aboutsummaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/Kconfig14
-rw-r--r--arch/s390/appldata/appldata_base.c1
-rw-r--r--arch/s390/appldata/appldata_os.c2
-rw-r--r--arch/s390/configs/default_defconfig46
-rw-r--r--arch/s390/configs/gcov_defconfig33
-rw-r--r--arch/s390/configs/performance_defconfig33
-rw-r--r--arch/s390/configs/zfcpdump_defconfig1
-rw-r--r--arch/s390/crypto/aes_s390.c65
-rw-r--r--arch/s390/crypto/des_s390.c101
-rw-r--r--arch/s390/defconfig10
-rw-r--r--arch/s390/hypfs/Makefile2
-rw-r--r--arch/s390/hypfs/hypfs.h7
-rw-r--r--arch/s390/hypfs/hypfs_dbfs.c16
-rw-r--r--arch/s390/hypfs/hypfs_sprp.c141
-rw-r--r--arch/s390/hypfs/hypfs_vm.c9
-rw-r--r--arch/s390/hypfs/inode.c15
-rw-r--r--arch/s390/include/asm/Kbuild4
-rw-r--r--arch/s390/include/asm/airq.h14
-rw-r--r--arch/s390/include/asm/atomic.h70
-rw-r--r--arch/s390/include/asm/barrier.h15
-rw-r--r--arch/s390/include/asm/bitops.h49
-rw-r--r--arch/s390/include/asm/ccwdev.h4
-rw-r--r--arch/s390/include/asm/ccwgroup.h1
-rw-r--r--arch/s390/include/asm/checksum.h11
-rw-r--r--arch/s390/include/asm/cio.h2
-rw-r--r--arch/s390/include/asm/cmpxchg.h5
-rw-r--r--arch/s390/include/asm/compat.h9
-rw-r--r--arch/s390/include/asm/cpu_mf.h181
-rw-r--r--arch/s390/include/asm/css_chars.h2
-rw-r--r--arch/s390/include/asm/futex.h63
-rw-r--r--arch/s390/include/asm/irq.h19
-rw-r--r--arch/s390/include/asm/kvm_host.h114
-rw-r--r--arch/s390/include/asm/mmu.h2
-rw-r--r--arch/s390/include/asm/mmu_context.h78
-rw-r--r--arch/s390/include/asm/pci.h1
-rw-r--r--arch/s390/include/asm/perf_event.h80
-rw-r--r--arch/s390/include/asm/pgalloc.h18
-rw-r--r--arch/s390/include/asm/pgtable.h229
-rw-r--r--arch/s390/include/asm/processor.h1
-rw-r--r--arch/s390/include/asm/ptrace.h1
-rw-r--r--arch/s390/include/asm/qdio.h35
-rw-r--r--arch/s390/include/asm/sclp.h6
-rw-r--r--arch/s390/include/asm/setup.h6
-rw-r--r--arch/s390/include/asm/sigp.h2
-rw-r--r--arch/s390/include/asm/switch_to.h1
-rw-r--r--arch/s390/include/asm/thread_info.h5
-rw-r--r--arch/s390/include/asm/tlb.h14
-rw-r--r--arch/s390/include/asm/tlbflush.h115
-rw-r--r--arch/s390/include/asm/uaccess.h169
-rw-r--r--arch/s390/include/uapi/asm/hypfs.h25
-rw-r--r--arch/s390/include/uapi/asm/kvm.h43
-rw-r--r--arch/s390/include/uapi/asm/ptrace.h6
-rw-r--r--arch/s390/include/uapi/asm/socket.h2
-rw-r--r--arch/s390/include/uapi/asm/statfs.h10
-rw-r--r--arch/s390/include/uapi/asm/unistd.h2
-rw-r--r--arch/s390/include/uapi/asm/zcrypt.h65
-rw-r--r--arch/s390/kernel/Makefile8
-rw-r--r--arch/s390/kernel/asm-offsets.c1
-rw-r--r--arch/s390/kernel/cache.c5
-rw-r--r--arch/s390/kernel/compat_exec_domain.c29
-rw-r--r--arch/s390/kernel/compat_linux.c120
-rw-r--r--arch/s390/kernel/compat_linux.h81
-rw-r--r--arch/s390/kernel/compat_signal.c9
-rw-r--r--arch/s390/kernel/compat_wrapper.S1414
-rw-r--r--arch/s390/kernel/compat_wrapper.c215
-rw-r--r--arch/s390/kernel/early.c4
-rw-r--r--arch/s390/kernel/entry.S33
-rw-r--r--arch/s390/kernel/entry.h6
-rw-r--r--arch/s390/kernel/entry64.S41
-rw-r--r--arch/s390/kernel/ftrace.c3
-rw-r--r--arch/s390/kernel/head64.S7
-rw-r--r--arch/s390/kernel/irq.c12
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c7
-rw-r--r--arch/s390/kernel/perf_cpum_cf_events.c322
-rw-r--r--arch/s390/kernel/perf_cpum_sf.c1643
-rw-r--r--arch/s390/kernel/perf_event.c174
-rw-r--r--arch/s390/kernel/process.c14
-rw-r--r--arch/s390/kernel/ptrace.c40
-rw-r--r--arch/s390/kernel/runtime_instr.c3
-rw-r--r--arch/s390/kernel/s390_ksyms.c2
-rw-r--r--arch/s390/kernel/sclp.S5
-rw-r--r--arch/s390/kernel/setup.c19
-rw-r--r--arch/s390/kernel/smp.c50
-rw-r--r--arch/s390/kernel/syscalls.S502
-rw-r--r--arch/s390/kernel/time.c6
-rw-r--r--arch/s390/kernel/topology.c1
-rw-r--r--arch/s390/kvm/Kconfig4
-rw-r--r--arch/s390/kvm/Makefile2
-rw-r--r--arch/s390/kvm/diag.c95
-rw-r--r--arch/s390/kvm/intercept.c11
-rw-r--r--arch/s390/kvm/interrupt.c704
-rw-r--r--arch/s390/kvm/irq.h22
-rw-r--r--arch/s390/kvm/kvm-s390.c309
-rw-r--r--arch/s390/kvm/kvm-s390.h25
-rw-r--r--arch/s390/kvm/priv.c54
-rw-r--r--arch/s390/kvm/sigp.c275
-rw-r--r--arch/s390/kvm/trace.h47
-rw-r--r--arch/s390/lib/Makefile3
-rw-r--r--arch/s390/lib/find.c2
-rw-r--r--arch/s390/lib/uaccess.c407
-rw-r--r--arch/s390/lib/uaccess.h21
-rw-r--r--arch/s390/lib/uaccess_mvcos.c197
-rw-r--r--arch/s390/lib/uaccess_pt.c474
-rw-r--r--arch/s390/mm/fault.c79
-rw-r--r--arch/s390/mm/hugetlbpage.c5
-rw-r--r--arch/s390/mm/init.c7
-rw-r--r--arch/s390/mm/maccess.c28
-rw-r--r--arch/s390/mm/page-states.c10
-rw-r--r--arch/s390/mm/pgtable.c177
-rw-r--r--arch/s390/mm/vmem.c2
-rw-r--r--arch/s390/net/bpf_jit_comp.c13
-rw-r--r--arch/s390/oprofile/hwsampler.c82
-rw-r--r--arch/s390/oprofile/hwsampler.h52
-rw-r--r--arch/s390/oprofile/init.c23
-rw-r--r--arch/s390/pci/pci.c36
-rw-r--r--arch/s390/pci/pci_debug.c2
-rw-r--r--arch/s390/pci/pci_dma.c21
-rw-r--r--arch/s390/pci/pci_event.c26
-rw-r--r--arch/s390/pci/pci_sysfs.c18
119 files changed, 6455 insertions, 3529 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a17c7f582e2..d68fe34799b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -52,7 +52,7 @@ config KEXEC
config AUDIT_ARCH
def_bool y
-config NO_IOPORT
+config NO_IOPORT_MAP
def_bool y
config PCI_QUIRKS
@@ -118,6 +118,7 @@ config S390
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
@@ -141,6 +142,7 @@ config S390
select OLD_SIGACTION
select OLD_SIGSUSPEND3
select SYSCTL_EXCEPTION_TRACE
+ select TTY
select VIRT_CPU_ACCOUNTING
select VIRT_TO_BUS
@@ -335,10 +337,10 @@ config SMP
a system with only one CPU, like most personal computers, say N. If
you have a system with more than one CPU, say Y.
- If you say N here, the kernel will run on single and multiprocessor
+ If you say N here, the kernel will run on uni- and multiprocessor
machines, but will use only one CPU of a multiprocessor machine. If
you say Y here, the kernel will run on many, but not all,
- singleprocessor machines. On a singleprocessor machine, the kernel
+ uniprocessor machines. On a uniprocessor machine, the kernel
will run faster if you say N here.
See also the SMP-HOWTO available at
@@ -416,6 +418,10 @@ 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"
@@ -597,7 +603,7 @@ config CRASH_DUMP
config ZFCPDUMP
def_bool n
prompt "zfcpdump support"
- depends on SMP
+ depends on 64BIT && SMP
help
Select this option if you want to build an zfcpdump enabled kernel.
Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this.
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 4c4a1cef520..47c8630c93c 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -529,6 +529,7 @@ static int __init appldata_init(void)
{
int rc;
+ init_virt_timer(&appldata_timer);
appldata_timer.function = appldata_timer_function;
appldata_timer.data = (unsigned long) &appldata_work;
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index de8e2b3b018..69b23b25ac3 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 e0af2ee5875..ddaae2f5c91 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 b9f6b4cab92..c81a74e3e25 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 91087b43e8f..b5ba8fe1cc6 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 d725c4d956e..cef073ca1f0 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/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b3feabd39f3..cf3c0089bef 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -25,6 +25,7 @@
#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
+#include <linux/spinlock.h>
#include "crypt_s390.h"
#define AES_KEYLEN_128 1
@@ -32,6 +33,7 @@
#define AES_KEYLEN_256 4
static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
static char keylen_flag;
struct s390_aes_ctx {
@@ -758,43 +760,67 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
return aes_set_key(tfm, in_key, key_len);
}
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+ unsigned int i, n;
+
+ /* only use complete blocks, max. PAGE_SIZE */
+ n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+ for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
+ memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE,
+ AES_BLOCK_SIZE);
+ crypto_inc(ctrptr + i, AES_BLOCK_SIZE);
+ }
+ return n;
+}
+
static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
struct s390_aes_ctx *sctx, struct blkcipher_walk *walk)
{
int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
- unsigned int i, n, nbytes;
- u8 buf[AES_BLOCK_SIZE];
- u8 *out, *in;
+ unsigned int n, nbytes;
+ u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE];
+ u8 *out, *in, *ctrptr = ctrbuf;
if (!walk->nbytes)
return ret;
- memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE);
+ if (spin_trylock(&ctrblk_lock))
+ ctrptr = ctrblk;
+
+ memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE);
while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
while (nbytes >= AES_BLOCK_SIZE) {
- /* only use complete blocks, max. PAGE_SIZE */
- n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
- nbytes & ~(AES_BLOCK_SIZE - 1);
- for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
- memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE,
- AES_BLOCK_SIZE);
- crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
- }
- ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
- if (ret < 0 || ret != n)
+ if (ctrptr == ctrblk)
+ n = __ctrblk_init(ctrptr, nbytes);
+ else
+ n = AES_BLOCK_SIZE;
+ ret = crypt_s390_kmctr(func, sctx->key, out, in,
+ n, ctrptr);
+ if (ret < 0 || ret != n) {
+ if (ctrptr == ctrblk)
+ spin_unlock(&ctrblk_lock);
return -EIO;
+ }
if (n > AES_BLOCK_SIZE)
- memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
+ memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE,
AES_BLOCK_SIZE);
- crypto_inc(ctrblk, AES_BLOCK_SIZE);
+ crypto_inc(ctrptr, AES_BLOCK_SIZE);
out += n;
in += n;
nbytes -= n;
}
ret = blkcipher_walk_done(desc, walk, nbytes);
}
+ if (ctrptr == ctrblk) {
+ if (nbytes)
+ memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE);
+ else
+ memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+ spin_unlock(&ctrblk_lock);
+ }
/*
* final block may be < AES_BLOCK_SIZE, copy only nbytes
*/
@@ -802,14 +828,15 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
ret = crypt_s390_kmctr(func, sctx->key, buf, in,
- AES_BLOCK_SIZE, ctrblk);
+ AES_BLOCK_SIZE, ctrbuf);
if (ret < 0 || ret != AES_BLOCK_SIZE)
return -EIO;
memcpy(out, buf, nbytes);
- crypto_inc(ctrblk, AES_BLOCK_SIZE);
+ crypto_inc(ctrbuf, AES_BLOCK_SIZE);
ret = blkcipher_walk_done(desc, walk, 0);
+ memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE);
}
- memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE);
+
return ret;
}
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index bcca01c9989..0a5aac8a941 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -25,6 +25,7 @@
#define DES3_KEY_SIZE (3 * DES_KEY_SIZE)
static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
struct s390_des_ctx {
u8 iv[DES_BLOCK_SIZE];
@@ -105,29 +106,35 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func,
}
static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
- u8 *iv, struct blkcipher_walk *walk)
+ struct blkcipher_walk *walk)
{
+ struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
int ret = blkcipher_walk_virt(desc, walk);
unsigned int nbytes = walk->nbytes;
+ struct {
+ u8 iv[DES_BLOCK_SIZE];
+ u8 key[DES3_KEY_SIZE];
+ } param;
if (!nbytes)
goto out;
- memcpy(iv, walk->iv, DES_BLOCK_SIZE);
+ memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+ memcpy(param.key, ctx->key, DES3_KEY_SIZE);
do {
/* only use complete blocks */
unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1);
u8 *out = walk->dst.virt.addr;
u8 *in = walk->src.virt.addr;
- ret = crypt_s390_kmc(func, iv, out, in, n);
+ ret = crypt_s390_kmc(func, &param, out, in, n);
if (ret < 0 || ret != n)
return -EIO;
nbytes &= DES_BLOCK_SIZE - 1;
ret = blkcipher_walk_done(desc, walk, nbytes);
} while ((nbytes = walk->nbytes));
- memcpy(walk->iv, iv, DES_BLOCK_SIZE);
+ memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
out:
return ret;
@@ -179,22 +186,20 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk);
}
static int cbc_des_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk);
}
static struct crypto_alg cbc_des_alg = {
@@ -237,9 +242,9 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key,
struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
u32 *flags = &tfm->crt_flags;
- if (!(memcmp(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
- memcmp(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
- DES_KEY_SIZE)) &&
+ if (!(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
+ crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
+ DES_KEY_SIZE)) &&
(*flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
*flags |= CRYPTO_TFM_RES_WEAK_KEY;
return -EINVAL;
@@ -327,22 +332,20 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk);
}
static int cbc_des3_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk);
}
static struct crypto_alg cbc_des3_alg = {
@@ -366,54 +369,80 @@ static struct crypto_alg cbc_des3_alg = {
}
};
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+ unsigned int i, n;
+
+ /* align to block size, max. PAGE_SIZE */
+ n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1);
+ for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
+ memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE);
+ crypto_inc(ctrptr + i, DES_BLOCK_SIZE);
+ }
+ return n;
+}
+
static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
- struct s390_des_ctx *ctx, struct blkcipher_walk *walk)
+ struct s390_des_ctx *ctx,
+ struct blkcipher_walk *walk)
{
int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
- unsigned int i, n, nbytes;
- u8 buf[DES_BLOCK_SIZE];
- u8 *out, *in;
+ unsigned int n, nbytes;
+ u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE];
+ u8 *out, *in, *ctrptr = ctrbuf;
+
+ if (!walk->nbytes)
+ return ret;
- memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE);
+ if (spin_trylock(&ctrblk_lock))
+ ctrptr = ctrblk;
+
+ memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE);
while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
while (nbytes >= DES_BLOCK_SIZE) {
- /* align to block size, max. PAGE_SIZE */
- n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
- nbytes & ~(DES_BLOCK_SIZE - 1);
- for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
- memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE,
- DES_BLOCK_SIZE);
- crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
- }
- ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
- if (ret < 0 || ret != n)
+ if (ctrptr == ctrblk)
+ n = __ctrblk_init(ctrptr, nbytes);
+ else
+ n = DES_BLOCK_SIZE;
+ ret = crypt_s390_kmctr(func, ctx->key, out, in,
+ n, ctrptr);
+ if (ret < 0 || ret != n) {
+ if (ctrptr == ctrblk)
+ spin_unlock(&ctrblk_lock);
return -EIO;
+ }
if (n > DES_BLOCK_SIZE)
- memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
+ memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE,
DES_BLOCK_SIZE);
- crypto_inc(ctrblk, DES_BLOCK_SIZE);
+ crypto_inc(ctrptr, DES_BLOCK_SIZE);
out += n;
in += n;
nbytes -= n;
}
ret = blkcipher_walk_done(desc, walk, nbytes);
}
-
+ if (ctrptr == ctrblk) {
+ if (nbytes)
+ memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE);
+ else
+ memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+ spin_unlock(&ctrblk_lock);
+ }
/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
if (nbytes) {
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
ret = crypt_s390_kmctr(func, ctx->key, buf, in,
- DES_BLOCK_SIZE, ctrblk);
+ DES_BLOCK_SIZE, ctrbuf);
if (ret < 0 || ret != DES_BLOCK_SIZE)
return -EIO;
memcpy(out, buf, nbytes);
- crypto_inc(ctrblk, DES_BLOCK_SIZE);
+ crypto_inc(ctrbuf, DES_BLOCK_SIZE);
ret = blkcipher_walk_done(desc, walk, 0);
+ memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE);
}
- memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE);
return ret;
}
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 33f57514f42..4557cb7ffdd 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/Makefile b/arch/s390/hypfs/Makefile
index 2e671d5004c..06f8d95a16c 100644
--- a/arch/s390/hypfs/Makefile
+++ b/arch/s390/hypfs/Makefile
@@ -4,4 +4,4 @@
obj-$(CONFIG_S390_HYPFS_FS) += s390_hypfs.o
-s390_hypfs-objs := inode.o hypfs_diag.o hypfs_vm.o hypfs_dbfs.o
+s390_hypfs-objs := inode.o hypfs_diag.o hypfs_vm.o hypfs_dbfs.o hypfs_sprp.o
diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h
index 79f2ac55253..b34b5ab90a3 100644
--- a/arch/s390/hypfs/hypfs.h
+++ b/arch/s390/hypfs/hypfs.h
@@ -13,6 +13,7 @@
#include <linux/debugfs.h>
#include <linux/workqueue.h>
#include <linux/kref.h>
+#include <asm/hypfs.h>
#define REG_FILE_MODE 0440
#define UPDATE_FILE_MODE 0220
@@ -36,6 +37,10 @@ extern int hypfs_vm_init(void);
extern void hypfs_vm_exit(void);
extern int hypfs_vm_create_files(struct dentry *root);
+/* Set Partition-Resource Parameter */
+int hypfs_sprp_init(void);
+void hypfs_sprp_exit(void);
+
/* debugfs interface */
struct hypfs_dbfs_file;
@@ -52,6 +57,8 @@ struct hypfs_dbfs_file {
int (*data_create)(void **data, void **data_free_ptr,
size_t *size);
void (*data_free)(const void *buf_free_ptr);
+ long (*unlocked_ioctl) (struct file *, unsigned int,
+ unsigned long);
/* Private data for hypfs_dbfs.c */
struct hypfs_dbfs_data *data;
diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index 17ab8b7b53c..2badf2bf9cd 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -81,9 +81,25 @@ static ssize_t dbfs_read(struct file *file, char __user *buf,
return rc;
}
+static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct hypfs_dbfs_file *df;
+ long rc;
+
+ df = file->f_path.dentry->d_inode->i_private;
+ mutex_lock(&df->lock);
+ if (df->unlocked_ioctl)
+ rc = df->unlocked_ioctl(file, cmd, arg);
+ else
+ rc = -ENOTTY;
+ mutex_unlock(&df->lock);
+ return rc;
+}
+
static const struct file_operations dbfs_ops = {
.read = dbfs_read,
.llseek = no_llseek,
+ .unlocked_ioctl = dbfs_ioctl,
};
int hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
new file mode 100644
index 00000000000..f043c3c7e73
--- /dev/null
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -0,0 +1,141 @@
+/*
+ * Hypervisor filesystem for Linux on s390.
+ * Set Partition-Resource Parameter interface.
+ *
+ * Copyright IBM Corp. 2013
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/compat.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <asm/compat.h>
+#include <asm/sclp.h>
+#include "hypfs.h"
+
+#define DIAG304_SET_WEIGHTS 0
+#define DIAG304_QUERY_PRP 1
+#define DIAG304_SET_CAPPING 2
+
+#define DIAG304_CMD_MAX 2
+
+static unsigned long hypfs_sprp_diag304(void *data, unsigned long cmd)
+{
+ register unsigned long _data asm("2") = (unsigned long) data;
+ register unsigned long _rc asm("3");
+ register unsigned long _cmd asm("4") = cmd;
+
+ asm volatile("diag %1,%2,0x304\n"
+ : "=d" (_rc) : "d" (_data), "d" (_cmd) : "memory");
+
+ return _rc;
+}
+
+static void hypfs_sprp_free(const void *data)
+{
+ free_page((unsigned long) data);
+}
+
+static int hypfs_sprp_create(void **data_ptr, void **free_ptr, size_t *size)
+{
+ unsigned long rc;
+ void *data;
+
+ data = (void *) get_zeroed_page(GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+ rc = hypfs_sprp_diag304(data, DIAG304_QUERY_PRP);
+ if (rc != 1) {
+ *data_ptr = *free_ptr = NULL;
+ *size = 0;
+ free_page((unsigned long) data);
+ return -EIO;
+ }
+ *data_ptr = *free_ptr = data;
+ *size = PAGE_SIZE;
+ return 0;
+}
+
+static int __hypfs_sprp_ioctl(void __user *user_area)
+{
+ struct hypfs_diag304 diag304;
+ unsigned long cmd;
+ void __user *udata;
+ void *data;
+ int rc;
+
+ if (copy_from_user(&diag304, user_area, sizeof(diag304)))
+ return -EFAULT;
+ if ((diag304.args[0] >> 8) != 0 || diag304.args[1] > DIAG304_CMD_MAX)
+ return -EINVAL;
+
+ data = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+ if (!data)
+ return -ENOMEM;
+
+ udata = (void __user *)(unsigned long) diag304.data;
+ if (diag304.args[1] == DIAG304_SET_WEIGHTS ||
+ diag304.args[1] == DIAG304_SET_CAPPING)
+ if (copy_from_user(data, udata, PAGE_SIZE)) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ cmd = *(unsigned long *) &diag304.args[0];
+ diag304.rc = hypfs_sprp_diag304(data, cmd);
+
+ if (diag304.args[1] == DIAG304_QUERY_PRP)
+ if (copy_to_user(udata, data, PAGE_SIZE)) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ rc = copy_to_user(user_area, &diag304, sizeof(diag304)) ? -EFAULT : 0;
+out:
+ free_page((unsigned long) data);
+ return rc;
+}
+
+static long hypfs_sprp_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ void __user *argp;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (is_compat_task())
+ argp = compat_ptr(arg);
+ else
+ argp = (void __user *) arg;
+ switch (cmd) {
+ case HYPFS_DIAG304:
+ return __hypfs_sprp_ioctl(argp);
+ default: /* unknown ioctl number */
+ return -ENOTTY;
+ }
+ return 0;
+}
+
+static struct hypfs_dbfs_file hypfs_sprp_file = {
+ .name = "diag_304",
+ .data_create = hypfs_sprp_create,
+ .data_free = hypfs_sprp_free,
+ .unlocked_ioctl = hypfs_sprp_ioctl,
+};
+
+int hypfs_sprp_init(void)
+{
+ if (!sclp_has_sprp())
+ return 0;
+ return hypfs_dbfs_create_file(&hypfs_sprp_file);
+}
+
+void hypfs_sprp_exit(void)
+{
+ if (!sclp_has_sprp())
+ return;
+ hypfs_dbfs_remove_file(&hypfs_sprp_file);
+}
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 24908ce149f..32040ace00e 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/hypfs/inode.c b/arch/s390/hypfs/inode.c
index ddfe09b4513..c952b981e4f 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -478,10 +478,14 @@ static int __init hypfs_init(void)
rc = -ENODATA;
goto fail_hypfs_diag_exit;
}
+ if (hypfs_sprp_init()) {
+ rc = -ENODATA;
+ goto fail_hypfs_vm_exit;
+ }
s390_kobj = kobject_create_and_add("s390", hypervisor_kobj);
if (!s390_kobj) {
rc = -ENOMEM;
- goto fail_hypfs_vm_exit;
+ goto fail_hypfs_sprp_exit;
}
rc = register_filesystem(&hypfs_type);
if (rc)
@@ -490,6 +494,8 @@ static int __init hypfs_init(void)
fail_filesystem:
kobject_put(s390_kobj);
+fail_hypfs_sprp_exit:
+ hypfs_sprp_exit();
fail_hypfs_vm_exit:
hypfs_vm_exit();
fail_hypfs_diag_exit:
@@ -502,11 +508,12 @@ fail_dbfs_exit:
static void __exit hypfs_exit(void)
{
- hypfs_diag_exit();
- hypfs_vm_exit();
- hypfs_dbfs_exit();
unregister_filesystem(&hypfs_type);
kobject_put(s390_kobj);
+ hypfs_sprp_exit();
+ hypfs_vm_exit();
+ hypfs_diag_exit();
+ hypfs_dbfs_exit();
}
module_init(hypfs_init)
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 7a5288f3479..57892a8a905 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,5 +1,7 @@
generic-y += clkdev.h
-generic-y += trace_clock.h
+generic-y += hash.h
+generic-y += mcs_spinlock.h
generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 4bbb5957ed1..bd93ff6661b 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/atomic.h b/arch/s390/include/asm/atomic.h
index fa9aaf7144b..1d4706114a4 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,23 +15,29 @@
#include <linux/compiler.h>
#include <linux/types.h>
+#include <asm/barrier.h>
#include <asm/cmpxchg.h>
#define ATOMIC_INIT(i) { (i) }
+#define __ATOMIC_NO_BARRIER "\n"
+
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
#define __ATOMIC_OR "lao"
#define __ATOMIC_AND "lan"
#define __ATOMIC_ADD "laa"
+#define __ATOMIC_BARRIER "bcr 14,0\n"
-#define __ATOMIC_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \
({ \
int old_val; \
\
typecheck(atomic_t *, ptr); \
asm volatile( \
+ __barrier \
op_string " %0,%2,%1\n" \
+ __barrier \
: "=d" (old_val), "+Q" ((ptr)->counter) \
: "d" (op_val) \
: "cc", "memory"); \
@@ -43,8 +49,9 @@
#define __ATOMIC_OR "or"
#define __ATOMIC_AND "nr"
#define __ATOMIC_ADD "ar"
+#define __ATOMIC_BARRIER "\n"
-#define __ATOMIC_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \
({ \
int old_val, new_val; \
\
@@ -82,7 +89,7 @@ static inline void atomic_set(atomic_t *v, int i)
static inline int atomic_add_return(int i, atomic_t *v)
{
- return __ATOMIC_LOOP(v, i, __ATOMIC_ADD) + i;
+ return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i;
}
static inline void atomic_add(int i, atomic_t *v)
@@ -94,12 +101,10 @@ static inline void atomic_add(int i, atomic_t *v)
: "+Q" (v->counter)
: "i" (i)
: "cc", "memory");
- } else {
- atomic_add_return(i, v);
+ return;
}
-#else
- atomic_add_return(i, v);
#endif
+ __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_NO_BARRIER);
}
#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0)
@@ -115,12 +120,12 @@ static inline void atomic_add(int i, atomic_t *v)
static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
{
- __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND);
+ __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER);
}
static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
{
- __ATOMIC_LOOP(v, mask, __ATOMIC_OR);
+ __ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER);
}
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
@@ -157,19 +162,24 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
#ifdef CONFIG_64BIT
+#define __ATOMIC64_NO_BARRIER "\n"
+
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
#define __ATOMIC64_OR "laog"
#define __ATOMIC64_AND "lang"
#define __ATOMIC64_ADD "laag"
+#define __ATOMIC64_BARRIER "bcr 14,0\n"
-#define __ATOMIC64_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \
({ \
long long old_val; \
\
typecheck(atomic64_t *, ptr); \
asm volatile( \
+ __barrier \
op_string " %0,%2,%1\n" \
+ __barrier \
: "=d" (old_val), "+Q" ((ptr)->counter) \
: "d" (op_val) \
: "cc", "memory"); \
@@ -181,8 +191,9 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
#define __ATOMIC64_OR "ogr"
#define __ATOMIC64_AND "ngr"
#define __ATOMIC64_ADD "agr"
+#define __ATOMIC64_BARRIER "\n"
-#define __ATOMIC64_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \
({ \
long long old_val, new_val; \
\
@@ -220,17 +231,32 @@ static inline void atomic64_set(atomic64_t *v, long long i)
static inline long long atomic64_add_return(long long i, atomic64_t *v)
{
- return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD) + i;
+ return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i;
+}
+
+static inline void atomic64_add(long long i, atomic64_t *v)
+{
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+ if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
+ asm volatile(
+ "agsi %0,%1\n"
+ : "+Q" (v->counter)
+ : "i" (i)
+ : "cc", "memory");
+ return;
+ }
+#endif
+ __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
}
static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v)
{
- __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND);
+ __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER);
}
static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
{
- __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR);
+ __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER);
}
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
@@ -334,25 +360,13 @@ static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v)
} while (atomic64_cmpxchg(v, old, new) != old);
}
-#endif /* CONFIG_64BIT */
-
static inline void atomic64_add(long long i, atomic64_t *v)
{
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
- if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
- asm volatile(
- "agsi %0,%1\n"
- : "+Q" (v->counter)
- : "i" (i)
- : "cc", "memory");
- } else {
- atomic64_add_return(i, v);
- }
-#else
atomic64_add_return(i, v);
-#endif
}
+#endif /* CONFIG_64BIT */
+
static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
{
long long c, old;
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 16760eeb79b..578680f6207 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -32,4 +32,19 @@
#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
#endif /* __ASM_BARRIER_H */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 6e6ad068082..52054247767 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
@@ -47,14 +47,18 @@
#include <linux/typecheck.h>
#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+#define __BITOPS_NO_BARRIER "\n"
#ifndef CONFIG_64BIT
#define __BITOPS_OR "or"
#define __BITOPS_AND "nr"
#define __BITOPS_XOR "xr"
+#define __BITOPS_BARRIER "\n"
-#define __BITOPS_LOOP(__addr, __val, __op_string) \
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \
({ \
unsigned long __old, __new; \
\
@@ -67,7 +71,7 @@
" jl 0b" \
: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
: "d" (__val) \
- : "cc"); \
+ : "cc", "memory"); \
__old; \
})
@@ -78,17 +82,20 @@
#define __BITOPS_OR "laog"
#define __BITOPS_AND "lang"
#define __BITOPS_XOR "laxg"
+#define __BITOPS_BARRIER "bcr 14,0\n"
-#define __BITOPS_LOOP(__addr, __val, __op_string) \
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \
({ \
unsigned long __old; \
\
typecheck(unsigned long *, (__addr)); \
asm volatile( \
+ __barrier \
__op_string " %0,%2,%1\n" \
+ __barrier \
: "=d" (__old), "+Q" (*(__addr)) \
: "d" (__val) \
- : "cc"); \
+ : "cc", "memory"); \
__old; \
})
@@ -97,8 +104,9 @@
#define __BITOPS_OR "ogr"
#define __BITOPS_AND "ngr"
#define __BITOPS_XOR "xgr"
+#define __BITOPS_BARRIER "\n"
-#define __BITOPS_LOOP(__addr, __val, __op_string) \
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \
({ \
unsigned long __old, __new; \
\
@@ -111,7 +119,7 @@
" jl 0b" \
: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
: "d" (__val) \
- : "cc"); \
+ : "cc", "memory"); \
__old; \
})
@@ -149,12 +157,12 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
"oi %0,%b1\n"
: "+Q" (*caddr)
: "i" (1 << (nr & 7))
- : "cc");
+ : "cc", "memory");
return;
}
#endif
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- __BITOPS_LOOP(addr, mask, __BITOPS_OR);
+ __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_NO_BARRIER);
}
static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -170,12 +178,12 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
"ni %0,%b1\n"
: "+Q" (*caddr)
: "i" (~(1 << (nr & 7)))
- : "cc");
+ : "cc", "memory");
return;
}
#endif
mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
- __BITOPS_LOOP(addr, mask, __BITOPS_AND);
+ __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_NO_BARRIER);
}
static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -191,12 +199,12 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
"xi %0,%b1\n"
: "+Q" (*caddr)
: "i" (1 << (nr & 7))
- : "cc");
+ : "cc", "memory");
return;
}
#endif
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- __BITOPS_LOOP(addr, mask, __BITOPS_XOR);
+ __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_NO_BARRIER);
}
static inline int
@@ -206,8 +214,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
unsigned long old, mask;
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- old = __BITOPS_LOOP(addr, mask, __BITOPS_OR);
- barrier();
+ old = __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_BARRIER);
return (old & mask) != 0;
}
@@ -218,8 +225,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
unsigned long old, mask;
mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
- old = __BITOPS_LOOP(addr, mask, __BITOPS_AND);
- barrier();
+ old = __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_BARRIER);
return (old & ~mask) != 0;
}
@@ -230,8 +236,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
unsigned long old, mask;
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR);
- barrier();
+ old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_BARRIER);
return (old & mask) != 0;
}
@@ -304,7 +309,7 @@ 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 f201af8be58..a9c2c068617 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/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index 23723ce5ca7..6e670f88d12 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -23,6 +23,7 @@ struct ccwgroup_device {
unsigned int count;
struct device dev;
struct ccw_device *cdev[0];
+ struct work_struct ungroup_work;
};
/**
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 4f57a4f3909..74036485635 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/cio.h b/arch/s390/include/asm/cio.h
index d42625053c3..09633920776 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -199,7 +199,7 @@ struct esw_eadm {
/**
* struct irb - interruption response block
* @scsw: subchannel status word
- * @esw: extened status word
+ * @esw: extended status word
* @ecw: extended control word
*
* The irb that is handed to the device driver when an interrupt occurs. For
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 0f636cbdf34..4236408070e 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -185,11 +185,12 @@ static inline unsigned long long __cmpxchg64(void *ptr,
{
register_pair rp_old = {.pair = old};
register_pair rp_new = {.pair = new};
+ unsigned long long *ullptr = ptr;
asm volatile(
" cds %0,%2,%1"
- : "+&d" (rp_old), "=Q" (ptr)
- : "d" (rp_new), "Q" (ptr)
+ : "+d" (rp_old), "+Q" (*ullptr)
+ : "d" (rp_new)
: "memory", "cc");
return rp_old.pair;
}
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 4bf9da03591..d350ed9d0fb 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -8,7 +8,11 @@
#include <linux/thread_info.h>
#define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64))
-#define __SC_DELOUSE(t,v) (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v))
+
+#define __SC_DELOUSE(t,v) ({ \
+ BUILD_BUG_ON(sizeof(t) > 4 && !__TYPE_IS_PTR(t)); \
+ (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \
+})
#define PSW32_MASK_PER 0x40000000UL
#define PSW32_MASK_DAT 0x04000000UL
@@ -38,7 +42,8 @@
#define PSW32_USER_BITS (PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | \
PSW32_DEFAULT_KEY | PSW32_MASK_BASE | \
- PSW32_MASK_MCHECK | PSW32_MASK_PSTATE | PSW32_ASC_HOME)
+ PSW32_MASK_MCHECK | PSW32_MASK_PSTATE | \
+ PSW32_ASC_PRIMARY)
#define COMPAT_USER_HZ 100
#define COMPAT_UTS_MACHINE "s390\0\0\0\0"
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index c879fad404c..cb700d54bd8 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -56,6 +56,96 @@ struct cpumf_ctr_info {
u32 reserved2[12];
} __packed;
+/* QUERY SAMPLING INFORMATION block */
+struct hws_qsi_info_block { /* Bit(s) */
+ unsigned int b0_13:14; /* 0-13: zeros */
+ unsigned int as:1; /* 14: basic-sampling authorization */
+ unsigned int ad:1; /* 15: diag-sampling authorization */
+ unsigned int b16_21:6; /* 16-21: zeros */
+ unsigned int es:1; /* 22: basic-sampling enable control */
+ unsigned int ed:1; /* 23: diag-sampling enable control */
+ unsigned int b24_29:6; /* 24-29: zeros */
+ unsigned int cs:1; /* 30: basic-sampling activation control */
+ unsigned int cd:1; /* 31: diag-sampling activation control */
+ unsigned int bsdes:16; /* 4-5: size of basic sampling entry */
+ unsigned int dsdes:16; /* 6-7: size of diagnostic sampling entry */
+ unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
+ unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
+ unsigned long tear; /* 24-31: TEAR contents */
+ unsigned long dear; /* 32-39: DEAR contents */
+ unsigned int rsvrd0; /* 40-43: reserved */
+ unsigned int cpu_speed; /* 44-47: CPU speed */
+ unsigned long long rsvrd1; /* 48-55: reserved */
+ unsigned long long rsvrd2; /* 56-63: reserved */
+} __packed;
+
+/* SET SAMPLING CONTROLS request block */
+struct hws_lsctl_request_block {
+ unsigned int s:1; /* 0: maximum buffer indicator */
+ unsigned int h:1; /* 1: part. level reserved for VM use*/
+ unsigned long long b2_53:52;/* 2-53: zeros */
+ unsigned int es:1; /* 54: basic-sampling enable control */
+ unsigned int ed:1; /* 55: diag-sampling enable control */
+ unsigned int b56_61:6; /* 56-61: - zeros */
+ unsigned int cs:1; /* 62: basic-sampling activation control */
+ unsigned int cd:1; /* 63: diag-sampling activation control */
+ unsigned long interval; /* 8-15: sampling interval */
+ unsigned long tear; /* 16-23: TEAR contents */
+ unsigned long dear; /* 24-31: DEAR contents */
+ /* 32-63: */
+ unsigned long rsvrd1; /* reserved */
+ unsigned long rsvrd2; /* reserved */
+ unsigned long rsvrd3; /* reserved */
+ unsigned long rsvrd4; /* reserved */
+} __packed;
+
+struct hws_basic_entry {
+ unsigned int def:16; /* 0-15 Data Entry Format */
+ unsigned int R:4; /* 16-19 reserved */
+ unsigned int U:4; /* 20-23 Number of unique instruct. */
+ unsigned int z:2; /* zeros */
+ unsigned int T:1; /* 26 PSW DAT mode */
+ unsigned int W:1; /* 27 PSW wait state */
+ unsigned int P:1; /* 28 PSW Problem state */
+ unsigned int AS:2; /* 29-30 PSW address-space control */
+ unsigned int I:1; /* 31 entry valid or invalid */
+ unsigned int:16;
+ unsigned int prim_asn:16; /* primary ASN */
+ unsigned long long ia; /* Instruction Address */
+ unsigned long long gpp; /* Guest Program Parameter */
+ unsigned long long hpp; /* Host Program Parameter */
+} __packed;
+
+struct hws_diag_entry {
+ unsigned int def:16; /* 0-15 Data Entry Format */
+ unsigned int R:14; /* 16-19 and 20-30 reserved */
+ unsigned int I:1; /* 31 entry valid or invalid */
+ u8 data[]; /* Machine-dependent sample data */
+} __packed;
+
+struct hws_combined_entry {
+ struct hws_basic_entry basic; /* Basic-sampling data entry */
+ struct hws_diag_entry diag; /* Diagnostic-sampling data entry */
+} __packed;
+
+struct hws_trailer_entry {
+ union {
+ struct {
+ unsigned int f:1; /* 0 - Block Full Indicator */
+ unsigned int a:1; /* 1 - Alert request control */
+ unsigned int t:1; /* 2 - Timestamp format */
+ unsigned long long:61; /* 3 - 63: Reserved */
+ };
+ unsigned long long flags; /* 0 - 63: All indicators */
+ };
+ unsigned long long overflow; /* 64 - sample Overflow count */
+ unsigned char timestamp[16]; /* 16 - 31 timestamp */
+ unsigned long long reserved1; /* 32 -Reserved */
+ unsigned long long reserved2; /* */
+ unsigned long long progusage1; /* 48 - reserved for programming use */
+ unsigned long long progusage2; /* */
+} __packed;
+
/* Query counter information */
static inline int qctri(struct cpumf_ctr_info *info)
{
@@ -99,4 +189,95 @@ static inline int ecctr(u64 ctr, u64 *val)
return cc;
}
+/* Query sampling information */
+static inline int qsi(struct hws_qsi_info_block *info)
+{
+ int cc;
+ cc = 1;
+
+ asm volatile(
+ "0: .insn s,0xb2860000,0(%1)\n"
+ "1: lhi %0,0\n"
+ "2:\n"
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+ : "=d" (cc), "+a" (info)
+ : "m" (*info)
+ : "cc", "memory");
+
+ return cc ? -EINVAL : 0;
+}
+
+/* Load sampling controls */
+static inline int lsctl(struct hws_lsctl_request_block *req)
+{
+ int cc;
+
+ cc = 1;
+ asm volatile(
+ "0: .insn s,0xb2870000,0(%1)\n"
+ "1: ipm %0\n"
+ " srl %0,28\n"
+ "2:\n"
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+ : "+d" (cc), "+a" (req)
+ : "m" (*req)
+ : "cc", "memory");
+
+ return cc ? -EINVAL : 0;
+}
+
+/* Sampling control helper functions */
+
+#include <linux/time.h>
+
+static inline unsigned long freq_to_sample_rate(struct hws_qsi_info_block *qsi,
+ unsigned long freq)
+{
+ return (USEC_PER_SEC / freq) * qsi->cpu_speed;
+}
+
+static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi,
+ unsigned long rate)
+{
+ return USEC_PER_SEC * qsi->cpu_speed / rate;
+}
+
+#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL
+#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
+
+/* Return TOD timestamp contained in an trailer entry */
+static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
+{
+ /* TOD in STCKE format */
+ if (te->t)
+ return *((unsigned long long *) &te->timestamp[1]);
+
+ /* TOD in STCK format */
+ return *((unsigned long long *) &te->timestamp[0]);
+}
+
+/* Return pointer to trailer entry of an sample data block */
+static inline unsigned long *trailer_entry_ptr(unsigned long v)
+{
+ void *ret;
+
+ ret = (void *) v;
+ ret += PAGE_SIZE;
+ ret -= sizeof(struct hws_trailer_entry);
+
+ return (unsigned long *) ret;
+}
+
+/* Return if the entry in the sample data block table (sdbt)
+ * is a link to the next sdbt */
+static inline int is_link_entry(unsigned long *s)
+{
+ return *s & 0x1ul ? 1 : 0;
+}
+
+/* Return pointer to the linked sdbt */
+static inline unsigned long *get_next_sdbt(unsigned long *s)
+{
+ return (unsigned long *) (*s & ~0x1ul);
+}
#endif /* _ASM_S390_CPU_MF_H */
diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h
index 7e1c917bbba..09d1dd46bd5 100644
--- a/arch/s390/include/asm/css_chars.h
+++ b/arch/s390/include/asm/css_chars.h
@@ -29,6 +29,8 @@ struct css_general_char {
u32 fcx : 1; /* bit 88 */
u32 : 19;
u32 alt_ssi : 1; /* bit 108 */
+ u32:1;
+ u32 narf:1; /* bit 110 */
} __packed;
extern struct css_general_char css_general_characteristics;
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 51bcaa0fdee..69cf5b5eddc 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -1,23 +1,63 @@
#ifndef _ASM_S390_FUTEX_H
#define _ASM_S390_FUTEX_H
-#include <linux/futex.h>
#include <linux/uaccess.h>
+#include <linux/futex.h>
+#include <asm/mmu_context.h>
#include <asm/errno.h>
-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg) \
+ asm volatile( \
+ " sacf 256\n" \
+ "0: l %1,0(%6)\n" \
+ "1:"insn \
+ "2: cs %1,%2,0(%6)\n" \
+ "3: jl 1b\n" \
+ " lhi %0,0\n" \
+ "4: sacf 768\n" \
+ EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b) \
+ : "=d" (ret), "=&d" (oldval), "=&d" (newval), \
+ "=m" (*uaddr) \
+ : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \
+ "m" (*uaddr) : "cc");
+
+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;
int oparg = (encoded_op << 8) >> 20;
int cmparg = (encoded_op << 20) >> 20;
- int oldval, ret;
+ int oldval = 0, newval, ret;
+ update_primary_asce(current);
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
pagefault_disable();
- ret = uaccess.futex_atomic_op(op, uaddr, oparg, &oldval);
+ switch (op) {
+ case FUTEX_OP_SET:
+ __futex_atomic_op("lr %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_ADD:
+ __futex_atomic_op("lr %2,%1\nar %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_OR:
+ __futex_atomic_op("lr %2,%1\nor %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_ANDN:
+ __futex_atomic_op("lr %2,%1\nnr %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_XOR:
+ __futex_atomic_op("lr %2,%1\nxr %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ default:
+ ret = -ENOSYS;
+ }
pagefault_enable();
if (!ret) {
@@ -37,7 +77,20 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
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);
+ int ret;
+
+ update_primary_asce(current);
+ asm volatile(
+ " sacf 256\n"
+ "0: cs %1,%4,0(%5)\n"
+ "1: la %0,0\n"
+ "2: sacf 768\n"
+ EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ : "=d" (ret), "+d" (oldval), "=m" (*uaddr)
+ : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
+ : "cc", "memory");
+ *uval = oldval;
+ return ret;
}
#endif /* _ASM_S390_FUTEX_H */
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 5f8bcc5fe42..c4dd400a279 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -16,6 +16,20 @@
/* This number is used when no interrupt has been assigned */
#define NO_IRQ 0
+/* External interruption codes */
+#define EXT_IRQ_INTERRUPT_KEY 0x0040
+#define EXT_IRQ_CLK_COMP 0x1004
+#define EXT_IRQ_CPU_TIMER 0x1005
+#define EXT_IRQ_WARNING_TRACK 0x1007
+#define EXT_IRQ_MALFUNC_ALERT 0x1200
+#define EXT_IRQ_EMERGENCY_SIG 0x1201
+#define EXT_IRQ_EXTERNAL_CALL 0x1202
+#define EXT_IRQ_TIMING_ALERT 0x1406
+#define EXT_IRQ_MEASURE_ALERT 0x1407
+#define EXT_IRQ_SERVICE_SIG 0x2401
+#define EXT_IRQ_CP_SERVICE 0x2603
+#define EXT_IRQ_IUCV 0x4000
+
#ifndef __ASSEMBLY__
#include <linux/hardirq.h>
@@ -53,6 +67,7 @@ enum interruption_class {
IRQIO_PCI,
IRQIO_MSI,
IRQIO_VIR,
+ IRQIO_VAI,
NMI_NMI,
CPU_RST,
NR_ARCH_IRQS
@@ -76,8 +91,8 @@ struct ext_code {
typedef void (*ext_int_handler_t)(struct ext_code, unsigned int, unsigned long);
-int register_external_interrupt(u16 code, ext_int_handler_t handler);
-int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
+int register_external_irq(u16 code, ext_int_handler_t handler);
+int unregister_external_irq(u16 code, ext_int_handler_t handler);
enum irq_subclass {
IRQ_SUBCLASS_MEASUREMENT_ALERT = 5,
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index d5bc3750616..154b60089be 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -16,12 +16,22 @@
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
+#include <linux/kvm.h>
#include <asm/debug.h>
#include <asm/cpu.h>
+#include <asm/isc.h>
#define KVM_MAX_VCPUS 64
#define KVM_USER_MEM_SLOTS 32
+/*
+ * These seem to be used for allocating ->chip in the routing table,
+ * which we don't use. 4096 is an out-of-thin-air value. If we need
+ * to look at ->chip later on, we'll need to revisit this.
