Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:

 - Update the compat layer to allow single-byte watchpoints on all
   addresses (similar to the native support)

 - arm_pmu: fix the restoration of the counters on the
   CPU_PM_ENTER_FAILED path

 - Fix build regression with vDSO and Makefile not stripping
   CROSS_COMPILE_COMPAT

 - Fix the CTR_EL0 (cache type register) sanitisation on heterogeneous
   machines (e.g. big.LITTLE)

 - Fix the interrupt controller priority mask value when pseudo-NMIs are
   enabled

 - arm64 kprobes fixes: recovering of the PSTATE.D flag in the
   single-step exception handler, NOKPROBE annotations for
   unwind_frame() and walk_stackframe(), remove unneeded
   rcu_read_lock/unlock from debug handlers

 - Several gcc fall-through warnings

 - Unused variable warnings

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: Make debug exception handlers visible from RCU
  arm64: kprobes: Recover pstate.D in single-step exception handler
  arm64/mm: fix variable 'tag' set but not used
  arm64/mm: fix variable 'pud' set but not used
  arm64: Remove unneeded rcu_read_lock from debug handlers
  arm64: unwind: Prohibit probing on return_address()
  arm64: Lower priority mask for GIC_PRIO_IRQON
  arm64/efi: fix variable 'si' set but not used
  arm64: cpufeature: Fix feature comparison for CTR_EL0.{CWG,ERG}
  arm64: vdso: Fix Makefile regression
  arm64: module: Mark expected switch fall-through
  arm64: smp: Mark expected switch fall-through
  arm64: hw_breakpoint: Fix warnings about implicit fallthrough
  drivers/perf: arm_pmu: Fix failure path in PM notifier
  arm64: compat: Allow single-byte watchpoints on all addresses

arch/arm64/Makefile

@@ -52,7 +52,7 @@ ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
 
   ifeq ($(CONFIG_CC_IS_CLANG), y)
     $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built)
-  else ifeq ($(CROSS_COMPILE_COMPAT),)
+  else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),)
     $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built)
   else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),)
     $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT)

arch/arm64/include/asm/arch_gicv3.h

@@ -155,6 +155,12 @@ static inline void gic_pmr_mask_irqs(void)
 	BUILD_BUG_ON(GICD_INT_DEF_PRI < (GIC_PRIO_IRQOFF |
 					 GIC_PRIO_PSR_I_SET));
 	BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON);
+	/*
+	 * Need to make sure IRQON allows IRQs when SCR_EL3.FIQ is cleared
+	 * and non-secure PMR accesses are not subject to the shifts that
+	 * are applied to IRQ priorities
+	 */
+	BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) >= GIC_PRIO_IRQON);
 	gic_write_pmr(GIC_PRIO_IRQOFF);
 }
 

arch/arm64/include/asm/cpufeature.h

@@ -35,9 +35,10 @@
  */
 
 enum ftr_type {
-	FTR_EXACT,	/* Use a predefined safe value */
-	FTR_LOWER_SAFE,	/* Smaller value is safe */
-	FTR_HIGHER_SAFE,/* Bigger value is safe */
+	FTR_EXACT,			/* Use a predefined safe value */
+	FTR_LOWER_SAFE,			/* Smaller value is safe */
+	FTR_HIGHER_SAFE,		/* Bigger value is safe */
+	FTR_HIGHER_OR_ZERO_SAFE,	/* Bigger value is safe, but 0 is biggest */
 };
 
 #define FTR_STRICT	true	/* SANITY check strict matching required */

arch/arm64/include/asm/daifflags.h

@@ -13,6 +13,8 @@
 #define DAIF_PROCCTX		0
 #define DAIF_PROCCTX_NOIRQ	PSR_I_BIT
 #define DAIF_ERRCTX		(PSR_I_BIT | PSR_A_BIT)
+#define DAIF_MASK		(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+
 
 /* mask/save/unmask/restore all exceptions, including interrupts. */
 static inline void local_daif_mask(void)

arch/arm64/include/asm/efi.h

@@ -105,7 +105,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
 #define alloc_screen_info(x...)		&screen_info
-#define free_screen_info(x...)
+
+static inline void free_screen_info(efi_system_table_t *sys_table_arg,
+				    struct screen_info *si)
+{
+}
 
 /* redeclare as 'hidden' so the compiler will generate relative references */
 extern struct screen_info screen_info __attribute__((__visibility__("hidden")));

arch/arm64/include/asm/memory.h

@@ -210,7 +210,11 @@ extern u64			vabits_user;
 #define __tag_reset(addr)	untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
 #else
-#define __tag_set(addr, tag)	(addr)
+static inline const void *__tag_set(const void *addr, u8 tag)
+{
+	return addr;
+}
+
 #define __tag_reset(addr)	(addr)
 #define __tag_get(addr)		0
 #endif
@@ -301,8 +305,8 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define page_to_virt(page)	({					\
 	unsigned long __addr =						\
 		((__page_to_voff(page)) | PAGE_OFFSET);			\
-	unsigned long __addr_tag =					\
-		 __tag_set(__addr, page_kasan_tag(page));		\
+	const void *__addr_tag =					\
+		__tag_set((void *)__addr, page_kasan_tag(page));	\
 	((void *)__addr_tag);						\
 })
 

arch/arm64/include/asm/pgtable.h

@@ -447,8 +447,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				 PMD_TYPE_SECT)
 
 #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
-#define pud_sect(pud)		(0)
-#define pud_table(pud)		(1)
+static inline bool pud_sect(pud_t pud) { return false; }
+static inline bool pud_table(pud_t pud) { return true; }
 #else
 #define pud_sect(pud)		((pud_val(pud) & PUD_TYPE_MASK) == \
 				 PUD_TYPE_SECT)

arch/arm64/include/asm/ptrace.h

@@ -30,7 +30,7 @@
  * in the  the priority mask, it indicates that PSR.I should be set and
  * interrupt disabling temporarily does not rely on IRQ priorities.
  */
-#define GIC_PRIO_IRQON			0xc0
+#define GIC_PRIO_IRQON			0xe0
 #define GIC_PRIO_IRQOFF			(GIC_PRIO_IRQON & ~0x80)
 #define GIC_PRIO_PSR_I_SET		(1 << 4)
 

arch/arm64/kernel/cpufeature.c

@@ -225,8 +225,8 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1),
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
@@ -468,6 +468,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
 	case FTR_LOWER_SAFE:
 		ret = new < cur ? new : cur;
 		break;
+	case FTR_HIGHER_OR_ZERO_SAFE:
+		if (!cur || !new)
+			break;
+		/* Fallthrough */
 	case FTR_HIGHER_SAFE:
 		ret = new > cur ? new : cur;
 		break;

arch/arm64/kernel/debug-monitors.c

@@ -207,16 +207,16 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 
 	list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
 
-	rcu_read_lock();
-
+	/*
+	 * Since single-step exception disables interrupt, this function is
+	 * entirely not preemptible, and we can use rcu list safely here.
+	 */
 	list_for_each_entry_rcu(hook, list, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
 	}
 
-	rcu_read_unlock();
-
 	return retval;
 }
 NOKPROBE_SYMBOL(call_step_hook);
@@ -305,14 +305,16 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 
 	list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
 
