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

…x/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
  ...

Documentation/trace/ftrace-design.txt

@@ -203,6 +203,17 @@ along to ftrace_push_return_trace() instead of a stub value of 0.
 
 Similarly, when you call ftrace_return_to_handler(), pass it the frame pointer.
 
+HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+--------------------------------
+
+An arch may pass in a pointer to the return address on the stack.  This
+prevents potential stack unwinding issues where the unwinder gets out of
+sync with ret_stack and the wrong addresses are reported by
+ftrace_graph_ret_addr().
+
+Adding support for it is easy: just define the macro in asm/ftrace.h and
+pass the return address pointer as the 'retp' argument to
+ftrace_push_return_trace().
 
 HAVE_FTRACE_NMI_ENTER
 ---------------------

arch/Kconfig

@@ -696,4 +696,38 @@ config ARCH_NO_COHERENT_DMA_MMAP
 config CPU_NO_EFFICIENT_FFS
 	def_bool n
 
+config HAVE_ARCH_VMAP_STACK
+	def_bool n
+	help
+	  An arch should select this symbol if it can support kernel stacks
+	  in vmalloc space.  This means:
+
+	  - vmalloc space must be large enough to hold many kernel stacks.
+	    This may rule out many 32-bit architectures.
+
+	  - Stacks in vmalloc space need to work reliably.  For example, if
+	    vmap page tables are created on demand, either this mechanism
+	    needs to work while the stack points to a virtual address with
+	    unpopulated page tables or arch code (switch_to() and switch_mm(),
+	    most likely) needs to ensure that the stack's page table entries
+	    are populated before running on a possibly unpopulated stack.
+
+	  - If the stack overflows into a guard page, something reasonable
+	    should happen.  The definition of "reasonable" is flexible, but
+	    instantly rebooting without logging anything would be unfriendly.
+
+config VMAP_STACK
+	default y
+	bool "Use a virtually-mapped stack"
+	depends on HAVE_ARCH_VMAP_STACK && !KASAN
+	---help---
+	  Enable this if you want the use virtually-mapped kernel stacks
+	  with guard pages.  This causes kernel stack overflows to be
+	  caught immediately rather than causing difficult-to-diagnose
+	  corruption.
+
+	  This is presently incompatible with KASAN because KASAN expects
+	  the stack to map directly to the KASAN shadow map using a formula
+	  that is incorrect if the stack is in vmalloc space.
+
 source "kernel/gcov/Kconfig"

arch/arm/kernel/ftrace.c

@@ -218,7 +218,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	}
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer);
+				       frame_pointer, NULL);
 	if (err == -EBUSY) {
 		*parent = old;
 		return;

arch/arm64/kernel/entry-ftrace.S

@@ -219,7 +219,7 @@ ENDPROC(ftrace_graph_caller)
  *
  * Run ftrace_return_to_handler() before going back to parent.
  * @fp is checked against the value passed by ftrace_graph_caller()
- * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
+ * only when HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
  */
 ENTRY(return_to_handler)
 	save_return_regs

arch/arm64/kernel/ftrace.c

@@ -138,7 +138,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer);
+				       frame_pointer, NULL);
 	if (err == -EBUSY)
 		return;
 	else

arch/blackfin/kernel/ftrace-entry.S

@@ -169,7 +169,7 @@ ENTRY(_ftrace_graph_caller)
 	r0 = sp;	/* unsigned long *parent */
 	r1 = [sp];	/* unsigned long self_addr */
 # endif
-# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+# ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	r2 = fp;	/* unsigned long frame_pointer */
 # endif
 	r0 += 16;	/* skip the 4 local regs on stack */
@@ -190,7 +190,7 @@ ENTRY(_return_to_handler)
 	[--sp] = r1;
 
