x86/mm/pti: Clone kernel-image on PTE level for 32 bit

On 32 bit the kernel sections are not huge-page aligned.  When we clone
them on PMD-level we unevitably map some areas that are normal kernel
memory and may contain secrets to user-space. To prevent that we need to
clone the kernel-image on PTE-level for 32 bit.

Also make the page-table cloning code more general so that it can handle
PMD and PTE level cloning. This can be generalized further in the future to
also handle clones on the P4D-level.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1533637471-30953-4-git-send-email-joro@8bytes.org

arch/x86/mm/pti.c

@@ -54,6 +54,16 @@
 #define __GFP_NOTRACK	0
 #endif
 
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PMD
+#else
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PTE
+#endif
+
 static void __init pti_print_if_insecure(const char *reason)
 {
 	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
@@ -228,7 +238,6 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	return pmd_offset(pud, address);
 }
 
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /*
  * Walk the shadow copy of the page tables (optionally) trying to allocate
  * page table pages on the way down.  Does not support large pages.
@@ -270,6 +279,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	return pte;
 }
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 static void __init pti_setup_vsyscall(void)
 {
 	pte_t *pte, *target_pte;
@@ -290,8 +300,14 @@ static void __init pti_setup_vsyscall(void)
 static void __init pti_setup_vsyscall(void) { }
 #endif
 
+enum pti_clone_level {
+	PTI_CLONE_PMD,
+	PTI_CLONE_PTE,
+};
+
 static void
-pti_clone_pmds(unsigned long start, unsigned long end)
+pti_clone_pgtable(unsigned long start, unsigned long end,
+		  enum pti_clone_level level)
 {
 	unsigned long addr;
 
@@ -299,7 +315,8 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 	 * Clone the populated PMDs which cover start to end. These PMD areas
 	 * can have holes.
 	 */
-	for (addr = start; addr < end; addr += PMD_SIZE) {
+	for (addr = start; addr < end;) {
+		pte_t *pte, *target_pte;
 		pmd_t *pmd, *target_pmd;
 		pgd_t *pgd;
 		p4d_t *p4d;
@@ -315,13 +332,20 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 		p4d = p4d_offset(pgd, addr);
 		if (WARN_ON(p4d_none(*p4d)))
 			return;
+
 		pud = pud_offset(p4d, addr);
-		if (pud_none(*pud))
+		if (pud_none(*pud)) {
+			addr += PUD_SIZE;
 			continue;
+		}
+
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd))
+		if (pmd_none(*pmd)) {
+			addr += PMD_SIZE;
 			continue;
+		}
 
+		if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
 			target_pmd = pti_user_pagetable_walk_pmd(addr);
 			if (WARN_ON(!target_pmd))
 				return;
@@ -353,6 +377,39 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 			 * address range
 			 */
 			*target_pmd = *pmd;
+
+			addr += PMD_SIZE;
+
+		} else if (level == PTI_CLONE_PTE) {
+
+			/* Walk the page-table down to the pte level */
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte)) {
+				addr += PAGE_SIZE;
+				continue;
+			}
+
+			/* Only clone present PTEs */
+			if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+				return;
+
+			/* Allocate PTE in the user page-table */
+			target_pte = pti_user_pagetable_walk_pte(addr);
+			if (WARN_ON(!target_pte))
+				return;
+
+			/* Set GLOBAL bit in both PTEs */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+			/* Clone the PTE */
+			*target_pte = *pte;
+
+			addr += PAGE_SIZE;
+
+		} else {
+			BUG();
+		}
 	}
 }
 
@@ -398,7 +455,7 @@ static void __init pti_clone_user_shared(void)
 	start = CPU_ENTRY_AREA_BASE;
 	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
 
-	pti_clone_pmds(start, end);
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
 }
 #endif /* CONFIG_X86_64 */
 
@@ -417,8 +474,9 @@ static void __init pti_setup_espfix64(void)
  */
 static void pti_clone_entry_text(void)
 {
-	pti_clone_pmds((unsigned long) __entry_text_start,
-		       (unsigned long) __irqentry_text_end);
+	pti_clone_pgtable((unsigned long) __entry_text_start,
+			  (unsigned long) __irqentry_text_end,
+			  PTI_CLONE_PMD);
 }
 
 /*
@@ -500,10 +558,10 @@ static void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end_clone);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
 
 	/*
-	 * pti_clone_pmds() will set the global bit in any PMDs
+	 * pti_clone_pgtable() will set the global bit in any PMDs
 	 * that it clones, but we also need to get any PTEs in
 	 * the last level for areas that are not huge-page-aligned.
 	 */