-	rcu_read_lock();
+	/*
+	 * Since brk exception disables interrupt, this function is
+	 * entirely not preemptible, and we can use rcu list safely here.
+	 */
 	list_for_each_entry_rcu(hook, list, node) {
 		unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
 
 		if ((comment & ~hook->mask) == hook->imm)
 			fn = hook->fn;
 	}
-	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }

arch/arm64/kernel/hw_breakpoint.c

@@ -536,13 +536,18 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 			/* Aligned */
 			break;
 		case 1:
-			/* Allow single byte watchpoint. */
-			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
-				break;
 		case 2:
 			/* Allow halfword watchpoints and breakpoints. */
 			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
+
+			/* Fallthrough */
+		case 3:
+			/* Allow single byte watchpoint. */
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
+				break;
+
+			/* Fallthrough */
 		default:
 			return -EINVAL;
 		}

arch/arm64/kernel/module.c

@@ -314,18 +314,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		/* MOVW instruction relocations. */
 		case R_AARCH64_MOVW_UABS_G0_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
 					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
 					      AARCH64_INSN_IMM_MOVKZ);
@@ -393,6 +396,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			break;
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
+			/* Fall through */
 		case R_AARCH64_ADR_PREL_PG_HI21:
 			ovf = reloc_insn_adrp(me, sechdrs, loc, val);
 			if (ovf && ovf != -ERANGE)

arch/arm64/kernel/probes/kprobes.c

@@ -21,6 +21,7 @@
 #include <asm/ptrace.h>
 #include <asm/cacheflush.h>
 #include <asm/debug-monitors.h>
+#include <asm/daifflags.h>
 #include <asm/system_misc.h>
 #include <asm/insn.h>
 #include <linux/uaccess.h>
@@ -167,33 +168,6 @@ static void __kprobes set_current_kprobe(struct kprobe *p)
 	__this_cpu_write(current_kprobe, p);
 }
 
-/*
- * When PSTATE.D is set (masked), then software step exceptions can not be
- * generated.
- * SPSR's D bit shows the value of PSTATE.D immediately before the
- * exception was taken. PSTATE.D is set while entering into any exception
- * mode, however software clears it for any normal (none-debug-exception)
- * mode in the exception entry. Therefore, when we are entering into kprobe
- * breakpoint handler from any normal mode then SPSR.D bit is already
- * cleared, however it is set when we are entering from any debug exception
- * mode.
- * Since we always need to generate single step exception after a kprobe
- * breakpoint exception therefore we need to clear it unconditionally, when
- * we become sure that the current breakpoint exception is for kprobe.
- */
-static void __kprobes
-spsr_set_debug_flag(struct pt_regs *regs, int mask)
-{
-	unsigned long spsr = regs->pstate;
-
-	if (mask)
-		spsr |= PSR_D_BIT;
-	else
-		spsr &= ~PSR_D_BIT;
-
-	regs->pstate = spsr;
-}
-
 /*
  * Interrupts need to be disabled before single-step mode is set, and not
  * reenabled until after single-step mode ends.
@@ -205,17 +179,17 @@ spsr_set_debug_flag(struct pt_regs *regs, int mask)
 static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
 						struct pt_regs *regs)
 {
-	kcb->saved_irqflag = regs->pstate;
+	kcb->saved_irqflag = regs->pstate & DAIF_MASK;
 	regs->pstate |= PSR_I_BIT;
+	/* Unmask PSTATE.D for enabling software step exceptions. */
+	regs->pstate &= ~PSR_D_BIT;
 }
 
 static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
 						struct pt_regs *regs)
 {
-	if (kcb->saved_irqflag & PSR_I_BIT)
-		regs->pstate |= PSR_I_BIT;
-	else
-		regs->pstate &= ~PSR_I_BIT;
+	regs->pstate &= ~DAIF_MASK;
+	regs->pstate |= kcb->saved_irqflag;
 }
 
 static void __kprobes
@@ -252,8 +226,6 @@ static void __kprobes setup_singlestep(struct kprobe *p,
 
 		set_ss_context(kcb, slot);	/* mark pending ss */
 
-		spsr_set_debug_flag(regs, 0);
-
 		/* IRQs and single stepping do not mix well. */
 		kprobes_save_local_irqflag(kcb, regs);
 		kernel_enable_single_step(regs);

arch/arm64/kernel/return_address.c

@@ -8,6 +8,7 @@
 
 #include <linux/export.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 
 #include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
@@ -29,6 +30,7 @@ static int save_return_addr(struct stackframe *frame, void *d)
 		return 0;
 	}
 }
+NOKPROBE_SYMBOL(save_return_addr);
 
