Merge tag 'x86-urgent-2020-05-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "A set of fixes for x86:

   - Ensure that direct mapping alias is always flushed when changing
     page attributes. The optimization for small ranges failed to do so
     when the virtual address was in the vmalloc or module space.

   - Unbreak the trace event registration for syscalls without arguments
     caused by the refactoring of the SYSCALL_DEFINE0() macro.

   - Move the printk in the TSC deadline timer code to a place where it
     is guaranteed to only be called once during boot and cannot be
     rearmed by clearing warn_once after boot. If it's invoked post boot
     then lockdep rightfully complains about a potential deadlock as the
     calling context is different.

   - A series of fixes for objtool and the ORC unwinder addressing
     variety of small issues:

       - Stack offset tracking for indirect CFAs in objtool ignored
         subsequent pushs and pops

       - Repair the unwind hints in the register clearing entry ASM code

       - Make the unwinding in the low level exit to usermode code stop
         after switching to the trampoline stack. The unwind hint is no
         longer valid and the ORC unwinder emits a warning as it can't
         find the registers anymore.

       - Fix unwind hints in switch_to_asm() and rewind_stack_do_exit()
         which caused objtool to generate bogus ORC data.

       - Prevent unwinder warnings when dumping the stack of a
         non-current task as there is no way to be sure about the
         validity because the dumped stack can be a moving target.

       - Make the ORC unwinder behave the same way as the frame pointer
         unwinder when dumping an inactive tasks stack and do not skip
         the first frame.

       - Prevent ORC unwinding before ORC data has been initialized

       - Immediately terminate unwinding when a unknown ORC entry type
         is found.

       - Prevent premature stop of the unwinder caused by IRET frames.

       - Fix another infinite loop in objtool caused by a negative
         offset which was not catched.

       - Address a few build warnings in the ORC unwinder and add
         missing static/ro_after_init annotations"

* tag 'x86-urgent-2020-05-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/unwind/orc: Move ORC sorting variables under !CONFIG_MODULES
  x86/apic: Move TSC deadline timer debug printk
  ftrace/x86: Fix trace event registration for syscalls without arguments
  x86/mm/cpa: Flush direct map alias during cpa
  objtool: Fix infinite loop in for_offset_range()
  x86/unwind/orc: Fix premature unwind stoppage due to IRET frames
  x86/unwind/orc: Fix error path for bad ORC entry type
  x86/unwind/orc: Prevent unwinding before ORC initialization
  x86/unwind/orc: Don't skip the first frame for inactive tasks
  x86/unwind: Prevent false warnings for non-current tasks
  x86/unwind/orc: Convert global variables to static
  x86/entry/64: Fix unwind hints in rewind_stack_do_exit()
  x86/entry/64: Fix unwind hints in __switch_to_asm()
  x86/entry/64: Fix unwind hints in kernel exit path
  x86/entry/64: Fix unwind hints in register clearing code
  objtool: Fix stack offset tracking for indirect CFAs

4 files changed, 93 insertions, 53 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 81b9c63dae1b..e53dda210cd7 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 		 * According to Intel, MFENCE can do the serialization here.
 		 */
 		asm volatile("mfence" : : : "memory");
-
-		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
 		return;
 	}
 
@@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-static u32 hsx_deadline_rev(void)
+static __init u32 hsx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x3a; /* EP */
@@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void)
 	return ~0U;
 }
 
-static u32 bdx_deadline_rev(void)
+static __init u32 bdx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x00000011;
@@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void)
 	return ~0U;
 }
 
-static u32 skx_deadline_rev(void)
+static __init u32 skx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x03: return 0x01000136;
@@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void)
 	return ~0U;
 }
 
-static const struct x86_cpu_id deadline_match[] = {
+static const struct x86_cpu_id deadline_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X,		&hsx_deadline_rev),
 	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,	0x0b000020),
 	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D,	&bdx_deadline_rev),
@@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = {
 	{},
 };
 
-static void apic_check_deadline_errata(void)
+static __init bool apic_validate_deadline_timer(void)
 {
 	const struct x86_cpu_id *m;
 	u32 rev;
 
-	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
-	    boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return;
+	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return false;
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return true;
 
 	m = x86_match_cpu(deadline_match);
 	if (!m)
-		return;
+		return true;
 
 	/*
 	 * Function pointers will have the MSB set due to address layout,
@@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void)
 		rev = (u32)m->driver_data;
 
 	if (boot_cpu_data.microcode >= rev)
-		return;
+		return true;
 
 	setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 	pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; "
 	       "please update microcode to version: 0x%x (or later)\n", rev);
+	return false;
 }
 
 /*
@@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void)
 {
 	unsigned int new_apicid;
 
-	apic_check_deadline_errata();
+	if (apic_validate_deadline_timer())
+		pr_debug("TSC deadline timer available\n");
 
 	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 87b97897a881..460ae7f66818 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -183,7 +183,8 @@ recursion_check:
 	 */
 	if (visit_mask) {
 		if (*visit_mask & (1UL << info->type)) {
-			printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
+			if (task == current)
+				printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
 			goto unknown;
 		}
 		*visit_mask |= 1UL << info->type;
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index a224b5ab103f..54226110bc7f 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -344,6 +344,9 @@ bad_address:
 	if (IS_ENABLED(CONFIG_X86_32))
 		goto the_end;
 
+	if (state->task != current)
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index e9cc182aa97e..5b0bd8581fe6 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -8,19 +8,21 @@
 #include <asm/orc_lookup.h>
 
