diff options
Diffstat (limited to 'arch/s390')
225 files changed, 19649 insertions, 11297 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b5ea38c2564..bb63499fc5d 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 @@ -60,86 +60,92 @@ config PCI_QUIRKS config S390 def_bool y - select USE_GENERIC_SMP_HELPERS if SMP - select GENERIC_CPU_DEVICES if !SMP - select HAVE_SYSCALL_WRAPPERS - select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST - select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_C_RECORDMCOUNT - select HAVE_SYSCALL_TRACEPOINTS - select SYSCTL_EXCEPTION_TRACE - select HAVE_DYNAMIC_FTRACE - select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_OPROFILE - select HAVE_KPROBES - select HAVE_KRETPROBES - select HAVE_KVM if 64BIT - select HAVE_ARCH_TRACEHOOK - select INIT_ALL_POSSIBLE - select HAVE_IRQ_WORK - select HAVE_PERF_EVENTS - select ARCH_HAVE_NMI_SAFE_CMPXCHG - select HAVE_DEBUG_KMEMLEAK - select HAVE_KERNEL_GZIP - select HAVE_KERNEL_BZIP2 - select HAVE_KERNEL_LZMA - select HAVE_KERNEL_LZO - select HAVE_KERNEL_XZ - select HAVE_ARCH_MUTEX_CPU_RELAX - select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 - select HAVE_BPF_JIT if 64BIT && PACK_STACK - select ARCH_SAVE_PAGE_KEYS if HIBERNATION select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select HAVE_MEMBLOCK - select HAVE_MEMBLOCK_NODE_MAP - select HAVE_CMPXCHG_LOCAL - select HAVE_CMPXCHG_DOUBLE - select HAVE_ALIGNED_STRUCT_PAGE if SLUB - select HAVE_VIRT_CPU_ACCOUNTING - select VIRT_CPU_ACCOUNTING - select ARCH_DISCARD_MEMBLOCK - select BUILDTIME_EXTABLE_SORT - select ARCH_INLINE_SPIN_TRYLOCK - select ARCH_INLINE_SPIN_TRYLOCK_BH - select ARCH_INLINE_SPIN_LOCK - select ARCH_INLINE_SPIN_LOCK_BH - select ARCH_INLINE_SPIN_LOCK_IRQ - select ARCH_INLINE_SPIN_LOCK_IRQSAVE - select ARCH_INLINE_SPIN_UNLOCK - select ARCH_INLINE_SPIN_UNLOCK_BH - select ARCH_INLINE_SPIN_UNLOCK_IRQ - select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE - select ARCH_INLINE_READ_TRYLOCK + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH select ARCH_INLINE_READ_LOCK_IRQ select ARCH_INLINE_READ_LOCK_IRQSAVE + select ARCH_INLINE_READ_TRYLOCK select ARCH_INLINE_READ_UNLOCK select ARCH_INLINE_READ_UNLOCK_BH select ARCH_INLINE_READ_UNLOCK_IRQ select ARCH_INLINE_READ_UNLOCK_IRQRESTORE - select ARCH_INLINE_WRITE_TRYLOCK + select ARCH_INLINE_SPIN_LOCK + select ARCH_INLINE_SPIN_LOCK_BH + select ARCH_INLINE_SPIN_LOCK_IRQ + select ARCH_INLINE_SPIN_LOCK_IRQSAVE + select ARCH_INLINE_SPIN_TRYLOCK + select ARCH_INLINE_SPIN_TRYLOCK_BH + select ARCH_INLINE_SPIN_UNLOCK + select ARCH_INLINE_SPIN_UNLOCK_BH + select ARCH_INLINE_SPIN_UNLOCK_IRQ + select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE select ARCH_INLINE_WRITE_LOCK select ARCH_INLINE_WRITE_LOCK_BH select ARCH_INLINE_WRITE_LOCK_IRQ select ARCH_INLINE_WRITE_LOCK_IRQSAVE + select ARCH_INLINE_WRITE_TRYLOCK select ARCH_INLINE_WRITE_UNLOCK select ARCH_INLINE_WRITE_UNLOCK_BH select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE - select HAVE_UID16 if 32BIT + select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION - select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT - select GENERIC_SMP_IDLE_THREAD - select GENERIC_TIME_VSYSCALL_OLD + select BUILDTIME_EXTABLE_SORT + select CLONE_BACKWARDS2 select GENERIC_CLOCKEVENTS - select KTIME_SCALAR if 32BIT + select GENERIC_CPU_DEVICES if !SMP + select GENERIC_FIND_FIRST_BIT + select GENERIC_SMP_IDLE_THREAD + select GENERIC_TIME_VSYSCALL + select HAVE_ALIGNED_STRUCT_PAGE if SLUB + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT + select HAVE_BPF_JIT if 64BIT && PACK_STACK + select HAVE_CMPXCHG_DOUBLE + select HAVE_CMPXCHG_LOCAL + select HAVE_C_RECORDMCOUNT + select HAVE_DEBUG_KMEMLEAK + select HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE_MCOUNT_RECORD + 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 + select HAVE_KERNEL_LZMA + select HAVE_KERNEL_LZO + select HAVE_KERNEL_XZ + select HAVE_KPROBES + select HAVE_KRETPROBES + select HAVE_KVM if 64BIT + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select HAVE_MEMBLOCK_PHYS_MAP select HAVE_MOD_ARCH_SPECIFIC + select HAVE_OPROFILE + select HAVE_PERF_EVENTS + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_UID16 if 32BIT + select HAVE_VIRT_CPU_ACCOUNTING + select KTIME_SCALAR if 32BIT select MODULES_USE_ELF_RELA - select CLONE_BACKWARDS2 + select NO_BOOTMEM + select OLD_SIGACTION + select OLD_SIGSUSPEND3 + select SYSCTL_EXCEPTION_TRACE + select TTY + select VIRT_CPU_ACCOUNTING + select VIRT_TO_BUS config SCHED_OMIT_FRAME_POINTER def_bool y @@ -225,11 +231,73 @@ config MARCH_Z196 not work on older machines. config MARCH_ZEC12 - bool "IBM zEC12" + bool "IBM zBC12 and zEC12" select HAVE_MARCH_ZEC12_FEATURES if 64BIT help - Select this to enable optimizations for IBM zEC12 (2827 series). The - kernel will be slightly faster but will not work on older machines. + Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and + 2827 series). The kernel will be slightly faster but will not work on + older machines. + +endchoice + +config MARCH_G5_TUNE + def_bool TUNE_G5 || MARCH_G5 && TUNE_DEFAULT + +config MARCH_Z900_TUNE + def_bool TUNE_Z900 || MARCH_Z900 && TUNE_DEFAULT + +config MARCH_Z990_TUNE + def_bool TUNE_Z990 || MARCH_Z990 && TUNE_DEFAULT + +config MARCH_Z9_109_TUNE + def_bool TUNE_Z9_109 || MARCH_Z9_109 && TUNE_DEFAULT + +config MARCH_Z10_TUNE + def_bool TUNE_Z10 || MARCH_Z10 && TUNE_DEFAULT + +config MARCH_Z196_TUNE + def_bool TUNE_Z196 || MARCH_Z196 && TUNE_DEFAULT + +config MARCH_ZEC12_TUNE + def_bool TUNE_ZEC12 || MARCH_ZEC12 && TUNE_DEFAULT + +choice + prompt "Tune code generation" + default TUNE_DEFAULT + help + Cause the compiler to tune (-mtune) the generated code for a machine. + This will make the code run faster on the selected machine but + somewhat slower on other machines. + This option only changes how the compiler emits instructions, not the + selection of instructions itself, so the resulting kernel will run on + all other machines. + +config TUNE_DEFAULT + bool "Default" + help + Tune the generated code for the target processor for which the kernel + will be compiled. + +config TUNE_G5 + bool "System/390 model G5 and G6" + +config TUNE_Z900 + bool "IBM zSeries model z800 and z900" + +config TUNE_Z990 + bool "IBM zSeries model z890 and z990" + +config TUNE_Z9_109 + bool "IBM System z9" + +config TUNE_Z10 + bool "IBM System z10" + +config TUNE_Z196 + bool "IBM zEnterprise 114 and 196" + +config TUNE_ZEC12 + bool "IBM zBC12 and zEC12" endchoice @@ -249,6 +317,7 @@ config COMPAT depends on 64BIT select COMPAT_BINFMT_ELF if BINFMT_ELF select ARCH_WANT_OLD_COMPAT_IPC + select COMPAT_OLD_SIGACTION help Select this option if you want to enable your system kernel to handle system-calls from ELF binaries for 31 bit ESA. This option @@ -269,10 +338,10 @@ 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 @@ -281,14 +350,14 @@ config SMP Even if you don't know what to do here, say Y. config NR_CPUS - int "Maximum number of CPUs (2-64)" - range 2 64 + int "Maximum number of CPUs (2-256)" + range 2 256 depends on SMP default "32" if !64BIT default "64" if 64BIT help This allows you to specify the maximum number of CPUs which this - kernel will support. The maximum supported value is 64 and the + kernel will support. The maximum supported value is 256 and the minimum value which makes sense is 2. This is purely to save memory - each supported CPU adds @@ -298,7 +367,6 @@ config HOTPLUG_CPU def_bool y prompt "Support for hot-pluggable CPUs" depends on SMP - select HOTPLUG help Say Y here to be able to turn CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu/cpu#. @@ -351,6 +419,10 @@ 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" @@ -371,19 +443,6 @@ config PACK_STACK Say Y if you are unsure. -config SMALL_STACK - def_bool n - prompt "Use 8kb for kernel stack instead of 16kb" - depends on PACK_STACK && 64BIT && !LOCKDEP - help - If you say Y here and the compiler supports the -mkernel-backchain - option the kernel will use a smaller kernel stack size. The reduced - size is 8kb instead of 16kb. This allows to run more threads on a - system and reduces the pressure on the memory management for higher - order page allocations. - - Say N if you are unsure. - config CHECK_STACK def_bool y prompt "Detect kernel stack overflow" @@ -439,7 +498,6 @@ menuconfig PCI bool "PCI support" default n depends on 64BIT - select ARCH_SUPPORTS_MSI select PCI_MSI help Enable PCI support. @@ -454,6 +512,16 @@ config PCI_NR_FUNCTIONS This allows you to specify the maximum number of PCI functions which this kernel will support. +config PCI_NR_MSI + int "Maximum number of MSI interrupts (64-32768)" + range 64 32768 + default "256" + help + This defines the number of virtual interrupts the kernel will + provide for MSI interrupts. If you configure your system to have + too few drivers will fail to allocate MSI interrupts for all + PCI devices. + source "drivers/pci/Kconfig" source "drivers/pci/pcie/Kconfig" source "drivers/pci/hotplug/Kconfig" @@ -530,15 +598,9 @@ config CRASH_DUMP Crash dump kernels are loaded in the main kernel with kexec-tools into a specially reserved region and then later executed after a crash by kdump/kexec. - For more details see Documentation/kdump/kdump.txt - -config ZFCPDUMP - def_bool n - prompt "zfcpdump support" - select 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. + This option also enables s390 zfcpdump. + See also <file:Documentation/s390/zfcpdump.txt> endmenu @@ -718,8 +780,9 @@ source "arch/s390/kvm/Kconfig" config S390_GUEST def_bool y - prompt "s390 support for virtio devices (EXPERIMENTAL)" - depends on 64BIT && EXPERIMENTAL + prompt "s390 support for virtio devices" + depends on 64BIT + select TTY select VIRTUALIZATION select VIRTIO select VIRTIO_CONSOLE diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index fc32a2df497..c56878e1245 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -17,20 +17,6 @@ config STRICT_DEVMEM If you are unsure, say Y. -config DEBUG_STRICT_USER_COPY_CHECKS - def_bool n - prompt "Strict user copy size checks" - ---help--- - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time warnings. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, or if you run an older (pre 4.4) gcc, say N. - config S390_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7e3ce78d429..874e6d6e9c5 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -35,13 +35,21 @@ endif export LD_BFD -cflags-$(CONFIG_MARCH_G5) += $(call cc-option,-march=g5) -cflags-$(CONFIG_MARCH_Z900) += $(call cc-option,-march=z900) -cflags-$(CONFIG_MARCH_Z990) += $(call cc-option,-march=z990) -cflags-$(CONFIG_MARCH_Z9_109) += $(call cc-option,-march=z9-109) -cflags-$(CONFIG_MARCH_Z10) += $(call cc-option,-march=z10) -cflags-$(CONFIG_MARCH_Z196) += $(call cc-option,-march=z196) -cflags-$(CONFIG_MARCH_ZEC12) += $(call cc-option,-march=zEC12) +cflags-$(CONFIG_MARCH_G5) += -march=g5 +cflags-$(CONFIG_MARCH_Z900) += -march=z900 +cflags-$(CONFIG_MARCH_Z990) += -march=z990 +cflags-$(CONFIG_MARCH_Z9_109) += -march=z9-109 +cflags-$(CONFIG_MARCH_Z10) += -march=z10 +cflags-$(CONFIG_MARCH_Z196) += -march=z196 +cflags-$(CONFIG_MARCH_ZEC12) += -march=zEC12 + +cflags-$(CONFIG_MARCH_G5_TUNE) += -mtune=g5 +cflags-$(CONFIG_MARCH_Z900_TUNE) += -mtune=z900 +cflags-$(CONFIG_MARCH_Z990_TUNE) += -mtune=z990 +cflags-$(CONFIG_MARCH_Z9_109_TUNE) += -mtune=z9-109 +cflags-$(CONFIG_MARCH_Z10_TUNE) += -mtune=z10 +cflags-$(CONFIG_MARCH_Z196_TUNE) += -mtune=z196 +cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 #KBUILD_IMAGE is necessary for make rpm KBUILD_IMAGE :=arch/s390/boot/image @@ -55,22 +63,12 @@ cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls ifeq ($(call cc-option-yn,-mkernel-backchain),y) cflags-$(CONFIG_PACK_STACK) += -mkernel-backchain -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -ifdef CONFIG_SMALL_STACK -STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) ) -endif endif # new style option for packed stacks ifeq ($(call cc-option-yn,-mpacked-stack),y) cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -cflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -aflags-$(CONFIG_SMALL_STACK) += -D__SMALL_STACK -ifdef CONFIG_SMALL_STACK -STACK_SIZE := $(shell echo $$(($(STACK_SIZE)/2)) ) -endif endif ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y) diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index bae0f402bf2..47c8630c93c 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -48,9 +48,9 @@ static struct platform_device *appldata_pdev; * /proc entries (sysctl) */ static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata"; -static int appldata_timer_handler(ctl_table *ctl, int write, +static int appldata_timer_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -static int appldata_interval_handler(ctl_table *ctl, int write, +static int appldata_interval_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -201,10 +201,10 @@ static void __appldata_vtimer_setup(int cmd) * Start/Stop timer, show status of timer (0 = not active, 1 = active) */ static int -appldata_timer_handler(ctl_table *ctl, int write, +appldata_timer_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int len; + unsigned int len; char buf[2]; if (!*lenp || *ppos) { @@ -212,7 +212,9 @@ appldata_timer_handler(ctl_table *ctl, int write, return 0; } if (!write) { - len = sprintf(buf, appldata_timer_active ? "1\n" : "0\n"); + strncpy(buf, appldata_timer_active ? "1\n" : "0\n", + ARRAY_SIZE(buf)); + len = strnlen(buf, ARRAY_SIZE(buf)); if (len > *lenp) len = *lenp; if (copy_to_user(buffer, buf, len)) @@ -241,10 +243,11 @@ out: * current timer interval. */ static int -appldata_interval_handler(ctl_table *ctl, int write, +appldata_interval_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int len, interval; + unsigned int len; + int interval; char buf[16]; if (!*lenp || *ppos) { @@ -284,11 +287,12 @@ out: * monitoring (0 = not in process, 1 = in process) */ static int -appldata_generic_handler(ctl_table *ctl, int write, +appldata_generic_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct appldata_ops *ops = NULL, *tmp_ops; - int rc, len, found; + unsigned int len; + int rc, found; char buf[2]; struct list_head *lh; @@ -317,7 +321,8 @@ appldata_generic_handler(ctl_table *ctl, int write, return 0; } if (!write) { - len = sprintf(buf, ops->active ? "1\n" : "0\n"); + strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf)); + len = strnlen(buf, ARRAY_SIZE(buf)); if (len > *lenp) len = *lenp; if (copy_to_user(buffer, buf, len)) { @@ -524,6 +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_mem.c b/arch/s390/appldata/appldata_mem.c index 02d9a1cf505..edcf2a70694 100644 --- a/arch/s390/appldata/appldata_mem.c +++ b/arch/s390/appldata/appldata_mem.c @@ -13,6 +13,7 @@ #include <linux/kernel_stat.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/slab.h> #include <asm/io.h> #include "appldata.h" @@ -32,7 +33,7 @@ * book: * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml */ -static struct appldata_mem_data { +struct appldata_mem_data { u64 timestamp; u32 sync_count_1; /* after VM collected the record data, */ u32 sync_count_2; /* sync_count_1 and sync_count_2 should be the @@ -63,7 +64,7 @@ static struct appldata_mem_data { u64 pgmajfault; /* page faults (major only) */ // <-- New in 2.6 -} __attribute__((packed)) appldata_mem_data; +} __packed; /* @@ -108,7 +109,7 @@ static void appldata_get_mem_data(void *data) mem_data->totalswap = P2K(val.totalswap); mem_data->freeswap = P2K(val.freeswap); - mem_data->timestamp = get_clock(); + mem_data->timestamp = get_tod_clock(); mem_data->sync_count_2++; } @@ -118,7 +119,6 @@ static struct appldata_ops ops = { .record_nr = APPLDATA_RECORD_MEM_ID, .size = sizeof(struct appldata_mem_data), .callback = &appldata_get_mem_data, - .data = &appldata_mem_data, .owner = THIS_MODULE, .mod_lvl = {0xF0, 0xF0}, /* EBCDIC "00" */ }; @@ -131,7 +131,17 @@ static struct appldata_ops ops = { */ static int __init appldata_mem_init(void) { - return appldata_register_ops(&ops); + int ret; + + ops.data = kzalloc(sizeof(struct appldata_mem_data), GFP_KERNEL); + if (!ops.data) + return -ENOMEM; + + ret = appldata_register_ops(&ops); + if (ret) + kfree(ops.data); + + return ret; } /* @@ -142,6 +152,7 @@ static int __init appldata_mem_init(void) static void __exit appldata_mem_exit(void) { appldata_unregister_ops(&ops); + kfree(ops.data); } diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c index 1370e358d49..66037d2622b 100644 --- a/arch/s390/appldata/appldata_net_sum.c +++ b/arch/s390/appldata/appldata_net_sum.c @@ -29,7 +29,7 @@ * book: * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml */ -static struct appldata_net_sum_data { +struct appldata_net_sum_data { u64 timestamp; u32 sync_count_1; /* after VM collected the record data, */ u32 sync_count_2; /* sync_count_1 and sync_count_2 should be the @@ -51,7 +51,7 @@ static struct appldata_net_sum_data { u64 rx_dropped; /* no space in linux buffers */ u64 tx_dropped; /* no space available in linux */ u64 collisions; /* collisions while transmitting */ -} __attribute__((packed)) appldata_net_sum_data; +} __packed; /* @@ -111,7 +111,7 @@ static void appldata_get_net_sum_data(void *data) net_data->tx_dropped = tx_dropped; net_data->collisions = collisions; - net_data->timestamp = get_clock(); + net_data->timestamp = get_tod_clock(); net_data->sync_count_2++; } @@ -121,7 +121,6 @@ static struct appldata_ops ops = { .record_nr = APPLDATA_RECORD_NET_SUM_ID, .size = sizeof(struct appldata_net_sum_data), .callback = &appldata_get_net_sum_data, - .data = &appldata_net_sum_data, .owner = THIS_MODULE, .mod_lvl = {0xF0, 0xF0}, /* EBCDIC "00" */ }; @@ -134,7 +133,17 @@ static struct appldata_ops ops = { */ static int __init appldata_net_init(void) { - return appldata_register_ops(&ops); + int ret; + + ops.data = kzalloc(sizeof(struct appldata_net_sum_data), GFP_KERNEL); + if (!ops.data) + return -ENOMEM; + + ret = appldata_register_ops(&ops); + if (ret) + kfree(ops.data); + + return ret; } /* @@ -145,6 +154,7 @@ static int __init appldata_net_init(void) static void __exit appldata_net_exit(void) { appldata_unregister_ops(&ops); + kfree(ops.data); } diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 87521ba682e..69b23b25ac3 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -156,7 +156,7 @@ static void appldata_get_os_data(void *data) } ops.size = new_size; } - os_data->timestamp = get_clock(); + os_data->timestamp = get_tod_clock(); os_data->sync_count_2++; } @@ -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/boot/Makefile b/arch/s390/boot/Makefile index f2737a005af..9a42ecec564 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -21,6 +21,6 @@ $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed $@ -install: $(CONFIGURE) $(obj)/image - sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/image \ +install: $(CONFIGURE) $(obj)/bzImage + sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 3ad8f61c998..f90d1fc6d60 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -6,13 +6,13 @@ BITS := $(if $(CONFIG_64BIT),64,31) -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \ - vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo misc.o piggy.o \ - sizes.h head$(BITS).o +targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 +targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 +targets += misc.o piggy.o sizes.h head$(BITS).o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS += $(cflags-y) +KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks KBUILD_CFLAGS += $(call cc-option,-mpacked-stack) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) @@ -48,6 +48,7 @@ vmlinux.bin.all-y := $(obj)/vmlinux.bin suffix-$(CONFIG_KERNEL_GZIP) := gz suffix-$(CONFIG_KERNEL_BZIP2) := bz2 +suffix-$(CONFIG_KERNEL_LZ4) := lz4 suffix-$(CONFIG_KERNEL_LZMA) := lzma suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_XZ) := xz @@ -56,6 +57,8 @@ $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) $(call if_changed,gzip) $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) + $(call if_changed,lz4) $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) $(call if_changed,lzma) $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index c4c6a1cf221..57cbaff1f39 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -47,6 +47,10 @@ static unsigned long free_mem_end_ptr; #include "../../../../lib/decompress_bunzip2.c" #endif +#ifdef CONFIG_KERNEL_LZ4 +#include "../../../../lib/decompress_unlz4.c" +#endif + #ifdef CONFIG_KERNEL_LZMA #include "../../../../lib/decompress_unlzma.c" #endif diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig new file mode 100644 index 00000000000..fd09a10a2b5 --- /dev/null +++ b/arch/s390/configs/default_defconfig @@ -0,0 +1,687 @@ +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_FHANDLE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_RCU_FAST_NO_HZ=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +CONFIG_CGROUP_PERF=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_CGROUP=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=m +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_BLK_DEV_INTEGRITY=y +CONFIG_BLK_DEV_THROTTLING=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_IBM_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_CFQ_GROUP_IOSCHED=y +CONFIG_DEFAULT_DEADLINE=y +CONFIG_MARCH_Z196=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=256 +CONFIG_PREEMPT=y +CONFIG_HZ_100=y +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_PCI=y +CONFIG_PCI_DEBUG=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y +CONFIG_CHSC_SCH=y +CONFIG_CRASH_DUMP=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=m +CONFIG_HIBERNATION=y +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=m +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=m +CONFIG_XFRM_USER=m +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_NET_IPVTI=m +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_XFRM_MODE_TRANSPORT=m +CONFIG_INET_XFRM_MODE_TUNNEL=m +CONFIG_INET_XFRM_MODE_BEET=m +CONFIG_INET_DIAG=m +CONFIG_INET_UDP_DIAG=m +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_HSTCP=m +CONFIG_TCP_CONG_HYBLA=m +CONFIG_TCP_CONG_SCALABLE=m +CONFIG_TCP_CONG_LP=m +CONFIG_TCP_CONG_VENO=m +CONFIG_TCP_CONG_YEAH=m +CONFIG_TCP_CONG_ILLINOIS=m +CONFIG_IPV6=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_MIP6=m +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 +CONFIG_IPV6_SUBTREES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_TIMEOUT=y +CONFIG_NF_CONNTRACK_TIMESTAMP=y +CONFIG_NF_CT_PROTO_DCCP=m +CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CONNTRACK_AMANDA=m +CONFIG_NF_CONNTRACK_FTP=m +CONFIG_NF_CONNTRACK_H323=m +CONFIG_NF_CONNTRACK_IRC=m +CONFIG_NF_CONNTRACK_NETBIOS_NS=m +CONFIG_NF_CONNTRACK_SNMP=m +CONFIG_NF_CONNTRACK_PPTP=m +CONFIG_NF_CONNTRACK_SANE=m +CONFIG_NF_CONNTRACK_SIP=m +CONFIG_NF_CONNTRACK_TFTP=m +CONFIG_NF_CT_NETLINK=m +CONFIG_NF_CT_NETLINK_TIMEOUT=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 +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m +CONFIG_NETFILTER_XT_TARGET_CONNMARK=m +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m +CONFIG_NETFILTER_XT_TARGET_CT=m +CONFIG_NETFILTER_XT_TARGET_DSCP=m +CONFIG_NETFILTER_XT_TARGET_HMARK=m +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NFLOG=m +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_TEE=m +CONFIG_NETFILTER_XT_TARGET_TPROXY=m +CONFIG_NETFILTER_XT_TARGET_TRACE=m +CONFIG_NETFILTER_XT_TARGET_SECMARK=m +CONFIG_NETFILTER_XT_TARGET_TCPMSS=m +CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CLUSTER=m +CONFIG_NETFILTER_XT_MATCH_COMMENT=m +CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m +CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m +CONFIG_NETFILTER_XT_MATCH_CONNMARK=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NETFILTER_XT_MATCH_CPU=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m +CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m +CONFIG_NETFILTER_XT_MATCH_DSCP=m +CONFIG_NETFILTER_XT_MATCH_ESP=m +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m +CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPRANGE=m +CONFIG_NETFILTER_XT_MATCH_IPVS=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_LIMIT=m +CONFIG_NETFILTER_XT_MATCH_MAC=m +CONFIG_NETFILTER_XT_MATCH_MARK=m +CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m +CONFIG_NETFILTER_XT_MATCH_NFACCT=m +CONFIG_NETFILTER_XT_MATCH_OSF=m +CONFIG_NETFILTER_XT_MATCH_OWNER=m +CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m +CONFIG_NETFILTER_XT_MATCH_QUOTA=m +CONFIG_NETFILTER_XT_MATCH_RATEEST=m +CONFIG_NETFILTER_XT_MATCH_REALM=m +CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m +CONFIG_NETFILTER_XT_MATCH_STATE=m +CONFIG_NETFILTER_XT_MATCH_STATISTIC=m +CONFIG_NETFILTER_XT_MATCH_STRING=m +CONFIG_NETFILTER_XT_MATCH_TCPMSS=m +CONFIG_NETFILTER_XT_MATCH_TIME=m +CONFIG_NETFILTER_XT_MATCH_U32=m +CONFIG_IP_SET=m +CONFIG_IP_SET_BITMAP_IP=m +CONFIG_IP_SET_BITMAP_IPMAC=m +CONFIG_IP_SET_BITMAP_PORT=m +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 +CONFIG_IP_VS=m +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m +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_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 +CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_CLUSTERIP=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_TTL=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_SECURITY=m +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 +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_MH=m +CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_TARGET_HL=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_RAW=m +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 +CONFIG_RDS_TCP=m +CONFIG_RDS_DEBUG=y +CONFIG_L2TP=m +CONFIG_L2TP_DEBUGFS=m +CONFIG_L2TP_V3=y +CONFIG_L2TP_IP=m +CONFIG_L2TP_ETH=m +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_MULTIQ=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFB=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_MQPRIO=m +CONFIG_NET_SCH_CHOKE=m +CONFIG_NET_SCH_QFQ=m +CONFIG_NET_SCH_CODEL=m +CONFIG_NET_SCH_FQ_CODEL=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_SCH_PLUG=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +CONFIG_CLS_U32_PERF=y +CONFIG_CLS_U32_MARK=y +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 +CONFIG_GACT_PROB=y +CONFIG_NET_ACT_MIRRED=m +CONFIG_NET_ACT_IPT=m +CONFIG_NET_ACT_NAT=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_SIMP=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_CSUM=m +CONFIG_DNS_RESOLVER=y +CONFIG_BPF_JIT=y +CONFIG_NET_PKTGEN=m +CONFIG_NET_TCPPROBE=m +CONFIG_DEVTMPFS=y +CONFIG_CONNECTOR=y +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_OSD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=32768 +CONFIG_BLK_DEV_XIP=y +CONFIG_CDROM_PKTCDVD=m +CONFIG_ATA_OVER_ETH=m +CONFIG_VIRTIO_BLK=y +CONFIG_ENCLOSURE_SERVICES=m +CONFIG_RAID_ATTRS=m +CONFIG_SCSI=y +CONFIG_SCSI_TGT=m +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=m +CONFIG_CHR_DEV_OSST=m +CONFIG_BLK_DEV_SR=m +CONFIG_CHR_DEV_SG=y +CONFIG_CHR_DEV_SCH=m +CONFIG_SCSI_ENCLOSURE=m +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_SPI_ATTRS=m +CONFIG_SCSI_SAS_LIBSAS=m +CONFIG_SCSI_SRP_ATTRS=m +CONFIG_SCSI_SRP_TGT_ATTRS=y +CONFIG_ISCSI_TCP=m +CONFIG_LIBFCOE=m +CONFIG_SCSI_DEBUG=m +CONFIG_ZFCP=y +CONFIG_SCSI_VIRTIO=m +CONFIG_SCSI_DH=m +CONFIG_SCSI_DH_RDAC=m +CONFIG_SCSI_DH_HP_SW=m +CONFIG_SCSI_DH_EMC=m +CONFIG_SCSI_DH_ALUA=m +CONFIG_SCSI_OSD_INITIATOR=m +CONFIG_SCSI_OSD_ULD=m +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=m +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_QL=m +CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_DELAY=m +CONFIG_DM_UEVENT=y +CONFIG_DM_FLAKEY=m +CONFIG_DM_VERITY=m +CONFIG_DM_SWITCH=m +CONFIG_NETDEVICES=y +CONFIG_BONDING=m +CONFIG_DUMMY=m +CONFIG_EQUALIZER=m +CONFIG_IFB=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_TUN=m +CONFIG_VETH=m +CONFIG_VIRTIO_NET=m +CONFIG_NLMON=m +CONFIG_VHOST_NET=m +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +CONFIG_MLX4_EN=m +# CONFIG_NET_VENDOR_NATSEMI is not set +CONFIG_PPP=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_MPPE=m +CONFIG_PPPOE=m +CONFIG_PPTP=m +CONFIG_PPPOL2TP=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +CONFIG_DEVPTS_MULTIPLE_INSTANCES=y +CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_HW_RANDOM_VIRTIO=m +CONFIG_RAW_DRIVER=m +CONFIG_HANGCHECK_TIMER=m +CONFIG_TN3270_FS=y +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_NOWAYOUT=y +CONFIG_SOFT_WATCHDOG=m +CONFIG_DIAG288_WATCHDOG=m +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_INFINIBAND=m +CONFIG_INFINIBAND_USER_ACCESS=m +CONFIG_MLX4_INFINIBAND=m +CONFIG_VIRTIO_BALLOON=m +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT2_FS_XIP=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_JBD_DEBUG=y +CONFIG_JBD2_DEBUG=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +CONFIG_JFS_SECURITY=y +CONFIG_JFS_STATISTICS=y +CONFIG_XFS_FS=m +CONFIG_XFS_QUOTA=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_XFS_RT=y +CONFIG_XFS_DEBUG=y +CONFIG_GFS2_FS=m +CONFIG_OCFS2_FS=m +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_NILFS2_FS=m +CONFIG_FANOTIFY=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +CONFIG_QFMT_V1=m +CONFIG_QFMT_V2=m +CONFIG_AUTOFS4_FS=m +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_FSCACHE=m +CONFIG_CACHEFILES=m +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_NTFS_FS=m +CONFIG_NTFS_RW=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_CONFIGFS_FS=m +CONFIG_ECRYPT_FS=m +CONFIG_CRAMFS=m +CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y +CONFIG_ROMFS_FS=m +CONFIG_NFS_FS=m +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=m +CONFIG_NFS_SWAP=y +CONFIG_NFSD=m +CONFIG_NFSD_V3_ACL=y +CONFIG_NFSD_V4=y +CONFIG_NFSD_V4_SECURITY_LABEL=y +CONFIG_CIFS=m +CONFIG_CIFS_STATS=y +CONFIG_CIFS_STATS2=y +CONFIG_CIFS_WEAK_PW_HASH=y +CONFIG_CIFS_UPCALL=y +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +# CONFIG_CIFS_DEBUG is not set +CONFIG_CIFS_DFS_UPCALL=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_ASCII=m +CONFIG_NLS_ISO8859_1=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_UTF8=m +CONFIG_DLM=m +CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +CONFIG_READABLE_ASM=y +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 +CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_LOCKING_API_SELFTESTS=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_DEBUG_CREDENTIALS=y +CONFIG_PROVE_RCU=y +CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_CPU_STALL_TIMEOUT=300 +CONFIG_NOTIFIER_ERROR_INJECTION=m +CONFIG_CPU_NOTIFIER_ERROR_INJECT=m +CONFIG_PM_NOTIFIER_ERROR_INJECT=m +CONFIG_FAULT_INJECTION=y +CONFIG_FAILSLAB=y +CONFIG_FAIL_PAGE_ALLOC=y +CONFIG_FAIL_MAKE_REQUEST=y +CONFIG_FAIL_IO_TIMEOUT=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y +CONFIG_LATENCYTOP=y +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=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 +CONFIG_S390_PTDUMP=y +CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEYS_DEBUG_PROC_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_IMA=y +CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_CCM=m +CONFIG_CRYPTO_GCM=m +CONFIG_CRYPTO_CTS=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_ZLIB=y +CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_ZCRYPT=m +CONFIG_CRYPTO_SHA1_S390=m +CONFIG_CRYPTO_SHA256_S390=m +CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_DES_S390=m +CONFIG_CRYPTO_AES_S390=m +CONFIG_CRYPTO_GHASH_S390=m +CONFIG_ASYMMETRIC_KEY_TYPE=m +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m +CONFIG_X509_CERTIFICATE_PARSER=m +CONFIG_CRC7=m +CONFIG_CRC8=m +CONFIG_XZ_DEC_X86=y +CONFIG_XZ_DEC_POWERPC=y +CONFIG_XZ_DEC_IA64=y +CONFIG_XZ_DEC_ARM=y +CONFIG_XZ_DEC_ARMTHUMB=y +CONFIG_XZ_DEC_SPARC=y +CONFIG_CORDIC=m +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_KVM_S390_UCONTROL=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig new file mode 100644 index 00000000000..b061180d354 --- /dev/null +++ b/arch/s390/configs/gcov_defconfig @@ -0,0 +1,640 @@ +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_FHANDLE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_RCU_FAST_NO_HZ=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +CONFIG_CGROUP_PERF=y +CONFIG_BLK_CGROUP=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=m +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_GCOV_KERNEL=y +CONFIG_GCOV_PROFILE_ALL=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_BLK_DEV_INTEGRITY=y +CONFIG_BLK_DEV_THROTTLING=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_IBM_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_CFQ_GROUP_IOSCHED=y +CONFIG_DEFAULT_DEADLINE=y +CONFIG_MARCH_Z196=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=256 +CONFIG_HZ_100=y +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_PCI=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y +CONFIG_CHSC_SCH=y +CONFIG_CRASH_DUMP=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=m +CONFIG_HIBERNATION=y +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=m +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=m +CONFIG_XFRM_USER=m +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_NET_IPVTI=m +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_XFRM_MODE_TRANSPORT=m +CONFIG_INET_XFRM_MODE_TUNNEL=m +CONFIG_INET_XFRM_MODE_BEET=m +CONFIG_INET_DIAG=m +CONFIG_INET_UDP_DIAG=m +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_HSTCP=m +CONFIG_TCP_CONG_HYBLA=m +CONFIG_TCP_CONG_SCALABLE=m +CONFIG_TCP_CONG_LP=m +CONFIG_TCP_CONG_VENO=m +CONFIG_TCP_CONG_YEAH=m +CONFIG_TCP_CONG_ILLINOIS=m +CONFIG_IPV6=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_MIP6=m +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 +CONFIG_IPV6_SUBTREES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_TIMEOUT=y +CONFIG_NF_CONNTRACK_TIMESTAMP=y +CONFIG_NF_CT_PROTO_DCCP=m +CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CONNTRACK_AMANDA=m +CONFIG_NF_CONNTRACK_FTP=m +CONFIG_NF_CONNTRACK_H323=m +CONFIG_NF_CONNTRACK_IRC=m +CONFIG_NF_CONNTRACK_NETBIOS_NS=m +CONFIG_NF_CONNTRACK_SNMP=m +CONFIG_NF_CONNTRACK_PPTP=m +CONFIG_NF_CONNTRACK_SANE=m +CONFIG_NF_CONNTRACK_SIP=m +CONFIG_NF_CONNTRACK_TFTP=m +CONFIG_NF_CT_NETLINK=m +CONFIG_NF_CT_NETLINK_TIMEOUT=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 +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m +CONFIG_NETFILTER_XT_TARGET_CONNMARK=m +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m +CONFIG_NETFILTER_XT_TARGET_CT=m +CONFIG_NETFILTER_XT_TARGET_DSCP=m +CONFIG_NETFILTER_XT_TARGET_HMARK=m +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NFLOG=m +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_TEE=m +CONFIG_NETFILTER_XT_TARGET_TPROXY=m +CONFIG_NETFILTER_XT_TARGET_TRACE=m +CONFIG_NETFILTER_XT_TARGET_SECMARK=m +CONFIG_NETFILTER_XT_TARGET_TCPMSS=m +CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CLUSTER=m +CONFIG_NETFILTER_XT_MATCH_COMMENT=m +CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m +CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m +CONFIG_NETFILTER_XT_MATCH_CONNMARK=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NETFILTER_XT_MATCH_CPU=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m +CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m +CONFIG_NETFILTER_XT_MATCH_DSCP=m +CONFIG_NETFILTER_XT_MATCH_ESP=m +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m +CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPRANGE=m +CONFIG_NETFILTER_XT_MATCH_IPVS=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_LIMIT=m +CONFIG_NETFILTER_XT_MATCH_MAC=m +CONFIG_NETFILTER_XT_MATCH_MARK=m +CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m +CONFIG_NETFILTER_XT_MATCH_NFACCT=m +CONFIG_NETFILTER_XT_MATCH_OSF=m +CONFIG_NETFILTER_XT_MATCH_OWNER=m +CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m +CONFIG_NETFILTER_XT_MATCH_QUOTA=m +CONFIG_NETFILTER_XT_MATCH_RATEEST=m +CONFIG_NETFILTER_XT_MATCH_REALM=m +CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m +CONFIG_NETFILTER_XT_MATCH_STATE=m +CONFIG_NETFILTER_XT_MATCH_STATISTIC=m +CONFIG_NETFILTER_XT_MATCH_STRING=m +CONFIG_NETFILTER_XT_MATCH_TCPMSS=m +CONFIG_NETFILTER_XT_MATCH_TIME=m +CONFIG_NETFILTER_XT_MATCH_U32=m +CONFIG_IP_SET=m +CONFIG_IP_SET_BITMAP_IP=m +CONFIG_IP_SET_BITMAP_IPMAC=m +CONFIG_IP_SET_BITMAP_PORT=m +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 +CONFIG_IP_VS=m +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m +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_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 +CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_CLUSTERIP=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_TTL=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_SECURITY=m +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 +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_MH=m +CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_TARGET_HL=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_RAW=m +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 +CONFIG_RDS_TCP=m +CONFIG_L2TP=m +CONFIG_L2TP_DEBUGFS=m +CONFIG_L2TP_V3=y +CONFIG_L2TP_IP=m +CONFIG_L2TP_ETH=m +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_MULTIQ=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFB=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_MQPRIO=m +CONFIG_NET_SCH_CHOKE=m +CONFIG_NET_SCH_QFQ=m +CONFIG_NET_SCH_CODEL=m +CONFIG_NET_SCH_FQ_CODEL=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_SCH_PLUG=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +CONFIG_CLS_U32_PERF=y +CONFIG_CLS_U32_MARK=y +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 +CONFIG_GACT_PROB=y +CONFIG_NET_ACT_MIRRED=m +CONFIG_NET_ACT_IPT=m +CONFIG_NET_ACT_NAT=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_SIMP=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_CSUM=m +CONFIG_DNS_RESOLVER=y +CONFIG_BPF_JIT=y +CONFIG_NET_PKTGEN=m +CONFIG_NET_TCPPROBE=m +CONFIG_DEVTMPFS=y +CONFIG_CONNECTOR=y +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_OSD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=32768 +CONFIG_BLK_DEV_XIP=y +CONFIG_CDROM_PKTCDVD=m +CONFIG_ATA_OVER_ETH=m +CONFIG_VIRTIO_BLK=y +CONFIG_ENCLOSURE_SERVICES=m +CONFIG_RAID_ATTRS=m +CONFIG_SCSI=y +CONFIG_SCSI_TGT=m +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=m +CONFIG_CHR_DEV_OSST=m +CONFIG_BLK_DEV_SR=m +CONFIG_CHR_DEV_SG=y +CONFIG_CHR_DEV_SCH=m +CONFIG_SCSI_ENCLOSURE=m +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_SPI_ATTRS=m +CONFIG_SCSI_SAS_LIBSAS=m +CONFIG_SCSI_SRP_ATTRS=m +CONFIG_SCSI_SRP_TGT_ATTRS=y +CONFIG_ISCSI_TCP=m +CONFIG_LIBFCOE=m +CONFIG_SCSI_DEBUG=m +CONFIG_ZFCP=y +CONFIG_SCSI_VIRTIO=m +CONFIG_SCSI_DH=m +CONFIG_SCSI_DH_RDAC=m +CONFIG_SCSI_DH_HP_SW=m +CONFIG_SCSI_DH_EMC=m +CONFIG_SCSI_DH_ALUA=m +CONFIG_SCSI_OSD_INITIATOR=m +CONFIG_SCSI_OSD_ULD=m +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=m +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_QL=m +CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_DELAY=m +CONFIG_DM_UEVENT=y +CONFIG_DM_FLAKEY=m +CONFIG_DM_VERITY=m +CONFIG_DM_SWITCH=m +CONFIG_NETDEVICES=y +CONFIG_BONDING=m +CONFIG_DUMMY=m +CONFIG_EQUALIZER=m +CONFIG_IFB=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_TUN=m +CONFIG_VETH=m +CONFIG_VIRTIO_NET=m +CONFIG_NLMON=m +CONFIG_VHOST_NET=m +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +CONFIG_MLX4_EN=m +# CONFIG_NET_VENDOR_NATSEMI is not set +CONFIG_PPP=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_MPPE=m +CONFIG_PPPOE=m +CONFIG_PPTP=m +CONFIG_PPPOL2TP=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +CONFIG_DEVPTS_MULTIPLE_INSTANCES=y +CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_HW_RANDOM_VIRTIO=m +CONFIG_RAW_DRIVER=m +CONFIG_HANGCHECK_TIMER=m +CONFIG_TN3270_FS=y +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_NOWAYOUT=y +CONFIG_SOFT_WATCHDOG=m +CONFIG_DIAG288_WATCHDOG=m +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_INFINIBAND=m +CONFIG_INFINIBAND_USER_ACCESS=m +CONFIG_MLX4_INFINIBAND=m +CONFIG_VIRTIO_BALLOON=m +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT2_FS_XIP=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_JBD_DEBUG=y +CONFIG_JBD2_DEBUG=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +CONFIG_JFS_SECURITY=y +CONFIG_JFS_STATISTICS=y +CONFIG_XFS_FS=m +CONFIG_XFS_QUOTA=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_XFS_RT=y +CONFIG_GFS2_FS=m +CONFIG_OCFS2_FS=m +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_NILFS2_FS=m +CONFIG_FANOTIFY=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +CONFIG_QFMT_V1=m +CONFIG_QFMT_V2=m +CONFIG_AUTOFS4_FS=m +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_FSCACHE=m +CONFIG_CACHEFILES=m +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_NTFS_FS=m +CONFIG_NTFS_RW=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_CONFIGFS_FS=m +CONFIG_ECRYPT_FS=m +CONFIG_CRAMFS=m +CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y +CONFIG_ROMFS_FS=m +CONFIG_NFS_FS=m +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=m +CONFIG_NFS_SWAP=y +CONFIG_NFSD=m +CONFIG_NFSD_V3_ACL=y +CONFIG_NFSD_V4=y +CONFIG_NFSD_V4_SECURITY_LABEL=y +CONFIG_CIFS=m +CONFIG_CIFS_STATS=y +CONFIG_CIFS_STATS2=y +CONFIG_CIFS_WEAK_PW_HASH=y +CONFIG_CIFS_UPCALL=y +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +# CONFIG_CIFS_DEBUG is not set +CONFIG_CIFS_DFS_UPCALL=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_ASCII=m +CONFIG_NLS_ISO8859_1=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_UTF8=m +CONFIG_DLM=m +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +CONFIG_UNUSED_SYMBOLS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m +CONFIG_TIMER_STATS=y +CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_NOTIFIER_ERROR_INJECTION=m +CONFIG_CPU_NOTIFIER_ERROR_INJECT=m +CONFIG_PM_NOTIFIER_ERROR_INJECT=m +CONFIG_LATENCYTOP=y +CONFIG_BLK_DEV_IO_TRACE=y +# CONFIG_KPROBE_EVENT is not set +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 +CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEYS_DEBUG_PROC_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_IMA=y +CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_CCM=m +CONFIG_CRYPTO_GCM=m +CONFIG_CRYPTO_CTS=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_ZLIB=y +CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_ZCRYPT=m +CONFIG_CRYPTO_SHA1_S390=m +CONFIG_CRYPTO_SHA256_S390=m +CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_DES_S390=m +CONFIG_CRYPTO_AES_S390=m +CONFIG_CRYPTO_GHASH_S390=m +CONFIG_ASYMMETRIC_KEY_TYPE=m +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m +CONFIG_X509_CERTIFICATE_PARSER=m +CONFIG_CRC7=m +CONFIG_CRC8=m +CONFIG_XZ_DEC_X86=y +CONFIG_XZ_DEC_POWERPC=y +CONFIG_XZ_DEC_IA64=y +CONFIG_XZ_DEC_ARM=y +CONFIG_XZ_DEC_ARMTHUMB=y +CONFIG_XZ_DEC_SPARC=y +CONFIG_CORDIC=m +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_KVM_S390_UCONTROL=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig new file mode 100644 index 00000000000..d279baa0801 --- /dev/null +++ b/arch/s390/configs/performance_defconfig @@ -0,0 +1,632 @@ +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_FHANDLE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_RCU_FAST_NO_HZ=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +CONFIG_CGROUP_PERF=y +CONFIG_BLK_CGROUP=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=m +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_BLK_DEV_INTEGRITY=y +CONFIG_BLK_DEV_THROTTLING=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_IBM_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_CFQ_GROUP_IOSCHED=y +CONFIG_DEFAULT_DEADLINE=y +CONFIG_MARCH_Z196=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=256 +CONFIG_HZ_100=y +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_PCI=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y +CONFIG_CHSC_SCH=y +CONFIG_CRASH_DUMP=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=m +CONFIG_HIBERNATION=y +CONFIG_PACKET=y +CONFIG_PACKET_DIAG=m +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=m +CONFIG_XFRM_USER=m +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_NET_IPVTI=m +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_XFRM_MODE_TRANSPORT=m +CONFIG_INET_XFRM_MODE_TUNNEL=m +CONFIG_INET_XFRM_MODE_BEET=m +CONFIG_INET_DIAG=m +CONFIG_INET_UDP_DIAG=m +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_HSTCP=m +CONFIG_TCP_CONG_HYBLA=m +CONFIG_TCP_CONG_SCALABLE=m +CONFIG_TCP_CONG_LP=m +CONFIG_TCP_CONG_VENO=m +CONFIG_TCP_CONG_YEAH=m +CONFIG_TCP_CONG_ILLINOIS=m +CONFIG_IPV6=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_IPV6_MIP6=m +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 +CONFIG_IPV6_SUBTREES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_TIMEOUT=y +CONFIG_NF_CONNTRACK_TIMESTAMP=y +CONFIG_NF_CT_PROTO_DCCP=m +CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CONNTRACK_AMANDA=m +CONFIG_NF_CONNTRACK_FTP=m +CONFIG_NF_CONNTRACK_H323=m +CONFIG_NF_CONNTRACK_IRC=m +CONFIG_NF_CONNTRACK_NETBIOS_NS=m +CONFIG_NF_CONNTRACK_SNMP=m +CONFIG_NF_CONNTRACK_PPTP=m +CONFIG_NF_CONNTRACK_SANE=m +CONFIG_NF_CONNTRACK_SIP=m +CONFIG_NF_CONNTRACK_TFTP=m +CONFIG_NF_CT_NETLINK=m +CONFIG_NF_CT_NETLINK_TIMEOUT=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 +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m +CONFIG_NETFILTER_XT_TARGET_CONNMARK=m +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m +CONFIG_NETFILTER_XT_TARGET_CT=m +CONFIG_NETFILTER_XT_TARGET_DSCP=m +CONFIG_NETFILTER_XT_TARGET_HMARK=m +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NFLOG=m +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_TEE=m +CONFIG_NETFILTER_XT_TARGET_TPROXY=m +CONFIG_NETFILTER_XT_TARGET_TRACE=m +CONFIG_NETFILTER_XT_TARGET_SECMARK=m +CONFIG_NETFILTER_XT_TARGET_TCPMSS=m +CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CLUSTER=m +CONFIG_NETFILTER_XT_MATCH_COMMENT=m +CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m +CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m +CONFIG_NETFILTER_XT_MATCH_CONNMARK=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NETFILTER_XT_MATCH_CPU=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m +CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m +CONFIG_NETFILTER_XT_MATCH_DSCP=m +CONFIG_NETFILTER_XT_MATCH_ESP=m +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m +CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPRANGE=m +CONFIG_NETFILTER_XT_MATCH_IPVS=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_LIMIT=m +CONFIG_NETFILTER_XT_MATCH_MAC=m +CONFIG_NETFILTER_XT_MATCH_MARK=m +CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m +CONFIG_NETFILTER_XT_MATCH_NFACCT=m +CONFIG_NETFILTER_XT_MATCH_OSF=m +CONFIG_NETFILTER_XT_MATCH_OWNER=m +CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m +CONFIG_NETFILTER_XT_MATCH_QUOTA=m +CONFIG_NETFILTER_XT_MATCH_RATEEST=m +CONFIG_NETFILTER_XT_MATCH_REALM=m +CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m +CONFIG_NETFILTER_XT_MATCH_STATE=m +CONFIG_NETFILTER_XT_MATCH_STATISTIC=m +CONFIG_NETFILTER_XT_MATCH_STRING=m +CONFIG_NETFILTER_XT_MATCH_TCPMSS=m +CONFIG_NETFILTER_XT_MATCH_TIME=m +CONFIG_NETFILTER_XT_MATCH_U32=m +CONFIG_IP_SET=m +CONFIG_IP_SET_BITMAP_IP=m +CONFIG_IP_SET_BITMAP_IPMAC=m +CONFIG_IP_SET_BITMAP_PORT=m +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 +CONFIG_IP_VS=m +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m +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_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 +CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_CLUSTERIP=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_TTL=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_SECURITY=m +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 +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_MH=m +CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_TARGET_HL=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_RAW=m +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 +CONFIG_RDS_TCP=m +CONFIG_L2TP=m +CONFIG_L2TP_DEBUGFS=m +CONFIG_L2TP_V3=y +CONFIG_L2TP_IP=m +CONFIG_L2TP_ETH=m +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_MULTIQ=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFB=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_MQPRIO=m +CONFIG_NET_SCH_CHOKE=m +CONFIG_NET_SCH_QFQ=m +CONFIG_NET_SCH_CODEL=m +CONFIG_NET_SCH_FQ_CODEL=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_SCH_PLUG=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +CONFIG_CLS_U32_PERF=y +CONFIG_CLS_U32_MARK=y +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 +CONFIG_GACT_PROB=y +CONFIG_NET_ACT_MIRRED=m +CONFIG_NET_ACT_IPT=m +CONFIG_NET_ACT_NAT=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_SIMP=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_CSUM=m +CONFIG_DNS_RESOLVER=y +CONFIG_BPF_JIT=y +CONFIG_NET_PKTGEN=m +CONFIG_NET_TCPPROBE=m +CONFIG_DEVTMPFS=y +CONFIG_CONNECTOR=y +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_OSD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=32768 +CONFIG_BLK_DEV_XIP=y +CONFIG_CDROM_PKTCDVD=m +CONFIG_ATA_OVER_ETH=m +CONFIG_VIRTIO_BLK=y +CONFIG_ENCLOSURE_SERVICES=m +CONFIG_RAID_ATTRS=m +CONFIG_SCSI=y +CONFIG_SCSI_TGT=m +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=m +CONFIG_CHR_DEV_OSST=m +CONFIG_BLK_DEV_SR=m +CONFIG_CHR_DEV_SG=y +CONFIG_CHR_DEV_SCH=m +CONFIG_SCSI_ENCLOSURE=m +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_SPI_ATTRS=m +CONFIG_SCSI_SAS_LIBSAS=m +CONFIG_SCSI_SRP_ATTRS=m +CONFIG_SCSI_SRP_TGT_ATTRS=y +CONFIG_ISCSI_TCP=m +CONFIG_LIBFCOE=m +CONFIG_SCSI_DEBUG=m +CONFIG_ZFCP=y +CONFIG_SCSI_VIRTIO=m +CONFIG_SCSI_DH=m +CONFIG_SCSI_DH_RDAC=m +CONFIG_SCSI_DH_HP_SW=m +CONFIG_SCSI_DH_EMC=m +CONFIG_SCSI_DH_ALUA=m +CONFIG_SCSI_OSD_INITIATOR=m +CONFIG_SCSI_OSD_ULD=m +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=m +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_QL=m +CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_DELAY=m +CONFIG_DM_UEVENT=y +CONFIG_DM_FLAKEY=m +CONFIG_DM_VERITY=m +CONFIG_DM_SWITCH=m +CONFIG_NETDEVICES=y +CONFIG_BONDING=m +CONFIG_DUMMY=m +CONFIG_EQUALIZER=m +CONFIG_IFB=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_TUN=m +CONFIG_VETH=m +CONFIG_VIRTIO_NET=m +CONFIG_NLMON=m +CONFIG_VHOST_NET=m +# CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +CONFIG_MLX4_EN=m +# CONFIG_NET_VENDOR_NATSEMI is not set +CONFIG_PPP=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_MPPE=m +CONFIG_PPPOE=m +CONFIG_PPTP=m +CONFIG_PPPOL2TP=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +CONFIG_DEVPTS_MULTIPLE_INSTANCES=y +CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_HW_RANDOM_VIRTIO=m +CONFIG_RAW_DRIVER=m +CONFIG_HANGCHECK_TIMER=m +CONFIG_TN3270_FS=y +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_NOWAYOUT=y +CONFIG_SOFT_WATCHDOG=m +CONFIG_DIAG288_WATCHDOG=m +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_INFINIBAND=m +CONFIG_INFINIBAND_USER_ACCESS=m +CONFIG_MLX4_INFINIBAND=m +CONFIG_VIRTIO_BALLOON=m +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT2_FS_XIP=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_JBD_DEBUG=y +CONFIG_JBD2_DEBUG=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +CONFIG_JFS_SECURITY=y +CONFIG_JFS_STATISTICS=y +CONFIG_XFS_FS=m +CONFIG_XFS_QUOTA=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_XFS_RT=y +CONFIG_GFS2_FS=m +CONFIG_OCFS2_FS=m +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_NILFS2_FS=m +CONFIG_FANOTIFY=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +CONFIG_QFMT_V1=m +CONFIG_QFMT_V2=m +CONFIG_AUTOFS4_FS=m +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_FSCACHE=m +CONFIG_CACHEFILES=m +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_NTFS_FS=m +CONFIG_NTFS_RW=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_CONFIGFS_FS=m +CONFIG_ECRYPT_FS=m +CONFIG_CRAMFS=m +CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y +CONFIG_ROMFS_FS=m +CONFIG_NFS_FS=m +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=m +CONFIG_NFS_SWAP=y +CONFIG_NFSD=m +CONFIG_NFSD_V3_ACL=y +CONFIG_NFSD_V4=y +CONFIG_NFSD_V4_SECURITY_LABEL=y +CONFIG_CIFS=m +CONFIG_CIFS_STATS=y +CONFIG_CIFS_STATS2=y +CONFIG_CIFS_WEAK_PW_HASH=y +CONFIG_CIFS_UPCALL=y +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +# CONFIG_CIFS_DEBUG is not set +CONFIG_CIFS_DFS_UPCALL=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_ASCII=m +CONFIG_NLS_ISO8859_1=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_UTF8=m +CONFIG_DLM=m +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +CONFIG_UNUSED_SYMBOLS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_TIMER_STATS=y +CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +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 +CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEYS_DEBUG_PROC_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_IMA=y +CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_CCM=m +CONFIG_CRYPTO_GCM=m +CONFIG_CRYPTO_CTS=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_ZLIB=y +CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_ZCRYPT=m +CONFIG_CRYPTO_SHA1_S390=m +CONFIG_CRYPTO_SHA256_S390=m +CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_DES_S390=m +CONFIG_CRYPTO_AES_S390=m +CONFIG_CRYPTO_GHASH_S390=m +CONFIG_ASYMMETRIC_KEY_TYPE=m +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m +CONFIG_X509_CERTIFICATE_PARSER=m +CONFIG_CRC7=m +CONFIG_CRC8=m +CONFIG_XZ_DEC_X86=y +CONFIG_XZ_DEC_POWERPC=y +CONFIG_XZ_DEC_IA64=y +CONFIG_XZ_DEC_ARM=y +CONFIG_XZ_DEC_ARMTHUMB=y +CONFIG_XZ_DEC_SPARC=y +CONFIG_CORDIC=m +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_KVM_S390_UCONTROL=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig new file mode 100644 index 00000000000..948e0e057a2 --- /dev/null +++ b/arch/s390/configs/zfcpdump_defconfig @@ -0,0 +1,86 @@ +# CONFIG_SWAP is not set +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_RCU_FAST_NO_HZ=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_IBM_PARTITION=y +CONFIG_DEFAULT_DEADLINE=y +CONFIG_MARCH_Z196=y +CONFIG_TUNE_ZEC12=y +# CONFIG_COMPAT is not set +CONFIG_NR_CPUS=2 +# CONFIG_HOTPLUG_CPU is not set +CONFIG_HZ_100=y +# CONFIG_COMPACTION is not set +# CONFIG_MIGRATION is not set +# CONFIG_CHECK_STACK is not set +# CONFIG_CHSC_SCH is not set +# CONFIG_SCM_BUS is