+ */
+#define KVM_NR_IRQCHIPS 1
+#define KVM_IRQCHIP_NUM_PINS 4096
+
struct sca_entry {
atomic_t scn;
__u32 reserved;
@@ -106,9 +116,26 @@ struct kvm_s390_sie_block {
__u64 gbea; /* 0x0180 */
__u8 reserved188[24]; /* 0x0188 */
__u32 fac; /* 0x01a0 */
- __u8 reserved1a4[92]; /* 0x01a4 */
+ __u8 reserved1a4[20]; /* 0x01a4 */
+ __u64 cbrlo; /* 0x01b8 */
+ __u8 reserved1c0[30]; /* 0x01c0 */
+ __u64 pp; /* 0x01de */
+ __u8 reserved1e6[2]; /* 0x01e6 */
+ __u64 itdba; /* 0x01e8 */
+ __u8 reserved1f0[16]; /* 0x01f0 */
} __attribute__((packed));
+struct kvm_s390_itdb {
+ __u8 data[256];
+} __packed;
+
+struct sie_page {
+ struct kvm_s390_sie_block sie_block;
+ __u8 reserved200[1024]; /* 0x0200 */
+ struct kvm_s390_itdb itdb; /* 0x0600 */
+ __u8 reserved700[2304]; /* 0x0700 */
+} __packed;
+
struct kvm_vcpu_stat {
u32 exit_userspace;
u32 exit_null;
@@ -142,6 +169,7 @@ 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;
@@ -155,18 +183,6 @@ struct kvm_vcpu_stat {
u32 diagnose_9c;
};
-struct kvm_s390_io_info {
- __u16 subchannel_id; /* 0x0b8 */
- __u16 subchannel_nr; /* 0x0ba */
- __u32 io_int_parm; /* 0x0bc */
- __u32 io_int_word; /* 0x0c0 */
-};
-
-struct kvm_s390_ext_info {
- __u32 ext_params;
- __u64 ext_params2;
-};
-
#define PGM_OPERATION 0x01
#define PGM_PRIVILEGED_OP 0x02
#define PGM_EXECUTE 0x03
@@ -175,27 +191,6 @@ struct kvm_s390_ext_info {
#define PGM_SPECIFICATION 0x06
#define PGM_DATA 0x07
-struct kvm_s390_pgm_info {
- __u16 code;
-};
-
-struct kvm_s390_prefix_info {
- __u32 address;
-};
-
-struct kvm_s390_extcall_info {
- __u16 code;
-};
-
-struct kvm_s390_emerg_info {
- __u16 code;
-};
-
-struct kvm_s390_mchk_info {
- __u64 cr14;
- __u64 mcic;
-};
-
struct kvm_s390_interrupt_info {
struct list_head list;
u64 type;
@@ -230,9 +225,8 @@ struct kvm_s390_float_interrupt {
struct list_head list;
atomic_t active;
int next_rr_cpu;
- unsigned long idle_mask[(KVM_MAX_VCPUS + sizeof(long) - 1)
- / sizeof(long)];
- struct kvm_s390_local_interrupt *local_int[KVM_MAX_VCPUS];
+ unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+ unsigned int irq_count;
};
@@ -249,6 +243,10 @@ struct kvm_vcpu_arch {
u64 stidp_data;
};
struct gmap *gmap;
+#define KVM_S390_PFAULT_TOKEN_INVALID (-1UL)
+ unsigned long pfault_token;
+ unsigned long pfault_select;
+ unsigned long pfault_compare;
};
struct kvm_vm_stat {
@@ -258,12 +256,36 @@ struct kvm_vm_stat {
struct kvm_arch_memory_slot {
};
+struct s390_map_info {
+ struct list_head list;
+ __u64 guest_addr;
+ __u64 addr;
+ struct page *page;
+};
+
+struct s390_io_adapter {
+ unsigned int id;
+ int isc;
+ bool maskable;
+ bool masked;
+ bool swap;
+ struct rw_semaphore maps_lock;
+ struct list_head maps;
+ atomic_t nr_maps;
+};
+
+#define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8)
+#define MAX_S390_ADAPTER_MAPS 256
+
struct kvm_arch{
struct sca_block *sca;
debug_info_t *dbf;
struct kvm_s390_float_interrupt float_int;
+ struct kvm_device *flic;
struct gmap *gmap;
int css_support;
+ int use_irqchip;
+ struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
};
#define KVM_HVA_ERR_BAD (-1UL)
@@ -274,6 +296,24 @@ static inline bool kvm_is_error_hva(unsigned long addr)
return IS_ERR_VALUE(addr);
}
+#define ASYNC_PF_PER_VCPU 64
+struct kvm_vcpu;
+struct kvm_async_pf;
+struct kvm_arch_async_pf {
+ unsigned long pfault_token;
+};
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+
extern int sie64a(struct kvm_s390_sie_block *, u64 *);
extern char sie_exit;
#endif
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index ff132ac64dd..f77695a82f6 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -1,9 +1,11 @@
#ifndef __MMU_H
#define __MMU_H
+#include <linux/cpumask.h>
#include <linux/errno.h>
typedef struct {
+ cpumask_t cpu_attach_mask;
atomic_t attach_count;
unsigned int flush_mm;
spinlock_t list_lock;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5d1f950704d..71be346d0e3 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
+ cpumask_clear(&mm->context.cpu_attach_mask);
atomic_set(&mm->context.attach_count, 0);
mm->context.flush_mm = 0;
mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
@@ -29,32 +30,81 @@ static inline int init_new_context(struct task_struct *tsk,
#define destroy_context(mm) do { } while (0)
-#ifndef CONFIG_64BIT
-#define LCTL_OPCODE "lctl"
-#else
-#define LCTL_OPCODE "lctlg"
-#endif
-
-static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
+static inline void update_user_asce(struct mm_struct *mm, int load_primary)
{
pgd_t *pgd = mm->pgd;
S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
- /* Load primary space page table origin. */
- asm volatile(LCTL_OPCODE" 1,1,%0\n" : : "m" (S390_lowcore.user_asce));
+ if (load_primary)
+ __ctl_load(S390_lowcore.user_asce, 1, 1);
set_fs(current->thread.mm_segment);
}
+static inline void clear_user_asce(struct mm_struct *mm, int load_primary)
+{
+ S390_lowcore.user_asce = S390_lowcore.kernel_asce;
+
+ if (load_primary)
+ __ctl_load(S390_lowcore.user_asce, 1, 1);
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
+}
+
+static inline void update_primary_asce(struct task_struct *tsk)
+{
+ unsigned long asce;
+
+ __ctl_store(asce, 1, 1);
+ if (asce != S390_lowcore.kernel_asce)
+ __ctl_load(S390_lowcore.kernel_asce, 1, 1);
+ set_tsk_thread_flag(tsk, TIF_ASCE);
+}
+
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();
+
+ update_primary_asce(tsk);
+ if (prev == next)
+ return;
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
+ if (atomic_inc_return(&next->context.attach_count) >> 16) {
+ /* Delay update_user_asce until all TLB flushes are done. */
+ set_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+ /* Clear old ASCE by loading the kernel ASCE. */
+ clear_user_asce(next, 0);
+ } else {
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+ update_user_asce(next, 0);
+ 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);
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+}
+
+#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_user_asce(mm, 0);
+ 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/pci.h b/arch/s390/include/asm/pci.h
index c129ab2ac73..2583466f576 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -144,6 +144,7 @@ int clp_disable_fh(struct zpci_dev *);
void zpci_event_error(void *);
void zpci_event_availability(void *);
void zpci_rescan(void);
+bool zpci_is_enabled(void);
#else /* CONFIG_PCI */
static inline void zpci_event_error(void *e) {}
static inline void zpci_event_availability(void *e) {}
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 1141fb3e7b2..159a8ec6da9 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -1,21 +1,40 @@
/*
* Performance event support - s390 specific definitions.
*
- * Copyright IBM Corp. 2009, 2012
+ * Copyright IBM Corp. 2009, 2013
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
* Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
*/
-#include <asm/cpu_mf.h>
+#ifndef _ASM_S390_PERF_EVENT_H
+#define _ASM_S390_PERF_EVENT_H
-/* CPU-measurement counter facility */
-#define PERF_CPUM_CF_MAX_CTR 256
+#ifdef CONFIG_64BIT
+
+#include <linux/perf_event.h>
+#include <linux/device.h>
+#include <asm/cpu_mf.h>
/* Per-CPU flags for PMU states */
#define PMU_F_RESERVED 0x1000
#define PMU_F_ENABLED 0x2000
+#define PMU_F_IN_USE 0x4000
+#define PMU_F_ERR_IBE 0x0100
+#define PMU_F_ERR_LSDA 0x0200
+#define PMU_F_ERR_MASK (PMU_F_ERR_IBE|PMU_F_ERR_LSDA)
+
+/* Perf defintions for PMU event attributes in sysfs */
+extern __init const struct attribute_group **cpumf_cf_event_group(void);
+extern ssize_t cpumf_events_sysfs_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page);
+#define EVENT_VAR(_cat, _name) event_attr_##_cat##_##_name
+#define EVENT_PTR(_cat, _name) (&EVENT_VAR(_cat, _name).attr.attr)
+
+#define CPUMF_EVENT_ATTR(cat, name, id) \
+ PMU_EVENT_ATTR(name, EVENT_VAR(cat, name), id, cpumf_events_sysfs_show)
+#define CPUMF_EVENT_PTR(cat, name) EVENT_PTR(cat, name)
-#ifdef CONFIG_64BIT
/* Perf callbacks */
struct pt_regs;
@@ -23,4 +42,55 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
+/* Perf pt_regs extension for sample-data-entry indicators */
+struct perf_sf_sde_regs {
+ unsigned char in_guest:1; /* guest sample */
+ unsigned long reserved:63; /* reserved */
+};
+
+/* Perf PMU definitions for the counter facility */
+#define PERF_CPUM_CF_MAX_CTR 256
+
+/* Perf PMU definitions for the sampling facility */
+#define PERF_CPUM_SF_MAX_CTR 2
+#define PERF_EVENT_CPUM_SF 0xB0000UL /* Event: Basic-sampling */
+#define PERF_EVENT_CPUM_SF_DIAG 0xBD000UL /* Event: Combined-sampling */
+#define PERF_CPUM_SF_BASIC_MODE 0x0001 /* Basic-sampling flag */
+#define PERF_CPUM_SF_DIAG_MODE 0x0002 /* Diagnostic-sampling flag */
+#define PERF_CPUM_SF_MODE_MASK (PERF_CPUM_SF_BASIC_MODE| \
+ PERF_CPUM_SF_DIAG_MODE)
+#define PERF_CPUM_SF_FULL_BLOCKS 0x0004 /* Process full SDBs only */
+
+#define REG_NONE 0
+#define REG_OVERFLOW 1
+#define OVERFLOW_REG(hwc) ((hwc)->extra_reg.config)
+#define SFB_ALLOC_REG(hwc) ((hwc)->extra_reg.alloc)
+#define RAWSAMPLE_REG(hwc) ((hwc)->config)
+#define TEAR_REG(hwc) ((hwc)->last_tag)
+#define SAMPL_RATE(hwc) ((hwc)->event_base)
+#define SAMPL_FLAGS(hwc) ((hwc)->config_base)
+#define SAMPL_DIAG_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE)
+#define SDB_FULL_BLOCKS(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS)
+
+/* Structure for sampling data entries to be passed as perf raw sample data
+ * to user space. Note that raw sample data must be aligned and, thus, might
+ * be padded with zeros.
+ */
+struct sf_raw_sample {
+#define SF_RAW_SAMPLE_BASIC PERF_CPUM_SF_BASIC_MODE
+#define SF_RAW_SAMPLE_DIAG PERF_CPUM_SF_DIAG_MODE
+ u64 format;
+ u32 size; /* Size of sf_raw_sample */
+ u16 bsdes; /* Basic-sampling data entry size */
+ u16 dsdes; /* Diagnostic-sampling data entry size */
+ struct hws_basic_entry basic; /* Basic-sampling data entry */
+ struct hws_diag_entry diag; /* Diagnostic-sampling data entry */
+ u8 padding[]; /* Padding to next multiple of 8 */
+} __packed;
+
+/* Perf hardware reserve and release functions */
+int perf_reserve_sampling(void);
+void perf_release_sampling(void);
+
#endif /* CONFIG_64BIT */
+#endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index e1408ddb94f..884017cbfa9 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 2204400d0bd..12f75313e08 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 */
@@ -767,6 +782,7 @@ static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
* @table: pointer to the page directory
* @asce: address space control element for gmap page table
* @crst_list: list of all crst tables used in the guest address space
+ * @pfault_enabled: defines if pfaults are applicable for the guest
*/
struct gmap {
struct list_head list;
@@ -775,6 +791,7 @@ struct gmap {
unsigned long asce;
void *private;
struct list_head crst_list;
+ bool pfault_enabled;
};
/**
@@ -821,20 +838,20 @@ 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 +869,7 @@ 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 +899,12 @@ 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 +1058,64 @@ 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_ipte_local(unsigned long address, pte_t *ptep)
+{
+ unsigned long pto = (unsigned long) ptep;
+
+#ifndef CONFIG_64BIT
+ /* pto in ESA mode must point to the start of the segment table */
+ pto &= 0x7ffffc00;
+#endif
+ /* Invalidation + local TLB flush for the pte */
+ asm volatile(
+ " .insn rrf,0xb2210000,%2,%3,0,1"
+ : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
+}
+
+static inline void ptep_flush_direct(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ int active, count;
+
+ if (pte_val(*ptep) & _PAGE_INVALID)
+ return;
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+ __ptep_ipte_local(address, ptep);
+ else
+ __ptep_ipte(address, ptep);
+ atomic_sub(0x10000, &mm->context.attach_count);
}
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 +1128,11 @@ 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 +1174,7 @@ 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 +1198,11 @@ 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 +1235,17 @@ 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 +1269,7 @@ 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 +1294,7 @@ 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 +1320,10 @@ 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);
@@ -1347,35 +1407,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
#define pte_unmap(pte) do { } while (0)
-static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
-{
- unsigned long sto = (unsigned long) pmdp -
- pmd_index(address) * sizeof(pmd_t);
-
- if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)) {
- asm volatile(
- " .insn rrf,0xb98e0000,%2,%3,0,0"
- : "=m" (*pmdp)
- : "m" (*pmdp), "a" (sto),
- "a" ((address & HPAGE_MASK))
- : "cc"
- );
- }
-}
-
-static inline void __pmd_csp(pmd_t *pmdp)
-{
- register unsigned long reg2 asm("2") = pmd_val(*pmdp);
- register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
- _SEGMENT_ENTRY_INVALID;
- register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
-
- asm volatile(
- " csp %1,%3"
- : "=m" (*pmdp)
- : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
-}
-
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
{
@@ -1444,15 +1475,81 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */
+static inline void __pmdp_csp(pmd_t *pmdp)
+{
+ register unsigned long reg2 asm("2") = pmd_val(*pmdp);
+ register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
+ _SEGMENT_ENTRY_INVALID;
+ register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
+
+ asm volatile(
+ " csp %1,%3"
+ : "=m" (*pmdp)
+ : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+}
+
+static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp)
+{
+ unsigned long sto;
+
+ sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t);
+ asm volatile(
+ " .insn rrf,0xb98e0000,%2,%3,0,0"
+ : "=m" (*pmdp)
+ : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK))
+ : "cc" );
+}
+
+static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp)
+{
+ unsigned long sto;
+
+ sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t);
+ asm volatile(
+ " .insn rrf,0xb98e0000,%2,%3,0,1"
+ : "=m" (*pmdp)
+ : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK))
+ : "cc" );
+}
+
+static inline void pmdp_flush_direct(struct mm_struct *mm,
+ unsigned long address, pmd_t *pmdp)
+{
+ int active, count;
+
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+ return;
+ if (!MACHINE_HAS_IDTE) {
+ __pmdp_csp(pmdp);
+ return;
+ }
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+ __pmdp_idte_local(address, pmdp);
+ else
+ __pmdp_idte(address, pmdp);
+ atomic_sub(0x10000, &mm->context.attach_count);
+}
+
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
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+ return;
+ 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 if (MACHINE_HAS_IDTE)
+ __pmdp_idte(address, pmdp);
+ else
+ __pmdp_csp(pmdp);
+ atomic_sub(0x10000, &mm->context.attach_count);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -1504,7 +1601,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
pmd_t pmd;
pmd = *pmdp;
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(vma->vm_mm, address, pmdp);
*pmdp = pmd_mkold(pmd);
return pmd_young(pmd);
}
@@ -1515,7 +1612,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
{
pmd_t pmd = *pmdp;
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(mm, address, pmdp);
pmd_clear(pmdp);
return pmd;
}
@@ -1531,7 +1628,7 @@ static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
static inline void pmdp_invalidate(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(vma->vm_mm, address, pmdp);
}
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
@@ -1541,7 +1638,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
pmd_t pmd = *pmdp;
if (pmd_write(pmd)) {
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(mm, address, pmdp);
set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd));
}
}
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 0a876bc543d..dc5fc4f90e5 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -79,6 +79,7 @@ struct thread_struct {
unsigned long ksp; /* kernel stack pointer */
mm_segment_t mm_segment;
unsigned long gmap_addr; /* address of last gmap fault. */
+ unsigned int gmap_pfault; /* signal of a pending guest pfault */
struct per_regs per_user; /* User specified PER registers */
struct per_event per_event; /* Cause of the last PER trap */
unsigned long per_flags; /* Flags to control debug behavior */
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 9c82cebddab..f4783c0b7b4 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/qdio.h b/arch/s390/include/asm/qdio.h
index 57d0d7e794b..d786c634e05 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -336,7 +336,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
#define QDIO_FLAG_CLEANUP_USING_HALT 0x02
/**
- * struct qdio_initialize - qdio initalization data
+ * struct qdio_initialize - qdio initialization data
* @cdev: associated ccw device
* @q_format: queue format
* @adapter_name: name for the adapter
@@ -378,6 +378,34 @@ struct qdio_initialize {
struct qdio_outbuf_state *output_sbal_state_array;
};
+/**
+ * enum qdio_brinfo_entry_type - type of address entry for qdio_brinfo_desc()
+ * @l3_ipv6_addr: entry contains IPv6 address
+ * @l3_ipv4_addr: entry contains IPv4 address
+ * @l2_addr_lnid: entry contains MAC address and VLAN ID
+ */
+enum qdio_brinfo_entry_type {l3_ipv6_addr, l3_ipv4_addr, l2_addr_lnid};
+
+/**
+ * struct qdio_brinfo_entry_XXX - Address entry for qdio_brinfo_desc()
+ * @nit: Network interface token
+ * @addr: Address of one of the three types
+ *
+ * The struct is passed to the callback function by qdio_brinfo_desc()
+ */
+struct qdio_brinfo_entry_l3_ipv6 {
+ u64 nit;
+ struct { unsigned char _s6_addr[16]; } addr;
+} __packed;
+struct qdio_brinfo_entry_l3_ipv4 {
+ u64 nit;
+ struct { uint32_t _s_addr; } addr;
+} __packed;
+struct qdio_brinfo_entry_l2 {
+ u64 nit;
+ struct { u8 mac[6]; u16 lnid; } addr_lnid;
+} __packed;
+
#define QDIO_STATE_INACTIVE 0x00000002 /* after qdio_cleanup */
#define QDIO_STATE_ESTABLISHED 0x00000004 /* after qdio_establish */
#define QDIO_STATE_ACTIVE 0x00000008 /* after qdio_activate */
@@ -399,5 +427,10 @@ extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *);
extern int qdio_shutdown(struct ccw_device *, int);
extern int qdio_free(struct ccw_device *);
extern int qdio_get_ssqd_desc(struct ccw_device *, struct qdio_ssqd_desc *);
+extern int qdio_pnso_brinfo(struct subchannel_id schid,
+ int cnc, u16 *response,
+ void (*cb)(void *priv, enum qdio_brinfo_entry_type type,
+ void *entry),
+ void *priv);
#endif /* __QDIO_H__ */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 2f390956c7c..2f5e9932b4d 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -46,14 +46,16 @@ 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);
int sclp_chp_deconfigure(struct chp_id chpid);
int sclp_chp_read_info(struct sclp_chp_info *info);
void sclp_get_ipl_info(struct sclp_ipl_info *info);
-bool sclp_has_linemode(void);
-bool sclp_has_vt220(void);
+bool __init sclp_has_linemode(void);
+bool __init sclp_has_vt220(void);
+bool sclp_has_sprp(void);
int sclp_pci_configure(u32 fid);
int sclp_pci_deconfigure(u32 fid);
int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 94cfbe442f1..b31b22dba94 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)
@@ -69,6 +68,7 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
#define MACHINE_FLAG_TOPOLOGY (1UL << 14)
#define MACHINE_FLAG_TE (1UL << 15)
#define MACHINE_FLAG_RRBM (1UL << 16)
+#define MACHINE_FLAG_TLB_LC (1UL << 17)
#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM)
#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -85,26 +85,26 @@ 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)
#define MACHINE_HAS_TOPOLOGY (0)
#define MACHINE_HAS_TE (0)
#define MACHINE_HAS_RRBM (0)
+#define MACHINE_HAS_TLB_LC (0)
#else /* CONFIG_64BIT */
#define MACHINE_HAS_IEEE (1)
#define MACHINE_HAS_CSP (1)
#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)
#define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
#define MACHINE_HAS_TE (S390_lowcore.machine_flags & MACHINE_FLAG_TE)
#define MACHINE_HAS_RRBM (S390_lowcore.machine_flags & MACHINE_FLAG_RRBM)
+#define MACHINE_HAS_TLB_LC (S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
#endif /* CONFIG_64BIT */
/*
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index 5a87d16d3e7..d091aa1aaf1 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -5,6 +5,7 @@
#define SIGP_SENSE 1
#define SIGP_EXTERNAL_CALL 2
#define SIGP_EMERGENCY_SIGNAL 3
+#define SIGP_START 4
#define SIGP_STOP 5
#define SIGP_RESTART 6
#define SIGP_STOP_AND_STORE_STATUS 9
@@ -12,6 +13,7 @@
#define SIGP_SET_PREFIX 13
#define SIGP_STORE_STATUS_AT_ADDRESS 14
#define SIGP_SET_ARCHITECTURE 18
+#define SIGP_COND_EMERGENCY_SIGNAL 19
#define SIGP_SENSE_RUNNING 21
/* SIGP condition codes */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 29c81f82705..e759181357f 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -132,6 +132,7 @@ static inline void restore_access_regs(unsigned int *acrs)
update_cr_regs(next); \
} \
prev = __switch_to(prev,next); \
+ update_primary_asce(current); \
} while (0)
#define finish_arch_switch(prev) do { \
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 10e0fcd3633..50630e6a35d 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -81,6 +81,8 @@ 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_ASCE 5 /* primary asce needs fixup / uaccess */
#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 +93,14 @@ 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<<TIF_SYSCALL)
#define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1<<TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED)
+#define _TIF_TLB_WAIT (1<<TIF_TLB_WAIT)
+#define _TIF_ASCE (1<<TIF_ASCE)
#define _TIF_PER_TRAP (1<<TIF_PER_TRAP)
#define _TIF_MCCK_PENDING (1<<TIF_MCCK_PENDING)
#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 2cb846c4b37..c544b6f05d9 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -57,8 +57,6 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
tlb->end = end;
tlb->fullmm = !(start | (end+1));
tlb->batch = NULL;
- if (tlb->fullmm)
- __tlb_flush_mm(mm);
}
static inline void tlb_flush_mmu(struct mmu_gather *tlb)
@@ -96,9 +94,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
unsigned long address)
{
- if (!tlb->fullmm)
- return page_table_free_rcu(tlb, (unsigned long *) pte);
- page_table_free(tlb->mm, (unsigned long *) pte);
+ page_table_free_rcu(tlb, (unsigned long *) pte);
}
/*
@@ -114,9 +110,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
#ifdef CONFIG_64BIT
if (tlb->mm->context.asce_limit <= (1UL << 31))
return;
- if (!tlb->fullmm)
- return tlb_remove_table(tlb, pmd);
- crst_table_free(tlb->mm, (unsigned long *) pmd);
+ tlb_remove_table(tlb, pmd);
#endif
}
@@ -133,9 +127,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
#ifdef CONFIG_64BIT
if (tlb->mm->context.asce_limit <= (1UL << 42))
return;
- if (!tlb->fullmm)
- return tlb_remove_table(tlb, pud);
- crst_table_free(tlb->mm, (unsigned long *) pud);
+ tlb_remove_table(tlb, pud);
#endif
}
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index f9fef0425fe..16c9c88658c 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -7,19 +7,41 @@
#include <asm/pgalloc.h>
/*
- * Flush all tlb entries on the local cpu.
+ * Flush all TLB entries on the local CPU.
*/
static inline void __tlb_flush_local(void)
{
asm volatile("ptlb" : : : "memory");
}
-#ifdef CONFIG_SMP
/*
- * Flush all tlb entries on all cpus.
+ * Flush TLB entries for a specific ASCE on all CPUs
*/
+static inline void __tlb_flush_idte(unsigned long asce)
+{
+ /* Global TLB flush for the mm */
+ asm volatile(
+ " .insn rrf,0xb98e0000,0,%0,%1,0"
+ : : "a" (2048), "a" (asce) : "cc");
+}
+
+/*
+ * Flush TLB entries for a specific ASCE on the local CPU
+ */
+static inline void __tlb_flush_idte_local(unsigned long asce)
+{
+ /* Local TLB flush for the mm */
+ asm volatile(
+ " .insn rrf,0xb98e0000,0,%0,%1,1"
+ : : "a" (2048), "a" (asce) : "cc");
+}
+
+#ifdef CONFIG_SMP
void smp_ptlb_all(void);
+/*
+ * Flush all TLB entries on all CPUs.
+ */
static inline void __tlb_flush_global(void)
{
register unsigned long reg2 asm("2");
@@ -42,36 +64,89 @@ static inline void __tlb_flush_global(void)
: : "d" (reg2), "d" (reg3), "d" (reg4), "m" (dummy) : "cc" );
}
+/*
+ * Flush TLB entries for a specific mm on all CPUs (in case gmap is used
+ * this implicates multiple ASCEs!).
+ */
static inline void __tlb_flush_full(struct mm_struct *mm)
{
- cpumask_t local_cpumask;
-
preempt_disable();
- /*
- * If the process only ran on the local cpu, do a local flush.
- */
- cpumask_copy(&local_cpumask, cpumask_of(smp_processor_id()));
- if (cpumask_equal(mm_cpumask(mm), &local_cpumask))
+ atomic_add(0x10000, &mm->context.attach_count);
+ if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ /* Local TLB flush */
__tlb_flush_local();
- else
+ } else {
+ /* Global TLB flush */
__tlb_flush_global();
+ /* Reset TLB flush mask */
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_copy(mm_cpumask(mm),
+ &mm->context.cpu_attach_mask);
+ }
+ atomic_sub(0x10000, &mm->context.attach_count);
preempt_enable();
}
+
+/*
+ * Flush TLB entries for a specific ASCE on all CPUs.
+ */
+static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
+{
+ int active, count;
+
+ preempt_disable();
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ __tlb_flush_idte_local(asce);
+ } else {
+ if (MACHINE_HAS_IDTE)
+ __tlb_flush_idte(asce);
+ else
+ __tlb_flush_global();
+ /* Reset TLB flush mask */
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_copy(mm_cpumask(mm),
+ &mm->context.cpu_attach_mask);
+ }
+ atomic_sub(0x10000, &mm->context.attach_count);
+ preempt_enable();
+}
+
+static inline void __tlb_flush_kernel(void)
+{
+ if (MACHINE_HAS_IDTE)
+ __tlb_flush_idte((unsigned long) init_mm.pgd |
+ init_mm.context.asce_bits);
+ else
+ __tlb_flush_global();
+}
#else
-#define __tlb_flush_full(mm) __tlb_flush_local()
#define __tlb_flush_global() __tlb_flush_local()
-#endif
+#define __tlb_flush_full(mm) __tlb_flush_local()
/*
- * Flush all tlb entries of a page table on all cpus.
+ * Flush TLB entries for a specific ASCE on all CPUs.
*/
-static inline void __tlb_flush_idte(unsigned long asce)
+static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
{
- asm volatile(
- " .insn rrf,0xb98e0000,0,%0,%1,0"
- : : "a" (2048), "a" (asce) : "cc" );
+ if (MACHINE_HAS_TLB_LC)
+ __tlb_flush_idte_local(asce);
+ else
+ __tlb_flush_local();
}
+static inline void __tlb_flush_kernel(void)
+{
+ if (MACHINE_HAS_TLB_LC)
+ __tlb_flush_idte_local((unsigned long) init_mm.pgd |
+ init_mm.context.asce_bits);
+ else
+ __tlb_flush_local();
+}
+#endif
+
static inline void __tlb_flush_mm(struct mm_struct * mm)
{
/*
@@ -80,7 +155,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
* only ran on the local cpu.
*/
if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
- __tlb_flush_idte((unsigned long) mm->pgd |
+ __tlb_flush_asce(mm, (unsigned long) mm->pgd |
mm->context.asce_bits);
else
__tlb_flush_full(mm);
@@ -130,7 +205,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
static inline void flush_tlb_kernel_range(unsigned long start,
unsigned long end)
{
- __tlb_flush_mm(&init_mm);
+ __tlb_flush_kernel();
}
#endif /* _S390_TLBFLUSH_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 79330af9a5f..1be64a1506d 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -92,33 +92,56 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
#define ARCH_HAS_SORT_EXTABLE
#define ARCH_HAS_SEARCH_EXTABLE
-struct uaccess_ops {
- size_t (*copy_from_user)(size_t, const void __user *, void *);
- size_t (*copy_to_user)(size_t, void __user *, const void *);
- size_t (*copy_in_user)(size_t, void __user *, const void __user *);
- size_t (*clear_user)(size_t, void __user *);
- size_t (*strnlen_user)(size_t, const char __user *);
- size_t (*strncpy_from_user)(size_t, const char __user *, char *);
- int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
- int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
-};
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to: Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n: Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Copy data from user space to kernel space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ */
+unsigned long __must_check __copy_from_user(void *to, const void __user *from,
+ unsigned long n);
-extern struct uaccess_ops uaccess;
-extern struct uaccess_ops uaccess_mvcos;
-extern struct uaccess_ops uaccess_pt;
+/**
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to: Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n: Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Copy data from kernel space to user space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+unsigned long __must_check __copy_to_user(void __user *to, const void *from,
+ unsigned long n);
-extern int __handle_fault(unsigned long, unsigned long, int);
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
-static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
+static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
{
- size = uaccess.copy_to_user(size, ptr, x);
- return size ? -EFAULT : size;
+ size = __copy_to_user(ptr, x, size);
+ return size ? -EFAULT : 0;
}
-static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
+static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
{
- size = uaccess.copy_from_user(size, ptr, x);
- return size ? -EFAULT : size;
+ size = __copy_from_user(x, ptr, size);
+ return size ? -EFAULT : 0;
}
/*
@@ -135,8 +158,8 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
case 2: \
case 4: \
case 8: \
- __pu_err = __put_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __pu_err = __put_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
break; \
default: \
__put_user_bad(); \
@@ -152,7 +175,7 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
})
-extern int __put_user_bad(void) __attribute__((noreturn));
+int __put_user_bad(void) __attribute__((noreturn));
#define __get_user(x, ptr) \
({ \
@@ -161,29 +184,29 @@ extern int __put_user_bad(void) __attribute__((noreturn));
switch (sizeof(*(ptr))) { \
case 1: { \
unsigned char __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
unsigned short __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
unsigned int __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
unsigned long long __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
@@ -200,35 +223,12 @@ extern int __put_user_bad(void) __attribute__((noreturn));
__get_user(x, ptr); \
})
-extern int __get_user_bad(void) __attribute__((noreturn));
+int __get_user_bad(void) __attribute__((noreturn));
#define __put_user_unaligned __put_user
#define __get_user_unaligned __get_user
/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- return uaccess.copy_to_user(n, to, from);
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/**
* copy_to_user: - Copy a block of data into user space.
* @to: Destination address, in user space.
* @from: Source address, in kernel space.
@@ -248,30 +248,7 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
return __copy_to_user(to, from, n);
}
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- return uaccess.copy_from_user(n, from, to);
-}
-
-extern void copy_from_user_overflow(void)
+void copy_from_user_overflow(void)
#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
__compiletime_warning("copy_from_user() buffer size is not provably correct")
#endif
@@ -306,11 +283,8 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
return __copy_from_user(to, from, n);
}
-static inline unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- return uaccess.copy_in_user(n, to, from);
-}
+unsigned long __must_check
+__copy_in_user(void __user *to, const void __user *from, unsigned long n);
static inline unsigned long __must_check
copy_in_user(void __user *to, const void __user *from, unsigned long n)
@@ -322,18 +296,22 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n)
/*
* Copy a null terminated string from userspace.
*/
+
+long __strncpy_from_user(char *dst, const char __user *src, long count);
+
static inline long __must_check
strncpy_from_user(char *dst, const char __user *src, long count)
{
might_fault();
- return uaccess.strncpy_from_user(count, src, dst);
+ return __strncpy_from_user(dst, src, count);
}
-static inline unsigned long
-strnlen_user(const char __user * src, unsigned long n)
+unsigned long __must_check __strnlen_user(const char __user *src, unsigned long count);
+
+static inline unsigned long strnlen_user(const char __user *src, unsigned long n)
{
might_fault();
- return uaccess.strnlen_user(n, src);
+ return __strnlen_user(src, n);
}
/**
@@ -355,21 +333,14 @@ strnlen_user(const char __user * src, unsigned long n)
/*
* Zero Userspace
*/
+unsigned long __must_check __clear_user(void __user *to, unsigned long size);
-static inline unsigned long __must_check
-__clear_user(void __user *to, unsigned long n)
-{
- return uaccess.clear_user(n, to);
-}
-
-static inline unsigned long __must_check
-clear_user(void __user *to, unsigned long n)
+static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
might_fault();
- return uaccess.clear_user(n, to);
+ return __clear_user(to, n);
}
-extern int copy_to_user_real(void __user *dest, void *src, size_t count);
-extern int copy_from_user_real(void *dest, void __user *src, size_t count);
+int copy_to_user_real(void __user *dest, void *src, unsigned long count);
#endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/uapi/asm/hypfs.h b/arch/s390/include/uapi/asm/hypfs.h
new file mode 100644
index 00000000000..37998b44953
--- /dev/null
+++ b/arch/s390/include/uapi/asm/hypfs.h
@@ -0,0 +1,25 @@
+/*
+ * IOCTL interface for hypfs
+ *
+ * Copyright IBM Corp. 2013
+ *
+ * Author: Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _ASM_HYPFS_CTL_H
+#define _ASM_HYPFS_CTL_H
+
+#include <linux/types.h>
+
+struct hypfs_diag304 {
+ __u32 args[2];
+ __u64 data;
+ __u64 rc;
+} __attribute__((packed));
+
+#define HYPFS_IOCTL_MAGIC 0x10
+
+#define HYPFS_DIAG304 \
+ _IOWR(HYPFS_IOCTL_MAGIC, 0x20, struct hypfs_diag304)
+
+#endif
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index d25da598ec6..c003c6a73b1 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -16,6 +16,44 @@
#define __KVM_S390
+/* Device control API: s390-specific devices */
+#define KVM_DEV_FLIC_GET_ALL_IRQS 1
+#define KVM_DEV_FLIC_ENQUEUE 2
+#define KVM_DEV_FLIC_CLEAR_IRQS 3
+#define KVM_DEV_FLIC_APF_ENABLE 4
+#define KVM_DEV_FLIC_APF_DISABLE_WAIT 5
+#define KVM_DEV_FLIC_ADAPTER_REGISTER 6
+#define KVM_DEV_FLIC_ADAPTER_MODIFY 7
+/*
+ * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
+ * as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
+ * There are also sclp and machine checks. This gives us
+ * sizeof(kvm_s390_irq)*(4*65536+8+64*64+1+1) = 72 * 266250 = 19170000
+ * Lets round up to 8192 pages.
+ */
+#define KVM_S390_MAX_FLOAT_IRQS 266250
+#define KVM_S390_FLIC_MAX_BUFFER 0x2000000
+
+struct kvm_s390_io_adapter {
+ __u32 id;
+ __u8 isc;
+ __u8 maskable;
+ __u8 swap;
+ __u8 pad;
+};
+
+#define KVM_S390_IO_ADAPTER_MASK 1
+#define KVM_S390_IO_ADAPTER_MAP 2
+#define KVM_S390_IO_ADAPTER_UNMAP 3
+
+struct kvm_s390_io_adapter_req {
+ __u32 id;
+ __u8 type;
+ __u8 mask;
+ __u16 pad0;
+ __u64 addr;
+};
+
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
/* general purpose regs for s390 */
@@ -57,4 +95,9 @@ struct kvm_sync_regs {
#define KVM_REG_S390_EPOCHDIFF (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x2)
#define KVM_REG_S390_CPU_TIMER (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x3)
#define KVM_REG_S390_CLOCK_COMP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_S390_PFTOKEN (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_S390_PFCOMPARE (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_S390_PFSELECT (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_S390_PP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_S390_GBEA (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x9)
#endif
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 7e0b498a2c2..a150f4fabe4 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -403,6 +403,12 @@ typedef struct
#define PTRACE_TE_ABORT_RAND 0x5011
/*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#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/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index c286c2e868f..e031332096d 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -84,4 +84,6 @@
#define SO_MAX_PACING_RATE 47
+#define SO_BPF_EXTENSIONS 48
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h
index a61d538756f..471eb09184d 100644
--- a/arch/s390/include/uapi/asm/statfs.h
+++ b/arch/s390/include/uapi/asm/statfs.h
@@ -35,11 +35,11 @@ struct statfs {
struct statfs64 {
unsigned int f_type;
unsigned int f_bsize;
- unsigned long f_blocks;
- unsigned long f_bfree;
- unsigned long f_bavail;
- unsigned long f_files;
- unsigned long f_ffree;
+ unsigned long long f_blocks;
+ unsigned long long f_bfree;
+ unsigned long long f_bavail;
+ unsigned long long f_files;
+ unsigned long long f_ffree;
__kernel_fsid_t f_fsid;
unsigned int f_namelen;
unsigned int f_frsize;
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 864f693c237..5eb5c9ddb12 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -280,6 +280,8 @@
#define __NR_s390_runtime_instr 342
#define __NR_kcmp 343
#define __NR_finit_module 344
+#define __NR_sched_setattr 345
+#define __NR_sched_getattr 346
#define NR_syscalls 345
/*
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index e83fc116f5b..f2b18eacaca 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -154,6 +154,67 @@ struct ica_xcRB {
unsigned short priority_window;
unsigned int status;
} __attribute__((packed));
+
+/**
+ * struct ep11_cprb - EP11 connectivity programming request block
+ * @cprb_len: CPRB header length [0x0020]
+ * @cprb_ver_id: CPRB version id. [0x04]
+ * @pad_000: Alignment pad bytes
+ * @flags: Admin cmd [0x80] or functional cmd [0x00]
+ * @func_id: Function id / subtype [0x5434]
+ * @source_id: Source id [originator id]
+ * @target_id: Target id [usage/ctrl domain id]
+ * @ret_code: Return code
+ * @reserved1: Reserved
+ * @reserved2: Reserved
+ * @payload_len: Payload length
+ */
+struct ep11_cprb {
+ uint16_t cprb_len;
+ unsigned char cprb_ver_id;
+ unsigned char pad_000[2];
+ unsigned char flags;
+ unsigned char func_id[2];
+ uint32_t source_id;
+ uint32_t target_id;
+ uint32_t ret_code;
+ uint32_t reserved1;
+ uint32_t reserved2;
+ uint32_t payload_len;
+} __attribute__((packed));
+
+/**
+ * struct ep11_target_dev - EP11 target device list
+ * @ap_id: AP device id
+ * @dom_id: Usage domain id
+ */
+struct ep11_target_dev {
+ uint16_t ap_id;
+ uint16_t dom_id;
+};
+
+/**
+ * struct ep11_urb - EP11 user request block
+ * @targets_num: Number of target adapters
+ * @targets: Addr to target adapter list
+ * @weight: Level of request priority
+ * @req_no: Request id/number
+ * @req_len: Request length
+ * @req: Addr to request block
+ * @resp_len: Response length
+ * @resp: Addr to response block
+ */
+struct ep11_urb {
+ uint16_t targets_num;
+ uint64_t targets;
+ uint64_t weight;
+ uint64_t req_no;
+ uint64_t req_len;
+ uint64_t req;
+ uint64_t resp_len;
+ uint64_t resp;
+} __attribute__((packed));
+
#define AUTOSELECT ((unsigned int)0xFFFFFFFF)
#define ZCRYPT_IOCTL_MAGIC 'z'
@@ -183,6 +244,9 @@ struct ica_xcRB {
* ZSECSENDCPRB
* Send an arbitrary CPRB to a crypto card.
*
+ * ZSENDEP11CPRB
+ * Send an arbitrary EP11 CPRB to an EP11 coprocessor crypto card.
+ *
* Z90STAT_STATUS_MASK
* Return an 64 element array of unsigned chars for the status of
* all devices.
@@ -256,6 +320,7 @@ struct ica_xcRB {
#define ICARSAMODEXPO _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x05, 0)
#define ICARSACRT _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x06, 0)
#define ZSECSENDCPRB _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x81, 0)
+#define ZSENDEP11CPRB _IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x04, 0)
/* New status calls */
#define Z90STAT_TOTALCOUNT _IOR(ZCRYPT_IOCTL_MAGIC, 0x40, int)
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2403303cfed..a95c4ca9961 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-$(CONFIG_KPROBES) += kprobes.o
@@ -60,7 +59,8 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
ifdef CONFIG_64BIT
-obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o perf_cpum_sf.o \
+ perf_cpum_cf_events.o
obj-y += runtime_instr.o cache.o
endif
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index e4c99a18365..cc10cdd4d6a 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -136,6 +136,7 @@ int main(void)
DEFINE(__LC_RESTART_FN, offsetof(struct _lowcore, restart_fn));
DEFINE(__LC_RESTART_DATA, offsetof(struct _lowcore, restart_data));
DEFINE(__LC_RESTART_SOURCE, offsetof(struct _lowcore, restart_source));
+ DEFINE(__LC_KERNEL_ASCE, offsetof(struct _lowcore, kernel_asce));
DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index 3a414c0f93e..c0b03c28d15 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -378,9 +378,12 @@ static int __init cache_init(void)
if (!test_facility(34))
return 0;
cache_build_info();
+
+ cpu_notifier_register_begin();
for_each_online_cpu(cpu)
cache_add_cpu(cpu);
- hotcpu_notifier(cache_hotplug, 0);
+ __hotcpu_notifier(cache_hotplug, 0);
+ cpu_notifier_register_done();
return 0;
}
device_initcall(cache_init);
diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c
deleted file mode 100644
index 765fabdada9..00000000000
--- 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 <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/personality.h>
-#include <linux/sched.h>
-
-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/compat_linux.c b/arch/s390/kernel/compat_linux.c
index e030d2bdec1..ca38139423a 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -86,48 +86,51 @@
#define SET_STAT_UID(stat, uid) (stat).st_uid = high2lowuid(uid)
#define SET_STAT_GID(stat, gid) (stat).st_gid = high2lowgid(gid)
-asmlinkage long sys32_chown16(const char __user * filename, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_chown16, const char __user *, filename,
+ u16, user, u16, group)
{
return sys_chown(filename, low2highuid(user), low2highgid(group));
}
-asmlinkage long sys32_lchown16(const char __user * filename, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_lchown16, const char __user *,
+ filename, u16, user, u16, group)
{
return sys_lchown(filename, low2highuid(user), low2highgid(group));
}
-asmlinkage long sys32_fchown16(unsigned int fd, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group)
{
return sys_fchown(fd, low2highuid(user), low2highgid(group));
}
-asmlinkage long sys32_setregid16(u16 rgid, u16 egid)
+COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid)
{
return sys_setregid(low2highgid(rgid), low2highgid(egid));
}
-asmlinkage long sys32_setgid16(u16 gid)
+COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
{
return sys_setgid((gid_t)gid);
}
-asmlinkage long sys32_setreuid16(u16 ruid, u16 euid)
+COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
{
return sys_setreuid(low2highuid(ruid), low2highuid(euid));
}
-asmlinkage long sys32_setuid16(u16 uid)
+COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
{
return sys_setuid((uid_t)uid);
}
-asmlinkage long sys32_setresuid16(u16 ruid, u16 euid, u16 suid)
+COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)
{
return sys_setresuid(low2highuid(ruid), low2highuid(euid),
- low2highuid(suid));
+ low2highuid(suid));
}
-asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __user *suidp)
+COMPAT_SYSCALL_DEFINE3(s390_getresuid16, u16 __user *, ruidp,
+ u16 __user *, euidp, u16 __user *, suidp)
{
const struct cred *cred = current_cred();
int retval;
@@ -144,13 +147,14 @@ asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __us
return retval;
}
-asmlinkage long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid)
+COMPAT_SYSCALL_DEFINE3(s390_setresgid16, u16, rgid, u16, egid, u16, sgid)
{
return sys_setresgid(low2highgid(rgid), low2highgid(egid),
- low2highgid(sgid));
+ low2highgid(sgid));
}
-asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __user *sgidp)
+COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp,
+ u16 __user *, egidp, u16 __user *, sgidp)
{
const struct cred *cred = current_cred();
int retval;
@@ -167,12 +171,12 @@ asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __us
return retval;
}
-asmlinkage long sys32_setfsuid16(u16 uid)
+COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
{
return sys_setfsuid((uid_t)uid);
}
-asmlinkage long sys32_setfsgid16(u16 gid)
+COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
{
return sys_setfsgid((gid_t)gid);
}
@@ -215,7 +219,7 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli
return 0;
}
-asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
+COMPAT_SYSCALL_DEFINE2(s390_getgroups16, int, gidsetsize, u16 __user *, grouplist)
{
const struct cred *cred = current_cred();
int i;
@@ -240,7 +244,7 @@ out:
return i;
}
-asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
+COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplist)
{
struct group_info *group_info;
int retval;
@@ -265,29 +269,29 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
return retval;
}
-asmlinkage long sys32_getuid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getuid16)
{
return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
}
-asmlinkage long sys32_geteuid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_geteuid16)
{
return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
}
-asmlinkage long sys32_getgid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getgid16)
{
return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
}
-asmlinkage long sys32_getegid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getegid16)
{
return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
}
#ifdef CONFIG_SYSVIPC
-COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second,
- unsigned long, third, compat_uptr_t, ptr)
+COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second,
+ compat_ulong_t, third, compat_uptr_t, ptr)
{
if (call >> 16) /* hack for backward compatibility */
return -EINVAL;
@@ -295,41 +299,35 @@ COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second,
}
#endif
-asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low)
+COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u32, low)
{
- if ((int)high < 0)
- return -EINVAL;
- else
- return sys_truncate(path, (high << 32) | low);
+ return sys_truncate(path, (unsigned long)high << 32 | low);
}
-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low)
+COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low)
{
- if ((int)high < 0)
- return -EINVAL;
- else
- return sys_ftruncate(fd, (high << 32) | low);
+ return sys_ftruncate(fd, (unsigned long)high << 32 | low);
}
-asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf,
- size_t count, u32 poshi, u32 poslo)
+COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf,
+ compat_size_t, count, u32, high, u32, low)
{
if ((compat_ssize_t) count < 0)
return -EINVAL;
- return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo));
+ return sys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low);
}
-asmlinkage long sys32_pwrite64(unsigned int fd, const char __user *ubuf,
- size_t count, u32 poshi, u32 poslo)
+COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubuf,
+ compat_size_t, count, u32, high, u32, low)
{
if ((compat_ssize_t) count < 0)
return -EINVAL;
- return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo));
+ return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low);
}
-asmlinkage compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count)
+COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count)
{
- return sys_readahead(fd, ((loff_t)AA(offhi) << 32) | AA(offlo), count);
+ return sys_readahead(fd, (unsigned long)high << 32 | low, count);
}
struct stat64_emu31 {
@@ -381,7 +379,7 @@ static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat)
return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}
-asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_stat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
{
struct kstat stat;
int ret = vfs_stat(filename, &stat);
@@ -390,7 +388,7 @@ asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 _
return ret;
}
-asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_lstat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
{
struct kstat stat;
int ret = vfs_lstat(filename, &stat);
@@ -399,7 +397,7 @@ asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31
return ret;
}
-asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_fstat64, unsigned int, fd, struct stat64_emu31 __user *, statbuf)
{
struct kstat stat;
int ret = vfs_fstat(fd, &stat);
@@ -408,8 +406,8 @@ asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * sta
return ret;
}
-asmlinkage long sys32_fstatat64(unsigned int dfd, const char __user *filename,
- struct stat64_emu31 __user* statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(s390_fstatat64, unsigned int, dfd, const char __user *, filename,
+ struct stat64_emu31 __user *, statbuf, int, flag)
{
struct kstat stat;
int error;
@@ -435,7 +433,7 @@ struct mmap_arg_struct_emu31 {
compat_ulong_t offset;
};
-asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg)
+COMPAT_SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct_emu31 __user *, arg)
{
struct mmap_arg_struct_emu31 a;
@@ -447,7 +445,7 @@ asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg)
a.offset >> PAGE_SHIFT);
}
-asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg)
+COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg)
{
struct mmap_arg_struct_emu31 a;
@@ -456,7 +454,7 @@ asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg)
return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
}
-asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count)
+COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_size_t, count)
{
if ((compat_ssize_t) count < 0)
return -EINVAL;
@@ -464,7 +462,7 @@ asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count)
return sys_read(fd, buf, count);
}
-asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t count)
+COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, compat_size_t, count)
{
if ((compat_ssize_t) count < 0)
return -EINVAL;
@@ -478,14 +476,13 @@ asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t cou
* because the 31 bit values differ from the 64 bit values.
*/
-asmlinkage long
-sys32_fadvise64(int fd, loff_t offset, size_t len, int advise)
+COMPAT_SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, high, u32, low, compat_size_t, len, int, advise)
{
if (advise == 4)
advise = POSIX_FADV_DONTNEED;
else if (advise == 5)
advise = POSIX_FADV_NOREUSE;
- return sys_fadvise64(fd, offset, len, advise);
+ return sys_fadvise64(fd, (unsigned long)high << 32 | low, len, advise);
}
struct fadvise64_64_args {
@@ -495,8 +492,7 @@ struct fadvise64_64_args {
int advice;
};
-asmlinkage long
-sys32_fadvise64_64(struct fadvise64_64_args __user *args)
+COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args)
{
struct fadvise64_64_args a;
@@ -508,3 +504,17 @@ sys32_fadvise64_64(struct fadvise64_64_args __user *args)
a.advice = POSIX_FADV_NOREUSE;
return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice);
}
+
+COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow,
+ u32, nhigh, u32, nlow, unsigned int, flags)
+{
+ return sys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow,
+ ((u64)nhigh << 32) + nlow, flags);
+}
+
+COMPAT_SYSCALL_DEFINE6(s390_fallocate, int, fd, int, mode, u32, offhigh, u32, offlow,
+ u32, lenhigh, u32, lenlow)
+{
+ return sys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow,
+ ((u64)lenhigh << 32) + lenlow);
+}
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 1bfda3eca37..39ddfdb40ae 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -76,46 +76,43 @@ struct stat64_emu31;
struct mmap_arg_struct_emu31;
struct fadvise64_64_args;
-long sys32_chown16(const char __user * filename, u16 user, u16 group);
-long sys32_lchown16(const char __user * filename, u16 user, u16 group);
-long sys32_fchown16(unsigned int fd, u16 user, u16 group);
-long sys32_setregid16(u16 rgid, u16 egid);
-long sys32_setgid16(u16 gid);
-long sys32_setreuid16(u16 ruid, u16 euid);
-long sys32_setuid16(u16 uid);
-long sys32_setresuid16(u16 ruid, u16 euid, u16 suid);
-long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
-long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid);
-long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
-long sys32_setfsuid16(u16 uid);
-long sys32_setfsgid16(u16 gid);
-long sys32_getgroups16(int gidsetsize, u16 __user *grouplist);
-long sys32_setgroups16(int gidsetsize, u16 __user *grouplist);
-long sys32_getuid16(void);
-long sys32_geteuid16(void);
-long sys32_getgid16(void);
-long sys32_getegid16(void);
-long sys32_truncate64(const char __user * path, unsigned long high,
- unsigned long low);
-long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low);
-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);
-long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count,
- u32 poshi, u32 poslo);
-long sys32_pwrite64(unsigned int fd, const char __user *ubuf,
- size_t count, u32 poshi, u32 poslo);
-compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count);
-long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf);
-long sys32_lstat64(const char __user * filename,
- struct stat64_emu31 __user * statbuf);
-long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf);
-long sys32_fstatat64(unsigned int dfd, const char __user *filename,
- struct stat64_emu31 __user* statbuf, int flag);
-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, const char __user * buf, size_t count);
-long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise);
-long sys32_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_chown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_lchown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_fchown16(unsigned int fd, u16 user, u16 group);
+long compat_sys_s390_setregid16(u16 rgid, u16 egid);
+long compat_sys_s390_setgid16(u16 gid);
+long compat_sys_s390_setreuid16(u16 ruid, u16 euid);
+long compat_sys_s390_setuid16(u16 uid);
+long compat_sys_s390_setresuid16(u16 ruid, u16 euid, u16 suid);
+long compat_sys_s390_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
+long compat_sys_s390_setresgid16(u16 rgid, u16 egid, u16 sgid);
+long compat_sys_s390_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
+long compat_sys_s390_setfsuid16(u16 uid);
+long compat_sys_s390_setfsgid16(u16 gid);
+long compat_sys_s390_getgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_setgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_getuid16(void);
+long compat_sys_s390_geteuid16(void);
+long compat_sys_s390_getgid16(void);
+long compat_sys_s390_getegid16(void);
+long compat_sys_s390_truncate64(const char __user *path, u32 high, u32 low);
+long compat_sys_s390_ftruncate64(unsigned int fd, u32 high, u32 low);
+long compat_sys_s390_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_readahead(int fd, u32 high, u32 low, s32 count);
+long compat_sys_s390_stat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_lstat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstat64(unsigned int fd, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstatat64(unsigned int dfd, const char __user *filename, struct stat64_emu31 __user *statbuf, int flag);
+long compat_sys_s390_old_mmap(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_mmap2(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_read(unsigned int fd, char __user * buf, compat_size_t count);
+long compat_sys_s390_write(unsigned int fd, const char __user * buf, compat_size_t count);
+long compat_sys_s390_fadvise64(int fd, u32 high, u32 low, compat_size_t len, int advise);
+long compat_sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_sync_file_range(int fd, u32 offhigh, u32 offlow, u32 nhigh, u32 nlow, unsigned int flags);
+long compat_sys_s390_fallocate(int fd, int mode, u32 offhigh, u32 offlow, u32 lenhigh, u32 lenlow);
+long compat_sys_sigreturn(void);
+long compat_sys_rt_sigreturn(void);
+
#endif /* _ASM_S390X_S390_H */
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 95e7ba0fbb7..7df5ed9f44d 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -241,7 +241,7 @@ static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
return 0;
}
-asmlinkage long sys32_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
{
struct pt_regs *regs = task_pt_regs(current);
sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15];
@@ -260,7 +260,7 @@ badframe:
return 0;
}
-asmlinkage long sys32_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = task_pt_regs(current);
rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15];
@@ -412,8 +412,9 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
} else {
regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
- err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
- (u16 __force __user *)(frame->retcode));
+ if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
+ (u16 __force __user *)(frame->retcode)))
+ goto give_sigsegv;
}
/* Set up backchain. */
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
deleted file mode 100644
index 9cb1b975b35..00000000000
--- a/arch/s390/kernel/compat_wrapper.S
+++ /dev/null
@@ -1,1414 +0,0 @@
-/*
-* wrapper for 31 bit compatible system calls.
-*
-* Copyright IBM Corp. 2000, 2006
-* Author(s): Gerhard Tonn (ton@de.ibm.com),
-* Thomas Spatzier (tspat@de.ibm.com)
-*/
-
-#include <linux/linkage.h>
-
-ENTRY(sys32_exit_wrapper)
- lgfr %r2,%r2 # int
- jg sys_exit # branch to sys_exit
-
-ENTRY(sys32_read_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # char *
- llgfr %r4,%r4 # size_t
- jg sys32_read # branch to sys_read
-
-ENTRY(sys32_write_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # size_t
- jg sys32_write # branch to system call
-
-ENTRY(sys32_close_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_close # branch to system call
-
-ENTRY(sys32_creat_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- jg sys_creat # branch to system call
-
-ENTRY(sys32_link_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # const char *
- jg sys_link # branch to system call
-
-ENTRY(sys32_unlink_wrapper)
- llgtr %r2,%r2 # const char *
- jg sys_unlink # branch to system call
-
-ENTRY(sys32_chdir_wrapper)
- llgtr %r2,%r2 # const char *
- jg sys_chdir # branch to system call
-
-ENTRY(sys32_time_wrapper)
- llgtr %r2,%r2 # int *
- jg compat_sys_time # branch to system call
-
-ENTRY(sys32_mknod_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- llgfr %r4,%r4 # dev
- jg sys_mknod # branch to system call
-
-ENTRY(sys32_chmod_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # mode_t
- jg sys_chmod # branch to system call
-
-ENTRY(sys32_lchown16_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # __kernel_old_uid_emu31_t
- llgfr %r4,%r4 # __kernel_old_uid_emu31_t
- jg sys32_lchown16 # branch to system call
-
-#sys32_getpid_wrapper # void
-
-ENTRY(sys32_mount_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # char *
- llgfr %r5,%r5 # unsigned long
- llgtr %r6,%r6 # void *
- jg compat_sys_mount # branch to system call
-
-ENTRY(sys32_oldumount_wrapper)
- llgtr %r2,%r2 # char *
- jg sys_oldumount # branch to system call
-
-ENTRY(sys32_setuid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_uid_emu31_t
- jg sys32_setuid16 # branch to system call
-
-#sys32_getuid16_wrapper # void
-
-ENTRY(sys32_ptrace_wrapper)
- lgfr %r2,%r2 # long
- lgfr %r3,%r3 # long
- llgtr %r4,%r4 # long
- llgfr %r5,%r5 # long
- jg compat_sys_ptrace # branch to system call
-
-ENTRY(sys32_alarm_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_alarm # branch to system call
-
-ENTRY(compat_sys_utime_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct compat_utimbuf *
- jg compat_sys_utime # branch to system call
-
-ENTRY(sys32_access_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- jg sys_access # branch to system call
-
-ENTRY(sys32_nice_wrapper)
- lgfr %r2,%r2 # int
- jg sys_nice # branch to system call
-
-#sys32_sync_wrapper # void
-
-ENTRY(sys32_kill_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- jg sys_kill # branch to system call
-
-ENTRY(sys32_rename_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # const char *
- jg sys_rename # branch to system call
-
-ENTRY(sys32_mkdir_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- jg sys_mkdir # branch to system call
-
-ENTRY(sys32_rmdir_wrapper)
- llgtr %r2,%r2 # const char *
- jg sys_rmdir # branch to system call
-
-ENTRY(sys32_dup_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_dup # branch to system call
-
-ENTRY(sys32_pipe_wrapper)
- llgtr %r2,%r2 # u32 *
- jg sys_pipe # branch to system call
-
-ENTRY(compat_sys_times_wrapper)
- llgtr %r2,%r2 # struct compat_tms *
- jg compat_sys_times # branch to system call
-
-ENTRY(sys32_brk_wrapper)
- llgtr %r2,%r2 # unsigned long
- jg sys_brk # branch to system call
-
-ENTRY(sys32_setgid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_gid_emu31_t
- jg sys32_setgid16 # branch to system call
-
-#sys32_getgid16_wrapper # void
-
-ENTRY(sys32_signal_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # __sighandler_t
- jg sys_signal
-
-#sys32_geteuid16_wrapper # void
-
-#sys32_getegid16_wrapper # void
-
-ENTRY(sys32_acct_wrapper)
- llgtr %r2,%r2 # char *
- jg sys_acct # branch to system call
-
-ENTRY(sys32_umount_wrapper)
- llgtr %r2,%r2 # char *
- lgfr %r3,%r3 # int
- jg sys_umount # branch to system call
-
-ENTRY(compat_sys_ioctl_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- llgfr %r4,%r4 # unsigned int
- jg compat_sys_ioctl # branch to system call
-
-ENTRY(compat_sys_fcntl_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- llgfr %r4,%r4 # unsigned long
- jg compat_sys_fcntl # branch to system call
-
-ENTRY(sys32_setpgid_wrapper)
- lgfr %r2,%r2 # pid_t
- lgfr %r3,%r3 # pid_t
- jg sys_setpgid # branch to system call
-
-ENTRY(sys32_umask_wrapper)
- lgfr %r2,%r2 # int
- jg sys_umask # branch to system call
-
-ENTRY(sys32_chroot_wrapper)
- llgtr %r2,%r2 # char *
- jg sys_chroot # branch to system call
-
-ENTRY(sys32_ustat_wrapper)
- llgfr %r2,%r2 # dev_t
- llgtr %r3,%r3 # struct ustat *
- jg compat_sys_ustat
-
-ENTRY(sys32_dup2_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- jg sys_dup2 # branch to system call
-
-#sys32_getppid_wrapper # void
-
-#sys32_getpgrp_wrapper # void
-
-#sys32_setsid_wrapper # void
-
-ENTRY(sys32_setreuid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_uid_emu31_t
- llgfr %r3,%r3 # __kernel_old_uid_emu31_t
- jg sys32_setreuid16 # branch to system call
-
-ENTRY(sys32_setregid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_gid_emu31_t
- llgfr %r3,%r3 # __kernel_old_gid_emu31_t
- jg sys32_setregid16 # branch to system call
-
-ENTRY(sys_sigsuspend_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- llgfr %r4,%r4 # old_sigset_t
- jg sys_sigsuspend
-
-ENTRY(compat_sys_sigpending_wrapper)
- llgtr %r2,%r2 # compat_old_sigset_t *
- jg compat_sys_sigpending # branch to system call
-
-ENTRY(sys32_sethostname_wrapper)
- llgtr %r2,%r2 # char *
- lgfr %r3,%r3 # int
- jg sys_sethostname # branch to system call
-
-ENTRY(compat_sys_setrlimit_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # struct rlimit_emu31 *
- jg compat_sys_setrlimit # branch to system call
-
-ENTRY(compat_sys_old_getrlimit_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # struct rlimit_emu31 *
- jg compat_sys_old_getrlimit # branch to system call
-
-ENTRY(compat_sys_getrlimit_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # struct rlimit_emu31 *
- jg compat_sys_getrlimit # branch to system call
-
-ENTRY(sys32_mmap2_wrapper)
- llgtr %r2,%r2 # struct mmap_arg_struct_emu31 *
- jg sys32_mmap2 # branch to system call
-
-ENTRY(compat_sys_gettimeofday_wrapper)
- llgtr %r2,%r2 # struct timeval_emu31 *
- llgtr %r3,%r3 # struct timezone *
- jg compat_sys_gettimeofday # branch to system call
-
-ENTRY(compat_sys_settimeofday_wrapper)
- llgtr %r2,%r2 # struct timeval_emu31 *
- llgtr %r3,%r3 # struct timezone *
- jg compat_sys_settimeofday # branch to system call
-
-ENTRY(sys32_getgroups16_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # __kernel_old_gid_emu31_t *
- jg sys32_getgroups16 # branch to system call
-
-ENTRY(sys32_setgroups16_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # __kernel_old_gid_emu31_t *
- jg sys32_setgroups16 # branch to system call
-
-ENTRY(sys32_symlink_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # const char *
- jg sys_symlink # branch to system call
-
-ENTRY(sys32_readlink_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # char *
- lgfr %r4,%r4 # int
- jg sys_readlink # branch to system call
-
-ENTRY(sys32_uselib_wrapper)
- llgtr %r2,%r2 # const char *
- jg sys_uselib # branch to system call
-
-ENTRY(sys32_swapon_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- jg sys_swapon # branch to system call
-
-ENTRY(sys32_reboot_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- llgfr %r4,%r4 # unsigned int
- llgtr %r5,%r5 # void *
- jg sys_reboot # branch to system call
-
-ENTRY(old32_readdir_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # void *
- llgfr %r4,%r4 # unsigned int
- jg compat_sys_old_readdir # branch to system call
-
-ENTRY(old32_mmap_wrapper)
- llgtr %r2,%r2 # struct mmap_arg_struct_emu31 *
- jg old32_mmap # branch to system call
-
-ENTRY(sys32_munmap_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # size_t
- jg sys_munmap # branch to system call
-
-ENTRY(sys32_fchmod_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # mode_t
- jg sys_fchmod # branch to system call
-
-ENTRY(sys32_fchown16_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # compat_uid_t
- llgfr %r4,%r4 # compat_uid_t
- jg sys32_fchown16 # branch to system call
-
-ENTRY(sys32_getpriority_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- jg sys_getpriority # branch to system call
-
-ENTRY(sys32_setpriority_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- lgfr %r4,%r4 # int
- jg sys_setpriority # branch to system call
-
-ENTRY(compat_sys_statfs_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct compat_statfs *
- jg compat_sys_statfs # branch to system call
-
-ENTRY(compat_sys_fstatfs_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # struct compat_statfs *
- jg compat_sys_fstatfs # branch to system call
-
-ENTRY(compat_sys_socketcall_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # u32 *
- jg compat_sys_socketcall # branch to system call
-
-ENTRY(sys32_syslog_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # char *
- lgfr %r4,%r4 # int
- jg sys_syslog # branch to system call
-
-ENTRY(compat_sys_newstat_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct stat_emu31 *
- jg compat_sys_newstat # branch to system call
-
-ENTRY(compat_sys_newlstat_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct stat_emu31 *
- jg compat_sys_newlstat # branch to system call
-
-ENTRY(compat_sys_newfstat_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # struct stat_emu31 *
- jg compat_sys_newfstat # branch to system call
-
-#sys32_vhangup_wrapper # void
-
-ENTRY(sys32_swapoff_wrapper)
- llgtr %r2,%r2 # const char *
- jg sys_swapoff # branch to system call
-
-ENTRY(compat_sys_sysinfo_wrapper)
- llgtr %r2,%r2 # struct sysinfo_emu31 *
- jg compat_sys_sysinfo # branch to system call
-
-ENTRY(sys32_fsync_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_fsync # branch to system call
-
-#sys32_sigreturn_wrapper # done in sigreturn_glue
-
-#sys32_clone_wrapper # done in clone_glue
-
-ENTRY(sys32_setdomainname_wrapper)
- llgtr %r2,%r2 # char *
- lgfr %r3,%r3 # int
- jg sys_setdomainname # branch to system call
-
-ENTRY(sys32_newuname_wrapper)
- llgtr %r2,%r2 # struct new_utsname *
- jg sys_newuname # branch to system call
-
-ENTRY(compat_sys_adjtimex_wrapper)
- llgtr %r2,%r2 # struct compat_timex *
- jg compat_sys_adjtimex # branch to system call
-
-ENTRY(sys32_mprotect_wrapper)
- llgtr %r2,%r2 # unsigned long (actually pointer
- llgfr %r3,%r3 # size_t
- llgfr %r4,%r4 # unsigned long
- jg sys_mprotect # branch to system call
-
-ENTRY(sys_init_module_wrapper)
- llgtr %r2,%r2 # void *
- llgfr %r3,%r3 # unsigned long
- llgtr %r4,%r4 # char *
- jg sys_init_module # branch to system call
-
-ENTRY(sys_delete_module_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # unsigned int
- jg sys_delete_module # branch to system call
-
-ENTRY(sys32_quotactl_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # qid_t
- llgtr %r5,%r5 # caddr_t
- jg sys_quotactl # branch to system call
-
-ENTRY(sys32_getpgid_wrapper)
- lgfr %r2,%r2 # pid_t
- jg sys_getpgid # branch to system call
-
-ENTRY(sys32_fchdir_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_fchdir # branch to system call
-
-ENTRY(sys32_bdflush_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # long
- jg sys_bdflush # branch to system call
-
-ENTRY(sys32_sysfs_wrapper)
- lgfr %r2,%r2 # int
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- jg sys_sysfs # branch to system call
-
-ENTRY(sys32_personality_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_s390_personality # branch to system call
-
-ENTRY(sys32_setfsuid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_uid_emu31_t
- jg sys32_setfsuid16 # branch to system call
-
-ENTRY(sys32_setfsgid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_gid_emu31_t
- jg sys32_setfsgid16 # branch to system call
-
-ENTRY(sys32_llseek_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- llgtr %r5,%r5 # loff_t *
- llgfr %r6,%r6 # unsigned int
- jg sys_llseek # branch to system call
-
-ENTRY(sys32_getdents_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # void *
- llgfr %r4,%r4 # unsigned int
- jg compat_sys_getdents # branch to system call
-
-ENTRY(compat_sys_select_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # compat_fd_set *
- llgtr %r4,%r4 # compat_fd_set *
- llgtr %r5,%r5 # compat_fd_set *
- llgtr %r6,%r6 # struct compat_timeval *
- jg compat_sys_select # branch to system call
-
-ENTRY(sys32_flock_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- jg sys_flock # branch to system call
-
-ENTRY(sys32_msync_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # size_t
- lgfr %r4,%r4 # int
- jg sys_msync # branch to system call
-
-ENTRY(compat_sys_readv_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const struct compat_iovec *
- llgfr %r4,%r4 # unsigned long
- jg compat_sys_readv # branch to system call
-
-ENTRY(compat_sys_writev_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const struct compat_iovec *
- llgfr %r4,%r4 # unsigned long
- jg compat_sys_writev # branch to system call
-
-ENTRY(sys32_getsid_wrapper)
- lgfr %r2,%r2 # pid_t
- jg sys_getsid # branch to system call
-
-ENTRY(sys32_fdatasync_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_fdatasync # branch to system call
-
-ENTRY(sys32_mlock_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # size_t
- jg sys_mlock # branch to system call
-
-ENTRY(sys32_munlock_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # size_t
- jg sys_munlock # branch to system call
-
-ENTRY(sys32_mlockall_wrapper)
- lgfr %r2,%r2 # int
- jg sys_mlockall # branch to system call
-
-#sys32_munlockall_wrapper # void
-
-ENTRY(sys32_sched_setparam_wrapper)
- lgfr %r2,%r2 # pid_t
- llgtr %r3,%r3 # struct sched_param *
- jg sys_sched_setparam # branch to system call
-
-ENTRY(sys32_sched_getparam_wrapper)
- lgfr %r2,%r2 # pid_t
- llgtr %r3,%r3 # struct sched_param *
- jg sys_sched_getparam # branch to system call
-
-ENTRY(sys32_sched_setscheduler_wrapper)
- lgfr %r2,%r2 # pid_t
- lgfr %r3,%r3 # int
- llgtr %r4,%r4 # struct sched_param *
- jg sys_sched_setscheduler # branch to system call
-
-ENTRY(sys32_sched_getscheduler_wrapper)
- lgfr %r2,%r2 # pid_t
- jg sys_sched_getscheduler # branch to system call
-
-#sys32_sched_yield_wrapper # void
-
-ENTRY(sys32_sched_get_priority_max_wrapper)
- lgfr %r2,%r2 # int
- jg sys_sched_get_priority_max # branch to system call
-
-ENTRY(sys32_sched_get_priority_min_wrapper)
- lgfr %r2,%r2 # int
- jg sys_sched_get_priority_min # branch to system call
-
-ENTRY(compat_sys_nanosleep_wrapper)
- llgtr %r2,%r2 # struct compat_timespec *
- llgtr %r3,%r3 # struct compat_timespec *
- jg compat_sys_nanosleep # branch to system call
-
-ENTRY(sys32_mremap_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- llgfr %r5,%r5 # unsigned long
- llgfr %r6,%r6 # unsigned long
- jg sys_mremap # branch to system call
-
-ENTRY(sys32_setresuid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_uid_emu31_t
- llgfr %r3,%r3 # __kernel_old_uid_emu31_t
- llgfr %r4,%r4 # __kernel_old_uid_emu31_t
- jg sys32_setresuid16 # branch to system call
-
-ENTRY(sys32_getresuid16_wrapper)
- llgtr %r2,%r2 # __kernel_old_uid_emu31_t *
- llgtr %r3,%r3 # __kernel_old_uid_emu31_t *
- llgtr %r4,%r4 # __kernel_old_uid_emu31_t *
- jg sys32_getresuid16 # branch to system call
-
-ENTRY(sys32_poll_wrapper)
- llgtr %r2,%r2 # struct pollfd *
- llgfr %r3,%r3 # unsigned int
- lgfr %r4,%r4 # int
- jg sys_poll # branch to system call
-
-ENTRY(sys32_setresgid16_wrapper)
- llgfr %r2,%r2 # __kernel_old_gid_emu31_t
- llgfr %r3,%r3 # __kernel_old_gid_emu31_t
- llgfr %r4,%r4 # __kernel_old_gid_emu31_t
- jg sys32_setresgid16 # branch to system call
-
-ENTRY(sys32_getresgid16_wrapper)
- llgtr %r2,%r2 # __kernel_old_gid_emu31_t *
- llgtr %r3,%r3 # __kernel_old_gid_emu31_t *
- llgtr %r4,%r4 # __kernel_old_gid_emu31_t *
- jg sys32_getresgid16 # branch to system call
-
-ENTRY(sys32_prctl_wrapper)
- lgfr %r2,%r2 # int
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- llgfr %r5,%r5 # unsigned long
- llgfr %r6,%r6 # unsigned long
- jg sys_prctl # branch to system call
-
-#sys32_rt_sigreturn_wrapper # done in rt_sigreturn_glue
-
-ENTRY(sys32_pread64_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # char *
- llgfr %r4,%r4 # size_t
- llgfr %r5,%r5 # u32
- llgfr %r6,%r6 # u32
- jg sys32_pread64 # branch to system call
-
-ENTRY(sys32_pwrite64_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # size_t
- llgfr %r5,%r5 # u32
- llgfr %r6,%r6 # u32
- jg sys32_pwrite64 # branch to system call
-
-ENTRY(sys32_chown16_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # __kernel_old_uid_emu31_t
- llgfr %r4,%r4 # __kernel_old_gid_emu31_t
- jg sys32_chown16 # branch to system call
-
-ENTRY(sys32_getcwd_wrapper)
- llgtr %r2,%r2 # char *
- llgfr %r3,%r3 # unsigned long
- jg sys_getcwd # branch to system call
-
-ENTRY(sys32_capget_wrapper)
- llgtr %r2,%r2 # cap_user_header_t
- llgtr %r3,%r3 # cap_user_data_t
- jg sys_capget # branch to system call
-
-ENTRY(sys32_capset_wrapper)
- llgtr %r2,%r2 # cap_user_header_t
- llgtr %r3,%r3 # const cap_user_data_t
- jg sys_capset # branch to system call
-
-#sys32_vfork_wrapper # done in vfork_glue
-
-ENTRY(sys32_truncate64_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- jg sys32_truncate64 # branch to system call
-
-ENTRY(sys32_ftruncate64_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- jg sys32_ftruncate64 # branch to system call
-
-ENTRY(sys32_lchown_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # uid_t
- llgfr %r4,%r4 # gid_t
- jg sys_lchown # branch to system call
-
-#sys32_getuid_wrapper # void
-#sys32_getgid_wrapper # void
-#sys32_geteuid_wrapper # void
-#sys32_getegid_wrapper # void
-
-ENTRY(sys32_setreuid_wrapper)
- llgfr %r2,%r2 # uid_t
- llgfr %r3,%r3 # uid_t
- jg sys_setreuid # branch to system call
-
-ENTRY(sys32_setregid_wrapper)
- llgfr %r2,%r2 # gid_t
- llgfr %r3,%r3 # gid_t
- jg sys_setregid # branch to system call
-
-ENTRY(sys32_getgroups_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # gid_t *
- jg sys_getgroups # branch to system call
-
-ENTRY(sys32_setgroups_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # gid_t *
- jg sys_setgroups # branch to system call
-
-ENTRY(sys32_fchown_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # uid_t
- llgfr %r4,%r4 # gid_t
- jg sys_fchown # branch to system call
-
-ENTRY(sys32_setresuid_wrapper)
- llgfr %r2,%r2 # uid_t
- llgfr %r3,%r3 # uid_t
- llgfr %r4,%r4 # uid_t
- jg sys_setresuid # branch to system call
-
-ENTRY(sys32_getresuid_wrapper)
- llgtr %r2,%r2 # uid_t *
- llgtr %r3,%r3 # uid_t *
- llgtr %r4,%r4 # uid_t *
- jg sys_getresuid # branch to system call
-
-ENTRY(sys32_setresgid_wrapper)
- llgfr %r2,%r2 # gid_t
- llgfr %r3,%r3 # gid_t
- llgfr %r4,%r4 # gid_t
- jg sys_setresgid # branch to system call
-
-ENTRY(sys32_getresgid_wrapper)
- llgtr %r2,%r2 # gid_t *
- llgtr %r3,%r3 # gid_t *
- llgtr %r4,%r4 # gid_t *
- jg sys_getresgid # branch to system call
-
-ENTRY(sys32_chown_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # uid_t
- llgfr %r4,%r4 # gid_t
- jg sys_chown # branch to system call
-
-ENTRY(sys32_setuid_wrapper)
- llgfr %r2,%r2 # uid_t
- jg sys_setuid # branch to system call
-
-ENTRY(sys32_setgid_wrapper)
- llgfr %r2,%r2 # gid_t
- jg sys_setgid # branch to system call
-
-ENTRY(sys32_setfsuid_wrapper)
- llgfr %r2,%r2 # uid_t
- jg sys_setfsuid # branch to system call
-
-ENTRY(sys32_setfsgid_wrapper)
- llgfr %r2,%r2 # gid_t
- jg sys_setfsgid # branch to system call
-
-ENTRY(sys32_pivot_root_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # const char *
- jg sys_pivot_root # branch to system call
-
-ENTRY(sys32_mincore_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # size_t
- llgtr %r4,%r4 # unsigned char *
- jg sys_mincore # branch to system call
-
-ENTRY(sys32_madvise_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # size_t
- lgfr %r4,%r4 # int
- jg sys_madvise # branch to system call
-
-ENTRY(sys32_getdents64_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # void *
- llgfr %r4,%r4 # unsigned int
- jg sys_getdents64 # branch to system call
-
-ENTRY(compat_sys_fcntl64_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- llgfr %r4,%r4 # unsigned long
- jg compat_sys_fcntl64 # branch to system call
-
-ENTRY(sys32_stat64_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct stat64 *
- jg sys32_stat64 # branch to system call
-
-ENTRY(sys32_lstat64_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct stat64 *
- jg sys32_lstat64 # branch to system call
-
-ENTRY(sys32_stime_wrapper)
- llgtr %r2,%r2 # long *
- jg compat_sys_stime # branch to system call
-
-ENTRY(sys32_fstat64_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgtr %r3,%r3 # struct stat64 *
- jg sys32_fstat64 # branch to system call
-
-ENTRY(sys32_setxattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # void *
- llgfr %r5,%r5 # size_t
- lgfr %r6,%r6 # int
- jg sys_setxattr
-
-ENTRY(sys32_lsetxattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # void *
- llgfr %r5,%r5 # size_t
- lgfr %r6,%r6 # int
- jg sys_lsetxattr
-
-ENTRY(sys32_fsetxattr_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # void *
- llgfr %r5,%r5 # size_t
- lgfr %r6,%r6 # int
- jg sys_fsetxattr
-
-ENTRY(sys32_getxattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # void *
- llgfr %r5,%r5 # size_t
- jg sys_getxattr
-
-ENTRY(sys32_lgetxattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # void *
- llgfr %r5,%r5 # size_t
- jg sys_lgetxattr
-
-ENTRY(sys32_fgetxattr_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # void *
- llgfr %r5,%r5 # size_t
- jg sys_fgetxattr
-
-ENTRY(sys32_listxattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgfr %r4,%r4 # size_t
- jg sys_listxattr
-
-ENTRY(sys32_llistxattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- llgfr %r4,%r4 # size_t
- jg sys_llistxattr
-
-ENTRY(sys32_flistxattr_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # char *
- llgfr %r4,%r4 # size_t
- jg sys_flistxattr
-
-ENTRY(sys32_removexattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- jg sys_removexattr
-
-ENTRY(sys32_lremovexattr_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # char *
- jg sys_lremovexattr
-
-ENTRY(sys32_fremovexattr_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # char *
- jg sys_fremovexattr
-
-ENTRY(sys32_sched_setaffinity_wrapper)
- lgfr %r2,%r2 # int
- llgfr %r3,%r3 # unsigned int
- llgtr %r4,%r4 # unsigned long *
- jg compat_sys_sched_setaffinity
-
-ENTRY(sys32_sched_getaffinity_wrapper)
- lgfr %r2,%r2 # int
- llgfr %r3,%r3 # unsigned int
- llgtr %r4,%r4 # unsigned long *
- jg compat_sys_sched_getaffinity
-
-ENTRY(sys32_exit_group_wrapper)
- lgfr %r2,%r2 # int
- jg sys_exit_group # branch to system call
-
-ENTRY(sys32_set_tid_address_wrapper)
- llgtr %r2,%r2 # int *
- jg sys_set_tid_address # branch to system call
-
-ENTRY(sys_epoll_create_wrapper)
- lgfr %r2,%r2 # int
- jg sys_epoll_create # branch to system call
-
-ENTRY(sys_epoll_ctl_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- lgfr %r4,%r4 # int
- llgtr %r5,%r5 # struct epoll_event *
- jg sys_epoll_ctl # branch to system call
-
-ENTRY(sys_epoll_wait_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # struct epoll_event *
- lgfr %r4,%r4 # int
- lgfr %r5,%r5 # int
- jg sys_epoll_wait # branch to system call
-
-ENTRY(sys32_fadvise64_wrapper)
- lgfr %r2,%r2 # int
- sllg %r3,%r3,32 # get high word of 64bit loff_t
- or %r3,%r4 # get low word of 64bit loff_t
- llgfr %r4,%r5 # size_t (unsigned long)
- lgfr %r5,%r6 # int
- jg sys32_fadvise64
-
-ENTRY(sys32_fadvise64_64_wrapper)
- llgtr %r2,%r2 # struct fadvise64_64_args *
- jg sys32_fadvise64_64
-
-ENTRY(sys32_clock_settime_wrapper)
- lgfr %r2,%r2 # clockid_t (int)
- llgtr %r3,%r3 # struct compat_timespec *
- jg compat_sys_clock_settime
-
-ENTRY(sys32_clock_gettime_wrapper)
- lgfr %r2,%r2 # clockid_t (int)
- llgtr %r3,%r3 # struct compat_timespec *
- jg compat_sys_clock_gettime
-
-ENTRY(sys32_clock_getres_wrapper)
- lgfr %r2,%r2 # clockid_t (int)
- llgtr %r3,%r3 # struct compat_timespec *
- jg compat_sys_clock_getres
-
-ENTRY(sys32_clock_nanosleep_wrapper)
- lgfr %r2,%r2 # clockid_t (int)
- lgfr %r3,%r3 # int
- llgtr %r4,%r4 # struct compat_timespec *
- llgtr %r5,%r5 # struct compat_timespec *
- jg compat_sys_clock_nanosleep
-
-ENTRY(sys32_timer_create_wrapper)
- lgfr %r2,%r2 # timer_t (int)
- llgtr %r3,%r3 # struct compat_sigevent *
- llgtr %r4,%r4 # timer_t *
- jg compat_sys_timer_create
-
-ENTRY(sys32_timer_settime_wrapper)
- lgfr %r2,%r2 # timer_t (int)
- lgfr %r3,%r3 # int
- llgtr %r4,%r4 # struct compat_itimerspec *
- llgtr %r5,%r5 # struct compat_itimerspec *
- jg compat_sys_timer_settime
-
-ENTRY(sys32_timer_gettime_wrapper)
- lgfr %r2,%r2 # timer_t (int)
- llgtr %r3,%r3 # struct compat_itimerspec *
- jg compat_sys_timer_gettime
-
-ENTRY(sys32_timer_getoverrun_wrapper)
- lgfr %r2,%r2 # timer_t (int)
- jg sys_timer_getoverrun
-
-ENTRY(sys32_timer_delete_wrapper)
- lgfr %r2,%r2 # timer_t (int)
- jg sys_timer_delete
-
-ENTRY(sys32_io_setup_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # u32 *
- jg compat_sys_io_setup
-
-ENTRY(sys32_io_destroy_wrapper)
- llgfr %r2,%r2 # (aio_context_t) u32
- jg sys_io_destroy
-
-ENTRY(sys32_io_getevents_wrapper)
- llgfr %r2,%r2 # (aio_context_t) u32
- lgfr %r3,%r3 # long
- lgfr %r4,%r4 # long
- llgtr %r5,%r5 # struct io_event *
- llgtr %r6,%r6 # struct compat_timespec *
- jg compat_sys_io_getevents
-
-ENTRY(sys32_io_submit_wrapper)
- llgfr %r2,%r2 # (aio_context_t) u32
- lgfr %r3,%r3 # long
- llgtr %r4,%r4 # struct iocb **
- jg compat_sys_io_submit
-
-ENTRY(sys32_io_cancel_wrapper)
- llgfr %r2,%r2 # (aio_context_t) u32
- llgtr %r3,%r3 # struct iocb *
- llgtr %r4,%r4 # struct io_event *
- jg sys_io_cancel
-
-ENTRY(compat_sys_statfs64_wrapper)
- llgtr %r2,%r2 # const char *
- llgfr %r3,%r3 # compat_size_t
- llgtr %r4,%r4 # struct compat_statfs64 *
- jg compat_sys_statfs64
-
-ENTRY(compat_sys_fstatfs64_wrapper)
- llgfr %r2,%r2 # unsigned int fd
- llgfr %r3,%r3 # compat_size_t
- llgtr %r4,%r4 # struct compat_statfs64 *
- jg compat_sys_fstatfs64
-
-ENTRY(compat_sys_mq_open_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- llgfr %r4,%r4 # mode_t
- llgtr %r5,%r5 # struct compat_mq_attr *
- jg compat_sys_mq_open
-
-ENTRY(sys32_mq_unlink_wrapper)
- llgtr %r2,%r2 # const char *
- jg sys_mq_unlink
-
-ENTRY(compat_sys_mq_timedsend_wrapper)
- lgfr %r2,%r2 # mqd_t
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # size_t
- llgfr %r5,%r5 # unsigned int
- llgtr %r6,%r6 # const struct compat_timespec *
- jg compat_sys_mq_timedsend
-
-ENTRY(compat_sys_mq_timedreceive_wrapper)
- lgfr %r2,%r2 # mqd_t
- llgtr %r3,%r3 # char *
- llgfr %r4,%r4 # size_t
- llgtr %r5,%r5 # unsigned int *
- llgtr %r6,%r6 # const struct compat_timespec *
- jg compat_sys_mq_timedreceive
-
-ENTRY(compat_sys_mq_notify_wrapper)
- lgfr %r2,%r2 # mqd_t
- llgtr %r3,%r3 # struct compat_sigevent *
- jg compat_sys_mq_notify
-
-ENTRY(compat_sys_mq_getsetattr_wrapper)
- lgfr %r2,%r2 # mqd_t
- llgtr %r3,%r3 # struct compat_mq_attr *
- llgtr %r4,%r4 # struct compat_mq_attr *
- jg compat_sys_mq_getsetattr
-
-ENTRY(compat_sys_add_key_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # const char *
- llgtr %r4,%r4 # const void *
- llgfr %r5,%r5 # size_t
- llgfr %r6,%r6 # (key_serial_t) u32
- jg sys_add_key
-
-ENTRY(compat_sys_request_key_wrapper)
- llgtr %r2,%r2 # const char *
- llgtr %r3,%r3 # const char *
- llgtr %r4,%r4 # const void *
- llgfr %r5,%r5 # (key_serial_t) u32
- jg sys_request_key
-
-ENTRY(sys32_remap_file_pages_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # unsigned long
- llgfr %r4,%r4 # unsigned long
- llgfr %r5,%r5 # unsigned long
- llgfr %r6,%r6 # unsigned long
- jg sys_remap_file_pages
-
-ENTRY(compat_sys_kexec_load_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # unsigned long
- llgtr %r4,%r4 # struct kexec_segment *
- llgfr %r5,%r5 # unsigned long
- jg compat_sys_kexec_load
-
-ENTRY(sys_ioprio_set_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- lgfr %r4,%r4 # int
- jg sys_ioprio_set
-
-ENTRY(sys_ioprio_get_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- jg sys_ioprio_get
-
-ENTRY(sys_inotify_add_watch_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # u32
- jg sys_inotify_add_watch
-
-ENTRY(sys_inotify_rm_watch_wrapper)
- lgfr %r2,%r2 # int
- llgfr %r3,%r3 # u32
- jg sys_inotify_rm_watch
-
-ENTRY(sys_mkdirat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- lgfr %r4,%r4 # int
- jg sys_mkdirat
-
-ENTRY(sys_mknodat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- lgfr %r4,%r4 # int
- llgfr %r5,%r5 # unsigned int
- jg sys_mknodat
-
-ENTRY(sys_fchownat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # uid_t
- llgfr %r5,%r5 # gid_t
- lgfr %r6,%r6 # int
- jg sys_fchownat
-
-ENTRY(compat_sys_futimesat_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # struct timeval *
- jg compat_sys_futimesat
-
-ENTRY(sys32_fstatat64_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # struct stat64 *
- lgfr %r5,%r5 # int
- jg sys32_fstatat64
-
-ENTRY(sys_unlinkat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- lgfr %r4,%r4 # int
- jg sys_unlinkat
-
-ENTRY(sys_renameat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- lgfr %r4,%r4 # int
- llgtr %r5,%r5 # const char *
- jg sys_renameat
-
-ENTRY(sys_linkat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- lgfr %r4,%r4 # int
- llgtr %r5,%r5 # const char *
- lgfr %r6,%r6 # int
- jg sys_linkat
-
-ENTRY(sys_symlinkat_wrapper)
- llgtr %r2,%r2 # const char *
- lgfr %r3,%r3 # int
- llgtr %r4,%r4 # const char *
- jg sys_symlinkat
-
-ENTRY(sys_readlinkat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- llgtr %r4,%r4 # char *
- lgfr %r5,%r5 # int
- jg sys_readlinkat
-
-ENTRY(sys_fchmodat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- llgfr %r4,%r4 # mode_t
- jg sys_fchmodat
-
-ENTRY(sys_faccessat_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char *
- lgfr %r4,%r4 # int
- jg sys_faccessat
-
-ENTRY(compat_sys_pselect6_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # fd_set *
- llgtr %r4,%r4 # fd_set *
- llgtr %r5,%r5 # fd_set *
- llgtr %r6,%r6 # struct timespec *
- llgt %r0,164(%r15) # void *
- stg %r0,160(%r15)
- jg compat_sys_pselect6
-
-ENTRY(compat_sys_ppoll_wrapper)
- llgtr %r2,%r2 # struct pollfd *
- llgfr %r3,%r3 # unsigned int
- llgtr %r4,%r4 # struct timespec *
- llgtr %r5,%r5 # const sigset_t *
- llgfr %r6,%r6 # size_t
- jg compat_sys_ppoll
-
-ENTRY(sys_unshare_wrapper)
- llgfr %r2,%r2 # unsigned long
- jg sys_unshare
-
-ENTRY(sys_splice_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # loff_t *
- lgfr %r4,%r4 # int
- llgtr %r5,%r5 # loff_t *
- llgfr %r6,%r6 # size_t
- llgf %r0,164(%r15) # unsigned int
- stg %r0,160(%r15)
- jg sys_splice
-
-ENTRY(sys_sync_file_range_wrapper)
- lgfr %r2,%r2 # int
- sllg %r3,%r3,32 # get high word of 64bit loff_t
- or %r3,%r4 # get low word of 64bit loff_t
- sllg %r4,%r5,32 # get high word of 64bit loff_t
- or %r4,%r6 # get low word of 64bit loff_t
- llgf %r5,164(%r15) # unsigned int
- jg sys_sync_file_range
-
-ENTRY(sys_tee_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- llgfr %r4,%r4 # size_t
- llgfr %r5,%r5 # unsigned int
- jg sys_tee
-
-ENTRY(sys_getcpu_wrapper)
- llgtr %r2,%r2 # unsigned *
- llgtr %r3,%r3 # unsigned *
- llgtr %r4,%r4 # struct getcpu_cache *
- jg sys_getcpu
-
-ENTRY(compat_sys_utimes_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # struct compat_timeval *
- jg compat_sys_utimes
-
-ENTRY(compat_sys_utimensat_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgtr %r3,%r3 # char *
- llgtr %r4,%r4 # struct compat_timespec *
- lgfr %r5,%r5 # int
- jg compat_sys_utimensat
-
-ENTRY(sys_eventfd_wrapper)
- llgfr %r2,%r2 # unsigned int
- jg sys_eventfd
-
-ENTRY(sys_fallocate_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- sllg %r4,%r4,32 # get high word of 64bit loff_t
- lr %r4,%r5 # get low word of 64bit loff_t
- sllg %r5,%r6,32 # get high word of 64bit loff_t
- l %r5,164(%r15) # get low word of 64bit loff_t
- jg sys_fallocate
-
-ENTRY(sys_timerfd_create_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- jg sys_timerfd_create
-
-ENTRY(sys_eventfd2_wrapper)
- llgfr %r2,%r2 # unsigned int
- lgfr %r3,%r3 # int
- jg sys_eventfd2
-
-ENTRY(sys_inotify_init1_wrapper)
- lgfr %r2,%r2 # int
- jg sys_inotify_init1
-
-ENTRY(sys_pipe2_wrapper)
- llgtr %r2,%r2 # u32 *
- lgfr %r3,%r3 # int
- jg sys_pipe2 # branch to system call
-
-ENTRY(sys_dup3_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- lgfr %r4,%r4 # int
- jg sys_dup3 # branch to system call
-
-ENTRY(sys_epoll_create1_wrapper)
- lgfr %r2,%r2 # int
- jg sys_epoll_create1 # branch to system call
-
-ENTRY(sys32_readahead_wrapper)
- lgfr %r2,%r2 # int
- llgfr %r3,%r3 # u32
- llgfr %r4,%r4 # u32
- lgfr %r5,%r5 # s32
- jg sys32_readahead # branch to system call
-
-ENTRY(sys_tkill_wrapper)
- lgfr %r2,%r2 # pid_t
- lgfr %r3,%r3 # int
- jg sys_tkill # branch to system call
-
-ENTRY(sys_tgkill_wrapper)
- lgfr %r2,%r2 # pid_t
- lgfr %r3,%r3 # pid_t
- lgfr %r4,%r4 # int
- jg sys_tgkill # branch to system call
-
-ENTRY(compat_sys_keyctl_wrapper)
- llgfr %r2,%r2 # u32
- llgfr %r3,%r3 # u32
- llgfr %r4,%r4 # u32
- llgfr %r5,%r5 # u32
- llgfr %r6,%r6 # u32
- jg compat_sys_keyctl # branch to system call
-
-ENTRY(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_event_open # branch to system call
-
-ENTRY(sys_clone_wrapper)
- llgfr %r2,%r2 # unsigned long
- llgfr %r3,%r3 # unsigned long
- llgtr %r4,%r4 # int *
- llgtr %r5,%r5 # int *
- jg sys_clone # branch to system call
-
-ENTRY(sys32_execve_wrapper)
- llgtr %r2,%r2 # char *
- llgtr %r3,%r3 # compat_uptr_t *
- llgtr %r4,%r4 # compat_uptr_t *
- jg compat_sys_execve # branch to system call
-
-ENTRY(sys_fanotify_init_wrapper)
- llgfr %r2,%r2 # unsigned int
- llgfr %r3,%r3 # unsigned int
- jg sys_fanotify_init # branch to system call
-
-ENTRY(sys_prlimit64_wrapper)
- lgfr %r2,%r2 # pid_t
- llgfr %r3,%r3 # unsigned int
- llgtr %r4,%r4 # const struct rlimit64 __user *
- llgtr %r5,%r5 # struct rlimit64 __user *
- jg sys_prlimit64 # branch to system call
-
-ENTRY(sys_name_to_handle_at_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char __user *
- llgtr %r4,%r4 # struct file_handle __user *
- llgtr %r5,%r5 # int __user *
- lgfr %r6,%r6 # int
- jg sys_name_to_handle_at
-
-ENTRY(compat_sys_clock_adjtime_wrapper)
- lgfr %r2,%r2 # clockid_t (int)
- llgtr %r3,%r3 # struct compat_timex __user *
- jg compat_sys_clock_adjtime
-
-ENTRY(sys_syncfs_wrapper)
- lgfr %r2,%r2 # int
- jg sys_syncfs
-
-ENTRY(sys_setns_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- jg sys_setns
-
-ENTRY(compat_sys_process_vm_readv_wrapper)
- lgfr %r2,%r2 # compat_pid_t
- llgtr %r3,%r3 # struct compat_iovec __user *
- llgfr %r4,%r4 # unsigned long
- llgtr %r5,%r5 # struct compat_iovec __user *
- llgfr %r6,%r6 # unsigned long
- llgf %r0,164(%r15) # unsigned long
- stg %r0,160(%r15)
- jg compat_sys_process_vm_readv
-
-ENTRY(compat_sys_process_vm_writev_wrapper)
- lgfr %r2,%r2 # compat_pid_t
- llgtr %r3,%r3 # struct compat_iovec __user *
- llgfr %r4,%r4 # unsigned long
- llgtr %r5,%r5 # struct compat_iovec __user *
- llgfr %r6,%r6 # unsigned long
- llgf %r0,164(%r15) # unsigned long
- stg %r0,160(%r15)
- jg compat_sys_process_vm_writev
-
-ENTRY(sys_s390_runtime_instr_wrapper)
- lgfr %r2,%r2 # int
- lgfr %r3,%r3 # int
- jg sys_s390_runtime_instr
-
-ENTRY(sys_kcmp_wrapper)
- lgfr %r2,%r2 # pid_t
- lgfr %r3,%r3 # pid_t
- lgfr %r4,%r4 # int
- llgfr %r5,%r5 # unsigned long
- llgfr %r6,%r6 # unsigned long
- jg sys_kcmp
-
-ENTRY(sys_finit_module_wrapper)
- lgfr %r2,%r2 # int
- llgtr %r3,%r3 # const char __user *
- lgfr %r4,%r4 # int
- jg sys_finit_module
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
new file mode 100644
index 00000000000..824c39dfddf
--- /dev/null
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -0,0 +1,215 @@
+/*
+ * Compat sytem call wrappers.
+ *
+ * Copyright IBM Corp. 2014
+ */
+
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include "entry.h"
+
+#define COMPAT_SYSCALL_WRAP1(name, ...) \
+ COMPAT_SYSCALL_WRAPx(1, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP2(name, ...) \
+ COMPAT_SYSCALL_WRAPx(2, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP3(name, ...) \
+ COMPAT_SYSCALL_WRAPx(3, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP4(name, ...) \
+ COMPAT_SYSCALL_WRAPx(4, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP5(name, ...) \
+ COMPAT_SYSCALL_WRAPx(5, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP6(name, ...) \
+ COMPAT_SYSCALL_WRAPx(6, _##name, __VA_ARGS__)
+
+#define __SC_COMPAT_TYPE(t, a) \
+ __typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a
+
+#define __SC_COMPAT_CAST(t, a) \
+({ \
+ long __ReS = a; \
+ \
+ BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) && \
+ !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t)); \
+ if (__TYPE_IS_L(t)) \
+ __ReS = (s32)a; \
+ if (__TYPE_IS_UL(t)) \
+ __ReS = (u32)a; \
+ if (__TYPE_IS_PTR(t)) \
+ __ReS = a & 0x7fffffff; \
+ (t)__ReS; \
+})
+
+/*
+ * The COMPAT_SYSCALL_WRAP macro generates system call wrappers to be used by
+ * compat tasks. These wrappers will only be used for system calls where only
+ * the system call arguments need sign or zero extension or zeroing of the upper
+ * 33 bits of pointers.
+ * Note: since the wrapper function will afterwards call a system call which
+ * again performs zero and sign extension for all system call arguments with
+ * a size of less than eight bytes, these compat wrappers only touch those
+ * system call arguments with a size of eight bytes ((unsigned) long and
+ * pointers). Zero and sign extension for e.g. int parameters will be done by
+ * the regular system call wrappers.
+ */
+#define COMPAT_SYSCALL_WRAPx(x, name, ...) \
+ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
+ asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__)) \
+ { \
+ return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__)); \
+ }
+
+COMPAT_SYSCALL_WRAP1(exit, int, error_code);
+COMPAT_SYSCALL_WRAP1(close, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename);
+COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name);
+COMPAT_SYSCALL_WRAP1(alarm, unsigned int, seconds);
+COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(nice, int, increment);
+COMPAT_SYSCALL_WRAP2(kill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(dup, unsigned int, fildes);
+COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes);
+COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk);
+COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler);
+COMPAT_SYSCALL_WRAP1(acct, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags);
+COMPAT_SYSCALL_WRAP2(setpgid, pid_t, pid, pid_t, pgid);
+COMPAT_SYSCALL_WRAP1(umask, int, mask);
+COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename);
+COMPAT_SYSCALL_WRAP2(dup2, unsigned int, oldfd, unsigned int, newfd);
+COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask);
+COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new);
+COMPAT_SYSCALL_WRAP3(readlink, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library);
+COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags);
+COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg);
+COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len);
+COMPAT_SYSCALL_WRAP2(fchmod, unsigned int, fd, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(getpriority, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(setpriority, int, which, int, who, int, niceval);
+COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len);
+COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile);
+COMPAT_SYSCALL_WRAP1(fsync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name);
+COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot);
+COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs);
+COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr);
+COMPAT_SYSCALL_WRAP1(getpgid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fchdir, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data);
+COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2);
+COMPAT_SYSCALL_WRAP1(s390_personality, unsigned int, personality);
+COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence);
+COMPAT_SYSCALL_WRAP2(flock, unsigned int, fd, unsigned int, cmd);
+COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags);
+COMPAT_SYSCALL_WRAP1(getsid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fdatasync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP1(mlockall, int, flags);
+COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP1(sched_getscheduler, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_max, int, policy);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_min, int, policy);
+COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr);
+COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout);
+COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5);
+COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size);
+COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr);
+COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data);
+COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP2(setreuid, uid_t, ruid, uid_t, euid);
+COMPAT_SYSCALL_WRAP2(setregid, gid_t, rgid, gid_t, egid);
+COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP3(fchown, unsigned int, fd, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid);
+COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid);
+COMPAT_SYSCALL_WRAP3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid);
+COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid);
+COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP1(setuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP1(setfsuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setfsgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old);
+COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec);
+COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior);
+COMPAT_SYSCALL_WRAP5(setxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(lsetxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(fsetxattr, int, fd, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count);
+COMPAT_SYSCALL_WRAP4(getxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(lgetxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP3(listxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(llistxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name);
+COMPAT_SYSCALL_WRAP1(exit_group, int, error_code);
+COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr);
+COMPAT_SYSCALL_WRAP1(epoll_create, int, size);
+COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event);
+COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout);
+COMPAT_SYSCALL_WRAP1(timer_getoverrun, timer_t, timer_id);
+COMPAT_SYSCALL_WRAP1(timer_delete, compat_timer_t, compat_timer_id);
+COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx);
+COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result);
+COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name);
+COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id);
+COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id);
+COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags);
+COMPAT_SYSCALL_WRAP3(ioprio_set, int, which, int, who, int, ioprio);
+COMPAT_SYSCALL_WRAP2(ioprio_get, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask);
+COMPAT_SYSCALL_WRAP2(inotify_rm_watch, int, fd, __s32, wd);
+COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag);
+COMPAT_SYSCALL_WRAP3(unlinkat, int, dfd, const char __user *, pathname, int, flag);
+COMPAT_SYSCALL_WRAP4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags);
+COMPAT_SYSCALL_WRAP3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP4(readlinkat, int, dfd, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP3(faccessat, int, dfd, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags);
+COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache);
+COMPAT_SYSCALL_WRAP1(eventfd, unsigned int, count);
+COMPAT_SYSCALL_WRAP2(timerfd_create, int, clockid, int, flags);
+COMPAT_SYSCALL_WRAP2(eventfd2, unsigned int, count, int, flags);
+COMPAT_SYSCALL_WRAP1(inotify_init1, int, flags);
+COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags);
+COMPAT_SYSCALL_WRAP3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags);
+COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags);
+COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
+COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val);
+COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags);
+COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
+COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
+COMPAT_SYSCALL_WRAP1(syncfs, int, fd);
+COMPAT_SYSCALL_WRAP2(setns, int, fd, int, nstype);
+COMPAT_SYSCALL_WRAP2(s390_runtime_instr, int, command, int, signum);
+COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2);
+COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
+COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index fca20b5fe79..a734f3585ce 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -380,14 +380,14 @@ 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))
S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
if (test_facility(66))
S390_lowcore.machine_flags |= MACHINE_FLAG_RRBM;
+ if (test_facility(51))
+ S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
#endif
}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 0dc2b6d0a1e..1662038516c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -38,11 +38,12 @@ __PT_R14 = __PT_GPRS + 56
__PT_R15 = __PT_GPRS + 60
_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
- _TIF_MCCK_PENDING | _TIF_PER_TRAP )
+ _TIF_MCCK_PENDING | _TIF_PER_TRAP | _TIF_ASCE)
_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
- _TIF_MCCK_PENDING)
+ _TIF_MCCK_PENDING | _TIF_ASCE)
_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
@@ -238,6 +241,8 @@ sysc_work:
jo sysc_sigpending
tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME
jo sysc_notify_resume
+ tm __TI_flags+3(%r12),_TIF_ASCE
+ jo sysc_uaccess
j sysc_return # beware of critical section cleanup
#
@@ -257,6 +262,14 @@ sysc_mcck_pending:
br %r1 # TIF bit will be cleared by handler
#
+# _TIF_ASCE is set, load user space asce
+#
+sysc_uaccess:
+ ni __TI_flags+3(%r12),255-_TIF_ASCE
+ lctl %c1,%c1,__LC_USER_ASCE # load primary asce
+ j sysc_return
+
+#
# _TIF_SIGPENDING is set, call do_signal
#
sysc_sigpending:
@@ -519,6 +532,8 @@ io_work_tif:
jo io_sigpending
tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME
jo io_notify_resume
+ tm __TI_flags+3(%r12),_TIF_ASCE
+ jo io_uaccess
j io_return # beware of critical section cleanup
#
@@ -532,6 +547,14 @@ io_mcck_pending:
j io_return
#
+# _TIF_ASCE is set, load user space asce
+#
+io_uaccess:
+ ni __TI_flags+3(%r12),255-_TIF_ASCE
+ lctl %c1,%c1,__LC_USER_ASCE # load primary asce
+ j io_return
+
+#
# _TIF_NEED_RESCHED is set, call schedule
#
io_reschedule:
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index cb533f78c09..6ac78192455 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -67,9 +67,7 @@ struct s390_mmap_arg_struct;
struct fadvise64_64_args;
struct old_sigaction;
-long sys_sigreturn(void);
-long sys_rt_sigreturn(void);
-long sys32_sigreturn(void);
-long sys32_rt_sigreturn(void);
+long sys_s390_personality(unsigned int personality);
+long sys_s390_runtime_instr(int command, int signum);
#endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index e5b43c97a83..5963e43618b 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -43,11 +43,12 @@ STACK_SIZE = 1 << STACK_SHIFT
STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
- _TIF_MCCK_PENDING | _TIF_PER_TRAP )
+ _TIF_MCCK_PENDING | _TIF_PER_TRAP | _TIF_ASCE)
_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
- _TIF_MCCK_PENDING)
+ _TIF_MCCK_PENDING | _TIF_ASCE)
_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)
@@ -74,7 +75,7 @@ _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
.endm
.macro LPP newpp
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_LPP
jz .+8
.insn s,0xb2800000,\newpp
@@ -82,7 +83,7 @@ _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
.endm
.macro HANDLE_SIE_INTERCEPT scratch,reason
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
tmhh %r8,0x0001 # interrupting from user ?
jnz .+62
lgr \scratch,%r9
@@ -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
@@ -272,6 +275,8 @@ sysc_work:
jo sysc_sigpending
tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME
jo sysc_notify_resume
+ tm __TI_flags+7(%r12),_TIF_ASCE
+ jo sysc_uaccess
j sysc_return # beware of critical section cleanup
#
@@ -289,6 +294,14 @@ sysc_mcck_pending:
jg s390_handle_mcck # TIF bit will be cleared by handler
#
+# _TIF_ASCE is set, load user space asce
+#
+sysc_uaccess:
+ ni __TI_flags+7(%r12),255-_TIF_ASCE
+ lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ j sysc_return
+
+#
# _TIF_SIGPENDING is set, call do_signal
#
sysc_sigpending:
@@ -556,6 +569,8 @@ io_work_tif:
jo io_sigpending
tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME
jo io_notify_resume
+ tm __TI_flags+7(%r12),_TIF_ASCE
+ jo io_uaccess
j io_return # beware of critical section cleanup
#
@@ -568,6 +583,14 @@ io_mcck_pending:
j io_return
#
+# _TIF_ASCE is set, load user space asce
+#
+io_uaccess:
+ ni __TI_flags+7(%r12),255-_TIF_ASCE
+ lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ j io_return
+
+#
# _TIF_NEED_RESCHED is set, call schedule
#
io_reschedule:
@@ -946,7 +969,7 @@ cleanup_idle_insn:
.quad __critical_end - __critical_start
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
/*
* sie64a calling convention:
* %r2 pointer to sie control block
@@ -975,7 +998,7 @@ sie_done:
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
# some program checks are suppressing. C code (e.g. do_protection_exception)
# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions beween sie64a and sie_done should not cause program
+# instructions between sie64a and sie_done should not cause program
# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
# See also HANDLE_SIE_INTERCEPT
rewind_pad:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 224db03e951..54d6493c4a5 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -130,9 +130,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
return 0;
}
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
{
- *(unsigned long *) data = 0;
return 0;
}
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae2579..d7c00507568 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@ ENTRY(startup_continue)
.quad 0 # cr12: tracing off
.quad 0 # cr13: home space segment table
.quad 0xc0000000 # cr14: machine check handling off
- .quad 0 # cr15: linkage stack operations
+ .quad .Llinkage_stack # cr15: linkage stack operations
.Lpcmsk:.quad 0x0000000180000000
.L4malign:.quad 0xffffffffffc00000
.Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8
@@ -67,12 +67,15 @@ ENTRY(startup_continue)
.Lparmaddr:
.quad PARMAREA
.align 64
-.Lduct: .long 0,0,0,0,.Lduald,0,0,0
+.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0
.long 0,0,0,0,0,0,0,0
+.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0
.align 128
.Lduald:.rept 8
.long 0x80000000,0,0,0 # invalid access-list entries
.endr
+.Llinkage_stack:
+ .long 0,0,0x89000000,0,0,0,0x8a000000,0
ENTRY(_ehead)
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index bb27a262c44..c7463aa0014 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -18,6 +18,7 @@
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/irq.h>
#include <asm/irq_regs.h>
#include <asm/cputime.h>
#include <asm/lowcore.h>
@@ -84,6 +85,7 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
[IRQIO_PCI] = {.name = "PCI", .desc = "[I/O] PCI Interrupt" },
[IRQIO_MSI] = {.name = "MSI", .desc = "[I/O] MSI Interrupt" },
[IRQIO_VIR] = {.name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
+ [IRQIO_VAI] = {.name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"},
[NMI_NMI] = {.name = "NMI", .desc = "[NMI] Machine Check"},
[CPU_RST] = {.name = "RST", .desc = "[CPU] CPU Restart"},
};
@@ -205,7 +207,7 @@ static inline int ext_hash(u16 code)
return (code + (code >> 9)) & (ARRAY_SIZE(ext_int_hash) - 1);
}
-int register_external_interrupt(u16 code, ext_int_handler_t handler)
+int register_external_irq(u16 code, ext_int_handler_t handler)
{
struct ext_int_info *p;
unsigned long flags;
@@ -223,9 +225,9 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler)
spin_unlock_irqrestore(&ext_int_hash_lock, flags);
return 0;
}
-EXPORT_SYMBOL(register_external_interrupt);
+EXPORT_SYMBOL(register_external_irq);
-int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
+int unregister_external_irq(u16 code, ext_int_handler_t handler)
{
struct ext_int_info *p;
unsigned long flags;
@@ -241,7 +243,7 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
spin_unlock_irqrestore(&ext_int_hash_lock, flags);
return 0;
}
-EXPORT_SYMBOL(unregister_external_interrupt);
+EXPORT_SYMBOL(unregister_external_irq);
static irqreturn_t do_ext_interrupt(int irq, void *dummy)
{
@@ -251,7 +253,7 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy)
int index;
ext_code = *(struct ext_code *) &regs->int_code;
- if (ext_code.code != 0x1004)
+ if (ext_code.code != EXT_IRQ_CLK_COMP)
__get_cpu_var(s390_idle).nohz_delay = 1;
index = ext_hash(ext_code.code);
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 1105502bf6e..ea75d011a6f 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -673,17 +673,20 @@ static int __init cpumf_pmu_init(void)
ctl_clear_bit(0, 48);
/* register handler for measurement-alert interruptions */
- rc = register_external_interrupt(0x1407, cpumf_measurement_alert);
+ rc = register_external_irq(EXT_IRQ_MEASURE_ALERT,
+ cpumf_measurement_alert);
if (rc) {
pr_err("Registering for CPU-measurement alerts "
"failed with rc=%i\n", rc);
goto out;
}
+ cpumf_pmu.attr_groups = cpumf_cf_event_group();
rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
if (rc) {
pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
- unregister_external_interrupt(0x1407, cpumf_measurement_alert);
+ unregister_external_irq(EXT_IRQ_MEASURE_ALERT,
+ cpumf_measurement_alert);
goto out;
}
perf_cpu_notifier(cpumf_pmu_notifier);
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
new file mode 100644
index 00000000000..4554a4bae39
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -0,0 +1,322 @@
+/*
+ * Perf PMU sysfs events attributes for available CPU-measurement counters
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+
+
+/* BEGIN: CPUM_CF COUNTER DEFINITIONS =================================== */
+
+CPUMF_EVENT_ATTR(cf, CPU_CYCLES, 0x0000);
+CPUMF_EVENT_ATTR(cf, INSTRUCTIONS, 0x0001);
+CPUMF_EVENT_ATTR(cf, L1I_DIR_WRITES, 0x0002);
+CPUMF_EVENT_ATTR(cf, L1I_PENALTY_CYCLES, 0x0003);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_CPU_CYCLES, 0x0020);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_INSTRUCTIONS, 0x0021);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_DIR_WRITES, 0x0022);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES, 0x0023);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_DIR_WRITES, 0x0024);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES, 0x0025);
+CPUMF_EVENT_ATTR(cf, L1D_DIR_WRITES, 0x0004);
+CPUMF_EVENT_ATTR(cf, L1D_PENALTY_CYCLES, 0x0005);
+CPUMF_EVENT_ATTR(cf, PRNG_FUNCTIONS, 0x0040);
+CPUMF_EVENT_ATTR(cf, PRNG_CYCLES, 0x0041);
+CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_FUNCTIONS, 0x0042);
+CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_CYCLES, 0x0043);
+CPUMF_EVENT_ATTR(cf, SHA_FUNCTIONS, 0x0044);
+CPUMF_EVENT_ATTR(cf, SHA_CYCLES, 0x0045);
+CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_FUNCTIONS, 0x0046);
+CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_CYCLES, 0x0047);
+CPUMF_EVENT_ATTR(cf, DEA_FUNCTIONS, 0x0048);
+CPUMF_EVENT_ATTR(cf, DEA_CYCLES, 0x0049);
+CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_FUNCTIONS, 0x004a);
+CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_CYCLES, 0x004b);
+CPUMF_EVENT_ATTR(cf, AES_FUNCTIONS, 0x004c);
+CPUMF_EVENT_ATTR(cf, AES_CYCLES, 0x004d);
+CPUMF_EVENT_ATTR(cf, AES_BLOCKED_FUNCTIONS, 0x004e);
+CPUMF_EVENT_ATTR(cf, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L3_LOCAL_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L3_REMOTE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L3_REMOTE_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_z10, L1D_LMEM_SOURCED_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z10, L1I_LMEM_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z10, L1D_RO_EXCL_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z10, L1I_CACHELINE_INVALIDATES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z10, ITLB1_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z10, DTLB1_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_PTE_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_z10, ITLB1_MISSES, 0x0091);
+CPUMF_EVENT_ATTR(cf_z10, DTLB1_MISSES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z10, L2C_STORES_SENT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z196, L1D_L2_SOURCED_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z196, L1I_L2_SOURCED_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z196, ITLB1_MISSES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z196, L2C_STORES_SENT, 0x0085);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z196, L1D_RO_EXCL_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_HPAGE_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_z196, L1D_LMEM_SOURCED_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_z196, L1I_LMEM_SOURCED_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_z196, ITLB1_WRITES, 0x0091);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_PTE_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES, 0x0093);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0096);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0098);
+CPUMF_EVENT_ATTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_MISSES, 0x0080);
+CPUMF_EVENT_ATTR(cf_zec12, ITLB1_MISSES, 0x0081);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_L2I_SOURCED_WRITES, 0x0082);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_L2I_SOURCED_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_L2D_SOURCED_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_LMEM_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_LMEM_SOURCED_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_RO_EXCL_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_HPAGE_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_zec12, ITLB1_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_PTE_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_WRITES, 0x008f);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0091);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0093);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TEND, 0x0095);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV, 0x0097);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV, 0x0098);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009a);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES, 0x009c);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x009d);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TEND, 0x009e);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV, 0x009f);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1);
+CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
+
+static struct attribute *cpumcf_pmu_event_attr[] = {
+ CPUMF_EVENT_PTR(cf, CPU_CYCLES),
+ CPUMF_EVENT_PTR(cf, INSTRUCTIONS),
+ CPUMF_EVENT_PTR(cf, L1I_DIR_WRITES),
+ CPUMF_EVENT_PTR(cf, L1I_PENALTY_CYCLES),
+ CPUMF_EVENT_PTR(cf, PROBLEM_STATE_CPU_CYCLES),
+ CPUMF_EVENT_PTR(cf, PROBLEM_STATE_INSTRUCTIONS),
+ CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_DIR_WRITES),
+ CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES),
+ CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_DIR_WRITES),
+ CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES),
+ CPUMF_EVENT_PTR(cf, L1D_DIR_WRITES),
+ CPUMF_EVENT_PTR(cf, L1D_PENALTY_CYCLES),
+ CPUMF_EVENT_PTR(cf, PRNG_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, PRNG_CYCLES),
+ CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf, SHA_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, SHA_CYCLES),
+ CPUMF_EVENT_PTR(cf, SHA_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, SHA_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf, DEA_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, DEA_CYCLES),
+ CPUMF_EVENT_PTR(cf, DEA_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, DEA_BLOCKED_CYCLES),
+ CPUMF_EVENT_PTR(cf, AES_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, AES_CYCLES),
+ CPUMF_EVENT_PTR(cf, AES_BLOCKED_FUNCTIONS),
+ CPUMF_EVENT_PTR(cf, AES_BLOCKED_CYCLES),
+ NULL,
+};
+
+static struct attribute *cpumcf_z10_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_z10, L1I_L2_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1D_L2_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1I_L3_LOCAL_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1D_L3_LOCAL_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1I_L3_REMOTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1D_L3_REMOTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1D_LMEM_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1I_LMEM_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1D_RO_EXCL_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, L1I_CACHELINE_INVALIDATES),
+ CPUMF_EVENT_PTR(cf_z10, ITLB1_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, DTLB1_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, TLB2_PTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_z10, ITLB1_MISSES),
+ CPUMF_EVENT_PTR(cf_z10, DTLB1_MISSES),
+ CPUMF_EVENT_PTR(cf_z10, L2C_STORES_SENT),
+ NULL,
+};
+
+static struct attribute *cpumcf_z196_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_z196, L1D_L2_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_L2_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, DTLB1_MISSES),
+ CPUMF_EVENT_PTR(cf_z196, ITLB1_MISSES),
+ CPUMF_EVENT_PTR(cf_z196, L2C_STORES_SENT),
+ CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1D_RO_EXCL_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, DTLB1_HPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1D_LMEM_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_LMEM_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, DTLB1_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, ITLB1_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, TLB2_PTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES),
+ NULL,
+};
+
+static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_zec12, DTLB1_MISSES),
+ CPUMF_EVENT_PTR(cf_zec12, ITLB1_MISSES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_L2I_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_L2I_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_L2D_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, DTLB1_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_LMEM_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_LMEM_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_RO_EXCL_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, DTLB1_HPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, ITLB1_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, TLB2_PTE_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, TX_NC_TEND),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV),
+ CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES),
+ CPUMF_EVENT_PTR(cf_zec12, TX_C_TEND),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV),
+ CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV),
+ CPUMF_EVENT_PTR(cf_zec12, TX_NC_TABORT),
+ CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_NO_SPECIAL),
+ CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_SPECIAL),
+ NULL,
+};
+
+/* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
+
+static struct attribute_group cpumsf_pmu_events_group = {
+ .name = "events",
+ .attrs = cpumcf_pmu_event_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cpumsf_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group cpumsf_pmu_format_group = {
+ .name = "format",
+ .attrs = cpumsf_pmu_format_attr,
+};
+
+static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
+ &cpumsf_pmu_events_group,
+ &cpumsf_pmu_format_group,
+ NULL,
+};
+
+
+static __init struct attribute **merge_attr(struct attribute **a,
+ struct attribute **b)
+{
+ struct attribute **new;
+ int j, i;
+
+ for (j = 0; a[j]; j++)
+ ;
+ for (i = 0; b[i]; i++)
+ j++;
+ j++;
+
+ new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+ if (!new)
+ return NULL;
+ j = 0;
+ for (i = 0; a[i]; i++)
+ new[j++] = a[i];
+ for (i = 0; b[i]; i++)
+ new[j++] = b[i];
+ new[j] = NULL;
+
+ return new;
+}
+
+__init const struct attribute_group **cpumf_cf_event_group(void)
+{
+ struct attribute **combined, **model;
+ struct cpuid cpu_id;
+
+ get_cpu_id(&cpu_id);
+ switch (cpu_id.machine) {
+ case 0x2097:
+ case 0x2098:
+ model = cpumcf_z10_pmu_event_attr;
+ break;
+ case 0x2817:
+ case 0x2818:
+ model = cpumcf_z196_pmu_event_attr;
+ break;
+ case 0x2827:
+ case 0x2828:
+ model = cpumcf_zec12_pmu_event_attr;
+ break;
+ default:
+ model = NULL;
+ break;
+ };
+
+ if (!model)
+ goto out;
+
+ combined = merge_attr(cpumcf_pmu_event_attr, model);
+ if (combined)
+ cpumsf_pmu_events_group.attrs = combined;
+out:
+ return cpumsf_pmu_attr_groups;
+}
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
new file mode 100644
index 00000000000..ea0c7b2ef03
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -0,0 +1,1643 @@
+/*
+ * Performance event support for the System z CPU-measurement Sampling Facility
+ *
+ * Copyright IBM Corp. 2013
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#define KMSG_COMPONENT "cpum_sf"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/moduleparam.h>
+#include <asm/cpu_mf.h>
+#include <asm/irq.h>
+#include <asm/debug.h>
+#include <asm/timex.h>
+
+/* Minimum number of sample-data-block-tables:
+ * At least one table is required for the sampling buffer structure.
+ * A single table contains up to 511 pointers to sample-data-blocks.
+ */
+#define CPUM_SF_MIN_SDBT 1
+
+/* Number of sample-data-blocks per sample-data-block-table (SDBT):
+ * A table contains SDB pointers (8 bytes) and one table-link entry
+ * that points to the origin of the next SDBT.
+ */
+#define CPUM_SF_SDB_PER_TABLE ((PAGE_SIZE - 8) / 8)
+
+/* Maximum page offset for an SDBT table-link entry:
+ * If this page offset is reached, a table-link entry to the next SDBT
+ * must be added.
+ */
+#define CPUM_SF_SDBT_TL_OFFSET (CPUM_SF_SDB_PER_TABLE * 8)
+static inline int require_table_link(const void *sdbt)
+{
+ return ((unsigned long) sdbt & ~PAGE_MASK) == CPUM_SF_SDBT_TL_OFFSET;
+}
+
+/* Minimum and maximum sampling buffer sizes:
+ *
+ * This number represents the maximum size of the sampling buffer taking
+ * the number of sample-data-block-tables into account. Note that these
+ * numbers apply to the basic-sampling function only.
+ * The maximum number of SDBs is increased by CPUM_SF_SDB_DIAG_FACTOR if
+ * the diagnostic-sampling function is active.
+ *
+ * Sampling buffer size Buffer characteristics
+ * ---------------------------------------------------
+ * 64KB == 16 pages (4KB per page)
+ * 1 page for SDB-tables
+ * 15 pages for SDBs
+ *
+ * 32MB == 8192 pages (4KB per page)
+ * 16 pages for SDB-tables
+ * 8176 pages for SDBs
+ */
+static unsigned long __read_mostly CPUM_SF_MIN_SDB = 15;
+static unsigned long __read_mostly CPUM_SF_MAX_SDB = 8176;
+static unsigned long __read_mostly CPUM_SF_SDB_DIAG_FACTOR = 1;
+
+struct sf_buffer {
+ unsigned long *sdbt; /* Sample-data-block-table origin */
+ /* buffer characteristics (required for buffer increments) */
+ unsigned long num_sdb; /* Number of sample-data-blocks */
+ unsigned long num_sdbt; /* Number of sample-data-block-tables */
+ unsigned long *tail; /* last sample-data-block-table */
+};
+
+struct cpu_hw_sf {
+ /* CPU-measurement sampling information block */
+ struct hws_qsi_info_block qsi;
+ /* CPU-measurement sampling control block */
+ struct hws_lsctl_request_block lsctl;
+ struct sf_buffer sfb; /* Sampling buffer */
+ unsigned int flags; /* Status flags */
+ struct perf_event *event; /* Scheduled perf event */
+};
+static DEFINE_PER_CPU(struct cpu_hw_sf, cpu_hw_sf);
+
+/* Debug feature */
+static debug_info_t *sfdbg;
+
+/*
+ * sf_disable() - Switch off sampling facility
+ */
+static int sf_disable(void)
+{
+ struct hws_lsctl_request_block sreq;
+
+ memset(&sreq, 0, sizeof(sreq));
+ return lsctl(&sreq);
+}
+
+/*
+ * sf_buffer_available() - Check for an allocated sampling buffer
+ */
+static int sf_buffer_available(struct cpu_hw_sf *cpuhw)
+{
+ return !!cpuhw->sfb.sdbt;
+}
+
+/*
+ * deallocate sampling facility buffer
+ */
+static void free_sampling_buffer(struct sf_buffer *sfb)
+{
+ unsigned long *sdbt, *curr;
+
+ if (!sfb->sdbt)
+ return;
+
+ sdbt = sfb->sdbt;
+ curr = sdbt;
+
+ /* Free the SDBT after all SDBs are processed... */
+ while (1) {
+ if (!*curr || !sdbt)
+ break;
+
+ /* Process table-link entries */
+ if (is_link_entry(curr)) {
+ curr = get_next_sdbt(curr);
+ if (sdbt)
+ free_page((unsigned long) sdbt);
+
+ /* If the origin is reached, sampling buffer is freed */
+ if (curr == sfb->sdbt)
+ break;
+ else
+ sdbt = curr;
+ } else {
+ /* Process SDB pointer */
+ if (*curr) {
+ free_page(*curr);
+ curr++;
+ }
+ }
+ }
+
+ debug_sprintf_event(sfdbg, 5,
+ "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt);
+ memset(sfb, 0, sizeof(*sfb));
+}
+
+static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags)
+{
+ unsigned long sdb, *trailer;
+
+ /* Allocate and initialize sample-data-block */
+ sdb = get_zeroed_page(gfp_flags);
+ if (!sdb)
+ return -ENOMEM;
+ trailer = trailer_entry_ptr(sdb);
+ *trailer = SDB_TE_ALERT_REQ_MASK;
+
+ /* Link SDB into the sample-data-block-table */
+ *sdbt = sdb;
+
+ return 0;
+}
+
+/*
+ * realloc_sampling_buffer() - extend sampler memory
+ *
+ * Allocates new sample-data-blocks and adds them to the specified sampling
+ * buffer memory.
+ *
+ * Important: This modifies the sampling buffer and must be called when the
+ * sampling facility is disabled.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+static int realloc_sampling_buffer(struct sf_buffer *sfb,
+ unsigned long num_sdb, gfp_t gfp_flags)
+{
+ int i, rc;
+ unsigned long *new, *tail;
+
+ if (!sfb->sdbt || !sfb->tail)
+ return -EINVAL;
+
+ if (!is_link_entry(sfb->tail))
+ return -EINVAL;
+
+ /* Append to the existing sampling buffer, overwriting the table-link
+ * register.
+ * The tail variables always points to the "tail" (last and table-link)
+ * entry in an SDB-table.
+ */
+ tail = sfb->tail;
+
+ /* Do a sanity check whether the table-link entry points to
+ * the sampling buffer origin.
+ */
+ if (sfb->sdbt != get_next_sdbt(tail)) {
+ debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: "
+ "sampling buffer is not linked: origin=%p"
+ "tail=%p\n",
+ (void *) sfb->sdbt, (void *) tail);
+ return -EINVAL;
+ }
+
+ /* Allocate remaining SDBs */
+ rc = 0;
+ for (i = 0; i < num_sdb; i++) {
+ /* Allocate a new SDB-table if it is full. */
+ if (require_table_link(tail)) {
+ new = (unsigned long *) get_zeroed_page(gfp_flags);
+ if (!new) {
+ rc = -ENOMEM;
+ break;
+ }
+ sfb->num_sdbt++;
+ /* Link current page to tail of chain */
+ *tail = (unsigned long)(void *) new + 1;
+ tail = new;
+ }
+
+ /* Allocate a new sample-data-block.
+ * If there is not enough memory, stop the realloc process
+ * and simply use what was allocated. If this is a temporary
+ * issue, a new realloc call (if required) might succeed.
+ */
+ rc = alloc_sample_data_block(tail, gfp_flags);
+ if (rc)
+ break;
+ sfb->num_sdb++;
+ tail++;
+ }
+
+ /* Link sampling buffer to its origin */
+ *tail = (unsigned long) sfb->sdbt + 1;
+ sfb->tail = tail;
+
+ debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer"
+ " settings: sdbt=%lu sdb=%lu\n",
+ sfb->num_sdbt, sfb->num_sdb);
+ return rc;
+}
+
+/*
+ * allocate_sampling_buffer() - allocate sampler memory
+ *
+ * Allocates and initializes a sampling buffer structure using the
+ * specified number of sample-data-blocks (SDB). For each allocation,
+ * a 4K page is used. The number of sample-data-block-tables (SDBT)
+ * are calculated from SDBs.
+ * Also set the ALERT_REQ mask in each SDBs trailer.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
+{
+ int rc;
+
+ if (sfb->sdbt)
+ return -EINVAL;
+
+ /* Allocate the sample-data-block-table origin */
+ sfb->sdbt = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+ if (!sfb->sdbt)
+ return -ENOMEM;
+ sfb->num_sdb = 0;
+ sfb->num_sdbt = 1;
+
+ /* Link the table origin to point to itself to prepare for
+ * realloc_sampling_buffer() invocation.
+ */
+ sfb->tail = sfb->sdbt;
+ *sfb->tail = (unsigned long)(void *) sfb->sdbt + 1;
+
+ /* Allocate requested number of sample-data-blocks */
+ rc = realloc_sampling_buffer(sfb, num_sdb, GFP_KERNEL);
+ if (rc) {
+ free_sampling_buffer(sfb);
+ debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: "
+ "realloc_sampling_buffer failed with rc=%i\n", rc);
+ } else
+ debug_sprintf_event(sfdbg, 4,
+ "alloc_sampling_buffer: tear=%p dear=%p\n",
+ sfb->sdbt, (void *) *sfb->sdbt);
+ return rc;
+}
+
+static void sfb_set_limits(unsigned long min, unsigned long max)
+{
+ struct hws_qsi_info_block si;
+
+ CPUM_SF_MIN_SDB = min;
+ CPUM_SF_MAX_SDB = max;
+
+ memset(&si, 0, sizeof(si));
+ if (!qsi(&si))
+ CPUM_SF_SDB_DIAG_FACTOR = DIV_ROUND_UP(si.dsdes, si.bsdes);
+}
+
+static unsigned long sfb_max_limit(struct hw_perf_event *hwc)
+{
+ return SAMPL_DIAG_MODE(hwc) ? CPUM_SF_MAX_SDB * CPUM_SF_SDB_DIAG_FACTOR
+ : CPUM_SF_MAX_SDB;
+}
+
+static unsigned long sfb_pending_allocs(struct sf_buffer *sfb,
+ struct hw_perf_event *hwc)
+{
+ if (!sfb->sdbt)
+ return SFB_ALLOC_REG(hwc);
+ if (SFB_ALLOC_REG(hwc) > sfb->num_sdb)
+ return SFB_ALLOC_REG(hwc) - sfb->num_sdb;
+ return 0;
+}
+
+static int sfb_has_pending_allocs(struct sf_buffer *sfb,
+ struct hw_perf_event *hwc)
+{
+ return sfb_pending_allocs(sfb, hwc) > 0;
+}
+
+static void sfb_account_allocs(unsigned long num, struct hw_perf_event *hwc)
+{
+ /* Limit the number of SDBs to not exceed the maximum */
+ num = min_t(unsigned long, num, sfb_max_limit(hwc) - SFB_ALLOC_REG(hwc));
+ if (num)
+ SFB_ALLOC_REG(hwc) += num;
+}
+
+static void sfb_init_allocs(unsigned long num, struct hw_perf_event *hwc)
+{
+ SFB_ALLOC_REG(hwc) = 0;
+ sfb_account_allocs(num, hwc);
+}
+
+static size_t event_sample_size(struct hw_perf_event *hwc)
+{
+ struct sf_raw_sample *sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc);
+ size_t sample_size;
+
+ /* The sample size depends on the sampling function: The basic-sampling
+ * function must be always enabled, diagnostic-sampling function is
+ * optional.
+ */
+ sample_size = sfr->bsdes;
+ if (SAMPL_DIAG_MODE(hwc))
+ sample_size += sfr->dsdes;
+
+ return sample_size;
+}
+
+static void deallocate_buffers(struct cpu_hw_sf *cpuhw)
+{
+ if (cpuhw->sfb.sdbt)
+ free_sampling_buffer(&cpuhw->sfb);
+}
+
+static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
+{
+ unsigned long n_sdb, freq, factor;
+ size_t sfr_size, sample_size;
+ struct sf_raw_sample *sfr;
+
+ /* Allocate raw sample buffer
+ *
+ * The raw sample buffer is used to temporarily store sampling data
+ * entries for perf raw sample processing. The buffer size mainly
+ * depends on the size of diagnostic-sampling data entries which is
+ * machine-specific. The exact size calculation includes:
+ * 1. The first 4 bytes of diagnostic-sampling data entries are
+ * already reflected in the sf_raw_sample structure. Subtract
+ * these bytes.
+ * 2. The perf raw sample data must be 8-byte aligned (u64) and
+ * perf's internal data size must be considered too. So add
+ * an additional u32 for correct alignment and subtract before
+ * allocating the buffer.
+ * 3. Store the raw sample buffer pointer in the perf event
+ * hardware structure.
+ */
+ sfr_size = ALIGN((sizeof(*sfr) - sizeof(sfr->diag) + cpuhw->qsi.dsdes) +
+ sizeof(u32), sizeof(u64));
+ sfr_size -= sizeof(u32);
+ sfr = kzalloc(sfr_size, GFP_KERNEL);
+ if (!sfr)
+ return -ENOMEM;
+ sfr->size = sfr_size;
+ sfr->bsdes = cpuhw->qsi.bsdes;
+ sfr->dsdes = cpuhw->qsi.dsdes;
+ RAWSAMPLE_REG(hwc) = (unsigned long) sfr;
+
+ /* Calculate sampling buffers using 4K pages
+ *
+ * 1. Determine the sample data size which depends on the used
+ * sampling functions, for example, basic-sampling or
+ * basic-sampling with diagnostic-sampling.
+ *
+ * 2. Use the sampling frequency as input. The sampling buffer is
+ * designed for almost one second. This can be adjusted through
+ * the "factor" variable.
+ * In any case, alloc_sampling_buffer() sets the Alert Request
+ * Control indicator to trigger a measurement-alert to harvest
+ * sample-data-blocks (sdb).
+ *
+ * 3. Compute the number of sample-data-blocks and ensure a minimum
+ * of CPUM_SF_MIN_SDB. Also ensure the upper limit does not
+ * exceed a "calculated" maximum. The symbolic maximum is
+ * designed for basic-sampling only and needs to be increased if
+ * diagnostic-sampling is active.
+ * See also the remarks for these symbolic constants.
+ *
+ * 4. Compute the number of sample-data-block-tables (SDBT) and
+ * ensure a minimum of CPUM_SF_MIN_SDBT (one table can manage up
+ * to 511 SDBs).
+ */
+ sample_size = event_sample_size(hwc);
+ freq = sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc));
+ factor = 1;
+ n_sdb = DIV_ROUND_UP(freq, factor * ((PAGE_SIZE-64) / sample_size));
+ if (n_sdb < CPUM_SF_MIN_SDB)
+ n_sdb = CPUM_SF_MIN_SDB;
+
+ /* If there is already a sampling buffer allocated, it is very likely
+ * that the sampling facility is enabled too. If the event to be
+ * initialized requires a greater sampling buffer, the allocation must
+ * be postponed. Changing the sampling buffer requires the sampling
+ * facility to be in the disabled state. So, account the number of
+ * required SDBs and let cpumsf_pmu_enable() resize the buffer just
+ * before the event is started.
+ */
+ sfb_init_allocs(n_sdb, hwc);
+ if (sf_buffer_available(cpuhw))
+ return 0;
+
+ debug_sprintf_event(sfdbg, 3,
+ "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu"
+ " sample_size=%lu cpuhw=%p\n",
+ SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc),
+ sample_size, cpuhw);
+
+ return alloc_sampling_buffer(&cpuhw->sfb,
+ sfb_pending_allocs(&cpuhw->sfb, hwc));
+}
+
+static unsigned long min_percent(unsigned int percent, unsigned long base,
+ unsigned long min)
+{
+ return min_t(unsigned long, min, DIV_ROUND_UP(percent * base, 100));
+}
+
+static unsigned long compute_sfb_extent(unsigned long ratio, unsigned long base)
+{
+ /* Use a percentage-based approach to extend the sampling facility
+ * buffer. Accept up to 5% sample data loss.
+ * Vary the extents between 1% to 5% of the current number of
+ * sample-data-blocks.
+ */
+ if (ratio <= 5)
+ return 0;
+ if (ratio <= 25)
+ return min_percent(1, base, 1);
+ if (ratio <= 50)
+ return min_percent(1, base, 1);
+ if (ratio <= 75)
+ return min_percent(2, base, 2);
+ if (ratio <= 100)
+ return min_percent(3, base, 3);
+ if (ratio <= 250)
+ return min_percent(4, base, 4);
+
+ return min_percent(5, base, 8);
+}
+
+static void sfb_account_overflows(struct cpu_hw_sf *cpuhw,
+ struct hw_perf_event *hwc)
+{
+ unsigned long ratio, num;
+
+ if (!OVERFLOW_REG(hwc))
+ return;
+
+ /* The sample_overflow contains the average number of sample data
+ * that has been lost because sample-data-blocks were full.
+ *
+ * Calculate the total number of sample data entries that has been
+ * discarded. Then calculate the ratio of lost samples to total samples
+ * per second in percent.
+ */
+ ratio = DIV_ROUND_UP(100 * OVERFLOW_REG(hwc) * cpuhw->sfb.num_sdb,
+ sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc)));
+
+ /* Compute number of sample-data-blocks */
+ num = compute_sfb_extent(ratio, cpuhw->sfb.num_sdb);
+ if (num)
+ sfb_account_allocs(num, hwc);
+
+ debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu"
+ " num=%lu\n", OVERFLOW_REG(hwc), ratio, num);
+ OVERFLOW_REG(hwc) = 0;
+}
+
+/* extend_sampling_buffer() - Extend sampling buffer
+ * @sfb: Sampling buffer structure (for local CPU)
+ * @hwc: Perf event hardware structure
+ *
+ * Use this function to extend the sampling buffer based on the overflow counter
+ * and postponed allocation extents stored in the specified Perf event hardware.
+ *
+ * Important: This function disables the sampling facility in order to safely
+ * change the sampling buffer structure. Do not call this function
+ * when the PMU is active.
+ */
+static void extend_sampling_buffer(struct sf_buffer *sfb,
+ struct hw_perf_event *hwc)
+{
+ unsigned long num, num_old;
+ int rc;
+
+ num = sfb_pending_allocs(sfb, hwc);
+ if (!num)
+ return;
+ num_old = sfb->num_sdb;
+
+ /* Disable the sampling facility to reset any states and also
+ * clear pending measurement alerts.
+ */
+ sf_disable();
+
+ /* Extend the sampling buffer.
+ * This memory allocation typically happens in an atomic context when
+ * called by perf. Because this is a reallocation, it is fine if the
+ * new SDB-request cannot be satisfied immediately.
+ */
+ rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC);
+ if (rc)
+ debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc "
+ "failed with rc=%i\n", rc);
+
+ if (sfb_has_pending_allocs(sfb, hwc))
+ debug_sprintf_event(sfdbg, 5, "sfb: extend: "
+ "req=%lu alloc=%lu remaining=%lu\n",
+ num, sfb->num_sdb - num_old,
+ sfb_pending_allocs(sfb, hwc));
+}
+
+
+/* Number of perf events counting hardware events */
+static atomic_t num_events;
+/* Used to avoid races in calling reserve/release_cpumf_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+#define PMC_INIT 0
+#define PMC_RELEASE 1
+#define PMC_FAILURE 2
+static void setup_pmc_cpu(void *flags)
+{
+ int err;
+ struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
+
+ err = 0;
+ switch (*((int *) flags)) {
+ case PMC_INIT:
+ memset(cpusf, 0, sizeof(*cpusf));
+ err = qsi(&cpusf->qsi);
+ if (err)
+ break;
+ cpusf->flags |= PMU_F_RESERVED;
+ err = sf_disable();
+ if (err)
+ pr_err("Switching off the sampling facility failed "
+ "with rc=%i\n", err);
+ debug_sprintf_event(sfdbg, 5,
+ "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf);
+ break;
+ case PMC_RELEASE:
+ cpusf->flags &= ~PMU_F_RESERVED;
+ err = sf_disable();
+ if (err) {
+ pr_err("Switching off the sampling facility failed "
+ "with rc=%i\n", err);
+ } else
+ deallocate_buffers(cpusf);
+ debug_sprintf_event(sfdbg, 5,
+ "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
+ break;
+ }
+ if (err)
+ *((int *) flags) |= PMC_FAILURE;
+}
+
+static void release_pmc_hardware(void)
+{
+ int flags = PMC_RELEASE;
+
+ irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+ on_each_cpu(setup_pmc_cpu, &flags, 1);
+ perf_release_sampling();
+}
+
+static int reserve_pmc_hardware(void)
+{
+ int flags = PMC_INIT;
+ int err;
+
+ err = perf_reserve_sampling();
+ if (err)
+ return err;
+ on_each_cpu(setup_pmc_cpu, &flags, 1);
+ if (flags & PMC_FAILURE) {
+ release_pmc_hardware();
+ return -ENODEV;
+ }
+ irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+ return 0;
+}
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+ /* Free raw sample buffer */
+ if (RAWSAMPLE_REG(&event->hw))
+ kfree((void *) RAWSAMPLE_REG(&event->hw));
+
+ /* Release PMC if this is the last perf event */
+ if (!atomic_add_unless(&num_events, -1, 1)) {
+ mutex_lock(&pmc_reserve_mutex);
+ if (atomic_dec_return(&num_events) == 0)
+ release_pmc_hardware();
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+}
+
+static void hw_init_period(struct hw_perf_event *hwc, u64 period)
+{
+ hwc->sample_period = period;
+ hwc->last_period = hwc->sample_period;
+ local64_set(&hwc->period_left, hwc->sample_period);
+}
+
+static void hw_reset_registers(struct hw_perf_event *hwc,
+ unsigned long *sdbt_origin)
+{
+ struct sf_raw_sample *sfr;
+
+ /* (Re)set to first sample-data-block-table */
+ TEAR_REG(hwc) = (unsigned long) sdbt_origin;
+
+ /* (Re)set raw sampling buffer register */
+ sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc);
+ memset(&sfr->basic, 0, sizeof(sfr->basic));
+ memset(&sfr->diag, 0, sfr->dsdes);
+}
+
+static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si,
+ unsigned long rate)
+{
+ return clamp_t(unsigned long, rate,
+ si->min_sampl_rate, si->max_sampl_rate);
+}
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+ struct cpu_hw_sf *cpuhw;
+ struct hws_qsi_info_block si;
+ struct perf_event_attr *attr = &event->attr;
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long rate;
+ int cpu, err;
+
+ /* Reserve CPU-measurement sampling facility */
+ err = 0;
+ if (!atomic_inc_not_zero(&num_events)) {
+ mutex_lock(&pmc_reserve_mutex);
+ if (atomic_read(&num_events) == 0 && reserve_pmc_hardware())
+ err = -EBUSY;
+ else
+ atomic_inc(&num_events);
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+ event->destroy = hw_perf_event_destroy;
+
+ if (err)
+ goto out;
+
+ /* Access per-CPU sampling information (query sampling info) */
+ /*
+ * The event->cpu value can be -1 to count on every CPU, for example,
+ * when attaching to a task. If this is specified, use the query
+ * sampling info from the current CPU, otherwise use event->cpu to
+ * retrieve the per-CPU information.
+ * Later, cpuhw indicates whether to allocate sampling buffers for a
+ * particular CPU (cpuhw!=NULL) or each online CPU (cpuw==NULL).
+ */
+ memset(&si, 0, sizeof(si));
+ cpuhw = NULL;
+ if (event->cpu == -1)
+ qsi(&si);
+ else {
+ /* Event is pinned to a particular CPU, retrieve the per-CPU
+ * sampling structure for accessing the CPU-specific QSI.
+ */
+ cpuhw = &per_cpu(cpu_hw_sf, event->cpu);
+ si = cpuhw->qsi;
+ }
+
+ /* Check sampling facility authorization and, if not authorized,
+ * fall back to other PMUs. It is safe to check any CPU because
+ * the authorization is identical for all configured CPUs.
+ */
+ if (!si.as) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ /* Always enable basic sampling */
+ SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE;
+
+ /* Check if diagnostic sampling is requested. Deny if the required
+ * sampling authorization is missing.
+ */
+ if (attr->config == PERF_EVENT_CPUM_SF_DIAG) {
+ if (!si.ad) {
+ err = -EPERM;
+ goto out;
+ }
+ SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_DIAG_MODE;
+ }
+
+ /* Check and set other sampling flags */
+ if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS)
+ SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS;
+
+ /* The sampling information (si) contains information about the
+ * min/max sampling intervals and the CPU speed. So calculate the
+ * correct sampling interval and avoid the whole period adjust
+ * feedback loop.
+ */
+ rate = 0;
+ if (attr->freq) {
+ rate = freq_to_sample_rate(&si, attr->sample_freq);
+ rate = hw_limit_rate(&si, rate);
+ attr->freq = 0;
+ attr->sample_period = rate;
+ } else {
+ /* The min/max sampling rates specifies the valid range
+ * of sample periods. If the specified sample period is
+ * out of range, limit the period to the range boundary.
+ */
+ rate = hw_limit_rate(&si, hwc->sample_period);
+
+ /* The perf core maintains a maximum sample rate that is
+ * configurable through the sysctl interface. Ensure the
+ * sampling rate does not exceed this value. This also helps
+ * to avoid throttling when pushing samples with
+ * perf_event_overflow().
+ */
+ if (sample_rate_to_freq(&si, rate) >
+ sysctl_perf_event_sample_rate) {
+ err = -EINVAL;
+ debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n");
+ goto out;
+ }
+ }
+ SAMPL_RATE(hwc) = rate;
+ hw_init_period(hwc, SAMPL_RATE(hwc));
+
+ /* Initialize sample data overflow accounting */
+ hwc->extra_reg.reg = REG_OVERFLOW;
+ OVERFLOW_REG(hwc) = 0;
+
+ /* Allocate the per-CPU sampling buffer using the CPU information
+ * from the event. If the event is not pinned to a particular
+ * CPU (event->cpu == -1; or cpuhw == NULL), allocate sampling
+ * buffers for each online CPU.
+ */
+ if (cpuhw)
+ /* Event is pinned to a particular CPU */
+ err = allocate_buffers(cpuhw, hwc);
+ else {
+ /* Event is not pinned, allocate sampling buffer on
+ * each online CPU
+ */
+ for_each_online_cpu(cpu) {
+ cpuhw = &per_cpu(cpu_hw_sf, cpu);
+ err = allocate_buffers(cpuhw, hwc);
+ if (err)
+ break;
+ }
+ }
+out:
+ return err;
+}
+
+static int cpumsf_pmu_event_init(struct perf_event *event)
+{
+ int err;
+
+ /* No support for taken branch sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
+ switch (event->attr.type) {
+ case PERF_TYPE_RAW:
+ if ((event->attr.config != PERF_EVENT_CPUM_SF) &&
+ (event->attr.config != PERF_EVENT_CPUM_SF_DIAG))
+ return -ENOENT;
+ break;
+ case PERF_TYPE_HARDWARE:
+ /* Support sampling of CPU cycles in addition to the
+ * counter facility. However, the counter facility
+ * is more precise and, hence, restrict this PMU to
+ * sampling events only.
+ */
+ if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES)
+ return -ENOENT;
+ if (!is_sampling_event(event))
+ return -ENOENT;
+ break;
+ default:
+ return -ENOENT;
+ }
+
+ /* Check online status of the CPU to which the event is pinned */
+ if (event->cpu >= nr_cpumask_bits ||
+ (event->cpu >= 0 && !cpu_online(event->cpu)))
+ return -ENODEV;
+
+ /* Force reset of idle/hv excludes regardless of what the
+ * user requested.
+ */
+ if (event->attr.exclude_hv)
+ event->attr.exclude_hv = 0;
+ if (event->attr.exclude_idle)
+ event->attr.exclude_idle = 0;
+
+ err = __hw_perf_event_init(event);
+ if (unlikely(err))
+ if (event->destroy)
+ event->destroy(event);
+ return err;
+}
+
+static void cpumsf_pmu_enable(struct pmu *pmu)
+{
+ struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+ struct hw_perf_event *hwc;
+ int err;
+
+ if (cpuhw->flags & PMU_F_ENABLED)
+ return;
+
+ if (cpuhw->flags & PMU_F_ERR_MASK)
+ return;
+
+ /* Check whether to extent the sampling buffer.
+ *
+ * Two conditions trigger an increase of the sampling buffer for a
+ * perf event:
+ * 1. Postponed buffer allocations from the event initialization.
+ * 2. Sampling overflows that contribute to pending allocations.
+ *
+ * Note that the extend_sampling_buffer() function disables the sampling
+ * facility, but it can be fully re-enabled using sampling controls that
+ * have been saved in cpumsf_pmu_disable().
+ */
+ if (cpuhw->event) {
+ hwc = &cpuhw->event->hw;
+ /* Account number of overflow-designated buffer extents */
+ sfb_account_overflows(cpuhw, hwc);
+ if (sfb_has_pending_allocs(&cpuhw->sfb, hwc))
+ extend_sampling_buffer(&cpuhw->sfb, hwc);
+ }
+
+ /* (Re)enable the PMU and sampling facility */
+ cpuhw->flags |= PMU_F_ENABLED;
+ barrier();
+
+ err = lsctl(&cpuhw->lsctl);
+ if (err) {
+ cpuhw->flags &= ~PMU_F_ENABLED;
+ pr_err("Loading sampling controls failed: op=%i err=%i\n",
+ 1, err);
+ return;
+ }
+
+ debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
+ "tear=%p dear=%p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs,
+ cpuhw->lsctl.ed, cpuhw->lsctl.cd,
+ (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear);
+}
+
+static void cpumsf_pmu_disable(struct pmu *pmu)
+{
+ struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+ struct hws_lsctl_request_block inactive;
+ struct hws_qsi_info_block si;
+ int err;
+
+ if (!(cpuhw->flags & PMU_F_ENABLED))
+ return;
+
+ if (cpuhw->flags & PMU_F_ERR_MASK)
+ return;
+
+ /* Switch off sampling activation control */
+ inactive = cpuhw->lsctl;
+ inactive.cs = 0;
+ inactive.cd = 0;
+
+ err = lsctl(&inactive);
+ if (err) {
+ pr_err("Loading sampling controls failed: op=%i err=%i\n",
+ 2, err);
+ return;
+ }
+
+ /* Save state of TEAR and DEAR register contents */
+ if (!qsi(&si)) {
+ /* TEAR/DEAR values are valid only if the sampling facility is
+ * enabled. Note that cpumsf_pmu_disable() might be called even
+ * for a disabled sampling facility because cpumsf_pmu_enable()
+ * controls the enable/disable state.
+ */
+ if (si.es) {
+ cpuhw->lsctl.tear = si.tear;
+ cpuhw->lsctl.dear = si.dear;
+ }
+ } else
+ debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: "
+ "qsi() failed with err=%i\n", err);
+
+ cpuhw->flags &= ~PMU_F_ENABLED;
+}
+
+/* perf_exclude_event() - Filter event
+ * @event: The perf event
+ * @regs: pt_regs structure
+ * @sde_regs: Sample-data-entry (sde) regs structure
+ *
+ * Filter perf events according to their exclude specification.
+ *
+ * Return non-zero if the event shall be excluded.
+ */
+static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs,
+ struct perf_sf_sde_regs *sde_regs)
+{
+ if (event->attr.exclude_user && user_mode(regs))
+ return 1;
+ if (event->attr.exclude_kernel && !user_mode(regs))
+ return 1;
+ if (event->attr.exclude_guest && sde_regs->in_guest)
+ return 1;
+ if (event->attr.exclude_host && !sde_regs->in_guest)
+ return 1;
+ return 0;
+}
+
+/* perf_push_sample() - Push samples to perf
+ * @event: The perf event
+ * @sample: Hardware sample data
+ *
+ * Use the hardware sample data to create perf event sample. The sample
+ * is the pushed to the event subsystem and the function checks for
+ * possible event overflows. If an event overflow occurs, the PMU is
+ * stopped.
+ *
+ * Return non-zero if an event overflow occurred.
+ */
+static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
+{
+ int overflow;
+ struct pt_regs regs;
+ struct perf_sf_sde_regs *sde_regs;
+ struct perf_sample_data data;
+ struct perf_raw_record raw;
+
+ /* Setup perf sample */
+ perf_sample_data_init(&data, 0, event->hw.last_period);
+ raw.size = sfr->size;
+ raw.data = sfr;
+ data.raw = &raw;
+
+ /* Setup pt_regs to look like an CPU-measurement external interrupt
+ * using the Program Request Alert code. The regs.int_parm_long
+ * field which is unused contains additional sample-data-entry related
+ * indicators.
+ */
+ memset(&regs, 0, sizeof(regs));
+ regs.int_code = 0x1407;
+ regs.int_parm = CPU_MF_INT_SF_PRA;
+ sde_regs = (struct perf_sf_sde_regs *) &regs.int_parm_long;
+
+ regs.psw.addr = sfr->basic.ia;
+ if (sfr->basic.T)
+ regs.psw.mask |= PSW_MASK_DAT;
+ if (sfr->basic.W)
+ regs.psw.mask |= PSW_MASK_WAIT;
+ if (sfr->basic.P)
+ regs.psw.mask |= PSW_MASK_PSTATE;
+ switch (sfr->basic.AS) {
+ case 0x0:
+ regs.psw.mask |= PSW_ASC_PRIMARY;
+ break;
+ case 0x1:
+ regs.psw.mask |= PSW_ASC_ACCREG;
+ break;
+ case 0x2:
+ regs.psw.mask |= PSW_ASC_SECONDARY;
+ break;
+ case 0x3:
+ regs.psw.mask |= PSW_ASC_HOME;
+ break;
+ }
+
+ /* The host-program-parameter (hpp) contains the sie control
+ * block that is set by sie64a() in entry64.S. Check if hpp
+ * refers to a valid control block and set sde_regs flags
+ * accordingly. This would allow to use hpp values for other
+ * purposes too.
+ * For now, simply use a non-zero value as guest indicator.
+ */
+ if (sfr->basic.hpp)
+ sde_regs->in_guest = 1;
+
+ overflow = 0;
+ if (perf_exclude_event(event, &regs, sde_regs))
+ goto out;
+ if (perf_event_overflow(event, &data, &regs)) {
+ overflow = 1;
+ event->pmu->stop(event, 0);
+ }
+ perf_event_update_userpage(event);
+out:
+ return overflow;
+}
+
+static void perf_event_count_update(struct perf_event *event, u64 count)
+{
+ local64_add(count, &event->count);
+}
+
+static int sample_format_is_valid(struct hws_combined_entry *sample,
+ unsigned int flags)
+{
+ if (likely(flags & PERF_CPUM_SF_BASIC_MODE))
+ /* Only basic-sampling data entries with data-entry-format
+ * version of 0x0001 can be processed.
+ */
+ if (sample->basic.def != 0x0001)
+ return 0;
+ if (flags & PERF_CPUM_SF_DIAG_MODE)
+ /* The data-entry-format number of diagnostic-sampling data
+ * entries can vary. Because diagnostic data is just passed
+ * through, do only a sanity check on the DEF.
+ */
+ if (sample->diag.def < 0x8001)
+ return 0;
+ return 1;
+}
+
+static int sample_is_consistent(struct hws_combined_entry *sample,
+ unsigned long flags)
+{
+ /* This check applies only to basic-sampling data entries of potentially
+ * combined-sampling data entries. Invalid entries cannot be processed
+ * by the PMU and, thus, do not deliver an associated
+ * diagnostic-sampling data entry.
+ */
+ if (unlikely(!(flags & PERF_CPUM_SF_BASIC_MODE)))
+ return 0;
+ /*
+ * Samples are skipped, if they are invalid or for which the
+ * instruction address is not predictable, i.e., the wait-state bit is
+ * set.
+ */
+ if (sample->basic.I || sample->basic.W)
+ return 0;
+ return 1;
+}
+
+static void reset_sample_slot(struct hws_combined_entry *sample,
+ unsigned long flags)
+{
+ if (likely(flags & PERF_CPUM_SF_BASIC_MODE))
+ sample->basic.def = 0;
+ if (flags & PERF_CPUM_SF_DIAG_MODE)
+ sample->diag.def = 0;
+}
+
+static void sfr_store_sample(struct sf_raw_sample *sfr,
+ struct hws_combined_entry *sample)
+{
+ if (likely(sfr->format & PERF_CPUM_SF_BASIC_MODE))
+ sfr->basic = sample->basic;
+ if (sfr->format & PERF_CPUM_SF_DIAG_MODE)
+ memcpy(&sfr->diag, &sample->diag, sfr->dsdes);
+}
+
+static void debug_sample_entry(struct hws_combined_entry *sample,
+ struct hws_trailer_entry *te,
+ unsigned long flags)
+{
+ debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
+ "sampling data entry: te->f=%i basic.def=%04x (%p)"
+ " diag.def=%04x (%p)\n", te->f,
+ sample->basic.def, &sample->basic,
+ (flags & PERF_CPUM_SF_DIAG_MODE)
+ ? sample->diag.def : 0xFFFF,
+ (flags & PERF_CPUM_SF_DIAG_MODE)
+ ? &sample->diag : NULL);
+}
+
+/* hw_collect_samples() - Walk through a sample-data-block and collect samples
+ * @event: The perf event
+ * @sdbt: Sample-data-block table
+ * @overflow: Event overflow counter
+ *
+ * Walks through a sample-data-block and collects sampling data entries that are
+ * then pushed to the perf event subsystem. Depending on the sampling function,
+ * there can be either basic-sampling or combined-sampling data entries. A
+ * combined-sampling data entry consists of a basic- and a diagnostic-sampling
+ * data entry. The sampling function is determined by the flags in the perf
+ * event hardware structure. The function always works with a combined-sampling
+ * data entry but ignores the the diagnostic portion if it is not available.
+ *
+ * Note that the implementation focuses on basic-sampling data entries and, if
+ * such an entry is not valid, the entire combined-sampling data entry is
+ * ignored.
+ *
+ * The overflow variables counts the number of samples that has been discarded
+ * due to a perf event overflow.
+ */
+static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
+ unsigned long long *overflow)
+{
+ unsigned long flags = SAMPL_FLAGS(&event->hw);
+ struct hws_combined_entry *sample;
+ struct hws_trailer_entry *te;
+ struct sf_raw_sample *sfr;
+ size_t sample_size;
+
+ /* Prepare and initialize raw sample data */
+ sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(&event->hw);
+ sfr->format = flags & PERF_CPUM_SF_MODE_MASK;
+
+ sample_size = event_sample_size(&event->hw);
+ te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
+ sample = (struct hws_combined_entry *) *sdbt;
+ while ((unsigned long *) sample < (unsigned long *) te) {
+ /* Check for an empty sample */
+ if (!sample->basic.def)
+ break;
+
+ /* Update perf event period */
+ perf_event_count_update(event, SAMPL_RATE(&event->hw));
+
+ /* Check sampling data entry */
+ if (sample_format_is_valid(sample, flags)) {
+ /* If an event overflow occurred, the PMU is stopped to
+ * throttle event delivery. Remaining sample data is
+ * discarded.
+ */
+ if (!*overflow) {
+ if (sample_is_consistent(sample, flags)) {
+ /* Deliver sample data to perf */
+ sfr_store_sample(sfr, sample);
+ *overflow = perf_push_sample(event, sfr);
+ }
+ } else
+ /* Count discarded samples */
+ *overflow += 1;
+ } else {
+ debug_sample_entry(sample, te, flags);
+ /* Sample slot is not yet written or other record.
+ *
+ * This condition can occur if the buffer was reused
+ * from a combined basic- and diagnostic-sampling.
+ * If only basic-sampling is then active, entries are
+ * written into the larger diagnostic entries.
+ * This is typically the case for sample-data-blocks
+ * that are not full. Stop processing if the first
+ * invalid format was detected.
+ */
+ if (!te->f)
+ break;
+ }
+
+ /* Reset sample slot and advance to next sample */
+ reset_sample_slot(sample, flags);
+ sample += sample_size;
+ }
+}
+
+/* hw_perf_event_update() - Process sampling buffer
+ * @event: The perf event
+ * @flush_all: Flag to also flush partially filled sample-data-blocks
+ *
+ * Processes the sampling buffer and create perf event samples.
+ * The sampling buffer position are retrieved and saved in the TEAR_REG
+ * register of the specified perf event.
+ *
+ * Only full sample-data-blocks are processed. Specify the flash_all flag
+ * to also walk through partially filled sample-data-blocks. It is ignored
+ * if PERF_CPUM_SF_FULL_BLOCKS is set. The PERF_CPUM_SF_FULL_BLOCKS flag
+ * enforces the processing of full sample-data-blocks only (trailer entries
+ * with the block-full-indicator bit set).
+ */
+static void hw_perf_event_update(struct perf_event *event, int flush_all)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hws_trailer_entry *te;
+ unsigned long *sdbt;
+ unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
+ int done;
+
+ if (flush_all && SDB_FULL_BLOCKS(hwc))
+ flush_all = 0;
+
+ sdbt = (unsigned long *) TEAR_REG(hwc);
+ done = event_overflow = sampl_overflow = num_sdb = 0;
+ while (!done) {
+ /* Get the trailer entry of the sample-data-block */
+ te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
+
+ /* Leave loop if no more work to do (block full indicator) */
+ if (!te->f) {
+ done = 1;
+ if (!flush_all)
+ break;
+ }
+
+ /* Check the sample overflow count */
+ if (te->overflow)
+ /* Account sample overflows and, if a particular limit
+ * is reached, extend the sampling buffer.
+ * For details, see sfb_account_overflows().
+ */
+ sampl_overflow += te->overflow;
+
+ /* Timestamps are valid for full sample-data-blocks only */
+ debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
+ "overflow=%llu timestamp=0x%llx\n",
+ sdbt, te->overflow,
+ (te->f) ? trailer_timestamp(te) : 0ULL);
+
+ /* Collect all samples from a single sample-data-block and
+ * flag if an (perf) event overflow happened. If so, the PMU
+ * is stopped and remaining samples will be discarded.
+ */
+ hw_collect_samples(event, sdbt, &event_overflow);
+ num_sdb++;
+
+ /* Reset trailer (using compare-double-and-swap) */
+ do {
+ te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
+ te_flags |= SDB_TE_ALERT_REQ_MASK;
+ } while (!cmpxchg_double(&te->flags, &te->overflow,
+ te->flags, te->overflow,
+ te_flags, 0ULL));
+
+ /* Advance to next sample-data-block */
+ sdbt++;
+ if (is_link_entry(sdbt))
+ sdbt = get_next_sdbt(sdbt);
+
+ /* Update event hardware registers */
+ TEAR_REG(hwc) = (unsigned long) sdbt;
+
+ /* Stop processing sample-data if all samples of the current
+ * sample-data-block were flushed even if it was not full.
+ */
+ if (flush_all && done)
+ break;
+
+ /* If an event overflow happened, discard samples by
+ * processing any remaining sample-data-blocks.
+ */
+ if (event_overflow)
+ flush_all = 1;
+ }
+
+ /* Account sample overflows in the event hardware structure */
+ if (sampl_overflow)
+ OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
+ sampl_overflow, 1 + num_sdb);
+ if (sampl_overflow || event_overflow)
+ debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
+ "overflow stats: sample=%llu event=%llu\n",
+ sampl_overflow, event_overflow);
+}
+
+static void cpumsf_pmu_read(struct perf_event *event)
+{
+ /* Nothing to do ... updates are interrupt-driven */
+}
+
+/* Activate sampling control.
+ * Next call of pmu_enable() starts sampling.
+ */
+static void cpumsf_pmu_start(struct perf_event *event, int flags)
+{
+ struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ if (flags & PERF_EF_RELOAD)
+ WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+ perf_pmu_disable(event->pmu);
+ event->hw.state = 0;
+ cpuhw->lsctl.cs = 1;
+ if (SAMPL_DIAG_MODE(&event->hw))
+ cpuhw->lsctl.cd = 1;
+ perf_pmu_enable(event->pmu);
+}
+
+/* Deactivate sampling control.
+ * Next call of pmu_enable() stops sampling.
+ */
+static void cpumsf_pmu_stop(struct perf_event *event, int flags)
+{
+ struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+ if (event->hw.state & PERF_HES_STOPPED)
+ return;
+
+ perf_pmu_disable(event->pmu);
+ cpuhw->lsctl.cs = 0;
+ cpuhw->lsctl.cd = 0;
+ event->hw.state |= PERF_HES_STOPPED;
+
+ if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+ hw_perf_event_update(event, 1);
+ event->hw.state |= PERF_HES_UPTODATE;
+ }
+ perf_pmu_enable(event->pmu);
+}
+
+static int cpumsf_pmu_add(struct perf_event *event, int flags)
+{
+ struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+ int err;
+
+ if (cpuhw->flags & PMU_F_IN_USE)
+ return -EAGAIN;
+
+ if (!cpuhw->sfb.sdbt)
+ return -EINVAL;
+
+ err = 0;
+ perf_pmu_disable(event->pmu);
+
+ event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+ /* Set up sampling controls. Always program the sampling register
+ * using the SDB-table start. Reset TEAR_REG event hardware register
+ * that is used by hw_perf_event_update() to store the sampling buffer
+ * position after samples have been flushed.
+ */
+ cpuhw->lsctl.s = 0;
+ cpuhw->lsctl.h = 1;
+ cpuhw->lsctl.tear = (unsigned long) cpuhw->sfb.sdbt;
+ cpuhw->lsctl.dear = *(unsigned long *) cpuhw->sfb.sdbt;
+ cpuhw->lsctl.interval = SAMPL_RATE(&event->hw);
+ hw_reset_registers(&event->hw, cpuhw->sfb.sdbt);
+
+ /* Ensure sampling functions are in the disabled state. If disabled,
+ * switch on sampling enable control. */
+ if (WARN_ON_ONCE(cpuhw->lsctl.es == 1 || cpuhw->lsctl.ed == 1)) {
+ err = -EAGAIN;
+ goto out;
+ }
+ cpuhw->lsctl.es = 1;
+ if (SAMPL_DIAG_MODE(&event->hw))
+ cpuhw->lsctl.ed = 1;
+
+ /* Set in_use flag and store event */
+ event->hw.idx = 0; /* only one sampling event per CPU supported */
+ cpuhw->event = event;
+ cpuhw->flags |= PMU_F_IN_USE;
+
+ if (flags & PERF_EF_START)
+ cpumsf_pmu_start(event, PERF_EF_RELOAD);
+out:
+ perf_event_update_userpage(event);
+ perf_pmu_enable(event->pmu);
+ return err;
+}
+
+static void cpumsf_pmu_del(struct perf_event *event, int flags)
+{
+ struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+ perf_pmu_disable(event->pmu);
+ cpumsf_pmu_stop(event, PERF_EF_UPDATE);
+
+ cpuhw->lsctl.es = 0;
+ cpuhw->lsctl.ed = 0;
+ cpuhw->flags &= ~PMU_F_IN_USE;
+ cpuhw->event = NULL;
+
+ perf_event_update_userpage(event);
+ perf_pmu_enable(event->pmu);
+}
+
+static int cpumsf_pmu_event_idx(struct perf_event *event)
+{
+ return event->hw.idx;
+}
+
+CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
+CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
+
+static struct attribute *cpumsf_pmu_events_attr[] = {
+ CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
+ CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG),
+ NULL,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cpumsf_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group cpumsf_pmu_events_group = {
+ .name = "events",
+ .attrs = cpumsf_pmu_events_attr,
+};
+static struct attribute_group cpumsf_pmu_format_group = {
+ .name = "format",
+ .attrs = cpumsf_pmu_format_attr,
+};
+static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
+ &cpumsf_pmu_events_group,
+ &cpumsf_pmu_format_group,
+ NULL,
+};
+
+static struct pmu cpumf_sampling = {
+ .pmu_enable = cpumsf_pmu_enable,
+ .pmu_disable = cpumsf_pmu_disable,
+
+ .event_init = cpumsf_pmu_event_init,
+ .add = cpumsf_pmu_add,
+ .del = cpumsf_pmu_del,
+
+ .start = cpumsf_pmu_start,
+ .stop = cpumsf_pmu_stop,
+ .read = cpumsf_pmu_read,
+
+ .event_idx = cpumsf_pmu_event_idx,
+ .attr_groups = cpumsf_pmu_attr_groups,
+};
+
+static void cpumf_measurement_alert(struct ext_code ext_code,
+ unsigned int alert, unsigned long unused)
+{
+ struct cpu_hw_sf *cpuhw;
+
+ if (!(alert & CPU_MF_INT_SF_MASK))
+ return;
+ inc_irq_stat(IRQEXT_CMS);
+ cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+ /* Measurement alerts are shared and might happen when the PMU
+ * is not reserved. Ignore these alerts in this case. */
+ if (!(cpuhw->flags & PMU_F_RESERVED))
+ return;
+
+ /* The processing below must take care of multiple alert events that
+ * might be indicated concurrently. */
+
+ /* Program alert request */
+ if (alert & CPU_MF_INT_SF_PRA) {
+ if (cpuhw->flags & PMU_F_IN_USE)
+ hw_perf_event_update(cpuhw->event, 0);
+ else
+ WARN_ON_ONCE(!(cpuhw->flags & PMU_F_IN_USE));
+ }
+
+ /* Report measurement alerts only for non-PRA codes */
+ if (alert != CPU_MF_INT_SF_PRA)
+ debug_sprintf_event(sfdbg, 6, "measurement alert: 0x%x\n", alert);
+
+ /* Sampling authorization change request */
+ if (alert & CPU_MF_INT_SF_SACA)
+ qsi(&cpuhw->qsi);
+
+ /* Loss of sample data due to high-priority machine activities */
+ if (alert & CPU_MF_INT_SF_LSDA) {
+ pr_err("Sample data was lost\n");
+ cpuhw->flags |= PMU_F_ERR_LSDA;
+ sf_disable();
+ }
+
+ /* Invalid sampling buffer entry */
+ if (alert & (CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE)) {
+ pr_err("A sampling buffer entry is incorrect (alert=0x%x)\n",
+ alert);
+ cpuhw->flags |= PMU_F_ERR_IBE;
+ sf_disable();
+ }
+}
+
+static int cpumf_pmu_notifier(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (long) hcpu;
+ int flags;
+
+ /* Ignore the notification if no events are scheduled on the PMU.
+ * This might be racy...
+ */
+ if (!atomic_read(&num_events))
+ return NOTIFY_OK;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ flags = PMC_INIT;
+ smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+ break;
+ case CPU_DOWN_PREPARE:
+ flags = PMC_RELEASE;
+ smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static int param_get_sfb_size(char *buffer, const struct kernel_param *kp)
+{
+ if (!cpum_sf_avail())
+ return -ENODEV;
+ return sprintf(buffer, "%lu,%lu", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+}
+
+static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
+{
+ int rc;
+ unsigned long min, max;
+
+ if (!cpum_sf_avail())
+ return -ENODEV;
+ if (!val || !strlen(val))
+ return -EINVAL;
+
+ /* Valid parameter values: "min,max" or "max" */
+ min = CPUM_SF_MIN_SDB;
+ max = CPUM_SF_MAX_SDB;
+ if (strchr(val, ','))
+ rc = (sscanf(val, "%lu,%lu", &min, &max) == 2) ? 0 : -EINVAL;
+ else
+ rc = kstrtoul(val, 10, &max);
+
+ if (min < 2 || min >= max || max > get_num_physpages())
+ rc = -EINVAL;
+ if (rc)
+ return rc;
+
+ sfb_set_limits(min, max);
+ pr_info("The sampling buffer limits have changed to: "
+ "min=%lu max=%lu (diag=x%lu)\n",
+ CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR);
+ return 0;
+}
+
+#define param_check_sfb_size(name, p) __param_check(name, p, void)
+static struct kernel_param_ops param_ops_sfb_size = {
+ .set = param_set_sfb_size,
+ .get = param_get_sfb_size,
+};
+
+#define RS_INIT_FAILURE_QSI 0x0001
+#define RS_INIT_FAILURE_BSDES 0x0002
+#define RS_INIT_FAILURE_ALRT 0x0003
+#define RS_INIT_FAILURE_PERF 0x0004
+static void __init pr_cpumsf_err(unsigned int reason)
+{
+ pr_err("Sampling facility support for perf is not available: "
+ "reason=%04x\n", reason);
+}
+
+static int __init init_cpum_sampling_pmu(void)
+{
+ struct hws_qsi_info_block si;
+ int err;
+
+ if (!cpum_sf_avail())
+ return -ENODEV;
+
+ memset(&si, 0, sizeof(si));
+ if (qsi(&si)) {
+ pr_cpumsf_err(RS_INIT_FAILURE_QSI);
+ return -ENODEV;
+ }
+
+ if (si.bsdes != sizeof(struct hws_basic_entry)) {
+ pr_cpumsf_err(RS_INIT_FAILURE_BSDES);
+ return -EINVAL;
+ }
+
+ if (si.ad)
+ sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+
+ sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
+ if (!sfdbg)
+ pr_err("Registering for s390dbf failed\n");
+ debug_register_view(sfdbg, &debug_sprintf_view);
+
+ err = register_external_irq(EXT_IRQ_MEASURE_ALERT,
+ cpumf_measurement_alert);
+ if (err) {
+ pr_cpumsf_err(RS_INIT_FAILURE_ALRT);
+ goto out;
+ }
+
+ err = perf_pmu_register(&cpumf_sampling, "cpum_sf", PERF_TYPE_RAW);
+ if (err) {
+ pr_cpumsf_err(RS_INIT_FAILURE_PERF);
+ unregister_external_irq(EXT_IRQ_MEASURE_ALERT,
+ cpumf_measurement_alert);
+ goto out;
+ }
+ perf_cpu_notifier(cpumf_pmu_notifier);
+out:
+ return err;
+}
+arch_initcall(init_cpum_sampling_pmu);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 2343c218b8f..61595c1f0a0 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -1,7 +1,7 @@
/*
* Performance event support for s390x
*
- * Copyright IBM Corp. 2012
+ * Copyright IBM Corp. 2012, 2013
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
*
* This program is free software; you can redistribute it and/or modify
@@ -16,15 +16,19 @@
#include <linux/kvm_host.h>
#include <linux/percpu.h>
#include <linux/export.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
#include <asm/irq.h>
#include <asm/cpu_mf.h>
#include <asm/lowcore.h>
#include <asm/processor.h>
+#include <asm/sysinfo.h>
const char *perf_pmu_name(void)
{
if (cpum_cf_avail() || cpum_sf_avail())
- return "CPU-measurement facilities (CPUMF)";
+ return "CPU-Measurement Facilities (CPU-MF)";
return "pmu";
}
EXPORT_SYMBOL(perf_pmu_name);
@@ -35,6 +39,8 @@ int perf_num_counters(void)
if (cpum_cf_avail())
num += PERF_CPUM_CF_MAX_CTR;
+ if (cpum_sf_avail())
+ num += PERF_CPUM_SF_MAX_CTR;
return num;
}
@@ -54,7 +60,7 @@ static bool is_in_guest(struct pt_regs *regs)
{
if (user_mode(regs))
return false;
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
return instruction_pointer(regs) == (unsigned long) &sie_exit;
#else
return false;
@@ -83,8 +89,31 @@ static unsigned long perf_misc_guest_flags(struct pt_regs *regs)
: PERF_RECORD_MISC_GUEST_KERNEL;
}
+static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
+{
+ struct perf_sf_sde_regs *sde_regs;
+ unsigned long flags;
+
+ sde_regs = (struct perf_sf_sde_regs *) &regs->int_parm_long;
+ if (sde_regs->in_guest)
+ flags = user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
+ : PERF_RECORD_MISC_GUEST_KERNEL;
+ else
+ flags = user_mode(regs) ? PERF_RECORD_MISC_USER
+ : PERF_RECORD_MISC_KERNEL;
+ return flags;
+}
+
unsigned long perf_misc_flags(struct pt_regs *regs)
{
+ /* Check if the cpum_sf PMU has created the pt_regs structure.
+ * In this case, perf misc flags can be easily extracted. Otherwise,
+ * do regular checks on the pt_regs content.
+ */
+ if (regs->int_code == 0x1407 && regs->int_parm == CPU_MF_INT_SF_PRA)
+ if (!regs->gprs[15])
+ return perf_misc_flags_sf(regs);
+
if (is_in_guest(regs))
return perf_misc_guest_flags(regs);
@@ -92,27 +121,107 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
: PERF_RECORD_MISC_KERNEL;
}
-void perf_event_print_debug(void)
+static void print_debug_cf(void)
{
struct cpumf_ctr_info cf_info;
- unsigned long flags;
- int cpu;
-
- if (!cpum_cf_avail())
- return;
-
- local_irq_save(flags);
+ int cpu = smp_processor_id();
- cpu = smp_processor_id();
memset(&cf_info, 0, sizeof(cf_info));
if (!qctri(&cf_info))
pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
cpu, cf_info.cfvn, cf_info.csvn,
cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
+}
+
+static void print_debug_sf(void)
+{
+ struct hws_qsi_info_block si;
+ int cpu = smp_processor_id();
+ memset(&si, 0, sizeof(si));
+ if (qsi(&si))
+ return;
+
+ pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%lu max=%lu cpu_speed=%u\n",
+ cpu, si.as, si.ad, si.min_sampl_rate, si.max_sampl_rate,
+ si.cpu_speed);
+
+ if (si.as)
+ pr_info("CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i"
+ " bsdes=%i tear=%016lx dear=%016lx\n", cpu,
+ si.as, si.es, si.cs, si.bsdes, si.tear, si.dear);
+ if (si.ad)
+ pr_info("CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i"
+ " dsdes=%i tear=%016lx dear=%016lx\n", cpu,
+ si.ad, si.ed, si.cd, si.dsdes, si.tear, si.dear);
+}
+
+void perf_event_print_debug(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ if (cpum_cf_avail())
+ print_debug_cf();
+ if (cpum_sf_avail())
+ print_debug_sf();
local_irq_restore(flags);
}
+/* Service level infrastructure */
+static void sl_print_counter(struct seq_file *m)
+{
+ struct cpumf_ctr_info ci;
+
+ memset(&ci, 0, sizeof(ci));
+ if (qctri(&ci))
+ return;
+
+ seq_printf(m, "CPU-MF: Counter facility: version=%u.%u "
+ "authorization=%04x\n", ci.cfvn, ci.csvn, ci.auth_ctl);
+}
+
+static void sl_print_sampling(struct seq_file *m)
+{
+ struct hws_qsi_info_block si;
+
+ memset(&si, 0, sizeof(si));
+ if (qsi(&si))
+ return;
+
+ if (!si.as && !si.ad)
+ return;
+
+ seq_printf(m, "CPU-MF: Sampling facility: min_rate=%lu max_rate=%lu"
+ " cpu_speed=%u\n", si.min_sampl_rate, si.max_sampl_rate,
+ si.cpu_speed);
+ if (si.as)
+ seq_printf(m, "CPU-MF: Sampling facility: mode=basic"
+ " sample_size=%u\n", si.bsdes);
+ if (si.ad)
+ seq_printf(m, "CPU-MF: Sampling facility: mode=diagnostic"
+ " sample_size=%u\n", si.dsdes);
+}
+
+static void service_level_perf_print(struct seq_file *m,
+ struct service_level *sl)
+{
+ if (cpum_cf_avail())
+ sl_print_counter(m);
+ if (cpum_sf_avail())
+ sl_print_sampling(m);
+}
+
+static struct service_level service_level_perf = {
+ .seq_print = service_level_perf_print,
+};
+
+static int __init service_level_perf_register(void)
+{
+ return register_service_level(&service_level_perf);
+}
+arch_initcall(service_level_perf_register);
+
/* See also arch/s390/kernel/traps.c */
static unsigned long __store_trace(struct perf_callchain_entry *entry,
unsigned long sp,
@@ -172,3 +281,44 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
__store_trace(entry, head, S390_lowcore.thread_info,
S390_lowcore.thread_info + THREAD_SIZE);
}
+
+/* Perf defintions for PMU event attributes in sysfs */
+ssize_t cpumf_events_sysfs_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+ return sprintf(page, "event=0x%04llx,name=%s\n",
+ pmu_attr->id, attr->attr.name);
+}
+
+/* Reserve/release functions for sharing perf hardware */
+static DEFINE_SPINLOCK(perf_hw_owner_lock);
+static void *perf_sampling_owner;
+
+int perf_reserve_sampling(void)
+{
+ int err;
+
+ err = 0;
+ spin_lock(&perf_hw_owner_lock);
+ if (perf_sampling_owner) {
+ pr_warn("The sampling facility is already reserved by %p\n",
+ perf_sampling_owner);
+ err = -EBUSY;
+ } else
+ perf_sampling_owner = __builtin_return_address(0);
+ spin_unlock(&perf_hw_owner_lock);
+ return err;
+}
+EXPORT_SYMBOL(perf_reserve_sampling);
+
+void perf_release_sampling(void)
+{
+ spin_lock(&perf_hw_owner_lock);
+ WARN_ON(!perf_sampling_owner);
+ perf_sampling_owner = NULL;
+ spin_unlock(&perf_hw_owner_lock);
+}
+EXPORT_SYMBOL(perf_release_sampling);
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 7ed0d4e2a43..dd145321d21 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -261,20 +261,18 @@ static inline unsigned long brk_rnd(void)
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
- unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd());
+ unsigned long ret;
- if (ret < mm->brk)
- return mm->brk;
- return ret;
+ ret = PAGE_ALIGN(mm->brk + brk_rnd());
+ return (ret > mm->brk) ? ret : mm->brk;
}
unsigned long randomize_et_dyn(unsigned long base)
{
- unsigned long ret = PAGE_ALIGN(base + brk_rnd());
+ unsigned long ret;
if (!(current->flags & PF_RANDOMIZE))
return base;
- if (ret < base)
- return base;
- return ret;
+ ret = PAGE_ALIGN(base + brk_rnd());
+ return (ret > base) ? ret : base;
}
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index e65c91c591e..4ac8fafec95 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -56,25 +56,26 @@ void update_cr_regs(struct task_struct *task)
#ifdef CONFIG_64BIT
/* Take care of the enable/disable of transactional execution. */
if (MACHINE_HAS_TE) {
- unsigned long cr[3], cr_new[3];
+ unsigned long cr, cr_new;
- __ctl_store(cr, 0, 2);
- cr_new[1] = cr[1];
+ __ctl_store(cr, 0, 0);
/* Set or clear transaction execution TXC bit 8. */
+ cr_new = cr | (1UL << 55);
if (task->thread.per_flags & PER_FLAG_NO_TE)
- cr_new[0] = cr[0] & ~(1UL << 55);
- else
- cr_new[0] = cr[0] | (1UL << 55);
+ cr_new &= ~(1UL << 55);
+ if (cr_new != cr)
+ __ctl_load(cr, 0, 0);
/* Set or clear transaction execution TDC bits 62 and 63. */
- cr_new[2] = cr[2] & ~3UL;
+ __ctl_store(cr, 2, 2);
+ cr_new = cr & ~3UL;
if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
- cr_new[2] |= 1UL;
+ cr_new |= 1UL;
else
- cr_new[2] |= 2UL;
+ cr_new |= 2UL;
}
- if (memcmp(&cr_new, &cr, sizeof(cr)))
- __ctl_load(cr_new, 0, 2);
+ if (cr_new != cr)
+ __ctl_load(cr_new, 2, 2);
}
#endif
/* Copy user specified PER registers */
@@ -84,7 +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;
@@ -106,16 +110,20 @@ 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);
- if (task == current)
- update_cr_regs(task);
}
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);
- if (task == current)
- update_cr_regs(task);
+}
+
+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);
}
/*
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index d817cce7e72..26b4ae96fdd 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -138,7 +138,8 @@ static int __init runtime_instr_init(void)
return 0;
irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
- rc = register_external_interrupt(0x1407, runtime_instr_int_handler);
+ rc = register_external_irq(EXT_IRQ_MEASURE_ALERT,
+ runtime_instr_int_handler);
if (rc)
irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
else
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 3bac589844a..9f60467938d 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -5,7 +5,7 @@
#ifdef CONFIG_FUNCTION_TRACER
EXPORT_SYMBOL(_mcount);
#endif
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
EXPORT_SYMBOL(sie64a);
EXPORT_SYMBOL(sie_exit);
#endif
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index 29bd7bec417..a41f2c99dcc 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
+#include <asm/irq.h>
LC_EXT_NEW_PSW = 0x58 # addr of ext int handler
LC_EXT_NEW_PSW_64 = 0x1b0 # addr of ext int handler 64 bit
@@ -73,9 +74,9 @@ _sclp_wait_int:
lpsw .LwaitpswS1-.LbaseS1(%r13) # wait until interrupt
.LwaitS1:
lh %r7,LC_EXT_INT_CODE
- chi %r7,0x1004 # timeout?
+ chi %r7,EXT_IRQ_CLK_COMP # timeout?
je .LtimeoutS1
- chi %r7,0x2401 # service int?
+ chi %r7,EXT_IRQ_SERVICE_SIG # service int?
jne .LloopS1
sr %r2,%r2
l %r3,LC_EXT_INT_PARAM
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 0f3d44ecbfc..f70f2489fa5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -47,7 +47,6 @@
#include <linux/compat.h>
#include <asm/ipl.h>
-#include <asm/uaccess.h>
#include <asm/facility.h>
#include <asm/smp.h>
#include <asm/mmu_context.h>
@@ -65,12 +64,6 @@
#include "entry.h"
/*
- * User copy operations.
- */
-struct uaccess_ops uaccess;
-EXPORT_SYMBOL(uaccess);
-
-/*
* Machine setup..
*/
unsigned int console_mode = 0;
@@ -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)
@@ -373,7 +358,7 @@ static void __init setup_lowcore(void)
/*
* Set up PSW restart to call ipl.c:do_restart(). Copy the relevant
- * restart data to the absolute zero lowcore. This is necesary if
+ * restart data to the absolute zero lowcore. This is necessary if
* PSW restart is done on an offline CPU that has lowcore zero.
*/
lc->restart_stack = (unsigned long) restart_stack;
@@ -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 958704798f4..512ce1cde2a 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -59,7 +59,7 @@ enum {
};
struct pcpu {
- struct cpu cpu;
+ struct cpu *cpu;
struct _lowcore *lowcore; /* lowcore page(s) for the cpu */
unsigned long async_stack; /* async stack for the cpu */
unsigned long panic_stack; /* panic stack for the cpu */
@@ -159,9 +159,9 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
{
int order;
- set_bit(ec_bit, &pcpu->ec_mask);
- order = pcpu_running(pcpu) ?
- SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
+ if (test_and_set_bit(ec_bit, &pcpu->ec_mask))
+ return;
+ order = pcpu_running(pcpu) ? SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
pcpu_sigp_retry(pcpu, order, 0);
}
@@ -236,6 +236,9 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
{
struct _lowcore *lc = pcpu->lowcore;
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
+ cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
atomic_inc(&init_mm.context.attach_count);
lc->cpu_nr = cpu;
lc->percpu_offset = __per_cpu_offset[cpu];
@@ -760,6 +763,9 @@ void __cpu_die(unsigned int cpu)
cpu_relax();
pcpu_free_lowcore(pcpu);
atomic_dec(&init_mm.context.attach_count);
+ cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
}
void __noreturn cpu_die(void)
@@ -773,11 +779,11 @@ 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);
}
@@ -785,10 +791,10 @@ void __init smp_fill_possible_mask(void)
void __init smp_prepare_cpus(unsigned int max_cpus)
{
/* request the 0x1201 emergency signal external interrupt */
- if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0)
+ if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt))
panic("Couldn't request external interrupt 0x1201");
/* request the 0x1202 external call external interrupt */
- if (register_external_interrupt(0x1202, do_ext_call_interrupt) != 0)
+ if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt))
panic("Couldn't request external interrupt 0x1202");
smp_detect_cpus();
}
@@ -965,7 +971,7 @@ static int smp_cpu_notify(struct notifier_block *self, unsigned long action,
void *hcpu)
{
unsigned int cpu = (unsigned int)(long)hcpu;
- struct cpu *c = &pcpu_devices[cpu].cpu;
+ struct cpu *c = pcpu_devices[cpu].cpu;
struct device *s = &c->dev;
int err = 0;
@@ -982,10 +988,15 @@ static int smp_cpu_notify(struct notifier_block *self, unsigned long action,
static int smp_add_present_cpu(int cpu)
{
- struct cpu *c = &pcpu_devices[cpu].cpu;
- struct device *s = &c->dev;
+ struct device *s;
+ struct cpu *c;
int rc;
+ c = kzalloc(sizeof(*c), GFP_KERNEL);
+ if (!c)
+ return -ENOMEM;
+ pcpu_devices[cpu].cpu = c;
+ s = &c->dev;
c->hotpluggable = 1;
rc = register_cpu(c, cpu);
if (rc)
@@ -1052,19 +1063,24 @@ static DEVICE_ATTR(rescan, 0200, NULL, rescan_store);
static int __init s390_smp_init(void)
{
- int cpu, rc;
+ int cpu, rc = 0;
- hotcpu_notifier(smp_cpu_notify, 0);
#ifdef CONFIG_HOTPLUG_CPU
rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan);
if (rc)
return rc;
#endif
+ cpu_notifier_register_begin();
for_each_present_cpu(cpu) {
rc = smp_add_present_cpu(cpu);
if (rc)
- return rc;
+ goto out;
}
- return 0;
+
+ __hotcpu_notifier(smp_cpu_notify, 0);
+
+out:
+ cpu_notifier_register_done();
+ return rc;
}
subsys_initcall(s390_smp_init);
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 913410bd74a..542ef488bac 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -9,347 +9,349 @@
#define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall,sys_ni_syscall)
NI_SYSCALL /* 0 */
-SYSCALL(sys_exit,sys_exit,sys32_exit_wrapper)
+SYSCALL(sys_exit,sys_exit,compat_sys_exit)
SYSCALL(sys_fork,sys_fork,sys_fork)
-SYSCALL(sys_read,sys_read,sys32_read_wrapper)
-SYSCALL(sys_write,sys_write,sys32_write_wrapper)
+SYSCALL(sys_read,sys_read,compat_sys_s390_read)
+SYSCALL(sys_write,sys_write,compat_sys_s390_write)
SYSCALL(sys_open,sys_open,compat_sys_open) /* 5 */
-SYSCALL(sys_close,sys_close,sys32_close_wrapper)
+SYSCALL(sys_close,sys_close,compat_sys_close)
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_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)
-SYSCALL(sys_chmod,sys_chmod,sys32_chmod_wrapper) /* 15 */
-SYSCALL(sys_lchown16,sys_ni_syscall,sys32_lchown16_wrapper) /* old lchown16 syscall*/
+SYSCALL(sys_creat,sys_creat,compat_sys_creat)
+SYSCALL(sys_link,sys_link,compat_sys_link)
+SYSCALL(sys_unlink,sys_unlink,compat_sys_unlink) /* 10 */
+SYSCALL(sys_execve,sys_execve,compat_sys_execve)
+SYSCALL(sys_chdir,sys_chdir,compat_sys_chdir)
+SYSCALL(sys_time,sys_ni_syscall,compat_sys_time) /* old time syscall */
+SYSCALL(sys_mknod,sys_mknod,compat_sys_mknod)
+SYSCALL(sys_chmod,sys_chmod,compat_sys_chmod) /* 15 */
+SYSCALL(sys_lchown16,sys_ni_syscall,compat_sys_s390_lchown16) /* old lchown16 syscall*/
NI_SYSCALL /* old break syscall holder */
NI_SYSCALL /* old stat syscall holder */
SYSCALL(sys_lseek,sys_lseek,compat_sys_lseek)
SYSCALL(sys_getpid,sys_getpid,sys_getpid) /* 20 */
-SYSCALL(sys_mount,sys_mount,sys32_mount_wrapper)
-SYSCALL(sys_oldumount,sys_oldumount,sys32_oldumount_wrapper)
-SYSCALL(sys_setuid16,sys_ni_syscall,sys32_setuid16_wrapper) /* old setuid16 syscall*/
-SYSCALL(sys_getuid16,sys_ni_syscall,sys32_getuid16) /* old getuid16 syscall*/
-SYSCALL(sys_stime,sys_ni_syscall,sys32_stime_wrapper) /* 25 old stime syscall */
-SYSCALL(sys_ptrace,sys_ptrace,sys32_ptrace_wrapper)
-SYSCALL(sys_alarm,sys_alarm,sys32_alarm_wrapper)
+SYSCALL(sys_mount,sys_mount,compat_sys_mount)
+SYSCALL(sys_oldumount,sys_oldumount,compat_sys_oldumount)
+SYSCALL(sys_setuid16,sys_ni_syscall,compat_sys_s390_setuid16) /* old setuid16 syscall*/
+SYSCALL(sys_getuid16,sys_ni_syscall,compat_sys_s390_getuid16) /* old getuid16 syscall*/
+SYSCALL(sys_stime,sys_ni_syscall,compat_sys_stime) /* 25 old stime syscall */
+SYSCALL(sys_ptrace,sys_ptrace,compat_sys_ptrace)
+SYSCALL(sys_alarm,sys_alarm,compat_sys_alarm)
NI_SYSCALL /* old fstat syscall */
SYSCALL(sys_pause,sys_pause,sys_pause)
-SYSCALL(sys_utime,sys_utime,compat_sys_utime_wrapper) /* 30 */
+SYSCALL(sys_utime,sys_utime,compat_sys_utime) /* 30 */
NI_SYSCALL /* old stty syscall */
NI_SYSCALL /* old gtty syscall */
-SYSCALL(sys_access,sys_access,sys32_access_wrapper)
-SYSCALL(sys_nice,sys_nice,sys32_nice_wrapper)
+SYSCALL(sys_access,sys_access,compat_sys_access)
+SYSCALL(sys_nice,sys_nice,compat_sys_nice)
NI_SYSCALL /* 35 old ftime syscall */
SYSCALL(sys_sync,sys_sync,sys_sync)
-SYSCALL(sys_kill,sys_kill,sys32_kill_wrapper)
-SYSCALL(sys_rename,sys_rename,sys32_rename_wrapper)
-SYSCALL(sys_mkdir,sys_mkdir,sys32_mkdir_wrapper)
-SYSCALL(sys_rmdir,sys_rmdir,sys32_rmdir_wrapper) /* 40 */
-SYSCALL(sys_dup,sys_dup,sys32_dup_wrapper)
-SYSCALL(sys_pipe,sys_pipe,sys32_pipe_wrapper)
-SYSCALL(sys_times,sys_times,compat_sys_times_wrapper)
+SYSCALL(sys_kill,sys_kill,compat_sys_kill)
+SYSCALL(sys_rename,sys_rename,compat_sys_rename)
+SYSCALL(sys_mkdir,sys_mkdir,compat_sys_mkdir)
+SYSCALL(sys_rmdir,sys_rmdir,compat_sys_rmdir) /* 40 */
+SYSCALL(sys_dup,sys_dup,compat_sys_dup)
+SYSCALL(sys_pipe,sys_pipe,compat_sys_pipe)
+SYSCALL(sys_times,sys_times,compat_sys_times)
NI_SYSCALL /* old prof syscall */
-SYSCALL(sys_brk,sys_brk,sys32_brk_wrapper) /* 45 */
-SYSCALL(sys_setgid16,sys_ni_syscall,sys32_setgid16_wrapper) /* old setgid16 syscall*/
-SYSCALL(sys_getgid16,sys_ni_syscall,sys32_getgid16) /* old getgid16 syscall*/
-SYSCALL(sys_signal,sys_signal,sys32_signal_wrapper)
-SYSCALL(sys_geteuid16,sys_ni_syscall,sys32_geteuid16) /* old geteuid16 syscall */
-SYSCALL(sys_getegid16,sys_ni_syscall,sys32_getegid16) /* 50 old getegid16 syscall */
-SYSCALL(sys_acct,sys_acct,sys32_acct_wrapper)
-SYSCALL(sys_umount,sys_umount,sys32_umount_wrapper)
+SYSCALL(sys_brk,sys_brk,compat_sys_brk) /* 45 */
+SYSCALL(sys_setgid16,sys_ni_syscall,compat_sys_s390_setgid16) /* old setgid16 syscall*/
+SYSCALL(sys_getgid16,sys_ni_syscall,compat_sys_s390_getgid16) /* old getgid16 syscall*/
+SYSCALL(sys_signal,sys_signal,compat_sys_signal)
+SYSCALL(sys_geteuid16,sys_ni_syscall,compat_sys_s390_geteuid16) /* old geteuid16 syscall */
+SYSCALL(sys_getegid16,sys_ni_syscall,compat_sys_s390_getegid16) /* 50 old getegid16 syscall */
+SYSCALL(sys_acct,sys_acct,compat_sys_acct)
+SYSCALL(sys_umount,sys_umount,compat_sys_umount)
NI_SYSCALL /* old lock syscall */
-SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl_wrapper)
-SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl_wrapper) /* 55 */
+SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl)
+SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl) /* 55 */
NI_SYSCALL /* intel mpx syscall */
-SYSCALL(sys_setpgid,sys_setpgid,sys32_setpgid_wrapper)
+SYSCALL(sys_setpgid,sys_setpgid,compat_sys_setpgid)
NI_SYSCALL /* old ulimit syscall */
NI_SYSCALL /* old uname syscall */
-SYSCALL(sys_umask,sys_umask,sys32_umask_wrapper) /* 60 */
-SYSCALL(sys_chroot,sys_chroot,sys32_chroot_wrapper)
-SYSCALL(sys_ustat,sys_ustat,sys32_ustat_wrapper)
-SYSCALL(sys_dup2,sys_dup2,sys32_dup2_wrapper)
+SYSCALL(sys_umask,sys_umask,compat_sys_umask) /* 60 */
+SYSCALL(sys_chroot,sys_chroot,compat_sys_chroot)
+SYSCALL(sys_ustat,sys_ustat,compat_sys_ustat)
+SYSCALL(sys_dup2,sys_dup2,compat_sys_dup2)
SYSCALL(sys_getppid,sys_getppid,sys_getppid)
SYSCALL(sys_getpgrp,sys_getpgrp,sys_getpgrp) /* 65 */
SYSCALL(sys_setsid,sys_setsid,sys_setsid)
SYSCALL(sys_sigaction,sys_sigaction,compat_sys_sigaction)
NI_SYSCALL /* old sgetmask syscall*/
NI_SYSCALL /* old ssetmask syscall*/
-SYSCALL(sys_setreuid16,sys_ni_syscall,sys32_setreuid16_wrapper) /* old setreuid16 syscall */
-SYSCALL(sys_setregid16,sys_ni_syscall,sys32_setregid16_wrapper) /* old setregid16 syscall */
-SYSCALL(sys_sigsuspend,sys_sigsuspend,sys_sigsuspend_wrapper)
-SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending_wrapper)
-SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper)
-SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper) /* 75 */
-SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit_wrapper)
+SYSCALL(sys_setreuid16,sys_ni_syscall,compat_sys_s390_setreuid16) /* old setreuid16 syscall */
+SYSCALL(sys_setregid16,sys_ni_syscall,compat_sys_s390_setregid16) /* old setregid16 syscall */
+SYSCALL(sys_sigsuspend,sys_sigsuspend,compat_sys_sigsuspend)
+SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending)
+SYSCALL(sys_sethostname,sys_sethostname,compat_sys_sethostname)
+SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit) /* 75 */
+SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit)
SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage)
-SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday_wrapper)
-SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday_wrapper)
-SYSCALL(sys_getgroups16,sys_ni_syscall,sys32_getgroups16_wrapper) /* 80 old getgroups16 syscall */
-SYSCALL(sys_setgroups16,sys_ni_syscall,sys32_setgroups16_wrapper) /* old setgroups16 syscall */
+SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday)
+SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday)
+SYSCALL(sys_getgroups16,sys_ni_syscall,compat_sys_s390_getgroups16) /* 80 old getgroups16 syscall */
+SYSCALL(sys_setgroups16,sys_ni_syscall,compat_sys_s390_setgroups16) /* old setgroups16 syscall */
NI_SYSCALL /* old select syscall */
-SYSCALL(sys_symlink,sys_symlink,sys32_symlink_wrapper)
+SYSCALL(sys_symlink,sys_symlink,compat_sys_symlink)
NI_SYSCALL /* old lstat syscall */
-SYSCALL(sys_readlink,sys_readlink,sys32_readlink_wrapper) /* 85 */
-SYSCALL(sys_uselib,sys_uselib,sys32_uselib_wrapper)
-SYSCALL(sys_swapon,sys_swapon,sys32_swapon_wrapper)
-SYSCALL(sys_reboot,sys_reboot,sys32_reboot_wrapper)
-SYSCALL(sys_ni_syscall,sys_ni_syscall,old32_readdir_wrapper) /* old readdir syscall */
-SYSCALL(sys_old_mmap,sys_old_mmap,old32_mmap_wrapper) /* 90 */
-SYSCALL(sys_munmap,sys_munmap,sys32_munmap_wrapper)
+SYSCALL(sys_readlink,sys_readlink,compat_sys_readlink) /* 85 */
+SYSCALL(sys_uselib,sys_uselib,compat_sys_uselib)
+SYSCALL(sys_swapon,sys_swapon,compat_sys_swapon)
+SYSCALL(sys_reboot,sys_reboot,compat_sys_reboot)
+SYSCALL(sys_ni_syscall,sys_ni_syscall,compat_sys_old_readdir) /* old readdir syscall */
+SYSCALL(sys_old_mmap,sys_old_mmap,compat_sys_s390_old_mmap) /* 90 */
+SYSCALL(sys_munmap,sys_munmap,compat_sys_munmap)
SYSCALL(sys_truncate,sys_truncate,compat_sys_truncate)
SYSCALL(sys_ftruncate,sys_ftruncate,compat_sys_ftruncate)
-SYSCALL(sys_fchmod,sys_fchmod,sys32_fchmod_wrapper)
-SYSCALL(sys_fchown16,sys_ni_syscall,sys32_fchown16_wrapper) /* 95 old fchown16 syscall*/
-SYSCALL(sys_getpriority,sys_getpriority,sys32_getpriority_wrapper)
-SYSCALL(sys_setpriority,sys_setpriority,sys32_setpriority_wrapper)
+SYSCALL(sys_fchmod,sys_fchmod,compat_sys_fchmod)
+SYSCALL(sys_fchown16,sys_ni_syscall,compat_sys_s390_fchown16) /* 95 old fchown16 syscall*/
+SYSCALL(sys_getpriority,sys_getpriority,compat_sys_getpriority)
+SYSCALL(sys_setpriority,sys_setpriority,compat_sys_setpriority)
NI_SYSCALL /* old profil syscall */
-SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs_wrapper)
-SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs_wrapper) /* 100 */
+SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs)
+SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs) /* 100 */
NI_SYSCALL /* ioperm for i386 */
-SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall_wrapper)
-SYSCALL(sys_syslog,sys_syslog,sys32_syslog_wrapper)
+SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall)
+SYSCALL(sys_syslog,sys_syslog,compat_sys_syslog)
SYSCALL(sys_setitimer,sys_setitimer,compat_sys_setitimer)
SYSCALL(sys_getitimer,sys_getitimer,compat_sys_getitimer) /* 105 */
-SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat_wrapper)
-SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat_wrapper)
-SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat_wrapper)
+SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat)
+SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat)
+SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat)
NI_SYSCALL /* old uname syscall */
SYSCALL(sys_lookup_dcookie,sys_lookup_dcookie,compat_sys_lookup_dcookie) /* 110 */
SYSCALL(sys_vhangup,sys_vhangup,sys_vhangup)
NI_SYSCALL /* old "idle" system call */
NI_SYSCALL /* vm86old for i386 */
SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4)
-SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper) /* 115 */
-SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper)
+SYSCALL(sys_swapoff,sys_swapoff,compat_sys_swapoff) /* 115 */
+SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo)
SYSCALL(sys_s390_ipc,sys_s390_ipc,compat_sys_s390_ipc)
-SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper)
-SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn)
-SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */
-SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper)
-SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper)
+SYSCALL(sys_fsync,sys_fsync,compat_sys_fsync)
+SYSCALL(sys_sigreturn,sys_sigreturn,compat_sys_sigreturn)
+SYSCALL(sys_clone,sys_clone,compat_sys_clone) /* 120 */
+SYSCALL(sys_setdomainname,sys_setdomainname,compat_sys_setdomainname)
+SYSCALL(sys_newuname,sys_newuname,compat_sys_newuname)
NI_SYSCALL /* modify_ldt for i386 */
-SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper)
-SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */
+SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex)
+SYSCALL(sys_mprotect,sys_mprotect,compat_sys_mprotect) /* 125 */
SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask)
NI_SYSCALL /* old "create module" */
-SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper)
-SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper)
+SYSCALL(sys_init_module,sys_init_module,compat_sys_init_module)
+SYSCALL(sys_delete_module,sys_delete_module,compat_sys_delete_module)
NI_SYSCALL /* 130: old get_kernel_syms */
-SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper)
-SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper)
-SYSCALL(sys_fchdir,sys_fchdir,sys32_fchdir_wrapper)
-SYSCALL(sys_bdflush,sys_bdflush,sys32_bdflush_wrapper)
-SYSCALL(sys_sysfs,sys_sysfs,sys32_sysfs_wrapper) /* 135 */
-SYSCALL(sys_personality,sys_s390_personality,sys32_personality_wrapper)
+SYSCALL(sys_quotactl,sys_quotactl,compat_sys_quotactl)
+SYSCALL(sys_getpgid,sys_getpgid,compat_sys_getpgid)
+SYSCALL(sys_fchdir,sys_fchdir,compat_sys_fchdir)
+SYSCALL(sys_bdflush,sys_bdflush,compat_sys_bdflush)
+SYSCALL(sys_sysfs,sys_sysfs,compat_sys_sysfs) /* 135 */
+SYSCALL(sys_personality,sys_s390_personality,compat_sys_s390_personality)
NI_SYSCALL /* for afs_syscall */
-SYSCALL(sys_setfsuid16,sys_ni_syscall,sys32_setfsuid16_wrapper) /* old setfsuid16 syscall */
-SYSCALL(sys_setfsgid16,sys_ni_syscall,sys32_setfsgid16_wrapper) /* old setfsgid16 syscall */
-SYSCALL(sys_llseek,sys_llseek,sys32_llseek_wrapper) /* 140 */
-SYSCALL(sys_getdents,sys_getdents,sys32_getdents_wrapper)
-SYSCALL(sys_select,sys_select,compat_sys_select_wrapper)
-SYSCALL(sys_flock,sys_flock,sys32_flock_wrapper)
-SYSCALL(sys_msync,sys_msync,sys32_msync_wrapper)
-SYSCALL(sys_readv,sys_readv,compat_sys_readv_wrapper) /* 145 */
-SYSCALL(sys_writev,sys_writev,compat_sys_writev_wrapper)
-SYSCALL(sys_getsid,sys_getsid,sys32_getsid_wrapper)
-SYSCALL(sys_fdatasync,sys_fdatasync,sys32_fdatasync_wrapper)
+SYSCALL(sys_setfsuid16,sys_ni_syscall,compat_sys_s390_setfsuid16) /* old setfsuid16 syscall */
+SYSCALL(sys_setfsgid16,sys_ni_syscall,compat_sys_s390_setfsgid16) /* old setfsgid16 syscall */
+SYSCALL(sys_llseek,sys_llseek,compat_sys_llseek) /* 140 */
+SYSCALL(sys_getdents,sys_getdents,compat_sys_getdents)
+SYSCALL(sys_select,sys_select,compat_sys_select)
+SYSCALL(sys_flock,sys_flock,compat_sys_flock)
+SYSCALL(sys_msync,sys_msync,compat_sys_msync)
+SYSCALL(sys_readv,sys_readv,compat_sys_readv) /* 145 */
+SYSCALL(sys_writev,sys_writev,compat_sys_writev)
+SYSCALL(sys_getsid,sys_getsid,compat_sys_getsid)
+SYSCALL(sys_fdatasync,sys_fdatasync,compat_sys_fdatasync)
SYSCALL(sys_sysctl,sys_sysctl,compat_sys_sysctl)
-SYSCALL(sys_mlock,sys_mlock,sys32_mlock_wrapper) /* 150 */
-SYSCALL(sys_munlock,sys_munlock,sys32_munlock_wrapper)
-SYSCALL(sys_mlockall,sys_mlockall,sys32_mlockall_wrapper)
+SYSCALL(sys_mlock,sys_mlock,compat_sys_mlock) /* 150 */
+SYSCALL(sys_munlock,sys_munlock,compat_sys_munlock)
+SYSCALL(sys_mlockall,sys_mlockall,compat_sys_mlockall)
SYSCALL(sys_munlockall,sys_munlockall,sys_munlockall)
-SYSCALL(sys_sched_setparam,sys_sched_setparam,sys32_sched_setparam_wrapper)
-SYSCALL(sys_sched_getparam,sys_sched_getparam,sys32_sched_getparam_wrapper) /* 155 */
-SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,sys32_sched_setscheduler_wrapper)
-SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,sys32_sched_getscheduler_wrapper)
+SYSCALL(sys_sched_setparam,sys_sched_setparam,compat_sys_sched_setparam)
+SYSCALL(sys_sched_getparam,sys_sched_getparam,compat_sys_sched_getparam) /* 155 */
+SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,compat_sys_sched_setscheduler)
+SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,compat_sys_sched_getscheduler)
SYSCALL(sys_sched_yield,sys_sched_yield,sys_sched_yield)
-SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,sys32_sched_get_priority_max_wrapper)
-SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,sys32_sched_get_priority_min_wrapper) /* 160 */
+SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,compat_sys_sched_get_priority_max)
+SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,compat_sys_sched_get_priority_min) /* 160 */
SYSCALL(sys_sched_rr_get_interval,sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval)
-SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep_wrapper)
-SYSCALL(sys_mremap,sys_mremap,sys32_mremap_wrapper)
-SYSCALL(sys_setresuid16,sys_ni_syscall,sys32_setresuid16_wrapper) /* old setresuid16 syscall */
-SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper) /* 165 old getresuid16 syscall */
+SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep)
+SYSCALL(sys_mremap,sys_mremap,compat_sys_mremap)
+SYSCALL(sys_setresuid16,sys_ni_syscall,compat_sys_s390_setresuid16) /* old setresuid16 syscall */
+SYSCALL(sys_getresuid16,sys_ni_syscall,compat_sys_s390_getresuid16) /* 165 old getresuid16 syscall */
NI_SYSCALL /* for vm86 */
NI_SYSCALL /* old sys_query_module */
-SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper)
+SYSCALL(sys_poll,sys_poll,compat_sys_poll)
NI_SYSCALL /* old nfsservctl */
-SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper) /* 170 old setresgid16 syscall */
-SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper) /* old getresgid16 syscall */
-SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper)
-SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,sys32_rt_sigreturn)
+SYSCALL(sys_setresgid16,sys_ni_syscall,compat_sys_s390_setresgid16) /* 170 old setresgid16 syscall */
+SYSCALL(sys_getresgid16,sys_ni_syscall,compat_sys_s390_getresgid16) /* old getresgid16 syscall */
+SYSCALL(sys_prctl,sys_prctl,compat_sys_prctl)
+SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,compat_sys_rt_sigreturn)
SYSCALL(sys_rt_sigaction,sys_rt_sigaction,compat_sys_rt_sigaction)
SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,compat_sys_rt_sigprocmask) /* 175 */
SYSCALL(sys_rt_sigpending,sys_rt_sigpending,compat_sys_rt_sigpending)
SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait)
SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,compat_sys_rt_sigqueueinfo)
SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend)
-SYSCALL(sys_pread64,sys_pread64,sys32_pread64_wrapper) /* 180 */
-SYSCALL(sys_pwrite64,sys_pwrite64,sys32_pwrite64_wrapper)
-SYSCALL(sys_chown16,sys_ni_syscall,sys32_chown16_wrapper) /* old chown16 syscall */
-SYSCALL(sys_getcwd,sys_getcwd,sys32_getcwd_wrapper)
-SYSCALL(sys_capget,sys_capget,sys32_capget_wrapper)
-SYSCALL(sys_capset,sys_capset,sys32_capset_wrapper) /* 185 */
+SYSCALL(sys_pread64,sys_pread64,compat_sys_s390_pread64) /* 180 */
+SYSCALL(sys_pwrite64,sys_pwrite64,compat_sys_s390_pwrite64)
+SYSCALL(sys_chown16,sys_ni_syscall,compat_sys_s390_chown16) /* old chown16 syscall */
+SYSCALL(sys_getcwd,sys_getcwd,compat_sys_getcwd)
+SYSCALL(sys_capget,sys_capget,compat_sys_capget)
+SYSCALL(sys_capset,sys_capset,compat_sys_capset) /* 185 */
SYSCALL(sys_sigaltstack,sys_sigaltstack,compat_sys_sigaltstack)
SYSCALL(sys_sendfile,sys_sendfile64,compat_sys_sendfile)
NI_SYSCALL /* streams1 */
NI_SYSCALL /* streams2 */
SYSCALL(sys_vfork,sys_vfork,sys_vfork) /* 190 */
-SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit_wrapper)
-SYSCALL(sys_mmap2,sys_mmap2,sys32_mmap2_wrapper)
-SYSCALL(sys_truncate64,sys_ni_syscall,sys32_truncate64_wrapper)
-SYSCALL(sys_ftruncate64,sys_ni_syscall,sys32_ftruncate64_wrapper)
-SYSCALL(sys_stat64,sys_ni_syscall,sys32_stat64_wrapper) /* 195 */
-SYSCALL(sys_lstat64,sys_ni_syscall,sys32_lstat64_wrapper)
-SYSCALL(sys_fstat64,sys_ni_syscall,sys32_fstat64_wrapper)
-SYSCALL(sys_lchown,sys_lchown,sys32_lchown_wrapper)
+SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit)
+SYSCALL(sys_mmap2,sys_mmap2,compat_sys_s390_mmap2)
+SYSCALL(sys_truncate64,sys_ni_syscall,compat_sys_s390_truncate64)
+SYSCALL(sys_ftruncate64,sys_ni_syscall,compat_sys_s390_ftruncate64)
+SYSCALL(sys_stat64,sys_ni_syscall,compat_sys_s390_stat64) /* 195 */
+SYSCALL(sys_lstat64,sys_ni_syscall,compat_sys_s390_lstat64)
+SYSCALL(sys_fstat64,sys_ni_syscall,compat_sys_s390_fstat64)
+SYSCALL(sys_lchown,sys_lchown,compat_sys_lchown)
SYSCALL(sys_getuid,sys_getuid,sys_getuid)
SYSCALL(sys_getgid,sys_getgid,sys_getgid) /* 200 */
SYSCALL(sys_geteuid,sys_geteuid,sys_geteuid)
SYSCALL(sys_getegid,sys_getegid,sys_getegid)
-SYSCALL(sys_setreuid,sys_setreuid,sys32_setreuid_wrapper)
-SYSCALL(sys_setregid,sys_setregid,sys32_setregid_wrapper)
-SYSCALL(sys_getgroups,sys_getgroups,sys32_getgroups_wrapper) /* 205 */
-SYSCALL(sys_setgroups,sys_setgroups,sys32_setgroups_wrapper)
-SYSCALL(sys_fchown,sys_fchown,sys32_fchown_wrapper)
-SYSCALL(sys_setresuid,sys_setresuid,sys32_setresuid_wrapper)
-SYSCALL(sys_getresuid,sys_getresuid,sys32_getresuid_wrapper)
-SYSCALL(sys_setresgid,sys_setresgid,sys32_setresgid_wrapper) /* 210 */
-SYSCALL(sys_getresgid,sys_getresgid,sys32_getresgid_wrapper)
-SYSCALL(sys_chown,sys_chown,sys32_chown_wrapper)
-SYSCALL(sys_setuid,sys_setuid,sys32_setuid_wrapper)
-SYSCALL(sys_setgid,sys_setgid,sys32_setgid_wrapper)
-SYSCALL(sys_setfsuid,sys_setfsuid,sys32_setfsuid_wrapper) /* 215 */
-SYSCALL(sys_setfsgid,sys_setfsgid,sys32_setfsgid_wrapper)
-SYSCALL(sys_pivot_root,sys_pivot_root,sys32_pivot_root_wrapper)
-SYSCALL(sys_mincore,sys_mincore,sys32_mincore_wrapper)
-SYSCALL(sys_madvise,sys_madvise,sys32_madvise_wrapper)
-SYSCALL(sys_getdents64,sys_getdents64,sys32_getdents64_wrapper) /* 220 */
-SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64_wrapper)
-SYSCALL(sys_readahead,sys_readahead,sys32_readahead_wrapper)
+SYSCALL(sys_setreuid,sys_setreuid,compat_sys_setreuid)
+SYSCALL(sys_setregid,sys_setregid,compat_sys_setregid)
+SYSCALL(sys_getgroups,sys_getgroups,compat_sys_getgroups) /* 205 */
+SYSCALL(sys_setgroups,sys_setgroups,compat_sys_setgroups)
+SYSCALL(sys_fchown,sys_fchown,compat_sys_fchown)
+SYSCALL(sys_setresuid,sys_setresuid,compat_sys_setresuid)
+SYSCALL(sys_getresuid,sys_getresuid,compat_sys_getresuid)
+SYSCALL(sys_setresgid,sys_setresgid,compat_sys_setresgid) /* 210 */
+SYSCALL(sys_getresgid,sys_getresgid,compat_sys_getresgid)
+SYSCALL(sys_chown,sys_chown,compat_sys_chown)
+SYSCALL(sys_setuid,sys_setuid,compat_sys_setuid)
+SYSCALL(sys_setgid,sys_setgid,compat_sys_setgid)
+SYSCALL(sys_setfsuid,sys_setfsuid,compat_sys_setfsuid) /* 215 */
+SYSCALL(sys_setfsgid,sys_setfsgid,compat_sys_setfsgid)
+SYSCALL(sys_pivot_root,sys_pivot_root,compat_sys_pivot_root)
+SYSCALL(sys_mincore,sys_mincore,compat_sys_mincore)
+SYSCALL(sys_madvise,sys_madvise,compat_sys_madvise)
+SYSCALL(sys_getdents64,sys_getdents64,compat_sys_getdents64) /* 220 */
+SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64)
+SYSCALL(sys_readahead,sys_readahead,compat_sys_s390_readahead)
SYSCALL(sys_sendfile64,sys_ni_syscall,compat_sys_sendfile64)
-SYSCALL(sys_setxattr,sys_setxattr,sys32_setxattr_wrapper)
-SYSCALL(sys_lsetxattr,sys_lsetxattr,sys32_lsetxattr_wrapper) /* 225 */
-SYSCALL(sys_fsetxattr,sys_fsetxattr,sys32_fsetxattr_wrapper)
-SYSCALL(sys_getxattr,sys_getxattr,sys32_getxattr_wrapper)
-SYSCALL(sys_lgetxattr,sys_lgetxattr,sys32_lgetxattr_wrapper)
-SYSCALL(sys_fgetxattr,sys_fgetxattr,sys32_fgetxattr_wrapper)
-SYSCALL(sys_listxattr,sys_listxattr,sys32_listxattr_wrapper) /* 230 */
-SYSCALL(sys_llistxattr,sys_llistxattr,sys32_llistxattr_wrapper)
-SYSCALL(sys_flistxattr,sys_flistxattr,sys32_flistxattr_wrapper)
-SYSCALL(sys_removexattr,sys_removexattr,sys32_removexattr_wrapper)
-SYSCALL(sys_lremovexattr,sys_lremovexattr,sys32_lremovexattr_wrapper)
-SYSCALL(sys_fremovexattr,sys_fremovexattr,sys32_fremovexattr_wrapper) /* 235 */
+SYSCALL(sys_setxattr,sys_setxattr,compat_sys_setxattr)
+SYSCALL(sys_lsetxattr,sys_lsetxattr,compat_sys_lsetxattr) /* 225 */
+SYSCALL(sys_fsetxattr,sys_fsetxattr,compat_sys_fsetxattr)
+SYSCALL(sys_getxattr,sys_getxattr,compat_sys_getxattr)
+SYSCALL(sys_lgetxattr,sys_lgetxattr,compat_sys_lgetxattr)
+SYSCALL(sys_fgetxattr,sys_fgetxattr,compat_sys_fgetxattr)
+SYSCALL(sys_listxattr,sys_listxattr,compat_sys_listxattr) /* 230 */
+SYSCALL(sys_llistxattr,sys_llistxattr,compat_sys_llistxattr)
+SYSCALL(sys_flistxattr,sys_flistxattr,compat_sys_flistxattr)
+SYSCALL(sys_removexattr,sys_removexattr,compat_sys_removexattr)
+SYSCALL(sys_lremovexattr,sys_lremovexattr,compat_sys_lremovexattr)
+SYSCALL(sys_fremovexattr,sys_fremovexattr,compat_sys_fremovexattr) /* 235 */
SYSCALL(sys_gettid,sys_gettid,sys_gettid)
-SYSCALL(sys_tkill,sys_tkill,sys_tkill_wrapper)
+SYSCALL(sys_tkill,sys_tkill,compat_sys_tkill)
SYSCALL(sys_futex,sys_futex,compat_sys_futex)
-SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,sys32_sched_setaffinity_wrapper)
-SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,sys32_sched_getaffinity_wrapper) /* 240 */
-SYSCALL(sys_tgkill,sys_tgkill,sys_tgkill_wrapper)
+SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,compat_sys_sched_setaffinity)
+SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,compat_sys_sched_getaffinity) /* 240 */
+SYSCALL(sys_tgkill,sys_tgkill,compat_sys_tgkill)
NI_SYSCALL /* reserved for TUX */
-SYSCALL(sys_io_setup,sys_io_setup,sys32_io_setup_wrapper)
-SYSCALL(sys_io_destroy,sys_io_destroy,sys32_io_destroy_wrapper)
-SYSCALL(sys_io_getevents,sys_io_getevents,sys32_io_getevents_wrapper) /* 245 */
-SYSCALL(sys_io_submit,sys_io_submit,sys32_io_submit_wrapper)
-SYSCALL(sys_io_cancel,sys_io_cancel,sys32_io_cancel_wrapper)
-SYSCALL(sys_exit_group,sys_exit_group,sys32_exit_group_wrapper)
-SYSCALL(sys_epoll_create,sys_epoll_create,sys_epoll_create_wrapper)
-SYSCALL(sys_epoll_ctl,sys_epoll_ctl,sys_epoll_ctl_wrapper) /* 250 */
-SYSCALL(sys_epoll_wait,sys_epoll_wait,sys_epoll_wait_wrapper)
-SYSCALL(sys_set_tid_address,sys_set_tid_address,sys32_set_tid_address_wrapper)
-SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,sys32_fadvise64_wrapper)
-SYSCALL(sys_timer_create,sys_timer_create,sys32_timer_create_wrapper)
-SYSCALL(sys_timer_settime,sys_timer_settime,sys32_timer_settime_wrapper) /* 255 */
-SYSCALL(sys_timer_gettime,sys_timer_gettime,sys32_timer_gettime_wrapper)
-SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,sys32_timer_getoverrun_wrapper)
-SYSCALL(sys_timer_delete,sys_timer_delete,sys32_timer_delete_wrapper)
-SYSCALL(sys_clock_settime,sys_clock_settime,sys32_clock_settime_wrapper)
-SYSCALL(sys_clock_gettime,sys_clock_gettime,sys32_clock_gettime_wrapper) /* 260 */
-SYSCALL(sys_clock_getres,sys_clock_getres,sys32_clock_getres_wrapper)
-SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,sys32_clock_nanosleep_wrapper)
+SYSCALL(sys_io_setup,sys_io_setup,compat_sys_io_setup)
+SYSCALL(sys_io_destroy,sys_io_destroy,compat_sys_io_destroy)
+SYSCALL(sys_io_getevents,sys_io_getevents,compat_sys_io_getevents) /* 245 */
+SYSCALL(sys_io_submit,sys_io_submit,compat_sys_io_submit)
+SYSCALL(sys_io_cancel,sys_io_cancel,compat_sys_io_cancel)
+SYSCALL(sys_exit_group,sys_exit_group,compat_sys_exit_group)
+SYSCALL(sys_epoll_create,sys_epoll_create,compat_sys_epoll_create)
+SYSCALL(sys_epoll_ctl,sys_epoll_ctl,compat_sys_epoll_ctl) /* 250 */
+SYSCALL(sys_epoll_wait,sys_epoll_wait,compat_sys_epoll_wait)
+SYSCALL(sys_set_tid_address,sys_set_tid_address,compat_sys_set_tid_address)
+SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,compat_sys_s390_fadvise64)
+SYSCALL(sys_timer_create,sys_timer_create,compat_sys_timer_create)
+SYSCALL(sys_timer_settime,sys_timer_settime,compat_sys_timer_settime) /* 255 */
+SYSCALL(sys_timer_gettime,sys_timer_gettime,compat_sys_timer_gettime)
+SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,compat_sys_timer_getoverrun)
+SYSCALL(sys_timer_delete,sys_timer_delete,compat_sys_timer_delete)
+SYSCALL(sys_clock_settime,sys_clock_settime,compat_sys_clock_settime)
+SYSCALL(sys_clock_gettime,sys_clock_gettime,compat_sys_clock_gettime) /* 260 */
+SYSCALL(sys_clock_getres,sys_clock_getres,compat_sys_clock_getres)
+SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,compat_sys_clock_nanosleep)
NI_SYSCALL /* reserved for vserver */
-SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,sys32_fadvise64_64_wrapper)
-SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64_wrapper)
-SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64_wrapper)
-SYSCALL(sys_remap_file_pages,sys_remap_file_pages,sys32_remap_file_pages_wrapper)
+SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,compat_sys_s390_fadvise64_64)
+SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64)
+SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64)
+SYSCALL(sys_remap_file_pages,sys_remap_file_pages,compat_sys_remap_file_pages)
NI_SYSCALL /* 268 sys_mbind */
NI_SYSCALL /* 269 sys_get_mempolicy */
NI_SYSCALL /* 270 sys_set_mempolicy */
-SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open_wrapper)
-SYSCALL(sys_mq_unlink,sys_mq_unlink,sys32_mq_unlink_wrapper)
-SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend_wrapper)
-SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive_wrapper)
-SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify_wrapper) /* 275 */
-SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr_wrapper)
-SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load_wrapper)
-SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key_wrapper)
-SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key_wrapper)
-SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl_wrapper) /* 280 */
+SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open)
+SYSCALL(sys_mq_unlink,sys_mq_unlink,compat_sys_mq_unlink)
+SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend)
+SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive)
+SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify) /* 275 */
+SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr)
+SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load)
+SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key)
+SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key)
+SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl) /* 280 */
SYSCALL(sys_waitid,sys_waitid,compat_sys_waitid)
-SYSCALL(sys_ioprio_set,sys_ioprio_set,sys_ioprio_set_wrapper)
-SYSCALL(sys_ioprio_get,sys_ioprio_get,sys_ioprio_get_wrapper)
+SYSCALL(sys_ioprio_set,sys_ioprio_set,compat_sys_ioprio_set)
+SYSCALL(sys_ioprio_get,sys_ioprio_get,compat_sys_ioprio_get)
SYSCALL(sys_inotify_init,sys_inotify_init,sys_inotify_init)
-SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,sys_inotify_add_watch_wrapper) /* 285 */
-SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,sys_inotify_rm_watch_wrapper)
+SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,compat_sys_inotify_add_watch) /* 285 */
+SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,compat_sys_inotify_rm_watch)
NI_SYSCALL /* 287 sys_migrate_pages */
SYSCALL(sys_openat,sys_openat,compat_sys_openat)
-SYSCALL(sys_mkdirat,sys_mkdirat,sys_mkdirat_wrapper)
-SYSCALL(sys_mknodat,sys_mknodat,sys_mknodat_wrapper) /* 290 */
-SYSCALL(sys_fchownat,sys_fchownat,sys_fchownat_wrapper)
-SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat_wrapper)
-SYSCALL(sys_fstatat64,sys_newfstatat,sys32_fstatat64_wrapper)
-SYSCALL(sys_unlinkat,sys_unlinkat,sys_unlinkat_wrapper)
-SYSCALL(sys_renameat,sys_renameat,sys_renameat_wrapper) /* 295 */
-SYSCALL(sys_linkat,sys_linkat,sys_linkat_wrapper)
-SYSCALL(sys_symlinkat,sys_symlinkat,sys_symlinkat_wrapper)
-SYSCALL(sys_readlinkat,sys_readlinkat,sys_readlinkat_wrapper)
-SYSCALL(sys_fchmodat,sys_fchmodat,sys_fchmodat_wrapper)
-SYSCALL(sys_faccessat,sys_faccessat,sys_faccessat_wrapper) /* 300 */
-SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6_wrapper)
-SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll_wrapper)
-SYSCALL(sys_unshare,sys_unshare,sys_unshare_wrapper)
+SYSCALL(sys_mkdirat,sys_mkdirat,compat_sys_mkdirat)
+SYSCALL(sys_mknodat,sys_mknodat,compat_sys_mknodat) /* 290 */
+SYSCALL(sys_fchownat,sys_fchownat,compat_sys_fchownat)
+SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat)
+SYSCALL(sys_fstatat64,sys_newfstatat,compat_sys_s390_fstatat64)
+SYSCALL(sys_unlinkat,sys_unlinkat,compat_sys_unlinkat)
+SYSCALL(sys_renameat,sys_renameat,compat_sys_renameat) /* 295 */
+SYSCALL(sys_linkat,sys_linkat,compat_sys_linkat)
+SYSCALL(sys_symlinkat,sys_symlinkat,compat_sys_symlinkat)
+SYSCALL(sys_readlinkat,sys_readlinkat,compat_sys_readlinkat)
+SYSCALL(sys_fchmodat,sys_fchmodat,compat_sys_fchmodat)
+SYSCALL(sys_faccessat,sys_faccessat,compat_sys_faccessat) /* 300 */
+SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6)
+SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll)
+SYSCALL(sys_unshare,sys_unshare,compat_sys_unshare)
SYSCALL(sys_set_robust_list,sys_set_robust_list,compat_sys_set_robust_list)
SYSCALL(sys_get_robust_list,sys_get_robust_list,compat_sys_get_robust_list)
-SYSCALL(sys_splice,sys_splice,sys_splice_wrapper)
-SYSCALL(sys_sync_file_range,sys_sync_file_range,sys_sync_file_range_wrapper)
-SYSCALL(sys_tee,sys_tee,sys_tee_wrapper)
+SYSCALL(sys_splice,sys_splice,compat_sys_splice)
+SYSCALL(sys_sync_file_range,sys_sync_file_range,compat_sys_s390_sync_file_range)
+SYSCALL(sys_tee,sys_tee,compat_sys_tee)
SYSCALL(sys_vmsplice,sys_vmsplice,compat_sys_vmsplice)
NI_SYSCALL /* 310 sys_move_pages */
-SYSCALL(sys_getcpu,sys_getcpu,sys_getcpu_wrapper)
+SYSCALL(sys_getcpu,sys_getcpu,compat_sys_getcpu)
SYSCALL(sys_epoll_pwait,sys_epoll_pwait,compat_sys_epoll_pwait)
-SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes_wrapper)
-SYSCALL(sys_s390_fallocate,sys_fallocate,sys_fallocate_wrapper)
-SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat_wrapper) /* 315 */
+SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes)
+SYSCALL(sys_s390_fallocate,sys_fallocate,compat_sys_s390_fallocate)
+SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat) /* 315 */
SYSCALL(sys_signalfd,sys_signalfd,compat_sys_signalfd)
NI_SYSCALL /* 317 old sys_timer_fd */
-SYSCALL(sys_eventfd,sys_eventfd,sys_eventfd_wrapper)
-SYSCALL(sys_timerfd_create,sys_timerfd_create,sys_timerfd_create_wrapper)
+SYSCALL(sys_eventfd,sys_eventfd,compat_sys_eventfd)
+SYSCALL(sys_timerfd_create,sys_timerfd_create,compat_sys_timerfd_create)
SYSCALL(sys_timerfd_settime,sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */
SYSCALL(sys_timerfd_gettime,sys_timerfd_gettime,compat_sys_timerfd_gettime)
SYSCALL(sys_signalfd4,sys_signalfd4,compat_sys_signalfd4)
-SYSCALL(sys_eventfd2,sys_eventfd2,sys_eventfd2_wrapper)
-SYSCALL(sys_inotify_init1,sys_inotify_init1,sys_inotify_init1_wrapper)
-SYSCALL(sys_pipe2,sys_pipe2,sys_pipe2_wrapper) /* 325 */
-SYSCALL(sys_dup3,sys_dup3,sys_dup3_wrapper)
-SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper)
+SYSCALL(sys_eventfd2,sys_eventfd2,compat_sys_eventfd2)
+SYSCALL(sys_inotify_init1,sys_inotify_init1,compat_sys_inotify_init1)
+SYSCALL(sys_pipe2,sys_pipe2,compat_sys_pipe2) /* 325 */
+SYSCALL(sys_dup3,sys_dup3,compat_sys_dup3)
+SYSCALL(sys_epoll_create1,sys_epoll_create1,compat_sys_epoll_create1)
SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv)
SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev)
SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */
-SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper)
-SYSCALL(sys_fanotify_init,sys_fanotify_init,sys_fanotify_init_wrapper)
+SYSCALL(sys_perf_event_open,sys_perf_event_open,compat_sys_perf_event_open)
+SYSCALL(sys_fanotify_init,sys_fanotify_init,compat_sys_fanotify_init)
SYSCALL(sys_fanotify_mark,sys_fanotify_mark,compat_sys_fanotify_mark)
-SYSCALL(sys_prlimit64,sys_prlimit64,sys_prlimit64_wrapper)
-SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,sys_name_to_handle_at_wrapper) /* 335 */
+SYSCALL(sys_prlimit64,sys_prlimit64,compat_sys_prlimit64)
+SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */
SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at)
-SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
-SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
-SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
-SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */
-SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper)
-SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,sys_s390_runtime_instr_wrapper)
-SYSCALL(sys_kcmp,sys_kcmp,sys_kcmp_wrapper)
-SYSCALL(sys_finit_module,sys_finit_module,sys_finit_module_wrapper)
+SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime)
+SYSCALL(sys_syncfs,sys_syncfs,compat_sys_syncfs)
+SYSCALL(sys_setns,sys_setns,compat_sys_setns)
+SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */
+SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev)
+SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,compat_sys_s390_runtime_instr)
+SYSCALL(sys_kcmp,sys_kcmp,compat_sys_kcmp)
+SYSCALL(sys_finit_module,sys_finit_module,compat_sys_finit_module)
+SYSCALL(sys_sched_setattr,sys_sched_setattr,compat_sys_sched_setattr) /* 345 */
+SYSCALL(sys_sched_getattr,sys_sched_getattr,compat_sys_sched_getattr)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index dd95f163162..386d37a228b 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -262,11 +262,11 @@ void __init time_init(void)
stp_reset();
/* request the clock comparator external interrupt */
- if (register_external_interrupt(0x1004, clock_comparator_interrupt))
- panic("Couldn't request external interrupt 0x1004");
+ if (register_external_irq(EXT_IRQ_CLK_COMP, clock_comparator_interrupt))
+ panic("Couldn't request external interrupt 0x1004");
/* request the timing alert external interrupt */
- if (register_external_interrupt(0x1406, timing_alert_interrupt))
+ if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt))
panic("Couldn't request external interrupt 0x1406");
if (clocksource_register(&clocksource_tod) != 0)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 4b2e3e31700..6298fed11ce 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/Kconfig b/arch/s390/kvm/Kconfig
index 70b46eacf8e..10d529ac982 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -23,6 +23,10 @@ config KVM
select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_EVENTFD
+ select KVM_ASYNC_PF
+ select KVM_ASYNC_PF_SYNC
+ select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQ_ROUTING
---help---
Support hosting paravirtualized guest machines using the SIE
virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 40b4c6470f8..d3adb37e93a 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
# as published by the Free Software Foundation.
KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 78d967f180f..08dfc839a6c 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -13,10 +13,12 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <asm/pgalloc.h>
#include <asm/virtio-ccw.h>
#include "kvm-s390.h"
#include "trace.h"
#include "trace-s390.h"
+#include "gaccess.h"
static int diag_release_pages(struct kvm_vcpu *vcpu)
{
@@ -46,6 +48,87 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
return 0;
}
+static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
+{
+ struct prs_parm {
+ u16 code;
+ u16 subcode;
+ u16 parm_len;
+ u16 parm_version;
+ u64 token_addr;
+ u64 select_mask;
+ u64 compare_mask;
+ u64 zarch;
+ };
+ struct prs_parm parm;
+ int rc;
+ u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
+ u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
+ unsigned long hva_token = KVM_HVA_ERR_BAD;
+
+ if (vcpu->run->s.regs.gprs[rx] & 7)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ if (copy_from_guest(vcpu, &parm, vcpu->run->s.regs.gprs[rx], sizeof(parm)))
+ return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ switch (parm.subcode) {
+ case 0: /* TOKEN */
+ if (vcpu->arch.pfault_token != KVM_S390_PFAULT_TOKEN_INVALID) {
+ /*
+ * If the pagefault handshake is already activated,
+ * the token must not be changed. We have to return
+ * decimal 8 instead, as mandated in SC24-6084.
+ */
+ vcpu->run->s.regs.gprs[ry] = 8;
+ return 0;
+ }
+
+ if ((parm.compare_mask & parm.select_mask) != parm.compare_mask ||
+ parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ hva_token = gfn_to_hva(vcpu->kvm, gpa_to_gfn(parm.token_addr));
+ if (kvm_is_error_hva(hva_token))
+ return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+ vcpu->arch.pfault_token = parm.token_addr;
+ vcpu->arch.pfault_select = parm.select_mask;
+ vcpu->arch.pfault_compare = parm.compare_mask;
+ vcpu->run->s.regs.gprs[ry] = 0;
+ rc = 0;
+ break;
+ case 1: /*
+ * CANCEL
+ * Specification allows to let already pending tokens survive
+ * the cancel, therefore to reduce code complexity, we assume
+ * all outstanding tokens are already pending.
+ */
+ if (parm.token_addr || parm.select_mask ||
+ parm.compare_mask || parm.zarch)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ vcpu->run->s.regs.gprs[ry] = 0;
+ /*
+ * If the pfault handling was not established or is already
+ * canceled SC24-6084 requests to return decimal 4.
+ */
+ if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+ vcpu->run->s.regs.gprs[ry] = 4;
+ else
+ vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+
+ rc = 0;
+ break;
+ default:
+ rc = -EOPNOTSUPP;
+ break;
+ }
+
+ return rc;
+}
+
static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
@@ -84,11 +167,17 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
switch (subcode) {
+ case 0:
+ case 1:
+ page_table_reset_pgste(current->mm, 0, TASK_SIZE);
+ return -EOPNOTSUPP;
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;
@@ -121,7 +210,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
* - gpr 4 contains the index on the bus (optionally)
*/
ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS,
- vcpu->run->s.regs.gprs[2],
+ vcpu->run->s.regs.gprs[2] & 0xffffffff,
8, &vcpu->run->s.regs.gprs[3],
vcpu->run->s.regs.gprs[4]);
@@ -137,7 +226,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
{
- int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+ int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -150,6 +239,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
return __diag_time_slice_end(vcpu);
case 0x9c:
return __diag_time_slice_end_directed(vcpu);
+ case 0x258:
+ return __diag_page_ref_service(vcpu);
case 0x308:
return __diag_ipl_functions(vcpu);
case 0x500:
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 5ddbbde6f65..eeb1ac7d8fa 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -112,6 +112,17 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
static int handle_prog(struct kvm_vcpu *vcpu)
{
vcpu->stat.exit_program_interruption++;
+
+ /* Restore ITDB to Program-Interruption TDB in guest memory */
+ if (IS_TE_ENABLED(vcpu) &&
+ !(current->thread.per_flags & PER_FLAG_NO_TE) &&
+ IS_ITDB_VALID(vcpu)) {
+ copy_to_guest(vcpu, TDB_ADDR, vcpu->arch.sie_block->itdba,
+ sizeof(struct kvm_s390_itdb));
+ memset((void *) vcpu->arch.sie_block->itdba, 0,
+ sizeof(struct kvm_s390_itdb));
+ }
+
trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc);
return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5f79d2d79ca..200a8f9390b 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,7 +1,7 @@
/*
* handling kvm guest interrupts
*
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2014
*
* 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)
@@ -13,6 +13,7 @@
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
#include <linux/hrtimer.h>
+#include <linux/mmu_context.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <asm/asm-offsets.h>
@@ -31,7 +32,7 @@ static int is_ioint(u64 type)
return ((type & 0xfffe0000u) != 0xfffe0000u);
}
-static int psw_extint_disabled(struct kvm_vcpu *vcpu)
+int psw_extint_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
}
@@ -78,11 +79,8 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
return 1;
return 0;
case KVM_S390_INT_SERVICE:
- if (psw_extint_disabled(vcpu))
- return 0;
- if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
- return 1;
- return 0;
+ case KVM_S390_INT_PFAULT_INIT:
+ case KVM_S390_INT_PFAULT_DONE:
case KVM_S390_INT_VIRTIO:
if (psw_extint_disabled(vcpu))
return 0;
@@ -117,14 +115,12 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
- BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
- BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}
@@ -150,6 +146,8 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
case KVM_S390_INT_EXTERNAL_CALL:
case KVM_S390_INT_EMERGENCY:
case KVM_S390_INT_SERVICE:
+ case KVM_S390_INT_PFAULT_INIT:
+ case KVM_S390_INT_PFAULT_DONE:
case KVM_S390_INT_VIRTIO:
if (psw_extint_disabled(vcpu))
__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
@@ -223,6 +221,30 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
rc |= put_guest(vcpu, inti->ext.ext_params,
(u32 __user *)__LC_EXT_PARAMS);
break;
+ case KVM_S390_INT_PFAULT_INIT:
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
+ inti->ext.ext_params2);
+ rc = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
+ rc |= put_guest(vcpu, 0x0600, (u16 __user *) __LC_EXT_CPU_ADDR);
+ rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ rc |= put_guest(vcpu, inti->ext.ext_params2,
+ (u64 __user *) __LC_EXT_PARAMS2);
+ break;
+ case KVM_S390_INT_PFAULT_DONE:
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
+ inti->ext.ext_params2);
+ rc = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
+ rc |= put_guest(vcpu, 0x0680, (u16 __user *) __LC_EXT_CPU_ADDR);
+ rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ rc |= put_guest(vcpu, inti->ext.ext_params2,
+ (u64 __user *) __LC_EXT_PARAMS2);
+ break;
case KVM_S390_INT_VIRTIO:
VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
inti->ext.ext_params, inti->ext.ext_params2);
@@ -357,7 +379,7 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
return 1;
}
-static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+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;
@@ -482,11 +504,26 @@ enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
struct kvm_vcpu *vcpu;
vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
+ vcpu->preempted = true;
tasklet_schedule(&vcpu->arch.tasklet);
return HRTIMER_NORESTART;
}
+void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ struct kvm_s390_interrupt_info *n, *inti = NULL;
+
+ spin_lock_bh(&li->lock);
+ list_for_each_entry_safe(inti, n, &li->list, list) {
+ list_del(&inti->list);
+ kfree(inti);
+ }
+ atomic_set(&li->active, 0);
+ spin_unlock_bh(&li->lock);
+}
+
void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -528,6 +565,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
list_for_each_entry_safe(inti, n, &fi->list, list) {
if (__interrupt_is_deliverable(vcpu, inti)) {
list_del(&inti->list);
+ fi->irq_count--;
deliver = 1;
break;
}
@@ -583,6 +621,7 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
if ((inti->type == KVM_S390_MCHK) &&
__interrupt_is_deliverable(vcpu, inti)) {
list_del(&inti->list);
+ fi->irq_count--;
deliver = 1;
break;
}
@@ -650,8 +689,10 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
inti = iter;
break;
}
- if (inti)
+ if (inti) {
list_del_init(&inti->list);
+ fi->irq_count--;
+ }
if (list_empty(&fi->list))
atomic_set(&fi->active, 0);
spin_unlock(&fi->lock);
@@ -659,53 +700,101 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
return inti;
}
-int kvm_s390_inject_vm(struct kvm *kvm,
- struct kvm_s390_interrupt *s390int)
+static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
{
struct kvm_s390_local_interrupt *li;
struct kvm_s390_float_interrupt *fi;
- struct kvm_s390_interrupt_info *inti, *iter;
+ struct kvm_s390_interrupt_info *iter;
+ struct kvm_vcpu *dst_vcpu = NULL;
int sigcpu;
+ int rc = 0;
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+ if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
+ rc = -EINVAL;
+ goto unlock_fi;
+ }
+ fi->irq_count++;
+ if (!is_ioint(inti->type)) {
+ list_add_tail(&inti->list, &fi->list);
+ } else {
+ u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
+ /* Keep I/O interrupts sorted in isc order. */
+ list_for_each_entry(iter, &fi->list, list) {
+ if (!is_ioint(iter->type))
+ continue;
+ if (int_word_to_isc_bits(iter->io.io_int_word)
+ <= isc_bits)
+ continue;
+ break;
+ }
+ list_add_tail(&inti->list, &iter->list);
+ }
+ atomic_set(&fi->active, 1);
+ sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
+ if (sigcpu == KVM_MAX_VCPUS) {
+ do {
+ sigcpu = fi->next_rr_cpu++;
+ if (sigcpu == KVM_MAX_VCPUS)
+ sigcpu = fi->next_rr_cpu = 0;
+ } while (kvm_get_vcpu(kvm, sigcpu) == NULL);
+ }
+ dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
+ li = &dst_vcpu->arch.local_int;
+ spin_lock_bh(&li->lock);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ if (waitqueue_active(li->wq))
+ wake_up_interruptible(li->wq);
+ kvm_get_vcpu(kvm, sigcpu)->preempted = true;
+ spin_unlock_bh(&li->lock);
+unlock_fi:
+ spin_unlock(&fi->lock);
+ mutex_unlock(&kvm->lock);
+ return rc;
+}
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+ struct kvm_s390_interrupt *s390int)
+{
+ struct kvm_s390_interrupt_info *inti;
inti = kzalloc(sizeof(*inti), GFP_KERNEL);
if (!inti)
return -ENOMEM;
- switch (s390int->type) {
+ inti->type = s390int->type;
+ switch (inti->type) {
case KVM_S390_INT_VIRTIO:
VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
s390int->parm, s390int->parm64);
- inti->type = s390int->type;
inti->ext.ext_params = s390int->parm;
inti->ext.ext_params2 = s390int->parm64;
break;
case KVM_S390_INT_SERVICE:
VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
- inti->type = s390int->type;
inti->ext.ext_params = s390int->parm;
break;
- case KVM_S390_PROGRAM_INT:
- case KVM_S390_SIGP_STOP:
- case KVM_S390_INT_EXTERNAL_CALL:
- case KVM_S390_INT_EMERGENCY:
- kfree(inti);
- return -EINVAL;
+ case KVM_S390_INT_PFAULT_DONE:
+ inti->type = s390int->type;
+ inti->ext.ext_params2 = s390int->parm64;
+ break;
case KVM_S390_MCHK:
VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
s390int->parm64);
- inti->type = s390int->type;
inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
inti->mchk.mcic = s390int->parm64;
break;
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- if (s390int->type & IOINT_AI_MASK)
+ if (inti->type & IOINT_AI_MASK)
VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
else
VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
s390int->type & IOINT_CSSID_MASK,
s390int->type & IOINT_SSID_MASK,
s390int->type & IOINT_SCHID_MASK);
- inti->type = s390int->type;
inti->io.subchannel_id = s390int->parm >> 16;
inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
inti->io.io_int_parm = s390int->parm64 >> 32;
@@ -718,43 +807,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
2);
- mutex_lock(&kvm->lock);
- fi = &kvm->arch.float_int;
- spin_lock(&fi->lock);
- if (!is_ioint(inti->type))
- list_add_tail(&inti->list, &fi->list);
- else {
- u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
-
- /* Keep I/O interrupts sorted in isc order. */
- list_for_each_entry(iter, &fi->list, list) {
- if (!is_ioint(iter->type))
- continue;
- if (int_word_to_isc_bits(iter->io.io_int_word)
- <= isc_bits)
- continue;
- break;
- }
- list_add_tail(&inti->list, &iter->list);
- }
- atomic_set(&fi->active, 1);
- sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
- if (sigcpu == KVM_MAX_VCPUS) {
- do {
- sigcpu = fi->next_rr_cpu++;
- if (sigcpu == KVM_MAX_VCPUS)
- sigcpu = fi->next_rr_cpu = 0;
- } while (fi->local_int[sigcpu] == NULL);
- }
- li = fi->local_int[sigcpu];
- spin_lock_bh(&li->lock);
- atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
- if (waitqueue_active(li->wq))
- wake_up_interruptible(li->wq);
- spin_unlock_bh(&li->lock);
- spin_unlock(&fi->lock);
- mutex_unlock(&kvm->lock);
- return 0;
+ return __inject_vm(kvm, inti);
}
int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
@@ -814,6 +867,10 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
inti->type = s390int->type;
inti->mchk.mcic = s390int->parm64;
break;
+ case KVM_S390_INT_PFAULT_INIT:
+ inti->type = s390int->type;
+ inti->ext.ext_params2 = s390int->parm64;
+ break;
case KVM_S390_INT_VIRTIO:
case KVM_S390_INT_SERVICE:
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
@@ -837,7 +894,528 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
+ vcpu->preempted = true;
spin_unlock_bh(&li->lock);
mutex_unlock(&vcpu->kvm->lock);
return 0;
}
+
+static void clear_floating_interrupts(struct kvm *kvm)
+{
+ struct kvm_s390_float_interrupt *fi;
+ struct kvm_s390_interrupt_info *n, *inti = NULL;
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+ list_for_each_entry_safe(inti, n, &fi->list, list) {
+ list_del(&inti->list);
+ kfree(inti);
+ }
+ fi->irq_count = 0;
+ atomic_set(&fi->active, 0);
+ spin_unlock(&fi->lock);
+ mutex_unlock(&kvm->lock);
+}
+
+static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
+ u8 *addr)
+{
+ struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
+ struct kvm_s390_irq irq = {0};
+
+ irq.type = inti->type;
+ switch (inti->type) {
+ case KVM_S390_INT_PFAULT_INIT:
+ case KVM_S390_INT_PFAULT_DONE:
+ case KVM_S390_INT_VIRTIO:
+ case KVM_S390_INT_SERVICE:
+ irq.u.ext = inti->ext;
+ break;
+ case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+ irq.u.io = inti->io;
+ break;
+ case KVM_S390_MCHK:
+ irq.u.mchk = inti->mchk;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (copy_to_user(uptr, &irq, sizeof(irq)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len)
+{
+ struct kvm_s390_interrupt_info *inti;
+ struct kvm_s390_float_interrupt *fi;
+ int ret = 0;
+ int n = 0;
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+
+ list_for_each_entry(inti, &fi->list, list) {
+ if (len < sizeof(struct kvm_s390_irq)) {
+ /* signal userspace to try again */
+ ret = -ENOMEM;
+ break;
+ }
+ ret = copy_irq_to_user(inti, buf);
+ if (ret)
+ break;
+ buf += sizeof(struct kvm_s390_irq);
+ len -= sizeof(struct kvm_s390_irq);
+ n++;
+ }
+
+ spin_unlock(&fi->lock);
+ mutex_unlock(&kvm->lock);
+
+ return ret < 0 ? ret : n;
+}
+
+static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ int r;
+
+ switch (attr->group) {
+ case KVM_DEV_FLIC_GET_ALL_IRQS:
+ r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr,
+ attr->attr);
+ break;
+ default:
+ r = -EINVAL;
+ }
+
+ return r;
+}
+
+static inline int copy_irq_from_user(struct kvm_s390_interrupt_info *inti,
+ u64 addr)
+{
+ struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
+ void *target = NULL;
+ void __user *source;
+ u64 size;
+
+ if (get_user(inti->type, (u64 __user *)addr))
+ return -EFAULT;
+
+ switch (inti->type) {
+ case KVM_S390_INT_PFAULT_INIT:
+ case KVM_S390_INT_PFAULT_DONE:
+ case KVM_S390_INT_VIRTIO:
+ case KVM_S390_INT_SERVICE:
+ target = (void *) &inti->ext;
+ source = &uptr->u.ext;
+ size = sizeof(inti->ext);
+ break;
+ case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+ target = (void *) &inti->io;
+ source = &uptr->u.io;
+ size = sizeof(inti->io);
+ break;
+ case KVM_S390_MCHK:
+ target = (void *) &inti->mchk;
+ source = &uptr->u.mchk;
+ size = sizeof(inti->mchk);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (copy_from_user(target, source, size))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int enqueue_floating_irq(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ struct kvm_s390_interrupt_info *inti = NULL;
+ int r = 0;
+ int len = attr->attr;
+
+ if (len % sizeof(struct kvm_s390_irq) != 0)
+ return -EINVAL;
+ else if (len > KVM_S390_FLIC_MAX_BUFFER)
+ return -EINVAL;
+
+ while (len >= sizeof(struct kvm_s390_irq)) {
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return -ENOMEM;
+
+ r = copy_irq_from_user(inti, attr->addr);
+ if (r) {
+ kfree(inti);
+ return r;
+ }
+ r = __inject_vm(dev->kvm, inti);
+ if (r) {
+ kfree(inti);
+ return r;
+ }
+ len -= sizeof(struct kvm_s390_irq);
+ attr->addr += sizeof(struct kvm_s390_irq);
+ }
+
+ return r;
+}
+
+static struct s390_io_adapter *get_io_adapter(struct kvm *kvm, unsigned int id)
+{
+ if (id >= MAX_S390_IO_ADAPTERS)
+ return NULL;
+ return kvm->arch.adapters[id];
+}
+
+static int register_io_adapter(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ struct s390_io_adapter *adapter;
+ struct kvm_s390_io_adapter adapter_info;
+
+ if (copy_from_user(&adapter_info,
+ (void __user *)attr->addr, sizeof(adapter_info)))
+ return -EFAULT;
+
+ if ((adapter_info.id >= MAX_S390_IO_ADAPTERS) ||
+ (dev->kvm->arch.adapters[adapter_info.id] != NULL))
+ return -EINVAL;
+
+ adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
+ if (!adapter)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&adapter->maps);
+ init_rwsem(&adapter->maps_lock);
+ atomic_set(&adapter->nr_maps, 0);
+ adapter->id = adapter_info.id;
+ adapter->isc = adapter_info.isc;
+ adapter->maskable = adapter_info.maskable;
+ adapter->masked = false;
+ adapter->swap = adapter_info.swap;
+ dev->kvm->arch.adapters[adapter->id] = adapter;
+
+ return 0;
+}
+
+int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked)
+{
+ int ret;
+ struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
+
+ if (!adapter || !adapter->maskable)
+ return -EINVAL;
+ ret = adapter->masked;
+ adapter->masked = masked;
+ return ret;
+}
+
+static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
+{
+ struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
+ struct s390_map_info *map;
+ int ret;
+
+ if (!adapter || !addr)
+ return -EINVAL;
+
+ map = kzalloc(sizeof(*map), GFP_KERNEL);
+ if (!map) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ INIT_LIST_HEAD(&map->list);
+ map->guest_addr = addr;
+ map->addr = gmap_translate(addr, kvm->arch.gmap);
+ if (map->addr == -EFAULT) {
+ ret = -EFAULT;
+ goto out;
+ }
+ ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
+ if (ret < 0)
+ goto out;
+ BUG_ON(ret != 1);
+ down_write(&adapter->maps_lock);
+ if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) {
+ list_add_tail(&map->list, &adapter->maps);
+ ret = 0;
+ } else {
+ put_page(map->page);
+ ret = -EINVAL;
+ }
+ up_write(&adapter->maps_lock);
+out:
+ if (ret)
+ kfree(map);
+ return ret;
+}
+
+static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
+{
+ struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
+ struct s390_map_info *map, *tmp;
+ int found = 0;
+
+ if (!adapter || !addr)
+ return -EINVAL;
+
+ down_write(&adapter->maps_lock);
+ list_for_each_entry_safe(map, tmp, &adapter->maps, list) {
+ if (map->guest_addr == addr) {
+ found = 1;
+ atomic_dec(&adapter->nr_maps);
+ list_del(&map->list);
+ put_page(map->page);
+ kfree(map);
+ break;
+ }
+ }
+ up_write(&adapter->maps_lock);
+
+ return found ? 0 : -EINVAL;
+}
+
+void kvm_s390_destroy_adapters(struct kvm *kvm)
+{
+ int i;
+ struct s390_map_info *map, *tmp;
+
+ for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) {
+ if (!kvm->arch.adapters[i])
+ continue;
+ list_for_each_entry_safe(map, tmp,
+ &kvm->arch.adapters[i]->maps, list) {
+ list_del(&map->list);
+ put_page(map->page);
+ kfree(map);
+ }
+ kfree(kvm->arch.adapters[i]);
+ }
+}
+
+static int modify_io_adapter(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ struct kvm_s390_io_adapter_req req;
+ struct s390_io_adapter *adapter;
+ int ret;
+
+ if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
+ return -EFAULT;
+
+ adapter = get_io_adapter(dev->kvm, req.id);
+ if (!adapter)
+ return -EINVAL;
+ switch (req.type) {
+ case KVM_S390_IO_ADAPTER_MASK:
+ ret = kvm_s390_mask_adapter(dev->kvm, req.id, req.mask);
+ if (ret > 0)
+ ret = 0;
+ break;
+ case KVM_S390_IO_ADAPTER_MAP:
+ ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr);
+ break;
+ case KVM_S390_IO_ADAPTER_UNMAP:
+ ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ int r = 0;
+ unsigned int i;
+ struct kvm_vcpu *vcpu;
+
+ switch (attr->group) {
+ case KVM_DEV_FLIC_ENQUEUE:
+ r = enqueue_floating_irq(dev, attr);
+ break;
+ case KVM_DEV_FLIC_CLEAR_IRQS:
+ r = 0;
+ clear_floating_interrupts(dev->kvm);
+ break;
+ case KVM_DEV_FLIC_APF_ENABLE:
+ dev->kvm->arch.gmap->pfault_enabled = 1;
+ break;
+ case KVM_DEV_FLIC_APF_DISABLE_WAIT:
+ dev->kvm->arch.gmap->pfault_enabled = 0;
+ /*
+ * Make sure no async faults are in transition when
+ * clearing the queues. So we don't need to worry
+ * about late coming workers.
+ */
+ synchronize_srcu(&dev->kvm->srcu);
+ kvm_for_each_vcpu(i, vcpu, dev->kvm)
+ kvm_clear_async_pf_completion_queue(vcpu);
+ break;
+ case KVM_DEV_FLIC_ADAPTER_REGISTER:
+ r = register_io_adapter(dev, attr);
+ break;
+ case KVM_DEV_FLIC_ADAPTER_MODIFY:
+ r = modify_io_adapter(dev, attr);
+ break;
+ default:
+ r = -EINVAL;
+ }
+
+ return r;
+}
+
+static int flic_create(struct kvm_device *dev, u32 type)
+{
+ if (!dev)
+ return -EINVAL;
+ if (dev->kvm->arch.flic)
+ return -EINVAL;
+ dev->kvm->arch.flic = dev;
+ return 0;
+}
+
+static void flic_destroy(struct kvm_device *dev)
+{
+ dev->kvm->arch.flic = NULL;
+ kfree(dev);
+}
+
+/* s390 floating irq controller (flic) */
+struct kvm_device_ops kvm_flic_ops = {
+ .name = "kvm-flic",
+ .get_attr = flic_get_attr,
+ .set_attr = flic_set_attr,
+ .create = flic_create,
+ .destroy = flic_destroy,
+};
+
+static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
+{
+ unsigned long bit;
+
+ bit = bit_nr + (addr % PAGE_SIZE) * 8;
+
+ return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
+}
+
+static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter,
+ u64 addr)
+{
+ struct s390_map_info *map;
+
+ if (!adapter)
+ return NULL;
+
+ list_for_each_entry(map, &adapter->maps, list) {
+ if (map->guest_addr == addr)
+ return map;
+ }
+ return NULL;
+}
+
+static int adapter_indicators_set(struct kvm *kvm,
+ struct s390_io_adapter *adapter,
+ struct kvm_s390_adapter_int *adapter_int)
+{
+ unsigned long bit;
+ int summary_set, idx;
+ struct s390_map_info *info;
+ void *map;
+
+ info = get_map_info(adapter, adapter_int->ind_addr);
+ if (!info)
+ return -1;
+ map = page_address(info->page);
+ bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap);
+ set_bit(bit, map);
+ idx = srcu_read_lock(&kvm->srcu);
+ mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
+ set_page_dirty_lock(info->page);
+ info = get_map_info(adapter, adapter_int->summary_addr);
+ if (!info) {
+ srcu_read_unlock(&kvm->srcu, idx);
+ return -1;
+ }
+ map = page_address(info->page);
+ bit = get_ind_bit(info->addr, adapter_int->summary_offset,
+ adapter->swap);
+ summary_set = test_and_set_bit(bit, map);
+ mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
+ set_page_dirty_lock(info->page);
+ srcu_read_unlock(&kvm->srcu, idx);
+ return summary_set ? 0 : 1;
+}
+
+/*
+ * < 0 - not injected due to error
+ * = 0 - coalesced, summary indicator already active
+ * > 0 - injected interrupt
+ */
+static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ int ret;
+ struct s390_io_adapter *adapter;
+
+ /* We're only interested in the 0->1 transition. */
+ if (!level)
+ return 0;
+ adapter = get_io_adapter(kvm, e->adapter.adapter_id);
+ if (!adapter)
+ return -1;
+ down_read(&adapter->maps_lock);
+ ret = adapter_indicators_set(kvm, adapter, &e->adapter);
+ up_read(&adapter->maps_lock);
+ if ((ret > 0) && !adapter->masked) {
+ struct kvm_s390_interrupt s390int = {
+ .type = KVM_S390_INT_IO(1, 0, 0, 0),
+ .parm = 0,
+ .parm64 = (adapter->isc << 27) | 0x80000000,
+ };
+ ret = kvm_s390_inject_vm(kvm, &s390int);
+ if (ret == 0)
+ ret = 1;
+ }
+ return ret;
+}
+
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+ struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+{
+ int ret;
+
+ switch (ue->type) {
+ case KVM_IRQ_ROUTING_S390_ADAPTER:
+ e->set = set_adapter_int;
+ e->adapter.summary_addr = ue->u.adapter.summary_addr;
+ e->adapter.ind_addr = ue->u.adapter.ind_addr;
+ e->adapter.summary_offset = ue->u.adapter.summary_offset;
+ e->adapter.ind_offset = ue->u.adapter.ind_offset;
+ e->adapter.adapter_id = ue->u.adapter.adapter_id;
+ ret = 0;
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status)
+{
+ return -EINVAL;
+}
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
new file mode 100644
index 00000000000..d98e4159643
--- /dev/null
+++ b/arch/s390/kvm/irq.h
@@ -0,0 +1,22 @@
+/*
+ * s390 irqchip routines
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ */
+#ifndef __KVM_IRQ_H
+#define __KVM_IRQ_H
+
+#include <linux/kvm_host.h>
+
+static inline int irqchip_in_kernel(struct kvm *kvm)
+{
+ return 1;
+}
+
+#endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 569494e01ec..b3ecb8f5b6c 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) },
@@ -152,11 +153,14 @@ int kvm_dev_ioctl_check_extension(long ext)
#ifdef CONFIG_KVM_S390_UCONTROL
case KVM_CAP_S390_UCONTROL:
#endif
+ case KVM_CAP_ASYNC_PF:
case KVM_CAP_SYNC_REGS:
case KVM_CAP_ONE_REG:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_S390_CSS_SUPPORT:
case KVM_CAP_IOEVENTFD:
+ case KVM_CAP_DEVICE_CTRL:
+ case KVM_CAP_ENABLE_CAP_VM:
r = 1;
break;
case KVM_CAP_NR_VCPUS:
@@ -185,6 +189,25 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
return 0;
}
+static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
+{
+ int r;
+
+ if (cap->flags)
+ return -EINVAL;
+
+ switch (cap->cap) {
+ case KVM_CAP_S390_IRQCHIP:
+ kvm->arch.use_irqchip = 1;
+ r = 0;
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -202,6 +225,26 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_s390_inject_vm(kvm, &s390int);
break;
}
+ case KVM_ENABLE_CAP: {
+ struct kvm_enable_cap cap;
+ r = -EFAULT;
+ if (copy_from_user(&cap, argp, sizeof(cap)))
+ break;
+ r = kvm_vm_ioctl_enable_cap(kvm, &cap);
+ break;
+ }
+ case KVM_CREATE_IRQCHIP: {
+ struct kvm_irq_routing_entry routing;
+
+ r = -EINVAL;
+ if (kvm->arch.use_irqchip) {
+ /* Set up dummy routing. */
+ memset(&routing, 0, sizeof(routing));
+ kvm_set_irq_routing(kvm, &routing, 0, 0);
+ r = 0;
+ }
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -213,6 +256,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int rc;
char debug_name[16];
+ static unsigned long sca_offset;
rc = -EINVAL;
#ifdef CONFIG_KVM_S390_UCONTROL
@@ -234,6 +278,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
if (!kvm->arch.sca)
goto out_err;
+ spin_lock(&kvm_lock);
+ sca_offset = (sca_offset + 16) & 0x7f0;
+ kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+ spin_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
@@ -254,9 +302,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (!kvm->arch.gmap)
goto out_nogmap;
kvm->arch.gmap->private = kvm;
+ kvm->arch.gmap->pfault_enabled = 0;
}
kvm->arch.css_support = 0;
+ kvm->arch.use_irqchip = 0;
return 0;
out_nogmap:
@@ -271,6 +321,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 3, "%s", "free cpu");
trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
+ kvm_clear_async_pf_completion_queue(vcpu);
if (!kvm_is_ucontrol(vcpu->kvm)) {
clear_bit(63 - vcpu->vcpu_id,
(unsigned long *) &vcpu->kvm->arch.sca->mcn);
@@ -283,7 +334,11 @@ 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);
}
@@ -315,11 +370,14 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
debug_unregister(kvm->arch.dbf);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
+ kvm_s390_destroy_adapters(kvm);
}
/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+ kvm_clear_async_pf_completion_queue(vcpu);
if (kvm_is_ucontrol(vcpu->kvm)) {
vcpu->arch.gmap = gmap_alloc(current->mm);
if (!vcpu->arch.gmap)
@@ -380,7 +438,11 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
vcpu->arch.guest_fpregs.fpc = 0;
asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
vcpu->arch.sie_block->gbea = 1;
+ vcpu->arch.sie_block->pp = 0;
+ vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+ kvm_clear_async_pf_completion_queue(vcpu);
atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_local_irqs(vcpu);
}
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
@@ -390,14 +452,27 @@ 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 |
CPUSTAT_GED);
vcpu->arch.sie_block->ecb = 6;
+ if (test_vfacility(50) && test_vfacility(73))
+ vcpu->arch.sie_block->ecb |= 0x10;
+
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);
@@ -411,6 +486,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
unsigned int id)
{
struct kvm_vcpu *vcpu;
+ struct sie_page *sie_page;
int rc = -EINVAL;
if (id >= KVM_MAX_VCPUS)
@@ -422,12 +498,13 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
if (!vcpu)
goto out;
- vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
- get_zeroed_page(GFP_KERNEL);
-
- if (!vcpu->arch.sie_block)
+ sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
+ if (!sie_page)
goto out_free_cpu;
+ vcpu->arch.sie_block = &sie_page->sie_block;
+ vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
+
vcpu->arch.sie_block->icpua = id;
if (!kvm_is_ucontrol(kvm)) {
if (!kvm->arch.sca) {
@@ -446,11 +523,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
spin_lock_init(&vcpu->arch.local_int.lock);
INIT_LIST_HEAD(&vcpu->arch.local_int.list);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
- spin_lock(&kvm->arch.float_int.lock);
- kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
vcpu->arch.local_int.wq = &vcpu->wq;
vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
- spin_unlock(&kvm->arch.float_int.lock);
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
@@ -470,9 +544,7 @@ out:
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
- /* kvm common code refers to this, but never calls it */
- BUG();
- return 0;
+ return kvm_cpu_has_interrupt(vcpu);
}
void s390_vcpu_block(struct kvm_vcpu *vcpu)
@@ -548,6 +620,26 @@ static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
r = put_user(vcpu->arch.sie_block->ckc,
(u64 __user *)reg->addr);
break;
+ case KVM_REG_S390_PFTOKEN:
+ r = put_user(vcpu->arch.pfault_token,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_PFCOMPARE:
+ r = put_user(vcpu->arch.pfault_compare,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_PFSELECT:
+ r = put_user(vcpu->arch.pfault_select,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_PP:
+ r = put_user(vcpu->arch.sie_block->pp,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_GBEA:
+ r = put_user(vcpu->arch.sie_block->gbea,
+ (u64 __user *)reg->addr);
+ break;
default:
break;
}
@@ -577,6 +669,26 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
r = get_user(vcpu->arch.sie_block->ckc,
(u64 __user *)reg->addr);
break;
+ case KVM_REG_S390_PFTOKEN:
+ r = get_user(vcpu->arch.pfault_token,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_PFCOMPARE:
+ r = get_user(vcpu->arch.pfault_compare,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_PFSELECT:
+ r = get_user(vcpu->arch.pfault_select,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_PP:
+ r = get_user(vcpu->arch.sie_block->pp,
+ (u64 __user *)reg->addr);
+ break;
+ case KVM_REG_S390_GBEA:
+ r = get_user(vcpu->arch.sie_block->gbea,
+ (u64 __user *)reg->addr);
+ break;
default:
break;
}
@@ -695,10 +807,100 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
return 0;
}
+static long kvm_arch_fault_in_sync(struct kvm_vcpu *vcpu)
+{
+ long rc;
+ hva_t fault = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
+ struct mm_struct *mm = current->mm;
+ down_read(&mm->mmap_sem);
+ rc = get_user_pages(current, mm, fault, 1, 1, 0, NULL, NULL);
+ up_read(&mm->mmap_sem);
+ return rc;
+}
+
+static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
+ unsigned long token)
+{
+ struct kvm_s390_interrupt inti;
+ inti.parm64 = token;
+
+ if (start_token) {
+ inti.type = KVM_S390_INT_PFAULT_INIT;
+ WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
+ } else {
+ inti.type = KVM_S390_INT_PFAULT_DONE;
+ WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
+ }
+}
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ trace_kvm_s390_pfault_init(vcpu, work->arch.pfault_token);
+ __kvm_inject_pfault_token(vcpu, true, work->arch.pfault_token);
+}
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ trace_kvm_s390_pfault_done(vcpu, work->arch.pfault_token);
+ __kvm_inject_pfault_token(vcpu, false, work->arch.pfault_token);
+}
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ /* s390 will always inject the page directly */
+}
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
+{
+ /*
+ * s390 will always inject the page directly,
+ * but we still want check_async_completion to cleanup
+ */
+ return true;
+}
+
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
+{
+ hva_t hva;
+ struct kvm_arch_async_pf arch;
+ int rc;
+
+ if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
+ return 0;
+ if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) !=
+ vcpu->arch.pfault_compare)
+ return 0;
+ if (psw_extint_disabled(vcpu))
+ return 0;
+ if (kvm_cpu_has_interrupt(vcpu))
+ return 0;
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
+ return 0;
+ if (!vcpu->arch.gmap->pfault_enabled)
+ return 0;
+
+ hva = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
+ if (copy_from_guest(vcpu, &arch.pfault_token, vcpu->arch.pfault_token, 8))
+ return 0;
+
+ rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
+ return rc;
+}
+
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
{
int rc, cpuflags;
+ /*
+ * On s390 notifications for arriving pages will be delivered directly
+ * to the guest but the house keeping for completed pfaults is
+ * handled outside the worker.
+ */
+ kvm_check_async_pf_completion(vcpu);
+
memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
if (need_resched())
@@ -724,7 +926,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
- int rc;
+ int rc = -1;
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
@@ -732,21 +934,33 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
if (exit_reason >= 0) {
rc = 0;
- } else {
- if (kvm_is_ucontrol(vcpu->kvm)) {
- rc = SIE_INTERCEPT_UCONTROL;
- } else {
- VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
- trace_kvm_s390_sie_fault(vcpu);
- rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
- }
+ } else if (kvm_is_ucontrol(vcpu->kvm)) {
+ vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
+ vcpu->run->s390_ucontrol.trans_exc_code =
+ current->thread.gmap_addr;
+ vcpu->run->s390_ucontrol.pgm_code = 0x10;
+ rc = -EREMOTE;
+
+ } else if (current->thread.gmap_pfault) {
+ trace_kvm_s390_major_guest_pfault(vcpu);
+ current->thread.gmap_pfault = 0;
+ if (kvm_arch_setup_async_pf(vcpu) ||
+ (kvm_arch_fault_in_sync(vcpu) >= 0))
+ rc = 0;
+ }
+
+ if (rc == -1) {
+ VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+ trace_kvm_s390_sie_fault(vcpu);
+ rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
}
memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
if (rc == 0) {
if (kvm_is_ucontrol(vcpu->kvm))
- rc = -EOPNOTSUPP;
+ /* Don't exit for host interrupts. */
+ rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
else
rc = kvm_handle_sie_intercept(vcpu);
}
@@ -754,6 +968,16 @@ 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;
@@ -799,8 +1023,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
- BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
-
switch (kvm_run->exit_reason) {
case KVM_EXIT_S390_SIEIC:
case KVM_EXIT_UNKNOWN:
@@ -833,16 +1055,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rc = -EINTR;
}
-#ifdef CONFIG_KVM_S390_UCONTROL
- if (rc == SIE_INTERCEPT_UCONTROL) {
- kvm_run->exit_reason = KVM_EXIT_S390_UCONTROL;
- kvm_run->s390_ucontrol.trans_exc_code =
- current->thread.gmap_addr;
- kvm_run->s390_ucontrol.pgm_code = 0x10;
- rc = 0;
- }
-#endif
-
if (rc == -EOPNOTSUPP) {
/* intercept cannot be handled in-kernel, prepare kvm-run */
kvm_run->exit_reason = KVM_EXIT_S390_SIEIC;
@@ -885,10 +1097,11 @@ static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
* KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
* KVM_S390_STORE_STATUS_PREFIXED: -> prefix
*/
-int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr)
{
unsigned char archmode = 1;
int prefix;
+ u64 clkcomp;
if (addr == KVM_S390_STORE_STATUS_NOADDR) {
if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
@@ -903,15 +1116,6 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
} else
prefix = 0;
- /*
- * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
- * copying in vcpu load/put. Lets update our copies before we save
- * it into the save area
- */
- save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
- save_fp_regs(vcpu->arch.guest_fpregs.fprs);
- save_access_regs(vcpu->run->s.regs.acrs);
-
if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
vcpu->arch.guest_fpregs.fprs, 128, prefix))
return -EFAULT;
@@ -941,8 +1145,9 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
&vcpu->arch.sie_block->cputm, 8, prefix))
return -EFAULT;
+ clkcomp = vcpu->arch.sie_block->ckc >> 8;
if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
- &vcpu->arch.sie_block->ckc, 8, prefix))
+ &clkcomp, 8, prefix))
return -EFAULT;
if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
@@ -956,6 +1161,20 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
return 0;
}
+int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+ /*
+ * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
+ * copying in vcpu load/put. Lets update our copies before we save
+ * it into the save area
+ */
+ save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
+ save_fp_regs(vcpu->arch.guest_fpregs.fprs);
+ save_access_regs(vcpu->run->s.regs.acrs);
+
+ return kvm_s390_store_status_unloaded(vcpu, addr);
+}
+
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
struct kvm_enable_cap *cap)
{
@@ -1183,8 +1402,8 @@ static int __init kvm_s390_init(void)
return -ENOMEM;
}
memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
- vfacilities[0] &= 0xff82fff3f47c0000UL;
- vfacilities[1] &= 0x001c000000000000UL;
+ vfacilities[0] &= 0xff82fff3f4fc2000UL;
+ vfacilities[1] &= 0x005c000000000000UL;
return 0;
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index b44912a3294..3c1e2274d9e 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,18 +19,19 @@
#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);
/* declare vfacilities extern */
extern unsigned long *vfacilities;
-/* negativ values are error codes, positive values for internal conditions */
-#define SIE_INTERCEPT_UCONTROL (1<<0)
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+/* Transactional Memory Execution related macros */
+#define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & 0x10))
+#define TDB_ADDR 0x1800UL
+#define TDB_FORMAT1 1
+#define IS_ITDB_VALID(vcpu) ((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1))
+
#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
do { \
debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \
@@ -128,14 +129,15 @@ enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
void kvm_s390_tasklet(unsigned long parm);
void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
+void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu);
int __must_check kvm_s390_inject_vm(struct kvm *kvm,
struct kvm_s390_interrupt *s390int);
int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
struct kvm_s390_interrupt *s390int);
int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
-int __must_check kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
u64 cr6, u64 schid);
+int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
/* implemented in priv.c */
int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
@@ -150,13 +152,20 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu);
int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
/* implemented in kvm-s390.c */
-int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu,
- unsigned long addr);
+int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
+int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
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);
+/* implemented in interrupt.c */
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int psw_extint_disabled(struct kvm_vcpu *vcpu);
+void kvm_s390_destroy_adapters(struct kvm *kvm);
+
#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 2440602e6df..476e9e218f4 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -197,7 +197,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
if (addr & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
cc = 0;
- inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6], 0);
+ inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0);
if (!inti)
goto no_interrupt;
cc = 1;
@@ -275,7 +275,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP;
} else {
/*
- * Set condition code 3 to stop the guest from issueing channel
+ * Set condition code 3 to stop the guest from issuing channel
* I/O instructions.
*/
kvm_s390_set_psw_cc(vcpu, 3);
@@ -396,15 +396,10 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
{
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
int cpus = 0;
int n;
- spin_lock(&fi->lock);
- for (n = 0; n < KVM_MAX_VCPUS; n++)
- if (fi->local_int[n])
- cpus++;
- spin_unlock(&fi->lock);
+ cpus = atomic_read(&vcpu->kvm->online_vcpus);
/* deal with other level 3 hypervisors */
if (stsi(mem, 3, 2, 2))
@@ -636,9 +631,49 @@ 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,
- [0x9c] = handle_io_inst,
+ [0xab] = handle_essa,
[0xaf] = handle_pfmf,
};
@@ -731,7 +766,6 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
static const intercept_handler_t eb_handlers[256] = {
[0x2f] = handle_lctlg,
- [0x8a] = handle_io_inst,
};
int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index bec398c57ac..26caeb530a7 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -1,7 +1,7 @@
/*
* handling interprocessor communication
*
- * Copyright IBM Corp. 2008, 2009
+ * Copyright IBM Corp. 2008, 2013
*
* 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)
@@ -23,29 +23,30 @@
static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
u64 *reg)
{
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_local_interrupt *li;
+ struct kvm_vcpu *dst_vcpu = NULL;
+ int cpuflags;
int rc;
if (cpu_addr >= KVM_MAX_VCPUS)
return SIGP_CC_NOT_OPERATIONAL;
- spin_lock(&fi->lock);
- if (fi->local_int[cpu_addr] == NULL)
- rc = SIGP_CC_NOT_OPERATIONAL;
- else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
- & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+ li = &dst_vcpu->arch.local_int;
+
+ cpuflags = atomic_read(li->cpuflags);
+ if (!(cpuflags & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
else {
*reg &= 0xffffffff00000000UL;
- if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
- & CPUSTAT_ECALL_PEND)
+ if (cpuflags & CPUSTAT_ECALL_PEND)
*reg |= SIGP_STATUS_EXT_CALL_PENDING;
- if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
- & CPUSTAT_STOPPED)
+ if (cpuflags & CPUSTAT_STOPPED)
*reg |= SIGP_STATUS_STOPPED;
rc = SIGP_CC_STATUS_STORED;
}
- spin_unlock(&fi->lock);
VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
return rc;
@@ -53,12 +54,13 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
{
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_local_interrupt *li;
struct kvm_s390_interrupt_info *inti;
- int rc;
+ struct kvm_vcpu *dst_vcpu = NULL;
- if (cpu_addr >= KVM_MAX_VCPUS)
+ if (cpu_addr < KVM_MAX_VCPUS)
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
return SIGP_CC_NOT_OPERATIONAL;
inti = kzalloc(sizeof(*inti), GFP_KERNEL);
@@ -68,13 +70,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
inti->type = KVM_S390_INT_EMERGENCY;
inti->emerg.code = vcpu->vcpu_id;
- spin_lock(&fi->lock);
- li = fi->local_int[cpu_addr];
- if (li == NULL) {
- rc = SIGP_CC_NOT_OPERATIONAL;
- kfree(inti);
- goto unlock;
- }
+ li = &dst_vcpu->arch.local_int;
spin_lock_bh(&li->lock);
list_add_tail(&inti->list, &li->list);
atomic_set(&li->active, 1);
@@ -82,21 +78,51 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
if (waitqueue_active(li->wq))
wake_up_interruptible(li->wq);
spin_unlock_bh(&li->lock);
- rc = SIGP_CC_ORDER_CODE_ACCEPTED;
VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
-unlock:
- spin_unlock(&fi->lock);
- return rc;
+
+ return SIGP_CC_ORDER_CODE_ACCEPTED;
+}
+
+static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr,
+ u16 asn, u64 *reg)
+{
+ struct kvm_vcpu *dst_vcpu = NULL;
+ const u64 psw_int_mask = PSW_MASK_IO | PSW_MASK_EXT;
+ u16 p_asn, s_asn;
+ psw_t *psw;
+ u32 flags;
+
+ if (cpu_addr < KVM_MAX_VCPUS)
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+ flags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags);
+ psw = &dst_vcpu->arch.sie_block->gpsw;
+ p_asn = dst_vcpu->arch.sie_block->gcr[4] & 0xffff; /* Primary ASN */
+ s_asn = dst_vcpu->arch.sie_block->gcr[3] & 0xffff; /* Secondary ASN */
+
+ /* Deliver the emergency signal? */
+ if (!(flags & CPUSTAT_STOPPED)
+ || (psw->mask & psw_int_mask) != psw_int_mask
+ || ((flags & CPUSTAT_WAIT) && psw->addr != 0)
+ || (!(flags & CPUSTAT_WAIT) && (asn == p_asn || asn == s_asn))) {
+ return __sigp_emergency(vcpu, cpu_addr);
+ } else {
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STATUS_INCORRECT_STATE;
+ return SIGP_CC_STATUS_STORED;
+ }
}
static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
{
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_local_interrupt *li;
struct kvm_s390_interrupt_info *inti;
- int rc;
+ struct kvm_vcpu *dst_vcpu = NULL;
- if (cpu_addr >= KVM_MAX_VCPUS)
+ if (cpu_addr < KVM_MAX_VCPUS)
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
return SIGP_CC_NOT_OPERATIONAL;
inti = kzalloc(sizeof(*inti), GFP_KERNEL);
@@ -106,13 +132,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
inti->type = KVM_S390_INT_EXTERNAL_CALL;
inti->extcall.code = vcpu->vcpu_id;
- spin_lock(&fi->lock);
- li = fi->local_int[cpu_addr];
- if (li == NULL) {
- rc = SIGP_CC_NOT_OPERATIONAL;
- kfree(inti);
- goto unlock;
- }
+ li = &dst_vcpu->arch.local_int;
spin_lock_bh(&li->lock);
list_add_tail(&inti->list, &li->list);
atomic_set(&li->active, 1);
@@ -120,16 +140,15 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
if (waitqueue_active(li->wq))
wake_up_interruptible(li->wq);
spin_unlock_bh(&li->lock);
- rc = SIGP_CC_ORDER_CODE_ACCEPTED;
VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr);
-unlock:
- spin_unlock(&fi->lock);
- return rc;
+
+ return SIGP_CC_ORDER_CODE_ACCEPTED;
}
static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
{
struct kvm_s390_interrupt_info *inti;
+ int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
inti = kzalloc(sizeof(*inti), GFP_ATOMIC);
if (!inti)
@@ -139,6 +158,8 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
spin_lock_bh(&li->lock);
if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
kfree(inti);
+ if ((action & ACTION_STORE_ON_STOP) != 0)
+ rc = -ESHUTDOWN;
goto out;
}
list_add_tail(&inti->list, &li->list);
@@ -150,42 +171,43 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
out:
spin_unlock_bh(&li->lock);
- return SIGP_CC_ORDER_CODE_ACCEPTED;
+ return rc;
}
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;
+ struct kvm_vcpu *dst_vcpu = NULL;
int rc;
if (cpu_addr >= KVM_MAX_VCPUS)
return SIGP_CC_NOT_OPERATIONAL;
- spin_lock(&fi->lock);
- li = fi->local_int[cpu_addr];
- if (li == NULL) {
- rc = SIGP_CC_NOT_OPERATIONAL;
- goto unlock;
- }
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+ li = &dst_vcpu->arch.local_int;
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);
+ if ((action & ACTION_STORE_ON_STOP) != 0 && rc == -ESHUTDOWN) {
+ /* If the CPU has already been stopped, we still have
+ * to save the status when doing stop-and-store. This
+ * has to be done after unlocking all spinlocks. */
+ rc = kvm_s390_store_status_unloaded(dst_vcpu,
+ KVM_S390_STORE_STATUS_NOADDR);
+ }
+
+ return rc;
}
static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
{
int rc;
+ unsigned int i;
+ struct kvm_vcpu *v;
switch (parameter & 0xff) {
case 0:
@@ -193,6 +215,11 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
break;
case 1:
case 2:
+ kvm_for_each_vcpu(i, v, vcpu->kvm) {
+ v->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+ kvm_clear_async_pf_completion_queue(v);
+ }
+
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
break;
default:
@@ -204,12 +231,18 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
u64 *reg)
{
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
- struct kvm_s390_local_interrupt *li = NULL;
+ struct kvm_s390_local_interrupt *li;
+ struct kvm_vcpu *dst_vcpu = NULL;
struct kvm_s390_interrupt_info *inti;
int rc;
u8 tmp;
+ if (cpu_addr < KVM_MAX_VCPUS)
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+ li = &dst_vcpu->arch.local_int;
+
/* make sure that the new value is valid memory */
address = address & 0x7fffe000u;
if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
@@ -223,18 +256,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
if (!inti)
return SIGP_CC_BUSY;
- spin_lock(&fi->lock);
- if (cpu_addr < KVM_MAX_VCPUS)
- li = fi->local_int[cpu_addr];
-
- if (li == NULL) {
- *reg &= 0xffffffff00000000UL;
- *reg |= SIGP_STATUS_INCORRECT_STATE;
- rc = SIGP_CC_STATUS_STORED;
- kfree(inti);
- goto out_fi;
- }
-
spin_lock_bh(&li->lock);
/* cpu must be in stopped state */
if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
@@ -257,36 +278,63 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
out_li:
spin_unlock_bh(&li->lock);
-out_fi:
- spin_unlock(&fi->lock);
+ return rc;
+}
+
+static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id,
+ u32 addr, u64 *reg)
+{
+ struct kvm_vcpu *dst_vcpu = NULL;
+ int flags;
+ int rc;
+
+ if (cpu_id < KVM_MAX_VCPUS)
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_id);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+
+ spin_lock_bh(&dst_vcpu->arch.local_int.lock);
+ flags = atomic_read(dst_vcpu->arch.local_int.cpuflags);
+ spin_unlock_bh(&dst_vcpu->arch.local_int.lock);
+ if (!(flags & CPUSTAT_STOPPED)) {
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STATUS_INCORRECT_STATE;
+ return SIGP_CC_STATUS_STORED;
+ }
+
+ addr &= 0x7ffffe00;
+ rc = kvm_s390_store_status_unloaded(dst_vcpu, addr);
+ if (rc == -EFAULT) {
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STATUS_INVALID_PARAMETER;
+ rc = SIGP_CC_STATUS_STORED;
+ }
return rc;
}
static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
u64 *reg)
{
+ struct kvm_s390_local_interrupt *li;
+ struct kvm_vcpu *dst_vcpu = NULL;
int rc;
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
if (cpu_addr >= KVM_MAX_VCPUS)
return SIGP_CC_NOT_OPERATIONAL;
- spin_lock(&fi->lock);
- if (fi->local_int[cpu_addr] == NULL)
- rc = SIGP_CC_NOT_OPERATIONAL;
- else {
- if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
- & CPUSTAT_RUNNING) {
- /* running */
- rc = SIGP_CC_ORDER_CODE_ACCEPTED;
- } else {
- /* not running */
- *reg &= 0xffffffff00000000UL;
- *reg |= SIGP_STATUS_NOT_RUNNING;
- rc = SIGP_CC_STATUS_STORED;
- }
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+ li = &dst_vcpu->arch.local_int;
+ if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+ /* running */
+ rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+ } else {
+ /* not running */
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STATUS_NOT_RUNNING;
+ rc = SIGP_CC_STATUS_STORED;
}
- spin_unlock(&fi->lock);
VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
rc);
@@ -294,31 +342,25 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
return rc;
}
-static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr)
+/* Test whether the destination CPU is available and not busy */
+static int sigp_check_callable(struct kvm_vcpu *vcpu, u16 cpu_addr)
{
- struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_local_interrupt *li;
int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+ struct kvm_vcpu *dst_vcpu = NULL;
if (cpu_addr >= KVM_MAX_VCPUS)
return SIGP_CC_NOT_OPERATIONAL;
- spin_lock(&fi->lock);
- li = fi->local_int[cpu_addr];
- if (li == NULL) {
- rc = SIGP_CC_NOT_OPERATIONAL;
- goto out;
- }
-
+ dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+ if (!dst_vcpu)
+ return SIGP_CC_NOT_OPERATIONAL;
+ li = &dst_vcpu->arch.local_int;
spin_lock_bh(&li->lock);
if (li->action_bits & ACTION_STOP_ON_STOP)
rc = SIGP_CC_BUSY;
- else
- VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace",
- cpu_addr);
spin_unlock_bh(&li->lock);
-out:
- spin_unlock(&fi->lock);
+
return rc;
}
@@ -366,6 +408,10 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP |
ACTION_STOP_ON_STOP);
break;
+ case SIGP_STORE_STATUS_AT_ADDRESS:
+ rc = __sigp_store_status_at_addr(vcpu, cpu_addr, parameter,
+ &vcpu->run->s.regs.gprs[r1]);
+ break;
case SIGP_SET_ARCHITECTURE:
vcpu->stat.instruction_sigp_arch++;
rc = __sigp_set_arch(vcpu, parameter);
@@ -375,17 +421,31 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
&vcpu->run->s.regs.gprs[r1]);
break;
+ case SIGP_COND_EMERGENCY_SIGNAL:
+ rc = __sigp_conditional_emergency(vcpu, cpu_addr, parameter,
+ &vcpu->run->s.regs.gprs[r1]);
+ break;
case SIGP_SENSE_RUNNING:
vcpu->stat.instruction_sigp_sense_running++;
rc = __sigp_sense_running(vcpu, cpu_addr,
&vcpu->run->s.regs.gprs[r1]);
break;
+ case SIGP_START:
+ rc = sigp_check_callable(vcpu, cpu_addr);
+ if (rc == SIGP_CC_ORDER_CODE_ACCEPTED)
+ rc = -EOPNOTSUPP; /* Handle START in user space */
+ break;
case SIGP_RESTART:
vcpu->stat.instruction_sigp_restart++;
- rc = __sigp_restart(vcpu, cpu_addr);
- if (rc == SIGP_CC_BUSY)
- break;
- /* user space must know about restart */
+ rc = sigp_check_callable(vcpu, cpu_addr);
+ if (rc == SIGP_CC_ORDER_CODE_ACCEPTED) {
+ VCPU_EVENT(vcpu, 4,
+ "sigp restart %x to handle userspace",
+ cpu_addr);
+ /* user space must know about restart */
+ rc = -EOPNOTSUPP;
+ }
+ break;
default:
return -EOPNOTSUPP;
}
@@ -393,7 +453,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
if (rc < 0)
return rc;
- vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
- vcpu->arch.sie_block->gpsw.mask |= (rc & 3ul) << 44;
+ kvm_s390_set_psw_cc(vcpu, rc);
return 0;
}
diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h
index 0c991c6748a..e8e7213d4cc 100644
--- a/arch/s390/kvm/trace.h
+++ b/arch/s390/kvm/trace.h
@@ -30,6 +30,52 @@
TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id, \
__entry->pswmask, __entry->pswaddr, p_args)
+TRACE_EVENT(kvm_s390_major_guest_pfault,
+ TP_PROTO(VCPU_PROTO_COMMON),
+ TP_ARGS(VCPU_ARGS_COMMON),
+
+ TP_STRUCT__entry(
+ VCPU_FIELD_COMMON
+ ),
+
+ TP_fast_assign(
+ VCPU_ASSIGN_COMMON
+ ),
+ VCPU_TP_PRINTK("%s", "major fault, maybe applicable for pfault")
+ );
+
+TRACE_EVENT(kvm_s390_pfault_init,
+ TP_PROTO(VCPU_PROTO_COMMON, long pfault_token),
+ TP_ARGS(VCPU_ARGS_COMMON, pfault_token),
+
+ TP_STRUCT__entry(
+ VCPU_FIELD_COMMON
+ __field(long, pfault_token)
+ ),
+
+ TP_fast_assign(
+ VCPU_ASSIGN_COMMON
+ __entry->pfault_token = pfault_token;
+ ),
+ VCPU_TP_PRINTK("init pfault token %ld", __entry->pfault_token)
+ );
+
+TRACE_EVENT(kvm_s390_pfault_done,
+ TP_PROTO(VCPU_PROTO_COMMON, long pfault_token),
+ TP_ARGS(VCPU_ARGS_COMMON, pfault_token),
+
+ TP_STRUCT__entry(
+ VCPU_FIELD_COMMON
+ __field(long, pfault_token)
+ ),
+
+ TP_fast_assign(
+ VCPU_ASSIGN_COMMON
+ __entry->pfault_token = pfault_token;
+ ),
+ VCPU_TP_PRINTK("done pfault token %ld", __entry->pfault_token)
+ );
+
/*
* Tracepoints for SIE entry and exit.
*/
@@ -175,6 +221,7 @@ TRACE_EVENT(kvm_s390_intercept_validity,
{SIGP_STOP_AND_STORE_STATUS, "stop and store status"}, \
{SIGP_SET_ARCHITECTURE, "set architecture"}, \
{SIGP_SET_PREFIX, "set prefix"}, \
+ {SIGP_STORE_STATUS_AT_ADDRESS, "store status at addr"}, \
{SIGP_SENSE_RUNNING, "sense running"}, \
{SIGP_RESTART, "restart"}
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index b068729e50a..c6d752e8bf2 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.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 620d34d6487..922003c1b90 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.c b/arch/s390/lib/uaccess.c
new file mode 100644
index 00000000000..23f866b4c7f
--- /dev/null
+++ b/arch/s390/lib/uaccess.c
@@ -0,0 +1,407 @@
+/*
+ * Standard user space access functions based on mvcp/mvcs and doing
+ * interesting things in the secondary space mode.
+ *
+ * Copyright IBM Corp. 2006,2014
+ * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ * Gerald Schaefer (gerald.schaefer@de.ibm.com)
+ */
+
+#include <linux/jump_label.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <asm/mmu_context.h>
+#include <asm/facility.h>
+
+#ifndef CONFIG_64BIT
+#define AHI "ahi"
+#define ALR "alr"
+#define CLR "clr"
+#define LHI "lhi"
+#define SLR "slr"
+#else
+#define AHI "aghi"
+#define ALR "algr"
+#define CLR "clgr"
+#define LHI "lghi"
+#define SLR "slgr"
+#endif
+
+static struct static_key have_mvcos = STATIC_KEY_INIT_FALSE;
+
+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;
+
+ tmp1 = -4096UL;
+ asm volatile(
+ "0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n"
+ "9: jz 7f\n"
+ "1:"ALR" %0,%3\n"
+ " "SLR" %1,%3\n"
+ " "SLR" %2,%3\n"
+ " j 0b\n"
+ "2: la %4,4095(%1)\n"/* %4 = ptr + 4095 */
+ " nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */
+ " "SLR" %4,%1\n"
+ " "CLR" %0,%4\n" /* copy crosses next page boundary? */
+ " jnh 4f\n"
+ "3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n"
+ "10:"SLR" %0,%4\n"
+ " "ALR" %2,%4\n"
+ "4:"LHI" %4,-1\n"
+ " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */
+ " bras %3,6f\n" /* memset loop */
+ " xc 0(1,%2),0(%2)\n"
+ "5: xc 0(256,%2),0(%2)\n"
+ " la %2,256(%2)\n"
+ "6:"AHI" %4,-256\n"
+ " jnm 5b\n"
+ " ex %4,0(%3)\n"
+ " j 8f\n"
+ "7:"SLR" %0,%0\n"
+ "8:\n"
+ 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;
+}
+
+static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
+ unsigned long size)
+{
+ unsigned long tmp1, tmp2;
+
+ update_primary_asce(current);
+ tmp1 = -256UL;
+ asm volatile(
+ " sacf 0\n"
+ "0: mvcp 0(%0,%2),0(%1),%3\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"
+ "11:jnz 1b\n"
+ " j 8f\n"
+ "3: la %4,255(%1)\n" /* %4 = ptr + 255 */
+ " "LHI" %3,-4096\n"
+ " nr %4,%3\n" /* %4 = (ptr + 255) & -4096 */
+ " "SLR" %4,%1\n"
+ " "CLR" %0,%4\n" /* copy crosses next page boundary? */
+ " jnh 5f\n"
+ "4: mvcp 0(%4,%2),0(%1),%3\n"
+ "12:"SLR" %0,%4\n"
+ " "ALR" %2,%4\n"
+ "5:"LHI" %4,-1\n"
+ " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */
+ " bras %3,7f\n" /* memset loop */
+ " xc 0(1,%2),0(%2)\n"
+ "6: xc 0(256,%2),0(%2)\n"
+ " la %2,256(%2)\n"
+ "7:"AHI" %4,-256\n"
+ " jnm 6b\n"
+ " ex %4,0(%3)\n"
+ " j 9f\n"
+ "8:"SLR" %0,%0\n"
+ "9: sacf 768\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;
+}
+
+unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ if (static_key_false(&have_mvcos))
+ return copy_from_user_mvcos(to, from, n);
+ return copy_from_user_mvcp(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;
+
+ tmp1 = -4096UL;
+ asm volatile(
+ "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
+ "6: jz 4f\n"
+ "1:"ALR" %0,%3\n"
+ " "SLR" %1,%3\n"
+ " "SLR" %2,%3\n"
+ " j 0b\n"
+ "2: la %4,4095(%1)\n"/* %4 = ptr + 4095 */
+ " nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */
+ " "SLR" %4,%1\n"
+ " "CLR" %0,%4\n" /* copy crosses next page boundary? */
+ " jnh 5f\n"
+ "3: .insn ss,0xc80000000000,0(%4,%1),0(%2),0\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(6b,2b) EX_TABLE(7b,5b)
+ : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+ : "d" (reg0) : "cc", "memory");
+ return size;
+}
+
+static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x,
+ unsigned long size)
+{
+ unsigned long tmp1, tmp2;
+
+ update_primary_asce(current);
+ tmp1 = -256UL;
+ asm volatile(
+ " sacf 0\n"
+ "0: mvcs 0(%0,%1),0(%2),%3\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"
+ "8: jnz 1b\n"
+ " j 5f\n"
+ "3: la %4,255(%1)\n" /* %4 = ptr + 255 */
+ " "LHI" %3,-4096\n"
+ " nr %4,%3\n" /* %4 = (ptr + 255) & -4096 */
+ " "SLR" %4,%1\n"
+ " "CLR" %0,%4\n" /* copy crosses next page boundary? */
+ " jnh 6f\n"
+ "4: mvcs 0(%4,%1),0(%2),%3\n"
+ "9:"SLR" %0,%4\n"
+ " j 6f\n"
+ "5:"SLR" %0,%0\n"
+ "6: sacf 768\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;
+}
+
+unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ if (static_key_false(&have_mvcos))
+ return copy_to_user_mvcos(to, from, n);
+ return copy_to_user_mvcs(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;
+
+ tmp1 = -4096UL;
+ /* FIXME: copy with reduced length. */
+ asm volatile(
+ "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
+ " jz 2f\n"
+ "1:"ALR" %0,%3\n"
+ " "SLR" %1,%3\n"
+ " "SLR" %2,%3\n"
+ " j 0b\n"
+ "2:"SLR" %0,%0\n"
+ "3: \n"
+ EX_TABLE(0b,3b)
+ : "+a" (size), "+a" (to), "+a" (from), "+a" (tmp1), "=a" (tmp2)
+ : "d" (reg0) : "cc", "memory");
+ return size;
+}
+
+static inline unsigned long copy_in_user_mvc(void __user *to, const void __user *from,
+ unsigned long size)
+{
+ unsigned long tmp1;
+
+ update_primary_asce(current);
+ asm volatile(
+ " sacf 256\n"
+ " "AHI" %0,-1\n"
+ " jo 5f\n"
+ " bras %3,3f\n"
+ "0:"AHI" %0,257\n"
+ "1: mvc 0(1,%1),0(%2)\n"
+ " la %1,1(%1)\n"
+ " la %2,1(%2)\n"
+ " "AHI" %0,-1\n"
+ " jnz 1b\n"
+ " j 5f\n"
+ "2: mvc 0(256,%1),0(%2)\n"
+ " la %1,256(%1)\n"
+ " la %2,256(%2)\n"
+ "3:"AHI" %0,-256\n"
+ " jnm 2b\n"
+ "4: ex %0,1b-0b(%3)\n"
+ "5: "SLR" %0,%0\n"
+ "6: sacf 768\n"
+ EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
+ : "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1)
+ : : "cc", "memory");
+ return size;
+}
+
+unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+ if (static_key_false(&have_mvcos))
+ return copy_in_user_mvcos(to, from, n);
+ return copy_in_user_mvc(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;
+
+ tmp1 = -4096UL;
+ asm volatile(
+ "0: .insn ss,0xc80000000000,0(%0,%1),0(%4),0\n"
+ " jz 4f\n"
+ "1:"ALR" %0,%2\n"
+ " "SLR" %1,%2\n"
+ " j 0b\n"
+ "2: la %3,4095(%1)\n"/* %4 = to + 4095 */
+ " nr %3,%2\n" /* %4 = (to + 4095) & -4096 */
+ " "SLR" %3,%1\n"
+ " "CLR" %0,%3\n" /* copy crosses next page boundary? */
+ " jnh 5f\n"
+ "3: .insn ss,0xc80000000000,0(%3,%1),0(%4),0\n"
+ " "SLR" %0,%3\n"
+ " j 5f\n"
+ "4:"SLR" %0,%0\n"
+ "5:\n"
+ EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+ : "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
+ : "a" (empty_zero_page), "d" (reg0) : "cc", "memory");
+ return size;
+}
+
+static inline unsigned long clear_user_xc(void __user *to, unsigned long size)
+{
+ unsigned long tmp1, tmp2;
+
+ update_primary_asce(current);
+ asm volatile(
+ " sacf 256\n"
+ " "AHI" %0,-1\n"
+ " jo 5f\n"
+ " bras %3,3f\n"
+ " xc 0(1,%1),0(%1)\n"
+ "0:"AHI" %0,257\n"
+ " la %2,255(%1)\n" /* %2 = ptr + 255 */
+ " srl %2,12\n"
+ " sll %2,12\n" /* %2 = (ptr + 255) & -4096 */
+ " "SLR" %2,%1\n"
+ " "CLR" %0,%2\n" /* clear crosses next page boundary? */
+ " jnh 5f\n"
+ " "AHI" %2,-1\n"
+ "1: ex %2,0(%3)\n"
+ " "AHI" %2,1\n"
+ " "SLR" %0,%2\n"
+ " j 5f\n"
+ "2: xc 0(256,%1),0(%1)\n"
+ " la %1,256(%1)\n"
+ "3:"AHI" %0,-256\n"
+ " jnm 2b\n"
+ "4: ex %0,0(%3)\n"
+ "5: "SLR" %0,%0\n"
+ "6: sacf 768\n"
+ EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
+ : "+a" (size), "+a" (to), "=a" (tmp1), "=a" (tmp2)
+ : : "cc", "memory");
+ return size;
+}
+
+unsigned long __clear_user(void __user *to, unsigned long size)
+{
+ if (static_key_false(&have_mvcos))
+ return clear_user_mvcos(to, size);
+ return clear_user_xc(to, size);
+}
+EXPORT_SYMBOL(__clear_user);
+
+static inline unsigned long strnlen_user_srst(const char __user *src,
+ unsigned long size)
+{
+ register unsigned long reg0 asm("0") = 0;
+ unsigned long tmp1, tmp2;
+
+ if (unlikely(!size))
+ return 0;
+ update_primary_asce(current);
+ asm volatile(
+ " la %2,0(%1)\n"
+ " la %3,0(%0,%1)\n"
+ " "SLR" %0,%0\n"
+ " sacf 256\n"
+ "0: srst %3,%2\n"
+ " jo 0b\n"
+ " la %0,1(%3)\n" /* strnlen_user results includes \0 */
+ " "SLR" %0,%1\n"
+ "1: sacf 768\n"
+ EX_TABLE(0b,1b)
+ : "+a" (size), "+a" (src), "=a" (tmp1), "=a" (tmp2)
+ : "d" (reg0) : "cc", "memory");
+ return size;
+}
+
+unsigned long __strnlen_user(const char __user *src, unsigned long size)
+{
+ update_primary_asce(current);
+ return strnlen_user_srst(src, size);
+}
+EXPORT_SYMBOL(__strnlen_user);
+
+long __strncpy_from_user(char *dst, const char __user *src, long size)
+{
+ size_t done, len, offset, len_str;
+
+ if (unlikely(size <= 0))
+ return 0;
+ done = 0;
+ do {
+ offset = (size_t)src & ~PAGE_MASK;
+ len = min(size - done, PAGE_SIZE - offset);
+ if (copy_from_user(dst, src, len))
+ return -EFAULT;
+ len_str = strnlen(dst, len);
+ done += len_str;
+ src += len_str;
+ dst += len_str;
+ } while ((len_str == len) && (done < size));
+ return done;
+}
+EXPORT_SYMBOL(__strncpy_from_user);
+
+/*
+ * The "old" uaccess variant without mvcos can be enforced with the
+ * uaccess_primary kernel parameter. This is mainly for debugging purposes.
