From 9b4fffa14906fce7aabf1f032ddd7efc7a031bba Mon Sep 17 00:00:00 2001
From: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Date: Tue, 9 Feb 2016 18:17:48 +1100
Subject: powerpc/powernv: new function to access OPAL msglog

Currently, the OPAL msglog/console buffer is exposed as a sysfs file, with
the sysfs read handler responsible for retrieving the log from the OPAL
buffer. We'd like to be able to use it in xmon as well.

Refactor the OPAL msglog code to create a new function, opal_msglog_copy(),
that copies to an arbitrary buffer. Separate the initialisation code into
generic memcons init and sysfs file creation.

Signed-off-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/opal.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 07a99e638449..9d86c6651716 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -248,6 +248,7 @@ extern int opal_elog_init(void);
 extern void opal_platform_dump_init(void);
 extern void opal_sys_param_init(void);
 extern void opal_msglog_init(void);
+extern void opal_msglog_sysfs_init(void);
 extern int opal_async_comp_init(void);
 extern int opal_sensor_init(void);
 extern int opal_hmi_handler_init(void);
@@ -273,6 +274,8 @@ void opal_free_sg_list(struct opal_sg_list *sg);
 
 extern int opal_error_code(int rc);
 
+ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_OPAL_H */
-- 
cgit v1.2.3


From ee8222fe95e40ade9f50b852095d4626631ebbbe Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Thu, 22 Oct 2015 09:22:16 +0800
Subject: powerpc/powernv: use one M64 BAR in Single PE mode for one VF BAR

In current implementation, when VF BAR is bigger than 64MB, it uses 4 M64
BARs in Single PE mode to cover the number of VFs required to be enabled.
By doing so, several VFs would be in one VF Group and leads to interference
between VFs in the same group.

And in this patch, m64_wins is renamed to m64_map, which means index number
of the M64 BAR used to map the VF BAR. Based on Gavin's comments. Also
makes sure the VF BAR size is bigger than 32MB when M64 BAR is used in
Single PE mode.

This patch changes the design by using one M64 BAR in Single PE mode for
one VF BAR. This gives absolute isolation for VFs.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/pci-bridge.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 54843ca5fa2b..11d3543a57f2 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -216,10 +216,9 @@ struct pci_dn {
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
 	int     offset;			/* PE# for the first VF PE */
-#define M64_PER_IOV 4
-	int     m64_per_iov;
+	bool    m64_single_mode;	/* Use M64 BAR in Single Mode */
 #define IODA_INVALID_M64        (-1)
-	int     m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV];
+	int     (*m64_map)[PCI_SRIOV_NUM_BARS];
 #endif /* CONFIG_PCI_IOV */
 #endif
 	struct list_head child_list;
-- 
cgit v1.2.3


From be283eeb7f6d9165b3c50f5222123ac25cf0d417 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Thu, 22 Oct 2015 09:22:19 +0800
Subject: powerpc/powernv: allocate sparse PE# when using M64 BAR in Single PE
 mode

When M64 BAR is set to Single PE mode, the PE# assigned to VF could be
sparse.

This patch restructures the code to allocate sparse PE# for VFs when M64
BAR is set to Single PE mode. Also it rename the offset to pe_num_map to
reflect the content is the PE number.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/pci-bridge.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 11d3543a57f2..b0b43f5fbc5f 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -215,7 +215,7 @@ struct pci_dn {
 #ifdef CONFIG_PCI_IOV
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
-	int     offset;			/* PE# for the first VF PE */
+	int     *pe_num_map;		/* PE# for the first VF PE or array */
 	bool    m64_single_mode;	/* Use M64 BAR in Single Mode */
 #define IODA_INVALID_M64        (-1)
 	int     (*m64_map)[PCI_SRIOV_NUM_BARS];
-- 
cgit v1.2.3


From dc53617c4a3f6ca35641dfd4279720365ce9f4da Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 6 Jan 2016 10:08:25 +0800
Subject: powerpc: atomic: Implement atomic{, 64}_*_return_* variants

On powerpc, acquire and release semantics can be achieved with
lightweight barriers("lwsync" and "ctrl+isync"), which can be used to
implement __atomic_op_{acquire,release}.

For release semantics, since we only need to ensure all memory accesses
that issue before must take effects before the -store- part of the
atomics, "lwsync" is what we only need. On the platform without
"lwsync", "sync" should be used. Therefore in __atomic_op_release() we
use PPC_RELEASE_BARRIER.

For acquire semantics, "lwsync" is what we only need for the similar
reason.  However on the platform without "lwsync", we can use "isync"
rather than "sync" as an acquire barrier. Therefore in
__atomic_op_acquire() we use PPC_ACQUIRE_BARRIER, which is barrier() on
UP, "lwsync" if available and "isync" otherwise.

Implement atomic{,64}_{add,sub,inc,dec}_return_relaxed, and build other
variants with these helpers.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/atomic.h | 147 ++++++++++++++++++++++----------------
 1 file changed, 85 insertions(+), 62 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 55f106ed12bf..a35c27709e05 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -12,6 +12,24 @@
 
 #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
+ * on the platform without lwsync.
+ */
+#define __atomic_op_acquire(op, args...)				\
+({									\
+	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory");	\
+	__ret;								\
+})
+
+#define __atomic_op_release(op, args...)				\
+({									\
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory");	\
+	op##_relaxed(args);						\
+})
+
 static __inline__ int atomic_read(const atomic_t *v)
 {
 	int t;
@@ -42,27 +60,27 @@ static __inline__ void atomic_##op(int a, atomic_t *v)			\
 	: "cc");							\
 }									\
 
-#define ATOMIC_OP_RETURN(op, asm_op)					\
-static __inline__ int atomic_##op##_return(int a, atomic_t *v)		\
+#define ATOMIC_OP_RETURN_RELAXED(op, asm_op)				\
+static inline int atomic_##op##_return_relaxed(int a, atomic_t *v)	\
 {									\
 	int t;								\
 									\
 	__asm__ __volatile__(						\
-	PPC_ATOMIC_ENTRY_BARRIER					\
-"1:	lwarx	%0,0,%2		# atomic_" #op "_return\n"		\
-	#asm_op " %0,%1,%0\n"						\
-	PPC405_ERR77(0,%2)						\
-"	stwcx.	%0,0,%2 \n"						\
+"1:	lwarx	%0,0,%3		# atomic_" #op "_return_relaxed\n"	\
+	#asm_op " %0,%2,%0\n"						\
+	PPC405_ERR77(0, %3)						\
+"	stwcx.	%0,0,%3\n"						\
 "	bne-	1b\n"							\
-	PPC_ATOMIC_EXIT_BARRIER						\
-	: "=&r" (t)							\
+	: "=&r" (t), "+m" (v->counter)					\
 	: "r" (a), "r" (&v->counter)					\
-	: "cc", "memory");						\
+	: "cc");							\
 									\
 	return t;							\
 }
 
-#define ATOMIC_OPS(op, asm_op) ATOMIC_OP(op, asm_op) ATOMIC_OP_RETURN(op, asm_op)
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_OP_RETURN_RELAXED(op, asm_op)
 
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)
@@ -71,8 +89,11 @@ ATOMIC_OP(and, and)
 ATOMIC_OP(or, or)
 ATOMIC_OP(xor, xor)
 
+#define atomic_add_return_relaxed atomic_add_return_relaxed
+#define atomic_sub_return_relaxed atomic_sub_return_relaxed
+
 #undef ATOMIC_OPS
-#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
@@ -92,21 +113,19 @@ static __inline__ void atomic_inc(atomic_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ int atomic_inc_return(atomic_t *v)
+static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 {
 	int t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# atomic_inc_return\n\
-	addic	%0,%0,1\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1 \n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
+"1:	lwarx	%0,0,%2		# atomic_inc_return_relaxed\n"
+"	addic	%0,%0,1\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%0,0,%2\n"
+"	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }
@@ -136,25 +155,26 @@ static __inline__ void atomic_dec(atomic_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ int atomic_dec_return(atomic_t *v)
+static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 {
 	int t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# atomic_dec_return\n\
-	addic	%0,%0,-1\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1\n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
+"1:	lwarx	%0,0,%2		# atomic_dec_return_relaxed\n"
+"	addic	%0,%0,-1\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%0,0,%2\n"
+"	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }
 
+#define atomic_inc_return_relaxed atomic_inc_return_relaxed
+#define atomic_dec_return_relaxed atomic_dec_return_relaxed
+
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -285,26 +305,27 @@ static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
 	: "cc");							\
 }
 
-#define ATOMIC64_OP_RETURN(op, asm_op)					\
-static __inline__ long atomic64_##op##_return(long a, atomic64_t *v)	\
+#define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
+static inline long							\
+atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
 {									\
 	long t;								\
 									\
 	__asm__ __volatile__(						\
-	PPC_ATOMIC_ENTRY_BARRIER					\
-"1:	ldarx	%0,0,%2		# atomic64_" #op "_return\n"		\
-	#asm_op " %0,%1,%0\n"						\
-"	stdcx.	%0,0,%2 \n"						\
+"1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
+	#asm_op " %0,%2,%0\n"						\
+"	stdcx.	%0,0,%3\n"						\
 "	bne-	1b\n"							\
-	PPC_ATOMIC_EXIT_BARRIER						\
-	: "=&r" (t)							\
+	: "=&r" (t), "+m" (v->counter)					\
 	: "r" (a), "r" (&v->counter)					\
-	: "cc", "memory");						\
+	: "cc");							\
 									\
 	return t;							\
 }
 
-#define ATOMIC64_OPS(op, asm_op) ATOMIC64_OP(op, asm_op) ATOMIC64_OP_RETURN(op, asm_op)
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)
@@ -312,8 +333,11 @@ ATOMIC64_OP(and, and)
 ATOMIC64_OP(or, or)
 ATOMIC64_OP(xor, xor)
 
-#undef ATOMIC64_OPS
-#undef ATOMIC64_OP_RETURN
+#define atomic64_add_return_relaxed atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
+
+#undef ATOPIC64_OPS
+#undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
@@ -332,20 +356,18 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ long atomic64_inc_return(atomic64_t *v)
+static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 {
 	long t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# atomic64_inc_return\n\
-	addic	%0,%0,1\n\
-	stdcx.	%0,0,%1 \n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
+"1:	ldarx	%0,0,%2		# atomic64_inc_return_relaxed\n"
+"	addic	%0,%0,1\n"
+"	stdcx.	%0,0,%2\n"
+"	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }
@@ -374,24 +396,25 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	: "cc", "xer");
 }
 
-static __inline__ long atomic64_dec_return(atomic64_t *v)
+static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 {
 	long t;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# atomic64_dec_return\n\
-	addic	%0,%0,-1\n\
-	stdcx.	%0,0,%1\n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
+"1:	ldarx	%0,0,%2		# atomic64_dec_return_relaxed\n"
+"	addic	%0,%0,-1\n"
+"	stdcx.	%0,0,%2\n"
+"	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc", "xer", "memory");
+	: "cc", "xer");
 
 	return t;
 }
 
+#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
+#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
+
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 
-- 
cgit v1.2.3


From 26760fc19a7e663e4f49d586aca6740fb21d887d Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Tue, 15 Dec 2015 22:24:16 +0800
Subject: powerpc: atomic: Implement acquire/release/relaxed variants for xchg

Implement xchg{,64}_relaxed and atomic{,64}_xchg_relaxed, based on these
_relaxed variants, release/acquire variants and fully ordered versions
can be built.

Note that xchg{,64}_relaxed and atomic_{,64}_xchg_relaxed are not
compiler barriers.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/atomic.h  |  2 ++
 arch/powerpc/include/asm/cmpxchg.h | 69 +++++++++++++++++---------------------
 2 files changed, 32 insertions(+), 39 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index a35c27709e05..a19fcdc318ee 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -177,6 +177,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
  * __atomic_add_unless - add unless the number is a given value
@@ -444,6 +445,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+#define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
  * atomic64_add_unless - add unless the number is a given value
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d1a8d93cccfd..17c7e14b37ca 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -9,21 +9,20 @@
 /*
  * Atomic exchange
  *
- * Changes the memory location '*ptr' to be val and returns
+ * Changes the memory location '*p' to be val and returns
  * the previous value stored there.
  */
+
 static __always_inline unsigned long
-__xchg_u32(volatile void *p, unsigned long val)
+__xchg_u32_local(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");
@@ -31,42 +30,34 @@ __xchg_u32(volatile void *p, unsigned long val)
 	return prev;
 }
 
-/*
- * Atomic exchange
- *
- * Changes the memory location '*ptr' to be val and returns
- * the previous value stored there.
- */
 static __always_inline unsigned long
-__xchg_u32_local(volatile void *p, unsigned long val)
+__xchg_u32_relaxed(u32 *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%3,0,%2 \n\
-	bne-	1b"
-	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+"1:	lwarx	%0,0,%2\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
 	: "r" (p), "r" (val)
-	: "cc", "memory");
+	: "cc");
 
 	return prev;
 }
 
 #ifdef CONFIG_PPC64
 static __always_inline unsigned long
-__xchg_u64(volatile void *p, unsigned long val)
+__xchg_u64_local(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2 \n"
 	PPC405_ERR77(0,%2)
 "	stdcx.	%3,0,%2 \n\
 	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
 	: "r" (p), "r" (val)
 	: "cc", "memory");
@@ -75,18 +66,18 @@ __xchg_u64(volatile void *p, unsigned long val)
 }
 
 static __always_inline unsigned long
-__xchg_u64_local(volatile void *p, unsigned long val)
+__xchg_u64_relaxed(u64 *p, unsigned long val)
 {
 	unsigned long prev;
 
 	__asm__ __volatile__(
-"1:	ldarx	%0,0,%2 \n"
-	PPC405_ERR77(0,%2)
-"	stdcx.	%3,0,%2 \n\
-	bne-	1b"
-	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+"1:	ldarx	%0,0,%2\n"
+	PPC405_ERR77(0, %2)
+"	stdcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
 	: "r" (p), "r" (val)
-	: "cc", "memory");
+	: "cc");
 
 	return prev;
 }
@@ -99,14 +90,14 @@ __xchg_u64_local(volatile void *p, unsigned long val)
 extern void __xchg_called_with_bad_pointer(void);
 
 static __always_inline unsigned long
-__xchg(volatile void *ptr, unsigned long x, unsigned int size)
+__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
 {
 	switch (size) {
 	case 4:
-		return __xchg_u32(ptr, x);
+		return __xchg_u32_local(ptr, x);
 #ifdef CONFIG_PPC64
 	case 8:
-		return __xchg_u64(ptr, x);
+		return __xchg_u64_local(ptr, x);
 #endif
 	}
 	__xchg_called_with_bad_pointer();
@@ -114,25 +105,19 @@ __xchg(volatile void *ptr, unsigned long x, unsigned int size)
 }
 
 static __always_inline unsigned long
-__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
+__xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
 {
 	switch (size) {
 	case 4:
-		return __xchg_u32_local(ptr, x);
+		return __xchg_u32_relaxed(ptr, x);
 #ifdef CONFIG_PPC64
 	case 8:
-		return __xchg_u64_local(ptr, x);
+		return __xchg_u64_relaxed(ptr, x);
 #endif
 	}
 	__xchg_called_with_bad_pointer();
 	return x;
 }
-#define xchg(ptr,x)							     \
-  ({									     \
-     __typeof__(*(ptr)) _x_ = (x);					     \
-     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
-  })
-
 #define xchg_local(ptr,x)						     \
   ({									     \
      __typeof__(*(ptr)) _x_ = (x);					     \
@@ -140,6 +125,12 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
      		(unsigned long)_x_, sizeof(*(ptr))); 			     \
   })
 
+#define xchg_relaxed(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
+			(unsigned long)_x_, sizeof(*(ptr)));		\
+})
 /*
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
-- 
cgit v1.2.3


From 56c08e6d226c860ad097fa6ba109133228c56722 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Tue, 15 Dec 2015 22:24:17 +0800
Subject: powerpc: atomic: Implement acquire/release/relaxed variants for
 cmpxchg

Implement cmpxchg{,64}_relaxed and atomic{,64}_cmpxchg_relaxed, based on
which _release variants can be built.

To avoid superfluous barriers in _acquire variants, we implement these
operations with assembly code rather use __atomic_op_acquire() to build
them automatically.

For the same reason, we keep the assembly implementation of fully
ordered cmpxchg operations.

However, we don't do the similar for _release, because that will require
putting barriers in the middle of ll/sc loops, which is probably a bad
idea.

Note cmpxchg{,64}_relaxed and atomic{,64}_cmpxchg_relaxed are not
compiler barriers.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/atomic.h  |  10 +++
 arch/powerpc/include/asm/cmpxchg.h | 149 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 158 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index a19fcdc318ee..ae0751ef8788 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -176,6 +176,11 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 #define atomic_dec_return_relaxed atomic_dec_return_relaxed
 
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
+#define atomic_cmpxchg_relaxed(v, o, n) \
+	cmpxchg_relaxed(&((v)->counter), (o), (n))
+#define atomic_cmpxchg_acquire(v, o, n) \
+	cmpxchg_acquire(&((v)->counter), (o), (n))
+
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
@@ -444,6 +449,11 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 }
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
+#define atomic64_cmpxchg_relaxed(v, o, n) \
+	cmpxchg_relaxed(&((v)->counter), (o), (n))
+#define atomic64_cmpxchg_acquire(v, o, n) \
+	cmpxchg_acquire(&((v)->counter), (o), (n))
+
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index 17c7e14b37ca..cae4fa85250c 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -181,6 +181,56 @@ __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
 	return prev;
 }
 
+static __always_inline unsigned long
+__cmpxchg_u32_relaxed(u32 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+/*
+ * cmpxchg family don't have order guarantee if cmp part fails, therefore we
+ * can avoid superfluous barriers if we use assembly code to implement
+ * cmpxchg() and cmpxchg_acquire(), however we don't do the similar for
+ * cmpxchg_release() because that will result in putting a barrier in the
+ * middle of a ll/sc loop, which is probably a bad idea. For example, this
+ * might cause the conditional store more likely to fail.
+ */
+static __always_inline unsigned long
+__cmpxchg_u32_acquire(u32 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+	PPC405_ERR77(0, %2)
+"	stwcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+	"\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
 #ifdef CONFIG_PPC64
 static __always_inline unsigned long
 __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
@@ -224,6 +274,46 @@ __cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
 
 	return prev;
 }
+
+static __always_inline unsigned long
+__cmpxchg_u64_relaxed(u64 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64_relaxed\n"
+"	cmpd	0,%0,%3\n"
+"	bne-	2f\n"
+"	stdcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64_acquire\n"
+"	cmpd	0,%0,%3\n"
+"	bne-	2f\n"
+"	stdcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+	"\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
 #endif
 
 /* This function doesn't exist, so you'll get a linker error
@@ -262,6 +352,37 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 	return old;
 }
 
+static __always_inline unsigned long
+__cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new,
+		  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_relaxed(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_relaxed(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new,
+		  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_acquire(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_acquire(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
 #define cmpxchg(ptr, o, n)						 \
   ({									 \
      __typeof__(*(ptr)) _o_ = (o);					 \
@@ -279,6 +400,23 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 				    (unsigned long)_n_, sizeof(*(ptr))); \
   })
 
+#define cmpxchg_relaxed(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
+			(unsigned long)_o_, (unsigned long)_n_,		\
+			sizeof(*(ptr)));				\
+})
+
+#define cmpxchg_acquire(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
+			(unsigned long)_o_, (unsigned long)_n_,		\
+			sizeof(*(ptr)));				\
+})
 #ifdef CONFIG_PPC64
 #define cmpxchg64(ptr, o, n)						\
   ({									\
@@ -290,7 +428,16 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg_local((ptr), (o), (n));					\
   })
-#define cmpxchg64_relaxed	cmpxchg64_local
+#define cmpxchg64_relaxed(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_relaxed((ptr), (o), (n));				\
+})
+#define cmpxchg64_acquire(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_acquire((ptr), (o), (n));				\
+})
 #else
 #include <asm-generic/cmpxchg-local.h>
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-- 
cgit v1.2.3


From ce5732a28dd09956540f61ba9d902b63e73a1232 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Fri, 19 Feb 2016 11:16:22 +1100
Subject: powerpc/powernv: Create separate subcores CPU feature bit

Subcores isn't really part of the 2.07 architecture but currently we
turn it on using the 2.07 feature bit.  Subcores is really a POWER8
specific feature.

This adds a new CPU_FTR bit just for subcores and moves the subcore
init code over to use this.

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cputable.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index b118072670fb..a47e175992b0 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -196,6 +196,7 @@ enum {
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_SUBCORE			LONG_ASM_CONST(0x2000000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -443,7 +444,7 @@ enum {
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
 #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-- 
cgit v1.2.3


From c3ab300ea55541014348561e7690c41c79966ac6 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Fri, 19 Feb 2016 11:16:24 +1100
Subject: powerpc: Add POWER9 cputable entry

Add a cputable entry for POWER9.  More code is required to actually
boot and run on a POWER9 but this gets the base piece in which we can
start building on.

Copies over from POWER8 except for:
- Adds a new CPU_FTR_ARCH_300 bit to start hanging new architecture
   features from (in subsequent patches).
- Advertises new user features bits PPC_FEATURE2_ARCH_3_00 &
  HAS_IEEE128 when on POWER9.
- Drops CPU_FTR_SUBCORE.
- Drops PMU code and machine check.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cputable.h   | 17 ++++++++++++++---
 arch/powerpc/include/asm/mmu-hash64.h |  1 +
 arch/powerpc/include/asm/mmu.h        |  1 +
 3 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index a47e175992b0..94ace9b4c4e1 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -171,7 +171,7 @@ enum {
 #define CPU_FTR_ARCH_201		LONG_ASM_CONST(0x0000000200000000)
 #define CPU_FTR_ARCH_206		LONG_ASM_CONST(0x0000000400000000)
 #define CPU_FTR_ARCH_207S		LONG_ASM_CONST(0x0000000800000000)
-/* Free					LONG_ASM_CONST(0x0000001000000000) */
+#define CPU_FTR_ARCH_300		LONG_ASM_CONST(0x0000001000000000)
 #define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000002000000000)
 #define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000004000000000)
 #define CPU_FTR_SMT			LONG_ASM_CONST(0x0000008000000000)
@@ -447,6 +447,16 @@ enum {
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
 #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
+#define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
+	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -465,7 +475,7 @@ enum {
 	    (CPU_FTRS_POWER4 | CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
 	     CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
 	     CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \
-	     CPU_FTRS_PA6T | CPU_FTR_VSX)
+	     CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9)
 #endif
 #else
 enum {
@@ -516,7 +526,8 @@ enum {
 	    (CPU_FTRS_POWER4 & CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
 	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
 	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
-	     CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE)
+	     CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & \
+	     CPU_FTRS_POWER9)
 #endif
 #else
 enum {
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 7352d3f212df..e36dc90c80d0 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -114,6 +114,7 @@
 
 #define POWER7_TLB_SETS		128	/* # sets in POWER7 TLB */
 #define POWER8_TLB_SETS		512	/* # sets in POWER8 TLB */
+#define POWER9_TLB_SETS_HASH	256	/* # sets in POWER9 TLB Hash mode */
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 3d5abfe6ba67..54d46504733d 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -97,6 +97,7 @@
 #define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER8		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
+#define MMU_FTRS_POWER9		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_CELL		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
 				MMU_FTR_CI_LARGE_PAGE
 #define MMU_FTRS_PA6T		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
-- 
cgit v1.2.3


From 10d8b1480e6966ba03cd3afad3b5d6eb5e341fae Mon Sep 17 00:00:00 2001
From: pan xinhui <xinhui.pan@linux.vnet.ibm.com>
Date: Tue, 23 Feb 2016 19:05:01 +0800
Subject: powerpc: Use BUILD_BUG_ON_MSG() for unsupported {cmp}xchg sizes

__xchg_called_with_bad_pointer() can't tell us which code uses {cmp}xchg
with an unsupported size, and no error is reported until the link stage.

To make such problems easier to debug, use BUILD_BUG_ON_MSG() instead.

