diff options
Diffstat (limited to 'arch/sparc')
143 files changed, 3852 insertions, 1322 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index cf4034c66362..a4a626199c47 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -31,7 +31,8 @@ config SPARC select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP select HAVE_NMI_WATCHDOG if SPARC64 - select HAVE_CBPF_JIT + select HAVE_CBPF_JIT if SPARC32 + select HAVE_EBPF_JIT if SPARC64 select HAVE_DEBUG_BUGVERBOSE select GENERIC_SMP_IDLE_THREAD select GENERIC_CLOCKEVENTS @@ -42,8 +43,8 @@ config SPARC select OLD_SIGSUSPEND select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS - select HAVE_ARCH_HARDENED_USERCOPY - select PROVE_LOCKING_SMALL if PROVE_LOCKING + select LOCKDEP_SMALL if LOCKDEP + select ARCH_WANT_RELAX_ORDER config SPARC32 def_bool !64BIT @@ -81,6 +82,9 @@ config SPARC64 select HAVE_ARCH_AUDITSYSCALL select ARCH_SUPPORTS_ATOMIC_RMW select HAVE_NMI + select HAVE_REGS_AND_STACK_ACCESS_API + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS config ARCH_DEFCONFIG string @@ -90,6 +94,9 @@ config ARCH_DEFCONFIG config ARCH_PROC_KCORE_TEXT def_bool y +config CPU_BIG_ENDIAN + def_bool y + config ARCH_ATU bool default y if SPARC64 @@ -190,9 +197,9 @@ config NR_CPUS int "Maximum number of CPUs" depends on SMP range 2 32 if SPARC32 - range 2 1024 if SPARC64 + range 2 4096 if SPARC64 default 32 if SPARC32 - default 64 if SPARC64 + default 4096 if SPARC64 source kernel/Kconfig.hz @@ -293,9 +300,13 @@ config NUMA depends on SPARC64 && SMP config NODES_SHIFT - int - default "4" + int "Maximum NUMA Nodes (as a power of 2)" + range 4 5 if SPARC64 + default "5" depends on NEED_MULTIPLE_NODES + help + Specify the maximum number of NUMA Nodes available on the target + system. Increases memory reserved to accommodate various tables. # Some NUMA nodes have memory ranges that span # other nodes. Even though a pfn is valid and @@ -571,9 +582,6 @@ config SYSVIPC_COMPAT depends on COMPAT && SYSVIPC default y -config KEYS_COMPAT - def_bool y if COMPAT && KEYS - endmenu source "net/Kconfig" diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 0569bfac4afb..80ddc01f57ac 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 @@ -19,5 +18,4 @@ generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h generic-y += trace_clock.h -generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/asm-prototypes.h b/arch/sparc/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..d381e11c5dbb --- /dev/null +++ b/arch/sparc/include/asm/asm-prototypes.h @@ -0,0 +1,24 @@ +/* + * Copyright (c) 2017 Oracle and/or its affiliates. All rights reserved. + */ + +#include <asm/xor.h> +#include <asm/checksum.h> +#include <asm/trap_block.h> +#include <asm/uaccess.h> +#include <asm/atomic.h> +#include <asm/ftrace.h> +#include <asm/cacheflush.h> +#include <asm/oplib.h> +#include <linux/atomic.h> + +void *__memscan_zero(void *, size_t); +void *__memscan_generic(void *, int, size_t); +void *__bzero(void *, size_t); +void VISenter(void); /* Dummy prototype to supress warning */ +#undef memcpy +#undef memset +void *memcpy(void *dest, const void *src, size_t n); +void *memset(void *s, int c, size_t n); +typedef int TItype __attribute__((mode(TI))); +TItype __multi3(TItype a, TItype b); diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h index faa2f61058c2..4028f4f1e561 100644 --- a/arch/sparc/include/asm/cmpxchg_64.h +++ b/arch/sparc/include/asm/cmpxchg_64.h @@ -6,6 +6,17 @@ #ifndef __ARCH_SPARC64_CMPXCHG__ #define __ARCH_SPARC64_CMPXCHG__ +static inline unsigned long +__cmpxchg_u32(volatile int *m, int old, int new) +{ + __asm__ __volatile__("cas [%2], %3, %0" + : "=&r" (new) + : "0" (new), "r" (m), "r" (old) + : "memory"); + + return new; +} + static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val) { unsigned long tmp1, tmp2; @@ -44,10 +55,38 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long void __xchg_called_with_bad_pointer(void); +/* + * Use 4 byte cas instruction to achieve 2 byte xchg. Main logic + * here is to get the bit shift of the byte we are interested in. + * The XOR is handy for reversing the bits for big-endian byte order. + */ +static inline unsigned long +xchg16(__volatile__ unsigned short *m, unsigned short val) +{ + unsigned long maddr = (unsigned long)m; + int bit_shift = (((unsigned long)m & 2) ^ 2) << 3; + unsigned int mask = 0xffff << bit_shift; + unsigned int *ptr = (unsigned int *) (maddr & ~2); + unsigned int old32, new32, load32; + + /* Read the old value */ + load32 = *ptr; + + do { + old32 = load32; + new32 = (load32 & (~mask)) | val << bit_shift; + load32 = __cmpxchg_u32(ptr, old32, new32); + } while (load32 != old32); + + return (load32 & mask) >> bit_shift; +} + static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { + case 2: + return xchg16(ptr, x); case 4: return xchg32(ptr, x); case 8: @@ -65,10 +104,11 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, #include <asm-generic/cmpxchg-local.h> + static inline unsigned long -__cmpxchg_u32(volatile int *m, int old, int new) +__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new) { - __asm__ __volatile__("cas [%2], %3, %0" + __asm__ __volatile__("casx [%2], %3, %0" : "=&r" (new) : "0" (new), "r" (m), "r" (old) : "memory"); @@ -76,15 +116,31 @@ __cmpxchg_u32(volatile int *m, int old, int new) return new; } +/* + * Use 4 byte cas instruction to achieve 1 byte cmpxchg. Main logic + * here is to get the bit shift of the byte we are interested in. + * The XOR is handy for reversing the bits for big-endian byte order + */ static inline unsigned long -__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new) +__cmpxchg_u8(volatile unsigned char *m, unsigned char old, unsigned char new) { - __asm__ __volatile__("casx [%2], %3, %0" - : "=&r" (new) - : "0" (new), "r" (m), "r" (old) - : "memory"); - - return new; + unsigned long maddr = (unsigned long)m; + int bit_shift = (((unsigned long)m & 3) ^ 3) << 3; + unsigned int mask = 0xff << bit_shift; + unsigned int *ptr = (unsigned int *) (maddr & ~3); + unsigned int old32, new32, load; + unsigned int load32 = *ptr; + + do { + new32 = (load32 & ~mask) | (new << bit_shift); + old32 = (load32 & ~mask) | (old << bit_shift); + load32 = __cmpxchg_u32(ptr, old32, new32); + if (load32 == old32) + return old; + load = (load32 & mask) >> bit_shift; + } while (load == old); + + return load; } /* This function doesn't exist, so you'll get a linker error @@ -95,6 +151,8 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) { switch (size) { + case 1: + return __cmpxchg_u8(ptr, old, new); case 4: return __cmpxchg_u32(ptr, old, new); case 8: diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h index 1180ae254154..60bf1633d554 100644 --- a/arch/sparc/include/asm/dma-mapping.h +++ b/arch/sparc/include/asm/dma-mapping.h @@ -5,11 +5,6 @@ #include <linux/mm.h> #include <linux/dma-debug.h> -#define DMA_ERROR_CODE (~(dma_addr_t)0x0) - -#define HAVE_ARCH_DMA_SUPPORTED 1 -int dma_supported(struct device *dev, u64 mask); - static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction dir) { @@ -18,20 +13,19 @@ 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 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; + return &pci32_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/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index dcbf985ab243..d1f837dc77a4 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -24,9 +24,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h index a145d798e112..49f8402035d7 100644 --- a/arch/sparc/include/asm/kprobes.h +++ b/arch/sparc/include/asm/kprobes.h @@ -1,13 +1,17 @@ #ifndef _SPARC64_KPROBES_H #define _SPARC64_KPROBES_H +#include <asm-generic/kprobes.h> + +#define BREAKPOINT_INSTRUCTION 0x91d02070 /* ta 0x70 */ +#define BREAKPOINT_INSTRUCTION_2 0x91d02071 /* ta 0x71 */ + +#ifdef CONFIG_KPROBES #include <linux/types.h> #include <linux/percpu.h> typedef u32 kprobe_opcode_t; -#define BREAKPOINT_INSTRUCTION 0x91d02070 /* ta 0x70 */ -#define BREAKPOINT_INSTRUCTION_2 0x91d02071 /* ta 0x71 */ #define MAX_INSN_SIZE 2 #define kretprobe_blacklist_size 0 @@ -48,4 +52,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, int kprobe_fault_handler(struct pt_regs *regs, int trapnr); asmlinkage void __kprobes kprobe_trap(unsigned long trap_level, struct pt_regs *regs); + +#endif /* CONFIG_KPROBES */ #endif /* _SPARC64_KPROBES_H */ diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h index 6e9004aa6f25..698738a10414 100644 --- a/arch/sparc/include/asm/ldc.h +++ b/arch/sparc/include/asm/ldc.h @@ -48,6 +48,8 @@ struct ldc_channel_config { #define LDC_STATE_READY 0x03 #define LDC_STATE_CONNECTED 0x04 +#define LDC_PACKET_SIZE 64 + struct ldc_channel; /* Allocate state for a channel. */ @@ -72,6 +74,12 @@ int ldc_connect(struct ldc_channel *lp); int ldc_disconnect(struct ldc_channel *lp); int ldc_state(struct ldc_channel *lp); +void ldc_set_state(struct ldc_channel *lp, u8 state); +int ldc_mode(struct ldc_channel *lp); +void __ldc_print(struct ldc_channel *lp, const char *caller); +int ldc_rx_reset(struct ldc_channel *lp); + +#define ldc_print(chan) __ldc_print(chan, __func__) /* Read and write operations. Only valid when the link is up. */ int ldc_write(struct ldc_channel *lp, const void *buf, diff --git a/arch/sparc/include/asm/mdesc.h b/arch/sparc/include/asm/mdesc.h index aebeb88f70db..e8a4c413a1c7 100644 --- a/arch/sparc/include/asm/mdesc.h +++ b/arch/sparc/include/asm/mdesc.h @@ -16,6 +16,7 @@ struct mdesc_handle *mdesc_grab(void); void mdesc_release(struct mdesc_handle *); #define MDESC_NODE_NULL (~(u64)0) +#define MDESC_MAX_STR_LEN 256 u64 mdesc_node_by_name(struct mdesc_handle *handle, u64 from_node, const char *name); @@ -62,15 +63,32 @@ u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc); void mdesc_update(void); struct mdesc_notifier_client { - void (*add)(struct mdesc_handle *handle, u64 node); - void (*remove)(struct mdesc_handle *handle, u64 node); - + void (*add)(struct mdesc_handle *handle, u64 node, + const char *node_name); + void (*remove)(struct mdesc_handle *handle, u64 node, + const char *node_name); const char *node_name; struct mdesc_notifier_client *next; }; void mdesc_register_notifier(struct mdesc_notifier_client *client); +union md_node_info { + struct vdev_port { + u64 id; /* id */ + u64 parent_cfg_hdl; /* parent config handle */ + const char *name; /* name (property) */ + } vdev_port; + struct ds_port { + u64 id; /* id */ + } ds_port; +}; + +u64 mdesc_get_node(struct mdesc_handle *hp, const char *node_name, + union md_node_info *node_info); +int mdesc_get_node_info(struct mdesc_handle *hp, u64 node, + const char *node_name, union md_node_info *node_info); + void mdesc_fill_in_cpu_data(cpumask_t *mask); void mdesc_populate_present_mask(cpumask_t *mask); void mdesc_get_page_sizes(cpumask_t *mask, unsigned long *pgsz_mask); diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h index f7de0dbc38af..83b36a5371ff 100644 --- a/arch/sparc/include/asm/mmu_64.h +++ b/arch/sparc/include/asm/mmu_64.h @@ -52,7 +52,7 @@ #define CTX_NR_MASK TAG_CONTEXT_BITS #define CTX_HW_MASK (CTX_NR_MASK | CTX_PGSZ_MASK) -#define CTX_FIRST_VERSION ((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL)) +#define CTX_FIRST_VERSION BIT(CTX_VERSION_SHIFT) #define CTX_VALID(__ctx) \ (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK)) #define CTX_HWBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_HW_MASK) diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index d0317993e947..2cddcda4f85f 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -6,6 +6,8 @@ #ifndef __ASSEMBLY__ #include <linux/spinlock.h> +#include <linux/mm_types.h> + #include <asm/spitfire.h> #include <asm-generic/mm_hooks.h> @@ -17,13 +19,8 @@ extern spinlock_t ctx_alloc_lock; extern unsigned long tlb_context_cache; extern unsigned long mmu_context_bmap[]; +DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm); void get_new_mmu_context(struct mm_struct *mm); -#ifdef CONFIG_SMP -void smp_new_mmu_context_version(void); -#else -#define smp_new_mmu_context_version() do { } while (0) -#endif - int init_new_context(struct task_struct *tsk, struct mm_struct *mm); void destroy_context(struct mm_struct *mm); @@ -74,8 +71,9 @@ void __flush_tlb_mm(unsigned long, unsigned long); static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk) { unsigned long ctx_valid, flags; - int cpu; + int cpu = smp_processor_id(); + per_cpu(per_cpu_secondary_mm, cpu) = mm; if (unlikely(mm == &init_mm)) return; @@ -121,7 +119,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str * for the first time, we must flush that context out of the * local TLB. */ - cpu = smp_processor_id(); if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) { cpumask_set_cpu(cpu, mm_cpumask(mm)); __flush_tlb_mm(CTX_HWBITS(mm->context), @@ -131,26 +128,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str } #define deactivate_mm(tsk,mm) do { } while (0) - -/* Activate a new MM instance for the current task. */ -static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm) -{ - unsigned long flags; - int cpu; - - spin_lock_irqsave(&mm->context.lock, flags); - if (!CTX_VALID(mm->context)) - get_new_mmu_context(mm); - cpu = smp_processor_id(); - if (!cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_set_cpu(cpu, mm_cpumask(mm)); - - load_secondary_context(mm); - __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT); - tsb_context_switch(mm); - spin_unlock_irqrestore(&mm->context.lock, flags); -} - +#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL) #endif /* !(__ASSEMBLY__) */ #endif /* !(__SPARC64_MMU_CONTEXT_H) */ diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h index 26ad2b2607c6..284eac3ffaf2 100644 --- a/arch/sparc/include/asm/nmi.h +++ b/arch/sparc/include/asm/nmi.h @@ -7,6 +7,7 @@ void nmi_adjust_hz(unsigned int new_hz); extern atomic_t nmi_active; +void arch_touch_nmi_watchdog(void); void start_nmi_watchdog(void *unused); void stop_nmi_watchdog(void *unused); diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index c1263fc390db..5961b2d8398a 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -17,7 +17,9 @@ #define HPAGE_SHIFT 23 #define REAL_HPAGE_SHIFT 22 - +#define HPAGE_2GB_SHIFT 31 +#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 +28,7 @@ #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 4 #endif #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h index 2303635158f5..b957ca5527a3 100644 --- a/arch/sparc/include/asm/pci_64.h +++ b/arch/sparc/include/asm/pci_64.h @@ -42,13 +42,10 @@ static inline int pci_proc_domain(struct pci_bus *bus) /* Platform support for /proc/bus/pci/X/Y mmap()s. */ #define HAVE_PCI_MMAP +#define arch_can_pci_mmap_io() 1 #define HAVE_ARCH_PCI_GET_UNMAPPED_AREA #define get_pci_unmapped_area get_fb_unmapped_area -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, - int write_combine); - static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) { return PCI_IRQ_NONE; diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index ce6f56980aef..cf190728360b 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -91,9 +91,9 @@ extern unsigned long pfn_base; * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page)) +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) /* * In general all page table modifications should use the V8 atomic diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 314b66851348..6fbd931f0570 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -12,6 +12,7 @@ * the SpitFire page tables. */ +#include <asm-generic/5level-fixup.h> #include <linux/compiler.h> #include <linux/const.h> #include <asm/types.h> @@ -375,7 +376,10 @@ 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 +399,14 @@ 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) @@ -673,26 +679,27 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return pte_pfn(pte); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline unsigned long pmd_dirty(pmd_t pmd) +#define __HAVE_ARCH_PMD_WRITE +static inline unsigned long pmd_write(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_dirty(pte); + return pte_write(pte); } -static inline unsigned long pmd_young(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline unsigned long pmd_dirty(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_young(pte); + return pte_dirty(pte); } -static inline unsigned long pmd_write(pmd_t pmd) +static inline unsigned long pmd_young(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - return pte_write(pte); + return pte_young(pte); } static inline unsigned long pmd_trans_huge(pmd_t pmd) @@ -873,12 +880,17 @@ static inline unsigned long pud_pfn(pud_t pud) #define pte_offset_map pte_index #define pte_unmap(pte) do { } while (0) +/* We cannot include <linux/mm_types.h> at this point yet: */ +extern struct mm_struct init_mm; + /* 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 +899,7 @@ 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 +918,7 @@ 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/pil.h b/arch/sparc/include/asm/pil.h index 266937030546..522b43db2ed3 100644 --- a/arch/sparc/include/asm/pil.h +++ b/arch/sparc/include/asm/pil.h @@ -20,7 +20,6 @@ #define PIL_SMP_CALL_FUNC 1 #define PIL_SMP_RECEIVE_SIGNAL 2 #define PIL_SMP_CAPTURE 3 -#define PIL_SMP_CTX_NEW_VERSION 4 #define PIL_DEVICE_IRQ 5 #define PIL_SMP_CALL_FUNC_SNGL 6 #define PIL_DEFERRED_PCR_WORK 7 diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index 365d4cb267b4..b395e5620c0b 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -18,12 +18,6 @@ #include <asm/signal.h> #include <asm/page.h> -/* - * The sparc has no problems with write protection - */ -#define wp_works_ok 1 -#define wp_works_ok__is_a_macro /* for versions in ksyms.c */ - /* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too... * That one page is used to protect kernel from intruders, so that * we can make our access_ok test faster @@ -73,9 +67,6 @@ struct thread_struct { .current_ds = KERNEL_DS, \ } -/* Return saved PC of a blocked thread. */ -unsigned long thread_saved_pc(struct task_struct *t); - /* Do necessary setup to start up a newly executed thread. */ static inline void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 6448cfc8292f..f04dc5a43062 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -18,10 +18,6 @@ #include <asm/ptrace.h> #include <asm/page.h> -/* The sparc has no problems with write protection */ -#define wp_works_ok 1 -#define wp_works_ok__is_a_macro /* for versions in ksyms.c */ - /* * User lives in his very own context, and cannot reference us. Note * that TASK_SIZE is a misnomer, it really gives maximum user virtual @@ -93,9 +89,7 @@ struct thread_struct { #include <linux/types.h> #include <asm/fpumacro.h> -/* Return saved PC of a blocked thread. */ struct task_struct; -unsigned long thread_saved_pc(struct task_struct *); /* On Uniprocessor, even in RMO processes see TSO semantics */ #ifdef CONFIG_SMP diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index ca57f08bd3db..d73428e4333c 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -83,7 +83,8 @@ unsigned long profile_pc(struct pt_regs *); #define MAX_REG_OFFSET (offsetof(struct pt_regs, magic)) -extern int regs_query_register_offset(const char *name); +int regs_query_register_offset(const char *name); +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); /** * regs_get_register() - get register value from its offset diff --git a/arch/sparc/include/asm/qrwlock.h b/arch/sparc/include/asm/qrwlock.h new file mode 100644 index 000000000000..d68a4b102100 --- /dev/null +++ b/arch/sparc/include/asm/qrwlock.h @@ -0,0 +1,7 @@ +#ifndef _ASM_SPARC_QRWLOCK_H +#define _ASM_SPARC_QRWLOCK_H + +#include <asm-generic/qrwlock_types.h> +#include <asm-generic/qrwlock.h> + +#endif /* _ASM_SPARC_QRWLOCK_H */ diff --git a/arch/sparc/include/asm/qspinlock.h b/arch/sparc/include/asm/qspinlock.h new file mode 100644 index 000000000000..5ae9a2802846 --- /dev/null +++ b/arch/sparc/include/asm/qspinlock.h @@ -0,0 +1,7 @@ +#ifndef _ASM_SPARC_QSPINLOCK_H +#define _ASM_SPARC_QSPINLOCK_H + +#include <asm-generic/qspinlock_types.h> +#include <asm-generic/qspinlock.h> + +#endif /* _ASM_SPARC_QSPINLOCK_H */ diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 29d64b1758ed..8b32538084f7 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -1,5 +1,5 @@ /* - * Just a place holder. + * Just a place holder. */ #ifndef _SPARC_SETUP_H #define _SPARC_SETUP_H @@ -16,7 +16,7 @@ extern char reboot_command[]; */ extern unsigned char boot_cpu_id; -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; extern int serial_console; static inline int con_is_present(void) @@ -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/siginfo.h b/arch/sparc/include/asm/siginfo.h deleted file mode 100644 index 48c34c19f810..000000000000 --- a/arch/sparc/include/asm/siginfo.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef __SPARC_SIGINFO_H -#define __SPARC_SIGINFO_H - -#include <uapi/asm/siginfo.h> - - -#ifdef CONFIG_COMPAT - -struct compat_siginfo; - -#endif /* CONFIG_COMPAT */ - -#endif /* !(__SPARC_SIGINFO_H) */ diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 07c9f2e9bf57..f7028f5e1a5a 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -10,216 +10,12 @@ #include <asm/processor.h> #include <asm/barrier.h> - -/* To get debugging spinlocks which detect and catch - * deadlock situations, set CONFIG_DEBUG_SPINLOCK - * and rebuild your kernel. - */ - -/* Because we play games to save cycles in the non-contention case, we - * need to be extra careful about branch targets into the "spinning" - * code. They live in their own section, but the newer V9 branches - * have a shorter range than the traditional 32-bit sparc branch - * variants. The rule is that the branches that go into and out of - * the spinner sections must be pre-V9 branches. - */ - -#define arch_spin_is_locked(lp) ((lp)->lock != 0) - -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - smp_cond_load_acquire(&lock->lock, !VAL); -} - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned long tmp; - - __asm__ __volatile__( -"1: ldstub [%1], %0\n" -" brnz,pn %0, 2f\n" -" nop\n" -" .subsection 2\n" -"2: ldub [%1], %0\n" -" brnz,pt %0, 2b\n" -" nop\n" -" ba,a,pt %%xcc, 1b\n" -" .previous" - : "=&r" (tmp) - : "r" (lock) - : "memory"); -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned long result; - - __asm__ __volatile__( -" ldstub [%1], %0\n" - : "=r" (result) - : "r" (lock) - : "memory"); - - return (result == 0UL); -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __asm__ __volatile__( -" stb %%g0, [%0]" - : /* No outputs */ - : "r" (lock) - : "memory"); -} - -static inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__( -"1: ldstub [%2], %0\n" -" brnz,pn %0, 2f\n" -" nop\n" -" .subsection 2\n" -"2: rdpr %%pil, %1\n" -" wrpr %3, %%pil\n" -"3: ldub [%2], %0\n" -" brnz,pt %0, 3b\n" -" nop\n" -" ba,pt %%xcc, 1b\n" -" wrpr %1, %%pil\n" -" .previous" - : "=&r" (tmp1), "=&r" (tmp2) - : "r"(lock), "r"(flags) - : "memory"); -} - -/* Multi-reader locks, these are much saner than the 32-bit Sparc ones... */ - -static inline void arch_read_lock(arch_rwlock_t *lock) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__ ( -"1: ldsw [%2], %0\n" -" brlz,pn %0, 2f\n" -"4: add %0, 1, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" nop\n" -" .subsection 2\n" -"2: ldsw [%2], %0\n" -" brlz,pt %0, 2b\n" -" nop\n" -" ba,a,pt %%xcc, 4b\n" -" .previous" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock) - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *lock) -{ - int tmp1, tmp2; - - __asm__ __volatile__ ( -"1: ldsw [%2], %0\n" -" brlz,a,pn %0, 2f\n" -" mov 0, %0\n" -" add %0, 1, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" mov 1, %0\n" -"2:" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock) - : "memory"); - - return tmp1; -} - -static inline void arch_read_unlock(arch_rwlock_t *lock) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__( -"1: lduw [%2], %0\n" -" sub %0, 1, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%xcc, 1b\n" -" nop" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock) - : "memory"); -} - -static inline void arch_write_lock(arch_rwlock_t *lock) -{ - unsigned long mask, tmp1, tmp2; - - mask = 0x80000000UL; - - __asm__ __volatile__( -"1: lduw [%2], %0\n" -" brnz,pn %0, 2f\n" -"4: or %0, %3, %1\n" -" cas [%2], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" nop\n" -" .subsection 2\n" -"2: lduw [%2], %0\n" -" brnz,pt %0, 2b\n" -" nop\n" -" ba,a,pt %%xcc, 4b\n" -" .previous" - : "=&r" (tmp1), "=&r" (tmp2) - : "r" (lock), "r" (mask) - : "memory"); -} - -static inline void arch_write_unlock(arch_rwlock_t *lock) -{ - __asm__ __volatile__( -" stw %%g0, [%0]" - : /* no outputs */ - : "r" (lock) - : "memory"); -} - -static inline int arch_write_trylock(arch_rwlock_t *lock) -{ - unsigned long mask, tmp1, tmp2, result; - - mask = 0x80000000UL; - - __asm__ __volatile__( -" mov 0, %2\n" -"1: lduw [%3], %0\n" -" brnz,pn %0, 2f\n" -" or %0, %4, %1\n" -" cas [%3], %0, %1\n" -" cmp %0, %1\n" -" bne,pn %%icc, 1b\n" -" nop\n" -" mov 1, %2\n" -"2:" - : "=&r" (tmp1), "=&r" (tmp2), "=&r" (result) - : "r" (lock), "r" (mask) - : "memory"); - - return result; -} +#include <asm/qrwlock.h> +#include <asm/qspinlock.h> #define arch_read_lock_flags(p, f) arch_read_lock(p) #define arch_write_lock_flags(p, f) arch_write_lock(p) -#define arch_read_can_lock(rw) (!((rw)->lock & 0x80000000UL)) -#define arch_write_can_lock(rw) (!(rw)->lock) - #define arch_spin_relax(lock) cpu_relax() #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() diff --git a/arch/sparc/include/asm/spinlock_types.h b/arch/sparc/include/asm/spinlock_types.h index 9c454fdeaad8..bce8ef44dfa9 100644 --- a/arch/sparc/include/asm/spinlock_types.h +++ b/arch/sparc/include/asm/spinlock_types.h @@ -1,20 +1,24 @@ #ifndef __SPARC_SPINLOCK_TYPES_H #define __SPARC_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm-generic/qspinlock_types.h> +#else typedef struct { volatile unsigned char lock; } arch_spinlock_t; #define __ARCH_SPIN_LOCK_UNLOCKED { 0 } +#endif /* CONFIG_QUEUED_SPINLOCKS */ +#ifdef CONFIG_QUEUED_RWLOCKS +#include <asm-generic/qrwlock_types.h> +#else typedef struct { volatile unsigned int lock; } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED { 0 } - +#endif /* CONFIG_QUEUED_RWLOCKS */ #endif diff --git a/arch/sparc/include/asm/switch_to_32.h b/arch/sparc/include/asm/switch_to_32.h index 16f10374feb3..475dd4158ae4 100644 --- a/arch/sparc/include/asm/switch_to_32.h +++ b/arch/sparc/include/asm/switch_to_32.h @@ -9,7 +9,7 @@ extern struct thread_info *current_set[NR_CPUS]; * Flush windows so that the VM switch which follows * would not pull the stack from under us. * - * SWITCH_ENTER and SWITH_DO_LAZY_FPU do not work yet (e.g. SMP does not work) + * SWITCH_ENTER and SWITCH_DO_LAZY_FPU do not work yet (e.g. SMP does not work) * XXX WTF is the above comment? Found in late teen 2.4.x. */ #ifdef CONFIG_SMP diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h index fce415034000..51bc3bc54bfe 100644 --- a/arch/sparc/include/asm/timer_64.h +++ b/arch/sparc/include/asm/timer_64.h @@ -9,7 +9,12 @@ #include <linux/types.h> #include <linux/init.h> +/* The most frequently accessed fields should be first, + * to fit into the same cacheline. + */ struct sparc64_tick_ops { + unsigned long ticks_per_nsec_quotient; + unsigned long offset; unsigned long long (*get_tick)(void); int (*add_compare)(unsigned long); unsigned long softint_mask; @@ -17,6 +22,8 @@ struct sparc64_tick_ops { void (*init_tick)(void); unsigned long (*add_tick)(unsigned long); + unsigned long (*get_frequency)(void); + unsigned long frequency; char *name; }; @@ -27,4 +34,64 @@ unsigned long sparc64_get_clock_tick(unsigned int cpu); void setup_sparc64_timer(void); void __init time_init(void); +#define TICK_PRIV_BIT BIT(63) +#define TICKCMP_IRQ_BIT BIT(63) + +#define HBIRD_STICKCMP_ADDR 0x1fe0000f060UL +#define HBIRD_STICK_ADDR 0x1fe0000f070UL + +#define GET_TICK_NINSTR 13 +struct get_tick_patch { + unsigned int addr; + unsigned int tick[GET_TICK_NINSTR]; + unsigned int stick[GET_TICK_NINSTR]; +}; + +extern struct get_tick_patch __get_tick_patch; +extern struct get_tick_patch __get_tick_patch_end; + +static inline unsigned long get_tick(void) +{ + unsigned long tick, tmp1, tmp2; + + __asm__ __volatile__( + /* read hbtick 13 instructions */ + "661:\n" + " mov 0x1fe, %1\n" + " sllx %1, 0x20, %1\n" + " sethi %%hi(0xf000), %2\n" + " or %2, 0x70, %2\n" + " or %1, %2, %1\n" /* %1 = HBIRD_STICK_ADDR */ + " add %1, 8, %2\n" + " ldxa [%2]%3, %0\n" + " ldxa [%1]%3, %1\n" + " ldxa [%2]%3, %2\n" + " sub %2, %0, %0\n" /* don't modify %xcc */ + " brnz,pn %0, 661b\n" /* restart to save one register */ + " sllx %2, 32, %2\n" + " or %2, %1, %0\n" + /* Common/not patched code */ + " sllx %0, 1, %0\n" + " srlx %0, 1, %0\n" /* Clear TICK_PRIV_BIT */ + /* Beginning of patch section */ + " .section .get_tick_patch, \"ax\"\n" + " .word 661b\n" + /* read tick 2 instructions and 11 skipped */ + " ba 1f\n" + " rd %%tick, %0\n" + " .skip 4 * (%4 - 2)\n" + "1:\n" + /* read stick 2 instructions and 11 skipped */ + " ba 1f\n" + " rd %%asr24, %0\n" + " .skip 4 * (%4 - 2)\n" + "1:\n" + /* End of patch section */ + " .previous\n" + : "=&r" (tick), "=&r" (tmp1), "=&r" (tmp2) + : "i" (ASI_PHYS_BYPASS_EC_E), "i" (GET_TICK_NINSTR)); + + return tick; +} + #endif /* _SPARC64_TIMER_H */ 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 225543000122..ad5293f89680 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -4,7 +4,6 @@ #ifdef CONFIG_NUMA #include <asm/mmzone.h> -#include <asm/cpudata.h> static inline int cpu_to_node(int cpu) { @@ -42,6 +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/trap_block.h b/arch/sparc/include/asm/trap_block.h index ec9c04de3664..ff05992dae7a 100644 --- a/arch/sparc/include/asm/trap_block.h +++ b/arch/sparc/include/asm/trap_block.h @@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS]; void init_cur_cpu_trap(struct thread_info *); void setup_tba(void); extern int ncpus_probed; +extern u64 cpu_mondo_counter[NR_CPUS]; unsigned long real_hard_smp_processor_id(void); diff --git a/arch/sparc/include/asm/uaccess.h b/arch/sparc/include/asm/uaccess.h index bd56c28fff9f..9e068bf9060a 100644 --- a/arch/sparc/include/asm/uaccess.h +++ b/arch/sparc/include/asm/uaccess.h @@ -7,7 +7,7 @@ #endif #define user_addr_max() \ - (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL) + (uaccess_kernel() ? ~0UL : TASK_SIZE) long strncpy_from_user(char *dest, const char __user *src, long count); diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index ea55f86d7ccd..bdb1447aa1bb 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -7,14 +7,8 @@ #ifndef _ASM_UACCESS_H #define _ASM_UACCESS_H -#ifdef __KERNEL__ #include <linux/compiler.h> -#include <linux/sched.h> #include <linux/string.h> -#include <linux/errno.h> -#endif - -#ifndef __ASSEMBLY__ #include <asm/processor.h> @@ -30,9 +24,6 @@ #define KERNEL_DS ((mm_segment_t) { 0 }) #define USER_DS ((mm_segment_t) { -1 }) -#define VERIFY_READ 0 -#define VERIFY_WRITE 1 - #define get_ds() (KERNEL_DS) #define get_fs() (current->thread.current_ds) #define set_fs(val) ((current->thread.current_ds) = (val)) @@ -45,7 +36,7 @@ * large size and address near to PAGE_OFFSET - a fault will break his intentions. */ #define __user_ok(addr, size) ({ (void)(size); (addr) < STACK_TOP; }) -#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS)) +#define __kernel_ok (uaccess_kernel()) #define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size))) #define access_ok(type, addr, size) \ ({ (void)(type); __access_ok((unsigned long)(addr), size); }) @@ -80,8 +71,6 @@ struct exception_table_entry /* Returns 0 if exception not found and fixup otherwise. */ unsigned long search_extables_range(unsigned long addr, unsigned long *g2); -void __ret_efault(void); - /* Uh, these should become the main single-value transfer routines.. * They automatically use the right size if we just have the right * pointer type.. @@ -246,39 +235,18 @@ int __get_user_bad(void); unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size); -static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) -{ - if (n && __access_ok((unsigned long) to, n)) { - check_object_size(from, n, true); - return __copy_user(to, (__force void __user *) from, n); - } else - return n; -} - -static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) +static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } -static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) -{ - if (n && __access_ok((unsigned long) from, n)) { - check_object_size(to, n, false); - return __copy_user((__force void __user *) to, from, n); - } else { - memset(to, 0, n); - return n; - } -} - -static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) +static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { return __copy_user((__force void __user *) to, from, n); } -#define __copy_to_user_inatomic __copy_to_user -#define __copy_from_user_inatomic __copy_from_user +#define INLINE_COPY_FROM_USER +#define INLINE_COPY_TO_USER static inline unsigned long __clear_user(void __user *addr, unsigned long size) { @@ -309,9 +277,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long n) return n; } -__must_check long strlen_user(const char __user *str); __must_check long strnlen_user(const char __user *str, long n); -#endif /* __ASSEMBLY__ */ - #endif /* _ASM_UACCESS_H */ diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 5373136c412b..6d4c997d1a9e 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -5,18 +5,11 @@ * User space memory access functions */ -#ifdef __KERNEL__ -#include <linux/errno.h> #include <linux/compiler.h> #include <linux/string.h> -#include <linux/thread_info.h> #include <asm/asi.h> #include <asm/spitfire.h> -#include <asm-generic/uaccess-unaligned.h> #include <asm/extable_64.h> -#endif - -#ifndef __ASSEMBLY__ #include <asm/processor.h> @@ -36,9 +29,6 @@ #define KERNEL_DS ((mm_segment_t) { ASI_P }) #define USER_DS ((mm_segment_t) { ASI_AIUS }) /* har har har */ -#define VERIFY_READ 0 -#define VERIFY_WRITE 1 - #define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)}) #define get_ds() (KERNEL_DS) @@ -185,55 +175,29 @@ __asm__ __volatile__( \ int __get_user_bad(void); -unsigned long __must_check ___copy_from_user(void *to, +unsigned long __must_check raw_copy_from_user(void *to, const void __user *from, unsigned long size); -static inline unsigned long __must_check -copy_from_user(void *to, const void __user *from, unsigned long size) -{ - check_object_size(to, size, false); - return ___copy_from_user(to, from, size); -} -#define __copy_from_user copy_from_user - -unsigned long __must_check ___copy_to_user(void __user *to, +unsigned long __must_check raw_copy_to_user(void __user *to, const void *from, unsigned long size); -static inline unsigned long __must_check -copy_to_user(void __user *to, const void *from, unsigned long size) -{ - check_object_size(from, size, true); +#define INLINE_COPY_FROM_USER +#define INLINE_COPY_TO_USER - return ___copy_to_user(to, from, size); -} -#define __copy_to_user copy_to_user - -unsigned long __must_check ___copy_in_user(void __user *to, +unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long size); -static inline unsigned long __must_check -copy_in_user(void __user *to, void __user *from, unsigned long size) -{ - return ___copy_in_user(to, from, size); -} -#define __copy_in_user copy_in_user unsigned long __must_check __clear_user(void __user *, unsigned long); #define clear_user __clear_user -__must_check long strlen_user(const char __user *str); __must_check long strnlen_user(const char __user *str, long n); -#define __copy_to_user_inatomic __copy_to_user -#define __copy_from_user_inatomic __copy_from_user - struct pt_regs; unsigned long compute_effective_address(struct pt_regs *, unsigned int insn, unsigned int rd); -#endif /* __ASSEMBLY__ */ - #endif /* _ASM_UACCESS_H */ diff --git a/arch/sparc/include/asm/uprobes.h b/arch/sparc/include/asm/uprobes.h index f87aae5a908e..36196c17aff8 100644 --- a/arch/sparc/include/asm/uprobes.h +++ b/arch/sparc/include/asm/uprobes.h @@ -42,8 +42,8 @@ struct arch_uprobe { }; struct arch_uprobe_task { - u32 saved_tpc; - u32 saved_tnpc; + u64 saved_tpc; + u64 saved_tnpc; }; struct task_struct; diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h index 8174f6cdbbbb..d1c47e9f0090 100644 --- a/arch/sparc/include/asm/vio.h +++ b/arch/sparc/include/asm/vio.h @@ -316,23 +316,33 @@ static inline u32 vio_dring_prev(struct vio_dring_state *dr, u32 index) } #define VIO_MAX_TYPE_LEN 32 +#define VIO_MAX_NAME_LEN 32 #define VIO_MAX_COMPAT_LEN 64 struct vio_dev { u64 mp; struct device_node *dp; + char node_name[VIO_MAX_NAME_LEN]; char type[VIO_MAX_TYPE_LEN]; char compat[VIO_MAX_COMPAT_LEN]; int compat_len; u64 dev_no; + unsigned long port_id; unsigned long channel_id; unsigned int tx_irq; unsigned int rx_irq; u64 rx_ino; + u64 tx_ino; + + /* Handle to the root of "channel-devices" sub-tree in MDESC */ + u64 cdev_handle; + + /* MD specific data used to identify the vdev in MD */ + union md_node_info md_node_info; struct device dev; }; @@ -346,6 +356,7 @@ struct vio_driver { void (*shutdown)(struct vio_dev *dev); unsigned long driver_data; struct device_driver driver; + bool no_irq; }; struct vio_version { @@ -489,5 +500,6 @@ int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev, void vio_port_up(struct vio_driver_state *vio); int vio_set_intr(unsigned long dev_ino, int state); +u64 vio_vdev_node(struct mdesc_handle *hp, struct vio_dev *vdev); #endif /* _SPARC64_VIO_H */ diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index b5843ee09fb5..2178c78c7c1a 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -1,50 +1,4 @@ # UAPI Header export list -# User exported sparc header files - include include/uapi/asm-generic/Kbuild.asm -header-y += apc.h -header-y += asi.h -header-y += auxvec.h -header-y += bitsperlong.h -header-y += byteorder.h -header-y += display7seg.h -header-y += envctrl.h -header-y += errno.h -header-y += fbio.h -header-y += fcntl.h -header-y += ioctl.h -header-y += ioctls.h -header-y += ipcbuf.h -header-y += jsflash.h -header-y += kvm_para.h -header-y += mman.h -header-y += msgbuf.h -header-y += openpromio.h -header-y += param.h -header-y += perfctr.h -header-y += poll.h -header-y += posix_types.h -header-y += psr.h -header-y += psrcompat.h -header-y += pstate.h -header-y += ptrace.h -header-y += resource.h -header-y += sembuf.h -header-y += setup.h -header-y += shmbuf.h -header-y += sigcontext.h -header-y += siginfo.h -header-y += signal.h -header-y += socket.h -header-y += sockios.h -header-y += stat.h -header-y += statfs.h -header-y += swab.h -header-y += termbits.h -header-y += termios.h -header-y += traps.h -header-y += uctx.h -header-y += unistd.h -header-y += utrap.h -header-y += watchdog.h +generic-y += types.h diff --git a/arch/sparc/include/uapi/asm/ioctls.h b/arch/sparc/include/uapi/asm/ioctls.h index 06b3f6c3bb9a..f5df72b93bb2 100644 --- a/arch/sparc/include/uapi/asm/ioctls.h +++ b/arch/sparc/include/uapi/asm/ioctls.h @@ -27,7 +27,7 @@ #define TIOCGRS485 _IOR('T', 0x41, struct serial_rs485) #define TIOCSRS485 _IOWR('T', 0x42, struct serial_rs485) -/* Note that all the ioctls that are not available in Linux have a +/* Note that all the ioctls that are not available in Linux have a * double underscore on the front to: a) avoid some programs to * think we support some ioctls under Linux (autoconfiguration stuff) */ @@ -88,6 +88,7 @@ #define TIOCGPTN _IOR('t', 134, unsigned int) /* Get Pty Number */ #define TIOCSPTLCK _IOW('t', 135, int) /* Lock/unlock PTY */ #define TIOCSIG _IOW('t', 136, int) /* Generate signal on Pty slave */ +#define TIOCGPTPEER _IO('t', 137) /* Safely open the slave */ /* Little f */ #define FIOCLEX _IO('f', 1) diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index a25dc32f5d6a..186fd8199f54 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -88,6 +88,16 @@ #define SCM_TIMESTAMPING_OPT_STATS 0x0038 +#define SO_MEMINFO 0x0039 + +#define SO_INCOMING_NAPI_ID 0x003a + +#define SO_COOKIE 0x003b + +#define SCM_TIMESTAMPING_PKTINFO 0x003c + +#define SO_PEERGROUPS 0x003d + /* 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/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index 36eee8132c22..ae77df75bffa 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -425,8 +425,9 @@ #define __NR_copy_file_range 357 #define __NR_preadv2 358 #define __NR_pwritev2 359 +#define __NR_statx 360 -#define NR_syscalls 360 +#define NR_syscalls 361 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 @@ -442,4 +443,9 @@ #define __IGNORE_getresgid #endif +/* Sparc doesn't have protection keys. */ +#define __IGNORE_pkey_mprotect +#define __IGNORE_pkey_alloc +#define __IGNORE_pkey_free + #endif /* _UAPI_SPARC_UNISTD_H */ diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index 9ebc37e7d64c..c988e7fa069b 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -167,7 +167,7 @@ static int apc_probe(struct platform_device *op) return 0; } -static struct of_device_id apc_match[] = { +static const struct of_device_id apc_match[] = { { .name = APC_OBPNAME, }, diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c index f76389a32342..3f09e1c83f58 100644 --- a/arch/sparc/kernel/asm-offsets.c +++ b/arch/sparc/kernel/asm-offsets.c @@ -11,6 +11,7 @@ */ #include <linux/sched.h> +#include <linux/mm_types.h> // #include <linux/mm.h> #include <linux/kbuild.h> diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index f87a55d77094..f87265afb175 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -9,6 +9,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/kthread.h> @@ -908,7 +909,7 @@ static int register_services(struct ds_info *dp) pbuf.req.handle = cp->handle; pbuf.req.major = 1; pbuf.req.minor = 0; - strcpy(pbuf.req.svc_id, cp->service_id); + strcpy(pbuf.id_buf, cp->service_id); err = __ds_send(lp, &pbuf, msg_len); if (err > 0) diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 6bcff698069b..cec54dc4ab81 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -130,17 +130,16 @@ unsigned long prepare_ftrace_return(unsigned long parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return parent + 8UL; - if (ftrace_push_return_trace(parent, self_addr, &trace.depth, - frame_pointer, NULL) == -EBUSY) - return parent + 8UL; - trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; + if (!ftrace_graph_entry(&trace)) + return parent + 8UL; + + if (ftrace_push_return_trace(parent, self_addr, &trace.depth, + frame_pointer, NULL) == -EBUSY) return parent + 8UL; - } return return_hooker; } diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S index 7bb317b87dde..7274e43ff9be 100644 --- a/arch/sparc/kernel/head_32.S +++ b/arch/sparc/kernel/head_32.S @@ -809,10 +809,3 @@ lvl14_save: .word 0 .word 0 .word t_irq14 - - .section ".fixup",#alloc,#execinstr - .globl __ret_efault -__ret_efault: - ret - restore %g0, -EFAULT, %o0 -EXPORT_SYMBOL(__ret_efault) diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 6aa3da152c20..41a407328667 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -96,6 +96,7 @@ sparc64_boot: andn %g1, PSTATE_AM, %g1 wrpr %g1, 0x0, %pstate ba,a,pt %xcc, 1f + nop .globl prom_finddev_name, prom_chosen_path, prom_root_node .globl prom_getprop_name, prom_mmu_name, prom_peer_name @@ -613,6 +614,7 @@ niagara_tlb_fixup: nop ba,a,pt %xcc, 80f + nop niagara4_patch: call niagara4_patch_copyops nop @@ -622,6 +624,7 @@ niagara4_patch: nop ba,a,pt %xcc, 80f + nop niagara2_patch: call niagara2_patch_copyops @@ -632,6 +635,7 @@ niagara2_patch: nop ba,a,pt %xcc, 80f + nop niagara_patch: call niagara_patch_copyops @@ -935,3 +939,9 @@ ENTRY(__retl_o1) retl mov %o1, %o0 ENDPROC(__retl_o1) + +ENTRY(__retl_o1_asi) + wr %o5, 0x0, %asi + retl + mov %o1, %o0 +ENDPROC(__retl_o1_asi) diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 9df997995f6b..fcbcc031f615 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -314,7 +314,7 @@ bad: bad_no_ctx: if (printk_ratelimit()) WARN_ON(1); - return DMA_ERROR_CODE; + return SPARC_MAPPING_ERROR; } static void strbuf_flush(struct strbuf *strbuf, struct iommu *iommu, @@ -547,7 +547,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist, if (outcount < incount) { outs = sg_next(outs); - outs->dma_address = DMA_ERROR_CODE; + outs->dma_address = SPARC_MAPPING_ERROR; outs->dma_length = 0; } @@ -573,7 +573,7 @@ iommu_map_failed: iommu_tbl_range_free(&iommu->tbl, vaddr, npages, IOMMU_ERROR_CODE); - s->dma_address = DMA_ERROR_CODE; + s->dma_address = SPARC_MAPPING_ERROR; s->dma_length = 0; } if (s == outs) @@ -741,40 +741,38 @@ 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 = { - .alloc = dma_4u_alloc_coherent, - .free = dma_4u_free_coherent, - .map_page = dma_4u_map_page, - .unmap_page = dma_4u_unmap_page, - .map_sg = dma_4u_map_sg, - .unmap_sg = dma_4u_unmap_sg, - .sync_single_for_cpu = dma_4u_sync_single_for_cpu, - .sync_sg_for_cpu = dma_4u_sync_sg_for_cpu, -}; - -struct dma_map_ops *dma_ops = &sun4u_dma_ops; -EXPORT_SYMBOL(dma_ops); +static int dma_4u_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == SPARC_MAPPING_ERROR; +} -int dma_supported(struct device *dev, u64 device_mask) +static int dma_4u_supported(struct device *dev, u64 device_mask) { struct iommu *iommu = dev->archdata.iommu; - u64 dma_addr_mask = iommu->dma_addr_mask; - - if (device_mask > DMA_BIT_MASK(32)) { - if (iommu->atu) - dma_addr_mask = iommu->atu->dma_addr_mask; - else - return 0; - } - if ((device_mask & dma_addr_mask) == dma_addr_mask) + if (device_mask > DMA_BIT_MASK(32)) + return 0; + if ((device_mask & iommu->dma_addr_mask) == iommu->dma_addr_mask) return 1; - #ifdef CONFIG_PCI if (dev_is_pci(dev)) return pci64_dma_supported(to_pci_dev(dev), device_mask); #endif - return 0; } -EXPORT_SYMBOL(dma_supported); + +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, + .unmap_page = dma_4u_unmap_page, + .map_sg = dma_4u_map_sg, + .unmap_sg = dma_4u_unmap_sg, + .sync_single_for_cpu = dma_4u_sync_single_for_cpu, + .sync_sg_for_cpu = dma_4u_sync_sg_for_cpu, + .dma_supported = dma_4u_supported, + .mapping_error = dma_4u_mapping_error, +}; + +const struct dma_map_ops *dma_ops = &sun4u_dma_ops; +EXPORT_SYMBOL(dma_ops); diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h index 828493329f68..5ea5c192b1d9 100644 --- a/arch/sparc/kernel/iommu_common.h +++ b/arch/sparc/kernel/iommu_common.h @@ -47,4 +47,6 @@ static inline int is_span_boundary(unsigned long entry, return iommu_is_span_boundary(entry, nr, shift, boundary_size); } +#define SPARC_MAPPING_ERROR (~(dma_addr_t)0x0) + #endif /* _IOMMU_COMMON_H */ diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 6ffaec44931a..12894f259bea 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -401,7 +401,12 @@ static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg, BUG(); } -static struct dma_map_ops sbus_dma_ops = { +static int sbus_dma_supported(struct device *dev, u64 mask) +{ + return 0; +} + +static const struct dma_map_ops sbus_dma_ops = { .alloc = sbus_alloc_coherent, .free = sbus_free_coherent, .map_page = sbus_map_page, @@ -410,6 +415,7 @@ static struct dma_map_ops sbus_dma_ops = { .unmap_sg = sbus_unmap_sg, .sync_sg_for_cpu = sbus_sync_sg_for_cpu, .sync_sg_for_device = sbus_sync_sg_for_device, + .dma_supported = sbus_dma_supported, }; static int __init sparc_register_ioport(void) @@ -637,7 +643,8 @@ static void pci32_sync_sg_for_device(struct device *device, struct scatterlist * } } -struct dma_map_ops pci32_dma_ops = { +/* note: leon re-uses pci32_dma_ops */ +const struct dma_map_ops pci32_dma_ops = { .alloc = pci32_alloc_coherent, .free = pci32_free_coherent, .map_page = pci32_map_page, @@ -651,29 +658,9 @@ 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; -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); - -/* - * Return whether the given PCI device DMA address mask can be - * supported properly. For example, if your device can only drive the - * low 24-bits during PCI bus mastering, then you would pass - * 0x00ffffff as the mask to this function. - */ -int dma_supported(struct device *dev, u64 mask) -{ - if (dev_is_pci(dev)) - return 1; - - return 0; -} -EXPORT_SYMBOL(dma_supported); - #ifdef CONFIG_PROC_FS static int sparc_io_proc_show(struct seq_file *m, void *v) diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 4d0248aa0928..99dd133a029f 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb) { #ifdef CONFIG_SMP unsigned long page; + void *mondo, *p; - BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64)); + BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE); + + /* Make sure mondo block is 64byte aligned */ + p = kzalloc(127, GFP_KERNEL); + if (!p) { + prom_printf("SUN4V: Error, cannot allocate mondo block.\n"); + prom_halt(); + } + mondo = (void *)(((unsigned long)p + 63) & ~0x3f); + tb->cpu_mondo_block_pa = __pa(mondo); page = get_zeroed_page(GFP_KERNEL); if (!page) { - prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n"); + prom_printf("SUN4V: Error, cannot allocate cpu list page.\n"); prom_halt(); } - tb->cpu_mondo_block_pa = __pa(page); - tb->cpu_list_pa = __pa(page + 64); + tb->cpu_list_pa = __pa(page); #endif } diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c index 07933b9e9ce0..93adde1ac166 100644 --- a/arch/sparc/kernel/jump_label.c +++ b/arch/sparc/kernel/jump_label.c @@ -41,12 +41,10 @@ void arch_jump_label_transform(struct jump_entry *entry, val = 0x01000000; } - get_online_cpus(); mutex_lock(&text_mutex); *insn = val; flushi(insn); mutex_unlock(&text_mutex); - put_online_cpus(); } #endif diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h index c9804551262c..b625db4cfb78 100644 --- a/arch/sparc/kernel/kernel.h +++ b/arch/sparc/kernel/kernel.h @@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr /* smp_64.c */ void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs); void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs); -void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs); void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs); void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs); @@ -53,6 +52,9 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs); void do_signal32(struct pt_regs * regs); asmlinkage int do_sys32_sigstack(u32 u_ssptr, u32 u_ossptr, unsigned long sp); +/* time_64.c */ +void __init time_init_early(void); + /* compat_audit.c */ extern unsigned int sparc32_dir_class[]; extern unsigned int sparc32_chattr_class[]; diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index 59d503866431..840e0b21bfe3 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -34,7 +34,6 @@ static char version[] = DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; -#define LDC_PACKET_SIZE 64 /* Packet header layout for unreliable and reliable mode frames. * When in RAW mode, packets are simply straight 64-byte payloads @@ -178,6 +177,8 @@ do { if (lp->cfg.debug & LDC_DEBUG_##TYPE) \ printk(KERN_INFO PFX "ID[%lu] " f, lp->id, ## a); \ } while (0) +#define LDC_ABORT(lp) ldc_abort((lp), __func__) + static const char *state_to_str(u8 state) { switch (state) { @@ -196,15 +197,6 @@ static const char *state_to_str(u8 state) } } -static void ldc_set_state(struct ldc_channel *lp, u8 state) -{ - ldcdbg(STATE, "STATE (%s) --> (%s)\n", - state_to_str(lp->state), - state_to_str(state)); - - lp->state = state; -} - static unsigned long __advance(unsigned long off, unsigned long num_entries) { off += LDC_PACKET_SIZE; @@ -516,11 +508,12 @@ static int send_data_nack(struct ldc_channel *lp, struct ldc_packet *data_pkt) return err; } -static int ldc_abort(struct ldc_channel *lp) +static int ldc_abort(struct ldc_channel *lp, const char *msg) { unsigned long hv_err; - ldcdbg(STATE, "ABORT\n"); + ldcdbg(STATE, "ABORT[%s]\n", msg); + ldc_print(lp); /* We report but do not act upon the hypervisor errors because * there really isn't much we can do if they fail at this point. @@ -605,7 +598,7 @@ static int process_ver_info(struct ldc_channel *lp, struct ldc_version *vp) } } if (err) - return ldc_abort(lp); + return LDC_ABORT(lp); return 0; } @@ -618,13 +611,13 @@ static int process_ver_ack(struct ldc_channel *lp, struct ldc_version *vp) if (lp->hs_state == LDC_HS_GOTVERS) { if (lp->ver.major != vp->major || lp->ver.minor != vp->minor) - return ldc_abort(lp); + return LDC_ABORT(lp); } else { lp->ver = *vp; lp->hs_state = LDC_HS_GOTVERS; } if (send_rts(lp)) - return ldc_abort(lp); + return LDC_ABORT(lp); return 0; } @@ -635,17 +628,17 @@ static int process_ver_nack(struct ldc_channel *lp, struct ldc_version *vp) unsigned long new_tail; if (vp->major == 0 && vp->minor == 0) - return ldc_abort(lp); + return LDC_ABORT(lp); vap = find_by_major(vp->major); if (!vap) - return ldc_abort(lp); + return LDC_ABORT(lp); p = handshake_compose_ctrl(lp, LDC_INFO, LDC_VERS, vap, sizeof(*vap), &new_tail); if (!p) - return ldc_abort(lp); + return LDC_ABORT(lp); return send_tx_packet(lp, p, new_tail); } @@ -668,7 +661,7 @@ static int process_version(struct ldc_channel *lp, return process_ver_nack(lp, vp); default: - return ldc_abort(lp); + return LDC_ABORT(lp); } } @@ -681,13 +674,13 @@ static int process_rts(struct ldc_channel *lp, if (p->stype != LDC_INFO || lp->hs_state != LDC_HS_GOTVERS || p->env != lp->cfg.mode) - return ldc_abort(lp); + return LDC_ABORT(lp); lp->snd_nxt = p->seqid; lp->rcv_nxt = p->seqid; lp->hs_state = LDC_HS_SENTRTR; if (send_rtr(lp)) - return ldc_abort(lp); + return LDC_ABORT(lp); return 0; } @@ -700,7 +693,7 @@ static int process_rtr(struct ldc_channel *lp, if (p->stype != LDC_INFO || p->env != lp->cfg.mode) - return ldc_abort(lp); + return LDC_ABORT(lp); lp->snd_nxt = p->seqid; lp->hs_state = LDC_HS_COMPLETE; @@ -723,7 +716,7 @@ static int process_rdx(struct ldc_channel *lp, if (p->stype != LDC_INFO || !(rx_seq_ok(lp, p->seqid))) - return ldc_abort(lp); + return LDC_ABORT(lp); lp->rcv_nxt = p->seqid; @@ -750,14 +743,14 @@ static int process_control_frame(struct ldc_channel *lp, return process_rdx(lp, p); default: - return ldc_abort(lp); + return LDC_ABORT(lp); } } static int process_error_frame(struct ldc_channel *lp, struct ldc_packet *p) { - return ldc_abort(lp); + return LDC_ABORT(lp); } static int process_data_ack(struct ldc_channel *lp, @@ -776,7 +769,7 @@ static int process_data_ack(struct ldc_channel *lp, return 0; } if (head == lp->tx_tail) - return ldc_abort(lp); + return LDC_ABORT(lp); } return 0; @@ -820,16 +813,21 @@ static irqreturn_t ldc_rx(int irq, void *dev_id) lp->hs_state = LDC_HS_COMPLETE; ldc_set_state(lp, LDC_STATE_CONNECTED); - event_mask |= LDC_EVENT_UP; - - orig_state = lp->chan_state; + /* + * Generate an LDC_EVENT_UP event if the channel + * was not already up. + */ + if (orig_state != LDC_CHANNEL_UP) { + event_mask |= LDC_EVENT_UP; + orig_state = lp->chan_state; + } } /* If we are in reset state, flush the RX queue and ignore * everything. */ if (lp->flags & LDC_FLAG_RESET) { - (void) __set_rx_head(lp, lp->rx_tail); + (void) ldc_rx_reset(lp); goto out; } @@ -880,7 +878,7 @@ handshake_complete: break; default: - err = ldc_abort(lp); + err = LDC_ABORT(lp); break; } @@ -895,7 +893,7 @@ handshake_complete: err = __set_rx_head(lp, new); if (err < 0) { - (void) ldc_abort(lp); + (void) LDC_ABORT(lp); break; } if (lp->hs_state == LDC_HS_COMPLETE) @@ -936,7 +934,14 @@ static irqreturn_t ldc_tx(int irq, void *dev_id) lp->hs_state = LDC_HS_COMPLETE; ldc_set_state(lp, LDC_STATE_CONNECTED); - event_mask |= LDC_EVENT_UP; + /* + * Generate an LDC_EVENT_UP event if the channel + * was not already up. + */ + if (orig_state != LDC_CHANNEL_UP) { + event_mask |= LDC_EVENT_UP; + orig_state = lp->chan_state; + } } spin_unlock_irqrestore(&lp->lock, flags); @@ -1342,6 +1347,14 @@ int ldc_bind(struct ldc_channel *lp) lp->hs_state = LDC_HS_OPEN; ldc_set_state(lp, LDC_STATE_BOUND); + if (lp->cfg.mode == LDC_MODE_RAW) { + /* + * There is no handshake in RAW mode, so handshake + * is completed. + */ + lp->hs_state = LDC_HS_COMPLETE; + } + spin_unlock_irqrestore(&lp->lock, flags); return 0; @@ -1447,12 +1460,54 @@ int ldc_state(struct ldc_channel *lp) } EXPORT_SYMBOL(ldc_state); +void ldc_set_state(struct ldc_channel *lp, u8 state) +{ + ldcdbg(STATE, "STATE (%s) --> (%s)\n", + state_to_str(lp->state), + state_to_str(state)); + + lp->state = state; +} +EXPORT_SYMBOL(ldc_set_state); + +int ldc_mode(struct ldc_channel *lp) +{ + return lp->cfg.mode; +} +EXPORT_SYMBOL(ldc_mode); + +int ldc_rx_reset(struct ldc_channel *lp) +{ + return __set_rx_head(lp, lp->rx_tail); +} + +void __ldc_print(struct ldc_channel *lp, const char *caller) +{ + pr_info("%s: id=0x%lx flags=0x%x state=%s cstate=0x%lx hsstate=0x%x\n" + "\trx_h=0x%lx rx_t=0x%lx rx_n=%ld\n" + "\ttx_h=0x%lx tx_t=0x%lx tx_n=%ld\n" + "\trcv_nxt=%u snd_nxt=%u\n", + caller, lp->id, lp->flags, state_to_str(lp->state), + lp->chan_state, lp->hs_state, + lp->rx_head, lp->rx_tail, lp->rx_num_entries, + lp->tx_head, lp->tx_tail, lp->tx_num_entries, + lp->rcv_nxt, lp->snd_nxt); +} + static int write_raw(struct ldc_channel *lp, const void *buf, unsigned int size) { struct ldc_packet *p; - unsigned long new_tail; + unsigned long new_tail, hv_err; int err; + hv_err = sun4v_ldc_tx_get_state(lp->id, &lp->tx_head, &lp->tx_tail, + &lp->chan_state); + if (unlikely(hv_err)) + return -EBUSY; + + if (unlikely(lp->chan_state != LDC_CHANNEL_UP)) + return LDC_ABORT(lp); + if (size > LDC_PACKET_SIZE) return -EMSGSIZE; @@ -1483,7 +1538,7 @@ static int read_raw(struct ldc_channel *lp, void *buf, unsigned int size) &lp->rx_tail, &lp->chan_state); if (hv_err) - return ldc_abort(lp); + return LDC_ABORT(lp); if (lp->chan_state == LDC_CHANNEL_DOWN || lp->chan_state == LDC_CHANNEL_RESETTING) @@ -1526,7 +1581,7 @@ static int write_nonraw(struct ldc_channel *lp, const void *buf, return -EBUSY; if (unlikely(lp->chan_state != LDC_CHANNEL_UP)) - return ldc_abort(lp); + return LDC_ABORT(lp); if (!tx_has_space_for(lp, size)) return -EAGAIN; @@ -1592,9 +1647,9 @@ static int rx_bad_seq(struct ldc_channel *lp, struct ldc_packet *p, if (err) return err; - err = __set_rx_head(lp, lp->rx_tail); + err = ldc_rx_reset(lp); if (err < 0) - return ldc_abort(lp); + return LDC_ABORT(lp); return 0; } @@ -1607,7 +1662,7 @@ static int data_ack_nack(struct ldc_channel *lp, struct ldc_packet *p) return err; } if (p->stype & LDC_NACK) - return ldc_abort(lp); + return LDC_ABORT(lp); return 0; } @@ -1627,7 +1682,7 @@ static int rx_data_wait(struct ldc_channel *lp, unsigned long cur_head) &lp->rx_tail, &lp->chan_state); if (hv_err) - return ldc_abort(lp); + return LDC_ABORT(lp); if (lp->chan_state == LDC_CHANNEL_DOWN || lp->chan_state == LDC_CHANNEL_RESETTING) @@ -1650,7 +1705,7 @@ static int rx_set_head(struct ldc_channel *lp, unsigned long head) int err = __set_rx_head(lp, head); if (err < 0) - return ldc_abort(lp); + return LDC_ABORT(lp); lp->rx_head = head; return 0; @@ -1689,7 +1744,7 @@ static int read_nonraw(struct ldc_channel *lp, void *buf, unsigned int size) &lp->rx_tail, &lp->chan_state); if (hv_err) - return ldc_abort(lp); + return LDC_ABORT(lp); if (lp->chan_state == LDC_CHANNEL_DOWN || lp->chan_state == LDC_CHANNEL_RESETTING) @@ -1733,9 +1788,14 @@ static int read_nonraw(struct ldc_channel *lp, void *buf, unsigned int size) lp->rcv_nxt = p->seqid; + /* + * If this is a control-only packet, there is nothing + * else to do but advance the rx queue since the packet + * was already processed above. + */ if (!(p->type & LDC_DATA)) { new = rx_advance(lp, new); - goto no_data; + break; } if (p->stype & (LDC_ACK | LDC_NACK)) { err = data_ack_nack(lp, p); @@ -1900,6 +1960,8 @@ int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size) unsigned long flags; int err; + ldcdbg(RX, "%s: entered size=%d\n", __func__, size); + if (!buf) return -EINVAL; @@ -1915,6 +1977,9 @@ int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size) spin_unlock_irqrestore(&lp->lock, flags); + ldcdbg(RX, "%s: mode=%d, head=%lu, tail=%lu rv=%d\n", __func__, + lp->cfg.mode, lp->rx_head, lp->rx_tail, err); + return err; } EXPORT_SYMBOL(ldc_read); diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c index 3ae36f36e758..e278bf52963b 100644 --- a/arch/sparc/kernel/led.c +++ b/arch/sparc/kernel/led.c @@ -8,6 +8,7 @@ #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/uaccess.h> +#include <linux/sched/loadavg.h> #include <asm/auxio.h> @@ -69,16 +70,9 @@ static ssize_t led_proc_write(struct file *file, const char __user *buffer, if (count > LED_MAX_LENGTH) count = LED_MAX_LENGTH; - buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (copy_from_user(buf, buffer, count)) { - kfree(buf); - return -EFAULT; - } - - buf[count] = '\0'; + buf = memdup_user_nul(buffer, count); + if (IS_ERR(buf)) + return PTR_ERR(buf); /* work around \n when echo'ing into proc */ if (buf[count - 1] == '\n') diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c index 71e16f2241c2..db7acf27bea2 100644 --- a/arch/sparc/kernel/leon_smp.c +++ b/arch/sparc/kernel/leon_smp.c @@ -9,7 +9,7 @@ #include <asm/head.h> #include <linux/kernel.h> -#include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/threads.h> #include <linux/smp.h> #include <linux/interrupt.h> @@ -93,7 +93,7 @@ void leon_cpu_pre_online(void *arg) : "memory" /* paranoid */); /* Attach to the address space of init_task. */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; while (!cpumask_test_cpu(cpuid, &smp_commenced_mask)) diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index c0765bbf60ea..fa466ce45bc9 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -75,6 +75,74 @@ struct mdesc_handle { struct mdesc_hdr mdesc; }; +typedef int (*mdesc_node_info_get_f)(struct mdesc_handle *, u64, + union md_node_info *); +typedef void (*mdesc_node_info_rel_f)(union md_node_info *); +typedef bool (*mdesc_node_match_f)(union md_node_info *, union md_node_info *); + +struct md_node_ops { + char *name; + mdesc_node_info_get_f get_info; + mdesc_node_info_rel_f rel_info; + mdesc_node_match_f node_match; +}; + +static int get_vdev_port_node_info(struct mdesc_handle *md, u64 node, + union md_node_info *node_info); +static void rel_vdev_port_node_info(union md_node_info *node_info); +static bool vdev_port_node_match(union md_node_info *a_node_info, + union md_node_info *b_node_info); + +static int get_ds_port_node_info(struct mdesc_handle *md, u64 node, + union md_node_info *node_info); +static void rel_ds_port_node_info(union md_node_info *node_info); +static bool ds_port_node_match(union md_node_info *a_node_info, + union md_node_info *b_node_info); + +/* supported node types which can be registered */ +static struct md_node_ops md_node_ops_table[] = { + {"virtual-device-port", get_vdev_port_node_info, + rel_vdev_port_node_info, vdev_port_node_match}, + {"domain-services-port", get_ds_port_node_info, + rel_ds_port_node_info, ds_port_node_match}, + {NULL, NULL, NULL, NULL} +}; + +static void mdesc_get_node_ops(const char *node_name, + mdesc_node_info_get_f *get_info_f, + mdesc_node_info_rel_f *rel_info_f, + mdesc_node_match_f *match_f) +{ + int i; + + if (get_info_f) + *get_info_f = NULL; + + if (rel_info_f) + *rel_info_f = NULL; + + if (match_f) + *match_f = NULL; + + if (!node_name) + return; + + for (i = 0; md_node_ops_table[i].name != NULL; i++) { + if (strcmp(md_node_ops_table[i].name, node_name) == 0) { + if (get_info_f) + *get_info_f = md_node_ops_table[i].get_info; + + if (rel_info_f) + *rel_info_f = md_node_ops_table[i].rel_info; + + if (match_f) + *match_f = md_node_ops_table[i].node_match; + + break; + } + } +} + static void mdesc_handle_init(struct mdesc_handle *hp, unsigned int handle_size, void *base) @@ -137,12 +205,10 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size) handle_size = (sizeof(struct mdesc_handle) - sizeof(struct mdesc_hdr) + mdesc_size); + base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + if (!base) + return NULL; - /* - * Allocation has to succeed because mdesc update would be missed - * and such events are not retransmitted. - */ - base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_NOFAIL); addr = (unsigned long)base; addr = (addr + 15UL) & ~15UL; hp = (struct mdesc_handle *) addr; @@ -218,14 +284,31 @@ static struct mdesc_notifier_client *client_list; void mdesc_register_notifier(struct mdesc_notifier_client *client) { + bool supported = false; u64 node; + int i; mutex_lock(&mdesc_mutex); + + /* check to see if the node is supported for registration */ + for (i = 0; md_node_ops_table[i].name != NULL; i++) { + if (strcmp(md_node_ops_table[i].name, client->node_name) == 0) { + supported = true; + break; + } + } + + if (!supported) { + pr_err("MD: %s node not supported\n", client->node_name); + mutex_unlock(&mdesc_mutex); + return; + } + client->next = client_list; client_list = client; mdesc_for_each_node_by_name(cur_mdesc, node, client->node_name) - client->add(cur_mdesc, node); + client->add(cur_mdesc, node, client->node_name); mutex_unlock(&mdesc_mutex); } @@ -249,59 +332,145 @@ static const u64 *parent_cfg_handle(struct mdesc_handle *hp, u64 node) return id; } +static int get_vdev_port_node_info(struct mdesc_handle *md, u64 node, + union md_node_info *node_info) +{ + const u64 *parent_cfg_hdlp; + const char *name; + const u64 *idp; + + /* + * Virtual device nodes are distinguished by: + * 1. "id" property + * 2. "name" property + * 3. parent node "cfg-handle" property + */ + idp = mdesc_get_property(md, node, "id", NULL); + name = mdesc_get_property(md, node, "name", NULL); + parent_cfg_hdlp = parent_cfg_handle(md, node); + + if (!idp || !name || !parent_cfg_hdlp) + return -1; + + node_info->vdev_port.id = *idp; + node_info->vdev_port.name = kstrdup_const(name, GFP_KERNEL); + node_info->vdev_port.parent_cfg_hdl = *parent_cfg_hdlp; + + return 0; +} + +static void rel_vdev_port_node_info(union md_node_info *node_info) +{ + if (node_info && node_info->vdev_port.name) { + kfree_const(node_info->vdev_port.name); + node_info->vdev_port.name = NULL; + } +} + +static bool vdev_port_node_match(union md_node_info *a_node_info, + union md_node_info *b_node_info) +{ + if (a_node_info->vdev_port.id != b_node_info->vdev_port.id) + return false; + + if (a_node_info->vdev_port.parent_cfg_hdl != + b_node_info->vdev_port.parent_cfg_hdl) + return false; + + if (strncmp(a_node_info->vdev_port.name, + b_node_info->vdev_port.name, MDESC_MAX_STR_LEN) != 0) + return false; + + return true; +} + +static int get_ds_port_node_info(struct mdesc_handle *md, u64 node, + union md_node_info *node_info) +{ + const u64 *idp; + + /* DS port nodes use the "id" property to distinguish them */ + idp = mdesc_get_property(md, node, "id", NULL); + if (!idp) + return -1; + + node_info->ds_port.id = *idp; + + return 0; +} + +static void rel_ds_port_node_info(union md_node_info *node_info) +{ +} + +static bool ds_port_node_match(union md_node_info *a_node_info, + union md_node_info *b_node_info) +{ + if (a_node_info->ds_port.id != b_node_info->ds_port.id) + return false; + + return true; +} + /* Run 'func' on nodes which are in A but not in B. */ static void invoke_on_missing(const char *name, struct mdesc_handle *a, struct mdesc_handle *b, - void (*func)(struct mdesc_handle *, u64)) + void (*func)(struct mdesc_handle *, u64, + const char *node_name)) { - u64 node; + mdesc_node_info_get_f get_info_func; + mdesc_node_info_rel_f rel_info_func; + mdesc_node_match_f node_match_func; + union md_node_info a_node_info; + union md_node_info b_node_info; + bool found; + u64 a_node; + u64 b_node; + int rv; - mdesc_for_each_node_by_name(a, node, name) { - int found = 0, is_vdc_port = 0; - const char *name_prop; - const u64 *id; - u64 fnode; - - name_prop = mdesc_get_property(a, node, "name", NULL); - if (name_prop && !strcmp(name_prop, "vdc-port")) { - is_vdc_port = 1; - id = parent_cfg_handle(a, node); - } else - id = mdesc_get_property(a, node, "id", NULL); - - if (!id) { - printk(KERN_ERR "MD: Cannot find ID for %s node.\n", - (name_prop ? name_prop : name)); + /* + * Find the get_info, rel_info and node_match ops for the given + * node name + */ + mdesc_get_node_ops(name, &get_info_func, &rel_info_func, + &node_match_func); + + /* If we didn't find a match, the node type is not supported */ + if (!get_info_func || !rel_info_func || !node_match_func) { + pr_err("MD: %s node type is not supported\n", name); + return; + } + + mdesc_for_each_node_by_name(a, a_node, name) { + found = false; + + rv = get_info_func(a, a_node, &a_node_info); + if (rv != 0) { + pr_err("MD: Cannot find 1 or more required match properties for %s node.\n", + name); continue; } - mdesc_for_each_node_by_name(b, fnode, name) { - const u64 *fid; - - if (is_vdc_port) { - name_prop = mdesc_get_property(b, fnode, - "name", NULL); - if (!name_prop || - strcmp(name_prop, "vdc-port")) - continue; - fid = parent_cfg_handle(b, fnode); - if (!fid) { - printk(KERN_ERR "MD: Cannot find ID " - "for vdc-port node.\n"); - continue; - } - } else - fid = mdesc_get_property(b, fnode, - "id", NULL); - - if (*id == *fid) { - found = 1; + /* Check each node in B for node matching a_node */ + mdesc_for_each_node_by_name(b, b_node, name) { + rv = get_info_func(b, b_node, &b_node_info); + if (rv != 0) + continue; + + if (node_match_func(&a_node_info, &b_node_info)) { + found = true; + rel_info_func(&b_node_info); break; } + + rel_info_func(&b_node_info); } + + rel_info_func(&a_node_info); + if (!found) - func(a, node); + func(a, a_node, name); } } @@ -367,6 +536,76 @@ out: mutex_unlock(&mdesc_mutex); } +u64 mdesc_get_node(struct mdesc_handle *hp, const char *node_name, + union md_node_info *node_info) +{ + mdesc_node_info_get_f get_info_func; + mdesc_node_info_rel_f rel_info_func; + mdesc_node_match_f node_match_func; + union md_node_info hp_node_info; + u64 hp_node; + int rv; + + if (hp == NULL || node_name == NULL || node_info == NULL) + return MDESC_NODE_NULL; + + /* Find the ops for the given node name */ + mdesc_get_node_ops(node_name, &get_info_func, &rel_info_func, + &node_match_func); + + /* If we didn't find ops for the given node name, it is not supported */ + if (!get_info_func || !rel_info_func || !node_match_func) { + pr_err("MD: %s node is not supported\n", node_name); + return -EINVAL; + } + + mdesc_for_each_node_by_name(hp, hp_node, node_name) { + rv = get_info_func(hp, hp_node, &hp_node_info); + if (rv != 0) + continue; + + if (node_match_func(node_info, &hp_node_info)) + break; + + rel_info_func(&hp_node_info); + } + + rel_info_func(&hp_node_info); + + return hp_node; +} +EXPORT_SYMBOL(mdesc_get_node); + +int mdesc_get_node_info(struct mdesc_handle *hp, u64 node, + const char *node_name, union md_node_info *node_info) +{ + mdesc_node_info_get_f get_info_func; + int rv; + + if (hp == NULL || node == MDESC_NODE_NULL || + node_name == NULL || node_info == NULL) + return -EINVAL; + + /* Find the get_info op for the given node name */ + mdesc_get_node_ops(node_name, &get_info_func, NULL, NULL); + + /* If we didn't find a get_info_func, the node name is not supported */ + if (get_info_func == NULL) { + pr_err("MD: %s node is not supported\n", node_name); + return -EINVAL; + } + + rv = get_info_func(hp, node, node_info); + if (rv != 0) { + pr_err("MD: Cannot find 1 or more required match properties for %s node.\n", + node_name); + return -1; + } + + return 0; +} +EXPORT_SYMBOL(mdesc_get_node_info); + static struct mdesc_elem *node_block(struct mdesc_hdr *mdesc) { return (struct mdesc_elem *) (mdesc + 1); diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S index 34b4933900bf..9276d2f0dd86 100644 --- a/arch/sparc/kernel/misctrap.S +++ b/arch/sparc/kernel/misctrap.S @@ -82,6 +82,7 @@ do_stdfmna: call handle_stdfmna add %sp, PTREGS_OFF, %o0 ba,a,pt %xcc, rtrap + nop .size do_stdfmna,.-do_stdfmna .type breakpoint_trap,#function diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 95e73c63c99d..048ad783ea3f 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum); static DEFINE_PER_CPU(long, alert_counter); static DEFINE_PER_CPU(int, nmi_touch); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { if (atomic_read(&nmi_active)) { int cpu; @@ -61,10 +61,8 @@ void touch_nmi_watchdog(void) per_cpu(nmi_touch, cpu) = 1; } } - - touch_softlockup_watchdog(); } -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) { diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 015e55a7495d..7eceaa10836f 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -862,9 +862,9 @@ static void __pci_mmap_set_pgprot(struct pci_dev *dev, struct vm_area_struct *vm * * Returns a negative error code on failure, zero on success. */ -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, - int write_combine) +int pci_mmap_page_range(struct pci_dev *dev, int bar, + struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine) { int ret; diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index f4daccd12bf5..f10e2f712394 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -24,6 +24,7 @@ #include "pci_impl.h" #include "iommu_common.h" +#include "kernel.h" #include "pci_sun4v.h" @@ -412,12 +413,12 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, bad: if (printk_ratelimit()) WARN_ON(1); - return DMA_ERROR_CODE; + return SPARC_MAPPING_ERROR; iommu_map_fail: local_irq_restore(flags); iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); - return DMA_ERROR_CODE; + return SPARC_MAPPING_ERROR; } static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, @@ -590,7 +591,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, if (outcount < incount) { outs = sg_next(outs); - outs->dma_address = DMA_ERROR_CODE; + outs->dma_address = SPARC_MAPPING_ERROR; outs->dma_length = 0; } @@ -607,7 +608,7 @@ iommu_map_failed: iommu_tbl_range_free(tbl, vaddr, npages, IOMMU_ERROR_CODE); /* XXX demap? XXX */ - s->dma_address = DMA_ERROR_CODE; + s->dma_address = SPARC_MAPPING_ERROR; s->dma_length = 0; } if (s == outs) @@ -669,13 +670,37 @@ 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 int dma_4v_supported(struct device *dev, u64 device_mask) +{ + struct iommu *iommu = dev->archdata.iommu; + u64 dma_addr_mask = iommu->dma_addr_mask; + + if (device_mask > DMA_BIT_MASK(32)) { + if (iommu->atu) + dma_addr_mask = iommu->atu->dma_addr_mask; + else + return 0; + } + + if ((device_mask & dma_addr_mask) == dma_addr_mask) + return 1; + return pci64_dma_supported(to_pci_dev(dev), device_mask); +} + +static int dma_4v_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == SPARC_MAPPING_ERROR; +} + +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, .unmap_page = dma_4v_unmap_page, .map_sg = dma_4v_map_sg, .unmap_sg = dma_4v_unmap_sg, + .dma_supported = dma_4v_supported, + .mapping_error = dma_4v_mapping_error, }; static void pci_sun4v_scan_bus(struct pci_pbm_info *pbm, struct device *parent) diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index f12b23f7b515..3b26cf62df6d 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -71,7 +71,7 @@ static int pmc_probe(struct platform_device *op) return 0; } -static struct of_device_id pmc_match[] = { +static const struct of_device_id pmc_match[] = { { .name = PMC_OBPNAME, }, diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index 48ffc3e7d1dd..9245f93398c7 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -14,6 +14,9 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/stddef.h> @@ -174,14 +177,6 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp) } /* - * Note: sparc64 has a pretty intricated thread_saved_pc, check it out. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return task_thread_info(tsk)->kpc; -} - -/* * Free current thread data structures etc.. */ void exit_thread(struct task_struct *tsk) diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d249ca10b203..b96104da5bd6 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -14,6 +14,9 @@ #include <linux/errno.h> #include <linux/export.h> #include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/fs.h> @@ -397,25 +400,6 @@ core_initcall(sparc_sysrq_init); #endif -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct thread_info *ti = task_thread_info(tsk); - unsigned long ret = 0xdeadbeefUL; - - if (ti && ti->ksp) { - unsigned long *sp; - sp = (unsigned long *)(ti->ksp + STACK_BIAS); - if (((unsigned long)sp & (sizeof(long) - 1)) == 0UL && - sp[14]) { - unsigned long *fp; - fp = (unsigned long *)(sp[14] + STACK_BIAS); - if (((unsigned long)fp & (sizeof(long) - 1)) == 0UL) - ret = fp[15]; - } - } - return ret; -} - /* Free current thread data structures etc.. */ void exit_thread(struct task_struct *tsk) { diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 20cc5d80a471..baeaeed64993 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -381,7 +381,7 @@ bool arch_find_n_match_cpu_physical_id(struct device_node *cpun, int this_cpu_id; /* On hypervisor based platforms we interrogate the 'reg' - * property. On everything else we look for a 'upa-portis', + * property. On everything else we look for a 'upa-portid', * 'portid', or 'cpuid' property. */ diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index 901063c1cf7e..e1d965e90e16 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/export.h> @@ -350,7 +351,7 @@ static int genregs64_set(struct task_struct *target, } if (!ret) { - unsigned long y; + unsigned long y = regs->y; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &y, @@ -1161,3 +1162,39 @@ int regs_query_register_offset(const char *name) return roff->offset; return -EINVAL; } + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static inline int regs_within_kernel_stack(struct pt_regs *regs, + unsigned long addr) +{ + unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS; + return ((addr & ~(THREAD_SIZE - 1)) == + (ksp & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS; + unsigned long *addr = (unsigned long *)ksp; + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 216948ca4382..709a82ebd294 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -237,6 +237,7 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 bne,pt %xcc, user_rtt_fill_32bit wrpr %g1, %cwp ba,a,pt %xcc, user_rtt_fill_64bit + nop user_rtt_fill_fixup_dax: ba,pt %xcc, user_rtt_fill_fixup_common diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index c4e65cb3280f..6722308d1a98 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(); @@ -148,7 +148,7 @@ static void __init boot_flags_init(char *commands) { while (*commands) { /* Move to the start of the next "argument". */ - while (*commands && *commands == ' ') + while (*commands == ' ') commands++; /* Process any command switches, otherwise skip it. */ diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 6b7331d198e9..4d9c3e13c150 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -95,7 +95,7 @@ static struct console prom_early_console = { .index = -1, }; -/* +/* * Process kernel command line switches that are specific to the * SPARC or that require special low-level processing. */ @@ -133,7 +133,7 @@ static void __init boot_flags_init(char *commands) { while (*commands) { /* Move to the start of the next "argument". */ - while (*commands && *commands == ' ') + while (*commands == ' ') commands++; /* Process any command switches, otherwise skip it. */ @@ -365,6 +365,7 @@ void __init start_early_boot(void) } current_thread_info()->cpu = cpu; + time_init_early(); prom_init_report(); start_kernel(); } @@ -639,7 +640,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_BLK_DEV_RAM rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK; rd_prompt = ((ram_flags & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((ram_flags & RAMDISK_LOAD_FLAG) != 0); + rd_doload = ((ram_flags & RAMDISK_LOAD_FLAG) != 0); #endif task_thread_info(&init_task)->kregs = &fake_swapper_regs; @@ -648,7 +649,7 @@ void __init setup_arch(char **cmdline_p) if (!ic_set_manually) { phandle chosen = prom_finddevice("/chosen"); u32 cl, sv, gw; - + cl = prom_getintdefault (chosen, "client-ip", 0); sv = prom_getintdefault (chosen, "server-ip", 0); gw = prom_getintdefault (chosen, "gateway-ip", 0); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 0ce347f8e4cc..3218bc43302e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -5,7 +5,8 @@ #include <linux/export.h> #include <linux/kernel.h> -#include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/hotplug.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/threads.h> @@ -122,7 +123,7 @@ void smp_callin(void) current_thread_info()->new_child = 0; /* Attach to the address space of init_task. */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; /* inform the notifiers about the new cpu */ @@ -621,22 +622,48 @@ retry: } } -/* Multi-cpu list version. */ +#define CPU_MONDO_COUNTER(cpuid) (cpu_mondo_counter[cpuid]) +#define MONDO_USEC_WAIT_MIN 2 +#define MONDO_USEC_WAIT_MAX 100 +#define MONDO_RETRY_LIMIT 500000 + +/* Multi-cpu list version. + * + * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'. + * Sometimes not all cpus receive the mondo, requiring us to re-send + * the mondo until all cpus have received, or cpus are truly stuck + * unable to receive mondo, and we timeout. + * Occasionally a target cpu strand is borrowed briefly by hypervisor to + * perform guest service, such as PCIe error handling. Consider the + * service time, 1 second overall wait is reasonable for 1 cpu. + * Here two in-between mondo check wait time are defined: 2 usec for + * single cpu quick turn around and up to 100usec for large cpu count. + * Deliver mondo to large number of cpus could take longer, we adjusts + * the retry count as long as target cpus are making forward progress. + */ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) { - int retries, this_cpu, prev_sent, i, saw_cpu_error; + int this_cpu, tot_cpus, prev_sent, i, rem; + int usec_wait, retries, tot_retries; + u16 first_cpu = 0xffff; + unsigned long xc_rcvd = 0; unsigned long status; + int ecpuerror_id = 0; + int enocpu_id = 0; u16 *cpu_list; + u16 cpu; this_cpu = smp_processor_id(); - cpu_list = __va(tb->cpu_list_pa); - - saw_cpu_error = 0; - retries = 0; + usec_wait = cnt * MONDO_USEC_WAIT_MIN; + if (usec_wait > MONDO_USEC_WAIT_MAX) + usec_wait = MONDO_USEC_WAIT_MAX; + retries = tot_retries = 0; + tot_cpus = cnt; prev_sent = 0; + do { - int forward_progress, n_sent; + int n_sent, mondo_delivered, target_cpu_busy; status = sun4v_cpu_mondo_send(cnt, tb->cpu_list_pa, @@ -644,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) /* HV_EOK means all cpus received the xcall, we're done. */ if (likely(status == HV_EOK)) - break; + goto xcall_done; + + /* If not these non-fatal errors, panic */ + if (unlikely((status != HV_EWOULDBLOCK) && + (status != HV_ECPUERROR) && + (status != HV_ENOCPU))) + goto fatal_errors; /* First, see if we made any forward progress. * + * Go through the cpu_list, count the target cpus that have + * received our mondo (n_sent), and those that did not (rem). + * Re-pack cpu_list with the cpus remain to be retried in the + * front - this simplifies tracking the truly stalled cpus. + * * The hypervisor indicates successful sends by setting * cpu list entries to the value 0xffff. + * + * EWOULDBLOCK means some target cpus did not receive the + * mondo and retry usually helps. + * + * ECPUERROR means at least one target cpu is in error state, + * it's usually safe to skip the faulty cpu and retry. + * + * ENOCPU means one of the target cpu doesn't belong to the + * domain, perhaps offlined which is unexpected, but not + * fatal and it's okay to skip the offlined cpu. */ + rem = 0; n_sent = 0; for (i = 0; i < cnt; i++) { - if (likely(cpu_list[i] == 0xffff)) + cpu = cpu_list[i]; + if (likely(cpu == 0xffff)) { n_sent++; + } else if ((status == HV_ECPUERROR) && + (sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) { + ecpuerror_id = cpu + 1; + } else if (status == HV_ENOCPU && !cpu_online(cpu)) { + enocpu_id = cpu + 1; + } else { + cpu_list[rem++] = cpu; + } } - forward_progress = 0; - if (n_sent > prev_sent) - forward_progress = 1; + /* No cpu remained, we're done. */ + if (rem == 0) + break; - prev_sent = n_sent; + /* Otherwise, update the cpu count for retry. */ + cnt = rem; - /* If we get a HV_ECPUERROR, then one or more of the cpus - * in the list are in error state. Use the cpu_state() - * hypervisor call to find out which cpus are in error state. + /* Record the overall number of mondos received by the + * first of the remaining cpus. */ - if (unlikely(status == HV_ECPUERROR)) { - for (i = 0; i < cnt; i++) { - long err; - u16 cpu; + if (first_cpu != cpu_list[0]) { + first_cpu = cpu_list[0]; + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); + } - cpu = cpu_list[i]; - if (cpu == 0xffff) - continue; + /* Was any mondo delivered successfully? */ + mondo_delivered = (n_sent > prev_sent); + prev_sent = n_sent; - err = sun4v_cpu_state(cpu); - if (err == HV_CPU_STATE_ERROR) { - saw_cpu_error = (cpu + 1); - cpu_list[i] = 0xffff; - } - } - } else if (unlikely(status != HV_EWOULDBLOCK)) - goto fatal_mondo_error; + /* or, was any target cpu busy processing other mondos? */ + target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu)); + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); - /* Don't bother rewriting the CPU list, just leave the - * 0xffff and non-0xffff entries in there and the - * hypervisor will do the right thing. - * - * Only advance timeout state if we didn't make any - * forward progress. + /* Retry count is for no progress. If we're making progress, + * reset the retry count. */ - if (unlikely(!forward_progress)) { - if (unlikely(++retries > 10000)) - goto fatal_mondo_timeout; - - /* Delay a little bit to let other cpus catch up - * on their cpu mondo queue work. - */ - udelay(2 * cnt); + if (likely(mondo_delivered || target_cpu_busy)) { + tot_retries += retries; + retries = 0; + } else if (unlikely(retries > MONDO_RETRY_LIMIT)) { + goto fatal_mondo_timeout; } - } while (1); - if (unlikely(saw_cpu_error)) - goto fatal_mondo_cpu_error; + /* Delay a little bit to let other cpus catch up on + * their cpu mondo queue work. + */ + if (!mondo_delivered) + udelay(usec_wait); - return; + retries++; + } while (1); -fatal_mondo_cpu_error: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus " - "(including %d) were in error state\n", - this_cpu, saw_cpu_error - 1); +xcall_done: + if (unlikely(ecpuerror_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n", + this_cpu, ecpuerror_id - 1); + } else if (unlikely(enocpu_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n", + this_cpu, enocpu_id - 1); + } return; +fatal_errors: + /* fatal errors include bad alignment, etc */ + pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n", + this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa); + panic("Unexpected SUN4V mondo error %lu\n", status); + fatal_mondo_timeout: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward " - " progress after %d retries.\n", - this_cpu, retries); - goto dump_cpu_list_and_out; - -fatal_mondo_error: - printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n", - this_cpu, status); - printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) " - "mondo_block_pa(%lx)\n", - this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa); - -dump_cpu_list_and_out: - printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu); - for (i = 0; i < cnt; i++) - printk("%u ", cpu_list[i]); - printk("]\n"); + /* some cpus being non-responsive to the cpu mondo */ + pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n", + this_cpu, first_cpu, (tot_retries + retries), tot_cpus); + panic("SUN4V mondo timeout panic\n"); } static void (*xcall_deliver_impl)(struct trap_per_cpu *, int); @@ -963,37 +1009,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page) preempt_enable(); } -void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) -{ - struct mm_struct *mm; - unsigned long flags; - - clear_softint(1 << irq); - - /* See if we need to allocate a new TLB context because - * the version of the one we are using is now out of date. - */ - mm = current->active_mm; - if (unlikely(!mm || (mm == &init_mm))) - return; - - spin_lock_irqsave(&mm->context.lock, flags); - - if (unlikely(!CTX_VALID(mm->context))) - get_new_mmu_context(mm); - - spin_unlock_irqrestore(&mm->context.lock, flags); - - load_secondary_context(mm); - __flush_tlb_mm(CTX_HWBITS(mm->context), - SECONDARY_CONTEXT); -} - -void smp_new_mmu_context_version(void) -{ - smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0); -} - #ifdef CONFIG_KGDB void kgdb_roundup_cpus(unsigned long flags) { @@ -1443,6 +1458,7 @@ 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 +1467,15 @@ 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/spiterrs.S b/arch/sparc/kernel/spiterrs.S index 4a73009f66a5..d7e540842809 100644 --- a/arch/sparc/kernel/spiterrs.S +++ b/arch/sparc/kernel/spiterrs.S @@ -86,6 +86,7 @@ __spitfire_cee_trap_continue: rd %pc, %g7 ba,a,pt %xcc, 2f + nop 1: ba,pt %xcc, etrap_irq rd %pc, %g7 diff --git a/arch/sparc/kernel/stacktrace.c b/arch/sparc/kernel/stacktrace.c index e78386a0029f..be4c14cccc05 100644 --- a/arch/sparc/kernel/stacktrace.c +++ b/arch/sparc/kernel/stacktrace.c @@ -1,4 +1,5 @@ #include <linux/sched.h> +#include <linux/sched/debug.h> #include <linux/stacktrace.h> #include <linux/thread_info.h> #include <linux/ftrace.h> diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c index 9d98e5002a09..af93b50e3ce4 100644 --- a/arch/sparc/kernel/sun4d_smp.c +++ b/arch/sparc/kernel/sun4d_smp.c @@ -10,7 +10,7 @@ #include <linux/interrupt.h> #include <linux/profile.h> #include <linux/delay.h> -#include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/cpu.h> #include <asm/cacheflush.h> @@ -93,7 +93,7 @@ void sun4d_cpu_pre_online(void *arg) show_leds(cpuid); /* Attach to the address space of init_task. */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; local_ops->cache_all(); diff --git a/arch/sparc/kernel/sun4m_irq.c b/arch/sparc/kernel/sun4m_irq.c index da737c712fa8..aa84da0b2d30 100644 --- a/arch/sparc/kernel/sun4m_irq.c +++ b/arch/sparc/kernel/sun4m_irq.c @@ -10,6 +10,7 @@ */ #include <linux/slab.h> +#include <linux/sched/debug.h> #include <asm/timer.h> #include <asm/traps.h> diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c index 278c40abce82..5547fcb1d72d 100644 --- a/arch/sparc/kernel/sun4m_smp.c +++ b/arch/sparc/kernel/sun4m_smp.c @@ -8,7 +8,7 @@ #include <linux/interrupt.h> #include <linux/profile.h> #include <linux/delay.h> -#include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/cpu.h> #include <asm/cacheflush.h> @@ -59,7 +59,7 @@ void sun4m_cpu_pre_online(void *arg) : "memory" /* paranoid */); /* Attach to the address space of init_task. */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; while (!cpumask_test_cpu(cpuid, &smp_commenced_mask)) diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S index 559bc5e9c199..34631995859a 100644 --- a/arch/sparc/kernel/sun4v_ivec.S +++ b/arch/sparc/kernel/sun4v_ivec.S @@ -26,6 +26,21 @@ sun4v_cpu_mondo: ldxa [%g0] ASI_SCRATCHPAD, %g4 sub %g4, TRAP_PER_CPU_FAULT_INFO, %g4 + /* Get smp_processor_id() into %g3 */ + sethi %hi(trap_block), %g5 + or %g5, %lo(trap_block), %g5 + sub %g4, %g5, %g3 + srlx %g3, TRAP_BLOCK_SZ_SHIFT, %g3 + + /* Increment cpu_mondo_counter[smp_processor_id()] */ + sethi %hi(cpu_mondo_counter), %g5 + or %g5, %lo(cpu_mondo_counter), %g5 + sllx %g3, 3, %g3 + add %g5, %g3, %g5 + ldx [%g5], %g3 + add %g3, 1, %g3 + stx %g3, [%g5] + /* Get CPU mondo queue base phys address into %g7. */ ldx [%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7 diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S index 6179e19bc9b9..c19f352f46c7 100644 --- a/arch/sparc/kernel/sun4v_tlb_miss.S +++ b/arch/sparc/kernel/sun4v_tlb_miss.S @@ -352,6 +352,7 @@ sun4v_mna: call sun4v_do_mna add %sp, PTREGS_OFF, %o0 ba,a,pt %xcc, rtrap + nop /* Privileged Action. */ sun4v_privact: diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index fb7b185ee941..7aecb239626d 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -7,7 +7,9 @@ #include <linux/errno.h> #include <linux/types.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/mm.h> +#include <linux/sched/debug.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/file.h> diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 884c70331345..043544d0cda3 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -7,7 +7,9 @@ #include <linux/errno.h> #include <linux/types.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/mm.h> +#include <linux/sched/debug.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> @@ -118,7 +120,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -181,7 +183,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c index 4808b6d23455..5fd352b759af 100644 --- a/arch/sparc/kernel/sysfs.c +++ b/arch/sparc/kernel/sysfs.c @@ -98,27 +98,7 @@ static struct attribute_group mmu_stat_group = { .name = "mmu_stats", }; -/* XXX convert to rusty's on_one_cpu */ -static unsigned long run_on_cpu(unsigned long cpu, - unsigned long (*func)(unsigned long), - unsigned long arg) -{ - cpumask_t old_affinity; - unsigned long ret; - - cpumask_copy(&old_affinity, tsk_cpus_allowed(current)); - /* should return -EINVAL to userspace */ - if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) - return 0; - - ret = func(arg); - - set_cpus_allowed_ptr(current, &old_affinity); - - return ret; -} - -static unsigned long read_mmustat_enable(unsigned long junk) +static long read_mmustat_enable(void *data __maybe_unused) { unsigned long ra = 0; @@ -127,11 +107,11 @@ static unsigned long read_mmustat_enable(unsigned long junk) return ra != 0; } -static unsigned long write_mmustat_enable(unsigned long val) +static long write_mmustat_enable(void *data) { - unsigned long ra, orig_ra; + unsigned long ra, orig_ra, *val = data; - if (val) + if (*val) ra = __pa(&per_cpu(mmu_stats, smp_processor_id())); else ra = 0UL; @@ -142,7 +122,8 @@ static unsigned long write_mmustat_enable(unsigned long val) static ssize_t show_mmustat_enable(struct device *s, struct device_attribute *attr, char *buf) { - unsigned long val = run_on_cpu(s->id, read_mmustat_enable, 0); + long val = work_on_cpu(s->id, read_mmustat_enable, NULL); + return sprintf(buf, "%lx\n", val); } @@ -150,13 +131,15 @@ static ssize_t store_mmustat_enable(struct device *s, struct device_attribute *attr, const char *buf, size_t count) { - unsigned long val, err; - int ret = sscanf(buf, "%lu", &val); + unsigned long val; + long err; + int ret; + ret = sscanf(buf, "%lu", &val); if (ret != 1) return -EINVAL; - err = run_on_cpu(s->id, write_mmustat_enable, val); + err = work_on_cpu(s->id, write_mmustat_enable, &val); if (err) return -EIO; diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index eac7f0db5c8c..5253e895b81b 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -89,3 +89,4 @@ sys_call_table: /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen /*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 +/*360*/ .long sys_statx diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index b0f17ff2ddba..82339f6be0b2 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -90,6 +90,7 @@ sys_call_table32: .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2 +/*360*/ .word sys_statx #endif /* CONFIG_COMPAT */ @@ -171,3 +172,4 @@ sys_call_table: .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen .word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 +/*360*/ .word sys_statx diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 244062bdaa56..2ce2e7b2abbb 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -228,7 +228,9 @@ void register_percpu_ce(int cpu) ce->mult = div_sc(sparc_config.clock_rate, NSEC_PER_SEC, ce->shift); ce->max_delta_ns = clockevent_delta2ns(sparc_config.clock_rate, ce); + ce->max_delta_ticks = (unsigned long)sparc_config.clock_rate; ce->min_delta_ns = clockevent_delta2ns(100, ce); + ce->min_delta_ticks = 100; clockevents_register_device(ce); } @@ -296,7 +298,7 @@ static int clock_probe(struct platform_device *op) return 0; } -static struct of_device_id clock_match[] = { +static const struct of_device_id clock_match[] = { { .name = "eeprom", }, diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 12a6d3555cb8..564f0e46ffd4 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -32,7 +32,6 @@ #include <linux/kernel_stat.h> #include <linux/clockchips.h> #include <linux/clocksource.h> -#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/ftrace.h> @@ -47,14 +46,13 @@ #include <asm/cpudata.h> #include <linux/uaccess.h> #include <asm/irq_regs.h> +#include <asm/cacheflush.h> #include "entry.h" +#include "kernel.h" DEFINE_SPINLOCK(rtc_lock); -#define TICK_PRIV_BIT (1UL << 63) -#define TICKCMP_IRQ_BIT (1UL << 63) - #ifdef CONFIG_SMP unsigned long profile_pc(struct pt_regs *regs) { @@ -164,13 +162,44 @@ static unsigned long tick_add_tick(unsigned long adj) return new_tick; } -static struct sparc64_tick_ops tick_operations __read_mostly = { +/* Searches for cpu clock frequency with given cpuid in OpenBoot tree */ +static unsigned long cpuid_to_freq(phandle node, int cpuid) +{ + bool is_cpu_node = false; + unsigned long freq = 0; + char type[128]; + + if (!node) + return freq; + + if (prom_getproperty(node, "device_type", type, sizeof(type)) != -1) + is_cpu_node = (strcmp(type, "cpu") == 0); + + /* try upa-portid then cpuid to get cpuid, see prom_64.c */ + if (is_cpu_node && (prom_getint(node, "upa-portid") == cpuid || + prom_getint(node, "cpuid") == cpuid)) + freq = prom_getintdefault(node, "clock-frequency", 0); + if (!freq) + freq = cpuid_to_freq(prom_getchild(node), cpuid); + if (!freq) + freq = cpuid_to_freq(prom_getsibling(node), cpuid); + + return freq; +} + +static unsigned long tick_get_frequency(void) +{ + return cpuid_to_freq(prom_root_node, hard_smp_processor_id()); +} + +static struct sparc64_tick_ops tick_operations __cacheline_aligned = { .name = "tick", .init_tick = tick_init_tick, .disable_irq = tick_disable_irq, .get_tick = tick_get_tick, .add_tick = tick_add_tick, .add_compare = tick_add_compare, + .get_frequency = tick_get_frequency, .softint_mask = 1UL << 0, }; @@ -250,6 +279,11 @@ static int stick_add_compare(unsigned long adj) return ((long)(new_tick - (orig_tick+adj))) > 0L; } +static unsigned long stick_get_frequency(void) +{ + return prom_getintdefault(prom_root_node, "stick-frequency", 0); +} + static struct sparc64_tick_ops stick_operations __read_mostly = { .name = "stick", .init_tick = stick_init_tick, @@ -257,6 +291,7 @@ static struct sparc64_tick_ops stick_operations __read_mostly = { .get_tick = stick_get_tick, .add_tick = stick_add_tick, .add_compare = stick_add_compare, + .get_frequency = stick_get_frequency, .softint_mask = 1UL << 16, }; @@ -277,9 +312,6 @@ static struct sparc64_tick_ops stick_operations __read_mostly = { * 2) write high * 3) write low */ -#define HBIRD_STICKCMP_ADDR 0x1fe0000f060UL -#define HBIRD_STICK_ADDR 0x1fe0000f070UL - static unsigned long __hbird_read_stick(void) { unsigned long ret, tmp1, tmp2, tmp3; @@ -381,6 +413,11 @@ static int hbtick_add_compare(unsigned long adj) return ((long)(val2 - val)) > 0L; } +static unsigned long hbtick_get_frequency(void) +{ + return prom_getintdefault(prom_root_node, "stick-frequency", 0); +} + static struct sparc64_tick_ops hbtick_operations __read_mostly = { .name = "hbtick", .init_tick = hbtick_init_tick, @@ -388,11 +425,10 @@ static struct sparc64_tick_ops hbtick_operations __read_mostly = { .get_tick = hbtick_get_tick, .add_tick = hbtick_add_tick, .add_compare = hbtick_add_compare, + .get_frequency = hbtick_get_frequency, .softint_mask = 1UL << 0, }; -static unsigned long timer_ticks_per_nsec_quotient __read_mostly; - unsigned long cmos_regs; EXPORT_SYMBOL(cmos_regs); @@ -582,34 +618,17 @@ static int __init clock_init(void) */ fs_initcall(clock_init); -/* This is gets the master TICK_INT timer going. */ -static unsigned long sparc64_init_timers(void) +/* Return true if this is Hummingbird, aka Ultra-IIe */ +static bool is_hummingbird(void) { - struct device_node *dp; - unsigned long freq; + unsigned long ver, manuf, impl; - dp = of_find_node_by_path("/"); - if (tlb_type == spitfire) { - unsigned long ver, manuf, impl; - - __asm__ __volatile__ ("rdpr %%ver, %0" - : "=&r" (ver)); - manuf = ((ver >> 48) & 0xffff); - impl = ((ver >> 32) & 0xffff); - if (manuf == 0x17 && impl == 0x13) { - /* Hummingbird, aka Ultra-IIe */ - tick_ops = &hbtick_operations; - freq = of_getintprop_default(dp, "stick-frequency", 0); - } else { - tick_ops = &tick_operations; - freq = local_cpu_data().clock_tick; - } - } else { - tick_ops = &stick_operations; - freq = of_getintprop_default(dp, "stick-frequency", 0); - } + __asm__ __volatile__ ("rdpr %%ver, %0" + : "=&r" (ver)); + manuf = ((ver >> 48) & 0xffff); + impl = ((ver >> 32) & 0xffff); - return freq; + return (manuf == 0x17 && impl == 0x13); } struct freq_table { @@ -671,12 +690,12 @@ core_initcall(register_sparc64_cpufreq_notifier); static int sparc64_next_event(unsigned long delta, struct clock_event_device *evt) { - return tick_ops->add_compare(delta) ? -ETIME : 0; + return tick_operations.add_compare(delta) ? -ETIME : 0; } static int sparc64_timer_shutdown(struct clock_event_device *evt) { - tick_ops->disable_irq(); + tick_operations.disable_irq(); return 0; } @@ -693,7 +712,7 @@ static DEFINE_PER_CPU(struct clock_event_device, sparc64_events); void __irq_entry timer_interrupt(int irq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - unsigned long tick_mask = tick_ops->softint_mask; + unsigned long tick_mask = tick_operations.softint_mask; int cpu = smp_processor_id(); struct clock_event_device *evt = &per_cpu(sparc64_events, cpu); @@ -728,7 +747,7 @@ void setup_sparc64_timer(void) : "=r" (pstate) : "i" (PSTATE_IE)); - tick_ops->init_tick(); + tick_operations.init_tick(); /* Restore PSTATE_IE. */ __asm__ __volatile__("wrpr %0, 0x0, %%pstate" @@ -755,12 +774,10 @@ static unsigned long tb_ticks_per_usec __read_mostly; void __delay(unsigned long loops) { - unsigned long bclock, now; + unsigned long bclock = get_tick(); - bclock = tick_ops->get_tick(); - do { - now = tick_ops->get_tick(); - } while ((now-bclock) < loops); + while ((get_tick() - bclock) < loops) + ; } EXPORT_SYMBOL(__delay); @@ -772,32 +789,79 @@ EXPORT_SYMBOL(udelay); static u64 clocksource_tick_read(struct clocksource *cs) { - return tick_ops->get_tick(); + return get_tick(); +} + +static void __init get_tick_patch(void) +{ + unsigned int *addr, *instr, i; + struct get_tick_patch *p; + + if (tlb_type == spitfire && is_hummingbird()) + return; + + for (p = &__get_tick_patch; p < &__get_tick_patch_end; p++) { + instr = (tlb_type == spitfire) ? p->tick : p->stick; + addr = (unsigned int *)(unsigned long)p->addr; + for (i = 0; i < GET_TICK_NINSTR; i++) { + addr[i] = instr[i]; + /* ensure that address is modified before flush */ + wmb(); + flushi(&addr[i]); + } + } +} + +static void init_tick_ops(struct sparc64_tick_ops *ops) +{ + unsigned long freq, quotient, tick; + + freq = ops->get_frequency(); + quotient = clocksource_hz2mult(freq, SPARC64_NSEC_PER_CYC_SHIFT); + tick = ops->get_tick(); + + ops->offset = (tick * quotient) >> SPARC64_NSEC_PER_CYC_SHIFT; + ops->ticks_per_nsec_quotient = quotient; + ops->frequency = freq; + tick_operations = *ops; + get_tick_patch(); +} + +void __init time_init_early(void) +{ + if (tlb_type == spitfire) { + if (is_hummingbird()) + init_tick_ops(&hbtick_operations); + else + init_tick_ops(&tick_operations); + } else { + init_tick_ops(&stick_operations); + } } void __init time_init(void) { - unsigned long freq = sparc64_init_timers(); + unsigned long freq; + freq = tick_operations.frequency; tb_ticks_per_usec = freq / USEC_PER_SEC; - timer_ticks_per_nsec_quotient = - clocksource_hz2mult(freq, SPARC64_NSEC_PER_CYC_SHIFT); - - clocksource_tick.name = tick_ops->name; + clocksource_tick.name = tick_operations.name; clocksource_tick.read = clocksource_tick_read; clocksource_register_hz(&clocksource_tick, freq); printk("clocksource: mult[%x] shift[%d]\n", clocksource_tick.mult, clocksource_tick.shift); - sparc64_clockevent.name = tick_ops->name; + sparc64_clockevent.name = tick_operations.name; clockevents_calc_mult_shift(&sparc64_clockevent, freq, 4); sparc64_clockevent.max_delta_ns = clockevent_delta2ns(0x7fffffffffffffffUL, &sparc64_clockevent); + sparc64_clockevent.max_delta_ticks = 0x7fffffffffffffffUL; sparc64_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &sparc64_clockevent); + sparc64_clockevent.min_delta_ticks = 0xF; printk("clockevent: mult[%x] shift[%d]\n", sparc64_clockevent.mult, sparc64_clockevent.shift); @@ -807,14 +871,21 @@ void __init time_init(void) unsigned long long sched_clock(void) { - unsigned long ticks = tick_ops->get_tick(); + unsigned long quotient = tick_operations.ticks_per_nsec_quotient; + unsigned long offset = tick_operations.offset; + + /* Use barrier so the compiler emits the loads first and overlaps load + * latency with reading tick, because reading %tick/%stick is a + * post-sync instruction that will flush and restart subsequent + * instructions after it commits. + */ + barrier(); - return (ticks * timer_ticks_per_nsec_quotient) - >> SPARC64_NSEC_PER_CYC_SHIFT; + return ((get_tick() * quotient) >> SPARC64_NSEC_PER_CYC_SHIFT) - offset; } int read_current_timer(unsigned long *timer_val) { - *timer_val = tick_ops->get_tick(); + *timer_val = get_tick(); return 0; } diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index 4f21df7d4f13..466d4aed06c7 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -9,7 +9,9 @@ * I hate traps on the sparc, grrr... */ -#include <linux/sched.h> /* for jiffies */ +#include <linux/sched/mm.h> +#include <linux/sched/debug.h> +#include <linux/mm_types.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/smp.h> @@ -448,7 +450,7 @@ void trap_init(void) thread_info_offsets_are_bolixed_pete(); /* Attach to the address space of init_task. */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; /* NOTE: Other cpus have this done as they are started diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index dfc97a47c9a0..ad31af1dd726 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -9,7 +9,8 @@ */ #include <linux/extable.h> -#include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/debug.h> #include <linux/linkage.h> #include <linux/kernel.h> #include <linux/signal.h> @@ -2732,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs) } } +u64 cpu_mondo_counter[NR_CPUS] = {0}; struct trap_per_cpu trap_block[NR_CPUS]; EXPORT_SYMBOL(trap_block); @@ -2837,6 +2839,6 @@ void __init trap_init(void) /* Attach to the address space of init_task. On SMP we * do this in smp.c:smp_callin for other cpus. */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; } diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index d568c8207af7..07c0df924960 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 @@ -470,13 +455,16 @@ __tsb_context_switch: .type copy_tsb,#function copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size * %o2=new_tsb_base, %o3=new_tsb_size + * %o4=page_size_shift */ sethi %uhi(TSB_PASS_BITS), %g7 srlx %o3, 4, %o3 - add %o0, %o1, %g1 /* end of old tsb */ + add %o0, %o1, %o1 /* end of old tsb */ sllx %g7, 32, %g7 sub %o3, 1, %o3 /* %o3 == new tsb hash mask */ + mov %o4, %g1 /* page_size_shift */ + 661: prefetcha [%o0] ASI_N, #one_read .section .tsb_phys_patch, "ax" .word 661b @@ -501,9 +489,9 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size /* This can definitely be computed faster... */ srlx %o0, 4, %o5 /* Build index */ and %o5, 511, %o5 /* Mask index */ - sllx %o5, PAGE_SHIFT, %o5 /* Put into vaddr position */ + sllx %o5, %g1, %o5 /* Put into vaddr position */ or %o4, %o5, %o4 /* Full VADDR. */ - srlx %o4, PAGE_SHIFT, %o4 /* Shift down to create index */ + srlx %o4, %g1, %o4 /* Shift down to create index */ and %o4, %o3, %o4 /* Mask with new_tsb_nents-1 */ sllx %o4, 4, %o4 /* Shift back up into tsb ent offset */ TSB_STORE(%o2 + %o4, %g2) /* Store TAG */ @@ -511,7 +499,7 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size TSB_STORE(%o2 + %o4, %g3) /* Store TTE */ 80: add %o0, 16, %o0 - cmp %o0, %g1 + cmp %o0, %o1 bne,pt %xcc, 90b nop diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S index 7bd8f6556352..efe93ab4a9c0 100644 --- a/arch/sparc/kernel/ttable_64.S +++ b/arch/sparc/kernel/ttable_64.S @@ -50,7 +50,7 @@ tl0_resv03e: BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40) tl0_irq1: TRAP_IRQ(smp_call_function_client, 1) tl0_irq2: TRAP_IRQ(smp_receive_signal_client, 2) tl0_irq3: TRAP_IRQ(smp_penguin_jailcell, 3) -tl0_irq4: TRAP_IRQ(smp_new_mmu_context_version_client, 4) +tl0_irq4: BTRAP(0x44) #else tl0_irq1: BTRAP(0x41) tl0_irq2: BTRAP(0x42) diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c index d20d4e3fd129..8367dce5f41b 100644 --- a/arch/sparc/kernel/unaligned_32.c +++ b/arch/sparc/kernel/unaligned_32.c @@ -8,7 +8,7 @@ #include <linux/kernel.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/mm.h> #include <asm/ptrace.h> #include <asm/processor.h> diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S index 5604a2b051d4..364af3250646 100644 --- a/arch/sparc/kernel/urtt_fill.S +++ b/arch/sparc/kernel/urtt_fill.S @@ -92,6 +92,7 @@ user_rtt_fill_fixup_common: call sun4v_data_access_exception nop ba,a,pt %xcc, rtrap + nop 1: call spitfire_data_access_exception nop diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index f6bb857254fc..1c8763c9c52b 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -70,15 +70,26 @@ static int vio_device_probe(struct device *dev) struct vio_dev *vdev = to_vio_dev(dev); struct vio_driver *drv = to_vio_driver(dev->driver); const struct vio_device_id *id; - int error = -ENODEV; - if (drv->probe) { - id = vio_match_device(drv->id_table, vdev); - if (id) - error = drv->probe(vdev, id); + if (!drv->probe) + return -ENODEV; + + id = vio_match_device(drv->id_table, vdev); + if (!id) + return -ENODEV; + + /* alloc irqs (unless the driver specified not to) */ + if (!drv->no_irq) { + if (vdev->tx_irq == 0 && vdev->tx_ino != ~0UL) + vdev->tx_irq = sun4v_build_virq(vdev->cdev_handle, + vdev->tx_ino); + + if (vdev->rx_irq == 0 && vdev->rx_ino != ~0UL) + vdev->rx_irq = sun4v_build_virq(vdev->cdev_handle, + vdev->rx_ino); } - return error; + return drv->probe(vdev, id); } static int vio_device_remove(struct device *dev) @@ -86,8 +97,15 @@ static int vio_device_remove(struct device *dev) struct vio_dev *vdev = to_vio_dev(dev); struct vio_driver *drv = to_vio_driver(dev->driver); - if (drv->remove) + if (drv->remove) { + /* + * Ideally, we would remove/deallocate tx/rx virqs + * here - however, there are currently no support + * routines to do so at the moment. TBD + */ + return drv->remove(vdev); + } return 1; } @@ -105,6 +123,7 @@ static ssize_t devspec_show(struct device *dev, return sprintf(buf, "%s\n", str); } +static DEVICE_ATTR_RO(devspec); static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -112,6 +131,7 @@ static ssize_t type_show(struct device *dev, struct vio_dev *vdev = to_vio_dev(dev); return sprintf(buf, "%s\n", vdev->type); } +static DEVICE_ATTR_RO(type); static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -120,17 +140,19 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, return sprintf(buf, "vio:T%sS%s\n", vdev->type, vdev->compat); } +static DEVICE_ATTR_RO(modalias); -static struct device_attribute vio_dev_attrs[] = { - __ATTR_RO(devspec), - __ATTR_RO(type), - __ATTR_RO(modalias), - __ATTR_NULL -}; +static struct attribute *vio_dev_attrs[] = { + &dev_attr_devspec.attr, + &dev_attr_type.attr, + &dev_attr_modalias.attr, + NULL, + }; +ATTRIBUTE_GROUPS(vio_dev); static struct bus_type vio_bus_type = { .name = "vio", - .dev_attrs = vio_dev_attrs, + .dev_groups = vio_dev_groups, .uevent = vio_hotplug, .match = vio_bus_match, .probe = vio_device_probe, @@ -181,11 +203,58 @@ static struct device_node *cdev_node; static struct vio_dev *root_vdev; static u64 cdev_cfg_handle; +static const u64 *vio_cfg_handle(struct mdesc_handle *hp, u64 node) +{ + const u64 *cfg_handle = NULL; + u64 a; + + mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) { + u64 target; + + target = mdesc_arc_target(hp, a); + cfg_handle = mdesc_get_property(hp, target, + "cfg-handle", NULL); + if (cfg_handle) + break; + } + + return cfg_handle; +} + +/** + * vio_vdev_node() - Find VDEV node in MD + * @hp: Handle to the MD + * @vdev: Pointer to VDEV + * + * Find the node in the current MD which matches the given vio_dev. This + * must be done dynamically since the node value can change if the MD + * is updated. + * + * NOTE: the MD must be locked, using mdesc_grab(), when calling this routine + * + * Return: The VDEV node in MDESC + */ +u64 vio_vdev_node(struct mdesc_handle *hp, struct vio_dev *vdev) +{ + u64 node; + + if (vdev == NULL) + return MDESC_NODE_NULL; + + node = mdesc_get_node(hp, (const char *)vdev->node_name, + &vdev->md_node_info); + + return node; +} + static void vio_fill_channel_info(struct mdesc_handle *hp, u64 mp, struct vio_dev *vdev) { u64 a; + vdev->tx_ino = ~0UL; + vdev->rx_ino = ~0UL; + vdev->channel_id = ~0UL; mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) { const u64 *chan_id; const u64 *irq; @@ -195,18 +264,18 @@ static void vio_fill_channel_info(struct mdesc_handle *hp, u64 mp, irq = mdesc_get_property(hp, target, "tx-ino", NULL); if (irq) - vdev->tx_irq = sun4v_build_virq(cdev_cfg_handle, *irq); + vdev->tx_ino = *irq; irq = mdesc_get_property(hp, target, "rx-ino", NULL); - if (irq) { - vdev->rx_irq = sun4v_build_virq(cdev_cfg_handle, *irq); + if (irq) vdev->rx_ino = *irq; - } chan_id = mdesc_get_property(hp, target, "id", NULL); if (chan_id) vdev->channel_id = *chan_id; } + + vdev->cdev_handle = cdev_cfg_handle; } int vio_set_intr(unsigned long dev_ino, int state) @@ -219,14 +288,14 @@ int vio_set_intr(unsigned long dev_ino, int state) EXPORT_SYMBOL(vio_set_intr); static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, + const char *node_name, struct device *parent) { - const char *type, *compat, *bus_id_name; + const char *type, *compat; struct device_node *dp; struct vio_dev *vdev; int err, tlen, clen; const u64 *id, *cfg_handle; - u64 a; type = mdesc_get_property(hp, mp, "device-type", &tlen); if (!type) { @@ -236,7 +305,7 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, tlen = strlen(type) + 1; } } - if (tlen > VIO_MAX_TYPE_LEN) { + if (tlen > VIO_MAX_TYPE_LEN || strlen(type) >= VIO_MAX_TYPE_LEN) { printk(KERN_ERR "VIO: Type string [%s] is too long.\n", type); return NULL; @@ -244,31 +313,7 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, id = mdesc_get_property(hp, mp, "id", NULL); - cfg_handle = NULL; - mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) { - u64 target; - - target = mdesc_arc_target(hp, a); - cfg_handle = mdesc_get_property(hp, target, - "cfg-handle", NULL); - if (cfg_handle) - break; - } - - bus_id_name = type; - if (!strcmp(type, "domain-services-port")) - bus_id_name = "ds"; - - /* - * 20 char is the old driver-core name size limit, which is no more. - * This check can probably be removed after review and possible - * adaption of the vio users name length handling. - */ - if (strlen(bus_id_name) >= 20 - 4) { - printk(KERN_ERR "VIO: bus_id_name [%s] is too long.\n", - bus_id_name); - return NULL; - } + cfg_handle = vio_cfg_handle(hp, mp); compat = mdesc_get_property(hp, mp, "device-type", &clen); if (!compat) { @@ -293,22 +338,23 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, memset(vdev->compat, 0, sizeof(vdev->compat)); vdev->compat_len = clen; - vdev->channel_id = ~0UL; - vdev->tx_irq = ~0; - vdev->rx_irq = ~0; + vdev->port_id = ~0UL; + vdev->tx_irq = 0; + vdev->rx_irq = 0; vio_fill_channel_info(hp, mp, vdev); if (!id) { - dev_set_name(&vdev->dev, "%s", bus_id_name); + dev_set_name(&vdev->dev, "%s", type); vdev->dev_no = ~(u64)0; } else if (!cfg_handle) { - dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id); + dev_set_name(&vdev->dev, "%s-%llu", type, *id); vdev->dev_no = *id; } else { - dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name, + dev_set_name(&vdev->dev, "%s-%llu-%llu", type, *cfg_handle, *id); vdev->dev_no = *cfg_handle; + vdev->port_id = *id; } vdev->dev.parent = parent; @@ -330,7 +376,26 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, } vdev->dp = dp; - printk(KERN_INFO "VIO: Adding device %s\n", dev_name(&vdev->dev)); + /* + * node_name is NULL for the parent/channel-devices node and + * the parent doesn't require the MD node info. + */ + if (node_name != NULL) { + (void) snprintf(vdev->node_name, VIO_MAX_NAME_LEN, "%s", + node_name); + + err = mdesc_get_node_info(hp, mp, node_name, + &vdev->md_node_info); + if (err) { + pr_err("VIO: Could not get MD node info %s, err=%d\n", + dev_name(&vdev->dev), err); + kfree(vdev); + return NULL; + } + } + + pr_info("VIO: Adding device %s (tx_ino = %llx, rx_ino = %llx)\n", + dev_name(&vdev->dev), vdev->tx_ino, vdev->rx_ino); err = device_register(&vdev->dev); if (err) { @@ -346,32 +411,50 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, return vdev; } -static void vio_add(struct mdesc_handle *hp, u64 node) +static void vio_add(struct mdesc_handle *hp, u64 node, + const char *node_name) { - (void) vio_create_one(hp, node, &root_vdev->dev); + (void) vio_create_one(hp, node, node_name, &root_vdev->dev); } +struct vio_remove_node_data { + struct mdesc_handle *hp; + u64 node; +}; + static int vio_md_node_match(struct device *dev, void *arg) { struct vio_dev *vdev = to_vio_dev(dev); + struct vio_remove_node_data *node_data; + u64 node; - if (vdev->mp == (u64) arg) - return 1; + node_data = (struct vio_remove_node_data *)arg; - return 0; + node = vio_vdev_node(node_data->hp, vdev); + + if (node == node_data->node) + return 1; + else + return 0; } -static void vio_remove(struct mdesc_handle *hp, u64 node) +static void vio_remove(struct mdesc_handle *hp, u64 node, const char *node_name) { + struct vio_remove_node_data node_data; struct device *dev; - dev = device_find_child(&root_vdev->dev, (void *) node, + node_data.hp = hp; + node_data.node = node; + + dev = device_find_child(&root_vdev->dev, (void *)&node_data, vio_md_node_match); if (dev) { printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev)); device_unregister(dev); put_device(dev); + } else { + pr_err("VIO: %s node not found in MDESC\n", node_name); } } @@ -386,7 +469,8 @@ static struct mdesc_notifier_client vio_device_notifier = { * under "openboot" that we should not mess with as aparently that is * reserved exclusively for OBP use. */ -static void vio_add_ds(struct mdesc_handle *hp, u64 node) +static void vio_add_ds(struct mdesc_handle *hp, u64 node, + const char *node_name) { int found; u64 a; @@ -403,7 +487,7 @@ static void vio_add_ds(struct mdesc_handle *hp, u64 node) } if (found) - (void) vio_create_one(hp, node, &root_vdev->dev); + (void) vio_create_one(hp, node, node_name, &root_vdev->dev); } static struct mdesc_notifier_client vio_ds_notifier = { @@ -470,7 +554,7 @@ static int __init vio_init(void) cdev_cfg_handle = *cfg_handle; - root_vdev = vio_create_one(hp, root, NULL); + root_vdev = vio_create_one(hp, root, NULL, NULL); err = -ENODEV; if (!root_vdev) { printk(KERN_ERR "VIO: Could not create root device.\n"); diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index 526fcb5d8ce9..d4f13c037a40 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -8,6 +8,7 @@ #include <linux/string.h> #include <linux/delay.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <linux/slab.h> #include <asm/ldc.h> @@ -222,6 +223,9 @@ static int send_rdx(struct vio_driver_state *vio) static int send_attr(struct vio_driver_state *vio) { + if (!vio->ops) + return -EINVAL; + return vio->ops->send_attr(vio); } @@ -282,6 +286,7 @@ static int process_ver_info(struct vio_driver_state *vio, ver.minor = vap->minor; pkt->minor = ver.minor; pkt->tag.stype = VIO_SUBTYPE_ACK; + pkt->dev_class = vio->dev_class; viodbg(HS, "SEND VERSION ACK maj[%u] min[%u]\n", pkt->major, pkt->minor); err = send_ctrl(vio, &pkt->tag, sizeof(*pkt)); @@ -373,6 +378,9 @@ static int process_attr(struct vio_driver_state *vio, void *pkt) if (!(vio->hs_state & VIO_HS_GOTVERS)) return handshake_failure(vio); + if (!vio->ops) + return 0; + err = vio->ops->handle_attr(vio, pkt); if (err < 0) { return handshake_failure(vio); @@ -387,6 +395,7 @@ static int process_attr(struct vio_driver_state *vio, void *pkt) vio->hs_state |= VIO_HS_SENT_DREG; } } + return 0; } @@ -646,10 +655,13 @@ int vio_control_pkt_engine(struct vio_driver_state *vio, void *pkt) err = process_unknown(vio, pkt); break; } + if (!err && vio->hs_state != prev_state && - (vio->hs_state & VIO_HS_COMPLETE)) - vio->ops->handshake_complete(vio); + (vio->hs_state & VIO_HS_COMPLETE)) { + if (vio->ops) + vio->ops->handshake_complete(vio); + } return err; } @@ -764,7 +776,11 @@ void vio_port_up(struct vio_driver_state *vio) } if (!err) { - err = ldc_connect(vio->lp); + if (ldc_mode(vio->lp) == LDC_MODE_RAW) + ldc_set_state(vio->lp, LDC_STATE_CONNECTED); + else + err = ldc_connect(vio->lp); + if (err) printk(KERN_WARNING "%s: Port %lu connect failed, " "err=%d\n", @@ -804,8 +820,7 @@ int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev, return -EINVAL; } - if (!ops->send_attr || - !ops->handle_attr || + if (!ops || !ops->send_attr || !ops->handle_attr || !ops->handshake_complete) return -EINVAL; diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c index c4ac58e483a4..8f35eea2103a 100644 --- a/arch/sparc/kernel/visemul.c +++ b/arch/sparc/kernel/visemul.c @@ -30,7 +30,7 @@ /* 001001011 - two 32-bit merges */ #define FPMERGE_OPF 0x04b -/* 000110001 - 8-by-16-bit partitoned product */ +/* 000110001 - 8-by-16-bit partitioned product */ #define FMUL8x16_OPF 0x031 /* 000110011 - 8-by-16-bit upper alpha partitioned product */ diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 572db686f845..03b3d65d1266 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -149,6 +149,11 @@ SECTIONS *(.sun_m7_2insn_patch) __sun_m7_2insn_patch_end = .; } + .get_tick_patch : { + __get_tick_patch = .; + *(.get_tick_patch) + __get_tick_patch_end = .; + } PERCPU_SECTION(SMP_CACHE_BYTES) #ifdef CONFIG_JUMP_LABEL diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S index 855019a8590e..1ee173cc3c39 100644 --- a/arch/sparc/kernel/winfixup.S +++ b/arch/sparc/kernel/winfixup.S @@ -152,6 +152,8 @@ fill_fixup_dax: call sun4v_data_access_exception nop ba,a,pt %xcc, rtrap + nop 1: call spitfire_data_access_exception nop ba,a,pt %xcc, rtrap + nop diff --git a/arch/sparc/lib/GENbzero.S b/arch/sparc/lib/GENbzero.S index 8e7a843ddd88..2fbf6297d57c 100644 --- a/arch/sparc/lib/GENbzero.S +++ b/arch/sparc/lib/GENbzero.S @@ -8,7 +8,7 @@ 98: x,y; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_o1; \ + .word 98b, __retl_o1_asi;\ .text; \ .align 4; diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S index 69a439fa2fc1..8aa16ef113f2 100644 --- a/arch/sparc/lib/GENcopy_from_user.S +++ b/arch/sparc/lib/GENcopy_from_user.S @@ -23,7 +23,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S index 9947427ce354..311c8fa5e98e 100644 --- a/arch/sparc/lib/GENcopy_to_user.S +++ b/arch/sparc/lib/GENcopy_to_user.S @@ -27,7 +27,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/GENpatch.S b/arch/sparc/lib/GENpatch.S index fab9e89f16bd..95e2f1f9e477 100644 --- a/arch/sparc/lib/GENpatch.S +++ b/arch/sparc/lib/GENpatch.S @@ -26,8 +26,8 @@ .type generic_patch_copyops,#function generic_patch_copyops: GEN_DO_PATCH(memcpy, GENmemcpy) - GEN_DO_PATCH(___copy_from_user, GENcopy_from_user) - GEN_DO_PATCH(___copy_to_user, GENcopy_to_user) + GEN_DO_PATCH(raw_copy_from_user, GENcopy_from_user) + GEN_DO_PATCH(raw_copy_to_user, GENcopy_to_user) retl nop .size generic_patch_copyops,.-generic_patch_copyops diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 69912d2f8b54..07c03e72d812 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -15,6 +15,7 @@ lib-$(CONFIG_SPARC32) += copy_user.o locks.o lib-$(CONFIG_SPARC64) += atomic_64.o lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o +lib-$(CONFIG_SPARC64) += multi3.o lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index b79a6998d87c..0d8a018118c2 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -36,7 +36,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index dcec55f254ab..a7a0ea0d8a0b 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -45,7 +45,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index c629dbd121b6..64dcd6cdb606 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -326,11 +326,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ blu 170f nop ba,a,pt %xcc, 180f + nop 4: /* 32 <= low bits < 48 */ blu 150f nop ba,a,pt %xcc, 160f + nop 5: /* 0 < low bits < 32 */ blu,a 6f cmp %g2, 8 @@ -338,6 +340,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ blu 130f nop ba,a,pt %xcc, 140f + nop 6: /* 0 < low bits < 16 */ bgeu 120f nop @@ -475,6 +478,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %o2, 85f sub %o0, %o1, GLOBAL_SPARE ba,a,pt %XCC, 90f + nop .align 64 75: /* 16 < len <= 64 */ diff --git a/arch/sparc/lib/NG2patch.S b/arch/sparc/lib/NG2patch.S index 28c36f06a6d1..56ccc19adde8 100644 --- a/arch/sparc/lib/NG2patch.S +++ b/arch/sparc/lib/NG2patch.S @@ -26,8 +26,8 @@ .type niagara2_patch_copyops,#function niagara2_patch_copyops: NG_DO_PATCH(memcpy, NG2memcpy) - NG_DO_PATCH(___copy_from_user, NG2copy_from_user) - NG_DO_PATCH(___copy_to_user, NG2copy_to_user) + NG_DO_PATCH(raw_copy_from_user, NG2copy_from_user) + NG_DO_PATCH(raw_copy_to_user, NG2copy_to_user) retl nop .size niagara2_patch_copyops,.-niagara2_patch_copyops diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S index 16a286c1a528..5bb506bd61fa 100644 --- a/arch/sparc/lib/NG4copy_from_user.S +++ b/arch/sparc/lib/NG4copy_from_user.S @@ -31,7 +31,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S index 6b0276ffc858..a82d4d45fc1c 100644 --- a/arch/sparc/lib/NG4copy_to_user.S +++ b/arch/sparc/lib/NG4copy_to_user.S @@ -40,7 +40,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 75bb93b1437f..78ea962edcbe 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -530,4 +530,5 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ bne,pt %icc, 1b EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1) ba,a,pt %icc, .Lexit + nop .size FUNC_NAME, .-FUNC_NAME diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S index 41da4bdd95cb..7c0c81f18837 100644 --- a/arch/sparc/lib/NG4memset.S +++ b/arch/sparc/lib/NG4memset.S @@ -102,4 +102,5 @@ NG4bzero: bne,pt %icc, 1b add %o0, 0x30, %o0 ba,a,pt %icc, .Lpostloop + nop .size NG4bzero,.-NG4bzero diff --git a/arch/sparc/lib/NG4patch.S b/arch/sparc/lib/NG4patch.S index a114cbcf2a48..3cc0f8cc95df 100644 --- a/arch/sparc/lib/NG4patch.S +++ b/arch/sparc/lib/NG4patch.S @@ -26,8 +26,8 @@ .type niagara4_patch_copyops,#function niagara4_patch_copyops: NG_DO_PATCH(memcpy, NG4memcpy) - NG_DO_PATCH(___copy_from_user, NG4copy_from_user) - NG_DO_PATCH(___copy_to_user, NG4copy_to_user) + NG_DO_PATCH(raw_copy_from_user, NG4copy_from_user) + NG_DO_PATCH(raw_copy_to_user, NG4copy_to_user) retl nop .size niagara4_patch_copyops,.-niagara4_patch_copyops diff --git a/arch/sparc/lib/NGbzero.S b/arch/sparc/lib/NGbzero.S index beab29bf419b..33053bdf3766 100644 --- a/arch/sparc/lib/NGbzero.S +++ b/arch/sparc/lib/NGbzero.S @@ -8,7 +8,7 @@ 98: x,y; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_o1; \ + .word 98b, __retl_o1_asi;\ .text; \ .align 4; diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S index 9cd42fcbc781..2333b6f3e824 100644 --- a/arch/sparc/lib/NGcopy_from_user.S +++ b/arch/sparc/lib/NGcopy_from_user.S @@ -25,7 +25,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S index 5c358afd464e..07ba20bc4ea4 100644 --- a/arch/sparc/lib/NGcopy_to_user.S +++ b/arch/sparc/lib/NGcopy_to_user.S @@ -28,7 +28,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S index d88c4ed50a00..cd654a719b27 100644 --- a/arch/sparc/lib/NGmemcpy.S +++ b/arch/sparc/lib/NGmemcpy.S @@ -394,6 +394,7 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ brz,pt %i2, 85f sub %o0, %i1, %i3 ba,a,pt %XCC, 90f + nop .align 64 70: /* 16 < len <= 64 */ diff --git a/arch/sparc/lib/NGpatch.S b/arch/sparc/lib/NGpatch.S index 3b0674fc3366..62ccda7e7b38 100644 --- a/arch/sparc/lib/NGpatch.S +++ b/arch/sparc/lib/NGpatch.S @@ -26,8 +26,8 @@ .type niagara_patch_copyops,#function niagara_patch_copyops: NG_DO_PATCH(memcpy, NGmemcpy) - NG_DO_PATCH(___copy_from_user, NGcopy_from_user) - NG_DO_PATCH(___copy_to_user, NGcopy_to_user) + NG_DO_PATCH(raw_copy_from_user, NGcopy_from_user) + NG_DO_PATCH(raw_copy_to_user, NGcopy_to_user) retl nop .size niagara_patch_copyops,.-niagara_patch_copyops diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index bb6ff73229e3..9a6e68a9bf4a 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -19,7 +19,7 @@ .text; \ .align 4; -#define FUNC_NAME ___copy_from_user +#define FUNC_NAME raw_copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_AIUS, dest #define EX_RETVAL(x) 0 @@ -31,7 +31,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop; \ #include "U1memcpy.S" diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index ed92ce739558..d7b28491eddf 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -19,7 +19,7 @@ .text; \ .align 4; -#define FUNC_NAME ___copy_to_user +#define FUNC_NAME raw_copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS #define EX_RETVAL(x) 0 @@ -31,7 +31,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop; \ #include "U1memcpy.S" diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index c4ee858e352a..f48fb87fe9f2 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -31,7 +31,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, ___copy_in_user; \ + bne,pn %icc, raw_copy_in_user; \ nop; \ #include "U3memcpy.S" diff --git a/arch/sparc/lib/U3patch.S b/arch/sparc/lib/U3patch.S index ecc302619a6e..91cd6539b6e1 100644 --- a/arch/sparc/lib/U3patch.S +++ b/arch/sparc/lib/U3patch.S @@ -26,8 +26,8 @@ .type cheetah_patch_copyops,#function cheetah_patch_copyops: ULTRA3_DO_PATCH(memcpy, U3memcpy) - ULTRA3_DO_PATCH(___copy_from_user, U3copy_from_user) - ULTRA3_DO_PATCH(___copy_to_user, U3copy_to_user) + ULTRA3_DO_PATCH(raw_copy_from_user, U3copy_from_user) + ULTRA3_DO_PATCH(raw_copy_to_user, U3copy_to_user) retl nop .size cheetah_patch_copyops,.-cheetah_patch_copyops diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S index 1c6a1bde5138..ce17c3094ba6 100644 --- a/arch/sparc/lib/atomic_64.S +++ b/arch/sparc/lib/atomic_64.S @@ -62,19 +62,23 @@ ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \ ENDPROC(atomic_fetch_##op); \ EXPORT_SYMBOL(atomic_fetch_##op); -#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op) +ATOMIC_OP(add) +ATOMIC_OP_RETURN(add) +ATOMIC_FETCH_OP(add) -ATOMIC_OPS(add) -ATOMIC_OPS(sub) +ATOMIC_OP(sub) +ATOMIC_OP_RETURN(sub) +ATOMIC_FETCH_OP(sub) -#undef ATOMIC_OPS -#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) +ATOMIC_OP(and) +ATOMIC_FETCH_OP(and) -ATOMIC_OPS(and) -ATOMIC_OPS(or) -ATOMIC_OPS(xor) +ATOMIC_OP(or) +ATOMIC_FETCH_OP(or) + +ATOMIC_OP(xor) +ATOMIC_FETCH_OP(xor) -#undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP @@ -124,19 +128,23 @@ ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \ ENDPROC(atomic64_fetch_##op); \ EXPORT_SYMBOL(atomic64_fetch_##op); -#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op) +ATOMIC64_OP(add) +ATOMIC64_OP_RETURN(add) +ATOMIC64_FETCH_OP(add) + +ATOMIC64_OP(sub) +ATOMIC64_OP_RETURN(sub) +ATOMIC64_FETCH_OP(sub) -ATOMIC64_OPS(add) -ATOMIC64_OPS(sub) +ATOMIC64_OP(and) +ATOMIC64_FETCH_OP(and) -#undef ATOMIC64_OPS -#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op) +ATOMIC64_OP(or) +ATOMIC64_FETCH_OP(or) -ATOMIC64_OPS(and) -ATOMIC64_OPS(or) -ATOMIC64_OPS(xor) +ATOMIC64_OP(xor) +ATOMIC64_FETCH_OP(xor) -#undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP diff --git a/arch/sparc/lib/checksum_64.S b/arch/sparc/lib/checksum_64.S index f6732174fe6b..6cfa521f444d 100644 --- a/arch/sparc/lib/checksum_64.S +++ b/arch/sparc/lib/checksum_64.S @@ -38,6 +38,7 @@ csum_partial_fix_alignment: .align 32 .globl csum_partial + .type csum_partial,#function EXPORT_SYMBOL(csum_partial) csum_partial: /* %o0=buff, %o1=len, %o2=sum */ prefetch [%o0 + 0x000], #n_reads diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S index 0252b218de45..1b73bb80aeb0 100644 --- a/arch/sparc/lib/copy_in_user.S +++ b/arch/sparc/lib/copy_in_user.S @@ -44,7 +44,7 @@ __retl_o2_plus_1: * to copy register windows around during thread cloning. */ -ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ +ENTRY(raw_copy_in_user) /* %o0=dst, %o1=src, %o2=len */ cmp %o2, 0 be,pn %XCC, 85f or %o0, %o1, %o3 @@ -105,5 +105,5 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ add %o0, 1, %o0 retl clr %o0 -ENDPROC(___copy_in_user) -EXPORT_SYMBOL(___copy_in_user) +ENDPROC(raw_copy_in_user) +EXPORT_SYMBOL(raw_copy_in_user) diff --git a/arch/sparc/lib/copy_user.S b/arch/sparc/lib/copy_user.S index cea644dc67a6..bc243ee807cc 100644 --- a/arch/sparc/lib/copy_user.S +++ b/arch/sparc/lib/copy_user.S @@ -364,21 +364,7 @@ short_aligned_end: 97: mov %o2, %g3 fixupretl: - sethi %hi(PAGE_OFFSET), %g1 - cmp %o0, %g1 - blu 1f - cmp %o1, %g1 - bgeu 1f - ld [%g6 + TI_PREEMPT], %g1 - cmp %g1, 0 - bne 1f - nop - save %sp, -64, %sp - mov %i0, %o0 - call __bzero - mov %g3, %o1 - restore -1: retl + retl mov %g3, %o0 /* exception routine sets %g2 to (broken_insn - first_insn)>>2 */ diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S index 0ecbafc30fd0..b1051e77c49a 100644 --- a/arch/sparc/lib/csum_copy.S +++ b/arch/sparc/lib/csum_copy.S @@ -65,6 +65,7 @@ add %o5, %o4, %o4 .globl FUNC_NAME + .type FUNC_NAME,#function EXPORT_SYMBOL(FUNC_NAME) FUNC_NAME: /* %o0=src, %o1=dst, %o2=len, %o3=sum */ LOAD(prefetch, %o0 + 0x000, #n_reads) diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S index f9985f129fb6..d21cf20e5c1e 100644 --- a/arch/sparc/lib/hweight.S +++ b/arch/sparc/lib/hweight.S @@ -4,9 +4,9 @@ .text .align 32 ENTRY(__arch_hweight8) - ba,pt %xcc, __sw_hweight8 + sethi %hi(__sw_hweight8), %g1 + jmpl %g1 + %lo(__sw_hweight8), %g0 nop - nop ENDPROC(__arch_hweight8) EXPORT_SYMBOL(__arch_hweight8) .section .popc_3insn_patch, "ax" @@ -17,9 +17,9 @@ EXPORT_SYMBOL(__arch_hweight8) .previous ENTRY(__arch_hweight16) - ba,pt %xcc, __sw_hweight16 + sethi %hi(__sw_hweight16), %g1 + jmpl %g1 + %lo(__sw_hweight16), %g0 nop - nop ENDPROC(__arch_hweight16) EXPORT_SYMBOL(__arch_hweight16) .section .popc_3insn_patch, "ax" @@ -30,9 +30,9 @@ EXPORT_SYMBOL(__arch_hweight16) .previous ENTRY(__arch_hweight32) - ba,pt %xcc, __sw_hweight32 + sethi %hi(__sw_hweight32), %g1 + jmpl %g1 + %lo(__sw_hweight32), %g0 nop - nop ENDPROC(__arch_hweight32) EXPORT_SYMBOL(__arch_hweight32) .section .popc_3insn_patch, "ax" @@ -43,9 +43,9 @@ EXPORT_SYMBOL(__arch_hweight32) .previous ENTRY(__arch_hweight64) - ba,pt %xcc, __sw_hweight64 + sethi %hi(__sw_hweight16), %g1 + jmpl %g1 + %lo(__sw_hweight16), %g0 nop - nop ENDPROC(__arch_hweight64) EXPORT_SYMBOL(__arch_hweight64) .section .popc_3insn_patch, "ax" diff --git a/arch/sparc/lib/memscan_64.S b/arch/sparc/lib/memscan_64.S index daa96f4b03e6..5efee1f4be36 100644 --- a/arch/sparc/lib/memscan_64.S +++ b/arch/sparc/lib/memscan_64.S @@ -14,6 +14,8 @@ .text .align 32 .globl __memscan_zero, __memscan_generic + .type __memscan_zero,#function + .type __memscan_generic,#function .globl memscan EXPORT_SYMBOL(__memscan_zero) EXPORT_SYMBOL(__memscan_generic) diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index bb539b42b088..e23338dbfc43 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -63,6 +63,7 @@ __bzero_begin: .globl __bzero + .type __bzero,#function .globl memset EXPORT_SYMBOL(__bzero) EXPORT_SYMBOL(memset) diff --git a/arch/sparc/lib/multi3.S b/arch/sparc/lib/multi3.S new file mode 100644 index 000000000000..d6b6c97fe3c7 --- /dev/null +++ b/arch/sparc/lib/multi3.S @@ -0,0 +1,35 @@ +#include <linux/linkage.h> +#include <asm/export.h> + + .text + .align 4 +ENTRY(__multi3) /* %o0 = u, %o1 = v */ + mov %o1, %g1 + srl %o3, 0, %g4 + mulx %g4, %g1, %o1 + srlx %g1, 0x20, %g3 + mulx %g3, %g4, %g5 + sllx %g5, 0x20, %o5 + srl %g1, 0, %g4 + sub %o1, %o5, %o5 + srlx %o5, 0x20, %o5 + addcc %g5, %o5, %g5 + srlx %o3, 0x20, %o5 + mulx %g4, %o5, %g4 + mulx %g3, %o5, %o5 + sethi %hi(0x80000000), %g3 + addcc %g5, %g4, %g5 + srlx %g5, 0x20, %g5 + add %g3, %g3, %g3 + movcc %xcc, %g0, %g3 + addcc %o5, %g5, %o5 + sllx %g4, 0x20, %g4 + add %o1, %g4, %o1 + add %o5, %g3, %g2 + mulx %g1, %o2, %g1 + add %g1, %g2, %g1 + mulx %o0, %o3, %o0 + retl + add %g1, %o0, %o0 +ENDPROC(__multi3) +EXPORT_SYMBOL(__multi3) diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c index 768a11e6bd4f..2422511dc8c5 100644 --- a/arch/sparc/mm/extable.c +++ b/arch/sparc/mm/extable.c @@ -3,6 +3,7 @@ */ #include <linux/module.h> +#include <linux/extable.h> #include <linux/uaccess.h> void sort_extable(struct exception_table_entry *start, @@ -12,11 +13,11 @@ void sort_extable(struct exception_table_entry *start, /* Caller knows they are in a range if ret->fixup == 0 */ const struct exception_table_entry * -search_extable(const struct exception_table_entry *start, - const struct exception_table_entry *last, +search_extable(const struct exception_table_entry *base, + const size_t num, unsigned long value) { - const struct exception_table_entry *walk; + int i; /* Single insn entries are encoded as: * word 1: insn address @@ -36,30 +37,30 @@ search_extable(const struct exception_table_entry *start, */ /* 1. Try to find an exact match. */ - for (walk = start; walk <= last; walk++) { - if (walk->fixup == 0) { + for (i = 0; i < num; i++) { + if (base[i].fixup == 0) { /* A range entry, skip both parts. */ - walk++; + i++; continue; } /* A deleted entry; see trim_init_extable */ - if (walk->fixup == -1) + if (base[i].fixup == -1) continue; - if (walk->insn == value) - return walk; + if (base[i].insn == value) + return &base[i]; } /* 2. Try to find a range match. */ - for (walk = start; walk <= (last - 1); walk++) { - if (walk->fixup) + for (i = 0; i < (num - 1); i++) { + if (base[i].fixup) continue; - if (walk[0].insn <= value && walk[1].insn > value) - return walk; + if (base[i].insn <= value && base[i + 1].insn > value) + return &base[i]; - walk++; + i++; } return NULL; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 643c149a3151..b84c4dd14954 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -10,6 +10,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/sched.h> +#include <linux/sched/debug.h> #include <linux/ptrace.h> #include <linux/mman.h> #include <linux/signal.h> diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index cd0e32bbcb1d..f80cfc64c55b 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -78,8 +78,8 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; refs = 0; - head = pmd_page(pmd); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + page = pmd_page(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + head = compound_head(page); do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 988acc8b1b80..28ee8d8ffa07 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -6,6 +6,7 @@ #include <linux/fs.h> #include <linux/mm.h> +#include <linux/sched/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/sysctl.h> @@ -28,6 +29,7 @@ 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 +40,7 @@ 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 +60,7 @@ 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 +72,7 @@ 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 +97,7 @@ 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 +105,7 @@ 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; @@ -113,10 +117,10 @@ 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)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) @@ -127,68 +131,234 @@ 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_2GB_SHIFT: + hugepage_size = _PAGE_SZ2GB_4V; + pte_val(entry) |= _PAGE_PMD_HUGE; + break; + 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_SZ2GB_4V: + shift = HPAGE_2GB_SHIFT; + break; + 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_SIZE) + pte = (pte_t *)pmd; + else + pte = pte_alloc_map(mm, pmd, addr); + } return pte; } -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_offset(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); 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; } @@ -292,6 +462,22 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; + addr &= PMD_MASK; + if (addr < floor) { + addr += PMD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= PMD_SIZE; + if (addr > end - 1) + return; + pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index eb8287155279..3bd0d513bddb 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) @@ -301,7 +290,7 @@ void __init mem_init(void) /* Saves us work later. */ - memset((void *)&empty_zero_page, 0, PAGE_SIZE); + memset((void *)empty_zero_page, 0, PAGE_SIZE); i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5); i += 1; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 5d2f91511c60..3c40ebd50f92 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -324,6 +324,55 @@ 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_2GB_SHIFT: + hv_pgsz_mask = HV_PGSZ_MASK_2GB; + hv_pgsz_idx = HV_PGSZ_IDX_2GB; + break; + 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) { + hugetlb_bad_size(); + pr_err("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 +396,7 @@ 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, @@ -658,10 +707,58 @@ EXPORT_SYMBOL(__flush_dcache_range); /* get_new_mmu_context() uses "cache + 1". */ DEFINE_SPINLOCK(ctx_alloc_lock); -unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1; +unsigned long tlb_context_cache = CTX_FIRST_VERSION; #define MAX_CTX_NR (1UL << CTX_NR_BITS) #define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR) DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR); +DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0}; + +static void mmu_context_wrap(void) +{ + unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK; + unsigned long new_ver, new_ctx, old_ctx; + struct mm_struct *mm; + int cpu; + + bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS); + + /* Reserve kernel context */ + set_bit(0, mmu_context_bmap); + + new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION; + if (unlikely(new_ver == 0)) + new_ver = CTX_FIRST_VERSION; + tlb_context_cache = new_ver; + + /* + * Make sure that any new mm that are added into per_cpu_secondary_mm, + * are going to go through get_new_mmu_context() path. + */ + mb(); + + /* + * Updated versions to current on those CPUs that had valid secondary + * contexts + */ + for_each_online_cpu(cpu) { + /* + * If a new mm is stored after we took this mm from the array, + * it will go into get_new_mmu_context() path, because we + * already bumped the version in tlb_context_cache. + */ + mm = per_cpu(per_cpu_secondary_mm, cpu); + + if (unlikely(!mm || mm == &init_mm)) + continue; + + old_ctx = mm->context.sparc64_ctx_val; + if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) { + new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver; + set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap); + mm->context.sparc64_ctx_val = new_ctx; + } + } +} /* Caller does TLB context flushing on local CPU if necessary. * The caller also ensures that CTX_VALID(mm->context) is false. @@ -677,48 +774,30 @@ void get_new_mmu_context(struct mm_struct *mm) { unsigned long ctx, new_ctx; unsigned long orig_pgsz_bits; - int new_version; spin_lock(&ctx_alloc_lock); +retry: + /* wrap might have happened, test again if our context became valid */ + if (unlikely(CTX_VALID(mm->context))) + goto out; orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK); ctx = (tlb_context_cache + 1) & CTX_NR_MASK; new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx); - new_version = 0; if (new_ctx >= (1 << CTX_NR_BITS)) { new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1); if (new_ctx >= ctx) { - int i; - new_ctx = (tlb_context_cache & CTX_VERSION_MASK) + - CTX_FIRST_VERSION; - if (new_ctx == 1) - new_ctx = CTX_FIRST_VERSION; - - /* Don't call memset, for 16 entries that's just - * plain silly... - */ - mmu_context_bmap[0] = 3; - mmu_context_bmap[1] = 0; - mmu_context_bmap[2] = 0; - mmu_context_bmap[3] = 0; - for (i = 4; i < CTX_BMAP_SLOTS; i += 4) { - mmu_context_bmap[i + 0] = 0; - mmu_context_bmap[i + 1] = 0; - mmu_context_bmap[i + 2] = 0; - mmu_context_bmap[i + 3] = 0; - } - new_version = 1; - goto out; + mmu_context_wrap(); + goto retry; } } + if (mm->context.sparc64_ctx_val) + cpumask_clear(mm_cpumask(mm)); mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63)); new_ctx |= (tlb_context_cache & CTX_VERSION_MASK); -out: tlb_context_cache = new_ctx; mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits; +out: spin_unlock(&ctx_alloc_lock); - - if (unlikely(new_version)) - smp_new_mmu_context_version(); } static int numa_enabled = 1; @@ -785,13 +864,23 @@ 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 +891,129 @@ 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; + } + + 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 (n != *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 +1054,8 @@ 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 +1073,6 @@ 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 +1161,10 @@ 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 +1184,8 @@ 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 +1320,6 @@ 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 +1327,7 @@ 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 +1382,10 @@ 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 +1482,7 @@ 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++; } @@ -1495,7 +1598,7 @@ bool kern_addr_valid(unsigned long addr) if ((long)addr < 0L) { unsigned long pa = __pa(addr); - if ((addr >> max_phys_bits) != 0UL) + if ((pa >> max_phys_bits) != 0UL) return false; return pfn_valid(pa >> PAGE_SHIFT); diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c7f2a5295b3a..8e76ebba2986 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -54,6 +54,7 @@ enum mbus_module srmmu_modtype; static unsigned int hwbug_bitmask; int vac_cache_size; +EXPORT_SYMBOL(vac_cache_size); int vac_line_size; extern struct resource sparc_iomap; @@ -1444,7 +1445,7 @@ 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 +1476,7 @@ 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 +1760,7 @@ 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..ee8066c3d96c 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 @@ -155,7 +154,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, if (pte_val(*pte) & _PAGE_VALID) { bool exec = pte_exec(*pte); - tlb_batch_add_one(mm, vaddr, exec, false); + tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT); } pte++; vaddr += PAGE_SIZE; @@ -210,9 +209,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pte_t orig_pte = __pte(pmd_val(orig)); bool exec = pte_exec(orig_pte); - tlb_batch_add_one(mm, addr, exec, true); + tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT); tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec, - true); + REAL_HPAGE_SHIFT); } else { tlb_batch_pmd_scan(mm, addr, orig); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index e20fbbafb0b0..0d4b998c7d7b 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -6,6 +6,8 @@ #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/slab.h> +#include <linux/mm_types.h> + #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mmu_context.h> @@ -86,6 +88,33 @@ 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 +122,61 @@ void flush_tsb_user(struct tlb_batch *tb) spin_lock_irqsave(&mm->context.lock, flags); - if (!tb->huge) { + if (tb->hugepage_shift < REAL_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 < REAL_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); @@ -451,7 +496,8 @@ retry_tsb_alloc: extern void copy_tsb(unsigned long old_tsb_base, unsigned long old_tsb_size, unsigned long new_tsb_base, - unsigned long new_tsb_size); + unsigned long new_tsb_size, + unsigned long page_size_shift); unsigned long old_tsb_base = (unsigned long) old_tsb; unsigned long new_tsb_base = (unsigned long) new_tsb; @@ -459,7 +505,9 @@ retry_tsb_alloc: old_tsb_base = __pa(old_tsb_base); new_tsb_base = __pa(new_tsb_base); } - copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size); + copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size, + tsb_index == MM_TSB_BASE ? + PAGE_SHIFT : REAL_HPAGE_SHIFT); } mm->context.tsb_block[tsb_index].tsb = new_tsb; diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index 5d2fd6cd3189..fcf4d27a38fb 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -971,11 +971,6 @@ xcall_capture: wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint retry - .globl xcall_new_mmu_context_version -xcall_new_mmu_context_version: - wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint - retry - #ifdef CONFIG_KGDB .globl xcall_kgdb_capture xcall_kgdb_capture: diff --git a/arch/sparc/net/Makefile b/arch/sparc/net/Makefile index 1306a58ac541..76fa8e95b721 100644 --- a/arch/sparc/net/Makefile +++ b/arch/sparc/net/Makefile @@ -1,4 +1,4 @@ # # Arch-specific network modules # -obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o +obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o diff --git a/arch/sparc/net/bpf_jit.h b/arch/sparc/net/bpf_jit_32.h index 33d6b375ff12..d5c069bff5f9 100644 --- a/arch/sparc/net/bpf_jit.h +++ b/arch/sparc/net/bpf_jit_32.h @@ -39,7 +39,7 @@ #define r_TMP2 G2 #define r_OFF G3 -/* assembly code in arch/sparc/net/bpf_jit_asm.S */ +/* assembly code in arch/sparc/net/bpf_jit_asm_32.S */ extern u32 bpf_jit_load_word[]; extern u32 bpf_jit_load_half[]; extern u32 bpf_jit_load_byte[]; diff --git a/arch/sparc/net/bpf_jit_64.h b/arch/sparc/net/bpf_jit_64.h new file mode 100644 index 000000000000..74abd45796ea --- /dev/null +++ b/arch/sparc/net/bpf_jit_64.h @@ -0,0 +1,66 @@ +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#ifndef __ASSEMBLER__ +#define G0 0x00 +#define G1 0x01 +#define G2 0x02 +#define G3 0x03 +#define G6 0x06 +#define G7 0x07 +#define O0 0x08 +#define O1 0x09 +#define O2 0x0a +#define O3 0x0b +#define O4 0x0c +#define O5 0x0d +#define SP 0x0e +#define O7 0x0f +#define L0 0x10 +#define L1 0x11 +#define L2 0x12 +#define L3 0x13 +#define L4 0x14 +#define L5 0x15 +#define L6 0x16 +#define L7 0x17 +#define I0 0x18 +#define I1 0x19 +#define I2 0x1a +#define I3 0x1b +#define I4 0x1c +#define I5 0x1d +#define FP 0x1e +#define I7 0x1f + +#define r_SKB L0 +#define r_HEADLEN L4 +#define r_SKB_DATA L5 +#define r_TMP G1 +#define r_TMP2 G3 + +/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */ +extern u32 bpf_jit_load_word[]; +extern u32 bpf_jit_load_half[]; +extern u32 bpf_jit_load_byte[]; +extern u32 bpf_jit_load_byte_msh[]; +extern u32 bpf_jit_load_word_positive_offset[]; +extern u32 bpf_jit_load_half_positive_offset[]; +extern u32 bpf_jit_load_byte_positive_offset[]; +extern u32 bpf_jit_load_byte_msh_positive_offset[]; +extern u32 bpf_jit_load_word_negative_offset[]; +extern u32 bpf_jit_load_half_negative_offset[]; +extern u32 bpf_jit_load_byte_negative_offset[]; +extern u32 bpf_jit_load_byte_msh_negative_offset[]; + +#else +#define r_RESULT %o0 +#define r_SKB %o0 +#define r_OFF %o1 +#define r_HEADLEN %l4 +#define r_SKB_DATA %l5 +#define r_TMP %g1 +#define r_TMP2 %g3 +#endif + +#endif /* _BPF_JIT_H */ diff --git a/arch/sparc/net/bpf_jit_asm.S b/arch/sparc/net/bpf_jit_asm_32.S index 8c83f4b8eb15..dcc402f5738a 100644 --- a/arch/sparc/net/bpf_jit_asm.S +++ b/arch/sparc/net/bpf_jit_asm_32.S @@ -1,18 +1,11 @@ #include <asm/ptrace.h> -#include "bpf_jit.h" +#include "bpf_jit_32.h" -#ifdef CONFIG_SPARC64 -#define SAVE_SZ 176 -#define SCRATCH_OFF STACK_BIAS + 128 -#define BE_PTR(label) be,pn %xcc, label -#define SIGN_EXTEND(reg) sra reg, 0, reg -#else #define SAVE_SZ 96 #define SCRATCH_OFF 72 #define BE_PTR(label) be label #define SIGN_EXTEND(reg) -#endif #define SKF_MAX_NEG_OFF (-0x200000) /* SKF_LL_OFF from filter.h */ diff --git a/arch/sparc/net/bpf_jit_asm_64.S b/arch/sparc/net/bpf_jit_asm_64.S new file mode 100644 index 000000000000..3b3f14655f81 --- /dev/null +++ b/arch/sparc/net/bpf_jit_asm_64.S @@ -0,0 +1,161 @@ +#include <asm/ptrace.h> + +#include "bpf_jit_64.h" + +#define SAVE_SZ 176 +#define SCRATCH_OFF STACK_BIAS + 128 +#define BE_PTR(label) be,pn %xcc, label +#define SIGN_EXTEND(reg) sra reg, 0, reg + +#define SKF_MAX_NEG_OFF (-0x200000) /* SKF_LL_OFF from filter.h */ + + .text + .globl bpf_jit_load_word +bpf_jit_load_word: + cmp r_OFF, 0 + bl bpf_slow_path_word_neg + nop + .globl bpf_jit_load_word_positive_offset +bpf_jit_load_word_positive_offset: + sub r_HEADLEN, r_OFF, r_TMP + cmp r_TMP, 3 + ble bpf_slow_path_word + add r_SKB_DATA, r_OFF, r_TMP + andcc r_TMP, 3, %g0 + bne load_word_unaligned + nop + retl + ld [r_TMP], r_RESULT +load_word_unaligned: + ldub [r_TMP + 0x0], r_OFF + ldub [r_TMP + 0x1], r_TMP2 + sll r_OFF, 8, r_OFF + or r_OFF, r_TMP2, r_OFF + ldub [r_TMP + 0x2], r_TMP2 + sll r_OFF, 8, r_OFF + or r_OFF, r_TMP2, r_OFF + ldub [r_TMP + 0x3], r_TMP2 + sll r_OFF, 8, r_OFF + retl + or r_OFF, r_TMP2, r_RESULT + + .globl bpf_jit_load_half +bpf_jit_load_half: + cmp r_OFF, 0 + bl bpf_slow_path_half_neg + nop + .globl bpf_jit_load_half_positive_offset +bpf_jit_load_half_positive_offset: + sub r_HEADLEN, r_OFF, r_TMP + cmp r_TMP, 1 + ble bpf_slow_path_half + add r_SKB_DATA, r_OFF, r_TMP + andcc r_TMP, 1, %g0 + bne load_half_unaligned + nop + retl + lduh [r_TMP], r_RESULT +load_half_unaligned: + ldub [r_TMP + 0x0], r_OFF + ldub [r_TMP + 0x1], r_TMP2 + sll r_OFF, 8, r_OFF + retl + or r_OFF, r_TMP2, r_RESULT + + .globl bpf_jit_load_byte +bpf_jit_load_byte: + cmp r_OFF, 0 + bl bpf_slow_path_byte_neg + nop + .globl bpf_jit_load_byte_positive_offset +bpf_jit_load_byte_positive_offset: + cmp r_OFF, r_HEADLEN + bge bpf_slow_path_byte + nop + retl + ldub [r_SKB_DATA + r_OFF], r_RESULT + +#define bpf_slow_path_common(LEN) \ + save %sp, -SAVE_SZ, %sp; \ + mov %i0, %o0; \ + mov %i1, %o1; \ + add %fp, SCRATCH_OFF, %o2; \ + call skb_copy_bits; \ + mov (LEN), %o3; \ + cmp %o0, 0; \ + restore; + +bpf_slow_path_word: + bpf_slow_path_common(4) + bl bpf_error + ld [%sp + SCRATCH_OFF], r_RESULT + retl + nop +bpf_slow_path_half: + bpf_slow_path_common(2) + bl bpf_error + lduh [%sp + SCRATCH_OFF], r_RESULT + retl + nop +bpf_slow_path_byte: + bpf_slow_path_common(1) + bl bpf_error + ldub [%sp + SCRATCH_OFF], r_RESULT + retl + nop + +#define bpf_negative_common(LEN) \ + save %sp, -SAVE_SZ, %sp; \ + mov %i0, %o0; \ + mov %i1, %o1; \ + SIGN_EXTEND(%o1); \ + call bpf_internal_load_pointer_neg_helper; \ + mov (LEN), %o2; \ + mov %o0, r_TMP; \ + cmp %o0, 0; \ + BE_PTR(bpf_error); \ + restore; + +bpf_slow_path_word_neg: + sethi %hi(SKF_MAX_NEG_OFF), r_TMP + cmp r_OFF, r_TMP + bl bpf_error + nop + .globl bpf_jit_load_word_negative_offset +bpf_jit_load_word_negative_offset: + bpf_negative_common(4) + andcc r_TMP, 3, %g0 + bne load_word_unaligned + nop + retl + ld [r_TMP], r_RESULT + +bpf_slow_path_half_neg: + sethi %hi(SKF_MAX_NEG_OFF), r_TMP + cmp r_OFF, r_TMP + bl bpf_error + nop + .globl bpf_jit_load_half_negative_offset +bpf_jit_load_half_negative_offset: + bpf_negative_common(2) + andcc r_TMP, 1, %g0 + bne load_half_unaligned + nop + retl + lduh [r_TMP], r_RESULT + +bpf_slow_path_byte_neg: + sethi %hi(SKF_MAX_NEG_OFF), r_TMP + cmp r_OFF, r_TMP + bl bpf_error + nop + .globl bpf_jit_load_byte_negative_offset +bpf_jit_load_byte_negative_offset: + bpf_negative_common(1) + retl + ldub [r_TMP], r_RESULT + +bpf_error: + /* Make the JIT program itself return zero. */ + ret + restore %g0, %g0, %o0 diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp_32.c index a6d9204a6a0b..d193748548e2 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -8,7 +8,7 @@ #include <asm/cacheflush.h> #include <asm/ptrace.h> -#include "bpf_jit.h" +#include "bpf_jit_32.h" int bpf_jit_enable __read_mostly; @@ -17,24 +17,6 @@ static inline bool is_simm13(unsigned int value) return value + 0x1000 < 0x2000; } -static void bpf_flush_icache(void *start_, void *end_) -{ -#ifdef CONFIG_SPARC64 - /* Cheetah's I-cache is fully coherent. */ - if (tlb_type == spitfire) { - unsigned long start = (unsigned long) start_; - unsigned long end = (unsigned long) end_; - - start &= ~7UL; - end = (end + 7UL) & ~7UL; - while (start < end) { - flushi(start); - start += 32; - } - } -#endif -} - #define SEEN_DATAREF 1 /* might call external helpers */ #define SEEN_XREG 2 /* ebx is used */ #define SEEN_MEM 4 /* use mem[] for temporary storage */ @@ -82,11 +64,7 @@ static void bpf_flush_icache(void *start_, void *end_) #define BE (F2(0, 2) | CONDE) #define BNE (F2(0, 2) | CONDNE) -#ifdef CONFIG_SPARC64 -#define BE_PTR (F2(0, 1) | CONDE | (2 << 20)) -#else #define BE_PTR BE -#endif #define SETHI(K, REG) \ (F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff)) @@ -116,13 +94,8 @@ static void bpf_flush_icache(void *start_, void *end_) #define LD64 F3(3, 0x0b) #define ST32 F3(3, 0x04) -#ifdef CONFIG_SPARC64 -#define LDPTR LD64 -#define BASE_STACKFRAME 176 -#else #define LDPTR LD32 #define BASE_STACKFRAME 96 -#endif #define LD32I (LD32 | IMMED) #define LD8I (LD8 | IMMED) @@ -234,11 +207,7 @@ do { BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u8)); \ __emit_load8(BASE, STRUCT, FIELD, DEST); \ } while (0) -#ifdef CONFIG_SPARC64 -#define BIAS (STACK_BIAS - 4) -#else #define BIAS (-4) -#endif #define emit_ldmem(OFF, DEST) \ do { *prog++ = LD32I | RS1(SP) | S13(BIAS - (OFF)) | RD(DEST); \ @@ -249,13 +218,8 @@ do { *prog++ = ST32I | RS1(SP) | S13(BIAS - (OFF)) | RD(SRC); \ } while (0) #ifdef CONFIG_SMP -#ifdef CONFIG_SPARC64 -#define emit_load_cpu(REG) \ - emit_load16(G6, struct thread_info, cpu, REG) -#else #define emit_load_cpu(REG) \ emit_load32(G6, struct thread_info, cpu, REG) -#endif #else #define emit_load_cpu(REG) emit_clear(REG) #endif @@ -486,7 +450,6 @@ void bpf_jit_compile(struct bpf_prog *fp) if (K == 1) break; emit_write_y(G0); -#ifdef CONFIG_SPARC32 /* The Sparc v8 architecture requires * three instructions between a %y * register write and the first use. @@ -494,31 +457,21 @@ void bpf_jit_compile(struct bpf_prog *fp) emit_nop(); emit_nop(); emit_nop(); -#endif emit_alu_K(DIV, K); break; case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */ emit_cmpi(r_X, 0); if (pc_ret0 > 0) { t_offset = addrs[pc_ret0 - 1]; -#ifdef CONFIG_SPARC32 emit_branch(BE, t_offset + 20); -#else - emit_branch(BE, t_offset + 8); -#endif emit_nop(); /* delay slot */ } else { emit_branch_off(BNE, 16); emit_nop(); -#ifdef CONFIG_SPARC32 emit_jump(cleanup_addr + 20); -#else - emit_jump(cleanup_addr + 8); -#endif emit_clear(r_A); } emit_write_y(G0); -#ifdef CONFIG_SPARC32 /* The Sparc v8 architecture requires * three instructions between a %y * register write and the first use. @@ -526,7 +479,6 @@ void bpf_jit_compile(struct bpf_prog *fp) emit_nop(); emit_nop(); emit_nop(); -#endif emit_alu_X(DIV); break; case BPF_ALU | BPF_NEG: @@ -797,7 +749,6 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; bpf_jit_dump(flen, proglen, pass + 1, image); if (image) { - bpf_flush_icache(image, image + proglen); fp->bpf_func = (void *)image; fp->jited = 1; } diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c new file mode 100644 index 000000000000..8799ae9a8788 --- /dev/null +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -0,0 +1,1572 @@ +#include <linux/moduleloader.h> +#include <linux/workqueue.h> +#include <linux/netdevice.h> +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/cache.h> +#include <linux/if_vlan.h> + +#include <asm/cacheflush.h> +#include <asm/ptrace.h> + +#include "bpf_jit_64.h" + +int bpf_jit_enable __read_mostly; + +static inline bool is_simm13(unsigned int value) +{ + return value + 0x1000 < 0x2000; +} + +static inline bool is_simm10(unsigned int value) +{ + return value + 0x200 < 0x400; +} + +static inline bool is_simm5(unsigned int value) +{ + return value + 0x10 < 0x20; +} + +static inline bool is_sethi(unsigned int value) +{ + return (value & ~0x3fffff) == 0; +} + +static void bpf_flush_icache(void *start_, void *end_) +{ + /* Cheetah's I-cache is fully coherent. */ + if (tlb_type == spitfire) { + unsigned long start = (unsigned long) start_; + unsigned long end = (unsigned long) end_; + + start &= ~7UL; + end = (end + 7UL) & ~7UL; + while (start < end) { + flushi(start); + start += 32; + } + } +} + +#define SEEN_DATAREF 1 /* might call external helpers */ +#define SEEN_XREG 2 /* ebx is used */ +#define SEEN_MEM 4 /* use mem[] for temporary storage */ + +#define S13(X) ((X) & 0x1fff) +#define S5(X) ((X) & 0x1f) +#define IMMED 0x00002000 +#define RD(X) ((X) << 25) +#define RS1(X) ((X) << 14) +#define RS2(X) ((X)) +#define OP(X) ((X) << 30) +#define OP2(X) ((X) << 22) +#define OP3(X) ((X) << 19) +#define COND(X) (((X) & 0xf) << 25) +#define CBCOND(X) (((X) & 0x1f) << 25) +#define F1(X) OP(X) +#define F2(X, Y) (OP(X) | OP2(Y)) +#define F3(X, Y) (OP(X) | OP3(Y)) +#define ASI(X) (((X) & 0xff) << 5) + +#define CONDN COND(0x0) +#define CONDE COND(0x1) +#define CONDLE COND(0x2) +#define CONDL COND(0x3) +#define CONDLEU COND(0x4) +#define CONDCS COND(0x5) +#define CONDNEG COND(0x6) +#define CONDVC COND(0x7) +#define CONDA COND(0x8) +#define CONDNE COND(0x9) +#define CONDG COND(0xa) +#define CONDGE COND(0xb) +#define CONDGU COND(0xc) +#define CONDCC COND(0xd) +#define CONDPOS COND(0xe) +#define CONDVS COND(0xf) + +#define CONDGEU CONDCC +#define CONDLU CONDCS + +#define WDISP22(X) (((X) >> 2) & 0x3fffff) +#define WDISP19(X) (((X) >> 2) & 0x7ffff) + +/* The 10-bit branch displacement for CBCOND is split into two fields */ +static u32 WDISP10(u32 off) +{ + u32 ret = ((off >> 2) & 0xff) << 5; + + ret |= ((off >> (2 + 8)) & 0x03) << 19; + + return ret; +} + +#define CBCONDE CBCOND(0x09) +#define CBCONDLE CBCOND(0x0a) +#define CBCONDL CBCOND(0x0b) +#define CBCONDLEU CBCOND(0x0c) +#define CBCONDCS CBCOND(0x0d) +#define CBCONDN CBCOND(0x0e) +#define CBCONDVS CBCOND(0x0f) +#define CBCONDNE CBCOND(0x19) +#define CBCONDG CBCOND(0x1a) +#define CBCONDGE CBCOND(0x1b) +#define CBCONDGU CBCOND(0x1c) +#define CBCONDCC CBCOND(0x1d) +#define CBCONDPOS CBCOND(0x1e) +#define CBCONDVC CBCOND(0x1f) + +#define CBCONDGEU CBCONDCC +#define CBCONDLU CBCONDCS + +#define ANNUL (1 << 29) +#define XCC (1 << 21) + +#define BRANCH (F2(0, 1) | XCC) +#define CBCOND_OP (F2(0, 3) | XCC) + +#define BA (BRANCH | CONDA) +#define BG (BRANCH | CONDG) +#define BGU (BRANCH | CONDGU) +#define BLEU (BRANCH | CONDLEU) +#define BGE (BRANCH | CONDGE) +#define BGEU (BRANCH | CONDGEU) +#define BLU (BRANCH | CONDLU) +#define BE (BRANCH | CONDE) +#define BNE (BRANCH | CONDNE) + +#define SETHI(K, REG) \ + (F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff)) +#define OR_LO(K, REG) \ + (F3(2, 0x02) | IMMED | RS1(REG) | ((K) & 0x3ff) | RD(REG)) + +#define ADD F3(2, 0x00) +#define AND F3(2, 0x01) +#define ANDCC F3(2, 0x11) +#define OR F3(2, 0x02) +#define XOR F3(2, 0x03) +#define SUB F3(2, 0x04) +#define SUBCC F3(2, 0x14) +#define MUL F3(2, 0x0a) +#define MULX F3(2, 0x09) +#define UDIVX F3(2, 0x0d) +#define DIV F3(2, 0x0e) +#define SLL F3(2, 0x25) +#define SLLX (F3(2, 0x25)|(1<<12)) +#define SRA F3(2, 0x27) +#define SRAX (F3(2, 0x27)|(1<<12)) +#define SRL F3(2, 0x26) +#define SRLX (F3(2, 0x26)|(1<<12)) +#define JMPL F3(2, 0x38) +#define SAVE F3(2, 0x3c) +#define RESTORE F3(2, 0x3d) +#define CALL F1(1) +#define BR F2(0, 0x01) +#define RD_Y F3(2, 0x28) +#define WR_Y F3(2, 0x30) + +#define LD32 F3(3, 0x00) +#define LD8 F3(3, 0x01) +#define LD16 F3(3, 0x02) +#define LD64 F3(3, 0x0b) +#define LD64A F3(3, 0x1b) +#define ST8 F3(3, 0x05) +#define ST16 F3(3, 0x06) +#define ST32 F3(3, 0x04) +#define ST64 F3(3, 0x0e) + +#define CAS F3(3, 0x3c) +#define CASX F3(3, 0x3e) + +#define LDPTR LD64 +#define BASE_STACKFRAME 176 + +#define LD32I (LD32 | IMMED) +#define LD8I (LD8 | IMMED) +#define LD16I (LD16 | IMMED) +#define LD64I (LD64 | IMMED) +#define LDPTRI (LDPTR | IMMED) +#define ST32I (ST32 | IMMED) + +struct jit_ctx { + struct bpf_prog *prog; + unsigned int *offset; + int idx; + int epilogue_offset; + bool tmp_1_used; + bool tmp_2_used; + bool tmp_3_used; + bool saw_ld_abs_ind; + bool saw_frame_pointer; + bool saw_call; + bool saw_tail_call; + u32 *image; +}; + +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) +#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 2) +#define SKB_DATA_REG (MAX_BPF_JIT_REG + 3) +#define TMP_REG_3 (MAX_BPF_JIT_REG + 4) + +/* Map BPF registers to SPARC registers */ +static const int bpf2sparc[] = { + /* return value from in-kernel function, and exit value from eBPF */ + [BPF_REG_0] = O5, + + /* arguments from eBPF program to in-kernel function */ + [BPF_REG_1] = O0, + [BPF_REG_2] = O1, + [BPF_REG_3] = O2, + [BPF_REG_4] = O3, + [BPF_REG_5] = O4, + + /* callee saved registers that in-kernel function will preserve */ + [BPF_REG_6] = L0, + [BPF_REG_7] = L1, + [BPF_REG_8] = L2, + [BPF_REG_9] = L3, + + /* read-only frame pointer to access stack */ + [BPF_REG_FP] = L6, + + [BPF_REG_AX] = G7, + + /* temporary register for internal BPF JIT */ + [TMP_REG_1] = G1, + [TMP_REG_2] = G2, + [TMP_REG_3] = G3, + + [SKB_HLEN_REG] = L4, + [SKB_DATA_REG] = L5, +}; + +static void emit(const u32 insn, struct jit_ctx *ctx) +{ + if (ctx->image != NULL) + ctx->image[ctx->idx] = insn; + + ctx->idx++; +} + +static void emit_call(u32 *func, struct jit_ctx *ctx) +{ + if (ctx->image != NULL) { + void *here = &ctx->image[ctx->idx]; + unsigned int off; + + off = (void *)func - here; + ctx->image[ctx->idx] = CALL | ((off >> 2) & 0x3fffffff); + } + ctx->idx++; +} + +static void emit_nop(struct jit_ctx *ctx) +{ + emit(SETHI(0, G0), ctx); +} + +static void emit_reg_move(u32 from, u32 to, struct jit_ctx *ctx) +{ + emit(OR | RS1(G0) | RS2(from) | RD(to), ctx); +} + +/* Emit 32-bit constant, zero extended. */ +static void emit_set_const(s32 K, u32 reg, struct jit_ctx *ctx) +{ + emit(SETHI(K, reg), ctx); + emit(OR_LO(K, reg), ctx); +} + +/* Emit 32-bit constant, sign extended. */ +static void emit_set_const_sext(s32 K, u32 reg, struct jit_ctx *ctx) +{ + if (K >= 0) { + emit(SETHI(K, reg), ctx); + emit(OR_LO(K, reg), ctx); + } else { + u32 hbits = ~(u32) K; + u32 lbits = -0x400 | (u32) K; + + emit(SETHI(hbits, reg), ctx); + emit(XOR | IMMED | RS1(reg) | S13(lbits) | RD(reg), ctx); + } +} + +static void emit_alu(u32 opcode, u32 src, u32 dst, struct jit_ctx *ctx) +{ + emit(opcode | RS1(dst) | RS2(src) | RD(dst), ctx); +} + +static void emit_alu3(u32 opcode, u32 a, u32 b, u32 c, struct jit_ctx *ctx) +{ + emit(opcode | RS1(a) | RS2(b) | RD(c), ctx); +} + +static void emit_alu_K(unsigned int opcode, unsigned int dst, unsigned int imm, + struct jit_ctx *ctx) +{ + bool small_immed = is_simm13(imm); + unsigned int insn = opcode; + + insn |= RS1(dst) | RD(dst); + if (small_immed) { + emit(insn | IMMED | S13(imm), ctx); + } else { + unsigned int tmp = bpf2sparc[TMP_REG_1]; + + ctx->tmp_1_used = true; + + emit_set_const_sext(imm, tmp, ctx); + emit(insn | RS2(tmp), ctx); + } +} + +static void emit_alu3_K(unsigned int opcode, unsigned int src, unsigned int imm, + unsigned int dst, struct jit_ctx *ctx) +{ + bool small_immed = is_simm13(imm); + unsigned int insn = opcode; + + insn |= RS1(src) | RD(dst); + if (small_immed) { + emit(insn | IMMED | S13(imm), ctx); + } else { + unsigned int tmp = bpf2sparc[TMP_REG_1]; + + ctx->tmp_1_used = true; + + emit_set_const_sext(imm, tmp, ctx); + emit(insn | RS2(tmp), ctx); + } +} + +static void emit_loadimm32(s32 K, unsigned int dest, struct jit_ctx *ctx) +{ + if (K >= 0 && is_simm13(K)) { + /* or %g0, K, DEST */ + emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx); + } else { + emit_set_const(K, dest, ctx); + } +} + +static void emit_loadimm(s32 K, unsigned int dest, struct jit_ctx *ctx) +{ + if (is_simm13(K)) { + /* or %g0, K, DEST */ + emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx); + } else { + emit_set_const(K, dest, ctx); + } +} + +static void emit_loadimm_sext(s32 K, unsigned int dest, struct jit_ctx *ctx) +{ + if (is_simm13(K)) { + /* or %g0, K, DEST */ + emit(OR | IMMED | RS1(G0) | S13(K) | RD(dest), ctx); + } else { + emit_set_const_sext(K, dest, ctx); + } +} + +static void analyze_64bit_constant(u32 high_bits, u32 low_bits, + int *hbsp, int *lbsp, int *abbasp) +{ + int lowest_bit_set, highest_bit_set, all_bits_between_are_set; + int i; + + lowest_bit_set = highest_bit_set = -1; + i = 0; + do { + if ((lowest_bit_set == -1) && ((low_bits >> i) & 1)) + lowest_bit_set = i; + if ((highest_bit_set == -1) && ((high_bits >> (32 - i - 1)) & 1)) + highest_bit_set = (64 - i - 1); + } while (++i < 32 && (highest_bit_set == -1 || + lowest_bit_set == -1)); + if (i == 32) { + i = 0; + do { + if (lowest_bit_set == -1 && ((high_bits >> i) & 1)) + lowest_bit_set = i + 32; + if (highest_bit_set == -1 && + ((low_bits >> (32 - i - 1)) & 1)) + highest_bit_set = 32 - i - 1; + } while (++i < 32 && (highest_bit_set == -1 || + lowest_bit_set == -1)); + } + + all_bits_between_are_set = 1; + for (i = lowest_bit_set; i <= highest_bit_set; i++) { + if (i < 32) { + if ((low_bits & (1 << i)) != 0) + continue; + } else { + if ((high_bits & (1 << (i - 32))) != 0) + continue; + } + all_bits_between_are_set = 0; + break; + } + *hbsp = highest_bit_set; + *lbsp = lowest_bit_set; + *abbasp = all_bits_between_are_set; +} + +static unsigned long create_simple_focus_bits(unsigned long high_bits, + unsigned long low_bits, + int lowest_bit_set, int shift) +{ + long hi, lo; + + if (lowest_bit_set < 32) { + lo = (low_bits >> lowest_bit_set) << shift; + hi = ((high_bits << (32 - lowest_bit_set)) << shift); + } else { + lo = 0; + hi = ((high_bits >> (lowest_bit_set - 32)) << shift); + } + return hi | lo; +} + +static bool const64_is_2insns(unsigned long high_bits, + unsigned long low_bits) +{ + int highest_bit_set, lowest_bit_set, all_bits_between_are_set; + + if (high_bits == 0 || high_bits == 0xffffffff) + return true; + + analyze_64bit_constant(high_bits, low_bits, + &highest_bit_set, &lowest_bit_set, + &all_bits_between_are_set); + + if ((highest_bit_set == 63 || lowest_bit_set == 0) && + all_bits_between_are_set != 0) + return true; + + if (highest_bit_set - lowest_bit_set < 21) + return true; + + return false; +} + +static void sparc_emit_set_const64_quick2(unsigned long high_bits, + unsigned long low_imm, + unsigned int dest, + int shift_count, struct jit_ctx *ctx) +{ + emit_loadimm32(high_bits, dest, ctx); + + /* Now shift it up into place. */ + emit_alu_K(SLLX, dest, shift_count, ctx); + + /* If there is a low immediate part piece, finish up by + * putting that in as well. + */ + if (low_imm != 0) + emit(OR | IMMED | RS1(dest) | S13(low_imm) | RD(dest), ctx); +} + +static void emit_loadimm64(u64 K, unsigned int dest, struct jit_ctx *ctx) +{ + int all_bits_between_are_set, lowest_bit_set, highest_bit_set; + unsigned int tmp = bpf2sparc[TMP_REG_1]; + u32 low_bits = (K & 0xffffffff); + u32 high_bits = (K >> 32); + + /* These two tests also take care of all of the one + * instruction cases. + */ + if (high_bits == 0xffffffff && (low_bits & 0x80000000)) + return emit_loadimm_sext(K, dest, ctx); + if (high_bits == 0x00000000) + return emit_loadimm32(K, dest, ctx); + + analyze_64bit_constant(high_bits, low_bits, &highest_bit_set, + &lowest_bit_set, &all_bits_between_are_set); + + /* 1) mov -1, %reg + * sllx %reg, shift, %reg + * 2) mov -1, %reg + * srlx %reg, shift, %reg + * 3) mov some_small_const, %reg + * sllx %reg, shift, %reg + */ + if (((highest_bit_set == 63 || lowest_bit_set == 0) && + all_bits_between_are_set != 0) || + ((highest_bit_set - lowest_bit_set) < 12)) { + int shift = lowest_bit_set; + long the_const = -1; + + if ((highest_bit_set != 63 && lowest_bit_set != 0) || + all_bits_between_are_set == 0) { + the_const = + create_simple_focus_bits(high_bits, low_bits, + lowest_bit_set, 0); + } else if (lowest_bit_set == 0) + shift = -(63 - highest_bit_set); + + emit(OR | IMMED | RS1(G0) | S13(the_const) | RD(dest), ctx); + if (shift > 0) + emit_alu_K(SLLX, dest, shift, ctx); + else if (shift < 0) + emit_alu_K(SRLX, dest, -shift, ctx); + + return; + } + + /* Now a range of 22 or less bits set somewhere. + * 1) sethi %hi(focus_bits), %reg + * sllx %reg, shift, %reg + * 2) sethi %hi(focus_bits), %reg + * srlx %reg, shift, %reg + */ + if ((highest_bit_set - lowest_bit_set) < 21) { + unsigned long focus_bits = + create_simple_focus_bits(high_bits, low_bits, + lowest_bit_set, 10); + + emit(SETHI(focus_bits, dest), ctx); + + /* If lowest_bit_set == 10 then a sethi alone could + * have done it. + */ + if (lowest_bit_set < 10) + emit_alu_K(SRLX, dest, 10 - lowest_bit_set, ctx); + else if (lowest_bit_set > 10) + emit_alu_K(SLLX, dest, lowest_bit_set - 10, ctx); + return; + } + + /* Ok, now 3 instruction sequences. */ + if (low_bits == 0) { + emit_loadimm32(high_bits, dest, ctx); + emit_alu_K(SLLX, dest, 32, ctx); + return; + } + + /* We may be able to do something quick + * when the constant is negated, so try that. + */ + if (const64_is_2insns((~high_bits) & 0xffffffff, + (~low_bits) & 0xfffffc00)) { + /* NOTE: The trailing bits get XOR'd so we need the + * non-negated bits, not the negated ones. + */ + unsigned long trailing_bits = low_bits & 0x3ff; + + if ((((~high_bits) & 0xffffffff) == 0 && + ((~low_bits) & 0x80000000) == 0) || + (((~high_bits) & 0xffffffff) == 0xffffffff && + ((~low_bits) & 0x80000000) != 0)) { + unsigned long fast_int = (~low_bits & 0xffffffff); + + if ((is_sethi(fast_int) && + (~high_bits & 0xffffffff) == 0)) { + emit(SETHI(fast_int, dest), ctx); + } else if (is_simm13(fast_int)) { + emit(OR | IMMED | RS1(G0) | S13(fast_int) | RD(dest), ctx); + } else { + emit_loadimm64(fast_int, dest, ctx); + } + } else { + u64 n = ((~low_bits) & 0xfffffc00) | + (((unsigned long)((~high_bits) & 0xffffffff))<<32); + emit_loadimm64(n, dest, ctx); + } + + low_bits = -0x400 | trailing_bits; + + emit(XOR | IMMED | RS1(dest) | S13(low_bits) | RD(dest), ctx); + return; + } + + /* 1) sethi %hi(xxx), %reg + * or %reg, %lo(xxx), %reg + * sllx %reg, yyy, %reg + */ + if ((highest_bit_set - lowest_bit_set) < 32) { + unsigned long focus_bits = + create_simple_focus_bits(high_bits, low_bits, + lowest_bit_set, 0); + + /* So what we know is that the set bits straddle the + * middle of the 64-bit word. + */ + sparc_emit_set_const64_quick2(focus_bits, 0, dest, + lowest_bit_set, ctx); + return; + } + + /* 1) sethi %hi(high_bits), %reg + * or %reg, %lo(high_bits), %reg + * sllx %reg, 32, %reg + * or %reg, low_bits, %reg + */ + if (is_simm13(low_bits) && ((int)low_bits > 0)) { + sparc_emit_set_const64_quick2(high_bits, low_bits, + dest, 32, ctx); + return; + } + + /* Oh well, we tried... Do a full 64-bit decomposition. */ + ctx->tmp_1_used = true; + + emit_loadimm32(high_bits, tmp, ctx); + emit_loadimm32(low_bits, dest, ctx); + emit_alu_K(SLLX, tmp, 32, ctx); + emit(OR | RS1(dest) | RS2(tmp) | RD(dest), ctx); +} + +static void emit_branch(unsigned int br_opc, unsigned int from_idx, unsigned int to_idx, + struct jit_ctx *ctx) +{ + unsigned int off = to_idx - from_idx; + + if (br_opc & XCC) + emit(br_opc | WDISP19(off << 2), ctx); + else + emit(br_opc | WDISP22(off << 2), ctx); +} + +static void emit_cbcond(unsigned int cb_opc, unsigned int from_idx, unsigned int to_idx, + const u8 dst, const u8 src, struct jit_ctx *ctx) +{ + unsigned int off = to_idx - from_idx; + + emit(cb_opc | WDISP10(off << 2) | RS1(dst) | RS2(src), ctx); +} + +static void emit_cbcondi(unsigned int cb_opc, unsigned int from_idx, unsigned int to_idx, + const u8 dst, s32 imm, struct jit_ctx *ctx) +{ + unsigned int off = to_idx - from_idx; + + emit(cb_opc | IMMED | WDISP10(off << 2) | RS1(dst) | S5(imm), ctx); +} + +#define emit_read_y(REG, CTX) emit(RD_Y | RD(REG), CTX) +#define emit_write_y(REG, CTX) emit(WR_Y | IMMED | RS1(REG) | S13(0), CTX) + +#define emit_cmp(R1, R2, CTX) \ + emit(SUBCC | RS1(R1) | RS2(R2) | RD(G0), CTX) + +#define emit_cmpi(R1, IMM, CTX) \ + emit(SUBCC | IMMED | RS1(R1) | S13(IMM) | RD(G0), CTX) + +#define emit_btst(R1, R2, CTX) \ + emit(ANDCC | RS1(R1) | RS2(R2) | RD(G0), CTX) + +#define emit_btsti(R1, IMM, CTX) \ + emit(ANDCC | IMMED | RS1(R1) | S13(IMM) | RD(G0), CTX) + +static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src, + const s32 imm, bool is_imm, int branch_dst, + struct jit_ctx *ctx) +{ + bool use_cbcond = (sparc64_elf_hwcap & AV_SPARC_CBCOND) != 0; + const u8 tmp = bpf2sparc[TMP_REG_1]; + + branch_dst = ctx->offset[branch_dst]; + + if (!is_simm10(branch_dst - ctx->idx) || + BPF_OP(code) == BPF_JSET) + use_cbcond = false; + + if (is_imm) { + bool fits = true; + + if (use_cbcond) { + if (!is_simm5(imm)) + fits = false; + } else if (!is_simm13(imm)) { + fits = false; + } + if (!fits) { + ctx->tmp_1_used = true; + emit_loadimm_sext(imm, tmp, ctx); + src = tmp; + is_imm = false; + } + } + + if (!use_cbcond) { + u32 br_opcode; + + if (BPF_OP(code) == BPF_JSET) { + if (is_imm) + emit_btsti(dst, imm, ctx); + else + emit_btst(dst, src, ctx); + } else { + if (is_imm) + emit_cmpi(dst, imm, ctx); + else + emit_cmp(dst, src, ctx); + } + switch (BPF_OP(code)) { + case BPF_JEQ: + br_opcode = BE; + break; + case BPF_JGT: + br_opcode = BGU; + break; + case BPF_JGE: + br_opcode = BGEU; + break; + case BPF_JSET: + case BPF_JNE: + br_opcode = BNE; + break; + case BPF_JSGT: + br_opcode = BG; + break; + case BPF_JSGE: + br_opcode = BGE; + break; + default: + /* Make sure we dont leak kernel information to the + * user. + */ + return -EFAULT; + } + emit_branch(br_opcode, ctx->idx, branch_dst, ctx); + emit_nop(ctx); + } else { + u32 cbcond_opcode; + + switch (BPF_OP(code)) { + case BPF_JEQ: + cbcond_opcode = CBCONDE; + break; + case BPF_JGT: + cbcond_opcode = CBCONDGU; + break; + case BPF_JGE: + cbcond_opcode = CBCONDGEU; + break; + case BPF_JNE: + cbcond_opcode = CBCONDNE; + break; + case BPF_JSGT: + cbcond_opcode = CBCONDG; + break; + case BPF_JSGE: + cbcond_opcode = CBCONDGE; + break; + default: + /* Make sure we dont leak kernel information to the + * user. + */ + return -EFAULT; + } + cbcond_opcode |= CBCOND_OP; + if (is_imm) + emit_cbcondi(cbcond_opcode, ctx->idx, branch_dst, + dst, imm, ctx); + else + emit_cbcond(cbcond_opcode, ctx->idx, branch_dst, + dst, src, ctx); + } + return 0; +} + +static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb) +{ + const u8 r_headlen = bpf2sparc[SKB_HLEN_REG]; + const u8 r_data = bpf2sparc[SKB_DATA_REG]; + const u8 r_tmp = bpf2sparc[TMP_REG_1]; + unsigned int off; + + off = offsetof(struct sk_buff, len); + emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx); + + off = offsetof(struct sk_buff, data_len); + emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx); + + emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx); + + off = offsetof(struct sk_buff, data); + emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx); +} + +/* Just skip the save instruction and the ctx register move. */ +#define BPF_TAILCALL_PROLOGUE_SKIP 16 +#define BPF_TAILCALL_CNT_SP_OFF (STACK_BIAS + 128) + +static void build_prologue(struct jit_ctx *ctx) +{ + s32 stack_needed = BASE_STACKFRAME; + + if (ctx->saw_frame_pointer || ctx->saw_tail_call) { + struct bpf_prog *prog = ctx->prog; + u32 stack_depth; + + stack_depth = prog->aux->stack_depth; + stack_needed += round_up(stack_depth, 16); + } + + if (ctx->saw_tail_call) + stack_needed += 8; + + /* save %sp, -176, %sp */ + emit(SAVE | IMMED | RS1(SP) | S13(-stack_needed) | RD(SP), ctx); + + /* tail_call_cnt = 0 */ + if (ctx->saw_tail_call) { + u32 off = BPF_TAILCALL_CNT_SP_OFF; + + emit(ST32 | IMMED | RS1(SP) | S13(off) | RD(G0), ctx); + } else { + emit_nop(ctx); + } + if (ctx->saw_frame_pointer) { + const u8 vfp = bpf2sparc[BPF_REG_FP]; + + emit(ADD | IMMED | RS1(FP) | S13(STACK_BIAS) | RD(vfp), ctx); + } + + emit_reg_move(I0, O0, ctx); + /* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */ + + if (ctx->saw_ld_abs_ind) + load_skb_regs(ctx, bpf2sparc[BPF_REG_1]); +} + +static void build_epilogue(struct jit_ctx *ctx) +{ + ctx->epilogue_offset = ctx->idx; + + /* ret (jmpl %i7 + 8, %g0) */ + emit(JMPL | IMMED | RS1(I7) | S13(8) | RD(G0), ctx); + + /* restore %i5, %g0, %o0 */ + emit(RESTORE | RS1(bpf2sparc[BPF_REG_0]) | RS2(G0) | RD(O0), ctx); +} + +static void emit_tail_call(struct jit_ctx *ctx) +{ + const u8 bpf_array = bpf2sparc[BPF_REG_2]; + const u8 bpf_index = bpf2sparc[BPF_REG_3]; + const u8 tmp = bpf2sparc[TMP_REG_1]; + u32 off; + + ctx->saw_tail_call = true; + + off = offsetof(struct bpf_array, map.max_entries); + emit(LD32 | IMMED | RS1(bpf_array) | S13(off) | RD(tmp), ctx); + emit_cmp(bpf_index, tmp, ctx); +#define OFFSET1 17 + emit_branch(BGEU, ctx->idx, ctx->idx + OFFSET1, ctx); + emit_nop(ctx); + + off = BPF_TAILCALL_CNT_SP_OFF; + emit(LD32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx); + emit_cmpi(tmp, MAX_TAIL_CALL_CNT, ctx); +#define OFFSET2 13 + emit_branch(BGU, ctx->idx, ctx->idx + OFFSET2, ctx); + emit_nop(ctx); + + emit_alu_K(ADD, tmp, 1, ctx); + off = BPF_TAILCALL_CNT_SP_OFF; + emit(ST32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx); + + emit_alu3_K(SLL, bpf_index, 3, tmp, ctx); + emit_alu(ADD, bpf_array, tmp, ctx); + off = offsetof(struct bpf_array, ptrs); + emit(LD64 | IMMED | RS1(tmp) | S13(off) | RD(tmp), ctx); + + emit_cmpi(tmp, 0, ctx); +#define OFFSET3 5 + emit_branch(BE, ctx->idx, ctx->idx + OFFSET3, ctx); + emit_nop(ctx); + + off = offsetof(struct bpf_prog, bpf_func); + emit(LD64 | IMMED | RS1(tmp) | S13(off) | RD(tmp), ctx); + + off = BPF_TAILCALL_PROLOGUE_SKIP; + emit(JMPL | IMMED | RS1(tmp) | S13(off) | RD(G0), ctx); + emit_nop(ctx); +} + +static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) +{ + const u8 code = insn->code; + const u8 dst = bpf2sparc[insn->dst_reg]; + const u8 src = bpf2sparc[insn->src_reg]; + const int i = insn - ctx->prog->insnsi; + const s16 off = insn->off; + const s32 imm = insn->imm; + u32 *func; + + if (insn->src_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + + switch (code) { + /* dst = src */ + case BPF_ALU | BPF_MOV | BPF_X: + emit_alu3_K(SRL, src, 0, dst, ctx); + break; + case BPF_ALU64 | BPF_MOV | BPF_X: + emit_reg_move(src, dst, ctx); + break; + /* dst = dst OP src */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_X: + emit_alu(ADD, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_X: + emit_alu(SUB, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_X: + emit_alu(AND, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + emit_alu(OR, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + emit_alu(XOR, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_MUL | BPF_X: + emit_alu(MUL, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_MUL | BPF_X: + emit_alu(MULX, src, dst, ctx); + break; + case BPF_ALU | BPF_DIV | BPF_X: + emit_cmp(src, G0, ctx); + emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx); + emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx); + + emit_write_y(G0, ctx); + emit_alu(DIV, src, dst, ctx); + break; + + case BPF_ALU64 | BPF_DIV | BPF_X: + emit_cmp(src, G0, ctx); + emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx); + emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx); + + emit_alu(UDIVX, src, dst, ctx); + break; + + case BPF_ALU | BPF_MOD | BPF_X: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + + ctx->tmp_1_used = true; + + emit_cmp(src, G0, ctx); + emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx); + emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx); + + emit_write_y(G0, ctx); + emit_alu3(DIV, dst, src, tmp, ctx); + emit_alu3(MULX, tmp, src, tmp, ctx); + emit_alu3(SUB, dst, tmp, dst, ctx); + goto do_alu32_trunc; + } + case BPF_ALU64 | BPF_MOD | BPF_X: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + + ctx->tmp_1_used = true; + + emit_cmp(src, G0, ctx); + emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx); + emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx); + + emit_alu3(UDIVX, dst, src, tmp, ctx); + emit_alu3(MULX, tmp, src, tmp, ctx); + emit_alu3(SUB, dst, tmp, dst, ctx); + break; + } + case BPF_ALU | BPF_LSH | BPF_X: + emit_alu(SLL, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_LSH | BPF_X: + emit_alu(SLLX, src, dst, ctx); + break; + case BPF_ALU | BPF_RSH | BPF_X: + emit_alu(SRL, src, dst, ctx); + break; + case BPF_ALU64 | BPF_RSH | BPF_X: + emit_alu(SRLX, src, dst, ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_X: + emit_alu(SRA, src, dst, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_ARSH | BPF_X: + emit_alu(SRAX, src, dst, ctx); + break; + + /* dst = -dst */ + case BPF_ALU | BPF_NEG: + case BPF_ALU64 | BPF_NEG: + emit(SUB | RS1(0) | RS2(dst) | RD(dst), ctx); + goto do_alu32_trunc; + + case BPF_ALU | BPF_END | BPF_FROM_BE: + switch (imm) { + case 16: + emit_alu_K(SLL, dst, 16, ctx); + emit_alu_K(SRL, dst, 16, ctx); + break; + case 32: + emit_alu_K(SRL, dst, 0, ctx); + break; + case 64: + /* nop */ + break; + + } + break; + + /* dst = BSWAP##imm(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + const u8 tmp2 = bpf2sparc[TMP_REG_2]; + + ctx->tmp_1_used = true; + switch (imm) { + case 16: + emit_alu3_K(AND, dst, 0xff, tmp, ctx); + emit_alu3_K(SRL, dst, 8, dst, ctx); + emit_alu3_K(AND, dst, 0xff, dst, ctx); + emit_alu3_K(SLL, tmp, 8, tmp, ctx); + emit_alu(OR, tmp, dst, ctx); + break; + + case 32: + ctx->tmp_2_used = true; + emit_alu3_K(SRL, dst, 24, tmp, ctx); /* tmp = dst >> 24 */ + emit_alu3_K(SRL, dst, 16, tmp2, ctx); /* tmp2 = dst >> 16 */ + emit_alu3_K(AND, tmp2, 0xff, tmp2, ctx);/* tmp2 = tmp2 & 0xff */ + emit_alu3_K(SLL, tmp2, 8, tmp2, ctx); /* tmp2 = tmp2 << 8 */ + emit_alu(OR, tmp2, tmp, ctx); /* tmp = tmp | tmp2 */ + emit_alu3_K(SRL, dst, 8, tmp2, ctx); /* tmp2 = dst >> 8 */ + emit_alu3_K(AND, tmp2, 0xff, tmp2, ctx);/* tmp2 = tmp2 & 0xff */ + emit_alu3_K(SLL, tmp2, 16, tmp2, ctx); /* tmp2 = tmp2 << 16 */ + emit_alu(OR, tmp2, tmp, ctx); /* tmp = tmp | tmp2 */ + emit_alu3_K(AND, dst, 0xff, dst, ctx); /* dst = dst & 0xff */ + emit_alu3_K(SLL, dst, 24, dst, ctx); /* dst = dst << 24 */ + emit_alu(OR, tmp, dst, ctx); /* dst = dst | tmp */ + break; + + case 64: + emit_alu3_K(ADD, SP, STACK_BIAS + 128, tmp, ctx); + emit(ST64 | RS1(tmp) | RS2(G0) | RD(dst), ctx); + emit(LD64A | ASI(ASI_PL) | RS1(tmp) | RS2(G0) | RD(dst), ctx); + break; + } + break; + } + /* dst = imm */ + case BPF_ALU | BPF_MOV | BPF_K: + emit_loadimm32(imm, dst, ctx); + break; + case BPF_ALU64 | BPF_MOV | BPF_K: + emit_loadimm_sext(imm, dst, ctx); + break; + /* dst = dst OP imm */ + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_K: + emit_alu_K(ADD, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_K: + emit_alu_K(SUB, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + emit_alu_K(AND, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + emit_alu_K(OR, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + emit_alu_K(XOR, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU | BPF_MUL | BPF_K: + emit_alu_K(MUL, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_MUL | BPF_K: + emit_alu_K(MULX, dst, imm, ctx); + break; + case BPF_ALU | BPF_DIV | BPF_K: + if (imm == 0) + return -EINVAL; + + emit_write_y(G0, ctx); + emit_alu_K(DIV, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_DIV | BPF_K: + if (imm == 0) + return -EINVAL; + + emit_alu_K(UDIVX, dst, imm, ctx); + break; + case BPF_ALU64 | BPF_MOD | BPF_K: + case BPF_ALU | BPF_MOD | BPF_K: { + const u8 tmp = bpf2sparc[TMP_REG_2]; + unsigned int div; + + if (imm == 0) + return -EINVAL; + + div = (BPF_CLASS(code) == BPF_ALU64) ? UDIVX : DIV; + + ctx->tmp_2_used = true; + + if (BPF_CLASS(code) != BPF_ALU64) + emit_write_y(G0, ctx); + if (is_simm13(imm)) { + emit(div | IMMED | RS1(dst) | S13(imm) | RD(tmp), ctx); + emit(MULX | IMMED | RS1(tmp) | S13(imm) | RD(tmp), ctx); + emit(SUB | RS1(dst) | RS2(tmp) | RD(dst), ctx); + } else { + const u8 tmp1 = bpf2sparc[TMP_REG_1]; + + ctx->tmp_1_used = true; + + emit_set_const_sext(imm, tmp1, ctx); + emit(div | RS1(dst) | RS2(tmp1) | RD(tmp), ctx); + emit(MULX | RS1(tmp) | RS2(tmp1) | RD(tmp), ctx); + emit(SUB | RS1(dst) | RS2(tmp) | RD(dst), ctx); + } + goto do_alu32_trunc; + } + case BPF_ALU | BPF_LSH | BPF_K: + emit_alu_K(SLL, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_LSH | BPF_K: + emit_alu_K(SLLX, dst, imm, ctx); + break; + case BPF_ALU | BPF_RSH | BPF_K: + emit_alu_K(SRL, dst, imm, ctx); + break; + case BPF_ALU64 | BPF_RSH | BPF_K: + emit_alu_K(SRLX, dst, imm, ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_K: + emit_alu_K(SRA, dst, imm, ctx); + goto do_alu32_trunc; + case BPF_ALU64 | BPF_ARSH | BPF_K: + emit_alu_K(SRAX, dst, imm, ctx); + break; + + do_alu32_trunc: + if (BPF_CLASS(code) == BPF_ALU) + emit_alu_K(SRL, dst, 0, ctx); + break; + + /* JUMP off */ + case BPF_JMP | BPF_JA: + emit_branch(BA, ctx->idx, ctx->offset[i + off], ctx); + emit_nop(ctx); + break; + /* IF (dst COND src) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSET | BPF_X: { + int err; + + err = emit_compare_and_branch(code, dst, src, 0, false, i + off, ctx); + if (err) + return err; + break; + } + /* IF (dst COND imm) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSET | BPF_K: { + int err; + + err = emit_compare_and_branch(code, dst, 0, imm, true, i + off, ctx); + if (err) + return err; + break; + } + + /* function call */ + case BPF_JMP | BPF_CALL: + { + u8 *func = ((u8 *)__bpf_call_base) + imm; + + ctx->saw_call = true; + + emit_call((u32 *)func, ctx); + emit_nop(ctx); + + emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx); + + if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind) + load_skb_regs(ctx, bpf2sparc[BPF_REG_6]); + break; + } + + /* tail call */ + case BPF_JMP | BPF_TAIL_CALL: + emit_tail_call(ctx); + break; + + /* function return */ + case BPF_JMP | BPF_EXIT: + /* Optimization: when last instruction is EXIT, + simply fallthrough to epilogue. */ + if (i == ctx->prog->len - 1) + break; + emit_branch(BA, ctx->idx, ctx->epilogue_offset, ctx); + emit_nop(ctx); + break; + + /* dst = imm64 */ + case BPF_LD | BPF_IMM | BPF_DW: + { + const struct bpf_insn insn1 = insn[1]; + u64 imm64; + + imm64 = (u64)insn1.imm << 32 | (u32)imm; + emit_loadimm64(imm64, dst, ctx); + + return 1; + } + + /* LDX: dst = *(size *)(src + off) */ + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_DW: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + u32 opcode = 0, rs2; + + ctx->tmp_1_used = true; + switch (BPF_SIZE(code)) { + case BPF_W: + opcode = LD32; + break; + case BPF_H: + opcode = LD16; + break; + case BPF_B: + opcode = LD8; + break; + case BPF_DW: + opcode = LD64; + break; + } + + if (is_simm13(off)) { + opcode |= IMMED; + rs2 = S13(off); + } else { + emit_loadimm(off, tmp, ctx); + rs2 = RS2(tmp); + } + emit(opcode | RS1(src) | rs2 | RD(dst), ctx); + break; + } + /* ST: *(size *)(dst + off) = imm */ + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_DW: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + const u8 tmp2 = bpf2sparc[TMP_REG_2]; + u32 opcode = 0, rs2; + + ctx->tmp_2_used = true; + emit_loadimm(imm, tmp2, ctx); + + switch (BPF_SIZE(code)) { + case BPF_W: + opcode = ST32; + break; + case BPF_H: + opcode = ST16; + break; + case BPF_B: + opcode = ST8; + break; + case BPF_DW: + opcode = ST64; + break; + } + + if (is_simm13(off)) { + opcode |= IMMED; + rs2 = S13(off); + } else { + ctx->tmp_1_used = true; + emit_loadimm(off, tmp, ctx); + rs2 = RS2(tmp); + } + emit(opcode | RS1(dst) | rs2 | RD(tmp2), ctx); + break; + } + + /* STX: *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_DW: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + u32 opcode = 0, rs2; + + switch (BPF_SIZE(code)) { + case BPF_W: + opcode = ST32; + break; + case BPF_H: + opcode = ST16; + break; + case BPF_B: + opcode = ST8; + break; + case BPF_DW: + opcode = ST64; + break; + } + if (is_simm13(off)) { + opcode |= IMMED; + rs2 = S13(off); + } else { + ctx->tmp_1_used = true; + emit_loadimm(off, tmp, ctx); + rs2 = RS2(tmp); + } + emit(opcode | RS1(dst) | rs2 | RD(src), ctx); + break; + } + + /* STX XADD: lock *(u32 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_W: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + const u8 tmp2 = bpf2sparc[TMP_REG_2]; + const u8 tmp3 = bpf2sparc[TMP_REG_3]; + + ctx->tmp_1_used = true; + ctx->tmp_2_used = true; + ctx->tmp_3_used = true; + emit_loadimm(off, tmp, ctx); + emit_alu3(ADD, dst, tmp, tmp, ctx); + + emit(LD32 | RS1(tmp) | RS2(G0) | RD(tmp2), ctx); + emit_alu3(ADD, tmp2, src, tmp3, ctx); + emit(CAS | ASI(ASI_P) | RS1(tmp) | RS2(tmp2) | RD(tmp3), ctx); + emit_cmp(tmp2, tmp3, ctx); + emit_branch(BNE, 4, 0, ctx); + emit_nop(ctx); + break; + } + /* STX XADD: lock *(u64 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_DW: { + const u8 tmp = bpf2sparc[TMP_REG_1]; + const u8 tmp2 = bpf2sparc[TMP_REG_2]; + const u8 tmp3 = bpf2sparc[TMP_REG_3]; + + ctx->tmp_1_used = true; + ctx->tmp_2_used = true; + ctx->tmp_3_used = true; + emit_loadimm(off, tmp, ctx); + emit_alu3(ADD, dst, tmp, tmp, ctx); + + emit(LD64 | RS1(tmp) | RS2(G0) | RD(tmp2), ctx); + emit_alu3(ADD, tmp2, src, tmp3, ctx); + emit(CASX | ASI(ASI_P) | RS1(tmp) | RS2(tmp2) | RD(tmp3), ctx); + emit_cmp(tmp2, tmp3, ctx); + emit_branch(BNE, 4, 0, ctx); + emit_nop(ctx); + break; + } +#define CHOOSE_LOAD_FUNC(K, func) \ + ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) + + /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ + case BPF_LD | BPF_ABS | BPF_W: + func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word); + goto common_load; + case BPF_LD | BPF_ABS | BPF_H: + func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half); + goto common_load; + case BPF_LD | BPF_ABS | BPF_B: + func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte); + goto common_load; + /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */ + case BPF_LD | BPF_IND | BPF_W: + func = bpf_jit_load_word; + goto common_load; + case BPF_LD | BPF_IND | BPF_H: + func = bpf_jit_load_half; + goto common_load; + + case BPF_LD | BPF_IND | BPF_B: + func = bpf_jit_load_byte; + common_load: + ctx->saw_ld_abs_ind = true; + + emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx); + emit_loadimm(imm, O1, ctx); + + if (BPF_MODE(code) == BPF_IND) + emit_alu(ADD, src, O1, ctx); + + emit_call(func, ctx); + emit_alu_K(SRA, O1, 0, ctx); + + emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx); + break; + + default: + pr_err_once("unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +static int build_body(struct jit_ctx *ctx) +{ + const struct bpf_prog *prog = ctx->prog; + int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + int ret; + + ret = build_insn(insn, ctx); + + if (ret > 0) { + i++; + ctx->offset[i] = ctx->idx; + continue; + } + ctx->offset[i] = ctx->idx; + if (ret) + return ret; + } + return 0; +} + +static void jit_fill_hole(void *area, unsigned int size) +{ + u32 *ptr; + /* We are guaranteed to have aligned memory. */ + for (ptr = area; size >= sizeof(u32); size -= sizeof(u32)) + *ptr++ = 0x91d02005; /* ta 5 */ +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + struct bpf_prog *tmp, *orig_prog = prog; + struct bpf_binary_header *header; + bool tmp_blinded = false; + struct jit_ctx ctx; + u32 image_size; + u8 *image_ptr; + int pass; + + if (!bpf_jit_enable) + return orig_prog; + + tmp = bpf_jit_blind_constants(prog); + /* If blinding was requested and we failed during blinding, + * we must fall back to the interpreter. + */ + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + memset(&ctx, 0, sizeof(ctx)); + ctx.prog = prog; + + ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL); + if (ctx.offset == NULL) { + prog = orig_prog; + goto out; + } + + /* Fake pass to detect features used, and get an accurate assessment + * of what the final image size will be. + */ + if (build_body(&ctx)) { + prog = orig_prog; + goto out_off; + } + build_prologue(&ctx); + build_epilogue(&ctx); + + /* Now we know the actual image size. */ + image_size = sizeof(u32) * ctx.idx; + header = bpf_jit_binary_alloc(image_size, &image_ptr, + sizeof(u32), jit_fill_hole); + if (header == NULL) { + prog = orig_prog; + goto out_off; + } + + ctx.image = (u32 *)image_ptr; + + for (pass = 1; pass < 3; pass++) { + ctx.idx = 0; + + build_prologue(&ctx); + + if (build_body(&ctx)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } + + build_epilogue(&ctx); + + if (bpf_jit_enable > 1) + pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass, + image_size - (ctx.idx * 4), + ctx.tmp_1_used ? '1' : ' ', + ctx.tmp_2_used ? '2' : ' ', + ctx.tmp_3_used ? '3' : ' ', + ctx.saw_ld_abs_ind ? 'L' : ' ', + ctx.saw_frame_pointer ? 'F' : ' ', + ctx.saw_call ? 'C' : ' ', + ctx.saw_tail_call ? 'T' : ' '); + } + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, image_size, pass, ctx.image); + + bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE)); + + bpf_jit_binary_lock_ro(header); + + prog->bpf_func = (void *)ctx.image; + prog->jited = 1; + prog->jited_len = image_size; + +out_off: + kfree(ctx.offset); +out: + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + return prog; +} |