-v1 in kmalloc_slab()
Review
Quoted 5 lines
I think it makes more sense to sanitize size in
size_index_elem(), don't you?(quoted diff) +1
-1- return (bytes - 1) / 8; + return array_index_nospec((bytes - 1) / 8, ARRAY_SIZE(size_index));
I think it should be fixed in poll.
Literally every small variable kmalloc call is going through this function.
Quoted 8 lines · Alexey Dobriyan
Review
Quoted 5 lines
I think it makes more sense to sanitize size in
size_index_elem(), don't you?(quoted diff) +1
-1- return (bytes - 1) / 8; + return array_index_nospec((bytes - 1) / 8, ARRAY_SIZE(size_index));I think it should be fixed in poll.
Literally every small variable kmalloc call is going through this function.
We could do that too, but don't we then have to audit every ioctl and similar to see if there's a k(v)malloc based on a size passed from userspace?