Merge tag 'locking-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - LKMM updates: mostly documentation changes, but also some new litmus
   tests for atomic ops.

 - KCSAN updates: the most important change is that GCC 11 now has all
   fixes in place to support KCSAN, so GCC support can be enabled again.
   Also more annotations.

 - futex updates: minor cleanups and simplifications

 - seqlock updates: merge preparatory changes/cleanups for the
   'associated locks' facilities.

 - lockdep updates:
    - simplify IRQ trace event handling
    - add various new debug checks
    - simplify header dependencies, split out <linux/lockdep_types.h>,
      decouple lockdep from other low level headers some more
    - fix NMI handling

 - misc cleanups and smaller fixes

* tag 'locking-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  kcsan: Improve IRQ state trace reporting
  lockdep: Refactor IRQ trace events fields into struct
  seqlock: lockdep assert non-preemptibility on seqcount_t write
  lockdep: Add preemption enabled/disabled assertion APIs
  seqlock: Implement raw_seqcount_begin() in terms of raw_read_seqcount()
  seqlock: Add kernel-doc for seqcount_t and seqlock_t APIs
  seqlock: Reorder seqcount_t and seqlock_t API definitions
  seqlock: seqcount_t latch: End read sections with read_seqcount_retry()
  seqlock: Properly format kernel-doc code samples
  Documentation: locking: Describe seqlock design and usage
  locking/qspinlock: Do not include atomic.h from qspinlock_types.h
  locking/atomic: Move ATOMIC_INIT into linux/types.h
  lockdep: Move list.h inclusion into lockdep.h
  locking/lockdep: Fix TRACE_IRQFLAGS vs. NMIs
  futex: Remove unused or redundant includes
  futex: Consistently use fshared as boolean
  futex: Remove needless goto's
  futex: Remove put_futex_key()
  rwsem: fix commas in initialisation
  docs: locking: Replace HTTP links with HTTPS ones
  ...

41 files changed, 172 insertions, 146 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 2f8f7e54792f..e41c113c6688 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -24,7 +24,6 @@
 #define __atomic_acquire_fence()
 #define __atomic_post_full_fence()
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 7298ce84762e..c614857eb209 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -14,8 +14,6 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifndef CONFIG_ARC_PLAT_EZNPS
 
 #define atomic_read(v)  READ_ONCE((v)->counter)
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 75bb2c543e59..455eb19a5ac1 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -15,8 +15,6 @@
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifdef __KERNEL__
 
 /*
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index 1a3eedbac4a2..e2fcb3cfd3de 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -5,7 +5,7 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
-#include <asm/thread_info.h>
+register unsigned long current_stack_pointer asm ("sp");
 
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 3609a6980c34..536b6b979f63 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -76,11 +76,6 @@ struct thread_info {
 }
 
 /*
- * how to get the current stack pointer in C
- */
-register unsigned long current_stack_pointer asm ("sp");
-
-/*
  * how to get the thread information struct from C
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index a08890da696c..015ddffaf6ca 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -99,8 +99,6 @@ static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define arch_atomic_read(v)			__READ_ONCE((v)->counter)
 #define arch_atomic_set(v, i)			__WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index c6b6a06231b2..a990d151f163 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -12,8 +12,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 0231d69c8bf2..4ab895d7111f 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -12,8 +12,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
-
 /*  Normal writes in our arch don't clear lock reservations  */
 
 static inline void atomic_set(atomic_t *v, int new)
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 50440f3ddc43..f267d956458f 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -19,7 +19,6 @@
 #include <asm/barrier.h>
 
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 47228b0d4163..756c5cc58f94 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -16,8 +16,6 @@
  * We do not have SMP m68k systems, so we don't have to deal with that.
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index e5ac88392d1f..f904084fcb1f 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -45,7 +45,6 @@ static __always_inline type pfx##_xchg(pfx##_t *v, type n)		\
 	return xchg(&v->counter, n);					\
 }
 
-#define ATOMIC_INIT(i)		{ (i) }
 ATOMIC_OPS(atomic, int)
 
