Map the vsyscall page with _PAGE_USER

This needs to happen early in kaiser_pagetable_walk(), before the
hierarchy is established so that _PAGE_USER permission can be really
set.

A proper fix would be to teach kaiser_pagetable_walk() to update those
permissions but the vsyscall page is the only exception here so ...
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -66,6 +66,11 @@ static int __init vsyscall_setup(char *str)
 }
 early_param("vsyscall", vsyscall_setup);
 
+bool vsyscall_enabled(void)
+{
+	return vsyscall_mode != NONE;
+}
+
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 			      const char *message)
 {

arch/x86/include/asm/vsyscall.h

@@ -12,12 +12,14 @@ extern void map_vsyscall(void);
  * Returns true if handled.
  */
 extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+extern bool vsyscall_enabled(void);
 #else
 static inline void map_vsyscall(void) {}
 static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 {
 	return false;
 }
+static inline bool vsyscall_enabled(void) { return false; }
 #endif
 
 #endif /* _ASM_X86_VSYSCALL_H */

arch/x86/mm/kaiser.c

@@ -20,6 +20,7 @@
 #include <asm/pgalloc.h>
 #include <asm/desc.h>
 #include <asm/cmdline.h>
+#include <asm/vsyscall.h>
 
 int kaiser_enabled __read_mostly = 1;
 EXPORT_SYMBOL(kaiser_enabled);	/* for inlined TLB flush functions */
@@ -111,12 +112,13 @@ static inline unsigned long get_pa_from_mapping(unsigned long vaddr)
  *
  * Returns a pointer to a PTE on success, or NULL on failure.
  */
-static pte_t *kaiser_pagetable_walk(unsigned long address)
+static pte_t *kaiser_pagetable_walk(unsigned long address, bool user)
 {
 	pmd_t *pmd;
 	pud_t *pud;
 	pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	unsigned long prot = _KERNPG_TABLE;
 
 	if (pgd_none(*pgd)) {
 		WARN_ONCE(1, "All shadow pgds should have been populated");
@@ -124,6 +126,17 @@ static pte_t *kaiser_pagetable_walk(unsigned long address)
 	}
 	BUILD_BUG_ON(pgd_large(*pgd) != 0);
 
+	if (user) {
+		/*
+		 * The vsyscall page is the only page that will have
+		 *  _PAGE_USER set. Catch everything else.
+		 */
+		BUG_ON(address != VSYSCALL_ADDR);
+
+		set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+		prot = _PAGE_TABLE;
+	}
+
 	pud = pud_offset(pgd, address);
 	/* The shadow page tables do not use large mappings: */
 	if (pud_large(*pud)) {
@@ -136,7 +149,7 @@ static pte_t *kaiser_pagetable_walk(unsigned long address)
 			return NULL;
 		spin_lock(&shadow_table_allocation_lock);
 		if (pud_none(*pud)) {
-			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+			set_pud(pud, __pud(prot | __pa(new_pmd_page)));
 			__inc_zone_page_state(virt_to_page((void *)
 						new_pmd_page), NR_KAISERTABLE);
 		} else
@@ -156,7 +169,7 @@ static pte_t *kaiser_pagetable_walk(unsigned long address)
 			return NULL;
 		spin_lock(&shadow_table_allocation_lock);
 		if (pmd_none(*pmd)) {
-			set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+			set_pmd(pmd, __pmd(prot | __pa(new_pte_page)));
 			__inc_zone_page_state(virt_to_page((void *)
 						new_pte_page), NR_KAISERTABLE);
 		} else
@@ -192,7 +205,7 @@ static int kaiser_add_user_map(const void *__start_addr, unsigned long size,
 			ret = -EIO;
 			break;
 		}
-		pte = kaiser_pagetable_walk(address);
+		pte = kaiser_pagetable_walk(address, flags & _PAGE_USER);
 		if (!pte) {
 			ret = -ENOMEM;
 			break;
@@ -319,6 +332,19 @@ void __init kaiser_init(void)
 
 	kaiser_init_all_pgds();
 
+	/*
+	 * Note that this sets _PAGE_USER and it needs to happen when the
+	 * pagetable hierarchy gets created, i.e., early. Otherwise
+	 * kaiser_pagetable_walk() will encounter initialized PTEs in the
+	 * hierarchy and not set the proper permissions, leading to the
+	 * pagefaults with page-protection violations when trying to read the
+	 * vsyscall page. For example.
+	 */
+	if (vsyscall_enabled())
+		kaiser_add_user_map_early((void *)VSYSCALL_ADDR,
+					  PAGE_SIZE,
+					   __PAGE_KERNEL_VSYSCALL);
+
 	for_each_possible_cpu(cpu) {
 		void *percpu_vaddr = __per_cpu_user_mapped_start +
 				     per_cpu_offset(cpu);