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

Pull arm64 fixes from Catalin Marinas:

 - Set the minimum GCC version to 5.1 for arm64 due to earlier compiler
   bugs.

 - Make atomic helpers __always_inline to avoid a section mismatch when
   compiling with clang.

 - Fix the CMA and crashkernel reservations to use ZONE_DMA (remove the
   arm64_dma32_phys_limit variable, no longer needed with a dynamic
   ZONE_DMA sizing in 5.11).

 - Remove redundant IRQ flag tracing that was leaving lockdep
   inconsistent with the hardware state.

 - Revert perf events based hard lockup detector that was causing
   smp_processor_id() to be called in preemptible context.

 - Some trivial cleanups - spelling fix, renaming S_FRAME_SIZE to
   PT_REGS_SIZE, function prototypes added.

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: selftests: Fix spelling of 'Mismatch'
  arm64: syscall: include prototype for EL0 SVC functions
  compiler.h: Raise minimum version of GCC to 5.1 for arm64
  arm64: make atomic helpers __always_inline
  arm64: rename S_FRAME_SIZE to PT_REGS_SIZE
  Revert "arm64: Enable perf events based hard lockup detector"
  arm64: entry: remove redundant IRQ flag tracing
  arm64: Remove arm64_dma32_phys_limit and its uses

arch/arm64/Kconfig

@@ -174,8 +174,6 @@ config ARM64
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
-	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API

arch/arm64/include/asm/atomic.h

@@ -17,7 +17,7 @@
 #include <asm/lse.h>
 
 #define ATOMIC_OP(op)							\
-static inline void arch_##op(int i, atomic_t *v)			\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub)
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, op)					\
-static inline int arch_##op##name(int i, atomic_t *v)			\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return)
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC64_OP(op)							\
-static inline void arch_##op(long i, atomic64_t *v)			\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, op)					\
-static inline long arch_##op##name(long i, atomic64_t *v)		\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return)
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }

arch/arm64/include/asm/processor.h

@@ -94,8 +94,7 @@
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
 extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT	((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
 
 struct debug_info {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT

arch/arm64/kernel/asm-offsets.c

@@ -75,7 +75,7 @@ int main(void)
   DEFINE(S_SDEI_TTBR1,		offsetof(struct pt_regs, sdei_ttbr1));
   DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
-  DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
+  DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
   BLANK();
 #ifdef CONFIG_COMPAT
   DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));

arch/arm64/kernel/entry-ftrace.S

@@ -35,7 +35,7 @@
  */
 	.macro  ftrace_regs_entry, allregs=0
 	/* Make room for pt_regs, plus a callee frame */
-	sub	sp, sp, #(S_FRAME_SIZE + 16)
+	sub	sp, sp, #(PT_REGS_SIZE + 16)
 
 	/* Save function arguments (and x9 for simplicity) */
 	stp	x0, x1, [sp, #S_X0]
@@ -61,15 +61,15 @@
 	.endif
 
 	/* Save the callsite's SP and LR */
-	add	x10, sp, #(S_FRAME_SIZE + 16)
+	add	x10, sp, #(PT_REGS_SIZE + 16)
 	stp	x9, x10, [sp, #S_LR]
 
 	/* Save the PC after the ftrace callsite */
 	str	x30, [sp, #S_PC]
 
 	/* Create a frame record for the callsite above pt_regs */
-	stp	x29, x9, [sp, #S_FRAME_SIZE]
-	add	x29, sp, #S_FRAME_SIZE
+	stp	x29, x9, [sp, #PT_REGS_SIZE]
+	add	x29, sp, #PT_REGS_SIZE
 
 	/* Create our frame record within pt_regs. */
 	stp	x29, x30, [sp, #S_STACKFRAME]
@@ -120,7 +120,7 @@ ftrace_common_return:
 	ldr	x9, [sp, #S_PC]
 
 	/* Restore the callsite's SP */
-	add	sp, sp, #S_FRAME_SIZE + 16
+	add	sp, sp, #PT_REGS_SIZE + 16
 
 	ret	x9
 SYM_CODE_END(ftrace_common)
@@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller)
 	ldr	x0, [sp, #S_PC]
 	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
-	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	ldr	x2, [sp, #PT_REGS_SIZE]	   	// parent fp (callsite's FP)
 	bl	prepare_ftrace_return
 	b	ftrace_common_return
 SYM_CODE_END(ftrace_graph_caller)

arch/arm64/kernel/entry.S

@@ -75,7 +75,7 @@ alternative_else_nop_endif
 	.endif
 #endif
 
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * Test whether the SP has overflowed, without corrupting a GPR.
@@ -96,7 +96,7 @@ alternative_else_nop_endif
 	 * userspace, and can clobber EL0 registers to free up GPRs.
 	 */
 
-	/* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+	/* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */
 	msr	tpidr_el0, x0
 
 	/* Recover the original x0 value and stash it in tpidrro_el0 */
@@ -253,7 +253,7 @@ alternative_else_nop_endif
 
 	scs_load tsk, x20
 	.else
-	add	x21, sp, #S_FRAME_SIZE
+	add	x21, sp, #PT_REGS_SIZE
 	get_current_task tsk
 	.endif /* \el == 0 */
 	mrs	x22, elr_el1
@@ -377,7 +377,7 @@ alternative_else_nop_endif
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #S_FRAME_SIZE		// restore sp
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
@@ -580,12 +580,12 @@ __bad_stack:
 
