diff options
Diffstat (limited to 'arch/s390')
113 files changed, 3957 insertions, 1665 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c03fef7a9c22..373679b3744a 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -81,6 +81,7 @@ config S390 select INIT_ALL_POSSIBLE select HAVE_IRQ_WORK select HAVE_PERF_EVENTS + select ARCH_HAVE_NMI_SAFE_CMPXCHG select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA @@ -90,6 +91,7 @@ config S390 select HAVE_ARCH_MUTEX_CPU_RELAX select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 select HAVE_RCU_TABLE_FREE if SMP + select ARCH_SAVE_PAGE_KEYS if HIBERNATION select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK @@ -273,11 +275,11 @@ config MARCH_Z10 on older machines. config MARCH_Z196 - bool "IBM zEnterprise 196" + bool "IBM zEnterprise 114 and 196" help - Select this to enable optimizations for IBM zEnterprise 196 - (2817 series). The kernel will be slightly faster but will not work - on older machines. + Select this to enable optimizations for IBM zEnterprise 114 and 196 + (2818 and 2817 series). The kernel will be slightly faster but will + not work on older machines. endchoice @@ -567,6 +569,17 @@ config KEXEC current kernel, and to start another kernel. It is like a reboot but is independent of hardware/microcode support. +config CRASH_DUMP + bool "kernel crash dumps" + depends on 64BIT + select KEXEC + help + Generate crash dump after being started by kexec. + Crash dump kernels are loaded in the main kernel with kexec-tools + into a specially reserved region and then later executed after + a crash by kdump/kexec. + For more details see Documentation/kdump/kdump.txt + config ZFCPDUMP def_bool n prompt "zfcpdump support" diff --git a/arch/s390/boot/compressed/head31.S b/arch/s390/boot/compressed/head31.S index 2a5523a32bcc..e8c9e18b8039 100644 --- a/arch/s390/boot/compressed/head31.S +++ b/arch/s390/boot/compressed/head31.S @@ -7,14 +7,14 @@ */ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> #include "sizes.h" __HEAD - .globl startup_continue -startup_continue: +ENTRY(startup_continue) basr %r13,0 # get base .LPG1: # setup stack diff --git a/arch/s390/boot/compressed/head64.S b/arch/s390/boot/compressed/head64.S index 2982cb140550..f86a4eef28a9 100644 --- a/arch/s390/boot/compressed/head64.S +++ b/arch/s390/boot/compressed/head64.S @@ -7,14 +7,14 @@ */ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> #include "sizes.h" __HEAD - .globl startup_continue -startup_continue: +ENTRY(startup_continue) basr %r13,0 # get base .LPG1: # setup stack diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 028f23ea81d1..465eca756feb 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -61,7 +61,7 @@ static unsigned long free_mem_end_ptr; extern _sclp_print_early(const char *); -int puts(const char *s) +static int puts(const char *s) { _sclp_print_early(s); return 0; diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h index 49676771bd66..ffd1ac255f19 100644 --- a/arch/s390/crypto/crypt_s390.h +++ b/arch/s390/crypto/crypt_s390.h @@ -368,9 +368,12 @@ static inline int crypt_s390_func_available(int func, if (facility_mask & CRYPT_S390_MSA && !test_facility(17)) return 0; - if (facility_mask & CRYPT_S390_MSA3 && !test_facility(76)) + + if (facility_mask & CRYPT_S390_MSA3 && + (!test_facility(2) || !test_facility(76))) return 0; - if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77)) + if (facility_mask & CRYPT_S390_MSA4 && + (!test_facility(2) || !test_facility(77))) return 0; switch (func & CRYPT_S390_OP_MASK) { diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 5ed8d64fc2ed..0317a3547cb9 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -1,15 +1,12 @@ /* * Cryptographic API. * - * s390 implementation of the SHA256 Secure Hash Algorithm. + * s390 implementation of the SHA256 and SHA224 Secure Hash Algorithm. * * s390 Version: - * Copyright IBM Corp. 2005,2007 + * Copyright IBM Corp. 2005,2011 * Author(s): Jan Glauber (jang@de.ibm.com) * - * Derived from "crypto/sha256_generic.c" - * and "arch/s390/crypto/sha1_s390.c" - * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) @@ -65,7 +62,7 @@ static int sha256_import(struct shash_desc *desc, const void *in) return 0; } -static struct shash_alg alg = { +static struct shash_alg sha256_alg = { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_init, .update = s390_sha_update, @@ -84,22 +81,69 @@ static struct shash_alg alg = { } }; -static int sha256_s390_init(void) +static int sha224_init(struct shash_desc *desc) { + struct s390_sha_ctx *sctx = shash_desc_ctx(desc); + + sctx->state[0] = SHA224_H0; + sctx->state[1] = SHA224_H1; + sctx->state[2] = SHA224_H2; + sctx->state[3] = SHA224_H3; + sctx->state[4] = SHA224_H4; + sctx->state[5] = SHA224_H5; + sctx->state[6] = SHA224_H6; + sctx->state[7] = SHA224_H7; + sctx->count = 0; + sctx->func = KIMD_SHA_256; + + return 0; +} + +static struct shash_alg sha224_alg = { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_init, + .update = s390_sha_update, + .final = s390_sha_final, + .export = sha256_export, + .import = sha256_import, + .descsize = sizeof(struct s390_sha_ctx), + .statesize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name= "sha224-s390", + .cra_priority = CRYPT_S390_PRIORITY, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int __init sha256_s390_init(void) +{ + int ret; + if (!crypt_s390_func_available(KIMD_SHA_256, CRYPT_S390_MSA)) return -EOPNOTSUPP; - - return crypto_register_shash(&alg); + ret = crypto_register_shash(&sha256_alg); + if (ret < 0) + goto out; + ret = crypto_register_shash(&sha224_alg); + if (ret < 0) + crypto_unregister_shash(&sha256_alg); +out: + return ret; } static void __exit sha256_s390_fini(void) { - crypto_unregister_shash(&alg); + crypto_unregister_shash(&sha224_alg); + crypto_unregister_shash(&sha256_alg); } module_init(sha256_s390_init); module_exit(sha256_s390_fini); MODULE_ALIAS("sha256"); +MODULE_ALIAS("sha224"); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm"); +MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index 48884f89ab92..bd37d09b9d3c 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -14,6 +14,7 @@ */ #include <crypto/internal/hash.h> +#include <linux/module.h> #include "sha.h" #include "crypt_s390.h" diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 29c82c640a88..6cf8e26b3137 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -68,7 +68,7 @@ CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 6023c6dc1fb7..74c8f5e76ce4 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -562,10 +562,9 @@ static int dbfs_d204_create(void **data, void **data_free_ptr, size_t *size) void *base; buf_size = PAGE_SIZE * (diag204_buf_pages + 1) + sizeof(d204->hdr); - base = vmalloc(buf_size); + base = vzalloc(buf_size); if (!base) return -ENOMEM; - memset(base, 0, buf_size); d204 = page_align_ptr(base + sizeof(d204->hdr)) - sizeof(d204->hdr); rc = diag204_do_store(d204->buf, diag204_buf_pages); if (rc) { diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 6fe874fc5f8e..481f4f76f664 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -108,9 +108,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode) ret->i_gid = hypfs_info->gid; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; if (mode & S_IFDIR) - ret->i_nlink = 2; - else - ret->i_nlink = 1; + set_nlink(ret, 2); } return ret; } @@ -361,7 +359,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb, } else if (mode & S_IFDIR) { inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; - parent->d_inode->i_nlink++; + inc_nlink(parent->d_inode); } else BUG(); inode->i_private = data; diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index d9db13810d15..8517d2ae3b5c 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -93,7 +93,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return old; } -static inline int atomic_add_unless(atomic_t *v, int a, int u) +static inline int __atomic_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); @@ -105,10 +105,9 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) break; c = old; } - return c != u; + return c; } -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #undef __CS_LOOP @@ -332,6 +331,4 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) #define smp_mb__before_atomic_inc() smp_mb() #define smp_mb__after_atomic_inc() smp_mb() -#include <asm-generic/atomic-long.h> - #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 667c6e9f6a34..e5beb490959b 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -832,10 +832,7 @@ static inline int find_next_bit_le(void *vaddr, unsigned long size, #include <asm-generic/bitops/le.h> -#define ext2_set_bit_atomic(lock, nr, addr) \ - test_and_set_bit_le(nr, addr) -#define ext2_clear_bit_atomic(lock, nr, addr) \ - test_and_clear_bit_le(nr, addr) +#include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index 623f2fb71774..9381c92cc779 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -11,6 +11,7 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> #include <asm/fcx.h> +#include <asm/irq.h> /* structs from asm/cio.h */ struct irb; @@ -127,6 +128,7 @@ enum uc_todo { * @restore: callback for restoring after hibernation * @uc_handler: callback for unit check handler * @driver: embedded device driver structure + * @int_class: interruption class to use for accounting interrupts */ struct ccw_driver { struct ccw_device_id *ids; @@ -144,6 +146,7 @@ struct ccw_driver { int (*restore)(struct ccw_device *); enum uc_todo (*uc_handler) (struct ccw_device *, struct irb *); struct device_driver driver; + enum interruption_class int_class; }; extern struct ccw_device *get_ccwdev_by_busid(struct ccw_driver *cdrv, diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index da359ca6fe55..2e49748b27da 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -12,6 +12,7 @@ #define PSW32_MASK_IO 0x02000000UL #define PSW32_MASK_EXT 0x01000000UL #define PSW32_MASK_KEY 0x00F00000UL +#define PSW32_MASK_BASE 0x00080000UL /* Always one */ #define PSW32_MASK_MCHECK 0x00040000UL #define PSW32_MASK_WAIT 0x00020000UL #define PSW32_MASK_PSTATE 0x00010000UL @@ -19,21 +20,19 @@ #define PSW32_MASK_CC 0x00003000UL #define PSW32_MASK_PM 0x00000f00UL -#define PSW32_ADDR_AMODE31 0x80000000UL +#define PSW32_MASK_USER 0x00003F00UL + +#define PSW32_ADDR_AMODE 0x80000000UL #define PSW32_ADDR_INSN 0x7FFFFFFFUL -#define PSW32_BASE_BITS 0x00080000UL +#define PSW32_DEFAULT_KEY (((u32) PAGE_DEFAULT_ACC) << 20) #define PSW32_ASC_PRIMARY 0x00000000UL #define PSW32_ASC_ACCREG 0x00004000UL #define PSW32_ASC_SECONDARY 0x00008000UL #define PSW32_ASC_HOME 0x0000C000UL -#define PSW32_MASK_MERGE(CURRENT,NEW) \ - (((CURRENT) & ~(PSW32_MASK_CC|PSW32_MASK_PM)) | \ - ((NEW) & (PSW32_MASK_CC|PSW32_MASK_PM))) - -extern long psw32_user_bits; +extern u32 psw32_user_bits; #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "s390\0\0\0\0" @@ -131,7 +130,8 @@ struct compat_statfs { compat_fsid_t f_fsid; s32 f_namelen; s32 f_frsize; - s32 f_spare[6]; + s32 f_flags; + s32 f_spare[5]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 64b61bf72e93..547f1a6a35d4 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -188,7 +188,8 @@ extern char elf_platform[]; #define SET_PERSONALITY(ex) \ do { \ if (personality(current->personality) != PER_LINUX32) \ - set_personality(PER_LINUX); \ + set_personality(PER_LINUX | \ + (current->personality & ~PER_MASK)); \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ set_thread_flag(TIF_31BIT); \ else \ diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 5e95d95450b3..6940abfbe1d9 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -167,5 +167,7 @@ enum diag308_rc { }; extern int diag308(unsigned long subcode, void *addr); +extern void diag308_reset(void); +extern void store_status(void); #endif /* _ASM_S390_IPL_H */ diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index ba7b01c726a3..ba6d85f88d50 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -8,7 +8,8 @@ enum interruption_class { EXTERNAL_INTERRUPT, IO_INTERRUPT, EXTINT_CLK, - EXTINT_IPI, + EXTINT_EXC, + EXTINT_EMS, EXTINT_TMR, EXTINT_TLA, EXTINT_PFL, @@ -17,8 +18,8 @@ enum interruption_class { EXTINT_SCP, EXTINT_IUC, EXTINT_CPM, + IOINT_CIO, IOINT_QAI, - IOINT_QDI, IOINT_DAS, IOINT_C15, IOINT_C70, @@ -28,6 +29,7 @@ enum interruption_class { IOINT_CLW, IOINT_CTC, IOINT_APB, + IOINT_CSC, NMI_NMI, NR_IRQS, }; diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h index 865d6d891ace..38fdf451febb 100644 --- a/arch/s390/include/asm/irqflags.h +++ b/arch/s390/include/asm/irqflags.h @@ -29,42 +29,42 @@ }) /* set system mask. */ -static inline void __arch_local_irq_ssm(unsigned long flags) +static inline notrace void __arch_local_irq_ssm(unsigned long flags) { asm volatile("ssm %0" : : "Q" (flags) : "memory"); } -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { return __arch_local_irq_stosm(0x00); } -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { return __arch_local_irq_stnsm(0xfc); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { arch_local_irq_save(); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { __arch_local_irq_stosm(0x03); } -static inline void arch_local_irq_restore(unsigned long flags) +static inline notrace void arch_local_irq_restore(unsigned long flags) { __arch_local_irq_ssm(flags); } -static inline bool arch_irqs_disabled_flags(unsigned long flags) +static inline notrace bool arch_irqs_disabled_flags(unsigned long flags) { return !(flags & (3UL << (BITS_PER_LONG - 8))); } -static inline bool arch_irqs_disabled(void) +static inline notrace bool arch_irqs_disabled(void) { return arch_irqs_disabled_flags(arch_local_save_flags()); } diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index bb729b84a21e..cf4e47b0948c 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -30,9 +30,15 @@ /* Not more than 2GB */ #define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31) +/* Maximum address we can use for the crash control pages */ +#define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL) + /* Allocate one page for the pdp and the second for the code */ #define KEXEC_CONTROL_PAGE_SIZE 4096 +/* Alignment of crashkernel memory */ +#define KEXEC_CRASH_MEM_ALIGN HPAGE_SIZE + /* The native architecture */ #define KEXEC_ARCH KEXEC_ARCH_S390 diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index cef7dbf69dfc..b0c235cb6ad5 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -47,7 +47,7 @@ struct sca_block { #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define CPUSTAT_HOST 0x80000000 +#define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 #define CPUSTAT_STOP_INT 0x04000000 @@ -93,9 +93,7 @@ struct kvm_s390_sie_block { __u32 scaol; /* 0x0064 */ __u8 reserved68[4]; /* 0x0068 */ __u32 todpr; /* 0x006c */ - __u8 reserved70[16]; /* 0x0070 */ - __u64 gmsor; /* 0x0080 */ - __u64 gmslm; /* 0x0088 */ + __u8 reserved70[32]; /* 0x0070 */ psw_t gpsw; /* 0x0090 */ __u64 gg14; /* 0x00a0 */ __u64 gg15; /* 0x00a8 */ @@ -121,6 +119,7 @@ struct kvm_vcpu_stat { u32 instruction_lctlg; u32 exit_program_interruption; u32 exit_instr_and_program; + u32 deliver_external_call; u32 deliver_emergency_signal; u32 deliver_service_signal; u32 deliver_virtio_interrupt; @@ -138,12 +137,16 @@ struct kvm_vcpu_stat { u32 instruction_chsc; u32 instruction_stsi; u32 instruction_stfl; + u32 instruction_tprot; u32 instruction_sigp_sense; + u32 instruction_sigp_sense_running; + u32 instruction_sigp_external_call; u32 instruction_sigp_emergency; u32 instruction_sigp_stop; u32 instruction_sigp_arch; u32 instruction_sigp_prefix; u32 instruction_sigp_restart; + u32 diagnose_10; u32 diagnose_44; }; @@ -175,6 +178,14 @@ struct kvm_s390_prefix_info { __u32 address; }; +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + struct kvm_s390_interrupt_info { struct list_head list; u64 type; @@ -182,6 +193,8 @@ struct kvm_s390_interrupt_info { struct kvm_s390_io_info io; struct kvm_s390_ext_info ext; struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; }; }; @@ -226,6 +239,7 @@ struct kvm_vcpu_arch { struct cpuid cpu_id; u64 stidp_data; }; + struct gmap *gmap; }; struct kvm_vm_stat { @@ -236,6 +250,7 @@ struct kvm_arch{ struct sca_block *sca; debug_info_t *dbf; struct kvm_s390_float_interrupt float_int; + struct gmap *gmap; }; extern int sie64a(struct kvm_s390_sie_block *, unsigned long *); diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h index 291c2d01c44f..fc8a8284778e 100644 --- a/arch/s390/include/asm/linkage.h +++ b/arch/s390/include/asm/linkage.h @@ -1,6 +1,9 @@ #ifndef __ASM_LINKAGE_H #define __ASM_LINKAGE_H -/* Nothing to see here... */ +#include <linux/stringify.h> + +#define __ALIGN .align 4, 0x07 +#define __ALIGN_STR __stringify(__ALIGN) #endif diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 228cf0b295db..9e13c7d56cc1 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -18,6 +18,7 @@ void system_call(void); void pgm_check_handler(void); void mcck_int_handler(void); void io_int_handler(void); +void psw_restart_int_handler(void); #ifdef CONFIG_32BIT @@ -150,7 +151,8 @@ struct _lowcore { */ __u32 ipib; /* 0x0e00 */ __u32 ipib_checksum; /* 0x0e04 */ - __u8 pad_0x0e08[0x0f00-0x0e08]; /* 0x0e08 */ + __u32 vmcore_info; /* 0x0e08 */ + __u8 pad_0x0e0c[0x0f00-0x0e0c]; /* 0x0e0c */ /* Extended facility list */ __u64 stfle_fac_list[32]; /* 0x0f00 */ @@ -268,7 +270,7 @@ struct _lowcore { __u64 vdso_per_cpu_data; /* 0x0358 */ __u64 machine_flags; /* 0x0360 */ __u64 ftrace_func; /* 0x0368 */ - __u64 sie_hook; /* 0x0370 */ + __u64 gmap; /* 0x0370 */ __u64 cmf_hpp; /* 0x0378 */ /* Interrupt response block. */ @@ -286,7 +288,8 @@ struct _lowcore { */ __u64 ipib; /* 0x0e00 */ __u32 ipib_checksum; /* 0x0e08 */ - __u8 pad_0x0e0c[0x0f00-0x0e0c]; /* 0x0e0c */ + __u64 vmcore_info; /* 0x0e0c */ + __u8 pad_0x0e14[0x0f00-0x0e14]; /* 0x0e14 */ /* Extended facility list */ __u64 stfle_fac_list[32]; /* 0x0f00 */ diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 82d0847896a0..4506791adcd5 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -6,6 +6,7 @@ typedef struct { unsigned int flush_mm; spinlock_t list_lock; struct list_head pgtable_list; + struct list_head gmap_list; unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; @@ -17,6 +18,7 @@ typedef struct { #define INIT_MM_CONTEXT(name) \ .context.list_lock = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \ - .context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), + .context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \ + .context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list), #endif diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index accb372ddc7e..f7ec548c2b9d 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,6 +177,7 @@ static inline int page_test_and_clear_young(unsigned long pfn) struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); +void arch_set_page_states(int make_stable); static inline int devmem_is_allowed(unsigned long pfn) { diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 38e71ebcd3c2..8eef9b5b3cf4 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -20,7 +20,7 @@ unsigned long *crst_table_alloc(struct mm_struct *); void crst_table_free(struct mm_struct *, unsigned long *); -unsigned long *page_table_alloc(struct mm_struct *); +unsigned long *page_table_alloc(struct mm_struct *, unsigned long); void page_table_free(struct mm_struct *, unsigned long *); #ifdef CONFIG_HAVE_RCU_TABLE_FREE void page_table_free_rcu(struct mmu_gather *, unsigned long *); @@ -115,6 +115,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { spin_lock_init(&mm->context.list_lock); INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); return (pgd_t *) crst_table_alloc(mm); } #define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) @@ -133,8 +134,8 @@ static inline void pmd_populate(struct mm_struct *mm, /* * page table entry allocation/free routines. */ -#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm)) -#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm)) +#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr)) +#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr)) #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte) #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 801fbe1d837d..524d23b8610c 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -593,6 +593,8 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) unsigned long address, bits; unsigned char skey; + if (!pte_present(*ptep)) + return pgste; address = pte_val(*ptep) & PAGE_MASK; skey = page_get_storage_key(address); bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); @@ -625,6 +627,8 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) #ifdef CONFIG_PGSTE int young; + if (!pte_present(*ptep)) + return pgste; young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); /* Transfer page referenced bit to pte software bit (host view) */ if (young || (pgste_val(pgste) & RCP_HR_BIT)) @@ -638,13 +642,15 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) } -static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste) +static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) { #ifdef CONFIG_PGSTE unsigned long address; unsigned long okey, nkey; - address = pte_val(*ptep) & PAGE_MASK; + if (!pte_present(entry)) + return; + address = pte_val(entry) & PAGE_MASK; okey = nkey = page_get_storage_key(address); nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT); /* Set page access key and fetch protection bit from pgste */ @@ -654,6 +660,52 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste) #endif } +/** + * struct gmap_struct - guest address space + * @mm: pointer to the parent mm_struct + * @table: pointer to the page directory + * @asce: address space control element for gmap page table + * @crst_list: list of all crst tables used in the guest address space + */ +struct gmap { + struct list_head list; + struct mm_struct *mm; + unsigned long *table; + unsigned long asce; + struct list_head crst_list; +}; + +/** + * struct gmap_rmap - reverse mapping for segment table entries + * @next: pointer to the next gmap_rmap structure in the list + * @entry: pointer to a segment table entry + */ +struct gmap_rmap { + struct list_head list; + unsigned long *entry; +}; + +/** + * struct gmap_pgtable - gmap information attached to a page table + * @vmaddr: address of the 1MB segment in the process virtual memory + * @mapper: list of segment table entries maping a page table + */ +struct gmap_pgtable { + unsigned long vmaddr; + struct list_head mapper; +}; + +struct gmap *gmap_alloc(struct mm_struct *mm); +void gmap_free(struct gmap *gmap); +void gmap_enable(struct gmap *gmap); +void gmap_disable(struct gmap *gmap); +int gmap_map_segment(struct gmap *gmap, unsigned long from, + unsigned long to, unsigned long length); +int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); +unsigned long __gmap_fault(unsigned long address, struct gmap *); +unsigned long gmap_fault(unsigned long address, struct gmap *); +void gmap_discard(unsigned long from, unsigned long to, struct gmap *); + /* * Certain architectures need to do special things when PTEs * within a page table are directly modified. Thus, the following @@ -666,7 +718,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste_set_pte(ptep, pgste); + pgste_set_pte(ptep, pgste, entry); *ptep = entry; pgste_set_unlock(ptep, pgste); } else diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 1300c3025334..5f33d37d032c 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -33,6 +33,8 @@ static inline void get_cpu_id(struct cpuid *ptr) extern void s390_adjust_jiffies(void); extern int get_cpu_capability(unsigned int *); +extern const struct seq_operations cpuinfo_op; +extern int sysctl_ieee_emulation_warnings; /* * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. @@ -80,6 +82,7 @@ struct thread_struct { mm_segment_t mm_segment; unsigned long prot_addr; /* address of protection-excep. */ unsigned int trap_no; + unsigned long gmap_addr; /* address of last gmap fault. */ struct per_regs per_user; /* User specified PER registers */ struct per_event per_event; /* Cause of the last PER trap */ /* pfault_wait is used to block the process on a pfault event */ @@ -117,19 +120,17 @@ struct stack_frame { /* * Do necessary setup to start up a new thread. */ -#define start_thread(regs, new_psw, new_stackp) do { \ - set_fs(USER_DS); \ - regs->psw.mask = psw_user_bits; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ - regs->gprs[15] = new_stackp; \ +#define start_thread(regs, new_psw, new_stackp) do { \ + regs->psw.mask = psw_user_bits | PSW_MASK_EA | PSW_MASK_BA; \ + regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->gprs[15] = new_stackp; \ } while (0) -#define start_thread31(regs, new_psw, new_stackp) do { \ - set_fs(USER_DS); \ - regs->psw.mask = psw_user32_bits; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ - regs->gprs[15] = new_stackp; \ - crst_table_downgrade(current->mm, 1UL << 31); \ +#define start_thread31(regs, new_psw, new_stackp) do { \ + regs->psw.mask = psw_user_bits | PSW_MASK_BA; \ + regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->gprs[15] = new_stackp; \ + crst_table_downgrade(current->mm, 1UL << 31); \ } while (0) /* Forward declaration, a strange C thing */ @@ -188,7 +189,6 @@ static inline void __load_psw(psw_t psw) * Set PSW mask to specified value, while leaving the * PSW addr pointing to the next instruction. */ - static inline void __load_psw_mask (unsigned long mask) { unsigned long addr; @@ -213,26 +213,37 @@ static inline void __load_psw_mask (unsigned long mask) : "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc"); #endif /* __s390x__ */ } - + /* - * Function to stop a processor until an interruption occurred + * Rewind PSW instruction address by specified number of bytes. */ -static inline void enabled_wait(void) +static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc) { - __load_psw_mask(PSW_BASE_BITS | PSW_MASK_IO | PSW_MASK_EXT | - PSW_MASK_MCHECK | PSW_MASK_WAIT | PSW_DEFAULT_KEY); -} +#ifndef __s390x__ + if (psw.addr & PSW_ADDR_AMODE) + /* 31 bit mode */ + return (psw.addr - ilc) | PSW_ADDR_AMODE; + /* 24 bit mode */ + return (psw.addr - ilc) & ((1UL << 24) - 1); +#else + unsigned long mask; + mask = (psw.mask & PSW_MASK_EA) ? -1UL : + (psw.mask & PSW_MASK_BA) ? (1UL << 31) - 1 : + (1UL << 24) - 1; + return (psw.addr - ilc) & mask; +#endif +} + /* * Function to drop a processor into disabled wait state */ - static inline void ATTRIB_NORET disabled_wait(unsigned long code) { unsigned long ctl_buf; psw_t dw_psw; - dw_psw.mask = PSW_BASE_BITS | PSW_MASK_WAIT; + dw_psw.mask = PSW_MASK_BASE | PSW_MASK_WAIT | PSW_MASK_BA | PSW_MASK_EA; dw_psw.addr = code; /* * Store status and then load disabled wait psw, diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 9ad628a8574a..a65846340d51 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -230,17 +230,21 @@ typedef struct #define PSW_MASK_IO 0x02000000UL #define PSW_MASK_EXT 0x01000000UL #define PSW_MASK_KEY 0x00F00000UL +#define PSW_MASK_BASE 0x00080000UL /* always one */ #define PSW_MASK_MCHECK 0x00040000UL #define PSW_MASK_WAIT 0x00020000UL #define PSW_MASK_PSTATE 0x00010000UL #define PSW_MASK_ASC 0x0000C000UL #define PSW_MASK_CC 0x00003000UL #define PSW_MASK_PM 0x00000F00UL +#define PSW_MASK_EA 0x00000000UL +#define PSW_MASK_BA 0x00000000UL + +#define PSW_MASK_USER 0x00003F00UL #define PSW_ADDR_AMODE 0x80000000UL #define PSW_ADDR_INSN 0x7FFFFFFFUL -#define PSW_BASE_BITS 0x00080000UL #define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 20) #define PSW_ASC_PRIMARY 0x00000000UL @@ -254,6 +258,7 @@ typedef struct #define PSW_MASK_DAT 0x0400000000000000UL #define PSW_MASK_IO 0x0200000000000000UL #define PSW_MASK_EXT 0x0100000000000000UL +#define PSW_MASK_BASE 0x0000000000000000UL #define PSW_MASK_KEY 0x00F0000000000000UL #define PSW_MASK_MCHECK 0x0004000000000000UL #define PSW_MASK_WAIT 0x0002000000000000UL @@ -261,12 +266,14 @@ typedef struct #define PSW_MASK_ASC 0x0000C00000000000UL #define PSW_MASK_CC 0x0000300000000000UL #define PSW_MASK_PM 0x00000F0000000000UL +#define PSW_MASK_EA 0x0000000100000000UL +#define PSW_MASK_BA 0x0000000080000000UL + +#define PSW_MASK_USER 0x00003F0180000000UL #define PSW_ADDR_AMODE 0x0000000000000000UL #define PSW_ADDR_INSN 0xFFFFFFFFFFFFFFFFUL -#define PSW_BASE_BITS 0x0000000180000000UL -#define PSW_BASE32_BITS 0x0000000080000000UL #define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 52) #define PSW_ASC_PRIMARY 0x0000000000000000UL @@ -279,18 +286,7 @@ typedef struct #ifdef __KERNEL__ extern long psw_kernel_bits; extern long psw_user_bits; -#ifdef CONFIG_64BIT -extern long psw_user32_bits; #endif -#endif - -/* This macro merges a NEW PSW mask specified by the user into - the currently active PSW mask CURRENT, modifying only those - bits in CURRENT that the user may be allowed to change: this - is the condition code and the program mask bits. */ -#define PSW_MASK_MERGE(CURRENT,NEW) \ - (((CURRENT) & ~(PSW_MASK_CC|PSW_MASK_PM)) | \ - ((NEW) & (PSW_MASK_CC|PSW_MASK_PM))) /* * The s390_regs structure is used to define the elf_gregset_t. @@ -328,8 +324,7 @@ struct pt_regs psw_t psw; unsigned long gprs[NUM_GPRS]; unsigned long orig_gpr2; - unsigned short ilc; - unsigned short svcnr; + unsigned int svc_code; }; /* @@ -487,6 +482,8 @@ typedef struct #define PTRACE_POKETEXT_AREA 0x5004 #define PTRACE_POKEDATA_AREA 0x5005 #define PTRACE_GET_LAST_BREAK 0x5006 +#define PTRACE_PEEK_SYSTEM_CALL 0x5007 +#define PTRACE_POKE_SYSTEM_CALL 0x5008 /* * PT_PROT definition is loosely based on hppa bsd definition in @@ -539,7 +536,6 @@ struct user_regs_struct * These are defined as per linux/ptrace.h, which see. */ #define arch_has_single_step() (1) -extern void show_regs(struct pt_regs * regs); #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0) #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN) diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 15c97625df8d..e63d13dd3bf5 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -46,6 +46,8 @@ struct qdesfmt0 { u32 : 16; } __attribute__ ((packed)); +#define QDR_AC_MULTI_BUFFER_ENABLE 0x01 + /** * struct qdr - queue description record (QDR) * @qfmt: queue format @@ -123,6 +125,40 @@ struct slibe { }; /** + * struct qaob - queue asynchronous operation block + * @res0: reserved parameters + * @res1: reserved parameter + * @res2: reserved parameter + * @res3: reserved parameter + * @aorc: asynchronous operation return code + * @flags: internal flags + * @cbtbs: control block type + * @sb_count: number of storage blocks + * @sba: storage block element addresses + * @dcount: size of storage block elements + * @user0: user defineable value + * @res4: reserved paramater + * @user1: user defineable value + * @user2: user defineable value + */ +struct qaob { + u64 res0[6]; + u8 res1; + u8 res2; + u8 res3; + u8 aorc; + u8 flags; + u16 cbtbs; + u8 sb_count; + u64 sba[QDIO_MAX_ELEMENTS_PER_BUFFER]; + u16 dcount[QDIO_MAX_ELEMENTS_PER_BUFFER]; + u64 user0; + u64 res4[2]; + u64 user1; + u64 user2; +} __attribute__ ((packed, aligned(256))); + +/** * struct slib - storage list information block (SLIB) * @nsliba: next SLIB address (if any) * @sla: SL address @@ -222,9 +258,46 @@ struct slsb { u8 val[QDIO_MAX_BUFFERS_PER_Q]; } __attribute__ ((packed, aligned(256))); +#define CHSC_AC2_MULTI_BUFFER_AVAILABLE 0x0080 +#define CHSC_AC2_MULTI_BUFFER_ENABLED 0x0040 #define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 #define CHSC_AC2_DATA_DIV_ENABLED 0x0002 +/** + * struct qdio_outbuf_state - SBAL related asynchronous operation information + * (for communication with upper layer programs) + * (only required for use with completion queues) + * @flags: flags indicating state of buffer + * @aob: pointer to QAOB used for the particular SBAL + * @user: pointer to upper layer program's state information related to SBAL + * (stored in user1 data of QAOB) + */ +struct qdio_outbuf_state { + u8 flags; + struct qaob *aob; + void *user; +}; + +#define QDIO_OUTBUF_STATE_FLAG_NONE 0x00 +#define QDIO_OUTBUF_STATE_FLAG_PENDING 0x01 + +#define CHSC_AC1_INITIATE_INPUTQ 0x80 + + +/* qdio adapter-characteristics-1 flag */ +#define AC1_SIGA_INPUT_NEEDED 0x40 /* process input queues */ +#define AC1_SIGA_OUTPUT_NEEDED 0x20 /* process output queues */ +#define AC1_SIGA_SYNC_NEEDED 0x10 /* ask hypervisor to sync */ +#define AC1_AUTOMATIC_SYNC_ON_THININT 0x08 /* set by hypervisor */ +#define AC1_AUTOMATIC_SYNC_ON_OUT_PCI 0x04 /* set by hypervisor */ +#define AC1_SC_QEBSM_AVAILABLE 0x02 /* available for subchannel */ +#define AC1_SC_QEBSM_ENABLED 0x01 /* enabled for subchannel */ + +#define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 +#define CHSC_AC2_DATA_DIV_ENABLED 0x0002 + +#define CHSC_AC3_FORMAT2_CQ_AVAILABLE 0x8000 + struct qdio_ssqd_desc { u8 flags; u8:8; @@ -243,8 +316,7 @@ struct qdio_ssqd_desc { u64 sch_token; u8 mro; u8 mri; - u8:8; - u8 sbalic; + u16 qdioac3; u16:16; u8:8; u8 mmwc; @@ -280,13 +352,16 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * @no_output_qs: number of output queues * @input_handler: handler to be called for input queues * @output_handler: handler to be called for output queues + * @queue_start_poll: polling handlers (one per input queue or NULL) * @int_parm: interruption parameter * @input_sbal_addr_array: address of no_input_qs * 128 pointers * @output_sbal_addr_array: address of no_output_qs * 128 pointers + * @output_sbal_state_array: no_output_qs * 128 state info (for CQ or NULL) */ struct qdio_initialize { struct ccw_device *cdev; unsigned char q_format; + unsigned char qdr_ac; unsigned char adapter_name[8]; unsigned int qib_param_field_format; unsigned char *qib_param_field; @@ -297,11 +372,12 @@ struct qdio_initialize { unsigned int no_output_qs; qdio_handler_t *input_handler; qdio_handler_t *output_handler; - void (*queue_start_poll) (struct ccw_device *, int, unsigned long); + void (**queue_start_poll) (struct ccw_device *, int, unsigned long); int scan_threshold; unsigned long int_parm; void **input_sbal_addr_array; void **output_sbal_addr_array; + struct qdio_outbuf_state *output_sbal_state_array; }; #define QDIO_STATE_INACTIVE 0x00000002 /* after qdio_cleanup */ @@ -316,6 +392,7 @@ struct qdio_initialize { extern int qdio_allocate(struct qdio_initialize *); extern int qdio_establish(struct qdio_initialize *); extern int qdio_activate(struct ccw_device *); +extern void qdio_release_aob(struct qaob *); extern int do_QDIO(struct ccw_device *, unsigned int, int, unsigned int, unsigned int); extern int qdio_start_irq(struct ccw_device *, int); diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h index f584f4a52581..3d6ad4ad2a3f 100644 --- a/arch/s390/include/asm/reset.h +++ b/arch/s390/include/asm/reset.h @@ -17,5 +17,5 @@ struct reset_call { extern void register_reset_call(struct reset_call *reset); extern void unregister_reset_call(struct reset_call *reset); -extern void s390_reset_system(void); +extern void s390_reset_system(void (*func)(void *), void *data); #endif /* _ASM_S390_RESET_H */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index d5e2ef10537d..097183c70407 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -26,15 +26,21 @@ #define IPL_DEVICE (*(unsigned long *) (0x10404)) #define INITRD_START (*(unsigned long *) (0x1040C)) #define INITRD_SIZE (*(unsigned long *) (0x10414)) +#define OLDMEM_BASE (*(unsigned long *) (0x1041C)) +#define OLDMEM_SIZE (*(unsigned long *) (0x10424)) #else /* __s390x__ */ #define IPL_DEVICE (*(unsigned long *) (0x10400)) #define INITRD_START (*(unsigned long *) (0x10408)) #define INITRD_SIZE (*(unsigned long *) (0x10410)) +#define OLDMEM_BASE (*(unsigned long *) (0x10418)) +#define OLDMEM_SIZE (*(unsigned long *) (0x10420)) #endif /* __s390x__ */ #define COMMAND_LINE ((char *) (0x10480)) #define CHUNK_READ_WRITE 0 #define CHUNK_READ_ONLY 1 +#define CHUNK_OLDMEM 4 +#define CHUNK_CRASHK 5 struct mem_chunk { unsigned long addr; @@ -48,6 +54,8 @@ extern int memory_end_set; extern unsigned long memory_end; void detect_memory_layout(struct mem_chunk chunk[]); +void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr, + unsigned long size, int type); #define PRIMARY_SPACE_MODE 0 #define ACCESS_REGISTER_MODE 1 @@ -74,6 +82,7 @@ extern unsigned int user_mode; #define MACHINE_FLAG_LPAR (1UL << 12) #define MACHINE_FLAG_SPP (1UL << 13) #define MACHINE_FLAG_TOPOLOGY (1UL << 14) +#define MACHINE_FLAG_STCKF (1UL << 15) #define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) #define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) @@ -92,6 +101,7 @@ extern unsigned int user_mode; #define MACHINE_HAS_PFMF (0) #define MACHINE_HAS_SPP (0) #define MACHINE_HAS_TOPOLOGY (0) +#define MACHINE_HAS_STCKF (0) #else /* __s390x__ */ #define MACHINE_HAS_IEEE (1) #define MACHINE_HAS_CSP (1) @@ -103,9 +113,11 @@ extern unsigned int user_mode; #define MACHINE_HAS_PFMF (S390_lowcore.machine_flags & MACHINE_FLAG_PFMF) #define MACHINE_HAS_SPP (S390_lowcore.machine_flags & MACHINE_FLAG_SPP) #define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY) +#define MACHINE_HAS_STCKF (S390_lowcore.machine_flags & MACHINE_FLAG_STCKF) #endif /* __s390x__ */ #define ZFCPDUMP_HSA_SIZE (32UL<<20) +#define ZFCPDUMP_HSA_SIZE_MAX (64UL<<20) /* * Console mode. Override with conmode= @@ -134,10 +146,14 @@ extern char kernel_nss_name[]; #define IPL_DEVICE 0x10404 #define INITRD_START 0x1040C #define INITRD_SIZE 0x10414 +#define OLDMEM_BASE 0x1041C +#define OLDMEM_SIZE 0x10424 #else /* __s390x__ */ #define IPL_DEVICE 0x10400 #define INITRD_START 0x10408 #define INITRD_SIZE 0x10410 +#define OLDMEM_BASE 0x10418 +#define OLDMEM_SIZE 0x10420 #endif /* __s390x__ */ #define COMMAND_LINE 0x10480 diff --git a/arch/s390/include/asm/sfp-util.h b/arch/s390/include/asm/sfp-util.h index 0addc6466d95..ca3f8814e361 100644 --- a/arch/s390/include/asm/sfp-util.h +++ b/arch/s390/include/asm/sfp-util.h @@ -72,6 +72,6 @@ extern unsigned long __udiv_qrnnd (unsigned int *, unsigned int, #define UDIV_NEEDS_NORMALIZATION 0 -#define abort() return 0 +#define abort() BUG() #define __BYTE_ORDER __BIG_ENDIAN diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 045e009fc164..ab47a69fdf07 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -33,6 +33,7 @@ extern struct save_area *zfcpdump_save_areas[NR_CPUS + 1]; extern void smp_switch_to_ipl_cpu(void (*func)(void *), void *); extern void smp_switch_to_cpu(void (*)(void *), void *, unsigned long sp, int from, int to); +extern void smp_restart_with_online_cpu(void); extern void smp_restart_cpu(void); /* @@ -64,6 +65,10 @@ static inline void smp_switch_to_ipl_cpu(void (*func)(void *), void *data) func(data); } +static inline void smp_restart_with_online_cpu(void) +{ +} + #define smp_vcpu_scheduled (1) #endif /* CONFIG_SMP */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 56612fc8186e..fd94dfec8d08 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -13,6 +13,8 @@ #include <linux/smp.h> +extern int spin_retry; + static inline int _raw_compare_and_swap(volatile unsigned int *lock, unsigned int old, unsigned int new) diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 5c0246b955d8..b239ff53b189 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -13,6 +13,7 @@ #define _ASM_SYSCALL_H 1 #include <linux/sched.h> +#include <linux/err.h> #include <asm/ptrace.h> /* @@ -25,7 +26,8 @@ extern const unsigned int sys_call_table[]; static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->svcnr ? regs->svcnr : -1; + return test_tsk_thread_flag(task, TIF_SYSCALL) ? + (regs->svc_code & 0xffff) : -1; } static inline void syscall_rollback(struct task_struct *task, @@ -37,7 +39,7 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return (regs->gprs[2] >= -4096UL) ? -regs->gprs[2] : 0; + return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h index d382629a0172..ef573c1d71a7 100644 --- a/arch/s390/include/asm/system.h +++ b/arch/s390/include/asm/system.h @@ -20,6 +20,8 @@ struct task_struct; +extern int sysctl_userprocess_debug; + extern struct task_struct *__switch_to(void *, void *); extern void update_per_regs(struct task_struct *task); @@ -113,6 +115,9 @@ extern void pfault_fini(void); extern void cmma_init(void); extern int memcpy_real(void *, void *, size_t); +extern void copy_to_absolute_zero(void *dest, void *src, size_t count); +extern int copy_to_user_real(void __user *dest, void *src, size_t count); +extern int copy_from_user_real(void *dest, void __user *src, size_t count); #define finish_arch_switch(prev) do { \ set_fs(current->thread.mm_segment); \ @@ -209,8 +214,10 @@ __set_psw_mask(unsigned long mask) __load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8))); } -#define local_mcck_enable() __set_psw_mask(psw_kernel_bits) -#define local_mcck_disable() __set_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK) +#define local_mcck_enable() \ + __set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK) +#define local_mcck_disable() \ + __set_psw_mask(psw_kernel_bits | PSW_MASK_DAT) #ifdef CONFIG_SMP diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index ad1382f7932e..a23183423b14 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -48,6 +48,7 @@ struct thread_info { unsigned int cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ struct restart_block restart_block; + unsigned int system_call; __u64 user_timer; __u64 system_timer; unsigned long last_break; /* last breaking-event-address. */ @@ -84,16 +85,17 @@ static inline struct thread_info *current_thread_info(void) /* * thread information flags bit numbers */ +#define TIF_SYSCALL 0 /* inside a system call */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ -#define TIF_RESTART_SVC 4 /* restart svc with new svc number */ #define TIF_PER_TRAP 6 /* deliver sigtrap on return to user */ #define TIF_MCCK_PENDING 7 /* machine check handling is pending */ #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_SYSCALL_TRACEPOINT 11 /* syscall tracepoint instrumentation */ +#define TIF_SIE 12 /* guest execution active */ #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_31BIT 17 /* 32bit process */ @@ -102,20 +104,21 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SINGLE_STEP 20 /* This task is single stepped */ #define TIF_FREEZE 21 /* thread is freezing for suspend */ +#define _TIF_SYSCALL (1<<TIF_SYSCALL) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_RESTORE_SIGMASK (1<<TIF_RESTORE_SIGMASK) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) -#define _TIF_RESTART_SVC (1<<TIF_RESTART_SVC) #define _TIF_PER_TRAP (1<<TIF_PER_TRAP) #define _TIF_MCCK_PENDING (1<<TIF_MCCK_PENDING) #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1<<TIF_SECCOMP) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) +#define _TIF_SIE (1<<TIF_SIE) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_31BIT (1<<TIF_31BIT) -#define _TIF_SINGLE_STEP (1<<TIF_FREEZE) +#define _TIF_SINGLE_STEP (1<<TIF_SINGLE_STEP) #define _TIF_FREEZE (1<<TIF_FREEZE) #ifdef CONFIG_64BIT diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 88829a40af6f..c447a27a7fdb 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -86,6 +86,17 @@ static inline void get_clock_ext(char *clk) asm volatile("stcke %0" : "=Q" (*clk) : : "cc"); } +static inline unsigned long long get_clock_fast(void) +{ + unsigned long long clk; + + if (MACHINE_HAS_STCKF) + asm volatile(".insn s,0xb27c0000,%0" : "=Q" (clk) : : "cc"); + else + clk = get_clock(); + return clk; +} + static inline unsigned long long get_clock_xt(void) { unsigned char clk[16]; diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index b7a4f2eb0057..1d8648cf2fea 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -59,6 +59,7 @@ static inline void __tlb_flush_full(struct mm_struct *mm) } #else #define __tlb_flush_full(mm) __tlb_flush_local() +#define __tlb_flush_global() __tlb_flush_local() #endif /* @@ -80,7 +81,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) * on all cpus instead of doing a local flush if the mm * only ran on the local cpu. */ - if (MACHINE_HAS_IDTE) + if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list)) __tlb_flush_idte((unsigned long) mm->pgd | mm->context.asce_bits); else diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 404bdb9671b4..58de4c91c333 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -277,7 +277,9 @@ #define __NR_clock_adjtime 337 #define __NR_syncfs 338 #define __NR_setns 339 -#define NR_syscalls 340 +#define __NR_process_vm_readv 340 +#define __NR_process_vm_writev 341 +#define NR_syscalls 342 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index df3732249baa..dd4f07640919 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += $(if $(CONFIG_64BIT),mcount64.o,mcount.o) obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o # Kexec part S390_KEXEC_OBJS := machine_kexec.o crash.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index edfbd17d7082..751318765e2e 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <asm/vdso.h> #include <asm/sigp.h> +#include <asm/pgtable.h> /* * Make sure that the compiler is new enough. We want a compiler that @@ -27,12 +28,9 @@ int main(void) BLANK(); DEFINE(__TASK_pid, offsetof(struct task_struct, pid)); BLANK(); - DEFINE(__THREAD_per_cause, - offsetof(struct task_struct, thread.per_event.cause)); - DEFINE(__THREAD_per_address, - offsetof(struct task_struct, thread.per_event.address)); - DEFINE(__THREAD_per_paid, - offsetof(struct task_struct, thread.per_event.paid)); + DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause)); + DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address)); + DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid)); BLANK(); DEFINE(__TI_task, offsetof(struct thread_info, task)); DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain)); @@ -47,8 +45,7 @@ int main(void) DEFINE(__PT_PSW, offsetof(struct pt_regs, psw)); DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs)); DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2)); - DEFINE(__PT_ILC, offsetof(struct pt_regs, ilc)); - DEFINE(__PT_SVCNR, offsetof(struct pt_regs, svcnr)); + DEFINE(__PT_SVC_CODE, offsetof(struct pt_regs, svc_code)); DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain)); @@ -129,6 +126,7 @@ int main(void) DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack)); DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack)); DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack)); + DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce)); DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags)); @@ -151,8 +149,9 @@ int main(void) DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area)); DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr)); DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data)); - DEFINE(__LC_SIE_HOOK, offsetof(struct _lowcore, sie_hook)); + DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap)); DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp)); + DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); #endif /* CONFIG_32BIT */ return 0; } diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index 15e46ca94335..f8828d38fa6e 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -6,13 +6,13 @@ * Michael Holzheu <holzheu@de.ibm.com> */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> #ifdef CONFIG_64BIT - .globl s390_base_mcck_handler -s390_base_mcck_handler: +ENTRY(s390_base_mcck_handler) basr %r13,0 0: lg %r15,__LC_PANIC_STACK # load panic stack aghi %r15,-STACK_FRAME_OVERHEAD @@ -26,13 +26,13 @@ s390_base_mcck_handler: lpswe __LC_MCK_OLD_PSW .section .bss + .align 8 .globl s390_base_mcck_handler_fn s390_base_mcck_handler_fn: .quad 0 .previous - .globl s390_base_ext_handler -s390_base_ext_handler: +ENTRY(s390_base_ext_handler) stmg %r0,%r15,__LC_SAVE_AREA basr %r13,0 0: aghi %r15,-STACK_FRAME_OVERHEAD @@ -46,13 +46,13 @@ s390_base_ext_handler: lpswe __LC_EXT_OLD_PSW .section .bss + .align 8 .globl s390_base_ext_handler_fn s390_base_ext_handler_fn: .quad 0 .previous - .globl s390_base_pgm_handler -s390_base_pgm_handler: +ENTRY(s390_base_pgm_handler) stmg %r0,%r15,__LC_SAVE_AREA basr %r13,0 0: aghi %r15,-STACK_FRAME_OVERHEAD @@ -70,15 +70,57 @@ disabled_wait_psw: .quad 0x0002000180000000,0x0000000000000000 + s390_base_pgm_handler .section .bss + .align 8 .globl s390_base_pgm_handler_fn s390_base_pgm_handler_fn: .quad 0 .previous +# +# Calls diag 308 subcode 1 and continues execution +# +# The following conditions must be ensured before calling this function: +# * Prefix register = 0 +# * Lowcore protection is disabled +# +ENTRY(diag308_reset) + larl %r4,.Lctlregs # Save control registers + stctg %c0,%c15,0(%r4) + larl %r4,.Lfpctl # Floating point control register + stfpc 0(%r4) + larl %r4,.Lrestart_psw # Setup restart PSW at absolute 0 + lghi %r3,0 + lg %r4,0(%r4) # Save PSW + sturg %r4,%r3 # Use sturg, because of large pages + lghi %r1,1 + diag %r1,%r1,0x308 +.Lrestart_part2: + lhi %r0,0 # Load r0 with zero + lhi %r1,2 # Use mode 2 = ESAME (dump) + sigp %r1,%r0,0x12 # Switch to ESAME mode + sam64 # Switch to 64 bit addressing mode + larl %r4,.Lctlregs # Restore control registers + lctlg %c0,%c15,0(%r4) + larl %r4,.Lfpctl # Restore floating point ctl register + lfpc 0(%r4) + br %r14 +.align 16 +.Lrestart_psw: + .long 0x00080000,0x80000000 + .Lrestart_part2 + + .section .bss +.align 8 +.Lctlregs: + .rept 16 + .quad 0 + .endr +.Lfpctl: + .long 0 + .previous + #else /* CONFIG_64BIT */ - .globl s390_base_mcck_handler -s390_base_mcck_handler: +ENTRY(s390_base_mcck_handler) basr %r13,0 0: l %r15,__LC_PANIC_STACK # load panic stack ahi %r15,-STACK_FRAME_OVERHEAD @@ -93,13 +135,13 @@ s390_base_mcck_handler: 2: .long s390_base_mcck_handler_fn .section .bss + .align 4 .globl s390_base_mcck_handler_fn s390_base_mcck_handler_fn: .long 0 .previous - .globl s390_base_ext_handler -s390_base_ext_handler: +ENTRY(s390_base_ext_handler) stm %r0,%r15,__LC_SAVE_AREA basr %r13,0 0: ahi %r15,-STACK_FRAME_OVERHEAD @@ -115,13 +157,13 @@ s390_base_ext_handler: 2: .long s390_base_ext_handler_fn .section .bss + .align 4 .globl s390_base_ext_handler_fn s390_base_ext_handler_fn: .long 0 .previous - .globl s390_base_pgm_handler -s390_base_pgm_handler: +ENTRY(s390_base_pgm_handler) stm %r0,%r15,__LC_SAVE_AREA basr %r13,0 0: ahi %r15,-STACK_FRAME_OVERHEAD @@ -142,6 +184,7 @@ disabled_wait_psw: .long 0x000a0000,0x00000000 + s390_base_pgm_handler .section .bss + .align 4 .globl s390_base_pgm_handler_fn s390_base_pgm_handler_fn: .long 0 diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 53acaa86dd94..84a982898448 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -60,12 +60,9 @@ #include "compat_linux.h" -long psw_user32_bits = (PSW_BASE32_BITS | PSW_MASK_DAT | PSW_ASC_HOME | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY); -long psw32_user_bits = (PSW32_BASE_BITS | PSW32_MASK_DAT | PSW32_ASC_HOME | - PSW32_MASK_IO | PSW32_MASK_EXT | PSW32_MASK_MCHECK | - PSW32_MASK_PSTATE); +u32 psw32_user_bits = PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | + PSW32_DEFAULT_KEY | PSW32_MASK_BASE | PSW32_MASK_MCHECK | + PSW32_MASK_PSTATE | PSW32_ASC_HOME; /* For this source file, we want overflow handling. */ @@ -365,12 +362,7 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, if (set) { if (copy_from_user (&s32, set, sizeof(compat_sigset_t))) return -EFAULT; - switch (_NSIG_WORDS) { - case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32); - case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32); - case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32); - case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); - } + s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); } set_fs (KERNEL_DS); ret = sys_rt_sigprocmask(how, @@ -380,12 +372,8 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, set_fs (old_fs); if (ret) return ret; if (oset) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } + s32.sig[1] = (s.sig[0] >> 32); + s32.sig[0] = s.sig[0]; if (copy_to_user (oset, &s32, sizeof(compat_sigset_t))) return -EFAULT; } @@ -404,12 +392,8 @@ asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set, ret = sys_rt_sigpending((sigset_t __force __user *) &s, sigsetsize); set_fs (old_fs); if (!ret) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } + s32.sig[1] = (s.sig[0] >> 32); + s32.sig[0] = s.sig[0]; if (copy_to_user (set, &s32, sizeof(compat_sigset_t))) return -EFAULT; } diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index eee999853a7c..4f68c81d3ffa 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -141,7 +141,8 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) break; case __SI_FAULT >> 16: err |= __get_user(tmp, &from->si_addr); - to->si_addr = (void __user *)(u64) (tmp & PSW32_ADDR_INSN); + to->si_addr = (void __force __user *) + (u64) (tmp & PSW32_ADDR_INSN); break; case __SI_POLL >> 16: err |= __get_user(to->si_band, &from->si_band); @@ -213,16 +214,8 @@ sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, ret = get_user(sa_handler, &act->sa_handler); ret |= __copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t)); - switch (_NSIG_WORDS) { - case 4: new_ka.sa.sa_mask.sig[3] = set32.sig[6] - | (((long)set32.sig[7]) << 32); - case 3: new_ka.sa.sa_mask.sig[2] = set32.sig[4] - | (((long)set32.sig[5]) << 32); - case 2: new_ka.sa.sa_mask.sig[1] = set32.sig[2] - | (((long)set32.sig[3]) << 32); - case 1: new_ka.sa.sa_mask.sig[0] = set32.sig[0] - | (((long)set32.sig[1]) << 32); - } + new_ka.sa.sa_mask.sig[0] = + set32.sig[0] | (((long)set32.sig[1]) << 32); ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags); if (ret) @@ -233,20 +226,8 @@ sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { - switch (_NSIG_WORDS) { - case 4: - set32.sig[7] = (old_ka.sa.sa_mask.sig[3] >> 32); - set32.sig[6] = old_ka.sa.sa_mask.sig[3]; - case 3: - set32.sig[5] = (old_ka.sa.sa_mask.sig[2] >> 32); - set32.sig[4] = old_ka.sa.sa_mask.sig[2]; - case 2: - set32.sig[3] = (old_ka.sa.sa_mask.sig[1] >> 32); - set32.sig[2] = old_ka.sa.sa_mask.sig[1]; - case 1: - set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); - set32.sig[0] = old_ka.sa.sa_mask.sig[0]; - } + set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); + set32.sig[0] = old_ka.sa.sa_mask.sig[0]; ret = put_user((unsigned long)old_ka.sa.sa_handler, &oact->sa_handler); ret |= __copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t)); @@ -300,9 +281,10 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) _s390_regs_common32 regs32; int err, i; - regs32.psw.mask = PSW32_MASK_MERGE(psw32_user_bits, - (__u32)(regs->psw.mask >> 32)); - regs32.psw.addr = PSW32_ADDR_AMODE31 | (__u32) regs->psw.addr; + regs32.psw.mask = psw32_user_bits | + ((__u32)(regs->psw.mask >> 32) & PSW32_MASK_USER); + regs32.psw.addr = (__u32) regs->psw.addr | + (__u32)(regs->psw.mask & PSW_MASK_BA); for (i = 0; i < NUM_GPRS; i++) regs32.gprs[i] = (__u32) regs->gprs[i]; save_access_regs(current->thread.acrs); @@ -327,8 +309,9 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) err = __copy_from_user(®s32, &sregs->regs, sizeof(regs32)); if (err) return err; - regs->psw.mask = PSW_MASK_MERGE(regs->psw.mask, - (__u64)regs32.psw.mask << 32); + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (__u64)(regs32.psw.mask & PSW32_MASK_USER) << 32 | + (__u64)(regs32.psw.addr & PSW32_ADDR_AMODE); regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN); for (i = 0; i < NUM_GPRS; i++) regs->gprs[i] = (__u64) regs32.gprs[i]; @@ -342,7 +325,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) return err; restore_fp_regs(¤t->thread.fp_regs); - regs->svcnr = 0; /* disable syscall checks */ + clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -380,20 +363,13 @@ asmlinkage long sys32_sigreturn(void) goto badframe; if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32)) goto badframe; - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - + set_current_blocked(&set); if (restore_sigregs32(regs, &frame->sregs)) goto badframe; if (restore_sigregs_gprs_high(regs, frame->gprs_high)) goto badframe; - return regs->gprs[2]; - badframe: force_sig(SIGSEGV, current); return 0; @@ -413,31 +389,22 @@ asmlinkage long sys32_rt_sigreturn(void) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - + set_current_blocked(&set); if (restore_sigregs32(regs, &frame->uc.uc_mcontext)) goto badframe; if (restore_sigregs_gprs_high(regs, frame->gprs_high)) goto badframe; - err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp); st.ss_sp = compat_ptr(ss_sp); err |= __get_user(st.ss_size, &frame->uc.uc_stack.ss_size); err |= __get_user(st.ss_flags, &frame->uc.uc_stack.ss_flags); if (err) goto badframe; - set_fs (KERNEL_DS); do_sigaltstack((stack_t __force __user *)&st, NULL, regs->gprs[15]); set_fs (old_fs); - return regs->gprs[2]; - badframe: force_sig(SIGSEGV, current); return 0; @@ -512,11 +479,11 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - regs->gprs[14] = (__u64) ka->sa.sa_restorer; + regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode; + regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, - (u16 __user *)(frame->retcode))) + (u16 __force __user *)(frame->retcode))) goto give_sigsegv; } @@ -525,11 +492,12 @@ static int setup_frame32(int sig, struct k_sigaction *ka, goto give_sigsegv; /* Set up registers for signal handler */ - regs->gprs[15] = (__u64) frame; - regs->psw.addr = (__u64) ka->sa.sa_handler; + regs->gprs[15] = (__force __u64) frame; + regs->psw.mask |= PSW_MASK_BA; /* force amode 31 */ + regs->psw.addr = (__force __u64) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); - regs->gprs[3] = (__u64) &frame->sc; + regs->gprs[3] = (__force __u64) &frame->sc; /* We forgot to include these in the sigcontext. To avoid breaking binary compatibility, they are passed as args. */ @@ -537,7 +505,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, regs->gprs[5] = current->thread.prot_addr; /* Place signal number on stack to allow backtrace from handler. */ - if (__put_user(regs->gprs[2], (int __user *) &frame->signo)) + if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo)) goto give_sigsegv; return 0; @@ -580,20 +548,21 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, } else { regs->gprs[14] = (__u64) frame->retcode; err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, - (u16 __user *)(frame->retcode)); + (u16 __force __user *)(frame->retcode)); } /* Set up backchain. */ - if (__put_user(regs->gprs[15], (unsigned int __user *) frame)) + if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame)) goto give_sigsegv; /* Set up registers for signal handler */ - regs->gprs[15] = (__u64) frame; + regs->gprs[15] = (__force __u64) frame; + regs->psw.mask |= PSW_MASK_BA; /* force amode 31 */ regs->psw.addr = (__u64) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); - regs->gprs[3] = (__u64) &frame->info; - regs->gprs[4] = (__u64) &frame->uc; + regs->gprs[3] = (__force __u64) &frame->info; + regs->gprs[4] = (__force __u64) &frame->uc; return 0; give_sigsegv: @@ -605,10 +574,10 @@ give_sigsegv: * OK, we're invoking a handler */ -int -handle_signal32(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, struct pt_regs * regs) +int handle_signal32(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int ret; /* Set up the stack frame */ @@ -616,15 +585,12 @@ handle_signal32(unsigned long sig, struct k_sigaction *ka, ret = setup_rt_frame32(sig, ka, info, oldset, regs); else ret = setup_frame32(sig, ka, oldset, regs); - - if (ret == 0) { - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - } - return ret; + if (ret) + return ret; + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(&blocked, sig); + set_current_blocked(&blocked); + return 0; } diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 1f5eb789c3a7..18c51df9fe06 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -7,86 +7,74 @@ * Thomas Spatzier (tspat@de.ibm.com) */ - .globl sys32_exit_wrapper -sys32_exit_wrapper: +#include <linux/linkage.h> + +ENTRY(sys32_exit_wrapper) lgfr %r2,%r2 # int jg sys_exit # branch to sys_exit - .globl sys32_read_wrapper -sys32_read_wrapper: +ENTRY(sys32_read_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # char * llgfr %r4,%r4 # size_t jg sys32_read # branch to sys_read - .globl sys32_write_wrapper -sys32_write_wrapper: +ENTRY(sys32_write_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # const char * llgfr %r4,%r4 # size_t jg sys32_write # branch to system call - .globl sys32_open_wrapper -sys32_open_wrapper: +ENTRY(sys32_open_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int lgfr %r4,%r4 # int jg sys_open # branch to system call - .globl sys32_close_wrapper -sys32_close_wrapper: +ENTRY(sys32_close_wrapper) llgfr %r2,%r2 # unsigned int jg sys_close # branch to system call - .globl sys32_creat_wrapper -sys32_creat_wrapper: +ENTRY(sys32_creat_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int jg sys_creat # branch to system call - .globl sys32_link_wrapper -sys32_link_wrapper: +ENTRY(sys32_link_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # const char * jg sys_link # branch to system call - .globl sys32_unlink_wrapper -sys32_unlink_wrapper: +ENTRY(sys32_unlink_wrapper) llgtr %r2,%r2 # const char * jg sys_unlink # branch to system call - .globl sys32_chdir_wrapper -sys32_chdir_wrapper: +ENTRY(sys32_chdir_wrapper) llgtr %r2,%r2 # const char * jg sys_chdir # branch to system call - .globl sys32_time_wrapper -sys32_time_wrapper: +ENTRY(sys32_time_wrapper) llgtr %r2,%r2 # int * jg compat_sys_time # branch to system call - .globl sys32_mknod_wrapper -sys32_mknod_wrapper: +ENTRY(sys32_mknod_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int llgfr %r4,%r4 # dev jg sys_mknod # branch to system call - .globl sys32_chmod_wrapper -sys32_chmod_wrapper: +ENTRY(sys32_chmod_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # mode_t jg sys_chmod # branch to system call - .globl sys32_lchown16_wrapper -sys32_lchown16_wrapper: +ENTRY(sys32_lchown16_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # __kernel_old_uid_emu31_t llgfr %r4,%r4 # __kernel_old_uid_emu31_t jg sys32_lchown16 # branch to system call - .globl sys32_lseek_wrapper -sys32_lseek_wrapper: +ENTRY(sys32_lseek_wrapper) llgfr %r2,%r2 # unsigned int lgfr %r3,%r3 # off_t llgfr %r4,%r4 # unsigned int @@ -94,8 +82,7 @@ sys32_lseek_wrapper: #sys32_getpid_wrapper # void - .globl sys32_mount_wrapper -sys32_mount_wrapper: +ENTRY(sys32_mount_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgtr %r4,%r4 # char * @@ -103,102 +90,85 @@ sys32_mount_wrapper: llgtr %r6,%r6 # void * jg compat_sys_mount # branch to system call - .globl sys32_oldumount_wrapper -sys32_oldumount_wrapper: +ENTRY(sys32_oldumount_wrapper) llgtr %r2,%r2 # char * jg sys_oldumount # branch to system call - .globl sys32_setuid16_wrapper -sys32_setuid16_wrapper: +ENTRY(sys32_setuid16_wrapper) llgfr %r2,%r2 # __kernel_old_uid_emu31_t jg sys32_setuid16 # branch to system call #sys32_getuid16_wrapper # void - .globl sys32_ptrace_wrapper -sys32_ptrace_wrapper: +ENTRY(sys32_ptrace_wrapper) lgfr %r2,%r2 # long lgfr %r3,%r3 # long llgtr %r4,%r4 # long llgfr %r5,%r5 # long jg compat_sys_ptrace # branch to system call - .globl sys32_alarm_wrapper -sys32_alarm_wrapper: +ENTRY(sys32_alarm_wrapper) llgfr %r2,%r2 # unsigned int jg sys_alarm # branch to system call - .globl compat_sys_utime_wrapper -compat_sys_utime_wrapper: +ENTRY(compat_sys_utime_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct compat_utimbuf * jg compat_sys_utime # branch to system call - .globl sys32_access_wrapper -sys32_access_wrapper: +ENTRY(sys32_access_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int jg sys_access # branch to system call - .globl sys32_nice_wrapper -sys32_nice_wrapper: +ENTRY(sys32_nice_wrapper) lgfr %r2,%r2 # int jg sys_nice # branch to system call #sys32_sync_wrapper # void - .globl sys32_kill_wrapper -sys32_kill_wrapper: +ENTRY(sys32_kill_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int jg sys_kill # branch to system call - .globl sys32_rename_wrapper -sys32_rename_wrapper: +ENTRY(sys32_rename_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # const char * jg sys_rename # branch to system call - .globl sys32_mkdir_wrapper -sys32_mkdir_wrapper: +ENTRY(sys32_mkdir_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int jg sys_mkdir # branch to system call - .globl sys32_rmdir_wrapper -sys32_rmdir_wrapper: +ENTRY(sys32_rmdir_wrapper) llgtr %r2,%r2 # const char * jg sys_rmdir # branch to system call - .globl sys32_dup_wrapper -sys32_dup_wrapper: +ENTRY(sys32_dup_wrapper) llgfr %r2,%r2 # unsigned int jg sys_dup # branch to system call - .globl sys32_pipe_wrapper -sys32_pipe_wrapper: +ENTRY(sys32_pipe_wrapper) llgtr %r2,%r2 # u32 * jg sys_pipe # branch to system call - .globl compat_sys_times_wrapper -compat_sys_times_wrapper: +ENTRY(compat_sys_times_wrapper) llgtr %r2,%r2 # struct compat_tms * jg compat_sys_times # branch to system call - .globl sys32_brk_wrapper -sys32_brk_wrapper: +ENTRY(sys32_brk_wrapper) llgtr %r2,%r2 # unsigned long jg sys_brk # branch to system call - .globl sys32_setgid16_wrapper -sys32_setgid16_wrapper: +ENTRY(sys32_setgid16_wrapper) llgfr %r2,%r2 # __kernel_old_gid_emu31_t jg sys32_setgid16 # branch to system call #sys32_getgid16_wrapper # void - .globl sys32_signal_wrapper -sys32_signal_wrapper: +ENTRY(sys32_signal_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # __sighandler_t jg sys_signal @@ -207,55 +177,46 @@ sys32_signal_wrapper: #sys32_getegid16_wrapper # void - .globl sys32_acct_wrapper -sys32_acct_wrapper: +ENTRY(sys32_acct_wrapper) llgtr %r2,%r2 # char * jg sys_acct # branch to system call - .globl sys32_umount_wrapper -sys32_umount_wrapper: +ENTRY(sys32_umount_wrapper) llgtr %r2,%r2 # char * lgfr %r3,%r3 # int jg sys_umount # branch to system call - .globl compat_sys_ioctl_wrapper -compat_sys_ioctl_wrapper: +ENTRY(compat_sys_ioctl_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int llgfr %r4,%r4 # unsigned int jg compat_sys_ioctl # branch to system call - .globl compat_sys_fcntl_wrapper -compat_sys_fcntl_wrapper: +ENTRY(compat_sys_fcntl_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int llgfr %r4,%r4 # unsigned long jg compat_sys_fcntl # branch to system call - .globl sys32_setpgid_wrapper -sys32_setpgid_wrapper: +ENTRY(sys32_setpgid_wrapper) lgfr %r2,%r2 # pid_t lgfr %r3,%r3 # pid_t jg sys_setpgid # branch to system call - .globl sys32_umask_wrapper -sys32_umask_wrapper: +ENTRY(sys32_umask_wrapper) lgfr %r2,%r2 # int jg sys_umask # branch to system call - .globl sys32_chroot_wrapper -sys32_chroot_wrapper: +ENTRY(sys32_chroot_wrapper) llgtr %r2,%r2 # char * jg sys_chroot # branch to system call - .globl sys32_ustat_wrapper -sys32_ustat_wrapper: +ENTRY(sys32_ustat_wrapper) llgfr %r2,%r2 # dev_t llgtr %r3,%r3 # struct ustat * jg compat_sys_ustat - .globl sys32_dup2_wrapper -sys32_dup2_wrapper: +ENTRY(sys32_dup2_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int jg sys_dup2 # branch to system call @@ -266,262 +227,220 @@ sys32_dup2_wrapper: #sys32_setsid_wrapper # void - .globl sys32_sigaction_wrapper -sys32_sigaction_wrapper: +ENTRY(sys32_sigaction_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const struct old_sigaction * llgtr %r4,%r4 # struct old_sigaction32 * jg sys32_sigaction # branch to system call - .globl sys32_setreuid16_wrapper -sys32_setreuid16_wrapper: +ENTRY(sys32_setreuid16_wrapper) llgfr %r2,%r2 # __kernel_old_uid_emu31_t llgfr %r3,%r3 # __kernel_old_uid_emu31_t jg sys32_setreuid16 # branch to system call - .globl sys32_setregid16_wrapper -sys32_setregid16_wrapper: +ENTRY(sys32_setregid16_wrapper) llgfr %r2,%r2 # __kernel_old_gid_emu31_t llgfr %r3,%r3 # __kernel_old_gid_emu31_t jg sys32_setregid16 # branch to system call - .globl sys_sigsuspend_wrapper -sys_sigsuspend_wrapper: +ENTRY(sys_sigsuspend_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgfr %r4,%r4 # old_sigset_t jg sys_sigsuspend - .globl compat_sys_sigpending_wrapper -compat_sys_sigpending_wrapper: +ENTRY(compat_sys_sigpending_wrapper) llgtr %r2,%r2 # compat_old_sigset_t * jg compat_sys_sigpending # branch to system call - .globl sys32_sethostname_wrapper -sys32_sethostname_wrapper: +ENTRY(sys32_sethostname_wrapper) llgtr %r2,%r2 # char * lgfr %r3,%r3 # int jg sys_sethostname # branch to system call - .globl compat_sys_setrlimit_wrapper -compat_sys_setrlimit_wrapper: +ENTRY(compat_sys_setrlimit_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # struct rlimit_emu31 * jg compat_sys_setrlimit # branch to system call - .globl compat_sys_old_getrlimit_wrapper -compat_sys_old_getrlimit_wrapper: +ENTRY(compat_sys_old_getrlimit_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # struct rlimit_emu31 * jg compat_sys_old_getrlimit # branch to system call - .globl compat_sys_getrlimit_wrapper -compat_sys_getrlimit_wrapper: +ENTRY(compat_sys_getrlimit_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # struct rlimit_emu31 * jg compat_sys_getrlimit # branch to system call - .globl sys32_mmap2_wrapper -sys32_mmap2_wrapper: +ENTRY(sys32_mmap2_wrapper) llgtr %r2,%r2 # struct mmap_arg_struct_emu31 * jg sys32_mmap2 # branch to system call - .globl compat_sys_getrusage_wrapper -compat_sys_getrusage_wrapper: +ENTRY(compat_sys_getrusage_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct rusage_emu31 * jg compat_sys_getrusage # branch to system call - .globl compat_sys_gettimeofday_wrapper -compat_sys_gettimeofday_wrapper: +ENTRY(compat_sys_gettimeofday_wrapper) llgtr %r2,%r2 # struct timeval_emu31 * llgtr %r3,%r3 # struct timezone * jg compat_sys_gettimeofday # branch to system call - .globl compat_sys_settimeofday_wrapper -compat_sys_settimeofday_wrapper: +ENTRY(compat_sys_settimeofday_wrapper) llgtr %r2,%r2 # struct timeval_emu31 * llgtr %r3,%r3 # struct timezone * jg compat_sys_settimeofday # branch to system call - .globl sys32_getgroups16_wrapper -sys32_getgroups16_wrapper: +ENTRY(sys32_getgroups16_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # __kernel_old_gid_emu31_t * jg sys32_getgroups16 # branch to system call - .globl sys32_setgroups16_wrapper -sys32_setgroups16_wrapper: +ENTRY(sys32_setgroups16_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # __kernel_old_gid_emu31_t * jg sys32_setgroups16 # branch to system call - .globl sys32_symlink_wrapper -sys32_symlink_wrapper: +ENTRY(sys32_symlink_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # const char * jg sys_symlink # branch to system call - .globl sys32_readlink_wrapper -sys32_readlink_wrapper: +ENTRY(sys32_readlink_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # char * lgfr %r4,%r4 # int jg sys_readlink # branch to system call - .globl sys32_uselib_wrapper -sys32_uselib_wrapper: +ENTRY(sys32_uselib_wrapper) llgtr %r2,%r2 # const char * jg sys_uselib # branch to system call - .globl sys32_swapon_wrapper -sys32_swapon_wrapper: +ENTRY(sys32_swapon_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int jg sys_swapon # branch to system call - .globl sys32_reboot_wrapper -sys32_reboot_wrapper: +ENTRY(sys32_reboot_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgfr %r4,%r4 # unsigned int llgtr %r5,%r5 # void * jg sys_reboot # branch to system call - .globl old32_readdir_wrapper -old32_readdir_wrapper: +ENTRY(old32_readdir_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # void * llgfr %r4,%r4 # unsigned int jg compat_sys_old_readdir # branch to system call - .globl old32_mmap_wrapper -old32_mmap_wrapper: +ENTRY(old32_mmap_wrapper) llgtr %r2,%r2 # struct mmap_arg_struct_emu31 * jg old32_mmap # branch to system call - .globl sys32_munmap_wrapper -sys32_munmap_wrapper: +ENTRY(sys32_munmap_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # size_t jg sys_munmap # branch to system call - .globl sys32_truncate_wrapper -sys32_truncate_wrapper: +ENTRY(sys32_truncate_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # long jg sys_truncate # branch to system call - .globl sys32_ftruncate_wrapper -sys32_ftruncate_wrapper: +ENTRY(sys32_ftruncate_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned long jg sys_ftruncate # branch to system call - .globl sys32_fchmod_wrapper -sys32_fchmod_wrapper: +ENTRY(sys32_fchmod_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # mode_t jg sys_fchmod # branch to system call - .globl sys32_fchown16_wrapper -sys32_fchown16_wrapper: +ENTRY(sys32_fchown16_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # compat_uid_t llgfr %r4,%r4 # compat_uid_t jg sys32_fchown16 # branch to system call - .globl sys32_getpriority_wrapper -sys32_getpriority_wrapper: +ENTRY(sys32_getpriority_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int jg sys_getpriority # branch to system call - .globl sys32_setpriority_wrapper -sys32_setpriority_wrapper: +ENTRY(sys32_setpriority_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int lgfr %r4,%r4 # int jg sys_setpriority # branch to system call - .globl compat_sys_statfs_wrapper -compat_sys_statfs_wrapper: +ENTRY(compat_sys_statfs_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct compat_statfs * jg compat_sys_statfs # branch to system call - .globl compat_sys_fstatfs_wrapper -compat_sys_fstatfs_wrapper: +ENTRY(compat_sys_fstatfs_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # struct compat_statfs * jg compat_sys_fstatfs # branch to system call - .globl compat_sys_socketcall_wrapper -compat_sys_socketcall_wrapper: +ENTRY(compat_sys_socketcall_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # u32 * jg compat_sys_socketcall # branch to system call - .globl sys32_syslog_wrapper -sys32_syslog_wrapper: +ENTRY(sys32_syslog_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # char * lgfr %r4,%r4 # int jg sys_syslog # branch to system call - .globl compat_sys_setitimer_wrapper -compat_sys_setitimer_wrapper: +ENTRY(compat_sys_setitimer_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct itimerval_emu31 * llgtr %r4,%r4 # struct itimerval_emu31 * jg compat_sys_setitimer # branch to system call - .globl compat_sys_getitimer_wrapper -compat_sys_getitimer_wrapper: +ENTRY(compat_sys_getitimer_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct itimerval_emu31 * jg compat_sys_getitimer # branch to system call - .globl compat_sys_newstat_wrapper -compat_sys_newstat_wrapper: +ENTRY(compat_sys_newstat_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct stat_emu31 * jg compat_sys_newstat # branch to system call - .globl compat_sys_newlstat_wrapper -compat_sys_newlstat_wrapper: +ENTRY(compat_sys_newlstat_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct stat_emu31 * jg compat_sys_newlstat # branch to system call - .globl compat_sys_newfstat_wrapper -compat_sys_newfstat_wrapper: +ENTRY(compat_sys_newfstat_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # struct stat_emu31 * jg compat_sys_newfstat # branch to system call #sys32_vhangup_wrapper # void - .globl compat_sys_wait4_wrapper -compat_sys_wait4_wrapper: +ENTRY(compat_sys_wait4_wrapper) lgfr %r2,%r2 # pid_t llgtr %r3,%r3 # unsigned int * lgfr %r4,%r4 # int llgtr %r5,%r5 # struct rusage * jg compat_sys_wait4 # branch to system call - .globl sys32_swapoff_wrapper -sys32_swapoff_wrapper: +ENTRY(sys32_swapoff_wrapper) llgtr %r2,%r2 # const char * jg sys_swapoff # branch to system call - .globl compat_sys_sysinfo_wrapper -compat_sys_sysinfo_wrapper: +ENTRY(compat_sys_sysinfo_wrapper) llgtr %r2,%r2 # struct sysinfo_emu31 * jg compat_sys_sysinfo # branch to system call - .globl sys32_ipc_wrapper -sys32_ipc_wrapper: +ENTRY(sys32_ipc_wrapper) llgfr %r2,%r2 # uint lgfr %r3,%r3 # int lgfr %r4,%r4 # int @@ -529,8 +448,7 @@ sys32_ipc_wrapper: llgfr %r6,%r6 # u32 jg sys32_ipc # branch to system call - .globl sys32_fsync_wrapper -sys32_fsync_wrapper: +ENTRY(sys32_fsync_wrapper) llgfr %r2,%r2 # unsigned int jg sys_fsync # branch to system call @@ -538,97 +456,81 @@ sys32_fsync_wrapper: #sys32_clone_wrapper # done in clone_glue - .globl sys32_setdomainname_wrapper -sys32_setdomainname_wrapper: +ENTRY(sys32_setdomainname_wrapper) llgtr %r2,%r2 # char * lgfr %r3,%r3 # int jg sys_setdomainname # branch to system call - .globl sys32_newuname_wrapper -sys32_newuname_wrapper: +ENTRY(sys32_newuname_wrapper) llgtr %r2,%r2 # struct new_utsname * jg sys_newuname # branch to system call - .globl compat_sys_adjtimex_wrapper -compat_sys_adjtimex_wrapper: +ENTRY(compat_sys_adjtimex_wrapper) llgtr %r2,%r2 # struct compat_timex * jg compat_sys_adjtimex # branch to system call - .globl sys32_mprotect_wrapper -sys32_mprotect_wrapper: +ENTRY(sys32_mprotect_wrapper) llgtr %r2,%r2 # unsigned long (actually pointer llgfr %r3,%r3 # size_t llgfr %r4,%r4 # unsigned long jg sys_mprotect # branch to system call - .globl compat_sys_sigprocmask_wrapper -compat_sys_sigprocmask_wrapper: +ENTRY(compat_sys_sigprocmask_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # compat_old_sigset_t * llgtr %r4,%r4 # compat_old_sigset_t * jg compat_sys_sigprocmask # branch to system call - .globl sys_init_module_wrapper -sys_init_module_wrapper: +ENTRY(sys_init_module_wrapper) llgtr %r2,%r2 # void * llgfr %r3,%r3 # unsigned long llgtr %r4,%r4 # char * jg sys_init_module # branch to system call - .globl sys_delete_module_wrapper -sys_delete_module_wrapper: +ENTRY(sys_delete_module_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # unsigned int jg sys_delete_module # branch to system call - .globl sys32_quotactl_wrapper -sys32_quotactl_wrapper: +ENTRY(sys32_quotactl_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # const char * llgfr %r4,%r4 # qid_t llgtr %r5,%r5 # caddr_t jg sys_quotactl # branch to system call - .globl sys32_getpgid_wrapper -sys32_getpgid_wrapper: +ENTRY(sys32_getpgid_wrapper) lgfr %r2,%r2 # pid_t jg sys_getpgid # branch to system call - .globl sys32_fchdir_wrapper -sys32_fchdir_wrapper: +ENTRY(sys32_fchdir_wrapper) llgfr %r2,%r2 # unsigned int jg sys_fchdir # branch to system call - .globl sys32_bdflush_wrapper -sys32_bdflush_wrapper: +ENTRY(sys32_bdflush_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # long jg sys_bdflush # branch to system call - .globl sys32_sysfs_wrapper -sys32_sysfs_wrapper: +ENTRY(sys32_sysfs_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long jg sys_sysfs # branch to system call - .globl sys32_personality_wrapper -sys32_personality_wrapper: +ENTRY(sys32_personality_wrapper) llgfr %r2,%r2 # unsigned int jg sys_s390_personality # branch to system call - .globl sys32_setfsuid16_wrapper -sys32_setfsuid16_wrapper: +ENTRY(sys32_setfsuid16_wrapper) llgfr %r2,%r2 # __kernel_old_uid_emu31_t jg sys32_setfsuid16 # branch to system call - .globl sys32_setfsgid16_wrapper -sys32_setfsgid16_wrapper: +ENTRY(sys32_setfsgid16_wrapper) llgfr %r2,%r2 # __kernel_old_gid_emu31_t jg sys32_setfsgid16 # branch to system call - .globl sys32_llseek_wrapper -sys32_llseek_wrapper: +ENTRY(sys32_llseek_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long @@ -636,15 +538,13 @@ sys32_llseek_wrapper: llgfr %r6,%r6 # unsigned int jg sys_llseek # branch to system call - .globl sys32_getdents_wrapper -sys32_getdents_wrapper: +ENTRY(sys32_getdents_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # void * llgfr %r4,%r4 # unsigned int jg compat_sys_getdents # branch to system call - .globl compat_sys_select_wrapper -compat_sys_select_wrapper: +ENTRY(compat_sys_select_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # compat_fd_set * llgtr %r4,%r4 # compat_fd_set * @@ -652,112 +552,94 @@ compat_sys_select_wrapper: llgtr %r6,%r6 # struct compat_timeval * jg compat_sys_select # branch to system call - .globl sys32_flock_wrapper -sys32_flock_wrapper: +ENTRY(sys32_flock_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int jg sys_flock # branch to system call - .globl sys32_msync_wrapper -sys32_msync_wrapper: +ENTRY(sys32_msync_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # size_t lgfr %r4,%r4 # int jg sys_msync # branch to system call - .globl compat_sys_readv_wrapper -compat_sys_readv_wrapper: +ENTRY(compat_sys_readv_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const struct compat_iovec * llgfr %r4,%r4 # unsigned long jg compat_sys_readv # branch to system call - .globl compat_sys_writev_wrapper -compat_sys_writev_wrapper: +ENTRY(compat_sys_writev_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const struct compat_iovec * llgfr %r4,%r4 # unsigned long jg compat_sys_writev # branch to system call - .globl sys32_getsid_wrapper -sys32_getsid_wrapper: +ENTRY(sys32_getsid_wrapper) lgfr %r2,%r2 # pid_t jg sys_getsid # branch to system call - .globl sys32_fdatasync_wrapper -sys32_fdatasync_wrapper: +ENTRY(sys32_fdatasync_wrapper) llgfr %r2,%r2 # unsigned int jg sys_fdatasync # branch to system call - .globl sys32_mlock_wrapper -sys32_mlock_wrapper: +ENTRY(sys32_mlock_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # size_t jg sys_mlock # branch to system call - .globl sys32_munlock_wrapper -sys32_munlock_wrapper: +ENTRY(sys32_munlock_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # size_t jg sys_munlock # branch to system call - .globl sys32_mlockall_wrapper -sys32_mlockall_wrapper: +ENTRY(sys32_mlockall_wrapper) lgfr %r2,%r2 # int jg sys_mlockall # branch to system call #sys32_munlockall_wrapper # void - .globl sys32_sched_setparam_wrapper -sys32_sched_setparam_wrapper: +ENTRY(sys32_sched_setparam_wrapper) lgfr %r2,%r2 # pid_t llgtr %r3,%r3 # struct sched_param * jg sys_sched_setparam # branch to system call - .globl sys32_sched_getparam_wrapper -sys32_sched_getparam_wrapper: +ENTRY(sys32_sched_getparam_wrapper) lgfr %r2,%r2 # pid_t llgtr %r3,%r3 # struct sched_param * jg sys_sched_getparam # branch to system call - .globl sys32_sched_setscheduler_wrapper -sys32_sched_setscheduler_wrapper: +ENTRY(sys32_sched_setscheduler_wrapper) lgfr %r2,%r2 # pid_t lgfr %r3,%r3 # int llgtr %r4,%r4 # struct sched_param * jg sys_sched_setscheduler # branch to system call - .globl sys32_sched_getscheduler_wrapper -sys32_sched_getscheduler_wrapper: +ENTRY(sys32_sched_getscheduler_wrapper) lgfr %r2,%r2 # pid_t jg sys_sched_getscheduler # branch to system call #sys32_sched_yield_wrapper # void - .globl sys32_sched_get_priority_max_wrapper -sys32_sched_get_priority_max_wrapper: +ENTRY(sys32_sched_get_priority_max_wrapper) lgfr %r2,%r2 # int jg sys_sched_get_priority_max # branch to system call - .globl sys32_sched_get_priority_min_wrapper -sys32_sched_get_priority_min_wrapper: +ENTRY(sys32_sched_get_priority_min_wrapper) lgfr %r2,%r2 # int jg sys_sched_get_priority_min # branch to system call - .globl sys32_sched_rr_get_interval_wrapper -sys32_sched_rr_get_interval_wrapper: +ENTRY(sys32_sched_rr_get_interval_wrapper) lgfr %r2,%r2 # pid_t llgtr %r3,%r3 # struct compat_timespec * jg sys32_sched_rr_get_interval # branch to system call - .globl compat_sys_nanosleep_wrapper -compat_sys_nanosleep_wrapper: +ENTRY(compat_sys_nanosleep_wrapper) llgtr %r2,%r2 # struct compat_timespec * llgtr %r3,%r3 # struct compat_timespec * jg compat_sys_nanosleep # branch to system call - .globl sys32_mremap_wrapper -sys32_mremap_wrapper: +ENTRY(sys32_mremap_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long @@ -765,50 +647,37 @@ sys32_mremap_wrapper: llgfr %r6,%r6 # unsigned long jg sys_mremap # branch to system call - .globl sys32_setresuid16_wrapper -sys32_setresuid16_wrapper: +ENTRY(sys32_setresuid16_wrapper) llgfr %r2,%r2 # __kernel_old_uid_emu31_t llgfr %r3,%r3 # __kernel_old_uid_emu31_t llgfr %r4,%r4 # __kernel_old_uid_emu31_t jg sys32_setresuid16 # branch to system call - .globl sys32_getresuid16_wrapper -sys32_getresuid16_wrapper: +ENTRY(sys32_getresuid16_wrapper) llgtr %r2,%r2 # __kernel_old_uid_emu31_t * llgtr %r3,%r3 # __kernel_old_uid_emu31_t * llgtr %r4,%r4 # __kernel_old_uid_emu31_t * jg sys32_getresuid16 # branch to system call - .globl sys32_poll_wrapper -sys32_poll_wrapper: +ENTRY(sys32_poll_wrapper) llgtr %r2,%r2 # struct pollfd * llgfr %r3,%r3 # unsigned int lgfr %r4,%r4 # long jg sys_poll # branch to system call - .globl compat_sys_nfsservctl_wrapper -compat_sys_nfsservctl_wrapper: - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct compat_nfsctl_arg* - llgtr %r4,%r4 # union compat_nfsctl_res* - jg compat_sys_nfsservctl # branch to system call - - .globl sys32_setresgid16_wrapper -sys32_setresgid16_wrapper: +ENTRY(sys32_setresgid16_wrapper) llgfr %r2,%r2 # __kernel_old_gid_emu31_t llgfr %r3,%r3 # __kernel_old_gid_emu31_t llgfr %r4,%r4 # __kernel_old_gid_emu31_t jg sys32_setresgid16 # branch to system call - .globl sys32_getresgid16_wrapper -sys32_getresgid16_wrapper: +ENTRY(sys32_getresgid16_wrapper) llgtr %r2,%r2 # __kernel_old_gid_emu31_t * llgtr %r3,%r3 # __kernel_old_gid_emu31_t * llgtr %r4,%r4 # __kernel_old_gid_emu31_t * jg sys32_getresgid16 # branch to system call - .globl sys32_prctl_wrapper -sys32_prctl_wrapper: +ENTRY(sys32_prctl_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long @@ -818,51 +687,44 @@ sys32_prctl_wrapper: #sys32_rt_sigreturn_wrapper # done in rt_sigreturn_glue - .globl sys32_rt_sigaction_wrapper -sys32_rt_sigaction_wrapper: +ENTRY(sys32_rt_sigaction_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const struct sigaction_emu31 * llgtr %r4,%r4 # const struct sigaction_emu31 * llgfr %r5,%r5 # size_t jg sys32_rt_sigaction # branch to system call - .globl sys32_rt_sigprocmask_wrapper -sys32_rt_sigprocmask_wrapper: +ENTRY(sys32_rt_sigprocmask_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # old_sigset_emu31 * llgtr %r4,%r4 # old_sigset_emu31 * llgfr %r5,%r5 # size_t jg sys32_rt_sigprocmask # branch to system call - .globl sys32_rt_sigpending_wrapper -sys32_rt_sigpending_wrapper: +ENTRY(sys32_rt_sigpending_wrapper) llgtr %r2,%r2 # sigset_emu31 * llgfr %r3,%r3 # size_t jg sys32_rt_sigpending # branch to system call - .globl compat_sys_rt_sigtimedwait_wrapper -compat_sys_rt_sigtimedwait_wrapper: +ENTRY(compat_sys_rt_sigtimedwait_wrapper) llgtr %r2,%r2 # const sigset_emu31_t * llgtr %r3,%r3 # siginfo_emu31_t * llgtr %r4,%r4 # const struct compat_timespec * llgfr %r5,%r5 # size_t jg compat_sys_rt_sigtimedwait # branch to system call - .globl sys32_rt_sigqueueinfo_wrapper -sys32_rt_sigqueueinfo_wrapper: +ENTRY(sys32_rt_sigqueueinfo_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgtr %r4,%r4 # siginfo_emu31_t * jg sys32_rt_sigqueueinfo # branch to system call - .globl compat_sys_rt_sigsuspend_wrapper -compat_sys_rt_sigsuspend_wrapper: +ENTRY(compat_sys_rt_sigsuspend_wrapper) llgtr %r2,%r2 # compat_sigset_t * llgfr %r3,%r3 # compat_size_t jg compat_sys_rt_sigsuspend - .globl sys32_pread64_wrapper -sys32_pread64_wrapper: +ENTRY(sys32_pread64_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # char * llgfr %r4,%r4 # size_t @@ -870,8 +732,7 @@ sys32_pread64_wrapper: llgfr %r6,%r6 # u32 jg sys32_pread64 # branch to system call - .globl sys32_pwrite64_wrapper -sys32_pwrite64_wrapper: +ENTRY(sys32_pwrite64_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # const char * llgfr %r4,%r4 # size_t @@ -879,39 +740,33 @@ sys32_pwrite64_wrapper: llgfr %r6,%r6 # u32 jg sys32_pwrite64 # branch to system call - .globl sys32_chown16_wrapper -sys32_chown16_wrapper: +ENTRY(sys32_chown16_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # __kernel_old_uid_emu31_t llgfr %r4,%r4 # __kernel_old_gid_emu31_t jg sys32_chown16 # branch to system call - .globl sys32_getcwd_wrapper -sys32_getcwd_wrapper: +ENTRY(sys32_getcwd_wrapper) llgtr %r2,%r2 # char * llgfr %r3,%r3 # unsigned long jg sys_getcwd # branch to system call - .globl sys32_capget_wrapper -sys32_capget_wrapper: +ENTRY(sys32_capget_wrapper) llgtr %r2,%r2 # cap_user_header_t llgtr %r3,%r3 # cap_user_data_t jg sys_capget # branch to system call - .globl sys32_capset_wrapper -sys32_capset_wrapper: +ENTRY(sys32_capset_wrapper) llgtr %r2,%r2 # cap_user_header_t llgtr %r3,%r3 # const cap_user_data_t jg sys_capset # branch to system call - .globl sys32_sigaltstack_wrapper -sys32_sigaltstack_wrapper: +ENTRY(sys32_sigaltstack_wrapper) llgtr %r2,%r2 # const stack_emu31_t * llgtr %r3,%r3 # stack_emu31_t * jg sys32_sigaltstack - .globl sys32_sendfile_wrapper -sys32_sendfile_wrapper: +ENTRY(sys32_sendfile_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgtr %r4,%r4 # __kernel_off_emu31_t * @@ -920,22 +775,19 @@ sys32_sendfile_wrapper: #sys32_vfork_wrapper # done in vfork_glue - .globl sys32_truncate64_wrapper -sys32_truncate64_wrapper: +ENTRY(sys32_truncate64_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long jg sys32_truncate64 # branch to system call - .globl sys32_ftruncate64_wrapper -sys32_ftruncate64_wrapper: +ENTRY(sys32_ftruncate64_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long jg sys32_ftruncate64 # branch to system call - .globl sys32_lchown_wrapper -sys32_lchown_wrapper: +ENTRY(sys32_lchown_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # uid_t llgfr %r4,%r4 # gid_t @@ -946,156 +798,131 @@ sys32_lchown_wrapper: #sys32_geteuid_wrapper # void #sys32_getegid_wrapper # void - .globl sys32_setreuid_wrapper -sys32_setreuid_wrapper: +ENTRY(sys32_setreuid_wrapper) llgfr %r2,%r2 # uid_t llgfr %r3,%r3 # uid_t jg sys_setreuid # branch to system call - .globl sys32_setregid_wrapper -sys32_setregid_wrapper: +ENTRY(sys32_setregid_wrapper) llgfr %r2,%r2 # gid_t llgfr %r3,%r3 # gid_t jg sys_setregid # branch to system call - .globl sys32_getgroups_wrapper -sys32_getgroups_wrapper: +ENTRY(sys32_getgroups_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # gid_t * jg sys_getgroups # branch to system call - .globl sys32_setgroups_wrapper -sys32_setgroups_wrapper: +ENTRY(sys32_setgroups_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # gid_t * jg sys_setgroups # branch to system call - .globl sys32_fchown_wrapper -sys32_fchown_wrapper: +ENTRY(sys32_fchown_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # uid_t llgfr %r4,%r4 # gid_t jg sys_fchown # branch to system call - .globl sys32_setresuid_wrapper -sys32_setresuid_wrapper: +ENTRY(sys32_setresuid_wrapper) llgfr %r2,%r2 # uid_t llgfr %r3,%r3 # uid_t llgfr %r4,%r4 # uid_t jg sys_setresuid # branch to system call - .globl sys32_getresuid_wrapper -sys32_getresuid_wrapper: +ENTRY(sys32_getresuid_wrapper) llgtr %r2,%r2 # uid_t * llgtr %r3,%r3 # uid_t * llgtr %r4,%r4 # uid_t * jg sys_getresuid # branch to system call - .globl sys32_setresgid_wrapper -sys32_setresgid_wrapper: +ENTRY(sys32_setresgid_wrapper) llgfr %r2,%r2 # gid_t llgfr %r3,%r3 # gid_t llgfr %r4,%r4 # gid_t jg sys_setresgid # branch to system call - .globl sys32_getresgid_wrapper -sys32_getresgid_wrapper: +ENTRY(sys32_getresgid_wrapper) llgtr %r2,%r2 # gid_t * llgtr %r3,%r3 # gid_t * llgtr %r4,%r4 # gid_t * jg sys_getresgid # branch to system call - .globl sys32_chown_wrapper -sys32_chown_wrapper: +ENTRY(sys32_chown_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # uid_t llgfr %r4,%r4 # gid_t jg sys_chown # branch to system call - .globl sys32_setuid_wrapper -sys32_setuid_wrapper: +ENTRY(sys32_setuid_wrapper) llgfr %r2,%r2 # uid_t jg sys_setuid # branch to system call - .globl sys32_setgid_wrapper -sys32_setgid_wrapper: +ENTRY(sys32_setgid_wrapper) llgfr %r2,%r2 # gid_t jg sys_setgid # branch to system call - .globl sys32_setfsuid_wrapper -sys32_setfsuid_wrapper: +ENTRY(sys32_setfsuid_wrapper) llgfr %r2,%r2 # uid_t jg sys_setfsuid # branch to system call - .globl sys32_setfsgid_wrapper -sys32_setfsgid_wrapper: +ENTRY(sys32_setfsgid_wrapper) llgfr %r2,%r2 # gid_t jg sys_setfsgid # branch to system call - .globl sys32_pivot_root_wrapper -sys32_pivot_root_wrapper: +ENTRY(sys32_pivot_root_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # const char * jg sys_pivot_root # branch to system call - .globl sys32_mincore_wrapper -sys32_mincore_wrapper: +ENTRY(sys32_mincore_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # size_t llgtr %r4,%r4 # unsigned char * jg sys_mincore # branch to system call - .globl sys32_madvise_wrapper -sys32_madvise_wrapper: +ENTRY(sys32_madvise_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # size_t lgfr %r4,%r4 # int jg sys_madvise # branch to system call - .globl sys32_getdents64_wrapper -sys32_getdents64_wrapper: +ENTRY(sys32_getdents64_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # void * llgfr %r4,%r4 # unsigned int jg sys_getdents64 # branch to system call - .globl compat_sys_fcntl64_wrapper -compat_sys_fcntl64_wrapper: +ENTRY(compat_sys_fcntl64_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int llgfr %r4,%r4 # unsigned long jg compat_sys_fcntl64 # branch to system call - .globl sys32_stat64_wrapper -sys32_stat64_wrapper: +ENTRY(sys32_stat64_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct stat64 * jg sys32_stat64 # branch to system call - .globl sys32_lstat64_wrapper -sys32_lstat64_wrapper: +ENTRY(sys32_lstat64_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct stat64 * jg sys32_lstat64 # branch to system call - .globl sys32_stime_wrapper -sys32_stime_wrapper: +ENTRY(sys32_stime_wrapper) llgtr %r2,%r2 # long * jg compat_sys_stime # branch to system call - .globl sys32_sysctl_wrapper -sys32_sysctl_wrapper: +ENTRY(sys32_sysctl_wrapper) llgtr %r2,%r2 # struct compat_sysctl_args * jg compat_sys_sysctl - .globl sys32_fstat64_wrapper -sys32_fstat64_wrapper: +ENTRY(sys32_fstat64_wrapper) llgfr %r2,%r2 # unsigned long llgtr %r3,%r3 # struct stat64 * jg sys32_fstat64 # branch to system call - .globl compat_sys_futex_wrapper -compat_sys_futex_wrapper: +ENTRY(compat_sys_futex_wrapper) llgtr %r2,%r2 # u32 * lgfr %r3,%r3 # int lgfr %r4,%r4 # int @@ -1105,8 +932,7 @@ compat_sys_futex_wrapper: stg %r0,160(%r15) jg compat_sys_futex # branch to system call - .globl sys32_setxattr_wrapper -sys32_setxattr_wrapper: +ENTRY(sys32_setxattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgtr %r4,%r4 # void * @@ -1114,8 +940,7 @@ sys32_setxattr_wrapper: lgfr %r6,%r6 # int jg sys_setxattr - .globl sys32_lsetxattr_wrapper -sys32_lsetxattr_wrapper: +ENTRY(sys32_lsetxattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgtr %r4,%r4 # void * @@ -1123,8 +948,7 @@ sys32_lsetxattr_wrapper: lgfr %r6,%r6 # int jg sys_lsetxattr - .globl sys32_fsetxattr_wrapper -sys32_fsetxattr_wrapper: +ENTRY(sys32_fsetxattr_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # char * llgtr %r4,%r4 # void * @@ -1132,124 +956,106 @@ sys32_fsetxattr_wrapper: lgfr %r6,%r6 # int jg sys_fsetxattr - .globl sys32_getxattr_wrapper -sys32_getxattr_wrapper: +ENTRY(sys32_getxattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgtr %r4,%r4 # void * llgfr %r5,%r5 # size_t jg sys_getxattr - .globl sys32_lgetxattr_wrapper -sys32_lgetxattr_wrapper: +ENTRY(sys32_lgetxattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgtr %r4,%r4 # void * llgfr %r5,%r5 # size_t jg sys_lgetxattr - .globl sys32_fgetxattr_wrapper -sys32_fgetxattr_wrapper: +ENTRY(sys32_fgetxattr_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # char * llgtr %r4,%r4 # void * llgfr %r5,%r5 # size_t jg sys_fgetxattr - .globl sys32_listxattr_wrapper -sys32_listxattr_wrapper: +ENTRY(sys32_listxattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgfr %r4,%r4 # size_t jg sys_listxattr - .globl sys32_llistxattr_wrapper -sys32_llistxattr_wrapper: +ENTRY(sys32_llistxattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * llgfr %r4,%r4 # size_t jg sys_llistxattr - .globl sys32_flistxattr_wrapper -sys32_flistxattr_wrapper: +ENTRY(sys32_flistxattr_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # char * llgfr %r4,%r4 # size_t jg sys_flistxattr - .globl sys32_removexattr_wrapper -sys32_removexattr_wrapper: +ENTRY(sys32_removexattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * jg sys_removexattr - .globl sys32_lremovexattr_wrapper -sys32_lremovexattr_wrapper: +ENTRY(sys32_lremovexattr_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # char * jg sys_lremovexattr - .globl sys32_fremovexattr_wrapper -sys32_fremovexattr_wrapper: +ENTRY(sys32_fremovexattr_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # char * jg sys_fremovexattr - .globl sys32_sched_setaffinity_wrapper -sys32_sched_setaffinity_wrapper: +ENTRY(sys32_sched_setaffinity_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # unsigned int llgtr %r4,%r4 # unsigned long * jg compat_sys_sched_setaffinity - .globl sys32_sched_getaffinity_wrapper -sys32_sched_getaffinity_wrapper: +ENTRY(sys32_sched_getaffinity_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # unsigned int llgtr %r4,%r4 # unsigned long * jg compat_sys_sched_getaffinity - .globl sys32_exit_group_wrapper -sys32_exit_group_wrapper: +ENTRY(sys32_exit_group_wrapper) lgfr %r2,%r2 # int jg sys_exit_group # branch to system call - .globl sys32_set_tid_address_wrapper -sys32_set_tid_address_wrapper: +ENTRY(sys32_set_tid_address_wrapper) llgtr %r2,%r2 # int * jg sys_set_tid_address # branch to system call - .globl sys_epoll_create_wrapper -sys_epoll_create_wrapper: +ENTRY(sys_epoll_create_wrapper) lgfr %r2,%r2 # int jg sys_epoll_create # branch to system call - .globl sys_epoll_ctl_wrapper -sys_epoll_ctl_wrapper: +ENTRY(sys_epoll_ctl_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int lgfr %r4,%r4 # int llgtr %r5,%r5 # struct epoll_event * jg sys_epoll_ctl # branch to system call - .globl sys_epoll_wait_wrapper -sys_epoll_wait_wrapper: +ENTRY(sys_epoll_wait_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct epoll_event * lgfr %r4,%r4 # int lgfr %r5,%r5 # int jg sys_epoll_wait # branch to system call - .globl sys32_lookup_dcookie_wrapper -sys32_lookup_dcookie_wrapper: +ENTRY(sys32_lookup_dcookie_wrapper) sllg %r2,%r2,32 # get high word of 64bit dcookie or %r2,%r3 # get low word of 64bit dcookie llgtr %r3,%r4 # char * llgfr %r4,%r5 # size_t jg sys_lookup_dcookie - .globl sys32_fadvise64_wrapper -sys32_fadvise64_wrapper: +ENTRY(sys32_fadvise64_wrapper) lgfr %r2,%r2 # int sllg %r3,%r3,32 # get high word of 64bit loff_t or %r3,%r4 # get low word of 64bit loff_t @@ -1257,81 +1063,68 @@ sys32_fadvise64_wrapper: lgfr %r5,%r6 # int jg sys32_fadvise64 - .globl sys32_fadvise64_64_wrapper -sys32_fadvise64_64_wrapper: +ENTRY(sys32_fadvise64_64_wrapper) llgtr %r2,%r2 # struct fadvise64_64_args * jg sys32_fadvise64_64 - .globl sys32_clock_settime_wrapper -sys32_clock_settime_wrapper: +ENTRY(sys32_clock_settime_wrapper) lgfr %r2,%r2 # clockid_t (int) llgtr %r3,%r3 # struct compat_timespec * jg compat_sys_clock_settime - .globl sys32_clock_gettime_wrapper -sys32_clock_gettime_wrapper: +ENTRY(sys32_clock_gettime_wrapper) lgfr %r2,%r2 # clockid_t (int) llgtr %r3,%r3 # struct compat_timespec * jg compat_sys_clock_gettime - .globl sys32_clock_getres_wrapper -sys32_clock_getres_wrapper: +ENTRY(sys32_clock_getres_wrapper) lgfr %r2,%r2 # clockid_t (int) llgtr %r3,%r3 # struct compat_timespec * jg compat_sys_clock_getres - .globl sys32_clock_nanosleep_wrapper -sys32_clock_nanosleep_wrapper: +ENTRY(sys32_clock_nanosleep_wrapper) lgfr %r2,%r2 # clockid_t (int) lgfr %r3,%r3 # int llgtr %r4,%r4 # struct compat_timespec * llgtr %r5,%r5 # struct compat_timespec * jg compat_sys_clock_nanosleep - .globl sys32_timer_create_wrapper -sys32_timer_create_wrapper: +ENTRY(sys32_timer_create_wrapper) lgfr %r2,%r2 # timer_t (int) llgtr %r3,%r3 # struct compat_sigevent * llgtr %r4,%r4 # timer_t * jg compat_sys_timer_create - .globl sys32_timer_settime_wrapper -sys32_timer_settime_wrapper: +ENTRY(sys32_timer_settime_wrapper) lgfr %r2,%r2 # timer_t (int) lgfr %r3,%r3 # int llgtr %r4,%r4 # struct compat_itimerspec * llgtr %r5,%r5 # struct compat_itimerspec * jg compat_sys_timer_settime - .globl sys32_timer_gettime_wrapper -sys32_timer_gettime_wrapper: +ENTRY(sys32_timer_gettime_wrapper) lgfr %r2,%r2 # timer_t (int) llgtr %r3,%r3 # struct compat_itimerspec * jg compat_sys_timer_gettime - .globl sys32_timer_getoverrun_wrapper -sys32_timer_getoverrun_wrapper: +ENTRY(sys32_timer_getoverrun_wrapper) lgfr %r2,%r2 # timer_t (int) jg sys_timer_getoverrun - .globl sys32_timer_delete_wrapper -sys32_timer_delete_wrapper: +ENTRY(sys32_timer_delete_wrapper) lgfr %r2,%r2 # timer_t (int) jg sys_timer_delete - .globl sys32_io_setup_wrapper -sys32_io_setup_wrapper: +ENTRY(sys32_io_setup_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # u32 * jg compat_sys_io_setup - .globl sys32_io_destroy_wrapper -sys32_io_destroy_wrapper: +ENTRY(sys32_io_destroy_wrapper) llgfr %r2,%r2 # (aio_context_t) u32 jg sys_io_destroy - .globl sys32_io_getevents_wrapper -sys32_io_getevents_wrapper: +ENTRY(sys32_io_getevents_wrapper) llgfr %r2,%r2 # (aio_context_t) u32 lgfr %r3,%r3 # long lgfr %r4,%r4 # long @@ -1339,49 +1132,42 @@ sys32_io_getevents_wrapper: llgtr %r6,%r6 # struct compat_timespec * jg compat_sys_io_getevents - .globl sys32_io_submit_wrapper -sys32_io_submit_wrapper: +ENTRY(sys32_io_submit_wrapper) llgfr %r2,%r2 # (aio_context_t) u32 lgfr %r3,%r3 # long llgtr %r4,%r4 # struct iocb ** jg compat_sys_io_submit - .globl sys32_io_cancel_wrapper -sys32_io_cancel_wrapper: +ENTRY(sys32_io_cancel_wrapper) llgfr %r2,%r2 # (aio_context_t) u32 llgtr %r3,%r3 # struct iocb * llgtr %r4,%r4 # struct io_event * jg sys_io_cancel - .globl compat_sys_statfs64_wrapper -compat_sys_statfs64_wrapper: +ENTRY(compat_sys_statfs64_wrapper) llgtr %r2,%r2 # const char * llgfr %r3,%r3 # compat_size_t llgtr %r4,%r4 # struct compat_statfs64 * jg compat_sys_statfs64 - .globl compat_sys_fstatfs64_wrapper -compat_sys_fstatfs64_wrapper: +ENTRY(compat_sys_fstatfs64_wrapper) llgfr %r2,%r2 # unsigned int fd llgfr %r3,%r3 # compat_size_t llgtr %r4,%r4 # struct compat_statfs64 * jg compat_sys_fstatfs64 - .globl compat_sys_mq_open_wrapper -compat_sys_mq_open_wrapper: +ENTRY(compat_sys_mq_open_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int llgfr %r4,%r4 # mode_t llgtr %r5,%r5 # struct compat_mq_attr * jg compat_sys_mq_open - .globl sys32_mq_unlink_wrapper -sys32_mq_unlink_wrapper: +ENTRY(sys32_mq_unlink_wrapper) llgtr %r2,%r2 # const char * jg sys_mq_unlink - .globl compat_sys_mq_timedsend_wrapper -compat_sys_mq_timedsend_wrapper: +ENTRY(compat_sys_mq_timedsend_wrapper) lgfr %r2,%r2 # mqd_t llgtr %r3,%r3 # const char * llgfr %r4,%r4 # size_t @@ -1389,8 +1175,7 @@ compat_sys_mq_timedsend_wrapper: llgtr %r6,%r6 # const struct compat_timespec * jg compat_sys_mq_timedsend - .globl compat_sys_mq_timedreceive_wrapper -compat_sys_mq_timedreceive_wrapper: +ENTRY(compat_sys_mq_timedreceive_wrapper) lgfr %r2,%r2 # mqd_t llgtr %r3,%r3 # char * llgfr %r4,%r4 # size_t @@ -1398,21 +1183,18 @@ compat_sys_mq_timedreceive_wrapper: llgtr %r6,%r6 # const struct compat_timespec * jg compat_sys_mq_timedreceive - .globl compat_sys_mq_notify_wrapper -compat_sys_mq_notify_wrapper: +ENTRY(compat_sys_mq_notify_wrapper) lgfr %r2,%r2 # mqd_t llgtr %r3,%r3 # struct compat_sigevent * jg compat_sys_mq_notify - .globl compat_sys_mq_getsetattr_wrapper -compat_sys_mq_getsetattr_wrapper: +ENTRY(compat_sys_mq_getsetattr_wrapper) lgfr %r2,%r2 # mqd_t llgtr %r3,%r3 # struct compat_mq_attr * llgtr %r4,%r4 # struct compat_mq_attr * jg compat_sys_mq_getsetattr - .globl compat_sys_add_key_wrapper -compat_sys_add_key_wrapper: +ENTRY(compat_sys_add_key_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # const char * llgtr %r4,%r4 # const void * @@ -1420,16 +1202,14 @@ compat_sys_add_key_wrapper: llgfr %r6,%r6 # (key_serial_t) u32 jg sys_add_key - .globl compat_sys_request_key_wrapper -compat_sys_request_key_wrapper: +ENTRY(compat_sys_request_key_wrapper) llgtr %r2,%r2 # const char * llgtr %r3,%r3 # const char * llgtr %r4,%r4 # const void * llgfr %r5,%r5 # (key_serial_t) u32 jg sys_request_key - .globl sys32_remap_file_pages_wrapper -sys32_remap_file_pages_wrapper: +ENTRY(sys32_remap_file_pages_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # unsigned long llgfr %r4,%r4 # unsigned long @@ -1437,8 +1217,7 @@ sys32_remap_file_pages_wrapper: llgfr %r6,%r6 # unsigned long jg sys_remap_file_pages - .globl compat_sys_waitid_wrapper -compat_sys_waitid_wrapper: +ENTRY(compat_sys_waitid_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # pid_t llgtr %r4,%r4 # siginfo_emu31_t * @@ -1446,65 +1225,56 @@ compat_sys_waitid_wrapper: llgtr %r6,%r6 # struct rusage_emu31 * jg compat_sys_waitid - .globl compat_sys_kexec_load_wrapper -compat_sys_kexec_load_wrapper: +ENTRY(compat_sys_kexec_load_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # unsigned long llgtr %r4,%r4 # struct kexec_segment * llgfr %r5,%r5 # unsigned long jg compat_sys_kexec_load - .globl sys_ioprio_set_wrapper -sys_ioprio_set_wrapper: +ENTRY(sys_ioprio_set_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int lgfr %r4,%r4 # int jg sys_ioprio_set - .globl sys_ioprio_get_wrapper -sys_ioprio_get_wrapper: +ENTRY(sys_ioprio_get_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int jg sys_ioprio_get - .globl sys_inotify_add_watch_wrapper -sys_inotify_add_watch_wrapper: +ENTRY(sys_inotify_add_watch_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * llgfr %r4,%r4 # u32 jg sys_inotify_add_watch - .globl sys_inotify_rm_watch_wrapper -sys_inotify_rm_watch_wrapper: +ENTRY(sys_inotify_rm_watch_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # u32 jg sys_inotify_rm_watch - .globl compat_sys_openat_wrapper -compat_sys_openat_wrapper: +ENTRY(compat_sys_openat_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int lgfr %r5,%r5 # int jg compat_sys_openat - .globl sys_mkdirat_wrapper -sys_mkdirat_wrapper: +ENTRY(sys_mkdirat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int jg sys_mkdirat - .globl sys_mknodat_wrapper -sys_mknodat_wrapper: +ENTRY(sys_mknodat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int llgfr %r5,%r5 # unsigned int jg sys_mknodat - .globl sys_fchownat_wrapper -sys_fchownat_wrapper: +ENTRY(sys_fchownat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * llgfr %r4,%r4 # uid_t @@ -1512,38 +1282,33 @@ sys_fchownat_wrapper: lgfr %r6,%r6 # int jg sys_fchownat - .globl compat_sys_futimesat_wrapper -compat_sys_futimesat_wrapper: +ENTRY(compat_sys_futimesat_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # char * llgtr %r4,%r4 # struct timeval * jg compat_sys_futimesat - .globl sys32_fstatat64_wrapper -sys32_fstatat64_wrapper: +ENTRY(sys32_fstatat64_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # char * llgtr %r4,%r4 # struct stat64 * lgfr %r5,%r5 # int jg sys32_fstatat64 - .globl sys_unlinkat_wrapper -sys_unlinkat_wrapper: +ENTRY(sys_unlinkat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int jg sys_unlinkat - .globl sys_renameat_wrapper -sys_renameat_wrapper: +ENTRY(sys_renameat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int llgtr %r5,%r5 # const char * jg sys_renameat - .globl sys_linkat_wrapper -sys_linkat_wrapper: +ENTRY(sys_linkat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int @@ -1551,37 +1316,32 @@ sys_linkat_wrapper: lgfr %r6,%r6 # int jg sys_linkat - .globl sys_symlinkat_wrapper -sys_symlinkat_wrapper: +ENTRY(sys_symlinkat_wrapper) llgtr %r2,%r2 # const char * lgfr %r3,%r3 # int llgtr %r4,%r4 # const char * jg sys_symlinkat - .globl sys_readlinkat_wrapper -sys_readlinkat_wrapper: +ENTRY(sys_readlinkat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * llgtr %r4,%r4 # char * lgfr %r5,%r5 # int jg sys_readlinkat - .globl sys_fchmodat_wrapper -sys_fchmodat_wrapper: +ENTRY(sys_fchmodat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * llgfr %r4,%r4 # mode_t jg sys_fchmodat - .globl sys_faccessat_wrapper -sys_faccessat_wrapper: +ENTRY(sys_faccessat_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char * lgfr %r4,%r4 # int jg sys_faccessat - .globl compat_sys_pselect6_wrapper -compat_sys_pselect6_wrapper: +ENTRY(compat_sys_pselect6_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # fd_set * llgtr %r4,%r4 # fd_set * @@ -1591,8 +1351,7 @@ compat_sys_pselect6_wrapper: stg %r0,160(%r15) jg compat_sys_pselect6 - .globl compat_sys_ppoll_wrapper -compat_sys_ppoll_wrapper: +ENTRY(compat_sys_ppoll_wrapper) llgtr %r2,%r2 # struct pollfd * llgfr %r3,%r3 # unsigned int llgtr %r4,%r4 # struct timespec * @@ -1600,26 +1359,22 @@ compat_sys_ppoll_wrapper: llgfr %r6,%r6 # size_t jg compat_sys_ppoll - .globl sys_unshare_wrapper -sys_unshare_wrapper: +ENTRY(sys_unshare_wrapper) llgfr %r2,%r2 # unsigned long jg sys_unshare - .globl compat_sys_set_robust_list_wrapper -compat_sys_set_robust_list_wrapper: +ENTRY(compat_sys_set_robust_list_wrapper) llgtr %r2,%r2 # struct compat_robust_list_head * llgfr %r3,%r3 # size_t jg compat_sys_set_robust_list - .globl compat_sys_get_robust_list_wrapper -compat_sys_get_robust_list_wrapper: +ENTRY(compat_sys_get_robust_list_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # compat_uptr_t_t * llgtr %r4,%r4 # compat_size_t * jg compat_sys_get_robust_list - .globl sys_splice_wrapper -sys_splice_wrapper: +ENTRY(sys_splice_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # loff_t * lgfr %r4,%r4 # int @@ -1629,8 +1384,7 @@ sys_splice_wrapper: stg %r0,160(%r15) jg sys_splice - .globl sys_sync_file_range_wrapper -sys_sync_file_range_wrapper: +ENTRY(sys_sync_file_range_wrapper) lgfr %r2,%r2 # int sllg %r3,%r3,32 # get high word of 64bit loff_t or %r3,%r4 # get low word of 64bit loff_t @@ -1639,31 +1393,27 @@ sys_sync_file_range_wrapper: llgf %r5,164(%r15) # unsigned int jg sys_sync_file_range - .globl sys_tee_wrapper -sys_tee_wrapper: +ENTRY(sys_tee_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgfr %r4,%r4 # size_t llgfr %r5,%r5 # unsigned int jg sys_tee - .globl compat_sys_vmsplice_wrapper -compat_sys_vmsplice_wrapper: +ENTRY(compat_sys_vmsplice_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # compat_iovec * llgfr %r4,%r4 # unsigned int llgfr %r5,%r5 # unsigned int jg compat_sys_vmsplice - .globl sys_getcpu_wrapper -sys_getcpu_wrapper: +ENTRY(sys_getcpu_wrapper) llgtr %r2,%r2 # unsigned * llgtr %r3,%r3 # unsigned * llgtr %r4,%r4 # struct getcpu_cache * jg sys_getcpu - .globl compat_sys_epoll_pwait_wrapper -compat_sys_epoll_pwait_wrapper: +ENTRY(compat_sys_epoll_pwait_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct compat_epoll_event * lgfr %r4,%r4 # int @@ -1673,34 +1423,29 @@ compat_sys_epoll_pwait_wrapper: stg %r0,160(%r15) jg compat_sys_epoll_pwait - .globl compat_sys_utimes_wrapper -compat_sys_utimes_wrapper: +ENTRY(compat_sys_utimes_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # struct compat_timeval * jg compat_sys_utimes - .globl compat_sys_utimensat_wrapper -compat_sys_utimensat_wrapper: +ENTRY(compat_sys_utimensat_wrapper) llgfr %r2,%r2 # unsigned int llgtr %r3,%r3 # char * llgtr %r4,%r4 # struct compat_timespec * lgfr %r5,%r5 # int jg compat_sys_utimensat - .globl compat_sys_signalfd_wrapper -compat_sys_signalfd_wrapper: +ENTRY(compat_sys_signalfd_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # compat_sigset_t * llgfr %r4,%r4 # compat_size_t jg compat_sys_signalfd - .globl sys_eventfd_wrapper -sys_eventfd_wrapper: +ENTRY(sys_eventfd_wrapper) llgfr %r2,%r2 # unsigned int jg sys_eventfd - .globl sys_fallocate_wrapper -sys_fallocate_wrapper: +ENTRY(sys_fallocate_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int sllg %r4,%r4,32 # get high word of 64bit loff_t @@ -1709,94 +1454,80 @@ sys_fallocate_wrapper: l %r5,164(%r15) # get low word of 64bit loff_t jg sys_fallocate - .globl sys_timerfd_create_wrapper -sys_timerfd_create_wrapper: +ENTRY(sys_timerfd_create_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int jg sys_timerfd_create - .globl compat_sys_timerfd_settime_wrapper -compat_sys_timerfd_settime_wrapper: +ENTRY(compat_sys_timerfd_settime_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgtr %r4,%r4 # struct compat_itimerspec * llgtr %r5,%r5 # struct compat_itimerspec * jg compat_sys_timerfd_settime - .globl compat_sys_timerfd_gettime_wrapper -compat_sys_timerfd_gettime_wrapper: +ENTRY(compat_sys_timerfd_gettime_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct compat_itimerspec * jg compat_sys_timerfd_gettime - .globl compat_sys_signalfd4_wrapper -compat_sys_signalfd4_wrapper: +ENTRY(compat_sys_signalfd4_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # compat_sigset_t * llgfr %r4,%r4 # compat_size_t lgfr %r5,%r5 # int jg compat_sys_signalfd4 - .globl sys_eventfd2_wrapper -sys_eventfd2_wrapper: +ENTRY(sys_eventfd2_wrapper) llgfr %r2,%r2 # unsigned int lgfr %r3,%r3 # int jg sys_eventfd2 - .globl sys_inotify_init1_wrapper -sys_inotify_init1_wrapper: +ENTRY(sys_inotify_init1_wrapper) lgfr %r2,%r2 # int jg sys_inotify_init1 - .globl sys_pipe2_wrapper -sys_pipe2_wrapper: +ENTRY(sys_pipe2_wrapper) llgtr %r2,%r2 # u32 * lgfr %r3,%r3 # int jg sys_pipe2 # branch to system call - .globl sys_dup3_wrapper -sys_dup3_wrapper: +ENTRY(sys_dup3_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int lgfr %r4,%r4 # int jg sys_dup3 # branch to system call - .globl sys_epoll_create1_wrapper -sys_epoll_create1_wrapper: +ENTRY(sys_epoll_create1_wrapper) lgfr %r2,%r2 # int jg sys_epoll_create1 # branch to system call - .globl sys32_readahead_wrapper -sys32_readahead_wrapper: +ENTRY(sys32_readahead_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # u32 llgfr %r4,%r4 # u32 lgfr %r5,%r5 # s32 jg sys32_readahead # branch to system call - .globl sys32_sendfile64_wrapper -sys32_sendfile64_wrapper: +ENTRY(sys32_sendfile64_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int llgtr %r4,%r4 # compat_loff_t * lgfr %r5,%r5 # s32 jg sys32_sendfile64 # branch to system call - .globl sys_tkill_wrapper -sys_tkill_wrapper: +ENTRY(sys_tkill_wrapper) lgfr %r2,%r2 # pid_t lgfr %r3,%r3 # int jg sys_tkill # branch to system call - .globl sys_tgkill_wrapper -sys_tgkill_wrapper: +ENTRY(sys_tgkill_wrapper) lgfr %r2,%r2 # pid_t lgfr %r3,%r3 # pid_t lgfr %r4,%r4 # int jg sys_tgkill # branch to system call - .globl compat_sys_keyctl_wrapper -compat_sys_keyctl_wrapper: +ENTRY(compat_sys_keyctl_wrapper) llgfr %r2,%r2 # u32 llgfr %r3,%r3 # u32 llgfr %r4,%r4 # u32 @@ -1804,8 +1535,7 @@ compat_sys_keyctl_wrapper: llgfr %r6,%r6 # u32 jg compat_sys_keyctl # branch to system call - .globl compat_sys_preadv_wrapper -compat_sys_preadv_wrapper: +ENTRY(compat_sys_preadv_wrapper) llgfr %r2,%r2 # unsigned long llgtr %r3,%r3 # compat_iovec * llgfr %r4,%r4 # unsigned long @@ -1813,8 +1543,7 @@ compat_sys_preadv_wrapper: llgfr %r6,%r6 # u32 jg compat_sys_preadv # branch to system call - .globl compat_sys_pwritev_wrapper -compat_sys_pwritev_wrapper: +ENTRY(compat_sys_pwritev_wrapper) llgfr %r2,%r2 # unsigned long llgtr %r3,%r3 # compat_iovec * llgfr %r4,%r4 # unsigned long @@ -1822,16 +1551,14 @@ compat_sys_pwritev_wrapper: llgfr %r6,%r6 # u32 jg compat_sys_pwritev # branch to system call - .globl compat_sys_rt_tgsigqueueinfo_wrapper -compat_sys_rt_tgsigqueueinfo_wrapper: +ENTRY(compat_sys_rt_tgsigqueueinfo_wrapper) lgfr %r2,%r2 # compat_pid_t lgfr %r3,%r3 # compat_pid_t lgfr %r4,%r4 # int llgtr %r5,%r5 # struct compat_siginfo * jg compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call - .globl sys_perf_event_open_wrapper -sys_perf_event_open_wrapper: +ENTRY(sys_perf_event_open_wrapper) llgtr %r2,%r2 # const struct perf_event_attr * lgfr %r3,%r3 # pid_t lgfr %r4,%r4 # int @@ -1839,29 +1566,25 @@ sys_perf_event_open_wrapper: llgfr %r6,%r6 # unsigned long jg sys_perf_event_open # branch to system call - .globl sys_clone_wrapper -sys_clone_wrapper: +ENTRY(sys_clone_wrapper) llgfr %r2,%r2 # unsigned long llgfr %r3,%r3 # unsigned long llgtr %r4,%r4 # int * llgtr %r5,%r5 # int * jg sys_clone # branch to system call - .globl sys32_execve_wrapper -sys32_execve_wrapper: +ENTRY(sys32_execve_wrapper) llgtr %r2,%r2 # char * llgtr %r3,%r3 # compat_uptr_t * llgtr %r4,%r4 # compat_uptr_t * jg sys32_execve # branch to system call - .globl sys_fanotify_init_wrapper -sys_fanotify_init_wrapper: +ENTRY(sys_fanotify_init_wrapper) llgfr %r2,%r2 # unsigned int llgfr %r3,%r3 # unsigned int jg sys_fanotify_init # branch to system call - .globl sys_fanotify_mark_wrapper -sys_fanotify_mark_wrapper: +ENTRY(sys_fanotify_mark_wrapper) lgfr %r2,%r2 # int llgfr %r3,%r3 # unsigned int sllg %r4,%r4,32 # get high word of 64bit mask @@ -1870,16 +1593,14 @@ sys_fanotify_mark_wrapper: llgt %r6,164(%r15) # char * jg sys_fanotify_mark # branch to system call - .globl sys_prlimit64_wrapper -sys_prlimit64_wrapper: +ENTRY(sys_prlimit64_wrapper) lgfr %r2,%r2 # pid_t llgfr %r3,%r3 # unsigned int llgtr %r4,%r4 # const struct rlimit64 __user * llgtr %r5,%r5 # struct rlimit64 __user * jg sys_prlimit64 # branch to system call - .globl sys_name_to_handle_at_wrapper -sys_name_to_handle_at_wrapper: +ENTRY(sys_name_to_handle_at_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # const char __user * llgtr %r4,%r4 # struct file_handle __user * @@ -1887,26 +1608,42 @@ sys_name_to_handle_at_wrapper: lgfr %r6,%r6 # int jg sys_name_to_handle_at - .globl compat_sys_open_by_handle_at_wrapper -compat_sys_open_by_handle_at_wrapper: +ENTRY(compat_sys_open_by_handle_at_wrapper) lgfr %r2,%r2 # int llgtr %r3,%r3 # struct file_handle __user * lgfr %r4,%r4 # int jg compat_sys_open_by_handle_at - .globl compat_sys_clock_adjtime_wrapper -compat_sys_clock_adjtime_wrapper: +ENTRY(compat_sys_clock_adjtime_wrapper) lgfr %r2,%r2 # clockid_t (int) llgtr %r3,%r3 # struct compat_timex __user * jg compat_sys_clock_adjtime - .globl sys_syncfs_wrapper -sys_syncfs_wrapper: +ENTRY(sys_syncfs_wrapper) lgfr %r2,%r2 # int jg sys_syncfs - .globl sys_setns_wrapper -sys_setns_wrapper: +ENTRY(sys_setns_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int jg sys_setns + +ENTRY(compat_sys_process_vm_readv_wrapper) + lgfr %r2,%r2 # compat_pid_t + llgtr %r3,%r3 # struct compat_iovec __user * + llgfr %r4,%r4 # unsigned long + llgtr %r5,%r5 # struct compat_iovec __user * + llgfr %r6,%r6 # unsigned long + llgf %r0,164(%r15) # unsigned long + stg %r0,160(%r15) + jg sys_process_vm_readv + +ENTRY(compat_sys_process_vm_writev_wrapper) + lgfr %r2,%r2 # compat_pid_t + llgtr %r3,%r3 # struct compat_iovec __user * + llgfr %r4,%r4 # unsigned long + llgtr %r5,%r5 # struct compat_iovec __user * + llgfr %r6,%r6 # unsigned long + llgf %r0,164(%r15) # unsigned long + stg %r0,160(%r15) + jg sys_process_vm_writev diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c new file mode 100644 index 000000000000..39f8fd4438fc --- /dev/null +++ b/arch/s390/kernel/crash_dump.c @@ -0,0 +1,426 @@ +/* + * S390 kdump implementation + * + * Copyright IBM Corp. 2011 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <linux/crash_dump.h> +#include <asm/lowcore.