+ */
+static int uaccess_primary __initdata;
+
+static int __init parse_uaccess_pt(char *__unused)
+{
+ uaccess_primary = 1;
+ return 0;
+}
+early_param("uaccess_primary", parse_uaccess_pt);
+
+static int __init uaccess_init(void)
+{
+ if (IS_ENABLED(CONFIG_64BIT) && !uaccess_primary && test_facility(27))
+ static_key_slow_inc(&have_mvcos);
+ return 0;
+}
+early_initcall(uaccess_init);
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
deleted file mode 100644
index 315dbe09983..00000000000
--- a/arch/s390/lib/uaccess.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright IBM Corp. 2007
- *
- */
-
-#ifndef __ARCH_S390_LIB_UACCESS_H
-#define __ARCH_S390_LIB_UACCESS_H
-
-extern size_t copy_from_user_std(size_t, const void __user *, void *);
-extern size_t copy_to_user_std(size_t, void __user *, const void *);
-extern size_t strnlen_user_std(size_t, const char __user *);
-extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
-extern int futex_atomic_cmpxchg_std(u32 *, u32 __user *, u32, u32);
-extern int futex_atomic_op_std(int, u32 __user *, int, int *);
-
-extern size_t copy_from_user_pt(size_t, const void __user *, void *);
-extern size_t copy_to_user_pt(size_t, void __user *, const void *);
-extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
-
-#endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c
deleted file mode 100644
index 4b7993bf69b..00000000000
--- a/arch/s390/lib/uaccess_mvcos.c
+++ /dev/null
@@ -1,197 +0,0 @@
-/*
- * Optimized user space space access functions based on mvcos.
- *
- * Copyright IBM Corp. 2006
- * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- * Gerald Schaefer (gerald.schaefer@de.ibm.com)
- */
-
-#include <linux/errno.h>
-#include <linux/mm.h>
-#include <asm/uaccess.h>
-#include <asm/futex.h>
-#include "uaccess.h"
-
-#ifndef CONFIG_64BIT
-#define AHI "ahi"
-#define ALR "alr"
-#define CLR "clr"
-#define LHI "lhi"
-#define SLR "slr"
-#else
-#define AHI "aghi"
-#define ALR "algr"
-#define CLR "clgr"
-#define LHI "lghi"
-#define SLR "slgr"
-#endif
-
-static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
-{
- register unsigned long reg0 asm("0") = 0x81UL;
- unsigned long tmp1, tmp2;
-
- tmp1 = -4096UL;
- asm volatile(
- "0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n"
- "9: jz 7f\n"
- "1:"ALR" %0,%3\n"
- " "SLR" %1,%3\n"
- " "SLR" %2,%3\n"
- " j 0b\n"
- "2: la %4,4095(%1)\n"/* %4 = ptr + 4095 */
- " nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */
- " "SLR" %4,%1\n"
- " "CLR" %0,%4\n" /* copy crosses next page boundary? */
- " jnh 4f\n"
- "3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n"
- "10:"SLR" %0,%4\n"
- " "ALR" %2,%4\n"
- "4:"LHI" %4,-1\n"
- " "ALR" %4,%0\n" /* copy remaining size, subtract 1 */
- " bras %3,6f\n" /* memset loop */
- " xc 0(1,%2),0(%2)\n"
- "5: xc 0(256,%2),0(%2)\n"
- " la %2,256(%2)\n"
- "6:"AHI" %4,-256\n"
- " jnm 5b\n"
- " ex %4,0(%3)\n"
- " j 8f\n"
- "7:"SLR" %0,%0\n"
- "8: \n"
- 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;
-}
-
-static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
-{
- register unsigned long reg0 asm("0") = 0x810000UL;
- unsigned long tmp1, tmp2;
-
- tmp1 = -4096UL;
- asm volatile(
- "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
- "6: jz 4f\n"
- "1:"ALR" %0,%3\n"
- " "SLR" %1,%3\n"
- " "SLR" %2,%3\n"
- " j 0b\n"
- "2: la %4,4095(%1)\n"/* %4 = ptr + 4095 */
- " nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */
- " "SLR" %4,%1\n"
- " "CLR" %0,%4\n" /* copy crosses next page boundary? */
- " jnh 5f\n"
- "3: .insn ss,0xc80000000000,0(%4,%1),0(%2),0\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(6b,2b) EX_TABLE(7b,5b)
- : "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
- : "d" (reg0) : "cc", "memory");
- return size;
-}
-
-static size_t copy_in_user_mvcos(size_t size, void __user *to,
- const void __user *from)
-{
- register unsigned long reg0 asm("0") = 0x810081UL;
- unsigned long tmp1, tmp2;
-
- tmp1 = -4096UL;
- /* FIXME: copy with reduced length. */
- asm volatile(
- "0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
- " jz 2f\n"
- "1:"ALR" %0,%3\n"
- " "SLR" %1,%3\n"
- " "SLR" %2,%3\n"
- " j 0b\n"
- "2:"SLR" %0,%0\n"
- "3: \n"
- EX_TABLE(0b,3b)
- : "+a" (size), "+a" (to), "+a" (from), "+a" (tmp1), "=a" (tmp2)
- : "d" (reg0) : "cc", "memory");
- return size;
-}
-
-static size_t clear_user_mvcos(size_t size, void __user *to)
-{
- register unsigned long reg0 asm("0") = 0x810000UL;
- unsigned long tmp1, tmp2;
-
- tmp1 = -4096UL;
- asm volatile(
- "0: .insn ss,0xc80000000000,0(%0,%1),0(%4),0\n"
- " jz 4f\n"
- "1:"ALR" %0,%2\n"
- " "SLR" %1,%2\n"
- " j 0b\n"
- "2: la %3,4095(%1)\n"/* %4 = to + 4095 */
- " nr %3,%2\n" /* %4 = (to + 4095) & -4096 */
- " "SLR" %3,%1\n"
- " "CLR" %0,%3\n" /* copy crosses next page boundary? */
- " jnh 5f\n"
- "3: .insn ss,0xc80000000000,0(%3,%1),0(%4),0\n"
- " "SLR" %0,%3\n"
- " j 5f\n"
- "4:"SLR" %0,%0\n"
- "5: \n"
- EX_TABLE(0b,2b) EX_TABLE(3b,5b)
- : "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
- : "a" (empty_zero_page), "d" (reg0) : "cc", "memory");
- return size;
-}
-
-static size_t strnlen_user_mvcos(size_t count, const char __user *src)
-{
- size_t done, len, offset, len_str;
- char buf[256];
-
- done = 0;
- do {
- offset = (size_t)src & ~PAGE_MASK;
- len = min(256UL, PAGE_SIZE - offset);
- len = min(count - done, len);
- if (copy_from_user_mvcos(len, src, buf))
- return 0;
- len_str = strnlen(buf, len);
- done += len_str;
- src += len_str;
- } while ((len_str == len) && (done < count));
- return done + 1;
-}
-
-static size_t strncpy_from_user_mvcos(size_t count, const char __user *src,
- char *dst)
-{
- size_t done, len, offset, len_str;
-
- if (unlikely(!count))
- return 0;
- done = 0;
- do {
- offset = (size_t)src & ~PAGE_MASK;
- len = min(count - done, PAGE_SIZE - offset);
- if (copy_from_user_mvcos(len, src, dst))
- return -EFAULT;
- len_str = strnlen(dst, len);
- done += len_str;
- src += len_str;
- dst += len_str;
- } while ((len_str == len) && (done < count));
- 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,
-};
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
deleted file mode 100644
index dbdab3e7a1a..00000000000
--- a/arch/s390/lib/uaccess_pt.c
+++ /dev/null
@@ -1,474 +0,0 @@
-/*
- * User access functions based on page table walks for enhanced
- * system layout without hardware support.
- *
- * Copyright IBM Corp. 2006, 2012
- * Author(s): Gerald Schaefer (gerald.schaefer@de.ibm.com)
- */
-
-#include <linux/errno.h>
-#include <linux/hardirq.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <asm/uaccess.h>
-#include <asm/futex.h>
-#include "uaccess.h"
-
-#ifndef CONFIG_64BIT
-#define AHI "ahi"
-#define SLR "slr"
-#else
-#define AHI "aghi"
-#define SLR "slgr"
-#endif
-
-static size_t strnlen_kernel(size_t count, const char __user *src)
-{
- register unsigned long reg0 asm("0") = 0UL;
- unsigned long tmp1, tmp2;
-
- asm volatile(
- " la %2,0(%1)\n"
- " la %3,0(%0,%1)\n"
- " "SLR" %0,%0\n"
- "0: srst %3,%2\n"
- " jo 0b\n"
- " la %0,1(%3)\n" /* strnlen_kernel results includes \0 */
- " "SLR" %0,%1\n"
- "1:\n"
- EX_TABLE(0b,1b)
- : "+a" (count), "+a" (src), "=a" (tmp1), "=a" (tmp2)
- : "d" (reg0) : "cc", "memory");
- return count;
-}
-
-static size_t copy_in_kernel(size_t count, void __user *to,
- const void __user *from)
-{
- unsigned long tmp1;
-
- asm volatile(
- " "AHI" %0,-1\n"
- " jo 5f\n"
- " bras %3,3f\n"
- "0:"AHI" %0,257\n"
- "1: mvc 0(1,%1),0(%2)\n"
- " la %1,1(%1)\n"
- " la %2,1(%2)\n"
- " "AHI" %0,-1\n"
- " jnz 1b\n"
- " j 5f\n"
- "2: mvc 0(256,%1),0(%2)\n"
- " la %1,256(%1)\n"
- " la %2,256(%2)\n"
- "3:"AHI" %0,-256\n"
- " jnm 2b\n"
- "4: ex %0,1b-0b(%3)\n"
- "5:"SLR" %0,%0\n"
- "6:\n"
- EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
- : "+a" (count), "+a" (to), "+a" (from), "=a" (tmp1)
- : : "cc", "memory");
- return count;
-}
-
-/*
- * Returns kernel address for user virtual address. If the returned address is
- * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address
- * contains the (negative) exception code.
- */
-#ifdef CONFIG_64BIT
-
-static unsigned long follow_table(struct mm_struct *mm,
- unsigned long address, int write)
-{
- unsigned long *table = (unsigned long *)__pa(mm->pgd);
-
- if (unlikely(address > mm->context.asce_limit - 1))
- return -0x38UL;
- switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
- case _ASCE_TYPE_REGION1:
- table = table + ((address >> 53) & 0x7ff);
- if (unlikely(*table & _REGION_ENTRY_INVALID))
- return -0x39UL;
- table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* fallthrough */
- case _ASCE_TYPE_REGION2:
- table = table + ((address >> 42) & 0x7ff);
- if (unlikely(*table & _REGION_ENTRY_INVALID))
- return -0x3aUL;
- table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* fallthrough */
- case _ASCE_TYPE_REGION3:
- table = table + ((address >> 31) & 0x7ff);
- if (unlikely(*table & _REGION_ENTRY_INVALID))
- return -0x3bUL;
- table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* fallthrough */
- case _ASCE_TYPE_SEGMENT:
- table = table + ((address >> 20) & 0x7ff);
- if (unlikely(*table & _SEGMENT_ENTRY_INVALID))
- return -0x10UL;
- if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) {
- if (write && (*table & _SEGMENT_ENTRY_PROTECT))
- return -0x04UL;
- return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) +
- (address & ~_SEGMENT_ENTRY_ORIGIN_LARGE);
- }
- table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
- }
- table = table + ((address >> 12) & 0xff);
- if (unlikely(*table & _PAGE_INVALID))
- return -0x11UL;
- if (write && (*table & _PAGE_PROTECT))
- return -0x04UL;
- return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
-}
-
-#else /* CONFIG_64BIT */
-
-static unsigned long follow_table(struct mm_struct *mm,
- unsigned long address, int write)
-{
- unsigned long *table = (unsigned long *)__pa(mm->pgd);
-
- table = table + ((address >> 20) & 0x7ff);
- if (unlikely(*table & _SEGMENT_ENTRY_INVALID))
- return -0x10UL;
- table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
- table = table + ((address >> 12) & 0xff);
- if (unlikely(*table & _PAGE_INVALID))
- return -0x11UL;
- if (write && (*table & _PAGE_PROTECT))
- return -0x04UL;
- return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
-}
-
-#endif /* CONFIG_64BIT */
-
-static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr,
- size_t n, int write_user)
-{
- struct mm_struct *mm = current->mm;
- unsigned long offset, done, size, kaddr;
- void *from, *to;
-
- done = 0;
-retry:
- spin_lock(&mm->page_table_lock);
- do {
- kaddr = follow_table(mm, uaddr, write_user);
- if (IS_ERR_VALUE(kaddr))
- goto fault;
-
- offset = uaddr & ~PAGE_MASK;
- size = min(n - done, PAGE_SIZE - offset);
- if (write_user) {
- to = (void *) kaddr;
- from = kptr + done;
- } else {
- from = (void *) kaddr;
- to = kptr + done;
- }
- memcpy(to, from, size);
- done += size;
- uaddr += size;
- } while (done < n);
- spin_unlock(&mm->page_table_lock);
- return n - done;
-fault:
- spin_unlock(&mm->page_table_lock);
- if (__handle_fault(uaddr, -kaddr, write_user))
- return n - done;
- goto retry;
-}
-
-/*
- * 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)
-{
- struct mm_struct *mm = current->mm;
- unsigned long kaddr;
- int rc;
-
-retry:
- kaddr = follow_table(mm, uaddr, write);
- if (IS_ERR_VALUE(kaddr))
- goto fault;
-
- return kaddr;
-fault:
- spin_unlock(&mm->page_table_lock);
- rc = __handle_fault(uaddr, -kaddr, write);
- spin_lock(&mm->page_table_lock);
- if (!rc)
- goto retry;
- return 0;
-}
-
-size_t copy_from_user_pt(size_t n, const void __user *from, void *to)
-{
- size_t rc;
-
- if (segment_eq(get_fs(), KERNEL_DS))
- return copy_in_kernel(n, (void __user *) to, from);
- rc = __user_copy_pt((unsigned long) from, to, n, 0);
- if (unlikely(rc))
- memset(to + n - rc, 0, rc);
- return rc;
-}
-
-size_t copy_to_user_pt(size_t n, void __user *to, const void *from)
-{
- if (segment_eq(get_fs(), KERNEL_DS))
- return copy_in_kernel(n, to, (void __user *) from);
- return __user_copy_pt((unsigned long) to, (void *) from, n, 1);
-}
-
-static size_t clear_user_pt(size_t n, void __user *to)
-{
- void *zpage = (void *) empty_zero_page;
- long done, size, ret;
-
- done = 0;
- do {
- if (n - done > PAGE_SIZE)
- size = PAGE_SIZE;
- else
- size = n - done;
- if (segment_eq(get_fs(), KERNEL_DS))
- ret = copy_in_kernel(n, to, (void __user *) zpage);
- else
- ret = __user_copy_pt((unsigned long) to, zpage, size, 1);
- done += size;
- to += size;
- if (ret)
- return ret + n - done;
- } while (done < n);
- return 0;
-}
-
-static size_t strnlen_user_pt(size_t count, const char __user *src)
-{
- unsigned long uaddr = (unsigned long) src;
- struct mm_struct *mm = current->mm;
- unsigned long offset, done, len, kaddr;
- size_t len_str;
-
- if (unlikely(!count))
- return 0;
- if (segment_eq(get_fs(), KERNEL_DS))
- return strnlen_kernel(count, src);
- done = 0;
-retry:
- spin_lock(&mm->page_table_lock);
- do {
- kaddr = follow_table(mm, uaddr, 0);
- if (IS_ERR_VALUE(kaddr))
- goto fault;
-
- offset = uaddr & ~PAGE_MASK;
- len = min(count - done, PAGE_SIZE - offset);
- len_str = strnlen((char *) kaddr, len);
- done += len_str;
- uaddr += len_str;
- } while ((len_str == len) && (done < count));
- spin_unlock(&mm->page_table_lock);
- return done + 1;
-fault:
- spin_unlock(&mm->page_table_lock);
- if (__handle_fault(uaddr, -kaddr, 0))
- return 0;
- goto retry;
-}
-
-static size_t strncpy_from_user_pt(size_t count, const char __user *src,
- char *dst)
-{
- size_t done, len, offset, len_str;
-
- if (unlikely(!count))
- return 0;
- done = 0;
- do {
- offset = (size_t)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))
- return -EFAULT;
- } else {
- if (__user_copy_pt((unsigned long) src, dst, len, 0))
- return -EFAULT;
- }
- len_str = strnlen(dst, len);
- done += len_str;
- src += len_str;
- dst += len_str;
- } while ((len_str == len) && (done < count));
- return done;
-}
-
-static size_t copy_in_user_pt(size_t n, void __user *to,
- const void __user *from)
-{
- struct mm_struct *mm = current->mm;
- unsigned long offset_max, uaddr, done, size, error_code;
- unsigned long uaddr_from = (unsigned long) from;
- unsigned long uaddr_to = (unsigned long) to;
- unsigned long kaddr_to, kaddr_from;
- int write_user;
-
- if (segment_eq(get_fs(), KERNEL_DS))
- return copy_in_kernel(n, to, from);
- done = 0;
-retry:
- spin_lock(&mm->page_table_lock);
- do {
- write_user = 0;
- uaddr = uaddr_from;
- kaddr_from = follow_table(mm, uaddr_from, 0);
- error_code = kaddr_from;
- if (IS_ERR_VALUE(error_code))
- goto fault;
-
- write_user = 1;
- uaddr = uaddr_to;
- kaddr_to = follow_table(mm, uaddr_to, 1);
- error_code = (unsigned long) kaddr_to;
- if (IS_ERR_VALUE(error_code))
- goto fault;
-
- offset_max = max(uaddr_from & ~PAGE_MASK,
- uaddr_to & ~PAGE_MASK);
- size = min(n - done, PAGE_SIZE - offset_max);
-
- memcpy((void *) kaddr_to, (void *) kaddr_from, size);
- done += size;
- uaddr_from += size;
- uaddr_to += size;
- } while (done < n);
- spin_unlock(&mm->page_table_lock);
- return n - done;
-fault:
- spin_unlock(&mm->page_table_lock);
- if (__handle_fault(uaddr, -error_code, write_user))
- return n - done;
- goto retry;
-}
-
-#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg) \
- asm volatile("0: l %1,0(%6)\n" \
- "1: " insn \
- "2: cs %1,%2,0(%6)\n" \
- "3: jl 1b\n" \
- " lhi %0,0\n" \
- "4:\n" \
- EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b) \
- : "=d" (ret), "=&d" (oldval), "=&d" (newval), \
- "=m" (*uaddr) \
- : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \
- "m" (*uaddr) : "cc" );
-
-static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
-{
- int oldval = 0, newval, ret;
-
- switch (op) {
- case FUTEX_OP_SET:
- __futex_atomic_op("lr %2,%5\n",
- ret, oldval, newval, uaddr, oparg);
- break;
- case FUTEX_OP_ADD:
- __futex_atomic_op("lr %2,%1\nar %2,%5\n",
- ret, oldval, newval, uaddr, oparg);
- break;
- case FUTEX_OP_OR:
- __futex_atomic_op("lr %2,%1\nor %2,%5\n",
- ret, oldval, newval, uaddr, oparg);
- break;
- case FUTEX_OP_ANDN:
- __futex_atomic_op("lr %2,%1\nnr %2,%5\n",
- ret, oldval, newval, uaddr, oparg);
- break;
- case FUTEX_OP_XOR:
- __futex_atomic_op("lr %2,%1\nxr %2,%5\n",
- ret, oldval, newval, uaddr, oparg);
- break;
- default:
- ret = -ENOSYS;
- }
- if (ret == 0)
- *old = oldval;
- return ret;
-}
-
-int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
-{
- int ret;
-
- if (segment_eq(get_fs(), KERNEL_DS))
- return __futex_atomic_op_pt(op, uaddr, oparg, old);
- spin_lock(&current->mm->page_table_lock);
- uaddr = (u32 __force __user *)
- __dat_user_addr((__force unsigned long) uaddr, 1);
- if (!uaddr) {
- spin_unlock(&current->mm->page_table_lock);
- return -EFAULT;
- }
- get_page(virt_to_page(uaddr));
- spin_unlock(&current->mm->page_table_lock);
- ret = __futex_atomic_op_pt(op, uaddr, oparg, old);
- put_page(virt_to_page(uaddr));
- return ret;
-}
-
-static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
- u32 oldval, u32 newval)
-{
- int ret;
-
- asm volatile("0: cs %1,%4,0(%5)\n"
- "1: la %0,0\n"
- "2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
- : "=d" (ret), "+d" (oldval), "=m" (*uaddr)
- : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
- : "cc", "memory" );
- *uval = oldval;
- return ret;
-}
-
-int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
- u32 oldval, u32 newval)
-{
- int ret;
-
- if (segment_eq(get_fs(), KERNEL_DS))
- return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
- spin_lock(&current->mm->page_table_lock);
- uaddr = (u32 __force __user *)
- __dat_user_addr((__force unsigned long) uaddr, 1);
- if (!uaddr) {
- spin_unlock(&current->mm->page_table_lock);
- return -EFAULT;
- }
- get_page(virt_to_page(uaddr));
- spin_unlock(&current->mm->page_table_lock);
- ret = __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
- 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/fault.c b/arch/s390/mm/fault.c
index d95265b2719..19f623f1f21 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -50,6 +50,7 @@
#define VM_FAULT_BADMAP 0x020000
#define VM_FAULT_BADACCESS 0x040000
#define VM_FAULT_SIGNAL 0x080000
+#define VM_FAULT_PFAULT 0x100000
static unsigned long store_indication __read_mostly;
@@ -105,21 +106,24 @@ void bust_spinlocks(int yes)
* Returns the address space associated with the fault.
* Returns 0 for kernel space and 1 for user space.
*/
-static inline int user_space_fault(unsigned long trans_exc_code)
+static inline int user_space_fault(struct pt_regs *regs)
{
+ unsigned long trans_exc_code;
+
/*
* The lowest two bits of the translation exception
* identification indicate which paging table was used.
*/
- trans_exc_code &= 3;
- if (trans_exc_code == 2)
- /* Access via secondary space, set_fs setting decides */
+ trans_exc_code = regs->int_parm_long & 3;
+ if (trans_exc_code == 3) /* home space -> kernel */
+ return 0;
+ if (user_mode(regs))
+ return 1;
+ if (trans_exc_code == 2) /* secondary space -> set_fs */
return current->thread.mm_segment.ar4;
- /*
- * Access via primary space or access register is from user space
- * and access via home space is from the kernel.
- */
- return trans_exc_code != 3;
+ if (current->flags & PF_VCPU)
+ return 1;
+ return 0;
}
static inline void report_user_fault(struct pt_regs *regs, long signr)
@@ -171,7 +175,7 @@ static noinline void do_no_context(struct pt_regs *regs)
* terminate things with extreme prejudice.
*/
address = regs->int_parm_long & __FAIL_ADDR_MASK;
- if (!user_space_fault(regs->int_parm_long))
+ if (!user_space_fault(regs))
printk(KERN_ALERT "Unable to handle kernel pointer dereference"
" at virtual kernel address %p\n", (void *)address);
else
@@ -227,6 +231,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
return;
}
case VM_FAULT_BADCONTEXT:
+ case VM_FAULT_PFAULT:
do_no_context(regs);
break;
case VM_FAULT_SIGNAL:
@@ -264,6 +269,9 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
*/
static inline int do_exception(struct pt_regs *regs, int access)
{
+#ifdef CONFIG_PGSTE
+ struct gmap *gmap;
+#endif
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
@@ -291,7 +299,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
* user context.
*/
fault = VM_FAULT_BADCONTEXT;
- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
+ if (unlikely(!user_space_fault(regs) || in_atomic() || !mm))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
@@ -304,9 +312,10 @@ static inline int do_exception(struct pt_regs *regs, int access)
down_read(&mm->mmap_sem);
#ifdef CONFIG_PGSTE
- if ((current->flags & PF_VCPU) && S390_lowcore.gmap) {
- address = __gmap_fault(address,
- (struct gmap *) S390_lowcore.gmap);
+ gmap = (struct gmap *)
+ ((current->flags & PF_VCPU) ? S390_lowcore.gmap : 0);
+ if (gmap) {
+ address = __gmap_fault(address, gmap);
if (address == -EFAULT) {
fault = VM_FAULT_BADMAP;
goto out_up;
@@ -315,6 +324,8 @@ static inline int do_exception(struct pt_regs *regs, int access)
fault = VM_FAULT_OOM;
goto out_up;
}
+ if (gmap->pfault_enabled)
+ flags |= FAULT_FLAG_RETRY_NOWAIT;
}
#endif
@@ -371,9 +382,19 @@ retry:
regs, address);
}
if (fault & VM_FAULT_RETRY) {
+#ifdef CONFIG_PGSTE
+ if (gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ /* FAULT_FLAG_RETRY_NOWAIT has been set,
+ * mmap_sem has not been released */
+ current->thread.gmap_pfault = 1;
+ fault = VM_FAULT_PFAULT;
+ goto out_up;
+ }
+#endif
/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
* of starvation. */
- flags &= ~FAULT_FLAG_ALLOW_RETRY;
+ flags &= ~(FAULT_FLAG_ALLOW_RETRY |
+ FAULT_FLAG_RETRY_NOWAIT);
flags |= FAULT_FLAG_TRIED;
down_read(&mm->mmap_sem);
goto retry;
@@ -423,30 +444,6 @@ void __kprobes do_dat_exception(struct pt_regs *regs)
do_fault_error(regs, fault);
}
-int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
-{
- struct pt_regs regs;
- int access, fault;
-
- /* Emulate a uaccess fault from kernel mode. */
- regs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK;
- if (!irqs_disabled())
- regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT;
- regs.psw.addr = (unsigned long) __builtin_return_address(0);
- regs.psw.addr |= PSW_ADDR_AMODE;
- regs.int_code = pgm_int_code;
- regs.int_parm_long = (uaddr & PAGE_MASK) | 2;
- access = write ? VM_WRITE : VM_READ;
- fault = do_exception(&regs, access);
- /*
- * Since the fault happened in kernel mode while performing a uaccess
- * all we need to do now is emulating a fixup in case "fault" is not
- * zero.
- * For the calling uaccess functions this results always in -EFAULT.
- */
- return fault ? -EFAULT : 0;
-}
-
#ifdef CONFIG_PFAULT
/*
* 'pfault' pseudo page faults routines.
@@ -627,7 +624,7 @@ static int __init pfault_irq_init(void)
{
int rc;
- rc = register_external_interrupt(0x2603, pfault_interrupt);
+ rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
if (rc)
goto out_extint;
rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
@@ -638,7 +635,7 @@ static int __init pfault_irq_init(void)
return 0;
out_pfault:
- unregister_external_interrupt(0x2603, pfault_interrupt);
+ unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
out_extint:
pfault_disable = 1;
return rc;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d261c62e40a..0727a55d87d 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -123,10 +123,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
pmd_t *pmdp = (pmd_t *) ptep;
pte_t pte = huge_ptep_get(ptep);
- if (MACHINE_HAS_IDTE)
- __pmd_idte(addr, pmdp);
- else
- __pmd_csp(pmdp);
+ pmdp_flush_direct(mm, addr, pmdp);
pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
return pte;
}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ad446b0c55b..0c1073ed1e8 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -124,8 +124,6 @@ void __init paging_init(void)
__ctl_load(S390_lowcore.kernel_asce, 13, 13);
arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
- atomic_set(&init_mm.context.attach_count, 1);
-
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
@@ -136,6 +134,11 @@ void __init paging_init(void)
void __init mem_init(void)
{
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
+ cpumask_set_cpu(0, mm_cpumask(&init_mm));
+ atomic_set(&init_mm.context.attach_count, 1);
+
max_mapnr = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index d1e0e0c7a7e..2a2e35416d2 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;
@@ -152,32 +152,6 @@ out:
}
/*
- * 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
*/
static int is_swapped(unsigned long addr)
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e9dfb..27c50f4d90c 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
#define ESSA_SET_STABLE 1
#define ESSA_SET_UNUSED 2
@@ -41,6 +43,14 @@ void __init cmma_init(void)
if (!cmma_flag)
return;
+ /*
+ * Disable CMM for dump, otherwise the tprot based memory
+ * detection can fail because of unstable pages.
+ */
+ if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+ cmma_flag = 0;
+ return;
+ }
asm volatile(
" .insn rrf,0xb9ab0000,%1,%1,0,0\n"
"0: la %0,0\n"
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index e794c88f699..d7cfd57815f 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -17,6 +17,7 @@
#include <linux/quicklist.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
+#include <linux/swapops.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -53,7 +54,7 @@ static void __crst_table_upgrade(void *arg)
struct mm_struct *mm = arg;
if (current->active_mm == mm)
- update_mm(mm, current);
+ update_user_asce(mm, 1);
__tlb_flush_local();
}
@@ -106,8 +107,10 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
{
pgd_t *pgd;
- if (current->active_mm == mm)
+ if (current->active_mm == mm) {
+ clear_user_asce(mm, 1);
__tlb_flush_mm(mm);
+ }
while (mm->context.asce_limit > limit) {
pgd = mm->pgd;
switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
@@ -131,7 +134,7 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
crst_table_free(mm, (unsigned long *) pgd);
}
if (current->active_mm == mm)
- update_mm(mm, current);
+ update_user_asce(mm, 1);
}
#endif
@@ -197,7 +200,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table)
static void gmap_flush_tlb(struct gmap *gmap)
{
if (MACHINE_HAS_IDTE)
- __tlb_flush_idte((unsigned long) gmap->table |
+ __tlb_flush_asce(gmap->mm, (unsigned long) gmap->table |
_ASCE_TYPE_REGION1);
else
__tlb_flush_global();
@@ -216,7 +219,7 @@ void gmap_free(struct gmap *gmap)
/* Flush tlb. */
if (MACHINE_HAS_IDTE)
- __tlb_flush_idte((unsigned long) gmap->table |
+ __tlb_flush_asce(gmap->mm, (unsigned long) gmap->table |
_ASCE_TYPE_REGION1);
else
__tlb_flush_global();
@@ -293,7 +296,7 @@ static int gmap_alloc_table(struct gmap *gmap,
* @addr: address in the guest address space
* @len: length of the memory area to unmap
*
- * Returns 0 if the unmap succeded, -EINVAL if not.
+ * Returns 0 if the unmap succeeded, -EINVAL if not.
*/
int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
{
@@ -344,7 +347,7 @@ EXPORT_SYMBOL_GPL(gmap_unmap_segment);
* @from: source address in the parent address space
* @to: target address in the guest address space
*
- * Returns 0 if the mmap succeded, -EINVAL or -ENOMEM if not.
+ * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not.
*/
int gmap_map_segment(struct gmap *gmap, unsigned long from,
unsigned long to, unsigned long len)
@@ -504,6 +507,9 @@ static int gmap_connect_pgtable(unsigned long address, unsigned long segment,
if (!pmd_present(*pmd) &&
__pte_alloc(mm, vma, pmd, vmaddr))
return -ENOMEM;
+ /* large pmds cannot yet be handled */
+ if (pmd_large(*pmd))
+ return -EFAULT;
/* pmd now points to a valid segment table entry. */
rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT);
if (!rmap)
@@ -594,6 +600,82 @@ 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 +753,7 @@ 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 +807,12 @@ 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 +883,78 @@ 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 +1401,7 @@ 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 +1417,7 @@ 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/mm/vmem.c b/arch/s390/mm/vmem.c
index bcfb70b60be..72b04de1828 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -138,7 +138,6 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
}
ret = 0;
out:
- flush_tlb_kernel_range(start, end);
return ret;
}
@@ -265,7 +264,6 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
memset((void *)start, 0, end - start);
ret = 0;
out:
- flush_tlb_kernel_range(start, end);
return ret;
}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 708d60e4006..9c36dc398f9 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -737,10 +737,10 @@ call_fn: /* lg %r1,<d(function)>(%r13) */
/* icm %r5,3,<d(type)>(%r1) */
EMIT4_DISP(0xbf531000, offsetof(struct net_device, type));
break;
- case BPF_S_ANC_RXHASH: /* A = skb->rxhash */
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
- /* l %r5,<d(rxhash)>(%r2) */
- EMIT4_DISP(0x58502000, offsetof(struct sk_buff, rxhash));
+ case BPF_S_ANC_RXHASH: /* A = skb->hash */
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+ /* l %r5,<d(hash)>(%r2) */
+ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash));
break;
case BPF_S_ANC_VLAN_TAG:
case BPF_S_ANC_VLAN_TAG_PRESENT:
@@ -877,6 +877,7 @@ void bpf_jit_compile(struct sk_filter *fp)
if (jit.start) {
set_memory_ro((unsigned long)header, header->pages);
fp->bpf_func = (void *) jit.start;
+ fp->jited = 1;
}
out:
kfree(addrs);
@@ -887,10 +888,12 @@ void bpf_jit_free(struct sk_filter *fp)
unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
struct bpf_binary_header *header = (void *)addr;
- if (fp->bpf_func == sk_run_filter)
+ if (!fp->jited)
goto free_filter;
+
set_memory_rw(addr, header->pages);
module_free(NULL, header);
+
free_filter:
kfree(fp);
}
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index 231cecafc2f..276f2e26c76 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -26,9 +26,6 @@
#define MAX_NUM_SDB 511
#define MIN_NUM_SDB 1
-#define ALERT_REQ_MASK 0x4000000000000000ul
-#define BUFFER_FULL_MASK 0x8000000000000000ul
-
DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
struct hws_execute_parms {
@@ -44,6 +41,7 @@ static DEFINE_MUTEX(hws_sem_oom);
static unsigned char hws_flush_all;
static unsigned int hws_oom;
+static unsigned int hws_alert;
static struct workqueue_struct *hws_wq;
static unsigned int hws_state;
@@ -65,43 +63,6 @@ static unsigned long interval;
static unsigned long min_sampler_rate;
static unsigned long max_sampler_rate;
-static int ssctl(void *buffer)
-{
- int cc;
-
- /* set in order to detect a program check */
- cc = 1;
-
- asm volatile(
- "0: .insn s,0xB2870000,0(%1)\n"
- "1: ipm %0\n"
- " srl %0,28\n"
- "2:\n"
- EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
- : "+d" (cc), "+a" (buffer)
- : "m" (*((struct hws_ssctl_request_block *)buffer))
- : "cc", "memory");
-
- return cc ? -EINVAL : 0 ;
-}
-
-static int qsi(void *buffer)
-{
- int cc;
- cc = 1;
-
- asm volatile(
- "0: .insn s,0xB2860000,0(%1)\n"
- "1: lhi %0,0\n"
- "2:\n"
- EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
- : "=d" (cc), "+a" (buffer)
- : "m" (*((struct hws_qsi_info_block *)buffer))
- : "cc", "memory");
-
- return cc ? -EINVAL : 0;
-}
-
static void execute_qsi(void *parms)
{
struct hws_execute_parms *ep = parms;
@@ -113,7 +74,7 @@ static void execute_ssctl(void *parms)
{
struct hws_execute_parms *ep = parms;
- ep->rc = ssctl(ep->buffer);
+ ep->rc = lsctl(ep->buffer);
}
static int smp_ctl_ssctl_stop(int cpu)
@@ -214,17 +175,6 @@ static int smp_ctl_qsi(int cpu)
return ep.rc;
}
-static inline unsigned long *trailer_entry_ptr(unsigned long v)
-{
- void *ret;
-
- ret = (void *)v;
- ret += PAGE_SIZE;
- ret -= sizeof(struct hws_trailer_entry);
-
- return (unsigned long *) ret;
-}
-
static void hws_ext_handler(struct ext_code ext_code,
unsigned int param32, unsigned long param64)
{
@@ -233,6 +183,9 @@ static void hws_ext_handler(struct ext_code ext_code,
if (!(param32 & CPU_MF_INT_SF_MASK))
return;
+ if (!hws_alert)
+ return;
+
inc_irq_stat(IRQEXT_CMS);
atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
@@ -256,16 +209,6 @@ static void init_all_cpu_buffers(void)
}
}
-static int is_link_entry(unsigned long *s)
-{
- return *s & 0x1ul ? 1 : 0;
-}
-
-static unsigned long *get_next_sdbt(unsigned long *s)
-{
- return (unsigned long *) (*s & ~0x1ul);
-}
-
static int prepare_cpu_buffers(void)
{
int cpu;
@@ -353,7 +296,7 @@ static int allocate_sdbt(int cpu)
}
*sdbt = sdb;
trailer = trailer_entry_ptr(*sdbt);
- *trailer = ALERT_REQ_MASK;
+ *trailer = SDB_TE_ALERT_REQ_MASK;
sdbt++;
mutex_unlock(&hws_sem_oom);
}
@@ -829,7 +772,7 @@ static void worker_on_interrupt(unsigned int cpu)
trailer = trailer_entry_ptr(*sdbt);
/* leave loop if no more work to do */
- if (!(*trailer & BUFFER_FULL_MASK)) {
+ if (!(*trailer & SDB_TE_BUFFER_FULL_MASK)) {
done = 1;
if (!hws_flush_all)
continue;
@@ -856,7 +799,7 @@ static void worker_on_interrupt(unsigned int cpu)
static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
unsigned long *dear)
{
- struct hws_data_entry *sample_data_ptr;
+ struct hws_basic_entry *sample_data_ptr;
unsigned long *trailer;
trailer = trailer_entry_ptr(*sdbt);
@@ -866,7 +809,7 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
trailer = dear;
}
- sample_data_ptr = (struct hws_data_entry *)(*sdbt);
+ sample_data_ptr = (struct hws_basic_entry *)(*sdbt);
while ((unsigned long *)sample_data_ptr < trailer) {
struct pt_regs *regs = NULL;
@@ -1002,6 +945,7 @@ int hwsampler_deallocate(void)
goto deallocate_exit;
irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+ hws_alert = 0;
deallocate_sdbt();
hws_state = HWS_DEALLOCATED;
@@ -1089,7 +1033,7 @@ int hwsampler_setup(void)
max_sampler_rate = cb->qsi.max_sampl_rate;
}
}
- register_external_interrupt(0x1407, hws_ext_handler);
+ register_external_irq(EXT_IRQ_MEASURE_ALERT, hws_ext_handler);
hws_state = HWS_DEALLOCATED;
rc = 0;
@@ -1116,6 +1060,7 @@ int hwsampler_shutdown(void)
if (hws_state == HWS_STOPPED) {
irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+ hws_alert = 0;
deallocate_sdbt();
}
if (hws_wq) {
@@ -1123,7 +1068,7 @@ int hwsampler_shutdown(void)
hws_wq = NULL;
}
- unregister_external_interrupt(0x1407, hws_ext_handler);
+ unregister_external_irq(EXT_IRQ_MEASURE_ALERT, hws_ext_handler);
hws_state = HWS_INIT;
rc = 0;
}
@@ -1190,6 +1135,7 @@ start_all_exit:
hws_oom = 1;
hws_flush_all = 0;
/* now let them in, 1407 CPUMF external interrupts */
+ hws_alert = 1;
irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
return 0;
diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h
index 0022e1ebfbd..a483d06f2fa 100644
--- a/arch/s390/oprofile/hwsampler.h
+++ b/arch/s390/oprofile/hwsampler.h
@@ -9,27 +9,7 @@
#define HWSAMPLER_H_
#include <linux/workqueue.h>
-
-struct hws_qsi_info_block /* QUERY SAMPLING information block */
-{ /* Bit(s) */
- unsigned int b0_13:14; /* 0-13: zeros */
- unsigned int as:1; /* 14: sampling authorisation control*/
- unsigned int b15_21:7; /* 15-21: zeros */
- unsigned int es:1; /* 22: sampling enable control */
- unsigned int b23_29:7; /* 23-29: zeros */
- unsigned int cs:1; /* 30: sampling activation control */
- unsigned int:1; /* 31: reserved */
- unsigned int bsdes:16; /* 4-5: size of sampling entry */
- unsigned int:16; /* 6-7: reserved */
- unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
- unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
- unsigned long tear; /* 24-31: TEAR contents */
- unsigned long dear; /* 32-39: DEAR contents */
- unsigned int rsvrd0; /* 40-43: reserved */
- unsigned int cpu_speed; /* 44-47: CPU speed */
- unsigned long long rsvrd1; /* 48-55: reserved */
- unsigned long long rsvrd2; /* 56-63: reserved */
-};
+#include <asm/cpu_mf.h>
struct hws_ssctl_request_block /* SET SAMPLING CONTROLS req block */
{ /* bytes 0 - 7 Bit(s) */
@@ -68,36 +48,6 @@ struct hws_cpu_buffer {
unsigned int stop_mode:1;
};
-struct hws_data_entry {
- unsigned int def:16; /* 0-15 Data Entry Format */
- unsigned int R:4; /* 16-19 reserved */
- unsigned int U:4; /* 20-23 Number of unique instruct. */
- unsigned int z:2; /* zeros */
- unsigned int T:1; /* 26 PSW DAT mode */
- unsigned int W:1; /* 27 PSW wait state */
- unsigned int P:1; /* 28 PSW Problem state */
- unsigned int AS:2; /* 29-30 PSW address-space control */
- unsigned int I:1; /* 31 entry valid or invalid */
- unsigned int:16;
- unsigned int prim_asn:16; /* primary ASN */
- unsigned long long ia; /* Instruction Address */
- unsigned long long gpp; /* Guest Program Parameter */
- unsigned long long hpp; /* Host Program Parameter */
-};
-
-struct hws_trailer_entry {
- unsigned int f:1; /* 0 - Block Full Indicator */
- unsigned int a:1; /* 1 - Alert request control */
- unsigned long:62; /* 2 - 63: Reserved */
- unsigned long overflow; /* 64 - sample Overflow count */
- unsigned long timestamp; /* 16 - time-stamp */
- unsigned long timestamp1; /* */
- unsigned long reserved1; /* 32 -Reserved */
- unsigned long reserved2; /* */
- unsigned long progusage1; /* 48 - reserved for programming use */
- unsigned long progusage2; /* */
-};
-
int hwsampler_setup(void);
int hwsampler_shutdown(void);
int hwsampler_allocate(unsigned long sdbt, unsigned long sdb);
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 04e1b6a8536..9ffe645d598 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -10,6 +10,7 @@
*/
#include <linux/oprofile.h>
+#include <linux/perf_event.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/fs.h>
@@ -67,6 +68,21 @@ module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
"(report cpu_type \"timer\"");
+static int __oprofile_hwsampler_start(void)
+{
+ int retval;
+
+ retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+ if (retval)
+ return retval;
+
+ retval = hwsampler_start_all(oprofile_hw_interval);
+ if (retval)
+ hwsampler_deallocate();
+
+ return retval;
+}
+
static int oprofile_hwsampler_start(void)
{
int retval;
@@ -76,13 +92,13 @@ static int oprofile_hwsampler_start(void)
if (!hwsampler_running)
return timer_ops.start();
- retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+ retval = perf_reserve_sampling();
if (retval)
return retval;
- retval = hwsampler_start_all(oprofile_hw_interval);
+ retval = __oprofile_hwsampler_start();
if (retval)
- hwsampler_deallocate();
+ perf_release_sampling();
return retval;
}
@@ -96,6 +112,7 @@ static void oprofile_hwsampler_stop(void)
hwsampler_stop_all();
hwsampler_deallocate();
+ perf_release_sampling();
return;
}
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index bf7c73d71ee..1df1d29ac81 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -407,8 +407,8 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
struct msi_msg msg;
int rc;
- if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
- return -EINVAL;
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
msi_vecs = min(nvec, ZPCI_MSI_VEC_MAX);
msi_vecs = min_t(unsigned int, msi_vecs, CONFIG_PCI_NR_MSI);
@@ -686,27 +686,13 @@ int pcibios_add_device(struct pci_dev *pdev)
int pcibios_enable_device(struct pci_dev *pdev, int mask)
{
struct zpci_dev *zdev = get_zdev(pdev);
- struct resource *res;
- u16 cmd;
- int i;
zdev->pdev = pdev;
zpci_debug_init_device(zdev);
zpci_fmb_enable_device(zdev);
zpci_map_resources(zdev);
- pci_read_config_word(pdev, PCI_COMMAND, &cmd);
- for (i = 0; i < PCI_BAR_COUNT; i++) {
- res = &pdev->resource[i];
-
- if (res->flags & IORESOURCE_IO)
- return -EINVAL;
-
- if (res->flags & IORESOURCE_MEM)
- cmd |= PCI_COMMAND_MEMORY;
- }
- pci_write_config_word(pdev, PCI_COMMAND, cmd);
- return 0;
+ return pci_enable_resources(pdev, mask);
}
void pcibios_disable_device(struct pci_dev *pdev)
@@ -919,17 +905,23 @@ static void zpci_mem_exit(void)
kmem_cache_destroy(zdev_fmb_cache);
}
-static unsigned int s390_pci_probe;
+static unsigned int s390_pci_probe = 1;
+static unsigned int s390_pci_initialized;
char * __init pcibios_setup(char *str)
{
- if (!strcmp(str, "on")) {
- s390_pci_probe = 1;
+ if (!strcmp(str, "off")) {
+ s390_pci_probe = 0;
return NULL;
}
return str;
}
+bool zpci_is_enabled(void)
+{
+ return s390_pci_initialized;
+}
+
static int __init pci_base_init(void)
{
int rc;
@@ -961,6 +953,7 @@ static int __init pci_base_init(void)
if (rc)
goto out_find;
+ s390_pci_initialized = 1;
return 0;
out_find:
@@ -978,5 +971,6 @@ subsys_initcall_sync(pci_base_init);
void zpci_rescan(void)
{
- clp_rescan_pci_devices_simple();
+ if (zpci_is_enabled())
+ clp_rescan_pci_devices_simple();
}
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 75c69b402e0..c5c66840ac0 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/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 9b83d080902..f91c0311980 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -206,11 +206,13 @@ static void dma_cleanup_tables(struct zpci_dev *zdev)
zdev->dma_table = NULL;
}
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
- int size)
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+ unsigned long start, int size)
{
- unsigned long boundary_size = 0x1000000;
+ unsigned long boundary_size;
+ boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+ PAGE_SIZE) >> PAGE_SHIFT;
return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
start, size, 0, boundary_size, 0);
}
@@ -285,7 +287,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
flags |= ZPCI_TABLE_PROTECTED;
if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) {
- atomic64_add(nr_pages, (atomic64_t *) &zdev->fmb->mapped_pages);
+ atomic64_add(nr_pages, &zdev->fmb->mapped_pages);
return dma_addr + (offset & ~PAGE_MASK);
}
@@ -313,7 +315,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
zpci_err_hex(&dma_addr, sizeof(dma_addr));
}
- atomic64_add(npages, (atomic64_t *) &zdev->fmb->unmapped_pages);
+ atomic64_add(npages, &zdev->fmb->unmapped_pages);
iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT;
dma_free_iommu(zdev, iommu_page_index, npages);
}
@@ -332,7 +334,6 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
if (!page)
return NULL;
- atomic64_add(size / PAGE_SIZE, (atomic64_t *) &zdev->fmb->allocated_pages);
pa = page_to_phys(page);
memset((void *) pa, 0, size);
@@ -343,6 +344,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
return NULL;
}
+ atomic64_add(size / PAGE_SIZE, &zdev->fmb->allocated_pages);
if (dma_handle)
*dma_handle = map;
return (void *) pa;
@@ -352,8 +354,11 @@ static void s390_dma_free(struct device *dev, size_t size,
void *pa, dma_addr_t dma_handle,
struct dma_attrs *attrs)
{
- s390_dma_unmap_pages(dev, dma_handle, PAGE_ALIGN(size),
- DMA_BIDIRECTIONAL, NULL);
+ struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+
+ size = PAGE_ALIGN(size);
+ atomic64_sub(size / PAGE_SIZE, &zdev->fmb->allocated_pages);
+ s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
free_pages((unsigned long) pa, get_order(size));
}
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 069607209a3..01e251b1da0 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -43,9 +43,8 @@ struct zpci_ccdf_avail {
u16 pec; /* PCI event code */
} __packed;
-void zpci_event_error(void *data)
+static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
{
- struct zpci_ccdf_err *ccdf = data;
struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
zpci_err("error CCDF:\n");
@@ -58,9 +57,14 @@ void zpci_event_error(void *data)
pci_name(zdev->pdev), ccdf->pec, ccdf->fid);
}
-void zpci_event_availability(void *data)
+void zpci_event_error(void *data)
+{
+ if (zpci_is_enabled())
+ __zpci_event_error(data);
+}
+
+static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
{
- struct zpci_ccdf_avail *ccdf = data;
struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
struct pci_dev *pdev = zdev ? zdev->pdev : NULL;
int ret;
@@ -99,8 +103,12 @@ void zpci_event_availability(void *data)
break;
case 0x0304: /* Configured -> Standby */
- if (pdev)
+ if (pdev) {
+ /* Give the driver a hint that the function is
+ * already unusable. */
+ pdev->error_state = pci_channel_io_perm_failure;
pci_stop_and_remove_bus_device(pdev);
+ }
zdev->fh = ccdf->fh;
zpci_disable_device(zdev);
@@ -110,6 +118,8 @@ void zpci_event_availability(void *data)
clp_rescan_pci_devices();
break;
case 0x0308: /* Standby -> Reserved */
+ if (!zdev)
+ break;
pci_stop_root_bus(zdev->bus);
pci_remove_root_bus(zdev->bus);
break;
@@ -117,3 +127,9 @@ void zpci_event_availability(void *data)
break;
}
}
+
+void zpci_event_availability(void *data)
+{
+ if (zpci_is_enabled())
+ __zpci_event_availability(data);
+}
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index cf8a12ff733..ab4a9139300 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -48,29 +48,27 @@ static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL);
-static void recover_callback(struct device *dev)
+static ssize_t store_recover(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct zpci_dev *zdev = get_zdev(pdev);
int ret;
+ if (!device_remove_file_self(dev, attr))
+ return count;
+
pci_stop_and_remove_bus_device(pdev);
ret = zpci_disable_device(zdev);
if (ret)
- return;
+ return ret;
ret = zpci_enable_device(zdev);
if (ret)
- return;
+ return ret;
pci_rescan_bus(zdev->bus);
-}
-
-static ssize_t store_recover(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- int rc = device_schedule_callback(dev, recover_callback);
- return rc ? rc : count;
+ return count;
}
static DEVICE_ATTR(recover, S_IWUSR, NULL, store_recover);