 #ifdef CONFIG_64BIT
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 6dd4171c9530..03862320f779 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -136,8 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i) { (i) }
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 498785ffc25f..0311c3c42960 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -11,8 +11,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
-
 /*
  * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h
new file mode 100644
index 000000000000..1625888f27ef
--- /dev/null
+++ b/arch/powerpc/include/asm/dtl.h
@@ -0,0 +1,52 @@
+#ifndef _ASM_POWERPC_DTL_H
+#define _ASM_POWERPC_DTL_H
+
+#include <asm/lppaca.h>
+#include <linux/spinlock_types.h>
+
+/*
+ * Layout of entries in the hypervisor's dispatch trace log buffer.
+ */
+struct dtl_entry {
+	u8	dispatch_reason;
+	u8	preempt_reason;
+	__be16	processor_id;
+	__be32	enqueue_to_dispatch_time;
+	__be32	ready_to_enqueue_time;
+	__be32	waiting_to_ready_time;
+	__be64	timebase;
+	__be64	fault_addr;
+	__be64	srr0;
+	__be64	srr1;
+};
+
+#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
+#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
+
+/*
+ * Dispatch trace log event enable mask:
+ *   0x1: voluntary virtual processor waits
+ *   0x2: time-slice preempts
+ *   0x4: virtual partition memory page faults
+ */
+#define DTL_LOG_CEDE		0x1
+#define DTL_LOG_PREEMPT		0x2
+#define DTL_LOG_FAULT		0x4
+#define DTL_LOG_ALL		(DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
+
+extern struct kmem_cache *dtl_cache;
+extern rwlock_t dtl_access_lock;
+
+/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
+ * reading from the dispatch trace log.  If other code wants to consume
+ * DTL entries, it can set this pointer to a function that will get
+ * called once for each DTL entry that gets processed.
+ */
+extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
+
+extern void register_dtl_buffer(int cpu);
+extern void alloc_dtl_buffers(unsigned long *time_limit);
+extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
+
+#endif /* _ASM_POWERPC_DTL_H */
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 3b4b305796ae..c390ec377bae 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -42,7 +42,6 @@
  */
 #include <linux/cache.h>
 #include <linux/threads.h>
-#include <linux/spinlock_types.h>
 #include <asm/types.h>
 #include <asm/mmu.h>
 #include <asm/firmware.h>
@@ -146,49 +145,6 @@ struct slb_shadow {
 	} save_area[SLB_NUM_BOLTED];
 } ____cacheline_aligned;
 
-/*
- * Layout of entries in the hypervisor's dispatch trace log buffer.
- */
-struct dtl_entry {
-	u8	dispatch_reason;
-	u8	preempt_reason;
-	__be16	processor_id;
-	__be32	enqueue_to_dispatch_time;
-	__be32	ready_to_enqueue_time;
-	__be32	waiting_to_ready_time;
-	__be64	timebase;
-	__be64	fault_addr;
-	__be64	srr0;
-	__be64	srr1;
-};
-
-#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
-#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
-
-/*
- * Dispatch trace log event enable mask:
- *   0x1: voluntary virtual processor waits
- *   0x2: time-slice preempts
- *   0x4: virtual partition memory page faults
- */
-#define DTL_LOG_CEDE		0x1
-#define DTL_LOG_PREEMPT		0x2
-#define DTL_LOG_FAULT		0x4
-#define DTL_LOG_ALL		(DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
-
-extern struct kmem_cache *dtl_cache;
-extern rwlock_t dtl_access_lock;
-
-/*
- * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
- * reading from the dispatch trace log.  If other code wants to consume
- * DTL entries, it can set this pointer to a function that will get
- * called once for each DTL entry that gets processed.
- */
-extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
-
-extern void register_dtl_buffer(int cpu);
-extern void alloc_dtl_buffers(unsigned long *time_limit);
 extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
 
 #endif /* CONFIG_PPC_BOOK3S */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 45a839a7c6cf..84b2564cf5a4 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -29,7 +29,6 @@
 #include <asm/hmi.h>
 #include <asm/cpuidle.h>
 #include <asm/atomic.h>
-#include <asm/rtas-types.h>
 
 #include <asm-generic/mmiowb_types.h>
 
@@ -53,6 +52,7 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
+struct rtas_args;
 
 /*
  * Defines the layout of the paca.
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6fcae436ae51..f85539ebb513 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -183,6 +183,8 @@ static inline unsigned long read_spurr(unsigned long tb)
 