Signed-off-by: pan xinhui <xinhui.pan@linux.vnet.ibm.com>
[mpe: Tweak change log wording & add relaxed/acquire]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

fixup
---
 arch/powerpc/include/asm/cmpxchg.h | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index cae4fa85250c..44efe739b6b9 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -5,6 +5,7 @@
 #include <linux/compiler.h>
 #include <asm/synch.h>
 #include <asm/asm-compat.h>
+#include <linux/bug.h>
 
 /*
  * Atomic exchange
@@ -83,12 +84,6 @@ __xchg_u64_relaxed(u64 *p, unsigned long val)
 }
 #endif
 
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid xchg().
- */
-extern void __xchg_called_with_bad_pointer(void);
-
 static __always_inline unsigned long
 __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
 {
@@ -100,7 +95,7 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
 		return __xchg_u64_local(ptr, x);
 #endif
 	}
-	__xchg_called_with_bad_pointer();
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg");
 	return x;
 }
 
@@ -115,7 +110,7 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
 		return __xchg_u64_relaxed(ptr, x);
 #endif
 	}
-	__xchg_called_with_bad_pointer();
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local");
 	return x;
 }
 #define xchg_local(ptr,x)						     \
@@ -316,10 +311,6 @@ __cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new)
 }
 #endif
 
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
 static __always_inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
 	  unsigned int size)
@@ -332,7 +323,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
 		return __cmpxchg_u64(ptr, old, new);
 #endif
 	}
-	__cmpxchg_called_with_bad_pointer();
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg");
 	return old;
 }
 
@@ -348,7 +339,7 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 		return __cmpxchg_u64_local(ptr, old, new);
 #endif
 	}
-	__cmpxchg_called_with_bad_pointer();
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_local");
 	return old;
 }
 
@@ -364,7 +355,7 @@ __cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new,
 		return __cmpxchg_u64_relaxed(ptr, old, new);
 #endif
 	}
-	__cmpxchg_called_with_bad_pointer();
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_relaxed");
 	return old;
 }
 
@@ -380,7 +371,7 @@ __cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new,
 		return __cmpxchg_u64_acquire(ptr, old, new);
 #endif
 	}
-	__cmpxchg_called_with_bad_pointer();
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_acquire");
 	return old;
 }
 #define cmpxchg(ptr, o, n)						 \
-- 
cgit v1.2.3


From 1ec3f937102154b54c3ba97b79d4bd3931bb0eaa Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:12 +1100
Subject: powerpc/mm/book3s-64: Clean up some obsolete or misleading comments

No code changes.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 8d1c8162f0c1..9a0a4ef53b6d 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -4,8 +4,7 @@
 
 /*
  * Common bits between 4K and 64K pages in a linux-style PTE.
- * These match the bits in the (hardware-defined) PowerPC PTE as closely
- * as possible. Additional bits may be defined in pgtable-hash64-*.h
+ * Additional bits may be defined in pgtable-hash64-*.h
  *
  * Note: We only support user read/write permissions. Supervisor always
  * have full read/write to pages above PAGE_OFFSET (pages below that
@@ -14,13 +13,13 @@
  * We could create separate kernel read-only if we used the 3 PP bits
  * combinations that newer processors provide but we currently don't.
  */
-#define _PAGE_PTE		0x00001
+#define _PAGE_PTE		0x00001	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		0x00002 /* software: pte contains a translation */
 #define _PAGE_BIT_SWAP_TYPE	2
-#define _PAGE_USER		0x00004 /* matches one of the PP bits */
-#define _PAGE_EXEC		0x00008 /* No execute on POWER4 and newer (we invert) */
-#define _PAGE_GUARDED		0x00010
-/* We can derive Memory coherence from _PAGE_NO_CACHE */
+#define _PAGE_USER		0x00004 /* page may be accessed by userspace */
+#define _PAGE_EXEC		0x00008 /* execute permission */
+#define _PAGE_GUARDED		0x00010 /* G: guarded (side-effect) page */
+/* M (memory coherence) is always set in the HPTE, so we don't need it here */
 #define _PAGE_COHERENT		0x0
 #define _PAGE_NO_CACHE		0x00020 /* I: cache inhibit */
 #define _PAGE_WRITETHRU		0x00040 /* W: cache write-through */
-- 
cgit v1.2.3


From f1a9ae034a263d93ea408825afe699aebf37010a Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:13 +1100
Subject: powerpc/mm/book3s-64: Free up 7 high-order bits in the Linux PTE

This frees up bits 57-63 in the Linux PTE on 64-bit Book 3S machines.
In the 4k page case, this is done just by reducing the size of the
RPN field to 39 bits, giving 51-bit real addresses.  In the 64k page
case, we had 10 unused bits in the middle of the PTE, so this moves
the RPN field down 10 bits to make use of those unused bits.  This
means the RPN field is now 3 bits larger at 37 bits, giving 53-bit
real addresses in the normal case, or 49-bit real addresses for the
special 4k PFN case.

We are doing this in order to be able to move some other PTE bits
into the positions where PowerISA V3.0 processors will expect to
find them in radix-tree mode.  Ultimately we will be able to move
the RPN field to lower bit positions and make it larger.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h  |  1 +
 arch/powerpc/include/asm/book3s/64/hash-64k.h | 10 ++++++----
 arch/powerpc/include/asm/book3s/64/hash.h     |  6 +++---
 arch/powerpc/include/asm/book3s/64/pgtable.h  |  6 +++---
 4 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index ea0414d6659e..bee3643fa097 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -53,6 +53,7 @@
 
 /* shift to put page number into pte */
 #define PTE_RPN_SHIFT	(18)
+#define PTE_RPN_SIZE	(39)	/* gives 51-bit real addresses */
 
 #define _PAGE_4K_PFN		0
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 849bbec80f7b..a8c4c2a1940b 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -39,10 +39,12 @@
 
 /* Shift to put page number into pte.
  *
- * That gives us a max RPN of 34 bits, which means a max of 50 bits
- * of addressable physical space, or 46 bits for the special 4k PFNs.
+ * That gives us a max RPN of 37 bits, which means a max of 53 bits
+ * of addressable physical space, or 49 bits for the special 4k PFNs.
  */
-#define PTE_RPN_SHIFT	(30)
+#define PTE_RPN_SHIFT	(20)
+#define PTE_RPN_SIZE	(37)
+
 /*
  * we support 16 fragments per PTE page of 64K size.
  */
@@ -120,7 +122,7 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
 	(((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K)
 
 #define remap_4k_pfn(vma, addr, pfn, prot)				\
-	(WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL :	\
+	(WARN_ON(((pfn) >= (1UL << PTE_RPN_SIZE))) ? -EINVAL :	\
 		remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,	\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN)))
 
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 9a0a4ef53b6d..64eff409b027 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -131,7 +131,7 @@
  * The mask convered by the RPN must be a ULL on 32-bit platforms with
  * 64-bit PTEs
  */
-#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+#define PTE_RPN_MASK	(((1UL << PTE_RPN_SIZE) - 1) << PTE_RPN_SHIFT)
 /*
  * _PAGE_CHG_MASK masks of bits that are to be preserved across
  * pgprot changes
@@ -412,13 +412,13 @@ static inline int pte_present(pte_t pte)
  */
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 {
-	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+	return __pte((((pte_basic_t)(pfn) << PTE_RPN_SHIFT) & PTE_RPN_MASK) |
 		     pgprot_val(pgprot));
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return pte_val(pte) >> PTE_RPN_SHIFT;
+	return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT;
 }
 
 /* Generic modifiers for PTE bits */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index ac07a30a7934..c8240b737d11 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -154,10 +154,10 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)		((x).val >> PTE_RPN_SHIFT)
+#define __swp_offset(x)		(((x).val & PTE_RPN_MASK) >> PTE_RPN_SHIFT)
 #define __swp_entry(type, offset)	((swp_entry_t) { \
-					((type) << _PAGE_BIT_SWAP_TYPE) \
-					| ((offset) << PTE_RPN_SHIFT) })
+				((type) << _PAGE_BIT_SWAP_TYPE) \
+				| (((offset) << PTE_RPN_SHIFT) & PTE_RPN_MASK)})
 /*
  * swp_entry_t must be independent of pte bits. We build a swp_entry_t from
  * swap type and offset we get from swap and convert that to pte to find a
-- 
cgit v1.2.3


From c61a8843124e353f4ba27c073133868da00e0335 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@ozlabs.org>
Date: Tue, 23 Feb 2016 13:36:17 +1100
Subject: powerpc/mm/book3s-64: Use physical addresses in upper page table tree
 levels

This changes the Linux page tables to store physical addresses
rather than kernel virtual addresses in the upper levels of the
tree (pgd, pud and pmd) for 64-bit Book 3S machines.

This also changes the hugepd pointers used to implement hugepages
when the base page size is 4k to store physical addresses rather than
virtual addresses (again just for 64-bit Book3S machines).

This frees up some high order bits, and will be needed with
PowerISA v3.0 machines which read the page table tree in hardware
in radix mode.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h |  2 +-
 arch/powerpc/include/asm/book3s/64/hash.h    | 13 +++++++------
 arch/powerpc/include/asm/hugetlb.h           |  2 +-
 arch/powerpc/include/asm/nohash/64/pgtable.h |  3 +++
 arch/powerpc/include/asm/page.h              |  7 +++++++
 arch/powerpc/include/asm/pgalloc-64.h        | 16 ++++++++--------
 6 files changed, 27 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index bee3643fa097..0425d3e1b7ae 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -64,7 +64,7 @@
 #define pgd_none(pgd)		(!pgd_val(pgd))
 #define pgd_bad(pgd)		(pgd_val(pgd) == 0)
 #define pgd_present(pgd)	(pgd_val(pgd) != 0)
-#define pgd_page_vaddr(pgd)	(pgd_val(pgd) & ~PGD_MASKED_BITS)
+#define pgd_page_vaddr(pgd)	__va(pgd_val(pgd) & ~PGD_MASKED_BITS)
 
 static inline void pgd_clear(pgd_t *pgdp)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 64eff409b027..5b8ba60032e2 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -222,13 +222,14 @@
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
 #ifndef __ASSEMBLY__
-#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
-				 || (pmd_val(pmd) & PMD_BAD_BITS))
-#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
+#define	pmd_bad(pmd)		(pmd_val(pmd) & PMD_BAD_BITS)
+#define pmd_page_vaddr(pmd)	__va(pmd_val(pmd) & ~PMD_MASKED_BITS)
 
-#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
-				 || (pud_val(pud) & PUD_BAD_BITS))
-#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
+#define	pud_bad(pud)		(pud_val(pud) & PUD_BAD_BITS)
+#define pud_page_vaddr(pud)	__va(pud_val(pud) & ~PUD_MASKED_BITS)
+
+/* Pointers in the page table tree are physical addresses */
+#define __pgtable_ptr_val(ptr)	__pa(ptr)
 
 #define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
 #define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 7eac89b9f02e..42814f0567cc 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -19,7 +19,7 @@ static inline pte_t *hugepd_page(hugepd_t hpd)
 	 * We have only four bits to encode, MMU page size
 	 */
 	BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
-	return (pte_t *)(hpd.pd & ~HUGEPD_SHIFT_MASK);
+	return __va(hpd.pd & HUGEPD_ADDR_MASK);
 }
 
 static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index b9f734dd5b81..10debb93c4a4 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -108,6 +108,9 @@
 #ifndef __ASSEMBLY__
 /* pte_clear moved to later in this file */
 
+/* Pointers in the page table tree are virtual addresses */
+#define __pgtable_ptr_val(ptr)	((unsigned long)(ptr))
+
 #define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index e34124f6fbf2..af7a3422a3ef 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -271,6 +271,13 @@ extern long long virt_phys_offset;
 #else
 #define PD_HUGE 0x80000000
 #endif
+
+#else	/* CONFIG_PPC_BOOK3S_64 */
+/*
+ * Book3S 64 stores real addresses in the hugepd entries to
+ * avoid overlaps with _PAGE_PRESENT and _PAGE_PTE.
+ */
+#define HUGEPD_ADDR_MASK	(0x0ffffffffffffffful & ~HUGEPD_SHIFT_MASK)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 /*
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 69ef28a81733..7ac59a32c66a 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -53,7 +53,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 #ifndef CONFIG_PPC_64K_PAGES
 
-#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, (unsigned long)PUD)
+#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, __pgtable_ptr_val(PUD))
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -68,19 +68,19 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pud_set(pud, (unsigned long)pmd);
+	pud_set(pud, __pgtable_ptr_val(pmd));
 }
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 				       pte_t *pte)
 {
-	pmd_set(pmd, (unsigned long)pte);
+	pmd_set(pmd, __pgtable_ptr_val(pte));
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_set(pmd, (unsigned long)page_address(pte_page));
+	pmd_set(pmd, __pgtable_ptr_val(page_address(pte_page)));
 }
 
 #define pmd_pgtable(pmd) pmd_page(pmd)
@@ -171,23 +171,23 @@ extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
 extern void __tlb_remove_table(void *_table);
 #endif
 
-#define pud_populate(mm, pud, pmd)	pud_set(pud, (unsigned long)pmd)
+#define pud_populate(mm, pud, pmd)	pud_set(pud, __pgtable_ptr_val(pmd))
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 				       pte_t *pte)
 {
-	pmd_set(pmd, (unsigned long)pte);
+	pmd_set(pmd, __pgtable_ptr_val(pte));
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_set(pmd, (unsigned long)pte_page);
+	pmd_set(pmd, __pgtable_ptr_val(pte_page));
 }
 
 static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
-	return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS);
+	return (pgtable_t)pmd_page_vaddr(pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-- 
cgit v1.2.3


From 849f86a630e9c84bf4c9d5dcbfe59dc94b2e15ce Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:15 +1100
Subject: powerpc/mm/book3s-64: Move _PAGE_PRESENT to the most significant bit

This changes _PAGE_PRESENT for 64-bit Book 3S processors from 0x2 to
0x8000_0000_0000_0000, because that is where PowerISA v3.0 CPUs in
radix mode will expect to find it.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-64k.h | 10 +++++-----
 arch/powerpc/include/asm/book3s/64/hash.h     |  5 +++--
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index a8c4c2a1940b..ed390e1915b7 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -210,30 +210,30 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp)
 /*
  * The linux hugepage PMD now include the pmd entries followed by the address
  * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
- * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
+ * [ 000 | 1 bit secondary | 3 bit hidx | 1 bit valid]. We use one byte per
  * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
  * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
  *
- * The last three bits are intentionally left to zero. This memory location
+ * The top three bits are intentionally left as zero. This memory location
  * are also used as normal page PTE pointers. So if we have any pointers
  * left around while we collapse a hugepage, we need to make sure
  * _PAGE_PRESENT bit of that is zero when we look at them
  */
 static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
 {
-	return (hpte_slot_array[index] >> 3) & 0x1;
+	return hpte_slot_array[index] & 0x1;
 }
 
 static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
 					   int index)
 {
-	return hpte_slot_array[index] >> 4;
+	return hpte_slot_array[index] >> 1;
 }
 
 static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
 					unsigned int index, unsigned int hidx)
 {
-	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
+	hpte_slot_array[index] = (hidx << 1) | 0x1;
 }
 
 /*
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 5b8ba60032e2..36ff107b9469 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -14,7 +14,6 @@
  * combinations that newer processors provide but we currently don't.
  */
 #define _PAGE_PTE		0x00001	/* distinguishes PTEs from pointers */
-#define _PAGE_PRESENT		0x00002 /* software: pte contains a translation */
 #define _PAGE_BIT_SWAP_TYPE	2
 #define _PAGE_USER		0x00004 /* page may be accessed by userspace */
 #define _PAGE_EXEC		0x00008 /* execute permission */
@@ -39,6 +38,8 @@
 #define _PAGE_SOFT_DIRTY	0x00000
 #endif
 
+#define _PAGE_PRESENT		(1ul << 63)	/* pte contains a translation */
+
 /*
  * We need to differentiate between explicit huge page and THP huge
  * page, since THP huge page also need to track real subpage details
@@ -402,7 +403,7 @@ static inline int pte_protnone(pte_t pte)
 
 static inline int pte_present(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_PRESENT;
+	return !!(pte_val(pte) & _PAGE_PRESENT);
 }
 
 /* Conversion functions: convert a page and protection to a page entry,
-- 
cgit v1.2.3


From 84c957560a7a8f548aaf6b6b2b15e6d03b7249e2 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:16 +1100
Subject: powerpc/mm/book3s-64: Move _PAGE_PTE to 2nd most significant bit

This changes _PAGE_PTE for 64-bit Book 3S processors from 0x1 to
0x4000_0000_0000_0000, because that bit is used as the L (leaf)
bit by PowerISA v3.0 CPUs in radix mode.  The "leaf" bit indicates
that the PTE points to a page directly rather than another radix
level, which is what the _PAGE_PTE bit means.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 36ff107b9469..14cfd49b2ab0 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -13,7 +13,6 @@
  * We could create separate kernel read-only if we used the 3 PP bits
  * combinations that newer processors provide but we currently don't.
  */
-#define _PAGE_PTE		0x00001	/* distinguishes PTEs from pointers */
 #define _PAGE_BIT_SWAP_TYPE	2
 #define _PAGE_USER		0x00004 /* page may be accessed by userspace */
 #define _PAGE_EXEC		0x00008 /* execute permission */
@@ -38,6 +37,7 @@
 #define _PAGE_SOFT_DIRTY	0x00000
 #endif
 
+#define _PAGE_PTE		(1ul << 62)	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		(1ul << 63)	/* pte contains a translation */
 
 /*
-- 
cgit v1.2.3


From a9d4996df1f49dc7b45e55060436cace87f1e0d4 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:17 +1100
Subject: powerpc/mm/book3s-64: Move HPTE-related bits in PTE to upper end

This moves the _PAGE_HASHPTE, _PAGE_F_GIX and _PAGE_F_SECOND fields in
the Linux PTE on 64-bit Book 3S systems to the most significant byte.
Of the 5 bits, one is a software-use bit and the other four are
reserved bit positions in the PowerISA v3.0 radix PTE format.
Using these bits is OK because these bits are all to do with tracking
the HPTE(s) associated with the Linux PTE, and therefore won't be
needed in radix mode.  This frees up bit positions in the lower two
bytes.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 14cfd49b2ab0..a59cfae7b9c2 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -24,11 +24,7 @@
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
 #define _PAGE_RW		0x00200 /* software: user write access allowed */
-#define _PAGE_HASHPTE		0x00400 /* software: pte has an associated HPTE */
 #define _PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
-#define _PAGE_F_GIX		0x07000 /* full page: hidx bits */
-#define _PAGE_F_GIX_SHIFT	12
-#define _PAGE_F_SECOND		0x08000 /* Whether to use secondary hash or not */
 #define _PAGE_SPECIAL		0x10000 /* software: special page */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
@@ -37,6 +33,10 @@
 #define _PAGE_SOFT_DIRTY	0x00000
 #endif
 
+#define _PAGE_F_GIX_SHIFT	57
+#define _PAGE_F_GIX		(7ul << 57)	/* HPTE index within HPTEG */
+#define _PAGE_F_SECOND		(1ul << 60)	/* HPTE is in 2ndary HPTEG */
+#define _PAGE_HASHPTE		(1ul << 61)	/* PTE has associated HPTE */
 #define _PAGE_PTE		(1ul << 62)	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		(1ul << 63)	/* pte contains a translation */
 
-- 
cgit v1.2.3


From c915df162d09f0957baf56fd3e2f03b8992699a6 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:18 +1100
Subject: powerpc/mm/book3s-64: Shuffle read, write, execute and user bits in
 PTE

This moves the _PAGE_EXEC, _PAGE_RW and _PAGE_USER bits around in
the Linux PTE on 64-bit Book 3S systems to correspond with the bit
positions used in radix mode by PowerISA v3.0 CPUs.  This also adds
a _PAGE_READ bit corresponding to the read permission bit in the
radix PTE.  _PAGE_READ is currently unused but could possibly be used
in future to improve pte_protnone().

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index a59cfae7b9c2..cd4bf957af5a 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -13,9 +13,12 @@
  * We could create separate kernel read-only if we used the 3 PP bits
  * combinations that newer processors provide but we currently don't.
  */
-#define _PAGE_BIT_SWAP_TYPE	2
-#define _PAGE_USER		0x00004 /* page may be accessed by userspace */
-#define _PAGE_EXEC		0x00008 /* execute permission */
+#define _PAGE_BIT_SWAP_TYPE	0
+
+#define _PAGE_EXEC		0x00001 /* execute permission */
+#define _PAGE_RW		0x00002 /* read & write access allowed */
+#define _PAGE_READ		0x00004	/* read access allowed */
+#define _PAGE_USER		0x00008 /* page may be accessed by userspace */
 #define _PAGE_GUARDED		0x00010 /* G: guarded (side-effect) page */
 /* M (memory coherence) is always set in the HPTE, so we don't need it here */
 #define _PAGE_COHERENT		0x0
@@ -23,7 +26,6 @@
 #define _PAGE_WRITETHRU		0x00040 /* W: cache write-through */
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
-#define _PAGE_RW		0x00200 /* software: user write access allowed */
 #define _PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
 #define _PAGE_SPECIAL		0x10000 /* software: special page */
 
-- 
cgit v1.2.3


From e726202f06cbfda4e42d2b32138cf288445ec80d Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:19 +1100
Subject: powerpc/mm/book3s-64: Move software-used bits in PTE

This moves the _PAGE_SPECIAL and _PAGE_SOFT_DIRTY bits in the Linux
PTE on 64-bit Book 3S systems to bit positions which are designated
for software use in the radix PTE format used by PowerISA v3.0 CPUs
in radix mode.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index cd4bf957af5a..ef9bd68f7e6d 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -26,13 +26,13 @@
 #define _PAGE_WRITETHRU		0x00040 /* W: cache write-through */
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
+#define _PAGE_SPECIAL		0x00400 /* software: special page */
 #define _PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
-#define _PAGE_SPECIAL		0x10000 /* software: special page */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY	0x20000 /* software: software dirty tracking */
+#define _PAGE_SOFT_DIRTY	0x200 /* software: software dirty tracking */
 #else
-#define _PAGE_SOFT_DIRTY	0x00000
+#define _PAGE_SOFT_DIRTY	0x000
 #endif
 
 #define _PAGE_F_GIX_SHIFT	57
-- 
cgit v1.2.3


From 8daf51f55febbc755fe20e74320a194e175811a9 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 22 Feb 2016 13:41:20 +1100
Subject: powerpc/mm/book3s-64: Expand the real page number field of the Linux
 PTE

Now that other PTE fields have been moved out of the way, we can
expand the RPN field of the PTE on 64-bit Book 3S systems and align
it with the RPN field in the radix PTE format used by PowerISA v3.0
CPUs in radix mode.  For 64k page size, this means we need to move
the _PAGE_COMBO and _PAGE_4K_PFN bits.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h  |  4 ++--
 arch/powerpc/include/asm/book3s/64/hash-64k.h | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 0425d3e1b7ae..7f60f7e814d4 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -52,8 +52,8 @@
 			 _PAGE_F_SECOND | _PAGE_F_GIX)
 
 /* shift to put page number into pte */
-#define PTE_RPN_SHIFT	(18)
-#define PTE_RPN_SIZE	(39)	/* gives 51-bit real addresses */
+#define PTE_RPN_SHIFT	(12)
+#define PTE_RPN_SIZE	(45)	/* gives 57-bit real addresses */
 
 #define _PAGE_4K_PFN		0
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index ed390e1915b7..8bb03251f34c 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -25,8 +25,8 @@
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-#define _PAGE_COMBO	0x00040000 /* this is a combo 4k page */
-#define _PAGE_4K_PFN	0x00080000 /* PFN is for a single 4k page */
+#define _PAGE_COMBO	0x00001000 /* this is a combo 4k page */
+#define _PAGE_4K_PFN	0x00002000 /* PFN is for a single 4k page */
 /*
  * Used to track subpage group valid if _PAGE_COMBO is set
  * This overloads _PAGE_F_GIX and _PAGE_F_SECOND
@@ -39,11 +39,11 @@
 
 /* Shift to put page number into pte.
  *
- * That gives us a max RPN of 37 bits, which means a max of 53 bits
- * of addressable physical space, or 49 bits for the special 4k PFNs.
+ * That gives us a max RPN of 41 bits, which means a max of 57 bits
+ * of addressable physical space, or 53 bits for the special 4k PFNs.
  */
-#define PTE_RPN_SHIFT	(20)
-#define PTE_RPN_SIZE	(37)
+#define PTE_RPN_SHIFT	(16)
+#define PTE_RPN_SIZE	(41)
 
 /*
  * we support 16 fragments per PTE page of 64K size.
-- 
cgit v1.2.3


From 446957ba5127141ee007fc61509e24a9e60853d9 Mon Sep 17 00:00:00 2001
From: Adam Buchbinder <adam.buchbinder@gmail.com>
Date: Wed, 24 Feb 2016 10:51:11 -0800
Subject: powerpc: Fix misspellings in comments.

