Merge tag 'powerpc-4.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for STRICT_KERNEL_RWX on 64-bit server CPUs.

   - Platform support for FSP2 (476fpe) board

   - Enable ZONE_DEVICE on 64-bit server CPUs.

   - Generic & powerpc spin loop primitives to optimise busy waiting

   - Convert VDSO update function to use new update_vsyscall() interface

   - Optimisations to hypercall/syscall/context-switch paths

   - Improvements to the CPU idle code on Power8 and Power9.

  As well as many other fixes and improvements.

  Thanks to: Akshay Adiga, Andrew Donnellan, Andrew Jeffery, Anshuman
  Khandual, Anton Blanchard, Balbir Singh, Benjamin Herrenschmidt,
  Christophe Leroy, Christophe Lombard, Colin Ian King, Dan Carpenter,
  Gautham R. Shenoy, Hari Bathini, Ian Munsie, Ivan Mikhaylov, Javier
  Martinez Canillas, Madhavan Srinivasan, Masahiro Yamada, Matt Brown,
  Michael Neuling, Michal Suchanek, Murilo Opsfelder Araujo, Naveen N.
  Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pavel Machek,
  Russell Currey, Santosh Sivaraj, Stephen Rothwell, Thiago Jung
  Bauermann, Yang Li"

* tag 'powerpc-4.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (158 commits)
  powerpc/Kconfig: Enable STRICT_KERNEL_RWX for some configs
  powerpc/mm/radix: Implement STRICT_RWX/mark_rodata_ro() for Radix
  powerpc/mm/hash: Implement mark_rodata_ro() for hash
  powerpc/vmlinux.lds: Align __init_begin to 16M
  powerpc/lib/code-patching: Use alternate map for patch_instruction()
  powerpc/xmon: Add patch_instruction() support for xmon
  powerpc/kprobes/optprobes: Use patch_instruction()
  powerpc/kprobes: Move kprobes over to patch_instruction()
  powerpc/mm/radix: Fix execute permissions for interrupt_vectors
  powerpc/pseries: Fix passing of pp0 in updatepp() and updateboltedpp()
  powerpc/64s: Blacklist rtas entry/exit from kprobes
  powerpc/64s: Blacklist functions invoked on a trap
  powerpc/64s: Un-blacklist system_call() from kprobes
  powerpc/64s: Move system_call() symbol to just after setting MSR_EE
  powerpc/64s: Blacklist system_call() and system_call_common() from kprobes
  powerpc/64s: Convert .L__replay_interrupt_return to a local label
  powerpc64/elfv1: Only dereference function descriptor for non-text symbols
  cxl: Export library to support IBM XSL
  powerpc/dts: Use #include "..." to include local DT
  powerpc/perf/hv-24x7: Aggregate result elements on POWER9 SMT8
  ...

27 files changed, 374 insertions, 135 deletions

diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index c0deafc212b8..25d42bd3f114 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -74,6 +74,11 @@ do {									\
 	___p1;								\
 })
 
+/*
+ * This must resolve to hwsync on SMP for the context switch path.
+ * See _switch, and core scheduler context switch memory ordering
+ * comments.
+ */
 #define smp_mb__before_spinlock()   smp_mb()
 
 #include <asm-generic/barrier.h>
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 33a24fdd7958..b750ffef83c7 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -206,68 +206,13 @@ static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr)
  * Return the zero-based bit position (LE, not IBM bit numbering) of
  * the most significant 1-bit in a double word.
  */
-static __inline__ __attribute__((const))
-int __ilog2(unsigned long x)
-{
-	int lz;
+#define __ilog2(x)	ilog2(x)
 
-	asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x));
-	return BITS_PER_LONG - 1 - lz;
-}
+#include <asm-generic/bitops/ffz.h>
 
-static inline __attribute__((const))
-int __ilog2_u32(u32 n)
-{
-	int bit;
-	asm ("cntlzw %0,%1" : "=r" (bit) : "r" (n));
-	return 31 - bit;
-}
+#include <asm-generic/bitops/builtin-__ffs.h>
 
-#ifdef __powerpc64__
-static inline __attribute__((const))
-int __ilog2_u64(u64 n)
-{
-	int bit;
-	asm ("cntlzd %0,%1" : "=r" (bit) : "r" (n));
-	return 63 - bit;
-}
-#endif
-
-/*
- * Determines the bit position of the least significant 0 bit in the
- * specified double word. The returned bit position will be
- * zero-based, starting from the right side (63/31 - 0).
- */
-static __inline__ unsigned long ffz(unsigned long x)
-{
-	/* no zero exists anywhere in the 8 byte area. */
-	if ((x = ~x) == 0)
-		return BITS_PER_LONG;
-
-	/*
-	 * Calculate the bit position of the least significant '1' bit in x
-	 * (since x has been changed this will actually be the least significant
-	 * '0' bit in * the original x).  Note: (x & -x) gives us a mask that
-	 * is the least significant * (RIGHT-most) 1-bit of the value in x.
-	 */
-	return __ilog2(x & -x);
-}
-
-static __inline__ unsigned long __ffs(unsigned long x)
-{
-	return __ilog2(x & -x);
-}
-
-/*
- * ffs: find first bit set. This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- */
-static __inline__ int ffs(int x)
-{
-	unsigned long i = (unsigned long)x;
-	return __ilog2(i & -i) + 1;
-}
+#include <asm-generic/bitops/builtin-ffs.h>
 
 /*
  * fls: find last (most-significant) bit set.
@@ -275,33 +220,15 @@ static __inline__ int ffs(int x)
  */
 static __inline__ int fls(unsigned int x)
 {
-	int lz;
-
-	asm ("cntlzw %0,%1" : "=r" (lz) : "r" (x));
-	return 32 - lz;
+	return 32 - __builtin_clz(x);
 }
 
-static __inline__ unsigned long __fls(unsigned long x)
-{
-	return __ilog2(x);
-}
+#include <asm-generic/bitops/builtin-__fls.h>
 
-/*
- * 64-bit can do this using one cntlzd (count leading zeroes doubleword)
- * instruction; for 32-bit we use the generic version, which does two
- * 32-bit fls calls.
- */
-#ifdef __powerpc64__
 static __inline__ int fls64(__u64 x)
 {
-	int lz;
-
-	asm ("cntlzd %0,%1" : "=r" (lz) : "r" (x));
-	return 64 - lz;
+	return 64 - __builtin_clzll(x);
 }
-#else
-#include <asm-generic/bitops/fls64.h>
-#endif /* __powerpc64__ */
 
 #ifdef CONFIG_PPC64
 unsigned int __arch_hweight8(unsigned int w);
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index d310546e5d9d..a120e7f8d535 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -31,7 +31,8 @@ extern struct kmem_cache *pgtable_cache[];
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+			pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 26ed228d4dc6..7fb755880409 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -297,6 +297,8 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
+int map_kernel_page(unsigned long va, phys_addr_t pa, int flags);
+
 /* Generic accessors to PTE bits */
 static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
 static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 4e957b027fe0..0ce513f2926f 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -89,6 +89,9 @@ static inline int hash__pgd_bad(pgd_t pgd)
 {
 	return (pgd_val(pgd) == 0);
 }
+#ifdef CONFIG_STRICT_KERNEL_RWX
+extern void hash__mark_rodata_ro(void);
+#endif
 
 extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, unsigned long pte, int huge);
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index cd5e7aa8cc34..20b1485ff1e8 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -53,10 +53,11 @@ extern void __tlb_remove_table(void *_table);
 static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
 {
 #ifdef CONFIG_PPC_64K_PAGES
-	return (pgd_t *)__get_free_page(PGALLOC_GFP);
+	return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
 #else
 	struct page *page;
-	page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4);
+	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT),
+				4);
 	if (!page)
 		return NULL;
 	return (pgd_t *) page_address(page);
@@ -76,7 +77,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	if (radix_enabled())
 		return radix__pgd_alloc(mm);
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+		pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -93,7 +95,8 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *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);
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
+		pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -119,7 +122,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
+		pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -168,7 +172,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	struct page *page;
 	pte_t *pte;
 
-	pte = pte_alloc_one_kernel(mm, address);
+	pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT);
 	if (!pte)
 		return NULL;
 	page = virt_to_page(pte);
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 85bc9875c3be..c0737c86a362 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -5,6 +5,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
+#include <linux/bug.h>
 #endif
 
 /*
@@ -79,6 +80,9 @@
 
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
+#define _PAGE_DEVMAP		_RPAGE_SW1 /* software: ZONE_DEVICE page */
+#define __HAVE_ARCH_PTE_DEVMAP
+
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
  * Instead of fixing all of them, add an alternate define which
@@ -599,6 +603,16 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+static inline pte_t pte_mkdevmap(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
+}
+
+static inline int pte_devmap(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP));
+}
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	/* FIXME!! check whether this need to be a conditional */
@@ -1146,6 +1160,37 @@ static inline bool arch_needs_pgtable_deposit(void)
 	return true;
 }
 
+
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
+static inline int pmd_devmap(pmd_t pmd)
+{
+	return pte_devmap(pmd_pte(pmd));
+}
+
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline const int pud_pfn(pud_t pud)
+{
+	/*
+	 * Currently all calls to pud_pfn() are gated around a pud_devmap()
+	 * check so this should never be used. If it grows another user we
+	 * want to know about it.
+	 */
+	BUILD_BUG();
+	return 0;
+}
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index ac16d1943022..487709ff6875 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -116,6 +116,10 @@
 #define RADIX_PUD_TABLE_SIZE	(sizeof(pud_t) << RADIX_PUD_INDEX_SIZE)
 #define RADIX_PGD_TABLE_SIZE	(sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE)
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+extern void radix__mark_rodata_ro(void);
+#endif
+
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {
@@ -252,7 +256,7 @@ static inline int radix__pgd_bad(pgd_t pgd)
 
 static inline int radix__pmd_trans_huge(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
 }
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index abef812de7f8..5482928eea1b 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -83,8 +83,16 @@ static inline unsigned long ppc_function_entry(void *func)
 	 * On PPC64 ABIv1 the function pointer actually points to the
 	 * function's descriptor. The first entry in the descriptor is the
 	 * address of the function text.
+	 *
+	 * However, we may also receive pointer to an assembly symbol. To
+	 * detect that, we first check if the function pointer we receive
+	 * already points to kernel/module text and we only dereference it
+	 * if it doesn't.
 	 */
-	return ((func_descr_t *)func)->entry;
+	if (kernel_text_address((unsigned long)func))
+		return (unsigned long)func;
+	else
+		return ((func_descr_t *)func)->entry;
 #else
 	return (unsigned long)func;
 #endif
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index f70cbfe0ec04..9f2ae0d25e15 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -56,6 +56,19 @@ static inline void ppc_msgsync(void)
 				: : "i" (CPU_FTR_HVMODE|CPU_FTR_ARCH_300));
 }
 
+static inline void _ppc_msgclr(u32 msg)
+{
+	__asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGCLR(%1), PPC_MSGCLRP(%1), %0)
+				: : "i" (CPU_FTR_HVMODE), "r" (msg));
+}
+
+static inline void ppc_msgclr(enum ppc_dbell type)
+{
+	u32 msg = PPC_DBELL_TYPE(type);
+
+	_ppc_msgclr(msg);
+}
+
 #else /* CONFIG_PPC_BOOK3S */
 
 #define PPC_DBELL_MSGTYPE		PPC_DBELL
diff --git a/arch/powerpc/include/asm/delay.h b/arch/powerpc/include/asm/delay.h
index 52e4d54da2a9..3df4417dd9c8 100644
--- a/arch/powerpc/include/asm/delay.h
+++ b/arch/powerpc/include/asm/delay.h
@@ -2,6 +2,7 @@
 #define _ASM_POWERPC_DELAY_H
 #ifdef __KERNEL__
 
+#include <linux/processor.h>
 #include <asm/time.h>
 
 /*
@@ -58,11 +59,18 @@ extern void udelay(unsigned long usecs);
 	typeof(condition) __ret;                                               \
 	unsigned long __loops = tb_ticks_per_usec * timeout;                   \
 	unsigned long __start = get_tbl();                                     \
-	while (!(__ret = (condition)) && (tb_ticks_since(__start) <= __loops)) \
-		if (delay)                                                     \
+                                                                               \
+	if (delay) {                                                           \
+		while (!(__ret = (condition)) &&                               \
+				(tb_ticks_since(__start) <= __loops))          \
 			udelay(delay);                                         \
-		else                                                           \
-			cpu_relax();                                           \
+	} else {                                                               \
+		spin_begin();                                                  \
+		while (!(__ret = (condition)) &&                               \
+				(tb_ticks_since(__start) <= __loops))          \
+			spin_cpu_relax();                                      \
+		spin_end();                                                    \
+	}                                                                      \
 	if (!__ret)                                                            \
 		__ret = (condition);                                           \
 	__ret;		                                                       \
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 183d73b6ed99..9a318973af05 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -36,20 +36,38 @@
  */
 #include <asm/head-64.h>
 
+/* PACA save area offsets (exgen, exmc, etc) */
 #define EX_R9		0
 #define EX_R10		8
 #define EX_R11		16
 #define EX_R12		24
 #define EX_R13		32
-#define EX_SRR0		40
-#define EX_DAR		48
-#define EX_DSISR	56
-#define EX_CCR		60
-#define EX_R3		64
-#define EX_LR		72
-#define EX_CFAR		80
-#define EX_PPR		88	/* SMT thread status register (priority) */
-#define EX_CTR		96
+#define EX_DAR		40
+#define EX_DSISR	48
+#define EX_CCR		52
+#define EX_CFAR		56
+#define EX_PPR		64
+#if defined(CONFIG_RELOCATABLE)
+#define EX_CTR		72
+#define EX_SIZE		10	/* size in u64 units */
+#else
+#define EX_SIZE		9	/* size in u64 units */
+#endif
+
+/*
+ * EX_LR is only used in EXSLB and where it does not overlap with EX_DAR
+ * EX_CCR similarly with DSISR, but being 4 byte registers there is a hole
+ * in the save area so it's not necessary to overlap them. Could be used
+ * for future savings though if another 4 byte register was to be saved.
+ */
+#define EX_LR		EX_DAR
+
+/*
+ * EX_R3 is only used by the bad_stack handler. bad_stack reloads and
+ * saves DAR from SPRN_DAR, and EX_DAR is not used. So EX_R3 can overlap
+ * with EX_DAR.
+ */
+#define EX_R3		EX_DAR
 
 #ifdef CONFIG_RELOCATABLE
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
@@ -236,6 +254,19 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define kvmppc_interrupt kvmppc_interrupt_pr
 #endif
 
+/*
+ * Branch to label using its 0xC000 address. This results in instruction
+ * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned
+ * on using mtmsr rather than rfid.
+ *
+ * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than
+ * load KBASE for a slight optimisation.
+ */
+#define BRANCH_TO_C000(reg, label)					\
+	__LOAD_HANDLER(reg, label);					\
+	mtctr	reg;							\
+	bctr
+
 #ifdef CONFIG_RELOCATABLE
 #define BRANCH_TO_COMMON(reg, label)					\
 	__LOAD_HANDLER(reg, label);					\
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 60b91084f33c..ce88bbe1d809 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -43,6 +43,9 @@
 #define MIN_BOOT_MEM	(((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
 			+ (0x1UL << 26))
 
+/* The upper limit percentage for user specified boot memory size (25%) */
+#define MAX_BOOT_MEM_RATIO			4
+
 #define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
 
 /* Firmware provided dump sections */
@@ -200,6 +203,7 @@ struct fad_crash_memory_ranges {
 	unsigned long long	size;
 };
 
+extern int is_fadump_boot_memory_area(u64 addr, ulong size);
 extern int early_init_dt_scan_fw_dump(unsigned long node,
 		const char *uname, int depth, void *data);
 extern int fadump_reserve_mem(void);
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index 86eb87382031..d81eac5b509f 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -3,6 +3,7 @@
 
 #include <asm/cache.h>
 
+#ifdef __ASSEMBLY__
 /*
  * We can't do CPP stringification and concatination directly into the section
  * name for some reason, so these macros can do it for us.
@@ -49,8 +50,8 @@
  *   CLOSE_FIXED_SECTION() or elsewhere, there may be something
  *   unexpected being added there. Remove the '. = x_len' line, rebuild, and
  *   check what is pushing the section down.
- * - If the build dies in linking, check arch/powerpc/kernel/vmlinux.lds.S
- *   for instructions.
+ * - If the build dies in linking, check arch/powerpc/tools/head_check.sh
+ *   comments.
  * - If the kernel crashes or hangs in very early boot, it could be linker
  *   stubs at the start of the main text.
  */
@@ -63,11 +64,29 @@
 	. = 0x0;						\
 start_##sname:
 
