Merge tag 'powerpc-4.8-2' of git://git.kernel.org/pub/scm/linux/kerne…

…l/git/powerpc/linux

Pull more powerpc updates from Michael Ellerman:
 "These were delayed for various reasons, so I let them sit in next a
  bit longer, rather than including them in my first pull request.

  Fixes:
   - Fix early access to cpu_spec relocation from Benjamin Herrenschmidt
   - Fix incorrect event codes in power9-event-list from Madhavan Srinivasan
   - Move register_process_table() out of ppc_md from Michael Ellerman

  Use jump_label use for [cpu|mmu]_has_feature():
   - Add mmu_early_init_devtree() from Michael Ellerman
   - Move disable_radix handling into mmu_early_init_devtree() from Michael Ellerman
   - Do hash device tree scanning earlier from Michael Ellerman
   - Do radix device tree scanning earlier from Michael Ellerman
   - Do feature patching before MMU init from Michael Ellerman
   - Check features don't change after patching from Michael Ellerman
   - Make MMU_FTR_RADIX a MMU family feature from Aneesh Kumar K.V
   - Convert mmu_has_feature() to returning bool from Michael Ellerman
   - Convert cpu_has_feature() to returning bool from Michael Ellerman
   - Define radix_enabled() in one place & use static inline from Michael Ellerman
   - Add early_[cpu|mmu]_has_feature() from Michael Ellerman
   - Convert early cpu/mmu feature check to use the new helpers from Aneesh Kumar K.V
   - jump_label: Make it possible for arches to invoke jump_label_init() earlier from Kevin Hao
   - Call jump_label_init() in apply_feature_fixups() from Aneesh Kumar K.V
   - Remove mfvtb() from Kevin Hao
   - Move cpu_has_feature() to a separate file from Kevin Hao
   - Add kconfig option to use jump labels for cpu/mmu_has_feature() from Michael Ellerman
   - Add option to use jump label for cpu_has_feature() from Kevin Hao
   - Add option to use jump label for mmu_has_feature() from Kevin Hao
   - Catch usage of cpu/mmu_has_feature() before jump label init from Aneesh Kumar K.V
   - Annotate jump label assembly from Michael Ellerman

  TLB flush enhancements from Aneesh Kumar K.V:
   - radix: Implement tlb mmu gather flush efficiently
   - Add helper for finding SLBE LLP encoding
   - Use hugetlb flush functions
   - Drop multiple definition of mm_is_core_local
   - radix: Add tlb flush of THP ptes
   - radix: Rename function and drop unused arg
   - radix/hugetlb: Add helper for finding page size
   - hugetlb: Add flush_hugetlb_tlb_range
   - remove flush_tlb_page_nohash

  Add new ptrace regsets from Anshuman Khandual and Simon Guo:
   - elf: Add powerpc specific core note sections
   - Add the function flush_tmregs_to_thread
   - Enable in transaction NT_PRFPREG ptrace requests
   - Enable in transaction NT_PPC_VMX ptrace requests
   - Enable in transaction NT_PPC_VSX ptrace requests
   - Adapt gpr32_get, gpr32_set functions for transaction
   - Enable support for NT_PPC_CGPR
   - Enable support for NT_PPC_CFPR
   - Enable support for NT_PPC_CVMX
   - Enable support for NT_PPC_CVSX
   - Enable support for TM SPR state
   - Enable NT_PPC_TM_CTAR, NT_PPC_TM_CPPR, NT_PPC_TM_CDSCR
   - Enable support for NT_PPPC_TAR, NT_PPC_PPR, NT_PPC_DSCR
   - Enable support for EBB registers
   - Enable support for Performance Monitor registers"

* tag 'powerpc-4.8-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (48 commits)
  powerpc/mm: Move register_process_table() out of ppc_md
  powerpc/perf: Fix incorrect event codes in power9-event-list
  powerpc/32: Fix early access to cpu_spec relocation
  powerpc/ptrace: Enable support for Performance Monitor registers
  powerpc/ptrace: Enable support for EBB registers
  powerpc/ptrace: Enable support for NT_PPPC_TAR, NT_PPC_PPR, NT_PPC_DSCR
  powerpc/ptrace: Enable NT_PPC_TM_CTAR, NT_PPC_TM_CPPR, NT_PPC_TM_CDSCR
  powerpc/ptrace: Enable support for TM SPR state
  powerpc/ptrace: Enable support for NT_PPC_CVSX
  powerpc/ptrace: Enable support for NT_PPC_CVMX
  powerpc/ptrace: Enable support for NT_PPC_CFPR
  powerpc/ptrace: Enable support for NT_PPC_CGPR
  powerpc/ptrace: Adapt gpr32_get, gpr32_set functions for transaction
  powerpc/ptrace: Enable in transaction NT_PPC_VSX ptrace requests
  powerpc/ptrace: Enable in transaction NT_PPC_VMX ptrace requests
  powerpc/ptrace: Enable in transaction NT_PRFPREG ptrace requests
  powerpc/process: Add the function flush_tmregs_to_thread
  elf: Add powerpc specific core note sections
  powerpc/mm: remove flush_tlb_page_nohash
  powerpc/mm/hugetlb: Add flush_hugetlb_tlb_range
  ...

arch/powerpc/Kconfig.debug

@@ -60,6 +60,25 @@ config CODE_PATCHING_SELFTEST
 	depends on DEBUG_KERNEL
 	default n
 
+config JUMP_LABEL_FEATURE_CHECKS
+	bool "Enable use of jump label for cpu/mmu_has_feature()"
+	depends on JUMP_LABEL
+	default y
+	help
+	  Selecting this options enables use of jump labels for some internal
+	  feature checks. This should generate more optimal code for those
+	  checks.
+
+config JUMP_LABEL_FEATURE_CHECK_DEBUG
+	bool "Do extra check on feature fixup calls"
+	depends on DEBUG_KERNEL && JUMP_LABEL_FEATURE_CHECKS
+	default n
+	help
+	  This tries to catch incorrect usage of cpu_has_feature() and
+	  mmu_has_feature() in the code.
+
+	  If you don't know what this means, say N.
+
 config FTR_FIXUP_SELFTEST
 	bool "Run self-tests of the feature-fixup code"
 	depends on DEBUG_KERNEL

arch/powerpc/include/asm/book3s/64/hugetlb-radix.h

@@ -11,4 +11,19 @@ extern unsigned long
 radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
+
+static inline int hstate_get_psize(struct hstate *hstate)
+{
+	unsigned long shift;
+
+	shift = huge_page_shift(hstate);
+	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
+		return MMU_PAGE_2M;
+	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
+		return MMU_PAGE_1G;
+	else {
+		WARN(1, "Wrong huge page shift\n");
+		return mmu_virtual_psize;
+	}
+}
 #endif

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -24,6 +24,7 @@
 #include <asm/book3s/64/pgtable.h>
 #include <asm/bug.h>
 #include <asm/processor.h>
+#include <asm/cpu_has_feature.h>
 
 /*
  * SLB
@@ -190,6 +191,15 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 	BUG();
 }
 
+static inline unsigned long get_sllp_encoding(int psize)
+{
+	unsigned long sllp;
+
+	sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) |
+		((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4);
+	return sllp;
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -23,13 +23,6 @@ struct mmu_psize_def {
 };
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 
-#ifdef CONFIG_PPC_RADIX_MMU
-#define radix_enabled() mmu_has_feature(MMU_FTR_RADIX)
-#else
-#define radix_enabled() (0)
-#endif
-
-
 #endif /* __ASSEMBLY__ */
 
 /* 64-bit classic hash table MMU */
@@ -107,6 +100,9 @@ extern int mmu_vmemmap_psize;
 extern int mmu_io_psize;
 
 /* MMU initialization */
+void mmu_early_init_devtree(void);
+void hash__early_init_devtree(void);
+void radix__early_init_devtree(void);
 extern void radix_init_native(void);
 extern void hash__early_init_mmu(void);
 extern void radix__early_init_mmu(void);
@@ -132,11 +128,15 @@ extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					      phys_addr_t first_memblock_size)
 {
-	if (radix_enabled())
+	if (early_radix_enabled())
 		return radix__setup_initial_memory_limit(first_memblock_base,
 						   first_memblock_size);
 	return hash__setup_initial_memory_limit(first_memblock_base,
 					   first_memblock_size);
 }
+
+extern int (*register_process_table)(unsigned long base, unsigned long page_size,
+				     unsigned long tbl_size);
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */

arch/powerpc/include/asm/book3s/64/tlbflush-hash.h

@@ -75,11 +75,6 @@ static inline void hash__flush_tlb_page(struct vm_area_struct *vma,
 {
 }
 
-static inline void hash__flush_tlb_page_nohash(struct vm_area_struct *vma,
-					   unsigned long vmaddr)
-{
-}
-
 static inline void hash__flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end)
 {

arch/powerpc/include/asm/book3s/64/tlbflush-radix.h

@@ -10,26 +10,32 @@ static inline int mmu_get_ap(int psize)
 	return mmu_psize_defs[psize].ap;
 }
 
+extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start, unsigned long end);
+extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+					 unsigned long end, int psize);
+extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end);
 extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end);
 extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
 extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
-				    unsigned long ap, int nid);
 extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
+extern void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
+					      int psize);
 extern void radix__tlb_flush(struct mmu_gather *tlb);
 #ifdef CONFIG_SMP
 extern void radix__flush_tlb_mm(struct mm_struct *mm);
 extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
-			      unsigned long ap, int nid);
 extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
+extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
+					int psize);
 #else
 #define radix__flush_tlb_mm(mm)		radix__local_flush_tlb_mm(mm)
 #define radix__flush_tlb_page(vma,addr)	radix__local_flush_tlb_page(vma,addr)
-#define radix___flush_tlb_page(mm,addr,p,i)	radix___local_flush_tlb_page(mm,addr,p,i)
+#define radix__flush_tlb_page_psize(mm,addr,p) radix__local_flush_tlb_page_psize(mm,addr,p)
 #define radix__flush_tlb_pwc(tlb, addr)	radix__local_flush_tlb_pwc(tlb, addr)
 #endif
 extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,

arch/powerpc/include/asm/book3s/64/tlbflush.h

@@ -7,6 +7,25 @@
 #include <asm/book3s/64/tlbflush-hash.h>
 #include <asm/book3s/64/tlbflush-radix.h>
 
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		return radix__flush_pmd_tlb_range(vma, start, end);
+	return hash__flush_tlb_range(vma, start, end);
+}
+
+#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start,
+					   unsigned long end)
+{
+	if (radix_enabled())
+		return radix__flush_hugetlb_tlb_range(vma, start, end);
+	return hash__flush_tlb_range(vma, start, end);
+}
+
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
@@ -38,14 +57,6 @@ static inline void local_flush_tlb_page(struct vm_area_struct *vma,
 	return hash__local_flush_tlb_page(vma, vmaddr);
 }
 
-static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
-					 unsigned long vmaddr)
-{
-	if (radix_enabled())
-		return radix__flush_tlb_page(vma, vmaddr);
-	return hash__flush_tlb_page_nohash(vma, vmaddr);
-}
-
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (radix_enabled())

arch/powerpc/include/asm/cacheflush.h

@@ -11,6 +11,7 @@
 
 #include <linux/mm.h>
 #include <asm/cputable.h>
+#include <asm/cpu_has_feature.h>
 
 /*
  * No cache flushing is required when address mappings are changed,

arch/powerpc/include/asm/cpu_has_feature.h

@@ -0,0 +1,53 @@
+#ifndef __ASM_POWERPC_CPUFEATURES_H
+#define __ASM_POWERPC_CPUFEATURES_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bug.h>
+#include <asm/cputable.h>
+
+static inline bool early_cpu_has_feature(unsigned long feature)
+{
+	return !!((CPU_FTRS_ALWAYS & feature) ||
+		  (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature));
+}
+
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
+#include <linux/jump_label.h>
+
+#define NUM_CPU_FTR_KEYS	64
+
+extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS];
+
+static __always_inline bool cpu_has_feature(unsigned long feature)
+{
+	int i;
+
+	BUILD_BUG_ON(!__builtin_constant_p(feature));
+
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
+	if (!static_key_initialized) {
+		printk("Warning! cpu_has_feature() used prior to jump label init!\n");
+		dump_stack();
+		return early_cpu_has_feature(feature);
+	}
+#endif
+
+	if (CPU_FTRS_ALWAYS & feature)
+		return true;
+
+	if (!(CPU_FTRS_POSSIBLE & feature))
+		return false;
+
+	i = __builtin_ctzl(feature);
+	return static_branch_likely(&cpu_feature_keys[i]);
+}
+#else
+static inline bool cpu_has_feature(unsigned long feature)
+{
+	return early_cpu_has_feature(feature);
+}
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_POWERPC_CPUFEATURE_H */

arch/powerpc/include/asm/cputable.h

@@ -2,6 +2,7 @@
 #define __ASM_POWERPC_CPUTABLE_H
 
 
+#include <linux/types.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 #include <uapi/asm/cputable.h>
@@ -122,6 +123,12 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start,
 
 extern const char *powerpc_base_platform;
 