not set +CONFIG_CRASH_DUMP=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_SECCOMP is not set +# CONFIG_IUCV is not set +CONFIG_ATM=y +CONFIG_ATM_LANE=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV_XPRAM is not set +# CONFIG_DCSSBLK is not set +# CONFIG_DASD is not set +CONFIG_ENCLOSURE_SERVICES=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_SCSI_ENCLOSURE=y +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y +CONFIG_SCSI_SRP_ATTRS=y +CONFIG_ZFCP=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_HVC_IUCV is not set +CONFIG_RAW_DRIVER=y +# CONFIG_SCLP_ASYNC is not set +# CONFIG_HMC_DRV is not set +# CONFIG_S390_TAPE is not set +# CONFIG_VMCP is not set +# CONFIG_MONWRITER is not set +# CONFIG_S390_VMUR is not set +# CONFIG_HID is not set +CONFIG_MEMSTICK=y +CONFIG_MEMSTICK_DEBUG=y +CONFIG_MEMSTICK_UNSAFE_RESUME=y +CONFIG_MSPRO_BLOCK=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +# CONFIG_INOTIFY_USER is not set +CONFIG_CONFIGFS_FS=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y +CONFIG_DEBUG_KERNEL=y +# CONFIG_SCHED_DEBUG is not set +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +# CONFIG_FTRACE is not set +# CONFIG_STRICT_DEVMEM is not set +CONFIG_XZ_DEC_X86=y +CONFIG_XZ_DEC_POWERPC=y +CONFIG_XZ_DEC_IA64=y +CONFIG_XZ_DEC_ARM=y +CONFIG_XZ_DEC_ARMTHUMB=y +CONFIG_XZ_DEC_SPARC=y +# CONFIG_PFAULT is not set +# CONFIG_S390_HYPFS_FS is not set +# CONFIG_VIRTUALIZATION is not set +# CONFIG_S390_GUEST is not set diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index b4dbade8ca2..23223cd63e5 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 @@ -32,10 +33,10 @@ #define AES_KEYLEN_256 4 static u8 *ctrblk; +static DEFINE_SPINLOCK(ctrblk_lock); static char keylen_flag; struct s390_aes_ctx { - u8 iv[AES_BLOCK_SIZE]; u8 key[AES_MAX_KEY_SIZE]; long enc; long dec; @@ -56,8 +57,7 @@ struct pcc_param { struct s390_xts_ctx { u8 key[32]; - u8 xts_param[16]; - struct pcc_param pcc; + u8 pcc_key[32]; long enc; long dec; int key_len; @@ -441,30 +441,36 @@ static int cbc_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, return aes_set_key(tfm, in_key, key_len); } -static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, void *param, +static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, struct blkcipher_walk *walk) { + struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm); int ret = blkcipher_walk_virt(desc, walk); unsigned int nbytes = walk->nbytes; + struct { + u8 iv[AES_BLOCK_SIZE]; + u8 key[AES_MAX_KEY_SIZE]; + } param; if (!nbytes) goto out; - memcpy(param, walk->iv, AES_BLOCK_SIZE); + memcpy(param.iv, walk->iv, AES_BLOCK_SIZE); + memcpy(param.key, sctx->key, sctx->key_len); do { /* only use complete blocks */ unsigned int n = nbytes & ~(AES_BLOCK_SIZE - 1); u8 *out = walk->dst.virt.addr; u8 *in = walk->src.virt.addr; - ret = crypt_s390_kmc(func, param, out, in, n); + ret = crypt_s390_kmc(func, ¶m, out, in, n); if (ret < 0 || ret != n) return -EIO; nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, walk, nbytes); } while ((nbytes = walk->nbytes)); - memcpy(walk->iv, param, AES_BLOCK_SIZE); + memcpy(walk->iv, param.iv, AES_BLOCK_SIZE); out: return ret; @@ -481,7 +487,7 @@ static int cbc_aes_encrypt(struct blkcipher_desc *desc, return fallback_blk_enc(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_aes_crypt(desc, sctx->enc, sctx->iv, &walk); + return cbc_aes_crypt(desc, sctx->enc, &walk); } static int cbc_aes_decrypt(struct blkcipher_desc *desc, @@ -495,7 +501,7 @@ static int cbc_aes_decrypt(struct blkcipher_desc *desc, return fallback_blk_dec(desc, dst, src, nbytes); blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_aes_crypt(desc, sctx->dec, sctx->iv, &walk); + return cbc_aes_crypt(desc, sctx->dec, &walk); } static struct crypto_alg cbc_aes_alg = { @@ -586,7 +592,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, xts_ctx->enc = KM_XTS_128_ENCRYPT; xts_ctx->dec = KM_XTS_128_DECRYPT; memcpy(xts_ctx->key + 16, in_key, 16); - memcpy(xts_ctx->pcc.key + 16, in_key + 16, 16); + memcpy(xts_ctx->pcc_key + 16, in_key + 16, 16); break; case 48: xts_ctx->enc = 0; @@ -597,7 +603,7 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, xts_ctx->enc = KM_XTS_256_ENCRYPT; xts_ctx->dec = KM_XTS_256_DECRYPT; memcpy(xts_ctx->key, in_key, 32); - memcpy(xts_ctx->pcc.key, in_key + 32, 32); + memcpy(xts_ctx->pcc_key, in_key + 32, 32); break; default: *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; @@ -616,29 +622,33 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, long func, unsigned int nbytes = walk->nbytes; unsigned int n; u8 *in, *out; - void *param; + struct pcc_param pcc_param; + struct { + u8 key[32]; + u8 init[16]; + } xts_param; if (!nbytes) goto out; - memset(xts_ctx->pcc.block, 0, sizeof(xts_ctx->pcc.block)); - memset(xts_ctx->pcc.bit, 0, sizeof(xts_ctx->pcc.bit)); - memset(xts_ctx->pcc.xts, 0, sizeof(xts_ctx->pcc.xts)); - memcpy(xts_ctx->pcc.tweak, walk->iv, sizeof(xts_ctx->pcc.tweak)); - param = xts_ctx->pcc.key + offset; - ret = crypt_s390_pcc(func, param); + memset(pcc_param.block, 0, sizeof(pcc_param.block)); + memset(pcc_param.bit, 0, sizeof(pcc_param.bit)); + memset(pcc_param.xts, 0, sizeof(pcc_param.xts)); + memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak)); + memcpy(pcc_param.key, xts_ctx->pcc_key, 32); + ret = crypt_s390_pcc(func, &pcc_param.key[offset]); if (ret < 0) return -EIO; - memcpy(xts_ctx->xts_param, xts_ctx->pcc.xts, 16); - param = xts_ctx->key + offset; + memcpy(xts_param.key, xts_ctx->key, 32); + memcpy(xts_param.init, pcc_param.xts, 16); do { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); out = walk->dst.virt.addr; in = walk->src.virt.addr; - ret = crypt_s390_km(func, param, out, in, n); + ret = crypt_s390_km(func, &xts_param.key[offset], out, in, n); if (ret < 0 || ret != n) return -EIO; @@ -725,6 +735,8 @@ static struct crypto_alg xts_aes_alg = { } }; +static int xts_aes_alg_reg; + static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { @@ -748,43 +760,70 @@ 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); + } else { + if (!nbytes) + memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); + } /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ @@ -792,14 +831,15 @@ 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; } @@ -846,6 +886,8 @@ static struct crypto_alg ctr_aes_alg = { } }; +static int ctr_aes_alg_reg; + static int __init aes_s390_init(void) { int ret; @@ -884,6 +926,7 @@ static int __init aes_s390_init(void) ret = crypto_register_alg(&xts_aes_alg); if (ret) goto xts_aes_err; + xts_aes_alg_reg = 1; } if (crypt_s390_func_available(KMCTR_AES_128_ENCRYPT, @@ -902,6 +945,7 @@ static int __init aes_s390_init(void) free_page((unsigned long) ctrblk); goto ctr_aes_err; } + ctr_aes_alg_reg = 1; } out: @@ -921,9 +965,12 @@ aes_err: static void __exit aes_s390_fini(void) { - crypto_unregister_alg(&ctr_aes_alg); - free_page((unsigned long) ctrblk); - crypto_unregister_alg(&xts_aes_alg); + if (ctr_aes_alg_reg) { + crypto_unregister_alg(&ctr_aes_alg); + free_page((unsigned long) ctrblk); + } + if (xts_aes_alg_reg) + crypto_unregister_alg(&xts_aes_alg); crypto_unregister_alg(&cbc_aes_alg); crypto_unregister_alg(&ecb_aes_alg); crypto_unregister_alg(&aes_alg); diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index bcca01c9989..7acb77f7ef1 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, ¶m, 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 +369,83 @@ 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); + } else { + if (!nbytes) + memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); + } /* 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 b74400e3e03..2e56498a40d 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,14 +1,13 @@ -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_FHANDLE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_AUDIT=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_RCU_FAST_NO_HZ=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -27,6 +26,7 @@ CONFIG_RD_BZIP2=y CONFIG_RD_LZMA=y CONFIG_RD_XZ=y CONFIG_RD_LZO=y +CONFIG_RD_LZ4=y CONFIG_EXPERT=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y @@ -39,10 +39,14 @@ CONFIG_MODVERSIONS=y 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 CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_CMA=y CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -92,40 +96,58 @@ CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y CONFIG_SCSI_SCAN_ASYNC=y CONFIG_ZFCP=y +CONFIG_SCSI_VIRTIO=y CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set CONFIG_RAW_DRIVER=m CONFIG_VIRTIO_BALLOON=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y +CONFIG_XFS_FS=y +CONFIG_XFS_QUOTA=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_XFS_RT=y +CONFIG_BTRFS_FS=y +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_FANOTIFY=y +CONFIG_FUSE_FS=y CONFIG_PROC_KCORE=y 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_PROVE_RCU=y CONFIG_LOCK_STAT=y CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_PI_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_KPROBES_SANITY_TEST=y -CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_PAGEALLOC=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_CRYPTO_NULL=m +CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m @@ -137,8 +159,11 @@ CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_CMAC=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_CRCT10DIF=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m @@ -165,6 +190,8 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m CONFIG_ZCRYPT=m CONFIG_CRYPTO_SHA1_S390=m CONFIG_CRYPTO_SHA256_S390=m @@ -172,4 +199,10 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRC7=m +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set CONFIG_CMM=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 f41e0ef7fdf..b34b5ab90a3 100644 --- a/arch/s390/hypfs/hypfs.h +++ b/arch/s390/hypfs/hypfs.h @@ -13,31 +13,33 @@ #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 #define DIR_MODE 0550 -extern struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent, - const char *name); +extern struct dentry *hypfs_mkdir(struct dentry *parent, const char *name); -extern struct dentry *hypfs_create_u64(struct super_block *sb, - struct dentry *dir, const char *name, +extern struct dentry *hypfs_create_u64(struct dentry *dir, const char *name, __u64 value); -extern struct dentry *hypfs_create_str(struct super_block *sb, - struct dentry *dir, const char *name, +extern struct dentry *hypfs_create_str(struct dentry *dir, const char *name, char *string); /* LPAR Hypervisor */ extern int hypfs_diag_init(void); extern void hypfs_diag_exit(void); -extern int hypfs_diag_create_files(struct super_block *sb, struct dentry *root); +extern int hypfs_diag_create_files(struct dentry *root); /* VM Hypervisor */ extern int hypfs_vm_init(void); extern void hypfs_vm_exit(void); -extern int hypfs_vm_create_files(struct super_block *sb, struct dentry *root); +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; @@ -55,6 +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 13e76dabbe8..2badf2bf9cd 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -54,7 +54,7 @@ static ssize_t dbfs_read(struct file *file, char __user *buf, if (*ppos != 0) return 0; - df = file->f_path.dentry->d_inode->i_private; + df = file_inode(file)->i_private; mutex_lock(&df->lock); if (!df->data) { data = hypfs_dbfs_data_alloc(df); @@ -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) @@ -105,9 +121,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df) int hypfs_dbfs_init(void) { dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); - if (IS_ERR(dbfs_dir)) - return PTR_ERR(dbfs_dir); - return 0; + return PTR_ERR_OR_ZERO(dbfs_dir); } void hypfs_dbfs_exit(void) diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 7fd3690b676..5eeffeefae0 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -623,8 +623,7 @@ void hypfs_diag_exit(void) * ******************************************* */ -static int hypfs_create_cpu_files(struct super_block *sb, - struct dentry *cpus_dir, void *cpu_info) +static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info) { struct dentry *cpu_dir; char buffer[TMP_SIZE]; @@ -632,32 +631,29 @@ static int hypfs_create_cpu_files(struct super_block *sb, snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_info_type, cpu_info)); - cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer); - rc = hypfs_create_u64(sb, cpu_dir, "mgmtime", + cpu_dir = hypfs_mkdir(cpus_dir, buffer); + rc = hypfs_create_u64(cpu_dir, "mgmtime", cpu_info__acc_time(diag204_info_type, cpu_info) - cpu_info__lp_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); - rc = hypfs_create_u64(sb, cpu_dir, "cputime", + rc = hypfs_create_u64(cpu_dir, "cputime", cpu_info__lp_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); if (diag204_info_type == INFO_EXT) { - rc = hypfs_create_u64(sb, cpu_dir, "onlinetime", + rc = hypfs_create_u64(cpu_dir, "onlinetime", cpu_info__online_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); } diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer); - rc = hypfs_create_str(sb, cpu_dir, "type", buffer); - if (IS_ERR(rc)) - return PTR_ERR(rc); - return 0; + rc = hypfs_create_str(cpu_dir, "type", buffer); + return PTR_RET(rc); } -static void *hypfs_create_lpar_files(struct super_block *sb, - struct dentry *systems_dir, void *part_hdr) +static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr) { struct dentry *cpus_dir; struct dentry *lpar_dir; @@ -667,16 +663,16 @@ static void *hypfs_create_lpar_files(struct super_block *sb, part_hdr__part_name(diag204_info_type, part_hdr, lpar_name); lpar_name[LPAR_NAME_LEN] = 0; - lpar_dir = hypfs_mkdir(sb, systems_dir, lpar_name); + lpar_dir = hypfs_mkdir(systems_dir, lpar_name); if (IS_ERR(lpar_dir)) return lpar_dir; - cpus_dir = hypfs_mkdir(sb, lpar_dir, "cpus"); + cpus_dir = hypfs_mkdir(lpar_dir, "cpus"); if (IS_ERR(cpus_dir)) return cpus_dir; cpu_info = part_hdr + part_hdr__size(diag204_info_type); for (i = 0; i < part_hdr__rcpus(diag204_info_type, part_hdr); i++) { int rc; - rc = hypfs_create_cpu_files(sb, cpus_dir, cpu_info); + rc = hypfs_create_cpu_files(cpus_dir, cpu_info); if (rc) return ERR_PTR(rc); cpu_info += cpu_info__size(diag204_info_type); @@ -684,8 +680,7 @@ static void *hypfs_create_lpar_files(struct super_block *sb, return cpu_info; } -static int hypfs_create_phys_cpu_files(struct super_block *sb, - struct dentry *cpus_dir, void *cpu_info) +static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info) { struct dentry *cpu_dir; char buffer[TMP_SIZE]; @@ -693,34 +688,31 @@ static int hypfs_create_phys_cpu_files(struct super_block *sb, snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_info_type, cpu_info)); - cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer); + cpu_dir = hypfs_mkdir(cpus_dir, buffer); if (IS_ERR(cpu_dir)) return PTR_ERR(cpu_dir); - rc = hypfs_create_u64(sb, cpu_dir, "mgmtime", + rc = hypfs_create_u64(cpu_dir, "mgmtime", phys_cpu__mgm_time(diag204_info_type, cpu_info)); if (IS_ERR(rc)) return PTR_ERR(rc); diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer); - rc = hypfs_create_str(sb, cpu_dir, "type", buffer); - if (IS_ERR(rc)) - return PTR_ERR(rc); - return 0; + rc = hypfs_create_str(cpu_dir, "type", buffer); + return PTR_RET(rc); } -static void *hypfs_create_phys_files(struct super_block *sb, - struct dentry *parent_dir, void *phys_hdr) +static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr) { int i; void *cpu_info; struct dentry *cpus_dir; - cpus_dir = hypfs_mkdir(sb, parent_dir, "cpus"); + cpus_dir = hypfs_mkdir(parent_dir, "cpus"); if (IS_ERR(cpus_dir)) return cpus_dir; cpu_info = phys_hdr + phys_hdr__size(diag204_info_type); for (i = 0; i < phys_hdr__cpus(diag204_info_type, phys_hdr); i++) { int rc; - rc = hypfs_create_phys_cpu_files(sb, cpus_dir, cpu_info); + rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info); if (rc) return ERR_PTR(rc); cpu_info += phys_cpu__size(diag204_info_type); @@ -728,7 +720,7 @@ static void *hypfs_create_phys_files(struct super_block *sb, return cpu_info; } -int hypfs_diag_create_files(struct super_block *sb, struct dentry *root) +int hypfs_diag_create_files(struct dentry *root) { struct dentry *systems_dir, *hyp_dir; void *time_hdr, *part_hdr; @@ -739,7 +731,7 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root) if (IS_ERR(buffer)) return PTR_ERR(buffer); - systems_dir = hypfs_mkdir(sb, root, "systems"); + systems_dir = hypfs_mkdir(root, "systems"); if (IS_ERR(systems_dir)) { rc = PTR_ERR(systems_dir); goto err_out; @@ -747,25 +739,25 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root) time_hdr = (struct x_info_blk_hdr *)buffer; part_hdr = time_hdr + info_blk_hdr__size(diag204_info_type); for (i = 0; i < info_blk_hdr__npar(diag204_info_type, time_hdr); i++) { - part_hdr = hypfs_create_lpar_files(sb, systems_dir, part_hdr); + part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr); if (IS_ERR(part_hdr)) { rc = PTR_ERR(part_hdr); goto err_out; } } if (info_blk_hdr__flags(diag204_info_type, time_hdr) & LPAR_PHYS_FLG) { - ptr = hypfs_create_phys_files(sb, root, part_hdr); + ptr = hypfs_create_phys_files(root, part_hdr); if (IS_ERR(ptr)) { rc = PTR_ERR(ptr); goto err_out; } } - hyp_dir = hypfs_mkdir(sb, root, "hyp"); + hyp_dir = hypfs_mkdir(root, "hyp"); if (IS_ERR(hyp_dir)) { rc = PTR_ERR(hyp_dir); goto err_out; } - ptr = hypfs_create_str(sb, hyp_dir, "type", "LPAR Hypervisor"); + ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor"); if (IS_ERR(ptr)) { rc = PTR_ERR(ptr); goto err_out; 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 4f6afaa8bd8..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; @@ -107,16 +107,15 @@ static void diag2fc_free(const void *data) vfree(data); } -#define ATTRIBUTE(sb, dir, name, member) \ +#define ATTRIBUTE(dir, name, member) \ do { \ void *rc; \ - rc = hypfs_create_u64(sb, dir, name, member); \ + rc = hypfs_create_u64(dir, name, member); \ if (IS_ERR(rc)) \ return PTR_ERR(rc); \ } while(0) -static int hpyfs_vm_create_guest(struct super_block *sb, - struct dentry *systems_dir, +static int hpyfs_vm_create_guest(struct dentry *systems_dir, struct diag2fc_data *data) { char guest_name[NAME_LEN + 1] = {}; @@ -130,46 +129,51 @@ static int hpyfs_vm_create_guest(struct super_block *sb, memcpy(guest_name, data->guest_name, NAME_LEN); EBCASC(guest_name, NAME_LEN); strim(guest_name); - guest_dir = hypfs_mkdir(sb, systems_dir, guest_name); + guest_dir = hypfs_mkdir(systems_dir, guest_name); if (IS_ERR(guest_dir)) return PTR_ERR(guest_dir); - ATTRIBUTE(sb, guest_dir, "onlinetime_us", data->el_time); + ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time); /* logical cpu information */ - cpus_dir = hypfs_mkdir(sb, guest_dir, "cpus"); + cpus_dir = hypfs_mkdir(guest_dir, "cpus"); if (IS_ERR(cpus_dir)) return PTR_ERR(cpus_dir); - ATTRIBUTE(sb, cpus_dir, "cputime_us", data->used_cpu); - ATTRIBUTE(sb, cpus_dir, "capped", capped_value); - ATTRIBUTE(sb, cpus_dir, "dedicated", dedicated_flag); - ATTRIBUTE(sb, cpus_dir, "count", data->vcpus); - ATTRIBUTE(sb, cpus_dir, "weight_min", data->cpu_min); - ATTRIBUTE(sb, cpus_dir, "weight_max", data->cpu_max); - ATTRIBUTE(sb, cpus_dir, "weight_cur", data->cpu_shares); + ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu); + ATTRIBUTE(cpus_dir, "capped", capped_value); + ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag); + ATTRIBUTE(cpus_dir, "count", data->vcpus); + /* + * 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); /* memory information */ - mem_dir = hypfs_mkdir(sb, guest_dir, "mem"); + mem_dir = hypfs_mkdir(guest_dir, "mem"); if (IS_ERR(mem_dir)) return PTR_ERR(mem_dir); - ATTRIBUTE(sb, mem_dir, "min_KiB", data->mem_min_kb); - ATTRIBUTE(sb, mem_dir, "max_KiB", data->mem_max_kb); - ATTRIBUTE(sb, mem_dir, "used_KiB", data->mem_used_kb); - ATTRIBUTE(sb, mem_dir, "share_KiB", data->mem_share_kb); + ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb); + ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb); + ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb); + ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb); /* samples */ - samples_dir = hypfs_mkdir(sb, guest_dir, "samples"); + samples_dir = hypfs_mkdir(guest_dir, "samples"); if (IS_ERR(samples_dir)) return PTR_ERR(samples_dir); - ATTRIBUTE(sb, samples_dir, "cpu_using", data->cpu_use_samp); - ATTRIBUTE(sb, samples_dir, "cpu_delay", data->cpu_delay_samp); - ATTRIBUTE(sb, samples_dir, "mem_delay", data->page_wait_samp); - ATTRIBUTE(sb, samples_dir, "idle", data->idle_samp); - ATTRIBUTE(sb, samples_dir, "other", data->other_samp); - ATTRIBUTE(sb, samples_dir, "total", data->total_samp); + ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp); + ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp); + ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp); + ATTRIBUTE(samples_dir, "idle", data->idle_samp); + ATTRIBUTE(samples_dir, "other", data->other_samp); + ATTRIBUTE(samples_dir, "total", data->total_samp); return 0; } -int hypfs_vm_create_files(struct super_block *sb, struct dentry *root) +int hypfs_vm_create_files(struct dentry *root) { struct dentry *dir, *file; struct diag2fc_data *data; @@ -181,38 +185,38 @@ int hypfs_vm_create_files(struct super_block *sb, struct dentry *root) return PTR_ERR(data); /* Hpervisor Info */ - dir = hypfs_mkdir(sb, root, "hyp"); + dir = hypfs_mkdir(root, "hyp"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); goto failed; } - file = hypfs_create_str(sb, dir, "type", "z/VM Hypervisor"); + file = hypfs_create_str(dir, "type", "z/VM Hypervisor"); if (IS_ERR(file)) { rc = PTR_ERR(file); goto failed; } /* physical cpus */ - dir = hypfs_mkdir(sb, root, "cpus"); + dir = hypfs_mkdir(root, "cpus"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); goto failed; } - file = hypfs_create_u64(sb, dir, "count", data->lcpus); + file = hypfs_create_u64(dir, "count", data->lcpus); if (IS_ERR(file)) { rc = PTR_ERR(file); goto failed; } /* guests */ - dir = hypfs_mkdir(sb, root, "systems"); + dir = hypfs_mkdir(root, "systems"); if (IS_ERR(dir)) { rc = PTR_ERR(dir); goto failed; } for (i = 0; i < count; i++) { - rc = hpyfs_vm_create_guest(sb, dir, &(data[i])); + rc = hpyfs_vm_create_guest(dir, &(data[i])); if (rc) goto failed; } @@ -245,7 +249,7 @@ static int dbfs_diag2fc_create(void **data, void **data_free_ptr, size_t *size) d2fc = diag2fc_store(guest_query, &count, sizeof(d2fc->hdr)); if (IS_ERR(d2fc)) return PTR_ERR(d2fc); - get_clock_ext(d2fc->hdr.tod_ext); + get_tod_clock_ext(d2fc->hdr.tod_ext); d2fc->hdr.len = count * sizeof(struct diag2fc_data); d2fc->hdr.version = DBFS_D2FC_HDR_VERSION; d2fc->hdr.count = count; diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 06ea69bd387..c952b981e4f 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -21,14 +21,14 @@ #include <linux/module.h> #include <linux/seq_file.h> #include <linux/mount.h> +#include <linux/aio.h> #include <asm/ebcdic.h> #include "hypfs.h" #define HYPFS_MAGIC 0x687970 /* ASCII 'hyp' */ #define TMP_SIZE 64 /* size of temporary buffers */ -static struct dentry *hypfs_create_update_file(struct super_block *sb, - struct dentry *dir); +static struct dentry *hypfs_create_update_file(struct dentry *dir); struct hypfs_sb_info { kuid_t uid; /* uid used for files and dirs */ @@ -119,7 +119,7 @@ static void hypfs_evict_inode(struct inode *inode) static int hypfs_open(struct inode *inode, struct file *filp) { - char *data = filp->f_path.dentry->d_inode->i_private; + char *data = file_inode(filp)->i_private; struct hypfs_sb_info *fs_info; if (filp->f_mode & FMODE_WRITE) { @@ -171,12 +171,10 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t offset) { int rc; - struct super_block *sb; - struct hypfs_sb_info *fs_info; + struct super_block *sb = file_inode(iocb->ki_filp)->i_sb; + struct hypfs_sb_info *fs_info = sb->s_fs_info; size_t count = iov_length(iov, nr_segs); - sb = iocb->ki_filp->f_path.dentry->d_inode->i_sb; - fs_info = sb->s_fs_info; /* * Currently we only allow one update per second for two reasons: * 1. diag 204 is VERY expensive @@ -194,9 +192,9 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, } hypfs_delete_tree(sb->s_root); if (MACHINE_IS_VM) - rc = hypfs_vm_create_files(sb, sb->s_root); + rc = hypfs_vm_create_files(sb->s_root); else - rc = hypfs_diag_create_files(sb, sb->s_root); + rc = hypfs_diag_create_files(sb->s_root); if (rc) { pr_err("Updating the hypfs tree failed\n"); hypfs_delete_tree(sb->s_root); @@ -303,12 +301,12 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent) if (!root_dentry) return -ENOMEM; if (MACHINE_IS_VM) - rc = hypfs_vm_create_files(sb, root_dentry); + rc = hypfs_vm_create_files(root_dentry); else - rc = hypfs_diag_create_files(sb, root_dentry); + rc = hypfs_diag_create_files(root_dentry); if (rc) return rc; - sbi->update_file = hypfs_create_update_file(sb, root_dentry); + sbi->update_file = hypfs_create_update_file(root_dentry); if (IS_ERR(sbi->update_file)) return PTR_ERR(sbi->update_file); hypfs_update_update(sb); @@ -335,8 +333,7 @@ static void hypfs_kill_super(struct super_block *sb) kill_litter_super(sb); } -static struct dentry *hypfs_create_file(struct super_block *sb, - struct dentry *parent, const char *name, +static struct dentry *hypfs_create_file(struct dentry *parent, const char *name, char *data, umode_t mode) { struct dentry *dentry; @@ -348,7 +345,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb, dentry = ERR_PTR(-ENOMEM); goto fail; } - inode = hypfs_make_inode(sb, mode); + inode = hypfs_make_inode(parent->d_sb, mode); if (!inode) { dput(dentry); dentry = ERR_PTR(-ENOMEM); @@ -374,24 +371,22 @@ fail: return dentry; } -struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent, - const char *name) +struct dentry *hypfs_mkdir(struct dentry *parent, const char *name) { struct dentry *dentry; - dentry = hypfs_create_file(sb, parent, name, NULL, S_IFDIR | DIR_MODE); + dentry = hypfs_create_file(parent, name, NULL, S_IFDIR | DIR_MODE); if (IS_ERR(dentry)) return dentry; hypfs_add_dentry(dentry); return dentry; } -static struct dentry *hypfs_create_update_file(struct super_block *sb, - struct dentry *dir) +static struct dentry *hypfs_create_update_file(struct dentry *dir) { struct dentry *dentry; - dentry = hypfs_create_file(sb, dir, "update", NULL, + dentry = hypfs_create_file(dir, "update", NULL, S_IFREG | UPDATE_FILE_MODE); /* * We do not put the update file on the 'delete' list with @@ -401,7 +396,7 @@ static struct dentry *hypfs_create_update_file(struct super_block *sb, return dentry; } -struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, +struct dentry *hypfs_create_u64(struct dentry *dir, const char *name, __u64 value) { char *buffer; @@ -413,7 +408,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, if (!buffer) return ERR_PTR(-ENOMEM); dentry = - hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE); + hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE); if (IS_ERR(dentry)) { kfree(buffer); return ERR_PTR(-ENOMEM); @@ -422,7 +417,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir, return dentry; } -struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir, +struct dentry *hypfs_create_str(struct dentry *dir, const char *name, char *string) { char *buffer; @@ -433,7 +428,7 @@ struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir, return ERR_PTR(-ENOMEM); sprintf(buffer, "%s\n", string); dentry = - hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE); + hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE); if (IS_ERR(dentry)) { kfree(buffer); return ERR_PTR(-ENOMEM); @@ -458,6 +453,7 @@ static struct file_system_type hypfs_type = { .mount = hypfs_mount, .kill_sb = hypfs_kill_super }; +MODULE_ALIAS_FS("s390_hypfs"); static const struct super_operations hypfs_s_ops = { .statfs = simple_statfs, @@ -482,10 +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) @@ -494,6 +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: @@ -506,11 +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 f313f9cbcf4..57892a8a905 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,4 +1,7 @@ generic-y += clkdev.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 9819891ed7a..bd93ff6661b 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -9,9 +9,95 @@ #ifndef _ASM_S390_AIRQ_H #define _ASM_S390_AIRQ_H -typedef void (*adapter_int_handler_t)(void *, void *); +#include <linux/bit_spinlock.h> -void *s390_register_adapter_interrupt(adapter_int_handler_t, void *, u8); -void s390_unregister_adapter_interrupt(void *, u8); +struct airq_struct { + struct hlist_node list; /* Handler queueing. */ + void (*handler)(struct airq_struct *); /* Thin-interrupt handler */ + u8 *lsi_ptr; /* Local-Summary-Indicator pointer */ + u8 lsi_mask; /* Local-Summary-Indicator mask */ + u8 isc; /* Interrupt-subclass */ + u8 flags; +}; + +#define AIRQ_PTR_ALLOCATED 0x01 + +int register_adapter_interrupt(struct airq_struct *airq); +void unregister_adapter_interrupt(struct airq_struct *airq); + +/* Adapter interrupt bit vector */ +struct airq_iv { + unsigned long *vector; /* Adapter interrupt bit vector */ + unsigned long *avail; /* Allocation bit mask for the bit vector */ + unsigned long *bitlock; /* Lock bit mask for the bit vector */ + unsigned long *ptr; /* Pointer associated with each bit */ + unsigned int *data; /* 32 bit value associated with each bit */ + unsigned long bits; /* Number of bits in the vector */ + unsigned long end; /* Number of highest allocated bit + 1 */ + spinlock_t lock; /* Lock to protect alloc & free */ +}; + +#define AIRQ_IV_ALLOC 1 /* Use an allocation bit mask */ +#define AIRQ_IV_BITLOCK 2 /* Allocate the lock bit mask */ +#define AIRQ_IV_PTR 4 /* Allocate the ptr array */ +#define AIRQ_IV_DATA 8 /* Allocate the data array */ + +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(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; +} + +static inline void airq_iv_lock(struct airq_iv *iv, unsigned long bit) +{ + const unsigned long be_to_le = BITS_PER_LONG - 1; + bit_spin_lock(bit ^ be_to_le, iv->bitlock); +} + +static inline void airq_iv_unlock(struct airq_iv *iv, unsigned long bit) +{ + const unsigned long be_to_le = BITS_PER_LONG - 1; + bit_spin_unlock(bit ^ be_to_le, iv->bitlock); +} + +static inline void airq_iv_set_data(struct airq_iv *iv, unsigned long bit, + unsigned int data) +{ + iv->data[bit] = data; +} + +static inline unsigned int airq_iv_get_data(struct airq_iv *iv, + unsigned long bit) +{ + return iv->data[bit]; +} + +static inline void airq_iv_set_ptr(struct airq_iv *iv, unsigned long bit, + unsigned long ptr) +{ + iv->ptr[bit] = ptr; +} + +static inline unsigned long airq_iv_get_ptr(struct airq_iv *iv, + unsigned long bit) +{ + return iv->ptr[bit]; +} #endif /* _ASM_S390_AIRQ_H */ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index c797832daa5..fa934fe080c 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -15,25 +15,61 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <asm/barrier.h> #include <asm/cmpxchg.h> #define ATOMIC_INIT(i) { (i) } -#define __CS_LOOP(ptr, op_val, op_string) ({ \ +#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, __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"); \ + old_val; \ +}) + +#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */ + +#define __ATOMIC_OR "or" +#define __ATOMIC_AND "nr" +#define __ATOMIC_ADD "ar" +#define __ATOMIC_BARRIER "\n" + +#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \ +({ \ int old_val, new_val; \ + \ + typecheck(atomic_t *, ptr); \ asm volatile( \ " l %0,%2\n" \ "0: lr %1,%0\n" \ op_string " %1,%3\n" \ " cs %0,%1,%2\n" \ " jl 0b" \ - : "=&d" (old_val), "=&d" (new_val), \ - "=Q" (((atomic_t *)(ptr))->counter) \ - : "d" (op_val), "Q" (((atomic_t *)(ptr))->counter) \ + : "=&d" (old_val), "=&d" (new_val), "+Q" ((ptr)->counter)\ + : "d" (op_val) \ : "cc", "memory"); \ - new_val; \ + old_val; \ }) +#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */ + static inline int atomic_read(const atomic_t *v) { int c; @@ -53,32 +89,43 @@ static inline void atomic_set(atomic_t *v, int i) static inline int atomic_add_return(int i, atomic_t *v) { - return __CS_LOOP(v, i, "ar"); + return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i; } -#define atomic_add(_i, _v) atomic_add_return(_i, _v) -#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) -#define atomic_inc(_v) atomic_add_return(1, _v) -#define atomic_inc_return(_v) atomic_add_return(1, _v) -#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) -static inline int atomic_sub_return(int i, atomic_t *v) +static inline void atomic_add(int i, atomic_t *v) { - return __CS_LOOP(v, i, "sr"); +#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES + if (__builtin_constant_p(i) && (i > -129) && (i < 128)) { + asm volatile( + "asi %0,%1\n" + : "+Q" (v->counter) + : "i" (i) + : "cc", "memory"); + return; + } +#endif + __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_NO_BARRIER); } -#define atomic_sub(_i, _v) atomic_sub_return(_i, _v) + +#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) +#define atomic_inc(_v) atomic_add(1, _v) +#define atomic_inc_return(_v) atomic_add_return(1, _v) +#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) +#define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v) +#define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v) #define atomic_sub_and_test(_i, _v) (atomic_sub_return(_i, _v) == 0) -#define atomic_dec(_v) atomic_sub_return(1, _v) +#define atomic_dec(_v) atomic_sub(1, _v) #define atomic_dec_return(_v) atomic_sub_return(1, _v) #define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) -static inline void atomic_clear_mask(unsigned long mask, atomic_t *v) +static inline void atomic_clear_mask(unsigned int mask, atomic_t *v) { - __CS_LOOP(v, ~mask, "nr"); + __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER); } -static inline void atomic_set_mask(unsigned long mask, atomic_t *v) +static inline void atomic_set_mask(unsigned int mask, atomic_t *v) { - __CS_LOOP(v, mask, "or"); + __ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER); } #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) @@ -87,8 +134,8 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { asm volatile( " cs %0,%2,%1" - : "+d" (old), "=Q" (v->counter) - : "d" (new), "Q" (v->counter) + : "+d" (old), "+Q" (v->counter) + : "d" (new) : "cc", "memory"); return old; } @@ -109,27 +156,62 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) } -#undef __CS_LOOP +#undef __ATOMIC_LOOP #define ATOMIC64_INIT(i) { (i) } #ifdef CONFIG_64BIT -#define __CSG_LOOP(ptr, op_val, op_string) ({ \ +#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, __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"); \ + old_val; \ +}) + +#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */ + +#define __ATOMIC64_OR "ogr" +#define __ATOMIC64_AND "ngr" +#define __ATOMIC64_ADD "agr" +#define __ATOMIC64_BARRIER "\n" + +#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \ +({ \ long long old_val, new_val; \ + \ + typecheck(atomic64_t *, ptr); \ asm volatile( \ " lg %0,%2\n" \ "0: lgr %1,%0\n" \ op_string " %1,%3\n" \ " csg %0,%1,%2\n" \ " jl 0b" \ - : "=&d" (old_val), "=&d" (new_val), \ - "=Q" (((atomic_t *)(ptr))->counter) \ - : "d" (op_val), "Q" (((atomic_t *)(ptr))->counter) \ + : "=&d" (old_val), "=&d" (new_val), "+Q" ((ptr)->counter)\ + : "d" (op_val) \ : "cc", "memory"); \ - new_val; \ + old_val; \ }) +#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */ + static inline long long atomic64_read(const atomic64_t *v) { long long c; @@ -149,22 +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 __CSG_LOOP(v, i, "agr"); + return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i; } -static inline long long atomic64_sub_return(long long i, atomic64_t *v) +static inline void atomic64_add(long long i, atomic64_t *v) { - return __CSG_LOOP(v, i, "sgr"); +#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) { - __CSG_LOOP(v, ~mask, "ngr"); + __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER); } static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v) { - __CSG_LOOP(v, mask, "ogr"); + __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER); } #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) @@ -174,13 +266,13 @@ static inline long long atomic64_cmpxchg(atomic64_t *v, { asm volatile( " csg %0,%2,%1" - : "+d" (old), "=Q" (v->counter) - : "d" (new), "Q" (v->counter) + : "+d" (old), "+Q" (v->counter) + : "d" (new) : "cc", "memory"); return old; } -#undef __CSG_LOOP +#undef __ATOMIC64_LOOP #else /* CONFIG_64BIT */ @@ -216,8 +308,8 @@ static inline long long atomic64_xchg(atomic64_t *v, long long new) " lm %0,%N0,%1\n" "0: cds %0,%2,%1\n" " jl 0b\n" - : "=&d" (rp_old), "=Q" (v->counter) - : "d" (rp_new), "Q" (v->counter) + : "=&d" (rp_old), "+Q" (v->counter) + : "d" (rp_new) : "cc"); return rp_old.pair; } @@ -230,8 +322,8 @@ static inline long long atomic64_cmpxchg(atomic64_t *v, asm volatile( " cds %0,%2,%1" - : "+&d" (rp_old), "=Q" (v->counter) - : "d" (rp_new), "Q" (v->counter) + : "+&d" (rp_old), "+Q" (v->counter) + : "d" (rp_new) : "cc"); return rp_old.pair; } @@ -248,17 +340,6 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v) return new; } -static inline long long atomic64_sub_return(long long i, atomic64_t *v) -{ - long long old, new; - - do { - old = atomic64_read(v); - new = old - i; - } while (atomic64_cmpxchg(v, old, new) != old); - return new; -} - static inline void atomic64_set_mask(unsigned long long mask, atomic64_t *v) { long long old, new; @@ -279,9 +360,14 @@ static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v) } while (atomic64_cmpxchg(v, old, new) != old); } +static inline void atomic64_add(long long i, atomic64_t *v) +{ + atomic64_add_return(i, v); +} + #endif /* CONFIG_64BIT */ -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u) { long long c, old; @@ -289,7 +375,7 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) for (;;) { if (unlikely(c == u)) break; - old = atomic64_cmpxchg(v, c, c + a); + old = atomic64_cmpxchg(v, c, c + i); if (likely(old == c)) break; c = old; @@ -314,21 +400,16 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return dec; } -#define atomic64_add(_i, _v) atomic64_add_return(_i, _v) #define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) -#define atomic64_inc(_v) atomic64_add_return(1, _v) +#define atomic64_inc(_v) atomic64_add(1, _v) #define atomic64_inc_return(_v) atomic64_add_return(1, _v) #define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) -#define atomic64_sub(_i, _v) atomic64_sub_return(_i, _v) +#define atomic64_sub_return(_i, _v) atomic64_add_return(-(long long)(_i), _v) +#define atomic64_sub(_i, _v) atomic64_add(-(long long)(_i), _v) #define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) -#define atomic64_dec(_v) atomic64_sub_return(1, _v) +#define atomic64_dec(_v) atomic64_sub(1, _v) #define atomic64_dec_return(_v) atomic64_sub_return(1, _v) #define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) -#define smp_mb__before_atomic_dec() smp_mb() -#define smp_mb__after_atomic_dec() smp_mb() -#define smp_mb__before_atomic_inc() smp_mb() -#define smp_mb__after_atomic_inc() smp_mb() - #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index 10a50880294..19ff956b752 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -13,15 +13,12 @@ * to devices. */ -static inline void mb(void) -{ #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES - /* Fast-BCR without checkpoint synchronization */ - asm volatile("bcr 14,0" : : : "memory"); +/* Fast-BCR without checkpoint synchronization */ +#define mb() do { asm volatile("bcr 14,0" : : : "memory"); } while (0) #else - asm volatile("bcr 15,0" : : : "memory"); +#define mb() do { asm volatile("bcr 15,0" : : : "memory"); } while (0) #endif -} #define rmb() mb() #define wmb() mb() @@ -30,9 +27,25 @@ static inline void mb(void) #define smp_rmb() rmb() #define smp_wmb() wmb() #define smp_read_barrier_depends() read_barrier_depends() -#define smp_mb__before_clear_bit() smp_mb() -#define smp_mb__after_clear_bit() smp_mb() + +#define smp_mb__before_atomic() smp_mb() +#define smp_mb__after_atomic() smp_mb() #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 15422933c60..52054247767 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -1,10 +1,40 @@ /* - * S390 version - * Copyright IBM Corp. 1999 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) + * Copyright IBM Corp. 1999,2013 * - * Derived from "include/asm-i386/bitops.h" - * Copyright (C) 1992, Linus Torvalds + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, + * + * The description below was taken in large parts from the powerpc + * bitops header file: + * Within a word, bits are numbered LSB first. Lot's of places make + * this assumption by directly testing bits with (val & (1<<nr)). + * This can cause confusion for large (> 1 word) bitmaps on a + * big-endian system because, unlike little endian, the number of each + * bit depends on the word size. + * + * 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...........192| + * and on s390: + * |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 + * byte-oriented: + * |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56| + * + * The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit + * number field needs to be reversed compared to the big-endian bit + * fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b). + * + * We also have special functions which work with an MSB0 encoding: + * on an s390x system the bits are numbered: + * |0..............63|64............127|128...........191|192...........255| + * and on s390: + * |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 + * fields. This can be achieved by XOR with 0x3f (64b) or 0x1f (32b). * */ @@ -15,561 +45,353 @@ #error only <linux/bitops.h> can be included directly #endif +#include <linux/typecheck.h> #include <linux/compiler.h> +#include <asm/barrier.h> -/* - * 32 bit bitops format: - * bit 0 is the LSB of *addr; bit 31 is the MSB of *addr; - * bit 32 is the LSB of *(addr+4). That combined with the - * big endian byte order on S390 give the following bit - * order in memory: - * 1f 1e 1d 1c 1b 1a 19 18 17 16 15 14 13 12 11 10 \ - * 0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00 - * after that follows the next long with bit numbers - * 3f 3e 3d 3c 3b 3a 39 38 37 36 35 34 33 32 31 30 - * 2f 2e 2d 2c 2b 2a 29 28 27 26 25 24 23 22 21 20 - * The reason for this bit ordering is the fact that - * in the architecture independent code bits operations - * of the form "flags |= (1 << bitnr)" are used INTERMIXED - * with operation of the form "set_bit(bitnr, flags)". - * - * 64 bit bitops format: - * bit 0 is the LSB of *addr; bit 63 is the MSB of *addr; - * bit 64 is the LSB of *(addr+8). That combined with the - * big endian byte order on S390 give the following bit - * order in memory: - * 3f 3e 3d 3c 3b 3a 39 38 37 36 35 34 33 32 31 30 - * 2f 2e 2d 2c 2b 2a 29 28 27 26 25 24 23 22 21 20 - * 1f 1e 1d 1c 1b 1a 19 18 17 16 15 14 13 12 11 10 - * 0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00 - * after that follows the next long with bit numbers - * 7f 7e 7d 7c 7b 7a 79 78 77 76 75 74 73 72 71 70 - * 6f 6e 6d 6c 6b 6a 69 68 67 66 65 64 63 62 61 60 - * 5f 5e 5d 5c 5b 5a 59 58 57 56 55 54 53 52 51 50 - * 4f 4e 4d 4c 4b 4a 49 48 47 46 45 44 43 42 41 40 - * The reason for this bit ordering is the fact that - * in the architecture independent code bits operations - * of the form "flags |= (1 << bitnr)" are used INTERMIXED - * with operation of the form "set_bit(bitnr, flags)". - */ - -/* bitmap tables from arch/s390/kernel/bitmap.c */ -extern const char _oi_bitmap[]; -extern const char _ni_bitmap[]; -extern const char _zb_findmap[]; -extern const char _sb_findmap[]; +#define __BITOPS_NO_BARRIER "\n" #ifndef CONFIG_64BIT -#define __BITOPS_ALIGN 3 -#define __BITOPS_WORDSIZE 32 #define __BITOPS_OR "or" #define __BITOPS_AND "nr" #define __BITOPS_XOR "xr" +#define __BITOPS_BARRIER "\n" -#define __BITOPS_LOOP(__old, __new, __addr, __val, __op_string) \ +#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \ +({ \ + unsigned long __old, __new; \ + \ + typecheck(unsigned long *, (__addr)); \ asm volatile( \ " l %0,%2\n" \ "0: lr %1,%0\n" \ __op_string " %1,%3\n" \ " cs %0,%1,%2\n" \ " jl 0b" \ - : "=&d" (__old), "=&d" (__new), \ - "=Q" (*(unsigned long *) __addr) \ - : "d" (__val), "Q" (*(unsigned long *) __addr) \ - : "cc"); + : "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\ + : "d" (__val) \ + : "cc", "memory"); \ + __old; \ +}) #else /* CONFIG_64BIT */ -#define __BITOPS_ALIGN 7 -#define __BITOPS_WORDSIZE 64 +#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES + +#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, __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", "memory"); \ + __old; \ +}) + +#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */ + #define __BITOPS_OR "ogr" #define __BITOPS_AND "ngr" #define __BITOPS_XOR "xgr" +#define __BITOPS_BARRIER "\n" -#define __BITOPS_LOOP(__old, __new, __addr, __val, __op_string) \ +#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \ +({ \ + unsigned long __old, __new; \ + \ + typecheck(unsigned long *, (__addr)); \ asm volatile( \ " lg %0,%2\n" \ "0: lgr %1,%0\n" \ __op_string " %1,%3\n" \ " csg %0,%1,%2\n" \ " jl 0b" \ - : "=&d" (__old), "=&d" (__new), \ - "=Q" (*(unsigned long *) __addr) \ - : "d" (__val), "Q" (*(unsigned long *) __addr) \ - : "cc"); + : "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\ + : "d" (__val) \ + : "cc", "memory"); \ + __old; \ +}) + +#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */ #endif /* CONFIG_64BIT */ -#define __BITOPS_WORDS(bits) (((bits)+__BITOPS_WORDSIZE-1)/__BITOPS_WORDSIZE) -#define __BITOPS_BARRIER() asm volatile("" : : : "memory") +#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG) -#ifdef CONFIG_SMP -/* - * SMP safe set_bit routine based on compare and swap (CS) - */ -static inline void set_bit_cs(unsigned long nr, volatile unsigned long *ptr) +static inline unsigned long * +__bitops_word(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr, old, new, mask; - - addr = (unsigned long) ptr; - /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; - /* make OR mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); - /* Do the atomic update. */ - __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR); + unsigned long addr; + + addr = (unsigned long)ptr + ((nr ^ (nr & (BITS_PER_LONG - 1))) >> 3); + return (unsigned long *)addr; } -/* - * SMP safe clear_bit routine based on compare and swap (CS) - */ -static inline void clear_bit_cs(unsigned long nr, volatile unsigned long *ptr) +static inline unsigned char * +__bitops_byte(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr, old, new, mask; - - addr = (unsigned long) ptr; - /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; - /* make AND mask */ - mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1))); - /* Do the atomic update. */ - __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND); + return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -/* - * SMP safe change_bit routine based on compare and swap (CS) - */ -static inline void change_bit_cs(unsigned long nr, volatile unsigned long *ptr) +static inline void set_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr, old, new, mask; - - addr = (unsigned long) ptr; - /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; - /* make XOR mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); - /* Do the atomic update. */ - __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR); + unsigned long *addr = __bitops_word(nr, ptr); + unsigned long mask; + +#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES + if (__builtin_constant_p(nr)) { + unsigned char *caddr = __bitops_byte(nr, ptr); + + asm volatile( + "oi %0,%b1\n" + : "+Q" (*caddr) + : "i" (1 << (nr & 7)) + : "cc", "memory"); + return; + } +#endif + mask = 1UL << (nr & (BITS_PER_LONG - 1)); + __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_NO_BARRIER); } -/* - * SMP safe test_and_set_bit routine based on compare and swap (CS) - */ -static inline int -test_and_set_bit_cs(unsigned long nr, volatile unsigned long *ptr) +static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr, old, new, mask; - - addr = (unsigned long) ptr; - /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; - /* make OR/test mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); - /* Do the atomic update. */ - __BITOPS_LOOP(old, new, addr, mask, __BITOPS_OR); - __BITOPS_BARRIER(); - return (old & mask) != 0; + unsigned long *addr = __bitops_word(nr, ptr); + unsigned long mask; + +#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES + if (__builtin_constant_p(nr)) { + unsigned char *caddr = __bitops_byte(nr, ptr); + + asm volatile( + "ni %0,%b1\n" + : "+Q" (*caddr) + : "i" (~(1 << (nr & 7))) + : "cc", "memory"); + return; + } +#endif + mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); + __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_NO_BARRIER); } -/* - * SMP safe test_and_clear_bit routine based on compare and swap (CS) - */ -static inline int -test_and_clear_bit_cs(unsigned long nr, volatile unsigned long *ptr) +static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr, old, new, mask; - - addr = (unsigned long) ptr; - /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; - /* make AND/test mask */ - mask = ~(1UL << (nr & (__BITOPS_WORDSIZE - 1))); - /* Do the atomic update. */ - __BITOPS_LOOP(old, new, addr, mask, __BITOPS_AND); - __BITOPS_BARRIER(); - return (old ^ new) != 0; + unsigned long *addr = __bitops_word(nr, ptr); + unsigned long mask; + +#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES + if (__builtin_constant_p(nr)) { + unsigned char *caddr = __bitops_byte(nr, ptr); + + asm volatile( + "xi %0,%b1\n" + : "+Q" (*caddr) + : "i" (1 << (nr & 7)) + : "cc", "memory"); + return; + } +#endif + mask = 1UL << (nr & (BITS_PER_LONG - 1)); + __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_NO_BARRIER); } -/* - * SMP safe test_and_change_bit routine based on compare and swap (CS) - */ static inline int -test_and_change_bit_cs(unsigned long nr, volatile unsigned long *ptr) +test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr, old, new, mask; - - addr = (unsigned long) ptr; - /* calculate address for CS */ - addr += (nr ^ (nr & (__BITOPS_WORDSIZE - 1))) >> 3; - /* make XOR/test mask */ - mask = 1UL << (nr & (__BITOPS_WORDSIZE - 1)); - /* Do the atomic update. */ - __BITOPS_LOOP(old, new, addr, mask, __BITOPS_XOR); - __BITOPS_BARRIER(); + unsigned long *addr = __bitops_word(nr, ptr); + unsigned long old, mask; + + mask = 1UL << (nr & (BITS_PER_LONG - 1)); + old = __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_BARRIER); return (old & mask) != 0; } -#endif /* CONFIG_SMP */ -/* - * fast, non-SMP set_bit routine - */ -static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline int +test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned long *addr = __bitops_word(nr, ptr); + unsigned long old, mask; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - asm volatile( - " oc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); + mask = ~(1UL << (nr & (BITS_PER_LONG - 1))); + old = __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_BARRIER); + return (old & ~mask) != 0; } -static inline void -__constant_set_bit(const unsigned long nr, volatile unsigned long *ptr) +static inline int +test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned long *addr = __bitops_word(nr, ptr); + unsigned long old, mask; - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - *(unsigned char *) addr |= 1 << (nr & 7); + mask = 1UL << (nr & (BITS_PER_LONG - 1)); + old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_BARRIER); + return (old & mask) != 0; } -#define set_bit_simple(nr,addr) \ -(__builtin_constant_p((nr)) ? \ - __constant_set_bit((nr),(addr)) : \ - __set_bit((nr),(addr)) ) - -/* - * fast, non-SMP clear_bit routine - */ -static inline void -__clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned char *addr = __bitops_byte(nr, ptr); - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - asm volatile( - " nc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" ); + *addr |= 1 << (nr & 7); } static inline void -__constant_clear_bit(const unsigned long nr, volatile unsigned long *ptr) +__clear_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned char *addr = __bitops_byte(nr, ptr); - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - *(unsigned char *) addr &= ~(1 << (nr & 7)); + *addr &= ~(1 << (nr & 7)); } -#define clear_bit_simple(nr,addr) \ -(__builtin_constant_p((nr)) ? \ - __constant_clear_bit((nr),(addr)) : \ - __clear_bit((nr),(addr)) ) - -/* - * fast, non-SMP change_bit routine - */ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; - - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - asm volatile( - " xc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); -} - -static inline void -__constant_change_bit(const unsigned long nr, volatile unsigned long *ptr) -{ - unsigned long addr; + unsigned char *addr = __bitops_byte(nr, ptr); - addr = ((unsigned long) ptr) + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - *(unsigned char *) addr ^= 1 << (nr & 7); + *addr ^= 1 << (nr & 7); } -#define change_bit_simple(nr,addr) \ -(__builtin_constant_p((nr)) ? \ - __constant_change_bit((nr),(addr)) : \ - __change_bit((nr),(addr)) ) - -/* - * fast, non-SMP test_and_set_bit routine - */ static inline int -test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr) +__test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - ch = *(unsigned char *) addr; - asm volatile( - " oc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) - : "cc", "memory"); + ch = *addr; + *addr |= 1 << (nr & 7); return (ch >> (nr & 7)) & 1; } -#define __test_and_set_bit(X,Y) test_and_set_bit_simple(X,Y) -/* - * fast, non-SMP test_and_clear_bit routine - */ static inline int -test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr) +__test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - ch = *(unsigned char *) addr; - asm volatile( - " nc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) - : "cc", "memory"); + ch = *addr; + *addr &= ~(1 << (nr & 7)); return (ch >> (nr & 7)) & 1; } -#define __test_and_clear_bit(X,Y) test_and_clear_bit_simple(X,Y) -/* - * fast, non-SMP test_and_change_bit routine - */ static inline int -test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr) +__test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) { - unsigned long addr; + unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - ch = *(unsigned char *) addr; - asm volatile( - " xc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) - : "cc", "memory"); + ch = *addr; + *addr ^= 1 << (nr & 7); return (ch >> (nr & 7)) & 1; } -#define __test_and_change_bit(X,Y) test_and_change_bit_simple(X,Y) - -#ifdef CONFIG_SMP -#define set_bit set_bit_cs -#define clear_bit clear_bit_cs -#define change_bit change_bit_cs -#define test_and_set_bit test_and_set_bit_cs -#define test_and_clear_bit test_and_clear_bit_cs -#define test_and_change_bit test_and_change_bit_cs -#else -#define set_bit set_bit_simple -#define clear_bit clear_bit_simple -#define change_bit change_bit_simple -#define test_and_set_bit test_and_set_bit_simple -#define test_and_clear_bit test_and_clear_bit_simple -#define test_and_change_bit test_and_change_bit_simple -#endif - -/* - * This routine doesn't need to be atomic. - */ - -static inline int __test_bit(unsigned long nr, const volatile unsigned long *ptr) +static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr) { - unsigned long addr; - unsigned char ch; + const volatile unsigned char *addr; - addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3); - ch = *(volatile unsigned char *) addr; - return (ch >> (nr & 7)) & 1; -} - -static inline int -__constant_test_bit(unsigned long nr, const volatile unsigned long *addr) { - return (((volatile char *) addr) - [(nr^(__BITOPS_WORDSIZE-8))>>3] & (1<<(nr&7))) != 0; + addr = ((const volatile unsigned char *)ptr); + addr += (nr ^ (BITS_PER_LONG - 8)) >> 3; + return (*addr >> (nr & 7)) & 1; } -#define test_bit(nr,addr) \ -(__builtin_constant_p((nr)) ? \ - __constant_test_bit((nr),(addr)) : \ - __test_bit((nr),(addr)) ) - /* - * Optimized find bit helper functions. + * Functions which use MSB0 bit numbering. + * On an s390x system the bits are numbered: + * |0..............63|64............127|128...........191|192...........255| + * and on s390: + * |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, + unsigned long offset); -/** - * __ffz_word_loop - find byte offset of first long != -1UL - * @addr: pointer to array of unsigned long - * @size: size of the array in bits - */ -static inline unsigned long __ffz_word_loop(const unsigned long *addr, - unsigned long size) +static inline void set_bit_inv(unsigned long nr, volatile unsigned long *ptr) { - typedef struct { long _[__BITOPS_WORDS(size)]; } addrtype; - unsigned long bytes = 0; - - asm volatile( -#ifndef CONFIG_64BIT - " ahi %1,-1\n" - " sra %1,5\n" - " jz 1f\n" - "0: c %2,0(%0,%3)\n" - " jne 1f\n" - " la %0,4(%0)\n" - " brct %1,0b\n" - "1:\n" -#else - " aghi %1,-1\n" - " srag %1,%1,6\n" - " jz 1f\n" - "0: cg %2,0(%0,%3)\n" - " jne 1f\n" - " la %0,8(%0)\n" - " brct %1,0b\n" - "1:\n" -#endif - : "+&a" (bytes), "+&d" (size) - : "d" (-1UL), "a" (addr), "m" (*(addrtype *) addr) - : "cc" ); - return bytes; -} - -/** - * __ffs_word_loop - find byte offset of first long != 0UL - * @addr: pointer to array of unsigned long - * @size: size of the array in bits - */ -static inline unsigned long __ffs_word_loop(const unsigned long *addr, - unsigned long size) -{ - typedef struct { long _[__BITOPS_WORDS(size)]; } addrtype; - unsigned long bytes = 0; - - asm volatile( -#ifndef CONFIG_64BIT - " ahi %1,-1\n" - " sra %1,5\n" - " jz 1f\n" - "0: c %2,0(%0,%3)\n" - " jne 1f\n" - " la %0,4(%0)\n" - " brct %1,0b\n" - "1:\n" -#else - " aghi %1,-1\n" - " srag %1,%1,6\n" - " jz 1f\n" - "0: cg %2,0(%0,%3)\n" - " jne 1f\n" - " la %0,8(%0)\n" - " brct %1,0b\n" - "1:\n" -#endif - : "+&a" (bytes), "+&a" (size) - : "d" (0UL), "a" (addr), "m" (*(addrtype *) addr) - : "cc" ); - return bytes; + return set_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -/** - * __ffz_word - add number of the first unset bit - * @nr: base value the bit number is added to - * @word: the word that is searched for unset bits - */ -static inline unsigned long __ffz_word(unsigned long nr, unsigned long word) +static inline void clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) { -#ifdef CONFIG_64BIT - if ((word & 0xffffffff) == 0xffffffff) { - word >>= 32; - nr += 32; - } -#endif - if ((word & 0xffff) == 0xffff) { - word >>= 16; - nr += 16; - } - if ((word & 0xff) == 0xff) { - word >>= 8; - nr += 8; - } - return nr + _zb_findmap[(unsigned char) word]; + return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -/** - * __ffs_word - add number of the first set bit - * @nr: base value the bit number is added to - * @word: the word that is searched for set bits - */ -static inline unsigned long __ffs_word(unsigned long nr, unsigned long word) +static inline void __set_bit_inv(unsigned long nr, volatile unsigned long *ptr) { -#ifdef CONFIG_64BIT - if ((word & 0xffffffff) == 0) { - word >>= 32; - nr += 32; - } -#endif - if ((word & 0xffff) == 0) { - word >>= 16; - nr += 16; - } - if ((word & 0xff) == 0) { - word >>= 8; - nr += 8; - } - return nr + _sb_findmap[(unsigned char) word]; + return __set_bit(nr ^ (BITS_PER_LONG - 1), ptr); } - -/** - * __load_ulong_be - load big endian unsigned long - * @p: pointer to array of unsigned long - * @offset: byte offset of source value in the array - */ -static inline unsigned long __load_ulong_be(const unsigned long *p, - unsigned long offset) +static inline void __clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) { - p = (unsigned long *)((unsigned long) p + offset); - return *p; + return __clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -/** - * __load_ulong_le - load little endian unsigned long - * @p: pointer to array of unsigned long - * @offset: byte offset of source value in the array - */ -static inline unsigned long __load_ulong_le(const unsigned long *p, - unsigned long offset) +static inline int test_bit_inv(unsigned long nr, + const volatile unsigned long *ptr) { - unsigned long word; - - p = (unsigned long *)((unsigned long) p + offset); -#ifndef CONFIG_64BIT - asm volatile( - " ic %0,%O1(%R1)\n" - " icm %0,2,%O1+1(%R1)\n" - " icm %0,4,%O1+2(%R1)\n" - " icm %0,8,%O1+3(%R1)" - : "=&d" (word) : "Q" (*p) : "cc"); -#else - asm volatile( - " lrvg %0,%1" - : "=d" (word) : "m" (*p) ); -#endif - return word; + return test_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -/* - * The various find bit functions. - */ +#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES -/* - * ffz - find first zero in word. - * @word: The word to search +/** + * __flogr - find leftmost one + * @word - The word to search * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -static inline unsigned long ffz(unsigned long word) -{ - return __ffz_word(0, word); + * Returns the bit number of the most significant bit set, + * where the most significant bit has bit number 0. + * If no bit is set this function returns 64. + */ +static inline unsigned char __flogr(unsigned long word) +{ + if (__builtin_constant_p(word)) { + unsigned long bit = 0; + + if (!word) + return 64; + if (!