+/*
+ * .linker_stub_catch section is used to catch linker stubs from being
+ * inserted in our .text section, above the start_text label (which breaks
+ * the ABS_ADDR calculation). See kernel/vmlinux.lds.S and tools/head_check.sh
+ * for more details. We would prefer to just keep a cacheline (0x80), but
+ * 0x100 seems to be how the linker aligns branch stub groups.
+ */
+#ifdef CONFIG_LD_HEAD_STUB_CATCH
+#define OPEN_TEXT_SECTION(start)				\
+	.section ".linker_stub_catch","ax",@progbits;		\
+linker_stub_catch:						\
+	. = 0x4;						\
+	text_start = (start) + 0x100;				\
+	.section ".text","ax",@progbits;			\
+	.balign 0x100;						\
+start_text:
+#else
 #define OPEN_TEXT_SECTION(start)				\
 	text_start = (start);					\
 	.section ".text","ax",@progbits;			\
 	. = 0x0;						\
 start_text:
+#endif
 
 #define ZERO_FIXED_SECTION(sname, start, end)			\
 	sname##_start = (start);				\
@@ -397,4 +416,6 @@ name:
 	EXC_COMMON_BEGIN(name);						\
 	STD_EXCEPTION_COMMON(realvec + 0x2, name, hdlr);		\
 
+#endif /* __ASSEMBLY__ */
+
 #endif	/* _ASM_POWERPC_HEAD_64_H */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index eba60416536e..c1dd1929342d 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -129,6 +129,10 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 }
 
 extern bool prep_irq_for_idle(void);
+extern bool prep_irq_for_idle_irqsoff(void);
+extern void irq_set_pending_from_srr1(unsigned long srr1);
+
+#define fini_irq_for_idle_irqsoff() trace_hardirqs_off();
 
 extern void force_external_irq_replay(void);
 
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index f90b22c722e1..cd2fc1cc1cc7 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -226,6 +226,7 @@ struct machdep_calls {
 extern void e500_idle(void);
 extern void power4_idle(void);
 extern void power7_idle(void);
+extern void power9_idle(void);
 extern void ppc6xx_idle(void);
 extern void book3e_idle(void);
 
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 81eff8631434..190d69a7f701 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -90,13 +90,14 @@ enum MCE_UserErrorType {
 enum MCE_RaErrorType {
 	MCE_RA_ERROR_INDETERMINATE = 0,
 	MCE_RA_ERROR_IFETCH = 1,
-	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
-	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
-	MCE_RA_ERROR_LOAD = 4,
-	MCE_RA_ERROR_STORE = 5,
-	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
-	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
-	MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+	MCE_RA_ERROR_IFETCH_FOREIGN = 2,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 3,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 4,
+	MCE_RA_ERROR_LOAD = 5,
+	MCE_RA_ERROR_STORE = 6,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 7,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 8,
+	MCE_RA_ERROR_LOAD_STORE_FOREIGN = 9,
 };
 
 enum MCE_LinkErrorType {
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 633139291a48..cc369a70f2bb 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -31,7 +31,8 @@ extern struct kmem_cache *pgtable_cache[];
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+			pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 5134ade2e850..91314268f04f 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -340,6 +340,8 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
+int map_kernel_page(unsigned long va, phys_addr_t pa, int flags);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_POWERPC_NOHASH_32_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 897d2e1c8a9b..9721c7867b9c 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -43,7 +43,8 @@ extern struct kmem_cache *pgtable_cache[];
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+			pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -57,7 +58,8 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 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);
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
+			pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -96,7 +98,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	struct page *page;
 	pte_t *pte;
 
-	pte = pte_alloc_one_kernel(mm, address);
+	pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT);
 	if (!pte)
 		return NULL;
 	page = virt_to_page(pte);
@@ -189,7 +191,8 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
+			pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index cb3e6242a78c..ef930ba500f9 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -667,12 +667,14 @@ enum {
 
 enum {
 	OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1,
-	OPAL_PHB_ERROR_DATA_TYPE_PHB3 = 2
+	OPAL_PHB_ERROR_DATA_TYPE_PHB3 = 2,
+	OPAL_PHB_ERROR_DATA_TYPE_PHB4 = 3
 };
 
 enum {
 	OPAL_P7IOC_NUM_PEST_REGS = 128,
-	OPAL_PHB3_NUM_PEST_REGS = 256
+	OPAL_PHB3_NUM_PEST_REGS = 256,
+	OPAL_PHB4_NUM_PEST_REGS = 512
 };
 
 struct OpalIoPhbErrorCommon {
@@ -802,6 +804,75 @@ struct OpalIoPhb3ErrorData {
 	__be64 pestB[OPAL_PHB3_NUM_PEST_REGS];
 };
 
+struct OpalIoPhb4ErrorData {
+	struct OpalIoPhbErrorCommon common;
+
+	__be32 brdgCtl;
+
+	/* PHB4 cfg regs */
+	__be32 deviceStatus;
+	__be32 slotStatus;
+	__be32 linkStatus;
+	__be32 devCmdStatus;
+	__be32 devSecStatus;
+
+	/* cfg AER regs */
+	__be32 rootErrorStatus;
+	__be32 uncorrErrorStatus;
+	__be32 corrErrorStatus;
+	__be32 tlpHdr1;
+	__be32 tlpHdr2;
+	__be32 tlpHdr3;
+	__be32 tlpHdr4;
+	__be32 sourceId;
+
+	/* PHB4 ETU Error Regs */
+	__be64 nFir;				/* 000 */
+	__be64 nFirMask;			/* 003 */
+	__be64 nFirWOF;				/* 008 */
+	__be64 phbPlssr;			/* 120 */
+	__be64 phbCsr;				/* 110 */
+	__be64 lemFir;				/* C00 */
+	__be64 lemErrorMask;			/* C18 */
+	__be64 lemWOF;				/* C40 */
+	__be64 phbErrorStatus;			/* C80 */
+	__be64 phbFirstErrorStatus;		/* C88 */
+	__be64 phbErrorLog0;			/* CC0 */
+	__be64 phbErrorLog1;			/* CC8 */
+	__be64 phbTxeErrorStatus;		/* D00 */
+	__be64 phbTxeFirstErrorStatus;		/* D08 */
+	__be64 phbTxeErrorLog0;			/* D40 */
+	__be64 phbTxeErrorLog1;			/* D48 */
+	__be64 phbRxeArbErrorStatus;		/* D80 */
+	__be64 phbRxeArbFirstErrorStatus;	/* D88 */
+	__be64 phbRxeArbErrorLog0;		/* DC0 */
+	__be64 phbRxeArbErrorLog1;		/* DC8 */
+	__be64 phbRxeMrgErrorStatus;		/* E00 */
+	__be64 phbRxeMrgFirstErrorStatus;	/* E08 */
+	__be64 phbRxeMrgErrorLog0;		/* E40 */
+	__be64 phbRxeMrgErrorLog1;		/* E48 */
+	__be64 phbRxeTceErrorStatus;		/* E80 */
+	__be64 phbRxeTceFirstErrorStatus;	/* E88 */
+	__be64 phbRxeTceErrorLog0;		/* EC0 */
+	__be64 phbRxeTceErrorLog1;		/* EC8 */
+
+	/* PHB4 REGB Error Regs */
+	__be64 phbPblErrorStatus;		/* 1900 */
+	__be64 phbPblFirstErrorStatus;		/* 1908 */
+	__be64 phbPblErrorLog0;			/* 1940 */
+	__be64 phbPblErrorLog1;			/* 1948 */
+	__be64 phbPcieDlpErrorLog1;		/* 1AA0 */
+	__be64 phbPcieDlpErrorLog2;		/* 1AA8 */
+	__be64 phbPcieDlpErrorStatus;		/* 1AB0 */
+	__be64 phbRegbErrorStatus;		/* 1C00 */
+	__be64 phbRegbFirstErrorStatus;		/* 1C08 */
+	__be64 phbRegbErrorLog0;		/* 1C40 */
+	__be64 phbRegbErrorLog1;		/* 1C48 */
+
+	__be64 pestA[OPAL_PHB4_NUM_PEST_REGS];
+	__be64 pestB[OPAL_PHB4_NUM_PEST_REGS];
+};
+
 enum {
 	OPAL_REINIT_CPUS_HILE_BE	= (1 << 0),
 	OPAL_REINIT_CPUS_HILE_LE	= (1 << 1),
@@ -877,6 +948,7 @@ enum {
 	OPAL_PHB_CAPI_MODE_SNOOP_OFF    = 2,
 	OPAL_PHB_CAPI_MODE_SNOOP_ON	= 3,
 	OPAL_PHB_CAPI_MODE_DMA		= 4,
+	OPAL_PHB_CAPI_MODE_DMA_TVT1	= 5,
 };
 
