Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 PTI and Spectre related fixes and updates from Ingo Molnar:
 "Here's the latest set of Spectre and PTI related fixes and updates:

  Spectre:
   - Add entry code register clearing to reduce the Spectre attack
     surface
   - Update the Spectre microcode blacklist
   - Inline the KVM Spectre helpers to get close to v4.14 performance
     again.
   - Fix indirect_branch_prediction_barrier()
   - Fix/improve Spectre related kernel messages
   - Fix array_index_nospec_mask() asm constraint
   - KVM: fix two MSR handling bugs

  PTI:
   - Fix a paranoid entry PTI CR3 handling bug
   - Fix comments

  objtool:
   - Fix paranoid_entry() frame pointer warning
   - Annotate WARN()-related UD2 as reachable
   - Various fixes
   - Add Add Peter Zijlstra as objtool co-maintainer

  Misc:
   - Various x86 entry code self-test fixes
   - Improve/simplify entry code stack frame generation and handling
     after recent heavy-handed PTI and Spectre changes. (There's two
     more WIP improvements expected here.)
   - Type fix for cache entries

  There's also some low risk non-fix changes I've included in this
  branch to reduce backporting conflicts:

   - rename a confusing x86_cpu field name
   - de-obfuscate the naming of single-TLB flushing primitives"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  x86/entry/64: Fix CR3 restore in paranoid_exit()
  x86/cpu: Change type of x86_cache_size variable to unsigned int
  x86/spectre: Fix an error message
  x86/cpu: Rename cpu_data.x86_mask to cpu_data.x86_stepping
  selftests/x86/mpx: Fix incorrect bounds with old _sigfault
  x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]()
  x86/speculation: Add <asm/msr-index.h> dependency
  nospec: Move array_index_nospec() parameter checking into separate macro
  x86/speculation: Fix up array_index_nospec_mask() asm constraint
  x86/debug: Use UD2 for WARN()
  x86/debug, objtool: Annotate WARN()-related UD2 as reachable
  objtool: Fix segfault in ignore_unreachable_insn()
  selftests/x86: Disable tests requiring 32-bit support on pure 64-bit systems
  selftests/x86: Do not rely on "int $0x80" in single_step_syscall.c
  selftests/x86: Do not rely on "int $0x80" in test_mremap_vdso.c
  selftests/x86: Fix build bug caused by the 5lvl test which has been moved to the VM directory
  selftests/x86/pkeys: Remove unused functions
  selftests/x86: Clean up and document sscanf() usage
  selftests/x86: Fix vDSO selftest segfault for vsyscall=none
  x86/entry/64: Remove the unused 'icebp' macro
  ...

9 files changed, 159 insertions, 54 deletions

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index b00b1896547e..a8cb69a26576 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -852,8 +852,14 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
  *    This is a fairly uncommon pattern which is new for GCC 6.  As of this
  *    writing, there are 11 occurrences of it in the allmodconfig kernel.
  *
+ *    As of GCC 7 there are quite a few more of these and the 'in between' code
+ *    is significant. Esp. with KASAN enabled some of the code between the mov
+ *    and jmpq uses .rodata itself, which can confuse things.
+ *
  *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
  *    ensure the same register is used in the mov and jump instructions.
+ *
+ *    NOTE: RETPOLINE made it harder still to decode dynamic jumps.
  */
 static struct rela *find_switch_table(struct objtool_file *file,
 				      struct symbol *func,
@@ -875,12 +881,25 @@ static struct rela *find_switch_table(struct objtool_file *file,
 						text_rela->addend + 4);
 		if (!rodata_rela)
 			return NULL;
+
 		file->ignore_unreachables = true;
 		return rodata_rela;
 	}
 
 	/* case 3 */
-	func_for_each_insn_continue_reverse(file, func, insn) {
+	/*
+	 * Backward search using the @first_jump_src links, these help avoid
+	 * much of the 'in between' code. Which avoids us getting confused by
+	 * it.
+	 */
+	for (insn = list_prev_entry(insn, list);
+
+	     &insn->list != &file->insn_list &&
+	     insn->sec == func->sec &&
+	     insn->offset >= func->offset;
+
+	     insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
+
 		if (insn->type == INSN_JUMP_DYNAMIC)
 			break;
 
@@ -910,14 +929,32 @@ static struct rela *find_switch_table(struct objtool_file *file,
 	return NULL;
 }
 
+
 static int add_func_switch_tables(struct objtool_file *file,
 				  struct symbol *func)
 {
-	struct instruction *insn, *prev_jump = NULL;
+	struct instruction *insn, *last = NULL, *prev_jump = NULL;
 	struct rela *rela, *prev_rela = NULL;
 	int ret;
 
 	func_for_each_insn(file, func, insn) {
+		if (!last)
+			last = insn;
+
+		/*
+		 * Store back-pointers for unconditional forward jumps such
+		 * that find_switch_table() can back-track using those and
+		 * avoid some potentially confusing code.
+		 */
+		if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest &&
+		    insn->offset > last->offset &&
+		    insn->jump_dest->offset > insn->offset &&
+		    !insn->jump_dest->first_jump_src) {
+
+			insn->jump_dest->first_jump_src = insn;
+			last = insn->jump_dest;
+		}
+
 		if (insn->type != INSN_JUMP_DYNAMIC)
 			continue;
 
@@ -1899,13 +1936,19 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 		if (is_kasan_insn(insn) || is_ubsan_insn(insn))
 			return true;
 
-		if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) {
-			insn = insn->jump_dest;
-			continue;
+		if (insn->type == INSN_JUMP_UNCONDITIONAL) {
+			if (insn->jump_dest &&
+			    insn->jump_dest->func == insn->func) {
+				insn = insn->jump_dest;
+				continue;
+			}
+
+			break;
 		}
 
 		if (insn->offset + insn->len >= insn->func->offset + insn->func->len)
 			break;
+
 		insn = list_next_entry(insn, list);
 	}
 
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index dbadb304a410..23a1d065cae1 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -47,6 +47,7 @@ struct instruction {
 	bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts;
 	struct symbol *call_dest;
 	struct instruction *jump_dest;
+	struct instruction *first_jump_src;
 	struct list_head alts;
 	struct symbol *func;
 	struct stack_op stack_op;
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 10ca46df1449..d744991c0f4f 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -5,16 +5,26 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \
+UNAME_M := $(shell uname -m)
+CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
+
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
+			check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \
 			protection_keys test_vdso test_vsyscall
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
+# Some selftests require 32bit support enabled also on 64bit systems
+TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
-TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) $(TARGETS_C_32BIT_NEEDED)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
+ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),11)
+TARGETS_C_64BIT_ALL += $(TARGETS_C_32BIT_NEEDED)
+endif
+
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
 BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
@@ -23,10 +33,6 @@ BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
 
-UNAME_M := $(shell uname -m)
-CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
-CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
-
 define gen-target-rule-32
 $(1) $(1)_32: $(OUTPUT)/$(1)_32
 .PHONY: $(1) $(1)_32
@@ -40,12 +46,14 @@ endef
 ifeq ($(CAN_BUILD_I386),1)
 all: all_32
 TEST_PROGS += $(BINARIES_32)
+EXTRA_CFLAGS += -DCAN_BUILD_32
 $(foreach t,$(TARGETS_C_32BIT_ALL),$(eval $(call gen-target-rule-32,$(t))))
 endif
 
 ifeq ($(CAN_BUILD_X86_64),1)
 all: all_64
 TEST_PROGS += $(BINARIES_64)
+EXTRA_CFLAGS += -DCAN_BUILD_64
 $(foreach t,$(TARGETS_C_64BIT_ALL),$(eval $(call gen-target-rule-64,$(t))))
 endif
 
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index ec0f6b45ce8b..9c0325e1ea68 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -315,11 +315,39 @@ static inline void *__si_bounds_upper(siginfo_t *si)
 	return si->si_upper;
 }
 #else
+
+/*
+ * This deals with old version of _sigfault in some distros:
+ *
+
+old _sigfault:
+        struct {
+            void *si_addr;
+	} _sigfault;
+
+new _sigfault:
+	struct {
+		void __user *_addr;
+		int _trapno;
+		short _addr_lsb;
+		union {
+			struct {
+				void __user *_lower;
+				void __user *_upper;
+			} _addr_bnd;
+			__u32 _pkey;
+		};
+	} _sigfault;
+ *
+ */
+
 static inline void **__si_bounds_hack(siginfo_t *si)
 {
 	void *sigfault = &si->_sifields._sigfault;
 	void *end_sigfault = sigfault + sizeof(si->_sifields._sigfault);
-	void **__si_lower = end_sigfault;
+	int *trapno = (int*)end_sigfault;
+	/* skip _trapno and _addr_lsb */
+	void **__si_lower = (void**)(trapno + 2);
 
 	return __si_lower;
 }
@@ -331,7 +359,7 @@ static inline void *__si_bounds_lower(siginfo_t *si)
 
 static inline void *__si_bounds_upper(siginfo_t *si)
 {
-	return (*__si_bounds_hack(si)) + sizeof(void *);
+	return *(__si_bounds_hack(si) + 1);
 }
 #endif
 
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index bc1b0735bb50..f15aa5a76fe3 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -393,34 +393,6 @@ pid_t fork_lazy_child(void)
 	return forkret;
 }
 
-void davecmp(void *_a, void *_b, int len)
-{
-	int i;
-	unsigned long *a = _a;
-	unsigned long *b = _b;
-
-	for (i = 0; i < len / sizeof(*a); i++) {
-		if (a[i] == b[i])
-			continue;
-
-		dprintf3("[%3d]: a: %016lx b: %016lx\n", i, a[i], b[i]);
-	}
-}
-
-void dumpit(char *f)
-{
-	int fd = open(f, O_RDONLY);
-	char buf[100];
-	int nr_read;
-
-	dprintf2("maps fd: %d\n", fd);
-	do {
-		nr_read = read(fd, &buf[0], sizeof(buf));
-		write(1, buf, nr_read);
-	} while (nr_read > 0);
-	close(fd);
-}
-
 #define PKEY_DISABLE_ACCESS    0x1
 #define PKEY_DISABLE_WRITE     0x2
 
