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
  ...

3 files changed, 173 insertions, 70 deletions

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 1433f6b4607d..bdd9cc59d20f 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -31,13 +31,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
-{
-	unsigned long top_of_stack =
-		(unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING;
-	return (struct thread_info *)(top_of_stack - THREAD_SIZE);
-}
-
 #ifdef CONFIG_CONTEXT_TRACKING
 /* Called on entry from user mode with IRQs off. */
 __visible inline void enter_from_user_mode(void)
@@ -71,7 +64,7 @@ static long syscall_trace_enter(struct pt_regs *regs)
 {
 	u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 
-	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	struct thread_info *ti = current_thread_info();
 	unsigned long ret = 0;
 	bool emulated = false;
 	u32 work;
@@ -173,18 +166,17 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		/* Disable IRQs and retry */
 		local_irq_disable();
 
-		cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+		cached_flags = READ_ONCE(current_thread_info()->flags);
 
 		if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
 			break;
-
 	}
 }
 
 /* Called with IRQs disabled. */
 __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 {
-	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	struct thread_info *ti = current_thread_info();
 	u32 cached_flags;
 
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
@@ -209,7 +201,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	 * special case only applies after poking regs and before the
 	 * very next return to user mode.
 	 */
-	ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
+	current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
 #endif
 
 	user_enter_irqoff();
@@ -247,7 +239,7 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
  */
 __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 {
-	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	struct thread_info *ti = current_thread_info();
 	u32 cached_flags = READ_ONCE(ti->flags);
 
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@@ -270,7 +262,7 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 #ifdef CONFIG_X86_64
 __visible void do_syscall_64(struct pt_regs *regs)
 {
-	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	struct thread_info *ti = current_thread_info();
 	unsigned long nr = regs->orig_ax;
 
 	enter_from_user_mode();
@@ -303,11 +295,11 @@ __visible void do_syscall_64(struct pt_regs *regs)
  */
 static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 {
-	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	struct thread_info *ti = current_thread_info();
 	unsigned int nr = (unsigned int)regs->orig_ax;
 
 #ifdef CONFIG_IA32_EMULATION
-	ti->status |= TS_COMPAT;
+	current->thread.status |= TS_COMPAT;
 #endif
 
 	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 0b56666e6039..b75a8bcd2d23 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -204,34 +204,70 @@
 	POP_GS_EX
 .endm
 
+/*
+ * %eax: prev task
+ * %edx: next task
+ */
+ENTRY(__switch_to_asm)
+	/*
+	 * Save callee-saved registers
+	 * This must match the order in struct inactive_task_frame
+	 */
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%edi
+	pushl	%esi
+
+	/* switch stack */
+	movl	%esp, TASK_threadsp(%eax)
+	movl	TASK_threadsp(%edx), %esp
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+	movl	TASK_stack_canary(%edx), %ebx
+	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+#endif
+
+	/* restore callee-saved registers */
+	popl	%esi
+	popl	%edi
+	popl	%ebx
+	popl	%ebp
+
+	jmp	__switch_to
+END(__switch_to_asm)
+
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * eax: prev task we switched from
+ * ebx: kernel thread func (NULL for user thread)
+ * edi: kernel thread arg
+ */
 ENTRY(ret_from_fork)
 	pushl	%eax
 	call	schedule_tail
 	popl	%eax
 
+	testl	%ebx, %ebx
+	jnz	1f		/* kernel threads are uncommon */
+
+2:
 	/* When we fork, we trace the syscall return in the child, too. */
 	movl    %esp, %eax
 	call    syscall_return_slowpath
 	jmp     restore_all
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
-	pushl	%eax
-	call	schedule_tail
-	popl	%eax
-	movl	PT_EBP(%esp), %eax
-	call	*PT_EBX(%esp)
-	movl	$0, PT_EAX(%esp)
 
+	/* kernel thread */
+1:	movl	%edi, %eax
+	call	*%ebx
 	/*
-	 * Kernel threads return to userspace as if returning from a syscall.
-	 * We should check whether anything actually uses this path and, if so,
-	 * consider switching it over to ret_from_fork.
+	 * A kernel thread is allowed to return here after successfully
+	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * syscall.
 	 */
-	movl    %esp, %eax
-	call    syscall_return_slowpath
-	jmp     restore_all
-ENDPROC(ret_from_kernel_thread)
+	movl	$0, PT_EAX(%esp)
+	jmp	2b
+END(ret_from_fork)
 
 /*
  * Return to user mode is not as complex as all this looks,
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 02fff3ebfb87..fee1d95902b5 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -179,7 +179,8 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	 * If we need to do entry work or if we guess we'll need to do
 	 * exit work, go straight to the slow path.
 	 */
-	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	movq	PER_CPU_VAR(current_task), %r11
+	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
 	jnz	entry_SYSCALL64_slow_path
 
 entry_SYSCALL_64_fastpath:
@@ -217,7 +218,8 @@ entry_SYSCALL_64_fastpath:
 	 */
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	movq	PER_CPU_VAR(current_task), %r11
+	testl	$_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
 	jnz	1f
 
 	LOCKDEP_SYS_EXIT
@@ -351,8 +353,7 @@ ENTRY(stub_ptregs_64)
 	jmp	entry_SYSCALL64_slow_path
 
 1:
-	/* Called from C */
-	jmp	*%rax				/* called from C */
+	jmp	*%rax				/* Called from C */
 END(stub_ptregs_64)
 
 .macro ptregs_stub func
@@ -369,41 +370,73 @@ END(ptregs_\func)
 #include <asm/syscalls_64.h>
 
 /*
+ * %rdi: prev task
+ * %rsi: next task
+ */
+ENTRY(__switch_to_asm)
+	/*
+	 * Save callee-saved registers
+	 * This must match the order in inactive_task_frame
+	 */
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+
+	/* switch stack */
+	movq	%rsp, TASK_threadsp(%rdi)
+	movq	TASK_threadsp(%rsi), %rsp
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+	movq	TASK_stack_canary(%rsi), %rbx
+	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+#endif
+
+	/* restore callee-saved registers */
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+
+	jmp	__switch_to
+END(__switch_to_asm)
+
+/*
  * A newly forked process directly context switches into this address.
  *
- * rdi: prev task we switched from
+ * rax: prev task we switched from
+ * rbx: kernel thread func (NULL for user thread)
+ * r12: kernel thread arg
  */
 ENTRY(ret_from_fork)
-	LOCK ; btr $TIF_FORK, TI_flags(%r8)
-
+	movq	%rax, %rdi
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
-	testb	$3, CS(%rsp)			/* from kernel_thread? */
-	jnz	1f
+	testq	%rbx, %rbx			/* from kernel_thread? */
+	jnz	1f				/* kernel threads are uncommon */
 
-	/*
-	 * We came from kernel_thread.  This code path is quite twisted, and
-	 * someone should clean it up.
-	 *
-	 * copy_thread_tls stashes the function pointer in RBX and the
-	 * parameter to be passed in RBP.  The called function is permitted
-	 * to call do_execve and thereby jump to user mode.
-	 */
-	movq	RBP(%rsp), %rdi
-	call	*RBX(%rsp)
-	movl	$0, RAX(%rsp)
-
-	/*
-	 * Fall through as though we're exiting a syscall.  This makes a
-	 * twisted sort of sense if we just called do_execve.
-	 */
-
-1:
+2:
 	movq	%rsp, %rdi
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
 	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
 	SWAPGS
 	jmp	restore_regs_and_iret
+
+1:
+	/* kernel thread */
+	movq	%r12, %rdi
+	call	*%rbx
+	/*
+	 * A kernel thread is allowed to return here after successfully
+	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * syscall.
+	 */
+	movq	$0, RAX(%rsp)
+	jmp	2b
 END(ret_from_fork)
 
 /*
@@ -555,27 +588,69 @@ native_irq_return_iret:
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
-	pushq	%rax
-	pushq	%rdi
+	/*
+	 * We are running with user GSBASE.  All GPRs contain their user
+	 * values.  We have a percpu ESPFIX stack that is eight slots
+	 * long (see ESPFIX_STACK_SIZE).  espfix_waddr points to the bottom
+	 * of the ESPFIX stack.
+	 *
+	 * We clobber RAX and RDI in this code.  We stash RDI on the
+	 * normal stack and RAX on the ESPFIX stack.
+	 *
+	 * The ESPFIX stack layout we set up looks like this:
+	 *
+	 * --- top of ESPFIX stack ---
+	 * SS
+	 * RSP
+	 * RFLAGS
+	 * CS
+	 * RIP  <-- RSP points here when we're done
+	 * RAX  <-- espfix_waddr points here
+	 * --- bottom of ESPFIX stack ---
+	 */
+
+	pushq	%rdi				/* Stash user RDI */
 	SWAPGS
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
-	movq	%rax, (0*8)(%rdi)		/* RAX */
-	movq	(2*8)(%rsp), %rax		/* RIP */
+	movq	%rax, (0*8)(%rdi)		/* user RAX */
+	movq	(1*8)(%rsp), %rax		/* user RIP */
 	movq	%rax, (1*8)(%rdi)
-	movq	(3*8)(%rsp), %rax		/* CS */
+	movq	(2*8)(%rsp), %rax		/* user CS */
 	movq	%rax, (2*8)(%rdi)
-	movq	(4*8)(%rsp), %rax		/* RFLAGS */
+	movq	(3*8)(%rsp), %rax		/* user RFLAGS */
 	movq	%rax, (3*8)(%rdi)
-	movq	(6*8)(%rsp), %rax		/* SS */
+	movq	(5*8)(%rsp), %rax		/* user SS */
 	movq	%rax, (5*8)(%rdi)
-	movq	(5*8)(%rsp), %rax		/* RSP */
+	movq	(4*8)(%rsp), %rax		/* user RSP */
 	movq	%rax, (4*8)(%rdi)
-	andl	$0xffff0000, %eax
-	popq	%rdi
+	/* Now RAX == RSP. */
+
+	andl	$0xffff0000, %eax		/* RAX = (RSP & 0xffff0000) */
+	popq	%rdi				/* Restore user RDI */
+
+	/*
+	 * espfix_stack[31:16] == 0.  The page tables are set up such that
+	 * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
+	 * espfix_waddr for any X.  That is, there are 65536 RO aliases of
+	 * the same page.  Set up RSP so that RSP[31:16] contains the
+	 * respective 16 bits of the /userspace/ RSP and RSP nonetheless
+	 * still points to an RO alias of the ESPFIX stack.
+	 */
 	orq	PER_CPU_VAR(espfix_stack), %rax
 	SWAPGS
 	movq	%rax, %rsp
-	popq	%rax
+
+	/*
+	 * At this point, we cannot write to the stack any more, but we can
+	 * still read.
+	 */
+	popq	%rax				/* Restore user RAX */
+
+	/*
+	 * RSP now points to an ordinary IRET frame, except that the page
+	 * is read-only and RSP[31:16] are preloaded with the userspace
+	 * values.  We can now IRET back to userspace.
+	 */
 	jmp	native_irq_return_iret
 #endif
 END(common_interrupt)