diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-05 09:00:54 -0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-05 09:00:54 -0400 |
| commit | 2cfd716d2777489db54a237f466a1c42700879c6 (patch) | |
| tree | a6d3a676c38f2e2dc7bd13d012ad1d986a14a5bb | |
| parent | 755b20f49220683bc2469f4d956dee39101440aa (diff) | |
| parent | eea8148c69f3aecbf297b12943a591467a1fb432 (diff) | |
| download | lwn-2cfd716d2777489db54a237f466a1c42700879c6.tar.gz lwn-2cfd716d2777489db54a237f466a1c42700879c6.zip | |
Merge tag 'powerpc-4.8-2' of git://git.kernel.org/pub/scm/linux/kernel/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
...
57 files changed, 2074 insertions, 210 deletions
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 171047822b56..63292f64b25a 100644 --- a/arch/powerpc/Kconfig.debug +++ b/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 diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h index 60f47649306f..c45189aa7476 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h +++ b/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 diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 5eaf86ac143d..287a656ceb57 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/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__ */ /* diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index d4eda6420523..8afb0e00f7d9 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/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_ */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index f12ddf5e8de5..2f6373144e2c 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/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) { diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 00703e7e4c94..65037762b120 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/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, diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 96e5769b18b0..72b925f97bab 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/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()) diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 69fb16d7a811..b77f0364df94 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/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, diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h new file mode 100644 index 000000000000..2ef55f8968a2 --- /dev/null +++ b/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 */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index df4fb5faba43..82026b419341 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/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__ */ diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 2dfd4fc41f3e..4f60db074725 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/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; diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 5fa6b20eba10..378167377065 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/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)) diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 4efc11dacb98..4a2beef74277 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/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; diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index e2d9f4996e5c..c5517f463ec7 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/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) diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 9af103a23975..9a287e0ac8b1 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/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 @@ l_yes: 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" diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 1f4497fb5b83..88d17b4ea9c8 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/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; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 76f5398e7152..0420b388dd83 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/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); diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index fc420cedecae..30922f699341 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/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() diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 54471228f7b8..e2fb408f8398 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -12,7 +12,7 @@ */ /* - * First half is MMU families + * MMU families */ #define MMU_FTR_HPTE_TABLE ASM_CONST(0x00000001) #define MMU_FTR_TYPE_8xx ASM_CONST(0x00000002) @@ -21,9 +21,13 @@ #define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010) #define MMU_FTR_TYPE_47x ASM_CONST(0x00000020) +/* Radix page table supported and enabled */ +#define MMU_FTR_TYPE_RADIX ASM_CONST(0x00000040) + /* - * This is individual features + * Individual features below. */ + /* * We need to clear top 16bits of va (from the remaining 64 bits )in * tlbie* instructions @@ -93,11 +97,6 @@ */ #define MMU_FTR_1T_SEGMENT ASM_CONST(0x40000000) -/* - * Radix page table available - */ -#define MMU_FTR_RADIX ASM_CONST(0x80000000) - /* MMU feature bit sets for various CPUs */ #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 \ MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2 @@ -113,6 +112,7 @@ #define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ MMU_FTR_CI_LARGE_PAGE | MMU_FTR_NO_SLBIE_B #ifndef __ASSEMBLY__ +#include <linux/bug.h> #include <asm/cputable.h> #ifdef CONFIG_PPC_FSL_BOOK3E @@ -131,20 +131,71 @@ enum { MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE | MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA | #ifdef CONFIG_PPC_RADIX_MMU - MMU_FTR_RADIX | + MMU_FTR_TYPE_RADIX | #endif 0, }; -static inline int mmu_has_feature(unsigned long feature) +static inline bool early_mmu_has_feature(unsigned long feature) { - return (MMU_FTRS_POSSIBLE & cur_cpu_spec->mmu_features & feature); + return !!(MMU_FTRS_POSSIBLE & cur_cpu_spec->mmu_features & feature); +} + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +#include <linux/jump_label.h> + +#define NUM_MMU_FTR_KEYS 32 + +extern struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS]; + +extern void mmu_feature_keys_init(void); + +static __always_inline bool mmu_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! mmu_has_feature() used prior to jump label init!\n"); + dump_stack(); + return early_mmu_has_feature(feature); + } +#endif + + if (!(MMU_FTRS_POSSIBLE & feature)) + return false; + + i = __builtin_ctzl(feature); + return static_branch_likely(&mmu_feature_keys[i]); } static inline void mmu_clear_feature(unsigned long feature) { + int i; + + i = __builtin_ctzl(feature); cur_cpu_spec->mmu_features &= ~feature; + static_branch_disable(&mmu_feature_keys[i]); } +#else + +static inline void mmu_feature_keys_init(void) +{ + +} + +static inline bool mmu_has_feature(unsigned long feature) +{ + return early_mmu_has_feature(feature); +} + +static inline void mmu_clear_feature(unsigned long feature) +{ + cur_cpu_spec->mmu_features &= ~feature; +} +#endif /* CONFIG_JUMP_LABEL */ extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup; @@ -164,6 +215,28 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) } #endif /* !CONFIG_DEBUG_VM */ +#ifdef CONFIG_PPC_RADIX_MMU +static inline bool radix_enabled(void) +{ + return mmu_has_feature(MMU_FTR_TYPE_RADIX); +} + +static inline bool early_radix_enabled(void) +{ + return early_mmu_has_feature(MMU_FTR_TYPE_RADIX); +} +#else +static inline bool radix_enabled(void) +{ + return false; +} + +static inline bool early_radix_enabled(void) +{ + return false; +} +#endif + #endif /* !