 #ifdef CONFIG_PPC_SPLPAR
 
+#include <asm/dtl.h>
+
 /*
  * Scan the dispatch trace log and count up the stolen time.
  * Should be called with interrupts disabled.
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6bf66649ab92..ebb04f331ad3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -74,6 +74,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/kvm_book3s_uvmem.h>
 #include <asm/ultravisor.h>
+#include <asm/dtl.h>
 
 #include "book3s.h"
 
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index eab8aa293743..982f069e4c31 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -12,6 +12,7 @@
 #include <asm/smp.h>
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
+#include <asm/dtl.h>
 #include <asm/lppaca.h>
 #include <asm/debugfs.h>
 #include <asm/plpar_wrappers.h>
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index fd26f3d21d7b..f71ff2c94efe 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -40,6 +40,7 @@
 #include <asm/fadump.h>
 #include <asm/asm-prototypes.h>
 #include <asm/debugfs.h>
+#include <asm/dtl.h>
 
 #include "pseries.h"
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2db8469e475f..27094c872fd6 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -70,6 +70,7 @@
 #include <asm/idle.h>
 #include <asm/swiotlb.h>
 #include <asm/svm.h>
+#include <asm/dtl.h>
 
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 40c0637203d5..e6d7a344d9f2 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -11,6 +11,7 @@
 #include <asm/svm.h>
 #include <asm/swiotlb.h>
 #include <asm/ultravisor.h>
+#include <asm/dtl.h>
 
 static int __init init_svm(void)
 {
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 96f95c9ebd97..400a8c8b6de7 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define __atomic_acquire_fence()					\
 	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
 
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 491ad53a0d4e..cae473a7b6f7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,8 +15,6 @@
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
-#define ATOMIC_INIT(i)  { (i) }
-
 static inline int atomic_read(const atomic_t *v)
 {
 	int c;
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 20b37b059e2b..7e155fb6c254 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -10,6 +10,7 @@
 
 #include <asm/sigp.h>
 #include <asm/lowcore.h>
+#include <asm/processor.h>
 
 #define raw_smp_processor_id()	(S390_lowcore.cpu_nr)
 
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index e582fbe59e20..13a04fcf7762 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -24,7 +24,6 @@
 #ifndef __ASSEMBLY__
 #include <asm/lowcore.h>
 #include <asm/page.h>
-#include <asm/processor.h>
 
 #define STACK_INIT_OFFSET \
 	(THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs))
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index f37b95a80232..7c2a8a703b9a 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v,i)		WRITE_ONCE((v)->counter, (i))
 
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 94c930f0bc62..efad5532f169 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -18,8 +18,6 @@
 #include <asm/barrier.h>
 #include <asm-generic/atomic64.h>
 
-#define ATOMIC_INIT(i)  { (i) }
-
 int atomic_add_return(int, atomic_t *);
 int atomic_fetch_add(int, atomic_t *);
 int atomic_fetch_and(int, atomic_t *);
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index b60448397d4f..6b235d3d1d9d 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -12,7 +12,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		READ_ONCE((v)->counter)
diff --git a/arch/sparc/include/asm/percpu_64.h b/arch/sparc/include/asm/percpu_64.h
index 32ef6f05cc56..a8786a4b90b6 100644
--- a/arch/sparc/include/asm/percpu_64.h
+++ b/arch/sparc/include/asm/percpu_64.h
@@ -4,7 +4,9 @@
 
 #include <linux/compiler.h>
 
+#ifndef BUILD_VDSO
 register unsigned long __local_per_cpu_offset asm("g5");
+#endif
 
 #ifdef CONFIG_SMP
 
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 0f6d0c4f6683..ace0d48e837e 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -2,6 +2,8 @@
 #ifndef _SPARC_TRAP_BLOCK_H
 #define _SPARC_TRAP_BLOCK_H
 
+#include <linux/threads.h>
+
 #include <asm/hypervisor.h>
 #include <asm/asi.h>
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 0dd319e6e5b4..ee1d3c5834c6 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -3,6 +3,9 @@
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
+config TRACE_IRQFLAGS_NMI_SUPPORT
+	def_bool y
+
 config EARLY_PRINTK_USB
 	bool
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index f09288431f28..54ad1890aefc 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -559,8 +559,7 @@ SYSCALL_DEFINE0(ni_syscall)
 }
 