(word & 0xffffffff00000000UL)) { + word <<= 32; + bit += 32; + } + if (!(word & 0xffff000000000000UL)) { + word <<= 16; + bit += 16; + } + if (!(word & 0xff00000000000000UL)) { + word <<= 8; + bit += 8; + } + if (!(word & 0xf000000000000000UL)) { + word <<= 4; + bit += 4; + } + if (!(word & 0xc000000000000000UL)) { + word <<= 2; + bit += 2; + } + if (!(word & 0x8000000000000000UL)) { + word <<= 1; + bit += 1; + } + return bit; + } else { + register unsigned long bit asm("4") = word; + register unsigned long out asm("5"); + + asm volatile( + " flogr %[bit],%[bit]\n" + : [bit] "+d" (bit), [out] "=d" (out) : : "cc"); + return bit; + } } /** @@ -578,337 +400,83 @@ static inline unsigned long ffz(unsigned long word) * * Undefined if no bit exists, so code should check against 0 first. */ -static inline unsigned long __ffs (unsigned long word) +static inline unsigned long __ffs(unsigned long word) { - return __ffs_word(0, word); + return __flogr(-word & word) ^ (BITS_PER_LONG - 1); } /** * ffs - find first bit set - * @x: the word to search + * @word: the word to search * - * This is defined the same way as - * the libc and compiler builtin ffs routines, therefore - * differs in spirit from the above ffz (man ffs). + * This is defined the same way as the libc and + * compiler builtin ffs routines (man ffs). */ -static inline int ffs(int x) +static inline int ffs(int word) { - if (!x) - return 0; - return __ffs_word(1, x); + unsigned long mask = 2 * BITS_PER_LONG - 1; + unsigned int val = (unsigned int)word; + + return (1 + (__flogr(-val & val) ^ (BITS_PER_LONG - 1))) & mask; } /** - * find_first_zero_bit - find the first zero bit in a memory region - * @addr: The address to start the search at - * @size: The maximum size to search + * __fls - find last (most-significant) set bit in a long word + * @word: the word to search * - * Returns the bit-number of the first zero bit, not the number of the byte - * containing a bit. + * Undefined if no set bit exists, so code should check against 0 first. */ -static inline unsigned long find_first_zero_bit(const unsigned long *addr, - unsigned long size) +static inline unsigned long __fls(unsigned long word) { - unsigned long bytes, bits; - - if (!size) - return 0; - bytes = __ffz_word_loop(addr, size); - bits = __ffz_word(bytes*8, __load_ulong_be(addr, bytes)); - return (bits < size) ? bits : size; + return __flogr(word) ^ (BITS_PER_LONG - 1); } -#define find_first_zero_bit find_first_zero_bit /** - * find_first_bit - find the first set bit in a memory region - * @addr: The address to start the search at - * @size: The maximum size to search + * fls64 - find last set bit in a 64-bit word + * @word: the word to search * - * Returns the bit-number of the first set bit, not the number of the byte - * containing a bit. - */ -static inline unsigned long find_first_bit(const unsigned long * addr, - unsigned long size) -{ - unsigned long bytes, bits; - - if (!size) - return 0; - bytes = __ffs_word_loop(addr, size); - bits = __ffs_word(bytes*8, __load_ulong_be(addr, bytes)); - return (bits < size) ? bits : size; -} -#define find_first_bit find_first_bit - -/* - * Big endian variant whichs starts bit counting from left using - * the flogr (find leftmost one) instruction. - */ -static inline unsigned long __flo_word(unsigned long nr, unsigned long val) -{ - register unsigned long bit asm("2") = val; - register unsigned long out asm("3"); - - asm volatile ( - " .insn rre,0xb9830000,%[bit],%[bit]\n" - : [bit] "+d" (bit), [out] "=d" (out) : : "cc"); - return nr + bit; -} - -/* - * 64 bit special left bitops format: - * order in memory: - * 00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f - * 10 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f - * 20 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f - * 30 31 32 33 34 35 36 37 38 39 3a 3b 3c 3d 3e 3f - * after that follows the next long with bit numbers - * 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f - * 50 51 52 53 54 55 56 57 58 59 5a 5b 5c 5d 5e 5f - * 60 61 62 63 64 65 66 67 68 69 6a 6b 6c 6d 6e 6f - * 70 71 72 73 74 75 76 77 78 79 7a 7b 7c 7d 7e 7f - * The reason for this bit ordering is the fact that - * the hardware sets bits in a bitmap starting at bit 0 - * and we don't want to scan the bitmap from the 'wrong - * end'. + * This is defined in a similar way as the libc and compiler builtin + * ffsll, but returns the position of the most significant set bit. + * + * fls64(value) returns 0 if value is 0 or the position of the last + * set bit if value is nonzero. The last (most significant) bit is + * at position 64. */ -static inline unsigned long find_first_bit_left(const unsigned long *addr, - unsigned long size) +static inline int fls64(unsigned long word) { - unsigned long bytes, bits; - - if (!size) - return 0; - bytes = __ffs_word_loop(addr, size); - bits = __flo_word(bytes * 8, __load_ulong_be(addr, bytes)); - return (bits < size) ? bits : size; -} - -static inline int find_next_bit_left(const unsigned long *addr, - unsigned long size, - unsigned long offset) -{ - const unsigned long *p; - unsigned long bit, set; - - if (offset >= size) - return size; - bit = offset & (__BITOPS_WORDSIZE - 1); - offset -= bit; - size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; - if (bit) { - set = __flo_word(0, *p & (~0UL << bit)); - if (set >= size) - return size + offset; - if (set < __BITOPS_WORDSIZE) - return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; - p++; - } - return offset + find_first_bit_left(p, size); -} + unsigned long mask = 2 * BITS_PER_LONG - 1; -#define for_each_set_bit_left(bit, addr, size) \ - for ((bit) = find_first_bit_left((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit_left((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_left_cont(bit, addr, size) \ - for ((bit) = find_next_bit_left((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit_left((addr), (size), (bit) + 1)) - -/** - * find_next_zero_bit - find the first zero bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search - */ -static inline int find_next_zero_bit (const unsigned long * addr, - unsigned long size, - unsigned long offset) -{ - const unsigned long *p; - unsigned long bit, set; - - if (offset >= size) - return size; - bit = offset & (__BITOPS_WORDSIZE - 1); - offset -= bit; - size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; - if (bit) { - /* - * __ffz_word returns __BITOPS_WORDSIZE - * if no zero bit is present in the word. - */ - set = __ffz_word(bit, *p >> bit); - if (set >= size) - return size + offset; - if (set < __BITOPS_WORDSIZE) - return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; - p++; - } - return offset + find_first_zero_bit(p, size); + return (1 + (__flogr(word) ^ (BITS_PER_LONG - 1))) & mask; } -#define find_next_zero_bit find_next_zero_bit /** - * find_next_bit - find the first set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search + * fls - find last (most-significant) bit set + * @word: the word to search + * + * This is defined the same way as ffs. + * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline int find_next_bit (const unsigned long * addr, - unsigned long size, - unsigned long offset) +static inline int fls(int word) { - const unsigned long *p; - unsigned long bit, set; - - if (offset >= size) - return size; - bit = offset & (__BITOPS_WORDSIZE - 1); - offset -= bit; - size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; - if (bit) { - /* - * __ffs_word returns __BITOPS_WORDSIZE - * if no one bit is present in the word. - */ - set = __ffs_word(0, *p & (~0UL << bit)); - if (set >= size) - return size + offset; - if (set < __BITOPS_WORDSIZE) - return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; - p++; - } - return offset + find_first_bit(p, size); + return fls64((unsigned int)word); } -#define find_next_bit find_next_bit -/* - * Every architecture must define this function. It's the fastest - * way of searching a 140-bit bitmap where the first 100 bits are - * unlikely to be set. It's guaranteed that at least one of the 140 - * bits is cleared. - */ -static inline int sched_find_first_bit(unsigned long *b) -{ - return find_first_bit(b, 140); -} +#else /* CONFIG_HAVE_MARCH_Z9_109_FEATURES */ -#include <asm-generic/bitops/fls.h> +#include <asm-generic/bitops/__ffs.h> +#include <asm-generic/bitops/ffs.h> #include <asm-generic/bitops/__fls.h> +#include <asm-generic/bitops/fls.h> #include <asm-generic/bitops/fls64.h> +#endif /* CONFIG_HAVE_MARCH_Z9_109_FEATURES */ + +#include <asm-generic/bitops/ffz.h> +#include <asm-generic/bitops/find.h> #include <asm-generic/bitops/hweight.h> #include <asm-generic/bitops/lock.h> - -/* - * ATTENTION: intel byte ordering convention for ext2 and minix !! - * bit 0 is the LSB of addr; bit 31 is the MSB of addr; - * bit 32 is the LSB of (addr+4). - * That combined with the little endian byte order of Intel gives the - * following bit order in memory: - * 07 06 05 04 03 02 01 00 15 14 13 12 11 10 09 08 \ - * 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24 - */ - -static inline int find_first_zero_bit_le(void *vaddr, unsigned int size) -{ - unsigned long bytes, bits; - - if (!size) - return 0; - bytes = __ffz_word_loop(vaddr, size); - bits = __ffz_word(bytes*8, __load_ulong_le(vaddr, bytes)); - return (bits < size) ? bits : size; -} -#define find_first_zero_bit_le find_first_zero_bit_le - -static inline int find_next_zero_bit_le(void *vaddr, unsigned long size, - unsigned long offset) -{ - unsigned long *addr = vaddr, *p; - unsigned long bit, set; - - if (offset >= size) - return size; - bit = offset & (__BITOPS_WORDSIZE - 1); - offset -= bit; - size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; - if (bit) { - /* - * s390 version of ffz returns __BITOPS_WORDSIZE - * if no zero bit is present in the word. - */ - set = __ffz_word(bit, __load_ulong_le(p, 0) >> bit); - if (set >= size) - return size + offset; - if (set < __BITOPS_WORDSIZE) - return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; - p++; - } - return offset + find_first_zero_bit_le(p, size); -} -#define find_next_zero_bit_le find_next_zero_bit_le - -static inline unsigned long find_first_bit_le(void *vaddr, unsigned long size) -{ - unsigned long bytes, bits; - - if (!size) - return 0; - bytes = __ffs_word_loop(vaddr, size); - bits = __ffs_word(bytes*8, __load_ulong_le(vaddr, bytes)); - return (bits < size) ? bits : size; -} -#define find_first_bit_le find_first_bit_le - -static inline int find_next_bit_le(void *vaddr, unsigned long size, - unsigned long offset) -{ - unsigned long *addr = vaddr, *p; - unsigned long bit, set; - - if (offset >= size) - return size; - bit = offset & (__BITOPS_WORDSIZE - 1); - offset -= bit; - size -= offset; - p = addr + offset / __BITOPS_WORDSIZE; - if (bit) { - /* - * s390 version of ffz returns __BITOPS_WORDSIZE - * if no zero bit is present in the word. - */ - set = __ffs_word(0, __load_ulong_le(p, 0) & (~0UL << bit)); - if (set >= size) - return size + offset; - if (set < __BITOPS_WORDSIZE) - return set + offset; - offset += __BITOPS_WORDSIZE; - size -= __BITOPS_WORDSIZE; - p++; - } - return offset + find_first_bit_le(p, size); -} -#define find_next_bit_le find_next_bit_le - +#include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/le.h> - #include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* _S390_BITOPS_H */ diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index e6061617a50..b80e456d642 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -219,12 +219,15 @@ 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 int ccw_device_force_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 *); int ccw_device_siosl(struct ccw_device *); extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *); -extern void *ccw_device_get_chp_desc(struct ccw_device *, int); +struct channel_path_desc *ccw_device_get_chp_desc(struct ccw_device *, int); #endif /* _S390_CCWDEV_H_ */ diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index 23723ce5ca7..057ce0ca637 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -10,6 +10,8 @@ struct ccw_driver; * @count: number of attached slave devices * @dev: embedded device structure * @cdev: variable number of slave devices, allocated as needed + * @ungroup_work: work to be done when a ccwgroup notifier has action + * type %BUS_NOTIFY_UNBIND_DRIVER */ struct ccwgroup_device { enum { @@ -22,6 +24,7 @@ struct ccwgroup_device { /* public: */ unsigned int count; struct device dev; + struct work_struct ungroup_work; struct ccw_device *cdev[0]; }; 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/chpid.h b/arch/s390/include/asm/chpid.h index 38c405ef89c..7298eec9854 100644 --- a/arch/s390/include/asm/chpid.h +++ b/arch/s390/include/asm/chpid.h @@ -8,6 +8,17 @@ #include <uapi/asm/chpid.h> #include <asm/cio.h> +struct channel_path_desc { + u8 flags; + u8 lsn; + u8 desc; + u8 chpid; + u8 swla; + u8 zeroes; + u8 chla; + u8 chpp; +} __packed; + static inline void chp_id_init(struct chp_id *chpid) { memset(chpid, 0, sizeof(struct chp_id)); diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index ad2b924167d..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 @@ -296,8 +296,7 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1, return 0; } -extern void wait_cons_dev(void); - +void channel_subsystem_reinit(void); extern void css_schedule_reprobe(void); extern void reipl_ccw_dev(struct ccw_dev_id *id); diff --git a/arch/s390/include/asm/clp.h b/arch/s390/include/asm/clp.h index 6c3aecc245f..a0e71a501f7 100644 --- a/arch/s390/include/asm/clp.h +++ b/arch/s390/include/asm/clp.h @@ -2,7 +2,7 @@ #define _ASM_S390_CLP_H /* CLP common request & response block size */ -#define CLP_BLK_SIZE (PAGE_SIZE * 2) +#define CLP_BLK_SIZE PAGE_SIZE struct clp_req_hdr { u16 len; 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 f8c6df6cd1f..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 @@ -22,6 +26,7 @@ #define PSW32_MASK_ASC 0x0000C000UL #define PSW32_MASK_CC 0x00003000UL #define PSW32_MASK_PM 0x00000f00UL +#define PSW32_MASK_RI 0x00000080UL #define PSW32_MASK_USER 0x0000FF00UL @@ -35,7 +40,10 @@ #define PSW32_ASC_SECONDARY 0x00008000UL #define PSW32_ASC_HOME 0x0000C000UL -extern u32 psw32_user_bits; +#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_PRIMARY) #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "s390\0\0\0\0" @@ -70,6 +78,22 @@ typedef u32 compat_ulong_t; typedef u64 compat_u64; typedef u32 compat_uptr_t; +typedef struct { + u32 mask; + u32 addr; +} __aligned(8) psw_compat_t; + +typedef struct { + psw_compat_t psw; + u32 gprs[NUM_GPRS]; + u32 acrs[NUM_ACRS]; + u32 orig_gpr2; +} s390_compat_regs; + +typedef struct { + u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; + struct compat_timespec { compat_time_t tv_sec; s32 tv_nsec; @@ -124,18 +148,33 @@ struct compat_flock64 { }; struct compat_statfs { - s32 f_type; - s32 f_bsize; - s32 f_blocks; - s32 f_bfree; - s32 f_bavail; - s32 f_files; - s32 f_ffree; + u32 f_type; + u32 f_bsize; + u32 f_blocks; + u32 f_bfree; + u32 f_bavail; + u32 f_files; + u32 f_ffree; compat_fsid_t f_fsid; - s32 f_namelen; - s32 f_frsize; - s32 f_flags; - s32 f_spare[5]; + u32 f_namelen; + u32 f_frsize; + u32 f_flags; + u32 f_spare[4]; +}; + +struct compat_statfs64 { + u32 f_type; + u32 f_bsize; + u64 f_blocks; + u64 f_bfree; + u64 f_bavail; + u64 f_files; + u64 f_ffree; + compat_fsid_t f_fsid; + u32 f_namelen; + u32 f_frsize; + u32 f_flags; + u32 f_spare[4]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff @@ -248,8 +287,6 @@ static inline int is_compat_task(void) return is_32bit_task(); } -#endif - static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; @@ -260,6 +297,8 @@ static inline void __user *arch_compat_alloc_user_space(long len) return (void __user *) (stack - len); } +#endif + struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index 35f0020b7ba..cb700d54bd8 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -12,6 +12,7 @@ #ifndef _ASM_S390_CPU_MF_H #define _ASM_S390_CPU_MF_H +#include <linux/errno.h> #include <asm/facility.h> #define CPU_MF_INT_SF_IAE (1 << 31) /* invalid entry address */ @@ -34,12 +35,12 @@ /* CPU measurement facility support */ static inline int cpum_cf_avail(void) { - return MACHINE_HAS_SPP && test_facility(67); + return MACHINE_HAS_LPP && test_facility(67); } static inline int cpum_sf_avail(void) { - return MACHINE_HAS_SPP && test_facility(68); + return MACHINE_HAS_LPP && test_facility(68); } @@ -55,6 +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) { @@ -98,4 +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/cputime.h b/arch/s390/include/asm/cputime.h index d2ff41370c0..f65bd363451 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -13,9 +13,6 @@ #include <asm/div64.h> -#define __ARCH_HAS_VTIME_ACCOUNT -#define __ARCH_HAS_VTIME_TASK_SWITCH - /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ typedef unsigned long long __nocast cputime_t; 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/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index debfda33d1f..31ab9f346d7 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -7,70 +7,76 @@ #ifndef __ASM_CTL_REG_H #define __ASM_CTL_REG_H -#ifdef CONFIG_64BIT - -#define __ctl_load(array, low, high) ({ \ - typedef struct { char _[sizeof(array)]; } addrtype; \ - asm volatile( \ - " lctlg %1,%2,%0\n" \ - : : "Q" (*(addrtype *)(&array)), \ - "i" (low), "i" (high)); \ - }) - -#define __ctl_store(array, low, high) ({ \ - typedef struct { char _[sizeof(array)]; } addrtype; \ - asm volatile( \ - " stctg %1,%2,%0\n" \ - : "=Q" (*(addrtype *)(&array)) \ - : "i" (low), "i" (high)); \ - }) - -#else /* CONFIG_64BIT */ - -#define __ctl_load(array, low, high) ({ \ - typedef struct { char _[sizeof(array)]; } addrtype; \ - asm volatile( \ - " lctl %1,%2,%0\n" \ - : : "Q" (*(addrtype *)(&array)), \ - "i" (low), "i" (high)); \ -}) - -#define __ctl_store(array, low, high) ({ \ - typedef struct { char _[sizeof(array)]; } addrtype; \ - asm volatile( \ - " stctl %1,%2,%0\n" \ - : "=Q" (*(addrtype *)(&array)) \ - : "i" (low), "i" (high)); \ - }) - -#endif /* CONFIG_64BIT */ - -#define __ctl_set_bit(cr, bit) ({ \ - unsigned long __dummy; \ - __ctl_store(__dummy, cr, cr); \ - __dummy |= 1UL << (bit); \ - __ctl_load(__dummy, cr, cr); \ -}) +#include <linux/bug.h> -#define __ctl_clear_bit(cr, bit) ({ \ - unsigned long __dummy; \ - __ctl_store(__dummy, cr, cr); \ - __dummy &= ~(1UL << (bit)); \ - __ctl_load(__dummy, cr, cr); \ -}) +#ifdef CONFIG_64BIT +# define __CTL_LOAD "lctlg" +# define __CTL_STORE "stctg" +#else +# define __CTL_LOAD "lctl" +# define __CTL_STORE "stctl" +#endif + +#define __ctl_load(array, low, high) { \ + typedef struct { char _[sizeof(array)]; } addrtype; \ + \ + BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\ + asm volatile( \ + __CTL_LOAD " %1,%2,%0\n" \ + : : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\ +} + +#define __ctl_store(array, low, high) { \ + typedef struct { char _[sizeof(array)]; } addrtype; \ + \ + BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\ + asm volatile( \ + __CTL_STORE " %1,%2,%0\n" \ + : "=Q" (*(addrtype *)(&array)) \ + : "i" (low), "i" (high)); \ +} + +static inline void __ctl_set_bit(unsigned int cr, unsigned int bit) +{ + unsigned long reg; + + __ctl_store(reg, cr, cr); + reg |= 1UL << bit; + __ctl_load(reg, cr, cr); +} + +static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit) +{ + unsigned long reg; + + __ctl_store(reg, cr, cr); + reg &= ~(1UL << bit); + __ctl_load(reg, cr, cr); +} + +void smp_ctl_set_bit(int cr, int bit); +void smp_ctl_clear_bit(int cr, int bit); + +union ctlreg0 { + unsigned long val; + struct { +#ifdef CONFIG_64BIT + unsigned long : 32; +#endif + unsigned long : 3; + unsigned long lap : 1; /* Low-address-protection control */ + unsigned long : 4; + unsigned long edat : 1; /* Enhanced-DAT-enablement control */ + unsigned long : 23; + }; +}; #ifdef CONFIG_SMP - -extern void smp_ctl_set_bit(int cr, int bit); -extern void smp_ctl_clear_bit(int cr, int bit); -#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit) -#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit) - +# define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit) +# define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit) #else - -#define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit) -#define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit) - -#endif /* CONFIG_SMP */ +# define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit) +# define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit) +#endif #endif /* __ASM_CTL_REG_H */ diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 188c5052a20..530c15eb01e 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -107,6 +107,11 @@ void debug_set_level(debug_info_t* id, int new_level); void debug_set_critical(void); void debug_stop_all(void); +static inline bool debug_level_enabled(debug_info_t* id, int level) +{ + return level <= id->level; +} + static inline debug_entry_t* debug_event(debug_info_t* id, int level, void* data, int length) { diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h new file mode 100644 index 00000000000..04a83f5773c --- /dev/null +++ b/arch/s390/include/asm/dis.h @@ -0,0 +1,52 @@ +/* + * Disassemble s390 instructions. + * + * Copyright IBM Corp. 2007 + * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), + */ + +#ifndef __ASM_S390_DIS_H__ +#define __ASM_S390_DIS_H__ + +/* Type of operand */ +#define OPERAND_GPR 0x1 /* Operand printed as %rx */ +#define OPERAND_FPR 0x2 /* Operand printed as %fx */ +#define OPERAND_AR 0x4 /* Operand printed as %ax */ +#define OPERAND_CR 0x8 /* Operand printed as %cx */ +#define OPERAND_DISP 0x10 /* Operand printed as displacement */ +#define OPERAND_BASE 0x20 /* Operand printed as base register */ +#define OPERAND_INDEX 0x40 /* Operand printed as index register */ +#define OPERAND_PCREL 0x80 /* Operand printed as pc-relative symbol */ +#define OPERAND_SIGNED 0x100 /* Operand printed as signed value */ +#define OPERAND_LENGTH 0x200 /* Operand printed as length (+1) */ + + +struct s390_operand { + int bits; /* The number of bits in the operand. */ + int shift; /* The number of bits to shift. */ + int flags; /* One bit syntax flags. */ +}; + +struct s390_insn { + const char name[5]; + unsigned char opfrag; + unsigned char format; +}; + + +static inline int insn_length(unsigned char code) +{ + return ((((int) code + 64) >> 7) + 1) << 1; +} + +void show_code(struct pt_regs *regs); +void print_fn_code(unsigned char *code, unsigned long len); +int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len); +struct s390_insn *find_insn(unsigned char *code); + +static inline int is_known_insn(unsigned char *code) +{ + return !!find_insn(code); +} + +#endif /* __ASM_S390_DIS_H__ */ diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h index 8a32f7dfd3a..3fbc67d9e19 100644 --- a/arch/s390/include/asm/dma-mapping.h +++ b/arch/s390/include/asm/dma-mapping.h @@ -19,9 +19,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) } extern int dma_set_mask(struct device *dev, u64 mask); -extern int dma_is_consistent(struct device *dev, dma_addr_t dma_handle); -extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction direction); + +static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction direction) +{ +} #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) @@ -48,9 +50,10 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *dma_ops = get_dma_ops(dev); + debug_dma_mapping_error(dev, dma_addr); if (dma_ops->mapping_error) return dma_ops->mapping_error(dev, dma_addr); - return (dma_addr == 0UL); + return dma_addr == DMA_ERROR_CODE; } static inline void *dma_alloc_coherent(struct device *dev, size_t size, @@ -69,8 +72,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size, { struct dma_map_ops *dma_ops = get_dma_ops(dev); - dma_ops->free(dev, size, cpu_addr, dma_handle, NULL); debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); + dma_ops->free(dev, size, cpu_addr, dma_handle, NULL); } #endif /* _ASM_S390_DMA_MAPPING_H */ diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index 8d4847191ec..67026300c88 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -34,6 +34,8 @@ struct arsb { u32 reserved[4]; } __packed; +#define EQC_WR_PROHIBIT 22 + struct msb { u8 fmt:4; u8 oc:4; @@ -96,29 +98,20 @@ struct scm_device { #define OP_STATE_TEMP_ERR 2 #define OP_STATE_PERM_ERR 3 +enum scm_event {SCM_CHANGE, SCM_AVAIL}; + struct scm_driver { struct device_driver drv; int (*probe) (struct scm_device *scmdev); int (*remove) (struct scm_device *scmdev); - void (*notify) (struct scm_device *scmdev); + void (*notify) (struct scm_device *scmdev, enum scm_event event); void (*handler) (struct scm_device *scmdev, void *data, int error); }; int scm_driver_register(struct scm_driver *scmdrv); void scm_driver_unregister(struct scm_driver *scmdrv); -int scm_start_aob(struct aob *aob); +int eadm_start_aob(struct aob *aob); void scm_irq_handler(struct aob *aob, int error); -struct eadm_ops { - int (*eadm_start) (struct aob *aob); - struct module *owner; -}; - -int scm_get_ref(void); -void scm_put_ref(void); - -void register_eadm_ops(struct eadm_ops *ops); -void unregister_eadm_ops(struct eadm_ops *ops); - #endif /* _ASM_S390_EADM_H */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 178ff966a8b..78f4f8711d5 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -119,6 +119,8 @@ */ #include <asm/ptrace.h> +#include <asm/compat.h> +#include <asm/syscall.h> #include <asm/user.h> typedef s390_fp_regs elf_fpregset_t; @@ -180,21 +182,31 @@ extern unsigned long elf_hwcap; extern char elf_platform[]; #define ELF_PLATFORM (elf_platform) -#ifndef CONFIG_64BIT +#ifndef CONFIG_COMPAT #define SET_PERSONALITY(ex) \ - set_personality(PER_LINUX | (current->personality & (~PER_MASK))) -#else /* CONFIG_64BIT */ +do { \ + set_personality(PER_LINUX | \ + (current->personality & (~PER_MASK))); \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table; \ +} while (0) +#else /* CONFIG_COMPAT */ #define SET_PERSONALITY(ex) \ do { \ if (personality(current->personality) != PER_LINUX32) \ set_personality(PER_LINUX | \ (current->personality & ~PER_MASK)); \ - if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ + if ((ex).e_ident[EI_CLASS] == ELFCLASS32) { \ set_thread_flag(TIF_31BIT); \ - else \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table_emu; \ + } else { \ clear_thread_flag(TIF_31BIT); \ + current_thread_info()->sys_call_table = \ + (unsigned long) &sys_call_table; \ + } \ } while (0) -#endif /* CONFIG_64BIT */ +#endif /* CONFIG_COMPAT */ #define STACK_RND_MASK 0x7ffUL diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 2ee66a65f2d..0aa6a7ed95a 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -13,6 +13,16 @@ #define MAX_FACILITY_BIT (256*8) /* stfle_fac_list has 256 bytes */ +static inline int __test_facility(unsigned long nr, void *facilities) +{ + unsigned char *ptr; + + if (nr >= MAX_FACILITY_BIT) + return 0; + ptr = (unsigned char *) facilities + (nr >> 3); + return (*ptr & (0x80 >> (nr & 7))) != 0; +} + /* * The test_facility function uses the bit odering where the MSB is bit 0. * That makes it easier to query facility bits with the bit number as @@ -20,12 +30,7 @@ */ static inline int test_facility(unsigned long nr) { - unsigned char *ptr; - - if (nr >= MAX_FACILITY_BIT) - return 0; - ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3); - return (*ptr & (0x80 >> (nr & 7))) != 0; + return __test_facility(nr, &S390_lowcore.stfle_fac_list); } /** diff --git a/arch/s390/include/asm/fcx.h b/arch/s390/include/asm/fcx.h index ef617099507..7ecb92b469b 100644 --- a/arch/s390/include/asm/fcx.h +++ b/arch/s390/include/asm/fcx.h @@ -12,9 +12,9 @@ #define TCW_FORMAT_DEFAULT 0 #define TCW_TIDAW_FORMAT_DEFAULT 0 -#define TCW_FLAGS_INPUT_TIDA 1 << (23 - 5) -#define TCW_FLAGS_TCCB_TIDA 1 << (23 - 6) -#define TCW_FLAGS_OUTPUT_TIDA 1 << (23 - 7) +#define TCW_FLAGS_INPUT_TIDA (1 << (23 - 5)) +#define TCW_FLAGS_TCCB_TIDA (1 << (23 - 6)) +#define TCW_FLAGS_OUTPUT_TIDA (1 << (23 - 7)) #define TCW_FLAGS_TIDAW_FORMAT(x) ((x) & 3) << (23 - 9) #define TCW_FLAGS_GET_TIDAW_FORMAT(x) (((x) >> (23 - 9)) & 3) @@ -54,11 +54,11 @@ struct tcw { u32 intrg; } __attribute__ ((packed, aligned(64))); -#define TIDAW_FLAGS_LAST 1 << (7 - 0) -#define TIDAW_FLAGS_SKIP 1 << (7 - 1) -#define TIDAW_FLAGS_DATA_INT 1 << (7 - 2) -#define TIDAW_FLAGS_TTIC 1 << (7 - 3) -#define TIDAW_FLAGS_INSERT_CBC 1 << (7 - 4) +#define TIDAW_FLAGS_LAST (1 << (7 - 0)) +#define TIDAW_FLAGS_SKIP (1 << (7 - 1)) +#define TIDAW_FLAGS_DATA_INT (1 << (7 - 2)) +#define TIDAW_FLAGS_TTIC (1 << (7 - 3)) +#define TIDAW_FLAGS_INSERT_CBC (1 << (7 - 4)) /** * struct tidaw - Transport-Indirect-Addressing Word (TIDAW) @@ -106,9 +106,9 @@ struct tsa_ddpc { u8 sense[32]; } __attribute__ ((packed)); -#define TSA_INTRG_FLAGS_CU_STATE_VALID 1 << (7 - 0) -#define TSA_INTRG_FLAGS_DEV_STATE_VALID 1 << (7 - 1) -#define TSA_INTRG_FLAGS_OP_STATE_VALID 1 << (7 - 2) +#define TSA_INTRG_FLAGS_CU_STATE_VALID (1 << (7 - 0)) +#define TSA_INTRG_FLAGS_DEV_STATE_VALID (1 << (7 - 1)) +#define TSA_INTRG_FLAGS_OP_STATE_VALID (1 << (7 - 2)) /** * struct tsa_intrg - Interrogate Transport-Status Area (Intrg. TSA) @@ -140,10 +140,10 @@ struct tsa_intrg { #define TSB_FORMAT_DDPC 2 #define TSB_FORMAT_INTRG 3 -#define TSB_FLAGS_DCW_OFFSET_VALID 1 << (7 - 0) -#define TSB_FLAGS_COUNT_VALID 1 << (7 - 1) -#define TSB_FLAGS_CACHE_MISS 1 << (7 - 2) -#define TSB_FLAGS_TIME_VALID 1 << (7 - 3) +#define TSB_FLAGS_DCW_OFFSET_VALID (1 << (7 - 0)) +#define TSB_FLAGS_COUNT_VALID (1 << (7 - 1)) +#define TSB_FLAGS_CACHE_MISS (1 << (7 - 2)) +#define TSB_FLAGS_TIME_VALID (1 << (7 - 3)) #define TSB_FLAGS_FORMAT(x) ((x) & 7) #define TSB_FORMAT(t) ((t)->flags & 7) @@ -179,9 +179,9 @@ struct tsb { #define DCW_INTRG_RCQ_PRIMARY 1 #define DCW_INTRG_RCQ_SECONDARY 2 -#define DCW_INTRG_FLAGS_MPM 1 < (7 - 0) -#define DCW_INTRG_FLAGS_PPR 1 < (7 - 1) -#define DCW_INTRG_FLAGS_CRIT 1 < (7 - 2) +#define DCW_INTRG_FLAGS_MPM (1 << (7 - 0)) +#define DCW_INTRG_FLAGS_PPR (1 << (7 - 1)) +#define DCW_INTRG_FLAGS_CRIT (1 << (7 - 2)) /** * struct dcw_intrg_data - Interrogate DCW data @@ -216,7 +216,7 @@ struct dcw_intrg_data { u8 prog_data[0]; } __attribute__ ((packed)); -#define DCW_FLAGS_CC 1 << (7 - 1) +#define DCW_FLAGS_CC (1 << (7 - 1)) #define DCW_CMD_WRITE 0x01 #define DCW_CMD_READ 0x02 diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index b7931faaef6..bf246dae136 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -9,11 +9,6 @@ struct dyn_arch_ftrace { }; #define MCOUNT_ADDR ((long)_mcount) -#ifdef CONFIG_64BIT -#define MCOUNT_INSN_SIZE 12 -#else -#define MCOUNT_INSN_SIZE 20 -#endif static inline unsigned long ftrace_call_adjust(unsigned long addr) { @@ -21,4 +16,11 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) } #endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define MCOUNT_INSN_SIZE 12 +#else +#define MCOUNT_INSN_SIZE 22 +#endif + #endif /* _ASM_S390_FTRACE_H */ diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index 96bc83ea5c9..a4811aa0304 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -1,26 +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; + load_kernel_asce(); if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - 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) { @@ -40,10 +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) { - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; + int ret; - return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval); + load_kernel_asce(); + 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/hardirq.h b/arch/s390/include/asm/hardirq.h index 0c82ba86e99..b7eabaaeffb 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -18,6 +18,9 @@ #define __ARCH_HAS_DO_SOFTIRQ #define __ARCH_IRQ_EXIT_IRQS_DISABLED -#define HARDIRQ_BITS 8 +static inline void ack_bad_irq(unsigned int irq) +{ + printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq); +} #endif /* __ASM_HARDIRQ_H */ diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 593753ee07f..11eae5f55b7 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -17,6 +17,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +pte_t huge_ptep_get(pte_t *ptep); +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); /* * If the arch doesn't supply something else, assume that hugepage @@ -38,93 +41,75 @@ static inline int prepare_hugepage_range(struct file *file, int arch_prepare_hugepage(struct page *page); void arch_release_hugepage(struct page *page); -static inline pte_t huge_pte_wrprotect(pte_t pte) +static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - pte_val(pte) |= _PAGE_RO; - return pte; + pte_val(*ptep) = _SEGMENT_ENTRY_EMPTY; } -static inline int huge_pte_none(pte_t pte) +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { - return (pte_val(pte) & _SEGMENT_ENTRY_INV) && - !(pte_val(pte) & _SEGMENT_ENTRY_RO); + huge_ptep_get_and_clear(vma->vm_mm, address, ptep); } -static inline pte_t huge_ptep_get(pte_t *ptep) +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) { - pte_t pte = *ptep; - unsigned long mask; - - if (!MACHINE_HAS_HPAGE) { - ptep = (pte_t *) (pte_val(pte) & _SEGMENT_ENTRY_ORIGIN); - if (ptep) { - mask = pte_val(pte) & - (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO); - pte = pte_mkhuge(*ptep); - pte_val(pte) |= mask; - } + int changed = !pte_same(huge_ptep_get(ptep), pte); + if (changed) { + huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); } - return pte; + return changed; +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep); + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); +} + +static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) +{ + return mk_pte(page, pgprot); } -static inline void __pmd_csp(pmd_t *pmdp) +static inline int huge_pte_none(pte_t pte) { - register unsigned long reg2 asm("2") = pmd_val(*pmdp); - register unsigned long reg3 asm("3") = pmd_val(*pmdp) | - _SEGMENT_ENTRY_INV; - 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"); + return pte_none(pte); } -static inline void huge_ptep_invalidate(struct mm_struct *mm, - unsigned long address, pte_t *ptep) +static inline int huge_pte_write(pte_t pte) { - pmd_t *pmdp = (pmd_t *) ptep; + return pte_write(pte); +} - if (MACHINE_HAS_IDTE) - __pmd_idte(address, pmdp); - else - __pmd_csp(pmdp); - pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY; +static inline int huge_pte_dirty(pte_t pte) +{ + return pte_dirty(pte); } -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_pte_mkwrite(pte_t pte) { - pte_t pte = huge_ptep_get(ptep); + return pte_mkwrite(pte); +} - huge_ptep_invalidate(mm, addr, ptep); - return pte; +static inline pte_t huge_pte_mkdirty(pte_t pte) +{ + return pte_mkdirty(pte); } -#define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \ -({ \ - int __changed = !pte_same(huge_ptep_get(__ptep), __entry); \ - if (__changed) { \ - huge_ptep_invalidate((__vma)->vm_mm, __addr, __ptep); \ - set_huge_pte_at((__vma)->vm_mm, __addr, __ptep, __entry); \ - } \ - __changed; \ -}) - -#define huge_ptep_set_wrprotect(__mm, __addr, __ptep) \ -({ \ - pte_t __pte = huge_ptep_get(__ptep); \ - if (pte_write(__pte)) { \ - huge_ptep_invalidate(__mm, __addr, __ptep); \ - set_huge_pte_at(__mm, __addr, __ptep, \ - huge_pte_wrprotect(__pte)); \ - } \ -}) +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) { - huge_ptep_invalidate(vma->vm_mm, address, ptep); + return pte_modify(pte, newprot); } #endif /* _ASM_S390_HUGETLB_H */ diff --git a/arch/s390/include/asm/hw_irq.h b/arch/s390/include/asm/hw_irq.h index 7e3d2586c1f..ee96a8b697f 100644 --- a/arch/s390/include/asm/hw_irq.h +++ b/arch/s390/include/asm/hw_irq.h @@ -4,19 +4,8 @@ #include <linux/msi.h> #include <linux/pci.h> -static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) -{ - return __irq_get_msi_desc(irq); -} - -/* Must be called with msi map lock held */ -static inline int irq_set_msi_desc(unsigned int irq, struct msi_desc *msi) -{ - if (!msi) - return -EINVAL; - - msi->irq = irq; - return 0; -} +void __init init_airq_interrupts(void); +void __init init_cio_interrupts(void); +void __init init_ext_interrupts(void); #endif diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 27cb32185ce..cd6b9ee7b69 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -13,29 +13,8 @@ #include <asm/page.h> #include <asm/pci_io.h> -/* - * Change virtual addresses to physical addresses and vv. - * These are pretty trivial - */ -static inline unsigned long virt_to_phys(volatile void * address) -{ - unsigned long real_address; - asm volatile( - " lra %0,0(%1)\n" - " jz 0f\n" - " la %0,0\n" - "0:" - : "=a" (real_address) : "a" (address) : "cc"); - return real_address; -} -#define virt_to_phys virt_to_phys - -static inline void * phys_to_virt(unsigned long address) -{ - return (void *) address; -} - void *xlate_dev_mem_ptr(unsigned long phys); +#define xlate_dev_mem_ptr xlate_dev_mem_ptr void unxlate_dev_mem_ptr(unsigned long phys, void *addr); /* @@ -50,10 +29,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr); #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache -/* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { return (void __iomem *) offset; diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 2bd6cb897b9..2fcccc0c997 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -7,6 +7,7 @@ #ifndef _ASM_S390_IPL_H #define _ASM_S390_IPL_H +#include <asm/lowcore.h> #include <asm/types.h> #include <asm/cio.h> #include <asm/setup.h> @@ -86,7 +87,14 @@ struct ipl_parameter_block { */ extern u32 ipl_flags; extern u32 dump_prefix_page; -extern unsigned int zfcpdump_prefix_array[]; + +struct dump_save_areas { + struct save_area **areas; + int count; +}; + +extern struct dump_save_areas dump_save_areas; +struct save_area *dump_save_area_create(int cpu); extern void do_reipl(void); extern void do_halt(void); diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index 7def77302d6..c4dd400a279 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -1,17 +1,42 @@ #ifndef _ASM_IRQ_H #define _ASM_IRQ_H +#define EXT_INTERRUPT 1 +#define IO_INTERRUPT 2 +#define THIN_INTERRUPT 3 + +#define NR_IRQS_BASE 4 + +#ifdef CONFIG_PCI_NR_MSI +# define NR_IRQS (NR_IRQS_BASE + CONFIG_PCI_NR_MSI) +#else +# define NR_IRQS NR_IRQS_BASE +#endif + +/* 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> #include <linux/percpu.h> #include <linux/cache.h> #include <linux/types.h> -enum interruption_main_class { - EXTERNAL_INTERRUPT, - IO_INTERRUPT, - NR_IRQS -}; - enum interruption_class { IRQEXT_CLK, IRQEXT_EXC, @@ -41,6 +66,8 @@ enum interruption_class { IRQIO_CSC, IRQIO_PCI, IRQIO_MSI, + IRQIO_VIR, + IRQIO_VAI, NMI_NMI, CPU_RST, NR_ARCH_IRQS @@ -64,21 +91,19 @@ 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); -void service_subclass_irq_register(void); -void service_subclass_irq_unregister(void); -void measurement_alert_subclass_register(void); -void measurement_alert_subclass_unregister(void); - -#ifdef CONFIG_LOCKDEP -# define disable_irq_nosync_lockdep(irq) disable_irq_nosync(irq) -# define disable_irq_nosync_lockdep_irqsave(irq, flags) \ - disable_irq_nosync(irq) -# define disable_irq_lockdep(irq) disable_irq(irq) -# define enable_irq_lockdep(irq) enable_irq(irq) -# define enable_irq_lockdep_irqrestore(irq, flags) \ - enable_irq(irq) -#endif +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, + IRQ_SUBCLASS_SERVICE_SIGNAL = 9, +}; + +void irq_subclass_register(enum irq_subclass subclass); +void irq_subclass_unregister(enum irq_subclass subclass); + +#define irq_canonicalize(irq) (irq) + +#endif /* __ASSEMBLY__ */ #endif /* _ASM_IRQ_H */ diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 6c32190dc73..346b1c85ffb 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -15,7 +15,7 @@ static __always_inline bool arch_static_branch(struct static_key *key) { - asm goto("0: brcl 0,0\n" + asm_volatile_goto("0: brcl 0,0\n" ".pushsection __jump_table, \"aw\"\n" ASM_ALIGN "\n" ASM_PTR " 0b, %l[label], %0\n" diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index dcf6948a875..4176dfe0fba 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -31,6 +31,8 @@ #include <linux/ptrace.h> #include <linux/percpu.h> +#define __ARCH_WANT_KPROBES_INSN_SLOT + struct pt_regs; struct kprobe; @@ -57,7 +59,7 @@ typedef u16 kprobe_opcode_t; /* Architecture specific copy of original instruction */ struct arch_specific_insn { /* copy of original instruction */ - kprobe_opcode_t insn[MAX_INSN_SIZE]; + kprobe_opcode_t *insn; }; struct prev_kprobe { diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index b7841546991..4181d7baabb 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -16,37 +16,48 @@ #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_MEMORY_SLOTS 32 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 4 +#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 + +#define SIGP_CTRL_C 0x00800000 struct sca_entry { - atomic_t scn; + atomic_t ctrl; __u32 reserved; __u64 sda; __u64 reserved2[2]; } __attribute__((packed)); +union ipte_control { + unsigned long val; + struct { + unsigned long k : 1; + unsigned long kh : 31; + unsigned long kg : 32; + }; +}; struct sca_block { - __u64 ipte_control; + union ipte_control ipte_control; __u64 reserved[5]; __u64 mcn; __u64 reserved2; struct sca_entry cpu[64]; } __attribute__((packed)); -#define KVM_NR_PAGE_SIZES 2 -#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 8) -#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) -#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) -#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) -#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) - #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -63,23 +74,51 @@ struct sca_block { #define CPUSTAT_ZARCH 0x00000800 #define CPUSTAT_MCDS 0x00000100 #define CPUSTAT_SM 0x00000080 +#define CPUSTAT_IBS 0x00000040 #define CPUSTAT_G 0x00000008 +#define CPUSTAT_GED 0x00000004 #define CPUSTAT_J 0x00000002 #define CPUSTAT_P 0x00000001 struct kvm_s390_sie_block { atomic_t cpuflags; /* 0x0000 */ - __u32 prefix; /* 0x0004 */ - __u8 reserved8[32]; /* 0x0008 */ + __u32 : 1; /* 0x0004 */ + __u32 prefix : 18; + __u32 : 13; + __u8 reserved08[4]; /* 0x0008 */ +#define PROG_IN_SIE (1<<0) + __u32 prog0c; /* 0x000c */ + __u8 reserved10[16]; /* 0x0010 */ +#define PROG_BLOCK_SIE 0x00000001 + atomic_t prog20; /* 0x0020 */ + __u8 reserved24[4]; /* 0x0024 */ __u64 cputm; /* 0x0028 */ __u64 ckc; /* 0x0030 */ __u64 epoch; /* 0x0038 */ __u8 reserved40[4]; /* 0x0040 */ #define LCTL_CR0 0x8000 +#define LCTL_CR6 0x0200 +#define LCTL_CR9 0x0040 +#define LCTL_CR10 0x0020 +#define LCTL_CR11 0x0010 +#define LCTL_CR14 0x0002 __u16 lctl; /* 0x0044 */ __s16 icpua; /* 0x0046 */ +#define ICTL_PINT 0x20000000 +#define ICTL_LPSW 0x00400000 +#define ICTL_STCTL 0x00040000 +#define ICTL_ISKE 0x00004000 +#define ICTL_SSKE 0x00002000 +#define ICTL_RRBE 0x00001000 +#define ICTL_TPROT 0x00000200 __u32 ictl; /* 0x0048 */ __u32 eca; /* 0x004c */ +#define ICPT_INST 0x04 +#define ICPT_PROGI 0x08 +#define ICPT_INSTPROGI 0x0C +#define ICPT_OPEREXC 0x2C +#define ICPT_PARTEXEC 0x38 +#define ICPT_IOINST 0x40 __u8 icptcode; /* 0x0050 */ __u8 reserved51; /* 0x0051 */ __u16 ihcpu; /* 0x0052 */ @@ -89,7 +128,8 @@ struct kvm_s390_sie_block { __u32 scaoh; /* 0x005c */ __u8 reserved60; /* 0x0060 */ __u8 ecb; /* 0x0061 */ - __u8 reserved62[2]; /* 0x0062 */ + __u8 ecb2; /* 0x0062 */ + __u8 reserved63[1]; /* 0x0063 */ __u32 scaol; /* 0x0064 */ __u8 reserved68[4]; /* 0x0068 */ __u32 todpr; /* 0x006c */ @@ -97,16 +137,48 @@ struct kvm_s390_sie_block { psw_t gpsw; /* 0x0090 */ __u64 gg14; /* 0x00a0 */ __u64 gg15; /* 0x00a8 */ - __u8 reservedb0[30]; /* 0x00b0 */ - __u16 iprcc; /* 0x00ce */ - __u8 reservedd0[48]; /* 0x00d0 */ + __u8 reservedb0[20]; /* 0x00b0 */ + __u16 extcpuaddr; /* 0x00c4 */ + __u16 eic; /* 0x00c6 */ + __u32 reservedc8; /* 0x00c8 */ + __u16 pgmilc; /* 0x00cc */ + __u16 iprcc; /* 0x00ce */ + __u32 dxc; /* 0x00d0 */ + __u16 mcn; /* 0x00d4 */ + __u8 perc; /* 0x00d6 */ + __u8 peratmid; /* 0x00d7 */ + __u64 peraddr; /* 0x00d8 */ + __u8 eai; /* 0x00e0 */ + __u8 peraid; /* 0x00e1 */ + __u8 oai; /* 0x00e2 */ + __u8 armid; /* 0x00e3 */ + __u8 reservede4[4]; /* 0x00e4 */ + __u64 tecmc; /* 0x00e8 */ + __u8 reservedf0[16]; /* 0x00f0 */ __u64 gcr[16]; /* 0x0100 */ __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; @@ -117,6 +189,8 @@ struct kvm_vcpu_stat { u32 exit_instruction; u32 instruction_lctl; u32 instruction_lctlg; + u32 instruction_stctl; + u32 instruction_stctg; u32 exit_program_interruption; u32 exit_instr_and_program; u32 deliver_external_call; @@ -127,17 +201,21 @@ struct kvm_vcpu_stat { u32 deliver_prefix_signal; u32 deliver_restart_signal; u32 deliver_program_int; + u32 deliver_io_int; u32 exit_wait_state; + u32 instruction_pfmf; u32 instruction_stidp; u32 instruction_spx; u32 instruction_stpx; u32 instruction_stap; u32 instruction_storage_key; + u32 instruction_ipte_interlock; u32 instruction_stsch; u32 instruction_chsc; 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; @@ -151,41 +229,58 @@ 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_OPERATION 0x02 -#define PGM_EXECUTE 0x03 -#define PGM_PROTECTION 0x04 -#define PGM_ADDRESSING 0x05 -#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; -}; +#define PGM_OPERATION 0x01 +#define PGM_PRIVILEGED_OP 0x02 +#define PGM_EXECUTE 0x03 +#define PGM_PROTECTION 0x04 +#define PGM_ADDRESSING 0x05 +#define PGM_SPECIFICATION 0x06 +#define PGM_DATA 0x07 +#define PGM_FIXED_POINT_OVERFLOW 0x08 +#define PGM_FIXED_POINT_DIVIDE 0x09 +#define PGM_DECIMAL_OVERFLOW 0x0a +#define PGM_DECIMAL_DIVIDE 0x0b +#define PGM_HFP_EXPONENT_OVERFLOW 0x0c +#define PGM_HFP_EXPONENT_UNDERFLOW 0x0d +#define PGM_HFP_SIGNIFICANCE 0x0e +#define PGM_HFP_DIVIDE 0x0f +#define PGM_SEGMENT_TRANSLATION 0x10 +#define PGM_PAGE_TRANSLATION 0x11 +#define PGM_TRANSLATION_SPEC 0x12 +#define PGM_SPECIAL_OPERATION 0x13 +#define PGM_OPERAND 0x15 +#define PGM_TRACE_TABEL 0x16 +#define PGM_SPACE_SWITCH 0x1c +#define PGM_HFP_SQUARE_ROOT 0x1d +#define PGM_PC_TRANSLATION_SPEC 0x1f +#define PGM_AFX_TRANSLATION 0x20 +#define PGM_ASX_TRANSLATION 0x21 +#define PGM_LX_TRANSLATION 0x22 +#define PGM_EX_TRANSLATION 0x23 +#define PGM_PRIMARY_AUTHORITY 0x24 +#define PGM_SECONDARY_AUTHORITY 0x25 +#define PGM_LFX_TRANSLATION 0x26 +#define PGM_LSX_TRANSLATION 0x27 +#define PGM_ALET_SPECIFICATION 0x28 +#define PGM_ALEN_TRANSLATION 0x29 +#define PGM_ALE_SEQUENCE 0x2a +#define PGM_ASTE_VALIDITY 0x2b +#define PGM_ASTE_SEQUENCE 0x2c +#define PGM_EXTENDED_AUTHORITY 0x2d +#define PGM_LSTE_SEQUENCE 0x2e +#define PGM_ASTE_INSTANCE 0x2f +#define PGM_STACK_FULL 0x30 +#define PGM_STACK_EMPTY 0x31 +#define PGM_STACK_SPECIFICATION 0x32 +#define PGM_STACK_TYPE 0x33 +#define PGM_STACK_OPERATION 0x34 +#define PGM_ASCE_TYPE 0x38 +#define PGM_REGION_FIRST_TRANS 0x39 +#define PGM_REGION_SECOND_TRANS 0x3a +#define PGM_REGION_THIRD_TRANS 0x3b +#define PGM_MONITOR 0x40 +#define PGM_PER 0x80 +#define PGM_CRYPTO_OPERATION 0x119 struct kvm_s390_interrupt_info { struct list_head list; @@ -197,13 +292,13 @@ struct kvm_s390_interrupt_info { struct kvm_s390_emerg_info emerg; struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; + struct kvm_s390_mchk_info mchk; }; }; /* for local_interrupt.action_flags */ #define ACTION_STORE_ON_STOP (1<<0) #define ACTION_STOP_ON_STOP (1<<1) -#define ACTION_RELOADVCPU_ON_STOP (1<<2) struct kvm_s390_local_interrupt { spinlock_t lock; @@ -211,7 +306,7 @@ struct kvm_s390_local_interrupt { atomic_t active; struct kvm_s390_float_interrupt *float_int; int timer_due; /* event indicator for waitqueue below */ - wait_queue_head_t wq; + wait_queue_head_t *wq; atomic_t *cpuflags; unsigned int action_bits; }; @@ -221,11 +316,49 @@ 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; +}; + +struct kvm_hw_wp_info_arch { + unsigned long addr; + unsigned long phys_addr; + int len; + char *old_data; +}; + +struct kvm_hw_bp_info_arch { + unsigned long addr; + int len; }; +/* + * Only the upper 16 bits of kvm_guest_debug->control are arch specific. + * Further KVM_GUESTDBG flags which an be used from userspace can be found in + * arch/s390/include/uapi/asm/kvm.h + */ +#define KVM_GUESTDBG_EXIT_PENDING 0x10000000 + +#define guestdbg_enabled(vcpu) \ + (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) +#define guestdbg_sstep_enabled(vcpu) \ + (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) +#define guestdbg_hw_bp_enabled(vcpu) \ + (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) +#define guestdbg_exit_pending(vcpu) (guestdbg_enabled(vcpu) && \ + (vcpu->guest_debug & KVM_GUESTDBG_EXIT_PENDING)) + +struct kvm_guestdbg_info_arch { + unsigned long cr0; + unsigned long cr9; + unsigned long cr10; + unsigned long cr11; + struct kvm_hw_bp_info_arch *hw_bp_info; + struct kvm_hw_wp_info_arch *hw_wp_info; + int nr_hw_bp; + int nr_hw_wp; + unsigned long last_bp; +}; struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; @@ -235,11 +368,17 @@ struct kvm_vcpu_arch { struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct tasklet_struct tasklet; + struct kvm_s390_pgm_info pgm; union { struct cpuid cpu_id; u64 stidp_data; }; struct gmap *gmap; + struct kvm_guestdbg_info_arch guestdbg; +#define KVM_S390_PFAULT_TOKEN_INVALID (-1UL) + unsigned long pfault_token; + unsigned long pfault_select; + unsigned long pfault_compare; }; struct kvm_vm_stat { @@ -249,12 +388,67 @@ 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; + int use_cmma; + struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS]; + wait_queue_head_t ipte_wq; + spinlock_t start_stop_lock; }; +#define KVM_HVA_ERR_BAD (-1UL) +#define KVM_HVA_ERR_RO_BAD (-2UL) + +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/lowcore.h b/arch/s390/include/asm/lowcore.h index bbf8141408c..4349197ab9d 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -56,13 +56,14 @@ struct _lowcore { __u16 pgm_code; /* 0x008e */ __u32 trans_exc_code; /* 0x0090 */ __u16 mon_class_num; /* 0x0094 */ - __u16 per_perc_atmid; /* 0x0096 */ + __u8 per_code; /* 0x0096 */ + __u8 per_atmid; /* 0x0097 */ __u32 per_address; /* 0x0098 */ __u32 monitor_code; /* 0x009c */ __u8 exc_access_id; /* 0x00a0 */ __u8 per_access_id; /* 0x00a1 */ __u8 op_access_id; /* 0x00a2 */ - __u8 ar_access_id; /* 0x00a3 */ + __u8 ar_mode_id; /* 0x00a3 */ __u8 pad_0x00a4[0x00b8-0x00a4]; /* 0x00a4 */ __u16 subchannel_id; /* 0x00b8 */ __u16 subchannel_nr; /* 0x00ba */ @@ -93,7 +94,9 @@ struct _lowcore { __u32 save_area_sync[8]; /* 0x0200 */ __u32 save_area_async[8]; /* 0x0220 */ __u32 save_area_restart[1]; /* 0x0240 */ - __u8 pad_0x0244[0x0248-0x0244]; /* 0x0244 */ + + /* CPU flags. */ + __u32 cpu_flags; /* 0x0244 */ /* Return psws. */ psw_t return_psw; /* 0x0248 */ @@ -139,12 +142,9 @@ struct _lowcore { __u32 percpu_offset; /* 0x02f0 */ __u32 machine_flags; /* 0x02f4 */ __u32 ftrace_func; /* 0x02f8 */ - __u8 pad_0x02fc[0x0300-0x02fc]; /* 0x02fc */ - - /* Interrupt response block */ - __u8 irb[64]; /* 0x0300 */ + __u32 spinlock_lockval; /* 0x02fc */ - __u8 pad_0x0340[0x0e00-0x0340]; /* 0x0340 */ + __u8 pad_0x0300[0x0e00-0x0300]; /* 0x0300 */ /* * 0xe00 contains the address of the IPL Parameter Information @@ -196,12 +196,13 @@ struct _lowcore { __u16 pgm_code; /* 0x008e */ __u32 data_exc_code; /* 0x0090 */ __u16 mon_class_num; /* 0x0094 */ - __u16 per_perc_atmid; /* 0x0096 */ + __u8 per_code; /* 0x0096 */ + __u8 per_atmid; /* 0x0097 */ __u64 per_address; /* 0x0098 */ __u8 exc_access_id; /* 0x00a0 */ __u8 per_access_id; /* 0x00a1 */ __u8 op_access_id; /* 0x00a2 */ - __u8 ar_access_id; /* 0x00a3 */ + __u8 ar_mode_id; /* 0x00a3 */ __u8 pad_0x00a4[0x00a8-0x00a4]; /* 0x00a4 */ __u64 trans_exc_code; /* 0x00a8 */ __u64 monitor_code; /* 0x00b0 */ @@ -237,7 +238,9 @@ struct _lowcore { __u64 save_area_sync[8]; /* 0x0200 */ __u64 save_area_async[8]; /* 0x0240 */ __u64 save_area_restart[1]; /* 0x0280 */ - __u8 pad_0x0288[0x0290-0x0288]; /* 0x0288 */ + + /* CPU flags. */ + __u64 cpu_flags; /* 0x0288 */ /* Return psws. */ psw_t return_psw; /* 0x0290 */ @@ -285,15 +288,13 @@ struct _lowcore { __u64 machine_flags; /* 0x0388 */ __u64 ftrace_func; /* 0x0390 */ __u64 gmap; /* 0x0398 */ - __u8 pad_0x03a0[0x0400-0x03a0]; /* 0x03a0 */ - - /* Interrupt response block. */ - __u8 irb[64]; /* 0x0400 */ + __u32 spinlock_lockval; /* 0x03a0 */ + __u8 pad_0x03a0[0x0400-0x03a4]; /* 0x03a4 */ /* Per cpu primary space access list */ - __u32 paste[16]; /* 0x0440 */ + __u32 paste[16]; /* 0x0400 */ - __u8 pad_0x0480[0x0e00-0x0480]; /* 0x0480 */ + __u8 pad_0x04c0[0x0e00-0x0440]; /* 0x0440 */ /* * 0xe00 contains the address of the IPL Parameter Information diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h index 0e47a576d66..9977e08df5b 100644 --- a/arch/s390/include/asm/mman.h +++ b/arch/s390/include/asm/mman.h @@ -9,7 +9,7 @@ #include <uapi/asm/mman.h> #if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT) -int s390_mmap_check(unsigned long addr, unsigned long len); -#define arch_mmap_check(addr,len,flags) s390_mmap_check(addr,len) +int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags); +#define arch_mmap_check(addr, len, flags) s390_mmap_check(addr, len, flags) #endif #endif /* __S390_MMAN_H__ */ diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 6340178748b..a5e656260a7 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; @@ -12,10 +14,10 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; - /* Cloned contexts will be created with extended page tables. */ - unsigned int alloc_pgste:1; /* The mmu context has extended page tables. */ unsigned int has_pgste:1; + /* The mmu context uses storage keys. */ + unsigned int use_skey:1; } mm_context_t; #define INIT_MM_CONTEXT(name) \ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 084e7755ed9..3815bfea1b2 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,30 +15,15 @@ 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; #ifdef CONFIG_64BIT mm->context.asce_bits |= _ASCE_TYPE_REGION3; #endif - if (current->mm && current->mm->context.alloc_pgste) { - /* - * alloc_pgste indicates, that any NEW context will be created - * with extended page tables. The old context is unchanged. The - * page table allocation and the page table operations will - * look at has_pgste to distinguish normal and extended page - * tables. The only way to create extended page tables is to - * set alloc_pgste and then create a new context (e.g. dup_mm). - * The page table allocation is called after init_new_context - * and if has_pgste is set, it will create extended page - * tables. - */ - mm->context.has_pgste = 1; - mm->context.alloc_pgste = 1; - } else { - mm->context.has_pgste = 0; - mm->context.alloc_pgste = 0; - } + mm->context.has_pgste = 0; + mm->context.use_skey = 0; mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; @@ -46,39 +31,69 @@ 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 set_user_asce(struct mm_struct *mm) +{ + S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd); + if (current->thread.mm_segment.ar4) + __ctl_load(S390_lowcore.user_asce, 7, 7); + set_cpu_flag(CIF_ASCE); +} -static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk) +static inline void clear_user_asce(void) { - pgd_t *pgd = mm->pgd; - - S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd); - if (s390_user_mode != HOME_SPACE_MODE) { - /* Load primary space page table origin. */ - asm volatile(LCTL_OPCODE" 1,1,%0\n" - : : "m" (S390_lowcore.user_asce) ); - } else - /* Load home space page table origin. */ - asm volatile(LCTL_OPCODE" 13,13,%0" - : : "m" (S390_lowcore.user_asce) ); - set_fs(current->thread.mm_segment); + S390_lowcore.user_asce = S390_lowcore.kernel_asce; + + __ctl_load(S390_lowcore.user_asce, 1, 1); + __ctl_load(S390_lowcore.user_asce, 7, 7); +} + +static inline void load_kernel_asce(void) +{ + unsigned long asce; + + __ctl_store(asce, 1, 1); + if (asce != S390_lowcore.kernel_asce) + __ctl_load(S390_lowcore.kernel_asce, 1, 1); + set_cpu_flag(CIF_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); - atomic_dec(&prev->context.attach_count); - WARN_ON(atomic_read(&prev->context.attach_count) < 0); + int cpu = smp_processor_id(); + + if (prev == next) + return; + if (MACHINE_HAS_TLB_LC) + cpumask_set_cpu(cpu, &next->context.cpu_attach_mask); + /* Clear old ASCE by loading the kernel ASCE. */ + __ctl_load(S390_lowcore.kernel_asce, 1, 1); + __ctl_load(S390_lowcore.kernel_asce, 7, 7); atomic_inc(&next->context.attach_count); - /* Check for TLBs not flushed yet */ - if (next->context.flush_mm) - __tlb_flush_mm(next); + atomic_dec(&prev->context.attach_count); + if (MACHINE_HAS_TLB_LC) + cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask); + S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); +} + +#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; + + load_kernel_asce(); + if (mm) { + preempt_disable(); + while (atomic_read(&mm->context.attach_count) >> 16) + cpu_relax(); + + cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); + if (mm->context.flush_mm) + __tlb_flush_mm(mm); + preempt_enable(); + } + set_fs(current->thread.mm_segment); } #define enter_lazy_tlb(mm,tsk) do { } while (0) @@ -87,7 +102,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - switch_mm(prev, next, current); + switch_mm(prev, next, current); + cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); + set_user_asce(next); } static inline void arch_dup_mmap(struct mm_struct *oldmm, diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h index 688271f5f2e..458c1f7fbc1 100644 --- a/arch/s390/include/asm/mutex.h +++ b/arch/s390/include/asm/mutex.h @@ -7,5 +7,3 @@ */ #include <asm-generic/mutex-dec.h> - -#define arch_mutex_cpu_relax() barrier() diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index a86ad408407..114258eeaac 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -30,60 +30,39 @@ #include <asm/setup.h> #ifndef __ASSEMBLY__ -void storage_key_init_range(unsigned long start, unsigned long end); - -static unsigned long pfmf(unsigned long function, unsigned long address) +static inline void storage_key_init_range(unsigned long start, unsigned long end) { - asm volatile( - " .insn rre,0xb9af0000,%[function],%[address]" - : [address] "+a" (address) - : [function] "d" (function) - : "memory"); - return address; +#if PAGE_DEFAULT_KEY + __storage_key_init_range(start, end); +#endif } static inline void clear_page(void *page) { - if (MACHINE_HAS_PFMF) { - pfmf(0x10000, (unsigned long)page); - } else { - register unsigned long reg1 asm ("1") = 0; - register void *reg2 asm ("2") = page; - register unsigned long reg3 asm ("3") = 4096; - asm volatile( - " mvcl 2,0" - : "+d" (reg2), "+d" (reg3) : "d" (reg1) - : "memory", "cc"); - } + register unsigned long reg1 asm ("1") = 0; + register void *reg2 asm ("2") = page; + register unsigned long reg3 asm ("3") = 4096; + asm volatile( + " mvcl 2,0" + : "+d" (reg2), "+d" (reg3) : "d" (reg1) + : "memory", "cc"); } +/* + * copy_page uses the mvcl instruction with 0xb0 padding byte in order to + * bypass caches when copying a page. Especially when copying huge pages + * this keeps L1 and L2 data caches alive. + */ static inline void copy_page(void *to, void *from) { - if (MACHINE_HAS_MVPG) { - register unsigned long reg0 asm ("0") = 0; - asm volatile( - " mvpg %0,%1" - : : "a" (to), "a" (from), "d" (reg0) - : "memory", "cc"); - } else - asm volatile( - " mvc 0(256,%0),0(%1)\n" - " mvc 256(256,%0),256(%1)\n" - " mvc 512(256,%0),512(%1)\n" - " mvc 768(256,%0),768(%1)\n" - " mvc 1024(256,%0),1024(%1)\n" - " mvc 1280(256,%0),1280(%1)\n" - " mvc 1536(256,%0),1536(%1)\n" - " mvc 1792(256,%0),1792(%1)\n" - " mvc 2048(256,%0),2048(%1)\n" - " mvc 2304(256,%0),2304(%1)\n" - " mvc 2560(256,%0),2560(%1)\n" - " mvc 2816(256,%0),2816(%1)\n" - " mvc 3072(256,%0),3072(%1)\n" - " mvc 3328(256,%0),3328(%1)\n" - " mvc 3584(256,%0),3584(%1)\n" - " mvc 3840(256,%0),3840(%1)\n" - : : "a" (to), "a" (from) : "memory"); + register void *reg2 asm ("2") = to; + register unsigned long reg3 asm ("3") = 0x1000; + register void *reg4 asm ("4") = from; + register unsigned long reg5 asm ("5") = 0xb0001000; + asm volatile( + " mvcl 2,4" + : "+d" (reg2), "+d" (reg3), "+d" (reg4), "+d" (reg5) + : : "memory", "cc"); } #define clear_user_page(page, vaddr, pg) clear_page(page) @@ -154,37 +133,6 @@ static inline int page_reset_referenced(unsigned long addr) #define _PAGE_FP_BIT 0x08 /* HW fetch protection bit */ #define _PAGE_ACC_BITS 0xf0 /* HW access control bits */ -/* - * Test and clear dirty bit in storage key. - * We can't clear the changed bit atomically. This is a potential - * race against modification of the referenced bit. This function - * should therefore only be called if it is not mapped in any - * address space. - * - * Note that the bit gets set whenever page content is changed. That means - * also when the page is modified by DMA or from inside the kernel. - */ -#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY -static inline int page_test_and_clear_dirty(unsigned long pfn, int mapped) -{ - unsigned char skey; - - skey = page_get_storage_key(pfn << PAGE_SHIFT); - if (!(skey & _PAGE_CHANGED)) - return 0; - page_set_storage_key(pfn << PAGE_SHIFT, skey & ~_PAGE_CHANGED, mapped); - return 1; -} - -/* - * Test and clear referenced bit in storage key. - */ -#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG -static inline int page_test_and_clear_young(unsigned long pfn) -{ - return page_reset_referenced(pfn << PAGE_SHIFT); -} - struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index b1fa93c606a..c030900320e 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -6,6 +6,7 @@ /* must be set before including pci_clp.h */ #define PCI_BAR_COUNT 6 +#include <linux/pci.h> #include <asm-generic/pci.h> #include <asm-generic/pci-dma-compat.h> #include <asm/pci_clp.h> @@ -21,10 +22,6 @@ void pci_iounmap(struct pci_dev *, void __iomem *); int pci_domain_nr(struct pci_bus *); int pci_proc_domain(struct pci_bus *); -/* MSI arch hooks */ -#define arch_setup_msi_irqs arch_setup_msi_irqs -#define arch_teardown_msi_irqs arch_teardown_msi_irqs - #define ZPCI_BUS_NR 0 /* default bus number */ #define ZPCI_DEVFN 0 /* default device number */ @@ -53,14 +50,9 @@ struct zpci_fmb { atomic64_t unmapped_pages; } __packed __aligned(16); -struct msi_map { - unsigned long irq; - struct msi_desc *msi; - struct hlist_node msi_chain; -}; - -#define ZPCI_NR_MSI_VECS 64 -#define ZPCI_MSI_MASK (ZPCI_NR_MSI_VECS - 1) +#define ZPCI_MSI_VEC_BITS 11 +#define ZPCI_MSI_VEC_MAX (1 << ZPCI_MSI_VEC_BITS) +#define ZPCI_MSI_VEC_MASK (ZPCI_MSI_VEC_MAX - 1) enum zpci_state { ZPCI_FN_STATE_RESERVED, @@ -71,9 +63,10 @@ enum zpci_state { }; struct zpci_bar_struct { + struct resource *res; /* bus resource */ u32 val; /* bar start & 3 flag bits */ - u8 size; /* order 2 exponent */ u16 map_idx; /* index into bar mapping array */ + u8 size; /* order 2 exponent */ }; /* Private data per function */ @@ -85,14 +78,19 @@ struct zpci_dev { enum zpci_state state; u32 fid; /* function ID, used by sclp */ u32 fh; /* function handle, used by insn's */ + u16 vfn; /* virtual function number */ u16 pchid; /* physical channel ID */ u8 pfgid; /* function group ID */ + u8 pft; /* pci function type */ u16 domain; + u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ + u32 uid; /* user defined id */ + u8 util_str[CLP_UTIL_STR_LEN]; /* utility string */ + /* IRQ stuff */ u64 msi_addr; /* MSI address */ - struct zdev_irq_map *irq_map; - struct msi_map *msi_map[ZPCI_NR_MSI_VECS]; + struct airq_iv *aibv; /* adapter interrupt bit vector */ unsigned int aisb; /* number of the summary bit */ /* DMA stuff */ @@ -106,6 +104,7 @@ struct zpci_dev { unsigned long iommu_pages; unsigned int next_bit; + char res_name[16]; struct zpci_bar_struct bars[PCI_BAR_COUNT]; u64 start_dma; /* Start of available DMA addresses */ @@ -120,12 +119,6 @@ struct zpci_dev { struct dentry *debugfs_dev; struct dentry *debugfs_perf; - struct dentry *debugfs_debug; -}; - -struct pci_hp_callback_ops { - int (*create_slot) (struct zpci_dev *zdev); - void (*remove_slot) (struct zpci_dev *zdev); }; static inline bool zdev_enabled(struct zpci_dev *zdev) @@ -133,56 +126,58 @@ static inline bool zdev_enabled(struct zpci_dev *zdev) return (zdev->fh & (1UL << 31)) ? true : false; } +extern const struct attribute_group *zpci_attr_groups[]; + /* ----------------------------------------------------------------------------- Prototypes ----------------------------------------------------------------------------- */ /* Base stuff */ -struct zpci_dev *zpci_alloc_device(void); int zpci_create_device(struct zpci_dev *); int zpci_enable_device(struct zpci_dev *); +int zpci_disable_device(struct zpci_dev *); void zpci_stop_device(struct zpci_dev *); -void zpci_free_device(struct zpci_dev *); -int zpci_scan_device(struct zpci_dev *); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); /* CLP */ -int clp_find_pci_devices(void); +int clp_scan_pci_devices(void); +int clp_rescan_pci_devices(void); +int clp_rescan_pci_devices_simple(void); int clp_add_pci_device(u32, u32, int); int clp_enable_fh(struct zpci_dev *, u8); int clp_disable_fh(struct zpci_dev *); -/* MSI */ -struct msi_desc *__irq_get_msi_desc(unsigned int); -int zpci_msi_set_mask_bits(struct msi_desc *, u32, u32); -int zpci_setup_msi_irq(struct zpci_dev *, struct msi_desc *, unsigned int, int); -void zpci_teardown_msi_irq(struct zpci_dev *, struct msi_desc *); -int zpci_msihash_init(void); -void zpci_msihash_exit(void); - +#ifdef CONFIG_PCI /* Error handling and recovery */ 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) {} +static inline void zpci_rescan(void) {} +#endif /* CONFIG_PCI */ + +#ifdef CONFIG_HOTPLUG_PCI_S390 +int zpci_init_slot(struct zpci_dev *); +void zpci_exit_slot(struct zpci_dev *); +#else /* CONFIG_HOTPLUG_PCI_S390 */ +static inline int zpci_init_slot(struct zpci_dev *zdev) +{ + return 0; +} +static inline void zpci_exit_slot(struct zpci_dev *zdev) {} +#endif /* CONFIG_HOTPLUG_PCI_S390 */ /* Helpers */ struct zpci_dev *get_zdev(struct pci_dev *); struct zpci_dev *get_zdev_by_fid(u32); -bool zpci_fid_present(u32); - -/* sysfs */ -int zpci_sysfs_add_device(struct device *); -void zpci_sysfs_remove_device(struct device *); /* DMA */ int zpci_dma_init(void); void zpci_dma_exit(void); -/* Hotplug */ -extern struct mutex zpci_list_lock; -extern struct list_head zpci_list; -extern struct pci_hp_callback_ops hotplug_ops; -extern unsigned int pci_probe; - /* FMB */ int zpci_fmb_enable_device(struct zpci_dev *); int zpci_fmb_disable_device(struct zpci_dev *); diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index d31d739f868..dd78f92f1cc 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -44,6 +44,7 @@ struct clp_fh_list_entry { #define CLP_SET_DISABLE_PCI_FN 1 /* Yes, 1 disables it */ #define CLP_UTIL_STR_LEN 64 +#define CLP_PFIP_NR_SEGMENTS 4 /* List PCI functions request */ struct clp_req_list_pci { @@ -85,7 +86,7 @@ struct clp_rsp_query_pci { struct clp_rsp_hdr hdr; u32 fmt : 4; /* cmd request block format */ u32 : 28; - u64 reserved1; + u64 : 64; u16 vfn; /* virtual fn number */ u16 : 7; u16 util_str_avail : 1; /* utility string available? */ @@ -94,10 +95,13 @@ struct clp_rsp_query_pci { u8 bar_size[PCI_BAR_COUNT]; u16 pchid; u32 bar[PCI_BAR_COUNT]; - u64 reserved2; + u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ + u32 : 24; + u8 pft; /* pci function type */ u64 sdma; /* start dma as */ u64 edma; /* end dma as */ - u64 reserved3[6]; + u32 reserved[11]; + u32 uid; /* user defined id */ u8 util_str[CLP_UTIL_STR_LEN]; /* utility string */ } __packed; diff --git a/arch/s390/include/asm/pci_debug.h b/arch/s390/include/asm/pci_debug.h index 6bbec4265b6..ac24b26fc06 100644 --- a/arch/s390/include/asm/pci_debug.h +++ b/arch/s390/include/asm/pci_debug.h @@ -6,16 +6,8 @@ extern debug_info_t *pci_debug_msg_id; extern debug_info_t *pci_debug_err_id; -#ifdef CONFIG_PCI_DEBUG -#define zpci_dbg(fmt, args...) \ - do { \ - if (pci_debug_msg_id->level >= 2) \ - debug_sprintf_event(pci_debug_msg_id, 2, fmt , ## args);\ - } while (0) - -#else /* !CONFIG_PCI_DEBUG */ -#define zpci_dbg(fmt, args...) do { } while (0) -#endif +#define zpci_dbg(imp, fmt, args...) \ + debug_sprintf_event(pci_debug_msg_id, imp, fmt, ##args) #define zpci_err(text...) \ do { \ diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index 1486a98d5da..649eb62c52b 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -1,10 +1,6 @@ #ifndef _ASM_S390_PCI_INSN_H #define _ASM_S390_PCI_INSN_H -#include <linux/delay.h> - -#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ - /* Load/Store status codes */ #define ZPCI_PCI_ST_FUNC_NOT_ENABLED 4 #define ZPCI_PCI_ST_FUNC_IN_ERR 8 @@ -58,11 +54,9 @@ struct zpci_fib { u32 fmt : 8; /* format */ u32 : 24; - u32 reserved1; + u32 : 32; u8 fc; /* function controls */ - u8 reserved2; - u16 reserved3; - u32 reserved4; + u64 : 56; u64 pba; /* PCI base address */ u64 pal; /* PCI address limit */ u64 iota; /* I/O Translation Anchor */ @@ -74,207 +68,19 @@ struct zpci_fib { u32 sum : 1; /* Adapter int summary bit enabled */ u32 : 1; u32 aisbo : 6; /* Adapter int summary bit offset */ - u32 reserved5; + u32 : 32; u64 aibv; /* Adapter int bit vector address */ u64 aisb; /* Adapter int summary bit address */ u64 fmb_addr; /* Function measurement block address and key */ - u64 reserved6; - u64 reserved7; -} __packed; - -/* Modify PCI Function Controls */ -static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) -{ - u8 cc; - - asm volatile ( - " .insn rxy,0xe300000000d0,%[req],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) - : : "cc"); - *status = req >> 24 & 0xff; - return cc; -} - -static inline int mpcifc_instr(u64 req, struct zpci_fib *fib) -{ - u8 cc, status; - - do { - cc = __mpcifc(req, fib, &status); - if (cc == 2) - msleep(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d\n", - __func__, cc, status); - return (cc) ? -EIO : 0; -} - -/* Refresh PCI Translations */ -static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) -{ - register u64 __addr asm("2") = addr; - register u64 __range asm("3") = range; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d30000,%[fn],%[addr]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn) - : [addr] "d" (__addr), "d" (__range) - : "cc"); - *status = fn >> 24 & 0xff; - return cc; -} - -static inline int rpcit_instr(u64 fn, u64 addr, u64 range) -{ - u8 cc, status; - - do { - cc = __rpcit(fn, addr, range, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d dma_addr: %Lx size: %Lx\n", - __func__, cc, status, addr, range); - return (cc) ? -EIO : 0; -} - -/* Store PCI function controls */ -static inline u8 __stpcifc(u32 handle, u8 space, struct zpci_fib *fib, u8 *status) -{ - u64 fn = (u64) handle << 32 | space << 16; - u8 cc; - - asm volatile ( - " .insn rxy,0xe300000000d4,%[fn],%[fib]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [fn] "+d" (fn), [fib] "=m" (*fib) - : : "cc"); - *status = fn >> 24 & 0xff; - return cc; -} - -/* Set Interruption Controls */ -static inline void sic_instr(u16 ctl, char *unused, u8 isc) -{ - asm volatile ( - " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" - : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); -} - -/* PCI Load */ -static inline u8 __pcilg(u64 *data, u64 req, u64 offset, u8 *status) -{ - register u64 __req asm("2") = req; - register u64 __offset asm("3") = offset; - u64 __data; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d20000,%[data],%[req]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [data] "=d" (__data), [req] "+d" (__req) - : "d" (__offset) - : "cc"); - *status = __req >> 24 & 0xff; - *data = __data; - return cc; -} - -static inline int pcilg_instr(u64 *data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcilg(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) { - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - /* TODO: on IO errors set data to 0xff... - * here or in users of pcilg (le conversion)? - */ - } - return (cc) ? -EIO : 0; -} - -/* PCI Store */ -static inline u8 __pcistg(u64 data, u64 req, u64 offset, u8 *status) -{ - register u64 __req asm("2") = req; - register u64 __offset asm("3") = offset; - u8 cc; - - asm volatile ( - " .insn rre,0xb9d00000,%[data],%[req]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (__req) - : "d" (__offset), [data] "d" (data) - : "cc"); - *status = __req >> 24 & 0xff; - return cc; -} - -static inline int pcistg_instr(u64 data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcistg(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - return (cc) ? -EIO : 0; -} - -/* PCI Store Block */ -static inline u8 __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) -{ - u8 cc; - - asm volatile ( - " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" - " ipm %[cc]\n" - " srl %[cc],28\n" - : [cc] "=d" (cc), [req] "+d" (req) - : [offset] "d" (offset), [data] "Q" (*data) - : "cc"); - *status = req >> 24 & 0xff; - return cc; -} - -static inline int pcistb_instr(const u64 *data, u64 req, u64 offset) -{ - u8 cc, status; - - do { - cc = __pcistb(data, req, offset, &status); - if (cc == 2) - udelay(ZPCI_INSN_BUSY_DELAY); - } while (cc == 2); - - if (cc) - printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", - __func__, cc, status, req, offset); - return (cc) ? -EIO : 0; -} + u32 : 32; + u32 gd; +} __packed __aligned(8); + +int zpci_mod_fc(u64 req, struct zpci_fib *fib); +int zpci_refresh_trans(u64 fn, u64 addr, u64 range); +int zpci_load(u64 *data, u64 req, u64 offset); +int zpci_store(u64 data, u64 req, u64 offset); +int zpci_store_block(const u64 *data, u64 req, u64 offset); +void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc); #endif diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 5fd81f31d6c..d194d544d69 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr) \ u64 data; \ int rc; \ \ - rc = pcilg_instr(&data, req, ZPCI_OFFSET(addr)); \ + rc = zpci_load(&data, req, ZPCI_OFFSET(addr)); \ if (rc) \ data = -1ULL; \ return (RETTYPE) data; \ @@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val, \ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH); \ u64 data = (VALTYPE) val; \ \ - pcistg_instr(data, req, ZPCI_OFFSET(addr)); \ + zpci_store(data, req, ZPCI_OFFSET(addr)); \ } zpci_read(8, u64) @@ -83,15 +83,18 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len val = 0; /* let FW report error */ break; } - return pcistg_instr(val, req, offset); + return zpci_store(val, req, offset); } static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) { u64 data; - u8 cc; + int cc; + + cc = zpci_load(&data, req, offset); + if (cc) + goto out; - cc = pcilg_instr(&data, req, offset); switch (len) { case 1: *((u8 *) dst) = (u8) data; @@ -106,12 +109,13 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) *((u64 *) dst) = (u64) data; break; } +out: return cc; } static inline int zpci_write_block(u64 req, const u64 *data, u64 offset) { - return pcistb_instr(data, req, offset); + return zpci_store_block(data, req, offset); } static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 86fe0ee2cee..fa91e009745 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -10,16 +10,22 @@ */ #define __my_cpu_offset S390_lowcore.percpu_offset +#ifdef CONFIG_64BIT + /* * For 64 bit module code, the module may be more than 4G above the * per cpu area, use weak definitions to force the compiler to * generate external references. */ -#if defined(CONFIG_SMP) && defined(CONFIG_64BIT) && defined(MODULE) +#if defined(CONFIG_SMP) && defined(MODULE) #define ARCH_NEEDS_WEAK_PER_CPU #endif -#define arch_this_cpu_to_op(pcp, val, op) \ +/* + * We use a compare-and-swap loop since that uses less cpu cycles than + * disabling and enabling interrupts like the generic variant would do. + */ +#define arch_this_cpu_to_op_simple(pcp, val, op) \ ({ \ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ old__, new__, prev__; \ @@ -30,42 +36,101 @@ do { \ old__ = prev__; \ new__ = old__ op (val); \ - switch (sizeof(*ptr__)) { \ - case 8: \ - prev__ = cmpxchg64(ptr__, old__, new__); \ - break; \ - default: \ - prev__ = cmpxchg(ptr__, old__, new__); \ - } \ + prev__ = cmpxchg(ptr__, old__, new__); \ } while (prev__ != old__); \ preempt_enable(); \ new__; \ }) -#define this_cpu_add_1(pcp, val) arch_this_cpu_to_op(pcp, val, +) -#define this_cpu_add_2(pcp, val) arch_this_cpu_to_op(pcp, val, +) -#define this_cpu_add_4(pcp, val) arch_this_cpu_to_op(pcp, val, +) -#define this_cpu_add_8(pcp, val) arch_this_cpu_to_op(pcp, val, +) +#define this_cpu_add_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_add_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_add_return_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_add_return_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_and_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &) +#define this_cpu_and_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &) +#define this_cpu_or_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |) +#define this_cpu_or_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |) + +#ifndef CONFIG_HAVE_MARCH_Z196_FEATURES + +#define this_cpu_add_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_add_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_add_return_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_add_return_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +) +#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &) +#define this_cpu_and_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &) +#define this_cpu_or_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |) +#define this_cpu_or_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |) + +#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */ + +#define arch_this_cpu_add(pcp, val, op1, op2, szcast) \ +{ \ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ val__ = (val); \ + pcp_op_T__ old__, *ptr__; \ + preempt_disable(); \ + ptr__ = __this_cpu_ptr(&(pcp)); \ + if (__builtin_constant_p(val__) && \ + ((szcast)val__ > -129) && ((szcast)val__ < 128)) { \ + asm volatile( \ + op2 " %[ptr__],%[val__]\n" \ + : [ptr__] "+Q" (*ptr__) \ + : [val__] "i" ((szcast)val__) \ + : "cc"); \ + } else { \ + asm volatile( \ + op1 " %[old__],%[val__],%[ptr__]\n" \ + : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ + : [val__] "d" (val__) \ + : "cc"); \ + } \ + preempt_enable(); \ +} -#define this_cpu_add_return_1(pcp, val) arch_this_cpu_to_op(pcp, val, +) -#define this_cpu_add_return_2(pcp, val) arch_this_cpu_to_op(pcp, val, +) -#define this_cpu_add_return_4(pcp, val) arch_this_cpu_to_op(pcp, val, +) -#define this_cpu_add_return_8(pcp, val) arch_this_cpu_to_op(pcp, val, +) +#define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int) +#define this_cpu_add_8(pcp, val) arch_this_cpu_add(pcp, val, "laag", "agsi", long) -#define this_cpu_and_1(pcp, val) arch_this_cpu_to_op(pcp, val, &) -#define this_cpu_and_2(pcp, val) arch_this_cpu_to_op(pcp, val, &) -#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, &) -#define this_cpu_and_8(pcp, val) arch_this_cpu_to_op(pcp, val, &) +#define arch_this_cpu_add_return(pcp, val, op) \ +({ \ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ val__ = (val); \ + pcp_op_T__ old__, *ptr__; \ + preempt_disable(); \ + ptr__ = __this_cpu_ptr(&(pcp)); \ + asm volatile( \ + op " %[old__],%[val__],%[ptr__]\n" \ + : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ + : [val__] "d" (val__) \ + : "cc"); \ + preempt_enable(); \ + old__ + val__; \ +}) -#define this_cpu_or_1(pcp, val) arch_this_cpu_to_op(pcp, val, |) -#define this_cpu_or_2(pcp, val) arch_this_cpu_to_op(pcp, val, |) -#define this_cpu_or_4(pcp, val) arch_this_cpu_to_op(pcp, val, |) -#define this_cpu_or_8(pcp, val) arch_this_cpu_to_op(pcp, val, |) +#define this_cpu_add_return_4(pcp, val) arch_this_cpu_add_return(pcp, val, "laa") +#define this_cpu_add_return_8(pcp, val) arch_this_cpu_add_return(pcp, val, "laag") -#define this_cpu_xor_1(pcp, val) arch_this_cpu_to_op(pcp, val, ^) -#define this_cpu_xor_2(pcp, val) arch_this_cpu_to_op(pcp, val, ^) -#define this_cpu_xor_4(pcp, val) arch_this_cpu_to_op(pcp, val, ^) -#define this_cpu_xor_8(pcp, val) arch_this_cpu_to_op(pcp, val, ^) +#define arch_this_cpu_to_op(pcp, val, op) \ +{ \ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ val__ = (val); \ + pcp_op_T__ old__, *ptr__; \ + preempt_disable(); \ + ptr__ = __this_cpu_ptr(&(pcp)); \ + asm volatile( \ + op " %[old__],%[val__],%[ptr__]\n" \ + : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ + : [val__] "d" (val__) \ + : "cc"); \ + preempt_enable(); \ +} + +#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan") +#define this_cpu_and_8(pcp, val) arch_this_cpu_to_op(pcp, val, "lang") +#define this_cpu_or_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lao") +#define this_cpu_or_8(pcp, val) arch_this_cpu_to_op(pcp, val, "laog") + +#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */ #define arch_this_cpu_cmpxchg(pcp, oval, nval) \ ({ \ @@ -74,13 +139,7 @@ pcp_op_T__ *ptr__; \ preempt_disable(); \ ptr__ = __this_cpu_ptr(&(pcp)); \ - switch (sizeof(*ptr__)) { \ - case 8: \ - ret__ = cmpxchg64(ptr__, oval, nval); \ - break; \ - default: \ - ret__ = cmpxchg(ptr__, oval, nval); \ - } \ + ret__ = cmpxchg(ptr__, oval, nval); \ preempt_enable(); \ ret__; \ }) @@ -104,9 +163,7 @@ #define this_cpu_xchg_1(pcp, nval) arch_this_cpu_xchg(pcp, nval) #define this_cpu_xchg_2(pcp, nval) arch_this_cpu_xchg(pcp, nval) #define this_cpu_xchg_4(pcp, nval) arch_this_cpu_xchg(pcp, nval) -#ifdef CONFIG_64BIT #define this_cpu_xchg_8(pcp, nval) arch_this_cpu_xchg(pcp, nval) -#endif #define arch_this_cpu_cmpxchg_double(pcp1, pcp2, o1, o2, n1, n2) \ ({ \ @@ -124,9 +181,9 @@ }) #define this_cpu_cmpxchg_double_4 arch_this_cpu_cmpxchg_double -#ifdef CONFIG_64BIT #define this_cpu_cmpxchg_double_8 arch_this_cpu_cmpxchg_double -#endif + +#endif /* CONFIG_64BIT */ #include <asm-generic/percpu.h> diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 5f0173a3169..159a8ec6da9 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -1,16 +1,96 @@ /* * 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) + + +/* Perf callbacks */ +struct pt_regs; +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 590c3219c63..9e18a61d3df 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -22,6 +22,11 @@ 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, + bool init_skey); +int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, + unsigned long key, bool nq); + static inline void clear_table(unsigned long *s, unsigned long val, size_t n) { typedef struct { char _[n]; } addrtype; @@ -88,11 +93,22 @@ 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 c1d7930a82f..fcba5e03839 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -29,6 +29,7 @@ #ifndef __ASSEMBLY__ #include <linux/sched.h> #include <linux/mm_types.h> +#include <linux/page-flags.h> #include <asm/bug.h> #include <asm/page.h> @@ -56,6 +57,7 @@ extern unsigned long zero_page_mask; (((unsigned long)(vaddr)) &zero_page_mask)))) #define __HAVE_COLOR_ZERO_PAGE +/* TODO: s390 cannot support io_remap_pfn_range... */ #endif /* !__ASSEMBLY__ */ /* @@ -215,61 +217,58 @@ extern unsigned long MODULES_END; /* Hardware bits in the page table entry */ #define _PAGE_CO 0x100 /* HW Change-bit override */ -#define _PAGE_RO 0x200 /* HW read-only bit */ +#define _PAGE_PROTECT 0x200 /* HW read-only bit */ #define _PAGE_INVALID 0x400 /* HW invalid bit */ +#define _PAGE_LARGE 0x800 /* Bit to mark a large pte */ /* Software bits in the page table entry */ -#define _PAGE_SWT 0x001 /* SW pte type bit t */ -#define _PAGE_SWX 0x002 /* SW pte type bit x */ -#define _PAGE_SWC 0x004 /* SW pte changed bit (for KVM) */ -#define _PAGE_SWR 0x008 /* SW pte referenced bit (for KVM) */ -#define _PAGE_SPECIAL 0x010 /* SW associated with special page */ +#define _PAGE_PRESENT 0x001 /* SW pte present bit */ +#define _PAGE_TYPE 0x002 /* SW pte type bit */ +#define _PAGE_YOUNG 0x004 /* SW pte young bit */ +#define _PAGE_DIRTY 0x008 /* SW pte dirty bit */ +#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 */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_SWC | _PAGE_SWR) - -/* Six different types of pages. */ -#define _PAGE_TYPE_EMPTY 0x400 -#define _PAGE_TYPE_NONE 0x401 -#define _PAGE_TYPE_SWAP 0x403 -#define _PAGE_TYPE_FILE 0x601 /* bit 0x002 is used for offset !! */ -#define _PAGE_TYPE_RO 0x200 -#define _PAGE_TYPE_RW 0x000 +#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \ + _PAGE_DIRTY | _PAGE_YOUNG) /* - * Only four types for huge pages, using the invalid bit and protection bit - * of a segment table entry. - */ -#define _HPAGE_TYPE_EMPTY 0x020 /* _SEGMENT_ENTRY_INV */ -#define _HPAGE_TYPE_NONE 0x220 -#define _HPAGE_TYPE_RO 0x200 /* _SEGMENT_ENTRY_RO */ -#define _HPAGE_TYPE_RW 0x000 - -/* - * PTE type bits are rather complicated. handle_pte_fault uses pte_present, - * pte_none and pte_file to find out the pte type WITHOUT holding the page - * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to - * invalidate a given pte. ipte sets the hw invalid bit and clears all tlbs - * for the page. The page table entry is set to _PAGE_TYPE_EMPTY afterwards. - * This change is done while holding the lock, but the intermediate step - * of a previously valid pte with the hw invalid bit set can be observed by - * handle_pte_fault. That makes it necessary that all valid pte types with - * the hw invalid bit set must be distinguishable from the four pte types - * empty, none, swap and file. + * handle_pte_fault uses pte_present, pte_none and pte_file to find out the + * pte type WITHOUT holding the page table lock. The _PAGE_PRESENT bit + * is used to distinguish present from not-present ptes. It is changed only + * with the page table lock held. + * + * The following table gives the different possible bit combinations for + * the pte hardware and software bits in the last 12 bits of a pte: * - * irxt ipte irxt - * _PAGE_TYPE_EMPTY 1000 -> 1000 - * _PAGE_TYPE_NONE 1001 -> 1001 - * _PAGE_TYPE_SWAP 1011 -> 1011 - * _PAGE_TYPE_FILE 11?1 -> 11?1 - * _PAGE_TYPE_RO 0100 -> 1100 - * _PAGE_TYPE_RW 0000 -> 1000 + * 842100000000 + * 000084210000 + * 000000008421 + * .IR...wrdytp + * empty .10...000000 + * swap .10...xxxx10 + * file .11...xxxxx0 + * prot-none, clean, old .11...000001 + * prot-none, clean, young .11...000101 + * prot-none, dirty, old .10...001001 + * prot-none, dirty, young .10...001101 + * read-only, clean, old .11...010001 + * read-only, clean, young .01...010101 + * read-only, dirty, old .11...011001 + * read-only, dirty, young .01...011101 + * read-write, clean, old .11...110001 + * read-write, clean, young .01...110101 + * read-write, dirty, old .10...111001 + * read-write, dirty, young .00...111101 * - * pte_none is true for bits combinations 1000, 1010, 1100, 1110 - * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001 - * pte_file is true for bits combinations 1101, 1111 - * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid. + * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001 + * pte_none is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400 + * pte_file is true for the bit pattern .11...xxxxx0, (pte & 0x601) == 0x600 + * pte_swap is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402 */ #ifndef CONFIG_64BIT @@ -282,27 +281,36 @@ extern unsigned long MODULES_END; #define _ASCE_TABLE_LENGTH 0x7f /* 128 x 64 entries = 8k */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_BITS 0x7fffffffUL /* Valid segment table bits */ #define _SEGMENT_ENTRY_ORIGIN 0x7fffffc0UL /* page table origin */ -#define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ -#define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ +#define _SEGMENT_ENTRY_PROTECT 0x200 /* page protection bit */ +#define _SEGMENT_ENTRY_INVALID 0x20 /* invalid segment table entry */ #define _SEGMENT_ENTRY_COMMON 0x10 /* common segment bit */ #define _SEGMENT_ENTRY_PTL 0x0f /* page table length */ +#define _SEGMENT_ENTRY_NONE _SEGMENT_ENTRY_PROTECT #define _SEGMENT_ENTRY (_SEGMENT_ENTRY_PTL) -#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) +#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INVALID) + +/* + * Segment table entry encoding (I = invalid, R = read-only bit): + * ..R...I..... + * prot-none ..1...1..... + * read-only ..1...0..... + * read-write ..0...0..... + * empty ..0...1..... + */ /* Page status table bits for virtualization */ -#define RCP_ACC_BITS 0xf0000000UL -#define RCP_FP_BIT 0x08000000UL -#define RCP_PCL_BIT 0x00800000UL -#define RCP_HR_BIT 0x00400000UL -#define RCP_HC_BIT 0x00200000UL -#define RCP_GR_BIT 0x00040000UL -#define RCP_GC_BIT 0x00020000UL - -/* User dirty / referenced bit for KVM's migration feature */ -#define KVM_UR_BIT 0x00008000UL -#define KVM_UC_BIT 0x00004000UL +#define PGSTE_ACC_BITS 0xf0000000UL +#define PGSTE_FP_BIT 0x08000000UL +#define PGSTE_PCL_BIT 0x00800000UL +#define PGSTE_HR_BIT 0x00400000UL +#define PGSTE_HC_BIT 0x00200000UL +#define PGSTE_GR_BIT 0x00040000UL +#define PGSTE_GC_BIT 0x00020000UL +#define PGSTE_UC_BIT 0x00008000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x00004000UL /* IPTE notify bit */ #else /* CONFIG_64BIT */ @@ -321,7 +329,8 @@ extern unsigned long MODULES_END; /* Bits in the region table entry */ #define _REGION_ENTRY_ORIGIN ~0xfffUL/* region/segment table origin */ -#define _REGION_ENTRY_INV 0x20 /* invalid region table entry */ +#define _REGION_ENTRY_PROTECT 0x200 /* region protection bit */ +#define _REGION_ENTRY_INVALID 0x20 /* invalid region table entry */ #define _REGION_ENTRY_TYPE_MASK 0x0c /* region/segment table type mask */ #define _REGION_ENTRY_TYPE_R1 0x0c /* region first table type */ #define _REGION_ENTRY_TYPE_R2 0x08 /* region second table type */ @@ -329,46 +338,71 @@ extern unsigned long MODULES_END; #define _REGION_ENTRY_LENGTH 0x03 /* region third length */ #define _REGION1_ENTRY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_LENGTH) -#define _REGION1_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INV) +#define _REGION1_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID) #define _REGION2_ENTRY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_LENGTH) -#define _REGION2_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INV) +#define _REGION2_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH) -#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV) +#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY_LARGE 0x400 /* RTTE-format control, large page */ +#define _REGION3_ENTRY_RO 0x200 /* page protection bit */ +#define _REGION3_ENTRY_CO 0x100 /* change-recording override */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL +#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff1ff33UL +#define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ #define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* segment table origin */ -#define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ -#define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ +#define _SEGMENT_ENTRY_PROTECT 0x200 /* page protection bit */ +#define _SEGMENT_ENTRY_INVALID 0x20 /* invalid segment table entry */ #define _SEGMENT_ENTRY (0) -#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) +#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INVALID) #define _SEGMENT_ENTRY_LARGE 0x400 /* STE-format control, large page */ #define _SEGMENT_ENTRY_CO 0x100 /* change-recording override */ +#define _SEGMENT_ENTRY_SPLIT 0x001 /* THP splitting bit */ +#define _SEGMENT_ENTRY_YOUNG 0x002 /* SW segment young bit */ +#define _SEGMENT_ENTRY_NONE _SEGMENT_ENTRY_YOUNG + +/* + * Segment table entry encoding (R = read-only, I = invalid, y = young bit): + * ..R...I...y. + * prot-none, old ..0...1...1. + * prot-none, young ..1...1...1. + * read-only, old ..1...1...0. + * read-only, young ..1...0...1. + * read-write, old ..0...1...0. + * read-write, young ..0...0...1. + * The segment table origin is used to distinguish empty (origin==0) from + * read-write, old segment table entries (origin!=0) + */ + #define _SEGMENT_ENTRY_SPLIT_BIT 0 /* THP splitting bit number */ -#define _SEGMENT_ENTRY_SPLIT (1UL << _SEGMENT_ENTRY_SPLIT_BIT) /* Set of bits not changed in pmd_modify */ #define _SEGMENT_CHG_MASK (_SEGMENT_ENTRY_ORIGIN | _SEGMENT_ENTRY_LARGE \ | _SEGMENT_ENTRY_SPLIT | _SEGMENT_ENTRY_CO) /* Page status table bits for virtualization */ -#define RCP_ACC_BITS 0xf000000000000000UL -#define RCP_FP_BIT 0x0800000000000000UL -#define RCP_PCL_BIT 0x0080000000000000UL -#define RCP_HR_BIT 0x0040000000000000UL -#define RCP_HC_BIT 0x0020000000000000UL -#define RCP_GR_BIT 0x0004000000000000UL -#define RCP_GC_BIT 0x0002000000000000UL - -/* User dirty / referenced bit for KVM's migration feature */ -#define KVM_UR_BIT 0x0000800000000000UL -#define KVM_UC_BIT 0x0000400000000000UL +#define PGSTE_ACC_BITS 0xf000000000000000UL +#define PGSTE_FP_BIT 0x0800000000000000UL +#define PGSTE_PCL_BIT 0x0080000000000000UL +#define PGSTE_HR_BIT 0x0040000000000000UL +#define PGSTE_HC_BIT 0x0020000000000000UL +#define PGSTE_GR_BIT 0x0004000000000000UL +#define PGSTE_GC_BIT 0x0002000000000000UL +#define PGSTE_UC_BIT 0x0000800000000000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x0000400000000000UL /* IPTE notify bit */ #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 @@ -380,12 +414,18 @@ extern unsigned long MODULES_END; /* * Page protection definitions. */ -#define PAGE_NONE __pgprot(_PAGE_TYPE_NONE) -#define PAGE_RO __pgprot(_PAGE_TYPE_RO) -#define PAGE_RW __pgprot(_PAGE_TYPE_RW) - -#define PAGE_KERNEL PAGE_RW -#define PAGE_COPY PAGE_RO +#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID) +#define PAGE_READ __pgprot(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_INVALID | _PAGE_PROTECT) +#define PAGE_WRITE __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_INVALID | _PAGE_PROTECT) + +#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_YOUNG | _PAGE_DIRTY) +#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_YOUNG | _PAGE_DIRTY) +#define PAGE_KERNEL_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ + _PAGE_PROTECT) /* * On s390 the page table entry has an invalid bit and a read-only bit. @@ -394,28 +434,31 @@ extern unsigned long MODULES_END; */ /*xwr*/ #define __P000 PAGE_NONE -#define __P001 PAGE_RO -#define __P010 PAGE_RO -#define __P011 PAGE_RO -#define __P100 PAGE_RO -#define __P101 PAGE_RO -#define __P110 PAGE_RO -#define __P111 PAGE_RO +#define __P001 PAGE_READ +#define __P010 PAGE_READ +#define __P011 PAGE_READ +#define __P100 PAGE_READ +#define __P101 PAGE_READ +#define __P110 PAGE_READ +#define __P111 PAGE_READ #define __S000 PAGE_NONE -#define __S001 PAGE_RO -#define __S010 PAGE_RW -#define __S011 PAGE_RW -#define __S100 PAGE_RO -#define __S101 PAGE_RO -#define __S110 PAGE_RW -#define __S111 PAGE_RW +#define __S001 PAGE_READ +#define __S010 PAGE_WRITE +#define __S011 PAGE_WRITE +#define __S100 PAGE_READ +#define __S101 PAGE_READ +#define __S110 PAGE_WRITE +#define __S111 PAGE_WRITE -static inline int mm_exclusive(struct mm_struct *mm) -{ - return likely(mm == current->active_mm && - atomic_read(&mm->context.attach_count) <= 1); -} +/* + * Segment entry (large page) protection definitions. + */ +#define SEGMENT_NONE __pgprot(_SEGMENT_ENTRY_INVALID | \ + _SEGMENT_ENTRY_NONE) +#define SEGMENT_READ __pgprot(_SEGMENT_ENTRY_INVALID | \ + _SEGMENT_ENTRY_PROTECT) +#define SEGMENT_WRITE __pgprot(_SEGMENT_ENTRY_INVALID) static inline int mm_has_pgste(struct mm_struct *mm) { @@ -425,6 +468,16 @@ static inline int mm_has_pgste(struct mm_struct *mm) #endif return 0; } + +static inline int mm_use_skey(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (mm->context.use_skey) + return 1; +#endif + return 0; +} + /* * pgd/pmd/pte query functions */ @@ -452,7 +505,7 @@ static inline int pgd_none(pgd_t pgd) { if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) return 0; - return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL; + return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL; } static inline int pgd_bad(pgd_t pgd) @@ -463,7 +516,7 @@ static inline int pgd_bad(pgd_t pgd) * invalid for either table entry. */ unsigned long mask = - ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV & + ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID & ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH; return (pgd_val(pgd) & mask) != 0; } @@ -479,7 +532,7 @@ static inline int pud_none(pud_t pud) { if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3) return 0; - return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL; + return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL; } static inline int pud_large(pud_t pud) @@ -497,7 +550,7 @@ static inline int pud_bad(pud_t pud) * invalid for either table entry. */ unsigned long mask = - ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV & + ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID & ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH; return (pud_val(pud) & mask) != 0; } @@ -506,30 +559,36 @@ static inline int pud_bad(pud_t pud) static inline int pmd_present(pmd_t pmd) { - unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO; - return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE || - !(pmd_val(pmd) & _SEGMENT_ENTRY_INV); + return pmd_val(pmd) != _SEGMENT_ENTRY_INVALID; } static inline int pmd_none(pmd_t pmd) { - return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) && - !(pmd_val(pmd) & _SEGMENT_ENTRY_RO); + return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID; } static inline int pmd_large(pmd_t pmd) { #ifdef CONFIG_64BIT - return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE); + return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; #else return 0; #endif } +static inline int pmd_prot_none(pmd_t pmd) +{ + return (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) && + (pmd_val(pmd) & _SEGMENT_ENTRY_NONE); +} + static inline int pmd_bad(pmd_t pmd) { - unsigned long mask = ~_SEGMENT_ENTRY_ORIGIN & ~_SEGMENT_ENTRY_INV; - return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY; +#ifdef CONFIG_64BIT + if (pmd_large(pmd)) + return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0; +#endif + return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH @@ -548,31 +607,48 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { - return (pmd_val(pmd) & _SEGMENT_ENTRY_RO) == 0; + if (pmd_prot_none(pmd)) + return 0; + return (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) == 0; } static inline int pmd_young(pmd_t pmd) { - return 0; + int young = 0; +#ifdef CONFIG_64BIT + if (pmd_prot_none(pmd)) + young = (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) != 0; + else + young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; +#endif + return young; +} + +static inline int pte_present(pte_t pte) +{ + /* Bit pattern: (pte & 0x001) == 0x001 */ + return (pte_val(pte) & _PAGE_PRESENT) != 0; } static inline int pte_none(pte_t pte) { - return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT); + /* Bit pattern: pte == 0x400 */ + return pte_val(pte) == _PAGE_INVALID; } -static inline int pte_present(pte_t pte) +static inline int pte_swap(pte_t pte) { - unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT | _PAGE_SWX; - return (pte_val(pte) & mask) == _PAGE_TYPE_NONE || - (!(pte_val(pte) & _PAGE_INVALID) && - !(pte_val(pte) & _PAGE_SWT)); + /* 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) { - unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT; - return (pte_val(pte) & mask) == _PAGE_TYPE_FILE; + /* Bit pattern: (pte & 0x601) == 0x600 */ + return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | _PAGE_PRESENT)) + == (_PAGE_INVALID | _PAGE_PROTECT); } static inline int pte_special(pte_t pte) @@ -596,12 +672,12 @@ static inline pgste_t pgste_get_lock(pte_t *ptep) asm( " lg %0,%2\n" "0: lgr %1,%0\n" - " nihh %0,0xff7f\n" /* clear RCP_PCL_BIT in old */ - " oihh %1,0x0080\n" /* set RCP_PCL_BIT in new */ + " nihh %0,0xff7f\n" /* clear PCL bit in old */ + " oihh %1,0x0080\n" /* set PCL bit in new */ " csg %0,%1,%2\n" " jl 0b\n" : "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE]) - : "Q" (ptep[PTRS_PER_PTE]) : "cc"); + : "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory"); #endif return __pgste(new); } @@ -610,132 +686,177 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE asm( - " nihh %1,0xff7f\n" /* clear RCP_PCL_BIT */ + " nihh %1,0xff7f\n" /* clear PCL bit */ " stg %1,%0\n" : "=Q" (ptep[PTRS_PER_PTE]) - : "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) : "cc"); + : "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) + : "cc", "memory"); preempt_enable(); #endif } -static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) +static inline pgste_t pgste_get(pte_t *ptep) { + unsigned long pgste = 0; #ifdef CONFIG_PGSTE - unsigned long address, bits; - unsigned char skey; - - if (!pte_present(*ptep)) - return pgste; - address = pte_val(*ptep) & PAGE_MASK; - skey = page_get_storage_key(address); - bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); - /* Clear page changed & referenced bit in the storage key */ - if (bits & _PAGE_CHANGED) - page_set_storage_key(address, skey ^ bits, 1); - else if (bits) - page_reset_referenced(address); - /* Transfer page changed & referenced bit to guest bits in pgste */ - pgste_val(pgste) |= bits << 48; /* RCP_GR_BIT & RCP_GC_BIT */ - /* Get host changed & referenced bits from pgste */ - bits |= (pgste_val(pgste) & (RCP_HR_BIT | RCP_HC_BIT)) >> 52; - /* Clear host bits in pgste. */ - pgste_val(pgste) &= ~(RCP_HR_BIT | RCP_HC_BIT); - pgste_val(pgste) &= ~(RCP_ACC_BITS | RCP_FP_BIT); - /* Copy page access key and fetch protection bit to pgste */ - pgste_val(pgste) |= - (unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; - /* Transfer changed and referenced to kvm user bits */ - pgste_val(pgste) |= bits << 45; /* KVM_UR_BIT & KVM_UC_BIT */ - /* Transfer changed & referenced to pte sofware bits */ - pte_val(*ptep) |= bits << 1; /* _PAGE_SWR & _PAGE_SWC */ + pgste = *(unsigned long *)(ptep + PTRS_PER_PTE); #endif - return pgste; + return __pgste(pgste); +} +static inline void pgste_set(pte_t *ptep, pgste_t pgste) +{ +#ifdef CONFIG_PGSTE + *(pgste_t *)(ptep + PTRS_PER_PTE) = pgste; +#endif } -static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) +static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste, + struct mm_struct *mm) { #ifdef CONFIG_PGSTE - int young; + unsigned long address, bits, skey; - if (!pte_present(*ptep)) + if (!mm_use_skey(mm) || pte_val(*ptep) & _PAGE_INVALID) return pgste; - young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); - /* Transfer page referenced bit to pte software bit (host view) */ - if (young || (pgste_val(pgste) & RCP_HR_BIT)) - pte_val(*ptep) |= _PAGE_SWR; - /* Clear host referenced bit in pgste. */ - pgste_val(pgste) &= ~RCP_HR_BIT; - /* Transfer page referenced bit to guest bit in pgste */ - pgste_val(pgste) |= (unsigned long) young << 50; /* set RCP_GR_BIT */ + address = pte_val(*ptep) & PAGE_MASK; + skey = (unsigned long) page_get_storage_key(address); + bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); + /* Transfer page changed & referenced bit to guest bits in pgste */ + pgste_val(pgste) |= bits << 48; /* GR bit & GC bit */ + /* Copy page access key and fetch protection bit to pgste */ + pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; #endif return pgste; } -static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) +static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry, + struct mm_struct *mm) { #ifdef CONFIG_PGSTE unsigned long address; - unsigned long okey, nkey; + unsigned long nkey; - if (!pte_present(entry)) + if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID) return; + VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID)); address = pte_val(entry) & PAGE_MASK; - okey = nkey = page_get_storage_key(address); - nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT); - /* Set page access key and fetch protection bit from pgste */ - nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56; - if (okey != nkey) - page_set_storage_key(address, nkey, 1); + /* + * Set page access key and fetch protection bit from pgste. + * The guest C/R information is still in the PGSTE, set real + * key C/R to 0. + */ + nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56; + nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48; + page_set_storage_key(address, nkey, 0); #endif } +static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) +{ + if ((pte_val(entry) & _PAGE_PRESENT) && + (pte_val(entry) & _PAGE_WRITE) && + !(pte_val(entry) & _PAGE_INVALID)) { + if (!MACHINE_HAS_ESOP) { + /* + * Without enhanced suppression-on-protection force + * the dirty bit on for all writable ptes. + */ + pte_val(entry) |= _PAGE_DIRTY; + pte_val(entry) &= ~_PAGE_PROTECT; + } + if (!(pte_val(entry) & _PAGE_PROTECT)) + /* This pte allows write access, set user-dirty */ + pgste_val(pgste) |= PGSTE_UC_BIT; + } + *ptep = entry; + return pgste; +} + /** * struct gmap_struct - guest address space * @mm: pointer to the parent mm_struct * @table: pointer to the page directory * @asce: address space control element for gmap page table * @crst_list: list of all crst tables used in the guest address space + * @pfault_enabled: defines if pfaults are applicable for the guest */ struct gmap { struct list_head list; struct mm_struct *mm; unsigned long *table; unsigned long asce; + void *private; struct list_head crst_list; + bool pfault_enabled; }; /** * struct gmap_rmap - reverse mapping for segment table entries - * @next: pointer to the next gmap_rmap structure in the list + * @gmap: pointer to the gmap_struct * @entry: pointer to a segment table entry + * @vmaddr: virtual address in the guest address space */ struct gmap_rmap { struct list_head list; + struct gmap *gmap; unsigned long *entry; + unsigned long vmaddr; }; /** * struct gmap_pgtable - gmap information attached to a page table * @vmaddr: address of the 1MB segment in the process virtual memory - * @mapper: list of segment table entries maping a page table + * @mapper: list of segment table entries mapping a page table */ struct gmap_pgtable { unsigned long vmaddr; struct list_head mapper; }; +/** + * struct gmap_notifier - notify function block for page invalidation + * @notifier_call: address of callback function + */ +struct gmap_notifier { + struct list_head list; + void (*notifier_call)(struct gmap *gmap, unsigned long address); +}; + struct gmap *gmap_alloc(struct mm_struct *mm); void gmap_free(struct gmap *gmap); void gmap_enable(struct gmap *gmap); void gmap_disable(struct gmap *gmap); int gmap_map_segment(struct gmap *gmap, unsigned long from, - unsigned long to, unsigned long length); + unsigned long to, unsigned long len); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); +unsigned long __gmap_translate(unsigned long address, struct gmap *); +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 *); +bool gmap_test_and_clear_dirty(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 *, pte_t *); + +static inline pgste_t pgste_ipte_notify(struct mm_struct *mm, + 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, ptep); + } +#endif + return pgste; +} /* * Certain architectures need to do special things when PTEs @@ -749,11 +870,15 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste_set_pte(ptep, pgste, entry); - *ptep = entry; + pgste_val(pgste) &= ~_PGSTE_GPS_ZERO; + pgste_set_key(ptep, pgste, entry, mm); + pgste = pgste_set_pte(ptep, pgste, entry); pgste_set_unlock(ptep, pgste); - } else + } else { + if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1) + pte_val(entry) |= _PAGE_CO; *ptep = entry; + } } /* @@ -762,25 +887,23 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, */ static inline int pte_write(pte_t pte) { - return (pte_val(pte) & _PAGE_RO) == 0; + return (pte_val(pte) & _PAGE_WRITE) != 0; } static inline int pte_dirty(pte_t pte) { -#ifdef CONFIG_PGSTE - if (pte_val(pte) & _PAGE_SWC) - return 1; -#endif - return 0; + return (pte_val(pte) & _PAGE_DIRTY) != 0; } static inline int pte_young(pte_t pte) { -#ifdef CONFIG_PGSTE - if (pte_val(pte) & _PAGE_SWR) - return 1; -#endif - return 0; + 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; } /* @@ -805,12 +928,12 @@ static inline void pud_clear(pud_t *pud) static inline void pmd_clear(pmd_t *pmdp) { - pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY; + pmd_val(*pmdp) = _SEGMENT_ENTRY_INVALID; } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; } /* @@ -821,46 +944,63 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pte_val(pte) &= _PAGE_CHG_MASK; pte_val(pte) |= pgprot_val(newprot); + /* + * newprot for PAGE_NONE, PAGE_READ and PAGE_WRITE has the + * invalid bit set, clear it again for readable, young pages + */ + if ((pte_val(pte) & _PAGE_YOUNG) && (pte_val(pte) & _PAGE_READ)) + pte_val(pte) &= ~_PAGE_INVALID; + /* + * newprot for PAGE_READ and PAGE_WRITE has the page protection + * bit set, clear it again for writable, dirty pages + */ + if ((pte_val(pte) & _PAGE_DIRTY) && (pte_val(pte) & _PAGE_WRITE)) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_wrprotect(pte_t pte) { - /* Do not clobber _PAGE_TYPE_NONE pages! */ - if (!(pte_val(pte) & _PAGE_INVALID)) - pte_val(pte) |= _PAGE_RO; + pte_val(pte) &= ~_PAGE_WRITE; + pte_val(pte) |= _PAGE_PROTECT; return pte; } static inline pte_t pte_mkwrite(pte_t pte) { - pte_val(pte) &= ~_PAGE_RO; + pte_val(pte) |= _PAGE_WRITE; + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_mkclean(pte_t pte) { -#ifdef CONFIG_PGSTE - pte_val(pte) &= ~_PAGE_SWC; -#endif + pte_val(pte) &= ~_PAGE_DIRTY; + pte_val(pte) |= _PAGE_PROTECT; return pte; } static inline pte_t pte_mkdirty(pte_t pte) { + pte_val(pte) |= _PAGE_DIRTY; + if (pte_val(pte) & _PAGE_WRITE) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_mkold(pte_t pte) { -#ifdef CONFIG_PGSTE - pte_val(pte) &= ~_PAGE_SWR; -#endif + pte_val(pte) &= ~_PAGE_YOUNG; + pte_val(pte) |= _PAGE_INVALID; return pte; } static inline pte_t pte_mkyoung(pte_t pte) { + pte_val(pte) |= _PAGE_YOUNG; + if (pte_val(pte) & _PAGE_READ) + pte_val(pte) &= ~_PAGE_INVALID; return pte; } @@ -873,68 +1013,101 @@ static inline pte_t pte_mkspecial(pte_t pte) #ifdef CONFIG_HUGETLB_PAGE static inline pte_t pte_mkhuge(pte_t pte) { - /* - * PROT_NONE needs to be remapped from the pte type to the ste type. - * The HW invalid bit is also different for pte and ste. The pte - * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE - * bit, so we don't have to clear it. - */ - if (pte_val(pte) & _PAGE_INVALID) { - if (pte_val(pte) & _PAGE_SWT) - pte_val(pte) |= _HPAGE_TYPE_NONE; - pte_val(pte) |= _SEGMENT_ENTRY_INV; - } - /* - * Clear SW pte bits SWT and SWX, there are no SW bits in a segment - * table entry. - */ - pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX); - /* - * Also set the change-override bit because we don't need dirty bit - * tracking for hugetlbfs pages. - */ - pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO); + pte_val(pte) |= _PAGE_LARGE; return pte; } #endif -/* - * Get (and clear) the user dirty bit for a pte. - */ -static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, - pte_t *ptep) +static inline void __ptep_ipte(unsigned long address, pte_t *ptep) { - pgste_t pgste; - int dirty = 0; + unsigned long pto = (unsigned long) ptep; - if (mm_has_pgste(mm)) { - pgste = pgste_get_lock(ptep); - pgste = pgste_update_all(ptep, pgste); - dirty = !!(pgste_val(pgste) & KVM_UC_BIT); - pgste_val(pgste) &= ~KVM_UC_BIT; - pgste_set_unlock(ptep, pgste); - return dirty; - } - return dirty; +#ifndef CONFIG_64BIT + /* pto in ESA mode must point to the start of the segment table */ + pto &= 0x7ffffc00; +#endif + /* 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, 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 ((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); } /* - * Get (and clear) the user referenced bit for a pte. + * Get (and clear) the user dirty bit for a pte. */ -static inline int ptep_test_and_clear_user_young(struct mm_struct *mm, +static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { pgste_t pgste; - int young = 0; + pte_t pte; + int dirty; - if (mm_has_pgste(mm)) { - pgste = pgste_get_lock(ptep); - pgste = pgste_update_young(ptep, pgste); - young = !!(pgste_val(pgste) & KVM_UR_BIT); - pgste_val(pgste) &= ~KVM_UR_BIT; - pgste_set_unlock(ptep, pgste); + if (!mm_has_pgste(mm)) + return 0; + pgste = pgste_get_lock(ptep); + dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT); + pgste_val(pgste) &= ~PGSTE_UC_BIT; + pte = *ptep; + if (dirty && (pte_val(pte) & _PAGE_PRESENT)) { + pgste = pgste_ipte_notify(mm, ptep, pgste); + __ptep_ipte(addr, ptep); + if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE)) + pte_val(pte) |= _PAGE_PROTECT; + else + pte_val(pte) |= _PAGE_INVALID; + *ptep = pte; } - return young; + pgste_set_unlock(ptep, pgste); + return dirty; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -943,46 +1116,34 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, { pgste_t pgste; pte_t pte; + int young; if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_update_young(ptep, pgste); - pte = *ptep; - *ptep = pte_mkold(pte); - pgste_set_unlock(ptep, pgste); - return pte_young(pte); + pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste); } - return 0; + + pte = *ptep; + ptep_flush_direct(vma->vm_mm, addr, ptep); + young = pte_young(pte); + pte = pte_mkold(pte); + + if (mm_has_pgste(vma->vm_mm)) { + pgste = pgste_set_pte(ptep, pgste, pte); + pgste_set_unlock(ptep, pgste); + } else + *ptep = pte; + + return young; } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - /* No need to flush TLB - * On s390 reference bits are in storage key and never in TLB - * With virtualization we handle the reference bit, without we - * we can simply return */ return ptep_test_and_clear_young(vma, address, ptep); } -static inline void __ptep_ipte(unsigned long address, pte_t *ptep) -{ - if (!(pte_val(*ptep) & _PAGE_INVALID)) { -#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; -#endif - asm volatile( - " ipte %2,%3" - : "=m" (*ptep) : "m" (*ptep), - "a" (pto), "a" (address)); - } -} - /* * This is hard to understand. ptep_get_and_clear and ptep_clear_flush * both clear the TLB for the unmapped pte. The reason is that @@ -1003,17 +1164,17 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, pgste_t pgste; pte_t pte; - mm->context.flush_mm = 1; - if (mm_has_pgste(mm)) + if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); + pgste = pgste_ipte_notify(mm, ptep, pgste); + } pte = *ptep; - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(mm)) { - pgste = pgste_update_all(&pte, pgste); + pgste = pgste_update_all(&pte, pgste, mm); pgste_set_unlock(ptep, pgste); } return pte; @@ -1024,15 +1185,21 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long address, pte_t *ptep) { + pgste_t pgste; pte_t pte; - mm->context.flush_mm = 1; - if (mm_has_pgste(mm)) - pgste_get_lock(ptep); + if (mm_has_pgste(mm)) { + pgste = pgste_get_lock(ptep); + pgste_ipte_notify(mm, ptep, pgste); + } pte = *ptep; - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); + ptep_flush_lazy(mm, address, ptep); + + if (mm_has_pgste(mm)) { + pgste = pgste_update_all(&pte, pgste, mm); + pgste_set(ptep, pgste); + } return pte; } @@ -1040,9 +1207,15 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long address, pte_t *ptep, pte_t pte) { - *ptep = pte; - if (mm_has_pgste(mm)) - pgste_set_unlock(ptep, *(pgste_t *)(ptep + PTRS_PER_PTE)); + pgste_t pgste; + + if (mm_has_pgste(mm)) { + pgste = pgste_get(ptep); + pgste_set_key(ptep, pgste, pte, mm); + pgste = pgste_set_pte(ptep, pgste, pte); + pgste_set_unlock(ptep, pgste); + } else + *ptep = pte; } #define __HAVE_ARCH_PTEP_CLEAR_FLUSH @@ -1052,15 +1225,20 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, pgste_t pgste; pte_t pte; - if (mm_has_pgste(vma->vm_mm)) + if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); + pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste); + } pte = *ptep; - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_direct(vma->vm_mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(vma->vm_mm)) { - pgste = pgste_update_all(&pte, pgste); + if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) == + _PGSTE_GPS_USAGE_UNUSED) + pte_val(pte) |= _PAGE_UNUSED; + pgste = pgste_update_all(&pte, pgste, vma->vm_mm); pgste_set_unlock(ptep, pgste); } return pte; @@ -1081,16 +1259,18 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, pgste_t pgste; pte_t pte; - if (mm_has_pgste(mm)) + if (!full && mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); + pgste = pgste_ipte_notify(mm, ptep, pgste); + } pte = *ptep; if (!full) - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; - if (mm_has_pgste(mm)) { - pgste = pgste_update_all(&pte, pgste); + if (!full && mm_has_pgste(mm)) { + pgste = pgste_update_all(&pte, pgste, mm); pgste_set_unlock(ptep, pgste); } return pte; @@ -1104,16 +1284,19 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm, pte_t pte = *ptep; if (pte_write(pte)) { - mm->context.flush_mm = 1; - if (mm_has_pgste(mm)) + if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); + pgste = pgste_ipte_notify(mm, ptep, pgste); + } - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); - *ptep = pte_wrprotect(pte); + ptep_flush_lazy(mm, address, ptep); + pte = pte_wrprotect(pte); - if (mm_has_pgste(mm)) + if (mm_has_pgste(mm)) { + pgste = pgste_set_pte(ptep, pgste, pte); pgste_set_unlock(ptep, pgste); + } else + *ptep = pte; } return pte; } @@ -1127,14 +1310,18 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, if (pte_same(*ptep, entry)) return 0; - if (mm_has_pgste(vma->vm_mm)) + if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); + pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste); + } - __ptep_ipte(address, ptep); - *ptep = entry; + ptep_flush_direct(vma->vm_mm, address, ptep); - if (mm_has_pgste(vma->vm_mm)) + if (mm_has_pgste(vma->vm_mm)) { + pgste = pgste_set_pte(ptep, pgste, entry); pgste_set_unlock(ptep, pgste); + } else + *ptep = entry; return 1; } @@ -1146,14 +1333,17 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); - return __pte; + return pte_mkyoung(__pte); } static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) { unsigned long physpage = page_to_phys(page); + pte_t __pte = mk_pte_phys(physpage, pgprot); - return mk_pte_phys(physpage, pgprot); + if (pte_write(__pte) && PageDirty(page)) + __pte = pte_mkdirty(__pte); + return __pte; } #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) @@ -1209,100 +1399,190 @@ 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) +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) +static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) { - unsigned long sto = (unsigned long) pmdp - - pmd_index(address) * sizeof(pmd_t); + /* + * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx) + * Convert to segment table entry format. + */ + if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE)) + return pgprot_val(SEGMENT_NONE); + if (pgprot_val(pgprot) == pgprot_val(PAGE_READ)) + return pgprot_val(SEGMENT_READ); + return pgprot_val(SEGMENT_WRITE); +} - if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) { - asm volatile( - " .insn rrf,0xb98e0000,%2,%3,0,0" - : "=m" (*pmdp) - : "m" (*pmdp), "a" (sto), - "a" ((address & HPAGE_MASK)) - : "cc" - ); +static inline pmd_t pmd_mkyoung(pmd_t pmd) +{ +#ifdef CONFIG_64BIT + if (pmd_prot_none(pmd)) { + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + } else { + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; } +#endif + return pmd; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pmd_mkold(pmd_t pmd) +{ +#ifdef CONFIG_64BIT + if (pmd_prot_none(pmd)) { + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + } else { + pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; + } +#endif + return pmd; +} -#define SEGMENT_NONE __pgprot(_HPAGE_TYPE_NONE) -#define SEGMENT_RO __pgprot(_HPAGE_TYPE_RO) -#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW) +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + int young; -#define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); + young = pmd_young(pmd); + pmd_val(pmd) &= _SEGMENT_CHG_MASK; + pmd_val(pmd) |= massage_pgprot_pmd(newprot); + if (young) + pmd = pmd_mkyoung(pmd); + return pmd; +} -#define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); +static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot) +{ + pmd_t __pmd; + pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot); + return pmd_mkyoung(__pmd); +} -static inline int pmd_trans_splitting(pmd_t pmd) +static inline pmd_t pmd_mkwrite(pmd_t pmd) { - return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT; + /* Do not clobber PROT_NONE segments! */ + if (!pmd_prot_none(pmd)) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + return pmd; } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ -static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, pmd_t entry) +static inline void __pmdp_csp(pmd_t *pmdp) { - *pmdp = entry; + 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 unsigned long massage_pgprot_pmd(pgprot_t pgprot) +static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp) { - /* - * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx) - * Convert to segment table entry format. - */ - if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE)) - return pgprot_val(SEGMENT_NONE); - if (pgprot_val(pgprot) == pgprot_val(PAGE_RO)) - return pgprot_val(SEGMENT_RO); - return pgprot_val(SEGMENT_RW); + 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 pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp) { - pmd_val(pmd) &= _SEGMENT_CHG_MASK; - pmd_val(pmd) |= massage_pgprot_pmd(newprot); - return pmd; + 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 pmd_t pmd_mkhuge(pmd_t pmd) +static inline void pmdp_flush_direct(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) { - pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; - return pmd; + 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 pmd_t pmd_mkwrite(pmd_t pmd) +static inline void pmdp_flush_lazy(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) { - /* Do not clobber _HPAGE_TYPE_NONE pages! */ - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV)) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO; - return pmd; + int active, count; + + 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); } -static inline pmd_t pmd_wrprotect(pmd_t pmd) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +#define __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); + +#define __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); + +static inline int pmd_trans_splitting(pmd_t pmd) { - pmd_val(pmd) |= _SEGMENT_ENTRY_RO; - return pmd; + return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT; } -static inline pmd_t pmd_mkdirty(pmd_t pmd) +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t entry) { - /* No dirty bit in the segment table entry. */ + if (!(pmd_val(entry) & _SEGMENT_ENTRY_INVALID) && MACHINE_HAS_EDAT1) + pmd_val(entry) |= _SEGMENT_ENTRY_CO; + *pmdp = entry; +} + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; return pmd; } -static inline pmd_t pmd_mkold(pmd_t pmd) +static inline pmd_t pmd_wrprotect(pmd_t pmd) { - /* No referenced bit in the segment table entry. */ + /* Do not clobber PROT_NONE segments! */ + if (!pmd_prot_none(pmd)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; return pmd; } -static inline pmd_t pmd_mkyoung(pmd_t pmd) +static inline pmd_t pmd_mkdirty(pmd_t pmd) { - /* No referenced bit in the segment table entry. */ + /* No dirty bit in the segment table entry. */ return pmd; } @@ -1310,34 +1590,12 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - unsigned long pmd_addr = pmd_val(*pmdp) & HPAGE_MASK; - long tmp, rc; - int counter; - - rc = 0; - if (MACHINE_HAS_RRBM) { - counter = PTRS_PER_PTE >> 6; - asm volatile( - "0: .insn rre,0xb9ae0000,%0,%3\n" /* rrbm */ - " ogr %1,%0\n" - " la %3,0(%4,%3)\n" - " brct %2,0b\n" - : "=&d" (tmp), "+&d" (rc), "+d" (counter), - "+a" (pmd_addr) - : "a" (64 * 4096UL) : "cc"); - rc = !!rc; - } else { - counter = PTRS_PER_PTE; - asm volatile( - "0: rrbe 0,%2\n" - " la %2,0(%3,%2)\n" - " brc 12,1f\n" - " lhi %0,1\n" - "1: brct %1,0b\n" - : "+d" (rc), "+d" (counter), "+a" (pmd_addr) - : "a" (4096UL) : "cc"); - } - return rc; + pmd_t pmd; + + pmd = *pmdp; + pmdp_flush_direct(vma->vm_mm, address, pmdp); + *pmdp = pmd_mkold(pmd); + return pmd_young(pmd); } #define __HAVE_ARCH_PMDP_GET_AND_CLEAR @@ -1346,7 +1604,7 @@ 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; } @@ -1362,14 +1620,19 @@ 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); } -static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot) +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) { - pmd_t __pmd; - pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot); - return __pmd; + pmd_t pmd = *pmdp; + + if (pmd_write(pmd)) { + pmdp_flush_direct(mm, address, pmdp); + set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd)); + } } #define pfn_pmd(pfn, pgprot) mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot)) @@ -1398,10 +1661,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd) * exception will occur instead of a page translation exception. The * specifiation exception has the bad habit not to store necessary * information in the lowcore. - * Bit 21 and bit 22 are the page invalid bit and the page protection - * bit. We set both to indicate a swapped page. - * Bit 30 and 31 are used to distinguish the different page types. For - * a swapped page these bits need to be zero. + * Bits 21, 22, 30 and 31 are used to indicate the page type. + * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402 * This leaves the bits 1-19 and bits 24-29 to store type and offset. * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19 * plus 24 for the offset. @@ -1415,10 +1676,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd) * exception will occur instead of a page translation exception. The * specifiation exception has the bad habit not to store necessary * information in the lowcore. - * Bit 53 and bit 54 are the page invalid bit and the page protection - * bit. We set both to indicate a swapped page. - * Bit 62 and 63 are used to distinguish the different page types. For - * a swapped page these bits need to be zero. + * Bits 53, 54, 62 and 63 are used to indicate the page type. + * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402 * This leaves the bits 0-51 and bits 56-61 to store type and offset. * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51 * plus 56 for the offset. @@ -1435,7 +1694,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) { pte_t pte; offset &= __SWP_OFFSET_MASK; - pte_val(pte) = _PAGE_TYPE_SWAP | ((type & 0x1f) << 2) | + pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) | ((offset & 1UL) << 7) | ((offset & ~1UL) << 11); return pte; } @@ -1458,7 +1717,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define pgoff_to_pte(__off) \ ((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \ - | _PAGE_TYPE_FILE }) + | _PAGE_INVALID | _PAGE_PROTECT }) #endif /* !__ASSEMBLY__ */ @@ -1467,11 +1726,13 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) extern int vmem_add_mapping(unsigned long start, unsigned long size); extern int vmem_remove_mapping(unsigned long start, unsigned long size); extern int s390_enable_sie(void); +extern void s390_enable_skey(void); /* * No page table caches to initialise */ -#define pgtable_cache_init() do { } while (0) +static inline void pgtable_cache_init(void) { } +static inline void check_pgt_cache(void) { } #include <asm-generic/pgtable.h> diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 94e749c9023..6f02d452bbe 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -11,6 +11,13 @@ #ifndef __ASM_S390_PROCESSOR_H #define __ASM_S390_PROCESSOR_H +#define CIF_MCCK_PENDING 0 /* machine check handling is pending */ +#define CIF_ASCE 1 /* user asce needs fixup / uaccess */ + +#define _CIF_MCCK_PENDING (1<<CIF_MCCK_PENDING) +#define _CIF_ASCE (1<<CIF_ASCE) + + #ifndef __ASSEMBLY__ #include <linux/linkage.h> @@ -21,6 +28,21 @@ #include <asm/setup.h> #include <asm/runtime_instr.h> +static inline void set_cpu_flag(int flag) +{ + S390_lowcore.cpu_flags |= (1U << flag); +} + +static inline void clear_cpu_flag(int flag) +{ + S390_lowcore.cpu_flags &= ~(1U << flag); +} + +static inline int test_cpu_flag(int flag) +{ + return !!(S390_lowcore.cpu_flags & (1U << flag)); +} + /* * Default implementation of macro that returns current * instruction pointer ("program counter"). @@ -43,6 +65,7 @@ extern void execve_tail(void); #ifndef CONFIG_64BIT #define TASK_SIZE (1UL << 31) +#define TASK_MAX_SIZE (1UL << 31) #define TASK_UNMAPPED_BASE (1UL << 30) #else /* CONFIG_64BIT */ @@ -51,6 +74,7 @@ extern void execve_tail(void); #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) +#define TASK_MAX_SIZE (1UL << 53) #endif /* CONFIG_64BIT */ @@ -77,6 +101,7 @@ 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 */ @@ -91,7 +116,15 @@ struct thread_struct { #endif }; -#define PER_FLAG_NO_TE 1UL /* Flag to disable transactions. */ +/* Flag to disable transactions. */ +#define PER_FLAG_NO_TE 1UL +/* Flag to enable random transaction aborts. */ +#define PER_FLAG_TE_ABORT_RAND 2UL +/* Flag to specify random transaction abort mode: + * - abort each transaction at a random instruction before TEND if set. + * - abort random transactions at a random instruction if cleared. + */ +#define PER_FLAG_TE_ABORT_RAND_TEND 4UL typedef struct thread_struct thread_struct; @@ -124,19 +157,17 @@ struct stack_frame { * Do necessary setup to start up a new thread. */ #define start_thread(regs, new_psw, new_stackp) do { \ - regs->psw.mask = psw_user_bits | PSW_MASK_EA | PSW_MASK_BA; \ + regs->psw.mask = PSW_USER_BITS | PSW_MASK_EA | PSW_MASK_BA; \ regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ regs->gprs[15] = new_stackp; \ execve_tail(); \ } while (0) #define start_thread31(regs, new_psw, new_stackp) do { \ - regs->psw.mask = psw_user_bits | PSW_MASK_BA; \ + regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ regs->gprs[15] = new_stackp; \ - __tlb_flush_mm(current->mm); \ crst_table_downgrade(current->mm, 1UL << 31); \ - update_mm(current->mm, current); \ execve_tail(); \ } while (0) @@ -159,16 +190,15 @@ extern void release_thread(struct task_struct *); */ extern unsigned long thread_saved_pc(struct task_struct *t); -extern void show_code(struct pt_regs *regs); -extern void print_fn_code(unsigned char *code, unsigned long len); -extern int insn_to_mnemonic(unsigned char *instruction, char buf[8]); - unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ (task_stack_page(tsk) + THREAD_SIZE) - 1) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->psw.addr) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->gprs[15]) +/* Has task runtime instrumentation enabled ? */ +#define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) + static inline unsigned short stap(void) { unsigned short cpu_address; @@ -187,6 +217,8 @@ static inline void cpu_relax(void) barrier(); } +#define arch_mutex_cpu_relax() barrier() + static inline void psw_set_key(unsigned int key) { asm volatile("spka 0(%0)" : : "d" (key)); @@ -335,9 +367,9 @@ __set_psw_mask(unsigned long mask) } #define local_mcck_enable() \ - __set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK) + __set_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK) #define local_mcck_disable() \ - __set_psw_mask(psw_kernel_bits | PSW_MASK_DAT) + __set_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT) /* * Basic Machine Check/Program Check Handler. diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 3ee5da3bc10..55d69dd7473 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -8,12 +8,63 @@ #include <uapi/asm/ptrace.h> +#define PIF_SYSCALL 0 /* inside a system call */ +#define PIF_PER_TRAP 1 /* deliver sigtrap on return to user */ + +#define _PIF_SYSCALL (1<<PIF_SYSCALL) +#define _PIF_PER_TRAP (1<<PIF_PER_TRAP) + #ifndef __ASSEMBLY__ -#ifndef __s390x__ -#else /* __s390x__ */ -#endif /* __s390x__ */ -extern long psw_kernel_bits; -extern long psw_user_bits; + +#define PSW_KERNEL_BITS (PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_HOME | \ + PSW_MASK_EA | PSW_MASK_BA) +#define PSW_USER_BITS (PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | \ + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | \ + PSW_MASK_PSTATE | PSW_ASC_PRIMARY) + +struct psw_bits { + unsigned long long : 1; + unsigned long long r : 1; /* PER-Mask */ + unsigned long long : 3; + unsigned long long t : 1; /* DAT Mode */ + unsigned long long i : 1; /* Input/Output Mask */ + unsigned long long e : 1; /* External Mask */ + unsigned long long key : 4; /* PSW Key */ + unsigned long long : 1; + unsigned long long m : 1; /* Machine-Check Mask */ + unsigned long long w : 1; /* Wait State */ + unsigned long long p : 1; /* Problem State */ + unsigned long long as : 2; /* Address Space Control */ + unsigned long long cc : 2; /* Condition Code */ + unsigned long long pm : 4; /* Program Mask */ + unsigned long long ri : 1; /* Runtime Instrumentation */ + unsigned long long : 6; + unsigned long long eaba : 2; /* Addressing Mode */ +#ifdef CONFIG_64BIT + unsigned long long : 31; + unsigned long long ia : 64;/* Instruction Address */ +#else + unsigned long long ia : 31;/* Instruction Address */ +#endif +}; + +enum { + PSW_AMODE_24BIT = 0, + PSW_AMODE_31BIT = 1, + PSW_AMODE_64BIT = 3 +}; + +enum { + PSW_AS_PRIMARY = 0, + PSW_AS_ACCREG = 1, + PSW_AS_SECONDARY = 2, + PSW_AS_HOME = 3 +}; + +#define psw_bits(__psw) (*({ \ + typecheck(psw_t, __psw); \ + &(*(struct psw_bits *)(&(__psw))); \ +})) /* * The pt_regs struct defines the way the registers are stored on @@ -26,7 +77,9 @@ struct pt_regs unsigned long gprs[NUM_GPRS]; unsigned long orig_gpr2; unsigned int int_code; + unsigned int int_parm; unsigned long int_parm_long; + unsigned long flags; }; /* @@ -77,12 +130,26 @@ struct per_struct_kernel { #define PER_CONTROL_SUSPENSION 0x00400000UL #define PER_CONTROL_ALTERATION 0x00200000UL -#ifdef __s390x__ -#endif /* __s390x__ */ +static inline void set_pt_regs_flag(struct pt_regs *regs, int flag) +{ + regs->flags |= (1U << flag); +} + +static inline void clear_pt_regs_flag(struct pt_regs *regs, int flag) +{ + regs->flags &= ~(1U << flag); +} + +static inline int test_pt_regs_flag(struct pt_regs *regs, int flag) +{ + return !!(regs->flags & (1U << flag)); +} + /* * 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 833788693f0..1aba89b53cb 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -8,6 +8,7 @@ #include <linux/types.h> #include <asm/chpid.h> +#include <asm/cpu.h> #define SCLP_CHP_INFO_MASK_SIZE 32 @@ -27,7 +28,11 @@ struct sclp_ipl_info { struct sclp_cpu_entry { u8 address; - u8 reserved0[13]; + u8 reserved0[2]; + u8 : 3; + u8 siif : 1; + u8 : 4; + u8 reserved2[10]; u8 type; u8 reserved1; } __attribute__((packed)); @@ -37,25 +42,30 @@ struct sclp_cpu_info { unsigned int standby; unsigned int combined; int has_cpu_type; - struct sclp_cpu_entry cpu[255]; + struct sclp_cpu_entry cpu[MAX_CPU_ADDRESS + 1]; }; int sclp_get_cpu_info(struct sclp_cpu_info *info); int sclp_cpu_configure(u8 cpu); int sclp_cpu_deconfigure(u8 cpu); -void sclp_facilities_detect(void); unsigned long long sclp_get_rnmax(void); unsigned long long sclp_get_rzm(void); -u8 sclp_get_fac85(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); +unsigned long sclp_get_hsa_size(void); +void sclp_early_detect(void); +int sclp_has_siif(void); +unsigned int sclp_get_ibc(void); #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/serial.h b/arch/s390/include/asm/serial.h new file mode 100644 index 00000000000..5b3e48ef534 --- /dev/null +++ b/arch/s390/include/asm/serial.h @@ -0,0 +1,6 @@ +#ifndef _ASM_S390_SERIAL_H +#define _ASM_S390_SERIAL_H + +#define BASE_BAUD 0 + +#endif /* _ASM_S390_SERIAL_H */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index f69f76b3447..089a49814c5 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -9,7 +9,6 @@ #define PARMAREA 0x10400 -#define MEMORY_CHUNKS 256 #ifndef __ASSEMBLY__ @@ -31,32 +30,11 @@ #endif /* CONFIG_64BIT */ #define COMMAND_LINE ((char *) (0x10480)) -#define CHUNK_READ_WRITE 0 -#define CHUNK_READ_ONLY 1 -#define CHUNK_OLDMEM 4 -#define CHUNK_CRASHK 5 - -struct mem_chunk { - unsigned long addr; - unsigned long size; - int type; -}; - -extern struct mem_chunk memory_chunk[]; -extern unsigned long real_memory_size; extern int memory_end_set; extern unsigned long memory_end; +extern unsigned long max_physmem_end; -void detect_memory_layout(struct mem_chunk chunk[]); -void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr, - unsigned long size, int type); - -#define PRIMARY_SPACE_MODE 0 -#define ACCESS_REGISTER_MODE 1 -#define SECONDARY_SPACE_MODE 2 -#define HOME_SPACE_MODE 3 - -extern unsigned int s390_user_mode; +extern void detect_memory_memblock(void); /* * Machine features detected in head.S @@ -64,26 +42,28 @@ extern unsigned int s390_user_mode; #define MACHINE_FLAG_VM (1UL << 0) #define MACHINE_FLAG_IEEE (1UL << 1) -#define MACHINE_FLAG_CSP (1UL << 3) -#define MACHINE_FLAG_MVPG (1UL << 4) -#define MACHINE_FLAG_DIAG44 (1UL << 5) -#define MACHINE_FLAG_IDTE (1UL << 6) -#define MACHINE_FLAG_DIAG9C (1UL << 7) -#define MACHINE_FLAG_MVCOS (1UL << 8) -#define MACHINE_FLAG_KVM (1UL << 9) +#define MACHINE_FLAG_CSP (1UL << 2) +#define MACHINE_FLAG_MVPG (1UL << 3) +#define MACHINE_FLAG_DIAG44 (1UL << 4) +#define MACHINE_FLAG_IDTE (1UL << 5) +#define MACHINE_FLAG_DIAG9C (1UL << 6) +#define MACHINE_FLAG_KVM (1UL << 8) +#define MACHINE_FLAG_ESOP (1UL << 9) #define MACHINE_FLAG_EDAT1 (1UL << 10) #define MACHINE_FLAG_EDAT2 (1UL << 11) #define MACHINE_FLAG_LPAR (1UL << 12) -#define MACHINE_FLAG_SPP (1UL << 13) +#define MACHINE_FLAG_LPP (1UL << 13) #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) #define MACHINE_IS_LPAR (S390_lowcore.machine_flags & MACHINE_FLAG_LPAR) #define MACHINE_HAS_DIAG9C (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C) +#define MACHINE_HAS_ESOP (S390_lowcore.machine_flags & MACHINE_FLAG_ESOP) #define MACHINE_HAS_PFMF MACHINE_HAS_EDAT1 #define MACHINE_HAS_HPAGE MACHINE_HAS_EDAT1 @@ -93,31 +73,28 @@ extern unsigned int s390_user_mode; #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_SPP (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_SPP (S390_lowcore.machine_flags & MACHINE_FLAG_SPP) +#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 */ -#define ZFCPDUMP_HSA_SIZE (32UL<<20) -#define ZFCPDUMP_HSA_SIZE_MAX (64UL<<20) - /* * Console mode. Override with conmode= */ diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h index db7ddfaf5b7..abf9e573594 100644 --- a/arch/s390/include/asm/signal.h +++ b/arch/s390/include/asm/signal.h @@ -21,22 +21,5 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; -struct old_sigaction { - __sighandler_t sa_handler; - old_sigset_t sa_mask; - unsigned long sa_flags; - void (*sa_restorer)(void); -}; - -struct sigaction { - __sighandler_t sa_handler; - unsigned long sa_flags; - void (*sa_restorer)(void); - sigset_t sa_mask; /* mask last for extensibility */ -}; - -struct k_sigaction { - struct sigaction sa; -}; - +#define __ARCH_HAS_SA_RESTORER #endif diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h index 5a87d16d3e7..bf9c823d402 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 */ @@ -29,4 +31,23 @@ #define SIGP_STATUS_INCORRECT_STATE 0x00000200UL #define SIGP_STATUS_NOT_RUNNING 0x00000400UL +#ifndef __ASSEMBLY__ + +static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status) +{ + register unsigned int reg1 asm ("1") = parm; + int cc; + + asm volatile( + " sigp %1,%2,0(%3)\n" + " ipm %0\n" + " srl %0,28\n" + : "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc"); + if (status && cc == 1) + *status = reg1; + return cc; +} + +#endif /* __ASSEMBLY__ */ + #endif /* __S390_ASM_SIGP_H */ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index b64f15c3b4c..4f1307962a9 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -7,6 +7,8 @@ #ifndef __ASM_SMP_H #define __ASM_SMP_H +#include <asm/sigp.h> + #ifdef CONFIG_SMP #include <asm/lowcore.h> @@ -14,7 +16,6 @@ #define raw_smp_processor_id() (S390_lowcore.cpu_nr) extern struct mutex smp_cpu_state_mutex; -extern struct save_area *zfcpdump_save_areas[NR_CPUS + 1]; extern int __cpu_up(unsigned int cpu, struct task_struct *tidle); @@ -29,9 +30,9 @@ extern int smp_store_status(int cpu); extern int smp_vcpu_scheduled(int cpu); extern void smp_yield_cpu(int cpu); extern void smp_yield(void); -extern void smp_stop_cpu(void); extern void smp_cpu_set_polarization(int cpu, int val); extern int smp_cpu_get_polarization(int cpu); +extern void smp_fill_possible_mask(void); #else /* CONFIG_SMP */ @@ -50,10 +51,20 @@ static inline int smp_store_status(int cpu) { return 0; } static inline int smp_vcpu_scheduled(int cpu) { return 1; } static inline void smp_yield_cpu(int cpu) { } static inline void smp_yield(void) { } -static inline void smp_stop_cpu(void) { } +static inline void smp_fill_possible_mask(void) { } #endif /* CONFIG_SMP */ +static inline void smp_stop_cpu(void) +{ + u16 pcpu = stap(); + + for (;;) { + __pcpu_sigp(pcpu, SIGP_STOP, 0, NULL); + cpu_relax(); + } +} + #ifdef CONFIG_HOTPLUG_CPU extern int smp_rescan_cpus(void); extern void __noreturn cpu_die(void); diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 701fe8c59e1..96879f7ad6d 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -11,18 +11,21 @@ #include <linux/smp.h> +#define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval) + extern int spin_retry; static inline int -_raw_compare_and_swap(volatile unsigned int *lock, - unsigned int old, unsigned int new) +_raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new) { + unsigned int old_expected = old; + asm volatile( " cs %0,%3,%1" : "=d" (old), "=Q" (*lock) : "0" (old), "d" (new), "Q" (*lock) : "cc", "memory" ); - return old; + return old == old_expected; } /* @@ -34,52 +37,69 @@ _raw_compare_and_swap(volatile unsigned int *lock, * (the type definitions are in asm/spinlock_types.h) */ -#define arch_spin_is_locked(x) ((x)->owner_cpu != 0) -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) \ - arch_spin_relax(lock); } while (0) +void arch_spin_lock_wait(arch_spinlock_t *); +int arch_spin_trylock_retry(arch_spinlock_t *); +void arch_spin_relax(arch_spinlock_t *); +void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags); -extern void arch_spin_lock_wait(arch_spinlock_t *); -extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags); -extern int arch_spin_trylock_retry(arch_spinlock_t *); -extern void arch_spin_relax(arch_spinlock_t *lock); +static inline u32 arch_spin_lockval(int cpu) +{ + return ~cpu; +} -static inline void arch_spin_lock(arch_spinlock_t *lp) +static inline int arch_spin_value_unlocked(arch_spinlock_t lock) { - int old; + return lock.lock == 0; +} - old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); - if (likely(old == 0)) - return; - arch_spin_lock_wait(lp); +static inline int arch_spin_is_locked(arch_spinlock_t *lp) +{ + return ACCESS_ONCE(lp->lock) != 0; } -static inline void arch_spin_lock_flags(arch_spinlock_t *lp, - unsigned long flags) +static inline int arch_spin_trylock_once(arch_spinlock_t *lp) { - int old; + barrier(); + return likely(arch_spin_value_unlocked(*lp) && + _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL)); +} - old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); - if (likely(old == 0)) - return; - arch_spin_lock_wait_flags(lp, flags); +static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp) +{ + return _raw_compare_and_swap(&lp->lock, SPINLOCK_LOCKVAL, 0); } -static inline int arch_spin_trylock(arch_spinlock_t *lp) +static inline void arch_spin_lock(arch_spinlock_t *lp) { - int old; + if (!arch_spin_trylock_once(lp)) + arch_spin_lock_wait(lp); +} - old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id()); - if (likely(old == 0)) - return 1; - return arch_spin_trylock_retry(lp); +static inline void arch_spin_lock_flags(arch_spinlock_t *lp, + unsigned long flags) +{ + if (!arch_spin_trylock_once(lp)) + arch_spin_lock_wait_flags(lp, flags); +} + +static inline int arch_spin_trylock(arch_spinlock_t *lp) +{ + if (!arch_spin_trylock_once(lp)) + return arch_spin_trylock_retry(lp); + return 1; } static inline void arch_spin_unlock(arch_spinlock_t *lp) { - _raw_compare_and_swap(&lp->owner_cpu, lp->owner_cpu, 0); + arch_spin_tryrelease_once(lp); +} + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + while (arch_spin_is_locked(lock)) + arch_spin_relax(lock); } - + /* * Read-write spinlocks, allowing multiple readers * but only one writer. @@ -110,42 +130,50 @@ extern void _raw_write_lock_wait(arch_rwlock_t *lp); extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags); extern int _raw_write_trylock_retry(arch_rwlock_t *lp); +static inline int arch_read_trylock_once(arch_rwlock_t *rw) +{ + unsigned int old = ACCESS_ONCE(rw->lock); + return likely((int) old >= 0 && + _raw_compare_and_swap(&rw->lock, old, old + 1)); +} + +static inline int arch_write_trylock_once(arch_rwlock_t *rw) +{ + unsigned int old = ACCESS_ONCE(rw->lock); + return likely(old == 0 && + _raw_compare_and_swap(&rw->lock, 0, 0x80000000)); +} + static inline void arch_read_lock(arch_rwlock_t *rw) { - unsigned int old; - old = rw->lock & 0x7fffffffU; - if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old) + if (!arch_read_trylock_once(rw)) _raw_read_lock_wait(rw); } static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags) { - unsigned int old; - old = rw->lock & 0x7fffffffU; - if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old) + if (!arch_read_trylock_once(rw)) _raw_read_lock_wait_flags(rw, flags); } static inline void arch_read_unlock(arch_rwlock_t *rw) { - unsigned int old, cmp; + unsigned int old; - old = rw->lock; do { - cmp = old; - old = _raw_compare_and_swap(&rw->lock, old, old - 1); - } while (cmp != old); + old = ACCESS_ONCE(rw->lock); + } while (!_raw_compare_and_swap(&rw->lock, old, old - 1)); } static inline void arch_write_lock(arch_rwlock_t *rw) { - if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0)) + if (!arch_write_trylock_once(rw)) _raw_write_lock_wait(rw); } static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags) { - if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0)) + if (!arch_write_trylock_once(rw)) _raw_write_lock_wait_flags(rw, flags); } @@ -156,18 +184,16 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) static inline int arch_read_trylock(arch_rwlock_t *rw) { - unsigned int old; - old = rw->lock & 0x7fffffffU; - if (likely(_raw_compare_and_swap(&rw->lock, old, old + 1) == old)) - return 1; - return _raw_read_trylock_retry(rw); + if (!arch_read_trylock_once(rw)) + return _raw_read_trylock_retry(rw); + return 1; } static inline int arch_write_trylock(arch_rwlock_t *rw) { - if (likely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0)) - return 1; - return _raw_write_trylock_retry(rw); + if (!arch_write_trylock_once(rw)) + return _raw_write_trylock_retry(rw); + return 1; } #define arch_read_relax(lock) cpu_relax() diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h index 9c76656a0af..b2cd6ff7c2c 100644 --- a/arch/s390/include/asm/spinlock_types.h +++ b/arch/s390/include/asm/spinlock_types.h @@ -6,13 +6,13 @@ #endif typedef struct { - volatile unsigned int owner_cpu; + unsigned int lock; } __attribute__ ((aligned (4))) arch_spinlock_t; -#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } +#define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0, } typedef struct { - volatile unsigned int lock; + unsigned int lock; } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED { 0 } diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index f3a9e0f9270..18ea9e3f814 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -8,91 +8,130 @@ #define __ASM_SWITCH_TO_H #include <linux/thread_info.h> +#include <asm/ptrace.h> extern struct task_struct *__switch_to(void *, void *); -extern void update_per_regs(struct task_struct *task); +extern void update_cr_regs(struct task_struct *task); -static inline void save_fp_regs(s390_fp_regs *fpregs) +static inline int test_fp_ctl(u32 fpc) { + u32 orig_fpc; + int rc; + + if (!MACHINE_HAS_IEEE) + return 0; + asm volatile( - " std 0,%O0+8(%R0)\n" - " std 2,%O0+24(%R0)\n" - " std 4,%O0+40(%R0)\n" - " std 6,%O0+56(%R0)" - : "=Q" (*fpregs) : "Q" (*fpregs)); + " efpc %1\n" + " sfpc %2\n" + "0: sfpc %1\n" + " la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc), "=d" (orig_fpc) + : "d" (fpc), "0" (-EINVAL)); + return rc; +} + +static inline void save_fp_ctl(u32 *fpc) +{ if (!MACHINE_HAS_IEEE) return; + asm volatile( - " stfpc %0\n" - " std 1,%O0+16(%R0)\n" - " std 3,%O0+32(%R0)\n" - " std 5,%O0+48(%R0)\n" - " std 7,%O0+64(%R0)\n" - " std 8,%O0+72(%R0)\n" - " std 9,%O0+80(%R0)\n" - " std 10,%O0+88(%R0)\n" - " std 11,%O0+96(%R0)\n" - " std 12,%O0+104(%R0)\n" - " std 13,%O0+112(%R0)\n" - " std 14,%O0+120(%R0)\n" - " std 15,%O0+128(%R0)\n" - : "=Q" (*fpregs) : "Q" (*fpregs)); + " stfpc %0\n" + : "+Q" (*fpc)); } -static inline void restore_fp_regs(s390_fp_regs *fpregs) +static inline int restore_fp_ctl(u32 *fpc) { + int rc; + + if (!MACHINE_HAS_IEEE) + return 0; + asm volatile( - " ld 0,%O0+8(%R0)\n" - " ld 2,%O0+24(%R0)\n" - " ld 4,%O0+40(%R0)\n" - " ld 6,%O0+56(%R0)" - : : "Q" (*fpregs)); + " lfpc %1\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "Q" (*fpc), "0" (-EINVAL)); + return rc; +} + +static inline void save_fp_regs(freg_t *fprs) +{ + asm volatile("std 0,%0" : "=Q" (fprs[0])); + asm volatile("std 2,%0" : "=Q" (fprs[2])); + asm volatile("std 4,%0" : "=Q" (fprs[4])); + asm volatile("std 6,%0" : "=Q" (fprs[6])); if (!MACHINE_HAS_IEEE) return; - asm volatile( - " lfpc %0\n" - " ld 1,%O0+16(%R0)\n" - " ld 3,%O0+32(%R0)\n" - " ld 5,%O0+48(%R0)\n" - " ld 7,%O0+64(%R0)\n" - " ld 8,%O0+72(%R0)\n" - " ld 9,%O0+80(%R0)\n" - " ld 10,%O0+88(%R0)\n" - " ld 11,%O0+96(%R0)\n" - " ld 12,%O0+104(%R0)\n" - " ld 13,%O0+112(%R0)\n" - " ld 14,%O0+120(%R0)\n" - " ld 15,%O0+128(%R0)\n" - : : "Q" (*fpregs)); + asm volatile("std 1,%0" : "=Q" (fprs[1])); + asm volatile("std 3,%0" : "=Q" (fprs[3])); + asm volatile("std 5,%0" : "=Q" (fprs[5])); + asm volatile("std 7,%0" : "=Q" (fprs[7])); + asm volatile("std 8,%0" : "=Q" (fprs[8])); + asm volatile("std 9,%0" : "=Q" (fprs[9])); + asm volatile("std 10,%0" : "=Q" (fprs[10])); + asm volatile("std 11,%0" : "=Q" (fprs[11])); + asm volatile("std 12,%0" : "=Q" (fprs[12])); + asm volatile("std 13,%0" : "=Q" (fprs[13])); + asm volatile("std 14,%0" : "=Q" (fprs[14])); + asm volatile("std 15,%0" : "=Q" (fprs[15])); +} + +static inline void restore_fp_regs(freg_t *fprs) +{ + asm volatile("ld 0,%0" : : "Q" (fprs[0])); + asm volatile("ld 2,%0" : : "Q" (fprs[2])); + asm volatile("ld 4,%0" : : "Q" (fprs[4])); + asm volatile("ld 6,%0" : : "Q" (fprs[6])); + if (!MACHINE_HAS_IEEE) + return; + asm volatile("ld 1,%0" : : "Q" (fprs[1])); + asm volatile("ld 3,%0" : : "Q" (fprs[3])); + asm volatile("ld 5,%0" : : "Q" (fprs[5])); + asm volatile("ld 7,%0" : : "Q" (fprs[7])); + asm volatile("ld 8,%0" : : "Q" (fprs[8])); + asm volatile("ld 9,%0" : : "Q" (fprs[9])); + asm volatile("ld 10,%0" : : "Q" (fprs[10])); + asm volatile("ld 11,%0" : : "Q" (fprs[11])); + asm volatile("ld 12,%0" : : "Q" (fprs[12])); + asm volatile("ld 13,%0" : : "Q" (fprs[13])); + asm volatile("ld 14,%0" : : "Q" (fprs[14])); + asm volatile("ld 15,%0" : : "Q" (fprs[15])); } static inline void save_access_regs(unsigned int *acrs) { - asm volatile("stam 0,15,%0" : "=Q" (*acrs)); + typedef struct { int _[NUM_ACRS]; } acrstype; + + asm volatile("stam 0,15,%0" : "=Q" (*(acrstype *)acrs)); } static inline void restore_access_regs(unsigned int *acrs) { - asm volatile("lam 0,15,%0" : : "Q" (*acrs)); + typedef struct { int _[NUM_ACRS]; } acrstype; + + asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs)); } #define switch_to(prev,next,last) do { \ if (prev->mm) { \ - save_fp_regs(&prev->thread.fp_regs); \ + save_fp_ctl(&prev->thread.fp_regs.fpc); \ + save_fp_regs(prev->thread.fp_regs.fprs); \ save_access_regs(&prev->thread.acrs[0]); \ save_ri_cb(prev->thread.ri_cb); \ } \ if (next->mm) { \ - restore_fp_regs(&next->thread.fp_regs); \ + restore_fp_ctl(&next->thread.fp_regs.fpc); \ + restore_fp_regs(next->thread.fp_regs.fprs); \ restore_access_regs(&next->thread.acrs[0]); \ restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ - update_per_regs(next); \ + update_cr_regs(next); \ } \ prev = __switch_to(prev,next); \ } while (0) -#define finish_arch_switch(prev) do { \ - set_fs(current->thread.mm_segment); \ -} while (0) - #endif /* __ASM_SWITCH_TO_H */ diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index fe7b99759e1..abad78d5b10 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -12,7 +12,7 @@ #ifndef _ASM_SYSCALL_H #define _ASM_SYSCALL_H 1 -#include <linux/audit.h> +#include <uapi/linux/audit.h> #include <linux/sched.h> #include <linux/err.h> #include <asm/ptrace.h> @@ -23,11 +23,12 @@ * type here is what we want [need] for both 32 bit and 64 bit systems. */ extern const unsigned int sys_call_table[]; +extern const unsigned int sys_call_table_emu[]; static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return test_tsk_thread_flag(task, TIF_SYSCALL) ? + return test_pt_regs_flag(regs, PIF_SYSCALL) ? (regs->int_code & 0xffff) : -1; } @@ -88,11 +89,10 @@ static inline void syscall_set_arguments(struct task_struct *task, regs->orig_gpr2 = args[0]; } -static inline int syscall_get_arch(struct task_struct *task, - struct pt_regs *regs) +static inline int syscall_get_arch(void) { #ifdef CONFIG_COMPAT - if (test_tsk_thread_flag(task, TIF_31BIT)) + if (test_tsk_thread_flag(current, TIF_31BIT)) return AUDIT_ARCH_S390; #endif return sizeof(long) == 8 ? AUDIT_ARCH_S390X : AUDIT_ARCH_S390; diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 9e2cfe0349c..b833e9c0bfb 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,13 +14,8 @@ #define THREAD_ORDER 1 #define ASYNC_ORDER 1 #else /* CONFIG_64BIT */ -#ifndef __SMALL_STACK #define THREAD_ORDER 2 #define ASYNC_ORDER 2 -#else -#define THREAD_ORDER 1 -#define ASYNC_ORDER 1 -#endif #endif /* CONFIG_64BIT */ #define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER) @@ -41,6 +36,7 @@ struct thread_info { struct task_struct *task; /* main task structure */ struct exec_domain *exec_domain; /* execution domain */ unsigned long flags; /* low level flags */ + unsigned long sys_call_table; /* System call table address */ unsigned int cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ struct restart_block restart_block; @@ -81,27 +77,22 @@ static inline struct thread_info *current_thread_info(void) /* * thread information flags bit numbers */ -#define TIF_SYSCALL 0 /* inside a system call */ -#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ -#define TIF_SIGPENDING 2 /* signal pending */ -#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ -#define TIF_PER_TRAP 6 /* deliver sigtrap on return to user */ -#define TIF_MCCK_PENDING 7 /* machine check handling is pending */ -#define TIF_SYSCALL_TRACE 8 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ -#define TIF_SECCOMP 10 /* secure computing */ -#define TIF_SYSCALL_TRACEPOINT 11 /* syscall tracepoint instrumentation */ -#define TIF_31BIT 17 /* 32bit process */ -#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_NOTIFY_RESUME 0 /* callback before returning to user */ +#define TIF_SIGPENDING 1 /* signal pending */ +#define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_SYSCALL_TRACE 3 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 4 /* syscall auditing active */ +#define TIF_SECCOMP 5 /* secure computing */ +#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ +#define TIF_31BIT 16 /* 32bit process */ +#define TIF_MEMDIE 17 /* is terminating due to OOM killer */ +#define TIF_RESTORE_SIGMASK 18 /* restore signal mask in do_signal() */ +#define TIF_SINGLE_STEP 19 /* This task is single stepped */ +#define TIF_BLOCK_STEP 20 /* 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_PER_TRAP (1<<TIF_PER_TRAP) -#define _TIF_MCCK_PENDING (1<<TIF_MCCK_PENDING) #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1<<TIF_SECCOMP) @@ -115,6 +106,4 @@ static inline struct thread_info *current_thread_info(void) #define is_32bit_task() (1) #endif -#define PREEMPT_ACTIVE 0x4000000 - #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 4c060bb5b8e..8beee1cceba 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -15,7 +15,7 @@ #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL /* Inline functions for clock register access. */ -static inline int set_clock(__u64 time) +static inline int set_tod_clock(__u64 time) { int cc; @@ -27,7 +27,7 @@ static inline int set_clock(__u64 time) return cc; } -static inline int store_clock(__u64 *time) +static inline int store_tod_clock(__u64 *time) { int cc; @@ -71,33 +71,35 @@ static inline void local_tick_enable(unsigned long long comp) typedef unsigned long long cycles_t; -static inline unsigned long long get_clock(void) +static inline void get_tod_clock_ext(char clk[16]) { - unsigned long long clk; + typedef struct { char _[sizeof(clk)]; } addrtype; -#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES - asm volatile(".insn s,0xb27c0000,%0" : "=Q" (clk) : : "cc"); -#else - asm volatile("stck %0" : "=Q" (clk) : : "cc"); -#endif - return clk; + asm volatile("stcke %0" : "=Q" (*(addrtype *) clk) : : "cc"); } -static inline void get_clock_ext(char *clk) +static inline unsigned long long get_tod_clock(void) { - asm volatile("stcke %0" : "=Q" (*clk) : : "cc"); + unsigned char clk[16]; + get_tod_clock_ext(clk); + return *((unsigned long long *)&clk[1]); } -static inline unsigned long long get_clock_xt(void) +static inline unsigned long long get_tod_clock_fast(void) { - unsigned char clk[16]; - get_clock_ext(clk); - return *((unsigned long long *)&clk[1]); +#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES + unsigned long long clk; + + asm volatile("stckf %0" : "=Q" (clk) : : "cc"); + return clk; +#else + return get_tod_clock(); +#endif } static inline cycles_t get_cycles(void) { - return (cycles_t) get_clock() >> 2; + return (cycles_t) get_tod_clock() >> 2; } int get_sync_clock(unsigned long long *clock); @@ -123,9 +125,9 @@ extern u64 sched_clock_base_cc; * function, otherwise the returned value is not guaranteed to * be monotonic. */ -static inline unsigned long long get_clock_monotonic(void) +static inline unsigned long long get_tod_clock_monotonic(void) { - return get_clock_xt() - sched_clock_base_cc; + return get_tod_clock() - sched_clock_base_cc; } /** diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index b75d7d68668..a25f09fbaf3 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -32,6 +32,7 @@ struct mmu_gather { struct mm_struct *mm; struct mmu_table_batch *batch; unsigned int fullmm; + unsigned long start, end; }; struct mmu_table_batch { @@ -48,24 +49,37 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table); static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned int full_mm_flush) + unsigned long start, + unsigned long end) { tlb->mm = mm; - tlb->fullmm = full_mm_flush; + tlb->start = start; + 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) +static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) +{ + __tlb_flush_mm_lazy(tlb->mm); +} + +static inline void tlb_flush_mmu_free(struct mmu_gather *tlb) { tlb_table_flush(tlb); } + +static inline void tlb_flush_mmu(struct mmu_gather *tlb) +{ + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); +} + static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - tlb_table_flush(tlb); + tlb_flush_mmu(tlb); } /* @@ -91,9 +105,7 @@ 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); } /* @@ -109,9 +121,7 @@ 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 } @@ -128,9 +138,7 @@ 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 1d8fe2b17ef..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"); @@ -42,53 +64,104 @@ 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) { - if (unlikely(cpumask_empty(mm_cpumask(mm)))) - return; /* * If the machine has IDTE we prefer to do a per mm flush * on all cpus instead of doing a local flush if the 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); } -static inline void __tlb_flush_mm_cond(struct mm_struct * mm) +static inline void __tlb_flush_mm_lazy(struct mm_struct * mm) { if (mm->context.flush_mm) { __tlb_flush_mm(mm); @@ -120,19 +193,19 @@ static inline void __tlb_flush_mm_cond(struct mm_struct * mm) static inline void flush_tlb_mm(struct mm_struct *mm) { - __tlb_flush_mm_cond(mm); + __tlb_flush_mm_lazy(mm); } static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - __tlb_flush_mm_cond(vma->vm_mm); + __tlb_flush_mm_lazy(vma->vm_mm); } 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/topology.h b/arch/s390/include/asm/topology.h index 05425b18c0a..56af53093d2 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -26,21 +26,12 @@ extern struct cpu_topology_s390 cpu_topology[NR_CPUS]; #define mc_capable() 1 -static inline const struct cpumask *cpu_coregroup_mask(int cpu) -{ - return &cpu_topology[cpu].core_mask; -} - -static inline const struct cpumask *cpu_book_mask(int cpu) -{ - return &cpu_topology[cpu].book_mask; -} - int topology_cpu_init(struct cpu *); int topology_set_cpu_management(int fc); void topology_schedule_update(void); void store_topology(struct sysinfo_15_1_x *info); void topology_expect_change(void); +const struct cpumask *cpu_coregroup_mask(int cpu); #else /* CONFIG_SCHED_BOOK */ @@ -64,8 +55,6 @@ static inline void s390_init_cpu_topology(void) }; #endif -#define SD_BOOK_INIT SD_CPU_INIT - #include <asm-generic/topology.h> #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 34268df959a..cd4c68e0398 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -92,39 +92,88 @@ 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_from_user_small)(size_t, const void __user *, void *); - size_t (*copy_to_user)(size_t, void __user *, const void *); - size_t (*copy_to_user_small)(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_std; -extern struct uaccess_ops uaccess_mvcos; -extern struct uaccess_ops uaccess_mvcos_switch; -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); + +#define __copy_to_user_inatomic __copy_to_user +#define __copy_from_user_inatomic __copy_from_user + +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + +#define __put_get_user_asm(to, from, size, spec) \ +({ \ + register unsigned long __reg0 asm("0") = spec; \ + int __rc; \ + \ + asm volatile( \ + "0: mvcos %1,%3,%2\n" \ + "1: xr %0,%0\n" \ + "2:\n" \ + ".pushsection .fixup, \"ax\"\n" \ + "3: lhi %0,%5\n" \ + " jg 2b\n" \ + ".popsection\n" \ + EX_TABLE(0b,3b) EX_TABLE(1b,3b) \ + : "=d" (__rc), "=Q" (*(to)) \ + : "d" (size), "Q" (*(from)), \ + "d" (__reg0), "K" (-EFAULT) \ + : "cc"); \ + __rc; \ +}) + +#define __put_user_fn(x, ptr, size) __put_get_user_asm(ptr, x, size, 0x810000UL) +#define __get_user_fn(x, ptr, size) __put_get_user_asm(x, ptr, size, 0x81UL) -extern int __handle_fault(unsigned long, unsigned long, int); +#else /* CONFIG_HAVE_MARCH_Z10_FEATURES */ -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_small(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_small(size, ptr, x); - return size ? -EFAULT : size; + size = __copy_from_user(x, ptr, size); + return size ? -EFAULT : 0; } +#endif /* CONFIG_HAVE_MARCH_Z10_FEATURES */ + /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. @@ -139,8 +188,8 @@ 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(); \ @@ -156,7 +205,7 @@ 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) \ ({ \ @@ -165,29 +214,29 @@ 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; \ }; \ @@ -204,38 +253,12 @@ 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) -{ - if (__builtin_constant_p(n) && (n <= 256)) - return uaccess.copy_to_user_small(n, to, from); - else - 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. @@ -252,38 +275,10 @@ static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); - if (access_ok(VERIFY_WRITE, to, n)) - n = __copy_to_user(to, from, n); - return 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) -{ - if (__builtin_constant_p(n) && (n <= 256)) - return uaccess.copy_from_user_small(n, from, to); - else - 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 @@ -315,46 +310,38 @@ copy_from_user(void *to, const void __user *from, unsigned long n) copy_from_user_overflow(); return n; } - if (access_ok(VERIFY_READ, from, n)) - n = __copy_from_user(to, from, n); - else - memset(to, 0, n); - return 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) { might_fault(); - if (__access_ok(from,n) && __access_ok(to,n)) - n = __copy_in_user(to, from, n); - return n; + return __copy_in_user(to, from, 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) { - long res = -EFAULT; might_fault(); - if (access_ok(VERIFY_READ, src, 1)) - res = uaccess.strncpy_from_user(count, src, dst); - return res; + 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); } /** @@ -376,23 +363,14 @@ 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(); - if (access_ok(VERIFY_WRITE, to, n)) - n = uaccess.clear_user(n, to); - return n; + 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/asm/unistd.h b/arch/s390/include/asm/unistd.h index 63653087251..65188635355 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -43,26 +43,15 @@ #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK -#define __ARCH_WANT_SYS_RT_SIGACTION -#define __ARCH_WANT_SYS_RT_SIGSUSPEND # ifndef CONFIG_64BIT # define __ARCH_WANT_STAT64 # define __ARCH_WANT_SYS_TIME # endif # ifdef CONFIG_COMPAT # define __ARCH_WANT_COMPAT_SYS_TIME -# define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND # endif #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE -/* - * "Conditional" syscalls - * - * What we want is __attribute__((weak,alias("sys_ni_syscall"))), - * but it doesn't work on all toolchains, so we just do it by hand - */ -#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") - #endif /* _ASM_S390_UNISTD_H_ */ diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index a73eb2e1e91..bc9746a7d47 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -26,8 +26,9 @@ struct vdso_data { __u64 wtom_clock_nsec; /* 0x28 */ __u32 tz_minuteswest; /* Minutes west of Greenwich 0x30 */ __u32 tz_dsttime; /* Type of dst correction 0x34 */ - __u32 ectg_available; - __u32 ntp_mult; /* NTP adjusted multiplier 0x3C */ + __u32 ectg_available; /* ECTG instruction present 0x38 */ + __u32 tk_mult; /* Mult. used for xtime_nsec 0x3c */ + __u32 tk_shift; /* Shift used for xtime_nsec 0x40 */ }; struct vdso_per_cpu_data { diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h new file mode 100644 index 00000000000..af9896c53eb --- /dev/null +++ b/arch/s390/include/asm/vtime.h @@ -0,0 +1,7 @@ +#ifndef _S390_VTIME_H +#define _S390_VTIME_H + +#define __ARCH_HAS_VTIME_ACCOUNT +#define __ARCH_HAS_VTIME_TASK_SWITCH + +#endif /* _S390_VTIME_H */ diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild index 7bf68fff7c5..736637363d3 100644 --- a/arch/s390/include/uapi/asm/Kbuild +++ b/arch/s390/include/uapi/asm/Kbuild @@ -35,6 +35,8 @@ header-y += siginfo.h header-y += signal.h header-y += socket.h header-y += sockios.h +header-y += sclp_ctl.h +header-y += sie.h header-y += stat.h header-y += statfs.h header-y += swab.h @@ -44,5 +46,6 @@ header-y += termios.h header-y += types.h header-y += ucontext.h header-y += unistd.h +header-y += virtio-ccw.h header-y += vtoc.h header-y += zcrypt.h diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h index 1c6a7f85a58..65dc694725a 100644 --- a/arch/s390/include/uapi/asm/chsc.h +++ b/arch/s390/include/uapi/asm/chsc.h @@ -29,6 +29,16 @@ struct chsc_async_area { __u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)]; } __attribute__ ((packed)); +struct chsc_header { + __u16 length; + __u16 code; +} __attribute__ ((packed)); + +struct chsc_sync_area { + struct chsc_header header; + __u8 data[CHSC_SIZE - sizeof(struct chsc_header)]; +} __attribute__ ((packed)); + struct chsc_response_struct { __u16 length; __u16 code; @@ -126,5 +136,8 @@ struct chsc_cpd_info { #define CHSC_INFO_CCL _IOWR(CHSC_IOCTL_MAGIC, 0x86, struct chsc_comp_list) #define CHSC_INFO_CPD _IOWR(CHSC_IOCTL_MAGIC, 0x87, struct chsc_cpd_info) #define CHSC_INFO_DCAL _IOWR(CHSC_IOCTL_MAGIC, 0x88, struct chsc_dcal) +#define CHSC_START_SYNC _IOWR(CHSC_IOCTL_MAGIC, 0x89, struct chsc_sync_area) +#define CHSC_ON_CLOSE_SET _IOWR(CHSC_IOCTL_MAGIC, 0x8a, struct chsc_async_area) +#define CHSC_ON_CLOSE_REMOVE _IO(CHSC_IOCTL_MAGIC, 0x8b) #endif diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h index 38eca3ba40e..5812a3b2df9 100644 --- a/arch/s390/include/uapi/asm/dasd.h +++ b/arch/s390/include/uapi/asm/dasd.h @@ -261,6 +261,10 @@ struct dasd_snid_ioctl_data { #define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6) /* Resume IO on device */ #define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7) +/* Abort all I/O on a device */ +#define BIODASDABORTIO _IO(DASD_IOCTL_LETTER, 240) +/* Allow I/O on a device */ +#define BIODASDALLOWIO _IO(DASD_IOCTL_LETTER, 241) /* retrieve API version number */ 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..0fc26430a1e 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -15,6 +15,52 @@ #include <linux/types.h> #define __KVM_S390 +#define __KVM_HAVE_GUEST_DEBUG + +/* 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; +}; + +/* kvm attr_group on vm fd */ +#define KVM_S390_VM_MEM_CTRL 0 + +/* kvm attributes for mem_ctrl */ +#define KVM_S390_VM_MEM_ENABLE_CMMA 0 +#define KVM_S390_VM_MEM_CLR_CMMA 1 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -34,11 +80,31 @@ struct kvm_fpu { __u64 fprs[16]; }; +#define KVM_GUESTDBG_USE_HW_BP 0x00010000 + +#define KVM_HW_BP 1 +#define KVM_HW_WP_WRITE 2 +#define KVM_SINGLESTEP 4 + struct kvm_debug_exit_arch { + __u64 addr; + __u8 type; + __u8 pad[7]; /* Should be set to 0 */ +}; + +struct kvm_hw_breakpoint { + __u64 addr; + __u64 phys_addr; + __u64 len; + __u8 type; + __u8 pad[7]; /* Should be set to 0 */ }; /* for KVM_SET_GUEST_DEBUG */ struct kvm_guest_debug_arch { + __u32 nr_hw_bp; + __u32 pad; /* Should be set to 0 */ + struct kvm_hw_breakpoint __user *hw_bp; }; #define KVM_SYNC_PREFIX (1UL << 0) @@ -57,4 +123,9 @@ 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 a5ca214b34f..a150f4fabe4 100644 --- a/arch/s390/include/uapi/asm/ptrace.h +++ b/arch/s390/include/uapi/asm/ptrace.h @@ -199,6 +199,7 @@ typedef union typedef struct { __u32 fpc; + __u32 pad; freg_t fprs[NUM_FPRS]; } s390_fp_regs; @@ -206,7 +207,6 @@ typedef struct #define FPC_FLAGS_MASK 0x00F80000 #define FPC_DXC_MASK 0x0000FF00 #define FPC_RM_MASK 0x00000003 -#define FPC_VALID_MASK 0xF8F8FF03 /* this typedef defines how a Program Status Word looks like */ typedef struct @@ -215,12 +215,6 @@ typedef struct unsigned long addr; } __attribute__ ((aligned(8))) psw_t; -typedef struct -{ - __u32 mask; - __u32 addr; -} __attribute__ ((aligned(8))) psw_compat_t; - #ifndef __s390x__ #define PSW_MASK_PER 0x40000000UL @@ -269,7 +263,7 @@ typedef struct #define PSW_MASK_EA 0x0000000100000000UL #define PSW_MASK_BA 0x0000000080000000UL -#define PSW_MASK_USER 0x0000FF8180000000UL +#define PSW_MASK_USER 0x0000FF0180000000UL #define PSW_ADDR_AMODE 0x0000000000000000UL #define PSW_ADDR_INSN 0xFFFFFFFFFFFFFFFFUL @@ -295,20 +289,6 @@ typedef struct unsigned long orig_gpr2; } s390_regs; -typedef struct -{ - psw_compat_t psw; - __u32 gprs[NUM_GPRS]; - __u32 acrs[NUM_ACRS]; - __u32 orig_gpr2; -} s390_compat_regs; - -typedef struct -{ - __u32 gprs_high[NUM_GPRS]; -} s390_compat_regs_high; - - /* * Now for the user space program event recording (trace) definitions. * The following structures are used only for the ptrace interface, don't @@ -420,6 +400,13 @@ typedef struct #define PTRACE_POKE_SYSTEM_CALL 0x5008 #define PTRACE_ENABLE_TE 0x5009 #define PTRACE_DISABLE_TE 0x5010 +#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 diff --git a/arch/s390/include/uapi/asm/sclp_ctl.h b/arch/s390/include/uapi/asm/sclp_ctl.h new file mode 100644 index 00000000000..f2818613ee4 --- /dev/null +++ b/arch/s390/include/uapi/asm/sclp_ctl.h @@ -0,0 +1,24 @@ +/* + * IOCTL interface for SCLP + * + * Copyright IBM Corp. 2012 + * + * Author: Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#ifndef _ASM_SCLP_CTL_H +#define _ASM_SCLP_CTL_H + +#include <linux/types.h> + +struct sclp_ctl_sccb { + __u32 cmdw; + __u64 sccb; +} __attribute__((packed)); + +#define SCLP_CTL_IOCTL_MAGIC 0x10 + +#define SCLP_CTL_SCCB \ + _IOWR(SCLP_CTL_IOCTL_MAGIC, 0x10, struct sclp_ctl_sccb) + +#endif diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h new file mode 100644 index 00000000000..5d9cc19462c --- /dev/null +++ b/arch/s390/include/uapi/asm/sie.h @@ -0,0 +1,243 @@ +#ifndef _UAPI_ASM_S390_SIE_H +#define _UAPI_ASM_S390_SIE_H + +#define diagnose_codes \ + { 0x10, "DIAG (0x10) release pages" }, \ + { 0x44, "DIAG (0x44) time slice end" }, \ + { 0x9c, "DIAG (0x9c) time slice end directed" }, \ + { 0x204, "DIAG (0x204) logical-cpu utilization" }, \ + { 0x258, "DIAG (0x258) page-reference services" }, \ + { 0x308, "DIAG (0x308) ipl functions" }, \ + { 0x500, "DIAG (0x500) KVM virtio functions" }, \ + { 0x501, "DIAG (0x501) KVM breakpoint" } + +#define sigp_order_codes \ + { 0x01, "SIGP sense" }, \ + { 0x02, "SIGP external call" }, \ + { 0x03, "SIGP emergency signal" }, \ + { 0x05, "SIGP stop" }, \ + { 0x06, "SIGP restart" }, \ + { 0x09, "SIGP stop and store status" }, \ + { 0x0b, "SIGP initial cpu reset" }, \ + { 0x0d, "SIGP set prefix" }, \ + { 0x0e, "SIGP store status at address" }, \ + { 0x12, "SIGP set architecture" }, \ + { 0x15, "SIGP sense running" } + +#define icpt_prog_codes \ + { 0x0001, "Prog Operation" }, \ + { 0x0002, "Prog Privileged Operation" }, \ + { 0x0003, "Prog Execute" }, \ + { 0x0004, "Prog Protection" }, \ + { 0x0005, "Prog Addressing" }, \ + { 0x0006, "Prog Specification" }, \ + { 0x0007, "Prog Data" }, \ + { 0x0008, "Prog Fixedpoint overflow" }, \ + { 0x0009, "Prog Fixedpoint divide" }, \ + { 0x000A, "Prog Decimal overflow" }, \ + { 0x000B, "Prog Decimal divide" }, \ + { 0x000C, "Prog HFP exponent overflow" }, \ + { 0x000D, "Prog HFP exponent underflow" }, \ + { 0x000E, "Prog HFP significance" }, \ + { 0x000F, "Prog HFP divide" }, \ + { 0x0010, "Prog Segment translation" }, \ + { 0x0011, "Prog Page translation" }, \ + { 0x0012, "Prog Translation specification" }, \ + { 0x0013, "Prog Special operation" }, \ + { 0x0015, "Prog Operand" }, \ + { 0x0016, "Prog Trace table" }, \ + { 0x0017, "Prog ASNtranslation specification" }, \ + { 0x001C, "Prog Spaceswitch event" }, \ + { 0x001D, "Prog HFP square root" }, \ + { 0x001F, "Prog PCtranslation specification" }, \ + { 0x0020, "Prog AFX translation" }, \ + { 0x0021, "Prog ASX translation" }, \ + { 0x0022, "Prog LX translation" }, \ + { 0x0023, "Prog EX translation" }, \ + { 0x0024, "Prog Primary authority" }, \ + { 0x0025, "Prog Secondary authority" }, \ + { 0x0026, "Prog LFXtranslation exception" }, \ + { 0x0027, "Prog LSXtranslation exception" }, \ + { 0x0028, "Prog ALET specification" }, \ + { 0x0029, "Prog ALEN translation" }, \ + { 0x002A, "Prog ALE sequence" }, \ + { 0x002B, "Prog ASTE validity" }, \ + { 0x002C, "Prog ASTE sequence" }, \ + { 0x002D, "Prog Extended authority" }, \ + { 0x002E, "Prog LSTE sequence" }, \ + { 0x002F, "Prog ASTE instance" }, \ + { 0x0030, "Prog Stack full" }, \ + { 0x0031, "Prog Stack empty" }, \ + { 0x0032, "Prog Stack specification" }, \ + { 0x0033, "Prog Stack type" }, \ + { 0x0034, "Prog Stack operation" }, \ + { 0x0039, "Prog Region first translation" }, \ + { 0x003A, "Prog Region second translation" }, \ + { 0x003B, "Prog Region third translation" }, \ + { 0x0040, "Prog Monitor event" }, \ + { 0x0080, "Prog PER event" }, \ + { 0x0119, "Prog Crypto operation" } + +#define exit_code_ipa0(ipa0, opcode, mnemonic) \ + { (ipa0 << 8 | opcode), #ipa0 " " mnemonic } +#define exit_code(opcode, mnemonic) \ + { opcode, mnemonic } + +#define icpt_insn_codes \ + exit_code_ipa0(0x01, 0x01, "PR"), \ + exit_code_ipa0(0x01, 0x04, "PTFF"), \ + exit_code_ipa0(0x01, 0x07, "SCKPF"), \ + exit_code_ipa0(0xAA, 0x00, "RINEXT"), \ + exit_code_ipa0(0xAA, 0x01, "RION"), \ + exit_code_ipa0(0xAA, 0x02, "TRIC"), \ + exit_code_ipa0(0xAA, 0x03, "RIOFF"), \ + exit_code_ipa0(0xAA, 0x04, "RIEMIT"), \ + exit_code_ipa0(0xB2, 0x02, "STIDP"), \ + exit_code_ipa0(0xB2, 0x04, "SCK"), \ + exit_code_ipa0(0xB2, 0x05, "STCK"), \ + exit_code_ipa0(0xB2, 0x06, "SCKC"), \ + exit_code_ipa0(0xB2, 0x07, "STCKC"), \ + exit_code_ipa0(0xB2, 0x08, "SPT"), \ + exit_code_ipa0(0xB2, 0x09, "STPT"), \ + exit_code_ipa0(0xB2, 0x0d, "PTLB"), \ + exit_code_ipa0(0xB2, 0x10, "SPX"), \ + exit_code_ipa0(0xB2, 0x11, "STPX"), \ + exit_code_ipa0(0xB2, 0x12, "STAP"), \ + exit_code_ipa0(0xB2, 0x14, "SIE"), \ + exit_code_ipa0(0xB2, 0x16, "SETR"), \ + exit_code_ipa0(0xB2, 0x17, "STETR"), \ + exit_code_ipa0(0xB2, 0x18, "PC"), \ + exit_code_ipa0(0xB2, 0x20, "SERVC"), \ + exit_code_ipa0(0xB2, 0x28, "PT"), \ + exit_code_ipa0(0xB2, 0x29, "ISKE"), \ + exit_code_ipa0(0xB2, 0x2a, "RRBE"), \ + exit_code_ipa0(0xB2, 0x2b, "SSKE"), \ + exit_code_ipa0(0xB2, 0x2c, "TB"), \ + exit_code_ipa0(0xB2, 0x2e, "PGIN"), \ + exit_code_ipa0(0xB2, 0x2f, "PGOUT"), \ + exit_code_ipa0(0xB2, 0x30, "CSCH"), \ + exit_code_ipa0(0xB2, 0x31, "HSCH"), \ + exit_code_ipa0(0xB2, 0x32, "MSCH"), \ + exit_code_ipa0(0xB2, 0x33, "SSCH"), \ + exit_code_ipa0(0xB2, 0x34, "STSCH"), \ + exit_code_ipa0(0xB2, 0x35, "TSCH"), \ + exit_code_ipa0(0xB2, 0x36, "TPI"), \ + exit_code_ipa0(0xB2, 0x37, "SAL"), \ + exit_code_ipa0(0xB2, 0x38, "RSCH"), \ + exit_code_ipa0(0xB2, 0x39, "STCRW"), \ + exit_code_ipa0(0xB2, 0x3a, "STCPS"), \ + exit_code_ipa0(0xB2, 0x3b, "RCHP"), \ + exit_code_ipa0(0xB2, 0x3c, "SCHM"), \ + exit_code_ipa0(0xB2, 0x40, "BAKR"), \ + exit_code_ipa0(0xB2, 0x48, "PALB"), \ + exit_code_ipa0(0xB2, 0x4c, "TAR"), \ + exit_code_ipa0(0xB2, 0x50, "CSP"), \ + exit_code_ipa0(0xB2, 0x54, "MVPG"), \ + exit_code_ipa0(0xB2, 0x58, "BSG"), \ + exit_code_ipa0(0xB2, 0x5a, "BSA"), \ + exit_code_ipa0(0xB2, 0x5f, "CHSC"), \ + exit_code_ipa0(0xB2, 0x74, "SIGA"), \ + exit_code_ipa0(0xB2, 0x76, "XSCH"), \ + exit_code_ipa0(0xB2, 0x78, "STCKE"), \ + exit_code_ipa0(0xB2, 0x7c, "STCKF"), \ + exit_code_ipa0(0xB2, 0x7d, "STSI"), \ + exit_code_ipa0(0xB2, 0xb0, "STFLE"), \ + exit_code_ipa0(0xB2, 0xb1, "STFL"), \ + exit_code_ipa0(0xB2, 0xb2, "LPSWE"), \ + exit_code_ipa0(0xB2, 0xf8, "TEND"), \ + exit_code_ipa0(0xB2, 0xfc, "TABORT"), \ + exit_code_ipa0(0xB9, 0x1e, "KMAC"), \ + exit_code_ipa0(0xB9, 0x28, "PCKMO"), \ + exit_code_ipa0(0xB9, 0x2a, "KMF"), \ + exit_code_ipa0(0xB9, 0x2b, "KMO"), \ + exit_code_ipa0(0xB9, 0x2d, "KMCTR"), \ + exit_code_ipa0(0xB9, 0x2e, "KM"), \ + exit_code_ipa0(0xB9, 0x2f, "KMC"), \ + exit_code_ipa0(0xB9, 0x3e, "KIMD"), \ + exit_code_ipa0(0xB9, 0x3f, "KLMD"), \ + exit_code_ipa0(0xB9, 0x8a, "CSPG"), \ + exit_code_ipa0(0xB9, 0x8d, "EPSW"), \ + exit_code_ipa0(0xB9, 0x8e, "IDTE"), \ + exit_code_ipa0(0xB9, 0x8f, "CRDTE"), \ + exit_code_ipa0(0xB9, 0x9c, "EQBS"), \ + exit_code_ipa0(0xB9, 0xa2, "PTF"), \ + exit_code_ipa0(0xB9, 0xab, "ESSA"), \ + exit_code_ipa0(0xB9, 0xae, "RRBM"), \ + exit_code_ipa0(0xB9, 0xaf, "PFMF"), \ + exit_code_ipa0(0xE3, 0x03, "LRAG"), \ + exit_code_ipa0(0xE3, 0x13, "LRAY"), \ + exit_code_ipa0(0xE3, 0x25, "NTSTG"), \ + exit_code_ipa0(0xE5, 0x00, "LASP"), \ + exit_code_ipa0(0xE5, 0x01, "TPROT"), \ + exit_code_ipa0(0xE5, 0x60, "TBEGIN"), \ + exit_code_ipa0(0xE5, 0x61, "TBEGINC"), \ + exit_code_ipa0(0xEB, 0x25, "STCTG"), \ + exit_code_ipa0(0xEB, 0x2f, "LCTLG"), \ + exit_code_ipa0(0xEB, 0x60, "LRIC"), \ + exit_code_ipa0(0xEB, 0x61, "STRIC"), \ + exit_code_ipa0(0xEB, 0x62, "MRIC"), \ + exit_code_ipa0(0xEB, 0x8a, "SQBS"), \ + exit_code_ipa0(0xC8, 0x01, "ECTG"), \ + exit_code(0x0a, "SVC"), \ + exit_code(0x80, "SSM"), \ + exit_code(0x82, "LPSW"), \ + exit_code(0x83, "DIAG"), \ + exit_code(0xae, "SIGP"), \ + exit_code(0xac, "STNSM"), \ + exit_code(0xad, "STOSM"), \ + exit_code(0xb1, "LRA"), \ + exit_code(0xb6, "STCTL"), \ + exit_code(0xb7, "LCTL"), \ + exit_code(0xee, "PLO") + +#define sie_intercept_code \ + { 0x00, "Host interruption" }, \ + { 0x04, "Instruction" }, \ + { 0x08, "Program interruption" }, \ + { 0x0c, "Instruction and program interruption" }, \ + { 0x10, "External request" }, \ + { 0x14, "External interruption" }, \ + { 0x18, "I/O request" }, \ + { 0x1c, "Wait state" }, \ + { 0x20, "Validity" }, \ + { 0x28, "Stop request" }, \ + { 0x2c, "Operation exception" }, \ + { 0x38, "Partial-execution" }, \ + { 0x3c, "I/O interruption" }, \ + { 0x40, "I/O instruction" }, \ + { 0x48, "Timing subset" } + +/* + * This is the simple interceptable instructions decoder. + * + * It will be used as userspace interface and it can be used in places + * that does not allow to use general decoder functions, + * such as trace events declarations. + * + * Some userspace tools may want to parse this code + * and would be confused by switch(), if() and other statements, + * but they can understand conditional operator. + */ +#define INSN_DECODE_IPA0(ipa0, insn, rshift, mask) \ + (insn >> 56) == (ipa0) ? \ + ((ipa0 << 8) | ((insn >> rshift) & mask)) : + +#define INSN_DECODE(insn) (insn >> 56) + +/* + * The macro icpt_insn_decoder() takes an intercepted instruction + * and returns a key, which can be used to find a mnemonic name + * of the instruction in the icpt_insn_codes table. + */ +#define icpt_insn_decoder(insn) \ + INSN_DECODE_IPA0(0x01, insn, 48, 0xff) \ + INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f) \ + INSN_DECODE_IPA0(0xb2, insn, 48, 0xff) \ + INSN_DECODE_IPA0(0xb9, insn, 48, 0xff) \ + INSN_DECODE_IPA0(0xe3, insn, 48, 0xff) \ + INSN_DECODE_IPA0(0xe5, insn, 48, 0xff) \ + INSN_DECODE_IPA0(0xeb, insn, 16, 0xff) \ + INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f) \ + INSN_DECODE(insn) + +#endif /* _UAPI_ASM_S390_SIE_H */ diff --git a/arch/s390/include/uapi/asm/sigcontext.h b/arch/s390/include/uapi/asm/sigcontext.h index 584787f6ce4..b30de9c01bb 100644 --- a/arch/s390/include/uapi/asm/sigcontext.h +++ b/arch/s390/include/uapi/asm/sigcontext.h @@ -49,6 +49,7 @@ typedef struct typedef struct { unsigned int fpc; + unsigned int pad; double fprs[__NUM_FPRS]; } _s390_fp_regs; diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 436d07c23be..e031332096d 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -28,7 +28,7 @@ #define SO_PRIORITY 12 #define SO_LINGER 13 #define SO_BSDCOMPAT 14 -/* To add :#define SO_REUSEPORT 15 */ +#define SO_REUSEPORT 15 #define SO_PASSCRED 16 #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 @@ -76,4 +76,14 @@ /* Instruct lower device to use last 4-bytes of skb data as FCS */ #define SO_NOFCS 43 +#define SO_LOCK_FILTER 44 + +#define SO_SELECT_ERR_QUEUE 45 + +#define SO_BUSY_POLL 46 + +#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 5acca0a34c2..471eb09184d 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -7,9 +7,6 @@ #ifndef _S390_STATFS_H #define _S390_STATFS_H -#ifndef __s390x__ -#include <asm-generic/statfs.h> -#else /* * We can't use <asm-generic/statfs.h> because in 64-bit mode * we mix ints of different sizes in our struct statfs. @@ -21,49 +18,33 @@ typedef __kernel_fsid_t fsid_t; #endif struct statfs { - int f_type; - int f_bsize; - long f_blocks; - long f_bfree; - long f_bavail; - long f_files; - long f_ffree; + 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; __kernel_fsid_t f_fsid; - int f_namelen; - int f_frsize; - int f_flags; - int f_spare[4]; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; }; struct statfs64 { - int f_type; - int f_bsize; - long f_blocks; - long f_bfree; - long f_bavail; - long f_files; - long f_ffree; + unsigned int f_type; + unsigned int f_bsize; + 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; - int f_namelen; - int f_frsize; - int f_flags; - int f_spare[4]; + unsigned int f_namelen; + unsigned int f_frsize; + unsigned int f_flags; + unsigned int f_spare[4]; }; -struct compat_statfs64 { - __u32 f_type; - __u32 f_bsize; - __u64 f_blocks; - __u64 f_bfree; - __u64 f_bavail; - __u64 f_files; - __u64 f_ffree; - __kernel_fsid_t f_fsid; - __u32 f_namelen; - __u32 f_frsize; - __u32 f_flags; - __u32 f_spare[4]; -}; - -#endif /* __s390x__ */ #endif diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h index 200e06325c6..3e077b2a470 100644 --- a/arch/s390/include/uapi/asm/ucontext.h +++ b/arch/s390/include/uapi/asm/ucontext.h @@ -16,7 +16,9 @@ struct ucontext_extended { struct ucontext *uc_link; stack_t uc_stack; _sigregs uc_mcontext; - unsigned long uc_sigmask[2]; + sigset_t uc_sigmask; + /* Allow for uc_sigmask growth. Glibc uses a 1024-bit sigset_t. */ + unsigned char __unused[128 - sizeof(sigset_t)]; unsigned long uc_gprs_high[16]; }; @@ -27,7 +29,9 @@ struct ucontext { struct ucontext *uc_link; stack_t uc_stack; _sigregs uc_mcontext; - sigset_t uc_sigmask; /* mask last for extensibility */ + sigset_t uc_sigmask; + /* Allow for uc_sigmask growth. Glibc uses a 1024-bit sigset_t. */ + unsigned char __unused[128 - sizeof(sigset_t)]; }; #endif /* !_ASM_S390_UCONTEXT_H */ diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index 864f693c237..3802d2d3a18 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -280,7 +280,10 @@ #define __NR_s390_runtime_instr 342 #define __NR_kcmp 343 #define __NR_finit_module 344 -#define NR_syscalls 345 +#define __NR_sched_setattr 345 +#define __NR_sched_getattr 346 +#define __NR_renameat2 347 +#define NR_syscalls 348 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/include/uapi/asm/virtio-ccw.h b/arch/s390/include/uapi/asm/virtio-ccw.h new file mode 100644 index 00000000000..a9a4ebf79fa --- /dev/null +++ b/arch/s390/include/uapi/asm/virtio-ccw.h @@ -0,0 +1,21 @@ +/* + * Definitions for virtio-ccw devices. + * + * Copyright IBM Corp. 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) + * as published by the Free Software Foundation. + * + * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> + */ +#ifndef __KVM_VIRTIO_CCW_H +#define __KVM_VIRTIO_CCW_H + +/* Alignment of vring buffers. */ +#define KVM_VIRTIO_CCW_RING_ALIGN 4096 + +/* Subcode for diagnose 500 (virtio hypercall). */ +#define KVM_S390_VIRTIO_CCW_NOTIFY 3 + +#endif 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 2ac311ef5c9..a95c4ca9961 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -14,16 +14,25 @@ endif CFLAGS_smp.o := -Wno-nonnull # +# Disable tailcall optimizations for stack / callchain walking functions +# since this might generate broken code when accessing register 15 and +# passing its content to other functions. +# +CFLAGS_stacktrace.o += -fno-optimize-sibling-calls +CFLAGS_dumpstack.o += -fno-optimize-sibling-calls + +# # Pass UTS_MACHINE for user_regset definition # CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w -obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \ - processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \ - debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \ - sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y := traps.o time.o process.o base.o early.o setup.o vtime.o +obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o +obj-y += debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o +obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o +obj-y += dumpstack.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) @@ -38,9 +47,8 @@ obj-$(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-$(CONFIG_KPROBES) += kprobes.o @@ -51,7 +59,8 @@ obj-$(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 fface87056e..afe1715a4eb 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -7,6 +7,7 @@ #define ASM_OFFSETS_C #include <linux/kbuild.h> +#include <linux/kvm_host.h> #include <linux/sched.h> #include <asm/cputime.h> #include <asm/vdso.h> @@ -35,6 +36,7 @@ int main(void) DEFINE(__TI_task, offsetof(struct thread_info, task)); DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain)); DEFINE(__TI_flags, offsetof(struct thread_info, flags)); + DEFINE(__TI_sysc_table, offsetof(struct thread_info, sys_call_table)); DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer)); @@ -46,7 +48,9 @@ int main(void) DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs)); DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2)); DEFINE(__PT_INT_CODE, offsetof(struct pt_regs, int_code)); + DEFINE(__PT_INT_PARM, offsetof(struct pt_regs, int_parm)); DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long)); + DEFINE(__PT_FLAGS, offsetof(struct pt_regs, flags)); DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain)); @@ -62,12 +66,14 @@ int main(void) DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest)); DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available)); - DEFINE(__VDSO_NTP_MULT, offsetof(struct vdso_data, ntp_mult)); + DEFINE(__VDSO_TK_MULT, offsetof(struct vdso_data, tk_mult)); + DEFINE(__VDSO_TK_SHIFT, offsetof(struct vdso_data, tk_shift)); DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base)); DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time)); /* constants used by the vdso */ DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); BLANK(); /* idle data offsets */ @@ -84,16 +90,22 @@ int main(void) DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc)); DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code)); DEFINE(__LC_TRANS_EXC_CODE, offsetof(struct _lowcore, trans_exc_code)); - DEFINE(__LC_PER_CAUSE, offsetof(struct _lowcore, per_perc_atmid)); + DEFINE(__LC_MON_CLASS_NR, offsetof(struct _lowcore, mon_class_num)); + DEFINE(__LC_PER_CODE, offsetof(struct _lowcore, per_code)); + DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_atmid)); DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address)); - DEFINE(__LC_PER_PAID, offsetof(struct _lowcore, per_access_id)); - DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_access_id)); + DEFINE(__LC_EXC_ACCESS_ID, offsetof(struct _lowcore, exc_access_id)); + DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id)); + DEFINE(__LC_OP_ACCESS_ID, offsetof(struct _lowcore, op_access_id)); + DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_mode_id)); + DEFINE(__LC_MON_CODE, offsetof(struct _lowcore, monitor_code)); DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id)); DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr)); DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm)); DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word)); DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list)); DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code)); + DEFINE(__LC_MCCK_EXT_DAM_CODE, offsetof(struct _lowcore, external_damage_code)); DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw)); DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw)); DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw)); @@ -110,6 +122,7 @@ int main(void) DEFINE(__LC_SAVE_AREA_SYNC, offsetof(struct _lowcore, save_area_sync)); DEFINE(__LC_SAVE_AREA_ASYNC, offsetof(struct _lowcore, save_area_async)); DEFINE(__LC_SAVE_AREA_RESTART, offsetof(struct _lowcore, save_area_restart)); + DEFINE(__LC_CPU_FLAGS, offsetof(struct _lowcore, cpu_flags)); DEFINE(__LC_RETURN_PSW, offsetof(struct _lowcore, return_psw)); DEFINE(__LC_RETURN_MCCK_PSW, offsetof(struct _lowcore, return_mcck_psw)); DEFINE(__LC_SYNC_ENTER_TIMER, offsetof(struct _lowcore, sync_enter_timer)); @@ -131,12 +144,12 @@ 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)); DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags)); DEFINE(__LC_FTRACE_FUNC, offsetof(struct _lowcore, ftrace_func)); - DEFINE(__LC_IRB, offsetof(struct _lowcore, irb)); DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib)); BLANK(); DEFINE(__LC_CPU_TIMER_SAVE_AREA, offsetof(struct _lowcore, cpu_timer_save_area)); @@ -150,6 +163,8 @@ int main(void) #ifdef CONFIG_32BIT DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr)); #else /* CONFIG_32BIT */ + DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code)); + DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address)); DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2)); DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area)); DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste)); @@ -160,6 +175,8 @@ int main(void) DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb)); DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb)); DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); + DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c)); + DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20)); #endif /* CONFIG_32BIT */ return 0; } diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c deleted file mode 100644 index 102da5e2303..00000000000 --- a/arch/s390/kernel/bitmap.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Bitmaps for set_bit, clear_bit, test_and_set_bit, ... - * See include/asm/{bitops.h|posix_types.h} for details - * - * Copyright IBM Corp. 1999, 2009 - * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, - */ - -#include <linux/bitops.h> -#include <linux/module.h> - -const char _oi_bitmap[] = { 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80 }; -EXPORT_SYMBOL(_oi_bitmap); - -const char _ni_bitmap[] = { 0xfe, 0xfd, 0xfb, 0xf7, 0xef, 0xdf, 0xbf, 0x7f }; -EXPORT_SYMBOL(_ni_bitmap); - -const char _zb_findmap[] = { - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,7, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4, - 0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,8 }; -EXPORT_SYMBOL(_zb_findmap); - -const char _sb_findmap[] = { - 8,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 7,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0, - 4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0 }; -EXPORT_SYMBOL(_sb_findmap); diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index 64b24650e4f..c0b03c28d15 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -146,15 +146,14 @@ static void __init cache_build_info(void) ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); for (level = 0; level < CACHE_MAX_LEVEL; level++) { switch (ct.ci[level].scope) { - case CACHE_SCOPE_NOTEXISTS: - case CACHE_SCOPE_RESERVED: - return; case CACHE_SCOPE_SHARED: private = 0; break; case CACHE_SCOPE_PRIVATE: private = 1; break; + default: + return; } if (ct.ci[level].type == CACHE_TYPE_SEPARATE) { rc = cache_add(level, private, CACHE_TYPE_DATA); @@ -173,7 +172,7 @@ error: } } -static struct cache_dir *__cpuinit cache_create_cache_dir(int cpu) +static struct cache_dir *cache_create_cache_dir(int cpu) { struct cache_dir *cache_dir; struct kobject *kobj = NULL; @@ -289,9 +288,8 @@ static struct kobj_type cache_index_type = { .default_attrs = cache_index_default_attrs, }; -static int __cpuinit cache_create_index_dir(struct cache_dir *cache_dir, - struct cache *cache, int index, - int cpu) +static int cache_create_index_dir(struct cache_dir *cache_dir, + struct cache *cache, int index, int cpu) { struct cache_index_dir *index_dir; int rc; @@ -313,7 +311,7 @@ out: return rc; } -static int __cpuinit cache_add_cpu(int cpu) +static int cache_add_cpu(int cpu) { struct cache_dir *cache_dir; struct cache *cache; @@ -335,7 +333,7 @@ static int __cpuinit cache_add_cpu(int cpu) return 0; } -static void __cpuinit cache_remove_cpu(int cpu) +static void cache_remove_cpu(int cpu) { struct cache_index_dir *index, *next; struct cache_dir *cache_dir; @@ -354,8 +352,8 @@ static void __cpuinit cache_remove_cpu(int cpu) cache_dir_cpu[cpu] = NULL; } -static int __cpuinit cache_hotplug(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cache_hotplug(struct notifier_block *nfb, unsigned long action, + void *hcpu) { int cpu = (long)hcpu; int rc = 0; @@ -380,9 +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 65cca95843e..ca38139423a 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -58,10 +58,6 @@ #include "compat_linux.h" -u32 psw32_user_bits = PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | - PSW32_DEFAULT_KEY | PSW32_MASK_BASE | PSW32_MASK_MCHECK | - PSW32_MASK_PSTATE | PSW32_ASC_HOME; - /* For this source file, we want overflow handling. */ #undef high2lowuid @@ -90,48 +86,51 @@ u32 psw32_user_bits = PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | #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; @@ -148,13 +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; @@ -171,12 +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); } @@ -219,31 +219,32 @@ 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; if (gidsetsize < 0) return -EINVAL; - get_group_info(current->cred->group_info); - i = current->cred->group_info->ngroups; + get_group_info(cred->group_info); + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->cred->group_info)) { + if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->cred->group_info); + put_group_info(cred->group_info); 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; @@ -268,231 +269,65 @@ 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())); } -/* - * sys32_ipc() is the de-multiplexer for the SysV IPC calls in 32bit emulation. - * - * This is really horribly ugly. - */ #ifdef CONFIG_SYSVIPC -asmlinkage long sys32_ipc(u32 call, int first, int second, int third, u32 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; - switch (call) { - case SEMTIMEDOP: - return compat_sys_semtimedop(first, compat_ptr(ptr), - second, compat_ptr(third)); - case SEMOP: - /* struct sembuf is the same on 32 and 64bit :)) */ - return sys_semtimedop(first, compat_ptr(ptr), - second, NULL); - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: - return compat_sys_semctl(first, second, third, - compat_ptr(ptr)); - case MSGSND: - return compat_sys_msgsnd(first, second, third, - compat_ptr(ptr)); - case MSGRCV: - return compat_sys_msgrcv(first, second, 0, third, - 0, compat_ptr(ptr)); - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return compat_sys_msgctl(first, second, compat_ptr(ptr)); - case SHMAT: - return compat_sys_shmat(first, second, third, - 0, compat_ptr(ptr)); - case SHMDT: - return sys_shmdt(compat_ptr(ptr)); - case SHMGET: - return sys_shmget(first, (unsigned)second, third); - case SHMCTL: - return compat_sys_shmctl(first, second, compat_ptr(ptr)); - } - - return -ENOSYS; + return compat_sys_ipc(call, first, second, third, ptr, third); } #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); -} - -asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low) -{ - if ((int)high < 0) - return -EINVAL; - else - return sys_ftruncate(fd, (high << 32) | low); -} - -asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval) -{ - struct timespec t; - int ret; - mm_segment_t old_fs = get_fs (); - - set_fs (KERNEL_DS); - ret = sys_sched_rr_get_interval(pid, - (struct timespec __force __user *) &t); - set_fs (old_fs); - if (put_compat_timespec(&t, interval)) - return -EFAULT; - return ret; -} - -asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, - compat_sigset_t __user *oset, size_t sigsetsize) -{ - sigset_t s; - compat_sigset_t s32; - int ret; - mm_segment_t old_fs = get_fs(); - - if (set) { - if (copy_from_user (&s32, set, sizeof(compat_sigset_t))) - return -EFAULT; - s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); - } - set_fs (KERNEL_DS); - ret = sys_rt_sigprocmask(how, - set ? (sigset_t __force __user *) &s : NULL, - oset ? (sigset_t __force __user *) &s : NULL, - sigsetsize); - set_fs (old_fs); - if (ret) return ret; - if (oset) { - s32.sig[1] = (s.sig[0] >> 32); - s32.sig[0] = s.sig[0]; - if (copy_to_user (oset, &s32, sizeof(compat_sigset_t))) - return -EFAULT; - } - return 0; -} - -asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set, - size_t sigsetsize) -{ - sigset_t s; - compat_sigset_t s32; - int ret; - mm_segment_t old_fs = get_fs(); - - set_fs (KERNEL_DS); - ret = sys_rt_sigpending((sigset_t __force __user *) &s, sigsetsize); - set_fs (old_fs); - if (!ret) { - s32.sig[1] = (s.sig[0] >> 32); - s32.sig[0] = s.sig[0]; - if (copy_to_user (set, &s32, sizeof(compat_sigset_t))) - return -EFAULT; - } - return ret; + return sys_truncate(path, (unsigned long)high << 32 | low); } -asmlinkage long -sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) +COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low) { - siginfo_t info; - int ret; - mm_segment_t old_fs = get_fs(); - - if (copy_siginfo_from_user32(&info, uinfo)) - return -EFAULT; - set_fs (KERNEL_DS); - ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __force __user *) &info); - set_fs (old_fs); - return ret; + 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)); -} - -asmlinkage compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count) -{ - return sys_readahead(fd, ((loff_t)AA(offhi) << 32) | AA(offlo), count); + return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low); } -asmlinkage long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, size_t count) +COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count) { - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - - if (offset && get_user(of, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile(out_fd, in_fd, - offset ? (off_t __force __user *) &of : NULL, count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; -} - -asmlinkage long sys32_sendfile64(int out_fd, int in_fd, - compat_loff_t __user *offset, s32 count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile64(out_fd, in_fd, - offset ? (loff_t __force __user *) &lof : NULL, - count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; + return sys_readahead(fd, (unsigned long)high << 32 | low, count); } struct stat64_emu31 { @@ -544,7 +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); @@ -553,7 +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); @@ -562,7 +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); @@ -571,8 +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; @@ -598,7 +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; @@ -610,7 +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; @@ -619,7 +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; @@ -627,7 +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; @@ -641,14 +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 { @@ -658,8 +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; @@ -671,3 +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 d4d0239970a..70d4b7c4bea 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -17,13 +17,6 @@ struct ipc_kludge_32 { __s32 msgtyp; }; -struct old_sigaction32 { - __u32 sa_handler; /* Really a pointer, but need to deal with 32 bits */ - compat_old_sigset_t sa_mask; /* A 32 bit mask */ - __u32 sa_flags; - __u32 sa_restorer; /* Another 32 bit pointer */ -}; - /* asm/sigcontext.h */ typedef union { @@ -34,6 +27,7 @@ typedef union typedef struct { unsigned int fpc; + unsigned int pad; freg_t32 fprs[__NUM_FPRS]; } _s390_fp_regs32; @@ -68,90 +62,59 @@ struct sigcontext32 }; /* asm/signal.h */ -struct sigaction32 { - __u32 sa_handler; /* pointer */ - __u32 sa_flags; - __u32 sa_restorer; /* pointer */ - compat_sigset_t sa_mask; /* mask last for extensibility */ -}; - -typedef struct { - __u32 ss_sp; /* pointer */ - int ss_flags; - compat_size_t ss_size; -} stack_t32; /* asm/ucontext.h */ struct ucontext32 { __u32 uc_flags; __u32 uc_link; /* pointer */ - stack_t32 uc_stack; + compat_stack_t uc_stack; _sigregs32 uc_mcontext; - compat_sigset_t uc_sigmask; /* mask last for extensibility */ + compat_sigset_t uc_sigmask; + /* Allow for uc_sigmask growth. Glibc uses a 1024-bit sigset_t. */ + unsigned char __unused[128 - sizeof(compat_sigset_t)]; }; struct stat64_emu31; struct mmap_arg_struct_emu31; struct fadvise64_64_args; -struct old_sigaction32; -struct old_sigaction32; -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_ipc(u32 call, int first, int second, int third, u32 ptr); -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_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval); -long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, - compat_sigset_t __user *oset, size_t sigsetsize); -long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize); -long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo); -long sys32_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_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, - size_t count); -long sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, - 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 sys32_sigaction(int sig, const struct old_sigaction32 __user *act, - struct old_sigaction32 __user *oact); -long sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, - struct sigaction32 __user *oact, size_t sigsetsize); -long sys32_sigaltstack(const stack_t32 __user *uss, stack_t32 __user *uoss); +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 593fcc9253f..f204d692036 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -49,13 +49,10 @@ typedef struct __u32 gprs_high[NUM_GPRS]; } rt_sigframe32; -int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) { int err; - if (!access_ok (VERIFY_WRITE, to, sizeof(compat_siginfo_t))) - return -EFAULT; - /* If you change siginfo_t structure, please be sure this code is fixed accordingly. It should never copy any pad contained in the structure @@ -102,7 +99,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) break; } } - return err; + return err ? -EFAULT : 0; } int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) @@ -110,9 +107,6 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) int err; u32 tmp; - if (!access_ok (VERIFY_READ, from, sizeof(compat_siginfo_t))) - return -EFAULT; - err = __get_user(to->si_signo, &from->si_signo); err |= __get_user(to->si_errno, &from->si_errno); err |= __get_user(to->si_code, &from->si_code); @@ -154,179 +148,72 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) break; } } - return err; -} - -asmlinkage long -sys32_sigaction(int sig, const struct old_sigaction32 __user *act, - struct old_sigaction32 __user *oact) -{ - struct k_sigaction new_ka, old_ka; - unsigned long sa_handler, sa_restorer; - int ret; - - if (act) { - compat_old_sigset_t mask; - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || - __get_user(sa_handler, &act->sa_handler) || - __get_user(sa_restorer, &act->sa_restorer) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags) || - __get_user(mask, &act->sa_mask)) - return -EFAULT; - new_ka.sa.sa_handler = (__sighandler_t) sa_handler; - new_ka.sa.sa_restorer = (void (*)(void)) sa_restorer; - siginitset(&new_ka.sa.sa_mask, mask); - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - sa_handler = (unsigned long) old_ka.sa.sa_handler; - sa_restorer = (unsigned long) old_ka.sa.sa_restorer; - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || - __put_user(sa_handler, &oact->sa_handler) || - __put_user(sa_restorer, &oact->sa_restorer) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) - return -EFAULT; - } - - return ret; -} - -asmlinkage long -sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, - struct sigaction32 __user *oact, size_t sigsetsize) -{ - struct k_sigaction new_ka, old_ka; - unsigned long sa_handler; - int ret; - compat_sigset_t set32; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - - if (act) { - ret = get_user(sa_handler, &act->sa_handler); - ret |= __copy_from_user(&set32, &act->sa_mask, - sizeof(compat_sigset_t)); - new_ka.sa.sa_mask.sig[0] = - set32.sig[0] | (((long)set32.sig[1]) << 32); - ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags); - - if (ret) - return -EFAULT; - new_ka.sa.sa_handler = (__sighandler_t) sa_handler; - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); - set32.sig[0] = old_ka.sa.sa_mask.sig[0]; - ret = put_user((unsigned long)old_ka.sa.sa_handler, &oact->sa_handler); - ret |= __copy_to_user(&oact->sa_mask, &set32, - sizeof(compat_sigset_t)); - ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - } - - return ret; -} - -asmlinkage long -sys32_sigaltstack(const stack_t32 __user *uss, stack_t32 __user *uoss) -{ - struct pt_regs *regs = task_pt_regs(current); - stack_t kss, koss; - unsigned long ss_sp; - int ret, err = 0; - mm_segment_t old_fs = get_fs(); - - if (uss) { - if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) - return -EFAULT; - err |= __get_user(ss_sp, &uss->ss_sp); - err |= __get_user(kss.ss_size, &uss->ss_size); - err |= __get_user(kss.ss_flags, &uss->ss_flags); - if (err) - return -EFAULT; - kss.ss_sp = (void __user *) ss_sp; - } - - set_fs (KERNEL_DS); - ret = do_sigaltstack((stack_t __force __user *) (uss ? &kss : NULL), - (stack_t __force __user *) (uoss ? &koss : NULL), - regs->gprs[15]); - set_fs (old_fs); - - if (!ret && uoss) { - if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss))) - return -EFAULT; - ss_sp = (unsigned long) koss.ss_sp; - err |= __put_user(ss_sp, &uoss->ss_sp); - err |= __put_user(koss.ss_size, &uoss->ss_size); - err |= __put_user(koss.ss_flags, &uoss->ss_flags); - if (err) - return -EFAULT; - } - return ret; + return err ? -EFAULT : 0; } static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) { - _s390_regs_common32 regs32; - int err, i; + _sigregs32 user_sregs; + int i; - regs32.psw.mask = psw32_user_bits | - ((__u32)(regs->psw.mask >> 32) & PSW32_MASK_USER); - regs32.psw.addr = (__u32) regs->psw.addr | + user_sregs.regs.psw.mask = (__u32)(regs->psw.mask >> 32); + user_sregs.regs.psw.mask &= PSW32_MASK_USER | PSW32_MASK_RI; + user_sregs.regs.psw.mask |= PSW32_USER_BITS; + user_sregs.regs.psw.addr = (__u32) regs->psw.addr | (__u32)(regs->psw.mask & PSW_MASK_BA); for (i = 0; i < NUM_GPRS; i++) - regs32.gprs[i] = (__u32) regs->gprs[i]; + user_sregs.regs.gprs[i] = (__u32) regs->gprs[i]; save_access_regs(current->thread.acrs); - memcpy(regs32.acrs, current->thread.acrs, sizeof(regs32.acrs)); - err = __copy_to_user(&sregs->regs, ®s32, sizeof(regs32)); - if (err) - return err; - save_fp_regs(¤t->thread.fp_regs); - /* s390_fp_regs and _s390_fp_regs32 are the same ! */ - return __copy_to_user(&sregs->fpregs, ¤t->thread.fp_regs, - sizeof(_s390_fp_regs32)); + memcpy(&user_sregs.regs.acrs, current->thread.acrs, + sizeof(user_sregs.regs.acrs)); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); + memcpy(&user_sregs.fpregs, ¤t->thread.fp_regs, + sizeof(user_sregs.fpregs)); + if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32))) + return -EFAULT; + return 0; } static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) { - _s390_regs_common32 regs32; - int err, i; + _sigregs32 user_sregs; + int i; /* Alwys make any pending restarted system call return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; - err = __copy_from_user(®s32, &sregs->regs, sizeof(regs32)); - if (err) - return err; - regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | - (__u64)(regs32.psw.mask & PSW32_MASK_USER) << 32 | - (__u64)(regs32.psw.addr & PSW32_ADDR_AMODE); + if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs))) + return -EFAULT; + + if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW32_MASK_RI)) + return -EINVAL; + + /* Loading the floating-point-control word can fail. Do that first. */ + if (restore_fp_ctl(&user_sregs.fpregs.fpc)) + return -EINVAL; + + /* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) | + (__u64)(user_sregs.regs.psw.mask & PSW32_MASK_USER) << 32 | + (__u64)(user_sregs.regs.psw.mask & PSW32_MASK_RI) << 32 | + (__u64)(user_sregs.regs.psw.addr & PSW32_ADDR_AMODE); /* Check for invalid user address space control. */ - if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC)) - regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) | + if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME) + regs->psw.mask = PSW_ASC_PRIMARY | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN); + regs->psw.addr = (__u64)(user_sregs.regs.psw.addr & PSW32_ADDR_INSN); for (i = 0; i < NUM_GPRS; i++) - regs->gprs[i] = (__u64) regs32.gprs[i]; - memcpy(current->thread.acrs, regs32.acrs, sizeof(current->thread.acrs)); + regs->gprs[i] = (__u64) user_sregs.regs.gprs[i]; + memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, + sizeof(current->thread.acrs)); restore_access_regs(current->thread.acrs); - err = __copy_from_user(¤t->thread.fp_regs, &sregs->fpregs, - sizeof(_s390_fp_regs32)); - current->thread.fp_regs.fpc &= FPC_VALID_MASK; - if (err) - return err; + memcpy(¤t->thread.fp_regs, &user_sregs.fpregs, + sizeof(current->thread.fp_regs)); - restore_fp_regs(¤t->thread.fp_regs); - clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ + restore_fp_regs(current->thread.fp_regs.fprs); + clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -337,31 +224,29 @@ static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) for (i = 0; i < NUM_GPRS; i++) gprs_high[i] = regs->gprs[i] >> 32; - - return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); + if (__copy_to_user(uregs, &gprs_high, sizeof(gprs_high))) + return -EFAULT; + return 0; } static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) { __u32 gprs_high[NUM_GPRS]; - int err, i; + int i; - err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); - if (err) - return err; + if (__copy_from_user(&gprs_high, uregs, sizeof(gprs_high))) + return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; 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]; sigset_t set; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32)) goto badframe; set_current_blocked(&set); @@ -375,18 +260,12 @@ 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]; sigset_t set; - stack_t st; - __u32 ss_sp; - int err; - mm_segment_t old_fs = get_fs(); - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; set_current_blocked(&set); @@ -394,15 +273,8 @@ asmlinkage long sys32_rt_sigreturn(void) goto badframe; if (restore_sigregs_gprs_high(regs, frame->gprs_high)) goto badframe; - err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp); - st.ss_sp = compat_ptr(ss_sp); - err |= __get_user(st.ss_size, &frame->uc.uc_stack.ss_size); - err |= __get_user(st.ss_flags, &frame->uc.uc_stack.ss_flags); - if (err) + if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; - set_fs (KERNEL_DS); - do_sigaltstack((stack_t __force __user *)&st, NULL, regs->gprs[15]); - set_fs (old_fs); return regs->gprs[2]; badframe: force_sig(SIGSEGV, current); @@ -452,8 +324,6 @@ static int setup_frame32(int sig, struct k_sigaction *ka, sigset_t *set, struct pt_regs * regs) { sigframe32 __user *frame = get_sigframe(ka, regs, sizeof(sigframe32)); - if (!access_ok(VERIFY_WRITE, frame, sizeof(sigframe32))) - goto give_sigsegv; if (frame == (void __user *) -1UL) goto give_sigsegv; @@ -471,9 +341,9 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, (u16 __force __user *)(frame->retcode))) goto give_sigsegv; @@ -487,7 +357,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, regs->gprs[15] = (__force __u64) frame; /* Force 31 bit amode and default user address space control. */ regs->psw.mask = PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); regs->psw.addr = (__force __u64) ka->sa.sa_handler; @@ -501,6 +371,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* set extra registers only for synchronous signals */ regs->gprs[4] = regs->int_code & 127; regs->gprs[5] = regs->int_parm_long; + regs->gprs[6] = task_thread_info(current)->last_break; } /* Place signal number on stack to allow backtrace from handler. */ @@ -518,8 +389,6 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, { int err = 0; rt_sigframe32 __user *frame = get_sigframe(ka, regs, sizeof(rt_sigframe32)); - if (!access_ok(VERIFY_WRITE, frame, sizeof(rt_sigframe32))) - goto give_sigsegv; if (frame == (void __user *) -1UL) goto give_sigsegv; @@ -530,10 +399,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, /* Create the ucontext. */ err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->gprs[15]), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]); err |= save_sigregs32(regs, &frame->uc.uc_mcontext); err |= save_sigregs_gprs_high(regs, frame->gprs_high); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); @@ -543,11 +409,12 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; + regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; - err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, - (u16 __force __user *)(frame->retcode)); + regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE; + if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, + (u16 __force __user *)(frame->retcode))) + goto give_sigsegv; } /* Set up backchain. */ @@ -558,13 +425,14 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[15] = (__force __u64) frame; /* Force 31 bit amode and default user address space control. */ regs->psw.mask = PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (__u64) ka->sa.sa_handler; + regs->psw.addr = (__u64 __force) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); regs->gprs[3] = (__force __u64) &frame->info; regs->gprs[4] = (__force __u64) &frame->uc; + regs->gprs[5] = task_thread_info(current)->last_break; return 0; give_sigsegv: diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S deleted file mode 100644 index 9b9a805656b..00000000000 --- a/arch/s390/kernel/compat_wrapper.S +++ /dev/null @@ -1,1667 +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_open_wrapper) - llgtr %r2,%r2 # const char * - lgfr %r3,%r3 # int - lgfr %r4,%r4 # int - jg compat_sys_open # 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 - -ENTRY(sys32_lseek_wrapper) - llgfr %r2,%r2 # unsigned int - lgfr %r3,%r3 # off_t - llgfr %r4,%r4 # unsigned int - jg sys_lseek # 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_sigaction_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # const struct old_sigaction * - llgtr %r4,%r4 # struct old_sigaction32 * - jg sys32_sigaction # branch to system call - -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_getrusage_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct rusage_emu31 * - jg compat_sys_getrusage # 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_truncate_wrapper) - llgtr %r2,%r2 # const char * - lgfr %r3,%r3 # long - jg sys_truncate # branch to system call - -ENTRY(sys32_ftruncate_wrapper) - llgfr %r2,%r2 # unsigned int - llgfr %r3,%r3 # unsigned long - jg sys_ftruncate # 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_setitimer_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct itimerval_emu31 * - llgtr %r4,%r4 # struct itimerval_emu31 * - jg compat_sys_setitimer # branch to system call - -ENTRY(compat_sys_getitimer_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct itimerval_emu31 * - jg compat_sys_getitimer # 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(compat_sys_wait4_wrapper) - lgfr %r2,%r2 # pid_t - llgtr %r3,%r3 # unsigned int * - lgfr %r4,%r4 # int - llgtr %r5,%r5 # struct rusage * - jg compat_sys_wait4 # branch to system call - -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_ipc_wrapper) - llgfr %r2,%r2 # uint - lgfr %r3,%r3 # int - lgfr %r4,%r4 # int - lgfr %r5,%r5 # int - llgfr %r6,%r6 # u32 - jg sys32_ipc # 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(compat_sys_sigprocmask_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # compat_old_sigset_t * - llgtr %r4,%r4 # compat_old_sigset_t * - jg compat_sys_sigprocmask # branch to system call - -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(sys32_sched_rr_get_interval_wrapper) - lgfr %r2,%r2 # pid_t - llgtr %r3,%r3 # struct compat_timespec * - jg sys32_sched_rr_get_interval # branch to system call - -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_rt_sigaction_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # const struct sigaction_emu31 * - llgtr %r4,%r4 # const struct sigaction_emu31 * - llgfr %r5,%r5 # size_t - jg sys32_rt_sigaction # branch to system call - -ENTRY(sys32_rt_sigprocmask_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # old_sigset_emu31 * - llgtr %r4,%r4 # old_sigset_emu31 * - llgfr %r5,%r5 # size_t - jg sys32_rt_sigprocmask # branch to system call - -ENTRY(sys32_rt_sigpending_wrapper) - llgtr %r2,%r2 # sigset_emu31 * - llgfr %r3,%r3 # size_t - jg sys32_rt_sigpending # branch to system call - -ENTRY(compat_sys_rt_sigtimedwait_wrapper) - llgtr %r2,%r2 # const sigset_emu31_t * - llgtr %r3,%r3 # siginfo_emu31_t * - llgtr %r4,%r4 # const struct compat_timespec * - llgfr %r5,%r5 # size_t - jg compat_sys_rt_sigtimedwait # branch to system call - -ENTRY(sys32_rt_sigqueueinfo_wrapper) - lgfr %r2,%r2 # int - lgfr %r3,%r3 # int - llgtr %r4,%r4 # siginfo_emu31_t * - jg sys32_rt_sigqueueinfo # branch to system call - -ENTRY(compat_sys_rt_sigsuspend_wrapper) - llgtr %r2,%r2 # compat_sigset_t * - llgfr %r3,%r3 # compat_size_t - jg compat_sys_rt_sigsuspend - -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 - -ENTRY(sys32_sigaltstack_wrapper) - llgtr %r2,%r2 # const stack_emu31_t * - llgtr %r3,%r3 # stack_emu31_t * - jg sys32_sigaltstack - -ENTRY(sys32_sendfile_wrapper) - lgfr %r2,%r2 # int - lgfr %r3,%r3 # int - llgtr %r4,%r4 # __kernel_off_emu31_t * - llgfr %r5,%r5 # size_t - jg sys32_sendfile # 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_sysctl_wrapper) - llgtr %r2,%r2 # struct compat_sysctl_args * - jg compat_sys_sysctl - -ENTRY(sys32_fstat64_wrapper) - llgfr %r2,%r2 # unsigned long - llgtr %r3,%r3 # struct stat64 * - jg sys32_fstat64 # branch to system call - -ENTRY(compat_sys_futex_wrapper) - llgtr %r2,%r2 # u32 * - lgfr %r3,%r3 # int - lgfr %r4,%r4 # int - llgtr %r5,%r5 # struct compat_timespec * - llgtr %r6,%r6 # u32 * - lgf %r0,164(%r15) # int - stg %r0,160(%r15) - jg compat_sys_futex # 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_lookup_dcookie_wrapper) - sllg %r2,%r2,32 # get high word of 64bit dcookie - or %r2,%r3 # get low word of 64bit dcookie - llgtr %r3,%r4 # char * - llgfr %r4,%r5 # size_t - jg sys_lookup_dcookie - -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_waitid_wrapper) - lgfr %r2,%r2 # int - lgfr %r3,%r3 # pid_t - llgtr %r4,%r4 # siginfo_emu31_t * - lgfr %r5,%r5 # int - llgtr %r6,%r6 # struct rusage_emu31 * - jg compat_sys_waitid - -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(compat_sys_openat_wrapper) - llgfr %r2,%r2 # unsigned int - llgtr %r3,%r3 # const char * - lgfr %r4,%r4 # int - lgfr %r5,%r5 # int - jg compat_sys_openat - -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(compat_sys_set_robust_list_wrapper) - llgtr %r2,%r2 # struct compat_robust_list_head * - llgfr %r3,%r3 # size_t - jg compat_sys_set_robust_list - -ENTRY(compat_sys_get_robust_list_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # compat_uptr_t_t * - llgtr %r4,%r4 # compat_size_t * - jg compat_sys_get_robust_list - -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(compat_sys_vmsplice_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # compat_iovec * - llgfr %r4,%r4 # unsigned int - llgfr %r5,%r5 # unsigned int - jg compat_sys_vmsplice - -ENTRY(sys_getcpu_wrapper) - llgtr %r2,%r2 # unsigned * - llgtr %r3,%r3 # unsigned * - llgtr %r4,%r4 # struct getcpu_cache * - jg sys_getcpu - -ENTRY(compat_sys_epoll_pwait_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct compat_epoll_event * - lgfr %r4,%r4 # int - lgfr %r5,%r5 # int - llgtr %r6,%r6 # compat_sigset_t * - llgf %r0,164(%r15) # compat_size_t - stg %r0,160(%r15) - jg compat_sys_epoll_pwait - -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(compat_sys_signalfd_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # compat_sigset_t * - llgfr %r4,%r4 # compat_size_t - jg compat_sys_signalfd - -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(compat_sys_timerfd_settime_wrapper) - lgfr %r2,%r2 # int - lgfr %r3,%r3 # int - llgtr %r4,%r4 # struct compat_itimerspec * - llgtr %r5,%r5 # struct compat_itimerspec * - jg compat_sys_timerfd_settime - -ENTRY(compat_sys_timerfd_gettime_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct compat_itimerspec * - jg compat_sys_timerfd_gettime - -ENTRY(compat_sys_signalfd4_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # compat_sigset_t * - llgfr %r4,%r4 # compat_size_t - lgfr %r5,%r5 # int - jg compat_sys_signalfd4 - -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(sys32_sendfile64_wrapper) - lgfr %r2,%r2 # int - lgfr %r3,%r3 # int - llgtr %r4,%r4 # compat_loff_t * - lgfr %r5,%r5 # s32 - jg sys32_sendfile64 # branch to system call - -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(compat_sys_preadv_wrapper) - llgfr %r2,%r2 # unsigned long - llgtr %r3,%r3 # compat_iovec * - llgfr %r4,%r4 # unsigned long - llgfr %r5,%r5 # u32 - llgfr %r6,%r6 # u32 - jg compat_sys_preadv # branch to system call - -ENTRY(compat_sys_pwritev_wrapper) - llgfr %r2,%r2 # unsigned long - llgtr %r3,%r3 # compat_iovec * - llgfr %r4,%r4 # unsigned long - llgfr %r5,%r5 # u32 - llgfr %r6,%r6 # u32 - jg compat_sys_pwritev # branch to system call - -ENTRY(compat_sys_rt_tgsigqueueinfo_wrapper) - lgfr %r2,%r2 # compat_pid_t - lgfr %r3,%r3 # compat_pid_t - lgfr %r4,%r4 # int - llgtr %r5,%r5 # struct compat_siginfo * - jg compat_sys_rt_tgsigqueueinfo_wrapper # branch to system call - -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_fanotify_mark_wrapper) - lgfr %r2,%r2 # int - llgfr %r3,%r3 # unsigned int - sllg %r4,%r4,32 # get high word of 64bit mask - lr %r4,%r5 # get low word of 64bit mask - llgfr %r5,%r6 # unsigned int - llgt %r6,164(%r15) # char * - jg sys_fanotify_mark # 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_open_by_handle_at_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct file_handle __user * - lgfr %r4,%r4 # int - jg compat_sys_open_by_handle_at - -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..45cdb37aa6f --- /dev/null +++ b/arch/s390/kernel/compat_wrapper.c @@ -0,0 +1,216 @@ +/* + * Compat system 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); +COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index fb8d8781a01..a3b9150e680 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -13,41 +13,233 @@ #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/elf.h> +#include <linux/memblock.h> #include <asm/os_info.h> #include <asm/elf.h> #include <asm/ipl.h> +#include <asm/sclp.h> #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) #define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y)))) +static struct memblock_region oldmem_region; + +static struct memblock_type oldmem_type = { + .cnt = 1, + .max = 1, + .total_size = 0, + .regions = &oldmem_region, +}; + +#define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid) \ + for (i = 0, __next_mem_range(&i, nid, &memblock.physmem, \ + &oldmem_type, p_start, \ + p_end, p_nid); \ + i != (u64)ULLONG_MAX; \ + __next_mem_range(&i, nid, &memblock.physmem, \ + &oldmem_type, \ + p_start, p_end, p_nid)) + +struct dump_save_areas dump_save_areas; + /* - * Copy one page from "oldmem" + * Allocate and add a save area for a CPU + */ +struct save_area *dump_save_area_create(int cpu) +{ + struct save_area **save_areas, *save_area; + + save_area = kmalloc(sizeof(*save_area), GFP_KERNEL); + if (!save_area) + return NULL; + if (cpu + 1 > dump_save_areas.count) { + dump_save_areas.count = cpu + 1; + save_areas = krealloc(dump_save_areas.areas, + dump_save_areas.count * sizeof(void *), + GFP_KERNEL | __GFP_ZERO); + if (!save_areas) { + kfree(save_area); + return NULL; + } + dump_save_areas.areas = save_areas; + } + dump_save_areas.areas[cpu] = save_area; + return save_area; +} + +/* + * Return physical address for virtual address + */ +static inline void *load_real_addr(void *addr) +{ + unsigned long real_addr; + + asm volatile( + " lra %0,0(%1)\n" + " jz 0f\n" + " la %0,0\n" + "0:" + : "=a" (real_addr) : "a" (addr) : "cc"); + return (void *)real_addr; +} + +/* + * Copy real to virtual or real memory + */ +static int copy_from_realmem(void *dest, void *src, size_t count) +{ + unsigned long size; + + if (!count) + return 0; + if (!is_vmalloc_or_module_addr(dest)) + return memcpy_real(dest, src, count); + do { + size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK)); + if (memcpy_real(load_real_addr(dest), src, size)) + return -EFAULT; + count -= size; + dest += size; + src += size; + } while (count); + return 0; +} + +/* + * Pointer to ELF header in new kernel + */ +static void *elfcorehdr_newmem; + +/* + * Copy one page from zfcpdump "oldmem" + * + * For pages below HSA size memory from the HSA is copied. Otherwise + * real memory copy is used. + */ +static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize, + unsigned long src, int userbuf) +{ + int rc; + + if (src < sclp_get_hsa_size()) { + rc = memcpy_hsa(buf, src, csize, userbuf); + } else { + if (userbuf) + rc = copy_to_user_real((void __force __user *) buf, + (void *) src, csize); + else + rc = memcpy_real(buf, (void *) src, csize); + } + return rc ? rc : csize; +} + +/* + * Copy one page from kdump "oldmem" * * For the kdump reserved memory this functions performs a swap operation: * - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE]. * - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] */ -ssize_t copy_oldmem_page(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, int userbuf) -{ - unsigned long src; +static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize, + unsigned long src, int userbuf) - if (!csize) - return 0; +{ + int rc; - src = (pfn << PAGE_SHIFT) + offset; if (src < OLDMEM_SIZE) src += OLDMEM_BASE; else if (src > OLDMEM_BASE && src < OLDMEM_BASE + OLDMEM_SIZE) src -= OLDMEM_BASE; if (userbuf) - copy_to_user_real((void __force __user *) buf, (void *) src, - csize); + rc = copy_to_user_real((void __force __user *) buf, + (void *) src, csize); + else + rc = copy_from_realmem(buf, (void *) src, csize); + return (rc == 0) ? rc : csize; +} + +/* + * Copy one page from "oldmem" + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf) +{ + unsigned long src; + + if (!csize) + return 0; + src = (pfn << PAGE_SHIFT) + offset; + if (OLDMEM_BASE) + return copy_oldmem_page_kdump(buf, csize, src, userbuf); + else + return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf); +} + +/* + * Remap "oldmem" for kdump + * + * For the kdump reserved memory this functions performs a swap operation: + * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] + */ +static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long size_old; + int rc; + + if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) { + size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT)); + rc = remap_pfn_range(vma, from, + pfn + (OLDMEM_BASE >> PAGE_SHIFT), + size_old, prot); + if (rc || size == size_old) + return rc; + size -= size_old; + from += size_old; + pfn += size_old >> PAGE_SHIFT; + } + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Remap "oldmem" for zfcpdump + * + * We only map available memory above HSA size. Memory below HSA size + * is read on demand using the copy_oldmem_page() function. + */ +static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma, + unsigned long from, + unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long hsa_end = sclp_get_hsa_size(); + unsigned long size_hsa; + + if (pfn < hsa_end >> PAGE_SHIFT) { + size_hsa = min(size, hsa_end - (pfn << PAGE_SHIFT)); + if (size == size_hsa) + return 0; + size -= size_hsa; + from += size_hsa; + pfn += size_hsa >> PAGE_SHIFT; + } + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * Remap "oldmem" for kdump or zfcpdump + */ +int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + if (OLDMEM_BASE) + return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot); else - memcpy_real(buf, (void *) src, csize); - return csize; + return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size, + prot); } /* @@ -58,13 +250,23 @@ int copy_from_oldmem(void *dest, void *src, size_t count) unsigned long copied = 0; int rc; - if ((unsigned long) src < OLDMEM_SIZE) { - copied = min(count, OLDMEM_SIZE - (unsigned long) src); - rc = memcpy_real(dest, src + OLDMEM_BASE, copied); - if (rc) - return rc; + if (OLDMEM_BASE) { + if ((unsigned long) src < OLDMEM_SIZE) { + copied = min(count, OLDMEM_SIZE - (unsigned long) src); + rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied); + if (rc) + return rc; + } + } else { + unsigned long hsa_end = sclp_get_hsa_size(); + if ((unsigned long) src < hsa_end) { + copied = min(count, hsa_end - (unsigned long) src); + rc = memcpy_hsa(dest, (unsigned long) src, copied, 0); + if (rc) + return rc; + } } - return memcpy_real(dest + copied, src + copied, count - copied); + return copy_from_realmem(dest + copied, src + copied, count - copied); } /* @@ -81,19 +283,6 @@ static void *kzalloc_panic(int len) } /* - * Get memory layout and create hole for oldmem - */ -static struct mem_chunk *get_memory_layout(void) -{ - struct mem_chunk *chunk_array; - - chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk)); - detect_memory_layout(chunk_array); - create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE, CHUNK_CRASHK); - return chunk_array; -} - -/* * Initialize ELF note */ static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len, @@ -294,8 +483,8 @@ static int get_cpu_cnt(void) { int i, cpus = 0; - for (i = 0; zfcpdump_save_areas[i]; i++) { - if (zfcpdump_save_areas[i]->pref_reg == 0) + for (i = 0; i < dump_save_areas.count; i++) { + if (dump_save_areas.areas[i]->pref_reg == 0) continue; cpus++; } @@ -307,60 +496,33 @@ static int get_cpu_cnt(void) */ static int get_mem_chunk_cnt(void) { - struct mem_chunk *chunk_array, *mem_chunk; - int i, cnt = 0; + int cnt = 0; + u64 idx; - chunk_array = get_memory_layout(); - for (i = 0; i < MEMORY_CHUNKS; i++) { - mem_chunk = &chunk_array[i]; - if (chunk_array[i].type != CHUNK_READ_WRITE && - chunk_array[i].type != CHUNK_READ_ONLY) - continue; - if (mem_chunk->size == 0) - continue; + for_each_dump_mem_range(idx, NUMA_NO_NODE, NULL, NULL, NULL) cnt++; - } - kfree(chunk_array); return cnt; } /* - * Relocate pointer in order to allow vmcore code access the data - */ -static inline unsigned long relocate(unsigned long addr) -{ - return OLDMEM_BASE + addr; -} - -/* * Initialize ELF loads (new kernel) */ -static int loads_init(Elf64_Phdr *phdr, u64 loads_offset) +static void loads_init(Elf64_Phdr *phdr, u64 loads_offset) { - struct mem_chunk *chunk_array, *mem_chunk; - int i; + phys_addr_t start, end; + u64 idx; - chunk_array = get_memory_layout(); - for (i = 0; i < MEMORY_CHUNKS; i++) { - mem_chunk = &chunk_array[i]; - if (mem_chunk->size == 0) - break; - if (chunk_array[i].type != CHUNK_READ_WRITE && - chunk_array[i].type != CHUNK_READ_ONLY) - continue; - else - phdr->p_filesz = mem_chunk->size; + for_each_dump_mem_range(idx, NUMA_NO_NODE, &start, &end, NULL) { + phdr->p_filesz = end - start; phdr->p_type = PT_LOAD; - phdr->p_offset = mem_chunk->addr; - phdr->p_vaddr = mem_chunk->addr; - phdr->p_paddr = mem_chunk->addr; - phdr->p_memsz = mem_chunk->size; + phdr->p_offset = start; + phdr->p_vaddr = start; + phdr->p_paddr = start; + phdr->p_memsz = end - start; phdr->p_flags = PF_R | PF_W | PF_X; phdr->p_align = PAGE_SIZE; phdr++; } - kfree(chunk_array); - return i; } /* @@ -374,8 +536,8 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) ptr = nt_prpsinfo(ptr); - for (i = 0; zfcpdump_save_areas[i]; i++) { - sa = zfcpdump_save_areas[i]; + for (i = 0; i < dump_save_areas.count; i++) { + sa = dump_save_areas.areas[i]; if (sa->pref_reg == 0) continue; ptr = fill_cpu_elf_notes(ptr, sa); @@ -383,7 +545,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) ptr = nt_vmcoreinfo(ptr); memset(phdr, 0, sizeof(*phdr)); phdr->p_type = PT_NOTE; - phdr->p_offset = relocate(notes_offset); + phdr->p_offset = notes_offset; phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start); phdr->p_memsz = phdr->p_filesz; return ptr; @@ -392,7 +554,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) /* * Create ELF core header (new kernel) */ -static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) +int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { Elf64_Phdr *phdr_notes, *phdr_loads; int mem_chunk_cnt; @@ -400,6 +562,23 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) u32 alloc_size; u64 hdr_off; + /* If we are not in kdump or zfcpdump mode return */ + if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP) + return 0; + /* If elfcorehdr= has been passed via cmdline, we use that one */ + if (elfcorehdr_addr != ELFCORE_ADDR_MAX) + return 0; + /* If we cannot get HSA size for zfcpdump return error */ + if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size()) + return -ENODEV; + + /* For kdump, exclude previous crashkernel memory */ + if (OLDMEM_BASE) { + oldmem_region.base = OLDMEM_BASE; + oldmem_region.size = OLDMEM_SIZE; + oldmem_type.total_size = OLDMEM_SIZE; + } + mem_chunk_cnt = get_mem_chunk_cnt(); alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + @@ -417,27 +596,52 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); /* Init loads */ hdr_off = PTR_DIFF(ptr, hdr); - loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off); - *elfcorebuf_sz = hdr_off; - *elfcorebuf = (void *) relocate((unsigned long) hdr); - BUG_ON(*elfcorebuf_sz > alloc_size); + loads_init(phdr_loads, hdr_off); + *addr = (unsigned long long) hdr; + elfcorehdr_newmem = hdr; + *size = (unsigned long long) hdr_off; + BUG_ON(elfcorehdr_size > alloc_size); + return 0; } /* - * Create kdump ELF core header in new kernel, if it has not been passed via - * the "elfcorehdr" kernel parameter + * Free ELF core header (new kernel) */ -static int setup_kdump_elfcorehdr(void) +void elfcorehdr_free(unsigned long long addr) { - size_t elfcorebuf_sz; - char *elfcorebuf; + if (!elfcorehdr_newmem) + return; + kfree((void *)(unsigned long)addr); +} - if (!OLDMEM_BASE || is_kdump_kernel()) - return -EINVAL; - s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz); - elfcorehdr_addr = (unsigned long long) elfcorebuf; - elfcorehdr_size = elfcorebuf_sz; - return 0; +/* + * Read from ELF header + */ +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + void *src = (void *)(unsigned long)*ppos; + + src = elfcorehdr_newmem ? src : src - OLDMEM_BASE; + memcpy(buf, src, count); + *ppos += count; + return count; } -subsys_initcall(setup_kdump_elfcorehdr); +/* + * Read from ELF notes data + */ +ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) +{ + void *src = (void *)(unsigned long)*ppos; + int rc; + + if (elfcorehdr_newmem) { + memcpy(buf, src, count); + } else { + rc = copy_from_oldmem(buf, src, count); + if (rc) + return rc; + } + *ppos += count; + return count; +} diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 4e8215e0d4b..ee8390da6ea 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -611,7 +611,7 @@ debug_open(struct inode *inode, struct file *file) debug_info_t *debug_info, *debug_info_snapshot; mutex_lock(&debug_mutex); - debug_info = file->f_path.dentry->d_inode->i_private; + debug_info = file_inode(file)->i_private; /* find debug view */ for (i = 0; i < DEBUG_MAX_VIEWS; i++) { if (!debug_info->views[i]) @@ -867,7 +867,7 @@ static inline void debug_finish_entry(debug_info_t * id, debug_entry_t* active, int level, int exception) { - active->id.stck = get_clock(); + active->id.stck = get_tod_clock_fast(); active->id.fields.cpuid = smp_processor_id(); active->caller = __builtin_return_address(0); active->id.fields.exception = exception; @@ -889,7 +889,7 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, +s390dbf_procactive(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index a7f9abd98cf..993efe6a887 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -23,6 +23,7 @@ #include <linux/kdebug.h> #include <asm/uaccess.h> +#include <asm/dis.h> #include <asm/io.h> #include <linux/atomic.h> #include <asm/mathemu.h> @@ -37,17 +38,6 @@ #define ONELONG "%016lx: " #endif /* CONFIG_64BIT */ -#define OPERAND_GPR 0x1 /* Operand printed as %rx */ -#define OPERAND_FPR 0x2 /* Operand printed as %fx */ -#define OPERAND_AR 0x4 /* Operand printed as %ax */ -#define OPERAND_CR 0x8 /* Operand printed as %cx */ -#define OPERAND_DISP 0x10 /* Operand printed as displacement */ -#define OPERAND_BASE 0x20 /* Operand printed as base register */ -#define OPERAND_INDEX 0x40 /* Operand printed as index register */ -#define OPERAND_PCREL 0x80 /* Operand printed as pc-relative symbol */ -#define OPERAND_SIGNED 0x100 /* Operand printed as signed value */ -#define OPERAND_LENGTH 0x200 /* Operand printed as length (+1) */ - enum { UNUSED, /* Indicates the end of the operand list */ R_8, /* GPR starting at position 8 */ @@ -155,19 +145,7 @@ enum { INSTR_S_00, INSTR_S_RD, }; -struct operand { - int bits; /* The number of bits in the operand. */ - int shift; /* The number of bits to shift. */ - int flags; /* One bit syntax flags. */ -}; - -struct insn { - const char name[5]; - unsigned char opfrag; - unsigned char format; -}; - -static const struct operand operands[] = +static const struct s390_operand operands[] = { [UNUSED] = { 0, 0, 0 }, [R_8] = { 4, 8, OPERAND_GPR }, @@ -479,7 +457,7 @@ static char *long_insn_name[] = { [LONG_INSN_PCISTB] = "pcistb", }; -static struct insn opcode[] = { +static struct s390_insn opcode[] = { #ifdef CONFIG_64BIT { "bprp", 0xc5, INSTR_MII_UPI }, { "bpp", 0xc7, INSTR_SMI_U0RDP }, @@ -668,7 +646,7 @@ static struct insn opcode[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_01[] = { +static struct s390_insn opcode_01[] = { #ifdef CONFIG_64BIT { "ptff", 0x04, INSTR_E }, { "pfpo", 0x0a, INSTR_E }, @@ -684,7 +662,7 @@ static struct insn opcode_01[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_a5[] = { +static struct s390_insn opcode_a5[] = { #ifdef CONFIG_64BIT { "iihh", 0x00, INSTR_RI_RU }, { "iihl", 0x01, INSTR_RI_RU }, @@ -706,7 +684,7 @@ static struct insn opcode_a5[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_a7[] = { +static struct s390_insn opcode_a7[] = { #ifdef CONFIG_64BIT { "tmhh", 0x02, INSTR_RI_RU }, { "tmhl", 0x03, INSTR_RI_RU }, @@ -728,7 +706,7 @@ static struct insn opcode_a7[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_aa[] = { +static struct s390_insn opcode_aa[] = { #ifdef CONFIG_64BIT { { 0, LONG_INSN_RINEXT }, 0x00, INSTR_RI_RI }, { "rion", 0x01, INSTR_RI_RI }, @@ -739,7 +717,7 @@ static struct insn opcode_aa[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_b2[] = { +static struct s390_insn opcode_b2[] = { #ifdef CONFIG_64BIT { "stckf", 0x7c, INSTR_S_RD }, { "lpp", 0x80, INSTR_S_RD }, @@ -840,7 +818,6 @@ static struct insn opcode_b2[] = { { "stcke", 0x78, INSTR_S_RD }, { "sacf", 0x79, INSTR_S_RD }, { "stsi", 0x7d, INSTR_S_RD }, - { "spp", 0x80, INSTR_S_RD }, { "srnm", 0x99, INSTR_S_RD }, { "stfpc", 0x9c, INSTR_S_RD }, { "lfpc", 0x9d, INSTR_S_RD }, @@ -852,7 +829,7 @@ static struct insn opcode_b2[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_b3[] = { +static struct s390_insn opcode_b3[] = { #ifdef CONFIG_64BIT { "maylr", 0x38, INSTR_RRF_F0FF }, { "mylr", 0x39, INSTR_RRF_F0FF }, @@ -1035,7 +1012,7 @@ static struct insn opcode_b3[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_b9[] = { +static struct s390_insn opcode_b9[] = { #ifdef CONFIG_64BIT { "lpgr", 0x00, INSTR_RRE_RR }, { "lngr", 0x01, INSTR_RRE_RR }, @@ -1168,7 +1145,7 @@ static struct insn opcode_b9[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c0[] = { +static struct s390_insn opcode_c0[] = { #ifdef CONFIG_64BIT { "lgfi", 0x01, INSTR_RIL_RI }, { "xihf", 0x06, INSTR_RIL_RU }, @@ -1188,7 +1165,7 @@ static struct insn opcode_c0[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c2[] = { +static struct s390_insn opcode_c2[] = { #ifdef CONFIG_64BIT { "msgfi", 0x00, INSTR_RIL_RI }, { "msfi", 0x01, INSTR_RIL_RI }, @@ -1206,7 +1183,7 @@ static struct insn opcode_c2[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c4[] = { +static struct s390_insn opcode_c4[] = { #ifdef CONFIG_64BIT { "llhrl", 0x02, INSTR_RIL_RP }, { "lghrl", 0x04, INSTR_RIL_RP }, @@ -1223,7 +1200,7 @@ static struct insn opcode_c4[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c6[] = { +static struct s390_insn opcode_c6[] = { #ifdef CONFIG_64BIT { "exrl", 0x00, INSTR_RIL_RP }, { "pfdrl", 0x02, INSTR_RIL_UP }, @@ -1241,7 +1218,7 @@ static struct insn opcode_c6[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_c8[] = { +static struct s390_insn opcode_c8[] = { #ifdef CONFIG_64BIT { "mvcos", 0x00, INSTR_SSF_RRDRD }, { "ectg", 0x01, INSTR_SSF_RRDRD }, @@ -1252,7 +1229,7 @@ static struct insn opcode_c8[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_cc[] = { +static struct s390_insn opcode_cc[] = { #ifdef CONFIG_64BIT { "brcth", 0x06, INSTR_RIL_RP }, { "aih", 0x08, INSTR_RIL_RI }, @@ -1264,7 +1241,7 @@ static struct insn opcode_cc[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_e3[] = { +static struct s390_insn opcode_e3[] = { #ifdef CONFIG_64BIT { "ltg", 0x02, INSTR_RXY_RRRD }, { "lrag", 0x03, INSTR_RXY_RRRD }, @@ -1370,7 +1347,7 @@ static struct insn opcode_e3[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_e5[] = { +static struct s390_insn opcode_e5[] = { #ifdef CONFIG_64BIT { "strag", 0x02, INSTR_SSE_RDRD }, { "mvhhi", 0x44, INSTR_SIL_RDI }, @@ -1392,7 +1369,7 @@ static struct insn opcode_e5[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_eb[] = { +static struct s390_insn opcode_eb[] = { #ifdef CONFIG_64BIT { "lmg", 0x04, INSTR_RSY_RRRD }, { "srag", 0x0a, INSTR_RSY_RRRD }, @@ -1466,7 +1443,7 @@ static struct insn opcode_eb[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_ec[] = { +static struct s390_insn opcode_ec[] = { #ifdef CONFIG_64BIT { "brxhg", 0x44, INSTR_RIE_RRP }, { "brxlg", 0x45, INSTR_RIE_RRP }, @@ -1505,7 +1482,7 @@ static struct insn opcode_ec[] = { { "", 0, INSTR_INVALID } }; -static struct insn opcode_ed[] = { +static struct s390_insn opcode_ed[] = { #ifdef CONFIG_64BIT { "mayl", 0x38, INSTR_RXF_FRRDF }, { "myl", 0x39, INSTR_RXF_FRRDF }, @@ -1573,7 +1550,7 @@ static struct insn opcode_ed[] = { /* Extracts an operand value from an instruction. */ static unsigned int extract_operand(unsigned char *code, - const struct operand *operand) + const struct s390_operand *operand) { unsigned int val; int bits; @@ -1609,16 +1586,11 @@ static unsigned int extract_operand(unsigned char *code, return val; } -static inline int insn_length(unsigned char code) -{ - return ((((int) code + 64) >> 7) + 1) << 1; -} - -static struct insn *find_insn(unsigned char *code) +struct s390_insn *find_insn(unsigned char *code) { unsigned char opfrag = code[1]; unsigned char opmask; - struct insn *table; + struct s390_insn *table; switch (code[0]) { case 0x01: @@ -1697,34 +1669,35 @@ static struct insn *find_insn(unsigned char *code) * insn_to_mnemonic - decode an s390 instruction * @instruction: instruction to decode * @buf: buffer to fill with mnemonic + * @len: length of buffer * * Decode the instruction at @instruction and store the corresponding - * mnemonic into @buf. + * mnemonic into @buf of length @len. * @buf is left unchanged if the instruction could not be decoded. * Returns: * %0 on success, %-ENOENT if the instruction was not found. */ -int insn_to_mnemonic(unsigned char *instruction, char buf[8]) +int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len) { - struct insn *insn; + struct s390_insn *insn; insn = find_insn(instruction); if (!insn) return -ENOENT; if (insn->name[0] == '\0') - snprintf(buf, sizeof(buf), "%s", + snprintf(buf, len, "%s", long_insn_name[(int) insn->name[1]]); else - snprintf(buf, sizeof(buf), "%.5s", insn->name); + snprintf(buf, len, "%.5s", insn->name); return 0; } EXPORT_SYMBOL_GPL(insn_to_mnemonic); static int print_insn(char *buffer, unsigned char *code, unsigned long addr) { - struct insn *insn; + struct s390_insn *insn; const unsigned char *ops; - const struct operand *operand; + const struct s390_operand *operand; unsigned int value; char separator; char *ptr; @@ -1862,6 +1835,8 @@ void print_fn_code(unsigned char *code, unsigned long len) while (len) { ptr = buffer; opsize = insn_length(*code); + if (opsize > len) + break; ptr += sprintf(ptr, "%p: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c new file mode 100644 index 00000000000..acb412442e5 --- /dev/null +++ b/arch/s390/kernel/dumpstack.c @@ -0,0 +1,217 @@ +/* + * Stack dumping functions + * + * Copyright IBM Corp. 1999, 2013 + */ + +#include <linux/kallsyms.h> +#include <linux/hardirq.h> +#include <linux/kprobes.h> +#include <linux/utsname.h> +#include <linux/export.h> +#include <linux/kdebug.h> +#include <linux/ptrace.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <asm/processor.h> +#include <asm/debug.h> +#include <asm/dis.h> +#include <asm/ipl.h> + +#ifndef CONFIG_64BIT +#define LONG "%08lx " +#define FOURLONG "%08lx %08lx %08lx %08lx\n" +static int kstack_depth_to_print = 12; +#else /* CONFIG_64BIT */ +#define LONG "%016lx " +#define FOURLONG "%016lx %016lx %016lx %016lx\n" +static int kstack_depth_to_print = 20; +#endif /* CONFIG_64BIT */ + +/* + * For show_trace we have tree different stack to consider: + * - the panic stack which is used if the kernel stack has overflown + * - the asynchronous interrupt stack (cpu related) + * - the synchronous kernel stack (process related) + * The stack trace can start at any of the three stack and can potentially + * touch all of them. The order is: panic stack, async stack, sync stack. + */ +static unsigned long +__show_trace(unsigned long sp, unsigned long low, unsigned long high) +{ + struct stack_frame *sf; + struct pt_regs *regs; + unsigned long addr; + + while (1) { + sp = sp & PSW_ADDR_INSN; + if (sp < low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + addr = sf->gprs[8] & PSW_ADDR_INSN; + printk("([<%016lx>] %pSR)\n", addr, (void *)addr); + /* Follow the backchain. */ + while (1) { + low = sp; + sp = sf->back_chain & PSW_ADDR_INSN; + if (!sp) + break; + if (sp <= low || sp > high - sizeof(*sf)) + return sp; + sf = (struct stack_frame *) sp; + addr = sf->gprs[8] & PSW_ADDR_INSN; + printk(" [<%016lx>] %pSR\n", addr, (void *)addr); + } + /* Zero backchain detected, check for interrupt frame. */ + sp = (unsigned long) (sf + 1); + if (sp <= low || sp > high - sizeof(*regs)) + return sp; + regs = (struct pt_regs *) sp; + addr = regs->psw.addr & PSW_ADDR_INSN; + printk(" [<%016lx>] %pSR\n", addr, (void *)addr); + low = sp; + sp = regs->gprs[15]; + } +} + +static void show_trace(struct task_struct *task, unsigned long *stack) +{ + const unsigned long frame_size = + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + register unsigned long __r15 asm ("15"); + unsigned long sp; + + sp = (unsigned long) stack; + if (!sp) + sp = task ? task->thread.ksp : __r15; + printk("Call Trace:\n"); +#ifdef CONFIG_CHECK_STACK + sp = __show_trace(sp, + S390_lowcore.panic_stack + frame_size - 4096, + S390_lowcore.panic_stack + frame_size); +#endif + sp = __show_trace(sp, + S390_lowcore.async_stack + frame_size - ASYNC_SIZE, + S390_lowcore.async_stack + frame_size); + if (task) + __show_trace(sp, (unsigned long) task_stack_page(task), + (unsigned long) task_stack_page(task) + THREAD_SIZE); + else + __show_trace(sp, S390_lowcore.thread_info, + S390_lowcore.thread_info + THREAD_SIZE); + if (!task) + task = current; + debug_show_held_locks(task); +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + register unsigned long *__r15 asm ("15"); + unsigned long *stack; + int i; + + if (!sp) + stack = task ? (unsigned long *) task->thread.ksp : __r15; + else + stack = sp; + + for (i = 0; i < kstack_depth_to_print; i++) { + if (((addr_t) stack & (THREAD_SIZE-1)) == 0) + break; + if ((i * sizeof(long) % 32) == 0) + printk("%s ", i == 0 ? "" : "\n"); + printk(LONG, *stack++); + } + printk("\n"); + show_trace(task, sp); +} + +static void show_last_breaking_event(struct pt_regs *regs) +{ +#ifdef CONFIG_64BIT + printk("Last Breaking-Event-Address:\n"); + printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]); +#endif +} + +static inline int mask_bits(struct pt_regs *regs, unsigned long bits) +{ + return (regs->psw.mask & bits) / ((~bits + 1) & bits); +} + +void show_registers(struct pt_regs *regs) +{ + char *mode; + + mode = user_mode(regs) ? "User" : "Krnl"; + printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr); + if (!user_mode(regs)) + printk(" (%pSR)", (void *)regs->psw.addr); + printk("\n"); + printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " + "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), + mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), + mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), + mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), + mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), + mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); +#ifdef CONFIG_64BIT + printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); +#endif + printk("\n%s GPRS: " FOURLONG, mode, + regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); + printk(" " FOURLONG, + regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); + printk(" " FOURLONG, + regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); + printk(" " FOURLONG, + regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); + show_code(regs); +} + +void show_regs(struct pt_regs *regs) +{ + show_regs_print_info(KERN_DEFAULT); + show_registers(regs); + /* Show stack backtrace if pt_regs is from kernel mode */ + if (!user_mode(regs)) + show_trace(NULL, (unsigned long *) regs->gprs[15]); + show_last_breaking_event(regs); +} + +static DEFINE_SPINLOCK(die_lock); + +void die(struct pt_regs *regs, const char *str) +{ + static int die_counter; + + oops_enter(); + lgr_info_log(); + debug_stop_all(); + console_verbose(); + spin_lock_irq(&die_lock); + bust_spinlocks(1); + printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); + print_modules(); + show_regs(regs); + bust_spinlocks(0); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + spin_unlock_irq(&die_lock); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception: panic_on_oops"); + oops_exit(); + do_exit(SIGSEGV); +} diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 1f0eee9e7da..0dff972a169 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -47,10 +47,10 @@ static void __init reset_tod_clock(void) { u64 time; - if (store_clock(&time) == 0) + if (store_tod_clock(&time) == 0) return; /* TOD clock not running. Set the clock to Unix Epoch. */ - if (set_clock(TOD_UNIX_EPOCH) != 0 || store_clock(&time) != 0) + if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0) disabled_wait(0); sched_clock_base_cc = TOD_UNIX_EPOCH; @@ -173,7 +173,7 @@ static noinline __init void create_kernel_nss(void) } /* re-initialize cputime accounting. */ - sched_clock_base_cc = get_clock(); + sched_clock_base_cc = get_tod_clock(); S390_lowcore.last_update_clock = sched_clock_base_cc; S390_lowcore.last_update_timer = 0x7fffffffffffffffULL; S390_lowcore.user_timer = 0; @@ -206,6 +206,7 @@ static noinline __init void clear_bss_section(void) */ static noinline __init void init_kernel_storage_key(void) { +#if PAGE_DEFAULT_KEY unsigned long end_pfn, init_pfn; end_pfn = PFN_UP(__pa(&_end)); @@ -213,6 +214,7 @@ static noinline __init void init_kernel_storage_key(void) for (init_pfn = 0 ; init_pfn < end_pfn; init_pfn++) page_set_storage_key(init_pfn << PAGE_SHIFT, PAGE_DEFAULT_KEY, 0); +#endif } static __initdata char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE); @@ -256,13 +258,19 @@ static __init void setup_topology(void) static void early_pgm_check_handler(void) { const struct exception_table_entry *fixup; + unsigned long cr0, cr0_new; unsigned long addr; addr = S390_lowcore.program_old_psw.addr; fixup = search_exception_tables(addr & PSW_ADDR_INSN); if (!fixup) disabled_wait(0); + /* Disable low address protection before storing into lowcore. */ + __ctl_store(cr0, 0, 0); + cr0_new = cr0 & ~(1UL << 28); + __ctl_load(cr0_new, 0, 0); S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE; + __ctl_load(cr0, 0, 0); } static noinline __init void setup_lowcore_early(void) @@ -378,14 +386,14 @@ 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_SPP; + 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 } @@ -481,8 +489,7 @@ void __init startup_init(void) detect_diag44(); detect_machine_facilities(); setup_topology(); - sclp_facilities_detect(); - detect_memory_layout(memory_chunk); + sclp_early_detect(); #ifdef CONFIG_DYNAMIC_FTRACE S390_lowcore.ftrace_func = (unsigned long)ftrace_caller; #endif diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 55022852326..70203265196 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <asm/processor.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ptrace.h> @@ -18,6 +19,7 @@ #include <asm/unistd.h> #include <asm/page.h> #include <asm/sigp.h> +#include <asm/irq.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 4 @@ -36,15 +38,15 @@ __PT_R13 = __PT_GPRS + 524 __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_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_MCCK_PENDING) -_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ - _TIF_SYSCALL_TRACEPOINT) - STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT +STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE + +_TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) +_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE) +_PIF_WORK = (_PIF_PER_TRAP) #define BASED(name) name-system_call(%r13) @@ -97,10 +99,10 @@ STACK_SIZE = 1 << STACK_SHIFT sra %r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: l %r15,\stack # load target stack -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro ADD64 high,low,timer @@ -150,18 +152,14 @@ ENTRY(__switch_to) l %r4,__THREAD_info(%r2) # get thread_info of prev l %r5,__THREAD_info(%r3) # get thread_info of next lr %r15,%r5 - ahi %r15,STACK_SIZE # end of kernel stack of next + ahi %r15,STACK_INIT # end of kernel stack of next st %r3,__LC_CURRENT # store task struct of next st %r5,__LC_THREAD_INFO # store thread info of next st %r15,__LC_KERNEL_STACK # store end of kernel stack 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? - 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 -0: lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task + lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 __critical_start: @@ -176,9 +174,9 @@ sysc_stm: stm %r8,%r15,__LC_SAVE_AREA_SYNC l %r12,__LC_THREAD_INFO l %r13,__LC_SVC_NEW_PSW+4 + lhi %r14,_PIF_SYSCALL sysc_per: l %r15,__LC_KERNEL_STACK - ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs sysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER @@ -186,8 +184,9 @@ sysc_vtime: mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(8,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC + st %r14,__PT_FLAGS(%r11) sysc_do_svc: - oi __TI_flags+3(%r12),_TIF_SYSCALL + l %r10,__TI_sysc_table(%r12) # 31 bit system call table lh %r8,__PT_INT_CODE+2(%r11) sla %r8,2 # shift and test for svc0 jnz sysc_nr_ok @@ -198,12 +197,11 @@ sysc_do_svc: lr %r8,%r1 sla %r8,2 sysc_nr_ok: - l %r10,BASED(.Lsys_call_table) # 31 bit system call table xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) st %r2,__PT_ORIG_GPR2(%r11) st %r7,STACK_FRAME_OVERHEAD(%r15) l %r9,0(%r8,%r10) # get system call addr. - tm __TI_flags+2(%r12),_TIF_TRACE >> 8 + tm __TI_flags+3(%r12),_TIF_TRACE jnz sysc_tracesys basr %r14,%r9 # call sys_xxxx st %r2,__PT_R2(%r11) # store return value @@ -213,9 +211,12 @@ sysc_return: sysc_tif: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno sysc_restore - tm __TI_flags+3(%r12),_TIF_WORK_SVC - jnz sysc_work # check for work - ni __TI_flags+3(%r12),255-_TIF_SYSCALL + tm __PT_FLAGS+3(%r11),_PIF_WORK + jnz sysc_work + tm __TI_flags+3(%r12),_TIF_WORK + jnz sysc_work # check for thread work + tm __LC_CPU_FLAGS+3,_CIF_WORK + jnz sysc_work sysc_restore: mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) stpt __LC_EXIT_TIMER @@ -227,16 +228,18 @@ sysc_done: # One of the work bits is on. Find out which one. # sysc_work: - tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+3,_CIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+3(%r12),_TIF_NEED_RESCHED jo sysc_reschedule - tm __TI_flags+3(%r12),_TIF_PER_TRAP + tm __PT_FLAGS+3(%r11),_PIF_PER_TRAP jo sysc_singlestep tm __TI_flags+3(%r12),_TIF_SIGPENDING jo sysc_sigpending tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME jo sysc_notify_resume + tm __LC_CPU_FLAGS+3,_CIF_ASCE + jo sysc_uaccess j sysc_return # beware of critical section cleanup # @@ -248,7 +251,7 @@ sysc_reschedule: br %r1 # call schedule # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # sysc_mcck_pending: l %r1,BASED(.Lhandle_mcck) @@ -256,15 +259,24 @@ sysc_mcck_pending: br %r1 # TIF bit will be cleared by handler # +# _CIF_ASCE is set, load user space asce +# +sysc_uaccess: + ni __LC_CPU_FLAGS+3,255-_CIF_ASCE + lctl %c1,%c1,__LC_USER_ASCE # load primary asce + j sysc_return + +# # _TIF_SIGPENDING is set, call do_signal # sysc_sigpending: lr %r2,%r11 # pass pointer to pt_regs l %r1,BASED(.Ldo_signal) basr %r14,%r1 # call do_signal - tm __TI_flags+3(%r12),_TIF_SYSCALL + tm __PT_FLAGS+3(%r11),_PIF_SYSCALL jno sysc_return lm %r2,%r7,__PT_R2(%r11) # load svc arguments + l %r10,__TI_sysc_table(%r12) # 31 bit system call table xr %r8,%r8 # svc 0 returns -ENOSYS clc __PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2) jnl sysc_nr_ok # invalid svc number -> do svc 0 @@ -282,10 +294,10 @@ sysc_notify_resume: br %r1 # call do_notify_resume # -# _TIF_PER_TRAP is set, call do_per_trap +# _PIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+3(%r12),255-_TIF_PER_TRAP + ni __PT_FLAGS+3(%r11),255-_PIF_PER_TRAP lr %r2,%r11 # pass pointer to pt_regs l %r1,BASED(.Ldo_per_trap) la %r14,BASED(sysc_return) @@ -315,7 +327,7 @@ sysc_tracego: basr %r14,%r9 # call sys_xxx st %r2,__PT_R2(%r11) # store return value sysc_tracenogo: - tm __TI_flags+2(%r12),_TIF_TRACE >> 8 + tm __TI_flags+3(%r12),_TIF_TRACE jz sysc_return l %r1,BASED(.Ltrace_exit) lr %r2,%r11 # pass pointer to pt_regs @@ -359,25 +371,26 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jnz pgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER l %r15,__LC_KERNEL_STACK -2: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC stm %r8,%r9,__PT_PSW(%r11) mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC mvc __PT_INT_PARM_LONG(4,%r11),__LC_TRANS_EXC_CODE + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) tm __LC_PGM_ILC+3,0x80 # check for per exception jz 0f l %r1,__TI_task(%r12) tmh %r8,0x0001 # kernel per event ? jz pgm_kprobe - oi __TI_flags+3(%r12),_TIF_PER_TRAP + oi __PT_FLAGS+3(%r11),_PIF_PER_TRAP mvc __THREAD_per_address(4,%r1),__LC_PER_ADDRESS - mvc __THREAD_per_cause(2,%r1),__LC_PER_CAUSE - mvc __THREAD_per_paid(1,%r1),__LC_PER_PAID + mvc __THREAD_per_cause(2,%r1),__LC_PER_CODE + mvc __THREAD_per_paid(1,%r1),__LC_PER_ACCESS_ID 0: REENABLE_IRQS xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) l %r1,BASED(.Ljump_table) @@ -405,9 +418,9 @@ pgm_kprobe: # single stepped system call # pgm_svcper: - oi __TI_flags+3(%r12),_TIF_PER_TRAP mvc __LC_RETURN_PSW(4),__LC_SVC_NEW_PSW mvc __LC_RETURN_PSW+4(4),BASED(.Lsysc_per) + lhi %r14,_PIF_SYSCALL | _PIF_PER_TRAP lpsw __LC_RETURN_PSW # branch to sysc_per and enable irqs /* @@ -429,17 +442,33 @@ io_skip: stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) +io_loop: l %r1,BASED(.Ldo_IRQ) lr %r2,%r11 # pass pointer to pt_regs + lhi %r3,IO_INTERRUPT + tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? + jz io_call + lhi %r3,THIN_INTERRUPT +io_call: basr %r14,%r1 # call do_IRQ + tm __LC_MACHINE_FLAGS+2,0x10 # MACHINE_FLAG_LPAR + jz io_return + tpi 0 + jz io_return + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + j io_loop io_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON io_tif: - tm __TI_flags+3(%r12),_TIF_WORK_INT + tm __TI_flags+3(%r12),_TIF_WORK jnz io_work # there is work to do (signals etc.) + tm __LC_CPU_FLAGS+3,_CIF_WORK + jnz io_work io_restore: mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) stpt __LC_EXIT_TIMER @@ -449,7 +478,7 @@ io_done: # # There is work todo, find out in which context we have been interrupted: -# 1) if we return to user space we can do all _TIF_WORK_INT work +# 1) if we return to user space we can do all _TIF_WORK work # 2) if we return to kernel code and preemptive scheduling is enabled check # the preemption counter and if it is zero call preempt_schedule_irq # Before any work can be done, a switch to the kernel stack is required. @@ -485,7 +514,6 @@ io_work: # io_work_user: l %r1,__LC_KERNEL_STACK - ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -493,11 +521,9 @@ io_work_user: # # One of the work bits is on. Find out which one. -# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED -# and _TIF_MCCK_PENDING # io_work_tif: - tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+3(%r12),_CIF_MCCK_PENDING jo io_mcck_pending tm __TI_flags+3(%r12),_TIF_NEED_RESCHED jo io_reschedule @@ -505,10 +531,12 @@ io_work_tif: jo io_sigpending tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME jo io_notify_resume + tm __LC_CPU_FLAGS+3,_CIF_ASCE + jo io_uaccess j io_return # beware of critical section cleanup # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # io_mcck_pending: # TRACE_IRQS_ON already done at io_return @@ -518,6 +546,14 @@ io_mcck_pending: j io_return # +# _CIF_ASCE is set, load user space asce +# +io_uaccess: + ni __LC_CPU_FLAGS+3,255-_CIF_ASCE + lctl %c1,%c1,__LC_USER_ASCE # load primary asce + j io_return + +# # _TIF_NEED_RESCHED is set, call schedule # io_reschedule: @@ -574,12 +610,14 @@ ext_skip: stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC stm %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR + mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF + l %r1,BASED(.Ldo_IRQ) lr %r2,%r11 # pass pointer to pt_regs - l %r3,__LC_EXT_CPU_ADDR # get cpu address + interruption code - l %r4,__LC_EXT_PARAMS # get external parameters - l %r1,BASED(.Ldo_extint) - basr %r14,%r1 # call do_extint + lhi %r3,EXT_INTERRUPT + basr %r14,%r1 # call do_IRQ j io_return /* @@ -636,8 +674,10 @@ ENTRY(mcck_int_handler) UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER mcck_skip: SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT - mvc __PT_R0(64,%r11),__LC_GPREGS_SAVE_AREA + stm %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32 stm %r8,%r9,__PT_PSW(%r11) + xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) l %r1,BASED(.Ldo_machine_check) lr %r2,%r11 # pass pointer to pt_regs @@ -645,13 +685,12 @@ mcck_skip: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno mcck_return l %r1,__LC_KERNEL_STACK # switch to kernel stack - ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r15) lr %r15,%r1 ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off - tm __TI_flags+3(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+3,_CIF_MCCK_PENDING jno mcck_return TRACE_IRQS_OFF l %r1,BASED(.Lhandle_mcck) @@ -673,6 +712,7 @@ mcck_panic: sra %r14,PAGE_SHIFT jz 0f l %r15,__LC_PANIC_STACK + j mcck_skip 0: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j mcck_skip @@ -713,12 +753,10 @@ ENTRY(restart_int_handler) */ stack_overflow: l %r15,__LC_PANIC_STACK # change to panic stack - ahi %r15,-__PT_SIZE # create pt_regs - stm %r0,%r7,__PT_R0(%r15) - stm %r8,%r9,__PT_PSW(%r15) + la %r11,STACK_FRAME_OVERHEAD(%r15) + stm %r0,%r7,__PT_R0(%r11) + stm %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(32,%r11),0(%r14) - lr %r15,%r11 - ahi %r15,-STACK_FRAME_OVERHEAD l %r1,BASED(1f) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) lr %r2,%r11 # pass pointer to pt_regs @@ -798,15 +836,16 @@ cleanup_system_call: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER # set up saved register 11 l %r15,__LC_KERNEL_STACK - ahi %r15,-__PT_SIZE - st %r15,12(%r11) # r11 pt_regs pointer + la %r9,STACK_FRAME_OVERHEAD(%r15) + st %r9,12(%r11) # r11 pt_regs pointer # fill pt_regs - mvc __PT_R8(32,%r15),__LC_SAVE_AREA_SYNC - stm %r0,%r7,__PT_R0(%r15) - mvc __PT_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + mvc __PT_R8(32,%r9),__LC_SAVE_AREA_SYNC + stm %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(8,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC + xc __PT_FLAGS(4,%r9),__PT_FLAGS(%r9) + mvi __PT_FLAGS+3(%r9),_PIF_SYSCALL # setup saved register 15 - ahi %r15,-STACK_FRAME_OVERHEAD st %r15,28(%r11) # r15 stack pointer # set new psw address and exit l %r9,BASED(cleanup_table+4) # sysc_do_svc + 0x80000000 @@ -874,13 +913,13 @@ cleanup_idle: stm %r9,%r10,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - n %r8,BASED(cleanup_idle_wait) # clear wait state bit + n %r8,BASED(cleanup_idle_wait) # clear irq & wait state bits l %r9,24(%r11) # return from psw_idle br %r14 cleanup_idle_insn: .long psw_idle_lpsw + 0x80000000 cleanup_idle_wait: - .long 0xfffdffff + .long 0xfcfdffff /* * Integer constants @@ -897,7 +936,6 @@ cleanup_idle_wait: .Ldo_machine_check: .long s390_do_machine_check .Lhandle_mcck: .long s390_handle_mcck .Ldo_IRQ: .long do_IRQ -.Ldo_extint: .long do_extint .Ldo_signal: .long do_signal .Ldo_notify_resume: .long do_notify_resume .Ldo_per_trap: .long do_per_trap @@ -909,7 +947,6 @@ cleanup_idle_wait: .Ltrace_enter: .long do_syscall_trace_enter .Ltrace_exit: .long do_syscall_trace_exit .Lschedule_tail: .long schedule_tail -.Lsys_call_table: .long sys_call_table .Lsysc_per: .long sysc_per + 0x80000000 #ifdef CONFIG_TRACE_IRQFLAGS .Lhardirqs_on: .long trace_hardirqs_on_caller diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 2711936fe70..6ac78192455 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -7,6 +7,7 @@ #include <asm/cputime.h> extern void *restart_stack; +extern unsigned long suspend_zero_pages; void system_call(void); void pgm_check_handler(void); @@ -22,7 +23,6 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); void do_protection_exception(struct pt_regs *regs); void do_dat_exception(struct pt_regs *regs); -void do_asce_exception(struct pt_regs *regs); void addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); @@ -52,34 +52,22 @@ void handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); void do_notify_resume(struct pt_regs *regs); -struct ext_code; -void do_extint(struct pt_regs *regs, struct ext_code, unsigned int, unsigned long); +void __init init_IRQ(void); +void do_IRQ(struct pt_regs *regs, int irq); void do_restart(void); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); - +int setup_profiling_timer(unsigned int multiplier); void __init time_init(void); +int pfn_is_nosave(unsigned long); +void s390_early_resume(void); +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; -long sys_mmap2(struct s390_mmap_arg_struct __user *arg); -long sys_s390_ipc(uint call, int first, unsigned long second, - unsigned long third, void __user *ptr); long sys_s390_personality(unsigned int personality); -long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low, - size_t len, int advice); -long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args); -long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, - u32 len_low); -long sys_sigsuspend(int history0, int history1, old_sigset_t mask); -long sys_sigaction(int sig, const struct old_sigaction __user *act, - struct old_sigaction __user *oact); -long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss); -long sys_sigreturn(void); -long sys_rt_sigreturn(void); -long sys32_sigreturn(void); -long sys32_rt_sigreturn(void); +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 6d34e0c97a3..f2e674c702e 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -19,6 +19,7 @@ #include <asm/unistd.h> #include <asm/page.h> #include <asm/sigp.h> +#include <asm/irq.