Signed-off-by: Adam Buchbinder <adam.buchbinder@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/hydra.h             | 2 +-
 arch/powerpc/include/asm/io.h                | 2 +-
 arch/powerpc/include/asm/machdep.h           | 4 ++--
 arch/powerpc/include/asm/module.h            | 2 +-
 arch/powerpc/include/asm/pmac_feature.h      | 2 +-
 arch/powerpc/include/asm/reg.h               | 8 ++++----
 arch/powerpc/include/asm/reg_booke.h         | 2 +-
 arch/powerpc/include/asm/smu.h               | 2 +-
 arch/powerpc/include/asm/uninorth.h          | 2 +-
 arch/powerpc/include/asm/xics.h              | 2 +-
 arch/powerpc/include/uapi/asm/epapr_hcalls.h | 4 ++--
 11 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/hydra.h b/arch/powerpc/include/asm/hydra.h
index 1cb39c96d155..b3b0f2d020f0 100644
--- a/arch/powerpc/include/asm/hydra.h
+++ b/arch/powerpc/include/asm/hydra.h
@@ -89,7 +89,7 @@ extern volatile struct Hydra __iomem *Hydra;
 #define HYDRA_INT_EXT2		13	/* PCI IRQX */
 #define HYDRA_INT_EXT3		14	/* PCI IRQY */
 #define HYDRA_INT_EXT4		15	/* PCI IRQZ */
-#define HYDRA_INT_EXT5		16	/* IDE Primay/Secondary */
+#define HYDRA_INT_EXT5		16	/* IDE Primary/Secondary */
 #define HYDRA_INT_EXT6		17	/* IDE Secondary */
 #define HYDRA_INT_EXT7		18	/* Power Off Request */
 #define HYDRA_INT_SPARE		19
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 6c1297ec374c..2fd1690b79d2 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -300,7 +300,7 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  * When CONFIG_PPC_INDIRECT_MMIO is set, the platform can provide hooks
  * on all MMIOs. (Note that this is all 64 bits only for now)
  *
- * To help platforms who may need to differenciate MMIO addresses in
+ * To help platforms who may need to differentiate MMIO addresses in
  * their hooks, a bitfield is reserved for use by the platform near the
  * top of MMIO addresses (not PIO, those have to cope the hard way).
  *
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 3f191f573d4f..5c38e49ddd42 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -174,11 +174,11 @@ struct machdep_calls {
 	   platform, called once per cpu. */
 	void		(*enable_pmcs)(void);
 
-	/* Set DABR for this platform, leave empty for default implemenation */
+	/* Set DABR for this platform, leave empty for default implementation */
 	int		(*set_dabr)(unsigned long dabr,
 				    unsigned long dabrx);
 
-	/* Set DAWR for this platform, leave empty for default implemenation */
+	/* Set DAWR for this platform, leave empty for default implementation */
 	int		(*set_dawr)(unsigned long dawr,
 				    unsigned long dawrx);
 
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index dcfcad139bcc..5f1526fddccf 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -19,7 +19,7 @@
  * Thanks to Paul M for explaining this.
  *
  * PPC can only do rel jumps += 32MB, and often the kernel and other
- * modules are furthur away than this.  So, we jump to a table of
+ * modules are further away than this.  So, we jump to a table of
  * trampolines attached to the module (the Procedure Linkage Table)
  * whenever that happens.
  */
diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h
index 10902c9375d0..925697968946 100644
--- a/arch/powerpc/include/asm/pmac_feature.h
+++ b/arch/powerpc/include/asm/pmac_feature.h
@@ -46,7 +46,7 @@
 
 /* PowerSurge are the first generation of PCI Pmacs. This include
  * all of the Grand-Central based machines. We currently don't
- * differenciate most of them.
+ * differentiate most of them.
  */
 #define PMAC_TYPE_PSURGE		0x10	/* PowerSurge */
 #define PMAC_TYPE_ANS			0x11	/* Apple Network Server */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c4cb2ffc624e..11a81bd5dabd 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -376,7 +376,7 @@
 #define SPRN_TSCR	0x399	/* Thread Switch Control Register */
 
 #define SPRN_DEC	0x016		/* Decrement Register */
-#define SPRN_DER	0x095		/* Debug Enable Regsiter */
+#define SPRN_DER	0x095		/* Debug Enable Register */
 #define DER_RSTE	0x40000000	/* Reset Interrupt */
 #define DER_CHSTPE	0x20000000	/* Check Stop */
 #define DER_MCIE	0x10000000	/* Machine Check Interrupt */
@@ -401,7 +401,7 @@
 #define SPRN_DPDES	0x0B0		/* Directed Priv. Doorbell Exc. State */
 #define SPRN_EAR	0x11A		/* External Address Register */
 #define SPRN_HASH1	0x3D2		/* Primary Hash Address Register */
-#define SPRN_HASH2	0x3D3		/* Secondary Hash Address Resgister */
+#define SPRN_HASH2	0x3D3		/* Secondary Hash Address Register */
 #define SPRN_HID0	0x3F0		/* Hardware Implementation Register 0 */
 #define HID0_HDICE_SH	(63 - 23)	/* 970 HDEC interrupt enable */
 #define HID0_EMCP	(1<<31)		/* Enable Machine Check pin */
@@ -514,7 +514,7 @@
 #define ICTRL_EICP	0x00000100	/* enable icache par. check */
 #define SPRN_IMISS	0x3D4		/* Instruction TLB Miss Register */
 #define SPRN_IMMR	0x27E		/* Internal Memory Map Register */
-#define SPRN_L2CR	0x3F9		/* Level 2 Cache Control Regsiter */
+#define SPRN_L2CR	0x3F9		/* Level 2 Cache Control Register */
 #define SPRN_L2CR2	0x3f8
 #define L2CR_L2E		0x80000000	/* L2 enable */
 #define L2CR_L2PE		0x40000000	/* L2 parity enable */
@@ -549,7 +549,7 @@
 #define L2CR_L2DO_745x		0x00010000	/* L2 data only (745x) */
 #define L2CR_L2REP_745x		0x00001000	/* L2 repl. algorithm (745x) */
 #define L2CR_L2HWF_745x		0x00000800	/* L2 hardware flush (745x) */
-#define SPRN_L3CR		0x3FA	/* Level 3 Cache Control Regsiter */
+#define SPRN_L3CR		0x3FA	/* Level 3 Cache Control Register */
 #define L3CR_L3E		0x80000000	/* L3 enable */
 #define L3CR_L3PE		0x40000000	/* L3 data parity enable */
 #define L3CR_L3APE		0x20000000	/* L3 addr parity enable */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 2fef74b474f0..737e012ef56e 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -681,7 +681,7 @@
 #define SPRN_CDBCR	0x3D7	/* Cache Debug Control Register */
 #define SPRN_TBHI	0x3DC	/* Time Base High */
 #define SPRN_TBLO	0x3DD	/* Time Base Low */
-#define SPRN_DBCR	0x3F2	/* Debug Control Regsiter */
+#define SPRN_DBCR	0x3F2	/* Debug Control Register */
 #define SPRN_PBL1	0x3FC	/* Protection Bound Lower 1 */
 #define SPRN_PBL2	0x3FE	/* Protection Bound Lower 2 */
 #define SPRN_PBU1	0x3FD	/* Protection Bound Upper 1 */
diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h
index 37d2da6feabf..f280dd11243f 100644
--- a/arch/powerpc/include/asm/smu.h
+++ b/arch/powerpc/include/asm/smu.h
@@ -154,7 +154,7 @@
   *
   * The Darwin I2C driver is less subtle though. On any non-success status
   * from the response command, it waits 5ms and tries again up to 20 times,
-  * it doesn't differenciate between fatal errors or "busy" status.
+  * it doesn't differentiate between fatal errors or "busy" status.
   *
   * This driver provides an asynchronous paramblock based i2c command
   * interface to be used either directly by low level code or by a higher
diff --git a/arch/powerpc/include/asm/uninorth.h b/arch/powerpc/include/asm/uninorth.h
index d12b11d7641e..a1d112979fd2 100644
--- a/arch/powerpc/include/asm/uninorth.h
+++ b/arch/powerpc/include/asm/uninorth.h
@@ -132,7 +132,7 @@
 
 /* This one _might_ return the CPU number of the CPU reading it;
  * the bootROM decides whether to boot or to sleep/spinloop depending
- * on this register beeing 0 or not
+ * on this register being 0 or not
  */
 #define UNI_N_CPU_NUMBER		0x0050
 
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 0e25bdb190bb..5d61bbced6a1 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -1,5 +1,5 @@
 /*
- * Common definitions accross all variants of ICP and ICS interrupt
+ * Common definitions across all variants of ICP and ICS interrupt
  * controllers.
  */
 
diff --git a/arch/powerpc/include/uapi/asm/epapr_hcalls.h b/arch/powerpc/include/uapi/asm/epapr_hcalls.h
index 7f9c74b46704..b4504f394427 100644
--- a/arch/powerpc/include/uapi/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/uapi/asm/epapr_hcalls.h
@@ -78,7 +78,7 @@
 #define EV_SUCCESS		0
 #define EV_EPERM		1	/* Operation not permitted */
 #define EV_ENOENT		2	/*  Entry Not Found */
-#define EV_EIO			3	/* I/O error occured */
+#define EV_EIO			3	/* I/O error occurred */
 #define EV_EAGAIN		4	/* The operation had insufficient
 					 * resources to complete and should be
 					 * retried
@@ -89,7 +89,7 @@
 #define EV_ENODEV		7	/* No such device */
 #define EV_EINVAL		8	/* An argument supplied to the hcall
 					   was out of range or invalid */
-#define EV_INTERNAL		9	/* An internal error occured */
+#define EV_INTERNAL		9	/* An internal error occurred */
 #define EV_CONFIG		10	/* A configuration error was detected */
 #define EV_INVALID_STATE	11	/* The object is in an invalid state */
 #define EV_UNIMPLEMENTED	12	/* Unimplemented hypercall */
-- 
cgit v1.2.3


From 27828f98a0522ad4a745a80407d051e5874c8d93 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Tue, 9 Feb 2016 13:32:41 +1000
Subject: powerpc/mm: Handle removing maybe-present bolted HPTEs

At the moment the hpte_removebolted callback in ppc_md returns void and
will BUG_ON() if the hpte it's asked to remove doesn't exist in the first
place.  This is awkward for the case of cleaning up a mapping which was
partially made before failing.

So, we add a return value to hpte_removebolted, and have it return ENOENT
in the case that the HPTE to remove didn't exist in the first place.

In the (sole) caller, we propagate errors in hpte_removebolted to its
caller to handle.  However, we handle ENOENT specially, continuing to
complete the unmapping over the specified range before returning the error
to the caller.

This means that htab_remove_mapping() will work sanely on a partially
present mapping, removing any HPTEs which are present, while also returning
ENOENT to its caller in case it's important there.

There are two callers of htab_remove_mapping():
   - In remove_section_mapping() we already WARN_ON() any error return,
     which is reasonable - in this case the mapping should be fully
     present
   - In vmemmap_remove_mapping() we BUG_ON() any error.  We change that to
     just a WARN_ON() in the case of ENOENT, since failing to remove a
     mapping that wasn't there in the first place probably shouldn't be
     fatal.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/machdep.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 5c38e49ddd42..fd22442d30a9 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -54,7 +54,7 @@ struct machdep_calls {
 				       int psize, int apsize,
 				       int ssize);
 	long		(*hpte_remove)(unsigned long hpte_group);
-	void            (*hpte_removebolted)(unsigned long ea,
+	int             (*hpte_removebolted)(unsigned long ea,
 					     int psize, int ssize);
 	void		(*flush_hash_range)(unsigned long number, int local);
 	void		(*hugepage_invalidate)(unsigned long vsid,
-- 
cgit v1.2.3


From 5c3c7ede2bdcb85fa2fd51c8147cdf70ebc17fcb Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Tue, 9 Feb 2016 13:32:43 +1000
Subject: powerpc/mm: Split hash page table sizing heuristic into a helper

htab_get_table_size() either retrieve the size of the hash page table (HPT)
from the device tree - if the HPT size is determined by firmware - or
uses a heuristic to determine a good size based on RAM size if the kernel
is responsible for allocating the HPT.

To support a PAPR extension allowing resizing of the HPT, we're going to
want the memory size -> HPT size logic elsewhere, so split it out into a
helper function.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/mmu-hash64.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index e36dc90c80d0..0cea4807e26f 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -608,6 +608,9 @@ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
 	context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
 	return get_vsid(context, ea, ssize);
 }
+
+unsigned htab_shift_for_mem_size(unsigned long mem_size);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_HASH64_H_ */
-- 
cgit v1.2.3


From 70fe3d980f5f14d8125869125ba9a0ea95e09c6b Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Mon, 29 Feb 2016 17:53:47 +1100
Subject: powerpc: Restore FPU/VEC/VSX if previously used

Currently the FPU, VEC and VSX facilities are lazily loaded. This is not
a problem unless a process is using these facilities.

Modern versions of GCC are very good at automatically vectorising code,
new and modernised workloads make use of floating point and vector
facilities, even the kernel makes use of vectorised memcpy.

All this combined greatly increases the cost of a syscall since the
kernel uses the facilities sometimes even in syscall fast-path making it
increasingly common for a thread to take an *_unavailable exception soon
after a syscall, not to mention potentially taking all three.

The obvious overcompensation to this problem is to simply always load
all the facilities on every exit to userspace. Loading up all FPU, VEC
and VSX registers every time can be expensive and if a workload does
avoid using them, it should not be forced to incur this penalty.

An 8bit counter is used to detect if the registers have been used in the
past and the registers are always loaded until the value wraps to back
to zero.

Several versions of the assembly in entry_64.S were tested:

  1. Always calling C.
  2. Performing a common case check and then calling C.
  3. A complex check in asm.

After some benchmarking it was determined that avoiding C in the common
case is a performance benefit (option 2). The full check in asm (option
3) greatly complicated that codepath for a negligible performance gain
and the trade-off was deemed not worth it.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
[mpe: Move load_vec in the struct to fill an existing hole, reword change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

fixup
---
 arch/powerpc/include/asm/processor.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index ac2330820b9a..8ab8a1a9610a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -236,7 +236,9 @@ struct thread_struct {
 #endif
 	struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
 	unsigned long	trap_nr;	/* last trap # on this thread */
+	u8 load_fp;
 #ifdef CONFIG_ALTIVEC
+	u8 load_vec;
 	struct thread_vr_state vr_state;
 	struct thread_vr_state *vr_save_area;
 	unsigned long	vrsave;
-- 
cgit v1.2.3


From de2a20aa7237b45d3c14a2505804a8daa95a8f53 Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Mon, 29 Feb 2016 17:53:48 +1100
Subject: powerpc: Prepare for splitting giveup_{fpu, altivec, vsx} in two

This prepares for the decoupling of saving {fpu,altivec,vsx} registers and
marking {fpu,altivec,vsx} as being unused by a thread.

Currently giveup_{fpu,altivec,vsx}() does both however optimisations to
task switching can be made if these two operations are decoupled.
save_all() will permit the saving of registers to thread structs and leave
threads MSR with bits enabled.

This patch introduces no functional change.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/reg.h       | 8 ++++++++
 arch/powerpc/include/asm/switch_to.h | 7 +++++++
 2 files changed, 15 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 11a81bd5dabd..52ed654d01ba 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -75,6 +75,14 @@
 #define MSR_HV		0
 #endif
 
+/*
+ * To be used in shared book E/book S, this avoids needing to worry about
+ * book S/book E in shared code
+ */
+#ifndef MSR_SPE
+#define MSR_SPE 	0
+#endif
+
 #define MSR_VEC		__MASK(MSR_VEC_LG)	/* Enable AltiVec */
 #define MSR_VSX		__MASK(MSR_VSX_LG)	/* Enable VSX */
 #define MSR_POW		__MASK(MSR_POW_LG)	/* Enable Power Management */
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 5b268b6be74c..3690041c126a 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -34,6 +34,7 @@ static inline void disable_kernel_fp(void)
 	msr_check_and_clear(MSR_FP);
 }
 #else
+static inline void __giveup_fpu(struct task_struct *t) { }
 static inline void flush_fp_to_thread(struct task_struct *t) { }
 #endif
 
@@ -46,6 +47,8 @@ static inline void disable_kernel_altivec(void)
 {
 	msr_check_and_clear(MSR_VEC);
 }
+#else
+static inline void __giveup_altivec(struct task_struct *t) { }
 #endif
 
 #ifdef CONFIG_VSX
@@ -57,6 +60,8 @@ static inline void disable_kernel_vsx(void)
 {
 	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
+#else
+static inline void __giveup_vsx(struct task_struct *t) { }
 #endif
 
 #ifdef CONFIG_SPE
@@ -68,6 +73,8 @@ static inline void disable_kernel_spe(void)
 {
 	msr_check_and_clear(MSR_SPE);
 }
+#else
+static inline void __giveup_spe(struct task_struct *t) { }
 #endif
 
 static inline void clear_task_ebb(struct task_struct *t)
-- 
cgit v1.2.3


From 8792468da5e12e77e76e1edf081acf0392abb331 Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Mon, 29 Feb 2016 17:53:49 +1100
Subject: powerpc: Add the ability to save FPU without giving it up

This patch adds the ability to be able to save the FPU registers to the
thread struct without giving up (disabling the facility) next time the
process returns to userspace.

This patch optimises the thread copy path (as a result of a fork() or
clone()) so that the parent thread can return to userspace with hot
registers avoiding a possibly pointless reload of FPU register state.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/switch_to.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 3690041c126a..6a201e8dc947 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -28,13 +28,14 @@ extern void giveup_all(struct task_struct *);
 extern void enable_kernel_fp(void);
 extern void flush_fp_to_thread(struct task_struct *);
 extern void giveup_fpu(struct task_struct *);
-extern void __giveup_fpu(struct task_struct *);
+extern void save_fpu(struct task_struct *);
 static inline void disable_kernel_fp(void)
 {
 	msr_check_and_clear(MSR_FP);
 }
 #else
 static inline void __giveup_fpu(struct task_struct *t) { }
+static inline void save_fpu(struct task_struct *t) { }
 static inline void flush_fp_to_thread(struct task_struct *t) { }
 #endif
 
-- 
cgit v1.2.3


From 6f515d842e8e1b205e54f44b9013bf14870b97a7 Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Mon, 29 Feb 2016 17:53:50 +1100
Subject: powerpc: Add the ability to save Altivec without giving it up

This patch adds the ability to be able to save the VEC registers to the
thread struct without giving up (disabling the facility) next time the
process returns to userspace.

This patch builds on a previous optimisation for the FPU registers in the
thread copy path to avoid a possibly pointless reload of VEC state.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/switch_to.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 6a201e8dc947..9028822bb73f 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -43,12 +43,13 @@ static inline void flush_fp_to_thread(struct task_struct *t) { }
 extern void enable_kernel_altivec(void);
 extern void flush_altivec_to_thread(struct task_struct *);
 extern void giveup_altivec(struct task_struct *);
-extern void __giveup_altivec(struct task_struct *);
+extern void save_altivec(struct task_struct *);
 static inline void disable_kernel_altivec(void)
 {
 	msr_check_and_clear(MSR_VEC);
 }
 #else
+static inline void save_altivec(struct task_struct *t) { }
 static inline void __giveup_altivec(struct task_struct *t) { }
 #endif
 
-- 
cgit v1.2.3


From bf6a4d5b75d1ea87897fe68d0e45d35a2996c678 Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Mon, 29 Feb 2016 17:53:51 +1100
Subject: powerpc: Add the ability to save VSX without giving it up

This patch adds the ability to be able to save the VSX registers to the
thread struct without giving up (disabling the facility) next time the
process returns to userspace.

This patch builds on a previous optimisation for the FPU and VEC registers
in the thread copy path to avoid a possibly pointless reload of VSX state.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/switch_to.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 9028822bb73f..17c8380673a6 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -56,14 +56,10 @@ static inline void __giveup_altivec(struct task_struct *t) { }
 #ifdef CONFIG_VSX
 extern void enable_kernel_vsx(void);
 extern void flush_vsx_to_thread(struct task_struct *);
-extern void giveup_vsx(struct task_struct *);
-extern void __giveup_vsx(struct task_struct *);
 static inline void disable_kernel_vsx(void)
 {
 	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
-#else
-static inline void __giveup_vsx(struct task_struct *t) { }
 #endif
 
 #ifdef CONFIG_SPE
-- 
cgit v1.2.3


From 2bf59916ef033edb9f8e968ee27e486ccb8ba1ce Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 1 Mar 2016 09:45:11 +0530
Subject: powerpc/mm: Split pgtable types to separate header

We move the page table accessors into a separate header. We will
later add a big endian variant of the table which is needed for radix.
No functionality change only code movement.

Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/page.h          | 104 +----------------------------
 arch/powerpc/include/asm/pgtable-types.h | 108 +++++++++++++++++++++++++++++++
 2 files changed, 109 insertions(+), 103 deletions(-)
 create mode 100644 arch/powerpc/include/asm/pgtable-types.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index af7a3422a3ef..ab3d8977bacd 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -288,109 +288,7 @@ extern long long virt_phys_offset;
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_STRICT_MM_TYPECHECKS
-/* These are used to make use of C type-checking. */
-
-/* PTE level */
-typedef struct { pte_basic_t pte; } pte_t;
-#define __pte(x)	((pte_t) { (x) })
-static inline pte_basic_t pte_val(pte_t x)
-{
-	return x.pte;
-}
-
-/* 64k pages additionally define a bigger "real PTE" type that gathers
- * the "second half" part of the PTE for pseudo 64k pages
- */
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
-typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
-#else
-typedef struct { pte_t pte; } real_pte_t;
-#endif
-
-/* PMD level */
-#ifdef CONFIG_PPC64
-typedef struct { unsigned long pmd; } pmd_t;
-#define __pmd(x)	((pmd_t) { (x) })
-static inline unsigned long pmd_val(pmd_t x)
-{
-	return x.pmd;
-}
-
-/* PUD level exusts only on 4k pages */
-#ifndef CONFIG_PPC_64K_PAGES
-typedef struct { unsigned long pud; } pud_t;
-#define __pud(x)	((pud_t) { (x) })
-static inline unsigned long pud_val(pud_t x)
-{
-	return x.pud;
-}
-#endif /* !CONFIG_PPC_64K_PAGES */
-#endif /* CONFIG_PPC64 */
-
-/* PGD level */
-typedef struct { unsigned long pgd; } pgd_t;
-#define __pgd(x)	((pgd_t) { (x) })
-static inline unsigned long pgd_val(pgd_t x)
-{
-	return x.pgd;
-}
-
-/* Page protection bits */
-typedef struct { unsigned long pgprot; } pgprot_t;
-#define pgprot_val(x)	((x).pgprot)
-#define __pgprot(x)	((pgprot_t) { (x) })
-
-#else
-
-/*
- * .. while these make it easier on the compiler
- */
-
-typedef pte_basic_t pte_t;
-#define __pte(x)	(x)
-static inline pte_basic_t pte_val(pte_t pte)
-{
-	return pte;
-}
-
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
-typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
-#else
-typedef pte_t real_pte_t;
-#endif
-
-
-#ifdef CONFIG_PPC64
-typedef unsigned long pmd_t;
-#define __pmd(x)	(x)
-static inline unsigned long pmd_val(pmd_t pmd)
-{
-	return pmd;
-}
-
-#ifndef CONFIG_PPC_64K_PAGES
-typedef unsigned long pud_t;
-#define __pud(x)	(x)
-static inline unsigned long pud_val(pud_t pud)
-{
-	return pud;
-}
-#endif /* !CONFIG_PPC_64K_PAGES */
-#endif /* CONFIG_PPC64 */
-
-typedef unsigned long pgd_t;
-#define __pgd(x)	(x)
-static inline unsigned long pgd_val(pgd_t pgd)
-{
-	return pgd;
-}
-
-typedef unsigned long pgprot_t;
-#define pgprot_val(x)	(x)
-#define __pgprot(x)	(x)
-
-#endif
+#include <asm/pgtable-types.h>
 
 typedef struct { signed long pd; } hugepd_t;
 
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
new file mode 100644
index 000000000000..2fac0c4acfa4
--- /dev/null
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -0,0 +1,108 @@
+#ifndef _ASM_POWERPC_PGTABLE_TYPES_H
+#define _ASM_POWERPC_PGTABLE_TYPES_H
+
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
+/* These are used to make use of C type-checking. */
+
+/* PTE level */
+typedef struct { pte_basic_t pte; } pte_t;
+#define __pte(x)	((pte_t) { (x) })
+static inline pte_basic_t pte_val(pte_t x)
+{
+	return x.pte;
+}
+
+/* 64k pages additionally define a bigger "real PTE" type that gathers
+ * the "second half" part of the PTE for pseudo 64k pages
+ */
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
+typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
+#else
+typedef struct { pte_t pte; } real_pte_t;
+#endif
+
+/* PMD level */
+#ifdef CONFIG_PPC64
+typedef struct { unsigned long pmd; } pmd_t;
+#define __pmd(x)	((pmd_t) { (x) })
+static inline unsigned long pmd_val(pmd_t x)
+{
+	return x.pmd;
+}
+
+/* PUD level exusts only on 4k pages */
+#ifndef CONFIG_PPC_64K_PAGES
+typedef struct { unsigned long pud; } pud_t;
+#define __pud(x)	((pud_t) { (x) })
+static inline unsigned long pud_val(pud_t x)
+{
+	return x.pud;
+}
+#endif /* !CONFIG_PPC_64K_PAGES */
+#endif /* CONFIG_PPC64 */
+
+/* PGD level */
+typedef struct { unsigned long pgd; } pgd_t;
+#define __pgd(x)	((pgd_t) { (x) })
+static inline unsigned long pgd_val(pgd_t x)
+{
+	return x.pgd;
+}
+
+/* Page protection bits */
+typedef struct { unsigned long pgprot; } pgprot_t;
+#define pgprot_val(x)	((x).pgprot)
+#define __pgprot(x)	((pgprot_t) { (x) })
+
+#else
+
+/*
+ * .. while these make it easier on the compiler
+ */
+
+typedef pte_basic_t pte_t;
+#define __pte(x)	(x)
+static inline pte_basic_t pte_val(pte_t pte)
+{
+	return pte;
+}
+
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
+typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
+#else
+typedef pte_t real_pte_t;
+#endif
+
+
+#ifdef CONFIG_PPC64
+typedef unsigned long pmd_t;
+#define __pmd(x)	(x)
+static inline unsigned long pmd_val(pmd_t pmd)
+{
+	return pmd;
+}
+
+#ifndef CONFIG_PPC_64K_PAGES
+typedef unsigned long pud_t;
+#define __pud(x)	(x)
+static inline unsigned long pud_val(pud_t pud)
+{
+	return pud;
+}
+#endif /* !CONFIG_PPC_64K_PAGES */
+#endif /* CONFIG_PPC64 */
+
+typedef unsigned long pgd_t;
+#define __pgd(x)	(x)
+static inline unsigned long pgd_val(pgd_t pgd)
+{
+	return pgd;
+}
+
+typedef unsigned long pgprot_t;
+#define pgprot_val(x)	(x)
+#define __pgprot(x)	(x)
+
+#endif
+
+#endif /* _ASM_POWERPC_PGTABLE_TYPES_H */
-- 
cgit v1.2.3


From ae9a71afa4d7cf29a816fbc387bfd59ad7c292b6 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 1 Mar 2016 09:45:12 +0530
Subject: powerpc/mm: Don't have conditional defines for real_pte_t

We remove real_pte_t out of STRICT_MM_TYPESCHECK.

Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h |  5 -----
 arch/powerpc/include/asm/pgtable-types.h     | 26 +++++++++-----------------
 2 files changed, 9 insertions(+), 22 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index c8240b737d11..7482f69117b6 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -43,13 +43,8 @@
  */
 #ifndef __real_pte
 
-#ifdef CONFIG_STRICT_MM_TYPECHECKS
 #define __real_pte(e,p)		((real_pte_t){(e)})
 #define __rpte_to_pte(r)	((r).pte)
-#else
-#define __real_pte(e,p)		(e)
-#define __rpte_to_pte(r)	(__pte(r))
-#endif
 #define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >>_PAGE_F_GIX_SHIFT)
 
 #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index 2fac0c4acfa4..71487e1ca638 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -12,15 +12,6 @@ static inline pte_basic_t pte_val(pte_t x)
 	return x.pte;
 }
 
-/* 64k pages additionally define a bigger "real PTE" type that gathers
- * the "second half" part of the PTE for pseudo 64k pages
- */
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
-typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
-#else
-typedef struct { pte_t pte; } real_pte_t;
-#endif
-
 /* PMD level */
 #ifdef CONFIG_PPC64
 typedef struct { unsigned long pmd; } pmd_t;
@@ -67,13 +58,6 @@ static inline pte_basic_t pte_val(pte_t pte)
 	return pte;
 }
 
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
-typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
-#else
-typedef pte_t real_pte_t;
-#endif
-
-
 #ifdef CONFIG_PPC64
 typedef unsigned long pmd_t;
 #define __pmd(x)	(x)
@@ -103,6 +87,14 @@ typedef unsigned long pgprot_t;
 #define pgprot_val(x)	(x)
 #define __pgprot(x)	(x)
 
+#endif /* CONFIG_STRICT_MM_TYPECHECKS */
+/*
+ * With hash config 64k pages additionally define a bigger "real PTE" type that
+ * gathers the "second half" part of the PTE for pseudo 64k pages
+ */
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64)
+typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
+#else
+typedef struct { pte_t pte; } real_pte_t;
 #endif
-
 #endif /* _ASM_POWERPC_PGTABLE_TYPES_H */
-- 
cgit v1.2.3


From 368ced78e6ed3d72c2acc61233b58487071ec289 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 1 Mar 2016 09:45:13 +0530
Subject: powerpc/mm: Switch book3s 64 with 64K page size to 4 level page table

This is needed so that we can support both hash and radix page table
using single kernel. Radix kernel uses a 4 level table.

We now use physical address in upper page table tree levels. Even though
they are aligned to their size, for the masked bits we use the
bit positions as per PowerISA 3.0.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h  | 33 +--------------------------
 arch/powerpc/include/asm/book3s/64/hash-64k.h | 33 ++++++++++++++-------------
 arch/powerpc/include/asm/book3s/64/hash.h     | 11 +++++++++
 arch/powerpc/include/asm/book3s/64/pgtable.h  | 25 +++++++++++++++++++-
 arch/powerpc/include/asm/pgalloc-64.h         | 28 ++++++++++++++++++++---
 arch/powerpc/include/asm/pgtable-types.h      | 13 +++++++----
 6 files changed, 86 insertions(+), 57 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 7f60f7e814d4..5f08a0832238 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -58,39 +58,8 @@
 #define _PAGE_4K_PFN		0
 #ifndef __ASSEMBLY__
 /*
- * 4-level page tables related bits
+ * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range()
  */
-
-#define pgd_none(pgd)		(!pgd_val(pgd))
-#define pgd_bad(pgd)		(pgd_val(pgd) == 0)
-#define pgd_present(pgd)	(pgd_val(pgd) != 0)
-#define pgd_page_vaddr(pgd)	__va(pgd_val(pgd) & ~PGD_MASKED_BITS)
-
-static inline void pgd_clear(pgd_t *pgdp)
-{
-	*pgdp = __pgd(0);
-}
-
-static inline pte_t pgd_pte(pgd_t pgd)
-{
-	return __pte(pgd_val(pgd));
-}
-
-static inline pgd_t pte_pgd(pte_t pte)
-{
-	return __pgd(pte_val(pte));
-}
-extern struct page *pgd_page(pgd_t pgd);
-
-#define pud_offset(pgdp, addr)	\
-  (((pud_t *) pgd_page_vaddr(*(pgdp))) + \
-    (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
-
-#define pud_ERROR(e) \
-	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
-
-/*
- * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */
 #define remap_4k_pfn(vma, addr, pfn, prot)	\
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
 
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 8bb03251f34c..0a7956a80a08 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -1,15 +1,14 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H
 #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H
 
-#include <asm-generic/pgtable-nopud.h>
-
 #define PTE_INDEX_SIZE  8
-#define PMD_INDEX_SIZE  10
-#define PUD_INDEX_SIZE	0
+#define PMD_INDEX_SIZE  5
+#define PUD_INDEX_SIZE	5
 #define PGD_INDEX_SIZE  12
 
 #define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PUD	(1 << PUD_INDEX_SIZE)
 #define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
 
 /* With 4k base page size, hugepage PTEs go at the PMD level */
@@ -20,8 +19,13 @@
 #define PMD_SIZE	(1UL << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))
 
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define PGDIR_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
+/* PUD_SHIFT determines what a third-level page table entry can map */
+#define PUD_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
+#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT	(PUD_SHIFT + PUD_INDEX_SIZE)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
@@ -56,13 +60,12 @@
 #define PTE_FRAG_SIZE_SHIFT  12
 #define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
 
-/*
- * Bits to mask out from a PMD to get to the PTE page
- * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned.
- */
-#define PMD_MASKED_BITS		(PTE_FRAG_SIZE - 1)
-/* Bits to mask out from a PGD/PUD to get to the PMD page */
-#define PUD_MASKED_BITS		0x1ff
+/* Bits to mask out from a PMD to get to the PTE page */
+#define PMD_MASKED_BITS		0xc0000000000000ffUL
+/* Bits to mask out from a PUD to get to the PMD page */
+#define PUD_MASKED_BITS		0xc0000000000000ffUL
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0xc0000000000000ffUL
 
 #ifndef __ASSEMBLY__
 
@@ -132,11 +135,9 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
 #else
 #define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
 #endif
+#define PUD_TABLE_SIZE	(sizeof(pud_t) << PUD_INDEX_SIZE)
 #define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
 
-#define pgd_pte(pgd)	(pud_pte(((pud_t){ pgd })))
-#define pte_pgd(pte)	((pgd_t)pte_pud(pte))
-
 #ifdef CONFIG_HUGETLB_PAGE
 /*
  * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index ef9bd68f7e6d..d0ee6fcef823 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -235,6 +235,7 @@
 #define __pgtable_ptr_val(ptr)	__pa(ptr)
 
 #define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
+#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1))
 #define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
 #define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1))
 
@@ -363,8 +364,18 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 	:"cc");
 }
 
+static inline int pgd_bad(pgd_t pgd)
+{
+	return (pgd_val(pgd) == 0);
+}
+
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
+static inline unsigned long pgd_page_vaddr(pgd_t pgd)
+{
+	return (unsigned long)__va(pgd_val(pgd) & ~PGD_MASKED_BITS);
+}
+
 
 /* Generic accessors to PTE bits */
 static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 7482f69117b6..77d3ce05798e 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -106,6 +106,26 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
 	*pgdp = __pgd(val);
 }
 
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	*pgdp = __pgd(0);
+}
+
+#define pgd_none(pgd)		(!pgd_val(pgd))
+#define pgd_present(pgd)	(!pgd_none(pgd))
+
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+	return __pte(pgd_val(pgd));
+}
+
+static inline pgd_t pte_pgd(pte_t pte)
+{
+	return __pgd(pte_val(pte));
+}
+
+extern struct page *pgd_page(pgd_t pgd);
+
 /*
  * Find an entry in a page-table-directory.  We combine the address region
  * (the high order N bits) and the pgd portion of the address.
@@ -113,9 +133,10 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
 
 #define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
 
+#define pud_offset(pgdp, addr)	\
+	(((pud_t *) pgd_page_vaddr(*(pgdp))) + pud_index(addr))
 #define pmd_offset(pudp,addr) \
 	(((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr))
-
 #define pte_offset_kernel(dir,addr) \
 	(((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr))
 
@@ -130,6 +151,8 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
 	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pud_ERROR(e) \
+	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 7ac59a32c66a..8d5fc3ac43da 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -171,7 +171,29 @@ extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
 extern void __tlb_remove_table(void *_table);
 #endif
 
-#define pud_populate(mm, pud, pmd)	pud_set(pud, __pgtable_ptr_val(pmd))
+#ifndef __PAGETABLE_PUD_FOLDED
+/* book3s 64 is 4 level page table */
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+{
+	pgd_set(pgd, __pgtable_ptr_val(pud));
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
+}
+#endif
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	pud_set(pud, __pgtable_ptr_val(pmd));
+}
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 				       pte_t *pte)
@@ -233,11 +255,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
-#ifndef CONFIG_PPC_64K_PAGES
+#ifndef __PAGETABLE_PUD_FOLDED
 #define __pud_free_tlb(tlb, pud, addr)		      \
 	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
 
-#endif /* CONFIG_PPC_64K_PAGES */
+#endif /* __PAGETABLE_PUD_FOLDED */
 
 #define check_pgt_cache()	do { } while (0)
 
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index 71487e1ca638..43140f8b0592 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -21,15 +21,18 @@ static inline unsigned long pmd_val(pmd_t x)
 	return x.pmd;
 }
 
-/* PUD level exusts only on 4k pages */
-#ifndef CONFIG_PPC_64K_PAGES
+/*
+ * 64 bit hash always use 4 level table. Everybody else use 4 level
+ * only for 4K page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) || !defined(CONFIG_PPC_64K_PAGES)
 typedef struct { unsigned long pud; } pud_t;
 #define __pud(x)	((pud_t) { (x) })
 static inline unsigned long pud_val(pud_t x)
 {
 	return x.pud;
 }
-#endif /* !CONFIG_PPC_64K_PAGES */
+#endif /* CONFIG_PPC_BOOK3S_64 || !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
@@ -66,14 +69,14 @@ static inline unsigned long pmd_val(pmd_t pmd)
 	return pmd;
 }
 
-#ifndef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_BOOK3S_64) || !defined(CONFIG_PPC_64K_PAGES)
 typedef unsigned long pud_t;
 #define __pud(x)	(x)
 static inline unsigned long pud_val(pud_t pud)
 {
 	return pud;
 }
-#endif /* !CONFIG_PPC_64K_PAGES */
+#endif /* CONFIG_PPC_BOOK3S_64 || !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 typedef unsigned long pgd_t;
-- 
cgit v1.2.3


From f64e8084c94bb0449177364856d8117e2f14c4c0 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 1 Mar 2016 12:59:20 +0530
Subject: powerpc/mm: Move hash related mmu-*.h headers to book3s/

No code changes.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/32/mmu-hash.h |  93 ++++
 arch/powerpc/include/asm/book3s/64/mmu-hash.h | 616 ++++++++++++++++++++++++++
 arch/powerpc/include/asm/mmu-hash32.h         |  93 ----
 arch/powerpc/include/asm/mmu-hash64.h         | 616 --------------------------
 arch/powerpc/include/asm/mmu.h                |   4 +-
 5 files changed, 711 insertions(+), 711 deletions(-)
 create mode 100644 arch/powerpc/include/asm/book3s/32/mmu-hash.h
 create mode 100644 arch/powerpc/include/asm/book3s/64/mmu-hash.h
 delete mode 100644 arch/powerpc/include/asm/mmu-hash32.h
 delete mode 100644 arch/powerpc/include/asm/mmu-hash64.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
new file mode 100644
index 000000000000..16f513e5cbd7
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
@@ -0,0 +1,93 @@
+#ifndef _ASM_POWERPC_MMU_HASH32_H_
+#define _ASM_POWERPC_MMU_HASH32_H_
+/*
+ * 32-bit hash table MMU support
+ */
+
+/*
+ * BATs
+ */
+
+/* Block size masks */
+#define BL_128K	0x000
+#define BL_256K 0x001
+#define BL_512K 0x003
+#define BL_1M   0x007
+#define BL_2M   0x00F
+#define BL_4M   0x01F
+#define BL_8M   0x03F
+#define BL_16M  0x07F
+#define BL_32M  0x0FF
+#define BL_64M  0x1FF
+#define BL_128M 0x3FF
+#define BL_256M 0x7FF
+
+/* BAT Access Protection */
+#define BPP_XX	0x00		/* No access */
+#define BPP_RX	0x01		/* Read only */
+#define BPP_RW	0x02		/* Read/write */
+
+#ifndef __ASSEMBLY__
+/* Contort a phys_addr_t into the right format/bits for a BAT */
+#ifdef CONFIG_PHYS_64BIT
+#define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \
+				((x & 0x0000000e00000000ULL) >> 24) | \
+				((x & 0x0000000100000000ULL) >> 30)))
+#else
+#define BAT_PHYS_ADDR(x) (x)
+#endif
+
+struct ppc_bat {
+	u32 batu;
+	u32 batl;
+};
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * Hash table
+ */
+
+/* Values for PP (assumes Ks=0, Kp=1) */
+#define PP_RWXX	0	/* Supervisor read/write, User none */
+#define PP_RWRX 1	/* Supervisor read/write, User read */
+#define PP_RWRW 2	/* Supervisor read/write, User read/write */
+#define PP_RXRX 3	/* Supervisor read,       User read */
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Hardware Page Table Entry
+ * Note that the xpn and x bitfields are used only by processors that
+ * support extended addressing; otherwise, those bits are reserved.
+ */
+struct hash_pte {
+	unsigned long v:1;	/* Entry is valid */
+	unsigned long vsid:24;	/* Virtual segment identifier */
+	unsigned long h:1;	/* Hash algorithm indicator */
+	unsigned long api:6;	/* Abbreviated page index */
+	unsigned long rpn:20;	/* Real (physical) page number */
+	unsigned long xpn:3;	/* Real page number bits 0-2, optional */
+	unsigned long r:1;	/* Referenced */
+	unsigned long c:1;	/* Changed */
+	unsigned long w:1;	/* Write-thru cache mode */
+	unsigned long i:1;	/* Cache inhibited */
+	unsigned long m:1;	/* Memory coherence */
+	unsigned long g:1;	/* Guarded */
+	unsigned long x:1;	/* Real page number bit 3, optional */
+	unsigned long pp:2;	/* Page protection */
+};
+
+typedef struct {
+	unsigned long id;
+	unsigned long vdso_base;
+} mm_context_t;
+
+#endif /* !__ASSEMBLY__ */
+
+/* We happily ignore the smaller BATs on 601, we don't actually use
+ * those definitions on hash32 at the moment anyway
+ */
+#define mmu_virtual_psize	MMU_PAGE_4K
+#define mmu_linear_psize	MMU_PAGE_256M
+
+#endif /* _ASM_POWERPC_MMU_HASH32_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
new file mode 100644
index 000000000000..0cea4807e26f
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -0,0 +1,616 @@
+#ifndef _ASM_POWERPC_MMU_HASH64_H_
+#define _ASM_POWERPC_MMU_HASH64_H_
+/*
+ * PowerPC64 memory management structures
+ *
+ * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com>
+ *   PPC64 rework.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/asm-compat.h>
+#include <asm/page.h>
+#include <asm/bug.h>
+
+/*
+ * This is necessary to get the definition of PGTABLE_RANGE which we
+ * need for various slices related matters. Note that this isn't the
+ * complete pgtable.h but only a portion of it.
+ */
+#include <asm/book3s/64/pgtable.h>
+#include <asm/bug.h>
+#include <asm/processor.h>
+
+/*
+ * SLB
+ */
+
+#define SLB_NUM_BOLTED		3
+#define SLB_CACHE_ENTRIES	8
+#define SLB_MIN_SIZE		32
+
+/* Bits in the SLB ESID word */
+#define SLB_ESID_V		ASM_CONST(0x0000000008000000) /* valid */
+
+/* Bits in the SLB VSID word */
+#define SLB_VSID_SHIFT		12
+#define SLB_VSID_SHIFT_1T	24
+#define SLB_VSID_SSIZE_SHIFT	62
+#define SLB_VSID_B		ASM_CONST(0xc000000000000000)
+#define SLB_VSID_B_256M		ASM_CONST(0x0000000000000000)
+#define SLB_VSID_B_1T		ASM_CONST(0x4000000000000000)
+#define SLB_VSID_KS		ASM_CONST(0x0000000000000800)
+#define SLB_VSID_KP		ASM_CONST(0x0000000000000400)
+#define SLB_VSID_N		ASM_CONST(0x0000000000000200) /* no-execute */
+#define SLB_VSID_L		ASM_CONST(0x0000000000000100)
+#define SLB_VSID_C		ASM_CONST(0x0000000000000080) /* class */
+#define SLB_VSID_LP		ASM_CONST(0x0000000000000030)
+#define SLB_VSID_LP_00		ASM_CONST(0x0000000000000000)
+#define SLB_VSID_LP_01		ASM_CONST(0x0000000000000010)
+#define SLB_VSID_LP_10		ASM_CONST(0x0000000000000020)
+#define SLB_VSID_LP_11		ASM_CONST(0x0000000000000030)
+#define SLB_VSID_LLP		(SLB_VSID_L|SLB_VSID_LP)
+
+#define SLB_VSID_KERNEL		(SLB_VSID_KP)
+#define SLB_VSID_USER		(SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C)
+
+#define SLBIE_C			(0x08000000)
+#define SLBIE_SSIZE_SHIFT	25
+
+/*
+ * Hash table
+ */
+
+#define HPTES_PER_GROUP 8
+
+#define HPTE_V_SSIZE_SHIFT	62
+#define HPTE_V_AVPN_SHIFT	7
+#define HPTE_V_AVPN		ASM_CONST(0x3fffffffffffff80)
+#define HPTE_V_AVPN_VAL(x)	(((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT)
+#define HPTE_V_COMPARE(x,y)	(!(((x) ^ (y)) & 0xffffffffffffff80UL))
+#define HPTE_V_BOLTED		ASM_CONST(0x0000000000000010)
+#define HPTE_V_LOCK		ASM_CONST(0x0000000000000008)
+#define HPTE_V_LARGE		ASM_CONST(0x0000000000000004)
+#define HPTE_V_SECONDARY	ASM_CONST(0x0000000000000002)
+#define HPTE_V_VALID		ASM_CONST(0x0000000000000001)
+
+#define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
+#define HPTE_R_TS		ASM_CONST(0x4000000000000000)
+#define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
+#define HPTE_R_RPN_SHIFT	12
+#define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
+#define HPTE_R_PP		ASM_CONST(0x0000000000000003)
+#define HPTE_R_N		ASM_CONST(0x0000000000000004)
+#define HPTE_R_G		ASM_CONST(0x0000000000000008)
+#define HPTE_R_M		ASM_CONST(0x0000000000000010)
+#define HPTE_R_I		ASM_CONST(0x0000000000000020)
+#define HPTE_R_W		ASM_CONST(0x0000000000000040)
+#define HPTE_R_WIMG		ASM_CONST(0x0000000000000078)
+#define HPTE_R_C		ASM_CONST(0x0000000000000080)
+#define HPTE_R_R		ASM_CONST(0x0000000000000100)
+#define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
+
+#define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
+#define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)
+
+/* Values for PP (assumes Ks=0, Kp=1) */
+#define PP_RWXX	0	/* Supervisor read/write, User none */
+#define PP_RWRX 1	/* Supervisor read/write, User read */
+#define PP_RWRW 2	/* Supervisor read/write, User read/write */
+#define PP_RXRX 3	/* Supervisor read,       User read */
+#define PP_RXXX	(HPTE_R_PP0 | 2)	/* Supervisor read, user none */
+
+/* Fields for tlbiel instruction in architecture 2.06 */
+#define TLBIEL_INVAL_SEL_MASK	0xc00	/* invalidation selector */
+#define  TLBIEL_INVAL_PAGE	0x000	/* invalidate a single page */
+#define  TLBIEL_INVAL_SET_LPID	0x800	/* invalidate a set for current LPID */
+#define  TLBIEL_INVAL_SET	0xc00	/* invalidate a set for all LPIDs */
+#define TLBIEL_INVAL_SET_MASK	0xfff000	/* set number to inval. */
+#define TLBIEL_INVAL_SET_SHIFT	12
+
+#define POWER7_TLB_SETS		128	/* # sets in POWER7 TLB */
+#define POWER8_TLB_SETS		512	/* # sets in POWER8 TLB */
+#define POWER9_TLB_SETS_HASH	256	/* # sets in POWER9 TLB Hash mode */
+
+#ifndef __ASSEMBLY__
+
+struct hash_pte {
+	__be64 v;
+	__be64 r;
+};
+
+extern struct hash_pte *htab_address;
+extern unsigned long htab_size_bytes;
+extern unsigned long htab_hash_mask;
+
+/*
+ * Page size definition
+ *
+ *    shift : is the "PAGE_SHIFT" value for that page size
+ *    sllp  : is a bit mask with the value of SLB L || LP to be or'ed
+ *            directly to a slbmte "vsid" value
+ *    penc  : is the HPTE encoding mask for the "LP" field:
+ *
+ */
+struct mmu_psize_def
+{
+	unsigned int	shift;	/* number of bits */
+	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
+	unsigned int	tlbiel;	/* tlbiel supported for that page size */
+	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
+	unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
+};
+extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+
+static inline int shift_to_mmu_psize(unsigned int shift)
+{
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+		if (mmu_psize_defs[psize].shift == shift)
+			return psize;
+	return -1;
+}
+
+static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
+{
+	if (mmu_psize_defs[mmu_psize].shift)
+		return mmu_psize_defs[mmu_psize].shift;
+	BUG();
+}
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Segment sizes.
+ * These are the values used by hardware in the B field of
+ * SLB entries and the first dword of MMU hashtable entries.
+ * The B field is 2 bits; the values 2 and 3 are unused and reserved.
+ */
+#define MMU_SEGSIZE_256M	0
+#define MMU_SEGSIZE_1T		1
+
+/*
+ * encode page number shift.
+ * in order to fit the 78 bit va in a 64 bit variable we shift the va by
+ * 12 bits. This enable us to address upto 76 bit va.
+ * For hpt hash from a va we can ignore the page size bits of va and for
+ * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure
+ * we work in all cases including 4k page size.
+ */
+#define VPN_SHIFT	12
+
+/*
+ * HPTE Large Page (LP) details
+ */
+#define LP_SHIFT	12
+#define LP_BITS		8
+#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
+
+#ifndef __ASSEMBLY__
+
+static inline int slb_vsid_shift(int ssize)
+{
+	if (ssize == MMU_SEGSIZE_256M)
+		return SLB_VSID_SHIFT;
+	return SLB_VSID_SHIFT_1T;
+}
+
+static inline int segment_shift(int ssize)
+{
+	if (ssize == MMU_SEGSIZE_256M)
+		return SID_SHIFT;
+	return SID_SHIFT_1T;
+}
+
+/*
+ * The current system page and segment sizes
+ */
+extern int mmu_linear_psize;
+extern int mmu_virtual_psize;
+extern int mmu_vmalloc_psize;
+extern int mmu_vmemmap_psize;
+extern int mmu_io_psize;
+extern int mmu_kernel_ssize;
+extern int mmu_highuser_ssize;
+extern u16 mmu_slb_size;
+extern unsigned long tce_alloc_start, tce_alloc_end;
+
+/*
+ * If the processor supports 64k normal pages but not 64k cache
+ * inhibited pages, we have to be prepared to switch processes
+ * to use 4k pages when they create cache-inhibited mappings.
+ * If this is the case, mmu_ci_restrictions will be set to 1.
+ */
+extern int mmu_ci_restrictions;
+
+/*
+ * This computes the AVPN and B fields of the first dword of a HPTE,
+ * for use when we want to match an existing PTE.  The bottom 7 bits
+ * of the returned value are zero.
+ */
+static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
+					     int ssize)
+{
+	unsigned long v;
+	/*
+	 * The AVA field omits the low-order 23 bits of the 78 bits VA.
+	 * These bits are not needed in the PTE, because the
+	 * low-order b of these bits are part of the byte offset
+	 * into the virtual page and, if b < 23, the high-order
+	 * 23-b of these bits are always used in selecting the
+	 * PTEGs to be searched
+	 */
+	v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
+	v <<= HPTE_V_AVPN_SHIFT;
+	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
+	return v;
+}
+
+/*
+ * This function sets the AVPN and L fields of the HPTE  appropriately
+ * using the base page size and actual page size.
+ */
+static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
+					  int actual_psize, int ssize)
+{
+	unsigned long v;
+	v = hpte_encode_avpn(vpn, base_psize, ssize);
+	if (actual_psize != MMU_PAGE_4K)
+		v |= HPTE_V_LARGE;
+	return v;
+}
+
+/*
+ * This function sets the ARPN, and LP fields of the HPTE appropriately
+ * for the page size. We assume the pa is already "clean" that is properly
+ * aligned for the requested page size
+ */
+static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
+					  int actual_psize)
+{
+	/* A 4K page needs no special encoding */
+	if (actual_psize == MMU_PAGE_4K)
+		return pa & HPTE_R_RPN;
+	else {
+		unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize];
+		unsigned int shift = mmu_psize_defs[actual_psize].shift;
+		return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT);
+	}
+}
+
+/*
+ * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size.
+ */
+static inline unsigned long hpt_vpn(unsigned long ea,
+				    unsigned long vsid, int ssize)
+{
+	unsigned long mask;
+	int s_shift = segment_shift(ssize);
+
+	mask = (1ul << (s_shift - VPN_SHIFT)) - 1;
+	return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask);
+}
+
+/*
+ * This hashes a virtual address
+ */
+static inline unsigned long hpt_hash(unsigned long vpn,
+				     unsigned int shift, int ssize)
+{
+	int mask;
+	unsigned long hash, vsid;
+
+	/* VPN_SHIFT can be atmost 12 */
+	if (ssize == MMU_SEGSIZE_256M) {
+		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
+		hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^
+			((vpn & mask) >> (shift - VPN_SHIFT));
+	} else {
+		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
+		vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT);
+		hash = vsid ^ (vsid << 25) ^
+			((vpn & mask) >> (shift - VPN_SHIFT)) ;
+	}
+	return hash & 0x7fffffffffUL;
+}
+
+#define HPTE_LOCAL_UPDATE	0x1
+#define HPTE_NOHPTE_UPDATE	0x2
+
+extern int __hash_page_4K(unsigned long ea, unsigned long access,
+			  unsigned long vsid, pte_t *ptep, unsigned long trap,
+			  unsigned long flags, int ssize, int subpage_prot);
+extern int __hash_page_64K(unsigned long ea, unsigned long access,
+			   unsigned long vsid, pte_t *ptep, unsigned long trap,
+			   unsigned long flags, int ssize);
+struct mm_struct;
+unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+			unsigned long access, unsigned long trap,
+			unsigned long flags);
+extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+		     unsigned long dsisr);
+int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+		     pte_t *ptep, unsigned long trap, unsigned long flags,
+		     int ssize, unsigned int shift, unsigned int mmu_psize);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern int __hash_page_thp(unsigned long ea, unsigned long access,
+			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
+			   unsigned long flags, int ssize, unsigned int psize);
+#else
+static inline int __hash_page_thp(unsigned long ea, unsigned long access,
+				  unsigned long vsid, pmd_t *pmdp,
+				  unsigned long trap, unsigned long flags,
+				  int ssize, unsigned int psize)
+{
+	BUG();
+	return -1;
+}
+#endif
+extern void hash_failure_debug(unsigned long ea, unsigned long access,
+			       unsigned long vsid, unsigned long trap,
+			       int ssize, int psize, int lpsize,
+			       unsigned long pte);
+extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
+			     unsigned long pstart, unsigned long prot,
+			     int psize, int ssize);
+int htab_remove_mapping(unsigned long vstart, unsigned long vend,
+			int psize, int ssize);
+extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
+extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
+
+extern void hpte_init_native(void);
+extern void hpte_init_lpar(void);
+extern void hpte_init_beat(void);
+extern void hpte_init_beat_v3(void);
+
+extern void slb_initialize(void);
+extern void slb_flush_and_rebolt(void);
+
+extern void slb_vmalloc_update(void);
+extern void slb_set_size(u16 size);
+#endif /* __ASSEMBLY__ */
+
+/*
+ * VSID allocation (256MB segment)
+ *
+ * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
+ * from mmu context id and effective segment id of the address.
+ *
+ * For user processes max context id is limited to ((1ul << 19) - 5)
+ * for kernel space, we use the top 4 context ids to map address as below
+ * NOTE: each context only support 64TB now.
+ * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ *
+ * The proto-VSIDs are then scrambled into real VSIDs with the
+ * multiplicative hash:
+ *
+ *	VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS
+ *
+ * VSID_MULTIPLIER is prime, so in particular it is
+ * co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
+ * Because the modulus is 2^n-1 we can compute it efficiently without
+ * a divide or extra multiply (see below). The scramble function gives
+ * robust scattering in the hash table (at least based on some initial
+ * results).
+ *
+ * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
+ * bad address. This enables us to consolidate bad address handling in
+ * hash_page.
+ *
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble. But the vmemmap
+ * (which is what uses region 0xf) will never be close to 64TB in size
+ * (it's 56 bytes per page of system memory).
+ */
+
+#define CONTEXT_BITS		19
+#define ESID_BITS		18
+#define ESID_BITS_1T		6
+
+/*
+ * 256MB segment
+ * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
+ * available for user + kernel mapping. The top 4 contexts are used for
+ * kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
+ * (19 == 37 + 28 - 46).
+ */
+#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 5)
+
+/*
+ * This should be computed such that protovosid * vsid_mulitplier
+ * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
+ */
+#define VSID_MULTIPLIER_256M	ASM_CONST(12538073)	/* 24-bit prime */
+#define VSID_BITS_256M		(CONTEXT_BITS + ESID_BITS)
+#define VSID_MODULUS_256M	((1UL<<VSID_BITS_256M)-1)
+
+#define VSID_MULTIPLIER_1T	ASM_CONST(12538073)	/* 24-bit prime */
+#define VSID_BITS_1T		(CONTEXT_BITS + ESID_BITS_1T)
+#define VSID_MODULUS_1T		((1UL<<VSID_BITS_1T)-1)
+
+
+#define USER_VSID_RANGE	(1UL << (ESID_BITS + SID_SHIFT))
+
+/*
+ * This macro generates asm code to compute the VSID scramble
+ * function.  Used in slb_allocate() and do_stab_bolted.  The function
+ * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
+ *
+ *	rt = register continaing the proto-VSID and into which the
+ *		VSID will be stored
+ *	rx = scratch register (clobbered)
+ *
+ * 	- rt and rx must be different registers
+ * 	- The answer will end up in the low VSID_BITS bits of rt.  The higher
+ * 	  bits may contain other garbage, so you may need to mask the
+ * 	  result.
+ */
+#define ASM_VSID_SCRAMBLE(rt, rx, size)					\
+	lis	rx,VSID_MULTIPLIER_##size@h;				\
+	ori	rx,rx,VSID_MULTIPLIER_##size@l;				\
+	mulld	rt,rt,rx;		/* rt = rt * MULTIPLIER */	\
+									\
+	srdi	rx,rt,VSID_BITS_##size;					\
+	clrldi	rt,rt,(64-VSID_BITS_##size);				\
+	add	rt,rt,rx;		/* add high and low bits */	\
+	/* NOTE: explanation based on VSID_BITS_##size = 36		\
+	 * Now, r3 == VSID (mod 2^36-1), and lies between 0 and		\
+	 * 2^36-1+2^28-1.  That in particular means that if r3 >=	\
+	 * 2^36-1, then r3+1 has the 2^36 bit set.  So, if r3+1 has	\
+	 * the bit clear, r3 already has the answer we want, if it	\
+	 * doesn't, the answer is the low 36 bits of r3+1.  So in all	\
+	 * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\
+	addi	rx,rt,1;						\
+	srdi	rx,rx,VSID_BITS_##size;	/* extract 2^VSID_BITS bit */	\
+	add	rt,rt,rx
+
+/* 4 bits per slice and we have one slice per 1TB */
+#define SLICE_ARRAY_SIZE  (PGTABLE_RANGE >> 41)
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+	unsigned long maxaddr;	/* only addresses < this are protected */
+	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
+	unsigned int *low_prot[4];
+};
+
+#define SBP_L1_BITS		(PAGE_SHIFT - 2)
+#define SBP_L2_BITS		(PAGE_SHIFT - 3)
+#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
+#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(struct mm_struct *mm);
+extern void subpage_prot_init_new_context(struct mm_struct *mm);
+#else
+static inline void subpage_prot_free(struct mm_struct *mm) {}
+static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+
+typedef unsigned long mm_context_id_t;
+struct spinlock;
+
+typedef struct {
+	mm_context_id_t id;
+	u16 user_psize;		/* page size index */
+
+#ifdef CONFIG_PPC_MM_SLICES
+	u64 low_slices_psize;	/* SLB page size encodings */
+	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
+#else
+	u16 sllp;		/* SLB page size encoding */
+#endif
+	unsigned long vdso_base;
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+	struct subpage_prot_table spt;
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+#ifdef CONFIG_PPC_ICSWX
+	struct spinlock *cop_lockp; /* guard acop and cop_pid */
+	unsigned long acop;	/* mask of enabled coprocessor types */
+	unsigned int cop_pid;	/* pid value used with coprocessors */
+#endif /* CONFIG_PPC_ICSWX */
+#ifdef CONFIG_PPC_64K_PAGES
+	/* for 4K PTE fragment support */
+	void *pte_frag;
+#endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	struct list_head iommu_group_mem_list;
+#endif
+} mm_context_t;
+
+
+#if 0
+/*
+ * The code below is equivalent to this function for arguments
+ * < 2^VSID_BITS, which is all this should ever be called
+ * with.  However gcc is not clever enough to compute the
+ * modulus (2^n-1) without a second multiply.
+ */
+#define vsid_scramble(protovsid, size) \
+	((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size))
+
+#else /* 1 */
+#define vsid_scramble(protovsid, size) \
+	({								 \
+		unsigned long x;					 \
+		x = (protovsid) * VSID_MULTIPLIER_##size;		 \
+		x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \
+		(x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \
+	})
+#endif /* 1 */
+
+/* Returns the segment size indicator for a user address */
+static inline int user_segment_size(unsigned long addr)
+{
+	/* Use 1T segments if possible for addresses >= 1T */
+	if (addr >= (1UL << SID_SHIFT_1T))
+		return mmu_highuser_ssize;
+	return MMU_SEGSIZE_256M;
+}
+
+static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
+				     int ssize)
+{
+	/*
+	 * Bad address. We return VSID 0 for that
+	 */
+	if ((ea & ~REGION_MASK) >= PGTABLE_RANGE)
+		return 0;
+
+	if (ssize == MMU_SEGSIZE_256M)
+		return vsid_scramble((context << ESID_BITS)
+				     | (ea >> SID_SHIFT), 256M);
+	return vsid_scramble((context << ESID_BITS_1T)
+			     | (ea >> SID_SHIFT_1T), 1T);
+}
+
+/*
+ * This is only valid for addresses >= PAGE_OFFSET
+ *
+ * For kernel space, we use the top 4 context ids to map address as below
+ * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ */
+static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
+{
+	unsigned long context;
+
+	/*
+	 * kernel take the top 4 context from the available range
+	 */
+	context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
+	return get_vsid(context, ea, ssize);
+}
+
+unsigned htab_shift_for_mem_size(unsigned long mem_size);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_MMU_HASH64_H_ */
diff --git a/arch/powerpc/include/asm/mmu-hash32.h b/arch/powerpc/include/asm/mmu-hash32.h
deleted file mode 100644
index 16f513e5cbd7..000000000000
--- a/arch/powerpc/include/asm/mmu-hash32.h
+++ /dev/null
@@ -1,93 +0,0 @@
-#ifndef _ASM_POWERPC_MMU_HASH32_H_
-#define _ASM_POWERPC_MMU_HASH32_H_
-/*
- * 32-bit hash table MMU support
- */
-
-/*
- * BATs
- */
-
-/* Block size masks */
-#define BL_128K	0x000
-#define BL_256K 0x001
-#define BL_512K 0x003
-#define BL_1M   0x007
-#define BL_2M   0x00F
-#define BL_4M   0x01F
-#define BL_8M   0x03F
-#define BL_16M  0x07F
-#define BL_32M  0x0FF
-#define BL_64M  0x1FF
-#define BL_128M 0x3FF
-#define BL_256M 0x7FF
-
-/* BAT Access Protection */
-#define BPP_XX	0x00		/* No access */
-#define BPP_RX	0x01		/* Read only */
-#define BPP_RW	0x02		/* Read/write */
-
-#ifndef __ASSEMBLY__
-/* Contort a phys_addr_t into the right format/bits for a BAT */
-#ifdef CONFIG_PHYS_64BIT
-#define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \
-				((x & 0x0000000e00000000ULL) >> 24) | \
-				((x & 0x0000000100000000ULL) >> 30)))
-#else
-#define BAT_PHYS_ADDR(x) (x)
-#endif
-
-struct ppc_bat {
-	u32 batu;
-	u32 batl;
-};
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Hash table
- */
-
-/* Values for PP (assumes Ks=0, Kp=1) */
-#define PP_RWXX	0	/* Supervisor read/write, User none */
-#define PP_RWRX 1	/* Supervisor read/write, User read */
-#define PP_RWRW 2	/* Supervisor read/write, User read/write */
-#define PP_RXRX 3	/* Supervisor read,       User read */
-
-#ifndef __ASSEMBLY__
-
-/*
- * Hardware Page Table Entry
- * Note that the xpn and x bitfields are used only by processors that
- * support extended addressing; otherwise, those bits are reserved.
- */
-struct hash_pte {
-	unsigned long v:1;	/* Entry is valid */
-	unsigned long vsid:24;	/* Virtual segment identifier */
-	unsigned long h:1;	/* Hash algorithm indicator */
-	unsigned long api:6;	/* Abbreviated page index */
-	unsigned long rpn:20;	/* Real (physical) page number */
-	unsigned long xpn:3;	/* Real page number bits 0-2, optional */
-	unsigned long r:1;	/* Referenced */
-	unsigned long c:1;	/* Changed */
-	unsigned long w:1;	/* Write-thru cache mode */
-	unsigned long i:1;	/* Cache inhibited */
-	unsigned long m:1;	/* Memory coherence */
-	unsigned long g:1;	/* Guarded */
-	unsigned long x:1;	/* Real page number bit 3, optional */
-	unsigned long pp:2;	/* Page protection */
-};
-
-typedef struct {
-	unsigned long id;
-	unsigned long vdso_base;
-} mm_context_t;
-
-#endif /* !__ASSEMBLY__ */
-
-/* We happily ignore the smaller BATs on 601, we don't actually use
- * those definitions on hash32 at the moment anyway
- */
-#define mmu_virtual_psize	MMU_PAGE_4K
-#define mmu_linear_psize	MMU_PAGE_256M
-
-#endif /* _ASM_POWERPC_MMU_HASH32_H_ */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
deleted file mode 100644
index 0cea4807e26f..000000000000
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ /dev/null
@@ -1,616 +0,0 @@
-#ifndef _ASM_POWERPC_MMU_HASH64_H_
-#define _ASM_POWERPC_MMU_HASH64_H_
-/*
- * PowerPC64 memory management structures
- *
- * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com>
- *   PPC64 rework.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <asm/asm-compat.h>
-#include <asm/page.h>
-#include <asm/bug.h>
-
-/*
- * This is necessary to get the definition of PGTABLE_RANGE which we
- * need for various slices related matters. Note that this isn't the
- * complete pgtable.h but only a portion of it.
- */
-#include <asm/book3s/64/pgtable.h>
-#include <asm/bug.h>
-#include <asm/processor.h>
-
-/*
- * SLB
- */
-
-#define SLB_NUM_BOLTED		3
-#define SLB_CACHE_ENTRIES	8
-#define SLB_MIN_SIZE		32
-
-/* Bits in the SLB ESID word */
-#define SLB_ESID_V		ASM_CONST(0x0000000008000000) /* valid */
-
-/* Bits in the SLB VSID word */
-#define SLB_VSID_SHIFT		12
-#define SLB_VSID_SHIFT_1T	24
-#define SLB_VSID_SSIZE_SHIFT	62
-#define SLB_VSID_B		ASM_CONST(0xc000000000000000)
-#define SLB_VSID_B_256M		ASM_CONST(0x0000000000000000)
-#define SLB_VSID_B_1T		ASM_CONST(0x4000000000000000)
-#define SLB_VSID_KS		ASM_CONST(0x0000000000000800)
-#define SLB_VSID_KP		ASM_CONST(0x0000000000000400)
-#define SLB_VSID_N		ASM_CONST(0x0000000000000200) /* no-execute */
-#define SLB_VSID_L		ASM_CONST(0x0000000000000100)
-#define SLB_VSID_C		ASM_CONST(0x0000000000000080) /* class */
-#define SLB_VSID_LP		ASM_CONST(0x0000000000000030)
-#define SLB_VSID_LP_00		ASM_CONST(0x0000000000000000)
-#define SLB_VSID_LP_01		ASM_CONST(0x0000000000000010)
-#define SLB_VSID_LP_10		ASM_CONST(0x0000000000000020)
-#define SLB_VSID_LP_11		ASM_CONST(0x0000000000000030)
-#define SLB_VSID_LLP		(SLB_VSID_L|SLB_VSID_LP)
-
-#define SLB_VSID_KERNEL		(SLB_VSID_KP)
-#define SLB_VSID_USER		(SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C)
-
-#define SLBIE_C			(0x08000000)
-#define SLBIE_SSIZE_SHIFT	25
-
-/*
- * Hash table
- */
-
-#define HPTES_PER_GROUP 8
-
-#define HPTE_V_SSIZE_SHIFT	62
-#define HPTE_V_AVPN_SHIFT	7
-#define HPTE_V_AVPN		ASM_CONST(0x3fffffffffffff80)
-#define HPTE_V_AVPN_VAL(x)	(((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT)
-#define HPTE_V_COMPARE(x,y)	(!(((x) ^ (y)) & 0xffffffffffffff80UL))
-#define HPTE_V_BOLTED		ASM_CONST(0x0000000000000010)
-#define HPTE_V_LOCK		ASM_CONST(0x0000000000000008)
-#define HPTE_V_LARGE		ASM_CONST(0x0000000000000004)
-#define HPTE_V_SECONDARY	ASM_CONST(0x0000000000000002)
-#define HPTE_V_VALID		ASM_CONST(0x0000000000000001)
-
-#define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
-#define HPTE_R_TS		ASM_CONST(0x4000000000000000)
-#define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
-#define HPTE_R_RPN_SHIFT	12
-#define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
-#define HPTE_R_PP		ASM_CONST(0x0000000000000003)
-#define HPTE_R_N		ASM_CONST(0x0000000000000004)
-#define HPTE_R_G		ASM_CONST(0x0000000000000008)
-#define HPTE_R_M		ASM_CONST(0x0000000000000010)
-#define HPTE_R_I		ASM_CONST(0x0000000000000020)
-#define HPTE_R_W		ASM_CONST(0x0000000000000040)
-#define HPTE_R_WIMG		ASM_CONST(0x0000000000000078)
-#define HPTE_R_C		ASM_CONST(0x0000000000000080)
-#define HPTE_R_R		ASM_CONST(0x0000000000000100)
-#define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
-
-#define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
-#define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)
-
-/* Values for PP (assumes Ks=0, Kp=1) */
-#define PP_RWXX	0	/* Supervisor read/write, User none */
-#define PP_RWRX 1	/* Supervisor read/write, User read */
-#define PP_RWRW 2	/* Supervisor read/write, User read/write */
-#define PP_RXRX 3	/* Supervisor read,       User read */
-#define PP_RXXX	(HPTE_R_PP0 | 2)	/* Supervisor read, user none */
-
-/* Fields for tlbiel instruction in architecture 2.06 */
-#define TLBIEL_INVAL_SEL_MASK	0xc00	/* invalidation selector */
-#define  TLBIEL_INVAL_PAGE	0x000	/* invalidate a single page */
-#define  TLBIEL_INVAL_SET_LPID	0x800	/* invalidate a set for current LPID */
-#define  TLBIEL_INVAL_SET	0xc00	/* invalidate a set for all LPIDs */
-#define TLBIEL_INVAL_SET_MASK	0xfff000	/* set number to inval. */
-#define TLBIEL_INVAL_SET_SHIFT	12
-
-#define POWER7_TLB_SETS		128	/* # sets in POWER7 TLB */
-#define POWER8_TLB_SETS		512	/* # sets in POWER8 TLB */
-#define POWER9_TLB_SETS_HASH	256	/* # sets in POWER9 TLB Hash mode */
-
-#ifndef __ASSEMBLY__
-
-struct hash_pte {
-	__be64 v;
-	__be64 r;
-};
-
-extern struct hash_pte *htab_address;
-extern unsigned long htab_size_bytes;
-extern unsigned long htab_hash_mask;
-
-/*
- * Page size definition
- *
- *    shift : is the "PAGE_SHIFT" value for that page size
- *    sllp  : is a bit mask with the value of SLB L || LP to be or'ed
- *            directly to a slbmte "vsid" value
- *    penc  : is the HPTE encoding mask for the "LP" field:
- *
- */
-struct mmu_psize_def
-{
-	unsigned int	shift;	/* number of bits */
-	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
-	unsigned int	tlbiel;	/* tlbiel supported for that page size */
-	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
-	unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
-};
-extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
-
-static inline int shift_to_mmu_psize(unsigned int shift)
-{
-	int psize;
-
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
-		if (mmu_psize_defs[psize].shift == shift)
-			return psize;
-	return -1;
-}
-
-static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
-{
-	if (mmu_psize_defs[mmu_psize].shift)
-		return mmu_psize_defs[mmu_psize].shift;
-	BUG();
-}
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * Segment sizes.
- * These are the values used by hardware in the B field of
- * SLB entries and the first dword of MMU hashtable entries.
- * The B field is 2 bits; the values 2 and 3 are unused and reserved.
- */
-#define MMU_SEGSIZE_256M	0
-#define MMU_SEGSIZE_1T		1
-
-/*
- * encode page number shift.
- * in order to fit the 78 bit va in a 64 bit variable we shift the va by
- * 12 bits. This enable us to address upto 76 bit va.
- * For hpt hash from a va we can ignore the page size bits of va and for
- * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure
- * we work in all cases including 4k page size.
- */
-#define VPN_SHIFT	12
-
-/*
- * HPTE Large Page (LP) details
- */
-#define LP_SHIFT	12
-#define LP_BITS		8
-#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
-
-#ifndef __ASSEMBLY__
-
-static inline int slb_vsid_shift(int ssize)
-{
-	if (ssize == MMU_SEGSIZE_256M)
-		return SLB_VSID_SHIFT;
-	return SLB_VSID_SHIFT_1T;
-}
-
-static inline int segment_shift(int ssize)
-{
-	if (ssize == MMU_SEGSIZE_256M)
-		return SID_SHIFT;
-	return SID_SHIFT_1T;
-}
-
-/*
- * The current system page and segment sizes
- */
-extern int mmu_linear_psize;
-extern int mmu_virtual_psize;
-extern int mmu_vmalloc_psize;
-extern int mmu_vmemmap_psize;
-extern int mmu_io_psize;
-extern int mmu_kernel_ssize;
-extern int mmu_highuser_ssize;
-extern u16 mmu_slb_size;
-extern unsigned long tce_alloc_start, tce_alloc_end;
-
-/*
- * If the processor supports 64k normal pages but not 64k cache
- * inhibited pages, we have to be prepared to switch processes
- * to use 4k pages when they create cache-inhibited mappings.
- * If this is the case, mmu_ci_restrictions will be set to 1.
- */
-extern int mmu_ci_restrictions;
-
-/*
- * This computes the AVPN and B fields of the first dword of a HPTE,
- * for use when we want to match an existing PTE.  The bottom 7 bits
- * of the returned value are zero.
- */
-static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
-					     int ssize)
-{
-	unsigned long v;
-	/*
-	 * The AVA field omits the low-order 23 bits of the 78 bits VA.
-	 * These bits are not needed in the PTE, because the
-	 * low-order b of these bits are part of the byte offset
-	 * into the virtual page and, if b < 23, the high-order
-	 * 23-b of these bits are always used in selecting the
-	 * PTEGs to be searched
-	 */
-	v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
-	v <<= HPTE_V_AVPN_SHIFT;
-	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
-	return v;
-}
-
-/*
- * This function sets the AVPN and L fields of the HPTE  appropriately
- * using the base page size and actual page size.
- */
-static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
-					  int actual_psize, int ssize)
-{
-	unsigned long v;
-	v = hpte_encode_avpn(vpn, base_psize, ssize);
-	if (actual_psize != MMU_PAGE_4K)
-		v |= HPTE_V_LARGE;
-	return v;
-}
-
-/*
- * This function sets the ARPN, and LP fields of the HPTE appropriately
- * for the page size. We assume the pa is already "clean" that is properly
- * aligned for the requested page size
- */
-static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
-					  int actual_psize)
-{
-	/* A 4K page needs no special encoding */
-	if (actual_psize == MMU_PAGE_4K)
-		return pa & HPTE_R_RPN;
-	else {
-		unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize];
-		unsigned int shift = mmu_psize_defs[actual_psize].shift;
-		return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT);
-	}
-}
-
-/*
- * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size.
- */
-static inline unsigned long hpt_vpn(unsigned long ea,
-				    unsigned long vsid, int ssize)
-{
-	unsigned long mask;
-	int s_shift = segment_shift(ssize);
-
-	mask = (1ul << (s_shift - VPN_SHIFT)) - 1;
-	return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask);
-}
-
-/*
- * This hashes a virtual address
- */
-static inline unsigned long hpt_hash(unsigned long vpn,
-				     unsigned int shift, int ssize)
-{
-	int mask;
-	unsigned long hash, vsid;
-
-	/* VPN_SHIFT can be atmost 12 */
-	if (ssize == MMU_SEGSIZE_256M) {
-		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
-		hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^
-			((vpn & mask) >> (shift - VPN_SHIFT));
-	} else {
-		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
-		vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT);
-		hash = vsid ^ (vsid << 25) ^
-			((vpn & mask) >> (shift - VPN_SHIFT)) ;
-	}
-	return hash & 0x7fffffffffUL;
-}
-
-#define HPTE_LOCAL_UPDATE	0x1
-#define HPTE_NOHPTE_UPDATE	0x2
-
-extern int __hash_page_4K(unsigned long ea, unsigned long access,
-			  unsigned long vsid, pte_t *ptep, unsigned long trap,
-			  unsigned long flags, int ssize, int subpage_prot);
-extern int __hash_page_64K(unsigned long ea, unsigned long access,
-			   unsigned long vsid, pte_t *ptep, unsigned long trap,
-			   unsigned long flags, int ssize);
-struct mm_struct;
-unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
-extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
-			unsigned long access, unsigned long trap,
-			unsigned long flags);
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
-		     unsigned long dsisr);
-int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
-		     pte_t *ptep, unsigned long trap, unsigned long flags,
-		     int ssize, unsigned int shift, unsigned int mmu_psize);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern int __hash_page_thp(unsigned long ea, unsigned long access,
-			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
-			   unsigned long flags, int ssize, unsigned int psize);
-#else
-static inline int __hash_page_thp(unsigned long ea, unsigned long access,
-				  unsigned long vsid, pmd_t *pmdp,
-				  unsigned long trap, unsigned long flags,
-				  int ssize, unsigned int psize)
-{
-	BUG();
-	return -1;
-}
-#endif
-extern void hash_failure_debug(unsigned long ea, unsigned long access,
-			       unsigned long vsid, unsigned long trap,
-			       int ssize, int psize, int lpsize,
-			       unsigned long pte);
-extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
-			     unsigned long pstart, unsigned long prot,
-			     int psize, int ssize);
-int htab_remove_mapping(unsigned long vstart, unsigned long vend,
-			int psize, int ssize);
-extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
-extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
-
-extern void hpte_init_native(void);
-extern void hpte_init_lpar(void);
-extern void hpte_init_beat(void);
-extern void hpte_init_beat_v3(void);
-
-extern void slb_initialize(void);
-extern void slb_flush_and_rebolt(void);
-
-extern void slb_vmalloc_update(void);
-extern void slb_set_size(u16 size);
-#endif /* __ASSEMBLY__ */
-
-/*
- * VSID allocation (256MB segment)
- *
- * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
- * from mmu context id and effective segment id of the address.
- *
- * For user processes max context id is limited to ((1ul << 19) - 5)
- * for kernel space, we use the top 4 context ids to map address as below
- * NOTE: each context only support 64TB now.
- * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
- *
- * The proto-VSIDs are then scrambled into real VSIDs with the
- * multiplicative hash:
- *
- *	VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS
- *
- * VSID_MULTIPLIER is prime, so in particular it is
- * co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
- * Because the modulus is 2^n-1 we can compute it efficiently without
- * a divide or extra multiply (see below). The scramble function gives
- * robust scattering in the hash table (at least based on some initial
- * results).
- *
- * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
- * bad address. This enables us to consolidate bad address handling in
- * hash_page.
- *
- * We also need to avoid the last segment of the last context, because that
- * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
- * because of the modulo operation in vsid scramble. But the vmemmap
- * (which is what uses region 0xf) will never be close to 64TB in size
- * (it's 56 bytes per page of system memory).
- */
-
-#define CONTEXT_BITS		19
-#define ESID_BITS		18
-#define ESID_BITS_1T		6
-
-/*
- * 256MB segment
- * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
- * available for user + kernel mapping. The top 4 contexts are used for
- * kernel mapping. Each segment contains 2^28 bytes. Each
- * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
- * (19 == 37 + 28 - 46).
- */
-#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 5)
-
-/*
- * This should be computed such that protovosid * vsid_mulitplier
- * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
- */
-#define VSID_MULTIPLIER_256M	ASM_CONST(12538073)	/* 24-bit prime */
-#define VSID_BITS_256M		(CONTEXT_BITS + ESID_BITS)
-#define VSID_MODULUS_256M	((1UL<<VSID_BITS_256M)-1)
-
-#define VSID_MULTIPLIER_1T	ASM_CONST(12538073)	/* 24-bit prime */
-#define VSID_BITS_1T		(CONTEXT_BITS + ESID_BITS_1T)
-#define VSID_MODULUS_1T		((1UL<<VSID_BITS_1T)-1)
-
-
-#define USER_VSID_RANGE	(1UL << (ESID_BITS + SID_SHIFT))
-
-/*
- * This macro generates asm code to compute the VSID scramble
- * function.  Used in slb_allocate() and do_stab_bolted.  The function
- * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
- *
- *	rt = register continaing the proto-VSID and into which the
- *		VSID will be stored
- *	rx = scratch register (clobbered)
- *
- * 	- rt and rx must be different registers
- * 	- The answer will end up in the low VSID_BITS bits of rt.  The higher
- * 	  bits may contain other garbage, so you may need to mask the
- * 	  result.
- */
-#define ASM_VSID_SCRAMBLE(rt, rx, size)					\
-	lis	rx,VSID_MULTIPLIER_##size@h;				\
-	ori	rx,rx,VSID_MULTIPLIER_##size@l;				\
-	mulld	rt,rt,rx;		/* rt = rt * MULTIPLIER */	\
-									\
-	srdi	rx,rt,VSID_BITS_##size;					\
-	clrldi	rt,rt,(64-VSID_BITS_##size);				\
-	add	rt,rt,rx;		/* add high and low bits */	\
-	/* NOTE: explanation based on VSID_BITS_##size = 36		\
-	 * Now, r3 == VSID (mod 2^36-1), and lies between 0 and		\
-	 * 2^36-1+2^28-1.  That in particular means that if r3 >=	\
-	 * 2^36-1, then r3+1 has the 2^36 bit set.  So, if r3+1 has	\
-	 * the bit clear, r3 already has the answer we want, if it	\
-	 * doesn't, the answer is the low 36 bits of r3+1.  So in all	\
-	 * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\
-	addi	rx,rt,1;						\
-	srdi	rx,rx,VSID_BITS_##size;	/* extract 2^VSID_BITS bit */	\
-	add	rt,rt,rx
-
-/* 4 bits per slice and we have one slice per 1TB */
-#define SLICE_ARRAY_SIZE  (PGTABLE_RANGE >> 41)
-
-#ifndef __ASSEMBLY__
-
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-/*
- * For the sub-page protection option, we extend the PGD with one of
- * these.  Basically we have a 3-level tree, with the top level being
- * the protptrs array.  To optimize speed and memory consumption when
- * only addresses < 4GB are being protected, pointers to the first
- * four pages of sub-page protection words are stored in the low_prot
- * array.
- * Each page of sub-page protection words protects 1GB (4 bytes
- * protects 64k).  For the 3-level tree, each page of pointers then
- * protects 8TB.
- */
-struct subpage_prot_table {
-	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
-	unsigned int *low_prot[4];
-};
-
-#define SBP_L1_BITS		(PAGE_SHIFT - 2)
-#define SBP_L2_BITS		(PAGE_SHIFT - 3)
-#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
-#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
-#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
-#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
-
-extern void subpage_prot_free(struct mm_struct *mm);
-extern void subpage_prot_init_new_context(struct mm_struct *mm);
-#else
-static inline void subpage_prot_free(struct mm_struct *mm) {}
-static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
-
-typedef unsigned long mm_context_id_t;
-struct spinlock;
-
-typedef struct {
-	mm_context_id_t id;
-	u16 user_psize;		/* page size index */
-
-#ifdef CONFIG_PPC_MM_SLICES
-	u64 low_slices_psize;	/* SLB page size encodings */
-	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
-#else
-	u16 sllp;		/* SLB page size encoding */
-#endif
-	unsigned long vdso_base;
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-	struct subpage_prot_table spt;
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
-#ifdef CONFIG_PPC_ICSWX
-	struct spinlock *cop_lockp; /* guard acop and cop_pid */
-	unsigned long acop;	/* mask of enabled coprocessor types */
-	unsigned int cop_pid;	/* pid value used with coprocessors */
-#endif /* CONFIG_PPC_ICSWX */
-#ifdef CONFIG_PPC_64K_PAGES
-	/* for 4K PTE fragment support */
-	void *pte_frag;
-#endif
-#ifdef CONFIG_SPAPR_TCE_IOMMU
-	struct list_head iommu_group_mem_list;
-#endif
-} mm_context_t;
-
-
-#if 0
-/*
- * The code below is equivalent to this function for arguments
- * < 2^VSID_BITS, which is all this should ever be called
- * with.  However gcc is not clever enough to compute the
- * modulus (2^n-1) without a second multiply.
- */
-#define vsid_scramble(protovsid, size) \
-	((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size))
-
-#else /* 1 */
-#define vsid_scramble(protovsid, size) \
-	({								 \
-		unsigned long x;					 \
-		x = (protovsid) * VSID_MULTIPLIER_##size;		 \
-		x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \
-		(x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \
-	})
-#endif /* 1 */
-
-/* Returns the segment size indicator for a user address */
-static inline int user_segment_size(unsigned long addr)
-{
-	/* Use 1T segments if possible for addresses >= 1T */
-	if (addr >= (1UL << SID_SHIFT_1T))
-		return mmu_highuser_ssize;
-	return MMU_SEGSIZE_256M;
-}
-
-static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
-				     int ssize)
-{
-	/*
-	 * Bad address. We return VSID 0 for that
-	 */
-	if ((ea & ~REGION_MASK) >= PGTABLE_RANGE)
-		return 0;
-
-	if (ssize == MMU_SEGSIZE_256M)
-		return vsid_scramble((context << ESID_BITS)
-				     | (ea >> SID_SHIFT), 256M);
-	return vsid_scramble((context << ESID_BITS_1T)
-			     | (ea >> SID_SHIFT_1T), 1T);
-}
-
-/*
- * This is only valid for addresses >= PAGE_OFFSET
- *
- * For kernel space, we use the top 4 context ids to map address as below
- * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
- */
-static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
-{
-	unsigned long context;
-
-	/*
-	 * kernel take the top 4 context from the available range
-	 */
-	context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
-	return get_vsid(context, ea, ssize);
-}
-
-unsigned htab_shift_for_mem_size(unsigned long mem_size);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_POWERPC_MMU_HASH64_H_ */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 54d46504733d..8ca1c983bf6c 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -183,10 +183,10 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 
 #if defined(CONFIG_PPC_STD_MMU_64)
 /* 64-bit classic hash table MMU */
-#  include <asm/mmu-hash64.h>
+#include <asm/book3s/64/mmu-hash.h>
 #elif defined(CONFIG_PPC_STD_MMU_32)
 /* 32-bit classic hash table MMU */
-#  include <asm/mmu-hash32.h>
+#include <asm/book3s/32/mmu-hash.h>
 #elif defined(CONFIG_40x)
 /* 40x-style software loaded TLB */
 #  include <asm/mmu-40x.h>
-- 
cgit v1.2.3


From ee3b93ebfbed6279f7a329001433c75c50ddfcc9 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 1 Mar 2016 12:59:21 +0530
Subject: powerpc/mm: Move hash64 tlbflush code into a new header

No code changes.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/tlbflush-hash.h | 94 ++++++++++++++++++++++
 arch/powerpc/include/asm/tlbflush.h                | 92 +--------------------
 2 files changed, 95 insertions(+), 91 deletions(-)
 create mode 100644 arch/powerpc/include/asm/book3s/64/tlbflush-hash.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
new file mode 100644
index 000000000000..1b753f96b374
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
@@ -0,0 +1,94 @@
+#ifndef _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H
+#define _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H
+
+#define MMU_NO_CONTEXT		0
+
+/*
+ * TLB flushing for 64-bit hash-MMU CPUs
+ */
+
+#include <linux/percpu.h>
+#include <asm/page.h>
+
+#define PPC64_TLB_BATCH_NR 192
+
+struct ppc64_tlb_batch {
+	int			active;
+	unsigned long		index;
+	struct mm_struct	*mm;
+	real_pte_t		pte[PPC64_TLB_BATCH_NR];
+	unsigned long		vpn[PPC64_TLB_BATCH_NR];
+	unsigned int		psize;
+	int			ssize;
+};
+DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
+
+extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
+
+	batch->active = 1;
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
+{
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
+
+	if (batch->index)
+		__flush_tlb_pending(batch);
+	batch->active = 0;
+}
+
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
+
+
+extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
+			    int ssize, unsigned long flags);
+extern void flush_hash_range(unsigned long number, int local);
+extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize,
+				unsigned long flags);
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
+					 unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+					  unsigned long end)
+{
+}
+
+/* Private function for use by PCI IO mapping code */
+extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
+				     unsigned long end);
+extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long addr);
+#endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H */
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 23d351ca0303..9f77f85e3e99 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -78,97 +78,7 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 }
 
 #elif defined(CONFIG_PPC_STD_MMU_64)
-
-#define MMU_NO_CONTEXT		0
-
-/*
- * TLB flushing for 64-bit hash-MMU CPUs
- */
-
-#include <linux/percpu.h>
-#include <asm/page.h>
-
-#define PPC64_TLB_BATCH_NR 192
-
-struct ppc64_tlb_batch {
-	int			active;
-	unsigned long		index;
-	struct mm_struct	*mm;
-	real_pte_t		pte[PPC64_TLB_BATCH_NR];
-	unsigned long		vpn[PPC64_TLB_BATCH_NR];
-	unsigned int		psize;
-	int			ssize;
-};
-DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
-
-extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
-
-#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
-
-static inline void arch_enter_lazy_mmu_mode(void)
-{
-	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
-
-	batch->active = 1;
-}
-
-static inline void arch_leave_lazy_mmu_mode(void)
-{
-	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
-
-	if (batch->index)
-		__flush_tlb_pending(batch);
-	batch->active = 0;
-}
-
-#define arch_flush_lazy_mmu_mode()      do {} while (0)
-
-
-extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
-			    int ssize, unsigned long flags);
-extern void flush_hash_range(unsigned long number, int local);
-extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
-				pmd_t *pmdp, unsigned int psize, int ssize,
-				unsigned long flags);
-
-static inline void local_flush_tlb_mm(struct mm_struct *mm)
-{
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-}
-
-static inline void local_flush_tlb_page(struct vm_area_struct *vma,
-					unsigned long vmaddr)
-{
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long vmaddr)
-{
-}
-
-static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
-					 unsigned long vmaddr)
-{
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
-					  unsigned long end)
-{
-}
-
-/* Private function for use by PCI IO mapping code */
-extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
-				     unsigned long end);
-extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd,
-				unsigned long addr);
+#include <asm/book3s/64/tlbflush-hash.h>
 #else
 #error Unsupported MMU type
 #endif
-- 
cgit v1.2.3


From 11dfbf588ae697bc5362c24294c2605f09c2d3d4 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 22 Sep 2015 16:34:21 +0200
Subject: powerpc: mark xer clobbered in csum_add()

addc uses carry so xer is clobbered in csum_add()

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/checksum.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index e8d9ef4755a4..d2ca07bb8837 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -141,7 +141,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 #else
 	asm("addc %0,%0,%1;"
 	    "addze %0,%0;"
-	    : "+r" (csum) : "r" (addend));
+	    : "+r" (csum) : "r" (addend) : "xer");
 	return csum;
 #endif
 }
-- 
cgit v1.2.3


From 03bc8b0fc87616c75c6dd060a2191e7fc8faacb6 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 22 Sep 2015 16:34:23 +0200
Subject: powerpc32: checksum_wrappers_64 becomes checksum_wrappers

The powerpc64 checksum wrapper functions adds csum_and_copy_to_user()
which otherwise is implemented in include/net/checksum.h by using
csum_partial() then copy_to_user()

Those two wrapper fonctions are also applicable to powerpc32 as it is
based on the use of csum_partial_copy_generic() which also
exists on powerpc32

This patch renames arch/powerpc/lib/checksum_wrappers_64.c to
arch/powerpc/lib/checksum_wrappers.c and
makes it non-conditional to CONFIG_WORD_SIZE

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/checksum.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index d2ca07bb8837..afa6722cb7d2 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -47,21 +47,12 @@ extern __wsum csum_partial_copy_generic(const void *src, void *dst,
 					      int len, __wsum sum,
 					      int *src_err, int *dst_err);
 
-#ifdef __powerpc64__
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 				      int len, __wsum sum, int *err_ptr);
 #define HAVE_CSUM_COPY_USER
 extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
 				    int len, __wsum sum, int *err_ptr);
-#else
-/*
- * the same as csum_partial, but copies from src to dst while it
- * checksums.
- */
-#define csum_partial_copy_from_user(src, dst, len, sum, errp)   \
-        csum_partial_copy_generic((__force const void *)(src), (dst), (len), (sum), (errp), NULL)
-#endif
 
 #define csum_partial_copy_nocheck(src, dst, len, sum)   \
         csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL)
-- 
cgit v1.2.3


From 37e08cad8f177f7bf6226a9b3724234ac3d3c81d Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 22 Sep 2015 16:34:25 +0200
Subject: powerpc: inline ip_fast_csum()

In several architectures, ip_fast_csum() is inlined
There are functions like ip_send_check() which do nothing
much more than calling ip_fast_csum().
Inlining ip_fast_csum() allows the compiler to optimise better

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[scottwood: whitespace and cast fixes]
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/checksum.h | 45 +++++++++++++++++++++++++++++++------
 1 file changed, 38 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index afa6722cb7d2..1778f75bf769 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -9,16 +9,9 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-/*
- * This is a version of ip_compute_csum() optimized for IP headers,
- * which always checksum on 4 octet boundaries.  ihl is the number
- * of 32-bit words and is always >= 5.
- */
 #ifdef CONFIG_GENERIC_CSUM
 #include <asm-generic/checksum.h>
 #else
-extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
-
 /*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
@@ -137,6 +130,44 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 #endif
 }
 
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.  ihl is the number
+ * of 32-bit words and is always >= 5.
+ */
+static inline __wsum ip_fast_csum_nofold(const void *iph, unsigned int ihl)
+{
+	const u32 *ptr = (const u32 *)iph + 1;
+#ifdef __powerpc64__
+	unsigned int i;
+	u64 s = *(const u32 *)iph;
+
+	for (i = 0; i < ihl - 1; i++, ptr++)
+		s += *ptr;
+	s += (s >> 32);
+	return (__force __wsum)s;
+#else
+	__wsum sum, tmp;
+
+	asm("mtctr %3;"
+	    "addc %0,%4,%5;"
+	    "1: lwzu %1, 4(%2);"
+	    "adde %0,%0,%1;"
+	    "bdnz 1b;"
+	    "addze %0,%0;"
+	    : "=r" (sum), "=r" (tmp), "+b" (ptr)
+	    : "r" (ihl - 2), "r" (*(const u32 *)iph), "r" (*ptr)
+	    : "ctr", "xer", "memory");
+
+	return sum;
+#endif
+}
+
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	return csum_fold(ip_fast_csum_nofold(iph, ihl));
+}
+
 #endif
 #endif /* __KERNEL__ */
 #endif
-- 
cgit v1.2.3


From 5a8847c83ce6072d6fdf0d15d9aa060c0b83537f Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 22 Sep 2015 16:34:34 +0200
Subject: powerpc: simplify csum_add(a, b) in case a or b is constant 0

Simplify csum_add(a, b) in case a or b is constant 0

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/checksum.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 1778f75bf769..74cd8d82628a 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -119,7 +119,13 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 {
 #ifdef __powerpc64__
 	u64 res = (__force u64)csum;
+#endif
+	if (__builtin_constant_p(csum) && csum == 0)
+		return addend;
+	if (__builtin_constant_p(addend) && addend == 0)
+		return csum;
 
+#ifdef __powerpc64__
 	res += (__force u64)addend;
 	return (__force __wsum)((u32)res + (res >> 32));
 #else
-- 
cgit v1.2.3


From ebb9d30a6a74f4ced5b7d35446ebb6362a724393 Mon Sep 17 00:00:00 2001
From: chenhui zhao <chenhui.zhao@freescale.com>
Date: Thu, 24 Dec 2015 08:39:57 +0800
Subject: powerpc/mm: any thread in one core can be the first to setup TLB1

On e6500, in the case of cpu hotplug, either thread in one core
may be the first thread initilzing the TLB1. The subsequent threads
must not setup it again.