 	/*
 	 * Store the original GPRs to the new stack. The orginal SP (minus
-	 * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+	 * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry.
 	 */
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 	kernel_entry 1
 	mrs	x0, tpidr_el0
-	add	x0, x0, #S_FRAME_SIZE
+	add	x0, x0, #PT_REGS_SIZE
 	str	x0, [sp, #S_SP]
 
 	/* Stash the regs for handle_bad_stack */

arch/arm64/kernel/perf_event.c

@@ -23,8 +23,6 @@
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
-	int ret;
-
 	if (acpi_disabled)
-		ret = platform_driver_register(&armv8_pmu_driver);
+		return platform_driver_register(&armv8_pmu_driver);
 	else
-		ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
-	/*
-	 * Try to re-initialize lockup detector after PMU init in
-	 * case PMU events are triggered via NMIs.
-	 */
-	if (ret == 0 && arm_pmu_irq_is_nmi())
-		lockup_detector_init();
-
-	return ret;
+		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
 
@@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time_zero = 1;
 	userpg->cap_user_time_short = 1;
 }
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ	5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
-	unsigned int cpu = smp_processor_id();
-	unsigned long max_cpu_freq;
-
-	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
-	if (!max_cpu_freq)
-		max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
-	return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif

arch/arm64/kernel/probes/kprobes_trampoline.S

@@ -25,7 +25,7 @@
 	stp x24, x25, [sp, #S_X24]
 	stp x26, x27, [sp, #S_X26]
 	stp x28, x29, [sp, #S_X28]
-	add x0, sp, #S_FRAME_SIZE
+	add x0, sp, #PT_REGS_SIZE
 	stp lr, x0, [sp, #S_LR]
 	/*
 	 * Construct a useful saved PSTATE
@@ -62,7 +62,7 @@
 	.endm
 
 SYM_CODE_START(kretprobe_trampoline)
-	sub sp, sp, #S_FRAME_SIZE
+	sub sp, sp, #PT_REGS_SIZE
 
 	save_all_base_regs
 
@@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline)
 
 	restore_all_base_regs
 
-	add sp, sp, #S_FRAME_SIZE
+	add sp, sp, #PT_REGS_SIZE
 	ret
 
 SYM_CODE_END(kretprobe_trampoline)

arch/arm64/kernel/signal.c

@@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
-	/*
-	 * The assembly code enters us with IRQs off, but it hasn't
-	 * informed the tracing code of that for efficiency reasons.
-	 * Update the trace code with the current status.
-	 */
-	trace_hardirqs_off();
-
 	do {
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			/* Unmask Debug and SError for the next task */

arch/arm64/kernel/syscall.c

@@ -9,6 +9,7 @@
 
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
+#include <asm/exception.h>
 #include <asm/fpsimd.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
@@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
-			/*
-			 * We're off to userspace, where interrupts are
-			 * always enabled after we restore the flags from
-			 * the SPSR.
-			 */
-			trace_hardirqs_on();
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
 			return;
-		}
 		local_daif_restore(DAIF_PROCCTX);
 	}
 

arch/arm64/mm/init.c

@@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
 /*
- * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
- * memory as some devices, namely the Raspberry Pi 4, have peripherals with
- * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
- * bit addressable memory area.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
-phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+		crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 	unsigned int __maybe_unused acpi_zone_dma_bits;
 	unsigned int __maybe_unused dt_zone_dma_bits;
+	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
 
 #ifdef CONFIG_ZONE_DMA
 	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -394,16 +399,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma32_phys_limit = max_zone_phys(32);
-	else
-		arm64_dma32_phys_limit = PHYS_MASK + 1;
-
 	reserve_elfcorehdr();
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
-	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -438,6 +436,11 @@ void __init bootmem_init(void)
 	sparse_init();
 	zone_sizes_init(min, max);
 
+	/*
+	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+	 */
+	dma_contiguous_reserve(arm64_dma_phys_limit);
+
 	/*
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
@@ -455,7 +458,7 @@ void __init bootmem_init(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;

drivers/perf/arm_pmu.c

@@ -726,11 +726,6 @@ static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
 	return per_cpu(hw_events->irq, cpu);
 }
 
-bool arm_pmu_irq_is_nmi(void)
-{
-	return has_nmi;
-}
-
 /*
  * PMU hardware loses all context when a CPU goes offline.
  * When a CPU is hotplugged back in, since some hardware registers are

include/asm-generic/bitops/atomic.h

@@ -11,19 +11,19 @@
  * See Documentation/atomic_bitops.txt for details.
  */
 
-static inline void set_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void set_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
 	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void clear_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
 	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static inline void change_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void change_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
 	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);

include/linux/compiler-gcc.h

@@ -13,6 +13,12 @@
 /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
 #if GCC_VERSION < 40900
 # error Sorry, your version of GCC is too old - please use 4.9 or newer.
+#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100
+/*
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293
+ * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk
+ */
+# error Sorry, your version of GCC is too old - please use 5.1 or newer.
 #endif
 
 /*

include/linux/perf/arm_pmu.h

@@ -163,8 +163,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
 static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 #endif
 
-bool arm_pmu_irq_is_nmi(void);
-
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);

tools/testing/selftests/arm64/fp/fpsimd-test.S

@@ -457,7 +457,7 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="

tools/testing/selftests/arm64/fp/sve-test.S

@@ -625,7 +625,7 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="