Re: [PATCH v3] x86/uaccess: Use pointer masking to limit uaccess speculation

[Thomas Gleixner]

On Mon, Sep 14 2020 at 14:53, Josh Poimboeuf wrote:
> Al,
>
> This depends on Christoph's set_fs() removal patches.  Would you be
> willing to take this in your tree?

Ack.

> On Thu, Sep 10, 2020 at 12:22:53PM -0500, Josh Poimboeuf wrote:
>> The x86 uaccess code uses barrier_nospec() in various places to prevent
>> speculative dereferencing of user-controlled pointers (which might be
>> combined with further gadgets or CPU bugs to leak data).
>> 
>> There are some issues with the current implementation:
>> 
>> - The barrier_nospec() in copy_from_user() was inadvertently removed
>>   with: 4b842e4e25b1 ("x86: get rid of small constant size cases in
>>   raw_copy_{to,from}_user()")
>> 
>> - copy_to_user() and friends should also have a speculation barrier,
>>   because a speculative write to a user-controlled address can still
>>   populate the cache line with the original data.
>> 
>> - The LFENCE in barrier_nospec() is overkill, when more lightweight user
>>   pointer masking can be used instead.
>> 
>> Remove all existing barrier_nospec() usage, and instead do user pointer
>> masking, throughout the x86 uaccess code.  This is similar to what arm64
>> is already doing with uaccess_mask_ptr().
>> 
>> barrier_nospec() is now unused, and can be removed.
>> 
>> Fixes: 4b842e4e25b1 ("x86: get rid of small constant size cases in raw_copy_{to,from}_user()")
>> Suggested-by: Will Deacon <will@xxxxxxxxxx>
>> Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>

Reviewed-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>