 /**
- * idtentry_enter_cond_rcu - Handle state tracking on idtentry with conditional
- *			     RCU handling
+ * idtentry_enter - Handle state tracking on ordinary idtentries
  * @regs:	Pointer to pt_regs of interrupted context
  *
  * Invokes:
@@ -572,6 +571,9 @@ SYSCALL_DEFINE0(ni_syscall)
  *  - The hardirq tracer to keep the state consistent as low level ASM
  *    entry disabled interrupts.
  *
+ * As a precondition, this requires that the entry came from user mode,
+ * idle, or a kernel context in which RCU is watching.
+ *
  * For kernel mode entries RCU handling is done conditional. If RCU is
  * watching then the only RCU requirement is to check whether the tick has
  * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
@@ -585,18 +587,21 @@ SYSCALL_DEFINE0(ni_syscall)
  * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
  * would not be possible.
  *
- * Returns: True if RCU has been adjusted on a kernel entry
- *	    False otherwise
+ * Returns: An opaque object that must be passed to idtentry_exit()
  *
- * The return value must be fed into the rcu_exit argument of
- * idtentry_exit_cond_rcu().
+ * The return value must be fed into the state argument of
+ * idtentry_exit().
  */
-bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
+noinstr idtentry_state_t idtentry_enter(struct pt_regs *regs)
 {
+	idtentry_state_t ret = {
+		.exit_rcu = false,
+	};
+
 	if (user_mode(regs)) {
 		check_user_regs(regs);
 		enter_from_user_mode();
-		return false;
+		return ret;
 	}
 
 	/*
@@ -634,7 +639,8 @@ bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
 		trace_hardirqs_off_finish();
 		instrumentation_end();
 
-		return true;
+		ret.exit_rcu = true;
+		return ret;
 	}
 
 	/*
@@ -649,7 +655,7 @@ bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
 	trace_hardirqs_off();
 	instrumentation_end();
 
-	return false;
+	return ret;
 }
 
 static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
@@ -667,10 +673,9 @@ static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
 }
 
 /**
- * idtentry_exit_cond_rcu - Handle return from exception with conditional RCU
- *			    handling
+ * idtentry_exit - Handle return from exception that used idtentry_enter()
  * @regs:	Pointer to pt_regs (exception entry regs)
- * @rcu_exit:	Invoke rcu_irq_exit() if true
+ * @state:	Return value from matching call to idtentry_enter()
  *
  * Depending on the return target (kernel/user) this runs the necessary
  * preemption and work checks if possible and reguired and returns to
@@ -679,10 +684,10 @@ static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
  * This is the last action before returning to the low level ASM code which
  * just needs to return to the appropriate context.
  *
- * Counterpart to idtentry_enter_cond_rcu(). The return value of the entry
- * function must be fed into the @rcu_exit argument.
+ * Counterpart to idtentry_enter(). The return value of the entry
+ * function must be fed into the @state argument.
  */
-void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
+noinstr void idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
 {
 	lockdep_assert_irqs_disabled();
 
@@ -695,7 +700,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
 		 * carefully and needs the same ordering of lockdep/tracing
 		 * and RCU as the return to user mode path.
 		 */
-		if (rcu_exit) {
+		if (state.exit_rcu) {
 			instrumentation_begin();
 			/* Tell the tracer that IRET will enable interrupts */
 			trace_hardirqs_on_prepare();
@@ -714,7 +719,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
 		 * IRQ flags state is correct already. Just tell RCU if it
 		 * was not watching on entry.
 		 */
-		if (rcu_exit)
+		if (state.exit_rcu)
 			rcu_irq_exit();
 	}
 }
@@ -726,7 +731,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
  * Invokes enter_from_user_mode() to establish the proper context for
  * NOHZ_FULL. Otherwise scheduling on exit would not be possible.
  */
-void noinstr idtentry_enter_user(struct pt_regs *regs)
+noinstr void idtentry_enter_user(struct pt_regs *regs)
 {
 	check_user_regs(regs);
 	enter_from_user_mode();
@@ -744,13 +749,47 @@ void noinstr idtentry_enter_user(struct pt_regs *regs)
  *
  * Counterpart to idtentry_enter_user().
  */
-void noinstr idtentry_exit_user(struct pt_regs *regs)
+noinstr void idtentry_exit_user(struct pt_regs *regs)
 {
 	lockdep_assert_irqs_disabled();
 