__ASSEMBLY__ */ /* The kernel use the constants below to index in the page sizes array. @@ -210,6 +283,7 @@ extern void early_init_mmu(void); extern void early_init_mmu_secondary(void); extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); +static inline void mmu_early_init_devtree(void) { } #endif /* __ASSEMBLY__ */ #endif @@ -230,9 +304,5 @@ extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, # include <asm/mmu-8xx.h> #endif -#ifndef radix_enabled -#define radix_enabled() (0) -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 40f3615bf940..f69f40f1519a 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1256,15 +1256,6 @@ static inline void msr_check_and_clear(unsigned long bits) __msr_check_and_clear(bits); } -static inline unsigned long mfvtb (void) -{ -#ifdef CONFIG_PPC_BOOK3S_64 - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - return mfspr(SPRN_VTB); -#endif - return 0; -} - #ifdef __powerpc64__ #if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) #define mftb() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 17c8380673a6..0a74ebe934e1 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -75,6 +75,14 @@ static inline void disable_kernel_spe(void) static inline void __giveup_spe(struct task_struct *t) { } #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +extern void flush_tmregs_to_thread(struct task_struct *); +#else +static inline void flush_tmregs_to_thread(struct task_struct *t) +{ +} +#endif + static inline void clear_task_ebb(struct task_struct *t) { #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 09211640a0e0..b240666b7bc1 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -18,6 +18,7 @@ #include <linux/percpu.h> #include <asm/processor.h> +#include <asm/cpu_has_feature.h> /* time.c */ extern unsigned long tb_ticks_per_jiffy; @@ -103,7 +104,7 @@ static inline u64 get_vtb(void) { #ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_ARCH_207S)) - return mfvtb(); + return mfspr(SPRN_VTB); #endif return 0; } diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 20733fa518ae..f6f68f73e858 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -46,5 +46,18 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, #endif } +#ifdef CONFIG_SMP +static inline int mm_is_core_local(struct mm_struct *mm) +{ + return cpumask_subset(mm_cpumask(mm), + topology_sibling_cpumask(smp_processor_id())); +} +#else +static inline int mm_is_core_local(struct mm_struct *mm) +{ + return 1; +} +#endif + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_TLB_H */ diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 1b38eea28e5a..13dbcd41885e 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -54,7 +54,6 @@ extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, #define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr) #define __flush_tlb_page(mm,addr,p,i) __local_flush_tlb_page(mm,addr,p,i) #endif -#define flush_tlb_page_nohash(vma,addr) flush_tlb_page(vma,addr) #elif defined(CONFIG_PPC_STD_MMU_32) diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h index 0abb97f3be10..a36c2069d8ed 100644 --- a/arch/powerpc/include/asm/xor.h +++ b/arch/powerpc/include/asm/xor.h @@ -23,6 +23,7 @@ #ifdef CONFIG_ALTIVEC #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, unsigned long *v2_in); diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index c2d21d11c2d2..3a9e44c45c78 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -91,6 +91,11 @@ #define ELF_NGREG 48 /* includes nip, msr, lr, etc. */ #define ELF_NFPREG 33 /* includes fpscr */ +#define ELF_NVMX 34 /* includes all vector registers */ +#define ELF_NVSX 32 /* includes all VSX registers */ +#define ELF_NTMSPRREG 3 /* include tfhar, tfiar, texasr */ +#define ELF_NEBB 3 /* includes ebbrr, ebbhr, bescr */ +#define ELF_NPMU 5 /* includes siar, sdar, sier, mmcr2, mmcr0 */ typedef unsigned long elf_greg_t64; typedef elf_greg_t64 elf_gregset_t64[ELF_NGREG]; diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index c7097f933114..033f3385fa49 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -26,6 +26,7 @@ #include <asm/emulated_ops.h> #include <asm/switch_to.h> #include <asm/disassemble.h> +#include <asm/cpu_has_feature.h> struct aligninfo { unsigned char len; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index d81f826d1029..74248ab18e98 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -15,6 +15,7 @@ #include <linux/threads.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/jump_label.h> #include <asm/oprofile_impl.h> #include <asm/cputable.h> @@ -2224,3 +2225,39 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) return NULL; } + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS] = { + [0 ... NUM_CPU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT +}; +EXPORT_SYMBOL_GPL(cpu_feature_keys); + +void __init cpu_feature_keys_init(void) +{ + int i; + + for (i = 0; i < NUM_CPU_FTR_KEYS; i++) { + unsigned long f = 1ul << i; + + if (!(cur_cpu_spec->cpu_features & f)) + static_branch_disable(&cpu_feature_keys[i]); + } +} + +struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS] = { + [0 ... NUM_MMU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT +}; +EXPORT_SYMBOL_GPL(mmu_feature_keys); + +void __init mmu_feature_keys_init(void) +{ + int i; + + for (i = 0; i < NUM_MMU_FTR_KEYS; i++) { + unsigned long f = 1ul << i; + + if (!(cur_cpu_spec->mmu_features & f)) + static_branch_disable(&mmu_feature_keys[i]); + } +} +#endif diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index fcb2887f5a33..6b8bc0dd09d4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -532,7 +532,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 694def6c9d61..41091fdf9bd8 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -940,7 +940,7 @@ BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) .align 7 .globl h_data_storage_common @@ -971,7 +971,7 @@ BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) @@ -1392,7 +1392,7 @@ slb_miss_realmode: #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION bl slb_allocate_realmode -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) #endif /* All done -- return from exception. */ @@ -1406,7 +1406,7 @@ BEGIN_MMU_FTR_SECTION beq- 2f FTR_SECTION_ELSE b 2f -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) .machine push .machine "power4" diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 8a56a51fc0cb..ba79d15f4ddd 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -572,7 +572,7 @@ common_exit: BEGIN_MMU_FTR_SECTION b no_segments -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) /* Restore SLB from PACA */ ld r8,PACA_SLBSHADOWPTR(r13) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ac910d9982df..08887cf2b20e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -75,6 +75,7 @@ #endif #define CREATE_TRACE_POINTS #include <asm/trace.h> +#include <asm/cpu_has_feature.h> DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 93dae296b6be..fa20060ff7a5 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -184,7 +184,7 @@ void setup_paca(struct paca_struct *new_paca) * if we do a GET_PACA() before the feature fixups have been * applied */ - if (cpu_has_feature(CPU_FTR_HVMODE)) + if (early_cpu_has_feature(CPU_FTR_HVMODE)) mtspr(SPRN_SPRG_HPACA, local_paca); #endif mtspr(SPRN_SPRG_PACA, local_paca); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a8cca88e972f..58ccf86415b4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -58,6 +58,7 @@ #include <asm/code-patching.h> #include <asm/exec.h> #include <asm/livepatch.h> +#include <asm/cpu_has_feature.h> #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -1073,6 +1074,26 @@ static inline void restore_sprs(struct thread_struct *old_thread, #endif } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +void flush_tmregs_to_thread(struct task_struct *tsk) +{ + /* + * Process self tracing is not yet supported through + * ptrace interface. Ptrace generic code should have + * prevented this from happening in the first place. + * Warn once here with the message, if some how it + * is attempted. + */ + WARN_ONCE(tsk == current, + "Not expecting ptrace on self: TM regs may be incorrect\n"); + + /* + * If task is not current, it should have been flushed + * already to it's thread_struct during __switch_to(). + */ +} +#endif + struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *new) { diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index bae3db791150..b0245bed6f54 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -170,7 +170,7 @@ static struct ibm_pa_feature { */ {CPU_FTR_TM_COMP, 0, 0, PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, - {0, MMU_FTR_RADIX, 0, 0, 40, 0, 0}, + {0, MMU_FTR_TYPE_RADIX, 0, 0, 40, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -647,14 +647,6 @@ static void __init early_reserve_mem(void) #endif } -static bool disable_radix; -static int __init parse_disable_radix(char *p) -{ - disable_radix = true; - return 0; -} -early_param("disable_radix", parse_disable_radix); - void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -744,11 +736,8 @@ void __init early_init_devtree(void *params) */ spinning_secondaries = boot_cpu_count - 1; #endif - /* - * now fixup radix MMU mode based on kernel command line - */ - if (disable_radix) - cur_cpu_spec->mmu_features &= ~MMU_FTR_RADIX; + + mmu_early_init_devtree(); #ifdef CONFIG_PPC_POWERNV /* Scan and build the list of machine check recoverable ranges */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 134bee9ac664..4f3c5756cc09 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -64,6 +64,10 @@ struct pt_regs_offset { {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])} #define REG_OFFSET_END {.name = NULL, .offset = 0} +#define TVSO(f) (offsetof(struct thread_vr_state, f)) +#define TFSO(f) (offsetof(struct thread_fp_state, f)) +#define TSO(f) (offsetof(struct thread_struct, f)) + static const struct pt_regs_offset regoffset_table[] = { GPR_OFFSET_NAME(0), GPR_OFFSET_NAME(1), @@ -181,6 +185,26 @@ static int set_user_msr(struct task_struct *task, unsigned long msr) return 0; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static unsigned long get_user_ckpt_msr(struct task_struct *task) +{ + return task->thread.ckpt_regs.msr | task->thread.fpexc_mode; +} + +static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr) +{ + task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE; + task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE; + return 0; +} + +static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap) +{ + task->thread.ckpt_regs.trap = trap & 0xfff0; + return 0; +} +#endif + #ifdef CONFIG_PPC64 static int get_user_dscr(struct task_struct *task, unsigned long *data) { @@ -358,6 +382,29 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, return ret; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which returns the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + * }; + * + * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM + * which determines the final code in this function. All the combinations of + * these two config options are possible except the one below as transactional + * memory config pulls in CONFIG_VSX automatically. + * + * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -368,14 +415,31 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #endif flush_fp_to_thread(target); -#ifdef CONFIG_VSX +#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + /* copy to local buffer then write that out */ + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_TRANS_FPR(i); + buf[32] = target->thread.transact_fp.fpscr; + } else { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_FPR(i); + buf[32] = target->thread.fp_state.fpscr; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +#endif + +#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) buf[i] = target->thread.TS_FPR(i); buf[32] = target->thread.fp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +#endif -#else +#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -384,6 +448,29 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #endif } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which setss the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + * }; + * + * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM + * which determines the final code in this function. All the combinations of + * these two config options are possible except the one below as transactional + * memory config pulls in CONFIG_VSX automatically. + * + * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) @@ -394,7 +481,27 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, #endif flush_fp_to_thread(target); -#ifdef CONFIG_VSX +#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + /* copy to local buffer then write that out */ + i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); + if (i) + return i; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + for (i = 0; i < 32 ; i++) + target->thread.TS_TRANS_FPR(i) = buf[i]; + target->thread.transact_fp.fpscr = buf[32]; + } else { + for (i = 0; i < 32 ; i++) + target->thread.TS_FPR(i) = buf[i]; + target->thread.fp_state.fpscr = buf[32]; + } + return 0; +#endif + +#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) @@ -403,7 +510,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, target->thread.TS_FPR(i) = buf[i]; target->thread.fp_state.fpscr = buf[32]; return 0; -#else +#endif + +#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -433,10 +542,28 @@ static int vr_active(struct task_struct *target, return target->thread.used_vr ? regset->n : 0; } +/* + * When the transaction is active, 'transact_vr' holds the current running + * value of all the VMX registers and 'vr_state' holds the last checkpointed + * value of all the VMX registers for the current transaction to fall back + * on in case it aborts. When transaction is not active 'vr_state' holds + * the current running state of all the VMX registers. So this function which + * gets the current running values of all the VMX registers, needs to know + * whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + * }; + */ static int vr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -444,8 +571,19 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_fp_to_thread(target); + flush_tmregs_to_thread(target); + addr = &target->thread.transact_vr; + } else { + addr = &target->thread.vr_state; + } +#else + addr = &target->thread.vr_state; +#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + addr, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -456,7 +594,16 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + vrsave.word = target->thread.transact_vrsave; + else + vrsave.word = target->thread.vrsave; +#else vrsave.word = target->thread.vrsave; +#endif + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); } @@ -464,10 +611,28 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, return ret; } +/* + * When the transaction is active, 'transact_vr' holds the current running + * value of all the VMX registers and 'vr_state' holds the last checkpointed + * value of all the VMX registers for the current transaction to fall back + * on in case it aborts. When transaction is not active 'vr_state' holds + * the current running state of all the VMX registers. So this function which + * sets the current running values of all the VMX registers, needs to know + * whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + * }; + */ static int vr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { + struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -475,8 +640,19 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_fp_to_thread(target); + flush_tmregs_to_thread(target); + addr = &target->thread.transact_vr; + } else { + addr = &target->thread.vr_state; + } +#else + addr = &target->thread.vr_state; +#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + addr, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -487,11 +663,28 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + vrsave.word = target->thread.transact_vrsave; + else + vrsave.word = target->thread.vrsave; +#else vrsave.word = target->thread.vrsave; +#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); - if (!ret) + if (!ret) { + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + target->thread.transact_vrsave = vrsave.word; + else + target->thread.vrsave = vrsave.word; +#else target->thread.vrsave = vrsave.word; +#endif + } } return ret; @@ -512,6 +705,21 @@ static int vsr_active(struct task_struct *target, return target->thread.used_vsr ? regset->n : 0; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which returns the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 vsx[32]; + * }; + */ static int vsr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -519,16 +727,47 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret, i; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); +#endif flush_vsx_to_thread(target); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread. + transact_fp.fpr[i][TS_VSRLOWOFFSET]; + } else { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread. + fp_state.fpr[i][TS_VSRLOWOFFSET]; + } +#else for (i = 0; i < 32 ; i++) buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; +#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); return ret; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which sets the current running values of all + * the FPR registers, needs to know whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 vsx[32]; + * }; + */ static int vsr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) @@ -536,12 +775,30 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret,i; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); +#endif flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + for (i = 0; i < 32 ; i++) + target->thread.transact_fp. + fpr[i][TS_VSRLOWOFFSET] = buf[i]; + } else { + for (i = 0; i < 32 ; i++) + target->thread.fp_state. + fpr[i][TS_VSRLOWOFFSET] = buf[i]; + } +#else for (i = 0; i < 32 ; i++) target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; +#endif return ret; @@ -614,8 +871,1030 @@ static int evr_set(struct task_struct *target, const struct user_regset *regset, } #endif /* CONFIG_SPE */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +/** + * tm_cgpr_active - get active number of registers in CGPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed GPR category. + */ +static int tm_cgpr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cgpr_get - get CGPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets transaction checkpointed GPR registers. + * + * When the transaction is active, 'ckpt_regs' holds all the checkpointed + * GPR register values for the current transaction to fall back on if it + * aborts in between. This function gets those checkpointed GPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * struct pt_regs ckpt_regs; + * }; + */ +static int tm_cgpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs, + 0, offsetof(struct pt_regs, msr)); + if (!ret) { + unsigned long msr = get_user_ckpt_msr(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr, + offsetof(struct pt_regs, msr), + offsetof(struct pt_regs, msr) + + sizeof(msr)); + } + + BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) != + offsetof(struct pt_regs, msr) + sizeof(long)); + + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs.orig_gpr3, + offsetof(struct pt_regs, orig_gpr3), + sizeof(struct pt_regs)); + if (!ret) + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_regs), -1); + + return ret; +} /* + * tm_cgpr_set - set the CGPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed GPR registers. + * + * When the transaction is active, 'ckpt_regs' holds the checkpointed + * GPR register values for the current transaction to fall back on if it + * aborts in between. This function sets those checkpointed GPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * struct pt_regs ckpt_regs; + * }; + */ +static int tm_cgpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned long reg; + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs, + 0, PT_MSR * sizeof(reg)); + + if (!ret && count > 0) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®, + PT_MSR * sizeof(reg), + (PT_MSR + 1) * sizeof(reg)); + if (!ret) + ret = set_user_ckpt_msr(target, reg); + } + + BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) != + offsetof(struct pt_regs, msr) + sizeof(long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs.orig_gpr3, + PT_ORIG_R3 * sizeof(reg), + (PT_MAX_PUT_REG + 1) * sizeof(reg)); + + if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret) + ret = user_regset_copyin_ignore( + &pos, &count, &kbuf, &ubuf, + (PT_MAX_PUT_REG + 1) * sizeof(reg), + PT_TRAP * sizeof(reg)); + + if (!ret && count > 0) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®, + PT_TRAP * sizeof(reg), + (PT_TRAP + 1) * sizeof(reg)); + if (!ret) + ret = set_user_ckpt_trap(target, reg); + } + + if (!ret) + ret = user_regset_copyin_ignore( + &pos, &count, &kbuf, &ubuf, + (PT_TRAP + 1) * sizeof(reg), -1); + + return ret; +} + +/** + * tm_cfpr_active - get active number of registers in CFPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed FPR category. + */ +static int tm_cfpr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cfpr_get - get CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed FPR registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * values for the current transaction to fall back on if it aborts + * in between. This function gets those checkpointed FPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + *}; + */ +static int tm_cfpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + u64 buf[33]; + int i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* copy to local buffer then write that out */ + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_FPR(i); + buf[32] = target->thread.fp_state.fpscr; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +} + +/** + * tm_cfpr_set - set CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed FPR registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * FPR register values for the current transaction to fall back on + * if it aborts in between. This function sets these checkpointed + * FPR registers. The userspace interface buffer layout is as follows. + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + *}; + */ +static int tm_cfpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 buf[33]; + int i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* copy to local buffer then write that out */ + i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); + if (i) + return i; + for (i = 0; i < 32 ; i++) + target->thread.TS_FPR(i) = buf[i]; + target->thread.fp_state.fpscr = buf[32]; + return 0; +} + +/** + * tm_cvmx_active - get active number of registers in CVMX + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in checkpointed VMX category. + */ +static int tm_cvmx_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cvmx_get - get CMVX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed VMX registers. + * + * When the transaction is active 'vr_state' and 'vr_save' hold + * the checkpointed values for the current transaction to fall + * back on if it aborts in between. The userspace interface buffer + * layout is as follows. + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + *}; + */ +static int tm_cvmx_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32])); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.vr_state, 0, + 33 * sizeof(vector128)); + if (!ret) { + /* + * Copy out only the low-order word of vrsave. + */ + union { + elf_vrreg_t reg; + u32 word; + } vrsave; + memset(&vrsave, 0, sizeof(vrsave)); + vrsave.word = target->thread.vrsave; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, + 33 * sizeof(vector128), -1); + } + + return ret; +} + +/** + * tm_cvmx_set - set CMVX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed VMX registers. + * + * When the transaction is active 'vr_state' and 'vr_save' hold + * the checkpointed values for the current transaction to fall + * back on if it aborts in between. The userspace interface buffer + * layout is as follows. + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + *}; + */ +static int tm_cvmx_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32])); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.vr_state, 0, + 33 * sizeof(vector128)); + if (!ret && count > 0) { + /* + * We use only the low-order word of vrsave. + */ + union { + elf_vrreg_t reg; + u32 word; + } vrsave; + memset(&vrsave, 0, sizeof(vrsave)); + vrsave.word = target->thread.vrsave; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, + 33 * sizeof(vector128), -1); + if (!ret) + target->thread.vrsave = vrsave.word; + } + + return ret; +} + +/** + * tm_cvsx_active - get active number of registers in CVSX + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed VSX category. + */ +static int tm_cvsx_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + flush_vsx_to_thread(target); + return target->thread.used_vsr ? regset->n : 0; +} + +/** + * tm_cvsx_get - get CVSX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed VSX registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * values for the current transaction to fall back on if it aborts + * in between. This function gets those checkpointed VSX registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * u64 vsx[32]; + *}; + */ +static int tm_cvsx_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + u64 buf[32]; + int ret, i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + flush_vsx_to_thread(target); + + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + buf, 0, 32 * sizeof(double)); + + return ret; +} + +/** + * tm_cvsx_set - set CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed VSX registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * VSX register values for the current transaction to fall back on + * if it aborts in between. This function sets these checkpointed + * FPR registers. The userspace interface buffer layout is as follows. + * + * struct data { + * u64 vsx[32]; + *}; + */ +static int tm_cvsx_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 buf[32]; + int ret, i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + flush_vsx_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + buf, 0, 32 * sizeof(double)); + for (i = 0; i < 32 ; i++) + target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + + return ret; +} + +/** + * tm_spr_active - get active number of registers in TM SPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks the active number of available + * regisers in the transactional memory SPR category. + */ +static int tm_spr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + return regset->n; +} + +/** + * tm_spr_get - get the TM related SPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets transactional memory related SPR registers. + * The userspace interface buffer layout is as follows. + * + * struct { + * u64 tm_tfhar; + * u64 tm_texasr; + * u64 tm_tfiar; + * }; + */ +static int tm_spr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + /* Build tests */ + BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr)); + BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar)); + BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs)); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + /* Flush the states */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* TFHAR register */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfhar, 0, sizeof(u64)); + + /* TEXASR register */ + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_texasr, sizeof(u64), + 2 * sizeof(u64)); + + /* TFIAR register */ + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfiar, + 2 * sizeof(u64), 3 * sizeof(u64)); + return ret; +} + +/** + * tm_spr_set - set the TM related SPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets transactional memory related SPR registers. + * The userspace interface buffer layout is as follows. + * + * struct { + * u64 tm_tfhar; + * u64 tm_texasr; + * u64 tm_tfiar; + * }; + */ +static int tm_spr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + /* Build tests */ + BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr)); + BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar)); + BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs)); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + /* Flush the states */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* TFHAR register */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfhar, 0, sizeof(u64)); + + /* TEXASR register */ + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_texasr, sizeof(u64), + 2 * sizeof(u64)); + + /* TFIAR register */ + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfiar, + 2 * sizeof(u64), 3 * sizeof(u64)); + return ret; +} + +static int tm_tar_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + +static int tm_tar_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tar, 0, sizeof(u64)); + return ret; +} + +static int tm_tar_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tar, 0, sizeof(u64)); + return ret; +} + +static int tm_ppr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + + +static int tm_ppr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_ppr, 0, sizeof(u64)); + return ret; +} + +static int tm_ppr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_ppr, 0, sizeof(u64)); + return ret; +} + +static int tm_dscr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + +static int tm_dscr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_dscr, 0, sizeof(u64)); + return ret; +} + +static int tm_dscr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_dscr, 0, sizeof(u64)); + return ret; +} +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +#ifdef CONFIG_PPC64 +static int ppr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); + return ret; +} + +static int ppr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); + return ret; +} + +static int dscr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); + return ret; +} +static int dscr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); + return ret; +} +#endif +#ifdef CONFIG_PPC_BOOK3S_64 +static int tar_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); + return ret; +} +static int tar_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); + return ret; +} + +static int ebb_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (target->thread.used_ebb) + return regset->n; + + return 0; +} + +static int ebb_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* Build tests */ + BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr)); + BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (!target->thread.used_ebb) + return -ENODATA; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbrr, 0, 3 * sizeof(unsigned long)); +} + +static int ebb_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + /* Build tests */ + BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr)); + BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (target->thread.used_ebb) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbrr, 0, sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbhr, sizeof(unsigned long), + 2 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.bescr, + 2 * sizeof(unsigned long), 3 * sizeof(unsigned long)); + + return ret; +} +static int pmu_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return regset->n; +} + +static int pmu_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* Build tests */ + BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar)); + BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier)); + BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2)); + BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.siar, 0, + 5 * sizeof(unsigned long)); +} + +static int pmu_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + /* Build tests */ + BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar)); + BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier)); + BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2)); + BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.siar, 0, + sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.sdar, sizeof(unsigned long), + 2 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.sier, 2 * sizeof(unsigned long), + 3 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.mmcr2, 3 * sizeof(unsigned long), + 4 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.mmcr0, 4 * sizeof(unsigned long), + 5 * sizeof(unsigned long)); + return ret; +} +#endif +/* * These are our native regset flavors. */ enum powerpc_regset { @@ -630,6 +1909,25 @@ enum powerpc_regset { #ifdef CONFIG_SPE REGSET_SPE, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + REGSET_TM_CGPR, /* TM checkpointed GPR registers */ + REGSET_TM_CFPR, /* TM checkpointed FPR registers */ + REGSET_TM_CVMX, /* TM checkpointed VMX registers */ + REGSET_TM_CVSX, /* TM checkpointed VSX registers */ + REGSET_TM_SPR, /* TM specific SPR registers */ + REGSET_TM_CTAR, /* TM checkpointed TAR register */ + REGSET_TM_CPPR, /* TM checkpointed PPR register */ + REGSET_TM_CDSCR, /* TM checkpointed DSCR register */ +#endif +#ifdef CONFIG_PPC64 + REGSET_PPR, /* PPR register */ + REGSET_DSCR, /* DSCR register */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + REGSET_TAR, /* TAR register */ + REGSET_EBB, /* EBB registers */ + REGSET_PMR, /* Performance Monitor Registers */ +#endif }; static const struct user_regset native_regsets[] = { @@ -664,6 +1962,77 @@ static const struct user_regset native_regsets[] = { .active = evr_active, .get = evr_get, .set = evr_set }, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + [REGSET_TM_CGPR] = { + .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + .size = sizeof(long), .align = sizeof(long), + .active = tm_cgpr_active, .get = tm_cgpr_get, .set = tm_cgpr_set + }, + [REGSET_TM_CFPR] = { + .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set + }, + [REGSET_TM_CVMX] = { + .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + .size = sizeof(vector128), .align = sizeof(vector128), + .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set + }, + [REGSET_TM_CVSX] = { + .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set + }, + [REGSET_TM_SPR] = { + .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set + }, + [REGSET_TM_CTAR] = { + .core_note_type = NT_PPC_TM_CTAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set + }, + [REGSET_TM_CPPR] = { + .core_note_type = NT_PPC_TM_CPPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set + }, + [REGSET_TM_CDSCR] = { + .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set + }, +#endif +#ifdef CONFIG_PPC64 + [REGSET_PPR] = { + .core_note_type = NT_PPC_PPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = ppr_get, .set = ppr_set + }, + [REGSET_DSCR] = { + .core_note_type = NT_PPC_DSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = dscr_get, .set = dscr_set + }, +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + [REGSET_TAR] = { + .core_note_type = NT_PPC_TAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = tar_get, .set = tar_set + }, + [REGSET_EBB] = { + .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + .size = sizeof(u64), .align = sizeof(u64), + .active = ebb_active, .get = ebb_get, .set = ebb_set + }, + [REGSET_PMR] = { + .core_note_type = NT_PPC_PMU, .n = ELF_NPMU, + .size = sizeof(u64), .align = sizeof(u64), + .active = pmu_active, .get = pmu_get, .set = pmu_set + }, +#endif }; static const struct user_regset_view user_ppc_native_view = { @@ -674,24 +2043,35 @@ static const struct user_regset_view user_ppc_native_view = { #ifdef CONFIG_PPC64 #include <linux/compat.h> -static int gpr32_get(struct task_struct *target, +static int gpr32_get_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + void *kbuf, void __user *ubuf, bool tm_active) { const unsigned long *regs = &target->thread.regs->gpr[0]; + const unsigned long *ckpt_regs; compat_ulong_t *k = kbuf; compat_ulong_t __user *u = ubuf; compat_ulong_t reg; int i; - if (target->thread.regs == NULL) - return -EIO; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ckpt_regs = &target->thread.ckpt_regs.gpr[0]; +#endif + if (tm_active) { + regs = ckpt_regs; + } else { + if (target->thread.regs == NULL) + return -EIO; - if (!FULL_REGS(target->thread.regs)) { - /* We have a partial register set. Fill 14-31 with bogus values */ - for (i = 14; i < 32; i++) - target->thread.regs->gpr[i] = NV_REG_POISON; + if (!FULL_REGS(target->thread.regs)) { + /* + * We have a partial register set. + * Fill 14-31 with bogus values. + */ + for (i = 14; i < 32; i++) + target->thread.regs->gpr[i] = NV_REG_POISON; + } } pos /= sizeof(reg); @@ -731,20 +2111,31 @@ static int gpr32_get(struct task_struct *target, PT_REGS_COUNT * sizeof(reg), -1); } -static int gpr32_set(struct task_struct *target, +static int gpr32_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + const void *kbuf, const void __user *ubuf, bool tm_active) { unsigned long *regs = &target->thread.regs->gpr[0]; + unsigned long *ckpt_regs; const compat_ulong_t *k = kbuf; const compat_ulong_t __user *u = ubuf; compat_ulong_t reg; - if (target->thread.regs == NULL) - return -EIO; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ckpt_regs = &target->thread.ckpt_regs.gpr[0]; +#endif - CHECK_FULL_REGS(target->thread.regs); + if (tm_active) { + regs = ckpt_regs; + } else { + regs = &target->thread.regs->gpr[0]; + + if (target->thread.regs == NULL) + return -EIO; + + CHECK_FULL_REGS(target->thread.regs); + } pos /= sizeof(reg); count /= sizeof(reg); @@ -804,6 +2195,40 @@ static int gpr32_set(struct task_struct *target, (PT_TRAP + 1) * sizeof(reg), -1); } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static int tm_cgpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 1); +} + +static int tm_cgpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 1); +} +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +static int gpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 0); +} + +static int gpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 0); +} + /* * These are the regset flavors matching the CONFIG_PPC32 native set. */ @@ -832,6 +2257,73 @@ static const struct user_regset compat_regsets[] = { .active = evr_active, .get = evr_get, .set = evr_set }, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + [REGSET_TM_CGPR] = { + .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + .size = sizeof(long), .align = sizeof(long), + .active = tm_cgpr_active, + .get = tm_cgpr32_get, .set = tm_cgpr32_set + }, + [REGSET_TM_CFPR] = { + .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set + }, + [REGSET_TM_CVMX] = { + .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + .size = sizeof(vector128), .align = sizeof(vector128), + .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set + }, + [REGSET_TM_CVSX] = { + .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set + }, + [REGSET_TM_SPR] = { + .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set + }, + [REGSET_TM_CTAR] = { + .core_note_type = NT_PPC_TM_CTAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set + }, + [REGSET_TM_CPPR] = { + .core_note_type = NT_PPC_TM_CPPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set + }, + [REGSET_TM_CDSCR] = { + .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set + }, +#endif +#ifdef CONFIG_PPC64 + [REGSET_PPR] = { + .core_note_type = NT_PPC_PPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = ppr_get, .set = ppr_set + }, + [REGSET_DSCR] = { + .core_note_type = NT_PPC_DSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = dscr_get, .set = dscr_set + }, +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + [REGSET_TAR] = { + .core_note_type = NT_PPC_TAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = tar_get, .set = tar_set + }, + [REGSET_EBB] = { + .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + .size = sizeof(u64), .align = sizeof(u64), + .active = ebb_active, .get = ebb_get, .set = ebb_set + }, +#endif }; static const struct user_regset_view user_ppc_compat_view = { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 714b4ba7ab86..dba265c586df 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -66,6 +66,7 @@ #include <asm/hugetlb.h> #include <asm/livepatch.h> #include <asm/mmu_context.h> +#include <asm/cpu_has_feature.h> #include "setup.h" diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 00f57754407e..c3e861df4b20 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -37,6 +37,7 @@ #include <asm/serial.h> #include <asm/udbg.h> #include <asm/code-patching.h> +#include <asm/cpu_has_feature.h> #define DBG(fmt...) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index d8216aed22b7..eafb9a79e011 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -227,8 +227,8 @@ static void __init configure_exceptions(void) opal_configure_cores(); /* Enable AIL if supported, and we are in hypervisor mode */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) { + if (early_cpu_has_feature(CPU_FTR_HVMODE) && + early_cpu_has_feature(CPU_FTR_ARCH_207S)) { unsigned long lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); } @@ -298,12 +298,12 @@ void __init early_setup(unsigned long dt_ptr) */ configure_exceptions(); - /* Initialize the hash table or TLB handling */ - early_init_mmu(); - /* Apply all the dynamic patching */ apply_feature_fixups(); + /* Initialize the hash table or TLB handling */ + early_init_mmu(); + /* * At this point, we can let interrupts switch to virtual mode * (the MMU has been setup), so adjust the MSR in the PACA to diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5a1f015ea9f3..25a39052bf6b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -55,6 +55,7 @@ #include <asm/debug.h> #include <asm/kexec.h> #include <asm/asm-prototypes.h> +#include <asm/cpu_has_feature.h> #ifdef DEBUG #include <asm/udbg.h> diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index defb2998b818..74145f02ad41 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -13,6 +13,7 @@ */ #include <linux/types.h> +#include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> @@ -152,9 +153,18 @@ static void do_final_fixups(void) #endif } -void apply_feature_fixups(void) +static unsigned long __initdata saved_cpu_features; +static unsigned int __initdata saved_mmu_features; +#ifdef CONFIG_PPC64 +static unsigned long __initdata saved_firmware_features; +#endif + +void __init apply_feature_fixups(void) { - struct cpu_spec *spec = *PTRRELOC(&cur_cpu_spec); + struct cpu_spec *spec = PTRRELOC(*PTRRELOC(&cur_cpu_spec)); + + *PTRRELOC(&saved_cpu_features) = spec->cpu_features; + *PTRRELOC(&saved_mmu_features) = spec->mmu_features; /* * Apply the CPU-specific and firmware specific fixups to kernel text @@ -173,11 +183,36 @@ void apply_feature_fixups(void) PTRRELOC(&__stop___lwsync_fixup)); #ifdef CONFIG_PPC64 + saved_firmware_features = powerpc_firmware_features; do_feature_fixups(powerpc_firmware_features, &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); #endif do_final_fixups(); + + /* + * Initialise jump label. This causes all the cpu/mmu_has_feature() + * checks to take on their correct polarity based on the current set of + * CPU/MMU features. + */ + jump_label_init(); + cpu_feature_keys_init(); + mmu_feature_keys_init(); +} + +static int __init check_features(void) +{ + WARN(saved_cpu_features != cur_cpu_spec->cpu_features, + "CPU features changed after feature patching!\n"); + WARN(saved_mmu_features != cur_cpu_spec->mmu_features, + "MMU features changed after feature patching!\n"); +#ifdef CONFIG_PPC64 + WARN(saved_firmware_features != powerpc_firmware_features, + "Firmware features changed after feature patching!\n"); +#endif + + return 0; } +late_initcall(check_features); #ifdef CONFIG_FTR_FIXUP_SELFTEST diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 88ce7d212320..0e4e9654bd2c 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -72,8 +72,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) /* clear out bits after (52) [0....52.....63] */ va &= ~((1ul << (64 - 52)) - 1); va |= ssize << 8; - sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) | - ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4); + sllp = get_sllp_encoding(apsize); va |= sllp << 5; asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) @@ -122,8 +121,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) /* clear out bits after(52) [0....52.....63] */ va &= ~((1ul << (64 - 52)) - 1); va |= ssize << 8; - sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) | - ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4); + sllp = get_sllp_encoding(apsize); va |= sllp << 5; asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)" : : "r"(va) : "memory"); @@ -749,5 +747,5 @@ void __init hpte_init_native(void) mmu_hash_ops.hugepage_invalidate = native_hugepage_invalidate; if (cpu_has_feature(CPU_FTR_ARCH_300)) - ppc_md.register_process_table = native_register_proc_table; + register_process_table = native_register_proc_table; } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index b78b5d211278..0821556e16f4 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -363,11 +363,6 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node, return 0; } -static void __init htab_init_seg_sizes(void) -{ - of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL); -} - static int __init get_idx_from_shift(unsigned int shift) { int idx = -1; @@ -539,7 +534,7 @@ static bool might_have_hea(void) #endif /* #ifdef CONFIG_PPC_64K_PAGES */ -static void __init htab_init_page_sizes(void) +static void __init htab_scan_page_sizes(void) { int rc; @@ -554,17 +549,23 @@ static void __init htab_init_page_sizes(void) * Try to find the available page sizes in the device-tree */ rc = of_scan_flat_dt(htab_dt_scan_page_sizes, NULL); - if (rc != 0) /* Found */ - goto found; - - /* - * Not in the device-tree, let's fallback on known size - * list for 16M capable GP & GR - */ - if (mmu_has_feature(MMU_FTR_16M_PAGE)) + if (rc == 0 && early_mmu_has_feature(MMU_FTR_16M_PAGE)) { + /* + * Nothing in the device-tree, but the CPU supports 16M pages, + * so let's fallback on a known size list for 16M capable CPUs. + */ memcpy(mmu_psize_defs, mmu_psize_defaults_gp, sizeof(mmu_psize_defaults_gp)); -found: + } + +#ifdef CONFIG_HUGETLB_PAGE + /* Reserve 16G huge page memory sections for huge pages */ + of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); +#endif /* CONFIG_HUGETLB_PAGE */ +} + +static void __init htab_init_page_sizes(void) +{ if (!debug_pagealloc_enabled()) { /* * Pick a size for the linear mapping. Currently, we only @@ -630,11 +631,6 @@ found: ,mmu_psize_defs[mmu_vmemmap_psize].shift #endif ); - -#ifdef CONFIG_HUGETLB_PAGE - /* Reserve 16G huge page memory sections for huge pages */ - of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); -#endif /* CONFIG_HUGETLB_PAGE */ } static int __init htab_dt_scan_pftsize(unsigned long node, @@ -759,12 +755,6 @@ static void __init htab_initialize(void) DBG(" -> htab_initialize()\n"); - /* Initialize segment sizes */ - htab_init_seg_sizes(); - - /* Initialize page sizes */ - htab_init_page_sizes(); - if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) { mmu_kernel_ssize = MMU_SEGSIZE_1T; mmu_highuser_ssize = MMU_SEGSIZE_1T; @@ -885,8 +875,19 @@ static void __init htab_initialize(void) #undef KB #undef MB +void __init hash__early_init_devtree(void) +{ + /* Initialize segment sizes */ + of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL); + + /* Initialize page sizes */ + htab_scan_page_sizes(); +} + void __init hash__early_init_mmu(void) { + htab_init_page_sizes(); + /* * initialize page table size */ diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 1e11559e1aac..35254a678456 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -5,39 +5,34 @@ #include <asm/cacheflush.h> #include <asm/machdep.h> #include <asm/mman.h> +#include <asm/tlb.h> void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { - unsigned long ap, shift; + int psize; struct hstate *hstate = hstate_file(vma->vm_file); - shift = huge_page_shift(hstate); - if (shift == mmu_psize_defs[MMU_PAGE_2M].shift) - ap = mmu_get_ap(MMU_PAGE_2M); - else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift) - ap = mmu_get_ap(MMU_PAGE_1G); - else { - WARN(1, "Wrong huge page shift\n"); - return ; - } - radix___flush_tlb_page(vma->vm_mm, vmaddr, ap, 0); + psize = hstate_get_psize(hstate); + radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, psize); } void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { - unsigned long ap, shift; + int psize; struct hstate *hstate = hstate_file(vma->vm_file); - shift = huge_page_shift(hstate); - if (shift == mmu_psize_defs[MMU_PAGE_2M].shift) - ap = mmu_get_ap(MMU_PAGE_2M); - else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift) - ap = mmu_get_ap(MMU_PAGE_1G); - else { - WARN(1, "Wrong huge page shift\n"); - return ; - } - radix___local_flush_tlb_page(vma->vm_mm, vmaddr, ap, 0); + psize = hstate_get_psize(hstate); + radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, psize); +} + +void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + int psize; + struct hstate *hstate = hstate_file(vma->vm_file); + + psize = hstate_get_psize(hstate); + radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize); } /* diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 33709bdb0419..16ada1eb7e26 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -411,3 +411,25 @@ struct page *realmode_pfn_to_page(unsigned long pfn) EXPORT_SYMBOL_GPL(realmode_pfn_to_page); #endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */ + +#ifdef CONFIG_PPC_STD_MMU_64 +static bool disable_radix; +static int __init parse_disable_radix(char *p) +{ + disable_radix = true; + return 0; +} +early_param("disable_radix", parse_disable_radix); + +void __init mmu_early_init_devtree(void) +{ + /* Disable radix mode based on kernel command line. */ + if (disable_radix) + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + + if (early_radix_enabled()) + radix__early_init_devtree(); + else + hash__early_init_devtree(); +} +#endif /* CONFIG_PPC_STD_MMU_64 */ diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 670318766545..34079302cc17 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -14,6 +14,9 @@ #include "mmu_decl.h" #include <trace/events/thp.h> +int (*register_process_table)(unsigned long base, unsigned long page_size, + unsigned long tbl_size); + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is called when relaxing access to a hugepage. It's also called in the page @@ -33,7 +36,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, changed = !pmd_same(*(pmdp), entry); if (changed) { __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } @@ -66,7 +69,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); /* * This ensures that generic code that rely on IRQ disabling * to prevent a parallel THP split work as expected. diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 003ff48a11b6..af897d91d09f 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -171,7 +171,7 @@ redo: * of process table here. But our linear mapping also enable us to use * physical address here. */ - ppc_md.register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); + register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd); } @@ -198,7 +198,7 @@ static void __init radix_init_partition_table(void) void __init radix_init_native(void) { - ppc_md.register_process_table = native_register_process_table; + register_process_table = native_register_process_table; } static int __init get_idx_from_shift(unsigned int shift) @@ -264,7 +264,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, return 1; } -static void __init radix_init_page_sizes(void) +void __init radix__early_init_devtree(void) { int rc; @@ -343,7 +343,6 @@ void __init radix__early_init_mmu(void) __pte_frag_nr = H_PTE_FRAG_NR; __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; - radix_init_page_sizes(); if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); lpcr = mfspr(SPRN_LPCR); diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 88a307504b5a..0b6fb244d0a1 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -225,7 +225,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, if (!is_vm_hugetlb_page(vma)) assert_pte_locked(vma->vm_mm, address); __ptep_set_access_flags(ptep, entry); - flush_tlb_page_nohash(vma, address); + flush_tlb_page(vma, address); } return changed; } diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index e1f22700fb16..48df05ef5231 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -140,10 +140,11 @@ void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) } EXPORT_SYMBOL(radix__local_flush_tlb_pwc); -void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - unsigned long ap, int nid) +void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize) { unsigned long pid; + unsigned long ap = mmu_get_ap(psize); preempt_disable(); pid = mm ? mm->context.id : 0; @@ -159,18 +160,12 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd if (vma && is_vm_hugetlb_page(vma)) return __local_flush_hugetlb_page(vma, vmaddr); #endif - radix___local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, - mmu_get_ap(mmu_virtual_psize), 0); + radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr, + mmu_virtual_psize); } EXPORT_SYMBOL(radix__local_flush_tlb_page); #ifdef CONFIG_SMP -static int mm_is_core_local(struct mm_struct *mm) -{ - return cpumask_subset(mm_cpumask(mm), - topology_sibling_cpumask(smp_processor_id())); -} - void radix__flush_tlb_mm(struct mm_struct *mm) { unsigned long pid; @@ -221,10 +216,11 @@ no_context: } EXPORT_SYMBOL(radix__flush_tlb_pwc); -void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - unsigned long ap, int nid) +void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize) { unsigned long pid; + unsigned long ap = mmu_get_ap(psize); preempt_disable(); pid = mm ? mm->context.id : 0; @@ -250,8 +246,8 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) if (vma && is_vm_hugetlb_page(vma)) return flush_hugetlb_page(vma, vmaddr); #endif - radix___flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, - mmu_get_ap(mmu_virtual_psize), 0); + radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr, + mmu_virtual_psize); } EXPORT_SYMBOL(radix__flush_tlb_page); @@ -299,8 +295,65 @@ static int radix_get_mmu_psize(int page_size) void radix__tlb_flush(struct mmu_gather *tlb) { + int psize = 0; struct mm_struct *mm = tlb->mm; - radix__flush_tlb_mm(mm); + int page_size = tlb->page_size; + + psize = radix_get_mmu_psize(page_size); + /* + * if page size is not something we understand, do a full mm flush + */ + if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all) + radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize); + else + radix__flush_tlb_mm(mm); +} + +#define TLB_FLUSH_ALL -1UL +/* + * Number of pages above which we will do a bcast tlbie. Just a + * number at this point copied from x86 + */ +static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; + +void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize) +{ + unsigned long pid; + unsigned long addr; + int local = mm_is_core_local(mm); + unsigned long ap = mmu_get_ap(psize); + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + unsigned long page_size = 1UL << mmu_psize_defs[psize].shift; + + + preempt_disable(); + pid = mm ? mm->context.id : 0; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto err_out; + + if (end == TLB_FLUSH_ALL || + (end - start) > tlb_single_page_flush_ceiling * page_size) { + if (local) + _tlbiel_pid(pid, RIC_FLUSH_TLB); + else + _tlbie_pid(pid, RIC_FLUSH_TLB); + goto err_out; + } + for (addr = start; addr < end; addr += page_size) { + + if (local) + _tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); + else { + if (lock_tlbie) + raw_spin_lock(&native_tlbie_lock); + _tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); + if (lock_tlbie) + raw_spin_unlock(&native_tlbie_lock); + } + } +err_out: + preempt_enable(); } void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa, @@ -340,3 +393,10 @@ void radix__flush_tlb_lpid(unsigned long lpid) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } EXPORT_SYMBOL(radix__flush_tlb_lpid); + +void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_2M); +} +EXPORT_SYMBOL(radix__flush_pmd_tlb_range); diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c index 558e30cce33e..702d7689d714 100644 --- a/arch/powerpc/mm/tlb_hash32.c +++ b/arch/powerpc/mm/tlb_hash32.c @@ -49,17 +49,6 @@ void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr) EXPORT_SYMBOL(flush_hash_entry); /* - * Called by ptep_set_access_flags, must flush on CPUs for which the - * DSI handler can't just "fixup" the TLB on a write fault - */ -void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr) -{ - if (Hash != 0) - return; - _tlbie(addr); -} - -/* * Called at the end of a mmu_gather operation to make sure the * TLB flush is completely done. */ diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index f4668488512c..050badc0ebd3 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -215,12 +215,6 @@ EXPORT_SYMBOL(local_flush_tlb_page); static DEFINE_RAW_SPINLOCK(tlbivax_lock); -static int mm_is_core_local(struct mm_struct *mm) -{ - return cpumask_subset(mm_cpumask(mm), - topology_sibling_cpumask(smp_processor_id())); -} - struct tlb_flush_param { unsigned long addr; unsigned int pid; diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h index cda6fcb809ca..6447dc1c3d89 100644 --- a/arch/powerpc/perf/power9-events-list.h +++ b/arch/powerpc/perf/power9-events-list.h @@ -34,15 +34,15 @@ EVENT(PM_L1_ICACHE_MISS, 0x200fd) /* Instruction Demand sectors wriittent into IL1 */ EVENT(PM_L1_DEMAND_WRITE, 0x0408c) /* Instruction prefetch written into IL1 */ -EVENT(PM_IC_PREF_WRITE, 0x0408e) +EVENT(PM_IC_PREF_WRITE, 0x0488c) /* The data cache was reloaded from local core's L3 due to a demand load */ EVENT(PM_DATA_FROM_L3, 0x4c042) /* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ EVENT(PM_DATA_FROM_L3MISS, 0x300fe) /* All successful D-side store dispatches for this thread */ -EVENT(PM_L2_ST, 0x16081) +EVENT(PM_L2_ST, 0x16880) /* All successful D-side store dispatches for this thread that were L2 Miss */ -EVENT(PM_L2_ST_MISS, 0x26081) +EVENT(PM_L2_ST_MISS, 0x26880) /* Total HW L3 prefetches(Load+store) */ EVENT(PM_L3_PREF_ALL, 0x4e052) /* Data PTEG reload */ diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c index d17e98bc0c10..e7d075077cb0 100644 --- a/arch/powerpc/platforms/cell/pervasive.c +++ b/arch/powerpc/platforms/cell/pervasive.c @@ -35,6 +35,7 @@ #include <asm/pgtable.h> #include <asm/reg.h> #include <asm/cell-regs.h> +#include <asm/cpu_has_feature.h> #include "pervasive.h" diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c index 89098f320ad5..ee9891734149 100644 --- a/arch/powerpc/xmon/ppc-dis.c +++ b/arch/powerpc/xmon/ppc-dis.c @@ -20,6 +20,7 @@ along with this file; see the file COPYING. If not, write to the Free Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA. */ #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> #include "nonstdio.h" #include "ansidecl.h" #include "ppc.h" diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 70b172ba41ce..b59ee077a596 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -382,6 +382,19 @@ typedef struct elf64_shdr { #define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ #define NT_PPC_SPE 0x101 /* PowerPC SPE/EVR registers */ #define NT_PPC_VSX 0x102 /* PowerPC VSX registers */ +#define NT_PPC_TAR 0x103 /* Target Address Register */ +#define NT_PPC_PPR 0x104 /* Program Priority Register */ +#define NT_PPC_DSCR 0x105 /* Data Stream Control Register */ +#define NT_PPC_EBB 0x106 /* Event Based Branch Registers */ +#define NT_PPC_PMU 0x107 /* Performance Monitor Registers */ +#define NT_PPC_TM_CGPR 0x108 /* TM checkpointed GPR Registers */ +#define NT_PPC_TM_CFPR 0x109 /* TM checkpointed FPR Registers */ +#define NT_PPC_TM_CVMX 0x10a /* TM checkpointed VMX Registers */ +#define NT_PPC_TM_CVSX 0x10b /* TM checkpointed VSX Registers */ +#define NT_PPC_TM_SPR 0x10c /* TM Special Purpose Registers */ +#define NT_PPC_TM_CTAR 0x10d /* TM checkpointed Target Address Register */ +#define NT_PPC_TM_CPPR 0x10e /* TM checkpointed Program Priority Register */ +#define NT_PPC_TM_CDSCR 0x10f /* TM checkpointed Data Stream Control Register */ #define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ #define NT_386_IOPERM 0x201 /* x86 io permission bitmap (1=deny) */ #define NT_X86_XSTATE 0x202 /* x86 extended state using xsave */ diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 20400055f177..93ad6c1fb9b6 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -288,6 +288,9 @@ void __init jump_label_init(void) BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); + if (static_key_initialized) + return; + jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ef968306fd5b..b9aa1b0b38b0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3942,6 +3942,14 @@ same_page: return i ? i : -EFAULT; } +#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +/* + * ARCHes with special requirements for evicting HUGETLB backing TLB entries can + * implement this. + */ +#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#endif + unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot) { @@ -4002,7 +4010,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. */ - flush_tlb_range(vma, start, end); + flush_hugetlb_tlb_range(vma, start, end); mmu_notifier_invalidate_range(mm, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(mm, start, end); |