 /* OPAL I2C request */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 1c09f8fe2ee8..dc88a31cc79a 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -21,7 +21,11 @@
 #include <asm/lppaca.h>
 #include <asm/mmu.h>
 #include <asm/page.h>
+#ifdef CONFIG_PPC_BOOK3E
 #include <asm/exception-64e.h>
+#else
+#include <asm/exception-64s.h>
+#endif
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 #include <asm/kvm_book3s_asm.h>
 #endif
@@ -98,8 +102,8 @@ struct paca_struct {
 	 * Now, starting in cacheline 2, the exception save areas
 	 */
 	/* used for most interrupts/exceptions */
-	u64 exgen[13] __attribute__((aligned(0x80)));
-	u64 exslb[13];		/* used for SLB/segment table misses
+	u64 exgen[EX_SIZE] __attribute__((aligned(0x80)));
+	u64 exslb[EX_SIZE];	/* used for SLB/segment table misses
  				 * on the linear mapping */
 	/* SLB related definitions */
 	u16 vmalloc_sllp;
@@ -177,12 +181,14 @@ struct paca_struct {
 	 * to the sibling threads' paca.
 	 */
 	struct paca_struct **thread_sibling_pacas;
+	/* The PSSCR value that the kernel requested before going to stop */
+	u64 requested_psscr;
 #endif
 
 #ifdef CONFIG_PPC_STD_MMU_64
 	/* Non-maskable exceptions that are not performance critical */
-	u64 exnmi[13];		/* used for system reset (nmi) */
-	u64 exmc[13];		/* used for machine checks */
+	u64 exnmi[EX_SIZE];	/* used for system reset (nmi) */
+	u64 exmc[EX_SIZE];	/* used for machine checks */
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Exclusive stacks for system reset and machine check exception. */
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 0413457ba11d..d795c5d5789c 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -3,6 +3,20 @@
 
 #include <linux/mm.h>
 
+#ifndef MODULE
+static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
+{
+	if (unlikely(mm == &init_mm))
+		return gfp;
+	return gfp | __GFP_ACCOUNT;
+}
+#else /* !MODULE */
+static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
+{
+	return gfp | __GFP_ACCOUNT;
+}
+#endif /* MODULE */
+
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/book3s/pgalloc.h>
 #else
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1a9b45198c06..fa9ebaead91e 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -191,8 +191,7 @@
 /* sorted alphabetically */
 #define PPC_INST_BHRBE			0x7c00025c
 #define PPC_INST_CLRBHRB		0x7c00035c
-#define PPC_INST_COPY			0x7c00060c
-#define PPC_INST_COPY_FIRST		0x7c20060c
+#define PPC_INST_COPY			0x7c20060c
 #define PPC_INST_CP_ABORT		0x7c00068c
 #define PPC_INST_DCBA			0x7c0005ec
 #define PPC_INST_DCBA_MASK		0xfc0007fe
@@ -223,10 +222,10 @@
 #define PPC_INST_MSGCLR			0x7c0001dc
 #define PPC_INST_MSGSYNC		0x7c0006ec
 #define PPC_INST_MSGSNDP		0x7c00011c
+#define PPC_INST_MSGCLRP		0x7c00015c
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
-#define PPC_INST_PASTE			0x7c00070c
-#define PPC_INST_PASTE_LAST		0x7c20070d
+#define PPC_INST_PASTE			0x7c20070d
 #define PPC_INST_POPCNTB		0x7c0000f4
 #define PPC_INST_POPCNTB_MASK		0xfc0007fe
 #define PPC_INST_POPCNTD		0x7c0003f4
@@ -394,6 +393,8 @@
 
 /* Deal with instructions that older assemblers aren't aware of */
 #define	PPC_CP_ABORT		stringify_in_c(.long PPC_INST_CP_ABORT)
+#define	PPC_COPY(a, b)		stringify_in_c(.long PPC_INST_COPY | \
+					___PPC_RA(a) | ___PPC_RB(b))
 #define	PPC_DCBAL(a, b)		stringify_in_c(.long PPC_INST_DCBAL | \
 					__PPC_RA(a) | __PPC_RB(b))
 #define	PPC_DCBZL(a, b)		stringify_in_c(.long PPC_INST_DCBZL | \
@@ -411,6 +412,8 @@
 					___PPC_RB(b))
 #define PPC_MSGSNDP(b)		stringify_in_c(.long PPC_INST_MSGSNDP | \
 					___PPC_RB(b))
+#define PPC_MSGCLRP(b)		stringify_in_c(.long PPC_INST_MSGCLRP | \
+					___PPC_RB(b))
 #define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \
 					__PPC_RA(a) | __PPC_RS(s))
 #define PPC_POPCNTD(a, s)	stringify_in_c(.long PPC_INST_POPCNTD | \
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 359c44341761..6baeeb9acd0d 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -770,15 +770,18 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #else
 #define FIXUP_ENDIAN						   \
 	tdi   0,0,0x48;	  /* Reverse endian of b . + 8		*/ \
-	b     $+36;	  /* Skip trampoline if endian is good	*/ \
-	.long 0x05009f42; /* bcl 20,31,$+4			*/ \
-	.long 0xa602487d; /* mflr r10				*/ \
-	.long 0x1c004a39; /* addi r10,r10,28			*/ \
+	b     $+44;	  /* Skip trampoline if endian is good	*/ \
 	.long 0xa600607d; /* mfmsr r11				*/ \
 	.long 0x01006b69; /* xori r11,r11,1			*/ \
+	.long 0x00004039; /* li r10,0				*/ \
+	.long 0x6401417d; /* mtmsrd r10,1			*/ \
+	.long 0x05009f42; /* bcl 20,31,$+4			*/ \
+	.long 0xa602487d; /* mflr r10				*/ \
+	.long 0x14004a39; /* addi r10,r10,20			*/ \
 	.long 0xa6035a7d; /* mtsrr0 r10				*/ \
 	.long 0xa6037b7d; /* mtsrr1 r11				*/ \
 	.long 0x2400004c  /* rfid				*/
+
 #endif /* !CONFIG_PPC_BOOK3E */
 
 #endif /*  __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 1189d04f3bd1..fab7ff877304 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -421,6 +421,26 @@ static inline unsigned long __pack_fe01(unsigned int fpmode)
 
 #ifdef CONFIG_PPC64
 #define cpu_relax()	do { HMT_low(); HMT_medium(); barrier(); } while (0)
+
+#define spin_begin()	HMT_low()
+
+#define spin_cpu_relax()	barrier()
+
+#define spin_cpu_yield()	spin_cpu_relax()
+
+#define spin_end()	HMT_medium()
+
+#define spin_until_cond(cond)					\
+do {								\
+	if (unlikely(!(cond))) {				\
+		spin_begin();					\
+		do {						\
+			spin_cpu_relax();			\
+		} while (!(cond));				\
+		spin_end();					\
+	}							\
+} while (0)
+
 #else
 #define cpu_relax()	barrier()
 #endif
@@ -474,11 +494,11 @@ extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-extern unsigned long power7_nap(int check_irq);
-extern unsigned long power7_sleep(void);
-extern unsigned long power7_winkle(void);
-extern unsigned long power9_idle_stop(unsigned long stop_psscr_val,
-				      unsigned long stop_psscr_mask);
+extern unsigned long power7_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc*/
+extern void power7_idle_type(unsigned long type);
+extern unsigned long power9_idle_stop(unsigned long psscr_val);
+extern void power9_idle_type(unsigned long stop_psscr_val,
+			      unsigned long stop_psscr_mask);
 
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index c05cef6ee06c..18f168aebae3 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -168,6 +168,39 @@ TRACE_EVENT(hash_fault,
 		      __entry->addr, __entry->access, __entry->trap)
 );
 
+
+TRACE_EVENT(tlbie,
+
+	TP_PROTO(unsigned long lpid, unsigned long local, unsigned long rb,
+		unsigned long rs, unsigned long ric, unsigned long prs,
+		unsigned long r),
+	TP_ARGS(lpid, local, rb, rs, ric, prs, r),
+	TP_STRUCT__entry(
+		__field(unsigned long, lpid)
+		__field(unsigned long, local)
+		__field(unsigned long, rb)
+		__field(unsigned long, rs)
+		__field(unsigned long, ric)
+		__field(unsigned long, prs)
+		__field(unsigned long, r)
+		),
+
+	TP_fast_assign(
+		__entry->lpid = lpid;
+		__entry->local = local;
+		__entry->rb = rb;
+		__entry->rs = rs;
+		__entry->ric = ric;
+		__entry->prs = prs;
+		__entry->r = r;
+		),
+
+	TP_printk("lpid=%ld, local=%ld, rb=0x%lx, rs=0x%lx, ric=0x%lx, "
+		"prs=0x%lx, r=0x%lx", __entry->lpid, __entry->local,
+		__entry->rb, __entry->rs, __entry->ric, __entry->prs,
+		__entry->r)
+);
+
 #endif /* _TRACE_POWERPC_H */
 
 #undef TRACE_INCLUDE_PATH