The code is derived from the comment of Scott Wood.

Signed-off-by: Chenhui Zhao <chenhui.zhao@freescale.com>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/cputhreads.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index ba42e46ea58e..ea9623147b87 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -94,6 +94,14 @@ static inline int cpu_last_thread_sibling(int cpu)
 	return cpu | (threads_per_core - 1);
 }
 
+static inline u32 get_tensr(void)
+{
+#ifdef	CONFIG_BOOKE
+	if (cpu_has_feature(CPU_FTR_SMT))
+		return mfspr(SPRN_TENSR);
+#endif
+	return 1;
+}
 
 
 #endif /* _ASM_POWERPC_CPUTHREADS_H */
-- 
cgit v1.2.3


From e7affb1dba0e9068aeb3978e858f39753e0dc20a Mon Sep 17 00:00:00 2001
From: chenhui zhao <chenhui.zhao@freescale.com>
Date: Fri, 20 Nov 2015 17:13:58 +0800
Subject: powerpc/cache: add cache flush operation for various e500

Various e500 core have different cache architecture, so they
need different cache flush operations. Therefore, add a callback
function cpu_flush_caches to the struct cpu_spec. The cache flush
operation for the specific kind of e500 is selected at init time.
The callback function will flush all caches inside the current cpu.

Signed-off-by: Chenhui Zhao <chenhui.zhao@freescale.com>
Signed-off-by: Tang Yuantian <Yuantian.Tang@feescale.com>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/cacheflush.h | 2 --
 arch/powerpc/include/asm/cputable.h   | 8 ++++++++
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 6229e6b6037b..47add2e2364a 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -30,8 +30,6 @@ extern void flush_dcache_page(struct page *page);
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
-extern void __flush_disable_L1(void);
-
 extern void flush_icache_range(unsigned long, unsigned long);
 extern void flush_icache_user_range(struct vm_area_struct *vma,
 				    struct page *page, unsigned long addr,
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 94ace9b4c4e1..df4fb5faba43 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -43,6 +43,11 @@ extern int machine_check_e500(struct pt_regs *regs);
 extern int machine_check_e200(struct pt_regs *regs);
 extern int machine_check_47x(struct pt_regs *regs);
 
+extern void cpu_down_flush_e500v2(void);
+extern void cpu_down_flush_e500mc(void);
+extern void cpu_down_flush_e5500(void);
+extern void cpu_down_flush_e6500(void);
+
 /* NOTE WELL: Update identify_cpu() if fields are added or removed! */
 struct cpu_spec {
 	/* CPU is matched via (PVR & pvr_mask) == pvr_value */
@@ -59,6 +64,9 @@ struct cpu_spec {
 	unsigned int	icache_bsize;
 	unsigned int	dcache_bsize;
 
+	/* flush caches inside the current cpu */
+	void (*cpu_down_flush)(void);
+
 	/* number of performance monitor counters */
 	unsigned int	num_pmcs;
 	enum powerpc_pmc_type pmc_type;
-- 
cgit v1.2.3


From d17799f9c10e283cccd4d598d3416e6fac336ab9 Mon Sep 17 00:00:00 2001
From: chenhui zhao <chenhui.zhao@freescale.com>
Date: Fri, 20 Nov 2015 17:13:59 +0800
Subject: powerpc/rcpm: add RCPM driver

There is a RCPM (Run Control/Power Management) in Freescale QorIQ
series processors. The device performs tasks associated with device
run control and power management.

The driver implements some features: mask/unmask irq, enter/exit low
power states, freeze time base, etc.

Signed-off-by: Chenhui Zhao <chenhui.zhao@freescale.com>
Signed-off-by: Tang Yuantian <Yuantian.Tang@freescale.com>
[scottwood: remove __KERNEL__ ifdef]
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/cputhreads.h |  1 +
 arch/powerpc/include/asm/fsl_pm.h     | 51 +++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 arch/powerpc/include/asm/fsl_pm.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index ea9623147b87..81f5b338c76d 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -103,6 +103,7 @@ static inline u32 get_tensr(void)
 	return 1;
 }
 
+void book3e_stop_thread(int thread);
 
 #endif /* _ASM_POWERPC_CPUTHREADS_H */
 
diff --git a/arch/powerpc/include/asm/fsl_pm.h b/arch/powerpc/include/asm/fsl_pm.h
new file mode 100644
index 000000000000..47df55e36d4f
--- /dev/null
+++ b/arch/powerpc/include/asm/fsl_pm.h
@@ -0,0 +1,51 @@
+/*
+ * Support Power Management
+ *
+ * Copyright 2014-2015 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#ifndef __PPC_FSL_PM_H
+#define __PPC_FSL_PM_H
+
+#define E500_PM_PH10	1
+#define E500_PM_PH15	2
+#define E500_PM_PH20	3
+#define E500_PM_PH30	4
+#define E500_PM_DOZE	E500_PM_PH10
+#define E500_PM_NAP	E500_PM_PH15
+
+#define PLAT_PM_SLEEP	20
+#define PLAT_PM_LPM20	30
+
+#define FSL_PM_SLEEP		(1 << 0)
+#define FSL_PM_DEEP_SLEEP	(1 << 1)
+
+struct fsl_pm_ops {
+	/* mask pending interrupts to the RCPM from MPIC */
+	void (*irq_mask)(int cpu);
+
+	/* unmask pending interrupts to the RCPM from MPIC */
+	void (*irq_unmask)(int cpu);
+	void (*cpu_enter_state)(int cpu, int state);
+	void (*cpu_exit_state)(int cpu, int state);
+	void (*cpu_up_prepare)(int cpu);
+	void (*cpu_die)(int cpu);
+	int (*plat_enter_sleep)(void);
+	void (*freeze_time_base)(bool freeze);
+
+	/* keep the power of IP blocks during sleep/deep sleep */
+	void (*set_ip_power)(bool enable, u32 mask);
+
+	/* get platform supported power management modes */
+	unsigned int (*get_pm_modes)(void);
+};
+
+extern const struct fsl_pm_ops *qoriq_pm_ops;
+
+int __init fsl_rcpm_init(void);
+
+#endif /* __PPC_FSL_PM_H */
-- 
cgit v1.2.3


From 2f4f1f815bc6d03ea42d4f67dd1e284525e7524e Mon Sep 17 00:00:00 2001
From: chenhui zhao <chenhui.zhao@freescale.com>
Date: Fri, 20 Nov 2015 17:14:01 +0800
Subject: powerpc/mpc85xx: Add hotplug support on E5500 and E500MC cores

Freescale E500MC and E5500 core-based platforms, like P4080, T1040,
support disabling/enabling CPU dynamically.
This patch adds this feature on those platforms.

Signed-off-by: Chenhui Zhao <chenhui.zhao@freescale.com>
Signed-off-by: Tang Yuantian <Yuantian.Tang@feescale.com>
[scottwood: removed unused pr_fmt]
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/smp.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 825663c30945..bdb811116d85 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -67,6 +67,9 @@ void generic_cpu_die(unsigned int cpu);
 void generic_set_cpu_dead(unsigned int cpu);
 void generic_set_cpu_up(unsigned int cpu);
 int generic_check_cpu_restart(unsigned int cpu);
+int is_cpu_dead(unsigned int cpu);
+#else
+#define generic_set_cpu_up(i)	do { } while (0)
 #endif
 
 #ifdef CONFIG_PPC64
-- 
cgit v1.2.3


From 6becef7ea04a695f64299238fe13d41e41607469 Mon Sep 17 00:00:00 2001
From: chenhui zhao <chenhui.zhao@freescale.com>
Date: Fri, 20 Nov 2015 17:14:02 +0800
Subject: powerpc/mpc85xx: Add CPU hotplug support for E6500

Support Freescale E6500 core-based platforms, like t4240.
Support disabling/enabling individual CPU thread dynamically.

Signed-off-by: Chenhui Zhao <chenhui.zhao@freescale.com>
---
 arch/powerpc/include/asm/cputhreads.h | 6 ++++++
 arch/powerpc/include/asm/smp.h        | 1 +
 2 files changed, 7 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 81f5b338c76d..666bef4ebfae 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_POWERPC_CPUTHREADS_H
 #define _ASM_POWERPC_CPUTHREADS_H
 
+#ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 
 /*
@@ -103,7 +104,12 @@ static inline u32 get_tensr(void)
 	return 1;
 }
 
+void book3e_start_thread(int thread, unsigned long addr);
 void book3e_stop_thread(int thread);
 
+#endif /* __ASSEMBLY__ */
+
+#define INVALID_THREAD_HWID	0x0fff
+
 #endif /* _ASM_POWERPC_CPUTHREADS_H */
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index bdb811116d85..174271ef2767 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -200,6 +200,7 @@ extern void generic_secondary_thread_init(void);
 extern unsigned long __secondary_hold_spinloop;
 extern unsigned long __secondary_hold_acknowledge;
 extern char __secondary_hold;
+extern unsigned int booting_thread_hwid;
 
 extern void __early_start(void);
 #endif /* __ASSEMBLY__ */
-- 
cgit v1.2.3


From a5cab83cd3d2d75d3893276cb5f27e163484ef04 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:53 +1100
Subject: powerpc: Create a helper for getting the kernel toc value

Move the logic to work out the kernel toc pointer into a header. This is
a good cleanup, and also means we can use it elsewhere in future.

Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/sections.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index a5e930aca804..abf5866e08c6 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -22,6 +22,18 @@ static inline int in_kernel_text(unsigned long addr)
 	return 0;
 }
 
+static inline unsigned long kernel_toc_addr(void)
+{
+	/* Defined by the linker, see vmlinux.lds.S */
+	extern unsigned long __toc_start;
+
+	/*
+	 * The TOC register (r2) points 32kB into the TOC, so that 64kB of
+	 * the TOC can be addressed using a single machine instruction.
+	 */
+	return (unsigned long)(&__toc_start) + 0x8000UL;
+}
+
 static inline int overlaps_interrupt_vector_text(unsigned long start,
 							unsigned long end)
 {
-- 
cgit v1.2.3


From 136cd3450af8092f30d0e289806f08ac2aeee38f Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:54 +1100
Subject: powerpc/module: Only try to generate the ftrace_caller() stub once

Currently we generate the module stub for ftrace_caller() at the bottom
of apply_relocate_add(). However apply_relocate_add() is potentially
called more than once per module, which means we will try to generate
the ftrace_caller() stub multiple times.

Although the current code deals with that correctly, ie. it only
generates a stub the first time, it would be clearer to only try to
generate the stub once.

Note also on first reading it may appear that we generate a different
stub for each section that requires relocation, but that is not the
case. The code in stub_for_addr() that searches for an existing stub
uses sechdrs[me->arch.stubs_section], ie. the single stub section for
this module.

A cleaner approach is to only generate the ftrace_caller() stub once,
from module_finalize(). Although the original code didn't check to see
if the stub was actually generated correctly, it seems prudent to add a
check, so do that. And an additional benefit is we can clean the ifdefs
up a little.

Finally we must propagate the const'ness of some of the pointers passed
to module_finalize(), but that is also an improvement.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/module.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index dcfcad139bcc..74d25a749018 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -82,6 +82,15 @@ bool is_module_trampoline(u32 *insns);
 int module_trampoline_target(struct module *mod, u32 *trampoline,
 			     unsigned long *target);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs);
+#else
+static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
+{
+	return 0;
+}
+#endif
+
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);
-- 
cgit v1.2.3


From f17c4e01e906c568fb03a2e6c2b99e4ee4587fbf Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 3 Mar 2016 15:26:55 +1100
Subject: powerpc/module: Mark module stubs with a magic value

When a module is loaded, calls out to the kernel go via a stub which is
generated at runtime. One of these stubs is used to call _mcount(),
which is the default target of tracing calls generated by the compiler
with -pg.

If dynamic ftrace is enabled (which it typically is), another stub is
used to call ftrace_caller(), which is the target of tracing calls when
ftrace is actually active.

ftrace then wants to disable the calls to _mcount() at module startup,
and enable/disable the calls to ftrace_caller() when enabling/disabling
tracing - all of these it does by patching the code.

As part of that code patching, the ftrace code wants to confirm that the
branch it is about to modify, is in fact a call to a module stub which
calls _mcount() or ftrace_caller().

Currently it does that by inspecting the instructions and confirming
they are what it expects. Although that works, the code to do it is
pretty intricate because it requires lots of knowledge about the exact
format of the stub.

We can make that process easier by marking the generated stubs with a
magic value, and then looking for that magic value. Altough this is not
as rigorous as the current method, I believe it is sufficient in
practice.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/module.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 74d25a749018..5b6b5a427b54 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -78,8 +78,7 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
-bool is_module_trampoline(u32 *insns);
-int module_trampoline_target(struct module *mod, u32 *trampoline,
+int module_trampoline_target(struct module *mod, unsigned long trampoline,
 			     unsigned long *target);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-- 
cgit v1.2.3


From 153086644fd1fb07fb3af84d9f11542a19b1e8b6 Mon Sep 17 00:00:00 2001
From: Torsten Duwe <duwe@suse.de>
Date: Thu, 3 Mar 2016 15:26:59 +1100
Subject: powerpc/ftrace: Add support for -mprofile-kernel ftrace ABI

The gcc switch -mprofile-kernel defines a new ABI for calling _mcount()
very early in the function with minimal overhead.

Although mprofile-kernel has been available since GCC 3.4, there were
bugs which were only fixed recently. Currently it is known to work in
GCC 4.9, 5 and 6.

Additionally there are two possible code sequences generated by the
flag, the first uses mflr/std/bl and the second is optimised to omit the
std. Currently only gcc 6 has the optimised sequence. This patch
supports both sequences.

Initial work started by Vojtech Pavlik, used with permission.

Key changes:
 - rework _mcount() to work for both the old and new ABIs.
 - implement new versions of ftrace_caller() and ftrace_graph_caller()
   which deal with the new ABI.
 - updates to __ftrace_make_nop() to recognise the new mcount calling
   sequence.
 - updates to __ftrace_make_call() to recognise the nop'ed sequence.
 - implement ftrace_modify_call().
 - updates to the module loader to surpress the toc save in the module
   stub when calling mcount with the new ABI.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Torsten Duwe <duwe@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/code-patching.h | 21 +++++++++++++++++++++
 arch/powerpc/include/asm/ftrace.h        |  5 +++++
 2 files changed, 26 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 840a5509b3f1..994c60a857ce 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -99,4 +99,25 @@ static inline unsigned long ppc_global_function_entry(void *func)
 #endif
 }
 
+#ifdef CONFIG_PPC64
+/*
+ * Some instruction encodings commonly used in dynamic ftracing
+ * and function live patching.
+ */
+
+/* This must match the definition of STK_GOT in <asm/ppc_asm.h> */
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define R2_STACK_OFFSET         24
+#else
+#define R2_STACK_OFFSET         40
+#endif
+
+#define PPC_INST_LD_TOC		(PPC_INST_LD  | ___PPC_RT(__REG_R2) | \
+				 ___PPC_RA(__REG_R1) | R2_STACK_OFFSET)
+
+/* usually preceded by a mflr r0 */
+#define PPC_INST_STD_LR		(PPC_INST_STD | ___PPC_RS(__REG_R0) | \
+				 ___PPC_RA(__REG_R1) | PPC_LR_STKOFF)
+#endif /* CONFIG_PPC64 */
+
 #endif /* _ASM_POWERPC_CODE_PATCHING_H */
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index ef89b1465573..50ca7585abe2 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -46,6 +46,8 @@
 extern void _mcount(void);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+# define FTRACE_ADDR ((unsigned long)ftrace_caller)
+# define FTRACE_REGS_ADDR FTRACE_ADDR
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
        /* reloction of mcount call site is the same as the address */
@@ -58,6 +60,9 @@ struct dyn_arch_ftrace {
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#endif
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
-- 
cgit v1.2.3


From 39218cd00ebf08b16edf015adc363de42d9ad612 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Fri, 4 Mar 2016 10:53:07 +1100
Subject: powerpc/eeh: EEH device for VF

VFs and their corresponding pdn are created and released dynamically
when their PF's SRIOV capability is enabled and disabled. This creates
and releases EEH devices for VFs when creating and releasing their pdn
instances, which means EEH devices and pdn instances have same life
cycle. Also, VF's EEH device is identified by (struct eeh_dev::physfn).

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/eeh.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 867c39b45df6..574ed49a4a0d 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -141,6 +141,7 @@ struct eeh_dev {
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct pci_dn *pdn;		/* Associated PCI device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	struct pci_dev *physfn;		/* Associated SRIOV PF		*/
 	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
 
-- 
cgit v1.2.3


From c29fa27d26e3189009ba42786f0c0dce14a90940 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Fri, 4 Mar 2016 10:53:08 +1100
Subject: powerpc/eeh: Create PE for VFs

This creates PEs for VFs in the weak function pcibios_bus_add_device().
Those PEs for VFs are identified with newly introduced flag EEH_PE_VF
so that we treat them differently during EEH recovery.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/eeh.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 574ed49a4a0d..0c551a27e37d 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -72,6 +72,7 @@ struct pci_dn;
 #define EEH_PE_PHB	(1 << 1)	/* PHB PE    */
 #define EEH_PE_DEVICE 	(1 << 2)	/* Device PE */
 #define EEH_PE_BUS	(1 << 3)	/* Bus PE    */
+#define EEH_PE_VF	(1 << 4)	/* VF PE     */
 
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
-- 
cgit v1.2.3


From 9312bc5bab5907937db20c9f8c094d0c02dd78db Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Fri, 4 Mar 2016 10:53:09 +1100
Subject: powerpc/powernv: Support EEH reset for VF PE

PEs for VFs don't have primary bus. So they have to have their own reset
backend, which is used during EEH recovery. The patch implements the reset
backend for VF's PE by issuing FLR or AF FLR to the VFs, which are contained
in the PE.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/eeh.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 0c551a27e37d..b5b5f45dfb0a 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -137,6 +137,7 @@ struct eeh_dev {
 	int pcix_cap;			/* Saved PCIx capability	*/
 	int pcie_cap;			/* Saved PCIe capability	*/
 	int aer_cap;			/* Saved AER capability		*/
+	int af_cap;			/* Saved AF capability		*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
-- 
cgit v1.2.3


From 0dc2830e0a48d520c7db7cc55dbbd0edefac02f5 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Fri, 4 Mar 2016 10:53:10 +1100
Subject: powerpc/powernv: Support PCI config restore for VFs

After PE reset, OPAL API opal_pci_reinit() is called on all devices
contained in the PE to reinitialize them. While skiboot is not aware of
VFs, we have to implement the function in kernel to reinitialize VFs after
reset on PE for VFs.

In this patch, two functions pnv_pci_fixup_vf_mps() and
pnv_eeh_restore_vf_config() both manipulate the MPS of the VF, since for a
VF it has three cases.

1. Normal creation for a VF
   In this case, pnv_pci_fixup_vf_mps() is called to make the MPS a proper
   value compared with its parent.
2. EEH recovery without VF removed
   In this case, MPS is stored in pci_dn and pnv_eeh_restore_vf_config() is
   called to restore it and reinitialize other part.
3. EEH recovery with VF removed
   In this case, VF will be removed then re-created. Both functions are
   called. First pnv_pci_fixup_vf_mps() is called to store the proper MPS
   to pci_dn and then pnv_eeh_restore_vf_config() is called to do proper
   thing.

This introduces two functions: pnv_pci_fixup_vf_mps() to fixup the VF's
MPS to make sure it is equal to parent's and store this value in pci_dn
for future use. pnv_eeh_restore_vf_config() to re-initialize on VF by
restoring MPS, disabling completion timeout, enabling SERR, etc.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/pci-bridge.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index b0b43f5fbc5f..f4d17587fa31 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -220,6 +220,7 @@ struct pci_dn {
 #define IODA_INVALID_M64        (-1)
 	int     (*m64_map)[PCI_SRIOV_NUM_BARS];
 #endif /* CONFIG_PCI_IOV */
+	int	mps;			/* Maximum Payload Size */
 #endif
 	struct list_head child_list;
 	struct list_head list;
-- 
cgit v1.2.3


From 67086e32b56481531ab1292b284e074b1a8d764c Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Fri, 4 Mar 2016 10:53:11 +1100
Subject: powerpc/eeh: powerpc/eeh: Support error recovery for VF PE

PFs are enumerated on PCI bus, while VFs are created by PF's driver.

In EEH recovery, it has two cases:
1. Device and driver is EEH aware, error handlers are called.
2. Device and driver is not EEH aware, un-plug the device and plug it again
by enumerating it.

The special thing happens on the second case. For a PF, we could use the
original pci core to enumerate the bus, while for VF we need to record the
VFs which aer un-plugged then plug it again.

Also The patch caches the VF index in pci_dn, which can be used to
calculate VF's bus, device and function number. Those information helps to
locate the VF's PCI device instance when doing hotplug during EEH recovery
if necessary.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/eeh.h        | 2 ++
 arch/powerpc/include/asm/pci-bridge.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index b5b5f45dfb0a..fb9f376ae27b 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -140,9 +140,11 @@ struct eeh_dev {
 	int af_cap;			/* Saved AF capability		*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
+	struct list_head rmv_list;	/* Record the removed edevs	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct pci_dn *pdn;		/* Associated PCI device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	bool in_error;			/* Error flag for edev		*/
 	struct pci_dev *physfn;		/* Associated SRIOV PF		*/
 	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index f4d17587fa31..9f165e8a77bf 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -212,6 +212,7 @@ struct pci_dn {
 #define IODA_INVALID_PE		(-1)
 #ifdef CONFIG_PPC_POWERNV
 	int	pe_number;
+	int     vf_index;		/* VF index in the PF */
 #ifdef CONFIG_PCI_IOV
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
-- 
cgit v1.2.3


From c0efa9aee8504ce16250320c1e5464bdb7e24400 Mon Sep 17 00:00:00 2001
From: Christophe Lombard <clombard@linux.vnet.ibm.com>
Date: Fri, 4 Mar 2016 12:26:33 +0100
Subject: powerpc: New possible return value from hcall

The hcalls introduced for cxl use a possible new value:
H_STATE (invalid state).

Co-authored-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
Reviewed-by: Manoj Kumar <manoj@linux.vnet.ibm.com>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/hvcall.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index e3b54dd4f730..0bc9c284aa10 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -94,6 +94,7 @@
 #define H_SG_LIST	-72
 #define H_OP_MODE	-73
 #define H_COP_HW	-74
+#define H_STATE		-75
 #define H_UNSUPPORTED_FLAG_START	-256
 #define H_UNSUPPORTED_FLAG_END		-511
 #define H_MULTI_THREADS_ACTIVE	-9005
-- 
cgit v1.2.3


From 7e393220b6e1ecfa5520d1b2ca31150b7588f458 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Mon, 7 Mar 2016 18:44:37 +0100
Subject: powerpc: optimise csum_partial() call when len is constant

csum_partial is often called for small fixed length packets
for which it is suboptimal to use the generic csum_partial()
function.

For instance, in my configuration, I got:
* One place calling it with constant len 4
* Seven places calling it with constant len 8
* Three places calling it with constant len 14
* One place calling it with constant len 20
* One place calling it with constant len 24
* One place calling it with constant len 32

This patch renames csum_partial() to __csum_partial() and
implements csum_partial() as a wrapper inline function which
* uses csum_add() for small 16bits multiple constant length
* uses ip_fast_csum() for other 32bits multiple constant
* uses __csum_partial() in all other cases

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/checksum.h | 79 ++++++++++++++++++++++++++-----------
 1 file changed, 56 insertions(+), 23 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 74cd8d82628a..ee655ed1ff1b 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -12,20 +12,6 @@
 #ifdef CONFIG_GENERIC_CSUM
 #include <asm-generic/checksum.h>
 #else
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-extern __wsum csum_partial(const void *buff, int len, __wsum sum);
-
 /*
  * Computes the checksum of a memory block at src, length len,
  * and adds in "sum" (32-bit), while copying the block to dst.
@@ -67,15 +53,6 @@ static inline __sum16 csum_fold(__wsum sum)
 	return (__force __sum16)(~((__force u32)sum + tmp) >> 16);
 }
 
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-static inline __sum16 ip_compute_csum(const void *buff, int len)
-{
-	return csum_fold(csum_partial(buff, len, 0));
-}
-
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
                                      unsigned short len,
                                      unsigned short proto,
@@ -174,6 +151,62 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	return csum_fold(ip_fast_csum_nofold(iph, ihl));
 }
 
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum __csum_partial(const void *buff, int len, __wsum sum);
+
+static inline __wsum csum_partial(const void *buff, int len, __wsum sum)
+{
+	if (__builtin_constant_p(len) && len <= 16 && (len & 1) == 0) {
+		if (len == 2)
+			sum = csum_add(sum, (__force __wsum)*(const u16 *)buff);
+		if (len >= 4)
+			sum = csum_add(sum, (__force __wsum)*(const u32 *)buff);
+		if (len == 6)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u16 *)(buff + 4));
+		if (len >= 8)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u32 *)(buff + 4));
+		if (len == 10)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u16 *)(buff + 8));
+		if (len >= 12)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u32 *)(buff + 8));
+		if (len == 14)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u16 *)(buff + 12));
+		if (len >= 16)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u32 *)(buff + 12));
+	} else if (__builtin_constant_p(len) && (len & 3) == 0) {
+		sum = csum_add(sum, ip_fast_csum_nofold(buff, len >> 2));
+	} else {
+		sum = __csum_partial(buff, len, sum);
+	}
+	return sum;
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+static inline __sum16 ip_compute_csum(const void *buff, int len)
+{
+	return csum_fold(csum_partial(buff, len, 0));
+}
+
 #endif
 #endif /* __KERNEL__ */
 #endif
-- 
cgit v1.2.3


From d4969e2459c6e852a6862256cf8e869aaa3e8adf Mon Sep 17 00:00:00 2001
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Date: Mon, 11 Jan 2016 14:55:25 -0800
Subject: powerpc/perf: Remove PME_ prefix for power7 events

We used the PME_ prefix earlier to avoid some macro/variable name
collisions.  We have since changed the way we define/use the event
macros so we no longer need the prefix.

By dropping the prefix, we keep the the event macros consistent with
their official names.

Reported-by: Michael Ellerman <ellerman@au1.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/perf_event_server.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 814622146d5a..069108717163 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -141,7 +141,7 @@ extern ssize_t power_events_sysfs_show(struct device *dev,
 #define	EVENT_PTR(_id, _suffix)		&EVENT_VAR(_id, _suffix).attr.attr
 
 #define	EVENT_ATTR(_name, _id, _suffix)					\
-	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id,	\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), _id,		\
 			power_events_sysfs_show)
 
 #define	GENERIC_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _g)
-- 
cgit v1.2.3


From e0728b50d480da6be228dd160a43b37e4c0b1636 Mon Sep 17 00:00:00 2001
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Date: Mon, 11 Jan 2016 14:55:26 -0800
Subject: powerpc/perf: Export Power8 generic and cache events to sysfs

Power8 supports a large number of events in each susbystem so when a
user runs:

	perf stat -e branch-instructions sleep 1
	perf stat -e L1-dcache-loads sleep 1

it is not clear as to which PMU events were monitored.

Export the generic hardware and cache perf events for Power8 to sysfs,
so users can precisely determine the PMU event monitored by the generic
event.

Eg:
	cat /sys/bus/event_source/devices/cpu/events/branch-instructions
	event=0x10068

	$ cat /sys/bus/event_source/devices/cpu/events/L1-dcache-loads
	event=0x100ee

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/perf_event_server.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 069108717163..e157489ee7a1 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -136,6 +136,11 @@ extern ssize_t power_events_sysfs_show(struct device *dev,
  * event 'cpu-cycles' can have two entries in sysfs: 'cpu-cycles' and
  * 'PM_CYC' where the latter is the name by which the event is known in
  * POWER CPU specification.
+ *
+ * Similarly, some hardware and cache events use the same event code. Eg.
+ * on POWER8, both "cache-references" and "L1-dcache-loads" events refer
+ * to the same event, PM_LD_REF_L1.  The suffix, allows us to have two
+ * sysfs objects for the same event and thus two entries/aliases in sysfs.
  */
 #define	EVENT_VAR(_id, _suffix)		event_attr_##_id##_suffix
 #define	EVENT_PTR(_id, _suffix)		&EVENT_VAR(_id, _suffix).attr.attr
@@ -147,5 +152,8 @@ extern ssize_t power_events_sysfs_show(struct device *dev,
 #define	GENERIC_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _g)
 #define	GENERIC_EVENT_PTR(_id)		EVENT_PTR(_id, _g)
 
+#define	CACHE_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _c)
+#define	CACHE_EVENT_PTR(_id)		EVENT_PTR(_id, _c)
+
 #define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _p)
 #define	POWER_EVENT_PTR(_id)		EVENT_PTR(_id, _p)
-- 
cgit v1.2.3


From be00ed728c32ed8311d5191637067c9eaf0fca4b Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:07:56 +0100
Subject: powerpc32: Fix pte_offset_kernel() to return NULL for bad pages

The fixmap related functions try to map kernel pages that are
already mapped through Large TLBs. pte_offset_kernel() has to
return NULL for LTLBs, otherwise the caller will try to access
level 2 table which doesn't exist

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/nohash/32/pgtable.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index c82cbf52d19e..e2016007c04e 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -309,7 +309,8 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pte_index(address)		\
 	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 #define pte_offset_kernel(dir, addr)	\
-	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
+	(pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \
+				  pte_index(addr))
 #define pte_offset_map(dir, addr)		\
 	((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
 #define pte_unmap(pte)		kunmap_atomic(pte)
-- 
cgit v1.2.3


From e974cd4be0be8de0d370ee4dbf181d614c0de386 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:10 +0100
Subject: powerpc32: remove ioremap_base

ioremap_base is not initialised and is nowhere used so remove it

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/nohash/32/pgtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index e2016007c04e..780847597514 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -86,7 +86,7 @@ extern int icache_44x_need_flush;
  * We no longer map larger than phys RAM with the BATs so we don't have
  * to worry about the VMALLOC_OFFSET causing problems.  We do have to worry
  * about clashes between our early calls to ioremap() that start growing down
- * from ioremap_base being run into the VM area allocations (growing upwards
+ * from IOREMAP_TOP being run into the VM area allocations (growing upwards
  * from VMALLOC_START).  For this reason we have ioremap_bot to check when
  * we actually run into our mappings setup in the early boot with the VM
  * system.  This really does become a problem for machines with good amounts
-- 
cgit v1.2.3


From 7ee5cf6bfad7990cc33d10888d869c1eb7d4a927 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:12 +0100
Subject: powerpc/8xx: Add missing SPRN defines into reg_8xx.h

Add missing SPRN defines into reg_8xx.h
Some of them are defined in mmu-8xx.h, so we include mmu-8xx.h in
reg_8xx.h, for that we remove references to PAGE_SHIFT in mmu-8xx.h
to have it self sufficient, as includers of reg_8xx.h don't all
include asm/page.h

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/mmu-8xx.h |  4 ++--
 arch/powerpc/include/asm/reg_8xx.h | 11 +++++++++++
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index f05500a29a60..0a566f15f985 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -171,9 +171,9 @@ typedef struct {
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */
 
-#if (PAGE_SHIFT == 12)
+#if defined(CONFIG_PPC_4K_PAGES)
 #define mmu_virtual_psize	MMU_PAGE_4K
-#elif (PAGE_SHIFT == 14)
+#elif defined(CONFIG_PPC_16K_PAGES)
 #define mmu_virtual_psize	MMU_PAGE_16K
 #else
 #error "Unsupported PAGE_SIZE"
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index e8ea346b21d3..0f71c811a841 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -4,6 +4,8 @@
 #ifndef _ASM_POWERPC_REG_8xx_H
 #define _ASM_POWERPC_REG_8xx_H
 
+#include <asm/mmu-8xx.h>
+
 /* Cache control on the MPC8xx is provided through some additional
  * special purpose registers.
  */
@@ -14,6 +16,15 @@
 #define SPRN_DC_ADR	569	/* Address needed for some commands */
 #define SPRN_DC_DAT	570	/* Read-only data register */
 
+/* Misc Debug */
+#define SPRN_DPDR	630
+#define SPRN_MI_CAM	816
+#define SPRN_MI_RAM0	817
+#define SPRN_MI_RAM1	818
+#define SPRN_MD_CAM	824
+#define SPRN_MD_RAM0	825
+#define SPRN_MD_RAM1	826
+
 /* Commands.  Only the first few are available to the instruction cache.
 */
 #define	IDC_ENABLE	0x02000000	/* Cache enable */
-- 
cgit v1.2.3


From 1458dd951f7cc0127508f928497c9ab06b5e557d Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:14 +0100
Subject: powerpc/8xx: Handle CPU6 ERRATA directly in mtspr() macro

MPC8xx has an ERRATA on the use of mtspr() for some registers
This patch includes the ERRATA handling directly into mtspr() macro
so that mtspr() users don't need to bother about that errata

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/reg.h     |  2 +
 arch/powerpc/include/asm/reg_8xx.h | 82 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 52ed654d01ba..f5f4c66bbbc9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1219,9 +1219,11 @@ static inline void mtmsr_isync(unsigned long val)
 #define mfspr(rn)	({unsigned long rval; \
 			asm volatile("mfspr %0," __stringify(rn) \
 				: "=r" (rval)); rval;})
+#ifndef mtspr
 #define mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" : \
 				     : "r" ((unsigned long)(v)) \
 				     : "memory")
+#endif
 
 extern void msr_check_and_set(unsigned long bits);
 extern bool strict_msr_control;
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index 0f71c811a841..d41412c7748b 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -50,4 +50,86 @@
 #define DC_DFWT		0x40000000	/* Data cache is forced write through */
 #define DC_LES		0x20000000	/* Caches are little endian mode */
 
+#ifdef CONFIG_8xx_CPU6
+#define do_mtspr_cpu6(rn, rn_addr, v)	\
+	do {								\
+		int _reg_cpu6 = rn_addr, _tmp_cpu6[1];		\
+		asm volatile("stw %0, %1;"				\
+			     "lwz %0, %1;"				\
+			     "mtspr " __stringify(rn) ",%2" :		\
+			     : "r" (_reg_cpu6), "m"(_tmp_cpu6),		\
+			       "r" ((unsigned long)(v))			\
+			     : "memory");				\
+	} while (0)
+
+#define do_mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" :	\
+				     : "r" ((unsigned long)(v))		\
+				     : "memory")
+#define mtspr(rn, v) \
+	do {								\
+		if (rn == SPRN_IMMR)					\
+			do_mtspr_cpu6(rn, 0x3d30, v);			\
+		else if (rn == SPRN_IC_CST)				\
+			do_mtspr_cpu6(rn, 0x2110, v);			\
+		else if (rn == SPRN_IC_ADR)				\
+			do_mtspr_cpu6(rn, 0x2310, v);			\
+		else if (rn == SPRN_IC_DAT)				\
+			do_mtspr_cpu6(rn, 0x2510, v);			\
+		else if (rn == SPRN_DC_CST)				\
+			do_mtspr_cpu6(rn, 0x3110, v);			\
+		else if (rn == SPRN_DC_ADR)				\
+			do_mtspr_cpu6(rn, 0x3310, v);			\
+		else if (rn == SPRN_DC_DAT)				\
+			do_mtspr_cpu6(rn, 0x3510, v);			\
+		else if (rn == SPRN_MI_CTR)				\
+			do_mtspr_cpu6(rn, 0x2180, v);			\
+		else if (rn == SPRN_MI_AP)				\
+			do_mtspr_cpu6(rn, 0x2580, v);			\
+		else if (rn == SPRN_MI_EPN)				\
+			do_mtspr_cpu6(rn, 0x2780, v);			\
+		else if (rn == SPRN_MI_TWC)				\
+			do_mtspr_cpu6(rn, 0x2b80, v);			\
+		else if (rn == SPRN_MI_RPN)				\
+			do_mtspr_cpu6(rn, 0x2d80, v);			\
+		else if (rn == SPRN_MI_CAM)				\
+			do_mtspr_cpu6(rn, 0x2190, v);			\
+		else if (rn == SPRN_MI_RAM0)				\
+			do_mtspr_cpu6(rn, 0x2390, v);			\
+		else if (rn == SPRN_MI_RAM1)				\
+			do_mtspr_cpu6(rn, 0x2590, v);			\
+		else if (rn == SPRN_MD_CTR)				\
+			do_mtspr_cpu6(rn, 0x3180, v);			\
+		else if (rn == SPRN_M_CASID)				\
+			do_mtspr_cpu6(rn, 0x3380, v);			\
+		else if (rn == SPRN_MD_AP)				\
+			do_mtspr_cpu6(rn, 0x3580, v);			\
+		else if (rn == SPRN_MD_EPN)				\
+			do_mtspr_cpu6(rn, 0x3780, v);			\
+		else if (rn == SPRN_M_TWB)				\
+			do_mtspr_cpu6(rn, 0x3980, v);			\
+		else if (rn == SPRN_MD_TWC)				\
+			do_mtspr_cpu6(rn, 0x3b80, v);			\
+		else if (rn == SPRN_MD_RPN)				\
+			do_mtspr_cpu6(rn, 0x3d80, v);			\
+		else if (rn == SPRN_M_TW)				\
+			do_mtspr_cpu6(rn, 0x3f80, v);			\
+		else if (rn == SPRN_MD_CAM)				\
+			do_mtspr_cpu6(rn, 0x3190, v);			\
+		else if (rn == SPRN_MD_RAM0)				\
+			do_mtspr_cpu6(rn, 0x3390, v);			\
+		else if (rn == SPRN_MD_RAM1)				\
+			do_mtspr_cpu6(rn, 0x3590, v);			\
+		else if (rn == SPRN_DEC)				\
+			do_mtspr_cpu6(rn, 0x2c00, v);			\
+		else if (rn == SPRN_TBWL)				\
+			do_mtspr_cpu6(rn, 0x3880, v);			\
+		else if (rn == SPRN_TBWU)				\
+			do_mtspr_cpu6(rn, 0x3a80, v);			\
+		else if (rn == SPRN_DPDR)				\
+			do_mtspr_cpu6(rn, 0x2d30, v);			\
+		else							\
+			do_mtspr(rn, v);				\
+	} while (0)
+#endif
+
 #endif /* _ASM_POWERPC_REG_8xx_H */
-- 
cgit v1.2.3


From 63e9e1c28fa6fe714364c7817e60dbaed3cec95e Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:16 +0100
Subject: powerpc/8xx: remove special handling of CPU6 errata in set_dec()

CPU6 ERRATA is now handled directly in mtspr(), so we can use the
standard set_dec() fonction in all cases.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/time.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 2d7109a8d296..1092fdd7e737 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -31,8 +31,6 @@ extern void tick_broadcast_ipi_handler(void);
 
 extern void generic_calibrate_decr(void);
 
-extern void set_dec_cpu6(unsigned int val);
-
 /* Some sane defaults: 125 MHz timebase, 1GHz processor */
 extern unsigned long ppc_proc_freq;
 #define DEFAULT_PROC_FREQ	(DEFAULT_TB_FREQ * 8)
@@ -166,14 +164,12 @@ static inline void set_dec(int val)
 {
 #if defined(CONFIG_40x)
 	mtspr(SPRN_PIT, val);
-#elif defined(CONFIG_8xx_CPU6)
-	set_dec_cpu6(val - 1);
 #else
 #ifndef CONFIG_BOOKE
 	--val;
 #endif
 	mtspr(SPRN_DEC, val);
-#endif /* not 40x or 8xx_CPU6 */
+#endif /* not 40x */
 }
 
 static inline unsigned long tb_ticks_since(unsigned long tstamp)
-- 
cgit v1.2.3


From d6bfa02fccf58b957f457c1bd0bb71f6ab169a0b Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:23 +0100
Subject: powerpc: add inline functions for cache related instructions

This patch adds inline functions to use dcbz, dcbi, dcbf, dcbst
from C functions

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/cache.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 5f8229e24fe6..ffbafbf76b19 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -69,6 +69,25 @@ extern void _set_L3CR(unsigned long);
 #define _set_L3CR(val)	do { } while(0)
 #endif
 
+static inline void dcbz(void *addr)
+{
+	__asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void dcbi(void *addr)
+{
+	__asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void dcbf(void *addr)
+{
+	__asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void dcbst(void *addr)
+{
+	__asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory");
+}
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_CACHE_H */
-- 
cgit v1.2.3


From 5736f96d12dd4204d3aac43bf7b512ab434b904f Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:25 +0100
Subject: powerpc32: Remove clear_pages() and define clear_page() inline

clear_pages() is never used expect by clear_page, and PPC32 is the
only architecture (still) having this function. Neither PPC64 nor
any other architecture has it.

This patch removes clear_pages() and moves clear_page() function
inline (same as PPC64) as it only is a few isns

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/page_32.h | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h
index 68d73b2a7bfc..6a8e1797f223 100644
--- a/arch/powerpc/include/asm/page_32.h
+++ b/arch/powerpc/include/asm/page_32.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_POWERPC_PAGE_32_H
 #define _ASM_POWERPC_PAGE_32_H
 
+#include <asm/cache.h>
+
 #if defined(CONFIG_PHYSICAL_ALIGN) && (CONFIG_PHYSICAL_START != 0)
 #if (CONFIG_PHYSICAL_START % CONFIG_PHYSICAL_ALIGN) != 0
 #error "CONFIG_PHYSICAL_START must be a multiple of CONFIG_PHYSICAL_ALIGN"
@@ -36,9 +38,18 @@ typedef unsigned long long pte_basic_t;
 typedef unsigned long pte_basic_t;
 #endif
 
-struct page;
-extern void clear_pages(void *page, int order);
-static inline void clear_page(void *page) { clear_pages(page, 0); }
+/*
+ * Clear page using the dcbz instruction, which doesn't cause any
+ * memory traffic (except to write out any cache lines which get
+ * displaced).  This only works on cacheable memory.
+ */
+static inline void clear_page(void *addr)
+{
+	unsigned int i;
+
+	for (i = 0; i < PAGE_SIZE / L1_CACHE_BYTES; i++, addr += L1_CACHE_BYTES)
+		dcbz(addr);
+}
 extern void copy_page(void *to, void *from);
 
 #include <asm-generic/getorder.h>
-- 
cgit v1.2.3


From affe587bacf48e328fb8d4c5ef9007b9c555b128 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 9 Feb 2016 17:08:27 +0100
Subject: powerpc32: move xxxxx_dcache_range() functions inline

flush/clean/invalidate _dcache_range() functions are all very
similar and are quite short. They are mainly used in __dma_sync()
perf_event locate them in the top 3 consumming functions during
heavy ethernet activity

They are good candidate for inlining, as __dma_sync() does
almost nothing but calling them

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>
---
 arch/powerpc/include/asm/cacheflush.h | 52 +++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 47add2e2364a..69fb16d7a811 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -45,12 +45,58 @@ static inline void __flush_dcache_icache_phys(unsigned long physaddr)
 }
 #endif
 
-extern void flush_dcache_range(unsigned long start, unsigned long stop);
 #ifdef CONFIG_PPC32
-extern void clean_dcache_range(unsigned long start, unsigned long stop);
-extern void invalidate_dcache_range(unsigned long start, unsigned long stop);
+/*
+ * Write any modified data cache blocks out to memory and invalidate them.
+ * Does not invalidate the corresponding instruction cache blocks.
+ */
+static inline void flush_dcache_range(unsigned long start, unsigned long stop)
+{
+	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
+	unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+		dcbf(addr);
+	mb();	/* sync */
+}
+
+/*
+ * Write any modified data cache blocks out to memory.
+ * Does not invalidate the corresponding cache lines (especially for
+ * any corresponding instruction cache).
+ */
+static inline void clean_dcache_range(unsigned long start, unsigned long stop)
+{
+	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
+	unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+		dcbst(addr);
+	mb();	/* sync */
+}
+
+/*
+ * Like above, but invalidate the D-cache.  This is used by the 8xx
+ * to invalidate the cache so the PPC core doesn't get stale data
+ * from the CPM (no cache snooping here :-).
+ */
+static inline void invalidate_dcache_range(unsigned long start,
+					   unsigned long stop)
+{
+	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
+	unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+		dcbi(addr);
+	mb();	/* sync */
+}
+
 #endif /* CONFIG_PPC32 */
 #ifdef CONFIG_PPC64
+extern void flush_dcache_range(unsigned long start, unsigned long stop);
 extern void flush_inval_dcache_range(unsigned long start, unsigned long stop);
 extern void flush_dcache_phys_range(unsigned long start, unsigned long stop);
 #endif
-- 
cgit v1.2.3


From 2e098dcee6208a690f73e11feb29d181cae7d978 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Tue, 15 Mar 2016 14:07:49 +0100
Subject: powerpc/8xx: Fix do_mtspr_cpu6() build on older compilers

GCC < 4.9 is unable to build this, saying:

  arch/powerpc/mm/8xx_mmu.c:139:2: error: memory input 1 is not directly addressable

Change the one-element array into a simple variable to avoid this.

Fixes: 1458dd951f7c ("powerpc/8xx: Handle CPU6 ERRATA directly in mtspr() macro")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Scott Wood <oss@buserror.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/reg_8xx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index d41412c7748b..94d01f81e668 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -53,7 +53,7 @@
 #ifdef CONFIG_8xx_CPU6
 #define do_mtspr_cpu6(rn, rn_addr, v)	\
 	do {								\
-		int _reg_cpu6 = rn_addr, _tmp_cpu6[1];		\
+		int _reg_cpu6 = rn_addr, _tmp_cpu6;		\
 		asm volatile("stw %0, %1;"				\
 			     "lwz %0, %1;"				\
 			     "mtspr " __stringify(rn) ",%2" :		\
-- 
cgit v1.2.3