 	prepare_exit_to_usermode(regs);
 }
 
+noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
+{
+	bool irq_state = lockdep_hardirqs_enabled();
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	rcu_nmi_enter();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (restore) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	}
+	instrumentation_end();
+
+	rcu_nmi_exit();
+	lockdep_hardirq_exit();
+	if (restore)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}
+
 #ifdef CONFIG_XEN_PV
 #ifndef CONFIG_PREEMPTION
 /*
@@ -800,9 +839,10 @@ static void __xen_pv_evtchn_do_upcall(void)
 __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
-	bool inhcall, rcu_exit;
+	bool inhcall;
+	idtentry_state_t state;
 
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 	old_regs = set_irq_regs(regs);
 
 	instrumentation_begin();
@@ -812,13 +852,13 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 
 	inhcall = get_and_clear_inhcall();
-	if (inhcall && !WARN_ON_ONCE(rcu_exit)) {
+	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
 		instrumentation_begin();
 		idtentry_exit_cond_resched(regs, true);
 		instrumentation_end();
 		restore_inhcall(inhcall);
 	} else {
-		idtentry_exit_cond_rcu(regs, rcu_exit);
+		idtentry_exit(regs, state);
 	}
 }
 #endif /* CONFIG_XEN_PV */
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index bf35e476a776..b6cac6e9bb70 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -14,8 +14,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /**
  * arch_atomic_read - read atomic variable
  * @v: pointer of type atomic_t
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 80d3b30d3ee3..d74128c964f8 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -13,8 +13,15 @@
 void idtentry_enter_user(struct pt_regs *regs);
 void idtentry_exit_user(struct pt_regs *regs);
 
-bool idtentry_enter_cond_rcu(struct pt_regs *regs);
-void idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit);
+typedef struct idtentry_state {
+	bool exit_rcu;
+} idtentry_state_t;
+
+idtentry_state_t idtentry_enter(struct pt_regs *regs);
+void idtentry_exit(struct pt_regs *regs, idtentry_state_t state);
+
+bool idtentry_enter_nmi(struct pt_regs *regs);
+void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
 
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
@@ -54,12 +61,12 @@ static __always_inline void __##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__##func (regs);						\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs)
@@ -101,12 +108,12 @@ static __always_inline void __##func(struct pt_regs *regs,		\
 __visible noinstr void func(struct pt_regs *regs,			\
 			    unsigned long error_code)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__##func (regs, error_code);					\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs,		\
@@ -199,7 +206,7 @@ static __always_inline void __##func(struct pt_regs *regs, u8 vector);	\
 __visible noinstr void func(struct pt_regs *regs,			\
 			    unsigned long error_code)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
@@ -207,7 +214,7 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	__##func (regs, (u8)error_code);				\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs, u8 vector)
@@ -241,7 +248,7 @@ static void __##func(struct pt_regs *regs);				\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
@@ -249,7 +256,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	run_on_irqstack_cond(__##func, regs, regs);			\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static noinline void __##func(struct pt_regs *regs)
@@ -270,7 +277,7 @@ static __always_inline void __##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	bool rcu_exit = idtentry_enter_cond_rcu(regs);			\
+	idtentry_state_t state = idtentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__irq_enter_raw();						\
@@ -278,7 +285,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	__##func (regs);						\
 	__irq_exit_raw();						\
 	instrumentation_end();						\
-	idtentry_exit_cond_rcu(regs, rcu_exit);				\
+	idtentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index df63786e7bfa..3f78482d9496 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
 noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
 	u32 reason = kvm_read_and_reset_apf_flags();
-	bool rcu_exit;
+	idtentry_state_t state;
 
 	switch (reason) {
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
@@ -243,7 +243,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 		return false;
 	}
 
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 	instrumentation_begin();
 
 	/*
@@ -264,7 +264,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 	}
 
 	instrumentation_end();
-	idtentry_exit_cond_rcu(regs, rcu_exit);
+	idtentry_exit(regs, state);
 	return true;
 }
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index d7c5e44b26f7..4fc9954a9560 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -330,7 +330,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 	__this_cpu_write(last_nmi_rip, regs->ip);
 
