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>

arch/x86/include/asm/pgtable-2level.h

@@ -95,4 +95,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+	return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_H */

arch/x86/include/asm/pgtable-3level.h

@@ -295,4 +295,6 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 	return pte;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */

arch/x86/include/asm/pgtable-invert.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return (val & (_PAGE_PRESENT|_PAGE_PROTNONE)) == _PAGE_PROTNONE;
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+	return __pte_needs_invert(val) ?  ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	/*
+	 * When a PTE transitions from NONE to !NONE or vice-versa
+	 * invert the PFN part to stop speculation.
+	 * pte_pfn undoes this when needed.
+	 */
+	if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+		val = (val & ~mask) | (~val & mask);
+	return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif

arch/x86/include/asm/pgtable.h

@@ -185,19 +185,29 @@ static inline int pte_special(pte_t pte)
 	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
+/* Entries that were set to PROT_NONE are inverted */
+
+static inline u64 protnone_mask(u64 val);
+
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	unsigned long pfn = pte_val(pte);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
+	unsigned long pfn = pmd_val(pmd);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+	unsigned long pfn = pud_val(pud);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long p4d_pfn(p4d_t p4d)
@@ -545,25 +555,33 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PTE_PFN_MASK;
+	return __pte(pfn | check_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PMD_PAGE_MASK;
+	return __pmd(pfn | check_pgprot(pgprot));
 }
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PUD_PAGE_MASK;
+	return __pud(pfn | check_pgprot(pgprot));
 }
 
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	pteval_t val = pte_val(pte);
+	pteval_t val = pte_val(pte), oldval = val;
 
 	/*
 	 * Chop off the NX bit (if present), and add the NX portion of
@@ -571,17 +589,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 */
 	val &= _PAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
 	return __pte(val);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmdval_t val = pmd_val(pmd);
+	pmdval_t val = pmd_val(pmd), oldval = val;
 
 	val &= _HPAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
 	return __pmd(val);
 }
 

arch/x86/include/asm/pgtable_64.h

@@ -357,5 +357,7 @@ static inline bool gup_fast_permitted(unsigned long start, int nr_pages,
 	return true;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */