diff options
Diffstat (limited to 'arch/s390')
73 files changed, 764 insertions, 644 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 1c866ef..16c6730 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -94,7 +94,35 @@ config S390 select HAVE_KVM if 64BIT select HAVE_ARCH_TRACEHOOK select INIT_ALL_POSSIBLE - select HAVE_PERF_COUNTERS + select HAVE_PERF_EVENTS + select ARCH_INLINE_SPIN_TRYLOCK + select ARCH_INLINE_SPIN_TRYLOCK_BH + select ARCH_INLINE_SPIN_LOCK + select ARCH_INLINE_SPIN_LOCK_BH + select ARCH_INLINE_SPIN_LOCK_IRQ + select ARCH_INLINE_SPIN_LOCK_IRQSAVE + select ARCH_INLINE_SPIN_UNLOCK + select ARCH_INLINE_SPIN_UNLOCK_BH + select ARCH_INLINE_SPIN_UNLOCK_IRQ + select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + select ARCH_INLINE_READ_TRYLOCK + select ARCH_INLINE_READ_LOCK + select ARCH_INLINE_READ_LOCK_BH + select ARCH_INLINE_READ_LOCK_IRQ + select ARCH_INLINE_READ_LOCK_IRQSAVE + select ARCH_INLINE_READ_UNLOCK + select ARCH_INLINE_READ_UNLOCK_BH + select ARCH_INLINE_READ_UNLOCK_IRQ + select ARCH_INLINE_READ_UNLOCK_IRQRESTORE + select ARCH_INLINE_WRITE_TRYLOCK + select ARCH_INLINE_WRITE_LOCK + select ARCH_INLINE_WRITE_LOCK_BH + select ARCH_INLINE_WRITE_LOCK_IRQ + select ARCH_INLINE_WRITE_LOCK_IRQSAVE + select ARCH_INLINE_WRITE_UNLOCK + select ARCH_INLINE_WRITE_UNLOCK_BH + select ARCH_INLINE_WRITE_UNLOCK_IRQ + select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE config SCHED_OMIT_FRAME_POINTER bool diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 264528e..b55fd7e 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -50,10 +50,9 @@ static struct platform_device *appldata_pdev; * /proc entries (sysctl) */ static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata"; -static int appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +static int appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); static int appldata_interval_handler(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -247,7 +246,7 @@ __appldata_vtimer_setup(int cmd) * Start/Stop timer, show status of timer (0 = not active, 1 = active) */ static int -appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len; @@ -289,7 +288,7 @@ out: * current timer interval. */ static int -appldata_interval_handler(ctl_table *ctl, int write, struct file *filp, +appldata_interval_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len, interval; @@ -335,7 +334,7 @@ out: * monitoring (0 = not in process, 1 = in process) */ static int -appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, +appldata_generic_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct appldata_ops *ops = NULL, *tmp_ops; diff --git a/arch/s390/boot/install.sh b/arch/s390/boot/install.sh index d4026f6..aed30696 100644 --- a/arch/s390/boot/install.sh +++ b/arch/s390/boot/install.sh @@ -21,8 +21,8 @@ # User may have a custom install script -if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi -if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi +if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi +if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi # Default install - same as make zlilo diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 4e91a25..ab44644 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.30 -# Mon Jun 22 11:08:16 2009 +# Linux kernel version: 2.6.31 +# Tue Sep 22 17:43:13 2009 # CONFIG_SCHED_MC=y CONFIG_MMU=y @@ -24,6 +24,7 @@ CONFIG_PGSTE=y CONFIG_VIRT_CPU_ACCOUNTING=y CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y CONFIG_S390=y +CONFIG_SCHED_OMIT_FRAME_POINTER=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" CONFIG_CONSTRUCTORS=y @@ -48,11 +49,12 @@ CONFIG_AUDIT=y # # RCU Subsystem # -CONFIG_CLASSIC_RCU=y -# CONFIG_TREE_RCU is not set -# CONFIG_PREEMPT_RCU is not set +CONFIG_TREE_RCU=y +# CONFIG_TREE_PREEMPT_RCU is not set +# CONFIG_RCU_TRACE is not set +CONFIG_RCU_FANOUT=64 +# CONFIG_RCU_FANOUT_EXACT is not set # CONFIG_TREE_RCU_TRACE is not set -# CONFIG_PREEMPT_RCU_TRACE is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 @@ -103,11 +105,12 @@ CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_AIO=y -CONFIG_HAVE_PERF_COUNTERS=y +CONFIG_HAVE_PERF_EVENTS=y # -# Performance Counters +# Kernel Performance Events And Counters # +# CONFIG_PERF_EVENTS is not set # CONFIG_PERF_COUNTERS is not set CONFIG_VM_EVENT_COUNTERS=y # CONFIG_STRIP_ASM_SYMS is not set @@ -116,7 +119,6 @@ CONFIG_SLAB=y # CONFIG_SLUB is not set # CONFIG_SLOB is not set # CONFIG_PROFILING is not set -# CONFIG_MARKERS is not set CONFIG_HAVE_OPROFILE=y CONFIG_KPROBES=y CONFIG_HAVE_SYSCALL_WRAPPERS=y @@ -176,6 +178,7 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_64BIT=y +# CONFIG_KTIME_SCALAR is not set CONFIG_SMP=y CONFIG_NR_CPUS=32 CONFIG_HOTPLUG_CPU=y @@ -257,7 +260,6 @@ CONFIG_FORCE_MAX_ZONEORDER=9 CONFIG_PFAULT=y # CONFIG_SHARED_KERNEL is not set # CONFIG_CMM is not set -# CONFIG_PAGE_STATES is not set # CONFIG_APPLDATA_BASE is not set CONFIG_HZ_100=y # CONFIG_HZ_250 is not set @@ -280,6 +282,7 @@ CONFIG_PM_SLEEP_SMP=y CONFIG_PM_SLEEP=y CONFIG_HIBERNATION=y CONFIG_PM_STD_PARTITION="" +# CONFIG_PM_RUNTIME is not set CONFIG_NET=y # @@ -394,6 +397,7 @@ CONFIG_IP_SCTP=m # CONFIG_SCTP_HMAC_NONE is not set # CONFIG_SCTP_HMAC_SHA1 is not set CONFIG_SCTP_HMAC_MD5=y +# CONFIG_RDS is not set # CONFIG_TIPC is not set # CONFIG_ATM is not set # CONFIG_BRIDGE is not set @@ -487,6 +491,7 @@ CONFIG_CCW=y # Generic Driver Options # CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_DEVTMPFS is not set CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y CONFIG_FW_LOADER=y @@ -501,6 +506,7 @@ CONFIG_BLK_DEV=y CONFIG_BLK_DEV_LOOP=m # CONFIG_BLK_DEV_CRYPTOLOOP is not set CONFIG_BLK_DEV_NBD=m +# CONFIG_BLK_DEV_OSD is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_BLK_DEV_RAM_SIZE=4096 @@ -594,8 +600,11 @@ CONFIG_BLK_DEV_DM=y CONFIG_DM_CRYPT=y CONFIG_DM_SNAPSHOT=y CONFIG_DM_MIRROR=y +# CONFIG_DM_LOG_USERSPACE is not set CONFIG_DM_ZERO=y CONFIG_DM_MULTIPATH=m +# CONFIG_DM_MULTIPATH_QL is not set +# CONFIG_DM_MULTIPATH_ST is not set # CONFIG_DM_DELAY is not set # CONFIG_DM_UEVENT is not set CONFIG_NETDEVICES=y @@ -615,7 +624,6 @@ CONFIG_NET_ETHERNET=y # CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set # CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set # CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set -# CONFIG_KS8842 is not set CONFIG_NETDEV_1000=y CONFIG_NETDEV_10000=y # CONFIG_TR is not set @@ -678,6 +686,7 @@ CONFIG_SCLP_CONSOLE=y CONFIG_SCLP_VT220_TTY=y CONFIG_SCLP_VT220_CONSOLE=y CONFIG_SCLP_CPI=m +CONFIG_SCLP_ASYNC=m CONFIG_S390_TAPE=m # @@ -737,6 +746,7 @@ CONFIG_FS_POSIX_ACL=y # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_BTRFS_FS is not set +# CONFIG_NILFS2_FS is not set CONFIG_FILE_LOCKING=y CONFIG_FSNOTIFY=y CONFIG_DNOTIFY=y @@ -798,7 +808,6 @@ CONFIG_MISC_FILESYSTEMS=y # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set # CONFIG_EXOFS_FS is not set -# CONFIG_NILFS2_FS is not set CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y @@ -885,11 +894,13 @@ CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set # CONFIG_DEBUG_NOTIFIERS is not set +# CONFIG_DEBUG_CREDENTIALS is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_RCU_CPU_STALL_DETECTOR is not set # CONFIG_KPROBES_SANITY_TEST is not set # CONFIG_BACKTRACE_SELF_TEST is not set # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set # CONFIG_LATENCYTOP is not set @@ -979,11 +990,13 @@ CONFIG_CRYPTO_PCBC=m # CONFIG_CRYPTO_HMAC=m # CONFIG_CRYPTO_XCBC is not set +CONFIG_CRYPTO_VMAC=m # # Digest # CONFIG_CRYPTO_CRC32C=m +CONFIG_CRYPTO_GHASH=m # CONFIG_CRYPTO_MD4 is not set CONFIG_CRYPTO_MD5=m # CONFIG_CRYPTO_MICHAEL_MIC is not set diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 704dd39..77df726 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -438,7 +438,7 @@ static int diag204_probe(void) } if (diag204((unsigned long)SUBC_STIB6 | (unsigned long)INFO_EXT, pages, buf) >= 0) { - diag204_store_sc = SUBC_STIB7; + diag204_store_sc = SUBC_STIB6; diag204_info_type = INFO_EXT; goto out; } diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index bd9914b..341aff2 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -41,7 +41,7 @@ struct hypfs_sb_info { static const struct file_operations hypfs_file_ops; static struct file_system_type hypfs_type; -static struct super_operations hypfs_s_ops; +static const struct super_operations hypfs_s_ops; /* start of list of all dentries, which have to be deleted on update */ static struct dentry *hypfs_last_dentry; @@ -472,7 +472,7 @@ static struct file_system_type hypfs_type = { .kill_sb = hypfs_kill_super }; -static struct super_operations hypfs_s_ops = { +static const struct super_operations hypfs_s_ops = { .statfs = simple_statfs, .drop_inode = hypfs_drop_inode, .show_options = hypfs_show_options, @@ -496,7 +496,7 @@ static int __init hypfs_init(void) } s390_kobj = kobject_create_and_add("s390", hypervisor_kobj); if (!s390_kobj) { - rc = -ENOMEM;; + rc = -ENOMEM; goto fail_sysfs; } rc = register_filesystem(&hypfs_type); diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 7efd0ab..efb74fd 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -49,7 +49,7 @@ #define BUG() do { \ __EMIT_BUG(0); \ - for (;;); \ + unreachable(); \ } while (0) #define WARN_ON(x) ({ \ diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 7a3817a..f23961a 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -42,6 +42,7 @@ __div(unsigned long long n, unsigned int base) #endif /* __s390x__ */ #define cputime_zero (0ULL) +#define cputime_one_jiffy jiffies_to_cputime(1) #define cputime_max ((~0UL >> 1) - 1) #define cputime_add(__a, __b) ((__a) + (__b)) #define cputime_sub(__a, __b) ((__a) - (__b)) @@ -77,7 +78,7 @@ cputime64_to_jiffies64(cputime64_t cputime) static inline unsigned int cputime_to_msecs(const cputime_t cputime) { - return __div(cputime, 4096000); + return cputime_div(cputime, 4096000); } static inline cputime_t @@ -159,7 +160,7 @@ cputime_to_timeval(const cputime_t cputime, struct timeval *value) static inline clock_t cputime_to_clock_t(cputime_t cputime) { - return __div(cputime, 4096000000ULL / USER_HZ); + return cputime_div(cputime, 4096000000ULL / USER_HZ); } static inline cputime_t @@ -174,7 +175,7 @@ clock_t_to_cputime(unsigned long x) static inline clock_t cputime64_to_clock_t(cputime64_t cputime) { - return __div(cputime, 4096000000ULL / USER_HZ); + return cputime_div(cputime, 4096000000ULL / USER_HZ); } struct s390_idle_data { diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h index a356c95..8a096b8 100644 --- a/arch/s390/include/asm/delay.h +++ b/arch/s390/include/asm/delay.h @@ -14,10 +14,11 @@ #ifndef _S390_DELAY_H #define _S390_DELAY_H -extern void __udelay(unsigned long usecs); -extern void udelay_simple(unsigned long usecs); +extern void __udelay(unsigned long long usecs); +extern void udelay_simple(unsigned long long usecs); extern void __delay(unsigned long loops); -#define udelay(n) __udelay(n) +#define udelay(n) __udelay((unsigned long long) (n)) +#define mdelay(n) __udelay((unsigned long long) (n) * 1000) #endif /* defined(_S390_DELAY_H) */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 74d0bbb..e885442 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -92,6 +92,18 @@ /* Keep this the last entry. */ #define R_390_NUM 61 +/* Bits present in AT_HWCAP. */ +#define HWCAP_S390_ESAN3 1 +#define HWCAP_S390_ZARCH 2 +#define HWCAP_S390_STFLE 4 +#define HWCAP_S390_MSA 8 +#define HWCAP_S390_LDISP 16 +#define HWCAP_S390_EIMM 32 +#define HWCAP_S390_DFP 64 +#define HWCAP_S390_HPAGE 128 +#define HWCAP_S390_ETF3EH 256 +#define HWCAP_S390_HIGH_GPRS 512 + /* * These are used to set parameters in the core dumps. */ diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index 0b2f829..3dfcaeb 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -15,15 +15,6 @@ */ #include <linux/types.h> -/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ -struct kvm_pic_state { - /* no PIC for s390 */ -}; - -struct kvm_ioapic_state { - /* no IOAPIC for s390 */ -}; - /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 698988f..27605b6 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1,7 +1,7 @@ /* * asm-s390/kvm_host.h - definition for kernel virtual machines on s390 * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * 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) @@ -40,7 +40,11 @@ struct sca_block { struct sca_entry cpu[64]; } __attribute__((packed)); -#define KVM_PAGES_PER_HPAGE 256 +#define KVM_NR_PAGE_SIZES 2 +#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + ((x) - 1) * 8) +#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) +#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_WAIT 0x10000000 @@ -182,8 +186,9 @@ struct kvm_s390_interrupt_info { }; /* for local_interrupt.action_flags */ -#define ACTION_STORE_ON_STOP 1 -#define ACTION_STOP_ON_STOP 2 +#define ACTION_STORE_ON_STOP (1<<0) +#define ACTION_STOP_ON_STOP (1<<1) +#define ACTION_RELOADVCPU_ON_STOP (1<<2) struct kvm_s390_local_interrupt { spinlock_t lock; @@ -227,8 +232,6 @@ struct kvm_vm_stat { }; struct kvm_arch{ - unsigned long guest_origin; - unsigned long guest_memsize; struct sca_block *sca; debug_info_t *dbf; struct kvm_s390_float_interrupt float_int; diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h index 2c50379..6964db2 100644 --- a/arch/s390/include/asm/kvm_para.h +++ b/arch/s390/include/asm/kvm_para.h @@ -13,6 +13,8 @@ #ifndef __S390_KVM_PARA_H #define __S390_KVM_PARA_H +#ifdef __KERNEL__ + /* * Hypercalls for KVM on s390. The calling convention is similar to the * s390 ABI, so we use R2-R6 for parameters 1-5. In addition we use R1 @@ -147,4 +149,6 @@ static inline unsigned int kvm_arch_para_features(void) return 0; } +#endif + #endif /* __S390_KVM_PARA_H */ diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 6bc9426..f2ef4b6 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -86,6 +86,7 @@ #define __LC_PGM_OLD_PSW 0x0150 #define __LC_MCK_OLD_PSW 0x0160 #define __LC_IO_OLD_PSW 0x0170 +#define __LC_RESTART_PSW 0x01a0 #define __LC_EXT_NEW_PSW 0x01b0 #define __LC_SVC_NEW_PSW 0x01c0 #define __LC_PGM_NEW_PSW 0x01d0 @@ -189,6 +190,14 @@ union save_area { #define SAVE_AREA_BASE SAVE_AREA_BASE_S390X #endif +#ifndef __s390x__ +#define LC_ORDER 0 +#else +#define LC_ORDER 1 +#endif + +#define LC_PAGES (1UL << LC_ORDER) + struct _lowcore { #ifndef __s390x__ diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h index f63fe7b..4e9c8ae 100644 --- a/arch/s390/include/asm/mman.h +++ b/arch/s390/include/asm/mman.h @@ -9,18 +9,7 @@ #ifndef __S390_MMAN_H__ #define __S390_MMAN_H__ -#include <asm-generic/mman-common.h> - -#define MAP_GROWSDOWN 0x0100 /* stack-like segment */ -#define MAP_DENYWRITE 0x0800 /* ETXTBSY */ -#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */ -#define MAP_LOCKED 0x2000 /* pages are locked */ -#define MAP_NORESERVE 0x4000 /* don't check for reservations */ -#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ -#define MAP_NONBLOCK 0x10000 /* do not block on IO */ - -#define MCL_CURRENT 1 /* lock all current mappings */ -#define MCL_FUTURE 2 /* lock all future mappings */ +#include <asm-generic/mman.h> #if defined(__KERNEL__) && !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) int s390_mmap_check(unsigned long addr, unsigned long len); diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 408d60b..f7ad871 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -1,37 +1,21 @@ #ifndef __ARCH_S390_PERCPU__ #define __ARCH_S390_PERCPU__ -#include <linux/compiler.h> -#include <asm/lowcore.h> - /* * s390 uses its own implementation for per cpu data, the offset of * the cpu local data area is cached in the cpu's lowcore memory. - * For 64 bit module code s390 forces the use of a GOT slot for the - * address of the per cpu variable. This is needed because the module - * may be more than 4G above the per cpu area. */ -#if defined(__s390x__) && defined(MODULE) - -#define SHIFT_PERCPU_PTR(ptr,offset) (({ \ - extern int simple_identifier_##var(void); \ - unsigned long *__ptr; \ - asm ( "larl %0, %1@GOTENT" \ - : "=a" (__ptr) : "X" (ptr) ); \ - (typeof(ptr))((*__ptr) + (offset)); })) - -#else - -#define SHIFT_PERCPU_PTR(ptr, offset) (({ \ - extern int simple_identifier_##var(void); \ - unsigned long __ptr; \ - asm ( "" : "=a" (__ptr) : "0" (ptr) ); \ - (typeof(ptr)) (__ptr + (offset)); })) +#define __my_cpu_offset S390_lowcore.percpu_offset +/* + * For 64 bit module code, the module may be more than 4G above the + * per cpu area, use weak definitions to force the compiler to + * generate external references. + */ +#if defined(CONFIG_SMP) && defined(__s390x__) && defined(MODULE) +#define ARCH_NEEDS_WEAK_PER_CPU #endif -#define __my_cpu_offset S390_lowcore.percpu_offset - #include <asm-generic/percpu.h> #endif /* __ARCH_S390_PERCPU__ */ diff --git a/arch/s390/include/asm/perf_counter.h b/arch/s390/include/asm/perf_counter.h deleted file mode 100644 index 7015188..0000000 --- a/arch/s390/include/asm/perf_counter.h +++ /dev/null @@ -1,10 +0,0 @@ -/* - * Performance counter support - s390 specific definitions. - * - * Copyright 2009 Martin Schwidefsky, IBM Corporation. - */ - -static inline void set_perf_counter_pending(void) {} -static inline void clear_perf_counter_pending(void) {} - -#define PERF_COUNTER_INDEX_OFFSET 0 diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h new file mode 100644 index 0000000..3840cbe --- /dev/null +++ b/arch/s390/include/asm/perf_event.h @@ -0,0 +1,10 @@ +/* + * Performance event support - s390 specific definitions. + * + * Copyright 2009 Martin Schwidefsky, IBM Corporation. + */ + +static inline void set_perf_event_pending(void) {} +static inline void clear_perf_event_pending(void) {} + +#define PERF_EVENT_INDEX_OFFSET 0 diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index cf8eed3..b427154 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -295,7 +295,7 @@ static inline void ATTRIB_NORET disabled_wait(unsigned long code) " oi 0x384(1),0x10\n"/* fake protection bit */ " lpswe 0(%1)" : "=m" (ctl_buf) - : "a" (&dw_psw), "a" (&ctl_buf), "m" (dw_psw) : "cc", "0"); + : "a" (&dw_psw), "a" (&ctl_buf), "m" (dw_psw) : "cc", "0", "1"); #endif /* __s390x__ */ while (1); } diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 539263f..95dcf18 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -311,6 +311,10 @@ typedef struct __u32 orig_gpr2; } s390_compat_regs; +typedef struct +{ + __u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; #ifdef __KERNEL__ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index c991fe6..a868b27 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -62,7 +62,7 @@ extern struct mutex smp_cpu_state_mutex; extern int smp_cpu_polarization[]; extern void arch_send_call_function_single_ipi(int cpu); -extern void arch_send_call_function_ipi(cpumask_t mask); +extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); #endif diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index 02330c5..e42df89 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -65,4 +65,7 @@ #define SO_TIMESTAMPING 37 #define SCM_TIMESTAMPING SO_TIMESTAMPING +#define SO_PROTOCOL 38 +#define SO_DOMAIN 39 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 41ce686..c9af0d19 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -191,33 +191,4 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() -#define __always_inline__spin_lock -#define __always_inline__read_lock -#define __always_inline__write_lock -#define __always_inline__spin_lock_bh -#define __always_inline__read_lock_bh -#define __always_inline__write_lock_bh -#define __always_inline__spin_lock_irq -#define __always_inline__read_lock_irq -#define __always_inline__write_lock_irq -#define __always_inline__spin_lock_irqsave -#define __always_inline__read_lock_irqsave -#define __always_inline__write_lock_irqsave -#define __always_inline__spin_trylock -#define __always_inline__read_trylock -#define __always_inline__write_trylock -#define __always_inline__spin_trylock_bh -#define __always_inline__spin_unlock -#define __always_inline__read_unlock -#define __always_inline__write_unlock -#define __always_inline__spin_unlock_bh -#define __always_inline__read_unlock_bh -#define __always_inline__write_unlock_bh -#define __always_inline__spin_unlock_irq -#define __always_inline__read_unlock_irq -#define __always_inline__write_unlock_irq -#define __always_inline__spin_unlock_irqrestore -#define __always_inline__read_unlock_irqrestore -#define __always_inline__write_unlock_irqrestore - #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 24aa1cd..68d9fea 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -88,6 +88,14 @@ int get_sync_clock(unsigned long long *clock); void init_cpu_timer(void); unsigned long long monotonic_clock(void); +void tod_to_timeval(__u64, struct timespec *); + +static inline +void stck_to_timespec(unsigned long long stck, struct timespec *ts) +{ + tod_to_timeval(stck - TOD_UNIX_EPOCH, ts); +} + extern u64 sched_clock_base_cc; /** diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 5e0ad61..6e7211a 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -9,7 +9,6 @@ const struct cpumask *cpu_coregroup_mask(unsigned int cpu); extern cpumask_t cpu_core_map[NR_CPUS]; -#define topology_core_siblings(cpu) (cpu_core_map[cpu]) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) int topology_set_cpu_management(int fc); diff --git a/arch/s390/include/asm/ucontext.h b/arch/s390/include/asm/ucontext.h index d69bec0..cfb874e 100644 --- a/arch/s390/include/asm/ucontext.h +++ b/arch/s390/include/asm/ucontext.h @@ -9,6 +9,21 @@ #ifndef _ASM_S390_UCONTEXT_H #define _ASM_S390_UCONTEXT_H +#define UC_EXTENDED 0x00000001 + +#ifndef __s390x__ + +struct ucontext_extended { + unsigned long uc_flags; + struct ucontext *uc_link; + stack_t uc_stack; + _sigregs uc_mcontext; + unsigned long uc_sigmask[2]; + unsigned long uc_gprs_high[16]; +}; + +#endif + struct ucontext { unsigned long uc_flags; struct ucontext *uc_link; diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index c80602d..cb5232d 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -268,7 +268,7 @@ #define __NR_preadv 328 #define __NR_pwritev 329 #define __NR_rt_tgsigqueueinfo 330 -#define __NR_perf_counter_open 331 +#define __NR_perf_event_open 331 #define NR_syscalls 332 /* diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index fa9905c..63e4643 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/kbuild.h> #include <asm/vdso.h> +#include <asm/sigp.h> int main(void) { @@ -59,6 +60,10 @@ int main(void) DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); - + /* constants for SIGP */ + DEFINE(__SIGP_STOP, sigp_stop); + DEFINE(__SIGP_RESTART, sigp_restart); + DEFINE(__SIGP_SENSE, sigp_sense); + DEFINE(__SIGP_INITIAL_CPU_RESET, sigp_initial_cpu_reset); return 0; } diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9ab188d..0debcec 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -24,7 +24,6 @@ #include <linux/signal.h> #include <linux/resource.h> #include <linux/times.h> -#include <linux/utsname.h> #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/sem.h> @@ -443,66 +442,28 @@ sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) * sys32_execve() executes a new program after the asm stub has set * things up for us. This should basically do what I want it to. */ -asmlinkage long sys32_execve(void) +asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp) { struct pt_regs *regs = task_pt_regs(current); char *filename; - unsigned long result; - int rc; - - filename = getname(compat_ptr(regs->orig_gpr2)); - if (IS_ERR(filename)) { - result = PTR_ERR(filename); - goto out; - } - rc = compat_do_execve(filename, compat_ptr(regs->gprs[3]), - compat_ptr(regs->gprs[4]), regs); - if (rc) { - result = rc; - goto out_putname; - } + long rc; + + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = compat_do_execve(filename, argv, envp, regs); + if (rc) + goto out; current->thread.fp_regs.fpc=0; asm volatile("sfpc %0,0" : : "d" (0)); - result = regs->gprs[2]; -out_putname: - putname(filename); + rc = regs->gprs[2]; out: - return result; -} - - -#ifdef CONFIG_MODULES - -asmlinkage long -sys32_init_module(void __user *umod, unsigned long len, - const char __user *uargs) -{ - return sys_init_module(umod, len, uargs); -} - -asmlinkage long -sys32_delete_module(const char __user *name_user, unsigned int flags) -{ - return sys_delete_module(name_user, flags); -} - -#else /* CONFIG_MODULES */ - -asmlinkage long -sys32_init_module(void __user *umod, unsigned long len, - const char __user *uargs) -{ - return -ENOSYS; + putname(filename); + return rc; } -asmlinkage long -sys32_delete_module(const char __user *name_user, unsigned int flags) -{ - return -ENOSYS; -} - -#endif /* CONFIG_MODULES */ - asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, u32 poshi, u32 poslo) { @@ -801,23 +762,6 @@ asmlinkage long sys32_write(unsigned int fd, char __user * buf, size_t count) return sys_write(fd, buf, count); } -asmlinkage long sys32_clone(void) -{ - struct pt_regs *regs = task_pt_regs(current); - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs->gprs[3] & 0xffffffffUL; - newsp = regs->orig_gpr2 & 0x7fffffffUL; - parent_tidptr = compat_ptr(regs->gprs[4]); - child_tidptr = compat_ptr(regs->gprs[5]); - if (!newsp) - newsp = regs->gprs[15]; - return do_fork(clone_flags, newsp, regs, 0, - parent_tidptr, child_tidptr); -} - /* * 31 bit emulation wrapper functions for sys_fadvise64/fadvise64_64. * These need to rewrite the advise values for POSIX_FADV_{DONTNEED,NOREUSE} diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 836a288..c07f9ca 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -198,7 +198,8 @@ long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, size_t sigsetsize); long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize); long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo); -long sys32_execve(void); +long sys32_execve(char __user *name, compat_uptr_t __user *argv, + compat_uptr_t __user *envp); long sys32_init_module(void __user *umod, unsigned long len, const char __user *uargs); long sys32_delete_module(const char __user *name_user, unsigned int flags); @@ -222,7 +223,6 @@ unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg); long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg); long sys32_read(unsigned int fd, char __user * buf, size_t count); long sys32_write(unsigned int fd, char __user * buf, size_t count); -long sys32_clone(void); long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise); long sys32_fadvise64_64(struct fadvise64_64_args __user *args); long sys32_sigaction(int sig, const struct old_sigaction32 __user *act, diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index b537cb0..eee9998 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -39,6 +39,7 @@ typedef struct struct sigcontext32 sc; _sigregs32 sregs; int signo; + __u32 gprs_high[NUM_GPRS]; __u8 retcode[S390_SYSCALL_SIZE]; } sigframe32; @@ -48,6 +49,7 @@ typedef struct __u8 retcode[S390_SYSCALL_SIZE]; compat_siginfo_t info; struct ucontext32 uc; + __u32 gprs_high[NUM_GPRS]; } rt_sigframe32; int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) @@ -344,6 +346,30 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) return 0; } +static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int i; + + for (i = 0; i < NUM_GPRS; i++) + gprs_high[i] = regs->gprs[i] >> 32; + + return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); +} + +static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int err, i; + + err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); + if (err) + return err; + for (i = 0; i < NUM_GPRS; i++) + *(__u32 *)®s->gprs[i] = gprs_high[i]; + return 0; +} + asmlinkage long sys32_sigreturn(void) { struct pt_regs *regs = task_pt_regs(current); @@ -363,6 +389,8 @@ asmlinkage long sys32_sigreturn(void) if (restore_sigregs32(regs, &frame->sregs)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; return regs->gprs[2]; @@ -394,6 +422,8 @@ asmlinkage long sys32_rt_sigreturn(void) 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); @@ -474,6 +504,8 @@ static int setup_frame32(int sig, struct k_sigaction *ka, if (save_sigregs32(regs, &frame->sregs)) goto give_sigsegv; + if (save_sigregs_gprs_high(regs, frame->gprs_high)) + goto give_sigsegv; if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs)) goto give_sigsegv; @@ -529,13 +561,14 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, goto give_sigsegv; /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); err |= __put_user(sas_ss_flags(regs->gprs[15]), &frame->uc.uc_stack.ss_flags); err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); err |= save_sigregs32(regs, &frame->uc.uc_mcontext); + err |= save_sigregs_gprs_high(regs, frame->gprs_high); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) goto give_sigsegv; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 88a83366..cbd9901 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -409,7 +409,7 @@ sys32_munmap_wrapper: .globl sys32_truncate_wrapper sys32_truncate_wrapper: llgtr %r2,%r2 # const char * - llgfr %r3,%r3 # unsigned long + lgfr %r3,%r3 # long jg sys_truncate # branch to system call .globl sys32_ftruncate_wrapper @@ -568,18 +568,18 @@ compat_sys_sigprocmask_wrapper: llgtr %r4,%r4 # compat_old_sigset_t * jg compat_sys_sigprocmask # branch to system call - .globl sys32_init_module_wrapper -sys32_init_module_wrapper: + .globl sys_init_module_wrapper +sys_init_module_wrapper: llgtr %r2,%r2 # void * llgfr %r3,%r3 # unsigned long llgtr %r4,%r4 # char * - jg sys32_init_module # branch to system call + jg sys_init_module # branch to system call - .globl sys32_delete_module_wrapper -sys32_delete_module_wrapper: + .globl sys_delete_module_wrapper +sys_delete_module_wrapper: llgtr %r2,%r2 # const char * llgfr %r3,%r3 # unsigned int - jg sys32_delete_module # branch to system call + jg sys_delete_module # branch to system call .globl sys32_quotactl_wrapper sys32_quotactl_wrapper: @@ -1832,11 +1832,26 @@ compat_sys_rt_tgsigqueueinfo_wrapper: llgtr %r5,%r5 # struct compat_siginfo * jg compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call - .globl sys_perf_counter_open_wrapper -sys_perf_counter_open_wrapper: - llgtr %r2,%r2 # const struct perf_counter_attr * + .globl sys_perf_event_open_wrapper +sys_perf_event_open_wrapper: + llgtr %r2,%r2 # const struct perf_event_attr * lgfr %r3,%r3 # pid_t lgfr %r4,%r4 # int lgfr %r5,%r5 # int llgfr %r6,%r6 # unsigned long - jg sys_perf_counter_open # branch to system call + jg sys_perf_event_open # branch to system call + + .globl sys_clone_wrapper +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: + llgtr %r2,%r2 # char * + llgtr %r3,%r3 # compat_uptr_t * + llgtr %r4,%r4 # compat_uptr_t * + jg sys32_execve # branch to system call diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index be8bcea..20f282c 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -63,8 +63,6 @@ typedef struct } debug_sprintf_entry_t; -extern void tod_to_timeval(uint64_t todval, struct timespec *xtime); - /* internal function prototyes */ static int debug_init(void); @@ -883,11 +881,11 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, struct file *filp, +s390dbf_procactive(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); else return 0; } @@ -1450,17 +1448,13 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, int area, debug_entry_t * entry, char *out_buf) { struct timespec time_spec; - unsigned long long time; char *except_str; unsigned long caller; int rc = 0; unsigned int level; level = entry->id.fields.level; - time = entry->id.stck; - /* adjust todclock to 1970 */ - time -= 0x8126d60e46000000LL - (0x3c26700LL * 1000000 * 4096); - tod_to_timeval(time, &time_spec); + stck_to_timespec(entry->id.stck, &time_spec); if (entry->id.fields.exception) except_str = "*"; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index bf8b4ae..e49e9e0 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -55,6 +55,7 @@ static void __init reset_tod_clock(void) disabled_wait(0); sched_clock_base_cc = TOD_UNIX_EPOCH; + S390_lowcore.last_update_clock = sched_clock_base_cc; } #ifdef CONFIG_SHARED_KERNEL @@ -167,6 +168,14 @@ static noinline __init void create_kernel_nss(void) return; } + /* re-initialize cputime accounting. */ + sched_clock_base_cc = get_clock(); + S390_lowcore.last_update_clock = sched_clock_base_cc; + S390_lowcore.last_update_timer = 0x7fffffffffffffffULL; + S390_lowcore.user_timer = 0; + S390_lowcore.system_timer = 0; + asm volatile("SPT 0(%0)" : : "a" (&S390_lowcore.last_update_timer)); + /* re-setup boot command line with new ipl vm parms */ ipl_update_parameters(); setup_boot_command_line(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index f43d2ee..48215d1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -565,10 +565,10 @@ pgm_svcper: lh %r7,0x8a # get svc number from lowcore l %r9,__LC_THREAD_INFO # load pointer to thread_info struct TRACE_IRQS_OFF - l %r1,__TI_task(%r9) - mvc __THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID - mvc __THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS - mvc __THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID + l %r8,__TI_task(%r9) + mvc __THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID + mvc __THREAD_per+__PER_address(4,%r8),__LC_PER_ADDRESS + mvc __THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID oi __TI_flags+3(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP TRACE_IRQS_ON stosm __SF_EMPTY(%r15),0x03 # reenable interrupts diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 950c59c..e1e5e76 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -42,10 +42,12 @@ long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, u32 len_low); long sys_fork(void); -long sys_clone(void); +long sys_clone(unsigned long newsp, unsigned long clone_flags, + int __user *parent_tidptr, int __user *child_tidptr); long sys_vfork(void); void execve_tail(void); -long sys_execve(void); +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp); long sys_sigsuspend(int history0, int history1, old_sigset_t mask); long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index a6f7b20..9aff1d4 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -543,10 +543,10 @@ pgm_svcper: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER llgh %r7,__LC_SVC_INT_CODE # get svc number from lowcore lg %r9,__LC_THREAD_INFO # load pointer to thread_info struct - lg %r1,__TI_task(%r9) - mvc __THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID - mvc __THREAD_per+__PER_address(8,%r1),__LC_PER_ADDRESS - mvc __THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID + lg %r8,__TI_task(%r9) + mvc __THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID + mvc __THREAD_per+__PER_address(8,%r8),__LC_PER_ADDRESS + mvc __THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID oi __TI_flags+7(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP TRACE_IRQS_ON stosm __SF_EMPTY(%r15),0x03 # reenable interrupts diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 57bdcb1..5a82bc6 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -185,9 +185,6 @@ unsigned long prepare_ftrace_return(unsigned long ip, unsigned long parent) { struct ftrace_graph_ent trace; - /* Nmi's are currently unsupported. */ - if (unlikely(in_nmi())) - goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) @@ -206,73 +203,10 @@ out: #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned int sys_call_table[]; -static struct syscall_metadata **syscalls_metadata; - -struct syscall_metadata *syscall_nr_to_meta(int nr) -{ - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -int syscall_name_to_nr(char *name) -{ - int i; - - if (!syscalls_metadata) - return -1; - for (i = 0; i < NR_syscalls; i++) - if (syscalls_metadata[i]) - if (!strcmp(syscalls_metadata[i]->name, name)) - return i; - return -1; -} - -void set_syscall_enter_id(int num, int id) -{ - syscalls_metadata[num]->enter_id = id; -} - -void set_syscall_exit_id(int num, int id) +unsigned long __init arch_syscall_addr(int nr) { - syscalls_metadata[num]->exit_id = id; -} - -static struct syscall_metadata *find_syscall_meta(unsigned long syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup(syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name + 3, str + 3)) - return start; - } - return NULL; -} - -static int __init arch_init_ftrace_syscalls(void) -{ - struct syscall_metadata *meta; - int i; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls, - GFP_KERNEL); - if (!syscalls_metadata) - return -ENOMEM; - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta((unsigned long)sys_call_table[i]); - syscalls_metadata[i] = meta; - } - return 0; + return (unsigned long)sys_call_table[nr]; } -arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/s390/kernel/init_task.c b/arch/s390/kernel/init_task.c index fe787f9..4d1c9fb 100644 --- a/arch/s390/kernel/init_task.c +++ b/arch/s390/kernel/init_task.c @@ -25,9 +25,8 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); * way process stacks are handled. This is done by having a special * "init_task" linker map entry.. */ -union thread_union init_thread_union - __attribute__((__section__(".data.init_task"))) = - { INIT_THREAD_INFO(init_task) }; +union thread_union init_thread_union __init_task_data = + { INIT_THREAD_INFO(init_task) }; /* * Initial task structure. diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index ee57a42..4890ac6 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1595,10 +1595,9 @@ static void stop_run(struct shutdown_trigger *trigger) { if (strcmp(trigger->name, ON_PANIC_STR) == 0) disabled_wait((unsigned long) __builtin_return_address(0)); - else { - signal_processor(smp_processor_id(), sigp_stop); - for (;;); - } + while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy) + cpu_relax(); + for (;;); } static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR, diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index ab2e3ed..639380a 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,6 +55,8 @@ void *module_alloc(unsigned long size) /* Free memory returned from module_alloc */ void module_free(struct module *mod, void *module_region) { + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; vfree(module_region); } @@ -402,6 +404,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { vfree(me->arch.syminfo); + me->arch.syminfo = NULL; return module_bug_finalize(hdr, sechdrs, me); } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 5a43f27..5417eb5 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -27,11 +27,11 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/notifier.h> -#include <linux/utsname.h> #include <linux/tick.h> #include <linux/elfcore.h> #include <linux/kernel_stat.h> #include <linux/syscalls.h> +#include <linux/compat.h> #include <asm/compat.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -230,17 +230,11 @@ SYSCALL_DEFINE0(fork) return do_fork(SIGCHLD, regs->gprs[15], regs, 0, NULL, NULL); } -SYSCALL_DEFINE0(clone) +SYSCALL_DEFINE4(clone, unsigned long, newsp, unsigned long, clone_flags, + int __user *, parent_tidptr, int __user *, child_tidptr) { struct pt_regs *regs = task_pt_regs(current); - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - clone_flags = regs->gprs[3]; - newsp = regs->orig_gpr2; - parent_tidptr = (int __user *) regs->gprs[4]; - child_tidptr = (int __user *) regs->gprs[5]; if (!newsp) newsp = regs->gprs[15]; return do_fork(clone_flags, newsp, regs, 0, @@ -274,30 +268,25 @@ asmlinkage void execve_tail(void) /* * sys_execve() executes a new program. */ -SYSCALL_DEFINE0(execve) +SYSCALL_DEFINE3(execve, char __user *, name, char __user * __user *, argv, + char __user * __user *, envp) { struct pt_regs *regs = task_pt_regs(current); char *filename; - unsigned long result; - int rc; + long rc; - filename = getname((char __user *) regs->orig_gpr2); - if (IS_ERR(filename)) { - result = PTR_ERR(filename); + filename = getname(name); + rc = PTR_ERR(filename); + if (IS_ERR(filename)) + return rc; + rc = do_execve(filename, argv, envp, regs); + if (rc) goto out; - } - rc = do_execve(filename, (char __user * __user *) regs->gprs[3], - (char __user * __user *) regs->gprs[4], regs); - if (rc) { - result = rc; - goto out_putname; - } execve_tail(); - result = regs->gprs[2]; -out_putname: - putname(filename); + rc = regs->gprs[2]; out: - return result; + putname(filename); + return rc; } /* diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 802c8ab..0729f36 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -31,9 +31,9 @@ void __cpuinit print_cpu_info(void) static int show_cpuinfo(struct seq_file *m, void *v) { - static const char *hwcap_str[9] = { + static const char *hwcap_str[10] = { "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", - "edat", "etf3eh" + "edat", "etf3eh", "highgprs" }; struct _lowcore *lc; unsigned long n = (unsigned long) v - 1; @@ -48,7 +48,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) num_online_cpus(), loops_per_jiffy/(500000/HZ), (loops_per_jiffy/(5000/HZ))%100); seq_puts(m, "features\t: "); - for (i = 0; i < 9; i++) + for (i = 0; i < 10; i++) if (hwcap_str[i] && (elf_hwcap & (1UL << i))) seq_printf(m, "%s ", hwcap_str[i]); seq_puts(m, "\n"); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index f3ddd7a..653c6a1 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -57,6 +57,7 @@ enum s390_regset { REGSET_GENERAL, REGSET_FP, + REGSET_GENERAL_EXTENDED, }; static void @@ -339,24 +340,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) int copied, ret; switch (request) { - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - /* Remove high order bit from address (only for 31 bit). */ - addr &= PSW_ADDR_INSN; - /* read word at location addr. */ - return generic_ptrace_peekdata(child, addr, data); - case PTRACE_PEEKUSR: /* read the word at location addr in the USER area. */ return peek_user(child, addr, data); - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - /* Remove high order bit from address (only for 31 bit). */ - addr &= PSW_ADDR_INSN; - /* write the word at location addr. */ - return generic_ptrace_pokedata(child, addr, data); - case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ return poke_user(child, addr, data); @@ -386,8 +373,11 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) copied += sizeof(unsigned long); } return 0; + default: + /* Removing high order bit from addr (only for 31 bit). */ + addr &= PSW_ADDR_INSN; + return ptrace_request(child, request, addr, data); } - return ptrace_request(child, request, addr, data); } #ifdef CONFIG_COMPAT @@ -890,6 +880,67 @@ static int s390_compat_regs_set(struct task_struct *target, return rc; } +static int s390_compat_regs_high_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + compat_ulong_t *gprs_high; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + compat_ulong_t *k = kbuf; + while (count > 0) { + *k++ = *gprs_high; + gprs_high += 2; + count -= sizeof(*k); + } + } else { + compat_ulong_t __user *u = ubuf; + while (count > 0) { + if (__put_user(*gprs_high, u++)) + return -EFAULT; + gprs_high += 2; + count -= sizeof(*u); + } + } + return 0; +} + +static int s390_compat_regs_high_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + compat_ulong_t *gprs_high; + int rc = 0; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count > 0) { + *gprs_high = *k++; + *gprs_high += 2; + count -= sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count > 0 && !rc) { + unsigned long word; + rc = __get_user(word, u++); + if (rc) + break; + *gprs_high = word; + *gprs_high += 2; + count -= sizeof(*u); + } + } + + return rc; +} + static const struct user_regset s390_compat_regsets[] = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, @@ -907,6 +958,14 @@ static const struct user_regset s390_compat_regsets[] = { .get = s390_fpregs_get, .set = s390_fpregs_set, }, + [REGSET_GENERAL_EXTENDED] = { + .core_note_type = NT_PRXSTATUS, + .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_compat_regs_high_get, + .set = s390_compat_regs_high_set, + }, }; static const struct user_regset_view user_s390_compat_view = { diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 20639df..e27ca63 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -24,8 +24,6 @@ LC_EXT_INT_CODE = 0x86 # addr of ext int code # R3 = external interruption parameter if R2=0 # -.section ".init.text","ax" - _sclp_wait_int: stm %r6,%r15,24(%r15) # save registers basr %r13,0 # get base register @@ -318,9 +316,8 @@ _sclp_print_early: .long _sclp_work_area .Lascebc: .long _ascebc -.previous -.section ".init.data","a" +.section .data,"aw",@progbits .balign 4096 _sclp_work_area: .fill 4096 diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 9ed13a1..061479f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -729,7 +729,7 @@ static void __init setup_hwcaps(void) if ((facility_list & (1UL << (31 - 22))) && (facility_list & (1UL << (31 - 30)))) - elf_hwcap |= 1UL << 8; + elf_hwcap |= HWCAP_S390_ETF3EH; /* * Check for additional facilities with store-facility-list-extended. @@ -748,11 +748,20 @@ static void __init setup_hwcaps(void) __stfle(&facility_list_extended, 1) > 0) { if ((facility_list_extended & (1ULL << (63 - 42))) && (facility_list_extended & (1ULL << (63 - 44)))) - elf_hwcap |= 1UL << 6; + elf_hwcap |= HWCAP_S390_DFP; } + /* + * Huge page support HWCAP_S390_HPAGE is bit 7. + */ if (MACHINE_HAS_HPAGE) - elf_hwcap |= 1UL << 7; + elf_hwcap |= HWCAP_S390_HPAGE; + + /* + * 64-bit register support for 31-bit processes + * HWCAP_S390_HIGH_GPRS is bit 9. + */ + elf_hwcap |= HWCAP_S390_HIGH_GPRS; switch (S390_lowcore.cpu_id.machine) { case 0x9672: diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 56c1687..93e5203 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -76,7 +76,6 @@ static int cpu_stopped(int cpu) __u32 status; switch (signal_processor_ps(&status, 0, cpu, sigp_sense)) { - case sigp_order_code_accepted: case sigp_status_stored: /* Check for stopped and check stop state */ if (status & 0x50) @@ -147,11 +146,11 @@ static void smp_ext_bitcall(int cpu, ec_bit_sig sig) udelay(10); } -void arch_send_call_function_ipi(cpumask_t mask) +void arch_send_call_function_ipi_mask(const struct cpumask *mask) { int cpu; - for_each_cpu_mask(cpu, mask) + for_each_cpu(cpu, mask) smp_ext_bitcall(cpu, ec_call_function); } @@ -475,10 +474,8 @@ static int __cpuinit smp_alloc_lowcore(int cpu) { unsigned long async_stack, panic_stack; struct _lowcore *lowcore; - int lc_order; - lc_order = sizeof(long) == 8 ? 1 : 0; - lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order); + lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); if (!lowcore) return -ENOMEM; async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); @@ -509,16 +506,14 @@ static int __cpuinit smp_alloc_lowcore(int cpu) out: free_page(panic_stack); free_pages(async_stack, ASYNC_ORDER); - free_pages((unsigned long) lowcore, lc_order); + free_pages((unsigned long) lowcore, LC_ORDER); return -ENOMEM; } static void smp_free_lowcore(int cpu) { struct _lowcore *lowcore; - int lc_order; - lc_order = sizeof(long) == 8 ? 1 : 0; lowcore = lowcore_ptr[cpu]; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) @@ -528,7 +523,7 @@ static void smp_free_lowcore(int cpu) #endif free_page(lowcore->panic_stack - PAGE_SIZE); free_pages(lowcore->async_stack - ASYNC_SIZE, ASYNC_ORDER); - free_pages((unsigned long) lowcore, lc_order); + free_pages((unsigned long) lowcore, LC_ORDER); lowcore_ptr[cpu] = NULL; } @@ -642,6 +637,8 @@ void __cpu_die(unsigned int cpu) /* Wait until target cpu is down */ while (!cpu_stopped(cpu)) cpu_relax(); + while (signal_processor_p(0, cpu, sigp_set_prefix) == sigp_busy) + udelay(10); smp_free_lowcore(cpu); pr_info("Processor %d stopped\n", cpu); } @@ -649,8 +646,8 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { idle_task_exit(); - signal_processor(smp_processor_id(), sigp_stop); - BUG(); + while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy) + cpu_relax(); for (;;); } @@ -664,7 +661,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) unsigned long async_stack, panic_stack; struct _lowcore *lowcore; unsigned int cpu; - int lc_order; smp_detect_cpus(); @@ -674,8 +670,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) print_cpu_info(); /* Reallocate current lowcore, but keep its contents. */ - lc_order = sizeof(long) == 8 ? 1 : 0; - lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order); + lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); panic_stack = __get_free_page(GFP_KERNEL); async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); BUG_ON(!lowcore || !panic_stack || !async_stack); @@ -1047,42 +1042,6 @@ out: static SYSDEV_CLASS_ATTR(dispatching, 0644, dispatching_show, dispatching_store); -/* - * If the resume kernel runs on another cpu than the suspended kernel, - * we have to switch the cpu IDs in the logical map. - */ -void smp_switch_boot_cpu_in_resume(u32 resume_phys_cpu_id, - struct _lowcore *suspend_lowcore) -{ - int cpu, suspend_cpu_id, resume_cpu_id; - u32 suspend_phys_cpu_id; - - suspend_phys_cpu_id = __cpu_logical_map[suspend_lowcore->cpu_nr]; - suspend_cpu_id = suspend_lowcore->cpu_nr; - - for_each_present_cpu(cpu) { - if (__cpu_logical_map[cpu] == resume_phys_cpu_id) { - resume_cpu_id = cpu; - goto found; - } - } - panic("Could not find resume cpu in logical map.\n"); - -found: - printk("Resume cpu ID: %i/%i\n", resume_phys_cpu_id, resume_cpu_id); - printk("Suspend cpu ID: %i/%i\n", suspend_phys_cpu_id, suspend_cpu_id); - - __cpu_logical_map[resume_cpu_id] = suspend_phys_cpu_id; - __cpu_logical_map[suspend_cpu_id] = resume_phys_cpu_id; - - lowcore_ptr[suspend_cpu_id]->cpu_addr = resume_phys_cpu_id; -} - -u32 smp_get_phys_cpu_id(void) -{ - return __cpu_logical_map[smp_processor_id()]; -} - static int __init topology_init(void) { int cpu; diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index 086bee9..cf9e5c6 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -6,36 +6,26 @@ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com> */ -#include <linux/suspend.h> -#include <linux/reboot.h> #include <linux/pfn.h> -#include <linux/mm.h> -#include <asm/sections.h> #include <asm/system.h> -#include <asm/ipl.h> /* * References to section boundaries */ extern const void __nosave_begin, __nosave_end; -/* - * check if given pfn is in the 'nosave' or in the read only NSS section - */ int pfn_is_nosave(unsigned long pfn) { - unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT; - unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) - >> PAGE_SHIFT; - unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1; - unsigned long stext_pfn = PFN_DOWN(__pa(&_stext)); + unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); + unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end)); + /* Always save lowcore pages (LC protection might be enabled). */ + if (pfn <= LC_PAGES) + return 0; if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn) return 1; - if (pfn >= stext_pfn && pfn <= eshared_pfn) { - if (ipl_info.type == IPL_TYPE_NSS) - return 1; - } else if ((tprot(pfn * PAGE_SIZE) && pfn > 0)) + /* Skip memory holes and read-only pages (NSS, DCSS, ...). */ + if (tprot(PFN_PHYS(pfn))) return 1; return 0; } diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index 7cd6b09..0c26cc1 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -9,6 +9,7 @@ #include <asm/page.h> #include <asm/ptrace.h> +#include <asm/thread_info.h> #include <asm/asm-offsets.h> /* @@ -41,6 +42,9 @@ swsusp_arch_suspend: /* Get pointer to save area */ lghi %r1,0x1000 + /* Save CPU address */ + stap __LC_CPU_ADDRESS(%r0) + /* Store registers */ mvc 0x318(4,%r1),__SF_EMPTY(%r15) /* move prefix to lowcore */ stfpc 0x31c(%r1) /* store fpu control */ @@ -65,8 +69,21 @@ swsusp_arch_suspend: stmg %r0,%r15,0x280(%r1) /* store general registers */ stpt 0x328(%r1) /* store timer */ + stck __SF_EMPTY(%r15) /* store clock */ stckc 0x330(%r1) /* store clock comparator */ + /* Update cputime accounting before going to sleep */ + lg %r0,__LC_LAST_UPDATE_TIMER + slg %r0,0x328(%r1) + alg %r0,__LC_SYSTEM_TIMER + stg %r0,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),0x328(%r1) + lg %r0,__LC_LAST_UPDATE_CLOCK + slg %r0,__SF_EMPTY(%r15) + alg %r0,__LC_STEAL_TIMER + stg %r0,__LC_STEAL_TIMER + mvc __LC_LAST_UPDATE_CLOCK(8),__SF_EMPTY(%r15) + /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 @@ -102,11 +119,10 @@ swsusp_arch_resume: aghi %r15,-STACK_FRAME_OVERHEAD stg %r1,__SF_BACKCHAIN(%r15) -#ifdef CONFIG_SMP - /* Save boot cpu number */ - brasl %r14,smp_get_phys_cpu_id - lgr %r10,%r2 -#endif + /* Make all free pages stable */ + lghi %r2,1 + brasl %r14,arch_set_page_states + /* Deactivate DAT */ stnsm __SF_EMPTY(%r15),0xfb @@ -133,9 +149,76 @@ swsusp_arch_resume: 2: ptlb /* flush tlb */ + /* Reset System */ + larl %r1,restart_entry + larl %r2,.Lrestart_diag308_psw + og %r1,0(%r2) + stg %r1,0(%r0) + larl %r1,.Lnew_pgm_check_psw + epsw %r2,%r3 + stm %r2,%r3,0(%r1) + mvc __LC_PGM_NEW_PSW(16,%r0),0(%r1) + lghi %r0,0 + diag %r0,%r0,0x308 +restart_entry: + lhi %r1,1 + sigp %r1,%r0,0x12 + sam64 + larl %r1,.Lnew_pgm_check_psw + lpswe 0(%r1) +pgm_check_entry: + + /* Switch to original suspend CPU */ + larl %r1,.Lresume_cpu /* Resume CPU address: r2 */ + stap 0(%r1) + llgh %r2,0(%r1) + llgh %r1,__LC_CPU_ADDRESS(%r0) /* Suspend CPU address: r1 */ + cgr %r1,%r2 + je restore_registers /* r1 = r2 -> nothing to do */ + larl %r4,.Lrestart_suspend_psw /* Set new restart PSW */ + mvc __LC_RESTART_PSW(16,%r0),0(%r4) +3: + sigp %r9,%r1,__SIGP_INITIAL_CPU_RESET + brc 8,4f /* accepted */ + brc 2,3b /* busy, try again */ + + /* Suspend CPU not available -> panic */ + larl %r15,init_thread_union + ahi %r15,1<<(PAGE_SHIFT+THREAD_ORDER) + larl %r2,.Lpanic_string + larl %r3,_sclp_print_early + lghi %r1,0 + sam31 + sigp %r1,%r0,0x12 + basr %r14,%r3 + larl %r3,.Ldisabled_wait_31 + lpsw 0(%r3) +4: + /* Switch to suspend CPU */ + sigp %r9,%r1,__SIGP_RESTART /* start suspend CPU */ + brc 2,4b /* busy, try again */ +5: + sigp %r9,%r2,__SIGP_STOP /* stop resume (current) CPU */ + brc 2,5b /* busy, try again */ +6: j 6b + +restart_suspend: + larl %r1,.Lresume_cpu + llgh %r2,0(%r1) +7: + sigp %r9,%r2,__SIGP_SENSE /* Wait for resume CPU */ + brc 8,7b /* accepted, status 0, still running */ + brc 2,7b /* busy, try again */ + tmll %r9,0x40 /* Test if resume CPU is stopped */ + jz 7b + +restore_registers: /* Restore registers */ - lghi %r13,0x1000 /* %r1 = pointer to save arae */ + lghi %r13,0x1000 /* %r1 = pointer to save area */ + /* Ignore time spent in suspended state. */ + llgf %r1,0x318(%r13) + stck __LC_LAST_UPDATE_CLOCK(%r1) spt 0x328(%r13) /* reprogram timer */ //sckc 0x330(%r13) /* set clock comparator */ @@ -163,22 +246,33 @@ swsusp_arch_resume: /* Load old stack */ lg %r15,0x2f8(%r13) - /* Pointer to save area */ - lghi %r13,0x1000 - -#ifdef CONFIG_SMP - /* Switch CPUs */ - lgr %r2,%r10 /* get cpu id */ - llgf %r3,0x318(%r13) - brasl %r14,smp_switch_boot_cpu_in_resume -#endif /* Restore prefix register */ spx 0x318(%r13) /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 + /* Make all free pages unstable */ + lghi %r2,0 + brasl %r14,arch_set_page_states + /* Return 0 */ lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) lghi %r2,0 br %r14 + + .section .data.nosave,"aw",@progbits + .align 8 +.Ldisabled_wait_31: + .long 0x000a0000,0x00000000 +.Lpanic_string: + .asciz "Resume not possible because suspend CPU is no longer available" + .align 8 +.Lrestart_diag308_psw: + .long 0x00080000,0x80000000 +.Lrestart_suspend_psw: + .quad 0x0000000180000000,restart_suspend +.Lnew_pgm_check_psw: + .quad 0,pgm_check_entry +.Lresume_cpu: + .byte 0,0 diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index c7ae4b1..e9d94f6 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -29,7 +29,6 @@ #include <linux/personality.h> #include <linux/unistd.h> #include <linux/ipc.h> -#include <linux/syscalls.h> #include <asm/uaccess.h> #include "entry.h" diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index ad1acd2..30eca07 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -19,7 +19,7 @@ SYSCALL(sys_restart_syscall,sys_restart_syscall,sys_restart_syscall) SYSCALL(sys_creat,sys_creat,sys32_creat_wrapper) SYSCALL(sys_link,sys_link,sys32_link_wrapper) SYSCALL(sys_unlink,sys_unlink,sys32_unlink_wrapper) /* 10 */ -SYSCALL(sys_execve,sys_execve,sys32_execve) +SYSCALL(sys_execve,sys_execve,sys32_execve_wrapper) SYSCALL(sys_chdir,sys_chdir,sys32_chdir_wrapper) SYSCALL(sys_time,sys_ni_syscall,sys32_time_wrapper) /* old time syscall */ SYSCALL(sys_mknod,sys_mknod,sys32_mknod_wrapper) @@ -128,7 +128,7 @@ SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) SYSCALL(sys_ipc,sys_ipc,sys32_ipc_wrapper) SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) -SYSCALL(sys_clone,sys_clone,sys32_clone) /* 120 */ +SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) SYSCALL(sys_newuname,sys_s390_newuname,sys32_newuname_wrapper) NI_SYSCALL /* modify_ldt for i386 */ @@ -136,8 +136,8 @@ SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask_wrapper) NI_SYSCALL /* old "create module" */ -SYSCALL(sys_init_module,sys_init_module,sys32_init_module_wrapper) -SYSCALL(sys_delete_module,sys_delete_module,sys32_delete_module_wrapper) +SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper) +SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper) NI_SYSCALL /* 130: old get_kernel_syms */ SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper) SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper) @@ -339,4 +339,4 @@ SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper) SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv_wrapper) SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev_wrapper) SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo_wrapper) /* 330 */ -SYSCALL(sys_perf_counter_open,sys_perf_counter_open,sys_perf_counter_open_wrapper) +SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 54e327e..34162a0 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -91,6 +91,7 @@ void tod_to_timeval(__u64 todval, struct timespec *xtime) todval -= (sec * 1000000) << 12; xtime->tv_nsec = ((todval * 1000) >> 12); } +EXPORT_SYMBOL(tod_to_timeval); void clock_comparator_work(void) { @@ -183,12 +184,14 @@ static void timing_alert_interrupt(__u16 code) static void etr_reset(void); static void stp_reset(void); -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - struct timespec ts; + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); +} - tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, &ts); - return ts.tv_sec; +void read_boot_clock(struct timespec *ts) +{ + tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts); } static cycle_t read_tod_clock(struct clocksource *cs) @@ -206,6 +209,10 @@ static struct clocksource clocksource_tod = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +struct clocksource * __init clocksource_default_clock(void) +{ + return &clocksource_tod; +} void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) { @@ -243,10 +250,6 @@ void update_vsyscall_tz(void) */ void __init time_init(void) { - struct timespec ts; - unsigned long flags; - cycle_t now; - /* Reset time synchronization interfaces. */ etr_reset(); stp_reset(); @@ -262,26 +265,6 @@ void __init time_init(void) if (clocksource_register(&clocksource_tod) != 0) panic("Could not register TOD clock source"); - /* - * The TOD clock is an accurate clock. The xtime should be - * initialized in a way that the difference between TOD and - * xtime is reasonably small. Too bad that timekeeping_init - * sets xtime.tv_nsec to zero. In addition the clock source - * change from the jiffies clock source to the TOD clock - * source add another error of up to 1/HZ second. The same - * function sets wall_to_monotonic to a value that is too - * small for /proc/uptime to be accurate. - * Reset xtime and wall_to_monotonic to sane values. - */ - write_seqlock_irqsave(&xtime_lock, flags); - now = get_clock(); - tod_to_timeval(now - TOD_UNIX_EPOCH, &xtime); - clocksource_tod.cycle_last = now; - clocksource_tod.raw_time = xtime; - tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &ts); - set_normalized_timespec(&wall_to_monotonic, -ts.tv_sec, -ts.tv_nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); - /* Enable TOD clock interrupts on the boot cpu. */ init_cpu_timer(); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 45e1708..adfb32a 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -75,7 +75,7 @@ __setup("vdso=", vdso_setup); static union { struct vdso_data data; u8 page[PAGE_SIZE]; -} vdso_data_store __attribute__((__section__(".data.page_aligned"))); +} vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; /* @@ -247,6 +247,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) } /* + * Put vDSO base into mm struct. We need to do this before calling + * install_special_mapping or the perf counter mmap tracking code + * will fail to recognise it as a vDSO (since arch_vma_name fails). + */ + current->mm->context.vdso_base = vdso_base; + + /* * our vma flags don't have VM_WRITE so by default, the process * isn't allowed to write those pages. * gdb can break that with ptrace interface, and thus trigger COW @@ -267,14 +274,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) VM_ALWAYSDUMP, vdso_pagelist); if (rc) - goto out_up; - - /* Put vDSO base into mm struct */ - current->mm->context.vdso_base = vdso_base; - - up_write(&mm->mmap_sem); - return 0; - + current->mm->context.vdso_base = 0; out_up: up_write(&mm->mmap_sem); return rc; diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index ca78ad6..d13e875 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -13,7 +13,7 @@ KBUILD_AFLAGS_31 += -m31 -s KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ - $(call ld-option, -Wl$(comma)--hash-style=sysv) + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31) diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S index 61639a8..ae42f8c 100644 --- a/arch/s390/kernel/vdso32/vdso32_wrapper.S +++ b/arch/s390/kernel/vdso32/vdso32_wrapper.S @@ -1,7 +1,8 @@ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/page.h> - .section ".data.page_aligned" + __PAGE_ALIGNED_DATA .globl vdso32_start, vdso32_end .balign PAGE_SIZE diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 6fc8e82..449352d 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -13,7 +13,7 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ - $(call ld-option, -Wl$(comma)--hash-style=sysv) + $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64) diff --git a/arch/s390/kernel/vdso64/vdso64_wrapper.S b/arch/s390/kernel/vdso64/vdso64_wrapper.S index d8e2ac1..c245842 100644 --- a/arch/s390/kernel/vdso64/vdso64_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso64_wrapper.S @@ -1,7 +1,8 @@ #include <linux/init.h> +#include <linux/linkage.h> #include <asm/page.h> - .section ".data.page_aligned" + __PAGE_ALIGNED_DATA .globl vdso64_start, vdso64_end .balign PAGE_SIZE diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 7315f9e..a68ac10 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -51,6 +51,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); _eshared = .; /* End of shareable data */ + _sdata = .; /* Start of data section */ EXCEPTION_TABLE(16) :data @@ -84,13 +85,10 @@ SECTIONS _end = . ; - /* Sections to be discarded */ - /DISCARD/ : { - EXIT_DATA - *(.exitcall.exit) - } - /* Debugging sections. */ STABS_DEBUG DWARF_DEBUG + + /* Sections to be discarded */ + DISCARDS } diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 3e260b7..bf164fc 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -1,11 +1,7 @@ # # KVM configuration # -config HAVE_KVM - bool - -config HAVE_KVM_IRQCHIP - bool +source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION bool "Virtualization" @@ -38,9 +34,6 @@ config KVM If unsure, say N. -config KVM_TRACE - bool - # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/virtio/Kconfig diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index ed60f3a..03c716a 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,7 +1,7 @@ /* * gaccess.h - access guest memory * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * 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) @@ -16,13 +16,14 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/uaccess.h> +#include "kvm-s390.h" 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->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestaddr < 2 * PAGE_SIZE) guestaddr += prefix; @@ -158,8 +159,8 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest, const void *from, unsigned long n) { unsigned long prefix = vcpu->arch.sie_block->prefix; - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + 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; @@ -209,8 +210,8 @@ 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; - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) goto slowpath; @@ -244,8 +245,8 @@ static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, unsigned long guestdest, const void *from, unsigned long n) { - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestdest + n > memsize) return -EFAULT; @@ -262,8 +263,8 @@ static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to, unsigned long guestsrc, unsigned long n) { - unsigned long origin = vcpu->kvm->arch.guest_origin; - unsigned long memsize = vcpu->kvm->arch.guest_memsize; + unsigned long origin = vcpu->arch.sie_block->gmsor; + unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu); if (guestsrc + n > memsize) return -EFAULT; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 98997cc..ba9d8a7 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -1,7 +1,7 @@ /* * intercept.c - in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * 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) @@ -128,7 +128,7 @@ static int handle_noop(struct kvm_vcpu *vcpu) static int handle_stop(struct kvm_vcpu *vcpu) { - int rc; + int rc = 0; vcpu->stat.exit_stop_request++; atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); @@ -141,12 +141,18 @@ static int handle_stop(struct kvm_vcpu *vcpu) rc = -ENOTSUPP; } + if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) { + vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP; + rc = SIE_INTERCEPT_RERUNVCPU; + vcpu->run->exit_reason = KVM_EXIT_INTR; + } + if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) { vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP; VCPU_EVENT(vcpu, 3, "%s", "cpu stopped"); rc = -ENOTSUPP; - } else - rc = 0; + } + spin_unlock_bh(&vcpu->arch.local_int.lock); return rc; } @@ -158,9 +164,9 @@ static int handle_validity(struct kvm_vcpu *vcpu) vcpu->stat.exit_validity++; if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix - <= vcpu->kvm->arch.guest_memsize - 2*PAGE_SIZE)){ + <= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) { rc = fault_in_pages_writeable((char __user *) - vcpu->kvm->arch.guest_origin + + vcpu->arch.sie_block->gmsor + vcpu->arch.sie_block->prefix, 2*PAGE_SIZE); if (rc) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 4d61341..43486c2 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -283,7 +283,7 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu) return 1; } -int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) +static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; @@ -320,12 +320,6 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) return rc; } -int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) -{ - /* do real check here */ - return 1; -} - int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return 0; @@ -484,7 +478,7 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) if (!inti) return -ENOMEM; - inti->type = KVM_S390_PROGRAM_INT;; + inti->type = KVM_S390_PROGRAM_INT; inti->pgm.code = code; VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 90d9d1b..07ced89 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1,7 +1,7 @@ /* * s390host.c -- hosting zSeries kernel virtual machines * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * 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) @@ -10,6 +10,7 @@ * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> * Heiko Carstens <heiko.carstens@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> */ #include <linux/compiler.h> @@ -210,13 +211,17 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { unsigned int i; + struct kvm_vcpu *vcpu; - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_arch_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_arch_vcpu_destroy(vcpu); + + mutex_lock(&kvm->lock); + for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) + kvm->vcpus[i] = NULL; + + atomic_set(&kvm->online_vcpus, 0); + mutex_unlock(&kvm->lock); } void kvm_arch_sync_events(struct kvm *kvm) @@ -278,16 +283,10 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->gbea = 1; } -/* The current code can have up to 256 pages for virtio */ -#define VIRTIODESCSPACE (256ul * 4096ul) - int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH); - vcpu->arch.sie_block->gmslm = vcpu->kvm->arch.guest_memsize + - vcpu->kvm->arch.guest_origin + - VIRTIODESCSPACE - 1ul; - vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin; + set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests); vcpu->arch.sie_block->ecb = 2; vcpu->arch.sie_block->eca = 0xC1002001U; vcpu->arch.sie_block->fac = (int) (long) facilities; @@ -319,8 +318,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, BUG_ON(!kvm->arch.sca); if (!kvm->arch.sca->cpu[id].sda) kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block; - else - BUG_ON(!kvm->vcpus[id]); /* vcpu does already exist */ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32); vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; @@ -490,9 +487,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu_load(vcpu); +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->kvm->arch.guest_memsize) { + if (!vcpu->arch.sie_block->gmslm) { vcpu_put(vcpu); + VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu"); return -EINVAL; } @@ -509,6 +512,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr; break; case KVM_EXIT_UNKNOWN: + case KVM_EXIT_INTR: case KVM_EXIT_S390_RESET: break; default: @@ -522,8 +526,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) rc = kvm_handle_sie_intercept(vcpu); } while (!signal_pending(current) && !rc); - if (signal_pending(current) && !rc) + if (rc == SIE_INTERCEPT_RERUNVCPU) + goto rerun_vcpu; + + if (signal_pending(current) && !rc) { + kvm_run->exit_reason = KVM_EXIT_INTR; rc = -EINTR; + } if (rc == -ENOTSUPP) { /* intercept cannot be handled in-kernel, prepare kvm-run */ @@ -676,6 +685,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm, int user_alloc) { int i; + struct kvm_vcpu *vcpu; /* A few sanity checks. We can have exactly one memory slot which has to start at guest virtual zero and which has to be located at a @@ -684,7 +694,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm, vmas. It is okay to mmap() and munmap() stuff in this slot after doing this call at any time */ - if (mem->slot || kvm->arch.guest_memsize) + if (mem->slot) return -EINVAL; if (mem->guest_phys_addr) @@ -699,36 +709,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (!user_alloc) return -EINVAL; - /* lock all vcpus */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (!kvm->vcpus[i]) + /* 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; - if (!mutex_trylock(&kvm->vcpus[i]->mutex)) - goto fail_out; - } - - kvm->arch.guest_origin = mem->userspace_addr; - kvm->arch.guest_memsize = mem->memory_size; - - /* update sie control blocks, and unlock all vcpus */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm->vcpus[i]->arch.sie_block->gmsor = - kvm->arch.guest_origin; - kvm->vcpus[i]->arch.sie_block->gmslm = - kvm->arch.guest_memsize + - kvm->arch.guest_origin + - VIRTIODESCSPACE - 1ul; - mutex_unlock(&kvm->vcpus[i]->mutex); - } + kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP); } return 0; - -fail_out: - for (; i >= 0; i--) - mutex_unlock(&kvm->vcpus[i]->mutex); - return -EINVAL; } 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 748fee8..06cce82 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -1,7 +1,7 @@ /* * kvm_s390.h - definition for kvm on s390 * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * 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) @@ -9,6 +9,7 @@ * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> */ #ifndef ARCH_S390_KVM_S390_H @@ -18,8 +19,13 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> +/* The current code can have up to 256 pages for virtio */ +#define VIRTIODESCSPACE (256ul * 4096ul) + typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); +/* negativ values are error codes, positive values for internal conditions */ +#define SIE_INTERCEPT_RERUNVCPU (1<<0) int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ @@ -50,6 +56,30 @@ int kvm_s390_inject_vm(struct kvm *kvm, int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt *s390int); 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) +{ + struct kvm_memory_slot *mem; + + down_read(&vcpu->kvm->slots_lock); + mem = &vcpu->kvm->memslots[0]; + + vcpu->arch.sie_block->gmsor = mem->userspace_addr; + vcpu->arch.sie_block->gmslm = + mem->userspace_addr + + (mem->npages << PAGE_SHIFT) + + VIRTIODESCSPACE - 1ul; + + up_read(&vcpu->kvm->slots_lock); +} /* implemented in priv.c */ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 0ef81d6..40c8c67 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -1,7 +1,7 @@ /* * sigp.c - handlinge interprocessor communication * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2009 * * 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) @@ -9,6 +9,7 @@ * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> */ #include <linux/kvm.h> @@ -107,46 +108,57 @@ unlock: return rc; } -static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store) +static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action) { - 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_SIGP_STOP; - 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_STOP_INT, li->cpuflags); - if (store) - li->action_bits |= ACTION_STORE_ON_STOP; - li->action_bits |= ACTION_STOP_ON_STOP; + li->action_bits |= action; if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - rc = 0; /* order accepted */ + + return 0; /* order accepted */ +} + +static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_local_interrupt *li; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + spin_lock(&fi->lock); + li = fi->local_int[cpu_addr]; + if (li == NULL) { + rc = 3; /* not operational */ + goto unlock; + } + + rc = __inject_sigp_stop(li, action); + unlock: spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr); return rc; } +int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + return __inject_sigp_stop(li, action); +} + static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) { int rc; @@ -177,9 +189,9 @@ 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_guest(vcpu, &tmp, - (u64) (address + vcpu->kvm->arch.guest_origin) , 1)) || + (u64) (address + vcpu->arch.sie_block->gmsor) , 1)) || (copy_from_guest(vcpu, &tmp, (u64) (address + - vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) { + vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) { *reg |= SIGP_STAT_INVALID_PARAMETER; return 1; /* invalid parameter */ } @@ -262,11 +274,11 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) break; case SIGP_STOP: vcpu->stat.instruction_sigp_stop++; - rc = __sigp_stop(vcpu, cpu_addr, 0); + rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP); break; case SIGP_STOP_STORE_STATUS: vcpu->stat.instruction_sigp_stop++; - rc = __sigp_stop(vcpu, cpu_addr, 1); + rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP); break; case SIGP_SET_ARCH: vcpu->stat.instruction_sigp_arch++; diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 97c1eca8..752b362 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -25,13 +25,13 @@ void __delay(unsigned long loops) asm volatile("0: brct %0,0b" : : "d" ((loops/2) + 1)); } -static void __udelay_disabled(unsigned long usecs) +static void __udelay_disabled(unsigned long long usecs) { unsigned long mask, cr0, cr0_saved; u64 clock_saved; clock_saved = local_tick_disable(); - set_clock_comparator(get_clock() + ((u64) usecs << 12)); + set_clock_comparator(get_clock() + (usecs << 12)); __ctl_store(cr0_saved, 0, 0); cr0 = (cr0_saved & 0xffff00e0) | 0x00000800; __ctl_load(cr0 , 0, 0); @@ -46,20 +46,25 @@ static void __udelay_disabled(unsigned long usecs) set_clock_comparator(S390_lowcore.clock_comparator); } -static void __udelay_enabled(unsigned long usecs) +static void __udelay_enabled(unsigned long long usecs) { unsigned long mask; - u64 end, time; + u64 clock_saved; + u64 end; mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT | PSW_MASK_IO; - end = get_clock() + ((u64) usecs << 12); + end = get_clock() + (usecs << 12); do { - time = end < S390_lowcore.clock_comparator ? - end : S390_lowcore.clock_comparator; - set_clock_comparator(time); + clock_saved = 0; + if (end < S390_lowcore.clock_comparator) { + clock_saved = local_tick_disable(); + set_clock_comparator(end); + } trace_hardirqs_on(); __load_psw_mask(mask); local_irq_disable(); + if (clock_saved) + local_tick_enable(clock_saved); } while (get_clock() < end); set_clock_comparator(S390_lowcore.clock_comparator); } @@ -67,7 +72,7 @@ static void __udelay_enabled(unsigned long usecs) /* * Waits for 'usecs' microseconds using the TOD clock comparator. */ -void __udelay(unsigned long usecs) +void __udelay(unsigned long long usecs) { unsigned long flags; @@ -101,11 +106,11 @@ EXPORT_SYMBOL(__udelay); * Simple udelay variant. To be used on startup and reboot * when the interrupt handler isn't working. */ -void udelay_simple(unsigned long usecs) +void udelay_simple(unsigned long long usecs) { u64 end; - end = get_clock() + ((u64) usecs << 12); + end = get_clock() + (usecs << 12); while (get_clock() < end) cpu_relax(); } diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 3f15aaf..58da3f4 100644 --- a/arch/s390/lib/uaccess_mvcos.c +++ b/arch/s390/lib/uaccess_mvcos.c @@ -36,7 +36,7 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) tmp1 = -4096UL; asm volatile( "0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n" - " jz 7f\n" + "9: jz 7f\n" "1:"ALR" %0,%3\n" " "SLR" %1,%3\n" " "SLR" %2,%3\n" @@ -47,7 +47,7 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 4f\n" "3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n" - " "SLR" %0,%4\n" + "10:"SLR" %0,%4\n" " "ALR" %2,%4\n" "4:"LHI" %4,-1\n" " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */ @@ -61,7 +61,7 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) " j 8f\n" "7:"SLR" %0,%0\n" "8: \n" - EX_TABLE(0b,2b) EX_TABLE(3b,4b) + EX_TABLE(0b,2b) EX_TABLE(3b,4b) EX_TABLE(9b,2b) EX_TABLE(10b,4b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : "d" (reg0) : "cc", "memory"); return size; @@ -82,7 +82,7 @@ static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x) tmp1 = -4096UL; asm volatile( "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n" - " jz 4f\n" + "6: jz 4f\n" "1:"ALR" %0,%3\n" " "SLR" %1,%3\n" " "SLR" %2,%3\n" @@ -93,11 +93,11 @@ static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 5f\n" "3: .insn ss,0xc80000000000,0(%4,%1),0(%2),0\n" - " "SLR" %0,%4\n" + "7:"SLR" %0,%4\n" " j 5f\n" "4:"SLR" %0,%0\n" "5: \n" - EX_TABLE(0b,2b) EX_TABLE(3b,5b) + EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : "d" (reg0) : "cc", "memory"); return size; diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index d2ffbad..07deaee 100644 --- a/arch/s390/lib/uaccess_std.c +++ b/arch/s390/lib/uaccess_std.c @@ -36,12 +36,12 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) tmp1 = -256UL; asm volatile( "0: mvcp 0(%0,%2),0(%1),%3\n" - " jz 8f\n" + "10:jz 8f\n" "1:"ALR" %0,%3\n" " la %1,256(%1)\n" " la %2,256(%2)\n" "2: mvcp 0(%0,%2),0(%1),%3\n" - " jnz 1b\n" + "11:jnz 1b\n" " j 8f\n" "3: la %4,255(%1)\n" /* %4 = ptr + 255 */ " "LHI" %3,-4096\n" @@ -50,7 +50,7 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 5f\n" "4: mvcp 0(%4,%2),0(%1),%3\n" - " "SLR" %0,%4\n" + "12:"SLR" %0,%4\n" " "ALR" %2,%4\n" "5:"LHI" %4,-1\n" " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */ @@ -65,6 +65,7 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) "8:"SLR" %0,%0\n" "9: \n" EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,5b) + EX_TABLE(10b,3b) EX_TABLE(11b,3b) EX_TABLE(12b,5b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : : "cc", "memory"); return size; @@ -85,12 +86,12 @@ size_t copy_to_user_std(size_t size, void __user *ptr, const void *x) tmp1 = -256UL; asm volatile( "0: mvcs 0(%0,%1),0(%2),%3\n" - " jz 5f\n" + "7: jz 5f\n" "1:"ALR" %0,%3\n" " la %1,256(%1)\n" " la %2,256(%2)\n" "2: mvcs 0(%0,%1),0(%2),%3\n" - " jnz 1b\n" + "8: jnz 1b\n" " j 5f\n" "3: la %4,255(%1)\n" /* %4 = ptr + 255 */ " "LHI" %3,-4096\n" @@ -99,11 +100,12 @@ size_t copy_to_user_std(size_t size, void __user *ptr, const void *x) " "CLR" %0,%4\n" /* copy crosses next page boundary? */ " jnh 6f\n" "4: mvcs 0(%4,%1),0(%2),%3\n" - " "SLR" %0,%4\n" + "9:"SLR" %0,%4\n" " j 6f\n" "5:"SLR" %0,%0\n" "6: \n" EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,6b) + EX_TABLE(7b,3b) EX_TABLE(8b,3b) EX_TABLE(9b,6b) : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2) : : "cc", "memory"); return size; diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 413c240..b201135 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -262,7 +262,7 @@ cmm_skip_blanks(char *cp, char **endp) static struct ctl_table cmm_table[]; static int -cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, +cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[16], *p; @@ -303,7 +303,7 @@ cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, } static int -cmm_timeout_handler(ctl_table *ctl, int write, struct file *filp, +cmm_timeout_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[64], *p; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 1abbadd..6d50746 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -10,7 +10,7 @@ * Copyright (C) 1995 Linus Torvalds */ -#include <linux/perf_counter.h> +#include <linux/perf_event.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -306,7 +306,7 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int write) * interrupts again and then search the VMAs */ local_irq_enable(); - perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); down_read(&mm->mmap_sem); si_code = SEGV_MAPERR; @@ -366,11 +366,11 @@ good_area: } if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; - perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, regs, address); } else { tsk->min_flt++; - perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, regs, address); } up_read(&mm->mmap_sem); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c634dfb..7656479 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -105,7 +105,7 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n", - (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), + nr_free_pages() << (PAGE_SHIFT-10), max_mapnr << (PAGE_SHIFT-10), codesize >> 10, reservedpages << (PAGE_SHIFT-10), diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index f92ec20..098923a 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -50,28 +50,64 @@ void __init cmma_init(void) cmma_flag = 0; } -void arch_free_page(struct page *page, int order) +static inline void set_page_unstable(struct page *page, int order) { int i, rc; - if (!cmma_flag) - return; for (i = 0; i < (1 << order); i++) asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" : "=&d" (rc) - : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT), + : "a" (page_to_phys(page + i)), "i" (ESSA_SET_UNUSED)); } -void arch_alloc_page(struct page *page, int order) +void arch_free_page(struct page *page, int order) { - int i, rc; - if (!cmma_flag) return; + set_page_unstable(page, order); +} + +static inline void set_page_stable(struct page *page, int order) +{ + int i, rc; + for (i = 0; i < (1 << order); i++) asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" : "=&d" (rc) - : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT), + : "a" (page_to_phys(page + i)), "i" (ESSA_SET_STABLE)); } + +void arch_alloc_page(struct page *page, int order) +{ + if (!cmma_flag) + return; + set_page_stable(page, order); +} + +void arch_set_page_states(int make_stable) +{ + unsigned long flags, order, t; + struct list_head *l; + struct page *page; + struct zone *zone; + + if (!cmma_flag) + return; + if (make_stable) + drain_local_pages(NULL); + for_each_populated_zone(zone) { + spin_lock_irqsave(&zone->lock, flags); + for_each_migratetype_order(order, t) { + list_for_each(l, &zone->free_area[order].free_list[t]) { + page = list_entry(l, struct page, lru); + if (make_stable) + set_page_stable(page, order); + else + set_page_unstable(page, order); + } + } + spin_unlock_irqrestore(&zone->lock, flags); + } +} diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index c702152..2757c56 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -279,7 +279,10 @@ int s390_enable_sie(void) /* lets check if we are allowed to replace the mm */ task_lock(tsk); if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || - tsk->mm != tsk->active_mm || !hlist_empty(&tsk->mm->ioctx_list)) { +#ifdef CONFIG_AIO + !hlist_empty(&tsk->mm->ioctx_list) || +#endif + tsk->mm != tsk->active_mm) { task_unlock(tsk); return -EINVAL; } @@ -295,7 +298,10 @@ int s390_enable_sie(void) /* Now lets check again if something happened */ task_lock(tsk); if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || - tsk->mm != tsk->active_mm || !hlist_empty(&tsk->mm->ioctx_list)) { +#ifdef CONFIG_AIO + !hlist_empty(&tsk->mm->ioctx_list) || +#endif + tsk->mm != tsk->active_mm) { mmput(mm); task_unlock(tsk); return -EINVAL; @@ -314,21 +320,18 @@ int s390_enable_sie(void) } EXPORT_SYMBOL_GPL(s390_enable_sie); -#ifdef CONFIG_DEBUG_PAGEALLOC -#ifdef CONFIG_HIBERNATION +#if defined(CONFIG_DEBUG_PAGEALLOC) && defined(CONFIG_HIBERNATION) bool kernel_page_present(struct page *page) { unsigned long addr; int cc; addr = page_to_phys(page); - asm("lra %1,0(%1)\n" - "ipm %0\n" - "srl %0,28" - :"=d"(cc),"+a"(addr)::"cc"); + asm volatile( + " lra %1,0(%1)\n" + " ipm %0\n" + " srl %0,28" + : "=d" (cc), "+a" (addr) : : "cc"); return cc == 0; } - -#endif /* CONFIG_HIBERNATION */ -#endif /* CONFIG_DEBUG_PAGEALLOC */ - +#endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */ |
