diff options
Diffstat (limited to 'arch/sparc')
67 files changed, 1167 insertions, 321 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 165ecdd24d22..68ac5c7cd982 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -44,6 +44,7 @@ config SPARC select CPU_NO_EFFICIENT_FFS select HAVE_ARCH_HARDENED_USERCOPY select PROVE_LOCKING_SMALL if PROVE_LOCKING + select ARCH_WANT_RELAX_ORDER config SPARC32 def_bool !64BIT @@ -155,6 +156,9 @@ config PGTABLE_LEVELS default 4 if 64BIT default 3 +config ARCH_SUPPORTS_UPROBES + def_bool y if SPARC64 + source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 3583d676a916..b2e650d1764f 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -213,6 +213,7 @@ CONFIG_SCHEDSTATS=y # CONFIG_RCU_CPU_STALL_DETECTOR is not set CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_UPROBE_EVENTS=y CONFIG_KEYS=y CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_TEST=m diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index cfc918067f80..e9e837bc3158 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += div64.h generic-y += emergency-restart.h generic-y += exec.h @@ -15,7 +14,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h -generic-y += mutex.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h index eff748c871ec..e25af5fc99fd 100644 --- a/arch/sparc/include/asm/checksum_32.h +++ b/arch/sparc/include/asm/checksum_32.h @@ -16,7 +16,7 @@ */ #include <linux/in6.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> /* computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h index 0395d75322e9..96a5ed58cea6 100644 --- a/arch/sparc/include/asm/checksum_64.h +++ b/arch/sparc/include/asm/checksum_64.h @@ -16,7 +16,7 @@ */ #include <linux/in6.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> /* computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h index 1180ae254154..69cc627779f2 100644 --- a/arch/sparc/include/asm/dma-mapping.h +++ b/arch/sparc/include/asm/dma-mapping.h @@ -18,20 +18,20 @@ static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, */ } -extern struct dma_map_ops *dma_ops; -extern struct dma_map_ops *leon_dma_ops; -extern struct dma_map_ops pci32_dma_ops; +extern const struct dma_map_ops *dma_ops; +extern const struct dma_map_ops *leon_dma_ops; +extern const struct dma_map_ops pci32_dma_ops; extern struct bus_type pci_bus_type; -static inline struct dma_map_ops *get_dma_ops(struct device *dev) +static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { #ifdef CONFIG_SPARC_LEON if (sparc_cpu_model == sparc_leon) return leon_dma_ops; #endif #if defined(CONFIG_SPARC32) && defined(CONFIG_PCI) - if (dev->bus == &pci_bus_type) + if (bus == &pci_bus_type) return &pci32_dma_ops; #endif return dma_ops; diff --git a/arch/sparc/include/asm/kdebug_64.h b/arch/sparc/include/asm/kdebug_64.h index 04465de8f3b5..867286bf7b1a 100644 --- a/arch/sparc/include/asm/kdebug_64.h +++ b/arch/sparc/include/asm/kdebug_64.h @@ -10,6 +10,8 @@ enum die_val { DIE_OOPS = 1, DIE_DEBUG, /* ta 0x70 */ DIE_DEBUG_2, /* ta 0x71 */ + DIE_BPT, /* ta 0x73 */ + DIE_SSTEP, /* ta 0x74 */ DIE_DIE, DIE_TRAP, DIE_TRAP_TL1, diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index b84be675e507..d0317993e947 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -35,15 +35,15 @@ void __tsb_context_switch(unsigned long pgd_pa, static inline void tsb_context_switch(struct mm_struct *mm) { __tsb_context_switch(__pa(mm->pgd), - &mm->context.tsb_block[0], + &mm->context.tsb_block[MM_TSB_BASE], #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - (mm->context.tsb_block[1].tsb ? - &mm->context.tsb_block[1] : + (mm->context.tsb_block[MM_TSB_HUGE].tsb ? + &mm->context.tsb_block[MM_TSB_HUGE] : NULL) #else NULL #endif - , __pa(&mm->context.tsb_descr[0])); + , __pa(&mm->context.tsb_descr[MM_TSB_BASE])); } void tsb_grow(struct mm_struct *mm, diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index c1263fc390db..f294dd42fc7d 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -17,7 +17,8 @@ #define HPAGE_SHIFT 23 #define REAL_HPAGE_SHIFT 22 - +#define HPAGE_256MB_SHIFT 28 +#define HPAGE_64K_SHIFT 16 #define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT) #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) @@ -26,6 +27,7 @@ #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT)) +#define HUGE_MAX_HSTATE 3 #endif #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 1fb317fbc0b3..7932a4a37817 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -375,7 +375,10 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot) #define pgprot_noncached pgprot_noncached #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) -static inline unsigned long __pte_huge_mask(void) +extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable); +#define arch_make_huge_pte arch_make_huge_pte +static inline unsigned long __pte_default_huge_mask(void) { unsigned long mask; @@ -395,12 +398,14 @@ static inline unsigned long __pte_huge_mask(void) static inline pte_t pte_mkhuge(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_PMD_HUGE | __pte_huge_mask()); + return __pte(pte_val(pte) | __pte_default_huge_mask()); } -static inline bool is_hugetlb_pte(pte_t pte) +static inline bool is_default_hugetlb_pte(pte_t pte) { - return !!(pte_val(pte) & __pte_huge_mask()); + unsigned long mask = __pte_default_huge_mask(); + + return (pte_val(pte) & mask) == mask; } static inline bool is_hugetlb_pmd(pmd_t pmd) @@ -826,7 +831,7 @@ static inline unsigned long __pmd_page(pmd_t pmd) #define pgd_page_vaddr(pgd) \ ((unsigned long) __va(pgd_val(pgd))) #define pgd_present(pgd) (pgd_val(pgd) != 0U) -#define pgd_clear(pgdp) (pgd_val(*(pgd)) = 0UL) +#define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0UL) static inline unsigned long pud_large(pud_t pud) { @@ -875,10 +880,12 @@ static inline unsigned long pud_pfn(pud_t pud) /* Actual page table PTE updates. */ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, - pte_t *ptep, pte_t orig, int fullmm); + pte_t *ptep, pte_t orig, int fullmm, + unsigned int hugepage_shift); static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, - pte_t *ptep, pte_t orig, int fullmm) + pte_t *ptep, pte_t orig, int fullmm, + unsigned int hugepage_shift) { /* It is more efficient to let flush_tlb_kernel_range() * handle init_mm tlb flushes. @@ -887,7 +894,7 @@ static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, * and SUN4V pte layout, so this inline test is fine. */ if (likely(mm != &init_mm) && pte_accessible(mm, orig)) - tlb_batch_add(mm, vaddr, ptep, orig, fullmm); + tlb_batch_add(mm, vaddr, ptep, orig, fullmm, hugepage_shift); } #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR @@ -906,7 +913,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t orig = *ptep; *ptep = pte; - maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm); + maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm, PAGE_SHIFT); } #define set_pte_at(mm,addr,ptep,pte) \ diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index 812fd08f3e62..365d4cb267b4 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -119,7 +119,6 @@ extern struct task_struct *last_task_used_math; int do_mathemu(struct pt_regs *regs, struct task_struct *fpt); #define cpu_relax() barrier() -#define cpu_relax_lowlatency() cpu_relax() extern void (*sparc_idle)(void); diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index ce2595c89471..6448cfc8292f 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -216,7 +216,6 @@ unsigned long get_wchan(struct task_struct *task); "nop\n\t" \ ".previous" \ ::: "memory") -#define cpu_relax_lowlatency() cpu_relax() /* Prefetch support. This is tuned for UltraSPARC-III and later. * UltraSPARC-I will treat these as nops, and UltraSPARC-II has diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index bac6a946ee00..ca57f08bd3db 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -61,7 +61,10 @@ extern union global_cpu_snapshot global_cpu_snapshot[NR_CPUS]; #define force_successful_syscall_return() set_thread_noerror(1) #define user_mode(regs) (!((regs)->tstate & TSTATE_PRIV)) #define instruction_pointer(regs) ((regs)->tpc) -#define instruction_pointer_set(regs, val) ((regs)->tpc = (val)) +#define instruction_pointer_set(regs, val) do { \ + (regs)->tpc = (val); \ + (regs)->tnpc = (val)+4; \ + } while (0) #define user_stack_pointer(regs) ((regs)->u_regs[UREG_FP]) static inline int is_syscall_success(struct pt_regs *regs) { @@ -77,6 +80,36 @@ unsigned long profile_pc(struct pt_regs *); #else #define profile_pc(regs) instruction_pointer(regs) #endif + +#define MAX_REG_OFFSET (offsetof(struct pt_regs, magic)) + +extern int regs_query_register_offset(const char *name); + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten + * @offset: offset number of the register. + * + * regs_get_register returns the value of a register whose + * offset from @regs. The @offset is the offset of the register + * in struct pt_regs. If @offset is bigger than MAX_REG_OFFSET, + * this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned long offset) +{ + if (unlikely(offset >= MAX_REG_OFFSET)) + return 0; + if (offset == PT_V9_Y) + return *(unsigned int *)((unsigned long)regs + offset); + return *(unsigned long *)((unsigned long)regs + offset); +} + +/* Valid only for Kernel mode traps. */ +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + return regs->u_regs[UREG_I6]; +} #else /* __ASSEMBLY__ */ #endif /* __ASSEMBLY__ */ #else /* (defined(__sparc__) && defined(__arch64__)) */ diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 29d64b1758ed..478bf6bb4598 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -59,8 +59,11 @@ extern atomic_t dcpage_flushes; extern atomic_t dcpage_flushes_xcall; extern int sysctl_tsb_ratio; -#endif +#ifdef CONFIG_SERIAL_SUNHV +void sunhv_migrate_hvcons_irq(int cpu); +#endif +#endif void sun_do_break(void); extern int stop_a_enabled; extern int scons_pwroff; diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index 3d7b925f6516..38a24f257b85 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -180,7 +180,7 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ /* flag bit 4 is available */ #define TIF_UNALIGNED 5 /* allowed to do unaligned accesses */ -/* flag bit 6 is available */ +#define TIF_UPROBE 6 /* breakpointed or singlestepped */ #define TIF_32BIT 7 /* 32-bit binary */ #define TIF_NOHZ 8 /* in adaptive nohz mode */ #define TIF_SECCOMP 9 /* secure computing */ @@ -199,6 +199,7 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) #define _TIF_UNALIGNED (1<<TIF_UNALIGNED) +#define _TIF_UPROBE (1<<TIF_UPROBE) #define _TIF_32BIT (1<<TIF_32BIT) #define _TIF_NOHZ (1<<TIF_NOHZ) #define _TIF_SECCOMP (1<<TIF_SECCOMP) @@ -209,7 +210,8 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define _TIF_USER_WORK_MASK ((0xff << TI_FLAG_WSAVED_SHIFT) | \ _TIF_DO_NOTIFY_RESUME_MASK | \ _TIF_NEED_RESCHED) -#define _TIF_DO_NOTIFY_RESUME_MASK (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING) +#define _TIF_DO_NOTIFY_RESUME_MASK (_TIF_NOTIFY_RESUME | \ + _TIF_SIGPENDING | _TIF_UPROBE) #define is_32bit_task() (test_thread_flag(TIF_32BIT)) diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index a8e192e90700..54be88a6774c 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -8,7 +8,7 @@ #define TLB_BATCH_NR 192 struct tlb_batch { - bool huge; + unsigned int hugepage_shift; struct mm_struct *mm; unsigned long tlb_nr; unsigned long active; @@ -17,7 +17,8 @@ struct tlb_batch { void flush_tsb_kernel_range(unsigned long start, unsigned long end); void flush_tsb_user(struct tlb_batch *tb); -void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge); +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, + unsigned int hugepage_shift); /* TLB flush operations. */ diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index 7b4898a36eee..ad5293f89680 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -41,6 +41,9 @@ int __node_distance(int, int); #endif /* !(CONFIG_NUMA) */ #ifdef CONFIG_SMP + +#include <asm/cpudata.h> + #define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id) #define topology_core_id(cpu) (cpu_data(cpu).core_id) #define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu]) diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h index 781b9f1dbdc2..82e7df296abc 100644 --- a/arch/sparc/include/asm/ttable.h +++ b/arch/sparc/include/asm/ttable.h @@ -186,6 +186,12 @@ #define KPROBES_TRAP(lvl) TRAP_ARG(bad_trap, lvl) #endif +#ifdef CONFIG_UPROBES +#define UPROBES_TRAP(lvl) TRAP_ARG(uprobe_trap, lvl) +#else +#define UPROBES_TRAP(lvl) TRAP_ARG(bad_trap, lvl) +#endif + #ifdef CONFIG_KGDB #define KGDB_TRAP(lvl) TRAP_IRQ(kgdb_trap, lvl) #else diff --git a/arch/sparc/include/asm/uprobes.h b/arch/sparc/include/asm/uprobes.h new file mode 100644 index 000000000000..36196c17aff8 --- /dev/null +++ b/arch/sparc/include/asm/uprobes.h @@ -0,0 +1,59 @@ +#ifndef _ASM_UPROBES_H +#define _ASM_UPROBES_H +/* + * User-space Probes (UProbes) for sparc + * + * Copyright (C) 2013 Oracle, Inc. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + * + * Authors: + * Jose E. Marchesi <jose.marchesi@oracle.com> + * Eric Saint Etienne <eric.saint.etienne@oracle.com> + */ + +typedef u32 uprobe_opcode_t; + +#define MAX_UINSN_BYTES 4 +#define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES * 2) + +#define UPROBE_SWBP_INSN_SIZE 4 +#define UPROBE_SWBP_INSN 0x91d02073 /* ta 0x73 */ +#define UPROBE_STP_INSN 0x91d02074 /* ta 0x74 */ + +#define ANNUL_BIT (1 << 29) + +struct arch_uprobe { + union { + u8 insn[MAX_UINSN_BYTES]; + u32 ixol; + }; +}; + +struct arch_uprobe_task { + u64 saved_tpc; + u64 saved_tnpc; +}; + +struct task_struct; +struct notifier_block; + +extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); +extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); +extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); +extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); + +#endif /* _ASM_UPROBES_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 31aede3af088..a25dc32f5d6a 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -86,6 +86,8 @@ #define SO_CNX_ADVICE 0x0037 +#define SCM_TIMESTAMPING_OPT_STATS 0x0038 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index fa3c02d41138..aac609889ee4 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -116,4 +116,5 @@ obj-$(CONFIG_COMPAT) += $(audit--y) pc--$(CONFIG_PERF_EVENTS) := perf_event.o obj-$(CONFIG_SPARC64) += $(pc--y) +obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_SPARC64) += jump_label.o diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index 742f6c4436bf..9ebc37e7d64c 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -17,7 +17,7 @@ #include <asm/io.h> #include <asm/oplib.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/auxio.h> #include <asm/apc.h> #include <asm/processor.h> diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 852a3291db96..c63ba99ca551 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -415,7 +415,7 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr, ctx = (iopte_val(*base) & IOPTE_CONTEXT) >> 47UL; /* Step 1: Kick data out of streaming buffers if necessary. */ - if (strbuf->strbuf_enabled) + if (strbuf->strbuf_enabled && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction); @@ -640,7 +640,7 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist, base = iommu->page_table + entry; dma_handle &= IO_PAGE_MASK; - if (strbuf->strbuf_enabled) + if (strbuf->strbuf_enabled && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) strbuf_flush(strbuf, iommu, dma_handle, ctx, npages, direction); @@ -741,7 +741,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev, spin_unlock_irqrestore(&iommu->lock, flags); } -static struct dma_map_ops sun4u_dma_ops = { +static const struct dma_map_ops sun4u_dma_ops = { .alloc = dma_4u_alloc_coherent, .free = dma_4u_free_coherent, .map_page = dma_4u_map_page, @@ -752,7 +752,7 @@ static struct dma_map_ops sun4u_dma_ops = { .sync_sg_for_cpu = dma_4u_sync_sg_for_cpu, }; -struct dma_map_ops *dma_ops = &sun4u_dma_ops; +const struct dma_map_ops *dma_ops = &sun4u_dma_ops; EXPORT_SYMBOL(dma_ops); int dma_supported(struct device *dev, u64 device_mask) diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 2344103414d1..cf20033a1458 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -401,7 +401,7 @@ static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg, BUG(); } -static struct dma_map_ops sbus_dma_ops = { +static const struct dma_map_ops sbus_dma_ops = { .alloc = sbus_alloc_coherent, .free = sbus_free_coherent, .map_page = sbus_map_page, @@ -527,7 +527,7 @@ static dma_addr_t pci32_map_page(struct device *dev, struct page *page, static void pci32_unmap_page(struct device *dev, dma_addr_t ba, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (dir != PCI_DMA_TODEVICE) + if (dir != PCI_DMA_TODEVICE && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_make_coherent(ba, PAGE_ALIGN(size)); } @@ -572,7 +572,7 @@ static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl, struct scatterlist *sg; int n; - if (dir != PCI_DMA_TODEVICE) { + if (dir != PCI_DMA_TODEVICE && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { for_each_sg(sgl, sg, nents, n) { dma_make_coherent(sg_phys(sg), PAGE_ALIGN(sg->length)); } @@ -637,7 +637,7 @@ static void pci32_sync_sg_for_device(struct device *device, struct scatterlist * } } -struct dma_map_ops pci32_dma_ops = { +const struct dma_map_ops pci32_dma_ops = { .alloc = pci32_alloc_coherent, .free = pci32_free_coherent, .map_page = pci32_map_page, @@ -652,10 +652,10 @@ struct dma_map_ops pci32_dma_ops = { EXPORT_SYMBOL(pci32_dma_ops); /* leon re-uses pci32_dma_ops */ -struct dma_map_ops *leon_dma_ops = &pci32_dma_ops; +const struct dma_map_ops *leon_dma_ops = &pci32_dma_ops; EXPORT_SYMBOL(leon_dma_ops); -struct dma_map_ops *dma_ops = &sbus_dma_ops; +const struct dma_map_ops *dma_ops = &sbus_dma_ops; EXPORT_SYMBOL(dma_ops); diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 34a7930b76ef..4d0248aa0928 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -35,7 +35,7 @@ #include <asm/timer.h> #include <asm/smp.h> #include <asm/starfire.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/cache.h> #include <asm/cpudata.h> #include <asm/auxio.h> @@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask) unsigned long order = get_order(size); unsigned long p; - p = __get_free_pages(GFP_KERNEL, order); + p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!p) { prom_printf("SUN4V: Error, cannot allocate queue.\n"); prom_halt(); diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index b0377db12d83..2d13a4fc0384 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -11,7 +11,7 @@ #include <linux/context_tracking.h> #include <asm/signal.h> #include <asm/cacheflush.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> /* We do not have hardware single-stepping on sparc64. * So we implement software single-stepping with breakpoint diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c index 33cd171d933e..afcdd5e4f43f 100644 --- a/arch/sparc/kernel/leon_kernel.c +++ b/arch/sparc/kernel/leon_kernel.c @@ -349,37 +349,37 @@ void __init leon_init_timers(void) /* Find GPTIMER Timer Registers base address otherwise bail out. */ nnp = rootnp; - do { - np = of_find_node_by_name(nnp, "GAISLER_GPTIMER"); - if (!np) { - np = of_find_node_by_name(nnp, "01_011"); - if (!np) - goto bad; - } - ampopts = 0; - pp = of_find_property(np, "ampopts", &len); - if (pp) { - ampopts = *(int *)pp->value; - if (ampopts == 0) { - /* Skip this instance, resource already - * allocated by other OS */ - nnp = np; - continue; - } +retry: + np = of_find_node_by_name(nnp, "GAISLER_GPTIMER"); + if (!np) { + np = of_find_node_by_name(nnp, "01_011"); + if (!np) + goto bad; + } + + ampopts = 0; + pp = of_find_property(np, "ampopts", &len); + if (pp) { + ampopts = *(int *)pp->value; + if (ampopts == 0) { + /* Skip this instance, resource already + * allocated by other OS */ + nnp = np; + goto retry; } + } + + /* Select Timer-Instance on Timer Core. Default is zero */ + leon3_gptimer_idx = ampopts & 0x7; - /* Select Timer-Instance on Timer Core. Default is zero */ - leon3_gptimer_idx = ampopts & 0x7; - - pp = of_find_property(np, "reg", &len); - if (pp) - leon3_gptimer_regs = *(struct leon3_gptimer_regs_map **) - pp->value; - pp = of_find_property(np, "interrupts", &len); - if (pp) - leon3_gptimer_irq = *(unsigned int *)pp->value; - } while (0); + pp = of_find_property(np, "reg", &len); + if (pp) + leon3_gptimer_regs = *(struct leon3_gptimer_regs_map **) + pp->value; + pp = of_find_property(np, "interrupts", &len); + if (pp) + leon3_gptimer_irq = *(unsigned int *)pp->value; if (!(leon3_gptimer_regs && leon3_irqctrl_regs && leon3_gptimer_irq)) goto bad; diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 8a6982dfd733..c0765bbf60ea 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -17,7 +17,7 @@ #include <asm/hypervisor.h> #include <asm/mdesc.h> #include <asm/prom.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/oplib.h> #include <asm/smp.h> diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index a9973bb4a1b2..95e73c63c99d 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -42,7 +42,7 @@ static int panic_on_timeout; */ atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ EXPORT_SYMBOL(nmi_active); - +static int nmi_init_done; static unsigned int nmi_hz = HZ; static DEFINE_PER_CPU(short, wd_enabled); static int endflag __initdata; @@ -153,6 +153,8 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count) void stop_nmi_watchdog(void *unused) { + if (!__this_cpu_read(wd_enabled)) + return; pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable); __this_cpu_write(wd_enabled, 0); atomic_dec(&nmi_active); @@ -207,6 +209,9 @@ error: void start_nmi_watchdog(void *unused) { + if (__this_cpu_read(wd_enabled)) + return; + __this_cpu_write(wd_enabled, 1); atomic_inc(&nmi_active); @@ -259,6 +264,8 @@ int __init nmi_init(void) } } + nmi_init_done = 1; + return err; } @@ -270,3 +277,38 @@ static int __init setup_nmi_watchdog(char *str) return 0; } __setup("nmi_watchdog=", setup_nmi_watchdog); + +/* + * sparc specific NMI watchdog enable function. + * Enables watchdog if it is not enabled already. + */ +int watchdog_nmi_enable(unsigned int cpu) +{ + if (atomic_read(&nmi_active) == -1) { + pr_warn("NMI watchdog cannot be enabled or disabled\n"); + return -1; + } + + /* + * watchdog thread could start even before nmi_init is called. + * Just Return in that case. Let nmi_init finish the init + * process first. + */ + if (!nmi_init_done) + return 0; + + smp_call_function_single(cpu, start_nmi_watchdog, NULL, 1); + + return 0; +} +/* + * sparc specific NMI watchdog disable function. + * Disables watchdog if it is not disabled already. + */ +void watchdog_nmi_disable(unsigned int cpu) +{ + if (atomic_read(&nmi_active) == -1) + pr_warn_once("NMI watchdog cannot be enabled or disabled\n"); + else + smp_call_function_single(cpu, stop_nmi_watchdog, NULL, 1); +} diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 9c1878f4fa9f..015e55a7495d 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -21,7 +21,7 @@ #include <linux/of.h> #include <linux/of_device.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> #include <asm/irq.h> #include <asm/prom.h> diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 06981cc716b6..68bec7c97cb8 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -242,6 +242,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, return ret; iommu_map_fail: + local_irq_restore(flags); iommu_tbl_range_free(tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); range_alloc_fail: @@ -414,6 +415,7 @@ bad: return DMA_ERROR_CODE; iommu_map_fail: + local_irq_restore(flags); iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); return DMA_ERROR_CODE; } @@ -478,11 +480,10 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; - atu = iommu->atu; - if (nelems == 0 || !iommu) return 0; - + atu = iommu->atu; + prot = HV_PCI_MAP_ATTR_READ; if (direction != DMA_TO_DEVICE) prot |= HV_PCI_MAP_ATTR_WRITE; @@ -668,7 +669,7 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, local_irq_restore(flags); } -static struct dma_map_ops sun4v_dma_ops = { +static const struct dma_map_ops sun4v_dma_ops = { .alloc = dma_4v_alloc_coherent, .free = dma_4v_free_coherent, .map_page = dma_4v_map_page, diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index 24384e1dc33d..a38787b84322 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -33,7 +33,7 @@ #include <asm/pcic.h> #include <asm/timex.h> #include <asm/timer.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/irq_regs.h> #include "kernel.h" diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index 97d123107ecb..f12b23f7b515 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -15,7 +15,7 @@ #include <asm/io.h> #include <asm/oplib.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/auxio.h> #include <asm/processor.h> diff --git a/arch/sparc/kernel/power.c b/arch/sparc/kernel/power.c index 1836cb965ff8..4b60f385c98f 100644 --- a/arch/sparc/kernel/power.c +++ b/arch/sparc/kernel/power.c @@ -67,9 +67,4 @@ static struct platform_driver power_driver = { }, }; -static int __init power_init(void) -{ - return platform_driver_register(&power_driver); -} - -device_initcall(power_init); +builtin_platform_driver(power_driver); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index b7780a5bef11..48ffc3e7d1dd 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -28,7 +28,7 @@ #include <asm/auxio.h> #include <asm/oplib.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 47ff5588e521..d249ca10b203 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -33,7 +33,7 @@ #include <linux/nmi.h> #include <linux/context_tracking.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c index a331fdc11a2c..eca3dc76793c 100644 --- a/arch/sparc/kernel/ptrace_32.c +++ b/arch/sparc/kernel/ptrace_32.c @@ -23,7 +23,7 @@ #include <linux/tracehook.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/cacheflush.h> #include "kernel.h" diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index ac082dd8c67d..901063c1cf7e 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -31,7 +31,7 @@ #include <asm/asi.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/psrcompat.h> #include <asm/visasm.h> #include <asm/spitfire.h> @@ -46,6 +46,43 @@ /* #define ALLOW_INIT_TRACING */ +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(n, r) \ + {.name = n, .offset = (PT_V9_##r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME("g0", G0), + REG_OFFSET_NAME("g1", G1), + REG_OFFSET_NAME("g2", G2), + REG_OFFSET_NAME("g3", G3), + REG_OFFSET_NAME("g4", G4), + REG_OFFSET_NAME("g5", G5), + REG_OFFSET_NAME("g6", G6), + REG_OFFSET_NAME("g7", G7), + + REG_OFFSET_NAME("i0", I0), + REG_OFFSET_NAME("i1", I1), + REG_OFFSET_NAME("i2", I2), + REG_OFFSET_NAME("i3", I3), + REG_OFFSET_NAME("i4", I4), + REG_OFFSET_NAME("i5", I5), + REG_OFFSET_NAME("i6", I6), + REG_OFFSET_NAME("i7", I7), + + REG_OFFSET_NAME("tstate", TSTATE), + REG_OFFSET_NAME("pc", TPC), + REG_OFFSET_NAME("npc", TNPC), + REG_OFFSET_NAME("y", Y), + REG_OFFSET_NAME("lr", I7), + + REG_OFFSET_END, +}; + /* * Called by kernel/ptrace.c when detaching.. * @@ -1107,3 +1144,20 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) if (test_thread_flag(TIF_NOHZ)) user_enter(); } + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index c4e65cb3280f..6f06058c5ae7 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -82,7 +82,7 @@ static void prom_sync_me(void) "nop\n\t" : : "r" (&trapbase)); prom_printf("PROM SYNC COMMAND...\n"); - show_free_areas(0); + show_free_areas(0, NULL); if (!is_idle_task(current)) { local_irq_enable(); sys_sync(); diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 91cc2f4ae4d9..b4096bb665b2 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -21,7 +21,7 @@ #include <linux/bitops.h> #include <linux/tracehook.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/ptrace.h> #include <asm/pgtable.h> #include <asm/psrcompat.h> diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 9c0c8fd0b292..62c3e255ae7c 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -20,7 +20,7 @@ #include <linux/bitops.h> #include <linux/tracehook.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/ptrace.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 5ee930c48f4c..965d50e833e7 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -25,7 +25,7 @@ #include <linux/bitops.h> #include <linux/context_tracking.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/ptrace.h> #include <asm/pgtable.h> #include <asm/fpumacro.h> @@ -545,6 +545,8 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long thread_info_flags) { user_exit(); + if (thread_info_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs, orig_i0); if (thread_info_flags & _TIF_NOTIFY_RESUME) { diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 8182f7caf5b1..90a02cb64e20 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -43,7 +43,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/oplib.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/starfire.h> #include <asm/tlb.h> #include <asm/sections.h> @@ -1443,6 +1443,7 @@ void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) static void stop_this_cpu(void *dummy) { + set_cpu_online(smp_processor_id(), false); prom_stopself(); } @@ -1451,9 +1452,15 @@ void smp_send_stop(void) int cpu; if (tlb_type == hypervisor) { + int this_cpu = smp_processor_id(); +#ifdef CONFIG_SERIAL_SUNHV + sunhv_migrate_hvcons_irq(this_cpu); +#endif for_each_online_cpu(cpu) { - if (cpu == smp_processor_id()) + if (cpu == this_cpu) continue; + + set_cpu_online(cpu, false); #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) { unsigned long hv_err; diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c index c59af546f522..3caed4023589 100644 --- a/arch/sparc/kernel/sstate.c +++ b/arch/sparc/kernel/sstate.c @@ -43,8 +43,8 @@ static const char poweroff_msg[32] __attribute__((aligned(32))) = "Linux powering off"; static const char rebooting_msg[32] __attribute__((aligned(32))) = "Linux rebooting"; -static const char panicing_msg[32] __attribute__((aligned(32))) = - "Linux panicing"; +static const char panicking_msg[32] __attribute__((aligned(32))) = + "Linux panicking"; static int sstate_reboot_call(struct notifier_block *np, unsigned long type, void *_unused) { @@ -76,7 +76,7 @@ static struct notifier_block sstate_reboot_notifier = { static int sstate_panic_event(struct notifier_block *n, unsigned long event, void *ptr) { - do_set_sstate(HV_SOFT_STATE_TRANSITION, panicing_msg); + do_set_sstate(HV_SOFT_STATE_TRANSITION, panicking_msg); return NOTIFY_DONE; } diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 022c30c72ebd..bca44f3e6b86 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -44,7 +44,7 @@ #include <linux/slab.h> #include <asm/types.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/fpumacro.h> #include <asm/mmu_context.h> #include <asm/compat_signal.h> diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 646988d4c1a3..fb7b185ee941 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -21,7 +21,7 @@ #include <linux/smp.h> #include <linux/ipc.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/unistd.h> #include "systbls.h" diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index fe8b8ee8e660..884c70331345 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -26,7 +26,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/utrap.h> #include <asm/unistd.h> diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c index fa8e21abb5e0..4808b6d23455 100644 --- a/arch/sparc/kernel/sysfs.c +++ b/arch/sparc/kernel/sysfs.c @@ -221,7 +221,7 @@ static struct device_attribute cpu_core_attrs[] = { static DEFINE_PER_CPU(struct cpu, cpu_devices); -static void register_cpu_online(unsigned int cpu) +static int register_cpu_online(unsigned int cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); struct device *s = &c->dev; @@ -231,11 +231,12 @@ static void register_cpu_online(unsigned int cpu) device_create_file(s, &cpu_core_attrs[i]); register_mmu_stats(s); + return 0; } -#ifdef CONFIG_HOTPLUG_CPU -static void unregister_cpu_online(unsigned int cpu) +static int unregister_cpu_online(unsigned int cpu) { +#ifdef CONFIG_HOTPLUG_CPU struct cpu *c = &per_cpu(cpu_devices, cpu); struct device *s = &c->dev; int i; @@ -243,33 +244,10 @@ static void unregister_cpu_online(unsigned int cpu) unregister_mmu_stats(s); for (i = 0; i < ARRAY_SIZE(cpu_core_attrs); i++) device_remove_file(s, &cpu_core_attrs[i]); -} -#endif - -static int sysfs_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - unsigned int cpu = (unsigned int)(long)hcpu; - - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - register_cpu_online(cpu); - break; -#ifdef CONFIG_HOTPLUG_CPU - case CPU_DEAD: - case CPU_DEAD_FROZEN: - unregister_cpu_online(cpu); - break; #endif - } - return NOTIFY_OK; + return 0; } -static struct notifier_block sysfs_cpu_nb = { - .notifier_call = sysfs_cpu_notify, -}; - static void __init check_mmu_stats(void) { unsigned long dummy1, err; @@ -294,26 +272,21 @@ static void register_nodes(void) static int __init topology_init(void) { - int cpu; + int cpu, ret; register_nodes(); check_mmu_stats(); - cpu_notifier_register_begin(); - for_each_possible_cpu(cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); register_cpu(c, cpu); - if (cpu_online(cpu)) - register_cpu_online(cpu); } - __register_cpu_notifier(&sysfs_cpu_nb); - - cpu_notifier_register_done(); - + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "sparc/topology:online", + register_cpu_online, unregister_cpu_online); + WARN_ON(ret < 0); return 0; } diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 1affabc96b08..244062bdaa56 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -148,7 +148,7 @@ static unsigned int sbus_cycles_offset(void) return offset; } -static cycle_t timer_cs_read(struct clocksource *cs) +static u64 timer_cs_read(struct clocksource *cs) { unsigned int seq, offset; u64 cycles; diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index c69b21e51efc..12a6d3555cb8 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -45,7 +45,7 @@ #include <asm/smp.h> #include <asm/sections.h> #include <asm/cpudata.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/irq_regs.h> #include "entry.h" @@ -770,7 +770,7 @@ void udelay(unsigned long usecs) } EXPORT_SYMBOL(udelay); -static cycle_t clocksource_tick_read(struct clocksource *cs) +static u64 clocksource_tick_read(struct clocksource *cs) { return tick_ops->get_tick(); } diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 4094a51b1970..dfc97a47c9a0 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -29,7 +29,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/unistd.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/fpumacro.h> #include <asm/lsu.h> #include <asm/dcu.h> @@ -85,7 +85,7 @@ static void dump_tl1_traplog(struct tl1_traplog *p) void bad_trap(struct pt_regs *regs, long lvl) { - char buffer[32]; + char buffer[36]; siginfo_t info; if (notify_die(DIE_TRAP, "bad trap", regs, @@ -116,7 +116,7 @@ void bad_trap(struct pt_regs *regs, long lvl) void bad_trap_tl1(struct pt_regs *regs, long lvl) { - char buffer[32]; + char buffer[36]; if (notify_die(DIE_TRAP_TL1, "bad trap tl1", regs, 0, lvl, SIGTRAP) == NOTIFY_STOP) @@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs) atomic_inc(&sun4v_resum_oflow_cnt); } +/* Given a set of registers, get the virtual addressi that was being accessed + * by the faulting instructions at tpc. + */ +static unsigned long sun4v_get_vaddr(struct pt_regs *regs) +{ + unsigned int insn; + + if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) { + return compute_effective_address(regs, insn, + (insn >> 25) & 0x1f); + } + return 0; +} + +/* Attempt to handle non-resumable errors generated from userspace. + * Returns true if the signal was handled, false otherwise. + */ +bool sun4v_nonresum_error_user_handled(struct pt_regs *regs, + struct sun4v_error_entry *ent) { + + unsigned int attrs = ent->err_attrs; + + if (attrs & SUN4V_ERR_ATTRS_MEMORY) { + unsigned long addr = ent->err_raddr; + siginfo_t info; + + if (addr == ~(u64)0) { + /* This seems highly unlikely to ever occur */ + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n"); + } else { + unsigned long page_cnt = DIV_ROUND_UP(ent->err_size, + PAGE_SIZE); + + /* Break the unfortunate news. */ + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n", + addr); + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Claiming %lu ages.\n", + page_cnt); + + while (page_cnt-- > 0) { + if (pfn_valid(addr >> PAGE_SHIFT)) + get_page(pfn_to_page(addr >> PAGE_SHIFT)); + addr += PAGE_SIZE; + } + } + info.si_signo = SIGKILL; + info.si_errno = 0; + info.si_trapno = 0; + force_sig_info(info.si_signo, &info, current); + + return true; + } + if (attrs & SUN4V_ERR_ATTRS_PIO) { + siginfo_t info; + + info.si_signo = SIGBUS; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)sun4v_get_vaddr(regs); + force_sig_info(info.si_signo, &info, current); + + return true; + } + + /* Default to doing nothing */ + return false; +} + /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate. * Log the event, clear the first word of the entry, and die. */ @@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset) put_cpu(); + if (!(regs->tstate & TSTATE_PRIV) && + sun4v_nonresum_error_user_handled(regs, &local_copy)) { + /* DON'T PANIC: This userspace error was handled. */ + return; + } + #ifdef CONFIG_PCI /* Check for the special PCI poke sequence. */ if (pci_poke_in_progress && pci_poke_cpu == cpu) { diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index d568c8207af7..10689cfd0ad4 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -117,26 +117,11 @@ tsb_miss_page_table_walk_sun4v_fastpath: /* Valid PTE is now in %g5. */ #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) -661: sethi %uhi(_PAGE_SZALL_4U), %g7 + sethi %uhi(_PAGE_PMD_HUGE), %g7 sllx %g7, 32, %g7 - .section .sun4v_2insn_patch, "ax" - .word 661b - mov _PAGE_SZALL_4V, %g7 - nop - .previous - - and %g5, %g7, %g2 - -661: sethi %uhi(_PAGE_SZHUGE_4U), %g7 - sllx %g7, 32, %g7 - .section .sun4v_2insn_patch, "ax" - .word 661b - mov _PAGE_SZHUGE_4V, %g7 - nop - .previous - cmp %g2, %g7 - bne,pt %xcc, 60f + andcc %g5, %g7, %g0 + be,pt %xcc, 60f nop /* It is a huge page, use huge page TSB entry address we diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S index c6dfdaa29e20..7bd8f6556352 100644 --- a/arch/sparc/kernel/ttable_64.S +++ b/arch/sparc/kernel/ttable_64.S @@ -165,7 +165,7 @@ tl0_resv169: BTRAP(0x169) BTRAP(0x16a) BTRAP(0x16b) BTRAP(0x16c) tl0_linux64: LINUX_64BIT_SYSCALL_TRAP tl0_gsctx: TRAP(sparc64_get_context) TRAP(sparc64_set_context) tl0_resv170: KPROBES_TRAP(0x170) KPROBES_TRAP(0x171) KGDB_TRAP(0x172) -tl0_resv173: BTRAP(0x173) BTRAP(0x174) BTRAP(0x175) BTRAP(0x176) BTRAP(0x177) +tl0_resv173: UPROBES_TRAP(0x173) UPROBES_TRAP(0x174) BTRAP(0x175) BTRAP(0x176) BTRAP(0x177) tl0_resv178: BTRAP(0x178) BTRAP(0x179) BTRAP(0x17a) BTRAP(0x17b) BTRAP(0x17c) tl0_resv17d: BTRAP(0x17d) BTRAP(0x17e) BTRAP(0x17f) #define BTRAPS(x) BTRAP(x) BTRAP(x+1) BTRAP(x+2) BTRAP(x+3) BTRAP(x+4) BTRAP(x+5) BTRAP(x+6) BTRAP(x+7) diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c index 32b61d1b6379..d20d4e3fd129 100644 --- a/arch/sparc/kernel/unaligned_32.c +++ b/arch/sparc/kernel/unaligned_32.c @@ -12,7 +12,7 @@ #include <linux/mm.h> #include <asm/ptrace.h> #include <asm/processor.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/smp.h> #include <linux/perf_event.h> diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index 52c00d90d4b4..cda7fd367c4f 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -16,7 +16,7 @@ #include <asm/ptrace.h> #include <asm/pstate.h> #include <asm/processor.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/smp.h> #include <linux/bitops.h> #include <linux/perf_event.h> diff --git a/arch/sparc/kernel/uprobes.c b/arch/sparc/kernel/uprobes.c new file mode 100644 index 000000000000..d852ae56ddc1 --- /dev/null +++ b/arch/sparc/kernel/uprobes.c @@ -0,0 +1,331 @@ +/* + * User-space Probes (UProbes) for sparc + * + * Copyright (C) 2013 Oracle Inc. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + * + * Authors: + * Jose E. Marchesi <jose.marchesi@oracle.com> + * Eric Saint Etienne <eric.saint.etienne@oracle.com> + */ + +#include <linux/kernel.h> +#include <linux/highmem.h> +#include <linux/uprobes.h> +#include <linux/uaccess.h> +#include <linux/sched.h> /* For struct task_struct */ +#include <linux/kdebug.h> + +#include <asm/cacheflush.h> +#include <linux/uaccess.h> + +/* Compute the address of the breakpoint instruction and return it. + * + * Note that uprobe_get_swbp_addr is defined as a weak symbol in + * kernel/events/uprobe.c. + */ +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +static void copy_to_page(struct page *page, unsigned long vaddr, + const void *src, int len) +{ + void *kaddr = kmap_atomic(page); + + memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len); + kunmap_atomic(kaddr); +} + +/* Fill in the xol area with the probed instruction followed by the + * single-step trap. Some fixups in the copied instruction are + * performed at this point. + * + * Note that uprobe_xol_copy is defined as a weak symbol in + * kernel/events/uprobe.c. + */ +void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + const u32 stp_insn = UPROBE_STP_INSN; + u32 insn = *(u32 *) src; + + /* Branches annulling their delay slot must be fixed to not do + * so. Clearing the annul bit on these instructions we can be + * sure the single-step breakpoint in the XOL slot will be + * executed. + */ + + u32 op = (insn >> 30) & 0x3; + u32 op2 = (insn >> 22) & 0x7; + + if (op == 0 && + (op2 == 1 || op2 == 2 || op2 == 3 || op2 == 5 || op2 == 6) && + (insn & ANNUL_BIT) == ANNUL_BIT) + insn &= ~ANNUL_BIT; + + copy_to_page(page, vaddr, &insn, len); + copy_to_page(page, vaddr+len, &stp_insn, 4); +} + + +/* Instruction analysis/validity. + * + * This function returns 0 on success or a -ve number on error. + */ +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, + struct mm_struct *mm, unsigned long addr) +{ + /* Any unsupported instruction? Then return -EINVAL */ + return 0; +} + +/* If INSN is a relative control transfer instruction, return the + * corrected branch destination value. + * + * Note that regs->tpc and regs->tnpc still hold the values of the + * program counters at the time of the single-step trap due to the + * execution of the UPROBE_STP_INSN at utask->xol_vaddr + 4. + * + */ +static unsigned long relbranch_fixup(u32 insn, struct uprobe_task *utask, + struct pt_regs *regs) +{ + /* Branch not taken, no mods necessary. */ + if (regs->tnpc == regs->tpc + 0x4UL) + return utask->autask.saved_tnpc + 0x4UL; + + /* The three cases are call, branch w/prediction, + * and traditional branch. + */ + if ((insn & 0xc0000000) == 0x40000000 || + (insn & 0xc1c00000) == 0x00400000 || + (insn & 0xc1c00000) == 0x00800000) { + unsigned long real_pc = (unsigned long) utask->vaddr; + unsigned long ixol_addr = utask->xol_vaddr; + + /* The instruction did all the work for us + * already, just apply the offset to the correct + * instruction location. + */ + return (real_pc + (regs->tnpc - ixol_addr)); + } + + /* It is jmpl or some other absolute PC modification instruction, + * leave NPC as-is. + */ + return regs->tnpc; +} + +/* If INSN is an instruction which writes its PC location + * into a destination register, fix that up. + */ +static int retpc_fixup(struct pt_regs *regs, u32 insn, + unsigned long real_pc) +{ + unsigned long *slot = NULL; + int rc = 0; + + /* Simplest case is 'call', which always uses %o7 */ + if ((insn & 0xc0000000) == 0x40000000) + slot = ®s->u_regs[UREG_I7]; + + /* 'jmpl' encodes the register inside of the opcode */ + if ((insn & 0xc1f80000) == 0x81c00000) { + unsigned long rd = ((insn >> 25) & 0x1f); + + if (rd <= 15) { + slot = ®s->u_regs[rd]; + } else { + unsigned long fp = regs->u_regs[UREG_FP]; + /* Hard case, it goes onto the stack. */ + flushw_all(); + + rd -= 16; + if (test_thread_64bit_stack(fp)) { + unsigned long __user *uslot = + (unsigned long __user *) (fp + STACK_BIAS) + rd; + rc = __put_user(real_pc, uslot); + } else { + unsigned int __user *uslot = (unsigned int + __user *) fp + rd; + rc = __put_user((u32) real_pc, uslot); + } + } + } + if (slot != NULL) + *slot = real_pc; + return rc; +} + +/* Single-stepping can be avoided for certain instructions: NOPs and + * instructions that can be emulated. This function determines + * whether the instruction where the uprobe is installed falls in one + * of these cases and emulates it. + * + * This function returns true if the single-stepping can be skipped, + * false otherwise. + */ +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + /* We currently only emulate NOP instructions. + */ + + if (auprobe->ixol == (1 << 24)) { + regs->tnpc += 4; + regs->tpc += 4; + return true; + } + + return false; +} + +/* Prepare to execute out of line. At this point + * current->utask->xol_vaddr points to an allocated XOL slot properly + * initialized with the original instruction and the single-stepping + * trap instruction. + * + * This function returns 0 on success, any other number on error. + */ +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + struct arch_uprobe_task *autask = ¤t->utask->autask; + + /* Save the current program counters so they can be restored + * later. + */ + autask->saved_tpc = regs->tpc; + autask->saved_tnpc = regs->tnpc; + + /* Adjust PC and NPC so the first instruction in the XOL slot + * will be executed by the user task. + */ + instruction_pointer_set(regs, utask->xol_vaddr); + + return 0; +} + +/* Prepare to resume execution after the single-step. Called after + * single-stepping. To avoid the SMP problems that can occur when we + * temporarily put back the original opcode to single-step, we + * single-stepped a copy of the instruction. + * + * This function returns 0 on success, any other number on error. + */ +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + struct arch_uprobe_task *autask = &utask->autask; + u32 insn = auprobe->ixol; + int rc = 0; + + if (utask->state == UTASK_SSTEP_ACK) { + regs->tnpc = relbranch_fixup(insn, utask, regs); + regs->tpc = autask->saved_tnpc; + rc = retpc_fixup(regs, insn, (unsigned long) utask->vaddr); + } else { + regs->tnpc = utask->vaddr+4; + regs->tpc = autask->saved_tnpc+4; + } + return rc; +} + +/* Handler for uprobe traps. This is called from the traps table and + * triggers the proper die notification. + */ +asmlinkage void uprobe_trap(struct pt_regs *regs, + unsigned long trap_level) +{ + BUG_ON(trap_level != 0x173 && trap_level != 0x174); + + /* We are only interested in user-mode code. Uprobe traps + * shall not be present in kernel code. + */ + if (!user_mode(regs)) { + local_irq_enable(); + bad_trap(regs, trap_level); + return; + } + + /* trap_level == 0x173 --> ta 0x73 + * trap_level == 0x174 --> ta 0x74 + */ + if (notify_die((trap_level == 0x173) ? DIE_BPT : DIE_SSTEP, + (trap_level == 0x173) ? "bpt" : "sstep", + regs, 0, trap_level, SIGTRAP) != NOTIFY_STOP) + bad_trap(regs, trap_level); +} + +/* Callback routine for handling die notifications. +*/ +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + int ret = NOTIFY_DONE; + struct die_args *args = (struct die_args *)data; + + /* We are only interested in userspace traps */ + if (args->regs && !user_mode(args->regs)) + return NOTIFY_DONE; + + switch (val) { + case DIE_BPT: + if (uprobe_pre_sstep_notifier(args->regs)) + ret = NOTIFY_STOP; + break; + + case DIE_SSTEP: + if (uprobe_post_sstep_notifier(args->regs)) + ret = NOTIFY_STOP; + + default: + break; + } + + return ret; +} + +/* This function gets called when a XOL instruction either gets + * trapped or the thread has a fatal signal, so reset the instruction + * pointer to its probed address. + */ +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + instruction_pointer_set(regs, utask->vaddr); +} + +/* If xol insn itself traps and generates a signal(Say, + * SIGILL/SIGSEGV/etc), then detect the case where a singlestepped + * instruction jumps back to its own address. + */ +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + return false; +} + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, + struct pt_regs *regs) +{ + unsigned long orig_ret_vaddr = regs->u_regs[UREG_I7]; + + regs->u_regs[UREG_I7] = trampoline_vaddr-8; + + return orig_ret_vaddr + 8; +} diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c index c096c624ac4d..c4ac58e483a4 100644 --- a/arch/sparc/kernel/visemul.c +++ b/arch/sparc/kernel/visemul.c @@ -10,7 +10,7 @@ #include <asm/ptrace.h> #include <asm/pstate.h> #include <asm/fpumacro.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/cacheflush.h> /* OPF field of various VIS instructions. */ diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c index 87bab0a3857a..435a467b0595 100644 --- a/arch/sparc/kernel/windows.c +++ b/arch/sparc/kernel/windows.c @@ -11,7 +11,7 @@ #include <linux/smp.h> #include <asm/cacheflush.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "kernel.h" diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c index 5ce8f2f64604..4d7e0fff054f 100644 --- a/arch/sparc/math-emu/math_32.c +++ b/arch/sparc/math-emu/math_32.c @@ -68,7 +68,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/perf_event.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "sfp-util_32.h" #include <math-emu/soft-fp.h> diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c index 034aadbff036..9647051853d3 100644 --- a/arch/sparc/math-emu/math_64.c +++ b/arch/sparc/math-emu/math_64.c @@ -15,7 +15,7 @@ #include <asm/fpumacro.h> #include <asm/ptrace.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/cacheflush.h> #include "sfp-util_64.h" diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c index a61c349448e1..db214e9931d9 100644 --- a/arch/sparc/mm/extable.c +++ b/arch/sparc/mm/extable.c @@ -3,7 +3,8 @@ */ #include <linux/module.h> -#include <asm/uaccess.h> +#include <linux/extable.h> +#include <linux/uaccess.h> void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 988acc8b1b80..e98a3f2e8f0f 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -28,6 +28,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(filp); unsigned long task_size = TASK_SIZE; struct vm_unmapped_area_info info; @@ -38,7 +39,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = min(task_size, VA_EXCLUDE_START); - info.align_mask = PAGE_MASK & ~HPAGE_MASK; + info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -58,6 +59,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long pgoff, const unsigned long flags) { + struct hstate *h = hstate_file(filp); struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; @@ -69,7 +71,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; - info.align_mask = PAGE_MASK & ~HPAGE_MASK; + info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -94,6 +96,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long task_size = TASK_SIZE; @@ -101,7 +104,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (test_thread_flag(TIF_32BIT)) task_size = STACK_TOP32; - if (len & ~HPAGE_MASK) + if (len & ~huge_page_mask(h)) return -EINVAL; if (len > task_size) return -ENOMEM; @@ -113,7 +116,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } if (addr) { - addr = ALIGN(addr, HPAGE_SIZE); + addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (task_size - len >= addr && (!vma || addr + len <= vma->vm_start)) @@ -127,17 +130,141 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, pgoff, flags); } +static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift) +{ + return entry; +} + +static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift) +{ + unsigned long hugepage_size = _PAGE_SZ4MB_4V; + + pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V; + + switch (shift) { + case HPAGE_256MB_SHIFT: + hugepage_size = _PAGE_SZ256MB_4V; + pte_val(entry) |= _PAGE_PMD_HUGE; + break; + case HPAGE_SHIFT: + pte_val(entry) |= _PAGE_PMD_HUGE; + break; + case HPAGE_64K_SHIFT: + hugepage_size = _PAGE_SZ64K_4V; + break; + default: + WARN_ONCE(1, "unsupported hugepage shift=%u\n", shift); + } + + pte_val(entry) = pte_val(entry) | hugepage_size; + return entry; +} + +static pte_t hugepage_shift_to_tte(pte_t entry, unsigned int shift) +{ + if (tlb_type == hypervisor) + return sun4v_hugepage_shift_to_tte(entry, shift); + else + return sun4u_hugepage_shift_to_tte(entry, shift); +} + +pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writeable) +{ + unsigned int shift = huge_page_shift(hstate_vma(vma)); + + return hugepage_shift_to_tte(entry, shift); +} + +static unsigned int sun4v_huge_tte_to_shift(pte_t entry) +{ + unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4V; + unsigned int shift; + + switch (tte_szbits) { + case _PAGE_SZ256MB_4V: + shift = HPAGE_256MB_SHIFT; + break; + case _PAGE_SZ4MB_4V: + shift = REAL_HPAGE_SHIFT; + break; + case _PAGE_SZ64K_4V: + shift = HPAGE_64K_SHIFT; + break; + default: + shift = PAGE_SHIFT; + break; + } + return shift; +} + +static unsigned int sun4u_huge_tte_to_shift(pte_t entry) +{ + unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4U; + unsigned int shift; + + switch (tte_szbits) { + case _PAGE_SZ256MB_4U: + shift = HPAGE_256MB_SHIFT; + break; + case _PAGE_SZ4MB_4U: + shift = REAL_HPAGE_SHIFT; + break; + case _PAGE_SZ64K_4U: + shift = HPAGE_64K_SHIFT; + break; + default: + shift = PAGE_SHIFT; + break; + } + return shift; +} + +static unsigned int huge_tte_to_shift(pte_t entry) +{ + unsigned long shift; + + if (tlb_type == hypervisor) + shift = sun4v_huge_tte_to_shift(entry); + else + shift = sun4u_huge_tte_to_shift(entry); + + if (shift == PAGE_SHIFT) + WARN_ONCE(1, "tto_to_shift: invalid hugepage tte=0x%lx\n", + pte_val(entry)); + + return shift; +} + +static unsigned long huge_tte_to_size(pte_t pte) +{ + unsigned long size = 1UL << huge_tte_to_shift(pte); + + if (size == REAL_HPAGE_SIZE) + size = HPAGE_SIZE; + return size; +} + pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; + pmd_t *pmd; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); - if (pud) - pte = (pte_t *)pmd_alloc(mm, pud, addr); + if (pud) { + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + if (sz == PMD_SHIFT) + pte = (pte_t *)pmd; + else + pte = pte_alloc_map(mm, pmd, addr); + } return pte; } @@ -146,49 +273,83 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; pud_t *pud; + pmd_t *pmd; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); if (!pgd_none(*pgd)) { pud = pud_offset(pgd, addr); - if (!pud_none(*pud)) - pte = (pte_t *)pmd_offset(pud, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) { + if (is_hugetlb_pmd(*pmd)) + pte = (pte_t *)pmd; + else + pte = pte_offset_map(pmd, addr); + } + } } + return pte; } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { + unsigned int i, nptes, orig_shift, shift; + unsigned long size; pte_t orig; + size = huge_tte_to_size(entry); + shift = size >= HPAGE_SIZE ? PMD_SHIFT : PAGE_SHIFT; + nptes = size >> shift; + if (!pte_present(*ptep) && pte_present(entry)) - mm->context.hugetlb_pte_count++; + mm->context.hugetlb_pte_count += nptes; - addr &= HPAGE_MASK; + addr &= ~(size - 1); orig = *ptep; - *ptep = entry; + orig_shift = pte_none(orig) ? PAGE_SHIFT : huge_tte_to_shift(orig); + + for (i = 0; i < nptes; i++) + ptep[i] = __pte(pte_val(entry) + (i << shift)); - /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */ - maybe_tlb_batch_add(mm, addr, ptep, orig, 0); - maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0); + maybe_tlb_batch_add(mm, addr, ptep, orig, 0, orig_shift); + /* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */ + if (size == HPAGE_SIZE) + maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0, + orig_shift); } pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { + unsigned int i, nptes, hugepage_shift; + unsigned long size; pte_t entry; entry = *ptep; + size = huge_tte_to_size(entry); + if (size >= HPAGE_SIZE) + nptes = size >> PMD_SHIFT; + else + nptes = size >> PAGE_SHIFT; + + hugepage_shift = pte_none(entry) ? PAGE_SHIFT : + huge_tte_to_shift(entry); + if (pte_present(entry)) - mm->context.hugetlb_pte_count--; + mm->context.hugetlb_pte_count -= nptes; - addr &= HPAGE_MASK; - *ptep = __pte(0UL); + addr &= ~(size - 1); + for (i = 0; i < nptes; i++) + ptep[i] = __pte(0UL); - /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */ - maybe_tlb_batch_add(mm, addr, ptep, entry, 0); - maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0); + maybe_tlb_batch_add(mm, addr, ptep, entry, 0, hugepage_shift); + /* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */ + if (size == HPAGE_SIZE) + maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0, + hugepage_shift); return entry; } diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index eb8287155279..c6afe98de4d9 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -55,17 +55,6 @@ extern unsigned int sparc_ramdisk_size; unsigned long highstart_pfn, highend_pfn; -void show_mem(unsigned int filter) -{ - printk("Mem-info:\n"); - show_free_areas(filter); - printk("Free swap: %6ldkB\n", - get_nr_swap_pages() << (PAGE_SHIFT-10)); - printk("%ld pages of RAM\n", totalram_pages); - printk("%ld free pages\n", nr_free_pages()); -} - - unsigned long last_valid_pfn; unsigned long calc_highpages(void) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 37aa537b3ad8..ccd455328989 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -35,7 +35,7 @@ #include <asm/oplib.h> #include <asm/iommu.h> #include <asm/io.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include <asm/dma.h> @@ -324,6 +324,50 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde tsb_insert(tsb, tag, tte); } +#ifdef CONFIG_HUGETLB_PAGE +static int __init setup_hugepagesz(char *string) +{ + unsigned long long hugepage_size; + unsigned int hugepage_shift; + unsigned short hv_pgsz_idx; + unsigned int hv_pgsz_mask; + int rc = 0; + + hugepage_size = memparse(string, &string); + hugepage_shift = ilog2(hugepage_size); + + switch (hugepage_shift) { + case HPAGE_256MB_SHIFT: + hv_pgsz_mask = HV_PGSZ_MASK_256MB; + hv_pgsz_idx = HV_PGSZ_IDX_256MB; + break; + case HPAGE_SHIFT: + hv_pgsz_mask = HV_PGSZ_MASK_4MB; + hv_pgsz_idx = HV_PGSZ_IDX_4MB; + break; + case HPAGE_64K_SHIFT: + hv_pgsz_mask = HV_PGSZ_MASK_64K; + hv_pgsz_idx = HV_PGSZ_IDX_64K; + break; + default: + hv_pgsz_mask = 0; + } + + if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) { + pr_warn("hugepagesz=%llu not supported by MMU.\n", + hugepage_size); + goto out; + } + + hugetlb_add_hstate(hugepage_shift - PAGE_SHIFT); + rc = 1; + +out: + return rc; +} +__setup("hugepagesz=", setup_hugepagesz); +#endif /* CONFIG_HUGETLB_PAGE */ + void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { struct mm_struct *mm; @@ -347,7 +391,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) && - is_hugetlb_pte(pte)) { + is_hugetlb_pmd(__pmd(pte_val(pte)))) { /* We are fabricating 8MB pages using 4MB real hw pages. */ pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT)); __update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT, @@ -785,13 +829,23 @@ static void __init find_ramdisk(unsigned long phys_base) struct node_mem_mask { unsigned long mask; - unsigned long val; + unsigned long match; }; static struct node_mem_mask node_masks[MAX_NUMNODES]; static int num_node_masks; #ifdef CONFIG_NEED_MULTIPLE_NODES +struct mdesc_mlgroup { + u64 node; + u64 latency; + u64 match; + u64 mask; +}; + +static struct mdesc_mlgroup *mlgroups; +static int num_mlgroups; + int numa_cpu_lookup_table[NR_CPUS]; cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES]; @@ -802,78 +856,129 @@ struct mdesc_mblock { }; static struct mdesc_mblock *mblocks; static int num_mblocks; -static int find_numa_node_for_addr(unsigned long pa, - struct node_mem_mask *pnode_mask); -static unsigned long __init ra_to_pa(unsigned long addr) +static struct mdesc_mblock * __init addr_to_mblock(unsigned long addr) { + struct mdesc_mblock *m = NULL; int i; for (i = 0; i < num_mblocks; i++) { - struct mdesc_mblock *m = &mblocks[i]; + m = &mblocks[i]; if (addr >= m->base && addr < (m->base + m->size)) { - addr += m->offset; break; } } - return addr; + + return m; } -static int __init find_node(unsigned long addr) +static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid) { - static bool search_mdesc = true; - static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL }; - static int last_index; - int i; + int prev_nid, new_nid; - addr = ra_to_pa(addr); - for (i = 0; i < num_node_masks; i++) { - struct node_mem_mask *p = &node_masks[i]; + prev_nid = -1; + for ( ; start < end; start += PAGE_SIZE) { + for (new_nid = 0; new_nid < num_node_masks; new_nid++) { + struct node_mem_mask *p = &node_masks[new_nid]; - if ((addr & p->mask) == p->val) - return i; - } - /* The following condition has been observed on LDOM guests because - * node_masks only contains the best latency mask and value. - * LDOM guest's mdesc can contain a single latency group to - * cover multiple address range. Print warning message only if the - * address cannot be found in node_masks nor mdesc. - */ - if ((search_mdesc) && - ((addr & last_mem_mask.mask) != last_mem_mask.val)) { - /* find the available node in the mdesc */ - last_index = find_numa_node_for_addr(addr, &last_mem_mask); - numadbg("find_node: latency group for address 0x%lx is %d\n", - addr, last_index); - if ((last_index < 0) || (last_index >= num_node_masks)) { - /* WARN_ONCE() and use default group 0 */ - WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0."); - search_mdesc = false; - last_index = 0; + if ((start & p->mask) == p->match) { + if (prev_nid == -1) + prev_nid = new_nid; + break; + } + } + + if (new_nid == num_node_masks) { + prev_nid = 0; + WARN_ONCE(1, "addr[%Lx] doesn't match a NUMA node rule. Some memory will be owned by node 0.", + start); + break; } + + if (prev_nid != new_nid) + break; } + *nid = prev_nid; - return last_index; + return start > end ? end : start; } static u64 __init memblock_nid_range(u64 start, u64 end, int *nid) { - *nid = find_node(start); - start += PAGE_SIZE; - while (start < end) { - int n = find_node(start); + u64 ret_end, pa_start, m_mask, m_match, m_end; + struct mdesc_mblock *mblock; + int _nid, i; + + if (tlb_type != hypervisor) + return memblock_nid_range_sun4u(start, end, nid); + + mblock = addr_to_mblock(start); + if (!mblock) { + WARN_ONCE(1, "memblock_nid_range: Can't find mblock addr[%Lx]", + start); + + _nid = 0; + ret_end = end; + goto done; + } - if (n != *nid) + pa_start = start + mblock->offset; + m_match = 0; + m_mask = 0; + + for (_nid = 0; _nid < num_node_masks; _nid++) { + struct node_mem_mask *const m = &node_masks[_nid]; + + if ((pa_start & m->mask) == m->match) { + m_match = m->match; + m_mask = m->mask; break; - start += PAGE_SIZE; + } + } + + if (num_node_masks == _nid) { + /* We could not find NUMA group, so default to 0, but lets + * search for latency group, so we could calculate the correct + * end address that we return + */ + _nid = 0; + + for (i = 0; i < num_mlgroups; i++) { + struct mdesc_mlgroup *const m = &mlgroups[i]; + + if ((pa_start & m->mask) == m->match) { + m_match = m->match; + m_mask = m->mask; + break; + } + } + + if (i == num_mlgroups) { + WARN_ONCE(1, "memblock_nid_range: Can't find latency group addr[%Lx]", + start); + + ret_end = end; + goto done; + } } - if (start > end) - start = end; + /* + * Each latency group has match and mask, and each memory block has an + * offset. An address belongs to a latency group if its address matches + * the following formula: ((addr + offset) & mask) == match + * It is, however, slow to check every single page if it matches a + * particular latency group. As optimization we calculate end value by + * using bit arithmetics. + */ + m_end = m_match + (1ul << __ffs(m_mask)) - mblock->offset; + m_end += pa_start & ~((1ul << fls64(m_mask)) - 1); + ret_end = m_end > end ? end : m_end; - return start; +done: + *nid = _nid; + return ret_end; } #endif @@ -914,7 +1019,8 @@ static void init_node_masks_nonnuma(void) numadbg("Initializing tables for non-numa.\n"); - node_masks[0].mask = node_masks[0].val = 0; + node_masks[0].mask = 0; + node_masks[0].match = 0; num_node_masks = 1; #ifdef CONFIG_NEED_MULTIPLE_NODES @@ -932,15 +1038,6 @@ EXPORT_SYMBOL(numa_cpu_lookup_table); EXPORT_SYMBOL(numa_cpumask_lookup_table); EXPORT_SYMBOL(node_data); -struct mdesc_mlgroup { - u64 node; - u64 latency; - u64 match; - u64 mask; -}; -static struct mdesc_mlgroup *mlgroups; -static int num_mlgroups; - static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio, u32 cfg_handle) { @@ -1029,6 +1126,10 @@ int of_node_to_nid(struct device_node *dp) static void __init add_node_ranges(void) { struct memblock_region *reg; + unsigned long prev_max; + +memblock_resized: + prev_max = memblock.memory.max; for_each_memblock(memory, reg) { unsigned long size = reg->size; @@ -1048,6 +1149,8 @@ static void __init add_node_ranges(void) memblock_set_node(start, this_end - start, &memblock.memory, nid); + if (memblock.memory.max != prev_max) + goto memblock_resized; start = this_end; } } @@ -1182,41 +1285,6 @@ int __node_distance(int from, int to) return numa_latency[from][to]; } -static int find_numa_node_for_addr(unsigned long pa, - struct node_mem_mask *pnode_mask) -{ - struct mdesc_handle *md = mdesc_grab(); - u64 node, arc; - int i = 0; - - node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); - if (node == MDESC_NODE_NULL) - goto out; - - mdesc_for_each_node_by_name(md, node, "group") { - mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) { - u64 target = mdesc_arc_target(md, arc); - struct mdesc_mlgroup *m = find_mlgroup(target); - - if (!m) - continue; - if ((pa & m->mask) == m->match) { - if (pnode_mask) { - pnode_mask->mask = m->mask; - pnode_mask->val = m->match; - } - mdesc_release(md); - return i; - } - } - i++; - } - -out: - mdesc_release(md); - return -1; -} - static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) { int i; @@ -1224,7 +1292,7 @@ static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) for (i = 0; i < MAX_NUMNODES; i++) { struct node_mem_mask *n = &node_masks[i]; - if ((grp->mask == n->mask) && (grp->match == n->val)) + if ((grp->mask == n->mask) && (grp->match == n->match)) break; } return i; @@ -1279,10 +1347,10 @@ static int __init numa_attach_mlgroup(struct mdesc_handle *md, u64 grp, n = &node_masks[num_node_masks++]; n->mask = candidate->mask; - n->val = candidate->match; + n->match = candidate->match; - numadbg("NUMA NODE[%d]: mask[%lx] val[%lx] (latency[%llx])\n", - index, n->mask, n->val, candidate->latency); + numadbg("NUMA NODE[%d]: mask[%lx] match[%lx] (latency[%llx])\n", + index, n->mask, n->match, candidate->latency); return 0; } @@ -1379,7 +1447,7 @@ static int __init numa_parse_jbus(void) numa_cpu_lookup_table[cpu] = index; cpumask_copy(&numa_cpumask_lookup_table[index], cpumask_of(cpu)); node_masks[index].mask = ~((1UL << 36UL) - 1UL); - node_masks[index].val = cpu << 36UL; + node_masks[index].match = cpu << 36UL; index++; } diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c7f2a5295b3a..def82f6d626f 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -1444,7 +1444,7 @@ static void poke_viking(void) srmmu_set_mmureg(mreg); } -static struct sparc32_cachetlb_ops viking_ops = { +static struct sparc32_cachetlb_ops viking_ops __ro_after_init = { .cache_all = viking_flush_cache_all, .cache_mm = viking_flush_cache_mm, .cache_page = viking_flush_cache_page, @@ -1475,7 +1475,7 @@ static struct sparc32_cachetlb_ops viking_ops = { * flushes going at once will require SMP locking anyways so there's * no real value in trying any harder than this. */ -static struct sparc32_cachetlb_ops viking_sun4d_smp_ops = { +static struct sparc32_cachetlb_ops viking_sun4d_smp_ops __ro_after_init = { .cache_all = viking_flush_cache_all, .cache_mm = viking_flush_cache_mm, .cache_page = viking_flush_cache_page, @@ -1759,7 +1759,7 @@ static void smp_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr) local_ops->sig_insns(mm, insn_addr); } -static struct sparc32_cachetlb_ops smp_cachetlb_ops = { +static struct sparc32_cachetlb_ops smp_cachetlb_ops __ro_after_init = { .cache_all = smp_flush_cache_all, .cache_mm = smp_flush_cache_mm, .cache_page = smp_flush_cache_page, diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index c56a195c9071..afda3bbf7854 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void) } static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, - bool exec, bool huge) + bool exec, unsigned int hugepage_shift) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); unsigned long nr; @@ -84,19 +84,19 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, } if (!tb->active) { - flush_tsb_user_page(mm, vaddr, huge); + flush_tsb_user_page(mm, vaddr, hugepage_shift); global_flush_tlb_page(mm, vaddr); goto out; } if (nr == 0) { tb->mm = mm; - tb->huge = huge; + tb->hugepage_shift = hugepage_shift; } - if (tb->huge != huge) { + if (tb->hugepage_shift != hugepage_shift) { flush_tlb_pending(); - tb->huge = huge; + tb->hugepage_shift = hugepage_shift; nr = 0; } @@ -110,10 +110,9 @@ out: } void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, - pte_t *ptep, pte_t orig, int fullmm) + pte_t *ptep, pte_t orig, int fullmm, + unsigned int hugepage_shift) { - bool huge = is_hugetlb_pte(orig); - if (tlb_type != hypervisor && pte_dirty(orig)) { unsigned long paddr, pfn = pte_pfn(orig); @@ -139,7 +138,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, no_cache_flush: if (!fullmm) - tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge); + tlb_batch_add_one(mm, vaddr, pte_exec(orig), hugepage_shift); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index e20fbbafb0b0..23479c3d39f0 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -86,6 +86,33 @@ static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) +static void __flush_huge_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries, + unsigned int hugepage_shift) +{ + unsigned int hpage_entries; + unsigned int i; + + hpage_entries = 1 << (hugepage_shift - hash_shift); + for (i = 0; i < hpage_entries; i++) + __flush_tsb_one_entry(tsb, v + (i << hash_shift), hash_shift, + nentries); +} + +static void __flush_huge_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, + unsigned long tsb, unsigned long nentries, + unsigned int hugepage_shift) +{ + unsigned long i; + + for (i = 0; i < tb->tlb_nr; i++) + __flush_huge_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, + nentries, hugepage_shift); +} +#endif + void flush_tsb_user(struct tlb_batch *tb) { struct mm_struct *mm = tb->mm; @@ -93,45 +120,61 @@ void flush_tsb_user(struct tlb_batch *tb) spin_lock_irqsave(&mm->context.lock, flags); - if (!tb->huge) { + if (tb->hugepage_shift < HPAGE_SHIFT) { base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) base = __pa(base); - __flush_tsb_one(tb, PAGE_SHIFT, base, nentries); + if (tb->hugepage_shift == PAGE_SHIFT) + __flush_tsb_one(tb, PAGE_SHIFT, base, nentries); +#if defined(CONFIG_HUGETLB_PAGE) + else + __flush_huge_tsb_one(tb, PAGE_SHIFT, base, nentries, + tb->hugepage_shift); +#endif } #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) { + else if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) base = __pa(base); - __flush_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries); + __flush_huge_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries, + tb->hugepage_shift); } #endif spin_unlock_irqrestore(&mm->context.lock, flags); } -void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge) +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, + unsigned int hugepage_shift) { unsigned long nentries, base, flags; spin_lock_irqsave(&mm->context.lock, flags); - if (!huge) { + if (hugepage_shift < HPAGE_SHIFT) { base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) base = __pa(base); - __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + if (hugepage_shift == PAGE_SHIFT) + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, + nentries); +#if defined(CONFIG_HUGETLB_PAGE) + else + __flush_huge_tsb_one_entry(base, vaddr, PAGE_SHIFT, + nentries, hugepage_shift); +#endif } #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) { + else if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) base = __pa(base); - __flush_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT, nentries); + __flush_huge_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT, + nentries, hugepage_shift); } #endif spin_unlock_irqrestore(&mm->context.lock, flags); |