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index a48da95c18fd..ddfdd635de16 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -119,7 +119,9 @@ static void check_result(void)
 
 int main()
 {
+#ifdef CAN_BUILD_32
 	int tmp;
+#endif
 
 	sethandler(SIGTRAP, sigtrap, 0);
 
@@ -139,12 +141,13 @@ int main()
 		      : : "c" (post_nop) : "r11");
 	check_result();
 #endif
-
+#ifdef CAN_BUILD_32
 	printf("[RUN]\tSet TF and check int80\n");
 	set_eflags(get_eflags() | X86_EFLAGS_TF);
 	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
 			: INT80_CLOBBERS);
 	check_result();
+#endif
 
 	/*
 	 * This test is particularly interesting if fast syscalls use
diff --git a/tools/testing/selftests/x86/test_mremap_vdso.c b/tools/testing/selftests/x86/test_mremap_vdso.c
index bf0d687c7db7..64f11c8d9b76 100644
--- a/tools/testing/selftests/x86/test_mremap_vdso.c
+++ b/tools/testing/selftests/x86/test_mremap_vdso.c
@@ -90,8 +90,12 @@ int main(int argc, char **argv, char **envp)
 			vdso_size += PAGE_SIZE;
 		}
 
+#ifdef __i386__
 		/* Glibc is likely to explode now - exit with raw syscall */
 		asm volatile ("int $0x80" : : "a" (__NR_exit), "b" (!!ret));
+#else /* __x86_64__ */
+		syscall(SYS_exit, ret);
+#endif
 	} else {
 		int status;
 
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 29973cde06d3..235259011704 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -26,20 +26,59 @@
 # endif
 #endif
 
+/* max length of lines in /proc/self/maps - anything longer is skipped here */
+#define MAPS_LINE_LEN 128
+
 int nerrs = 0;
 
+typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
+
+getcpu_t vgetcpu;
+getcpu_t vdso_getcpu;
+
+static void *vsyscall_getcpu(void)
+{
 #ifdef __x86_64__
-# define VSYS(x) (x)
+	FILE *maps;
+	char line[MAPS_LINE_LEN];
+	bool found = false;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) /* might still be present, but ignore it here, as we test vDSO not vsyscall */
+		return NULL;
+
+	while (fgets(line, MAPS_LINE_LEN, maps)) {
+		char r, x;
+		void *start, *end;
+		char name[MAPS_LINE_LEN];
+
+		/* sscanf() is safe here as strlen(name) >= strlen(line) */
+		if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s",
+			   &start, &end, &r, &x, name) != 5)
+			continue;
+
+		if (strcmp(name, "[vsyscall]"))
+			continue;
+
+		/* assume entries are OK, as we test vDSO here not vsyscall */
+		found = true;
+		break;
+	}
+
+	fclose(maps);
+
+	if (!found) {
+		printf("Warning: failed to find vsyscall getcpu\n");
+		return NULL;
+	}
+	return (void *) (0xffffffffff600800);
 #else
-# define VSYS(x) 0
+	return NULL;
 #endif
+}
 
-typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
-
-const getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800);
-getcpu_t vdso_getcpu;
 
-void fill_function_pointers()
+static void fill_function_pointers()
 {
 	void *vdso = dlopen("linux-vdso.so.1",
 			    RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
@@ -54,6 +93,8 @@ void fill_function_pointers()
 	vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu");
 	if (!vdso_getcpu)
 		printf("Warning: failed to find getcpu in vDSO\n");
+
+	vgetcpu = (getcpu_t) vsyscall_getcpu();
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index 7a744fa7b786..be81621446f0 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -33,6 +33,9 @@
 # endif
 #endif
 
+/* max length of lines in /proc/self/maps - anything longer is skipped here */
+#define MAPS_LINE_LEN 128
+
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		       int flags)
 {
@@ -98,7 +101,7 @@ static int init_vsys(void)
 #ifdef __x86_64__
 	int nerrs = 0;
 	FILE *maps;
-	char line[128];
+	char line[MAPS_LINE_LEN];
 	bool found = false;
 
 	maps = fopen("/proc/self/maps", "r");
@@ -108,10 +111,12 @@ static int init_vsys(void)
 		return 0;
 	}
 
-	while (fgets(line, sizeof(line), maps)) {
+	while (fgets(line, MAPS_LINE_LEN, maps)) {
 		char r, x;
 		void *start, *end;
-		char name[128];
+		char name[MAPS_LINE_LEN];
+
+		/* sscanf() is safe here as strlen(name) >= strlen(line) */
 		if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s",
 			   &start, &end, &r, &x, name) != 5)
 			continue;