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, 71 insertions, 2 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index dc80230..0b92fce 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -753,6 +753,38 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		return;
 	}
 
+#ifdef CONFIG_VMAP_STACK
+	/*
+	 * Stack overflow?  During boot, we can fault near the initial
+	 * stack in the direct map, but that's not an overflow -- check
+	 * that we're in vmalloc space to avoid this.
+	 */
+	if (is_vmalloc_addr((void *)address) &&
+	    (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
+	     address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
+		register void *__sp asm("rsp");
+		unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
+		/*
+		 * We're likely to be running with very little stack space
+		 * left.  It's plausible that we'd hit this condition but
+		 * double-fault even before we get this far, in which case
+		 * we're fine: the double-fault handler will deal with it.
+		 *
+		 * We don't want to make it all the way into the oops code
+		 * and then double-fault, though, because we're likely to
+		 * break the console driver and lose most of the stack dump.
+		 */
+		asm volatile ("movq %[stack], %%rsp\n\t"
+			      "call handle_stack_overflow\n\t"
+			      "1: jmp 1b"
+			      : "+r" (__sp)
+			      : "D" ("kernel stack overflow (page fault)"),
+				"S" (regs), "d" (address),
+				[stack] "rm" (stack));
+		unreachable();
+	}
+#endif
+
 	/*
 	 * 32-bit:
 	 *
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index bda8d5e..ddd2661 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -40,17 +40,26 @@
  * You need to add an if/def entry if you introduce a new memory region
  * compatible with KASLR. Your entry must be in logical order with memory
  * layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to
+ * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
  * ensure that this order is correct and won't be changed.
  */
 static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-static const unsigned long vaddr_end = VMEMMAP_START;
+
+#if defined(CONFIG_X86_ESPFIX64)
+static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
+#elif defined(CONFIG_EFI)
+static const unsigned long vaddr_end = EFI_VA_START;
+#else
+static const unsigned long vaddr_end = __START_KERNEL_map;
+#endif
 
 /* Default values */
 unsigned long page_offset_base = __PAGE_OFFSET_BASE;
 EXPORT_SYMBOL(page_offset_base);
 unsigned long vmalloc_base = __VMALLOC_BASE;
 EXPORT_SYMBOL(vmalloc_base);
+unsigned long vmemmap_base = __VMEMMAP_BASE;
+EXPORT_SYMBOL(vmemmap_base);
 
 /*
  * Memory regions randomized by KASLR (except modules that use a separate logic
@@ -63,6 +72,7 @@ static __initdata struct kaslr_memory_region {
 } kaslr_regions[] = {
 	{ &page_offset_base, 64/* Maximum */ },
 	{ &vmalloc_base, VMALLOC_SIZE_TB },
+	{ &vmemmap_base, 1 },
 };
 
 /* Get size in bytes used by the memory region */
@@ -89,6 +99,18 @@ void __init kernel_randomize_memory(void)
 	struct rnd_state rand_state;
 	unsigned long remain_entropy;
 
+	/*
+	 * All these BUILD_BUG_ON checks ensures the memory layout is
+	 * consistent with the vaddr_start/vaddr_end variables.
+	 */
+	BUILD_BUG_ON(vaddr_start >= vaddr_end);
+	BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+		     vaddr_end >= EFI_VA_START);
+	BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
+		      config_enabled(CONFIG_EFI)) &&
+		     vaddr_end >= __START_KERNEL_map);
+	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
 	if (!kaslr_memory_enabled())
 		return;
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4dbe656..a7655f6 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -77,10 +77,25 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	unsigned cpu = smp_processor_id();
 
 	if (likely(prev != next)) {
+		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
+			/*
+			 * If our current stack is in vmalloc space and isn't
+			 * mapped in the new pgd, we'll double-fault.  Forcibly
+			 * map it.
+			 */
+			unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
+
+			pgd_t *pgd = next->pgd + stack_pgd_index;
+
+			if (unlikely(pgd_none(*pgd)))
+				set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
+		}
+
 #ifdef CONFIG_SMP
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		this_cpu_write(cpu_tlbstate.active_mm, next);
 #endif
+
 		cpumask_set_cpu(cpu, mm_cpumask(next));
 
 		/*