Merge tag 'powerpc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:

   - Enable support for memory protection keys aka "pkeys" on Power7/8/9
     when using the hash table MMU.

   - Extend our interrupt soft masking to support masking PMU interrupts
     as well as "normal" interrupts, and then use that to implement
     local_t for a ~4x speedup vs the current atomics-based
     implementation.

   - A new driver "ocxl" for "Open Coherent Accelerator Processor
     Interface (OpenCAPI)" devices.

   - Support for new device tree properties on PowerVM to describe
     hotpluggable memory and devices.

   - Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE to the 64-bit
     VDSO.

   - Freescale updates from Scott: fixes for CPM GPIO and an FSL PCI
     erratum workaround, plus a minor cleanup patch.

  As well as quite a lot of other changes all over the place, and small
  fixes and cleanups as always.

  Thanks to: Alan Modra, Alastair D'Silva, Alexey Kardashevskiy,
  Alistair Popple, Andreas Schwab, Andrew Donnellan, Aneesh Kumar K.V,
  Anju T Sudhakar, Anshuman Khandual, Anton Blanchard, Arnd Bergmann,
  Balbir Singh, Benjamin Herrenschmidt, Bhaktipriya Shridhar, Bryant G.
  Ly, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Cyril Bur,
  David Gibson, Desnes A. Nunes do Rosario, Dmitry Torokhov, Frederic
  Barrat, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo A. R. Silva,
  Gustavo Romero, Ivan Mikhaylov, Joakim Tjernlund, Joe Perches, Josh
  Poimboeuf, Juan J. Alvarez, Julia Cartwright, Kamalesh Babulal,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
  Bringmann, Michael Hanselmann, Michael Neuling, Nathan Fontenot,
  Naveen N. Rao, Nicholas Piggin, Paul Mackerras, Philippe Bergheaud,
  Ram Pai, Russell Currey, Santosh Sivaraj, Scott Wood, Seth Forshee,
  Simon Guo, Stewart Smith, Sukadev Bhattiprolu, Thiago Jung Bauermann,
  Vaibhav Jain, Vasyl Gomonovych"

* tag 'powerpc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (199 commits)
  powerpc/mm/radix: Fix build error when RADIX_MMU=n
  macintosh/ams-input: Use true and false for boolean values
  macintosh: change some data types from int to bool
  powerpc/watchdog: Print the NIP in soft_nmi_interrupt()
  powerpc/watchdog: regs can't be null in soft_nmi_interrupt()
  powerpc/watchdog: Tweak watchdog printks
  powerpc/cell: Remove axonram driver
  rtc-opal: Fix handling of firmware error codes, prevent busy loops
  powerpc/mpc52xx_gpt: make use of raw_spinlock variants
  macintosh/adb: Properly mark continued kernel messages
  powerpc/pseries: Fix cpu hotplug crash with memoryless nodes
  powerpc/numa: Ensure nodes initialized for hotplug
  powerpc/numa: Use ibm,max-associativity-domains to discover possible nodes
  powerpc/kernel: Block interrupts when updating TIDR
  powerpc/powernv/idoa: Remove unnecessary pcidev from pci_dn
  powerpc/mm/nohash: do not flush the entire mm when range is a single page
  powerpc/pseries: Add Initialization of VF Bars
  powerpc/pseries/pci: Associate PEs to VFs in configure SR-IOV
  powerpc/eeh: Add EEH notify resume sysfs
  powerpc/eeh: Add EEH operations to notify resume
  ...

1 files changed, 86 insertions, 114 deletions

diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index 600a68bd77f5..fdd00939270b 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -2,76 +2,64 @@
 #ifndef _ARCH_POWERPC_LOCAL_H
 #define _ARCH_POWERPC_LOCAL_H
 
+#ifdef CONFIG_PPC_BOOK3S_64
+
 #include <linux/percpu.h>
 #include <linux/atomic.h>
+#include <linux/irqflags.h>
+
+#include <asm/hw_irq.h>
 
 typedef struct
 {
-	atomic_long_t a;
+	long v;
 } local_t;
 
-#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
-
-#define local_read(l)	atomic_long_read(&(l)->a)
-#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
+#define LOCAL_INIT(i)	{ (i) }
 
-#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
-#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
-#define local_inc(l)	atomic_long_inc(&(l)->a)
-#define local_dec(l)	atomic_long_dec(&(l)->a)
-
-static __inline__ long local_add_return(long a, local_t *l)
+static __inline__ long local_read(local_t *l)
 {
-	long t;
-
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%2,0) "			# local_add_return\n\
-	add	%0,%1,%0\n"
-	PPC405_ERR77(0,%2)
-	PPC_STLCX	"%0,0,%2 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (a), "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
+	return READ_ONCE(l->v);
 }
 
-#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
-
-static __inline__ long local_sub_return(long a, local_t *l)
+static __inline__ void local_set(local_t *l, long i)
 {
-	long t;
+	WRITE_ONCE(l->v, i);
+}
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%2,0) "			# local_sub_return\n\
-	subf	%0,%1,%0\n"
-	PPC405_ERR77(0,%2)
-	PPC_STLCX	"%0,0,%2 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (a), "r" (&(l->a.counter))
-	: "cc", "memory");
+#define LOCAL_OP(op, c_op)						\
+static __inline__ void local_##op(long i, local_t *l)			\
+{									\
+	unsigned long flags;						\
+									\
+	powerpc_local_irq_pmu_save(flags);				\
+	l->v c_op i;						\
+	powerpc_local_irq_pmu_restore(flags);				\
+}
 
-	return t;
+#define LOCAL_OP_RETURN(op, c_op)					\
+static __inline__ long local_##op##_return(long a, local_t *l)		\
+{									\
+	long t;								\
+	unsigned long flags;						\
+									\
+	powerpc_local_irq_pmu_save(flags);				\
+	t = (l->v c_op a);						\
+	powerpc_local_irq_pmu_restore(flags);				\
+									\
+	return t;							\
 }
 
-static __inline__ long local_inc_return(local_t *l)
-{
-	long t;
+#define LOCAL_OPS(op, c_op)		\
+	LOCAL_OP(op, c_op)		\
+	LOCAL_OP_RETURN(op, c_op)
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_inc_return\n\
-	addic	%0,%0,1\n"
-	PPC405_ERR77(0,%1)
-	PPC_STLCX	"%0,0,%1 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "xer", "memory");
+LOCAL_OPS(add, +=)
+LOCAL_OPS(sub, -=)
 
-	return t;
-}
+#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
+#define local_inc_return(l)		local_add_return(1LL, l)
+#define local_inc(l)			local_inc_return(l)
 
 /*
  * local_inc_and_test - increment and test
@@ -81,28 +69,39 @@ static __inline__ long local_inc_return(local_t *l)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-#define local_inc_and_test(l) (local_inc_return(l) == 0)
+#define local_inc_and_test(l)		(local_inc_return(l) == 0)
 
-static __inline__ long local_dec_return(local_t *l)
+#define local_dec_return(l)		local_sub_return(1LL, l)
+#define local_dec(l)			local_dec_return(l)
+#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
+#define local_dec_and_test(l)		(local_dec_return((l)) == 0)
+
+static __inline__ long local_cmpxchg(local_t *l, long o, long n)
 {
 	long t;
+	unsigned long flags;
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_dec_return\n\
-	addic	%0,%0,-1\n"
-	PPC405_ERR77(0,%1)
-	PPC_STLCX	"%0,0,%1\n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "xer", "memory");
+	powerpc_local_irq_pmu_save(flags);
+	t = l->v;
+	if (t == o)
+		l->v = n;
+	powerpc_local_irq_pmu_restore(flags);
 
 	return t;
 }
 
-#define local_cmpxchg(l, o, n) \
-	(cmpxchg_local(&((l)->a.counter), (o), (n)))
-#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+static __inline__ long local_xchg(local_t *l, long n)
+{
+	long t;
+	unsigned long flags;
+
+	powerpc_local_irq_pmu_save(flags);
+	t = l->v;
+	l->v = n;
+	powerpc_local_irq_pmu_restore(flags);
+
+	return t;
+}
 
 /**
  * local_add_unless - add unless the number is a given value
@@ -115,62 +114,35 @@ static __inline__ long local_dec_return(local_t *l)
  */
 static __inline__ int local_add_unless(local_t *l, long a, long u)
 {
-	long t;
-
-	__asm__ __volatile__ (
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_add_unless\n\
-	cmpw	0,%0,%3 \n\
-	beq-	2f \n\
-	add	%0,%2,%0 \n"
-	PPC405_ERR77(0,%2)
-	PPC_STLCX	"%0,0,%1 \n\
-	bne-	1b \n"
-"	subf	%0,%2,%0 \n\
-2:"
-	: "=&r" (t)
-	: "r" (&(l->a.counter)), "r" (a), "r" (u)
-	: "cc", "memory");
-
-	return t != u;
-}
-
-#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
-
-#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
-#define local_dec_and_test(l)		(local_dec_return((l)) == 0)
-
-/*
- * Atomically test *l and decrement if it is greater than 0.
- * The function returns the old value of *l minus 1.
- */
-static __inline__ long local_dec_if_positive(local_t *l)
-{
-	long t;
+	unsigned long flags;
+	int ret = 0;
 
-	__asm__ __volatile__(
-"1:"	PPC_LLARX(%0,0,%1,0) "			# local_dec_if_positive\n\
-	cmpwi	%0,1\n\
-	addi	%0,%0,-1\n\
-	blt-	2f\n"
-	PPC405_ERR77(0,%1)
-	PPC_STLCX	"%0,0,%1\n\
-	bne-	1b"
-	"\n\
-2:"	: "=&b" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "memory");
+	powerpc_local_irq_pmu_save(flags);
+	if (l->v != u) {
+		l->v += a;
+		ret = 1;
+	}
+	powerpc_local_irq_pmu_restore(flags);
 
-	return t;
+	return ret;
 }
 
+#define local_inc_not_zero(l)		local_add_unless((l), 1, 0)
+
 /* Use these for per-cpu local_t variables: on some archs they are
  * much more efficient than these naive implementations.  Note they take
  * a variable, not an address.
  */
 
-#define __local_inc(l)		((l)->a.counter++)
-#define __local_dec(l)		((l)->a.counter++)
-#define __local_add(i,l)	((l)->a.counter+=(i))
-#define __local_sub(i,l)	((l)->a.counter-=(i))
+#define __local_inc(l)		((l)->v++)
+#define __local_dec(l)		((l)->v++)
+#define __local_add(i,l)	((l)->v+=(i))
+#define __local_sub(i,l)	((l)->v-=(i))
+
+#else /* CONFIG_PPC64 */
+
+#include <asm-generic/local.h>
+
+#endif /* CONFIG_PPC64 */
 
 #endif /* _ARCH_POWERPC_LOCAL_H */