Commit 2cfd716d authored by Linus Torvalds's avatar Linus Torvalds

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
  ...
parents 755b20f4 eea8148c
......@@ -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
......
......@@ -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
......@@ -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__ */
/*
......
......@@ -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_ */
......@@ -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)
{
......
......@@ -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,
......
......@@ -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())
......
......@@ -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,
......
#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 */
......@@ -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__ */
......
......@@ -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;
......
......@@ -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))
......
......@@ -24,6 +24,7 @@
#include <linux/spinlock.h>
#include <asm/cputable.h>
#include <asm/cpu_has_feature.h>
typedef struct {
unsigned int base;
......
......@@ -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)
......
......@@ -22,7 +22,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
asm_volatile_goto("1:\n\t"
"nop\n\t"
"nop # arch_static_branch\n\t"
".pushsection __jump_table, \"aw\"\n\t"
JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
".popsection \n\t"
......@@ -36,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
asm_volatile_goto("1:\n\t"
"b %l[l_yes]\n\t"
"b %l[l_yes] # arch_static_branch_jump\n\t"
".pushsection __jump_table, \"aw\"\n\t"
JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
".popsection \n\t"
......
......@@ -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;
......
......@@ -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);
......
......@@ -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()
......
......@@ -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_ */
......@@ -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; \
......
......@@ -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
......
......@@ -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;
}
......
......@@ -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 */
......@@ -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)
......
......@@ -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);
......
......@@ -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];
......
......@@ -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;
......
......@@ -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
......@@ -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 */
......
......@@ -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"
......
......@@ -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)
......
......@@ -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);
......
......@@ -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);
......
......@@ -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)
{
......
......@@ -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 */
......
This diff is collapsed.
......@@ -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"
......
......@@ -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...)
......
......@@ -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
......
......@@ -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>
......
......@@ -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
......
......@@ -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;
}
......@@ -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 @@ static void __init htab_init_page_sizes(void)
,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
*/
......
......@@ -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);
}
/*
......
......@@ -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 */
......@@ -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.
......
......@@ -171,7 +171,7 @@ static void __init radix_init_pgtable(void)
* 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);
......
......@@ -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;
}
......
......@@ -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 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
}
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);
......@@ -48,17 +48,6 @@ 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.
......
......@@ -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;
......
......@@ -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 */
......
......@@ -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"
......
......@@ -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"
......
......@@ -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 */
......
......@@ -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);
......
......@@ -3942,6 +3942,14 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
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);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment