diff --git a/MAINTAINERS b/MAINTAINERS index 900d98eec2fc..79031a56711b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7405,10 +7405,26 @@ W: http://www.ibm.com/developerworks/linux/linux390/ S: Supported F: arch/s390/ F: drivers/s390/ -F: block/partitions/ibm.c F: Documentation/s390/ F: Documentation/DocBook/s390* +S390 COMMON I/O LAYER +M: Sebastian Ott +M: Peter Oberparleiter +L: linux-s390@vger.kernel.org +W: http://www.ibm.com/developerworks/linux/linux390/ +S: Supported +F: drivers/s390/cio/ + +S390 DASD DRIVER +M: Stefan Weinhuber +M: Stefan Haberland +L: linux-s390@vger.kernel.org +W: http://www.ibm.com/developerworks/linux/linux390/ +S: Supported +F: drivers/s390/block/dasd* +F: block/partitions/ibm.c + S390 NETWORK DRIVERS M: Ursula Braun M: Frank Blaschka @@ -7418,6 +7434,15 @@ W: http://www.ibm.com/developerworks/linux/linux390/ S: Supported F: drivers/s390/net/ +S390 PCI SUBSYSTEM +M: Sebastian Ott +M: Gerald Schaefer +L: linux-s390@vger.kernel.org +W: http://www.ibm.com/developerworks/linux/linux390/ +S: Supported +F: arch/s390/pci/ +F: drivers/pci/hotplug/s390_pci_hpc.c + S390 ZCRYPT DRIVER M: Ingo Tuchscherer M: linux390@de.ibm.com diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bb74b21f007a..953f17c8d17c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -141,6 +141,7 @@ config S390 select OLD_SIGACTION select OLD_SIGSUSPEND3 select SYSCTL_EXCEPTION_TRACE + select TTY select VIRT_CPU_ACCOUNTING select VIRT_TO_BUS @@ -416,6 +417,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + def_bool y + depends on 64BIT + config FORCE_MAX_ZONEORDER int default "9" diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index de8e2b3b0180..69b23b25ac34 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -171,7 +171,7 @@ static int __init appldata_os_init(void) int rc, max_size; max_size = sizeof(struct appldata_os_data) + - (NR_CPUS * sizeof(struct appldata_os_per_cpu)); + (num_possible_cpus() * sizeof(struct appldata_os_per_cpu)); if (max_size > APPLDATA_MAX_REC_SIZE) { pr_err("Maximum OS record size %i exceeds the maximum " "record size %i\n", max_size, APPLDATA_MAX_REC_SIZE); diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index e0af2ee58751..ddaae2f5c913 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -46,6 +46,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y CONFIG_MARCH_Z9_109=y +CONFIG_NR_CPUS=256 CONFIG_PREEMPT=y CONFIG_HZ_100=y CONFIG_MEMORY_HOTPLUG=y @@ -58,7 +59,6 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y CONFIG_CRASH_DUMP=y -CONFIG_ZFCPDUMP=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -101,7 +101,6 @@ CONFIG_TCP_CONG_VENO=m CONFIG_TCP_CONG_YEAH=m CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m @@ -111,6 +110,7 @@ CONFIG_INET6_XFRM_MODE_TRANSPORT=m CONFIG_INET6_XFRM_MODE_TUNNEL=m CONFIG_INET6_XFRM_MODE_BEET=m CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m +CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y @@ -135,7 +135,17 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m -CONFIG_NETFILTER_TPROXY=m +CONFIG_NF_TABLES=m +CONFIG_NFT_EXTHDR=m +CONFIG_NFT_META=m +CONFIG_NFT_CT=m +CONFIG_NFT_RBTREE=m +CONFIG_NFT_HASH=m +CONFIG_NFT_COUNTER=m +CONFIG_NFT_LOG=m +CONFIG_NFT_LIMIT=m +CONFIG_NFT_NAT=m +CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -204,7 +214,9 @@ CONFIG_IP_SET_HASH_IP=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m +CONFIG_IP_SET_HASH_NETNET=m CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m @@ -227,6 +239,11 @@ CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NF_CONNTRACK_IPV4=m # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set +CONFIG_NF_TABLES_IPV4=m +CONFIG_NFT_REJECT_IPV4=m +CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NF_TABLES_ARP=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -249,6 +266,9 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_NF_TABLES_IPV6=m +CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -268,6 +288,7 @@ CONFIG_IP6_NF_SECURITY=m CONFIG_NF_NAT_IPV6=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m +CONFIG_NF_TABLES_BRIDGE=m CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m @@ -314,6 +335,7 @@ CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y +CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m @@ -381,8 +403,8 @@ CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_MIRROR=m -CONFIG_DM_RAID=m CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m @@ -434,7 +456,6 @@ CONFIG_TN3270_FS=y CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m -CONFIG_ZVM_WATCHDOG=m # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m @@ -534,13 +555,23 @@ CONFIG_UNUSED_SYMBOLS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_SELFTEST=y +CONFIG_DEBUG_OBJECTS_FREE=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y CONFIG_SLUB_DEBUG_ON=y CONFIG_SLUB_STATS=y +CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_VM=y CONFIG_DEBUG_VM_RB=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_DETECT_HUNG_TASK=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_RT_MUTEX_TESTER=y @@ -573,9 +604,11 @@ CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_LKDTM=m +CONFIG_TEST_LIST_SORT=y CONFIG_KPROBES_SANITY_TEST=y -CONFIG_RBTREE_TEST=m +CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m +CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_DMA_API_DEBUG=y # CONFIG_STRICT_DEVMEM is not set @@ -638,7 +671,6 @@ CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_ASYMMETRIC_KEY_TYPE=m CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m -CONFIG_PUBLIC_KEY_ALGO_RSA=m CONFIG_X509_CERTIFICATE_PARSER=m CONFIG_CRC7=m CONFIG_CRC8=m diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index b9f6b4cab927..c81a74e3e25a 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -46,6 +46,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y CONFIG_MARCH_Z9_109=y +CONFIG_NR_CPUS=256 CONFIG_HZ_100=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y @@ -56,7 +57,6 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y CONFIG_CRASH_DUMP=y -CONFIG_ZFCPDUMP=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -99,7 +99,6 @@ CONFIG_TCP_CONG_VENO=m CONFIG_TCP_CONG_YEAH=m CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m @@ -109,6 +108,7 @@ CONFIG_INET6_XFRM_MODE_TRANSPORT=m CONFIG_INET6_XFRM_MODE_TUNNEL=m CONFIG_INET6_XFRM_MODE_BEET=m CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m +CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y @@ -133,7 +133,17 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m -CONFIG_NETFILTER_TPROXY=m +CONFIG_NF_TABLES=m +CONFIG_NFT_EXTHDR=m +CONFIG_NFT_META=m +CONFIG_NFT_CT=m +CONFIG_NFT_RBTREE=m +CONFIG_NFT_HASH=m +CONFIG_NFT_COUNTER=m +CONFIG_NFT_LOG=m +CONFIG_NFT_LIMIT=m +CONFIG_NFT_NAT=m +CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -202,7 +212,9 @@ CONFIG_IP_SET_HASH_IP=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m +CONFIG_IP_SET_HASH_NETNET=m CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m @@ -225,6 +237,11 @@ CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NF_CONNTRACK_IPV4=m # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set +CONFIG_NF_TABLES_IPV4=m +CONFIG_NFT_REJECT_IPV4=m +CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NF_TABLES_ARP=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -247,6 +264,9 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_NF_TABLES_IPV6=m +CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -266,6 +286,7 @@ CONFIG_IP6_NF_SECURITY=m CONFIG_NF_NAT_IPV6=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m +CONFIG_NF_TABLES_BRIDGE=m CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m @@ -311,6 +332,7 @@ CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y +CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m @@ -378,8 +400,8 @@ CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_MIRROR=m -CONFIG_DM_RAID=m CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m @@ -431,7 +453,6 @@ CONFIG_TN3270_FS=y CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m -CONFIG_ZVM_WATCHDOG=m # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m @@ -540,6 +561,7 @@ CONFIG_BLK_DEV_IO_TRACE=y CONFIG_LKDTM=m CONFIG_RBTREE_TEST=m CONFIG_INTERVAL_TREE_TEST=m +CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y # CONFIG_STRICT_DEVMEM is not set CONFIG_S390_PTDUMP=y @@ -601,7 +623,6 @@ CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_ASYMMETRIC_KEY_TYPE=m CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m -CONFIG_PUBLIC_KEY_ALGO_RSA=m CONFIG_X509_CERTIFICATE_PARSER=m CONFIG_CRC7=m CONFIG_CRC8=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 91087b43e8fa..b5ba8fe1cc64 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -44,6 +44,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y CONFIG_MARCH_Z9_109=y +CONFIG_NR_CPUS=256 CONFIG_HZ_100=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y @@ -54,7 +55,6 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y CONFIG_CRASH_DUMP=y -CONFIG_ZFCPDUMP=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -97,7 +97,6 @@ CONFIG_TCP_CONG_VENO=m CONFIG_TCP_CONG_YEAH=m CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m @@ -107,6 +106,7 @@ CONFIG_INET6_XFRM_MODE_TRANSPORT=m CONFIG_INET6_XFRM_MODE_TUNNEL=m CONFIG_INET6_XFRM_MODE_BEET=m CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m +CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y @@ -131,7 +131,17 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m -CONFIG_NETFILTER_TPROXY=m +CONFIG_NF_TABLES=m +CONFIG_NFT_EXTHDR=m +CONFIG_NFT_META=m +CONFIG_NFT_CT=m +CONFIG_NFT_RBTREE=m +CONFIG_NFT_HASH=m +CONFIG_NFT_COUNTER=m +CONFIG_NFT_LOG=m +CONFIG_NFT_LIMIT=m +CONFIG_NFT_NAT=m +CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -200,7 +210,9 @@ CONFIG_IP_SET_HASH_IP=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m +CONFIG_IP_SET_HASH_NETNET=m CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m @@ -223,6 +235,11 @@ CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NF_CONNTRACK_IPV4=m # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set +CONFIG_NF_TABLES_IPV4=m +CONFIG_NFT_REJECT_IPV4=m +CONFIG_NFT_CHAIN_ROUTE_IPV4=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NF_TABLES_ARP=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -245,6 +262,9 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_NF_TABLES_IPV6=m +CONFIG_NFT_CHAIN_ROUTE_IPV6=m +CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -264,6 +284,7 @@ CONFIG_IP6_NF_SECURITY=m CONFIG_NF_NAT_IPV6=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m +CONFIG_NF_TABLES_BRIDGE=m CONFIG_NET_SCTPPROBE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m @@ -309,6 +330,7 @@ CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y +CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m @@ -376,8 +398,8 @@ CONFIG_BLK_DEV_DM=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_MIRROR=m -CONFIG_DM_RAID=m CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m @@ -429,7 +451,6 @@ CONFIG_TN3270_FS=y CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m -CONFIG_ZVM_WATCHDOG=m # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m @@ -532,6 +553,7 @@ CONFIG_LATENCYTOP=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_LKDTM=m +CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y # CONFIG_STRICT_DEVMEM is not set CONFIG_S390_PTDUMP=y @@ -593,7 +615,6 @@ CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_ASYMMETRIC_KEY_TYPE=m CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m -CONFIG_PUBLIC_KEY_ALGO_RSA=m CONFIG_X509_CERTIFICATE_PARSER=m CONFIG_CRC7=m CONFIG_CRC8=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index d725c4d956e4..cef073ca1f07 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -19,7 +19,6 @@ CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -CONFIG_ZFCPDUMP=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_SECCOMP is not set # CONFIG_IUCV is not set diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 33f57514f424..4557cb7ffddf 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -40,6 +40,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y CONFIG_MARCH_Z196=y +CONFIG_NR_CPUS=256 CONFIG_HZ_100=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y @@ -122,22 +123,31 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DETECT_HUNG_TASK=y CONFIG_TIMER_STATS=y +CONFIG_DEBUG_RT_MUTEXES=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_WRITECOUNT=y CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_PROVE_RCU=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y +CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_KPROBES_SANITY_TEST=y # CONFIG_STRICT_DEVMEM is not set +CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 24908ce149f1..32040ace00ea 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -32,7 +32,7 @@ struct diag2fc_data { __u32 pcpus; __u32 lcpus; __u32 vcpus; - __u32 cpu_min; + __u32 ocpus; __u32 cpu_max; __u32 cpu_shares; __u32 cpu_use_samp; @@ -142,7 +142,12 @@ static int hpyfs_vm_create_guest(struct dentry *systems_dir, ATTRIBUTE(cpus_dir, "capped", capped_value); ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag); ATTRIBUTE(cpus_dir, "count", data->vcpus); - ATTRIBUTE(cpus_dir, "weight_min", data->cpu_min); + /* + * Note: The "weight_min" attribute got the wrong name. + * The value represents the number of non-stopped (operating) + * CPUS. + */ + ATTRIBUTE(cpus_dir, "weight_min", data->ocpus); ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max); ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares); diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 4bbb5957ed1b..bd93ff6661b8 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -44,11 +44,21 @@ struct airq_iv { struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags); void airq_iv_release(struct airq_iv *iv); -unsigned long airq_iv_alloc_bit(struct airq_iv *iv); -void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit); +unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num); +void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num); unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start, unsigned long end); +static inline unsigned long airq_iv_alloc_bit(struct airq_iv *iv) +{ + return airq_iv_alloc(iv, 1); +} + +static inline void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit) +{ + airq_iv_free(iv, bit, 1); +} + static inline unsigned long airq_iv_end(struct airq_iv *iv) { return iv->end; diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 6e6ad0680829..ec5ef891db6b 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -13,9 +13,9 @@ * * The bitop functions are defined to work on unsigned longs, so for an * s390x system the bits end up numbered: - * |63..............0|127............64|191...........128|255...........196| + * |63..............0|127............64|191...........128|255...........192| * and on s390: - * |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224| + * |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224| * * There are a few little-endian macros used mostly for filesystem * bitmaps, these work on similar bit arrays layouts, but @@ -30,7 +30,7 @@ * on an s390x system the bits are numbered: * |0..............63|64............127|128...........191|192...........255| * and on s390: - * |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255| + * |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255| * * The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit * number field needs to be reversed compared to the LSB0 encoded bit @@ -304,7 +304,7 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr) * On an s390x system the bits are numbered: * |0..............63|64............127|128...........191|192...........255| * and on s390: - * |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255| + * |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255| */ unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size); unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size, diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index f201af8be580..a9c2c0686177 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -219,7 +219,9 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *); #define to_ccwdev(n) container_of(n, struct ccw_device, dev) #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver) -extern struct ccw_device *ccw_device_probe_console(void); +extern struct ccw_device *ccw_device_create_console(struct ccw_driver *); +extern void ccw_device_destroy_console(struct ccw_device *); +extern int ccw_device_enable_console(struct ccw_device *); extern void ccw_device_wait_idle(struct ccw_device *); extern int ccw_device_force_console(struct ccw_device *); diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 4f57a4f3909a..740364856355 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -44,22 +44,15 @@ csum_partial(const void *buff, int len, __wsum sum) * here even more important to align src and dst on a 32-bit (or even * better 64-bit) boundary * - * Copy from userspace and compute checksum. If we catch an exception - * then zero the rest of the buffer. + * Copy from userspace and compute checksum. */ static inline __wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr) { - int missing; - - missing = copy_from_user(dst, src, len); - if (missing) { - memset(dst + len - missing, 0, missing); + if (unlikely(copy_from_user(dst, src, len))) *err_ptr = -EFAULT; - } - return csum_partial(dst, len, sum); } diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index 51bcaa0fdeef..fda46bd38c99 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -5,7 +5,10 @@ #include #include -static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval); +int __futex_atomic_op_inuser(int op, u32 __user *uaddr, int oparg, int *old); + +static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -17,7 +20,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) oparg = 1 << oparg; pagefault_disable(); - ret = uaccess.futex_atomic_op(op, uaddr, oparg, &oldval); + ret = __futex_atomic_op_inuser(op, uaddr, oparg, &oldval); pagefault_enable(); if (!ret) { @@ -34,10 +37,4 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) return ret; } -static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) -{ - return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval); -} - #endif /* _ASM_S390_FUTEX_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index eef3dd3fd9a9..9bf95bb30f1a 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -106,7 +106,9 @@ struct kvm_s390_sie_block { __u64 gbea; /* 0x0180 */ __u8 reserved188[24]; /* 0x0188 */ __u32 fac; /* 0x01a0 */ - __u8 reserved1a4[68]; /* 0x01a4 */ + __u8 reserved1a4[20]; /* 0x01a4 */ + __u64 cbrlo; /* 0x01b8 */ + __u8 reserved1c0[40]; /* 0x01c0 */ __u64 itdba; /* 0x01e8 */ __u8 reserved1f0[16]; /* 0x01f0 */ } __attribute__((packed)); @@ -155,6 +157,7 @@ struct kvm_vcpu_stat { u32 instruction_stsi; u32 instruction_stfl; u32 instruction_tprot; + u32 instruction_essa; u32 instruction_sigp_sense; u32 instruction_sigp_sense_running; u32 instruction_sigp_external_call; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 5d1f950704dc..38149b63dc44 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -48,13 +48,42 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk) static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { - cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); - update_mm(next, tsk); + int cpu = smp_processor_id(); + + if (prev == next) + return; + if (atomic_inc_return(&next->context.attach_count) >> 16) { + /* Delay update_mm until all TLB flushes are done. */ + set_tsk_thread_flag(tsk, TIF_TLB_WAIT); + } else { + cpumask_set_cpu(cpu, mm_cpumask(next)); + update_mm(next, tsk); + if (next->context.flush_mm) + /* Flush pending TLBs */ + __tlb_flush_mm(next); + } atomic_dec(&prev->context.attach_count); WARN_ON(atomic_read(&prev->context.attach_count) < 0); - atomic_inc(&next->context.attach_count); - /* Check for TLBs not flushed yet */ - __tlb_flush_mm_lazy(next); +} + +#define finish_arch_post_lock_switch finish_arch_post_lock_switch +static inline void finish_arch_post_lock_switch(void) +{ + struct task_struct *tsk = current; + struct mm_struct *mm = tsk->mm; + + if (!test_tsk_thread_flag(tsk, TIF_TLB_WAIT)) + return; + preempt_disable(); + clear_tsk_thread_flag(tsk, TIF_TLB_WAIT); + while (atomic_read(&mm->context.attach_count) >> 16) + cpu_relax(); + + cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); + update_mm(mm, tsk); + if (mm->context.flush_mm) + __tlb_flush_mm(mm); + preempt_enable(); } #define enter_lazy_tlb(mm,tsk) do { } while (0) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index e1408ddb94f8..884017cbfa9f 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -22,6 +22,7 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long); void page_table_free(struct mm_struct *, unsigned long *); void page_table_free_rcu(struct mmu_gather *, unsigned long *); +void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long); int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned long key, bool nq); @@ -91,11 +92,22 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) { unsigned long *table = crst_table_alloc(mm); - if (table) - crst_table_init(table, _SEGMENT_ENTRY_EMPTY); + + if (!table) + return NULL; + crst_table_init(table, _SEGMENT_ENTRY_EMPTY); + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } return (pmd_t *) table; } -#define pmd_free(mm, pmd) crst_table_free(mm, (unsigned long *) pmd) + +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +{ + pgtable_pmd_page_dtor(virt_to_page(pmd)); + crst_table_free(mm, (unsigned long *) pmd); +} static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 2204400d0bd5..1ab75eaacbd4 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -229,6 +229,7 @@ extern unsigned long MODULES_END; #define _PAGE_READ 0x010 /* SW pte read bit */ #define _PAGE_WRITE 0x020 /* SW pte write bit */ #define _PAGE_SPECIAL 0x040 /* SW associated with special page */ +#define _PAGE_UNUSED 0x080 /* SW bit for pgste usage state */ #define __HAVE_ARCH_PTE_SPECIAL /* Set of bits not changed in pte_modify */ @@ -394,6 +395,12 @@ extern unsigned long MODULES_END; #endif /* CONFIG_64BIT */ +/* Guest Page State used for virtualization */ +#define _PGSTE_GPS_ZERO 0x0000000080000000UL +#define _PGSTE_GPS_USAGE_MASK 0x0000000003000000UL +#define _PGSTE_GPS_USAGE_STABLE 0x0000000000000000UL +#define _PGSTE_GPS_USAGE_UNUSED 0x0000000001000000UL + /* * A user page table pointer has the space-switch-event bit, the * private-space-control bit and the storage-alteration-event-control @@ -617,6 +624,14 @@ static inline int pte_none(pte_t pte) return pte_val(pte) == _PAGE_INVALID; } +static inline int pte_swap(pte_t pte) +{ + /* Bit pattern: (pte & 0x603) == 0x402 */ + return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | + _PAGE_TYPE | _PAGE_PRESENT)) + == (_PAGE_INVALID | _PAGE_TYPE); +} + static inline int pte_file(pte_t pte) { /* Bit pattern: (pte & 0x601) == 0x600 */ @@ -821,20 +836,20 @@ unsigned long gmap_translate(unsigned long address, struct gmap *); unsigned long __gmap_fault(unsigned long address, struct gmap *); unsigned long gmap_fault(unsigned long address, struct gmap *); void gmap_discard(unsigned long from, unsigned long to, struct gmap *); +void __gmap_zap(unsigned long address, struct gmap *); void gmap_register_ipte_notifier(struct gmap_notifier *); void gmap_unregister_ipte_notifier(struct gmap_notifier *); int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len); -void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *); +void gmap_do_ipte_notify(struct mm_struct *, pte_t *); static inline pgste_t pgste_ipte_notify(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE if (pgste_val(pgste) & PGSTE_IN_BIT) { pgste_val(pgste) &= ~PGSTE_IN_BIT; - gmap_do_ipte_notify(mm, addr, ptep); + gmap_do_ipte_notify(mm, ptep); } #endif return pgste; @@ -852,6 +867,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); + pgste_val(pgste) &= ~_PGSTE_GPS_ZERO; pgste_set_key(ptep, pgste, entry); pgste_set_pte(ptep, entry); pgste_set_unlock(ptep, pgste); @@ -881,6 +897,12 @@ static inline int pte_young(pte_t pte) return (pte_val(pte) & _PAGE_YOUNG) != 0; } +#define __HAVE_ARCH_PTE_UNUSED +static inline int pte_unused(pte_t pte) +{ + return pte_val(pte) & _PAGE_UNUSED; +} + /* * pgd/pmd/pte modification functions */ @@ -1034,30 +1056,41 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm, static inline void __ptep_ipte(unsigned long address, pte_t *ptep) { - if (!(pte_val(*ptep) & _PAGE_INVALID)) { + unsigned long pto = (unsigned long) ptep; + #ifndef CONFIG_64BIT - /* pto must point to the start of the segment table */ - pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00); -#else - /* ipte in zarch mode can do the math */ - pte_t *pto = ptep; + /* pto in ESA mode must point to the start of the segment table */ + pto &= 0x7ffffc00; #endif - asm volatile( - " ipte %2,%3" - : "=m" (*ptep) : "m" (*ptep), - "a" (pto), "a" (address)); - } + /* Invalidation + global TLB flush for the pte */ + asm volatile( + " ipte %2,%3" + : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address)); +} + +static inline void ptep_flush_direct(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + if (pte_val(*ptep) & _PAGE_INVALID) + return; + __ptep_ipte(address, ptep); } static inline void ptep_flush_lazy(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - int active = (mm == current->active_mm) ? 1 : 0; + int active, count; - if (atomic_read(&mm->context.attach_count) > active) - __ptep_ipte(address, ptep); - else + if (pte_val(*ptep) & _PAGE_INVALID) + return; + active = (mm == current->active_mm) ? 1 : 0; + count = atomic_add_return(0x10000, &mm->context.attach_count); + if ((count & 0xffff) <= active) { + pte_val(*ptep) |= _PAGE_INVALID; mm->context.flush_mm = 1; + } else + __ptep_ipte(address, ptep); + atomic_sub(0x10000, &mm->context.attach_count); } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -1070,11 +1103,11 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste); + pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste); } pte = *ptep; - __ptep_ipte(addr, ptep); + ptep_flush_direct(vma->vm_mm, addr, ptep); young = pte_young(pte); pte = pte_mkold(pte); @@ -1116,7 +1149,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_ipte_notify(mm, address, ptep, pgste); + pgste = pgste_ipte_notify(mm, ptep, pgste); } pte = *ptep; @@ -1140,12 +1173,11 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste_ipte_notify(mm, address, ptep, pgste); + pgste_ipte_notify(mm, ptep, pgste); } pte = *ptep; ptep_flush_lazy(mm, address, ptep); - pte_val(*ptep) |= _PAGE_INVALID; if (mm_has_pgste(mm)) { pgste = pgste_update_all(&pte, pgste); @@ -1178,14 +1210,17 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste); + pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste); } pte = *ptep; - __ptep_ipte(address, ptep); + ptep_flush_direct(vma->vm_mm, address, ptep); pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(vma->vm_mm)) { + if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) == + _PGSTE_GPS_USAGE_UNUSED) + pte_val(pte) |= _PAGE_UNUSED; pgste = pgste_update_all(&pte, pgste); pgste_set_unlock(ptep, pgste); } @@ -1209,7 +1244,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, if (!full && mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_ipte_notify(mm, address, ptep, pgste); + pgste = pgste_ipte_notify(mm, ptep, pgste); } pte = *ptep; @@ -1234,7 +1269,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm, if (pte_write(pte)) { if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_ipte_notify(mm, address, ptep, pgste); + pgste = pgste_ipte_notify(mm, ptep, pgste); } ptep_flush_lazy(mm, address, ptep); @@ -1260,10 +1295,10 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return 0; if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste); + pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste); } - __ptep_ipte(address, ptep); + ptep_flush_direct(vma->vm_mm, address, ptep); if (mm_has_pgste(vma->vm_mm)) { pgste_set_pte(ptep, entry); @@ -1447,12 +1482,16 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) static inline void pmdp_flush_lazy(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - int active = (mm == current->active_mm) ? 1 : 0; + int active, count; - if ((atomic_read(&mm->context.attach_count) & 0xffff) > active) - __pmd_idte(address, pmdp); - else + active = (mm == current->active_mm) ? 1 : 0; + count = atomic_add_return(0x10000, &mm->context.attach_count); + if ((count & 0xffff) <= active) { + pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID; mm->context.flush_mm = 1; + } else + __pmd_idte(address, pmdp); + atomic_sub(0x10000, &mm->context.attach_count); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 9c82cebddabd..f4783c0b7b43 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -83,6 +83,7 @@ struct per_struct_kernel { * These are defined as per linux/ptrace.h, which see. */ #define arch_has_single_step() (1) +#define arch_has_block_step() (1) #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0) #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index abaca2275c7a..2f5e9932b4de 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -46,6 +46,7 @@ int sclp_cpu_configure(u8 cpu); int sclp_cpu_deconfigure(u8 cpu); unsigned long long sclp_get_rnmax(void); unsigned long long sclp_get_rzm(void); +unsigned int sclp_get_max_cpu(void); int sclp_sdias_blk_count(void); int sclp_sdias_copy(void *dest, int blk_num, int nr_blks); int sclp_chp_configure(struct chp_id chpid); diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 94cfbe442f12..406f3a1e63ef 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -59,7 +59,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr, #define MACHINE_FLAG_DIAG44 (1UL << 4) #define MACHINE_FLAG_IDTE (1UL << 5) #define MACHINE_FLAG_DIAG9C (1UL << 6) -#define MACHINE_FLAG_MVCOS (1UL << 7) #define MACHINE_FLAG_KVM (1UL << 8) #define MACHINE_FLAG_ESOP (1UL << 9) #define MACHINE_FLAG_EDAT1 (1UL << 10) @@ -85,7 +84,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr, #define MACHINE_HAS_IDTE (0) #define MACHINE_HAS_DIAG44 (1) #define MACHINE_HAS_MVPG (S390_lowcore.machine_flags & MACHINE_FLAG_MVPG) -#define MACHINE_HAS_MVCOS (0) #define MACHINE_HAS_EDAT1 (0) #define MACHINE_HAS_EDAT2 (0) #define MACHINE_HAS_LPP (0) @@ -98,7 +96,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr, #define MACHINE_HAS_IDTE (S390_lowcore.machine_flags & MACHINE_FLAG_IDTE) #define MACHINE_HAS_DIAG44 (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44) #define MACHINE_HAS_MVPG (1) -#define MACHINE_HAS_MVCOS (S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS) #define MACHINE_HAS_EDAT1 (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT1) #define MACHINE_HAS_EDAT2 (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT2) #define MACHINE_HAS_LPP (S390_lowcore.machine_flags & MACHINE_FLAG_LPP) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 10e0fcd3633d..3ccd71b90345 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -81,6 +81,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_TLB_WAIT 4 /* wait for TLB flush completion */ #define TIF_PER_TRAP 6 /* deliver sigtrap on return to user */ #define TIF_MCCK_PENDING 7 /* machine check handling is pending */ #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ @@ -91,11 +92,13 @@ static inline struct thread_info *current_thread_info(void) #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 19 /* restore signal mask in do_signal() */ #define TIF_SINGLE_STEP 20 /* This task is single stepped */ +#define TIF_BLOCK_STEP 21 /* This task is block stepped */ #define _TIF_SYSCALL (1<. + */ +#define PTRACE_SINGLEBLOCK 12 /* resume execution until next branch */ + /* * PT_PROT definition is loosely based on hppa bsd definition in * gdb/hppab-nat.c diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 1b3ac09c11b6..a95c4ca99617 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -47,9 +47,8 @@ obj-$(CONFIG_SCHED_BOOK) += topology.o obj-$(CONFIG_HIBERNATION) += suspend.o swsusp_asm64.o obj-$(CONFIG_AUDIT) += audit.o compat-obj-$(CONFIG_AUDIT) += compat_audit.o -obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o \ - compat_wrapper.o compat_exec_domain.o \ - $(compat-obj-y) +obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o +obj-$(CONFIG_COMPAT) += compat_wrapper.o $(compat-obj-y) obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_KPROBES) += kprobes.o diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c deleted file mode 100644 index 765fabdada9f..000000000000 --- a/arch/s390/kernel/compat_exec_domain.c +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Support for 32-bit Linux for S390 personality. - * - * Copyright IBM Corp. 2000 - * Author(s): Gerhard Tonn (ton@de.ibm.com) - * - * - */ - -#include -#include -#include -#include - -static struct exec_domain s390_exec_domain; - -static int __init s390_init (void) -{ - s390_exec_domain.name = "Linux/s390"; - s390_exec_domain.handler = NULL; - s390_exec_domain.pers_low = PER_LINUX32; - s390_exec_domain.pers_high = PER_LINUX32; - s390_exec_domain.signal_map = default_exec_domain.signal_map; - s390_exec_domain.signal_invmap = default_exec_domain.signal_invmap; - register_exec_domain(&s390_exec_domain); - return 0; -} - -__initcall(s390_init); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index fca20b5fe79e..6b594439cca5 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -380,8 +380,6 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2; if (test_facility(3)) S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; - if (test_facility(27)) - S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; if (test_facility(40)) S390_lowcore.machine_flags |= MACHINE_FLAG_LPP; if (test_facility(50) && test_facility(73)) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 0dc2b6d0a1ec..526d3735ed29 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -43,6 +43,7 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) +_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT @@ -159,10 +160,12 @@ ENTRY(__switch_to) lctl %c4,%c4,__TASK_pid(%r3) # load pid to control reg. 4 mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next l %r15,__THREAD_ksp(%r3) # load kernel stack of next - tm __TI_flags+3(%r4),_TIF_MCCK_PENDING # machine check pending? + lhi %r6,_TIF_TRANSFER # transfer TIF bits + n %r6,__TI_flags(%r4) # isolate TIF bits jz 0f - ni __TI_flags+3(%r4),255-_TIF_MCCK_PENDING # clear flag in prev - oi __TI_flags+3(%r5),_TIF_MCCK_PENDING # set it in next + o %r6,__TI_flags(%r5) # set TIF bits of next + st %r6,__TI_flags(%r5) + ni __TI_flags+3(%r4),255-_TIF_TRANSFER # clear TIF bits of prev 0: lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 384e609b4711..e09dbe5f2901 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -48,6 +48,7 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) +_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT) #define BASED(name) name-system_call(%r13) @@ -189,10 +190,12 @@ ENTRY(__switch_to) lctl %c4,%c4,__TASK_pid(%r3) # load pid to control reg. 4 mvc __LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next lg %r15,__THREAD_ksp(%r3) # load kernel stack of next - tm __TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending? + llill %r6,_TIF_TRANSFER # transfer TIF bits + ng %r6,__TI_flags(%r4) # isolate TIF bits jz 0f - ni __TI_flags+7(%r4),255-_TIF_MCCK_PENDING # clear flag in prev - oi __TI_flags+7(%r5),_TIF_MCCK_PENDING # set it in next + og %r6,__TI_flags(%r5) # set TIF bits of next + stg %r6,__TI_flags(%r5) + ni __TI_flags+7(%r4),255-_TIF_TRANSFER # clear TIF bits of prev 0: lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 5d2dfa31c4ef..61595c1f0a0f 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -121,7 +121,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) : PERF_RECORD_MISC_KERNEL; } -void print_debug_cf(void) +static void print_debug_cf(void) { struct cpumf_ctr_info cf_info; int cpu = smp_processor_id(); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index f6be6087a0e9..4ac8fafec95f 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -85,7 +85,10 @@ void update_cr_regs(struct task_struct *task) /* merge TIF_SINGLE_STEP into user specified PER registers. */ if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) { - new.control |= PER_EVENT_IFETCH; + if (test_tsk_thread_flag(task, TIF_BLOCK_STEP)) + new.control |= PER_EVENT_BRANCH; + else + new.control |= PER_EVENT_IFETCH; #ifdef CONFIG_64BIT new.control |= PER_CONTROL_SUSPENSION; new.control |= PER_EVENT_TRANSACTION_END; @@ -107,14 +110,22 @@ void update_cr_regs(struct task_struct *task) void user_enable_single_step(struct task_struct *task) { + clear_tsk_thread_flag(task, TIF_BLOCK_STEP); set_tsk_thread_flag(task, TIF_SINGLE_STEP); } void user_disable_single_step(struct task_struct *task) { + clear_tsk_thread_flag(task, TIF_BLOCK_STEP); clear_tsk_thread_flag(task, TIF_SINGLE_STEP); } +void user_enable_block_step(struct task_struct *task) +{ + set_tsk_thread_flag(task, TIF_SINGLE_STEP); + set_tsk_thread_flag(task, TIF_BLOCK_STEP); +} + /* * Called by kernel/ptrace.c when detaching.. * diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 09e2f468f48b..f70f2489fa5f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -47,7 +47,6 @@ #include #include -#include #include #include #include @@ -64,12 +63,6 @@ #include #include "entry.h" -/* - * User copy operations. - */ -struct uaccess_ops uaccess; -EXPORT_SYMBOL(uaccess); - /* * Machine setup.. */ @@ -294,14 +287,6 @@ static int __init parse_vmalloc(char *arg) } early_param("vmalloc", parse_vmalloc); -static int __init early_parse_user_mode(char *p) -{ - if (!p || strcmp(p, "primary") == 0) - return 0; - return 1; -} -early_param("user_mode", early_parse_user_mode); - void *restart_stack __attribute__((__section__(".data"))); static void __init setup_lowcore(void) @@ -1009,8 +994,6 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) &_edata; init_mm.brk = (unsigned long) &_end; - uaccess = MACHINE_HAS_MVCOS ? uaccess_mvcos : uaccess_pt; - parse_early_param(); detect_memory_layout(memory_chunk, memory_end); os_info_init(); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index a7125b62a9a6..8827883310dd 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -773,11 +773,11 @@ void __noreturn cpu_die(void) void __init smp_fill_possible_mask(void) { - unsigned int possible, cpu; + unsigned int possible, sclp, cpu; - possible = setup_possible_cpus; - if (!possible) - possible = MACHINE_IS_VM ? 64 : nr_cpu_ids; + sclp = sclp_get_max_cpu() ?: nr_cpu_ids; + possible = setup_possible_cpus ?: nr_cpu_ids; + possible = min(possible, sclp); for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++) set_cpu_possible(cpu, true); } diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4b2e3e317004..6298fed11ced 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -451,7 +451,6 @@ static int __init topology_init(void) } set_topology_timer(); out: - update_cpu_masks(); return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 8216c0e0b2e2..6f9cfa500372 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -13,6 +13,7 @@ #include #include +#include #include #include "kvm-s390.h" #include "trace.h" @@ -86,9 +87,11 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) switch (subcode) { case 3: vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR; + page_table_reset_pgste(current->mm, 0, TASK_SIZE); break; case 4: vcpu->run->s390_reset_flags = 0; + page_table_reset_pgste(current->mm, 0, TASK_SIZE); break; default: return -EOPNOTSUPP; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e0676f390d57..10b5db3c9bc4 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -68,6 +68,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_storage_key", VCPU_STAT(instruction_storage_key) }, { "instruction_stsch", VCPU_STAT(instruction_stsch) }, { "instruction_chsc", VCPU_STAT(instruction_chsc) }, + { "instruction_essa", VCPU_STAT(instruction_essa) }, { "instruction_stsi", VCPU_STAT(instruction_stsi) }, { "instruction_stfl", VCPU_STAT(instruction_stfl) }, { "instruction_tprot", VCPU_STAT(instruction_tprot) }, @@ -283,7 +284,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) if (kvm_is_ucontrol(vcpu->kvm)) gmap_free(vcpu->arch.gmap); + if (vcpu->arch.sie_block->cbrlo) + __free_page(__pfn_to_page( + vcpu->arch.sie_block->cbrlo >> PAGE_SHIFT)); free_page((unsigned long)(vcpu->arch.sie_block)); + kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vcpu); } @@ -390,6 +395,8 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { + struct page *cbrl; + atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | CPUSTAT_STOPPED | @@ -401,6 +408,14 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ecb2 = 8; vcpu->arch.sie_block->eca = 0xC1002001U; vcpu->arch.sie_block->fac = (int) (long) vfacilities; + if (kvm_enabled_cmma()) { + cbrl = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (cbrl) { + vcpu->arch.sie_block->ecb2 |= 0x80; + vcpu->arch.sie_block->ecb2 &= ~0x08; + vcpu->arch.sie_block->cbrlo = page_to_phys(cbrl); + } + } hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, (unsigned long) vcpu); @@ -761,6 +776,16 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) return rc; } +bool kvm_enabled_cmma(void) +{ + if (!MACHINE_IS_LPAR) + return false; + /* only enable for z10 and later */ + if (!MACHINE_HAS_EDAT1) + return false; + return true; +} + static int __vcpu_run(struct kvm_vcpu *vcpu) { int rc, exit_reason; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index f9559b0bd620..564514f410f4 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -156,6 +156,8 @@ void s390_vcpu_block(struct kvm_vcpu *vcpu); void s390_vcpu_unblock(struct kvm_vcpu *vcpu); void exit_sie(struct kvm_vcpu *vcpu); void exit_sie_sync(struct kvm_vcpu *vcpu); +/* are we going to support cmma? */ +bool kvm_enabled_cmma(void); /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 75beea632a10..aacb6b129914 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -636,8 +636,49 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) return 0; } +static int handle_essa(struct kvm_vcpu *vcpu) +{ + /* entries expected to be 1FF */ + int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3; + unsigned long *cbrlo, cbrle; + struct gmap *gmap; + int i; + + VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries); + gmap = vcpu->arch.gmap; + vcpu->stat.instruction_essa++; + if (!kvm_enabled_cmma() || !vcpu->arch.sie_block->cbrlo) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* Rewind PSW to repeat the ESSA instruction */ + vcpu->arch.sie_block->gpsw.addr = + __rewind_psw(vcpu->arch.sie_block->gpsw, 4); + vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ + cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); + down_read(&gmap->mm->mmap_sem); + for (i = 0; i < entries; ++i) { + cbrle = cbrlo[i]; + if (unlikely(cbrle & ~PAGE_MASK || cbrle < 2 * PAGE_SIZE)) + /* invalid entry */ + break; + /* try to free backing */ + __gmap_zap(cbrle, gmap); + } + up_read(&gmap->mm->mmap_sem); + if (i < entries) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + return 0; +} + static const intercept_handler_t b9_handlers[256] = { [0x8d] = handle_epsw, + [0xab] = handle_essa, [0xaf] = handle_pfmf, }; diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index b068729e50ac..e3fffe1dff51 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -2,8 +2,7 @@ # Makefile for s390-specific library files.. # -lib-y += delay.o string.o uaccess_pt.o find.o +lib-y += delay.o string.o uaccess_pt.o uaccess_mvcos.o find.o obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o obj-$(CONFIG_64BIT) += mem64.o -lib-$(CONFIG_64BIT) += uaccess_mvcos.o lib-$(CONFIG_SMP) += spinlock.o diff --git a/arch/s390/lib/find.c b/arch/s390/lib/find.c index 620d34d6487e..922003c1b90d 100644 --- a/arch/s390/lib/find.c +++ b/arch/s390/lib/find.c @@ -4,7 +4,7 @@ * On s390x the bits are numbered: * |0..............63|64............127|128...........191|192...........255| * and on s390: - * |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255| + * |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255| * * The reason for this bit numbering is the fact that the hardware sets bits * in a bitmap starting at bit 0 (MSB) and we don't want to scan the bitmap diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h index b1a22173d027..c7e0e81f4b4e 100644 --- a/arch/s390/lib/uaccess.h +++ b/arch/s390/lib/uaccess.h @@ -6,7 +6,11 @@ #ifndef __ARCH_S390_LIB_UACCESS_H #define __ARCH_S390_LIB_UACCESS_H -extern int futex_atomic_op_pt(int, u32 __user *, int, int *); -extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32); +unsigned long copy_from_user_pt(void *to, const void __user *from, unsigned long n); +unsigned long copy_to_user_pt(void __user *to, const void *from, unsigned long n); +unsigned long copy_in_user_pt(void __user *to, const void __user *from, unsigned long n); +unsigned long clear_user_pt(void __user *to, unsigned long n); +unsigned long strnlen_user_pt(const char __user *src, unsigned long count); +long strncpy_from_user_pt(char *dst, const char __user *src, long count); #endif /* __ARCH_S390_LIB_UACCESS_H */ diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 4b7993bf69b9..ae97b8df11aa 100644 --- a/arch/s390/lib/uaccess_mvcos.c +++ b/arch/s390/lib/uaccess_mvcos.c @@ -6,8 +6,11 @@ * Gerald Schaefer (gerald.schaefer@de.ibm.com) */ +#include #include +#include #include +#include #include #include #include "uaccess.h" @@ -26,7 +29,10 @@ #define SLR "slgr" #endif -static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) +static struct static_key have_mvcos = STATIC_KEY_INIT_TRUE; + +static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr, + unsigned long size) { register unsigned long reg0 asm("0") = 0x81UL; unsigned long tmp1, tmp2; @@ -65,7 +71,16 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x) return size; } -static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x) +unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) +{ + if (static_key_true(&have_mvcos)) + return copy_from_user_mvcos(to, from, n); + return copy_from_user_pt(to, from, n); +} +EXPORT_SYMBOL(__copy_from_user); + +static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x, + unsigned long size) { register unsigned long reg0 asm("0") = 0x810000UL; unsigned long tmp1, tmp2; @@ -94,8 +109,16 @@ static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x) return size; } -static size_t copy_in_user_mvcos(size_t size, void __user *to, - const void __user *from) +unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) +{ + if (static_key_true(&have_mvcos)) + return copy_to_user_mvcos(to, from, n); + return copy_to_user_pt(to, from, n); +} +EXPORT_SYMBOL(__copy_to_user); + +static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from, + unsigned long size) { register unsigned long reg0 asm("0") = 0x810081UL; unsigned long tmp1, tmp2; @@ -117,7 +140,15 @@ static size_t copy_in_user_mvcos(size_t size, void __user *to, return size; } -static size_t clear_user_mvcos(size_t size, void __user *to) +unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n) +{ + if (static_key_true(&have_mvcos)) + return copy_in_user_mvcos(to, from, n); + return copy_in_user_pt(to, from, n); +} +EXPORT_SYMBOL(__copy_in_user); + +static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size) { register unsigned long reg0 asm("0") = 0x810000UL; unsigned long tmp1, tmp2; @@ -145,17 +176,26 @@ static size_t clear_user_mvcos(size_t size, void __user *to) return size; } -static size_t strnlen_user_mvcos(size_t count, const char __user *src) +unsigned long __clear_user(void __user *to, unsigned long size) { - size_t done, len, offset, len_str; + if (static_key_true(&have_mvcos)) + return clear_user_mvcos(to, size); + return clear_user_pt(to, size); +} +EXPORT_SYMBOL(__clear_user); + +static inline unsigned long strnlen_user_mvcos(const char __user *src, + unsigned long count) +{ + unsigned long done, len, offset, len_str; char buf[256]; done = 0; do { - offset = (size_t)src & ~PAGE_MASK; + offset = (unsigned long)src & ~PAGE_MASK; len = min(256UL, PAGE_SIZE - offset); len = min(count - done, len); - if (copy_from_user_mvcos(len, src, buf)) + if (copy_from_user_mvcos(buf, src, len)) return 0; len_str = strnlen(buf, len); done += len_str; @@ -164,18 +204,26 @@ static size_t strnlen_user_mvcos(size_t count, const char __user *src) return done + 1; } -static size_t strncpy_from_user_mvcos(size_t count, const char __user *src, - char *dst) +unsigned long __strnlen_user(const char __user *src, unsigned long count) { - size_t done, len, offset, len_str; + if (static_key_true(&have_mvcos)) + return strnlen_user_mvcos(src, count); + return strnlen_user_pt(src, count); +} +EXPORT_SYMBOL(__strnlen_user); - if (unlikely(!count)) +static inline long strncpy_from_user_mvcos(char *dst, const char __user *src, + long count) +{ + unsigned long done, len, offset, len_str; + + if (unlikely(count <= 0)) return 0; done = 0; do { - offset = (size_t)src & ~PAGE_MASK; + offset = (unsigned long)src & ~PAGE_MASK; len = min(count - done, PAGE_SIZE - offset); - if (copy_from_user_mvcos(len, src, dst)) + if (copy_from_user_mvcos(dst, src, len)) return -EFAULT; len_str = strnlen(dst, len); done += len_str; @@ -185,13 +233,31 @@ static size_t strncpy_from_user_mvcos(size_t count, const char __user *src, return done; } -struct uaccess_ops uaccess_mvcos = { - .copy_from_user = copy_from_user_mvcos, - .copy_to_user = copy_to_user_mvcos, - .copy_in_user = copy_in_user_mvcos, - .clear_user = clear_user_mvcos, - .strnlen_user = strnlen_user_mvcos, - .strncpy_from_user = strncpy_from_user_mvcos, - .futex_atomic_op = futex_atomic_op_pt, - .futex_atomic_cmpxchg = futex_atomic_cmpxchg_pt, -}; +long __strncpy_from_user(char *dst, const char __user *src, long count) +{ + if (static_key_true(&have_mvcos)) + return strncpy_from_user_mvcos(dst, src, count); + return strncpy_from_user_pt(dst, src, count); +} +EXPORT_SYMBOL(__strncpy_from_user); + +/* + * The uaccess page tabe walk variant can be enforced with the "uaccesspt" + * kernel parameter. This is mainly for debugging purposes. + */ +static int force_uaccess_pt __initdata; + +static int __init parse_uaccess_pt(char *__unused) +{ + force_uaccess_pt = 1; + return 0; +} +early_param("uaccesspt", parse_uaccess_pt); + +static int __init uaccess_init(void) +{ + if (IS_ENABLED(CONFIG_32BIT) || force_uaccess_pt || !test_facility(27)) + static_key_slow_dec(&have_mvcos); + return 0; +} +early_initcall(uaccess_init); diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 61ebcc9ccb34..8d39760bae68 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -22,7 +22,7 @@ #define SLR "slgr" #endif -static size_t strnlen_kernel(size_t count, const char __user *src) +static unsigned long strnlen_kernel(const char __user *src, unsigned long count) { register unsigned long reg0 asm("0") = 0UL; unsigned long tmp1, tmp2; @@ -42,8 +42,8 @@ static size_t strnlen_kernel(size_t count, const char __user *src) return count; } -static size_t copy_in_kernel(size_t count, void __user *to, - const void __user *from) +static unsigned long copy_in_kernel(void __user *to, const void __user *from, + unsigned long count) { unsigned long tmp1; @@ -146,8 +146,8 @@ static unsigned long follow_table(struct mm_struct *mm, #endif /* CONFIG_64BIT */ -static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr, - size_t n, int write_user) +static inline unsigned long __user_copy_pt(unsigned long uaddr, void *kptr, + unsigned long n, int write_user) { struct mm_struct *mm = current->mm; unsigned long offset, done, size, kaddr; @@ -189,8 +189,7 @@ fault: * Do DAT for user address by page table walk, return kernel address. * This function needs to be called with current->mm->page_table_lock held. */ -static __always_inline unsigned long __dat_user_addr(unsigned long uaddr, - int write) +static inline unsigned long __dat_user_addr(unsigned long uaddr, int write) { struct mm_struct *mm = current->mm; unsigned long kaddr; @@ -211,29 +210,29 @@ fault: return 0; } -static size_t copy_from_user_pt(size_t n, const void __user *from, void *to) +unsigned long copy_from_user_pt(void *to, const void __user *from, unsigned long n) { - size_t rc; + unsigned long rc; if (segment_eq(get_fs(), KERNEL_DS)) - return copy_in_kernel(n, (void __user *) to, from); + return copy_in_kernel((void __user *) to, from, n); rc = __user_copy_pt((unsigned long) from, to, n, 0); if (unlikely(rc)) memset(to + n - rc, 0, rc); return rc; } -static size_t copy_to_user_pt(size_t n, void __user *to, const void *from) +unsigned long copy_to_user_pt(void __user *to, const void *from, unsigned long n) { if (segment_eq(get_fs(), KERNEL_DS)) - return copy_in_kernel(n, to, (void __user *) from); + return copy_in_kernel(to, (void __user *) from, n); return __user_copy_pt((unsigned long) to, (void *) from, n, 1); } -static size_t clear_user_pt(size_t n, void __user *to) +unsigned long clear_user_pt(void __user *to, unsigned long n) { void *zpage = (void *) empty_zero_page; - long done, size, ret; + unsigned long done, size, ret; done = 0; do { @@ -242,7 +241,7 @@ static size_t clear_user_pt(size_t n, void __user *to) else size = n - done; if (segment_eq(get_fs(), KERNEL_DS)) - ret = copy_in_kernel(n, to, (void __user *) zpage); + ret = copy_in_kernel(to, (void __user *) zpage, n); else ret = __user_copy_pt((unsigned long) to, zpage, size, 1); done += size; @@ -253,17 +252,17 @@ static size_t clear_user_pt(size_t n, void __user *to) return 0; } -static size_t strnlen_user_pt(size_t count, const char __user *src) +unsigned long strnlen_user_pt(const char __user *src, unsigned long count) { unsigned long uaddr = (unsigned long) src; struct mm_struct *mm = current->mm; unsigned long offset, done, len, kaddr; - size_t len_str; + unsigned long len_str; if (unlikely(!count)) return 0; if (segment_eq(get_fs(), KERNEL_DS)) - return strnlen_kernel(count, src); + return strnlen_kernel(src, count); if (!mm) return 0; done = 0; @@ -289,19 +288,18 @@ fault: goto retry; } -static size_t strncpy_from_user_pt(size_t count, const char __user *src, - char *dst) +long strncpy_from_user_pt(char *dst, const char __user *src, long count) { - size_t done, len, offset, len_str; + unsigned long done, len, offset, len_str; - if (unlikely(!count)) + if (unlikely(count <= 0)) return 0; done = 0; do { - offset = (size_t)src & ~PAGE_MASK; + offset = (unsigned long)src & ~PAGE_MASK; len = min(count - done, PAGE_SIZE - offset); if (segment_eq(get_fs(), KERNEL_DS)) { - if (copy_in_kernel(len, (void __user *) dst, src)) + if (copy_in_kernel((void __user *) dst, src, len)) return -EFAULT; } else { if (__user_copy_pt((unsigned long) src, dst, len, 0)) @@ -315,8 +313,8 @@ static size_t strncpy_from_user_pt(size_t count, const char __user *src, return done; } -static size_t copy_in_user_pt(size_t n, void __user *to, - const void __user *from) +unsigned long copy_in_user_pt(void __user *to, const void __user *from, + unsigned long n) { struct mm_struct *mm = current->mm; unsigned long offset_max, uaddr, done, size, error_code; @@ -326,7 +324,7 @@ static size_t copy_in_user_pt(size_t n, void __user *to, int write_user; if (segment_eq(get_fs(), KERNEL_DS)) - return copy_in_kernel(n, to, from); + return copy_in_kernel(to, from, n); if (!mm) return n; done = 0; @@ -411,7 +409,7 @@ static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) return ret; } -int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) +int __futex_atomic_op_inuser(int op, u32 __user *uaddr, int oparg, int *old) { int ret; @@ -449,8 +447,8 @@ static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, return ret; } -int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) +int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { int ret; @@ -471,14 +469,3 @@ int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, put_page(virt_to_page(uaddr)); return ret; } - -struct uaccess_ops uaccess_pt = { - .copy_from_user = copy_from_user_pt, - .copy_to_user = copy_to_user_pt, - .copy_in_user = copy_in_user_pt, - .clear_user = clear_user_pt, - .strnlen_user = strnlen_user_pt, - .strncpy_from_user = strncpy_from_user_pt, - .futex_atomic_op = futex_atomic_op_pt, - .futex_atomic_cmpxchg = futex_atomic_cmpxchg_pt, -}; diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index d1e0e0c7a7e2..2a2e35416d2f 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -128,7 +128,7 @@ void memcpy_absolute(void *dest, void *src, size_t count) /* * Copy memory from kernel (real) to user (virtual) */ -int copy_to_user_real(void __user *dest, void *src, size_t count) +int copy_to_user_real(void __user *dest, void *src, unsigned long count) { int offs = 0, size, rc; char *buf; @@ -151,32 +151,6 @@ out: return rc; } -/* - * Copy memory from user (virtual) to kernel (real) - */ -int copy_from_user_real(void *dest, void __user *src, size_t count) -{ - int offs = 0, size, rc; - char *buf; - - buf = (char *) __get_free_page(GFP_KERNEL); - if (!buf) - return -ENOMEM; - rc = -EFAULT; - while (offs < count) { - size = min(PAGE_SIZE, count - offs); - if (copy_from_user(buf, src + offs, size)) - goto out; - if (memcpy_real(dest + offs, buf, size)) - goto out; - offs += size; - } - rc = 0; -out: - free_page((unsigned long) buf); - return rc; -} - /* * Check if physical address is within prefix or zero page */ diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3584ed9b20a1..796c9320c709 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -594,6 +595,82 @@ unsigned long gmap_fault(unsigned long address, struct gmap *gmap) } EXPORT_SYMBOL_GPL(gmap_fault); +static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm) +{ + if (!non_swap_entry(entry)) + dec_mm_counter(mm, MM_SWAPENTS); + else if (is_migration_entry(entry)) { + struct page *page = migration_entry_to_page(entry); + + if (PageAnon(page)) + dec_mm_counter(mm, MM_ANONPAGES); + else + dec_mm_counter(mm, MM_FILEPAGES); + } + free_swap_and_cache(entry); +} + +/** + * The mm->mmap_sem lock must be held + */ +static void gmap_zap_unused(struct mm_struct *mm, unsigned long address) +{ + unsigned long ptev, pgstev; + spinlock_t *ptl; + pgste_t pgste; + pte_t *ptep, pte; + + ptep = get_locked_pte(mm, address, &ptl); + if (unlikely(!ptep)) + return; + pte = *ptep; + if (!pte_swap(pte)) + goto out_pte; + /* Zap unused and logically-zero pages */ + pgste = pgste_get_lock(ptep); + pgstev = pgste_val(pgste); + ptev = pte_val(pte); + if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) || + ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID))) { + gmap_zap_swap_entry(pte_to_swp_entry(pte), mm); + pte_clear(mm, address, ptep); + } + pgste_set_unlock(ptep, pgste); +out_pte: + pte_unmap_unlock(*ptep, ptl); +} + +/* + * this function is assumed to be called with mmap_sem held + */ +void __gmap_zap(unsigned long address, struct gmap *gmap) +{ + unsigned long *table, *segment_ptr; + unsigned long segment, pgstev, ptev; + struct gmap_pgtable *mp; + struct page *page; + + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return; + segment = *segment_ptr; + if (segment & _SEGMENT_ENTRY_INVALID) + return; + page = pfn_to_page(segment >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + address = mp->vmaddr | (address & ~PMD_MASK); + /* Page table is present */ + table = (unsigned long *)(segment & _SEGMENT_ENTRY_ORIGIN); + table = table + ((address >> 12) & 0xff); + pgstev = table[PTRS_PER_PTE]; + ptev = table[0]; + /* quick check, checked again with locks held */ + if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) || + ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID))) + gmap_zap_unused(gmap->mm, address); +} +EXPORT_SYMBOL_GPL(__gmap_zap); + void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) { @@ -671,7 +748,7 @@ EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier); /** * gmap_ipte_notify - mark a range of ptes for invalidation notification * @gmap: pointer to guest mapping meta data structure - * @address: virtual address in the guest address space + * @start: virtual address in the guest address space * @len: size of area * * Returns 0 if for each page in the given range a gmap mapping exists and @@ -725,13 +802,12 @@ EXPORT_SYMBOL_GPL(gmap_ipte_notify); /** * gmap_do_ipte_notify - call all invalidation callbacks for a specific pte. * @mm: pointer to the process mm_struct - * @addr: virtual address in the process address space * @pte: pointer to the page table entry * * This function is assumed to be called with the page table lock held * for the pte to notify. */ -void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte) +void gmap_do_ipte_notify(struct mm_struct *mm, pte_t *pte) { unsigned long segment_offset; struct gmap_notifier *nb; @@ -802,6 +878,78 @@ static inline void page_table_free_pgste(unsigned long *table) __free_page(page); } +static inline unsigned long page_table_reset_pte(struct mm_struct *mm, + pmd_t *pmd, unsigned long addr, unsigned long end) +{ + pte_t *start_pte, *pte; + spinlock_t *ptl; + pgste_t pgste; + + start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = start_pte; + do { + pgste = pgste_get_lock(pte); + pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK; + pgste_set_unlock(pte, pgste); + } while (pte++, addr += PAGE_SIZE, addr != end); + pte_unmap_unlock(start_pte, ptl); + + return addr; +} + +static inline unsigned long page_table_reset_pmd(struct mm_struct *mm, + pud_t *pud, unsigned long addr, unsigned long end) +{ + unsigned long next; + pmd_t *pmd; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) + continue; + next = page_table_reset_pte(mm, pmd, addr, next); + } while (pmd++, addr = next, addr != end); + + return addr; +} + +static inline unsigned long page_table_reset_pud(struct mm_struct *mm, + pgd_t *pgd, unsigned long addr, unsigned long end) +{ + unsigned long next; + pud_t *pud; + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + next = page_table_reset_pmd(mm, pud, addr, next); + } while (pud++, addr = next, addr != end); + + return addr; +} + +void page_table_reset_pgste(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + unsigned long addr, next; + pgd_t *pgd; + + addr = start; + down_read(&mm->mmap_sem); + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + next = page_table_reset_pud(mm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); + up_read(&mm->mmap_sem); +} +EXPORT_SYMBOL(page_table_reset_pgste); + int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned long key, bool nq) { @@ -1248,7 +1396,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, { struct list_head *lh = (struct list_head *) pgtable; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ if (!pmd_huge_pte(mm, pmdp)) @@ -1264,7 +1412,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) pgtable_t pgtable; pte_t *ptep; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ pgtable = pmd_huge_pte(mm, pmdp); diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index 75c69b402e05..c5c66840ac00 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -139,7 +139,7 @@ void zpci_debug_exit_device(struct zpci_dev *zdev) int __init zpci_debug_init(void) { /* event trace buffer */ - pci_debug_msg_id = debug_register("pci_msg", 16, 1, 16 * sizeof(long)); + pci_debug_msg_id = debug_register("pci_msg", 8, 1, 8 * sizeof(long)); if (!pci_debug_msg_id) return -EINVAL; debug_register_view(pci_debug_msg_id, &debug_sprintf_view); diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index eb5d22795c47..5af7f0bd6125 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -922,7 +922,7 @@ static int __init con3215_init(void) raw3215_freelist = req; } - cdev = ccw_device_probe_console(); + cdev = ccw_device_create_console(&raw3215_ccw_driver); if (IS_ERR(cdev)) return -ENODEV; @@ -932,6 +932,12 @@ static int __init con3215_init(void) cdev->handler = raw3215_irq; raw->flags |= RAW3215_FIXED; + if (ccw_device_enable_console(cdev)) { + ccw_device_destroy_console(cdev); + raw3215_free_info(raw); + raw3215[0] = NULL; + return -ENODEV; + } /* Request the console irq */ if (raw3215_startup(raw) != 0) { diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c index 699fd3e363df..75ffe9980c3e 100644 --- a/drivers/s390/char/con3270.c +++ b/drivers/s390/char/con3270.c @@ -7,6 +7,7 @@ * Copyright IBM Corp. 2003, 2009 */ +#include #include #include #include @@ -30,6 +31,9 @@ static struct raw3270_fn con3270_fn; +static bool auto_update = 1; +module_param(auto_update, bool, 0); + /* * Main 3270 console view data structure. */ @@ -204,6 +208,8 @@ con3270_update(struct con3270 *cp) struct string *s, *n; int rc; + if (!auto_update && !raw3270_view_active(&cp->view)) + return; if (cp->view.dev) raw3270_activate_view(&cp->view); @@ -529,6 +535,7 @@ con3270_flush(void) if (!cp->view.dev) return; raw3270_pm_unfreeze(&cp->view); + raw3270_activate_view(&cp->view); spin_lock_irqsave(&cp->view.lock, flags); con3270_wait_write(cp); cp->nr_up = 0; @@ -576,7 +583,6 @@ static struct console con3270 = { static int __init con3270_init(void) { - struct ccw_device *cdev; struct raw3270 *rp; void *cbuf; int i; @@ -591,10 +597,7 @@ con3270_init(void) cpcmd("TERM AUTOCR OFF", NULL, 0, NULL); } - cdev = ccw_device_probe_console(); - if (IS_ERR(cdev)) - return -ENODEV; - rp = raw3270_setup_console(cdev); + rp = raw3270_setup_console(); if (IS_ERR(rp)) return PTR_ERR(rp); diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 2cdec21e8924..9f849df4381e 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -275,6 +275,15 @@ __raw3270_start(struct raw3270 *rp, struct raw3270_view *view, return 0; } +int +raw3270_view_active(struct raw3270_view *view) +{ + struct raw3270 *rp = view->dev; + + return rp && rp->view == view && + !test_bit(RAW3270_FLAGS_FROZEN, &rp->flags); +} + int raw3270_start(struct raw3270_view *view, struct raw3270_request *rq) { @@ -776,22 +785,37 @@ raw3270_setup_device(struct ccw_device *cdev, struct raw3270 *rp, char *ascebc) } #ifdef CONFIG_TN3270_CONSOLE +/* Tentative definition - see below for actual definition. */ +static struct ccw_driver raw3270_ccw_driver; + /* * Setup 3270 device configured as console. */ -struct raw3270 __init *raw3270_setup_console(struct ccw_device *cdev) +struct raw3270 __init *raw3270_setup_console(void) { + struct ccw_device *cdev; unsigned long flags; struct raw3270 *rp; char *ascebc; int rc; + cdev = ccw_device_create_console(&raw3270_ccw_driver); + if (IS_ERR(cdev)) + return ERR_CAST(cdev); + rp = kzalloc(sizeof(struct raw3270), GFP_KERNEL | GFP_DMA); ascebc = kzalloc(256, GFP_KERNEL); rc = raw3270_setup_device(cdev, rp, ascebc); if (rc) return ERR_PTR(rc); set_bit(RAW3270_FLAGS_CONSOLE, &rp->flags); + + rc = ccw_device_enable_console(cdev); + if (rc) { + ccw_device_destroy_console(cdev); + return ERR_PTR(rc); + } + spin_lock_irqsave(get_ccwdev_lock(rp->cdev), flags); do { __raw3270_reset_device(rp); diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h index 7b73ff8c1bd7..e1e41c2861fb 100644 --- a/drivers/s390/char/raw3270.h +++ b/drivers/s390/char/raw3270.h @@ -173,6 +173,7 @@ int raw3270_start_locked(struct raw3270_view *, struct raw3270_request *); int raw3270_start_irq(struct raw3270_view *, struct raw3270_request *); int raw3270_reset(struct raw3270_view *); struct raw3270_view *raw3270_view(struct raw3270_view *); +int raw3270_view_active(struct raw3270_view *); /* Reference count inliner for view structures. */ static inline void @@ -190,7 +191,7 @@ raw3270_put_view(struct raw3270_view *view) wake_up(&raw3270_wait_queue); } -struct raw3270 *raw3270_setup_console(struct ccw_device *cdev); +struct raw3270 *raw3270_setup_console(void); void raw3270_wait_cons_dev(struct raw3270 *); /* Notifier for device addition/removal */ diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index 82f2c389b4d1..14196ea0fdf3 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -20,7 +20,9 @@ struct read_info_sccb { struct sccb_header header; /* 0-7 */ u16 rnmax; /* 8-9 */ u8 rnsize; /* 10 */ - u8 _reserved0[24 - 11]; /* 11-15 */ + u8 _reserved0[16 - 11]; /* 11-15 */ + u16 ncpurl; /* 16-17 */ + u8 _reserved7[24 - 18]; /* 18-23 */ u8 loadparm[8]; /* 24-31 */ u8 _reserved1[48 - 32]; /* 32-47 */ u64 facilities; /* 48-55 */ @@ -32,13 +34,16 @@ struct read_info_sccb { u8 _reserved4[100 - 92]; /* 92-99 */ u32 rnsize2; /* 100-103 */ u64 rnmax2; /* 104-111 */ - u8 _reserved5[4096 - 112]; /* 112-4095 */ + u8 _reserved5[120 - 112]; /* 112-119 */ + u16 hcpua; /* 120-121 */ + u8 _reserved6[4096 - 122]; /* 122-4095 */ } __packed __aligned(PAGE_SIZE); static char sccb_early[PAGE_SIZE] __aligned(PAGE_SIZE) __initdata; static unsigned int sclp_con_has_vt220 __initdata; static unsigned int sclp_con_has_linemode __initdata; static unsigned long sclp_hsa_size; +static unsigned int sclp_max_cpu; static struct sclp_ipl_info sclp_ipl_info; u64 sclp_facilities; @@ -102,6 +107,15 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb) sclp_rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2; sclp_rzm <<= 20; + if (!sccb->hcpua) { + if (MACHINE_IS_VM) + sclp_max_cpu = 64; + else + sclp_max_cpu = sccb->ncpurl; + } else { + sclp_max_cpu = sccb->hcpua + 1; + } + /* Save IPL information */ sclp_ipl_info.is_valid = 1; if (sccb->flags & 0x2) @@ -129,6 +143,11 @@ unsigned long long sclp_get_rzm(void) return sclp_rzm; } +unsigned int sclp_get_max_cpu(void) +{ + return sclp_max_cpu; +} + /* * This function will be called after sclp_facilities_detect(), which gets * called from early.c code. The sclp_facilities_detect() function retrieves @@ -184,9 +203,9 @@ static long __init sclp_hsa_size_init(struct sdias_sccb *sccb) sccb_init_eq_size(sccb); if (sclp_cmd_early(SCLP_CMDW_WRITE_EVENT_DATA, sccb)) return -EIO; - if (sccb->evbuf.blk_cnt != 0) - return (sccb->evbuf.blk_cnt - 1) * PAGE_SIZE; - return 0; + if (sccb->evbuf.blk_cnt == 0) + return 0; + return (sccb->evbuf.blk_cnt - 1) * PAGE_SIZE; } static long __init sclp_hsa_copy_wait(struct sccb_header *sccb) @@ -195,6 +214,8 @@ static long __init sclp_hsa_copy_wait(struct sccb_header *sccb) sccb->length = PAGE_SIZE; if (sclp_cmd_early(SCLP_CMDW_READ_EVENT_DATA, sccb)) return -EIO; + if (((struct sdias_sccb *) sccb)->evbuf.blk_cnt == 0) + return 0; return (((struct sdias_sccb *) sccb)->evbuf.blk_cnt - 1) * PAGE_SIZE; } diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c index f055df0b167f..445564c790f6 100644 --- a/drivers/s390/cio/airq.c +++ b/drivers/s390/cio/airq.c @@ -186,55 +186,71 @@ void airq_iv_release(struct airq_iv *iv) EXPORT_SYMBOL(airq_iv_release); /** - * airq_iv_alloc_bit - allocate an irq bit from an interrupt vector + * airq_iv_alloc - allocate irq bits from an interrupt vector * @iv: pointer to an interrupt vector structure + * @num: number of consecutive irq bits to allocate * - * Returns the bit number of the allocated irq, or -1UL if no bit - * is available or the AIRQ_IV_ALLOC flag has not been specified + * Returns the bit number of the first irq in the allocated block of irqs, + * or -1UL if no bit is available or the AIRQ_IV_ALLOC flag has not been + * specified */ -unsigned long airq_iv_alloc_bit(struct airq_iv *iv) +unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num) { - unsigned long bit; + unsigned long bit, i; - if (!iv->avail) + if (!iv->avail || num == 0) return -1UL; spin_lock(&iv->lock); bit = find_first_bit_inv(iv->avail, iv->bits); - if (bit < iv->bits) { - clear_bit_inv(bit, iv->avail); - if (bit >= iv->end) - iv->end = bit + 1; - } else + while (bit + num <= iv->bits) { + for (i = 1; i < num; i++) + if (!test_bit_inv(bit + i, iv->avail)) + break; + if (i >= num) { + /* Found a suitable block of irqs */ + for (i = 0; i < num; i++) + clear_bit_inv(bit + i, iv->avail); + if (bit + num >= iv->end) + iv->end = bit + num + 1; + break; + } + bit = find_next_bit_inv(iv->avail, iv->bits, bit + i + 1); + } + if (bit + num > iv->bits) bit = -1UL; spin_unlock(&iv->lock); return bit; } -EXPORT_SYMBOL(airq_iv_alloc_bit); +EXPORT_SYMBOL(airq_iv_alloc); /** - * airq_iv_free_bit - free an irq bit of an interrupt vector + * airq_iv_free - free irq bits of an interrupt vector * @iv: pointer to interrupt vector structure - * @bit: number of the irq bit to free + * @bit: number of the first irq bit to free + * @num: number of consecutive irq bits to free */ -void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit) +void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num) { - if (!iv->avail) + unsigned long i; + + if (!iv->avail || num == 0) return; spin_lock(&iv->lock); - /* Clear (possibly left over) interrupt bit */ - clear_bit_inv(bit, iv->vector); - /* Make the bit position available again */ - set_bit_inv(bit, iv->avail); - if (bit == iv->end - 1) { + for (i = 0; i < num; i++) { + /* Clear (possibly left over) interrupt bit */ + clear_bit_inv(bit + i, iv->vector); + /* Make the bit positions available again */ + set_bit_inv(bit + i, iv->avail); + } + if (bit + num >= iv->end) { /* Find new end of bit-field */ - while (--iv->end > 0) - if (!test_bit_inv(iv->end - 1, iv->avail)) - break; + while (iv->end > 0 && !test_bit_inv(iv->end - 1, iv->avail)) + iv->end--; } spin_unlock(&iv->lock); } -EXPORT_SYMBOL(airq_iv_free_bit); +EXPORT_SYMBOL(airq_iv_free); /** * airq_iv_scan - scan interrupt vector for non-zero bits diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index 7b29d0be0ca3..1d3661af7bd8 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -173,8 +173,7 @@ static struct css_driver chsc_subchannel_driver = { static int __init chsc_init_dbfs(void) { - chsc_debug_msg_id = debug_register("chsc_msg", 16, 1, - 16 * sizeof(long)); + chsc_debug_msg_id = debug_register("chsc_msg", 8, 1, 4 * sizeof(long)); if (!chsc_debug_msg_id) goto out; debug_register_view(chsc_debug_msg_id, &debug_sprintf_view); diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index 8ee88c4ebd83..97c48b38d67d 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -54,7 +54,7 @@ debug_info_t *cio_debug_crw_id; */ static int __init cio_debug_init(void) { - cio_debug_msg_id = debug_register("cio_msg", 16, 1, 16 * sizeof(long)); + cio_debug_msg_id = debug_register("cio_msg", 16, 1, 11 * sizeof(long)); if (!cio_debug_msg_id) goto out_unregister; debug_register_view(cio_debug_msg_id, &debug_sprintf_view); @@ -64,7 +64,7 @@ static int __init cio_debug_init(void) goto out_unregister; debug_register_view(cio_debug_trace_id, &debug_hex_ascii_view); debug_set_level(cio_debug_trace_id, 2); - cio_debug_crw_id = debug_register("cio_crw", 16, 1, 16 * sizeof(long)); + cio_debug_crw_id = debug_register("cio_crw", 8, 1, 8 * sizeof(long)); if (!cio_debug_crw_id) goto out_unregister; debug_register_view(cio_debug_crw_id, &debug_sprintf_view); diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index e9d783563cbb..d8d9b5b5cc56 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1571,12 +1571,27 @@ out: return rc; } -#ifdef CONFIG_CCW_CONSOLE -static int ccw_device_console_enable(struct ccw_device *cdev, - struct subchannel *sch) +static void ccw_device_set_int_class(struct ccw_device *cdev) { + struct ccw_driver *cdrv = cdev->drv; + + /* Note: we interpret class 0 in this context as an uninitialized + * field since it translates to a non-I/O interrupt class. */ + if (cdrv->int_class != 0) + cdev->private->int_class = cdrv->int_class; + else + cdev->private->int_class = IRQIO_CIO; +} + +#ifdef CONFIG_CCW_CONSOLE +int __init ccw_device_enable_console(struct ccw_device *cdev) +{ + struct subchannel *sch = to_subchannel(cdev->dev.parent); int rc; + if (!cdev->drv || !cdev->handler) + return -EINVAL; + io_subchannel_init_fields(sch); rc = cio_commit_config(sch); if (rc) @@ -1609,12 +1624,11 @@ out_unlock: return rc; } -struct ccw_device *ccw_device_probe_console(void) +struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv) { struct io_subchannel_private *io_priv; struct ccw_device *cdev; struct subchannel *sch; - int ret; sch = cio_probe_console(); if (IS_ERR(sch)) @@ -1631,18 +1645,23 @@ struct ccw_device *ccw_device_probe_console(void) kfree(io_priv); return cdev; } + cdev->drv = drv; set_io_private(sch, io_priv); - ret = ccw_device_console_enable(cdev, sch); - if (ret) { - set_io_private(sch, NULL); - put_device(&sch->dev); - put_device(&cdev->dev); - kfree(io_priv); - return ERR_PTR(ret); - } + ccw_device_set_int_class(cdev); return cdev; } +void __init ccw_device_destroy_console(struct ccw_device *cdev) +{ + struct subchannel *sch = to_subchannel(cdev->dev.parent); + struct io_subchannel_private *io_priv = to_io_private(sch); + + set_io_private(sch, NULL); + put_device(&sch->dev); + put_device(&cdev->dev); + kfree(io_priv); +} + /** * ccw_device_wait_idle() - busy wait for device to become idle * @cdev: ccw device @@ -1726,15 +1745,8 @@ ccw_device_probe (struct device *dev) int ret; cdev->drv = cdrv; /* to let the driver call _set_online */ - /* Note: we interpret class 0 in this context as an uninitialized - * field since it translates to a non-I/O interrupt class. */ - if (cdrv->int_class != 0) - cdev->private->int_class = cdrv->int_class; - else - cdev->private->int_class = IRQIO_CIO; - + ccw_device_set_int_class(cdev); ret = cdrv->probe ? cdrv->probe(cdev) : -ENODEV; - if (ret) { cdev->drv = NULL; cdev->private->int_class = IRQIO_CIO; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 795ed61a5496..a0aff2eb247c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -33,8 +33,8 @@ struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS] = { /* N P A M L V H */ [QETH_DBF_SETUP] = {"qeth_setup", 8, 1, 8, 5, &debug_hex_ascii_view, NULL}, - [QETH_DBF_MSG] = {"qeth_msg", - 8, 1, 128, 3, &debug_sprintf_view, NULL}, + [QETH_DBF_MSG] = {"qeth_msg", 8, 1, 11 * sizeof(long), 3, + &debug_sprintf_view, NULL}, [QETH_DBF_CTRL] = {"qeth_control", 8, 1, QETH_DBF_CTRL_LEN, 5, &debug_hex_ascii_view, NULL}, }; diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 34c7bdc06014..1ec08c198b66 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -193,6 +193,19 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) } #endif +#ifndef __HAVE_ARCH_PTE_UNUSED +/* + * Some architectures provide facilities to virtualization guests + * so that they can flag allocated pages as unused. This allows the + * host to transparently reclaim unused pages. This function returns + * whether the pte's page is unused. + */ +static inline int pte_unused(pte_t pte) +{ + return 0; +} +#endif + #ifndef __HAVE_ARCH_PMD_SAME #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) diff --git a/include/linux/mm.h b/include/linux/mm.h index c1b7414c7bef..a0df4295e171 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1487,9 +1487,15 @@ static inline void pgtable_page_dtor(struct page *page) #if USE_SPLIT_PMD_PTLOCKS +static struct page *pmd_to_page(pmd_t *pmd) +{ + unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); + return virt_to_page((void *)((unsigned long) pmd & mask)); +} + static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { - return ptlock_ptr(virt_to_page(pmd)); + return ptlock_ptr(pmd_to_page(pmd)); } static inline bool pgtable_pmd_page_ctor(struct page *page) @@ -1508,7 +1514,7 @@ static inline void pgtable_pmd_page_dtor(struct page *page) ptlock_free(page); } -#define pmd_huge_pte(mm, pmd) (virt_to_page(pmd)->pmd_huge_pte) +#define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte) #else diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ae365aaa8181..a47902c687ae 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4721,8 +4721,10 @@ void idle_task_exit(void) BUG_ON(cpu_online(smp_processor_id())); - if (mm != &init_mm) + if (mm != &init_mm) { switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } mmdrop(mm); } diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 8a8cd0265e52..f802c2d216a7 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -31,6 +31,9 @@ void use_mm(struct mm_struct *mm) tsk->mm = mm; switch_mm(active_mm, mm, tsk); task_unlock(tsk); +#ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); +#endif if (active_mm != mm) mmdrop(active_mm); diff --git a/mm/rmap.c b/mm/rmap.c index 8fc049f9a5a6..11cf322f8133 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1165,6 +1165,16 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); + } else if (pte_unused(pteval)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + */ + if (PageAnon(page)) + dec_mm_counter(mm, MM_ANONPAGES); + else + dec_mm_counter(mm, MM_FILEPAGES); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; pte_t swp_pte;