diff options
Diffstat (limited to 'arch/s390/include/asm')
| -rw-r--r-- | arch/s390/include/asm/Kbuild | 1 | ||||
| -rw-r--r-- | arch/s390/include/asm/atomic.h | 41 | ||||
| -rw-r--r-- | arch/s390/include/asm/barrier.h | 4 | ||||
| -rw-r--r-- | arch/s390/include/asm/cpufeature.h | 29 | ||||
| -rw-r--r-- | arch/s390/include/asm/ctl_reg.h | 2 | ||||
| -rw-r--r-- | arch/s390/include/asm/dma-mapping.h | 55 | ||||
| -rw-r--r-- | arch/s390/include/asm/etr.h | 3 | ||||
| -rw-r--r-- | arch/s390/include/asm/fpu-internal.h | 110 | ||||
| -rw-r--r-- | arch/s390/include/asm/io.h | 2 | ||||
| -rw-r--r-- | arch/s390/include/asm/jump_label.h | 19 | ||||
| -rw-r--r-- | arch/s390/include/asm/kvm_host.h | 12 | ||||
| -rw-r--r-- | arch/s390/include/asm/linkage.h | 22 | ||||
| -rw-r--r-- | arch/s390/include/asm/mmzone.h | 16 | ||||
| -rw-r--r-- | arch/s390/include/asm/numa.h | 35 | ||||
| -rw-r--r-- | arch/s390/include/asm/pci.h | 22 | ||||
| -rw-r--r-- | arch/s390/include/asm/pgtable.h | 13 | ||||
| -rw-r--r-- | arch/s390/include/asm/processor.h | 36 | ||||
| -rw-r--r-- | arch/s390/include/asm/sclp.h | 2 | ||||
| -rw-r--r-- | arch/s390/include/asm/switch_to.h | 135 | ||||
| -rw-r--r-- | arch/s390/include/asm/topology.h | 39 | ||||
| -rw-r--r-- | arch/s390/include/asm/unistd.h | 12 | ||||
| -rw-r--r-- | arch/s390/include/asm/vx-insn.h | 480 |
22 files changed, 843 insertions, 247 deletions
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 5ad26dd94..9043d2e1e 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -6,3 +6,4 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h generic-y += trace_clock.h +generic-y += word-at-a-time.h diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index adbe3802e..117fa5c92 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -27,6 +27,7 @@ #define __ATOMIC_OR "lao" #define __ATOMIC_AND "lan" #define __ATOMIC_ADD "laa" +#define __ATOMIC_XOR "lax" #define __ATOMIC_BARRIER "bcr 14,0\n" #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \ @@ -49,6 +50,7 @@ #define __ATOMIC_OR "or" #define __ATOMIC_AND "nr" #define __ATOMIC_ADD "ar" +#define __ATOMIC_XOR "xr" #define __ATOMIC_BARRIER "\n" #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \ @@ -118,15 +120,17 @@ static inline void atomic_add(int i, atomic_t *v) #define atomic_dec_return(_v) atomic_sub_return(1, _v) #define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) -static inline void atomic_clear_mask(unsigned int mask, atomic_t *v) -{ - __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER); +#define ATOMIC_OP(op, OP) \ +static inline void atomic_##op(int i, atomic_t *v) \ +{ \ + __ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER); \ } -static inline void atomic_set_mask(unsigned int mask, atomic_t *v) -{ - __ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER); -} +ATOMIC_OP(and, AND) +ATOMIC_OP(or, OR) +ATOMIC_OP(xor, XOR) + +#undef ATOMIC_OP #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) @@ -167,6 +171,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) #define __ATOMIC64_OR "laog" #define __ATOMIC64_AND "lang" #define __ATOMIC64_ADD "laag" +#define __ATOMIC64_XOR "laxg" #define __ATOMIC64_BARRIER "bcr 14,0\n" #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \ @@ -189,6 +194,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) #define __ATOMIC64_OR "ogr" #define __ATOMIC64_AND "ngr" #define __ATOMIC64_ADD "agr" +#define __ATOMIC64_XOR "xgr" #define __ATOMIC64_BARRIER "\n" #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \ @@ -247,16 +253,6 @@ static inline void atomic64_add(long long i, atomic64_t *v) __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER); } -static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v) -{ - __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER); -} - -static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v) -{ - __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER); -} - #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) static inline long long atomic64_cmpxchg(atomic64_t *v, @@ -270,6 +266,17 @@ static inline long long atomic64_cmpxchg(atomic64_t *v, return old; } +#define ATOMIC64_OP(op, OP) \ +static inline void atomic64_##op(long i, atomic64_t *v) \ +{ \ + __ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER); \ +} + +ATOMIC64_OP(and, AND) +ATOMIC64_OP(or, OR) +ATOMIC64_OP(xor, XOR) + +#undef ATOMIC64_OP #undef __ATOMIC64_LOOP static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u) diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index e6f8615a1..d48fe0162 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -42,12 +42,12 @@ do { \ compiletime_assert_atomic_type(*p); \ barrier(); \ - ACCESS_ONCE(*p) = (v); \ + WRITE_ONCE(*p, v); \ } while (0) #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ barrier(); \ ___p1; \ diff --git a/arch/s390/include/asm/cpufeature.h b/arch/s390/include/asm/cpufeature.h new file mode 100644 index 000000000..fa7e69b7c --- /dev/null +++ b/arch/s390/include/asm/cpufeature.h @@ -0,0 +1,29 @@ +/* + * Module interface for CPU features + * + * Copyright IBM Corp. 2015 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + */ + +#ifndef __ASM_S390_CPUFEATURE_H +#define __ASM_S390_CPUFEATURE_H + +#include <asm/elf.h> + +/* Hardware features on Linux on z Systems are indicated by facility bits that + * are mapped to the so-called machine flags. Particular machine flags are + * then used to define ELF hardware capabilities; most notably hardware flags + * that are essential for user space / glibc. + * + * Restrict the set of exposed CPU features to ELF hardware capabilities for + * now. Additional machine flags can be indicated by values larger than + * MAX_ELF_HWCAP_FEATURES. + */ +#define MAX_ELF_HWCAP_FEATURES (8 * sizeof(elf_hwcap)) +#define MAX_CPU_FEATURES MAX_ELF_HWCAP_FEATURES + +#define cpu_feature(feat) ilog2(HWCAP_S390_ ## feat) + +int cpu_have_feature(unsigned int nr); + +#endif /* __ASM_S390_CPUFEATURE_H */ diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index d7697ab80..17a373576 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -46,6 +46,8 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit) __ctl_load(reg, cr, cr); } +void __ctl_set_vx(void); + void smp_ctl_set_bit(int cr, int bit); void smp_ctl_clear_bit(int cr, int bit); diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h index 9d395961e..b3fd54d93 100644 --- a/arch/s390/include/asm/dma-mapping.h +++ b/arch/s390/include/asm/dma-mapping.h @@ -18,27 +18,13 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) return &s390_dma_ops; } -extern int dma_set_mask(struct device *dev, u64 mask); - static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { } -#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) -#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) - #include <asm-generic/dma-mapping-common.h> -static inline int dma_supported(struct device *dev, u64 mask) -{ - struct dma_map_ops *dma_ops = get_dma_ops(dev); - - if (dma_ops->dma_supported == NULL) - return 1; - return dma_ops->dma_supported(dev, mask); -} - static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { if (!dev->dma_mask) @@ -46,45 +32,4 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) return addr + size - 1 <= *dev->dma_mask; } -static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - struct dma_map_ops *dma_ops = get_dma_ops(dev); - - debug_dma_mapping_error(dev, dma_addr); - if (dma_ops->mapping_error) - return dma_ops->mapping_error(dev, dma_addr); - return dma_addr == DMA_ERROR_CODE; -} - -#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL) - -static inline void *dma_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - void *cpu_addr; - - BUG_ON(!ops); - - cpu_addr = ops->alloc(dev, size, dma_handle, flags, attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr); - - return cpu_addr; -} - -#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL) - -static inline void dma_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!ops); - - debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); - ops->free(dev, size, cpu_addr, dma_handle, attrs); -} - #endif /* _ASM_S390_DMA_MAPPING_H */ diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h index 629b79a93..f7e5c3668 100644 --- a/arch/s390/include/asm/etr.h +++ b/arch/s390/include/asm/etr.h @@ -214,6 +214,9 @@ static inline int etr_ptff(void *ptff_block, unsigned int func) void etr_switch_to_local(void); void etr_sync_check(void); +/* notifier for syncs */ +extern struct atomic_notifier_head s390_epoch_delta_notifier; + /* STP interruption parameter */ struct stp_irq_parm { unsigned int _pad0 : 14; diff --git a/arch/s390/include/asm/fpu-internal.h b/arch/s390/include/asm/fpu-internal.h new file mode 100644 index 000000000..55dc2c0fb --- /dev/null +++ b/arch/s390/include/asm/fpu-internal.h @@ -0,0 +1,110 @@ +/* + * General floating pointer and vector register helpers + * + * Copyright IBM Corp. 2015 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + */ + +#ifndef _ASM_S390_FPU_INTERNAL_H +#define _ASM_S390_FPU_INTERNAL_H + +#define FPU_USE_VX 1 /* Vector extension is active */ + +#ifndef __ASSEMBLY__ + +#include <linux/errno.h> +#include <linux/string.h> +#include <asm/linkage.h> +#include <asm/ctl_reg.h> +#include <asm/sigcontext.h> + +struct fpu { + __u32 fpc; /* Floating-point control */ + __u32 flags; + union { + void *regs; + freg_t *fprs; /* Floating-point register save area */ + __vector128 *vxrs; /* Vector register save area */ + }; +}; + +void save_fpu_regs(void); + +#define is_vx_fpu(fpu) (!!