 void *return_address(unsigned int level)
 {
@@ -49,3 +51,4 @@ void *return_address(unsigned int level)
 		return NULL;
 }
 EXPORT_SYMBOL_GPL(return_address);
+NOKPROBE_SYMBOL(return_address);

arch/arm64/kernel/smp.c

@@ -152,8 +152,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 				pr_crit("CPU%u: died during early boot\n", cpu);
 				break;
 			}
-			/* Fall through */
 			pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+			/* Fall through */
 		case CPU_STUCK_IN_KERNEL:
 			pr_crit("CPU%u: is stuck in kernel\n", cpu);
 			if (status & CPU_STUCK_REASON_52_BIT_VA)

arch/arm64/kernel/stacktrace.c

@@ -7,6 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
@@ -111,6 +112,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 
 	return 0;
 }
+NOKPROBE_SYMBOL(unwind_frame);
 
 void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 		     int (*fn)(struct stackframe *, void *), void *data)
@@ -125,6 +127,7 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			break;
 	}
 }
+NOKPROBE_SYMBOL(walk_stackframe);
 
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {

arch/arm64/mm/fault.c

@@ -777,6 +777,53 @@ void __init hook_debug_fault_code(int nr,
 	debug_fault_info[nr].name	= name;
 }
 
+/*
+ * In debug exception context, we explicitly disable preemption despite
+ * having interrupts disabled.
+ * This serves two purposes: it makes it much less likely that we would
+ * accidentally schedule in exception context and it will force a warning
+ * if we somehow manage to schedule by accident.
+ */
+static void debug_exception_enter(struct pt_regs *regs)
+{
+	/*
+	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
+	 * already disabled to preserve the last enabled/disabled addresses.
+	 */
+	if (interrupts_enabled(regs))
+		trace_hardirqs_off();
+
+	if (user_mode(regs)) {
+		RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+	} else {
+		/*
+		 * We might have interrupted pretty much anything.  In
+		 * fact, if we're a debug exception, we can even interrupt
+		 * NMI processing. We don't want this code makes in_nmi()
+		 * to return true, but we need to notify RCU.
+		 */
+		rcu_nmi_enter();
+	}
+
+	preempt_disable();
+
+	/* This code is a bit fragile.  Test it. */
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work");
+}
+NOKPROBE_SYMBOL(debug_exception_enter);
+
+static void debug_exception_exit(struct pt_regs *regs)
+{
+	preempt_enable_no_resched();
+
+	if (!user_mode(regs))
+		rcu_nmi_exit();
+
+	if (interrupts_enabled(regs))
+		trace_hardirqs_on();
+}
+NOKPROBE_SYMBOL(debug_exception_exit);
+
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
 
@@ -817,12 +864,7 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
 	if (cortex_a76_erratum_1463225_debug_handler(regs))
 		return;
 
-	/*
-	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
-	 * already disabled to preserve the last enabled/disabled addresses.
-	 */
-	if (interrupts_enabled(regs))
-		trace_hardirqs_off();
+	debug_exception_enter(regs);
 
 	if (user_mode(regs) && !is_ttbr0_addr(pc))
 		arm64_apply_bp_hardening();
@@ -832,7 +874,6 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
 				 inf->sig, inf->code, (void __user *)pc, esr);
 	}
 
-	if (interrupts_enabled(regs))
-		trace_hardirqs_on();
+	debug_exception_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug_exception);

drivers/perf/arm_pmu.c

@@ -723,8 +723,8 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd,
 		cpu_pm_pmu_setup(armpmu, cmd);
 		break;
 	case CPU_PM_EXIT:
-		cpu_pm_pmu_setup(armpmu, cmd);
 	case CPU_PM_ENTER_FAILED:
+		cpu_pm_pmu_setup(armpmu, cmd);
 		armpmu->start(armpmu);
 		break;
 	default: