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

Pull low-level x86 updates from Ingo Molnar:
 "In this cycle this topic tree has become one of those 'super topics'
  that accumulated a lot of changes:

   - Add CONFIG_VMAP_STACK=y support to the core kernel and enable it on
     x86 - preceded by an array of changes. v4.8 saw preparatory changes
     in this area already - this is the rest of the work. Includes the
     thread stack caching performance optimization. (Andy Lutomirski)

   - switch_to() cleanups and all around enhancements. (Brian Gerst)

   - A large number of dumpstack infrastructure enhancements and an
     unwinder abstraction. The secret long term plan is safe(r) live
     patching plus maybe another attempt at debuginfo based unwinding -
     but all these current bits are standalone enhancements in a frame
     pointer based debug environment as well. (Josh Poimboeuf)

   - More __ro_after_init and const annotations. (Kees Cook)

   - Enable KASLR for the vmemmap memory region. (Thomas Garnier)"

[ The virtually mapped stack changes are pretty fundamental, and not
  x86-specific per se, even if they are only used on x86 right now. ]

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  x86/asm: Get rid of __read_cr4_safe()
  thread_info: Use unsigned long for flags
  x86/alternatives: Add stack frame dependency to alternative_call_2()
  x86/dumpstack: Fix show_stack() task pointer regression
  x86/dumpstack: Remove dump_trace() and related callbacks
  x86/dumpstack: Convert show_trace_log_lvl() to use the new unwinder
  oprofile/x86: Convert x86_backtrace() to use the new unwinder
  x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder
  perf/x86: Convert perf_callchain_kernel() to use the new unwinder
  x86/unwind: Add new unwind interface and implementations
  x86/dumpstack: Remove NULL task pointer convention
  fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y
  sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK
  lib/syscall: Pin the task stack in collect_syscall()
  x86/process: Pin the target stack in get_wchan()
  x86/dumpstack: Pin the target stack when dumping it
  kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function
  sched/core: Add try_get_task_stack() and put_task_stack()
  x86/entry/64: Fix a minor comment rebase error
  iommu/amd: Don't put completion-wait semaphore on stack
  ...

2 files changed, 10 insertions, 10 deletions

diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 421456784bc6..b037ce9cf116 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -147,7 +147,7 @@ static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *))
 	if (args.nr != getpid() ||
 	    args.arg0 != 10 || args.arg1 != 11 || args.arg2 != 12 ||
 	    args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) {
-		printf("[FAIL]\tgetpid() failed to preseve regs\n");
+		printf("[FAIL]\tgetpid() failed to preserve regs\n");
 		nerrs++;
 	} else {
 		printf("[OK]\tgetpid() preserves regs\n");
@@ -162,7 +162,7 @@ static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *))
 	if (args.nr != 0 ||
 	    args.arg0 != getpid() || args.arg1 != SIGUSR1 || args.arg2 != 12 ||
 	    args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) {
-		printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preseve regs\n");
+		printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preserve regs\n");
 		nerrs++;
 	} else {
 		printf("[OK]\tkill(getpid(), SIGUSR1) preserves regs\n");
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 8a577e7070c6..246145b84a12 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -106,7 +106,7 @@ asm (".pushsection .text\n\t"
      ".type int3, @function\n\t"
      ".align 4096\n\t"
      "int3:\n\t"
-     "mov %ss,%eax\n\t"
+     "mov %ss,%ecx\n\t"
      "int3\n\t"
      ".size int3, . - int3\n\t"
      ".align 4096, 0xcc\n\t"
@@ -306,7 +306,7 @@ static volatile sig_atomic_t sig_corrupt_final_ss;
 #ifdef __x86_64__
 # define REG_IP REG_RIP
 # define REG_SP REG_RSP
-# define REG_AX REG_RAX
+# define REG_CX REG_RCX
 
 struct selectors {
 	unsigned short cs, gs, fs, ss;
@@ -326,7 +326,7 @@ static unsigned short *csptr(ucontext_t *ctx)
 #else
 # define REG_IP REG_EIP
 # define REG_SP REG_ESP
-# define REG_AX REG_EAX
+# define REG_CX REG_ECX
 
 static greg_t *ssptr(ucontext_t *ctx)
 {
@@ -457,10 +457,10 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 	ctx->uc_mcontext.gregs[REG_IP] =
 		sig_cs == code16_sel ? 0 : (unsigned long)&int3;
 	ctx->uc_mcontext.gregs[REG_SP] = (unsigned long)0x8badf00d5aadc0deULL;
-	ctx->uc_mcontext.gregs[REG_AX] = 0;
+	ctx->uc_mcontext.gregs[REG_CX] = 0;
 
 	memcpy(&requested_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
-	requested_regs[REG_AX] = *ssptr(ctx);	/* The asm code does this. */
+	requested_regs[REG_CX] = *ssptr(ctx);	/* The asm code does this. */
 
 	return;
 }
@@ -482,7 +482,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 	unsigned short ss;
 	asm ("mov %%ss,%0" : "=r" (ss));
 
-	greg_t asm_ss = ctx->uc_mcontext.gregs[REG_AX];
+	greg_t asm_ss = ctx->uc_mcontext.gregs[REG_CX];
 	if (asm_ss != sig_ss && sig == SIGTRAP) {
 		/* Sanity check failure. */
 		printf("[FAIL]\tSIGTRAP: ss = %hx, frame ss = %hx, ax = %llx\n",
@@ -654,8 +654,8 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss)
 #endif
 
 		/* Sanity check on the kernel */
-		if (i == REG_AX && requested_regs[i] != resulting_regs[i]) {
-			printf("[FAIL]\tAX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n",
+		if (i == REG_CX && requested_regs[i] != resulting_regs[i]) {
+			printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n",
 			       (unsigned long long)requested_regs[i],
 			       (unsigned long long)resulting_regs[i]);
 			nerrs++;