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/crash_dump.h> +#include <linux/bootmem.h> +#include <linux/elf.h> +#include <asm/ipl.h> + +#define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) +#define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) +#define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y)))) + +/* + * Copy one page from "oldmem" + * + * For the kdump reserved memory this functions performs a swap operation: + * - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE]. + * - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, int userbuf) +{ + unsigned long src; + + if (!csize) + return 0; + + src = (pfn << PAGE_SHIFT) + offset; + if (src < OLDMEM_SIZE) + src += OLDMEM_BASE; + else if (src > OLDMEM_BASE && + src < OLDMEM_BASE + OLDMEM_SIZE) + src -= OLDMEM_BASE; + if (userbuf) + copy_to_user_real((void __force __user *) buf, (void *) src, + csize); + else + memcpy_real(buf, (void *) src, csize); + return csize; +} + +/* + * Copy memory from old kernel + */ +static int copy_from_oldmem(void *dest, void *src, size_t count) +{ + unsigned long copied = 0; + int rc; + + if ((unsigned long) src < OLDMEM_SIZE) { + copied = min(count, OLDMEM_SIZE - (unsigned long) src); + rc = memcpy_real(dest, src + OLDMEM_BASE, copied); + if (rc) + return rc; + } + return memcpy_real(dest + copied, src + copied, count - copied); +} + +/* + * Alloc memory and panic in case of ENOMEM + */ +static void *kzalloc_panic(int len) +{ + void *rc; + + rc = kzalloc(len, GFP_KERNEL); + if (!rc) + panic("s390 kdump kzalloc (%d) failed", len); + return rc; +} + +/* + * Get memory layout and create hole for oldmem + */ +static struct mem_chunk *get_memory_layout(void) +{ + struct mem_chunk *chunk_array; + + chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk)); + detect_memory_layout(chunk_array); + create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE, CHUNK_CRASHK); + return chunk_array; +} + +/* + * Initialize ELF note + */ +static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len, + const char *name) +{ + Elf64_Nhdr *note; + u64 len; + + note = (Elf64_Nhdr *)buf; + note->n_namesz = strlen(name) + 1; + note->n_descsz = d_len; + note->n_type = type; + len = sizeof(Elf64_Nhdr); + + memcpy(buf + len, name, note->n_namesz); + len = roundup(len + note->n_namesz, 4); + + memcpy(buf + len, desc, note->n_descsz); + len = roundup(len + note->n_descsz, 4); + + return PTR_ADD(buf, len); +} + +/* + * Initialize prstatus note + */ +static void *nt_prstatus(void *ptr, struct save_area *sa) +{ + struct elf_prstatus nt_prstatus; + static int cpu_nr = 1; + + memset(&nt_prstatus, 0, sizeof(nt_prstatus)); + memcpy(&nt_prstatus.pr_reg.gprs, sa->gp_regs, sizeof(sa->gp_regs)); + memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw)); + memcpy(&nt_prstatus.pr_reg.acrs, sa->acc_regs, sizeof(sa->acc_regs)); + nt_prstatus.pr_pid = cpu_nr; + cpu_nr++; + + return nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus), + "CORE"); +} + +/* + * Initialize fpregset (floating point) note + */ +static void *nt_fpregset(void *ptr, struct save_area *sa) +{ + elf_fpregset_t nt_fpregset; + + memset(&nt_fpregset, 0, sizeof(nt_fpregset)); + memcpy(&nt_fpregset.fpc, &sa->fp_ctrl_reg, sizeof(sa->fp_ctrl_reg)); + memcpy(&nt_fpregset.fprs, &sa->fp_regs, sizeof(sa->fp_regs)); + + return nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset), + "CORE"); +} + +/* + * Initialize timer note + */ +static void *nt_s390_timer(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer), + KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize TOD clock comparator note + */ +static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp, + sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize TOD programmable register note + */ +static void *nt_s390_tod_preg(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg, + sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize control register note + */ +static void *nt_s390_ctrs(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs, + sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize prefix register note + */ +static void *nt_s390_prefix(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg, + sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME); +} + +/* + * Fill ELF notes for one CPU with save area registers + */ +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa) +{ + ptr = nt_prstatus(ptr, sa); + ptr = nt_fpregset(ptr, sa); + ptr = nt_s390_timer(ptr, sa); + ptr = nt_s390_tod_cmp(ptr, sa); + ptr = nt_s390_tod_preg(ptr, sa); + ptr = nt_s390_ctrs(ptr, sa); + ptr = nt_s390_prefix(ptr, sa); + return ptr; +} + +/* + * Initialize prpsinfo note (new kernel) + */ +static void *nt_prpsinfo(void *ptr) +{ + struct elf_prpsinfo prpsinfo; + + memset(&prpsinfo, 0, sizeof(prpsinfo)); + prpsinfo.pr_sname = 'R'; + strcpy(prpsinfo.pr_fname, "vmlinux"); + return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo), + KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize vmcoreinfo note (new kernel) + */ +static void *nt_vmcoreinfo(void *ptr) +{ + char nt_name[11], *vmcoreinfo; + Elf64_Nhdr note; + void *addr; + + if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr))) + return ptr; + memset(nt_name, 0, sizeof(nt_name)); + if (copy_from_oldmem(¬e, addr, sizeof(note))) + return ptr; + if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1)) + return ptr; + if (strcmp(nt_name, "VMCOREINFO") != 0) + return ptr; + vmcoreinfo = kzalloc_panic(note.n_descsz + 1); + if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz)) + return ptr; + vmcoreinfo[note.n_descsz + 1] = 0; + return nt_init(ptr, 0, vmcoreinfo, note.n_descsz, "VMCOREINFO"); +} + +/* + * Initialize ELF header (new kernel) + */ +static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) +{ + memset(ehdr, 0, sizeof(*ehdr)); + memcpy(ehdr->e_ident, ELFMAG, SELFMAG); + ehdr->e_ident[EI_CLASS] = ELFCLASS64; + ehdr->e_ident[EI_DATA] = ELFDATA2MSB; + ehdr->e_ident[EI_VERSION] = EV_CURRENT; + memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); + ehdr->e_type = ET_CORE; + ehdr->e_machine = EM_S390; + ehdr->e_version = EV_CURRENT; + ehdr->e_phoff = sizeof(Elf64_Ehdr); + ehdr->e_ehsize = sizeof(Elf64_Ehdr); + ehdr->e_phentsize = sizeof(Elf64_Phdr); + ehdr->e_phnum = mem_chunk_cnt + 1; + return ehdr + 1; +} + +/* + * Return CPU count for ELF header (new kernel) + */ +static int get_cpu_cnt(void) +{ + int i, cpus = 0; + + for (i = 0; zfcpdump_save_areas[i]; i++) { + if (zfcpdump_save_areas[i]->pref_reg == 0) + continue; + cpus++; + } + return cpus; +} + +/* + * Return memory chunk count for ELF header (new kernel) + */ +static int get_mem_chunk_cnt(void) +{ + struct mem_chunk *chunk_array, *mem_chunk; + int i, cnt = 0; + + chunk_array = get_memory_layout(); + for (i = 0; i < MEMORY_CHUNKS; i++) { + mem_chunk = &chunk_array[i]; + if (chunk_array[i].type != CHUNK_READ_WRITE && + chunk_array[i].type != CHUNK_READ_ONLY) + continue; + if (mem_chunk->size == 0) + continue; + cnt++; + } + kfree(chunk_array); + return cnt; +} + +/* + * Relocate pointer in order to allow vmcore code access the data + */ +static inline unsigned long relocate(unsigned long addr) +{ + return OLDMEM_BASE + addr; +} + +/* + * Initialize ELF loads (new kernel) + */ +static int loads_init(Elf64_Phdr *phdr, u64 loads_offset) +{ + struct mem_chunk *chunk_array, *mem_chunk; + int i; + + chunk_array = get_memory_layout(); + for (i = 0; i < MEMORY_CHUNKS; i++) { + mem_chunk = &chunk_array[i]; + if (mem_chunk->size == 0) + break; + if (chunk_array[i].type != CHUNK_READ_WRITE && + chunk_array[i].type != CHUNK_READ_ONLY) + continue; + else + phdr->p_filesz = mem_chunk->size; + phdr->p_type = PT_LOAD; + phdr->p_offset = mem_chunk->addr; + phdr->p_vaddr = mem_chunk->addr; + phdr->p_paddr = mem_chunk->addr; + phdr->p_memsz = mem_chunk->size; + phdr->p_flags = PF_R | PF_W | PF_X; + phdr->p_align = PAGE_SIZE; + phdr++; + } + kfree(chunk_array); + return i; +} + +/* + * Initialize notes (new kernel) + */ +static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) +{ + struct save_area *sa; + void *ptr_start = ptr; + int i; + + ptr = nt_prpsinfo(ptr); + + for (i = 0; zfcpdump_save_areas[i]; i++) { + sa = zfcpdump_save_areas[i]; + if (sa->pref_reg == 0) + continue; + ptr = fill_cpu_elf_notes(ptr, sa); + } + ptr = nt_vmcoreinfo(ptr); + memset(phdr, 0, sizeof(*phdr)); + phdr->p_type = PT_NOTE; + phdr->p_offset = relocate(notes_offset); + phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start); + phdr->p_memsz = phdr->p_filesz; + return ptr; +} + +/* + * Create ELF core header (new kernel) + */ +static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) +{ + Elf64_Phdr *phdr_notes, *phdr_loads; + int mem_chunk_cnt; + void *ptr, *hdr; + u32 alloc_size; + u64 hdr_off; + + mem_chunk_cnt = get_mem_chunk_cnt(); + + alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + + mem_chunk_cnt * sizeof(Elf64_Phdr); + hdr = kzalloc_panic(alloc_size); + /* Init elf header */ + ptr = ehdr_init(hdr, mem_chunk_cnt); + /* Init program headers */ + phdr_notes = ptr; + ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); + phdr_loads = ptr; + ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt); + /* Init notes */ + hdr_off = PTR_DIFF(ptr, hdr); + ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); + /* Init loads */ + hdr_off = PTR_DIFF(ptr, hdr); + loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off); + *elfcorebuf_sz = hdr_off; + *elfcorebuf = (void *) relocate((unsigned long) hdr); + BUG_ON(*elfcorebuf_sz > alloc_size); +} + +/* + * Create kdump ELF core header in new kernel, if it has not been passed via + * the "elfcorehdr" kernel parameter + */ +static int setup_kdump_elfcorehdr(void) +{ + size_t elfcorebuf_sz; + char *elfcorebuf; + + if (!OLDMEM_BASE || is_kdump_kernel()) + return -EINVAL; + s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz); + elfcorehdr_addr = (unsigned long long) elfcorebuf; + elfcorehdr_size = elfcorebuf_sz; + return 0; +} + +subsys_initcall(setup_kdump_elfcorehdr); diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 1ca3d1d6a86c..45df6d456aa1 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -27,7 +27,7 @@ #include <asm/system.h> #include <asm/uaccess.h> #include <asm/io.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/mathemu.h> #include <asm/cpcmd.h> #include <asm/lowcore.h> diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 068f8465c4ee..c9ffe0025197 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -252,7 +252,7 @@ static noinline __init void setup_lowcore_early(void) { psw_t psw; - psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; @@ -390,23 +390,27 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; if (test_facility(40)) S390_lowcore.machine_flags |= MACHINE_FLAG_SPP; + if (test_facility(25)) + S390_lowcore.machine_flags |= MACHINE_FLAG_STCKF; #endif } static __init void rescue_initrd(void) { #ifdef CONFIG_BLK_DEV_INITRD + unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20); /* - * Move the initrd right behind the bss section in case it starts - * within the bss section. So we don't overwrite it when the bss - * section gets cleared. + * Just like in case of IPL from VM reader we make sure there is a + * gap of 4MB between end of kernel and start of initrd. + * That way we can also be sure that saving an NSS will succeed, + * which however only requires different segments. */ if (!INITRD_START || !INITRD_SIZE) return; - if (INITRD_START >= (unsigned long) __bss_stop) + if (INITRD_START >= min_initrd_addr) return; - memmove(__bss_stop, (void *) INITRD_START, INITRD_SIZE); - INITRD_START = (unsigned long) __bss_stop; + memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE); + INITRD_START = min_initrd_addr; #endif } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 0476174dfff5..b13157057e02 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -9,8 +9,8 @@ * Heiko Carstens <heiko.carstens@de.ibm.com> */ -#include <linux/linkage.h> #include <linux/init.h> +#include <linux/linkage.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ptrace.h> @@ -43,16 +43,15 @@ SP_R13 = STACK_FRAME_OVERHEAD + __PT_GPRS + 52 SP_R14 = STACK_FRAME_OVERHEAD + __PT_GPRS + 56 SP_R15 = STACK_FRAME_OVERHEAD + __PT_GPRS + 60 SP_ORIG_R2 = STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2 -SP_ILC = STACK_FRAME_OVERHEAD + __PT_ILC -SP_SVCNR = STACK_FRAME_OVERHEAD + __PT_SVCNR +SP_SVC_CODE = STACK_FRAME_OVERHEAD + __PT_SVC_CODE SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_PER_TRAP ) + _TIF_MCCK_PENDING | _TIF_PER_TRAP ) _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) -_TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT @@ -197,8 +196,7 @@ STACK_SIZE = 1 << STACK_SHIFT * Returns: * gpr2 = prev */ - .globl __switch_to -__switch_to: +ENTRY(__switch_to) basr %r1,0 0: l %r4,__THREAD_info(%r2) # get thread_info of prev l %r5,__THREAD_info(%r3) # get thread_info of next @@ -224,15 +222,15 @@ __critical_start: * are executed with interrupts enabled. */ - .globl system_call -system_call: +ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER sysc_saveall: SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC l %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+3(%r12),_TIF_SYSCALL sysc_vtime: UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER sysc_stime: @@ -241,17 +239,17 @@ sysc_update: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER sysc_do_svc: xr %r7,%r7 - icm %r7,3,SP_SVCNR(%r15) # load svc number and test for svc 0 + icm %r7,3,SP_SVC_CODE+2(%r15)# load svc number and test for svc 0 bnz BASED(sysc_nr_ok) # svc number > 0 # svc 0: system call number in %r1 cl %r1,BASED(.Lnr_syscalls) bnl BASED(sysc_nr_ok) - sth %r1,SP_SVCNR(%r15) + sth %r1,SP_SVC_CODE+2(%r15) lr %r7,%r1 # copy svc number to %r7 sysc_nr_ok: sll %r7,2 # svc number *4 l %r10,BASED(.Lsysc_table) - tm __TI_flags+2(%r12),_TIF_SYSCALL + tm __TI_flags+2(%r12),_TIF_TRACE >> 8 mvc SP_ARGS(4,%r15),SP_R7(%r15) l %r8,0(%r7,%r10) # get system call addr. bnz BASED(sysc_tracesys) @@ -261,23 +259,19 @@ sysc_nr_ok: sysc_return: LOCKDEP_SYS_EXIT sysc_tif: + tm SP_PSW+1(%r15),0x01 # returning to user ? + bno BASED(sysc_restore) tm __TI_flags+3(%r12),_TIF_WORK_SVC bnz BASED(sysc_work) # there is work to do (signals etc.) + ni __TI_flags+3(%r12),255-_TIF_SYSCALL sysc_restore: RESTORE_ALL __LC_RETURN_PSW,1 sysc_done: # -# There is work to do, but first we need to check if we return to userspace. -# -sysc_work: - tm SP_PSW+1(%r15),0x01 # returning to user ? - bno BASED(sysc_restore) - -# # One of the work bits is on. Find out which one. # -sysc_work_tif: +sysc_work: tm __TI_flags+3(%r12),_TIF_MCCK_PENDING bo BASED(sysc_mcck_pending) tm __TI_flags+3(%r12),_TIF_NEED_RESCHED @@ -286,8 +280,6 @@ sysc_work_tif: bo BASED(sysc_sigpending) tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME bo BASED(sysc_notify_resume) - tm __TI_flags+3(%r12),_TIF_RESTART_SVC - bo BASED(sysc_restart) tm __TI_flags+3(%r12),_TIF_PER_TRAP bo BASED(sysc_singlestep) b BASED(sysc_return) # beware of critical section cleanup @@ -316,11 +308,14 @@ sysc_sigpending: la %r2,SP_PTREGS(%r15) # load pt_regs l %r1,BASED(.Ldo_signal) basr %r14,%r1 # call do_signal - tm __TI_flags+3(%r12),_TIF_RESTART_SVC - bo BASED(sysc_restart) - tm __TI_flags+3(%r12),_TIF_PER_TRAP - bo BASED(sysc_singlestep) - b BASED(sysc_return) + tm __TI_flags+3(%r12),_TIF_SYSCALL + bno BASED(sysc_return) + lm %r2,%r6,SP_R2(%r15) # load svc arguments + xr %r7,%r7 # svc 0 returns -ENOSYS + clc SP_SVC_CODE+2(2,%r15),BASED(.Lnr_syscalls+2) + bnl BASED(sysc_nr_ok) # invalid svc number -> do svc 0 + icm %r7,3,SP_SVC_CODE+2(%r15)# load new svc number + b BASED(sysc_nr_ok) # restart svc # # _TIF_NOTIFY_RESUME is set, call do_notify_resume @@ -331,24 +326,11 @@ sysc_notify_resume: la %r14,BASED(sysc_return) br %r1 # call do_notify_resume - -# -# _TIF_RESTART_SVC is set, set up registers and restart svc -# -sysc_restart: - ni __TI_flags+3(%r12),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC - l %r7,SP_R2(%r15) # load new svc number - mvc SP_R2(4,%r15),SP_ORIG_R2(%r15) # restore first argument - lm %r2,%r6,SP_R2(%r15) # load svc arguments - sth %r7,SP_SVCNR(%r15) - b BASED(sysc_nr_ok) # restart svc - # # _TIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+3(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) # clear svc number + ni __TI_flags+3(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP) la %r2,SP_PTREGS(%r15) # address of register-save area l %r1,BASED(.Lhandle_per) # load adr. of per handler la %r14,BASED(sysc_return) # load adr. of system return @@ -363,7 +345,7 @@ sysc_tracesys: la %r2,SP_PTREGS(%r15) # load pt_regs la %r3,0 xr %r0,%r0 - icm %r0,3,SP_SVCNR(%r15) + icm %r0,3,SP_SVC_CODE(%r15) st %r0,SP_R2(%r15) basr %r14,%r1 cl %r2,BASED(.Lnr_syscalls) @@ -378,7 +360,7 @@ sysc_tracego: basr %r14,%r8 # call sys_xxx st %r2,SP_R2(%r15) # store return value sysc_tracenogo: - tm __TI_flags+2(%r12),_TIF_SYSCALL + tm __TI_flags+2(%r12),_TIF_TRACE >> 8 bz BASED(sysc_return) l %r1,BASED(.Ltrace_exit) la %r2,SP_PTREGS(%r15) # load pt_regs @@ -388,8 +370,7 @@ sysc_tracenogo: # # a new process exits the kernel with ret_from_fork # - .globl ret_from_fork -ret_from_fork: +ENTRY(ret_from_fork) l %r13,__LC_SVC_NEW_PSW+4 l %r12,__LC_THREAD_INFO # load pointer to thread_info struct tm SP_PSW+1(%r15),0x01 # forking a kernel thread ? @@ -405,8 +386,7 @@ ret_from_fork: # kernel_execve function needs to deal with pt_regs that is not # at the usual place # - .globl kernel_execve -kernel_execve: +ENTRY(kernel_execve) stm %r12,%r15,48(%r15) lr %r14,%r15 l %r13,__LC_SVC_NEW_PSW+4 @@ -438,8 +418,7 @@ kernel_execve: * Program check handler routine */ - .globl pgm_check_handler -pgm_check_handler: +ENTRY(pgm_check_handler) /* * First we need to check for a special case: * Single stepping an instruction that disables the PER event mask will @@ -459,7 +438,6 @@ pgm_check_handler: bnz BASED(pgm_per) # got per exception -> special case SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - xc SP_ILC(4,%r15),SP_ILC(%r15) mvc SP_PSW(8,%r15),__LC_PGM_OLD_PSW l %r12,__LC_THREAD_INFO # load pointer to thread_info struct tm SP_PSW+1(%r15),0x01 # interrupting from user ? @@ -535,9 +513,10 @@ pgm_exit2: pgm_svcper: SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC l %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+3(%r12),(_TIF_SYSCALL | _TIF_PER_TRAP) UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER @@ -545,7 +524,6 @@ pgm_svcper: mvc __THREAD_per_cause(2,%r8),__LC_PER_CAUSE mvc __THREAD_per_address(4,%r8),__LC_PER_ADDRESS mvc __THREAD_per_paid(1,%r8),__LC_PER_PAID - oi __TI_flags+3(%r12),_TIF_PER_TRAP # set TIF_PER_TRAP stosm __SF_EMPTY(%r15),0x03 # reenable interrupts lm %r2,%r6,SP_R2(%r15) # load svc arguments b BASED(sysc_do_svc) @@ -555,7 +533,6 @@ pgm_svcper: # kernel_per: REENABLE_IRQS - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) la %r2,SP_PTREGS(%r15) # address of register-save area l %r1,BASED(.Lhandle_per) # load adr. of per handler basr %r14,%r1 # branch to do_single_step @@ -565,8 +542,7 @@ kernel_per: * IO interrupt handler routine */ - .globl io_int_handler -io_int_handler: +ENTRY(io_int_handler) stck __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+16 @@ -703,8 +679,7 @@ io_notify_resume: * External interrupt handler routine */ - .globl ext_int_handler -ext_int_handler: +ENTRY(ext_int_handler) stck __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+16 @@ -731,8 +706,7 @@ __critical_end: * Machine check handler routines */ - .globl mcck_int_handler -mcck_int_handler: +ENTRY(mcck_int_handler) stck __LC_MCCK_CLOCK spt __LC_CPU_TIMER_SAVE_AREA # revalidate cpu timer lm %r0,%r15,__LC_GPREGS_SAVE_AREA # revalidate gprs @@ -818,8 +792,7 @@ mcck_return: */ #ifdef CONFIG_SMP __CPUINIT - .globl restart_int_handler -restart_int_handler: +ENTRY(restart_int_handler) basr %r1,0 restart_base: spt restart_vtime-restart_base(%r1) @@ -848,8 +821,7 @@ restart_vtime: /* * If we do not run with SMP enabled, let the new CPU crash ... */ - .globl restart_int_handler -restart_int_handler: +ENTRY(restart_int_handler) basr %r1,0 restart_base: lpsw restart_crash-restart_base(%r1) @@ -859,6 +831,34 @@ restart_crash: restart_go: #endif +# +# PSW restart interrupt handler +# +ENTRY(psw_restart_int_handler) + st %r15,__LC_SAVE_AREA+48(%r0) # save r15 + basr %r15,0 +0: l %r15,.Lrestart_stack-0b(%r15) # load restart stack + l %r15,0(%r15) + ahi %r15,-SP_SIZE # make room for pt_regs + stm %r0,%r14,SP_R0(%r15) # store gprs %r0-%r14 to stack + mvc SP_R15(4,%r15),__LC_SAVE_AREA+48(%r0)# store saved %r15 to stack + mvc SP_PSW(8,%r15),__LC_RST_OLD_PSW(%r0) # store restart old psw + xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0 + basr %r14,0 +1: l %r14,.Ldo_restart-1b(%r14) + basr %r14,%r14 + + basr %r14,0 # load disabled wait PSW if +2: lpsw restart_psw_crash-2b(%r14) # do_restart returns + .align 4 +.Ldo_restart: + .long do_restart +.Lrestart_stack: + .long restart_stack + .align 8 +restart_psw_crash: + .long 0x000a0000,0x00000000 + restart_psw_crash + .section .kprobes.text, "ax" #ifdef CONFIG_CHECK_STACK @@ -947,9 +947,11 @@ cleanup_system_call: s %r15,BASED(.Lc_spsize) # make room for registers & psw st %r15,12(%r12) CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC mvc 0(4,%r12),__LC_THREAD_INFO + l %r12,__LC_THREAD_INFO + mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+3(%r12),_TIF_SYSCALL cleanup_vtime: clc __LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+12) bhe BASED(cleanup_stime) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 17a6f83a2d67..ef8fb1d6e8d7 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -5,12 +5,16 @@ #include <linux/signal.h> #include <asm/ptrace.h> -typedef void pgm_check_handler_t(struct pt_regs *, long, unsigned long); -extern pgm_check_handler_t *pgm_check_table[128]; -pgm_check_handler_t do_protection_exception; -pgm_check_handler_t do_dat_exception; -extern int sysctl_userprocess_debug; +extern void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long); +extern void *restart_stack; + +asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); +asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); + +void do_protection_exception(struct pt_regs *, long, unsigned long); +void do_dat_exception(struct pt_regs *, long, unsigned long); +void do_asce_exception(struct pt_regs *, long, unsigned long); void do_per_trap(struct pt_regs *regs); void syscall_trace(struct pt_regs *regs, int entryexit); @@ -18,12 +22,16 @@ void kernel_stack_overflow(struct pt_regs * regs); void do_signal(struct pt_regs *regs); int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); +void do_notify_resume(struct pt_regs *regs); void do_extint(struct pt_regs *regs, unsigned int, unsigned int, unsigned long); +void do_restart(void); int __cpuinit start_secondary(void *cpuvoid); void __init startup_init(void); void die(const char * str, struct pt_regs * regs, long err); +void __init time_init(void); + struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index d61967e2eab0..83a93747e2fd 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -9,8 +9,8 @@ * Heiko Carstens <heiko.carstens@de.ibm.com> */ -#include <linux/linkage.h> #include <linux/init.h> +#include <linux/linkage.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ptrace.h> @@ -43,28 +43,40 @@ SP_R13 = STACK_FRAME_OVERHEAD + __PT_GPRS + 104 SP_R14 = STACK_FRAME_OVERHEAD + __PT_GPRS + 112 SP_R15 = STACK_FRAME_OVERHEAD + __PT_GPRS + 120 SP_ORIG_R2 = STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2 -SP_ILC = STACK_FRAME_OVERHEAD + __PT_ILC -SP_SVCNR = STACK_FRAME_OVERHEAD + __PT_SVCNR +SP_SVC_CODE = STACK_FRAME_OVERHEAD + __PT_SVC_CODE SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_PER_TRAP ) + _TIF_MCCK_PENDING | _TIF_PER_TRAP ) _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) -_TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) +_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) #define BASED(name) name-system_call(%r13) + .macro SPP newpp +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_SPP + jz .+8 + .insn s,0xb2800000,\newpp +#endif + .endm + .macro HANDLE_SIE_INTERCEPT #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) - lg %r3,__LC_SIE_HOOK - ltgr %r3,%r3 + tm __TI_flags+6(%r12),_TIF_SIE>>8 jz 0f - basr %r14,%r3 + SPP __LC_CMF_HPP # set host id + clc SP_PSW+8(8,%r15),BASED(.Lsie_loop) + jl 0f + clc SP_PSW+8(8,%r15),BASED(.Lsie_done) + jhe 0f + mvc SP_PSW+8(8,%r15),BASED(.Lsie_loop) 0: #endif .endm @@ -206,8 +218,7 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ * Returns: * gpr2 = prev */ - .globl __switch_to -__switch_to: +ENTRY(__switch_to) lg %r4,__THREAD_info(%r2) # get thread_info of prev lg %r5,__THREAD_info(%r3) # get thread_info of next tm __TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending? @@ -232,15 +243,15 @@ __critical_start: * are executed with interrupts enabled. */ - .globl system_call -system_call: +ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER sysc_saveall: SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+7(%r12),_TIF_SYSCALL sysc_vtime: UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER sysc_stime: @@ -249,14 +260,14 @@ sysc_update: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER LAST_BREAK sysc_do_svc: - llgh %r7,SP_SVCNR(%r15) + llgh %r7,SP_SVC_CODE+2(%r15) slag %r7,%r7,2 # shift and test for svc 0 jnz sysc_nr_ok # svc 0: system call number in %r1 llgfr %r1,%r1 # clear high word in r1 cghi %r1,NR_syscalls jnl sysc_nr_ok - sth %r1,SP_SVCNR(%r15) + sth %r1,SP_SVC_CODE+2(%r15) slag %r7,%r1,2 # shift and test for svc 0 sysc_nr_ok: larl %r10,sys_call_table @@ -266,7 +277,7 @@ sysc_nr_ok: larl %r10,sys_call_table_emu # use 31 bit emulation system calls sysc_noemu: #endif - tm __TI_flags+6(%r12),_TIF_SYSCALL + tm __TI_flags+6(%r12),_TIF_TRACE >> 8 mvc SP_ARGS(8,%r15),SP_R7(%r15) lgf %r8,0(%r7,%r10) # load address of system call routine jnz sysc_tracesys @@ -276,23 +287,19 @@ sysc_noemu: sysc_return: LOCKDEP_SYS_EXIT sysc_tif: + tm SP_PSW+1(%r15),0x01 # returning to user ? + jno sysc_restore tm __TI_flags+7(%r12),_TIF_WORK_SVC jnz sysc_work # there is work to do (signals etc.) + ni __TI_flags+7(%r12),255-_TIF_SYSCALL sysc_restore: RESTORE_ALL __LC_RETURN_PSW,1 sysc_done: # -# There is work to do, but first we need to check if we return to userspace. -# -sysc_work: - tm SP_PSW+1(%r15),0x01 # returning to user ? - jno sysc_restore - -# # One of the work bits is on. Find out which one. # -sysc_work_tif: +sysc_work: tm __TI_flags+7(%r12),_TIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED @@ -301,8 +308,6 @@ sysc_work_tif: jo sysc_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME jo sysc_notify_resume - tm __TI_flags+7(%r12),_TIF_RESTART_SVC - jo sysc_restart tm __TI_flags+7(%r12),_TIF_PER_TRAP jo sysc_singlestep j sysc_return # beware of critical section cleanup @@ -328,11 +333,15 @@ sysc_sigpending: ni __TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP la %r2,SP_PTREGS(%r15) # load pt_regs brasl %r14,do_signal # call do_signal - tm __TI_flags+7(%r12),_TIF_RESTART_SVC - jo sysc_restart - tm __TI_flags+7(%r12),_TIF_PER_TRAP - jo sysc_singlestep - j sysc_return + tm __TI_flags+7(%r12),_TIF_SYSCALL + jno sysc_return + lmg %r2,%r6,SP_R2(%r15) # load svc arguments + lghi %r7,0 # svc 0 returns -ENOSYS + lh %r1,SP_SVC_CODE+2(%r15) # load new svc number + cghi %r1,NR_syscalls + jnl sysc_nr_ok # invalid svc number -> do svc 0 + slag %r7,%r1,2 + j sysc_nr_ok # restart svc # # _TIF_NOTIFY_RESUME is set, call do_notify_resume @@ -343,23 +352,10 @@ sysc_notify_resume: jg do_notify_resume # call do_notify_resume # -# _TIF_RESTART_SVC is set, set up registers and restart svc -# -sysc_restart: - ni __TI_flags+7(%r12),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC - lg %r7,SP_R2(%r15) # load new svc number - mvc SP_R2(8,%r15),SP_ORIG_R2(%r15) # restore first argument - lmg %r2,%r6,SP_R2(%r15) # load svc arguments - sth %r7,SP_SVCNR(%r15) - slag %r7,%r7,2 - j sysc_nr_ok # restart svc - -# # _TIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) # clear svc number + ni __TI_flags+7(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP) la %r2,SP_PTREGS(%r15) # address of register-save area larl %r14,sysc_return # load adr. of system return jg do_per_trap @@ -371,7 +367,7 @@ sysc_singlestep: sysc_tracesys: la %r2,SP_PTREGS(%r15) # load pt_regs la %r3,0 - llgh %r0,SP_SVCNR(%r15) + llgh %r0,SP_SVC_CODE+2(%r15) stg %r0,SP_R2(%r15) brasl %r14,do_syscall_trace_enter lghi %r0,NR_syscalls @@ -386,7 +382,7 @@ sysc_tracego: basr %r14,%r8 # call sys_xxx stg %r2,SP_R2(%r15) # store return value sysc_tracenogo: - tm __TI_flags+6(%r12),_TIF_SYSCALL + tm __TI_flags+6(%r12),_TIF_TRACE >> 8 jz sysc_return la %r2,SP_PTREGS(%r15) # load pt_regs larl %r14,sysc_return # return point is sysc_return @@ -395,8 +391,7 @@ sysc_tracenogo: # # a new process exits the kernel with ret_from_fork # - .globl ret_from_fork -ret_from_fork: +ENTRY(ret_from_fork) lg %r13,__LC_SVC_NEW_PSW+8 lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct tm SP_PSW+1(%r15),0x01 # forking a kernel thread ? @@ -411,8 +406,7 @@ ret_from_fork: # kernel_execve function needs to deal with pt_regs that is not # at the usual place # - .globl kernel_execve -kernel_execve: +ENTRY(kernel_execve) stmg %r12,%r15,96(%r15) lgr %r14,%r15 aghi %r15,-SP_SIZE @@ -442,8 +436,7 @@ kernel_execve: * Program check handler routine */ - .globl pgm_check_handler -pgm_check_handler: +ENTRY(pgm_check_handler) /* * First we need to check for a special case: * Single stepping an instruction that disables the PER event mask will @@ -462,9 +455,9 @@ pgm_check_handler: jnz pgm_per # got per exception -> special case SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - xc SP_ILC(4,%r15),SP_ILC(%r15) mvc SP_PSW(16,%r15),__LC_PGM_OLD_PSW lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + HANDLE_SIE_INTERCEPT tm SP_PSW+1(%r15),0x01 # interrupting from user ? jz pgm_no_vtime UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER @@ -472,7 +465,6 @@ pgm_check_handler: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER LAST_BREAK pgm_no_vtime: - HANDLE_SIE_INTERCEPT stg %r11,SP_ARGS(%r15) lgf %r3,__LC_PGM_ILC # load program interruption code lg %r4,__LC_TRANS_EXC_CODE @@ -507,6 +499,7 @@ pgm_per_std: CREATE_STACK_FRAME __LC_SAVE_AREA mvc SP_PSW(16,%r15),__LC_PGM_OLD_PSW lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + HANDLE_SIE_INTERCEPT tm SP_PSW+1(%r15),0x01 # interrupting from user ? jz pgm_no_vtime2 UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER @@ -514,7 +507,6 @@ pgm_per_std: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER LAST_BREAK pgm_no_vtime2: - HANDLE_SIE_INTERCEPT lg %r1,__TI_task(%r12) tm SP_PSW+1(%r15),0x01 # kernel per event ? jz kernel_per @@ -542,9 +534,10 @@ pgm_exit2: pgm_svcper: SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+7(%r12),(_TIF_SYSCALL | _TIF_PER_TRAP) UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER @@ -553,7 +546,6 @@ pgm_svcper: mvc __THREAD_per_cause(2,%r8),__LC_PER_CAUSE mvc __THREAD_per_address(8,%r8),__LC_PER_ADDRESS mvc __THREAD_per_paid(1,%r8),__LC_PER_PAID - oi __TI_flags+7(%r12),_TIF_PER_TRAP # set TIF_PER_TRAP stosm __SF_EMPTY(%r15),0x03 # reenable interrupts lmg %r2,%r6,SP_R2(%r15) # load svc arguments j sysc_do_svc @@ -563,7 +555,6 @@ pgm_svcper: # kernel_per: REENABLE_IRQS - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) # clear svc number la %r2,SP_PTREGS(%r15) # address of register-save area brasl %r14,do_per_trap j pgm_exit @@ -571,14 +562,14 @@ kernel_per: /* * IO interrupt handler routine */ - .globl io_int_handler -io_int_handler: +ENTRY(io_int_handler) stck __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+40 CREATE_STACK_FRAME __LC_SAVE_AREA+40 mvc SP_PSW(16,%r15),0(%r12) # move user PSW to stack lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + HANDLE_SIE_INTERCEPT tm SP_PSW+1(%r15),0x01 # interrupting from user ? jz io_no_vtime UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER @@ -586,7 +577,6 @@ io_int_handler: mvc __LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER LAST_BREAK io_no_vtime: - HANDLE_SIE_INTERCEPT TRACE_IRQS_OFF la %r2,SP_PTREGS(%r15) # address of register-save area brasl %r14,do_IRQ # call standard irq handler @@ -706,14 +696,14 @@ io_notify_resume: /* * External interrupt handler routine */ - .globl ext_int_handler -ext_int_handler: +ENTRY(ext_int_handler) stck __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+40 CREATE_STACK_FRAME __LC_SAVE_AREA+40 mvc SP_PSW(16,%r15),0(%r12) # move user PSW to stack lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + HANDLE_SIE_INTERCEPT tm SP_PSW+1(%r15),0x01 # interrupting from user ? jz ext_no_vtime UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER @@ -721,7 +711,6 @@ ext_int_handler: mvc __LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER LAST_BREAK ext_no_vtime: - HANDLE_SIE_INTERCEPT TRACE_IRQS_OFF lghi %r1,4096 la %r2,SP_PTREGS(%r15) # address of register-save area @@ -736,8 +725,7 @@ __critical_end: /* * Machine check handler routines */ - .globl mcck_int_handler -mcck_int_handler: +ENTRY(mcck_int_handler) stck __LC_MCCK_CLOCK la %r1,4095 # revalidate r1 spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # revalidate cpu timer @@ -785,6 +773,7 @@ mcck_int_main: lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct tm __LC_MCCK_CODE+2,0x08 # mwp of old psw valid? jno mcck_no_vtime # no -> no timer update + HANDLE_SIE_INTERCEPT tm SP_PSW+1(%r15),0x01 # interrupting from user ? jz mcck_no_vtime UPDATE_VTIME __LC_EXIT_TIMER,__LC_MCCK_ENTER_TIMER,__LC_USER_TIMER @@ -804,7 +793,6 @@ mcck_no_vtime: stosm __SF_EMPTY(%r15),0x04 # turn dat on tm __TI_flags+7(%r12),_TIF_MCCK_PENDING jno mcck_return - HANDLE_SIE_INTERCEPT TRACE_IRQS_OFF brasl %r14,s390_handle_mcck TRACE_IRQS_ON @@ -823,8 +811,7 @@ mcck_done: */ #ifdef CONFIG_SMP __CPUINIT - .globl restart_int_handler -restart_int_handler: +ENTRY(restart_int_handler) basr %r1,0 restart_base: spt restart_vtime-restart_base(%r1) @@ -851,8 +838,7 @@ restart_vtime: /* * If we do not run with SMP enabled, let the new CPU crash ... */ - .globl restart_int_handler -restart_int_handler: +ENTRY(restart_int_handler) basr %r1,0 restart_base: lpswe restart_crash-restart_base(%r1) @@ -862,6 +848,26 @@ restart_crash: restart_go: #endif +# +# PSW restart interrupt handler +# +ENTRY(psw_restart_int_handler) + stg %r15,__LC_SAVE_AREA+120(%r0) # save r15 + larl %r15,restart_stack # load restart stack + lg %r15,0(%r15) + aghi %r15,-SP_SIZE # make room for pt_regs + stmg %r0,%r14,SP_R0(%r15) # store gprs %r0-%r14 to stack + mvc SP_R15(8,%r15),__LC_SAVE_AREA+120(%r0)# store saved %r15 to stack + mvc SP_PSW(16,%r15),__LC_RST_OLD_PSW(%r0)# store restart old psw + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0 + brasl %r14,do_restart + + larl %r14,restart_psw_crash # load disabled wait PSW if + lpswe 0(%r14) # do_restart returns + .align 8 +restart_psw_crash: + .quad 0x0002000080000000,0x0000000000000000 + restart_psw_crash + .section .kprobes.text, "ax" #ifdef CONFIG_CHECK_STACK @@ -949,9 +955,11 @@ cleanup_system_call: stg %r15,32(%r12) stg %r11,0(%r12) CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC mvc 8(8,%r12),__LC_THREAD_INFO + lg %r12,__LC_THREAD_INFO + mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+7(%r12),_TIF_SYSCALL cleanup_vtime: clc __LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+24) jhe cleanup_stime @@ -1036,6 +1044,63 @@ cleanup_io_restore_insn: .Lcritical_end: .quad __critical_end +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +/* + * sie64a calling convention: + * %r2 pointer to sie control block + * %r3 guest register save area + */ +ENTRY(sie64a) + stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers + stg %r2,__SF_EMPTY(%r15) # save control block pointer + stg %r3,__SF_EMPTY+8(%r15) # save guest register save area + lmg %r0,%r13,0(%r3) # load guest gprs 0-13 + lg %r14,__LC_THREAD_INFO # pointer thread_info struct + oi __TI_flags+6(%r14),_TIF_SIE>>8 +sie_loop: + lg %r14,__LC_THREAD_INFO # pointer thread_info struct + tm __TI_flags+7(%r14),_TIF_EXIT_SIE + jnz sie_exit + lg %r14,__LC_GMAP # get gmap pointer + ltgr %r14,%r14 + jz sie_gmap + lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce +sie_gmap: + lg %r14,__SF_EMPTY(%r15) # get control block pointer + SPP __SF_EMPTY(%r15) # set guest id + sie 0(%r14) +sie_done: + SPP __LC_CMF_HPP # set host id + lg %r14,__LC_THREAD_INFO # pointer thread_info struct +sie_exit: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) + lg %r14,__SF_EMPTY+8(%r15) # load guest register save area + stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers + lghi %r2,0 + br %r14 +sie_fault: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + lg %r14,__LC_THREAD_INFO # pointer thread_info struct + ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) + lg %r14,__SF_EMPTY+8(%r15) # load guest register save area + stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers + lghi %r2,-EFAULT + br %r14 + + .align 8 +.Lsie_loop: + .quad sie_loop +.Lsie_done: + .quad sie_done + + .section __ex_table,"a" + .quad sie_loop,sie_fault + .previous +#endif + .section .rodata, "a" #define SYSCALL(esa,esame,emu) .long esame .globl sys_call_table diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index fb317bf2c378..900068d2bf92 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -22,6 +22,7 @@ */ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> @@ -383,8 +384,7 @@ iplstart: # doesn't need a builtin ipl record. # .org 0x800 - .globl start -start: +ENTRY(start) stm %r0,%r15,0x07b0 # store registers basr %r12,%r0 .base: @@ -448,12 +448,29 @@ start: # or linload or SALIPL # .org 0x10000 - .globl startup -startup: +ENTRY(startup) + j .Lep_startup_normal + .org 0x10008 +# +# This is a list of s390 kernel entry points. At address 0x1000f the number of +# valid entry points is stored. +# +# IMPORTANT: Do not change this table, it is s390 kernel ABI! +# + .ascii "S390EP" + .byte 0x00,0x01 +# +# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode +# + .org 0x10010 +ENTRY(startup_kdump) + j .Lep_startup_kdump +.Lep_startup_normal: basr %r13,0 # get base .LPG0: xc 0x200(256),0x200 # partially clear lowcore xc 0x300(256),0x300 + xc 0xe00(256),0xe00 stck __LC_LAST_UPDATE_CLOCK spt 5f-.LPG0(%r13) mvc __LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13) @@ -535,6 +552,8 @@ startup: .align 8 5: .long 0x7fffffff,0xffffffff +#include "head_kdump.S" + # # params at 10400 (setup.h) # @@ -542,6 +561,8 @@ startup: .long 0,0 # IPL_DEVICE .long 0,0 # INITRD_START .long 0,0 # INITRD_SIZE + .long 0,0 # OLDMEM_BASE + .long 0,0 # OLDMEM_SIZE .org COMMAND_LINE .byte "root=/dev/ram0 ro" diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index b8f8dc126102..d3f1ab7d90ad 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -11,13 +11,13 @@ */ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> __HEAD - .globl startup_continue -startup_continue: +ENTRY(startup_continue) basr %r13,0 # get base .LPG1: @@ -45,7 +45,7 @@ startup_continue: # virtual and never return ... .align 8 .Lentry:.long 0x00080000,0x80000000 + _stext -.Lctl: .long 0x04b50002 # cr0: various things +.Lctl: .long 0x04b50000 # cr0: various things .long 0 # cr1: primary space segment table .long .Lduct # cr2: dispatchable unit control table .long 0 # cr3: instruction authorization @@ -78,8 +78,7 @@ startup_continue: .Lbase_cc: .long sched_clock_base_cc - .globl _ehead -_ehead: +ENTRY(_ehead) #ifdef CONFIG_SHARED_KERNEL .org 0x100000 - 0x11000 # head.o ends at 0x11000 @@ -88,12 +87,12 @@ _ehead: # # startup-code, running in absolute addressing mode # - .globl _stext -_stext: basr %r13,0 # get base +ENTRY(_stext) + basr %r13,0 # get base .LPG3: # check control registers stctl %c0,%c15,0(%r15) - oi 2(%r15),0x40 # enable sigp emergency signal + oi 2(%r15),0x60 # enable sigp emergency & external call oi 0(%r15),0x10 # switch on low address protection lctl %c0,%c15,0(%r15) diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index cdef68717416..99348c0eaa41 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -11,13 +11,13 @@ */ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> __HEAD - .globl startup_continue -startup_continue: +ENTRY(startup_continue) larl %r1,sched_clock_base_cc mvc 0(8,%r1),__LC_LAST_UPDATE_CLOCK larl %r13,.LPG1 # get base @@ -46,7 +46,7 @@ startup_continue: .align 16 .LPG1: .Lentry:.quad 0x0000000180000000,_stext -.Lctl: .quad 0x04350002 # cr0: various things +.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space .quad 0 # cr1: primary space segment table .quad .Lduct # cr2: dispatchable unit control table .quad 0 # cr3: instruction authorization @@ -76,8 +76,7 @@ startup_continue: .long 0x80000000,0,0,0 # invalid access-list entries .endr - .globl _ehead -_ehead: +ENTRY(_ehead) #ifdef CONFIG_SHARED_KERNEL .org 0x100000 - 0x11000 # head.o ends at 0x11000 @@ -86,12 +85,12 @@ _ehead: # # startup-code, running in absolute addressing mode # - .globl _stext -_stext: basr %r13,0 # get base +ENTRY(_stext) + basr %r13,0 # get base .LPG3: # check control registers stctg %c0,%c15,0(%r15) - oi 6(%r15),0x40 # enable sigp emergency signal + oi 6(%r15),0x60 # enable sigp emergency & external call oi 4(%r15),0x10 # switch on low address proctection lctlg %c0,%c15,0(%r15) diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S new file mode 100644 index 000000000000..e1ac3893e972 --- /dev/null +++ b/arch/s390/kernel/head_kdump.S @@ -0,0 +1,119 @@ +/* + * S390 kdump lowlevel functions (new kernel) + * + * Copyright IBM Corp. 2011 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#define DATAMOVER_ADDR 0x4000 +#define COPY_PAGE_ADDR 0x6000 + +#ifdef CONFIG_CRASH_DUMP + +# +# kdump entry (new kernel - not yet relocated) +# +# Note: This code has to be position independent +# + +.align 2 +.Lep_startup_kdump: + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # Switch to esame mode + sam64 # Switch to 64 bit addressing + basr %r13,0 +.Lbase: + larl %r2,.Lbase_addr # Check, if we have been + lg %r2,0(%r2) # already relocated: + clgr %r2,%r13 # + jne .Lrelocate # No : Start data mover + lghi %r2,0 # Yes: Start kdump kernel + brasl %r14,startup_kdump_relocated + +.Lrelocate: + larl %r4,startup + lg %r2,0x418(%r4) # Get kdump base + lg %r3,0x420(%r4) # Get kdump size + + larl %r10,.Lcopy_start # Source of data mover + lghi %r8,DATAMOVER_ADDR # Target of data mover + mvc 0(256,%r8),0(%r10) # Copy data mover code + + agr %r8,%r2 # Copy data mover to + mvc 0(256,%r8),0(%r10) # reserved mem + + lghi %r14,DATAMOVER_ADDR # Jump to copied data mover + basr %r14,%r14 +.Lbase_addr: + .quad .Lbase + +# +# kdump data mover code (runs at address DATAMOVER_ADDR) +# +# r2: kdump base address +# r3: kdump size +# +.Lcopy_start: + basr %r13,0 # Base +0: + lgr %r11,%r2 # Save kdump base address + lgr %r12,%r2 + agr %r12,%r3 # Compute kdump end address + + lghi %r5,0 + lghi %r10,COPY_PAGE_ADDR # Load copy page address +1: + mvc 0(256,%r10),0(%r5) # Copy old kernel to tmp + mvc 0(256,%r5),0(%r11) # Copy new kernel to old + mvc 0(256,%r11),0(%r10) # Copy tmp to new + aghi %r11,256 + aghi %r5,256 + clgr %r11,%r12 + jl 1b + + lg %r14,.Lstartup_kdump-0b(%r13) + basr %r14,%r14 # Start relocated kernel +.Lstartup_kdump: + .long 0x00000000,0x00000000 + startup_kdump_relocated +.Lcopy_end: + +# +# Startup of kdump (relocated new kernel) +# +.align 2 +startup_kdump_relocated: + basr %r13,0 +0: + mvc 0(8,%r0),.Lrestart_psw-0b(%r13) # Setup restart PSW + mvc 464(16,%r0),.Lpgm_psw-0b(%r13) # Setup pgm check PSW + lhi %r1,1 # Start new kernel + diag %r1,%r1,0x308 # with diag 308 + +.Lno_diag308: # No diag 308 + sam31 # Switch to 31 bit addr mode + sr %r1,%r1 # Erase register r1 + sr %r2,%r2 # Erase register r2 + sigp %r1,%r2,0x12 # Switch to 31 bit arch mode + lpsw 0 # Start new kernel... +.align 8 +.Lrestart_psw: + .long 0x00080000,0x80000000 + startup +.Lpgm_psw: + .quad 0x0000000180000000,0x0000000000000000 + .Lno_diag308 +#else +.align 2 +.Lep_startup_kdump: +#ifdef CONFIG_64BIT + larl %r13,startup_kdump_crash + lpswe 0(%r13) +.align 8 +startup_kdump_crash: + .quad 0x0002000080000000,0x0000000000000000 + startup_kdump_crash +#else + basr %r13,0 +0: lpsw startup_kdump_crash-0b(%r13) +.align 8 +startup_kdump_crash: + .long 0x000a0000,0x00000000 + startup_kdump_crash +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_CRASH_DUMP */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index a689070be287..affa8e68124a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -16,6 +16,7 @@ #include <linux/ctype.h> #include <linux/fs.h> #include <linux/gfp.h> +#include <linux/crash_dump.h> #include <asm/ipl.h> #include <asm/smp.h> #include <asm/setup.h> @@ -26,6 +27,7 @@ #include <asm/sclp.h> #include <asm/sigp.h> #include <asm/checksum.h> +#include "entry.h" #define IPL_PARM_BLOCK_VERSION 0 @@ -45,11 +47,13 @@ * - halt * - power off * - reipl + * - restart */ #define ON_PANIC_STR "on_panic" #define ON_HALT_STR "on_halt" #define ON_POFF_STR "on_poff" #define ON_REIPL_STR "on_reboot" +#define ON_RESTART_STR "on_restart" struct shutdown_action; struct shutdown_trigger { @@ -273,8 +277,8 @@ static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr, static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type); /* VM IPL PARM routines */ -size_t reipl_get_ascii_vmparm(char *dest, size_t size, - const struct ipl_parameter_block *ipb) +static size_t reipl_get_ascii_vmparm(char *dest, size_t size, + const struct ipl_parameter_block *ipb) { int i; size_t len; @@ -336,8 +340,8 @@ static size_t scpdata_length(const char* buf, size_t count) return count; } -size_t reipl_append_ascii_scpdata(char *dest, size_t size, - const struct ipl_parameter_block *ipb) +static size_t reipl_append_ascii_scpdata(char *dest, size_t size, + const struct ipl_parameter_block *ipb) { size_t count; size_t i; @@ -1218,7 +1222,7 @@ static int __init reipl_fcp_init(void) /* sysfs: create fcp kset for mixing attr group and bin attrs */ reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL, &reipl_kset->kobj); - if (!reipl_kset) { + if (!reipl_fcp_kset) { free_page((unsigned long) reipl_block_fcp); return -ENOMEM; } @@ -1544,17 +1548,20 @@ static char vmcmd_on_reboot[128]; static char vmcmd_on_panic[128]; static char vmcmd_on_halt[128]; static char vmcmd_on_poff[128]; +static char vmcmd_on_restart[128]; DEFINE_IPL_ATTR_STR_RW(vmcmd, on_reboot, "%s\n", "%s\n", vmcmd_on_reboot); DEFINE_IPL_ATTR_STR_RW(vmcmd, on_panic, "%s\n", "%s\n", vmcmd_on_panic); DEFINE_IPL_ATTR_STR_RW(vmcmd, on_halt, "%s\n", "%s\n", vmcmd_on_halt); DEFINE_IPL_ATTR_STR_RW(vmcmd, on_poff, "%s\n", "%s\n", vmcmd_on_poff); +DEFINE_IPL_ATTR_STR_RW(vmcmd, on_restart, "%s\n", "%s\n", vmcmd_on_restart); static struct attribute *vmcmd_attrs[] = { &sys_vmcmd_on_reboot_attr.attr, &sys_vmcmd_on_panic_attr.attr, &sys_vmcmd_on_halt_attr.attr, &sys_vmcmd_on_poff_attr.attr, + &sys_vmcmd_on_restart_attr.attr, NULL, }; @@ -1576,6 +1583,8 @@ static void vmcmd_run(struct shutdown_trigger *trigger) cmd = vmcmd_on_halt; else if (strcmp(trigger->name, ON_POFF_STR) == 0) cmd = vmcmd_on_poff; + else if (strcmp(trigger->name, ON_RESTART_STR) == 0) + cmd = vmcmd_on_restart; else return; @@ -1611,7 +1620,8 @@ static struct shutdown_action vmcmd_action = {SHUTDOWN_ACTION_VMCMD_STR, static void stop_run(struct shutdown_trigger *trigger) { - if (strcmp(trigger->name, ON_PANIC_STR) == 0) + if (strcmp(trigger->name, ON_PANIC_STR) == 0 || + strcmp(trigger->name, ON_RESTART_STR) == 0) disabled_wait((unsigned long) __builtin_return_address(0)); while (sigp(smp_processor_id(), sigp_stop) == sigp_busy) cpu_relax(); @@ -1707,6 +1717,38 @@ static void do_panic(void) stop_run(&on_panic_trigger); } +/* on restart */ + +static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR, + &stop_action}; + +static ssize_t on_restart_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%s\n", on_restart_trigger.action->name); +} + +static ssize_t on_restart_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return set_trigger(buf, &on_restart_trigger, len); +} + +static struct kobj_attribute on_restart_attr = + __ATTR(on_restart, 0644, on_restart_show, on_restart_store); + +void do_restart(void) +{ + smp_restart_with_online_cpu(); + smp_send_stop(); +#ifdef CONFIG_CRASH_DUMP + crash_kexec(NULL); +#endif + on_restart_trigger.action->fn(&on_restart_trigger); + stop_run(&on_restart_trigger); +} + /* on halt */ static struct shutdown_trigger on_halt_trigger = {ON_HALT_STR, &stop_action}; @@ -1783,7 +1825,9 @@ static void __init shutdown_triggers_init(void) if (sysfs_create_file(&shutdown_actions_kset->kobj, &on_poff_attr.attr)) goto fail; - + if (sysfs_create_file(&shutdown_actions_kset->kobj, + &on_restart_attr.attr)) + goto fail; return; fail: panic("shutdown_triggers_init failed\n"); @@ -1959,13 +2003,19 @@ static void do_reset_calls(void) { struct reset_call *reset; +#ifdef CONFIG_64BIT + if (diag308_set_works) { + diag308_reset(); + return; + } +#endif list_for_each_entry(reset, &rcall, list) reset->fn(); } u32 dump_prefix_page; -void s390_reset_system(void) +void s390_reset_system(void (*func)(void *), void *data) { struct _lowcore *lc; @@ -1984,15 +2034,19 @@ void s390_reset_system(void) __ctl_clear_bit(0,28); /* Set new machine check handler */ - S390_lowcore.mcck_new_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK; + S390_lowcore.mcck_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; S390_lowcore.mcck_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler; /* Set new program check handler */ - S390_lowcore.program_new_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; S390_lowcore.program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + /* Store status at absolute zero */ + store_status(); + do_reset_calls(); + if (func) + func(data); } - diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index e3264f6a9720..b9a7fdd9c814 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -33,7 +33,8 @@ static const struct irq_class intrclass_names[] = { {.name = "EXT" }, {.name = "I/O" }, {.name = "CLK", .desc = "[EXT] Clock Comparator" }, - {.name = "IPI", .desc = "[EXT] Signal Processor" }, + {.name = "EXC", .desc = "[EXT] External Call" }, + {.name = "EMS", .desc = "[EXT] Emergency Signal" }, {.name = "TMR", .desc = "[EXT] CPU Timer" }, {.name = "TAL", .desc = "[EXT] Timing Alert" }, {.name = "PFL", .desc = "[EXT] Pseudo Page Fault" }, @@ -42,8 +43,8 @@ static const struct irq_class intrclass_names[] = { {.name = "SCP", .desc = "[EXT] Service Call" }, {.name = "IUC", .desc = "[EXT] IUCV" }, {.name = "CPM", .desc = "[EXT] CPU Measurement" }, + {.name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt" }, {.name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt" }, - {.name = "QDI", .desc = "[I/O] QDIO Interrupt" }, {.name = "DAS", .desc = "[I/O] DASD" }, {.name = "C15", .desc = "[I/O] 3215" }, {.name = "C70", .desc = "[I/O] 3270" }, @@ -53,6 +54,7 @@ static const struct irq_class intrclass_names[] = { {.name = "CLW", .desc = "[I/O] CLAW" }, {.name = "CTC", .desc = "[I/O] CTC" }, {.name = "APB", .desc = "[I/O] AP Bus" }, + {.name = "CSC", .desc = "[I/O] CHSC Subchannel" }, {.name = "NMI", .desc = "[NMI] Machine Check" }, }; @@ -88,15 +90,6 @@ int show_interrupts(struct seq_file *p, void *v) } /* - * For compatibilty only. S/390 specific setup of interrupts et al. is done - * much later in init_channel_subsystem(). - */ -void __init init_IRQ(void) -{ - /* nothing... */ -} - -/* * Switch to the asynchronous interrupt stack for softirq execution. */ asmlinkage void do_softirq(void) @@ -144,28 +137,45 @@ void init_irq_proc(void) #endif /* - * ext_int_hash[index] is the start of the list for all external interrupts - * that hash to this index. With the current set of external interrupts - * (0x1202 external call, 0x1004 cpu timer, 0x2401 hwc console, 0x4000 - * iucv and 0x2603 pfault) this is always the first element. + * ext_int_hash[index] is the list head for all external interrupts that hash + * to this index. */ +static struct list_head ext_int_hash[256]; struct ext_int_info { - struct ext_int_info *next; ext_int_handler_t handler; u16 code; + struct list_head entry; + struct rcu_head rcu; }; -static struct ext_int_info *ext_int_hash[256]; +/* ext_int_hash_lock protects the handler lists for external interrupts */ +DEFINE_SPINLOCK(ext_int_hash_lock); + +static void __init init_external_interrupts(void) +{ + int idx; + + for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) + INIT_LIST_HEAD(&ext_int_hash[idx]); +} static inline int ext_hash(u16 code) { return (code + (code >> 9)) & 0xff; } +static void ext_int_hash_update(struct rcu_head *head) +{ + struct ext_int_info *p = container_of(head, struct ext_int_info, rcu); + + kfree(p); +} + int register_external_interrupt(u16 code, ext_int_handler_t handler) { struct ext_int_info *p; + unsigned long flags; int index; p = kmalloc(sizeof(*p), GFP_ATOMIC); @@ -174,33 +184,27 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler) p->code = code; p->handler = handler; index = ext_hash(code); - p->next = ext_int_hash[index]; - ext_int_hash[index] = p; + + spin_lock_irqsave(&ext_int_hash_lock, flags); + list_add_rcu(&p->entry, &ext_int_hash[index]); + spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; } EXPORT_SYMBOL(register_external_interrupt); int unregister_external_interrupt(u16 code, ext_int_handler_t handler) { - struct ext_int_info *p, *q; - int index; + struct ext_int_info *p; + unsigned long flags; + int index = ext_hash(code); - index = ext_hash(code); - q = NULL; - p = ext_int_hash[index]; - while (p) { - if (p->code == code && p->handler == handler) - break; - q = p; - p = p->next; - } - if (!p) - return -ENOENT; - if (q) - q->next = p->next; - else - ext_int_hash[index] = p->next; - kfree(p); + spin_lock_irqsave(&ext_int_hash_lock, flags); + list_for_each_entry_rcu(p, &ext_int_hash[index], entry) + if (p->code == code && p->handler == handler) { + list_del_rcu(&p->entry); + call_rcu(&p->rcu, ext_int_hash_update); + } + spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; } EXPORT_SYMBOL(unregister_external_interrupt); @@ -224,15 +228,22 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned int ext_int_code, kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++; if (code != 0x1004) __get_cpu_var(s390_idle).nohz_delay = 1; + index = ext_hash(code); - for (p = ext_int_hash[index]; p; p = p->next) { + rcu_read_lock(); + list_for_each_entry_rcu(p, &ext_int_hash[index], entry) if (likely(p->code == code)) p->handler(ext_int_code, param32, param64); - } + rcu_read_unlock(); irq_exit(); set_irq_regs(old_regs); } +void __init init_IRQ(void) +{ + init_external_interrupts(); +} + static DEFINE_SPINLOCK(sc_irq_lock); static int sc_irq_refcount; diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index 44cc06bedf77..b987ab2c1541 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -18,26 +18,15 @@ struct insn { } __packed; struct insn_args { - unsigned long *target; - struct insn *insn; - ssize_t size; + struct jump_entry *entry; + enum jump_label_type type; }; -static int __arch_jump_label_transform(void *data) +static void __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) { - struct insn_args *args = data; - int rc; - - rc = probe_kernel_write(args->target, args->insn, args->size); - WARN_ON_ONCE(rc < 0); - return 0; -} - -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) -{ - struct insn_args args; struct insn insn; + int rc; if (type == JUMP_LABEL_ENABLE) { /* brcl 15,offset */ @@ -49,11 +38,33 @@ void arch_jump_label_transform(struct jump_entry *entry, insn.offset = 0; } - args.target = (void *) entry->code; - args.insn = &insn; - args.size = JUMP_LABEL_NOP_SIZE; + rc = probe_kernel_write((void *)entry->code, &insn, JUMP_LABEL_NOP_SIZE); + WARN_ON_ONCE(rc < 0); +} - stop_machine(__arch_jump_label_transform, &args, NULL); +static int __sm_arch_jump_label_transform(void *data) +{ + struct insn_args *args = data; + + __jump_label_transform(args->entry, args->type); + return 0; +} + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + struct insn_args args; + + args.entry = entry; + args.type = type; + + stop_machine(__sm_arch_jump_label_transform, &args, NULL); +} + +void arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) +{ + __jump_label_transform(entry, type); } #endif diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 1d05d669107c..64b761aef004 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -635,7 +635,7 @@ void __kprobes jprobe_return(void) asm volatile(".word 0x0002"); } -void __kprobes jprobe_return_end(void) +static void __used __kprobes jprobe_return_end(void) { asm volatile("bcr 0,0"); } diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b09b9c62573e..3cd0f25ab015 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -1,10 +1,11 @@ /* * arch/s390/kernel/machine_kexec.c * - * Copyright IBM Corp. 2005,2006 + * Copyright IBM Corp. 2005,2011 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> */ #include <linux/device.h> @@ -21,12 +22,162 @@ #include <asm/smp.h> #include <asm/reset.h> #include <asm/ipl.h> +#include <asm/diag.h> +#include <asm/asm-offsets.h> typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long); extern const unsigned char relocate_kernel[]; extern const unsigned long long relocate_kernel_len; +#ifdef CONFIG_CRASH_DUMP + +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa); + +/* + * Create ELF notes for one CPU + */ +static void add_elf_notes(int cpu) +{ + struct save_area *sa = (void *) 4608 + store_prefix(); + void *ptr; + + memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa)); + ptr = (u64 *) per_cpu_ptr(crash_notes, cpu); + ptr = fill_cpu_elf_notes(ptr, sa); + memset(ptr, 0, sizeof(struct elf_note)); +} + +/* + * Store status of next available physical CPU + */ +static int store_status_next(int start_cpu, int this_cpu) +{ + struct save_area *sa = (void *) 4608 + store_prefix(); + int cpu, rc; + + for (cpu = start_cpu; cpu < 65536; cpu++) { + if (cpu == this_cpu) + continue; + do { + rc = raw_sigp(cpu, sigp_stop_and_store_status); + } while (rc == sigp_busy); + if (rc != sigp_order_code_accepted) + continue; + if (sa->pref_reg) + return cpu; + } + return -1; +} + +/* + * Initialize CPU ELF notes + */ +void setup_regs(void) +{ + unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE; + int cpu, this_cpu, phys_cpu = 0, first = 1; + + this_cpu = stap(); + + if (!S390_lowcore.prefixreg_save_area) + first = 0; + for_each_online_cpu(cpu) { + if (first) { + add_elf_notes(cpu); + first = 0; + continue; + } + phys_cpu = store_status_next(phys_cpu, this_cpu); + if (phys_cpu == -1) + break; + add_elf_notes(cpu); + phys_cpu++; + } + /* Copy dump CPU store status info to absolute zero */ + memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); +} + +#endif + +/* + * Start kdump: We expect here that a store status has been done on our CPU + */ +static void __do_machine_kdump(void *image) +{ +#ifdef CONFIG_CRASH_DUMP + int (*start_kdump)(int) = (void *)((struct kimage *) image)->start; + + __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); + setup_regs(); + start_kdump(1); +#endif +} + +/* + * Check if kdump checksums are valid: We call purgatory with parameter "0" + */ +static int kdump_csum_valid(struct kimage *image) +{ +#ifdef CONFIG_CRASH_DUMP + int (*start_kdump)(int) = (void *)image->start; + int rc; + + __arch_local_irq_stnsm(0xfb); /* disable DAT */ + rc = start_kdump(0); + __arch_local_irq_stosm(0x04); /* enable DAT */ + return rc ? 0 : -EINVAL; +#else + return -EINVAL; +#endif +} + +/* + * Map or unmap crashkernel memory + */ +static void crash_map_pages(int enable) +{ + unsigned long size = resource_size(&crashk_res); + + BUG_ON(crashk_res.start % KEXEC_CRASH_MEM_ALIGN || + size % KEXEC_CRASH_MEM_ALIGN); + if (enable) + vmem_add_mapping(crashk_res.start, size); + else + vmem_remove_mapping(crashk_res.start, size); +} + +/* + * Map crashkernel memory + */ +void crash_map_reserved_pages(void) +{ + crash_map_pages(1); +} + +/* + * Unmap crashkernel memory + */ +void crash_unmap_reserved_pages(void) +{ + crash_map_pages(0); +} + +/* + * Give back memory to hypervisor before new kdump is loaded + */ +static int machine_kexec_prepare_kdump(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (MACHINE_IS_VM) + diag10_range(PFN_DOWN(crashk_res.start), + PFN_DOWN(crashk_res.end - crashk_res.start + 1)); + return 0; +#else + return -EINVAL; +#endif +} + int machine_kexec_prepare(struct kimage *image) { void *reboot_code_buffer; @@ -35,6 +186,9 @@ int machine_kexec_prepare(struct kimage *image) if (ipl_flags & IPL_NSS_VALID) return -ENOSYS; + if (image->type == KEXEC_TYPE_CRASH) + return machine_kexec_prepare_kdump(); + /* We don't support anything but the default image type for now. */ if (image->type != KEXEC_TYPE_DEFAULT) return -EINVAL; @@ -51,27 +205,53 @@ void machine_kexec_cleanup(struct kimage *image) { } +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_SYMBOL(lowcore_ptr); + VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); +} + void machine_shutdown(void) { } -static void __machine_kexec(void *data) +/* + * Do normal kexec + */ +static void __do_machine_kexec(void *data) { relocate_kernel_t data_mover; struct kimage *image = data; - pfault_fini(); - s390_reset_system(); - data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page); /* Call the moving routine */ (*data_mover)(&image->head, image->start); - for (;;); } +/* + * Reset system and call either kdump or normal kexec + */ +static void __machine_kexec(void *data) +{ + struct kimage *image = data; + + pfault_fini(); + if (image->type == KEXEC_TYPE_CRASH) + s390_reset_system(__do_machine_kdump, data); + else + s390_reset_system(__do_machine_kexec, data); + disabled_wait((unsigned long) __builtin_return_address(0)); +} + +/* + * Do either kdump or normal kexec. In case of kdump we first ask + * purgatory, if kdump checksums are valid. + */ void machine_kexec(struct kimage *image) { + if (image->type == KEXEC_TYPE_CRASH && !kdump_csum_valid(image)) + return; tracer_disable(); smp_send_stop(); smp_switch_to_ipl_cpu(__machine_kexec, image); diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 1e6a55795628..7e2c38ba1373 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -5,21 +5,19 @@ * */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> .section .kprobes.text, "ax" - .globl ftrace_stub -ftrace_stub: +ENTRY(ftrace_stub) br %r14 - .globl _mcount -_mcount: +ENTRY(_mcount) #ifdef CONFIG_DYNAMIC_FTRACE br %r14 - .globl ftrace_caller -ftrace_caller: +ENTRY(ftrace_caller) #endif stm %r2,%r5,16(%r15) bras %r1,2f @@ -41,8 +39,7 @@ ftrace_caller: #ifdef CONFIG_FUNCTION_GRAPH_TRACER l %r2,100(%r15) l %r3,152(%r15) - .globl ftrace_graph_caller -ftrace_graph_caller: +ENTRY(ftrace_graph_caller) # The bras instruction gets runtime patched to call prepare_ftrace_return. # See ftrace_enable_ftrace_graph_caller. The patched instruction is: # bras %r14,prepare_ftrace_return @@ -56,8 +53,7 @@ ftrace_graph_caller: #ifdef CONFIG_FUNCTION_GRAPH_TRACER - .globl return_to_handler -return_to_handler: +ENTRY(return_to_handler) stm %r2,%r5,16(%r15) st %r14,56(%r15) lr %r0,%r15 diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index e73667286ac0..f70cadec68fc 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -5,21 +5,19 @@ * */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> .section .kprobes.text, "ax" - .globl ftrace_stub -ftrace_stub: +ENTRY(ftrace_stub) br %r14 - .globl _mcount -_mcount: +ENTRY(_mcount) #ifdef CONFIG_DYNAMIC_FTRACE br %r14 - .globl ftrace_caller -ftrace_caller: +ENTRY(ftrace_caller) #endif larl %r1,function_trace_stop icm %r1,0xf,0(%r1) @@ -37,8 +35,7 @@ ftrace_caller: #ifdef CONFIG_FUNCTION_GRAPH_TRACER lg %r2,168(%r15) lg %r3,272(%r15) - .globl ftrace_graph_caller -ftrace_graph_caller: +ENTRY(ftrace_graph_caller) # The bras instruction gets runtime patched to call prepare_ftrace_return. # See ftrace_enable_ftrace_graph_caller. The patched instruction is: # bras %r14,prepare_ftrace_return @@ -52,8 +49,7 @@ ftrace_graph_caller: #ifdef CONFIG_FUNCTION_GRAPH_TRACER - .globl return_to_handler -return_to_handler: +ENTRY(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 aghi %r15,-160 diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c index 0fbe4e32f7ba..19b4568f4cee 100644 --- a/arch/s390/kernel/mem_detect.c +++ b/arch/s390/kernel/mem_detect.c @@ -62,3 +62,72 @@ void detect_memory_layout(struct mem_chunk chunk[]) arch_local_irq_restore(flags); } EXPORT_SYMBOL(detect_memory_layout); + +/* + * Create memory hole with given address, size, and type + */ +void create_mem_hole(struct mem_chunk chunks[], unsigned long addr, + unsigned long size, int type) +{ + unsigned long start, end, new_size; + int i; + + for (i = 0; i < MEMORY_CHUNKS; i++) { + if (chunks[i].size == 0) + continue; + if (addr + size < chunks[i].addr) + continue; + if (addr >= chunks[i].addr + chunks[i].size) + continue; + start = max(addr, chunks[i].addr); + end = min(addr + size, chunks[i].addr + chunks[i].size); + new_size = end - start; + if (new_size == 0) + continue; + if (start == chunks[i].addr && + end == chunks[i].addr + chunks[i].size) { + /* Remove chunk */ + chunks[i].type = type; + } else if (start == chunks[i].addr) { + /* Make chunk smaller at start */ + if (i >= MEMORY_CHUNKS - 1) + panic("Unable to create memory hole"); + memmove(&chunks[i + 1], &chunks[i], + sizeof(struct mem_chunk) * + (MEMORY_CHUNKS - (i + 1))); + chunks[i + 1].addr = chunks[i].addr + new_size; + chunks[i + 1].size = chunks[i].size - new_size; + chunks[i].size = new_size; + chunks[i].type = type; + i += 1; + } else if (end == chunks[i].addr + chunks[i].size) { + /* Make chunk smaller at end */ + if (i >= MEMORY_CHUNKS - 1) + panic("Unable to create memory hole"); + memmove(&chunks[i + 1], &chunks[i], + sizeof(struct mem_chunk) * + (MEMORY_CHUNKS - (i + 1))); + chunks[i + 1].addr = start; + chunks[i + 1].size = new_size; + chunks[i + 1].type = type; + chunks[i].size -= new_size; + i += 1; + } else { + /* Create memory hole */ + if (i >= MEMORY_CHUNKS - 2) + panic("Unable to create memory hole"); + memmove(&chunks[i + 2], &chunks[i], + sizeof(struct mem_chunk) * + (MEMORY_CHUNKS - (i + 2))); + chunks[i + 1].addr = addr; + chunks[i + 1].size = size; + chunks[i + 1].type = type; + chunks[i + 2].addr = addr + size; + chunks[i + 2].size = + chunks[i].addr + chunks[i].size - (addr + size); + chunks[i + 2].type = chunks[i].type; + chunks[i].size = addr - chunks[i].addr; + i += 2; + } + } +} diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index f7167ee4604c..dfcb3436bad0 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -45,13 +45,6 @@ #define PLT_ENTRY_SIZE 20 #endif /* CONFIG_64BIT */ -void *module_alloc(unsigned long size) -{ - if (size == 0) - return NULL; - return vmalloc(size); -} - /* Free memory returned from module_alloc */ void module_free(struct module *mod, void *module_region) { @@ -176,15 +169,6 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, return 0; } -int -apply_relocate(Elf_Shdr *sechdrs, const char *strtab, unsigned int symindex, - unsigned int relsec, struct module *me) -{ - printk(KERN_ERR "module %s: RELOCATION unsupported\n", - me->name); - return -ENOEXEC; -} - static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, struct module *me) @@ -409,7 +393,3 @@ int module_finalize(const Elf_Ehdr *hdr, me->arch.syminfo = NULL; return 0; } - -void module_arch_cleanup(struct module *mod) -{ -} diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 541a7509faeb..9451b210a1b4 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -12,6 +12,7 @@ #include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/elfcore.h> #include <linux/smp.h> #include <linux/slab.h> #include <linux/interrupt.h> @@ -117,7 +118,8 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) struct pt_regs regs; memset(®s, 0, sizeof(regs)); - regs.psw.mask = psw_kernel_bits | PSW_MASK_IO | PSW_MASK_EXT; + regs.psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE; regs.gprs[9] = (unsigned long) fn; regs.gprs[10] = (unsigned long) arg; diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 311e9d712888..6e0073e43f54 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -74,7 +74,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? (void *)((unsigned long) *pos + 1) : NULL; + return *pos < nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ef86ad243986..450931a45b68 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -42,34 +42,37 @@ enum s390_regset { REGSET_GENERAL, REGSET_FP, REGSET_LAST_BREAK, + REGSET_SYSTEM_CALL, REGSET_GENERAL_EXTENDED, }; void update_per_regs(struct task_struct *task) { - static const struct per_regs per_single_step = { - .control = PER_EVENT_IFETCH, - .start = 0, - .end = PSW_ADDR_INSN, - }; struct pt_regs *regs = task_pt_regs(task); struct thread_struct *thread = &task->thread; - const struct per_regs *new; - struct per_regs old; - - /* TIF_SINGLE_STEP overrides the user specified PER registers. */ - new = test_tsk_thread_flag(task, TIF_SINGLE_STEP) ? - &per_single_step : &thread->per_user; + struct per_regs old, new; + + /* Copy user specified PER registers */ + new.control = thread->per_user.control; + new.start = thread->per_user.start; + new.end = thread->per_user.end; + + /* merge TIF_SINGLE_STEP into user specified PER registers. */ + if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) { + new.control |= PER_EVENT_IFETCH; + new.start = 0; + new.end = PSW_ADDR_INSN; + } /* Take care of the PER enablement bit in the PSW. */ - if (!(new->control & PER_EVENT_MASK)) { + if (!(new.control & PER_EVENT_MASK)) { regs->psw.mask &= ~PSW_MASK_PER; return; } regs->psw.mask |= PSW_MASK_PER; __ctl_store(old, 9, 11); - if (memcmp(new, &old, sizeof(struct per_regs)) != 0) - __ctl_load(*new, 9, 11); + if (memcmp(&new, &old, sizeof(struct per_regs)) != 0) + __ctl_load(new, 9, 11); } void user_enable_single_step(struct task_struct *task) @@ -166,8 +169,8 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) */ tmp = *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr); if (addr == (addr_t) &dummy->regs.psw.mask) - /* Remove per bit from user psw. */ - tmp &= ~PSW_MASK_PER; + /* Return a clean psw mask. */ + tmp = psw_user_bits | (tmp & PSW_MASK_USER); } else if (addr < (addr_t) &dummy->regs.orig_gpr2) { /* @@ -289,18 +292,17 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) * psw and gprs are stored on the stack */ if (addr == (addr_t) &dummy->regs.psw.mask && -#ifdef CONFIG_COMPAT - data != PSW_MASK_MERGE(psw_user32_bits, data) && -#endif - data != PSW_MASK_MERGE(psw_user_bits, data)) + ((data & ~PSW_MASK_USER) != psw_user_bits || + ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)))) /* Invalid psw mask. */ return -EINVAL; -#ifndef CONFIG_64BIT if (addr == (addr_t) &dummy->regs.psw.addr) - /* I'd like to reject addresses without the - high order bit but older gdb's rely on it */ - data |= PSW_ADDR_AMODE; -#endif + /* + * The debugger changed the instruction address, + * reset system call restart, see signal.c:do_signal + */ + task_thread_info(child)->system_call = 0; + *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { @@ -495,21 +497,21 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) __u32 tmp; if (addr < (addr_t) &dummy32->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw and gprs are stored on the stack */ if (addr == (addr_t) &dummy32->regs.psw.mask) { /* Fake a 31 bit psw mask. */ - tmp = (__u32)(task_pt_regs(child)->psw.mask >> 32); - tmp = PSW32_MASK_MERGE(psw32_user_bits, tmp); + tmp = (__u32)(regs->psw.mask >> 32); + tmp = psw32_user_bits | (tmp & PSW32_MASK_USER); } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Fake a 31 bit psw address. */ - tmp = (__u32) task_pt_regs(child)->psw.addr | - PSW32_ADDR_AMODE31; + tmp = (__u32) regs->psw.addr | + (__u32)(regs->psw.mask & PSW_MASK_BA); } else { /* gpr 0-15 */ - tmp = *(__u32 *)((addr_t) &task_pt_regs(child)->psw + - addr*2 + 4); + tmp = *(__u32 *)((addr_t) ®s->psw + addr*2 + 4); } } else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) { /* @@ -594,24 +596,32 @@ static int __poke_user_compat(struct task_struct *child, addr_t offset; if (addr < (addr_t) &dummy32->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw, gprs, acrs and orig_gpr2 are stored on the stack */ if (addr == (addr_t) &dummy32->regs.psw.mask) { /* Build a 64 bit psw mask from 31 bit mask. */ - if (tmp != PSW32_MASK_MERGE(psw32_user_bits, tmp)) + if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits) /* Invalid psw mask. */ return -EINVAL; - task_pt_regs(child)->psw.mask = - PSW_MASK_MERGE(psw_user32_bits, (__u64) tmp << 32); + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (regs->psw.mask & PSW_MASK_BA) | + (__u64)(tmp & PSW32_MASK_USER) << 32; } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Build a 64 bit psw address from 31 bit address. */ - task_pt_regs(child)->psw.addr = - (__u64) tmp & PSW32_ADDR_INSN; + regs->psw.addr = (__u64) tmp & PSW32_ADDR_INSN; + /* Transfer 31 bit amode bit to psw mask. */ + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) | + (__u64)(tmp & PSW32_ADDR_AMODE); + /* + * The debugger changed the instruction address, + * reset system call restart, see signal.c:do_signal + */ + task_thread_info(child)->system_call = 0; } else { /* gpr 0-15 */ - *(__u32*)((addr_t) &task_pt_regs(child)->psw - + addr*2 + 4) = tmp; + *(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp; } } else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) { /* @@ -735,7 +745,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) * debugger stored an invalid system call number. Skip * the system call and the system call restart handling. */ - regs->svcnr = 0; + clear_thread_flag(TIF_SYSCALL); ret = -1; } @@ -897,6 +907,26 @@ static int s390_last_break_get(struct task_struct *target, #endif +static int s390_system_call_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int *data = &task_thread_info(target)->system_call; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(unsigned int)); +} + +static int s390_system_call_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int *data = &task_thread_info(target)->system_call; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(unsigned int)); +} + static const struct user_regset s390_regsets[] = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, @@ -923,6 +953,14 @@ static const struct user_regset s390_regsets[] = { .get = s390_last_break_get, }, #endif + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_S390_SYSTEM_CALL, + .n = 1, + .size = sizeof(unsigned int), + .align = sizeof(unsigned int), + .get = s390_system_call_get, + .set = s390_system_call_set, + }, }; static const struct user_regset_view user_s390_view = { @@ -1102,6 +1140,14 @@ static const struct user_regset s390_compat_regsets[] = { .align = sizeof(long), .get = s390_compat_last_break_get, }, + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_S390_SYSTEM_CALL, + .n = 1, + .size = sizeof(compat_uint_t), + .align = sizeof(compat_uint_t), + .get = s390_system_call_get, + .set = s390_system_call_set, + }, [REGSET_GENERAL_EXTENDED] = { .core_note_type = NT_S390_HIGH_GPRS, .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index cb899d9f8505..ad67c214be04 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -6,14 +6,21 @@ * Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com) */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> # +# store_status: Empty implementation until kdump is supported on 31 bit +# +ENTRY(store_status) + br %r14 + +# # do_reipl_asm # Parameter: r2 = schid of reipl device # - .globl do_reipl_asm -do_reipl_asm: basr %r13,0 +ENTRY(do_reipl_asm) + basr %r13,0 .Lpg0: lpsw .Lnewpsw-.Lpg0(%r13) .Lpg1: # do store status of all registers diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S index 9eabbc90795d..732a793ec53a 100644 --- a/arch/s390/kernel/reipl64.S +++ b/arch/s390/kernel/reipl64.S @@ -1,35 +1,82 @@ /* - * Copyright IBM Corp 2000,2009 + * Copyright IBM Corp 2000,2011 * Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>, * Denis Joseph Barrow, */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> # +# store_status +# +# Prerequisites to run this function: +# - Prefix register is set to zero +# - Original prefix register is stored in "dump_prefix_page" +# - Lowcore protection is off +# +ENTRY(store_status) + /* Save register one and load save area base */ + stg %r1,__LC_SAVE_AREA+120(%r0) + lghi %r1,SAVE_AREA_BASE + /* General purpose registers */ + stmg %r0,%r15,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + lg %r2,__LC_SAVE_AREA+120(%r0) + stg %r2,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE+8(%r1) + /* Control registers */ + stctg %c0,%c15,__LC_CREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Access registers */ + stam %a0,%a15,__LC_AREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Floating point registers */ + std %f0, 0x00 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f1, 0x08 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f2, 0x10 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f3, 0x18 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f4, 0x20 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f5, 0x28 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f6, 0x30 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f7, 0x38 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f8, 0x40 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f9, 0x48 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f10,0x50 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f11,0x58 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f12,0x60 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f13,0x68 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f14,0x70 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + std %f15,0x78 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Floating point control register */ + stfpc __LC_FP_CREG_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* CPU timer */ + stpt __LC_CPU_TIMER_SAVE_AREA-SAVE_AREA_BASE(%r1) + /* Saved prefix register */ + larl %r2,dump_prefix_page + mvc __LC_PREFIX_SAVE_AREA-SAVE_AREA_BASE(4,%r1),0(%r2) + /* Clock comparator - seven bytes */ + larl %r2,.Lclkcmp + stckc 0(%r2) + mvc __LC_CLOCK_COMP_SAVE_AREA-SAVE_AREA_BASE + 1(7,%r1),1(%r2) + /* Program status word */ + epsw %r2,%r3 + st %r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 0(%r1) + st %r3,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 4(%r1) + larl %r2,store_status + stg %r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 8(%r1) + br %r14 + + .section .bss + .align 8 +.Lclkcmp: .quad 0x0000000000000000 + .previous + +# # do_reipl_asm # Parameter: r2 = schid of reipl device # - .globl do_reipl_asm -do_reipl_asm: basr %r13,0 +ENTRY(do_reipl_asm) + basr %r13,0 .Lpg0: lpswe .Lnewpsw-.Lpg0(%r13) -.Lpg1: # do store status of all registers - - stg %r1,.Lregsave-.Lpg0(%r13) - lghi %r1,0x1000 - stmg %r0,%r15,__LC_GPREGS_SAVE_AREA-0x1000(%r1) - lg %r0,.Lregsave-.Lpg0(%r13) - stg %r0,__LC_GPREGS_SAVE_AREA-0x1000+8(%r1) - stctg %c0,%c15,__LC_CREGS_SAVE_AREA-0x1000(%r1) - stam %a0,%a15,__LC_AREGS_SAVE_AREA-0x1000(%r1) - lg %r10,.Ldump_pfx-.Lpg0(%r13) - mvc __LC_PREFIX_SAVE_AREA-0x1000(4,%r1),0(%r10) - stfpc __LC_FP_CREG_SAVE_AREA-0x1000(%r1) - stckc .Lclkcmp-.Lpg0(%r13) - mvc __LC_CLOCK_COMP_SAVE_AREA-0x1000(7,%r1),.Lclkcmp-.Lpg0(%r13) - stpt __LC_CPU_TIMER_SAVE_AREA-0x1000(%r1) - stg %r13, __LC_PSW_SAVE_AREA-0x1000+8(%r1) +.Lpg1: brasl %r14,store_status lctlg %c6,%c6,.Lall-.Lpg0(%r13) lgr %r1,%r2 @@ -66,10 +113,7 @@ do_reipl_asm: basr %r13,0 st %r14,.Ldispsw+12-.Lpg0(%r13) lpswe .Ldispsw-.Lpg0(%r13) .align 8 -.Lclkcmp: .quad 0x0000000000000000 .Lall: .quad 0x00000000ff000000 -.Ldump_pfx: .quad dump_prefix_page -.Lregsave: .quad 0x0000000000000000 .align 16 /* * These addresses have to be 31 bit otherwise diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S index 3b456b80bcee..c91d70aede91 100644 --- a/arch/s390/kernel/relocate_kernel.S +++ b/arch/s390/kernel/relocate_kernel.S @@ -8,6 +8,8 @@ * */ +#include <linux/linkage.h> + /* * moves the new kernel to its destination... * %r2 = pointer to first kimage_entry_t @@ -22,8 +24,7 @@ */ .text - .globl relocate_kernel - relocate_kernel: +ENTRY(relocate_kernel) basr %r13,0 # base address .base: stnsm sys_msk-.base(%r13),0xfb # disable DAT @@ -112,6 +113,7 @@ .byte 0 .align 8 relocate_kernel_end: + .align 8 .globl relocate_kernel_len relocate_kernel_len: .quad relocate_kernel_end - relocate_kernel diff --git a/arch/s390/kernel/relocate_kernel64.S b/arch/s390/kernel/relocate_kernel64.S index 1f9ea2067b59..7c3ce589a7f0 100644 --- a/arch/s390/kernel/relocate_kernel64.S +++ b/arch/s390/kernel/relocate_kernel64.S @@ -8,6 +8,8 @@ * */ +#include <linux/linkage.h> + /* * moves the new kernel to its destination... * %r2 = pointer to first kimage_entry_t @@ -23,8 +25,7 @@ */ .text - .globl relocate_kernel - relocate_kernel: +ENTRY(relocate_kernel) basr %r13,0 # base address .base: stnsm sys_msk-.base(%r13),0xfb # disable DAT @@ -115,6 +116,7 @@ .byte 0 .align 8 relocate_kernel_end: + .align 8 .globl relocate_kernel_len relocate_kernel_len: .quad relocate_kernel_end - relocate_kernel diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 656fcbb9bd83..57b536649b00 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -1,6 +1,10 @@ #include <linux/module.h> +#include <linux/kvm_host.h> #include <asm/ftrace.h> #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); #endif +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +EXPORT_SYMBOL(sie64a); +#endif diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 2e82fdd89320..95792d846bb6 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -8,6 +8,8 @@ * */ +#include <linux/linkage.h> + LC_EXT_NEW_PSW = 0x58 # addr of ext int handler LC_EXT_NEW_PSW_64 = 0x1b0 # addr of ext int handler 64 bit LC_EXT_INT_PARAM = 0x80 # addr of ext int parameter @@ -260,8 +262,7 @@ _sclp_print: # R2 = 0 on success, 1 on failure # - .globl _sclp_print_early -_sclp_print_early: +ENTRY(_sclp_print_early) stm %r6,%r15,24(%r15) # save registers ahi %r15,-96 # create stack frame #ifdef CONFIG_64BIT diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 0c35dee10b00..e58a462949b1 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -42,6 +42,9 @@ #include <linux/reboot.h> #include <linux/topology.h> #include <linux/ftrace.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> +#include <linux/memory.h> #include <asm/ipl.h> #include <asm/uaccess.h> @@ -57,12 +60,13 @@ #include <asm/ebcdic.h> #include <asm/compat.h> #include <asm/kvm_virtio.h> +#include <asm/diag.h> -long psw_kernel_bits = (PSW_BASE_BITS | PSW_MASK_DAT | PSW_ASC_PRIMARY | - PSW_MASK_MCHECK | PSW_DEFAULT_KEY); -long psw_user_bits = (PSW_BASE_BITS | PSW_MASK_DAT | PSW_ASC_HOME | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY); +long psw_kernel_bits = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY | + PSW_MASK_EA | PSW_MASK_BA; +long psw_user_bits = PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | + PSW_MASK_PSTATE | PSW_ASC_HOME; /* * User copy operations. @@ -207,6 +211,8 @@ static void __init setup_zfcpdump(unsigned int console_devno) if (ipl_info.type != IPL_TYPE_FCP_DUMP) return; + if (OLDMEM_BASE) + return; if (console_devno != -1) sprintf(str, " cio_ignore=all,!0.0.%04x,!0.0.%04x", ipl_info.data.fcp.dev_id.devno, console_devno); @@ -274,22 +280,14 @@ early_param("mem", early_parse_mem); unsigned int user_mode = HOME_SPACE_MODE; EXPORT_SYMBOL_GPL(user_mode); -static int set_amode_and_uaccess(unsigned long user_amode, - unsigned long user32_amode) +static int set_amode_primary(void) { - psw_user_bits = PSW_BASE_BITS | PSW_MASK_DAT | user_amode | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY; + psw_kernel_bits = (psw_kernel_bits & ~PSW_MASK_ASC) | PSW_ASC_HOME; + psw_user_bits = (psw_user_bits & ~PSW_MASK_ASC) | PSW_ASC_PRIMARY; #ifdef CONFIG_COMPAT - psw_user32_bits = PSW_BASE32_BITS | PSW_MASK_DAT | user_amode | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY; - psw32_user_bits = PSW32_BASE_BITS | PSW32_MASK_DAT | user32_amode | - PSW32_MASK_IO | PSW32_MASK_EXT | PSW32_MASK_MCHECK | - PSW32_MASK_PSTATE; + psw32_user_bits = + (psw32_user_bits & ~PSW32_MASK_ASC) | PSW32_ASC_PRIMARY; #endif - psw_kernel_bits = PSW_BASE_BITS | PSW_MASK_DAT | PSW_ASC_HOME | - PSW_MASK_MCHECK | PSW_DEFAULT_KEY; if (MACHINE_HAS_MVCOS) { memcpy(&uaccess, &uaccess_mvcos_switch, sizeof(uaccess)); @@ -325,7 +323,7 @@ early_param("user_mode", early_parse_user_mode); static void setup_addressing_mode(void) { if (user_mode == PRIMARY_SPACE_MODE) { - if (set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY)) + if (set_amode_primary()) pr_info("Address spaces switched, " "mvcos available\n"); else @@ -344,24 +342,25 @@ setup_lowcore(void) */ BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096); lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0); - lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + lc->restart_psw.mask = psw_kernel_bits; lc->restart_psw.addr = - PSW_ADDR_AMODE | (unsigned long) restart_int_handler; - if (user_mode != HOME_SPACE_MODE) - lc->restart_psw.mask |= PSW_ASC_HOME; - lc->external_new_psw.mask = psw_kernel_bits; + PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; + lc->external_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; lc->external_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) ext_int_handler; - lc->svc_new_psw.mask = psw_kernel_bits | PSW_MASK_IO | PSW_MASK_EXT; + lc->svc_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call; - lc->program_new_psw.mask = psw_kernel_bits; + lc->program_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; lc->program_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long)pgm_check_handler; - lc->mcck_new_psw.mask = - psw_kernel_bits & ~PSW_MASK_MCHECK & ~PSW_MASK_DAT; + PSW_ADDR_AMODE | (unsigned long) pgm_check_handler; + lc->mcck_new_psw.mask = psw_kernel_bits; lc->mcck_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) mcck_int_handler; - lc->io_new_psw.mask = psw_kernel_bits; + lc->io_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; @@ -435,10 +434,14 @@ static void __init setup_resources(void) for (i = 0; i < MEMORY_CHUNKS; i++) { if (!memory_chunk[i].size) continue; + if (memory_chunk[i].type == CHUNK_OLDMEM || + memory_chunk[i].type == CHUNK_CRASHK) + continue; res = alloc_bootmem_low(sizeof(*res)); res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; switch (memory_chunk[i].type) { case CHUNK_READ_WRITE: + case CHUNK_CRASHK: res->name = "System RAM"; break; case CHUNK_READ_ONLY: @@ -479,8 +482,9 @@ static void __init setup_memory_end(void) unsigned long max_mem; int i; + #ifdef CONFIG_ZFCPDUMP - if (ipl_info.type == IPL_TYPE_FCP_DUMP) { + if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) { memory_end = ZFCPDUMP_HSA_SIZE; memory_end_set = 1; } @@ -529,6 +533,217 @@ static void __init setup_memory_end(void) memory_end = memory_size; } +void *restart_stack __attribute__((__section__(".data"))); + +/* + * Setup new PSW and allocate stack for PSW restart interrupt + */ +static void __init setup_restart_psw(void) +{ + psw_t psw; + + restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0); + restart_stack += ASYNC_SIZE; + + /* + * Setup restart PSW for absolute zero lowcore. This is necesary + * if PSW restart is done on an offline CPU that has lowcore zero + */ + psw.mask = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; + psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; + copy_to_absolute_zero(&S390_lowcore.restart_psw, &psw, sizeof(psw)); +} + +static void __init setup_vmcoreinfo(void) +{ +#ifdef CONFIG_KEXEC + unsigned long ptr = paddr_vmcoreinfo_note(); + + copy_to_absolute_zero(&S390_lowcore.vmcore_info, &ptr, sizeof(ptr)); +#endif +} + +#ifdef CONFIG_CRASH_DUMP + +/* + * Find suitable location for crashkernel memory + */ +static unsigned long __init find_crash_base(unsigned long crash_size, + char **msg) +{ + unsigned long crash_base; + struct mem_chunk *chunk; + int i; + + if (memory_chunk[0].size < crash_size) { + *msg = "first memory chunk must be at least crashkernel size"; + return 0; + } + if (is_kdump_kernel() && (crash_size == OLDMEM_SIZE)) + return OLDMEM_BASE; + + for (i = MEMORY_CHUNKS - 1; i >= 0; i--) { + chunk = &memory_chunk[i]; + if (chunk->size == 0) + continue; + if (chunk->type != CHUNK_READ_WRITE) + continue; + if (chunk->size < crash_size) + continue; + crash_base = (chunk->addr + chunk->size) - crash_size; + if (crash_base < crash_size) + continue; + if (crash_base < ZFCPDUMP_HSA_SIZE_MAX) + continue; + if (crash_base < (unsigned long) INITRD_START + INITRD_SIZE) + continue; + return crash_base; + } + *msg = "no suitable area found"; + return 0; +} + +/* + * Check if crash_base and crash_size is valid + */ +static int __init verify_crash_base(unsigned long crash_base, + unsigned long crash_size, + char **msg) +{ + struct mem_chunk *chunk; + int i; + + /* + * Because we do the swap to zero, we must have at least 'crash_size' + * bytes free space before crash_base + */ + if (crash_size > crash_base) { + *msg = "crashkernel offset must be greater than size"; + return -EINVAL; + } + + /* First memory chunk must be at least crash_size */ + if (memory_chunk[0].size < crash_size) { + *msg = "first memory chunk must be at least crashkernel size"; + return -EINVAL; + } + /* Check if we fit into the respective memory chunk */ + for (i = 0; i < MEMORY_CHUNKS; i++) { + chunk = &memory_chunk[i]; + if (chunk->size == 0) + continue; + if (crash_base < chunk->addr) + continue; + if (crash_base >= chunk->addr + chunk->size) + continue; + /* we have found the memory chunk */ + if (crash_base + crash_size > chunk->addr + chunk->size) { + *msg = "selected memory chunk is too small for " + "crashkernel memory"; + return -EINVAL; + } + return 0; + } + *msg = "invalid memory range specified"; + return -EINVAL; +} + +/* + * Reserve kdump memory by creating a memory hole in the mem_chunk array + */ +static void __init reserve_kdump_bootmem(unsigned long addr, unsigned long size, + int type) +{ + + create_mem_hole(memory_chunk, addr, size, type); +} + +/* + * When kdump is enabled, we have to ensure that no memory from + * the area [0 - crashkernel memory size] and + * [crashk_res.start - crashk_res.end] is set offline. + */ +static int kdump_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct memory_notify *arg = data; + + if (arg->start_pfn < PFN_DOWN(resource_size(&crashk_res))) + return NOTIFY_BAD; + if (arg->start_pfn > PFN_DOWN(crashk_res.end)) + return NOTIFY_OK; + if (arg->start_pfn + arg->nr_pages - 1 < PFN_DOWN(crashk_res.start)) + return NOTIFY_OK; + return NOTIFY_BAD; +} + +static struct notifier_block kdump_mem_nb = { + .notifier_call = kdump_mem_notifier, +}; + +#endif + +/* + * Make sure that oldmem, where the dump is stored, is protected + */ +static void reserve_oldmem(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (!OLDMEM_BASE) + return; + + reserve_kdump_bootmem(OLDMEM_BASE, OLDMEM_SIZE, CHUNK_OLDMEM); + reserve_kdump_bootmem(OLDMEM_SIZE, memory_end - OLDMEM_SIZE, + CHUNK_OLDMEM); + if (OLDMEM_BASE + OLDMEM_SIZE == real_memory_size) + saved_max_pfn = PFN_DOWN(OLDMEM_BASE) - 1; + else + saved_max_pfn = PFN_DOWN(real_memory_size) - 1; +#endif +} + +/* + * Reserve memory for kdump kernel to be loaded with kexec + */ +static void __init reserve_crashkernel(void) +{ +#ifdef CONFIG_CRASH_DUMP + unsigned long long crash_base, crash_size; + char *msg; + int rc; + + rc = parse_crashkernel(boot_command_line, memory_end, &crash_size, + &crash_base); + if (rc || crash_size == 0) + return; + crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN); + crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN); + if (register_memory_notifier(&kdump_mem_nb)) + return; + if (!crash_base) + crash_base = find_crash_base(crash_size, &msg); + if (!crash_base) { + pr_info("crashkernel reservation failed: %s\n", msg); + unregister_memory_notifier(&kdump_mem_nb); + return; + } + if (verify_crash_base(crash_base, crash_size, &msg)) { + pr_info("crashkernel reservation failed: %s\n", msg); + unregister_memory_notifier(&kdump_mem_nb); + return; + } + if (!OLDMEM_BASE && MACHINE_IS_VM) + diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size)); + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + insert_resource(&iomem_resource, &crashk_res); + reserve_kdump_bootmem(crash_base, crash_size, CHUNK_CRASHK); + pr_info("Reserving %lluMB of memory at %lluMB " + "for crashkernel (System RAM: %luMB)\n", + crash_size >> 20, crash_base >> 20, memory_end >> 20); +#endif +} + static void __init setup_memory(void) { @@ -559,6 +774,14 @@ setup_memory(void) if (PFN_PHYS(start_pfn) + bmap_size > INITRD_START) { start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE; +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE) { + /* Move initrd behind kdump oldmem */ + if (start + INITRD_SIZE > OLDMEM_BASE && + start < OLDMEM_BASE + OLDMEM_SIZE) + start = OLDMEM_BASE + OLDMEM_SIZE; + } +#endif if (start + INITRD_SIZE > memory_end) { pr_err("initrd extends beyond end of " "memory (0x%08lx > 0x%08lx) " @@ -589,7 +812,8 @@ setup_memory(void) for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { unsigned long start_chunk, end_chunk, pfn; - if (memory_chunk[i].type != CHUNK_READ_WRITE) + if (memory_chunk[i].type != CHUNK_READ_WRITE && + memory_chunk[i].type != CHUNK_CRASHK) continue; start_chunk = PFN_DOWN(memory_chunk[i].addr); end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size); @@ -623,6 +847,15 @@ setup_memory(void) reserve_bootmem(start_pfn << PAGE_SHIFT, bootmap_size, BOOTMEM_DEFAULT); +#ifdef CONFIG_CRASH_DUMP + if (crashk_res.start) + reserve_bootmem(crashk_res.start, + crashk_res.end - crashk_res.start + 1, + BOOTMEM_DEFAULT); + if (is_kdump_kernel()) + reserve_bootmem(elfcorehdr_addr - OLDMEM_BASE, + PAGE_ALIGN(elfcorehdr_size), BOOTMEM_DEFAULT); +#endif #ifdef CONFIG_BLK_DEV_INITRD if (INITRD_START && INITRD_SIZE) { if (INITRD_START + INITRD_SIZE <= memory_end) { @@ -731,6 +964,7 @@ static void __init setup_hwcaps(void) strcpy(elf_platform, "z10"); break; case 0x2817: + case 0x2818: strcpy(elf_platform, "z196"); break; } @@ -790,8 +1024,12 @@ setup_arch(char **cmdline_p) setup_ipl(); setup_memory_end(); setup_addressing_mode(); + reserve_oldmem(); + reserve_crashkernel(); setup_memory(); setup_resources(); + setup_vmcoreinfo(); + setup_restart_psw(); setup_lowcore(); cpu_init(); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index abbb3c3c7aab..05a85bc14c98 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -30,6 +30,7 @@ #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/lowcore.h> +#include <asm/compat.h> #include "entry.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -57,17 +58,15 @@ typedef struct */ SYSCALL_DEFINE3(sigsuspend, int, history0, int, history1, old_sigset_t, mask) { - mask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); - current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, mask); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; + mask &= _BLOCKABLE; + siginitset(&blocked, mask); + set_current_blocked(&blocked); set_current_state(TASK_INTERRUPTIBLE); schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); - + set_restore_sigmask(); return -ERESTARTNOHAND; } @@ -118,7 +117,8 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) /* Copy a 'clean' PSW mask to the user to avoid leaking information about whether PER is currently on. */ - user_sregs.regs.psw.mask = PSW_MASK_MERGE(psw_user_bits, regs->psw.mask); + user_sregs.regs.psw.mask = psw_user_bits | + (regs->psw.mask & PSW_MASK_USER); user_sregs.regs.psw.addr = regs->psw.addr; memcpy(&user_sregs.regs.gprs, ®s->gprs, sizeof(sregs->regs.gprs)); memcpy(&user_sregs.regs.acrs, current->thread.acrs, @@ -145,9 +145,13 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) err = __copy_from_user(&user_sregs, sregs, sizeof(_sigregs)); if (err) return err; - regs->psw.mask = PSW_MASK_MERGE(regs->psw.mask, - user_sregs.regs.psw.mask); - regs->psw.addr = PSW_ADDR_AMODE | user_sregs.regs.psw.addr; + /* Use regs->psw.mask instead of psw_user_bits to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (user_sregs.regs.psw.mask & PSW_MASK_USER); + /* Check for invalid amode */ + if (regs->psw.mask & PSW_MASK_EA) + regs->psw.mask |= PSW_MASK_BA; + regs->psw.addr = user_sregs.regs.psw.addr; memcpy(®s->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs)); memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, sizeof(sregs->regs.acrs)); @@ -158,7 +162,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) current->thread.fp_regs.fpc &= FPC_VALID_MASK; restore_fp_regs(¤t->thread.fp_regs); - regs->svcnr = 0; /* disable syscall checks */ + clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -172,18 +176,11 @@ SYSCALL_DEFINE0(sigreturn) goto badframe; if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE)) goto badframe; - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - + set_current_blocked(&set); if (restore_sigregs(regs, &frame->sregs)) goto badframe; - return regs->gprs[2]; - badframe: force_sig(SIGSEGV, current); return 0; @@ -199,21 +196,14 @@ SYSCALL_DEFINE0(rt_sigreturn) goto badframe; if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - + set_current_blocked(&set); if (restore_sigregs(regs, &frame->uc.uc_mcontext)) goto badframe; - if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->gprs[15]) == -EFAULT) goto badframe; return regs->gprs[2]; - badframe: force_sig(SIGSEGV, current); return 0; @@ -304,6 +294,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, /* Set up registers for signal handler */ regs->gprs[15] = (unsigned long) frame; + regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA; /* 64 bit amode */ regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; regs->gprs[2] = map_signal(sig); @@ -372,6 +363,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up registers for signal handler */ regs->gprs[15] = (unsigned long) frame; + regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA; /* 64 bit amode */ regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; regs->gprs[2] = map_signal(sig); @@ -385,14 +377,11 @@ give_sigsegv: return -EFAULT; } -/* - * OK, we're invoking a handler - */ - -static int -handle_signal(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, struct pt_regs * regs) +static int handle_signal(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, + struct pt_regs *regs) { + sigset_t blocked; int ret; /* Set up the stack frame */ @@ -400,17 +389,13 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, ret = setup_rt_frame(sig, ka, info, oldset, regs); else ret = setup_frame(sig, ka, oldset, regs); - - if (ret == 0) { - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - } - - return ret; + if (ret) + return ret; + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(&blocked, sig); + set_current_blocked(&blocked); + return 0; } /* @@ -424,7 +409,6 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, */ void do_signal(struct pt_regs *regs) { - unsigned long retval = 0, continue_addr = 0, restart_addr = 0; siginfo_t info; int signr; struct k_sigaction ka; @@ -444,54 +428,45 @@ void do_signal(struct pt_regs *regs) else oldset = ¤t->blocked; - /* Are we from a system call? */ - if (regs->svcnr) { - continue_addr = regs->psw.addr; - restart_addr = continue_addr - regs->ilc; - retval = regs->gprs[2]; - - /* Prepare for system call restart. We do this here so that a - debugger will see the already changed PSW. */ - switch (retval) { - case -ERESTARTNOHAND: - case -ERESTARTSYS: - case -ERESTARTNOINTR: - regs->gprs[2] = regs->orig_gpr2; - regs->psw.addr = restart_addr; - break; - case -ERESTART_RESTARTBLOCK: - regs->gprs[2] = -EINTR; - } - regs->svcnr = 0; /* Don't deal with this again. */ - } - - /* Get signal to deliver. When running under ptrace, at this point - the debugger may change all our registers ... */ + /* + * Get signal to deliver. When running under ptrace, at this point + * the debugger may change all our registers, including the system + * call information. + */ + current_thread_info()->system_call = + test_thread_flag(TIF_SYSCALL) ? regs->svc_code : 0; signr = get_signal_to_deliver(&info, &ka, regs, NULL); - /* Depending on the signal settings we may need to revert the - decision to restart the system call. */ - if (signr > 0 && regs->psw.addr == restart_addr) { - if (retval == -ERESTARTNOHAND - || (retval == -ERESTARTSYS - && !(current->sighand->action[signr-1].sa.sa_flags - & SA_RESTART))) { - regs->gprs[2] = -EINTR; - regs->psw.addr = continue_addr; - } - } - if (signr > 0) { /* Whee! Actually deliver the signal. */ - int ret; -#ifdef CONFIG_COMPAT - if (is_compat_task()) { - ret = handle_signal32(signr, &ka, &info, oldset, regs); - } - else -#endif - ret = handle_signal(signr, &ka, &info, oldset, regs); - if (!ret) { + if (current_thread_info()->system_call) { + regs->svc_code = current_thread_info()->system_call; + /* Check for system call restarting. */ + switch (regs->gprs[2]) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->gprs[2] = -EINTR; + break; + case -ERESTARTSYS: + if (!(ka.sa.sa_flags & SA_RESTART)) { + regs->gprs[2] = -EINTR; + break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->gprs[2] = regs->orig_gpr2; + regs->psw.addr = + __rewind_psw(regs->psw, + regs->svc_code >> 16); + break; + } + /* No longer in a system call */ + clear_thread_flag(TIF_SYSCALL); + } + + if ((is_compat_task() ? + handle_signal32(signr, &ka, &info, oldset, regs) : + handle_signal(signr, &ka, &info, oldset, regs)) == 0) { /* * A signal was successfully delivered; the saved * sigmask will have been stored in the signal frame, @@ -505,11 +480,32 @@ void do_signal(struct pt_regs *regs) * Let tracing know that we've done the handler setup. */ tracehook_signal_handler(signr, &info, &ka, regs, - test_thread_flag(TIF_SINGLE_STEP)); + test_thread_flag(TIF_SINGLE_STEP)); } return; } + /* No handlers present - check for system call restart */ + if (current_thread_info()->system_call) { + regs->svc_code = current_thread_info()->system_call; + switch (regs->gprs[2]) { + case -ERESTART_RESTARTBLOCK: + /* Restart with sys_restart_syscall */ + regs->svc_code = __NR_restart_syscall; + /* fallthrough */ + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + /* Restart system call with magic TIF bit. */ + regs->gprs[2] = regs->orig_gpr2; + set_thread_flag(TIF_SYSCALL); + break; + default: + clear_thread_flag(TIF_SYSCALL); + break; + } + } + /* * If there's no signal to deliver, we just put the saved sigmask back. */ @@ -517,13 +513,6 @@ void do_signal(struct pt_regs *regs) clear_thread_flag(TIF_RESTORE_SIGMASK); sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } - - /* Restart a different system call. */ - if (retval == -ERESTART_RESTARTBLOCK - && regs->psw.addr == continue_addr) { - regs->gprs[2] = __NR_restart_syscall; - set_thread_flag(TIF_RESTART_SVC); - } } void do_notify_resume(struct pt_regs *regs) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1d55c95f617c..3ea872890da2 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -38,6 +38,7 @@ #include <linux/timex.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <linux/crash_dump.h> #include <asm/asm-offsets.h> #include <asm/ipl.h> #include <asm/setup.h> @@ -97,6 +98,29 @@ static inline int cpu_stopped(int cpu) return raw_cpu_stopped(cpu_logical_map(cpu)); } +/* + * Ensure that PSW restart is done on an online CPU + */ +void smp_restart_with_online_cpu(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + if (stap() == __cpu_logical_map[cpu]) { + /* We are online: Enable DAT again and return */ + __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + return; + } + } + /* We are not online: Do PSW restart on an online CPU */ + while (sigp(cpu, sigp_restart) == sigp_busy) + cpu_relax(); + /* And stop ourself */ + while (raw_sigp(stap(), sigp_stop) == sigp_busy) + cpu_relax(); + for (;;); +} + void smp_switch_to_ipl_cpu(void (*func)(void *), void *data) { struct _lowcore *lc, *current_lc; @@ -106,14 +130,16 @@ void smp_switch_to_ipl_cpu(void (*func)(void *), void *data) if (smp_processor_id() == 0) func(data); - __load_psw_mask(PSW_BASE_BITS | PSW_DEFAULT_KEY); + __load_psw_mask(PSW_DEFAULT_KEY | PSW_MASK_BASE | + PSW_MASK_EA | PSW_MASK_BA); /* Disable lowcore protection */ __ctl_clear_bit(0, 28); current_lc = lowcore_ptr[smp_processor_id()]; lc = lowcore_ptr[0]; if (!lc) lc = current_lc; - lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + lc->restart_psw.mask = + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) smp_restart_cpu; if (!cpu_online(0)) smp_switch_to_cpu(func, data, 0, stap(), __cpu_logical_map[0]); @@ -135,7 +161,7 @@ void smp_send_stop(void) int cpu, rc; /* Disable all interrupts/machine checks */ - __load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK); + __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); trace_hardirqs_off(); /* stop all processors */ @@ -161,7 +187,10 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, { unsigned long bits; - kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++; + if (ext_int_code == 0x1202) + kstat_cpu(smp_processor_id()).irqs[EXTINT_EXC]++; + else + kstat_cpu(smp_processor_id()).irqs[EXTINT_EMS]++; /* * handle bit signal external calls */ @@ -183,12 +212,19 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, */ static void smp_ext_bitcall(int cpu, int sig) { + int order; + /* * Set signaling bit in lowcore of target cpu and kick it */ set_bit(sig, (unsigned long *) &lowcore_ptr[cpu]->ext_call_fast); - while (sigp(cpu, sigp_emergency_signal) == sigp_busy) + while (1) { + order = smp_vcpu_scheduled(cpu) ? + sigp_external_call : sigp_emergency_signal; + if (sigp(cpu, order) != sigp_busy) + break; udelay(10); + } } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -281,11 +317,13 @@ void smp_ctl_clear_bit(int cr, int bit) } EXPORT_SYMBOL(smp_ctl_clear_bit); -#ifdef CONFIG_ZFCPDUMP +#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_CRASH_DUMP) static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { - if (ipl_info.type != IPL_TYPE_FCP_DUMP) + if (ipl_info.type != IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) + return; + if (is_kdump_kernel()) return; if (cpu >= NR_CPUS) { pr_warning("CPU %i exceeds the maximum %i and is excluded from " @@ -403,6 +441,18 @@ static void __init smp_detect_cpus(void) info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) panic("smp_detect_cpus failed to allocate memory\n"); +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE && !is_kdump_kernel()) { + struct save_area *save_area; + + save_area = kmalloc(sizeof(*save_area), GFP_KERNEL); + if (!save_area) + panic("could not allocate memory for save area\n"); + copy_oldmem_page(1, (void *) save_area, sizeof(*save_area), + 0x200, 0); + zfcpdump_save_areas[0] = save_area; + } +#endif /* Use sigp detection algorithm if sclp doesn't work. */ if (sclp_get_cpu_info(info)) { smp_use_sigp_detection = 1; @@ -452,23 +502,28 @@ out: */ int __cpuinit start_secondary(void *cpuvoid) { - /* Setup the cpu */ cpu_init(); preempt_disable(); - /* Enable TOD clock interrupts on the secondary cpu. */ init_cpu_timer(); - /* Enable cpu timer interrupts on the secondary cpu. */ init_cpu_vtimer(); - /* Enable pfault pseudo page faults on this cpu. */ pfault_init(); - /* call cpu notifiers */ notify_cpu_starting(smp_processor_id()); - /* Mark this cpu as online */ ipi_call_lock(); set_cpu_online(smp_processor_id(), true); ipi_call_unlock(); - /* Switch on interrupts */ + __ctl_clear_bit(0, 28); /* Disable lowcore protection */ + S390_lowcore.restart_psw.mask = + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; + S390_lowcore.restart_psw.addr = + PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; + __ctl_set_bit(0, 28); /* Enable lowcore protection */ + /* + * Wait until the cpu which brought this one up marked it + * active before enabling interrupts. + */ + while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) + cpu_relax(); local_irq_enable(); /* cpu_idle will call schedule for us */ cpu_idle(); @@ -507,7 +562,12 @@ static int __cpuinit smp_alloc_lowcore(int cpu) memset((char *)lowcore + 512, 0, sizeof(*lowcore) - 512); lowcore->async_stack = async_stack + ASYNC_SIZE; lowcore->panic_stack = panic_stack + PAGE_SIZE; - + lowcore->restart_psw.mask = + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; + lowcore->restart_psw.addr = + PSW_ADDR_AMODE | (unsigned long) restart_int_handler; + if (user_mode != HOME_SPACE_MODE) + lowcore->restart_psw.mask |= PSW_ASC_HOME; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { unsigned long save_area; @@ -654,7 +714,8 @@ int __cpu_disable(void) /* disable all external interrupts */ cr_parms.orvals[0] = 0; cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 11 | - 1 << 10 | 1 << 9 | 1 << 6 | 1 << 4); + 1 << 10 | 1 << 9 | 1 << 6 | 1 << 5 | + 1 << 4); /* disable all I/O interrupts */ cr_parms.orvals[6] = 0; cr_parms.andvals[6] = ~(1 << 31 | 1 << 30 | 1 << 29 | 1 << 28 | @@ -703,6 +764,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) /* request the 0x1201 emergency signal external interrupt */ if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0) panic("Couldn't request external interrupt 0x1201"); + /* request the 0x1202 external call external interrupt */ + if (register_external_interrupt(0x1202, do_ext_call_interrupt) != 0) + panic("Couldn't request external interrupt 0x1202"); /* Reallocate current lowcore, but keep its contents. */ lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index cf9e5c6d5527..47df775c844d 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -7,6 +7,8 @@ */ #include <linux/pfn.h> +#include <linux/suspend.h> +#include <linux/mm.h> #include <asm/system.h> /* @@ -14,6 +16,123 @@ */ extern const void __nosave_begin, __nosave_end; +/* + * The restore of the saved pages in an hibernation image will set + * the change and referenced bits in the storage key for each page. + * Overindication of the referenced bits after an hibernation cycle + * does not cause any harm but the overindication of the change bits + * would cause trouble. + * Use the ARCH_SAVE_PAGE_KEYS hooks to save the storage key of each + * page to the most significant byte of the associated page frame + * number in the hibernation image. + */ + +/* + * Key storage is allocated as a linked list of pages. + * The size of the keys array is (PAGE_SIZE - sizeof(long)) + */ +struct page_key_data { + struct page_key_data *next; + unsigned char data[]; +}; + +#define PAGE_KEY_DATA_SIZE (PAGE_SIZE - sizeof(struct page_key_data *)) + +static struct page_key_data *page_key_data; +static struct page_key_data *page_key_rp, *page_key_wp; +static unsigned long page_key_rx, page_key_wx; + +/* + * For each page in the hibernation image one additional byte is + * stored in the most significant byte of the page frame number. + * On suspend no additional memory is required but on resume the + * keys need to be memorized until the page data has been restored. + * Only then can the storage keys be set to their old state. + */ +unsigned long page_key_additional_pages(unsigned long pages) +{ + return DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE); +} + +/* + * Free page_key_data list of arrays. + */ +void page_key_free(void) +{ + struct page_key_data *pkd; + + while (page_key_data) { + pkd = page_key_data; + page_key_data = pkd->next; + free_page((unsigned long) pkd); + } +} + +/* + * Allocate page_key_data list of arrays with enough room to store + * one byte for each page in the hibernation image. + */ +int page_key_alloc(unsigned long pages) +{ + struct page_key_data *pk; + unsigned long size; + + size = DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE); + while (size--) { + pk = (struct page_key_data *) get_zeroed_page(GFP_KERNEL); + if (!pk) { + page_key_free(); + return -ENOMEM; + } + pk->next = page_key_data; + page_key_data = pk; + } + page_key_rp = page_key_wp = page_key_data; + page_key_rx = page_key_wx = 0; + return 0; +} + +/* + * Save the storage key into the upper 8 bits of the page frame number. + */ +void page_key_read(unsigned long *pfn) +{ + unsigned long addr; + + addr = (unsigned long) page_address(pfn_to_page(*pfn)); + *(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr); +} + +/* + * Extract the storage key from the upper 8 bits of the page frame number + * and store it in the page_key_data list of arrays. + */ +void page_key_memorize(unsigned long *pfn) +{ + page_key_wp->data[page_key_wx] = *(unsigned char *) pfn; + *(unsigned char *) pfn = 0; + if (++page_key_wx < PAGE_KEY_DATA_SIZE) + return; + page_key_wp = page_key_wp->next; + page_key_wx = 0; +} + +/* + * Get the next key from the page_key_data list of arrays and set the + * storage key of the page referred by @address. If @address refers to + * a "safe" page the swsusp_arch_resume code will transfer the storage + * key from the buffer page to the original page. + */ +void page_key_write(void *address) +{ + page_set_storage_key((unsigned long) address, + page_key_rp->data[page_key_rx], 0); + if (++page_key_rx >= PAGE_KEY_DATA_SIZE) + return; + page_key_rp = page_key_rp->next; + page_key_rx = 0; +} + int pfn_is_nosave(unsigned long pfn) { unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); diff --git a/arch/s390/kernel/switch_cpu.S b/arch/s390/kernel/switch_cpu.S index 20530dd2eab1..bfe070bc7659 100644 --- a/arch/s390/kernel/switch_cpu.S +++ b/arch/s390/kernel/switch_cpu.S @@ -5,6 +5,7 @@ * */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> @@ -16,9 +17,7 @@ # %r6 - destination cpu .section .text - .align 4 - .globl smp_switch_to_cpu -smp_switch_to_cpu: +ENTRY(smp_switch_to_cpu) stm %r6,%r15,__SF_GPRS(%r15) lr %r1,%r15 ahi %r15,-STACK_FRAME_OVERHEAD @@ -33,8 +32,7 @@ smp_switch_to_cpu: brc 2,2b /* busy, try again */ 3: j 3b - .globl smp_restart_cpu -smp_restart_cpu: +ENTRY(smp_restart_cpu) basr %r13,0 0: la %r1,.gprregs_addr-0b(%r13) l %r1,0(%r1) diff --git a/arch/s390/kernel/switch_cpu64.S b/arch/s390/kernel/switch_cpu64.S index 5be3f43898f9..fcc42d799e41 100644 --- a/arch/s390/kernel/switch_cpu64.S +++ b/arch/s390/kernel/switch_cpu64.S @@ -5,6 +5,7 @@ * */ +#include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> @@ -16,9 +17,7 @@ # %r6 - destination cpu .section .text - .align 4 - .globl smp_switch_to_cpu -smp_switch_to_cpu: +ENTRY(smp_switch_to_cpu) stmg %r6,%r15,__SF_GPRS(%r15) lgr %r1,%r15 aghi %r15,-STACK_FRAME_OVERHEAD @@ -31,8 +30,7 @@ smp_switch_to_cpu: brc 2,2b /* busy, try again */ 3: j 3b - .globl smp_restart_cpu -smp_restart_cpu: +ENTRY(smp_restart_cpu) larl %r1,.gprregs lmg %r0,%r15,0(%r1) 1: sigp %r0,%r5,__SIGP_SENSE /* Wait for calling CPU */ diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index 1f066e46e83e..acb78cdee896 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -7,6 +7,7 @@ * Michael Holzheu <holzheu@linux.vnet.ibm.com> */ +#include <linux/linkage.h> #include <asm/page.h> #include <asm/ptrace.h> #include <asm/thread_info.h> @@ -22,9 +23,7 @@ * This function runs with disabled interrupts. */ .section .text - .align 4 - .globl swsusp_arch_suspend -swsusp_arch_suspend: +ENTRY(swsusp_arch_suspend) stmg %r6,%r15,__SF_GPRS(%r15) lgr %r1,%r15 aghi %r15,-STACK_FRAME_OVERHEAD @@ -112,8 +111,7 @@ swsusp_arch_suspend: * Then we return to the function that called swsusp_arch_suspend(). * swsusp_arch_resume() runs with disabled interrupts. */ - .globl swsusp_arch_resume -swsusp_arch_resume: +ENTRY(swsusp_arch_resume) stmg %r6,%r15,__SF_GPRS(%r15) lgr %r1,%r15 aghi %r15,-STACK_FRAME_OVERHEAD @@ -138,11 +136,14 @@ swsusp_arch_resume: 0: lg %r2,8(%r1) lg %r4,0(%r1) + iske %r0,%r4 lghi %r3,PAGE_SIZE lghi %r5,PAGE_SIZE 1: mvcle %r2,%r4,0 jo 1b + lg %r2,8(%r1) + sske %r0,%r2 lg %r1,16(%r1) ltgr %r1,%r1 jnz 0b diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 6ee39ef8fe4a..bcab2f04ba58 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -177,7 +177,7 @@ SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper) /* 165 old get NI_SYSCALL /* for vm86 */ NI_SYSCALL /* old sys_query_module */ SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper) -SYSCALL(sys_nfsservctl,sys_nfsservctl,compat_sys_nfsservctl_wrapper) +NI_SYSCALL /* old nfsservctl */ SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper) /* 170 old setresgid16 syscall */ SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper) /* old getresgid16 syscall */ SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper) @@ -348,3 +348,5 @@ SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper) SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper) SYSCALL(sys_setns,sys_setns,sys_setns_wrapper) +SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */ +SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper) diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 5c9e439bf3f6..2a94b774695c 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -442,7 +442,7 @@ void s390_adjust_jiffies(void) */ FP_UNPACK_SP(SA, &fmil); if ((info->capability >> 23) == 0) - FP_FROM_INT_S(SB, info->capability, 32, int); + FP_FROM_INT_S(SB, (long) info->capability, 64, long); else FP_UNPACK_SP(SB, &info->capability); FP_DIV_S(SR, SA, SB); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index dff933065ab6..ebbfab3c6e5a 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -48,6 +48,7 @@ #include <asm/timer.h> #include <asm/etr.h> #include <asm/cio.h> +#include "entry.h" /* change this if you have some constant time drift */ #define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) @@ -109,10 +110,14 @@ static void fixup_clock_comparator(unsigned long long delta) set_clock_comparator(S390_lowcore.clock_comparator); } -static int s390_next_event(unsigned long delta, +static int s390_next_ktime(ktime_t expires, struct clock_event_device *evt) { - S390_lowcore.clock_comparator = get_clock() + delta; + u64 nsecs; + + nsecs = ktime_to_ns(ktime_sub(expires, ktime_get_monotonic_offset())); + do_div(nsecs, 125); + S390_lowcore.clock_comparator = TOD_UNIX_EPOCH + (nsecs << 9); set_clock_comparator(S390_lowcore.clock_comparator); return 0; } @@ -137,14 +142,15 @@ void init_cpu_timer(void) cpu = smp_processor_id(); cd = &per_cpu(comparators, cpu); cd->name = "comparator"; - cd->features = CLOCK_EVT_FEAT_ONESHOT; + cd->features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_KTIME; cd->mult = 16777; cd->shift = 12; cd->min_delta_ns = 1; cd->max_delta_ns = LONG_MAX; cd->rating = 400; cd->cpumask = cpumask_of(cpu); - cd->set_next_event = s390_next_event; + cd->set_next_ktime = s390_next_ktime; cd->set_mode = s390_set_mode; clockevents_register_device(cd); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 0cd340b72632..fdb5b8cb260f 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -68,8 +68,10 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) return mask; } -static void add_cpus_to_mask(struct topology_cpu *tl_cpu, - struct mask_info *book, struct mask_info *core) +static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu, + struct mask_info *book, + struct mask_info *core, + int z10) { unsigned int cpu; @@ -88,10 +90,16 @@ static void add_cpus_to_mask(struct topology_cpu *tl_cpu, cpu_book_id[lcpu] = book->id; #endif cpumask_set_cpu(lcpu, &core->mask); - cpu_core_id[lcpu] = core->id; + if (z10) { + cpu_core_id[lcpu] = rcpu; + core = core->next; + } else { + cpu_core_id[lcpu] = core->id; + } smp_cpu_polarization[lcpu] = tl_cpu->pp; } } + return core; } static void clear_masks(void) @@ -123,18 +131,41 @@ static void tl_to_cores(struct sysinfo_15_1_x *info) { #ifdef CONFIG_SCHED_BOOK struct mask_info *book = &book_info; + struct cpuid cpu_id; #else struct mask_info *book = NULL; #endif struct mask_info *core = &core_info; union topology_entry *tle, *end; + int z10 = 0; - +#ifdef CONFIG_SCHED_BOOK + get_cpu_id(&cpu_id); + z10 = cpu_id.machine == 0x2097 || cpu_id.machine == 0x2098; +#endif spin_lock_irq(&topology_lock); clear_masks(); tle = info->tle; end = (union topology_entry *)((unsigned long)info + info->length); while (tle < end) { +#ifdef CONFIG_SCHED_BOOK + if (z10) { + switch (tle->nl) { + case 1: + book = book->next; + book->id = tle->container.id; + break; + case 0: + core = add_cpus_to_mask(&tle->cpu, book, core, z10); + break; + default: + clear_masks(); + goto out; + } + tle = next_tle(tle); + continue; + } +#endif switch (tle->nl) { #ifdef CONFIG_SCHED_BOOK case 2: @@ -147,7 +178,7 @@ static void tl_to_cores(struct sysinfo_15_1_x *info) core->id = tle->container.id; break; case 0: - add_cpus_to_mask(&tle->cpu, book, core); + add_cpus_to_mask(&tle->cpu, book, core, z10); break; default: clear_masks(); @@ -299,8 +330,8 @@ out: } __initcall(init_topology_update); -static void alloc_masks(struct sysinfo_15_1_x *info, struct mask_info *mask, - int offset) +static void __init alloc_masks(struct sysinfo_15_1_x *info, + struct mask_info *mask, int offset) { int i, nr_masks; @@ -328,8 +359,8 @@ void __init s390_init_cpu_topology(void) for (i = 0; i < TOPOLOGY_NR_MAG; i++) printk(" %d", info->mag[i]); printk(" / %d\n", info->mnest); - alloc_masks(info, &core_info, 2); + alloc_masks(info, &core_info, 1); #ifdef CONFIG_SCHED_BOOK - alloc_masks(info, &book_info, 3); + alloc_masks(info, &book_info, 2); #endif } diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index a65d2e82f61d..a9807dd86276 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -18,7 +18,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> -#include <linux/tracehook.h> +#include <linux/ptrace.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/smp.h> @@ -36,21 +36,17 @@ #include <asm/system.h> #include <asm/uaccess.h> #include <asm/io.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/mathemu.h> #include <asm/cpcmd.h> #include <asm/lowcore.h> #include <asm/debug.h> #include "entry.h" -pgm_check_handler_t *pgm_check_table[128]; +void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long); int show_unhandled_signals; -extern pgm_check_handler_t do_protection_exception; -extern pgm_check_handler_t do_dat_exception; -extern pgm_check_handler_t do_asce_exception; - #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; }) #ifndef CONFIG_64BIT @@ -204,7 +200,7 @@ void show_registers(struct pt_regs *regs) mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); #ifdef CONFIG_64BIT - printk(" EA:%x", mask_bits(regs, PSW_BASE_BITS)); + printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); #endif printk("\n%s GPRS: " FOURLONG, mode, regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); @@ -329,10 +325,18 @@ static inline void __user *get_psw_address(struct pt_regs *regs, void __kprobes do_per_trap(struct pt_regs *regs) { + siginfo_t info; + if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP) return; - if (tracehook_consider_fatal_signal(current, SIGTRAP)) - force_sig(SIGTRAP, current); + if (!current->ptrace) + return; + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_HWBKPT; + info.si_addr = + (void __force __user *) current->thread.per_event.address; + force_sig_info(SIGTRAP, &info, current); } static void default_trap_handler(struct pt_regs *regs, long pgm_int_code, @@ -425,9 +429,13 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code, if (get_user(*((__u16 *) opcode), (__u16 __user *) location)) return; if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) { - if (tracehook_consider_fatal_signal(current, SIGTRAP)) - force_sig(SIGTRAP, current); - else + if (current->ptrace) { + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_BRKPT; + info.si_addr = location; + force_sig_info(SIGTRAP, &info, current); + } else signal = SIGILL; #ifdef CONFIG_MATHEMU } else if (opcode[0] == 0xb3) { @@ -489,9 +497,8 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code, #ifdef CONFIG_MATHEMU -asmlinkage void specification_exception(struct pt_regs *regs, - long pgm_int_code, - unsigned long trans_exc_code) +void specification_exception(struct pt_regs *regs, long pgm_int_code, + unsigned long trans_exc_code) { __u8 opcode[6]; __u16 __user *location = NULL; @@ -648,7 +655,7 @@ static void space_switch_exception(struct pt_regs *regs, long pgm_int_code, do_trap(pgm_int_code, SIGILL, "space switch event", regs, &info); } -asmlinkage void __kprobes kernel_stack_overflow(struct pt_regs * regs) +void __kprobes kernel_stack_overflow(struct pt_regs * regs) { bust_spinlocks(1); printk("Kernel stack overflow.\n"); diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 56fe6bc81fee..e4c79ebb40e6 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -43,6 +43,8 @@ SECTIONS NOTES :text :note + .dummy : { *(.dummy) } :data + RODATA #ifdef CONFIG_SHARED_KERNEL diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 2d6228f60cd6..bb48977f5469 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -170,7 +170,8 @@ void __kprobes vtime_stop_cpu(void) psw_t psw; /* Wait for external, I/O or machine check interrupt. */ - psw.mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_IO | PSW_MASK_EXT; + psw.mask = psw_kernel_bits | PSW_MASK_WAIT | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; idle->nohz_delay = 0; @@ -183,7 +184,8 @@ void __kprobes vtime_stop_cpu(void) * set_cpu_timer(VTIMER_MAX_SLICE); * idle->idle_enter = get_clock(); * __load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT | - * PSW_MASK_IO | PSW_MASK_EXT); + * PSW_MASK_DAT | PSW_MASK_IO | + * PSW_MASK_EXT | PSW_MASK_MCHECK); * The difference is that the inline assembly makes sure that * the last three instruction are stpt, stck and lpsw in that * order. This is done to increase the precision. @@ -216,7 +218,8 @@ void __kprobes vtime_stop_cpu(void) * vq->idle = get_cpu_timer(); * idle->idle_enter = get_clock(); * __load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT | - * PSW_MASK_IO | PSW_MASK_EXT); + * PSW_MASK_DAT | PSW_MASK_IO | + * PSW_MASK_EXT | PSW_MASK_MCHECK); * The difference is that the inline assembly makes sure that * the last three instruction are stpt, stck and lpsw in that * order. This is done to increase the precision. @@ -458,7 +461,7 @@ void add_virt_timer_periodic(void *new) } EXPORT_SYMBOL(add_virt_timer_periodic); -int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) +static int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) { struct vtimer_queue *vq; unsigned long flags; diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index f66a1bdbb61d..a21634173a66 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -37,6 +37,5 @@ config KVM # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/vhost/Kconfig -source drivers/virtio/Kconfig endif # VIRTUALIZATION diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 860d26514c08..3975722bb19d 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -10,5 +10,5 @@ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o) ccflags-y := -Ivirt/kvm -Iarch/s390/kvm -kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o +kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 9e4c84187cf5..8943e82cd4d9 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -1,7 +1,7 @@ /* * diag.c - handling diagnose instructions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2011 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -15,6 +15,34 @@ #include <linux/kvm_host.h> #include "kvm-s390.h" +static int diag_release_pages(struct kvm_vcpu *vcpu) +{ + unsigned long start, end; + unsigned long prefix = vcpu->arch.sie_block->prefix; + + start = vcpu->arch.guest_gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; + end = vcpu->arch.guest_gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096; + + if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end + || start < 2 * PAGE_SIZE) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end); + vcpu->stat.diagnose_10++; + + /* we checked for start > end above */ + if (end < prefix || start >= prefix + 2 * PAGE_SIZE) { + gmap_discard(start, end, vcpu->arch.gmap); + } else { + if (start < prefix) + gmap_discard(start, prefix, vcpu->arch.gmap); + if (end >= prefix) + gmap_discard(prefix + 2 * PAGE_SIZE, + end, vcpu->arch.gmap); + } + return 0; +} + static int __diag_time_slice_end(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 5, "%s", "diag time slice end"); @@ -42,7 +70,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } - atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL; vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT; @@ -57,6 +85,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16; switch (code) { + case 0x10: + return diag_release_pages(vcpu); case 0x44: return __diag_time_slice_end(vcpu); case 0x308: diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 03c716a0f01f..c86f6ae43f76 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,5 +1,5 @@ /* - * gaccess.h - access guest memory + * access.h - access guest memory * * Copyright IBM Corp. 2008,2009 * @@ -22,20 +22,13 @@ static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu, unsigned long guestaddr) { unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->arch.sie_block->gmsor; - unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestaddr < 2 * PAGE_SIZE) guestaddr += prefix; else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE)) guestaddr -= prefix; - if (guestaddr > memsize) - return (void __user __force *) ERR_PTR(-EFAULT); - - guestaddr += origin; - - return (void __user *) guestaddr; + return (void __user *) gmap_fault(guestaddr, vcpu->arch.gmap); } static inline int get_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr, @@ -141,11 +134,11 @@ static inline int put_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr, static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, unsigned long guestdest, - const void *from, unsigned long n) + void *from, unsigned long n) { int rc; unsigned long i; - const u8 *data = from; + u8 *data = from; for (i = 0; i < n; i++) { rc = put_guest_u8(vcpu, guestdest++, *(data++)); @@ -155,12 +148,95 @@ static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, return 0; } +static inline int __copy_to_guest_fast(struct kvm_vcpu *vcpu, + unsigned long guestdest, + void *from, unsigned long n) +{ + int r; + void __user *uptr; + unsigned long size; + + if (guestdest + n < guestdest) + return -EFAULT; + + /* simple case: all within one segment table entry? */ + if ((guestdest & PMD_MASK) == ((guestdest+n) & PMD_MASK)) { + uptr = (void __user *) gmap_fault(guestdest, vcpu->arch.gmap); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + r = copy_to_user(uptr, from, n); + + if (r) + r = -EFAULT; + + goto out; + } + + /* copy first segment */ + uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + size = PMD_SIZE - (guestdest & ~PMD_MASK); + + r = copy_to_user(uptr, from, size); + + if (r) { + r = -EFAULT; + goto out; + } + from += size; + n -= size; + guestdest += size; + + /* copy full segments */ + while (n >= PMD_SIZE) { + uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + r = copy_to_user(uptr, from, PMD_SIZE); + + if (r) { + r = -EFAULT; + goto out; + } + from += PMD_SIZE; + n -= PMD_SIZE; + guestdest += PMD_SIZE; + } + + /* copy the tail segment */ + if (n) { + uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + r = copy_to_user(uptr, from, n); + + if (r) + r = -EFAULT; + } +out: + return r; +} + +static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, + unsigned long guestdest, + void *from, unsigned long n) +{ + return __copy_to_guest_fast(vcpu, guestdest, from, n); +} + static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest, - const void *from, unsigned long n) + void *from, unsigned long n) { unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->arch.sie_block->gmsor; - unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE)) goto slowpath; @@ -177,15 +253,7 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest, else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE)) guestdest -= prefix; - if (guestdest + n > memsize) - return -EFAULT; - - if (guestdest + n < guestdest) - return -EFAULT; - - guestdest += origin; - - return copy_to_user((void __user *) guestdest, from, n); + return __copy_to_guest_fast(vcpu, guestdest, from, n); slowpath: return __copy_to_guest_slow(vcpu, guestdest, from, n); } @@ -206,74 +274,113 @@ static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to, return 0; } -static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to, - unsigned long guestsrc, unsigned long n) +static inline int __copy_from_guest_fast(struct kvm_vcpu *vcpu, void *to, + unsigned long guestsrc, + unsigned long n) { - unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->arch.sie_block->gmsor; - unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); + int r; + void __user *uptr; + unsigned long size; - if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) - goto slowpath; + if (guestsrc + n < guestsrc) + return -EFAULT; - if ((guestsrc < prefix) && (guestsrc + n > prefix)) - goto slowpath; + /* simple case: all within one segment table entry? */ + if ((guestsrc & PMD_MASK) == ((guestsrc+n) & PMD_MASK)) { + uptr = (void __user *) gmap_fault(guestsrc, vcpu->arch.gmap); - if ((guestsrc < prefix + 2 * PAGE_SIZE) - && (guestsrc + n > prefix + 2 * PAGE_SIZE)) - goto slowpath; + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); - if (guestsrc < 2 * PAGE_SIZE) - guestsrc += prefix; - else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE)) - guestsrc -= prefix; + r = copy_from_user(to, uptr, n); - if (guestsrc + n > memsize) - return -EFAULT; + if (r) + r = -EFAULT; - if (guestsrc + n < guestsrc) - return -EFAULT; + goto out; + } - guestsrc += origin; + /* copy first segment */ + uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap); - return copy_from_user(to, (void __user *) guestsrc, n); -slowpath: - return __copy_from_guest_slow(vcpu, to, guestsrc, n); -} + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); -static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, - unsigned long guestdest, - const void *from, unsigned long n) -{ - unsigned long origin = vcpu->arch.sie_block->gmsor; - unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); + size = PMD_SIZE - (guestsrc & ~PMD_MASK); - if (guestdest + n > memsize) - return -EFAULT; + r = copy_from_user(to, uptr, size); - if (guestdest + n < guestdest) - return -EFAULT; + if (r) { + r = -EFAULT; + goto out; + } + to += size; + n -= size; + guestsrc += size; + + /* copy full segments */ + while (n >= PMD_SIZE) { + uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + r = copy_from_user(to, uptr, PMD_SIZE); + + if (r) { + r = -EFAULT; + goto out; + } + to += PMD_SIZE; + n -= PMD_SIZE; + guestsrc += PMD_SIZE; + } + + /* copy the tail segment */ + if (n) { + uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap); - guestdest += origin; + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); - return copy_to_user((void __user *) guestdest, from, n); + r = copy_from_user(to, uptr, n); + + if (r) + r = -EFAULT; + } +out: + return r; } static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to, unsigned long guestsrc, unsigned long n) { - unsigned long origin = vcpu->arch.sie_block->gmsor; - unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); + return __copy_from_guest_fast(vcpu, to, guestsrc, n); +} - if (guestsrc + n > memsize) - return -EFAULT; +static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to, + unsigned long guestsrc, unsigned long n) +{ + unsigned long prefix = vcpu->arch.sie_block->prefix; - if (guestsrc + n < guestsrc) - return -EFAULT; + if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) + goto slowpath; - guestsrc += origin; + if ((guestsrc < prefix) && (guestsrc + n > prefix)) + goto slowpath; + + if ((guestsrc < prefix + 2 * PAGE_SIZE) + && (guestsrc + n > prefix + 2 * PAGE_SIZE)) + goto slowpath; + + if (guestsrc < 2 * PAGE_SIZE) + guestsrc += prefix; + else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE)) + guestsrc -= prefix; - return copy_from_user(to, (void __user *) guestsrc, n); + return __copy_from_guest_fast(vcpu, to, guestsrc, n); +slowpath: + return __copy_from_guest_slow(vcpu, to, guestsrc, n); } #endif diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index f7b6df45d8be..02434543eabb 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -105,6 +105,7 @@ static intercept_handler_t instruction_handlers[256] = { [0xae] = kvm_s390_handle_sigp, [0xb2] = kvm_s390_handle_b2, [0xb7] = handle_lctl, + [0xe5] = kvm_s390_handle_e5, [0xeb] = handle_lctlg, }; @@ -131,7 +132,6 @@ static int handle_stop(struct kvm_vcpu *vcpu) int rc = 0; vcpu->stat.exit_stop_request++; - atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); spin_lock_bh(&vcpu->arch.local_int.lock); if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) { vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP; @@ -148,6 +148,8 @@ static int handle_stop(struct kvm_vcpu *vcpu) } if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) { + atomic_set_mask(CPUSTAT_STOPPED, + &vcpu->arch.sie_block->cpuflags); vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP; VCPU_EVENT(vcpu, 3, "%s", "cpu stopped"); rc = -EOPNOTSUPP; @@ -159,22 +161,42 @@ static int handle_stop(struct kvm_vcpu *vcpu) static int handle_validity(struct kvm_vcpu *vcpu) { + unsigned long vmaddr; int viwhy = vcpu->arch.sie_block->ipb >> 16; int rc; vcpu->stat.exit_validity++; - if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix - <= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) { - rc = fault_in_pages_writeable((char __user *) - vcpu->arch.sie_block->gmsor + - vcpu->arch.sie_block->prefix, - 2*PAGE_SIZE); - if (rc) + if (viwhy == 0x37) { + vmaddr = gmap_fault(vcpu->arch.sie_block->prefix, + vcpu->arch.gmap); + if (IS_ERR_VALUE(vmaddr)) { + rc = -EOPNOTSUPP; + goto out; + } + rc = fault_in_pages_writeable((char __user *) vmaddr, + PAGE_SIZE); + if (rc) { + /* user will receive sigsegv, exit to user */ + rc = -EOPNOTSUPP; + goto out; + } + vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE, + vcpu->arch.gmap); + if (IS_ERR_VALUE(vmaddr)) { + rc = -EOPNOTSUPP; + goto out; + } + rc = fault_in_pages_writeable((char __user *) vmaddr, + PAGE_SIZE); + if (rc) { /* user will receive sigsegv, exit to user */ rc = -EOPNOTSUPP; + goto out; + } } else rc = -EOPNOTSUPP; +out: if (rc) VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", viwhy); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 35c21bf910c5..278ee009ce65 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -38,6 +38,11 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { switch (inti->type) { + case KVM_S390_INT_EXTERNAL_CALL: + if (psw_extint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) + return 1; case KVM_S390_INT_EMERGENCY: if (psw_extint_disabled(vcpu)) return 0; @@ -98,6 +103,7 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { switch (inti->type) { + case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: case KVM_S390_INT_SERVICE: case KVM_S390_INT_VIRTIO: @@ -128,6 +134,32 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, if (rc == -EFAULT) exception = 1; + rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->emerg.code); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_EXT_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + + case KVM_S390_INT_EXTERNAL_CALL: + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call"); + vcpu->stat.deliver_external_call++; + rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1202); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->extcall.code); + if (rc == -EFAULT) + exception = 1; + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); if (rc == -EFAULT) @@ -220,6 +252,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, offsetof(struct _lowcore, restart_psw), sizeof(psw_t)); if (rc == -EFAULT) exception = 1; + atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); break; case KVM_S390_PROGRAM_INT: @@ -518,6 +551,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, break; case KVM_S390_PROGRAM_INT: case KVM_S390_SIGP_STOP: + case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: default: kfree(inti); @@ -577,6 +611,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, break; case KVM_S390_SIGP_STOP: case KVM_S390_RESTART: + case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type); inti->type = s390int->type; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 67345ae7ce8d..d1c445732451 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -46,6 +46,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, { "instruction_lctl", VCPU_STAT(instruction_lctl) }, { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, + { "deliver_external_call", VCPU_STAT(deliver_external_call) }, { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, { "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) }, { "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) }, @@ -62,12 +63,16 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_chsc", VCPU_STAT(instruction_chsc) }, { "instruction_stsi", VCPU_STAT(instruction_stsi) }, { "instruction_stfl", VCPU_STAT(instruction_stfl) }, + { "instruction_tprot", VCPU_STAT(instruction_tprot) }, { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) }, + { "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) }, + { "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) }, { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) }, { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, + { "diagnose_10", VCPU_STAT(diagnose_10) }, { "diagnose_44", VCPU_STAT(diagnose_44) }, { NULL } }; @@ -122,6 +127,8 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_S390_PSW: + case KVM_CAP_S390_GMAP: + case KVM_CAP_SYNC_MMU: r = 1; break; default: @@ -173,6 +180,8 @@ int kvm_arch_init_vm(struct kvm *kvm) if (rc) goto out_err; + rc = -ENOMEM; + kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL); if (!kvm->arch.sca) goto out_err; @@ -189,7 +198,13 @@ int kvm_arch_init_vm(struct kvm *kvm) debug_register_view(kvm->arch.dbf, &debug_sprintf_view); VM_EVENT(kvm, 3, "%s", "vm created"); + kvm->arch.gmap = gmap_alloc(current->mm); + if (!kvm->arch.gmap) + goto out_nogmap; + return 0; +out_nogmap: + debug_unregister(kvm->arch.dbf); out_nodbf: free_page((unsigned long)(kvm->arch.sca)); out_err: @@ -234,11 +249,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_free_vcpus(kvm); free_page((unsigned long)(kvm->arch.sca)); debug_unregister(kvm->arch.dbf); + gmap_free(kvm->arch.gmap); } /* Section: vcpu related */ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { + vcpu->arch.gmap = vcpu->kvm->arch.gmap; return 0; } @@ -254,10 +271,14 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK; restore_fp_regs(&vcpu->arch.guest_fpregs); restore_access_regs(vcpu->arch.guest_acrs); + gmap_enable(vcpu->arch.gmap); + atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + gmap_disable(vcpu->arch.gmap); save_fp_regs(&vcpu->arch.guest_fpregs); save_access_regs(vcpu->arch.guest_acrs); restore_fp_regs(&vcpu->arch.host_fpregs); @@ -284,8 +305,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH); - set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests); + atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | + CPUSTAT_SM | + CPUSTAT_STOPPED); vcpu->arch.sie_block->ecb = 6; vcpu->arch.sie_block->eca = 0xC1002001U; vcpu->arch.sie_block->fac = (int) (long) facilities; @@ -301,11 +323,17 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { - struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); - int rc = -ENOMEM; + struct kvm_vcpu *vcpu; + int rc = -EINVAL; + if (id >= KVM_MAX_VCPUS) + goto out; + + rc = -ENOMEM; + + vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); if (!vcpu) - goto out_nomem; + goto out; vcpu->arch.sie_block = (struct kvm_s390_sie_block *) get_zeroed_page(GFP_KERNEL); @@ -341,7 +369,7 @@ out_free_sie_block: free_page((unsigned long)(vcpu->arch.sie_block)); out_free_cpu: kfree(vcpu); -out_nomem: +out: return ERR_PTR(rc); } @@ -375,6 +403,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs)); memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs)); + restore_access_regs(vcpu->arch.guest_acrs); return 0; } @@ -390,6 +419,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); vcpu->arch.guest_fpregs.fpc = fpu->fpc; + restore_fp_regs(&vcpu->arch.guest_fpregs); return 0; } @@ -404,7 +434,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw) { int rc = 0; - if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING) + if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED)) rc = -EBUSY; else { vcpu->run->psw_mask = psw.mask; @@ -474,21 +504,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) sigset_t sigsaved; rerun_vcpu: - if (vcpu->requests) - if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) - kvm_s390_vcpu_set_mem(vcpu); - - /* verify, that memory has been registered */ - if (!vcpu->arch.sie_block->gmslm) { - vcpu_put(vcpu); - VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu"); - return -EINVAL; - } - if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); - atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL); @@ -545,7 +564,7 @@ rerun_vcpu: return rc; } -static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from, +static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from, unsigned long n, int prefix) { if (prefix) @@ -562,7 +581,7 @@ static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from, */ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) { - const unsigned char