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
 
 	handled = nmi_handle(NMI_LOCAL, regs);
 	__this_cpu_add(nmi_stats.normal, handled);
@@ -417,8 +416,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 		unknown_nmi_error(reason, regs);
 
 out:
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
 	instrumentation_end();
 }
 
@@ -478,6 +475,8 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
+	bool irq_state;
+
 	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
 		return;
 
@@ -491,14 +490,14 @@ nmi_restart:
 
 	this_cpu_write(nmi_dr7, local_db_save());
 
-	nmi_enter();
+	irq_state = idtentry_enter_nmi(regs);
 
 	inc_irq_stat(__nmi_count);
 
 	if (!ignore_nmis)
 		default_do_nmi(regs);
 
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 
 	local_db_restore(this_cpu_read(nmi_dr7));
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b7cb3e0716f7..8493f55e1167 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -245,7 +245,7 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 
 DEFINE_IDTENTRY_RAW(exc_invalid_op)
 {
-	bool rcu_exit;
+	idtentry_state_t state;
 
 	/*
 	 * We use UD2 as a short encoding for 'CALL __WARN', as such
@@ -255,11 +255,11 @@ DEFINE_IDTENTRY_RAW(exc_invalid_op)
 	if (!user_mode(regs) && handle_bug(regs))
 		return;
 
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 	instrumentation_begin();
 	handle_invalid_op(regs);
 	instrumentation_end();
-	idtentry_exit_cond_rcu(regs, rcu_exit);
+	idtentry_exit(regs, state);
 }
 
 DEFINE_IDTENTRY(exc_coproc_segment_overrun)
@@ -405,7 +405,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 	}
 #endif
 
-	nmi_enter();
+	idtentry_enter_nmi(regs);
 	instrumentation_begin();
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -651,15 +651,12 @@ DEFINE_IDTENTRY_RAW(exc_int3)
 		instrumentation_end();
 		idtentry_exit_user(regs);
 	} else {
-		nmi_enter();
+		bool irq_state = idtentry_enter_nmi(regs);
 		instrumentation_begin();
-		trace_hardirqs_off_finish();
 		if (!do_int3(regs))
 			die("int3", regs, 0);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
 		instrumentation_end();
-		nmi_exit();
+		idtentry_exit_nmi(regs, irq_state);
 	}
 }
 
@@ -867,9 +864,8 @@ out:
 static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 					     unsigned long dr6)
 {
-	nmi_enter();
+	bool irq_state = idtentry_enter_nmi(regs);
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
 
 	/*
 	 * If something gets miswired and we end up here for a user mode
@@ -886,10 +882,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 
 	handle_debug(regs, dr6, false);
 
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
 	instrumentation_end();
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 }
 
 static __always_inline void exc_debug_user(struct pt_regs *regs,
@@ -905,6 +899,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 	instrumentation_begin();
 
 	handle_debug(regs, dr6, true);
+
 	instrumentation_end();
 	idtentry_exit_user(regs);
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 1ead568c0101..5e41949453cc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1377,7 +1377,7 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
 	unsigned long address = read_cr2();
-	bool rcu_exit;
+	idtentry_state_t state;
 
 	prefetchw(&current->mm->mmap_lock);
 
@@ -1412,11 +1412,11 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 	 * code reenabled RCU to avoid subsequent wreckage which helps
 	 * debugability.
 	 */
-	rcu_exit = idtentry_enter_cond_rcu(regs);
+	state = idtentry_enter(regs);
 
 	instrumentation_begin();
 	handle_page_fault(regs, error_code, address);
 	instrumentation_end();
 
-	idtentry_exit_cond_rcu(regs, rcu_exit);
+	idtentry_exit(regs, state);
 }
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 77e04304a2a7..d1b2a889f035 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -135,7 +135,7 @@ static inline void cpa_inc_2m_checked(void)
 
 static inline void cpa_inc_4k_install(void)
 {
-	cpa_4k_install++;
+	data_race(cpa_4k_install++);
 }
 
 static inline void cpa_inc_lp_sameprot(int level)
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 3e7c6134ed32..744c2f463845 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -19,8 +19,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /*
  * This Xtensa implementation assumes that the right mechanism
  * for exclusion is for locking interrupts to level EXCM_LEVEL.