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
+extern void cpu_feature_keys_init(void);
+#else
+static inline void cpu_feature_keys_init(void) { }
+#endif
+
 /* TLB flush actions. Used as argument to cpu_spec.flush_tlb() hook */
 enum {
 	TLB_INVAL_SCOPE_GLOBAL = 0,	/* invalidate all TLBs */
@@ -576,14 +583,6 @@ enum {
 };
 #endif /* __powerpc64__ */
 
-static inline int cpu_has_feature(unsigned long feature)
-{
-	return (CPU_FTRS_ALWAYS & feature) ||
-	       (CPU_FTRS_POSSIBLE
-		& cur_cpu_spec->cpu_features
-		& feature);
-}
-
 #define HBP_NUM 1
 
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/cputime.h

@@ -28,6 +28,7 @@ static inline void setup_cputime_one_jiffy(void) { }
 #include <asm/div64.h>
 #include <asm/time.h>
 #include <asm/param.h>
+#include <asm/cpu_has_feature.h>
 
 typedef u64 __nocast cputime_t;
 typedef u64 __nocast cputime64_t;

arch/powerpc/include/asm/dbell.h

@@ -16,6 +16,7 @@
 #include <linux/threads.h>
 
 #include <asm/ppc-opcode.h>
+#include <asm/cpu_has_feature.h>
 
 #define PPC_DBELL_MSG_BRDCAST	(0x04000000)
 #define PPC_DBELL_TYPE(x)	(((x) & 0xf) << (63-36))

arch/powerpc/include/asm/dcr-native.h

@@ -24,6 +24,7 @@
 
 #include <linux/spinlock.h>
 #include <asm/cputable.h>
+#include <asm/cpu_has_feature.h>
 
 typedef struct {
 	unsigned int base;

arch/powerpc/include/asm/hugetlb.h

@@ -147,7 +147,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 	pte_t pte;
 	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
-	flush_tlb_page(vma, addr);
+	flush_hugetlb_page(vma, addr);
 }
 
 static inline int huge_pte_none(pte_t pte)

arch/powerpc/include/asm/jump_label.h

@@ -22,7 +22,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
-		 "nop\n\t"
+		 "nop # arch_static_branch\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
 		 ".popsection \n\t"
@@ -36,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
-		 "b %l[l_yes]\n\t"
+		 "b %l[l_yes] # arch_static_branch_jump\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
 		 ".popsection \n\t"

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -181,8 +181,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 
 	switch (b_psize) {
 	case MMU_PAGE_4K:
-		sllp = ((mmu_psize_defs[a_psize].sllp & SLB_VSID_L) >> 6) |
-			((mmu_psize_defs[a_psize].sllp & SLB_VSID_LP) >> 4);
+		sllp = get_sllp_encoding(a_psize);
 		rb |= sllp << 5;	/*  AP field */
 		rb |= (va_low & 0x7ff) << 12;	/* remaining 11 bits of AVA */
 		break;

arch/powerpc/include/asm/machdep.h

@@ -219,8 +219,6 @@ struct machdep_calls {
 #ifdef CONFIG_ARCH_RANDOM
 	int (*get_random_seed)(unsigned long *v);
 #endif
-	int (*register_process_table)(unsigned long base, unsigned long page_size,
-				      unsigned long tbl_size);
 };
 
 extern void e500_idle(void);

arch/powerpc/include/asm/mman.h

@@ -13,6 +13,7 @@
 
 #include <asm/cputable.h>
 #include <linux/mm.h>
+#include <asm/cpu_has_feature.h>
 
 /*
  * This file is included by linux/mman.h, so we can't use cacl_vm_prot_bits()