 #define orc_warn(fmt, ...) \
-	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
+	printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__)
+
+#define orc_warn_current(args...)					\
+({									\
+	if (state->task == current)					\
+		orc_warn(args);						\
+})
 
 extern int __start_orc_unwind_ip[];
 extern int __stop_orc_unwind_ip[];
 extern struct orc_entry __start_orc_unwind[];
 extern struct orc_entry __stop_orc_unwind[];
 
-static DEFINE_MUTEX(sort_mutex);
-int *cur_orc_ip_table = __start_orc_unwind_ip;
-struct orc_entry *cur_orc_table = __start_orc_unwind;
-
-unsigned int lookup_num_blocks;
-bool orc_init;
+static bool orc_init __ro_after_init;
+static unsigned int lookup_num_blocks __ro_after_init;
 
 static inline unsigned long orc_ip(const int *ip)
 {
@@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip)
 {
 	static struct orc_entry *orc;
 
-	if (!orc_init)
-		return NULL;
-
 	if (ip == 0)
 		return &null_orc_entry;
 
@@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip)
 
 #ifdef CONFIG_MODULES
 
+static DEFINE_MUTEX(sort_mutex);
+static int *cur_orc_ip_table = __start_orc_unwind_ip;
+static struct orc_entry *cur_orc_table = __start_orc_unwind;
+
 static void orc_sort_swap(void *_a, void *_b, int size)
 {
 	struct orc_entry *orc_a, *orc_b;
@@ -381,9 +384,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 	return true;
 }
 
+/*
+ * If state->regs is non-NULL, and points to a full pt_regs, just get the reg
+ * value from state->regs.
+ *
+ * Otherwise, if state->regs just points to IRET regs, and the previous frame
+ * had full regs, it's safe to get the value from the previous regs.  This can
+ * happen when early/late IRQ entry code gets interrupted by an NMI.
+ */
+static bool get_reg(struct unwind_state *state, unsigned int reg_off,
+		    unsigned long *val)
+{
+	unsigned int reg = reg_off/8;
+
+	if (!state->regs)
+		return false;
+
+	if (state->full_regs) {
+		*val = ((unsigned long *)state->regs)[reg];
+		return true;
+	}
+
+	if (state->prev_regs) {
+		*val = ((unsigned long *)state->prev_regs)[reg];
+		return true;
+	}
+
+	return false;
+}
+
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -445,43 +477,39 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_R10:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R10 at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) {
+			orc_warn_current("missing R10 value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r10;
 		break;
 
 	case ORC_REG_R13:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R13 at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) {
+			orc_warn_current("missing R13 value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r13;
 		break;
 
 	case ORC_REG_DI:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DI at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) {
+			orc_warn_current("missing RDI value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->di;
 		break;
 
 	case ORC_REG_DX:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DX at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) {
+			orc_warn_current("missing DX value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->dx;
 		break;
 
 	default:
-		orc_warn("unknown SP base reg %d for ip %pB\n",
+		orc_warn("unknown SP base reg %d at %pB\n",
 			 orc->sp_reg, (void *)state->ip);
 		goto err;
 	}
@@ -504,44 +532,48 @@ bool unwind_next_frame(struct unwind_state *state)
 
 		state->sp = sp;
 		state->regs = NULL;
+		state->prev_regs = NULL;
 		state->signal = false;
 		break;
 
 	case ORC_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
-			orc_warn("can't dereference registers at %p for ip %pB\n",
-				 (void *)sp, (void *)orig_ip);
+			orc_warn_current("can't access registers at %pB\n",
+					 (void *)orig_ip);
 			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
+		state->prev_regs = NULL;
 		state->full_regs = true;
 		state->signal = true;
 		break;
 
 	case ORC_TYPE_REGS_IRET:
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
-			orc_warn("can't dereference iret registers at %p for ip %pB\n",
-				 (void *)sp, (void *)orig_ip);
+			orc_warn_current("can't access iret registers at %pB\n",
+					 (void *)orig_ip);
 			goto err;
 		}
 
+		if (state->full_regs)
+			state->prev_regs = state->regs;
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
 		state->full_regs = false;
 		state->signal = true;
 		break;
 
 	default:
-		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
+		orc_warn("unknown .orc_unwind entry type %d at %pB\n",
 			 orc->type, (void *)orig_ip);
-		break;
+		goto err;
 	}
 
 	/* Find BP: */
 	switch (orc->bp_reg) {
 	case ORC_REG_UNDEFINED:
-		if (state->regs && state->full_regs)
-			state->bp = state->regs->bp;
+		if (get_reg(state, offsetof(struct pt_regs, bp), &tmp))
+			state->bp = tmp;
 		break;
 
 	case ORC_REG_PREV_SP:
@@ -564,8 +596,8 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (state->stack_info.type == prev_type &&
 	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
 	    state->sp <= prev_sp) {
-		orc_warn("stack going in the wrong direction? ip=%pB\n",
-			 (void *)orig_ip);
+		orc_warn_current("stack going in the wrong direction? at %pB\n",
+				 (void *)orig_ip);
 		goto err;
 	}
 
@@ -585,6 +617,9 @@ EXPORT_SYMBOL_GPL(unwind_next_frame);
 void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		    struct pt_regs *regs, unsigned long *first_frame)
 {
+	if (!orc_init)
+		goto done;
+
 	memset(state, 0, sizeof(*state));
 	state->task = task;
 
@@ -651,7 +686,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	/* Otherwise, skip ahead to the user-specified starting frame: */
 	while (!unwind_done(state) &&
 	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
-			state->sp <= (unsigned long)first_frame))
+			state->sp < (unsigned long)first_frame))
 		unwind_next_frame(state);
 
 	return;