archmode = 1; + unsigned char archmode = 1; int prefix; if (addr == KVM_S390_STORE_STATUS_NOADDR) { @@ -680,10 +699,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (mem->guest_phys_addr) return -EINVAL; - if (mem->userspace_addr & (PAGE_SIZE - 1)) + if (mem->userspace_addr & 0xffffful) return -EINVAL; - if (mem->memory_size & (PAGE_SIZE - 1)) + if (mem->memory_size & 0xffffful) return -EINVAL; if (!user_alloc) @@ -697,15 +716,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot old, int user_alloc) { - int i; - struct kvm_vcpu *vcpu; + int rc; - /* request update of sie control block for all available vcpus */ - kvm_for_each_vcpu(i, vcpu, kvm) { - if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) - continue; - kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP); - } + + rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, + mem->guest_phys_addr, mem->memory_size); + if (rc) + printk(KERN_WARNING "kvm-s390: failed to commit memory region\n"); + return; } void kvm_arch_flush_shadow(struct kvm *kvm) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a7b7586626db..99b0b7597115 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -58,35 +58,9 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action); -static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.sie_block->gmslm - - vcpu->arch.sie_block->gmsor - - VIRTIODESCSPACE + 1ul; -} - -static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu) -{ - int idx; - struct kvm_memory_slot *mem; - struct kvm_memslots *memslots; - - idx = srcu_read_lock(&vcpu->kvm->srcu); - memslots = kvm_memslots(vcpu->kvm); - - mem = &memslots->memslots[0]; - - vcpu->arch.sie_block->gmsor = mem->userspace_addr; - vcpu->arch.sie_block->gmslm = - mem->userspace_addr + - (mem->npages << PAGE_SHIFT) + - VIRTIODESCSPACE - 1ul; - - srcu_read_unlock(&vcpu->kvm->srcu, idx); -} - /* implemented in priv.c */ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); +int kvm_s390_handle_e5(struct kvm_vcpu *vcpu); /* implemented in sigp.c */ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 73c47bd95db3..d02638959922 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -326,3 +326,58 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) } return -EOPNOTSUPP; } + +static int handle_tprot(struct kvm_vcpu *vcpu) +{ + int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; + int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; + int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12; + int disp2 = vcpu->arch.sie_block->ipb & 0x0fff; + u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0; + u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0; + struct vm_area_struct *vma; + unsigned long user_address; + + vcpu->stat.instruction_tprot++; + + /* we only handle the Linux memory detection case: + * access key == 0 + * guest DAT == off + * everything else goes to userspace. */ + if (address2 & 0xf0) + return -EOPNOTSUPP; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) + return -EOPNOTSUPP; + + + /* we must resolve the address without holding the mmap semaphore. + * This is ok since the userspace hypervisor is not supposed to change + * the mapping while the guest queries the memory. Otherwise the guest + * might crash or get wrong info anyway. */ + user_address = (unsigned long) __guestaddr_to_user(vcpu, address1); + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, user_address); + if (!vma) { + up_read(¤t->mm->mmap_sem); + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ)) + vcpu->arch.sie_block->gpsw.mask |= (1ul << 44); + if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ)) + vcpu->arch.sie_block->gpsw.mask |= (2ul << 44); + + up_read(¤t->mm->mmap_sem); + return 0; +} + +int kvm_s390_handle_e5(struct kvm_vcpu *vcpu) +{ + /* For e5xx... instructions we only handle TPROT */ + if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01) + return handle_tprot(vcpu); + return -EOPNOTSUPP; +} + diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S deleted file mode 100644 index 5faa1b1b23fa..000000000000 --- a/arch/s390/kvm/sie64a.S +++ /dev/null @@ -1,98 +0,0 @@ -/* - * sie64a.S - low level sie call - * - * Copyright IBM Corp. 2008,2010 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * - * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> - * Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com> - */ - -#include <linux/errno.h> -#include <asm/asm-offsets.h> -#include <asm/setup.h> -#include <asm/asm-offsets.h> -#include <asm/ptrace.h> -#include <asm/thread_info.h> - -_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) - -/* - * offsets into stackframe - * SP_ = offsets into stack sie64 is called with - * SPI_ = offsets into irq stack - */ -SP_GREGS = __SF_EMPTY -SP_HOOK = __SF_EMPTY+8 -SP_GPP = __SF_EMPTY+16 -SPI_PSW = STACK_FRAME_OVERHEAD + __PT_PSW - - - .macro SPP newpp - tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_SPP - jz 0f - .insn s,0xb2800000,\newpp -0: - .endm - -sie_irq_handler: - SPP __LC_CMF_HPP # set host id - larl %r2,sie_inst - clg %r2,SPI_PSW+8(0,%r15) # intercepted sie - jne 1f - xc __LC_SIE_HOOK(8),__LC_SIE_HOOK - lg %r2,__LC_THREAD_INFO # pointer thread_info struct - tm __TI_flags+7(%r2),_TIF_EXIT_SIE - jz 0f - larl %r2,sie_exit # work pending, leave sie - stg %r2,SPI_PSW+8(0,%r15) - br %r14 -0: larl %r2,sie_reenter # re-enter with guest id - stg %r2,SPI_PSW+8(0,%r15) -1: br %r14 - -/* - * sie64a calling convention: - * %r2 pointer to sie control block - * %r3 guest register save area - */ - .globl sie64a -sie64a: - stg %r3,SP_GREGS(%r15) # save guest register save area - stmg %r6,%r14,__SF_GPRS(%r15) # save registers on entry - lgr %r14,%r2 # pointer to sie control block - larl %r5,sie_irq_handler - stg %r2,SP_GPP(%r15) - stg %r5,SP_HOOK(%r15) # save hook target - lmg %r0,%r13,0(%r3) # load guest gprs 0-13 -sie_reenter: - mvc __LC_SIE_HOOK(8),SP_HOOK(%r15) - SPP SP_GPP(%r15) # set guest id -sie_inst: - sie 0(%r14) - xc __LC_SIE_HOOK(8),__LC_SIE_HOOK - SPP __LC_CMF_HPP # set host id -sie_exit: - lg %r14,SP_GREGS(%r15) - stmg %r0,%r13,0(%r14) # save guest gprs 0-13 - lghi %r2,0 - lmg %r6,%r14,__SF_GPRS(%r15) - br %r14 - -sie_err: - xc __LC_SIE_HOOK(8),__LC_SIE_HOOK - SPP __LC_CMF_HPP # set host id - lg %r14,SP_GREGS(%r15) - stmg %r0,%r13,0(%r14) # save guest gprs 0-13 - lghi %r2,-EFAULT - lmg %r6,%r14,__SF_GPRS(%r15) - br %r14 - - .section __ex_table,"a" - .quad sie_inst,sie_err - .quad sie_exit,sie_err - .quad sie_reenter,sie_err - .previous diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 702276f5e2fa..0a7941d74bc6 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -31,9 +31,11 @@ #define SIGP_SET_PREFIX 0x0d #define SIGP_STORE_STATUS_ADDR 0x0e #define SIGP_SET_ARCH 0x12 +#define SIGP_SENSE_RUNNING 0x15 /* cpu status bits */ #define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL +#define SIGP_STAT_NOT_RUNNING 0x00000400UL #define SIGP_STAT_INCORRECT_STATE 0x00000200UL #define SIGP_STAT_INVALID_PARAMETER 0x00000100UL #define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL @@ -57,8 +59,8 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, spin_lock(&fi->lock); if (fi->local_int[cpu_addr] == NULL) rc = 3; /* not operational */ - else if (atomic_read(fi->local_int[cpu_addr]->cpuflags) - & CPUSTAT_RUNNING) { + else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_STOPPED)) { *reg &= 0xffffffff00000000UL; rc = 1; /* status stored */ } else { @@ -87,6 +89,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) return -ENOMEM; inti->type = KVM_S390_INT_EMERGENCY; + inti->emerg.code = vcpu->vcpu_id; spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; @@ -103,9 +106,47 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); rc = 0; /* order accepted */ + VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); +unlock: + spin_unlock(&fi->lock); + return rc; +} + +static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_local_interrupt *li; + struct kvm_s390_interrupt_info *inti; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + inti->type = KVM_S390_INT_EXTERNAL_CALL; + inti->extcall.code = vcpu->vcpu_id; + + spin_lock(&fi->lock); + li = fi->local_int[cpu_addr]; + if (li == NULL) { + rc = 3; /* not operational */ + kfree(inti); + goto unlock; + } + spin_lock_bh(&li->lock); + list_add_tail(&inti->list, &li->list); + atomic_set(&li->active, 1); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&li->wq); + spin_unlock_bh(&li->lock); + rc = 0; /* order accepted */ + VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); unlock: spin_unlock(&fi->lock); - VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); return rc; } @@ -189,10 +230,8 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, /* make sure that the new value is valid memory */ address = address & 0x7fffe000u; - if ((copy_from_user(&tmp, (void __user *) - (address + vcpu->arch.sie_block->gmsor) , 1)) || - (copy_from_user(&tmp, (void __user *)(address + - vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) { + if (copy_from_guest_absolute(vcpu, &tmp, address, 1) || + copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) { *reg |= SIGP_STAT_INVALID_PARAMETER; return 1; /* invalid parameter */ } @@ -214,7 +253,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, spin_lock_bh(&li->lock); /* cpu must be in stopped state */ - if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) { + if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { rc = 1; /* incorrect state */ *reg &= SIGP_STAT_INCORRECT_STATE; kfree(inti); @@ -238,6 +277,38 @@ out_fi: return rc; } +static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, + unsigned long *reg) +{ + int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + spin_lock(&fi->lock); + if (fi->local_int[cpu_addr] == NULL) + rc = 3; /* not operational */ + else { + if (atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_RUNNING) { + /* running */ + rc = 1; + } else { + /* not running */ + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STAT_NOT_RUNNING; + rc = 0; + } + } + spin_unlock(&fi->lock); + + VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr, + rc); + + return rc; +} + int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) { int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; @@ -269,6 +340,10 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) rc = __sigp_sense(vcpu, cpu_addr, &vcpu->arch.guest_gprs[r1]); break; + case SIGP_EXTERNAL_CALL: + vcpu->stat.instruction_sigp_external_call++; + rc = __sigp_external_call(vcpu, cpu_addr); + break; case SIGP_EMERGENCY: vcpu->stat.instruction_sigp_emergency++; rc = __sigp_emergency(vcpu, cpu_addr); @@ -290,6 +365,11 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) rc = __sigp_set_prefix(vcpu, cpu_addr, parameter, &vcpu->arch.guest_gprs[r1]); break; + case SIGP_SENSE_RUNNING: + vcpu->stat.instruction_sigp_sense_running++; + rc = __sigp_sense_running(vcpu, cpu_addr, + &vcpu->arch.guest_gprs[r1]); + break; case SIGP_RESTART: vcpu->stat.instruction_sigp_restart++; /* user space must know about restart */ diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index a65229d91c92..db92f044024c 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -32,7 +32,8 @@ static void __udelay_disabled(unsigned long long usecs) u64 clock_saved; u64 end; - mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; + mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_WAIT | + PSW_MASK_EXT | PSW_MASK_MCHECK; end = get_clock() + (usecs << 12); clock_saved = local_tick_disable(); __ctl_store(cr0_saved, 0, 0); diff --git a/arch/s390/lib/qrnnd.S b/arch/s390/lib/qrnnd.S index eb1df632e749..d321329130ec 100644 --- a/arch/s390/lib/qrnnd.S +++ b/arch/s390/lib/qrnnd.S @@ -1,5 +1,7 @@ # S/390 __udiv_qrnnd +#include <linux/linkage.h> + # r2 : &__r # r3 : upper half of 64 bit word n # r4 : lower half of 64 bit word n @@ -8,8 +10,7 @@ # the quotient q is to be returned .text - .globl __udiv_qrnnd -__udiv_qrnnd: +ENTRY(__udiv_qrnnd) st %r2,24(%r15) # store pointer to reminder for later lr %r0,%r3 # reload n lr %r1,%r4 diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 74833831417f..342ae35a5ba9 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -342,7 +342,8 @@ int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) if (segment_eq(get_fs(), KERNEL_DS)) return __futex_atomic_op_pt(op, uaddr, oparg, old); spin_lock(¤t->mm->page_table_lock); - uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); + uaddr = (u32 __force __user *) + __dat_user_addr((__force unsigned long) uaddr); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; @@ -378,7 +379,8 @@ int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, if (segment_eq(get_fs(), KERNEL_DS)) return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval); spin_lock(¤t->mm->page_table_lock); - uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); + uaddr = (u32 __force __user *) + __dat_user_addr((__force unsigned long) uaddr); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index fe103e891e7a..a9a301866b3c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -299,13 +299,28 @@ static inline int do_exception(struct pt_regs *regs, int access, goto out; address = trans_exc_code & __FAIL_ADDR_MASK; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); flags = FAULT_FLAG_ALLOW_RETRY; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) flags |= FAULT_FLAG_WRITE; -retry: down_read(&mm->mmap_sem); +#ifdef CONFIG_PGSTE + if (test_tsk_thread_flag(current, TIF_SIE) && S390_lowcore.gmap) { + address = __gmap_fault(address, + (struct gmap *) S390_lowcore.gmap); + if (address == -EFAULT) { + fault = VM_FAULT_BADMAP; + goto out_up; + } + if (address == -ENOMEM) { + fault = VM_FAULT_OOM; + goto out_up; + } + } +#endif + +retry: fault = VM_FAULT_BADMAP; vma = find_vma(mm, address); if (!vma) @@ -345,17 +360,18 @@ retry: if (flags & FAULT_FLAG_ALLOW_RETRY) { if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); } else { tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } if (fault & VM_FAULT_RETRY) { /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + down_read(&mm->mmap_sem); goto retry; } } @@ -377,7 +393,7 @@ void __kprobes do_protection_exception(struct pt_regs *regs, long pgm_int_code, int fault; /* Protection exception is suppressing, decrement psw address. */ - regs->psw.addr -= (pgm_int_code >> 16); + regs->psw.addr = __rewind_psw(regs->psw, pgm_int_code >> 16); /* * Check for low-address protection. This needs to be treated * as a special case because the translation exception code @@ -438,7 +454,7 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write) struct pt_regs regs; int access, fault; - regs.psw.mask = psw_kernel_bits; + regs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK; if (!irqs_disabled()) regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT; regs.psw.addr = (unsigned long) __builtin_return_address(0); @@ -571,8 +587,13 @@ static void pfault_interrupt(unsigned int ext_int_code, } else { /* Completion interrupt was faster than initial * interrupt. Set pfault_wait to -1 so the initial - * interrupt doesn't put the task to sleep. */ - tsk->thread.pfault_wait = -1; + * interrupt doesn't put the task to sleep. + * If the task is not running, ignore the completion + * interrupt since it must be a leftover of a PFAULT + * CANCEL operation which didn't remove all pending + * completion interrupts. */ + if (tsk->state == TASK_RUNNING) + tsk->thread.pfault_wait = -1; } put_task_struct(tsk); } else { diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 45b405ca2567..65cb06e2af4e 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -52,7 +52,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask, result; - struct page *head, *page; + struct page *head, *page, *tail; int refs; result = write ? 0 : _SEGMENT_ENTRY_RO; @@ -64,6 +64,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -81,6 +82,17 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, *nr -= refs; while (refs--) put_page(head); + return 0; + } + + /* + * Any tail page need their mapcount reference taken before we + * return. + */ + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; } return 1; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index a4d856db9154..597bb2d27c3c 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -35,7 +35,7 @@ int arch_prepare_hugepage(struct page *page) if (MACHINE_HAS_HPAGE) return 0; - ptep = (pte_t *) pte_alloc_one(&init_mm, address); + ptep = (pte_t *) pte_alloc_one(&init_mm, addr); if (!ptep) return -ENOMEM; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 59b663109d90..d4b9fb4d0042 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -26,6 +26,7 @@ #include <linux/pfn.h> #include <linux/poison.h> #include <linux/initrd.h> +#include <linux/export.h> #include <linux/gfp.h> #include <asm/processor.h> #include <asm/system.h> diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 51e5cd9b906a..1cb8427bedfb 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/errno.h> +#include <linux/gfp.h> #include <asm/system.h> /* @@ -60,6 +61,9 @@ long probe_kernel_write(void *dst, const void *src, size_t size) return copied < 0 ? -EFAULT : 0; } +/* + * Copy memory in real mode (kernel to kernel) + */ int memcpy_real(void *dest, void *src, size_t count) { register unsigned long _dest asm("2") = (unsigned long) dest; @@ -85,3 +89,71 @@ int memcpy_real(void *dest, void *src, size_t count) arch_local_irq_restore(flags); return rc; } + +/* + * Copy memory to absolute zero + */ +void copy_to_absolute_zero(void *dest, void *src, size_t count) +{ + unsigned long cr0; + + BUG_ON((unsigned long) dest + count >= sizeof(struct _lowcore)); + preempt_disable(); + __ctl_store(cr0, 0, 0); + __ctl_clear_bit(0, 28); /* disable lowcore protection */ + memcpy_real(dest + store_prefix(), src, count); + __ctl_load(cr0, 0, 0); + preempt_enable(); +} + +/* + * Copy memory from kernel (real) to user (virtual) + */ +int copy_to_user_real(void __user *dest, void *src, size_t count) +{ + int offs = 0, size, rc; + char *buf; + + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + rc = -EFAULT; + while (offs < count) { + size = min(PAGE_SIZE, count - offs); + if (memcpy_real(buf, src + offs, size)) + goto out; + if (copy_to_user(dest + offs, buf, size)) + goto out; + offs += size; + } + rc = 0; +out: + free_page((unsigned long) buf); + return rc; +} + +/* + * Copy memory from user (virtual) to kernel (real) + */ +int copy_from_user_real(void *dest, void __user *src, size_t count) +{ + int offs = 0, size, rc; + char *buf; + + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + rc = -EFAULT; + while (offs < count) { + size = min(PAGE_SIZE, count - offs); + if (copy_from_user(buf, src + offs, size)) + goto out; + if (memcpy_real(dest + offs, buf, size)) + goto out; + offs += size; + } + rc = 0; +out: + free_page((unsigned long) buf); + return rc; +} diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index c9a9f7f18188..f09c74881b7e 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -26,6 +26,7 @@ #include <linux/personality.h> #include <linux/mm.h> +#include <linux/mman.h> #include <linux/module.h> #include <linux/random.h> #include <asm/pgalloc.h> diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index d013ed39743b..b36537a5f43e 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/mm.h> #include <linux/hugetlb.h> +#include <asm/cacheflush.h> #include <asm/pgtable.h> static void change_page_attr(unsigned long addr, int numpages, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 37a23c223705..301c84d3b542 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2007,2009 + * Copyright IBM Corp. 2007,2011 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/quicklist.h> #include <linux/rcupdate.h> +#include <linux/slab.h> #include <asm/system.h> #include <asm/pgtable.h> @@ -133,30 +134,439 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) } #endif -static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits) +#ifdef CONFIG_PGSTE + +/** + * gmap_alloc - allocate a guest address space + * @mm: pointer to the parent mm_struct + * + * Returns a guest address space structure. + */ +struct gmap *gmap_alloc(struct mm_struct *mm) { - unsigned int old, new; + struct gmap *gmap; + struct page *page; + unsigned long *table; - do { - old = atomic_read(v); - new = old ^ bits; - } while (atomic_cmpxchg(v, old, new) != old); - return new; + gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL); + if (!gmap) + goto out; + INIT_LIST_HEAD(&gmap->crst_list); + gmap->mm = mm; + page = alloc_pages(GFP_KERNEL, ALLOC_ORDER); + if (!page) + goto out_free; + list_add(&page->lru, &gmap->crst_list); + table = (unsigned long *) page_to_phys(page); + crst_table_init(table, _REGION1_ENTRY_EMPTY); + gmap->table = table; + gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | __pa(table); + list_add(&gmap->list, &mm->context.gmap_list); + return gmap; + +out_free: + kfree(gmap); +out: + return NULL; +} +EXPORT_SYMBOL_GPL(gmap_alloc); + +static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table) +{ + struct gmap_pgtable *mp; + struct gmap_rmap *rmap; + struct page *page; + + if (*table & _SEGMENT_ENTRY_INV) + return 0; + page = pfn_to_page(*table >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + list_for_each_entry(rmap, &mp->mapper, list) { + if (rmap->entry != table) + continue; + list_del(&rmap->list); + kfree(rmap); + break; + } + *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + return 1; +} + +static void gmap_flush_tlb(struct gmap *gmap) +{ + if (MACHINE_HAS_IDTE) + __tlb_flush_idte((unsigned long) gmap->table | + _ASCE_TYPE_REGION1); + else + __tlb_flush_global(); } +/** + * gmap_free - free a guest address space + * @gmap: pointer to the guest address space structure + */ +void gmap_free(struct gmap *gmap) +{ + struct page *page, *next; + unsigned long *table; + int i; + + + /* Flush tlb. */ + if (MACHINE_HAS_IDTE) + __tlb_flush_idte((unsigned long) gmap->table | + _ASCE_TYPE_REGION1); + else + __tlb_flush_global(); + + /* Free all segment & region tables. */ + down_read(&gmap->mm->mmap_sem); + spin_lock(&gmap->mm->page_table_lock); + list_for_each_entry_safe(page, next, &gmap->crst_list, lru) { + table = (unsigned long *) page_to_phys(page); + if ((*table & _REGION_ENTRY_TYPE_MASK) == 0) + /* Remove gmap rmap structures for segment table. */ + for (i = 0; i < PTRS_PER_PMD; i++, table++) + gmap_unlink_segment(gmap, table); + __free_pages(page, ALLOC_ORDER); + } + spin_unlock(&gmap->mm->page_table_lock); + up_read(&gmap->mm->mmap_sem); + list_del(&gmap->list); + kfree(gmap); +} +EXPORT_SYMBOL_GPL(gmap_free); + +/** + * gmap_enable - switch primary space to the guest address space + * @gmap: pointer to the guest address space structure + */ +void gmap_enable(struct gmap *gmap) +{ + S390_lowcore.gmap = (unsigned long) gmap; +} +EXPORT_SYMBOL_GPL(gmap_enable); + +/** + * gmap_disable - switch back to the standard primary address space + * @gmap: pointer to the guest address space structure + */ +void gmap_disable(struct gmap *gmap) +{ + S390_lowcore.gmap = 0UL; +} +EXPORT_SYMBOL_GPL(gmap_disable); + /* - * page table entry allocation/free routines. + * gmap_alloc_table is assumed to be called with mmap_sem held */ -#ifdef CONFIG_PGSTE -static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm) +static int gmap_alloc_table(struct gmap *gmap, + unsigned long *table, unsigned long init) { struct page *page; + unsigned long *new; + + page = alloc_pages(GFP_KERNEL, ALLOC_ORDER); + if (!page) + return -ENOMEM; + new = (unsigned long *) page_to_phys(page); + crst_table_init(new, init); + if (*table & _REGION_ENTRY_INV) { + list_add(&page->lru, &gmap->crst_list); + *table = (unsigned long) new | _REGION_ENTRY_LENGTH | + (*table & _REGION_ENTRY_TYPE_MASK); + } else + __free_pages(page, ALLOC_ORDER); + return 0; +} + +/** + * gmap_unmap_segment - unmap segment from the guest address space + * @gmap: pointer to the guest address space structure + * @addr: address in the guest address space + * @len: length of the memory area to unmap + * + * Returns 0 if the unmap succeded, -EINVAL if not. + */ +int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) +{ unsigned long *table; + unsigned long off; + int flush; + + if ((to | len) & (PMD_SIZE - 1)) + return -EINVAL; + if (len == 0 || to + len < to) + return -EINVAL; + + flush = 0; + down_read(&gmap->mm->mmap_sem); + spin_lock(&gmap->mm->page_table_lock); + for (off = 0; off < len; off += PMD_SIZE) { + /* Walk the guest addr space page table */ + table = gmap->table + (((to + off) >> 53) & 0x7ff); + if (*table & _REGION_ENTRY_INV) + goto out; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + (((to + off) >> 42) & 0x7ff); + if (*table & _REGION_ENTRY_INV) + goto out; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + (((to + off) >> 31) & 0x7ff); + if (*table & _REGION_ENTRY_INV) + goto out; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + (((to + off) >> 20) & 0x7ff); + + /* Clear segment table entry in guest address space. */ + flush |= gmap_unlink_segment(gmap, table); + *table = _SEGMENT_ENTRY_INV; + } +out: + spin_unlock(&gmap->mm->page_table_lock); + up_read(&gmap->mm->mmap_sem); + if (flush) + gmap_flush_tlb(gmap); + return 0; +} +EXPORT_SYMBOL_GPL(gmap_unmap_segment); + +/** + * gmap_mmap_segment - map a segment to the guest address space + * @gmap: pointer to the guest address space structure + * @from: source address in the parent address space + * @to: target address in the guest address space + * + * Returns 0 if the mmap succeded, -EINVAL or -ENOMEM if not. + */ +int gmap_map_segment(struct gmap *gmap, unsigned long from, + unsigned long to, unsigned long len) +{ + unsigned long *table; + unsigned long off; + int flush; + + if ((from | to | len) & (PMD_SIZE - 1)) + return -EINVAL; + if (len == 0 || from + len > PGDIR_SIZE || + from + len < from || to + len < to) + return -EINVAL; + + flush = 0; + down_read(&gmap->mm->mmap_sem); + spin_lock(&gmap->mm->page_table_lock); + for (off = 0; off < len; off += PMD_SIZE) { + /* Walk the gmap address space page table */ + table = gmap->table + (((to + off) >> 53) & 0x7ff); + if ((*table & _REGION_ENTRY_INV) && + gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY)) + goto out_unmap; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + (((to + off) >> 42) & 0x7ff); + if ((*table & _REGION_ENTRY_INV) && + gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY)) + goto out_unmap; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + (((to + off) >> 31) & 0x7ff); + if ((*table & _REGION_ENTRY_INV) && + gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY)) + goto out_unmap; + table = (unsigned long *) (*table & _REGION_ENTRY_ORIGIN); + table = table + (((to + off) >> 20) & 0x7ff); + + /* Store 'from' address in an invalid segment table entry. */ + flush |= gmap_unlink_segment(gmap, table); + *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off); + } + spin_unlock(&gmap->mm->page_table_lock); + up_read(&gmap->mm->mmap_sem); + if (flush) + gmap_flush_tlb(gmap); + return 0; + +out_unmap: + spin_unlock(&gmap->mm->page_table_lock); + up_read(&gmap->mm->mmap_sem); + gmap_unmap_segment(gmap, to, len); + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(gmap_map_segment); + +/* + * this function is assumed to be called with mmap_sem held + */ +unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +{ + unsigned long *table, vmaddr, segment; + struct mm_struct *mm; + struct gmap_pgtable *mp; + struct gmap_rmap *rmap; + struct vm_area_struct *vma; + struct page *page; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + current->thread.gmap_addr = address; + mm = gmap->mm; + /* Walk the gmap address space page table */ + table = gmap->table + ((address >> 53) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -EFAULT; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 42) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -EFAULT; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 31) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -EFAULT; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 20) & 0x7ff); + + /* Convert the gmap address to an mm address. */ + segment = *table; + if (likely(!(segment & _SEGMENT_ENTRY_INV))) { + page = pfn_to_page(segment >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + return mp->vmaddr | (address & ~PMD_MASK); + } else if (segment & _SEGMENT_ENTRY_RO) { + vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; + vma = find_vma(mm, vmaddr); + if (!vma || vma->vm_start > vmaddr) + return -EFAULT; + + /* Walk the parent mm page table */ + pgd = pgd_offset(mm, vmaddr); + pud = pud_alloc(mm, pgd, vmaddr); + if (!pud) + return -ENOMEM; + pmd = pmd_alloc(mm, pud, vmaddr); + if (!pmd) + return -ENOMEM; + if (!pmd_present(*pmd) && + __pte_alloc(mm, vma, pmd, vmaddr)) + return -ENOMEM; + /* pmd now points to a valid segment table entry. */ + rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT); + if (!rmap) + return -ENOMEM; + /* Link gmap segment table entry location to page table. */ + page = pmd_page(*pmd); + mp = (struct gmap_pgtable *) page->index; + rmap->entry = table; + spin_lock(&mm->page_table_lock); + list_add(&rmap->list, &mp->mapper); + spin_unlock(&mm->page_table_lock); + /* Set gmap segment table entry to page table. */ + *table = pmd_val(*pmd) & PAGE_MASK; + return vmaddr | (address & ~PMD_MASK); + } + return -EFAULT; +} + +unsigned long gmap_fault(unsigned long address, struct gmap *gmap) +{ + unsigned long rc; + + down_read(&gmap->mm->mmap_sem); + rc = __gmap_fault(address, gmap); + up_read(&gmap->mm->mmap_sem); + + return rc; +} +EXPORT_SYMBOL_GPL(gmap_fault); + +void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) +{ + + unsigned long *table, address, size; + struct vm_area_struct *vma; + struct gmap_pgtable *mp; + struct page *page; + + down_read(&gmap->mm->mmap_sem); + address = from; + while (address < to) { + /* Walk the gmap address space page table */ + table = gmap->table + ((address >> 53) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 42) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 31) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 20) & 0x7ff); + if (unlikely(*table & _SEGMENT_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + page = pfn_to_page(*table >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + vma = find_vma(gmap->mm, mp->vmaddr); + size = min(to - address, PMD_SIZE - (address & ~PMD_MASK)); + zap_page_range(vma, mp->vmaddr | (address & ~PMD_MASK), + size, NULL); + address = (address + PMD_SIZE) & PMD_MASK; + } + up_read(&gmap->mm->mmap_sem); +} +EXPORT_SYMBOL_GPL(gmap_discard); + +void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table) +{ + struct gmap_rmap *rmap, *next; + struct gmap_pgtable *mp; + struct page *page; + int flush; + + flush = 0; + spin_lock(&mm->page_table_lock); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + list_for_each_entry_safe(rmap, next, &mp->mapper, list) { + *rmap->entry = + _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + list_del(&rmap->list); + kfree(rmap); + flush = 1; + } + spin_unlock(&mm->page_table_lock); + if (flush) + __tlb_flush_global(); +} + +static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, + unsigned long vmaddr) +{ + struct page *page; + unsigned long *table; + struct gmap_pgtable *mp; page = alloc_page(GFP_KERNEL|__GFP_REPEAT); if (!page) return NULL; + mp = kmalloc(sizeof(*mp), GFP_KERNEL|__GFP_REPEAT); + if (!mp) { + __free_page(page); + return NULL; + } pgtable_page_ctor(page); + mp->vmaddr = vmaddr & PMD_MASK; + INIT_LIST_HEAD(&mp->mapper); + page->index = (unsigned long) mp; atomic_set(&page->_mapcount, 3); table = (unsigned long *) page_to_phys(page); clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2); @@ -167,24 +577,58 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm) static inline void page_table_free_pgste(unsigned long *table) { struct page *page; + struct gmap_pgtable *mp; page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + BUG_ON(!list_empty(&mp->mapper)); pgtable_page_ctor(page); atomic_set(&page->_mapcount, -1); + kfree(mp); __free_page(page); } -#endif -unsigned long *page_table_alloc(struct mm_struct *mm) +#else /* CONFIG_PGSTE */ + +static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, + unsigned long vmaddr) +{ + return NULL; +} + +static inline void page_table_free_pgste(unsigned long *table) +{ +} + +static inline void gmap_unmap_notifier(struct mm_struct *mm, + unsigned long *table) +{ +} + +#endif /* CONFIG_PGSTE */ + +static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits) +{ + unsigned int old, new; + + do { + old = atomic_read(v); + new = old ^ bits; + } while (atomic_cmpxchg(v, old, new) != old); + return new; +} + +/* + * page table entry allocation/free routines. + */ +unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr) { struct page *page; unsigned long *table; unsigned int mask, bit; -#ifdef CONFIG_PGSTE if (mm_has_pgste(mm)) - return page_table_alloc_pgste(mm); -#endif + return page_table_alloc_pgste(mm, vmaddr); /* Allocate fragments of a 4K page as 1K/2K page table */ spin_lock_bh(&mm->context.list_lock); mask = FRAG_MASK; @@ -222,10 +666,10 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) struct page *page; unsigned int bit, mask; -#ifdef CONFIG_PGSTE - if (mm_has_pgste(mm)) + if (mm_has_pgste(mm)) { + gmap_unmap_notifier(mm, table); return page_table_free_pgste(table); -#endif + } /* Free 1K/2K page table fragment of a 4K page */ page = pfn_to_page(__pa(table) >> PAGE_SHIFT); bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t))); @@ -249,10 +693,8 @@ static void __page_table_free_rcu(void *table, unsigned bit) { struct page *page; -#ifdef CONFIG_PGSTE if (bit == FRAG_MASK) return page_table_free_pgste(table); -#endif /* Free 1K/2K page table fragment of a 4K page */ page = pfn_to_page(__pa(table) >> PAGE_SHIFT); if (atomic_xor_bits(&page->_mapcount, bit) == 0) { @@ -269,13 +711,12 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) unsigned int bit, mask; mm = tlb->mm; -#ifdef CONFIG_PGSTE if (mm_has_pgste(mm)) { + gmap_unmap_notifier(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; } -#endif bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t))); page = pfn_to_page(__pa(table) >> PAGE_SHIFT); spin_lock_bh(&mm->context.list_lock); @@ -291,8 +732,9 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) void __tlb_remove_table(void *_table) { - void *table = (void *)((unsigned long) _table & PAGE_MASK); - unsigned type = (unsigned long) _table & ~PAGE_MASK; + const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK; + void *table = (void *)((unsigned long) _table & ~mask); + unsigned type = (unsigned long) _table & mask; if (type) __page_table_free_rcu(table, type); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 8c1970d1dd91..4799383e2df9 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -61,12 +61,12 @@ static inline pmd_t *vmem_pmd_alloc(void) return pmd; } -static pte_t __ref *vmem_pte_alloc(void) +static pte_t __ref *vmem_pte_alloc(unsigned long address) { pte_t *pte; if (slab_is_available()) - pte = (pte_t *) page_table_alloc(&init_mm); + pte = (pte_t *) page_table_alloc(&init_mm, address); else pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t)); if (!pte) @@ -120,7 +120,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) } #endif if (pmd_none(*pm_dir)) { - pt_dir = vmem_pte_alloc(); + pt_dir = vmem_pte_alloc(address); if (!pt_dir) goto out; pmd_populate(&init_mm, pm_dir, pt_dir); @@ -205,7 +205,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) pm_dir = pmd_offset(pu_dir, address); if (pmd_none(*pm_dir)) { - pt_dir = vmem_pte_alloc(); + pt_dir = vmem_pte_alloc(address); if (!pt_dir) goto out; pmd_populate(&init_mm, pm_dir, pt_dir); @@ -335,6 +335,9 @@ void __init vmem_map_init(void) ro_start = ((unsigned long)&_stext) & PAGE_MASK; ro_end = PFN_ALIGN((unsigned long)&_eshared); for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { + if (memory_chunk[i].type == CHUNK_CRASHK || + memory_chunk[i].type == CHUNK_OLDMEM) + continue; start = memory_chunk[i].addr; end = memory_chunk[i].addr + memory_chunk[i].size; if (start >= ro_end || end <= ro_start) @@ -368,6 +371,9 @@ static int __init vmem_convert_memory_chunk(void) for (i = 0; i < MEMORY_CHUNKS; i++) { if (!memory_chunk[i].size) continue; + if (memory_chunk[i].type == CHUNK_CRASHK || + memory_chunk[i].type == CHUNK_OLDMEM) + continue; seg = kzalloc(sizeof(*seg), GFP_KERNEL); if (!seg) panic("Out of memory...\n"); diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c index 4552ce40c81a..f43c0e4282af 100644 --- a/arch/s390/oprofile/hwsampler.c +++ b/arch/s390/oprofile/hwsampler.c @@ -994,7 +994,7 @@ allocate_error: * * Returns 0 on success, !0 on failure. */ -int hwsampler_deallocate() +int hwsampler_deallocate(void) { int rc; @@ -1035,7 +1035,7 @@ unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu) return cb->sample_overflow; } -int hwsampler_setup() +int hwsampler_setup(void) { int rc; int cpu; @@ -1102,7 +1102,7 @@ setup_exit: return rc; } -int hwsampler_shutdown() +int hwsampler_shutdown(void) { int rc; @@ -1203,7 +1203,7 @@ start_all_exit: * * Returns 0 on success, !0 on failure. */ -int hwsampler_stop_all() +int hwsampler_stop_all(void) { int tmp_rc, rc, cpu; struct hws_cpu_buffer *cb; diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 0e358c2cffeb..6efc18b5e60a 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -13,8 +13,6 @@ #include <linux/oprofile.h> #include <linux/init.h> #include <linux/errno.h> -#include <linux/oprofile.h> -#include <linux/errno.h> #include <linux/fs.h> #include "../../../drivers/oprofile/oprof.h" |