((fpu)->flags & FPU_USE_VX)) +#define is_vx_task(tsk) (!!((tsk)->thread.fpu.flags & FPU_USE_VX)) + +/* VX array structure for address operand constraints in inline assemblies */ +struct vx_array { __vector128 _[__NUM_VXRS]; }; + +static inline int test_fp_ctl(u32 fpc) +{ + u32 orig_fpc; + int rc; + + asm volatile( + " efpc %1\n" + " sfpc %2\n" + "0: sfpc %1\n" + " la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc), "=d" (orig_fpc) + : "d" (fpc), "0" (-EINVAL)); + return rc; +} + +static inline void save_vx_regs_safe(__vector128 *vxrs) +{ + unsigned long cr0, flags; + + flags = arch_local_irq_save(); + __ctl_store(cr0, 0, 0); + __ctl_set_bit(0, 17); + __ctl_set_bit(0, 18); + asm volatile( + " la 1,%0\n" + " .word 0xe70f,0x1000,0x003e\n" /* vstm 0,15,0(1) */ + " .word 0xe70f,0x1100,0x0c3e\n" /* vstm 16,31,256(1) */ + : "=Q" (*(struct vx_array *) vxrs) : : "1"); + __ctl_load(cr0, 0, 0); + arch_local_irq_restore(flags); +} + +static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs) +{ + int i; + + for (i = 0; i < __NUM_FPRS; i++) + fprs[i] = *(freg_t *)(vxrs + i); +} + +static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) +{ + int i; + + for (i = 0; i < __NUM_FPRS; i++) + *(freg_t *)(vxrs + i) = fprs[i]; +} + +static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) +{ + fpregs->pad = 0; + if (is_vx_fpu(fpu)) + convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); + else + memcpy((freg_t *)&fpregs->fprs, fpu->fprs, + sizeof(fpregs->fprs)); +} + +static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) +{ + if (is_vx_fpu(fpu)) + convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); + else + memcpy(fpu->fprs, (freg_t *)&fpregs->fprs, + sizeof(fpregs->fprs)); +} + +#endif + +#endif /* _ASM_S390_FPU_INTERNAL_H */ diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index cb5fdf3a7..437e9af96 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -57,6 +57,8 @@ static inline void ioport_unmap(void __iomem *p) */ #define pci_iomap pci_iomap #define pci_iounmap pci_iounmap +#define pci_iomap_wc pci_iomap +#define pci_iomap_wc_range pci_iomap_range #define memcpy_fromio(dst, src, count) zpci_memcpy_fromio(dst, src, count) #define memcpy_toio(dst, src, count) zpci_memcpy_toio(dst, src, count) diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 69972b795..7f9fd5e3f 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -12,14 +12,29 @@ * We use a brcl 0,2 instruction for jump labels at compile time so it * can be easily distinguished from a hotpatch generated instruction. */ -static __always_inline bool arch_static_branch(struct static_key *key) +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n" ".pushsection __jump_table, \"aw\"\n" ".balign 8\n" ".quad 0b, %l[label], %0\n" ".popsection\n" - : : "X" (key) : : label); + : : "X" (&((char *)key)[branch]) : : label); + + return false; +label: + return true; +} + +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) +{ + asm_volatile_goto("0: brcl 15, %l[label]\n" + ".pushsection __jump_table, \"aw\"\n" + ".balign 8\n" + ".quad 0b, %l[label], %0\n" + ".popsection\n" + : : "X" (&((char *)key)[branch]) : : label); + return false; label: return true; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 3024acbe1..8ced42609 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -22,6 +22,7 @@ #include <linux/kvm.h> #include <asm/debug.h> #include <asm/cpu.h> +#include <asm/fpu-internal.h> #include <asm/isc.h> #define KVM_MAX_VCPUS 64 @@ -34,6 +35,7 @@ */ #define KVM_NR_IRQCHIPS 1 #define KVM_IRQCHIP_NUM_PINS 4096 +#define KVM_HALT_POLL_NS_DEFAULT 0 #define SIGP_CTRL_C 0x80 #define SIGP_CTRL_SCN_MASK 0x3f @@ -209,6 +211,7 @@ struct kvm_vcpu_stat { u32 exit_validity; u32 exit_instruction; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 instruction_lctl; u32 instruction_lctlg; @@ -258,6 +261,9 @@ struct kvm_vcpu_stat { u32 diagnose_10; u32 diagnose_44; u32 diagnose_9c; + u32 diagnose_258; + u32 diagnose_308; + u32 diagnose_500; }; #define PGM_OPERATION 0x01 @@ -498,10 +504,9 @@ struct kvm_guestdbg_info_arch { struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; - s390_fp_regs host_fpregs; unsigned int host_acrs[NUM_ACRS]; - s390_fp_regs guest_fpregs; - struct kvm_s390_vregs *host_vregs; + struct fpu host_fpregs; + struct fpu guest_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; @@ -630,7 +635,6 @@ extern char sie_exit; static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_check_processor_compat(void *rtn) {} -static inline void kvm_arch_exit(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h index fc8a82847..27da78cf4 100644 --- a/arch/s390/include/asm/linkage.h +++ b/arch/s390/include/asm/linkage.h @@ -6,4 +6,26 @@ #define __ALIGN .align 4, 0x07 #define __ALIGN_STR __stringify(__ALIGN) +#ifndef __ASSEMBLY__ + +/* + * Helper macro for exception table entries + */ +#define EX_TABLE(_fault, _target) \ + ".section __ex_table,\"a\"\n" \ + ".align 4\n" \ + ".long (" #_fault ") - .\n" \ + ".long (" #_target ") - .\n" \ + ".previous\n" + +#else /* __ASSEMBLY__ */ + +#define EX_TABLE(_fault, _target) \ + .section __ex_table,"a" ; \ + .align 4 ; \ + .long (_fault) - . ; \ + .long (_target) - . ; \ + .previous + +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/s390/include/asm/mmzone.h b/arch/s390/include/asm/mmzone.h new file mode 100644 index 000000000..a9e834e60 --- /dev/null +++ b/arch/s390/include/asm/mmzone.h @@ -0,0 +1,16 @@ +/* + * NUMA support for s390 + * + * Copyright IBM Corp. 2015 + */ + +#ifndef _ASM_S390_MMZONE_H +#define _ASM_S390_MMZONE_H + +#ifdef CONFIG_NUMA + +extern struct pglist_data *node_data[]; +#define NODE_DATA(nid) (node_data[nid]) + +#endif /* CONFIG_NUMA */ +#endif /* _ASM_S390_MMZONE_H */ diff --git a/arch/s390/include/asm/numa.h b/arch/s390/include/asm/numa.h new file mode 100644 index 000000000..dc19ee0c9 --- /dev/null +++ b/arch/s390/include/asm/numa.h @@ -0,0 +1,35 @@ +/* + * NUMA support for s390 + * + * Declare the NUMA core code structures and functions. + * + * Copyright IBM Corp. 2015 + */ + +#ifndef _ASM_S390_NUMA_H +#define _ASM_S390_NUMA_H + +#ifdef CONFIG_NUMA + +#include <linux/numa.h> +#include <linux/cpumask.h> + +void numa_setup(void); +int numa_pfn_to_nid(unsigned long pfn); +int __node_distance(int a, int b); +void numa_update_cpu_topology(void); + +extern cpumask_t node_to_cpumask_map[MAX_NUMNODES]; +extern int numa_debug_enabled; + +#else + +static inline void numa_setup(void) { } +static inline void numa_update_cpu_topology(void) { } +static inline int numa_pfn_to_nid(unsigned long pfn) +{ + return 0; +} + +#endif /* CONFIG_NUMA */ +#endif /* _ASM_S390_NUMA_H */ diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index a648338c4..34d960353 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -170,7 +170,11 @@ static inline void zpci_exit_slot(struct zpci_dev *zdev) {} #endif /* CONFIG_HOTPLUG_PCI_S390 */ /* Helpers */ -struct zpci_dev *get_zdev(struct pci_dev *); +static inline struct zpci_dev *to_zpci(struct pci_dev *pdev) +{ + return pdev->sysdata; +} + struct zpci_dev *get_zdev_by_fid(u32); /* DMA */ @@ -188,4 +192,20 @@ void zpci_debug_init_device(struct zpci_dev *); void zpci_debug_exit_device(struct zpci_dev *); void zpci_debug_info(struct zpci_dev *, struct seq_file *); +#ifdef CONFIG_NUMA + +/* Returns the node based on PCI bus */ +static inline int __pcibus_to_node(const struct pci_bus *bus) +{ + return NUMA_NO_NODE; +} + +static inline const struct cpumask * +cpumask_of_pcibus(const struct pci_bus *bus) +{ + return cpu_online_mask; +} + +#endif /* CONFIG_NUMA */ + #endif diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index f66d82798..bdb2f5112 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -576,6 +576,19 @@ static inline int pte_same(pte_t a, pte_t b) return pte_val(a) == pte_val(b); } +#ifdef CONFIG_NUMA_BALANCING +static inline int pte_protnone(pte_t pte) +{ + return pte_present(pte) && !(pte_val(pte) & _PAGE_READ); +} + +static inline int pmd_protnone(pmd_t pmd) +{ + /* pmd_large(pmd) implies pmd_present(pmd) */ + return pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_READ); +} +#endif + static inline pgste_t pgste_get_lock(pte_t *ptep) { unsigned long new = 0; diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index dedb62185..085fb0d3c 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -14,10 +14,12 @@ #define CIF_MCCK_PENDING 0 /* machine check handling is pending */ #define CIF_ASCE 1 /* user asce needs fixup / uaccess */ #define CIF_NOHZ_DELAY 2 /* delay HZ disable for a tick */ +#define CIF_FPU 3 /* restore vector registers */ #define _CIF_MCCK_PENDING (1<<CIF_MCCK_PENDING) #define _CIF_ASCE (1<<CIF_ASCE) #define _CIF_NOHZ_DELAY (1<<CIF_NOHZ_DELAY) +#define _CIF_FPU (1<<CIF_FPU) #ifndef __ASSEMBLY__ @@ -28,6 +30,7 @@ #include <asm/ptrace.h> #include <asm/setup.h> #include <asm/runtime_instr.h> +#include <asm/fpu-internal.h> static inline void set_cpu_flag(int flag) { @@ -85,7 +88,7 @@ typedef struct { * Thread structure */ struct thread_struct { - s390_fp_regs fp_regs; + struct fpu fpu; /* FP and VX register save area */ unsigned int acrs[NUM_ACRS]; unsigned long ksp; /* kernel stack pointer */ mm_segment_t mm_segment; @@ -101,7 +104,6 @@ struct thread_struct { struct runtime_instr_cb *ri_cb; int ri_signum; unsigned char trap_tdb[256]; /* Transaction abort diagnose block */ - __vector128 *vxrs; /* Vector register save area */ }; /* Flag to disable transactions. */ @@ -231,6 +233,17 @@ static inline void __load_psw_mask (unsigned long mask) } /* + * Extract current PSW mask + */ +static inline unsigned long __extract_psw(void) +{ + unsigned int reg1, reg2; + + asm volatile("epsw %0,%1" : "=d" (reg1), "=a" (reg2)); + return (((unsigned long) reg1) << 32) | ((unsigned long) reg2); +} + +/* * Rewind PSW instruction address by specified number of bytes. */ static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc) @@ -336,25 +349,6 @@ extern void memcpy_absolute(void *, void *, size_t); memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ } -/* - * Helper macro for exception table entries - */ -#define EX_TABLE(_fault, _target) \ - ".section __ex_table,\"a\"\n" \ - ".align 4\n" \ - ".long (" #_fault ") - .\n" \ - ".long (" #_target ") - .\n" \ - ".previous\n" - -#else /* __ASSEMBLY__ */ - -#define EX_TABLE(_fault, _target) \ - .section __ex_table,"a" ; \ - .align 4 ; \ - .long (_fault) - . ; \ - .long (_target) - . ; \ - .previous - #endif /* __ASSEMBLY__ */ #endif /* __ASM_S390_PROCESSOR_H */ diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index f6ff06077..821dde5f4 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -79,6 +79,6 @@ int sclp_pci_configure(u32 fid); int sclp_pci_deconfigure(u32 fid); int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode); void sclp_early_detect(void); -long _sclp_print_early(const char *); +int _sclp_print_early(const char *); #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index d62e7a696..dcadfde32 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -8,139 +8,12 @@ #define __ASM_SWITCH_TO_H #include <linux/thread_info.h> +#include <asm/fpu-internal.h> #include <asm/ptrace.h> extern struct task_struct *__switch_to(void *, void *); extern void update_cr_regs(struct task_struct *task); -static inline int test_fp_ctl(u32 fpc) -{ - u32 orig_fpc; - int rc; - - asm volatile( - " efpc %1\n" - " sfpc %2\n" - "0: sfpc %1\n" - " la %0,0\n" - "1:\n" - EX_TABLE(0b,1b) - : "=d" (rc), "=d" (orig_fpc) - : "d" (fpc), "0" (-EINVAL)); - return rc; -} - -static inline void save_fp_ctl(u32 *fpc) -{ - asm volatile( - " stfpc %0\n" - : "+Q" (*fpc)); -} - -static inline int restore_fp_ctl(u32 *fpc) -{ - int rc; - - asm volatile( - " lfpc %1\n" - "0: la %0,0\n" - "1:\n" - EX_TABLE(0b,1b) - : "=d" (rc) : "Q" (*fpc), "0" (-EINVAL)); - return rc; -} - -static inline void save_fp_regs(freg_t *fprs) -{ - asm volatile("std 0,%0" : "=Q" (fprs[0])); - asm volatile("std 2,%0" : "=Q" (fprs[2])); - asm volatile("std 4,%0" : "=Q" (fprs[4])); - asm volatile("std 6,%0" : "=Q" (fprs[6])); - asm volatile("std 1,%0" : "=Q" (fprs[1])); - asm volatile("std 3,%0" : "=Q" (fprs[3])); - asm volatile("std 5,%0" : "=Q" (fprs[5])); - asm volatile("std 7,%0" : "=Q" (fprs[7])); - asm volatile("std 8,%0" : "=Q" (fprs[8])); - asm volatile("std 9,%0" : "=Q" (fprs[9])); - asm volatile("std 10,%0" : "=Q" (fprs[10])); - asm volatile("std 11,%0" : "=Q" (fprs[11])); - asm volatile("std 12,%0" : "=Q" (fprs[12])); - asm volatile("std 13,%0" : "=Q" (fprs[13])); - asm volatile("std 14,%0" : "=Q" (fprs[14])); - asm volatile("std 15,%0" : "=Q" (fprs[15])); -} - -static inline void restore_fp_regs(freg_t *fprs) -{ - asm volatile("ld 0,%0" : : "Q" (fprs[0])); - asm volatile("ld 2,%0" : : "Q" (fprs[2])); - asm volatile("ld 4,%0" : : "Q" (fprs[4])); - asm volatile("ld 6,%0" : : "Q" (fprs[6])); - asm volatile("ld 1,%0" : : "Q" (fprs[1])); - asm volatile("ld 3,%0" : : "Q" (fprs[3])); - asm volatile("ld 5,%0" : : "Q" (fprs[5])); - asm volatile("ld 7,%0" : : "Q" (fprs[7])); - asm volatile("ld 8,%0" : : "Q" (fprs[8])); - asm volatile("ld 9,%0" : : "Q" (fprs[9])); - asm volatile("ld 10,%0" : : "Q" (fprs[10])); - asm volatile("ld 11,%0" : : "Q" (fprs[11])); - asm volatile("ld 12,%0" : : "Q" (fprs[12])); - asm volatile("ld 13,%0" : : "Q" (fprs[13])); - asm volatile("ld 14,%0" : : "Q" (fprs[14])); - asm volatile("ld 15,%0" : : "Q" (fprs[15])); -} - -static inline void save_vx_regs(__vector128 *vxrs) -{ - typedef struct { __vector128 _[__NUM_VXRS]; } addrtype; - - asm volatile( - " la 1,%0\n" - " .word 0xe70f,0x1000,0x003e\n" /* vstm 0,15,0(1) */ - " .word 0xe70f,0x1100,0x0c3e\n" /* vstm 16,31,256(1) */ - : "=Q" (*(addrtype *) vxrs) : : "1"); -} - -static inline void save_vx_regs_safe(__vector128 *vxrs) -{ - unsigned long cr0, flags; - - flags = arch_local_irq_save(); - __ctl_store(cr0, 0, 0); - __ctl_set_bit(0, 17); - __ctl_set_bit(0, 18); - save_vx_regs(vxrs); - __ctl_load(cr0, 0, 0); - arch_local_irq_restore(flags); -} - -static inline void restore_vx_regs(__vector128 *vxrs) -{ - typedef struct { __vector128 _[__NUM_VXRS]; } addrtype; - - asm volatile( - " la 1,%0\n" - " .word 0xe70f,0x1000,0x0036\n" /* vlm 0,15,0(1) */ - " .word 0xe70f,0x1100,0x0c36\n" /* vlm 16,31,256(1) */ - : : "Q" (*(addrtype *) vxrs) : "1"); -} - -static inline void save_fp_vx_regs(struct task_struct *task) -{ - if (task->thread.vxrs) - save_vx_regs(task->thread.vxrs); - else - save_fp_regs(task->thread.fp_regs.fprs); -} - -static inline void restore_fp_vx_regs(struct task_struct *task) -{ - if (task->thread.vxrs) - restore_vx_regs(task->thread.vxrs); - else - restore_fp_regs(task->thread.fp_regs.fprs); -} - static inline void save_access_regs(unsigned int *acrs) { typedef struct { int _[NUM_ACRS]; } acrstype; @@ -157,15 +30,13 @@ static inline void restore_access_regs(unsigned int *acrs) #define switch_to(prev,next,last) do { \ if (prev->mm) { \ - save_fp_ctl(&prev->thread.fp_regs.fpc); \ - save_fp_vx_regs(prev); \ + save_fpu_regs(); \ save_access_regs(&prev->thread.acrs[0]); \ save_ri_cb(prev->thread.ri_cb); \ } \ if (next->mm) { \ update_cr_regs(next); \ - restore_fp_ctl(&next->thread.fp_regs.fpc); \ - restore_fp_vx_regs(next); \ + set_cpu_flag(CIF_FPU); \ restore_access_regs(&next->thread.acrs[0]); \ restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ } \ diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 4990f6c66..94fc55fc7 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -2,6 +2,7 @@ #define _ASM_S390_TOPOLOGY_H #include <linux/cpumask.h> +#include <asm/numa.h> struct sysinfo_15_1_x; struct cpu; @@ -13,6 +14,7 @@ struct cpu_topology_s390 { unsigned short core_id; unsigned short socket_id; unsigned short book_id; + unsigned short node_id; cpumask_t thread_mask; cpumask_t core_mask; cpumask_t book_mask; @@ -52,6 +54,43 @@ static inline void topology_expect_change(void) { } #define POLARIZATION_VM (2) #define POLARIZATION_VH (3) +#define SD_BOOK_INIT SD_CPU_INIT + +#ifdef CONFIG_NUMA + +#define cpu_to_node cpu_to_node +static inline int cpu_to_node(int cpu) +{ + return per_cpu(cpu_topology, cpu).node_id; +} + +/* Returns a pointer to the cpumask of CPUs on node 'node'. */ +#define cpumask_of_node cpumask_of_node +static inline const struct cpumask *cpumask_of_node(int node) +{ + return &node_to_cpumask_map[node]; +} + +/* + * Returns the number of the node containing node 'node'. This + * architecture is flat, so it is a pretty simple function! + */ +#define parent_node(node) (node) + +#define pcibus_to_node(bus) __pcibus_to_node(bus) + +#define node_distance(a, b) __node_distance(a, b) + +#else /* !CONFIG_NUMA */ + +#define numa_node_id numa_node_id +static inline int numa_node_id(void) +{ + return 0; +} + +#endif /* CONFIG_NUMA */ + #include <asm-generic/topology.h> #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 91f56b1d8..02613bad8 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -8,20 +8,8 @@ #include <uapi/asm/unistd.h> - #define __IGNORE_time -/* Ignore NUMA system calls. Not wired up on s390. */ -#define __IGNORE_mbind -#define __IGNORE_get_mempolicy -#define __IGNORE_set_mempolicy -#define __IGNORE_migrate_pages -#define __IGNORE_move_pages - -/* Ignore system calls that are also reachable via sys_socket */ -#define __IGNORE_recvmmsg -#define __IGNORE_sendmmsg - #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h new file mode 100644 index 000000000..4a3135620 --- /dev/null +++ b/arch/s390/include/asm/vx-insn.h @@ -0,0 +1,480 @@ +/* + * Support for Vector Instructions + * + * Assembler macros to generate .byte/.word code for particular + * vector instructions that are supported by recent binutils (>= 2.26) only. + * + * Copyright IBM Corp. 2015 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + */ + +#ifndef __ASM_S390_VX_INSN_H +#define __ASM_S390_VX_INSN_H + +#ifdef __ASSEMBLY__ + + +/* Macros to generate vector instruction byte code */ + +#define REG_NUM_INVALID 255 + +/* GR_NUM - Retrieve general-purpose register number + * + * @opd: Operand to store register number + * @r64: String designation register in the format "%rN" + */ +.macro GR_NUM opd gr + \opd = REG_NUM_INVALID + .ifc \gr,%r0 + \opd = 0 + .endif + .ifc \gr,%r1 + \opd = 1 + .endif + .ifc \gr,%r2 + \opd = 2 + .endif + .ifc \gr,%r3 + \opd = 3 + .endif + .ifc \gr,%r4 + \opd = 4 + .endif + .ifc \gr,%r5 + \opd = 5 + .endif + .ifc \gr,%r6 + \opd = 6 + .endif + .ifc \gr,%r7 + \opd = 7 + .endif + .ifc \gr,%r8 + \opd = 8 + .endif + .ifc \gr,%r9 + \opd = 9 + .endif + .ifc \gr,%r10 + \opd = 10 + .endif + .ifc \gr,%r11 + \opd = 11 + .endif + .ifc \gr,%r12 + \opd = 12 + .endif + .ifc \gr,%r13 + \opd = 13 + .endif + .ifc \gr,%r14 + \opd = 14 + .endif + .ifc \gr,%r15 + \opd = 15 + .endif + .if \opd == REG_NUM_INVALID + .error "Invalid general-purpose register designation: \gr" + .endif +.endm + +/* VX_R() - Macro to encode the VX_NUM into the instruction */ +#define VX_R(v) (v & 0x0F) + +/* VX_NUM - Retrieve vector register number + * + * @opd: Operand to store register number + * @vxr: String designation register in the format "%vN" + * + * The vector register number is used for as input number to the + * instruction and, as well as, to compute the RXB field of the + * instruction. To encode the particular vector register number, + * use the VX_R(v) macro to extract the instruction opcode. + */ +.macro VX_NUM opd vxr + \opd = REG_NUM_INVALID + .ifc \vxr,%v0 + \opd = 0 + .endif + .ifc \vxr,%v1 + \opd = 1 + .endif + .ifc \vxr,%v2 + \opd = 2 + .endif + .ifc \vxr,%v3 + \opd = 3 + .endif + .ifc \vxr,%v4 + \opd = 4 + .endif + .ifc \vxr,%v5 + \opd = 5 + .endif + .ifc \vxr,%v6 + \opd = 6 + .endif + .ifc \vxr,%v7 + \opd = 7 + .endif + .ifc \vxr,%v8 + \opd = 8 + .endif + .ifc \vxr,%v9 + \opd = 9 + .endif + .ifc \vxr,%v10 + \opd = 10 + .endif + .ifc \vxr,%v11 + \opd = 11 + .endif + .ifc \vxr,%v12 + \opd = 12 + .endif + .ifc \vxr,%v13 + \opd = 13 + .endif + .ifc \vxr,%v14 + \opd = 14 + .endif + .ifc \vxr,%v15 + \opd = 15 + .endif + .ifc \vxr,%v16 + \opd = 16 + .endif + .ifc \vxr,%v17 + \opd = 17 + .endif + .ifc \vxr,%v18 + \opd = 18 + .endif + .ifc \vxr,%v19 + \opd = 19 + .endif + .ifc \vxr,%v20 + \opd = 20 + .endif + .ifc \vxr,%v21 + \opd = 21 + .endif + .ifc \vxr,%v22 + \opd = 22 + .endif + .ifc \vxr,%v23 + \opd = 23 + .endif + .ifc \vxr,%v24 + \opd = 24 + .endif + .ifc \vxr,%v25 + \opd = 25 + .endif + .ifc \vxr,%v26 + \opd = 26 + .endif + .ifc \vxr,%v27 + \opd = 27 + .endif + .ifc \vxr,%v28 + \opd = 28 + .endif + .ifc \vxr,%v29 + \opd = 29 + .endif + .ifc \vxr,%v30 + \opd = 30 + .endif + .ifc \vxr,%v31 + \opd = 31 + .endif + .if \opd == REG_NUM_INVALID + .error "Invalid vector register designation: \vxr" + .endif +.endm + +/* RXB - Compute most significant bit used vector registers + * + * @rxb: Operand to store computed RXB value + * @v1: First vector register designated operand + * @v2: Second vector register designated operand + * @v3: Third vector register designated operand + * @v4: Fourth vector register designated operand + */ +.macro RXB rxb v1 v2=0 v3=0 v4=0 + \rxb = 0 + .if \v1 & 0x10 + \rxb = \rxb | 0x08 + .endif + .if \v2 & 0x10 + \rxb = \rxb | 0x04 + .endif + .if \v3 & 0x10 + \rxb = \rxb | 0x02 + .endif + .if \v4 & 0x10 + \rxb = \rxb | 0x01 + .endif +.endm + +/* MRXB - Generate Element Size Control and RXB value + * + * @m: Element size control + * @v1: First vector register designated operand (for RXB) + * @v2: Second vector register designated operand (for RXB) + * @v3: Third vector register designated operand (for RXB) + * @v4: Fourth vector register designated operand (for RXB) + */ +.macro MRXB m v1 v2=0 v3=0 v4=0 + rxb = 0 + RXB rxb, \v1, \v2, \v3, \v4 + .byte (\m << 4) | rxb +.endm + +/* MRXBOPC - Generate Element Size Control, RXB, and final Opcode fields + * + * @m: Element size control + * @opc: Opcode + * @v1: First vector register designated operand (for RXB) + * @v2: Second vector register designated operand (for RXB) + * @v3: Third vector register designated operand (for RXB) + * @v4: Fourth vector register designated operand (for RXB) + */ +.macro MRXBOPC m opc v1 v2=0 v3=0 v4=0 + MRXB \m, \v1, \v2, \v3, \v4 + .byte \opc +.endm + +/* Vector support instructions */ + +/* VECTOR GENERATE BYTE MASK */ +.macro VGBM vr imm2 + VX_NUM v1, \vr + .word (0xE700 | (VX_R(v1) << 4)) + .word \imm2 + MRXBOPC 0, 0x44, v1 +.endm +.macro VZERO vxr + VGBM \vxr, 0 +.endm +.macro VONE vxr + VGBM \vxr, 0xFFFF +.endm + +/* VECTOR LOAD VR ELEMENT FROM GR */ +.macro VLVG v, gr, disp, m + VX_NUM v1, \v + GR_NUM b2, "%r0" + GR_NUM r3, \gr + .word 0xE700 | (VX_R(v1) << 4) | r3 + .word (b2 << 12) | (\disp) + MRXBOPC \m, 0x22, v1 +.endm +.macro VLVGB v, gr, index, base + VLVG \v, \gr, \index, \base, 0 +.endm +.macro VLVGH v, gr, index + VLVG \v, \gr, \index, 1 +.endm +.macro VLVGF v, gr, index + VLVG \v, \gr, \index, 2 +.endm +.macro VLVGG v, gr, index + VLVG \v, \gr, \index, 3 +.endm + +/* VECTOR LOAD */ +.macro VL v, disp, index="%r0", base + VX_NUM v1, \v + GR_NUM x2, \index + GR_NUM b2, \base + .word 0xE700 | (VX_R(v1) << 4) | x2 + .word (b2 << 12) | (\disp) + MRXBOPC 0, 0x06, v1 +.endm + +/* VECTOR LOAD ELEMENT */ +.macro VLEx vr1, disp, index="%r0", base, m3, opc + VX_NUM v1, \vr1 + GR_NUM x2, \index + GR_NUM b2, \base + .word 0xE700 | (VX_R(v1) << 4) | x2 + .word (b2 << 12) | (\disp) + MRXBOPC \m3, \opc, v1 +.endm +.macro VLEB vr1, disp, index="%r0", base, m3 + VLEx \vr1, \disp, \index, \base, \m3, 0x00 +.endm +.macro VLEH vr1, disp, index="%r0", base, m3 + VLEx \vr1, \disp, \index, \base, \m3, 0x01 +.endm +.macro VLEF vr1, disp, index="%r0", base, m3 + VLEx \vr1, \disp, \index, \base, \m3, 0x03 +.endm +.macro VLEG vr1, disp, index="%r0", base, m3 + VLEx \vr1, \disp, \index, \base, \m3, 0x02 +.endm + +/* VECTOR LOAD ELEMENT IMMEDIATE */ +.macro VLEIx vr1, imm2, m3, opc + VX_NUM v1, \vr1 + .word 0xE700 | (VX_R(v1) << 4) + .word \imm2 + MRXBOPC \m3, \opc, v1 +.endm +.macro VLEIB vr1, imm2, index + VLEIx \vr1, \imm2, \index, 0x40 +.endm +.macro VLEIH vr1, imm2, index + VLEIx \vr1, \imm2, \index, 0x41 +.endm +.macro VLEIF vr1, imm2, index + VLEIx \vr1, \imm2, \index, 0x43 +.endm +.macro VLEIG vr1, imm2, index + VLEIx \vr1, \imm2, \index, 0x42 +.endm + +/* VECTOR LOAD GR FROM VR ELEMENT */ +.macro VLGV gr, vr, disp, base="%r0", m + GR_NUM r1, \gr + GR_NUM b2, \base + VX_NUM v3, \vr + .word 0xE700 | (r1 << 4) | VX_R(v3) + .word (b2 << 12) | (\disp) + MRXBOPC \m, 0x21, v3 +.endm +.macro VLGVB gr, vr, disp, base="%r0" + VLGV \gr, \vr, \disp, \base, 0 +.endm +.macro VLGVH gr, vr, disp, base="%r0" + VLGV \gr, \vr, \disp, \base, 1 +.endm +.macro VLGVF gr, vr, disp, base="%r0" + VLGV \gr, \vr, \disp, \base, 2 +.endm +.macro VLGVG gr, vr, disp, base="%r0" + VLGV \gr, \vr, \disp, \base, 3 +.endm + +/* VECTOR LOAD MULTIPLE */ +.macro VLM vfrom, vto, disp, base + VX_NUM v1, \vfrom + VX_NUM v3, \vto + GR_NUM b2, \base /* Base register */ + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v3) + .word (b2 << 12) | (\disp) + MRXBOPC 0, 0x36, v1, v3 +.endm + +/* VECTOR STORE MULTIPLE */ +.macro VSTM vfrom, vto, disp, base + VX_NUM v1, \vfrom + VX_NUM v3, \vto + GR_NUM b2, \base /* Base register */ + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v3) + .word (b2 << 12) | (\disp) + MRXBOPC 0, 0x3E, v1, v3 +.endm + +/* VECTOR PERMUTE */ +.macro VPERM vr1, vr2, vr3, vr4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + VX_NUM v4, \vr4 + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word (VX_R(v3) << 12) + MRXBOPC VX_R(v4), 0x8C, v1, v2, v3, v4 +.endm + +/* VECTOR UNPACK LOGICAL LOW */ +.macro VUPLL vr1, vr2, m3 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word 0x0000 + MRXBOPC \m3, 0xD4, v1, v2 +.endm +.macro VUPLLB vr1, vr2 + VUPLL \vr1, \vr2, 0 +.endm +.macro VUPLLH vr1, vr2 + VUPLL \vr1, \vr2, 1 +.endm +.macro VUPLLF vr1, vr2 + VUPLL \vr1, \vr2, 2 +.endm + + +/* Vector integer instructions */ + +/* VECTOR EXCLUSIVE OR */ +.macro VX vr1, vr2, vr3 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word (VX_R(v3) << 12) + MRXBOPC 0, 0x6D, v1, v2, v3 +.endm + +/* VECTOR GALOIS FIELD MULTIPLY SUM */ +.macro VGFM vr1, vr2, vr3, m4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word (VX_R(v3) << 12) + MRXBOPC \m4, 0xB4, v1, v2, v3 +.endm +.macro VGFMB vr1, vr2, vr3 + VGFM \vr1, \vr2, \vr3, 0 +.endm +.macro VGFMH vr1, vr2, vr3 + VGFM \vr1, \vr2, \vr3, 1 +.endm +.macro VGFMF vr1, vr2, vr3 + VGFM \vr1, \vr2, \vr3, 2 +.endm +.macro VGFMG vr1, vr2, vr3 + VGFM \vr1, \vr2, \vr3, 3 +.endm + +/* VECTOR GALOIS FIELD MULTIPLY SUM AND ACCUMULATE */ +.macro VGFMA vr1, vr2, vr3, vr4, m5 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + VX_NUM v4, \vr4 + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word (VX_R(v3) << 12) | (\m5 << 8) + MRXBOPC VX_R(v4), 0xBC, v1, v2, v3, v4 +.endm +.macro VGFMAB vr1, vr2, vr3, vr4 + VGFMA \vr1, \vr2, \vr3, \vr4, 0 +.endm +.macro VGFMAH vr1, vr2, vr3, vr4 + VGFMA \vr1, \vr2, \vr3, \vr4, 1 +.endm +.macro VGFMAF vr1, vr2, vr3, vr4 + VGFMA \vr1, \vr2, \vr3, \vr4, 2 +.endm +.macro VGFMAG vr1, vr2, vr3, vr4 + VGFMA \vr1, \vr2, \vr3, \vr4, 3 +.endm + +/* VECTOR SHIFT RIGHT LOGICAL BY BYTE */ +.macro VSRLB vr1, vr2, vr3 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | (VX_R(v1) << 4) | VX_R(v2) + .word (VX_R(v3) << 12) + MRXBOPC 0, 0x7D, v1, v2, v3 +.endm + + +#endif /* __ASSEMBLY__ */ +#endif /* __ASM_S390_VX_INSN_H */ |