x86/speculation/l1tf: Exempt zeroed PTEs from inversion

It turns out that we should *not* invert all not-present mappings,
because the all zeroes case is obviously special.

clear_page() does not undergo the XOR logic to invert the address bits,
i.e. PTE, PMD and PUD entries that have not been individually written
will have val=0 and so will trigger __pte_needs_invert(). As a result,
{pte,pmd,pud}_pfn() will return the wrong PFN value, i.e. all ones
(adjusted by the max PFN mask) instead of zero. A zeroed entry is ok
because the page at physical address 0 is reserved early in boot
specifically to mitigate L1TF, so explicitly exempt them from the
inversion when reading the PFN.

Manifested as an unexpected mprotect(..., PROT_NONE) failure when called
on a VMA that has VM_PFNMAP and was mmap'd to as something other than
PROT_NONE but never used. mprotect() sends the PROT_NONE request down
prot_none_walk(), which walks the PTEs to check the PFNs.
prot_none_pte_entry() gets the bogus PFN from pte_pfn() and returns
-EACCES because it thinks mprotect() is trying to adjust a high MMIO
address.

[ This is a very modified version of Sean's original patch, but all
credit goes to Sean for doing this and also pointing out that
sometimes the __pte_needs_invert() function only gets the protection
bits, not the full eventual pte. But zero remains special even in
just protection bits, so that's ok. - Linus ]

Fixes: f22cc87f6c1f ("x86/speculation/l1tf: Invert all not present mappings")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

x86/speculation/l1tf: Invert all not present mappings

For kernel mappings PAGE_PROTNONE is not necessarily set for a non present
mapping, but the inversion logic explicitely checks for !PRESENT and
PROT_NONE.

Remove the PROT_NONE check and make the inversion unconditional for all not
present mappings.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

x86/speculation/l1tf: Protect PROT_NONE PTEs against speculation

When PTEs are set to PROT_NONE the kernel just clears the Present bit and
preserves the PFN, which creates attack surface for L1TF speculation
speculation attacks.

This is important inside guests, because L1TF speculation bypasses physical
page remapping. While the host has its own migitations preventing leaking
data from other VMs into the guest, this would still risk leaking the wrong
page inside the current guest.

This uses the same technique as Linus' swap entry patch: while an entry is
is in PROTNONE state invert the complete PFN part part of it. This ensures
that the the highest bit will point to non existing memory.

The invert is done by pte/pmd_modify and pfn/pmd/pud_pte for PROTNONE and
pte/pmd/pud_pfn undo it.

This assume that no code path touches the PFN part of a PTE directly
without using these primitives.

This doesn't handle the case that MMIO is on the top of the CPU physical
memory. If such an MMIO region was exposed by an unpriviledged driver for
mmap it would be possible to attack some real memory. However this
situation is all rather unlikely.

For 32bit non PAE the inversion is not done because there are really not
enough bits to protect anything.

Q: Why does the guest need to be protected when the HyperVisor already has
L1TF mitigations?

A: Here's an example:

Physical pages 1 2 get mapped into a guest as
GPA 1 -> PA 2
GPA 2 -> PA 1
through EPT.

The L1TF speculation ignores the EPT remapping.

Now the guest kernel maps GPA 1 to process A and GPA 2 to process B, and
they belong to different users and should be isolated.

A sets the GPA 1 PA 2 PTE to PROT_NONE to bypass the EPT remapping and
gets read access to the underlying physical page. Which in this case
points to PA 2, so it can read process B's data, if it happened to be in
L1, so isolation inside the guest is broken.

There's nothing the hypervisor can do about this. This mitigation has to
be done in the guest itself.

[ tglx: Massaged changelog ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Dave Hansen <dave.hansen@intel.com>