 	/* get original return address */
-# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+# ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	r0 = fp;	/* Blackfin is sane, so omit this */
 # endif
 	call _ftrace_return_to_handler;

arch/blackfin/kernel/ftrace.c

@@ -107,7 +107,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		return;
 
 	if (ftrace_push_return_trace(*parent, self_addr, &trace.depth,
-	                             frame_pointer) == -EBUSY)
+				     frame_pointer, NULL) == -EBUSY)
 		return;
 
 	trace.func = self_addr;

arch/ia64/include/asm/thread_info.h

@@ -56,7 +56,7 @@ struct thread_info {
 #define alloc_thread_stack_node(tsk, node)	((unsigned long *) 0)
 #define task_thread_info(tsk)	((struct thread_info *) 0)
 #endif
-#define free_thread_stack(ti)	/* nothing */
+#define free_thread_stack(tsk)	/* nothing */
 #define task_stack_page(tsk)	((void *)(tsk))
 
 #define __HAVE_THREAD_FUNCTIONS

arch/microblaze/kernel/ftrace.c

@@ -63,7 +63,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL);
 	if (err == -EBUSY) {
 		*parent = old;
 		return;

arch/mips/kernel/ftrace.c

@@ -382,8 +382,8 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
 	if (unlikely(faulted))
 		goto out;
 
-	if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp)
-	    == -EBUSY) {
+	if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp,
+				     NULL) == -EBUSY) {
 		*parent_ra_addr = old_parent_ra;
 		return;
 	}

arch/parisc/kernel/ftrace.c

@@ -48,7 +48,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent,
 		return;
 
         if (ftrace_push_return_trace(old, self_addr, &trace.depth,
-			0 ) == -EBUSY)
+				     0, NULL) == -EBUSY)
                 return;
 
 	/* activate parisc_return_to_handler() as return point */

arch/powerpc/kernel/ftrace.c

@@ -593,7 +593,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 	if (!ftrace_graph_entry(&trace))
 		goto out;
 
-	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+				     NULL) == -EBUSY)
 		goto out;
 
 	parent = return_hooker;

arch/s390/kernel/ftrace.c

@@ -209,7 +209,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 	/* Only trace if the calling function expects to. */
 	if (!ftrace_graph_entry(&trace))
 		goto out;
-	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+				     NULL) == -EBUSY)
 		goto out;
 	parent = (unsigned long) return_to_handler;
 out:

arch/sh/kernel/ftrace.c

@@ -382,7 +382,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL);
 	if (err == -EBUSY) {
 		__raw_writel(old, parent);
 		return;

arch/sparc/Kconfig

@@ -56,7 +56,6 @@ config SPARC64
 	def_bool 64BIT
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP

arch/sparc/include/asm/ftrace.h

@@ -9,6 +9,10 @@
 void _mcount(void);
 #endif
 
+#endif /* CONFIG_MCOUNT */
+
+#if defined(CONFIG_SPARC64) && !defined(CC_USE_FENTRY)
+#define HAVE_FUNCTION_GRAPH_FP_TEST
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE

arch/sparc/kernel/ftrace.c

@@ -131,7 +131,7 @@ unsigned long prepare_ftrace_return(unsigned long parent,
 		return parent + 8UL;
 
 	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
-				     frame_pointer) == -EBUSY)
+				     frame_pointer, NULL) == -EBUSY)
 		return parent + 8UL;
 
 	trace.func = self_addr;

arch/tile/kernel/ftrace.c

@@ -184,7 +184,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	*parent = return_hooker;
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
-				       frame_pointer);
+				       frame_pointer, NULL);
 	if (err == -EBUSY) {
 		*parent = old;
 		return;

arch/x86/Kconfig

@@ -93,6 +93,7 @@ config X86
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_EBPF_JIT			if X86_64
+	select HAVE_ARCH_VMAP_STACK		if X86_64
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
@@ -109,7 +110,6 @@ config X86
 	select HAVE_EXIT_THREAD
 	select HAVE_FENTRY			if X86_64
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
@@ -157,6 +157,7 @@ config X86
 	select SPARSE_IRQ
 	select SRCU
 	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
 	select USER_STACKTRACE_SUPPORT
 	select VIRT_TO_BUS
 	select X86_DEV_DMA_OPS			if X86_64

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) {