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 8 @@ -39,14 +40,13 @@ __PT_R15 = __PT_GPRS + 120 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER 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_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_MCCK_PENDING) -_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ - _TIF_SYSCALL_TRACEPOINT) -_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) +_TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) +_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE) +_PIF_WORK = (_PIF_PER_TRAP) #define BASED(name) name-system_call(%r13) @@ -72,31 +72,35 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) #endif .endm - .macro SPP newpp -#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) - tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_SPP + .macro LPP newpp +#if IS_ENABLED(CONFIG_KVM) + tm __LC_MACHINE_FLAGS+6,0x20 # MACHINE_FLAG_LPP jz .+8 .insn s,0xb2800000,\newpp #endif .endm - .macro HANDLE_SIE_INTERCEPT scratch,pgmcheck -#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + .macro HANDLE_SIE_INTERCEPT scratch,reason +#if IS_ENABLED(CONFIG_KVM) tmhh %r8,0x0001 # interrupting from user ? - jnz .+42 + jnz .+62 lgr \scratch,%r9 - slg \scratch,BASED(.Lsie_loop) - clg \scratch,BASED(.Lsie_length) - .if \pgmcheck + slg \scratch,BASED(.Lsie_critical) + clg \scratch,BASED(.Lsie_critical_length) + .if \reason==1 # Some program interrupts are suppressing (e.g. protection). # We must also check the instruction after SIE in that case. # do_protection_exception will rewind to rewind_pad - jh .+22 + jh .+42 .else - jhe .+22 + jhe .+42 .endif - lg %r9,BASED(.Lsie_loop) - SPP BASED(.Lhost_id) # set host id + lg %r14,__SF_EMPTY(%r15) # get control block pointer + LPP __SF_EMPTY+16(%r15) # set host id + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + larl %r9,sie_exit # skip forward to sie_exit + mvi __SF_EMPTY+31(%r15),\reason # set exit reason #endif .endm @@ -124,10 +128,10 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) srag %r14,%r14,\shift jnz 1f CHECK_STACK 1<<\shift,\savearea + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: lg %r15,\stack # load target stack -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm .macro UPDATE_VTIME scratch,enter_timer @@ -177,18 +181,14 @@ ENTRY(__switch_to) lg %r4,__THREAD_info(%r2) # get thread_info of prev lg %r5,__THREAD_info(%r3) # get thread_info of next lgr %r15,%r5 - aghi %r15,STACK_SIZE # end of kernel stack of next + aghi %r15,STACK_INIT # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r5,__LC_THREAD_INFO # store thread info of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack 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? - 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 -0: lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task + lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 __critical_start: @@ -203,10 +203,9 @@ sysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO - larl %r13,system_call + lghi %r14,_PIF_SYSCALL sysc_per: lg %r15,__LC_KERNEL_STACK - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs sysc_vtime: UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER @@ -215,8 +214,9 @@ sysc_vtime: mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC + stg %r14,__PT_FLAGS(%r11) sysc_do_svc: - oi __TI_flags+7(%r12),_TIF_SYSCALL + lg %r10,__TI_sysc_table(%r12) # address of system call table llgh %r8,__PT_INT_CODE+2(%r11) slag %r8,%r8,2 # shift and test for svc 0 jnz sysc_nr_ok @@ -227,18 +227,11 @@ sysc_do_svc: sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,2 sysc_nr_ok: - larl %r10,sys_call_table # 64 bit system call table -#ifdef CONFIG_COMPAT - tm __TI_flags+5(%r12),(_TIF_31BIT>>16) - jno sysc_noemu - larl %r10,sys_call_table_emu # 31 bit system call table -sysc_noemu: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stg %r2,__PT_ORIG_GPR2(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lgf %r9,0(%r8,%r10) # get system call add. - tm __TI_flags+6(%r12),_TIF_TRACE >> 8 + tm __TI_flags+7(%r12),_TIF_TRACE jnz sysc_tracesys basr %r14,%r9 # call sys_xxxx stg %r2,__PT_R2(%r11) # store return value @@ -248,9 +241,12 @@ sysc_return: sysc_tif: tm __PT_PSW+1(%r11),0x01 # returning to user ? jno sysc_restore - tm __TI_flags+7(%r12),_TIF_WORK_SVC + tm __PT_FLAGS+7(%r11),_PIF_WORK + jnz sysc_work + tm __TI_flags+7(%r12),_TIF_WORK jnz sysc_work # check for work - ni __TI_flags+7(%r12),255-_TIF_SYSCALL + tm __LC_CPU_FLAGS+7,_CIF_WORK + jnz sysc_work sysc_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) @@ -265,16 +261,18 @@ sysc_done: # One of the work bits is on. Find out which one. # sysc_work: - tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED jo sysc_reschedule - tm __TI_flags+7(%r12),_TIF_PER_TRAP + tm __PT_FLAGS+7(%r11),_PIF_PER_TRAP jo sysc_singlestep tm __TI_flags+7(%r12),_TIF_SIGPENDING jo sysc_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME jo sysc_notify_resume + tm __LC_CPU_FLAGS+7,_CIF_ASCE + jo sysc_uaccess j sysc_return # beware of critical section cleanup # @@ -285,21 +283,30 @@ sysc_reschedule: jg schedule # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # sysc_mcck_pending: larl %r14,sysc_return jg s390_handle_mcck # TIF bit will be cleared by handler # +# _CIF_ASCE is set, load user space asce +# +sysc_uaccess: + ni __LC_CPU_FLAGS+7,255-_CIF_ASCE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + j sysc_return + +# # _TIF_SIGPENDING is set, call do_signal # sysc_sigpending: lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_signal - tm __TI_flags+7(%r12),_TIF_SYSCALL + tm __PT_FLAGS+7(%r11),_PIF_SYSCALL jno sysc_return lmg %r2,%r7,__PT_R2(%r11) # load svc arguments + lg %r10,__TI_sysc_table(%r12) # address of system call table lghi %r8,0 # svc 0 returns -ENOSYS llgh %r1,__PT_INT_CODE+2(%r11) # load new svc number cghi %r1,NR_syscalls @@ -316,10 +323,10 @@ sysc_notify_resume: jg do_notify_resume # -# _TIF_PER_TRAP is set, call do_per_trap +# _PIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+7(%r12),255-_TIF_PER_TRAP + ni __PT_FLAGS+7(%r11),255-_PIF_PER_TRAP lgr %r2,%r11 # pass pointer to pt_regs larl %r14,sysc_return jg do_per_trap @@ -346,7 +353,7 @@ sysc_tracego: basr %r14,%r9 # call sys_xxx stg %r2,__PT_R2(%r11) # store return value sysc_tracenogo: - tm __TI_flags+6(%r12),_TIF_TRACE >> 8 + tm __TI_flags+7(%r12),_TIF_TRACE jz sysc_return lgr %r2,%r11 # pass pointer to pt_regs larl %r14,sysc_return @@ -389,6 +396,7 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jnz pgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC + aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER LAST_BREAK %r14 @@ -398,22 +406,22 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+2,0x02 # check for transaction abort jz 2f mvc __THREAD_trap_tdb(256,%r14),0(%r13) -2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - la %r11,STACK_FRAME_OVERHEAD(%r15) +2: la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC mvc __PT_INT_PARM_LONG(8,%r11),__LC_TRANS_EXC_CODE + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) stg %r10,__PT_ARGS(%r11) tm __LC_PGM_ILC+3,0x80 # check for per exception jz 0f tmhh %r8,0x0001 # kernel per event ? jz pgm_kprobe - oi __TI_flags+7(%r12),_TIF_PER_TRAP + oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS - mvc __THREAD_per_cause(2,%r14),__LC_PER_CAUSE - mvc __THREAD_per_paid(1,%r14),__LC_PER_PAID + mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE + mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID 0: REENABLE_IRQS xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) larl %r1,pgm_check_table @@ -440,10 +448,10 @@ pgm_kprobe: # single stepped system call # pgm_svcper: - oi __TI_flags+7(%r12),_TIF_PER_TRAP mvc __LC_RETURN_PSW(8),__LC_SVC_NEW_PSW larl %r14,sysc_per stg %r14,__LC_RETURN_PSW+8 + lghi %r14,_PIF_SYSCALL | _PIF_PER_TRAP lpswe __LC_RETURN_PSW # branch to sysc_per and enable irqs /* @@ -457,7 +465,7 @@ ENTRY(io_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_IO_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,2 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user? jz io_skip @@ -467,16 +475,32 @@ io_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) +io_loop: lgr %r2,%r11 # pass pointer to pt_regs + lghi %r3,IO_INTERRUPT + tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? + jz io_call + lghi %r3,THIN_INTERRUPT +io_call: brasl %r14,do_IRQ + tm __LC_MACHINE_FLAGS+6,0x10 # MACHINE_FLAG_LPAR + jz io_return + tpi 0 + jz io_return + mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID + j io_loop io_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON io_tif: - tm __TI_flags+7(%r12),_TIF_WORK_INT + tm __TI_flags+7(%r12),_TIF_WORK jnz io_work # there is work to do (signals etc.) + tm __LC_CPU_FLAGS+7,_CIF_WORK + jnz io_work io_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) @@ -489,7 +513,7 @@ io_done: # # There is work todo, find out in which context we have been interrupted: -# 1) if we return to user space we can do all _TIF_WORK_INT work +# 1) if we return to user space we can do all _TIF_WORK work # 2) if we return to kernel code and kvm is enabled check if we need to # modify the psw to leave SIE # 3) if we return to kernel code and preemptive scheduling is enabled check @@ -526,7 +550,6 @@ io_work: # io_work_user: lg %r1,__LC_KERNEL_STACK - aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) @@ -534,11 +557,9 @@ io_work_user: # # One of the work bits is on. Find out which one. -# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED -# and _TIF_MCCK_PENDING # io_work_tif: - tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING jo io_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED jo io_reschedule @@ -546,10 +567,12 @@ io_work_tif: jo io_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME jo io_notify_resume + tm __LC_CPU_FLAGS+7,_CIF_ASCE + jo io_uaccess j io_return # beware of critical section cleanup # -# _TIF_MCCK_PENDING is set, call handler +# _CIF_MCCK_PENDING is set, call handler # io_mcck_pending: # TRACE_IRQS_ON already done at io_return @@ -558,6 +581,14 @@ io_mcck_pending: j io_return # +# _CIF_ASCE is set, load user space asce +# +io_uaccess: + ni __LC_CPU_FLAGS+7,255-_CIF_ASCE + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce + j io_return + +# # _TIF_NEED_RESCHED is set, call schedule # io_reschedule: @@ -603,7 +634,7 @@ ENTRY(ext_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_EXT_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,3 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user ? jz ext_skip @@ -613,14 +644,16 @@ ext_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) + lghi %r1,__LC_EXT_PARAMS2 + mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR + mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS + mvc __PT_INT_PARM_LONG(8,%r11),0(%r1) + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) - lghi %r1,4096 lgr %r2,%r11 # pass pointer to pt_regs - llgf %r3,__LC_EXT_CPU_ADDR # get cpu address + interruption code - llgf %r4,__LC_EXT_PARAMS # get external parameter - lg %r5,__LC_EXT_PARAMS2-4096(%r1) # get 64 bit external parameter - brasl %r14,do_extint + lghi %r3,EXT_INTERRUPT + brasl %r14,do_IRQ j io_return /* @@ -651,7 +684,7 @@ ENTRY(mcck_int_handler) lg %r12,__LC_THREAD_INFO larl %r13,system_call lmg %r8,%r9,__LC_MCK_OLD_PSW - HANDLE_SIE_INTERCEPT %r14,0 + HANDLE_SIE_INTERCEPT %r14,4 tm __LC_MCCK_CODE,0x80 # system damage? jo mcck_panic # yes -> rest of mcck code invalid lghi %r14,__LC_CPU_TIMER_SAVE_AREA @@ -678,22 +711,23 @@ ENTRY(mcck_int_handler) UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER LAST_BREAK %r14 mcck_skip: - lghi %r14,__LC_GPREGS_SAVE_AREA - mvc __PT_R0(128,%r11),0(%r14) + lghi %r14,__LC_GPREGS_SAVE_AREA+64 + stmg %r0,%r7,__PT_R0(%r11) + mvc __PT_R8(64,%r11),0(%r14) stmg %r8,%r9,__PT_PSW(%r11) + xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,s390_do_machine_check tm __PT_PSW+1(%r11),0x01 # returning to user ? jno mcck_return lg %r1,__LC_KERNEL_STACK # switch to kernel stack - aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) lgr %r15,%r1 ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off - tm __TI_flags+7(%r12),_TIF_MCCK_PENDING + tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING jno mcck_return TRACE_IRQS_OFF brasl %r14,s390_handle_mcck @@ -754,14 +788,12 @@ ENTRY(restart_int_handler) * Setup a pt_regs so that show_trace can provide a good call trace. */ stack_overflow: - lg %r11,__LC_PANIC_STACK # change to panic stack - aghi %r11,-__PT_SIZE # create pt_regs + lg %r15,__LC_PANIC_STACK # change to panic stack + la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(64,%r11),0(%r14) stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2 - lgr %r15,%r11 - aghi %r15,-STACK_FRAME_OVERHEAD xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_overflow @@ -845,15 +877,16 @@ cleanup_system_call: mvc __TI_last_break(8,%r12),16(%r11) 0: # set up saved register r11 lg %r15,__LC_KERNEL_STACK - aghi %r15,-__PT_SIZE - stg %r15,24(%r11) # r11 pt_regs pointer + la %r9,STACK_FRAME_OVERHEAD(%r15) + stg %r9,24(%r11) # r11 pt_regs pointer # fill pt_regs - mvc __PT_R8(64,%r15),__LC_SAVE_AREA_SYNC - stmg %r0,%r7,__PT_R0(%r15) - mvc __PT_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r15),__LC_SVC_ILC + mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC + stmg %r0,%r7,__PT_R0(%r9) + mvc __PT_PSW(16,%r9),__LC_SVC_OLD_PSW + mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC + xc __PT_FLAGS(8,%r9),__PT_FLAGS(%r9) + mvi __PT_FLAGS+7(%r9),_PIF_SYSCALL # setup saved register r15 - aghi %r15,-STACK_FRAME_OVERHEAD stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit larl %r9,sysc_do_svc @@ -922,7 +955,7 @@ cleanup_idle: stg %r9,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - nihh %r8,0xfffd # clear wait state bit + nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle br %r14 cleanup_idle_insn: @@ -938,7 +971,7 @@ 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 @@ -948,56 +981,50 @@ ENTRY(sie64a) stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers stg %r2,__SF_EMPTY(%r15) # save control block pointer stg %r3,__SF_EMPTY+8(%r15) # save guest register save area - xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0 + xc __SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason lmg %r0,%r13,0(%r3) # load guest gprs 0-13 -# 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 in the sie_loop 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: - nop 0 -sie_loop: - lg %r14,__LC_THREAD_INFO # pointer thread_info struct - tm __TI_flags+7(%r14),_TIF_EXIT_SIE - jnz sie_exit lg %r14,__LC_GMAP # get gmap pointer ltgr %r14,%r14 jz sie_gmap lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce sie_gmap: lg %r14,__SF_EMPTY(%r15) # get control block pointer - SPP __SF_EMPTY(%r15) # set guest id + oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now + tm __SIE_PROG20+3(%r14),1 # last exit... + jnz sie_done + LPP __SF_EMPTY(%r15) # set guest id sie 0(%r14) sie_done: - SPP __SF_EMPTY+16(%r15) # set host id - lg %r14,__LC_THREAD_INFO # pointer thread_info struct -sie_exit: + LPP __SF_EMPTY+16(%r15) # set host id + ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE 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 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: + nop 0 + .globl sie_exit +sie_exit: lg %r14,__SF_EMPTY+8(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers - lghi %r2,0 + lg %r2,__SF_EMPTY+24(%r15) # return exit reason code br %r14 sie_fault: - lctlg %c1,%c1,__LC_USER_ASCE # load primary asce - lg %r14,__LC_THREAD_INFO # pointer thread_info struct - lg %r14,__SF_EMPTY+8(%r15) # load guest register save area - stmg %r0,%r13,0(%r14) # save guest gprs 0-13 - lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers - lghi %r2,-EFAULT - br %r14 + lghi %r14,-EFAULT + stg %r14,__SF_EMPTY+24(%r15) # set exit reason code + j sie_exit .align 8 -.Lsie_loop: - .quad sie_loop -.Lsie_length: - .quad sie_done - sie_loop -.Lhost_id: - .quad 0 +.Lsie_critical: + .quad sie_gmap +.Lsie_critical_length: + .quad sie_done - sie_gmap EX_TABLE(rewind_pad,sie_fault) - EX_TABLE(sie_loop,sie_fault) + EX_TABLE(sie_exit,sie_fault) #endif .section .rodata, "a" @@ -1010,6 +1037,7 @@ sys_call_table: #ifdef CONFIG_COMPAT #define SYSCALL(esa,esame,emu) .long emu + .globl sys_call_table_emu sys_call_table_emu: #include "syscalls.S" #undef SYSCALL diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 78bdf0e5dff..54d6493c4a5 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -15,12 +15,7 @@ #include <linux/kprobes.h> #include <trace/syscall.h> #include <asm/asm-offsets.h> - -#ifdef CONFIG_64BIT -#define MCOUNT_OFFSET_RET 12 -#else -#define MCOUNT_OFFSET_RET 22 -#endif +#include "entry.h" #ifdef CONFIG_DYNAMIC_FTRACE @@ -135,9 +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; } @@ -155,14 +149,14 @@ unsigned long __kprobes prepare_ftrace_return(unsigned long parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) - goto out; - trace.func = (ip & PSW_ADDR_INSN) - MCOUNT_OFFSET_RET; + ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE; + trace.func = ip; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to. */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; + if (!ftrace_graph_entry(&trace)) + goto out; + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) goto out; - } parent = (unsigned long) return_to_handler; out: return parent; @@ -182,7 +176,7 @@ int ftrace_enable_ftrace_graph_caller(void) offset = ((void *) prepare_ftrace_return - (void *) ftrace_graph_caller) / 2; - return probe_kernel_write(ftrace_graph_caller + 2, + return probe_kernel_write((void *) ftrace_graph_caller + 2, &offset, sizeof(offset)); } @@ -190,7 +184,7 @@ int ftrace_disable_ftrace_graph_caller(void) { static unsigned short offset = 0x0002; - return probe_kernel_write(ftrace_graph_caller + 2, + return probe_kernel_write((void *) ftrace_graph_caller + 2, &offset, sizeof(offset)); } diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index fd8db63dfc9..e88d35d7495 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -437,13 +437,13 @@ ENTRY(startup_kdump) #if defined(CONFIG_64BIT) #if defined(CONFIG_MARCH_ZEC12) - .long 3, 0xc100efe3, 0xf46ce000, 0x00400000 + .long 3, 0xc100eff2, 0xf46ce800, 0x00400000 #elif defined(CONFIG_MARCH_Z196) - .long 2, 0xc100efe3, 0xf46c0000 + .long 2, 0xc100eff2, 0xf46c0000 #elif defined(CONFIG_MARCH_Z10) - .long 2, 0xc100efe3, 0xf0680000 + .long 2, 0xc100eff2, 0xf0680000 #elif defined(CONFIG_MARCH_Z9_109) - .long 1, 0xc100efc3 + .long 1, 0xc100efc2 #elif defined(CONFIG_MARCH_Z990) .long 1, 0xc0002000 #elif defined(CONFIG_MARCH_Z900) diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index 9a99856df1c..6dbe80983a2 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -59,7 +59,6 @@ ENTRY(startup_continue) .long 0 # cr13: home space segment table .long 0xc0000000 # cr14: machine check handling off .long 0 # cr15: linkage stack operations -.Lmchunk:.long memory_chunk .Lbss_bgn: .long __bss_start .Lbss_end: .long _end .Lparmaddr: .long PARMAREA 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/ipl.c b/arch/s390/kernel/ipl.c index 6ffcd320321..633ca750453 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -754,9 +754,9 @@ static struct bin_attribute sys_reipl_fcp_scp_data_attr = { .write = reipl_fcp_scpdata_write, }; -DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n", reipl_block_fcp->ipl_info.fcp.wwpn); -DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n", reipl_block_fcp->ipl_info.fcp.lun); DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n", reipl_block_fcp->ipl_info.fcp.bootprog); @@ -1323,9 +1323,9 @@ static struct shutdown_action __refdata reipl_action = { /* FCP dump device attributes */ -DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n", dump_block_fcp->ipl_info.fcp.wwpn); -DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%016llx\n", +DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n", dump_block_fcp->ipl_info.fcp.lun); DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n", dump_block_fcp->ipl_info.fcp.bootprog); @@ -1414,6 +1414,16 @@ static struct kobj_attribute dump_type_attr = static struct kset *dump_kset; +static void diag308_dump(void *dump_block) +{ + diag308(DIAG308_SET, dump_block); + while (1) { + if (diag308(DIAG308_DUMP, NULL) != 0x302) + break; + udelay_simple(USEC_PER_SEC); + } +} + static void __dump_run(void *unused) { struct ccw_dev_id devid; @@ -1432,12 +1442,10 @@ static void __dump_run(void *unused) __cpcmd(buf, NULL, 0, NULL); break; case DUMP_METHOD_CCW_DIAG: - diag308(DIAG308_SET, dump_block_ccw); - diag308(DIAG308_DUMP, NULL); + diag308_dump(dump_block_ccw); break; case DUMP_METHOD_FCP_DIAG: - diag308(DIAG308_SET, dump_block_fcp); - diag308(DIAG308_DUMP, NULL); + diag308_dump(dump_block_fcp); break; default: break; @@ -2043,12 +2051,12 @@ void s390_reset_system(void (*func)(void *), void *data) __ctl_clear_bit(0,28); /* Set new machine check handler */ - S390_lowcore.mcck_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; + S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.mcck_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler; /* Set new program check handler */ - S390_lowcore.program_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; + S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 9df824ea166..99b0b09646c 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -18,10 +18,12 @@ #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> #include <asm/irq.h> +#include <asm/hw_irq.h> #include "entry.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat); @@ -33,7 +35,7 @@ struct irq_class { }; /* - * The list of "main" irq classes on s390. This is the list of interrrupts + * The list of "main" irq classes on s390. This is the list of interrupts * that appear both in /proc/stat ("intr" line) and /proc/interrupts. * Historically only external and I/O interrupts have been part of /proc/stat. * We can't add the split external and I/O sub classes since the first field @@ -42,9 +44,10 @@ struct irq_class { * Since the external and I/O interrupt fields are already sums we would end * up with having a sum which accounts each interrupt twice. */ -static const struct irq_class irqclass_main_desc[NR_IRQS] = { - [EXTERNAL_INTERRUPT] = {.name = "EXT"}, - [IO_INTERRUPT] = {.name = "I/O"} +static const struct irq_class irqclass_main_desc[NR_IRQS_BASE] = { + [EXT_INTERRUPT] = {.name = "EXT"}, + [IO_INTERRUPT] = {.name = "I/O"}, + [THIN_INTERRUPT] = {.name = "AIO"}, }; /* @@ -81,10 +84,33 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = { [IRQIO_CSC] = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"}, [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"}, }; +void __init init_IRQ(void) +{ + init_cio_interrupts(); + init_airq_interrupts(); + init_ext_interrupts(); +} + +void do_IRQ(struct pt_regs *regs, int irq) +{ + struct pt_regs *old_regs; + + old_regs = set_irq_regs(regs); + irq_enter(); + if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) + /* Serve timer interrupts first. */ + clock_comparator_work(); + generic_handle_irq(irq); + irq_exit(); + set_irq_regs(old_regs); +} + /* * show_interrupts is needed by /proc/interrupts. */ @@ -99,105 +125,88 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(cpu) seq_printf(p, "CPU%d ", cpu); seq_putc(p, '\n'); + goto out; } if (irq < NR_IRQS) { + if (irq >= NR_IRQS_BASE) + goto out; seq_printf(p, "%s: ", irqclass_main_desc[irq].name); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[irq]); + seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu)); seq_putc(p, '\n'); - goto skip_arch_irqs; + goto out; } for (irq = 0; irq < NR_ARCH_IRQS; irq++) { seq_printf(p, "%s: ", irqclass_sub_desc[irq].name); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).irqs[irq]); + seq_printf(p, "%10u ", + per_cpu(irq_stat, cpu).irqs[irq]); if (irqclass_sub_desc[irq].desc) seq_printf(p, " %s", irqclass_sub_desc[irq].desc); seq_putc(p, '\n'); } -skip_arch_irqs: +out: put_online_cpus(); return 0; } +unsigned int arch_dynirq_lower_bound(unsigned int from) +{ + return from < THIN_INTERRUPT ? THIN_INTERRUPT : from; +} + /* * Switch to the asynchronous interrupt stack for softirq execution. */ -asmlinkage void do_softirq(void) +void do_softirq_own_stack(void) { - unsigned long flags, old, new; - - if (in_interrupt()) - return; - - local_irq_save(flags); - - if (local_softirq_pending()) { - /* Get current stack pointer. */ - asm volatile("la %0,0(15)" : "=a" (old)); - /* Check against async. stack address range. */ - new = S390_lowcore.async_stack; - if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) { - /* Need to switch to the async. stack. */ - new -= STACK_FRAME_OVERHEAD; - ((struct stack_frame *) new)->back_chain = old; - - asm volatile(" la 15,0(%0)\n" - " basr 14,%2\n" - " la 15,0(%1)\n" - : : "a" (new), "a" (old), - "a" (__do_softirq) - : "0", "1", "2", "3", "4", "5", "14", - "cc", "memory" ); - } else { - /* We are already on the async stack. */ - __do_softirq(); - } + unsigned long old, new; + + /* Get current stack pointer. */ + asm volatile("la %0,0(15)" : "=a" (old)); + /* Check against async. stack address range. */ + new = S390_lowcore.async_stack; + if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) { + /* Need to switch to the async. stack. */ + new -= STACK_FRAME_OVERHEAD; + ((struct stack_frame *) new)->back_chain = old; + asm volatile(" la 15,0(%0)\n" + " basr 14,%2\n" + " la 15,0(%1)\n" + : : "a" (new), "a" (old), + "a" (__do_softirq) + : "0", "1", "2", "3", "4", "5", "14", + "cc", "memory" ); + } else { + /* We are already on the async stack. */ + __do_softirq(); } - - local_irq_restore(flags); } -#ifdef CONFIG_PROC_FS -void init_irq_proc(void) -{ - struct proc_dir_entry *root_irq_dir; - - root_irq_dir = proc_mkdir("irq", NULL); - create_prof_cpu_mask(root_irq_dir); -} -#endif - /* * ext_int_hash[index] is the list head for all external interrupts that hash * to this index. */ -static struct list_head ext_int_hash[256]; +static struct hlist_head ext_int_hash[32] ____cacheline_aligned; struct ext_int_info { ext_int_handler_t handler; - u16 code; - struct list_head entry; + struct hlist_node entry; struct rcu_head rcu; + u16 code; }; /* ext_int_hash_lock protects the handler lists for external interrupts */ -DEFINE_SPINLOCK(ext_int_hash_lock); - -static void __init init_external_interrupts(void) -{ - int idx; - - for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) - INIT_LIST_HEAD(&ext_int_hash[idx]); -} +static DEFINE_SPINLOCK(ext_int_hash_lock); static inline int ext_hash(u16 code) { - return (code + (code >> 9)) & 0xff; + BUILD_BUG_ON(!is_power_of_2(ARRAY_SIZE(ext_int_hash))); + + 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; @@ -211,104 +220,88 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler) index = ext_hash(code); spin_lock_irqsave(&ext_int_hash_lock, flags); - list_add_rcu(&p->entry, &ext_int_hash[index]); + hlist_add_head_rcu(&p->entry, &ext_int_hash[index]); 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; int index = ext_hash(code); spin_lock_irqsave(&ext_int_hash_lock, flags); - list_for_each_entry_rcu(p, &ext_int_hash[index], entry) { + hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) { if (p->code == code && p->handler == handler) { - list_del_rcu(&p->entry); + hlist_del_rcu(&p->entry); kfree_rcu(p, rcu); } } spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; } -EXPORT_SYMBOL(unregister_external_interrupt); +EXPORT_SYMBOL(unregister_external_irq); -void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code, - unsigned int param32, unsigned long param64) +static irqreturn_t do_ext_interrupt(int irq, void *dummy) { - struct pt_regs *old_regs; + struct pt_regs *regs = get_irq_regs(); + struct ext_code ext_code; struct ext_int_info *p; int index; - old_regs = set_irq_regs(regs); - irq_enter(); - if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) { - /* Serve timer interrupts first. */ - clock_comparator_work(); - } - kstat_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL); - if (ext_code.code != 0x1004) + ext_code = *(struct ext_code *) ®s->int_code; + if (ext_code.code != EXT_IRQ_CLK_COMP) __get_cpu_var(s390_idle).nohz_delay = 1; index = ext_hash(ext_code.code); rcu_read_lock(); - list_for_each_entry_rcu(p, &ext_int_hash[index], entry) - if (likely(p->code == ext_code.code)) - p->handler(ext_code, param32, param64); + hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) { + if (unlikely(p->code != ext_code.code)) + continue; + p->handler(ext_code, regs->int_parm, regs->int_parm_long); + } rcu_read_unlock(); - irq_exit(); - set_irq_regs(old_regs); -} - -void __init init_IRQ(void) -{ - init_external_interrupts(); + return IRQ_HANDLED; } -static DEFINE_SPINLOCK(sc_irq_lock); -static int sc_irq_refcount; +static struct irqaction external_interrupt = { + .name = "EXT", + .handler = do_ext_interrupt, +}; -void service_subclass_irq_register(void) +void __init init_ext_interrupts(void) { - spin_lock(&sc_irq_lock); - if (!sc_irq_refcount) - ctl_set_bit(0, 9); - sc_irq_refcount++; - spin_unlock(&sc_irq_lock); -} -EXPORT_SYMBOL(service_subclass_irq_register); + int idx; -void service_subclass_irq_unregister(void) -{ - spin_lock(&sc_irq_lock); - sc_irq_refcount--; - if (!sc_irq_refcount) - ctl_clear_bit(0, 9); - spin_unlock(&sc_irq_lock); + for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) + INIT_HLIST_HEAD(&ext_int_hash[idx]); + + irq_set_chip_and_handler(EXT_INTERRUPT, + &dummy_irq_chip, handle_percpu_irq); + setup_irq(EXT_INTERRUPT, &external_interrupt); } -EXPORT_SYMBOL(service_subclass_irq_unregister); -static DEFINE_SPINLOCK(ma_subclass_lock); -static int ma_subclass_refcount; +static DEFINE_SPINLOCK(irq_subclass_lock); +static unsigned char irq_subclass_refcount[64]; -void measurement_alert_subclass_register(void) +void irq_subclass_register(enum irq_subclass subclass) { - spin_lock(&ma_subclass_lock); - if (!ma_subclass_refcount) - ctl_set_bit(0, 5); - ma_subclass_refcount++; - spin_unlock(&ma_subclass_lock); + spin_lock(&irq_subclass_lock); + if (!irq_subclass_refcount[subclass]) + ctl_set_bit(0, subclass); + irq_subclass_refcount[subclass]++; + spin_unlock(&irq_subclass_lock); } -EXPORT_SYMBOL(measurement_alert_subclass_register); +EXPORT_SYMBOL(irq_subclass_register); -void measurement_alert_subclass_unregister(void) +void irq_subclass_unregister(enum irq_subclass subclass) { - spin_lock(&ma_subclass_lock); - ma_subclass_refcount--; - if (!ma_subclass_refcount) - ctl_clear_bit(0, 5); - spin_unlock(&ma_subclass_lock); + spin_lock(&irq_subclass_lock); + irq_subclass_refcount[subclass]--; + if (!irq_subclass_refcount[subclass]) + ctl_clear_bit(0, subclass); + spin_unlock(&irq_subclass_lock); } -EXPORT_SYMBOL(measurement_alert_subclass_unregister); +EXPORT_SYMBOL(irq_subclass_unregister); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index d1c7214e157..bc71a7b95af 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -26,19 +26,42 @@ #include <linux/stop_machine.h> #include <linux/kdebug.h> #include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/sections.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/hardirq.h> +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <asm/dis.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe); DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); struct kretprobe_blackpoint kretprobe_blacklist[] = { }; +DEFINE_INSN_CACHE_OPS(dmainsn); + +static void *alloc_dmainsn_page(void) +{ + return (void *)__get_free_page(GFP_KERNEL | GFP_DMA); +} + +static void free_dmainsn_page(void *page) +{ + free_page((unsigned long)page); +} + +struct kprobe_insn_cache kprobe_dmainsn_slots = { + .mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex), + .alloc = alloc_dmainsn_page, + .free = free_dmainsn_page, + .pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages), + .insn_size = MAX_INSN_SIZE, +}; + static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn) { + if (!is_known_insn((unsigned char *)insn)) + return -EINVAL; switch (insn[0] >> 8) { case 0x0c: /* bassm */ case 0x0b: /* bsm */ @@ -47,6 +70,11 @@ static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn) case 0xac: /* stnsm */ case 0xad: /* stosm */ return -EINVAL; + case 0xc6: + switch (insn[0] & 0x0f) { + case 0x00: /* exrl */ + return -EINVAL; + } } switch (insn[0]) { case 0x0101: /* pr */ @@ -100,35 +128,160 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn) fixup |= FIXUP_RETURN_REGISTER; break; case 0xc0: - if ((insn[0] & 0x0f) == 0x00 || /* larl */ - (insn[0] & 0x0f) == 0x05) /* brasl */ - fixup |= FIXUP_RETURN_REGISTER; + if ((insn[0] & 0x0f) == 0x05) /* brasl */ + fixup |= FIXUP_RETURN_REGISTER; break; case 0xeb: - if ((insn[2] & 0xff) == 0x44 || /* bxhg */ - (insn[2] & 0xff) == 0x45) /* bxleg */ + switch (insn[2] & 0xff) { + case 0x44: /* bxhg */ + case 0x45: /* bxleg */ fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } break; case 0xe3: /* bctg */ if ((insn[2] & 0xff) == 0x46) fixup = FIXUP_BRANCH_NOT_TAKEN; break; + case 0xec: + switch (insn[2] & 0xff) { + case 0xe5: /* clgrb */ + case 0xe6: /* cgrb */ + case 0xf6: /* crb */ + case 0xf7: /* clrb */ + case 0xfc: /* cgib */ + case 0xfd: /* cglib */ + case 0xfe: /* cib */ + case 0xff: /* clib */ + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } + break; } return fixup; } +static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn) +{ + /* Check if we have a RIL-b or RIL-c format instruction which + * we need to modify in order to avoid instruction emulation. */ + switch (insn[0] >> 8) { + case 0xc0: + if ((insn[0] & 0x0f) == 0x00) /* larl */ + return true; + break; + case 0xc4: + switch (insn[0] & 0x0f) { + case 0x02: /* llhrl */ + case 0x04: /* lghrl */ + case 0x05: /* lhrl */ + case 0x06: /* llghrl */ + case 0x07: /* sthrl */ + case 0x08: /* lgrl */ + case 0x0b: /* stgrl */ + case 0x0c: /* lgfrl */ + case 0x0d: /* lrl */ + case 0x0e: /* llgfrl */ + case 0x0f: /* strl */ + return true; + } + break; + case 0xc6: + switch (insn[0] & 0x0f) { + case 0x02: /* pfdrl */ + case 0x04: /* cghrl */ + case 0x05: /* chrl */ + case 0x06: /* clghrl */ + case 0x07: /* clhrl */ + case 0x08: /* cgrl */ + case 0x0a: /* clgrl */ + case 0x0c: /* cgfrl */ + case 0x0d: /* crl */ + case 0x0e: /* clgfrl */ + case 0x0f: /* clrl */ + return true; + } + break; + } + return false; +} + +static void __kprobes copy_instruction(struct kprobe *p) +{ + s64 disp, new_disp; + u64 addr, new_addr; + + memcpy(p->ainsn.insn, p->addr, insn_length(p->opcode >> 8)); + if (!is_insn_relative_long(p->ainsn.insn)) + return; + /* + * For pc-relative instructions in RIL-b or RIL-c format patch the + * RI2 displacement field. We have already made sure that the insn + * slot for the patched instruction is within the same 2GB area + * as the original instruction (either kernel image or module area). + * Therefore the new displacement will always fit. + */ + disp = *(s32 *)&p->ainsn.insn[1]; + addr = (u64)(unsigned long)p->addr; + new_addr = (u64)(unsigned long)p->ainsn.insn; + new_disp = ((addr + (disp * 2)) - new_addr) / 2; + *(s32 *)&p->ainsn.insn[1] = new_disp; +} + +static inline int is_kernel_addr(void *addr) +{ + return addr < (void *)_end; +} + +static inline int is_module_addr(void *addr) +{ +#ifdef CONFIG_64BIT + BUILD_BUG_ON(MODULES_LEN > (1UL << 31)); + if (addr < (void *)MODULES_VADDR) + return 0; + if (addr > (void *)MODULES_END) + return 0; +#endif + return 1; +} + +static int __kprobes s390_get_insn_slot(struct kprobe *p) +{ + /* + * Get an insn slot that is within the same 2GB area like the original + * instruction. That way instructions with a 32bit signed displacement + * field can be patched and executed within the insn slot. + */ + p->ainsn.insn = NULL; + if (is_kernel_addr(p->addr)) + p->ainsn.insn = get_dmainsn_slot(); + else if (is_module_addr(p->addr)) + p->ainsn.insn = get_insn_slot(); + return p->ainsn.insn ? 0 : -ENOMEM; +} + +static void __kprobes s390_free_insn_slot(struct kprobe *p) +{ + if (!p->ainsn.insn) + return; + if (is_kernel_addr(p->addr)) + free_dmainsn_slot(p->ainsn.insn, 0); + else + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; +} + int __kprobes arch_prepare_kprobe(struct kprobe *p) { if ((unsigned long) p->addr & 0x01) return -EINVAL; - /* Make sure the probe isn't going on a difficult instruction */ if (is_prohibited_opcode(p->addr)) return -EINVAL; - + if (s390_get_insn_slot(p)) + return -ENOMEM; p->opcode = *p->addr; - memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2); - + copy_instruction(p); return 0; } @@ -169,6 +322,7 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) void __kprobes arch_remove_kprobe(struct kprobe *p) { + s390_free_insn_slot(p); } static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb, @@ -354,7 +508,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { struct kretprobe_instance *ri; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address; unsigned long trampoline_address; kprobe_opcode_t *correct_ret_addr; @@ -379,7 +533,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, orig_ret_address = 0; correct_ret_addr = NULL; trampoline_address = (unsigned long) &kretprobe_trampoline; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -398,7 +552,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -427,7 +581,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } @@ -457,7 +611,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn; if (fixup & FIXUP_BRANCH_NOT_TAKEN) { - int ilen = ((p->ainsn.insn[0] >> 14) + 3) & -2; + int ilen = insn_length(p->ainsn.insn[0] >> 8); if (ip - (unsigned long) p->ainsn.insn == ilen) ip = (unsigned long) p->addr + ilen; } @@ -526,7 +680,7 @@ static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(p); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b3de2770001..719e27b2cf2 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <linux/suspend.h> #include <asm/cio.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -49,7 +50,7 @@ static void add_elf_notes(int cpu) /* * Initialize CPU ELF notes */ -void setup_regs(void) +static void setup_regs(void) { unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE; int cpu, this_cpu; @@ -67,6 +68,35 @@ void setup_regs(void) memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); } +/* + * PM notifier callback for kdump + */ +static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + if (crashk_res.start) + crash_map_reserved_pages(); + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + if (crashk_res.start) + crash_unmap_reserved_pages(); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init machine_kdump_pm_init(void) +{ + pm_notifier(machine_kdump_pm_cb, 0); + return 0; +} +arch_initcall(machine_kdump_pm_init); #endif /* diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 4567ce20d90..08dcf21cb8d 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/ftrace.h> .section .kprobes.text, "ax" @@ -33,6 +34,7 @@ ENTRY(ftrace_caller) la %r2,0(%r14) st %r0,__SF_BACKCHAIN(%r15) la %r3,0(%r3) + ahi %r2,-MCOUNT_INSN_SIZE l %r14,0b-0b(%r1) l %r14,0(%r14) basr %r14,%r14 diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index 11332193db3..1c52eae3396 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/ftrace.h> .section .kprobes.text, "ax" @@ -29,6 +30,7 @@ ENTRY(ftrace_caller) stg %r1,__SF_BACKCHAIN(%r15) lgr %r2,%r14 lg %r3,168(%r15) + aghi %r2,-MCOUNT_INSN_SIZE larl %r14,ftrace_trace_function lg %r14,0(%r14) basr %r14,%r14 diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c deleted file mode 100644 index 22d502e885e..00000000000 --- a/arch/s390/kernel/mem_detect.c +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Copyright IBM Corp. 2008, 2009 - * - * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <asm/ipl.h> -#include <asm/sclp.h> -#include <asm/setup.h> - -#define ADDR2G (1ULL << 31) - -static void find_memory_chunks(struct mem_chunk chunk[]) -{ - unsigned long long memsize, rnmax, rzm; - unsigned long addr = 0, size; - int i = 0, type; - - rzm = sclp_get_rzm(); - rnmax = sclp_get_rnmax(); - memsize = rzm * rnmax; - if (!rzm) - rzm = 1ULL << 17; - if (sizeof(long) == 4) { - rzm = min(ADDR2G, rzm); - memsize = memsize ? min(ADDR2G, memsize) : ADDR2G; - } - do { - size = 0; - type = tprot(addr); - do { - size += rzm; - if (memsize && addr + size >= memsize) - break; - } while (type == tprot(addr + size)); - if (type == CHUNK_READ_WRITE || type == CHUNK_READ_ONLY) { - chunk[i].addr = addr; - chunk[i].size = size; - chunk[i].type = type; - i++; - } - addr += size; - } while (addr < memsize && i < MEMORY_CHUNKS); -} - -void detect_memory_layout(struct mem_chunk chunk[]) -{ - unsigned long flags, cr0; - - memset(chunk, 0, MEMORY_CHUNKS * sizeof(struct mem_chunk)); - /* Disable IRQs, DAT and low address protection so tprot does the - * right thing and we don't get scheduled away with low address - * protection disabled. - */ - flags = __arch_local_irq_stnsm(0xf8); - __ctl_store(cr0, 0, 0); - __ctl_clear_bit(0, 28); - find_memory_chunks(chunk); - __ctl_load(cr0, 0, 0); - arch_local_irq_restore(flags); -} -EXPORT_SYMBOL(detect_memory_layout); - -/* - * Move memory chunks array from index "from" to index "to" - */ -static void mem_chunk_move(struct mem_chunk chunk[], int to, int from) -{ - int cnt = MEMORY_CHUNKS - to; - - memmove(&chunk[to], &chunk[from], cnt * sizeof(struct mem_chunk)); -} - -/* - * Initialize memory chunk - */ -static void mem_chunk_init(struct mem_chunk *chunk, unsigned long addr, - unsigned long size, int type) -{ - chunk->type = type; - chunk->addr = addr; - chunk->size = size; -} - -/* - * Create memory hole with given address, size, and type - */ -void create_mem_hole(struct mem_chunk chunk[], unsigned long addr, - unsigned long size, int type) -{ - unsigned long lh_start, lh_end, lh_size, ch_start, ch_end, ch_size; - int i, ch_type; - - for (i = 0; i < MEMORY_CHUNKS; i++) { - if (chunk[i].size == 0) - continue; - - /* Define chunk properties */ - ch_start = chunk[i].addr; - ch_size = chunk[i].size; - ch_end = ch_start + ch_size - 1; - ch_type = chunk[i].type; - - /* Is memory chunk hit by memory hole? */ - if (addr + size <= ch_start) - continue; /* No: memory hole in front of chunk */ - if (addr > ch_end) - continue; /* No: memory hole after chunk */ - - /* Yes: Define local hole properties */ - lh_start = max(addr, chunk[i].addr); - lh_end = min(addr + size - 1, ch_end); - lh_size = lh_end - lh_start + 1; - - if (lh_start == ch_start && lh_end == ch_end) { - /* Hole covers complete memory chunk */ - mem_chunk_init(&chunk[i], lh_start, lh_size, type); - } else if (lh_end == ch_end) { - /* Hole starts in memory chunk and convers chunk end */ - mem_chunk_move(chunk, i + 1, i); - mem_chunk_init(&chunk[i], ch_start, ch_size - lh_size, - ch_type); - mem_chunk_init(&chunk[i + 1], lh_start, lh_size, type); - i += 1; - } else if (lh_start == ch_start) { - /* Hole ends in memory chunk */ - mem_chunk_move(chunk, i + 1, i); - mem_chunk_init(&chunk[i], lh_start, lh_size, type); - mem_chunk_init(&chunk[i + 1], lh_end + 1, - ch_size - lh_size, ch_type); - break; - } else { - /* Hole splits memory chunk */ - mem_chunk_move(chunk, i + 2, i); - mem_chunk_init(&chunk[i], ch_start, - lh_start - ch_start, ch_type); - mem_chunk_init(&chunk[i + 1], lh_start, lh_size, type); - mem_chunk_init(&chunk[i + 2], lh_end + 1, - ch_end - lh_end, ch_type); - break; - } - } -} diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 4610deafd95..b89b59158b9 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -50,7 +50,7 @@ void *module_alloc(unsigned long size) if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL, -1, + GFP_KERNEL, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } #endif @@ -65,8 +65,7 @@ void module_free(struct module *mod, void *module_region) vfree(module_region); } -static void -check_rela(Elf_Rela *rela, struct module *me) +static void check_rela(Elf_Rela *rela, struct module *me) { struct mod_arch_syminfo *info; @@ -115,9 +114,8 @@ check_rela(Elf_Rela *rela, struct module *me) * Account for GOT and PLT relocations. We can't add sections for * got and plt but we can increase the core module size. */ -int -module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, - char *secstrings, struct module *me) +int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *me) { Elf_Shdr *symtab; Elf_Sym *symbols; @@ -179,13 +177,52 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, return 0; } -static int -apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, - struct module *me) +static int apply_rela_bits(Elf_Addr loc, Elf_Addr val, + int sign, int bits, int shift) +{ + unsigned long umax; + long min, max; + + if (val & ((1UL << shift) - 1)) + return -ENOEXEC; + if (sign) { + val = (Elf_Addr)(((long) val) >> shift); + min = -(1L << (bits - 1)); + max = (1L << (bits - 1)) - 1; + if ((long) val < min || (long) val > max) + return -ENOEXEC; + } else { + val >>= shift; + umax = ((1UL << (bits - 1)) << 1) - 1; + if ((unsigned long) val > umax) + return -ENOEXEC; + } + + if (bits == 8) + *(unsigned char *) loc = val; + else if (bits == 12) + *(unsigned short *) loc = (val & 0xfff) | + (*(unsigned short *) loc & 0xf000); + else if (bits == 16) + *(unsigned short *) loc = val; + else if (bits == 20) + *(unsigned int *) loc = (val & 0xfff) << 16 | + (val & 0xff000) >> 4 | + (*(unsigned int *) loc & 0xf00000ff); + else if (bits == 32) + *(unsigned int *) loc = val; + else if (bits == 64) + *(unsigned long *) loc = val; + return 0; +} + +static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, + const char *strtab, struct module *me) { struct mod_arch_syminfo *info; Elf_Addr loc, val; int r_type, r_sym; + int rc = -ENOEXEC; /* This is where to make the change */ loc = base + rela->r_offset; @@ -197,6 +234,9 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val = symtab[r_sym].st_value; switch (r_type) { + case R_390_NONE: /* No relocation. */ + rc = 0; + break; case R_390_8: /* Direct 8 bit. */ case R_390_12: /* Direct 12 bit. */ case R_390_16: /* Direct 16 bit. */ @@ -205,20 +245,17 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_64: /* Direct 64 bit. */ val += rela->r_addend; if (r_type == R_390_8) - *(unsigned char *) loc = val; + rc = apply_rela_bits(loc, val, 0, 8, 0); else if (r_type == R_390_12) - *(unsigned short *) loc = (val & 0xfff) | - (*(unsigned short *) loc & 0xf000); + rc = apply_rela_bits(loc, val, 0, 12, 0); else if (r_type == R_390_16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_20) - *(unsigned int *) loc = - (*(unsigned int *) loc & 0xf00000ff) | - (val & 0xfff) << 16 | (val & 0xff000) >> 4; + rc = apply_rela_bits(loc, val, 1, 20, 0); else if (r_type == R_390_32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); break; case R_390_PC16: /* PC relative 16 bit. */ case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */ @@ -227,15 +264,15 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PC64: /* PC relative 64 bit. */ val += rela->r_addend - loc; if (r_type == R_390_PC16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 1, 16, 0); else if (r_type == R_390_PC16DBL) - *(unsigned short *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 16, 1); else if (r_type == R_390_PC32DBL) - *(unsigned int *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 32, 1); else if (r_type == R_390_PC32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 1, 32, 0); else if (r_type == R_390_PC64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 1, 64, 0); break; case R_390_GOT12: /* 12 bit GOT offset. */ case R_390_GOT16: /* 16 bit GOT offset. */ @@ -260,26 +297,24 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val = info->got_offset + rela->r_addend; if (r_type == R_390_GOT12 || r_type == R_390_GOTPLT12) - *(unsigned short *) loc = (val & 0xfff) | - (*(unsigned short *) loc & 0xf000); + rc = apply_rela_bits(loc, val, 0, 12, 0); else if (r_type == R_390_GOT16 || r_type == R_390_GOTPLT16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOT20 || r_type == R_390_GOTPLT20) - *(unsigned int *) loc = - (*(unsigned int *) loc & 0xf00000ff) | - (val & 0xfff) << 16 | (val & 0xff000) >> 4; + rc = apply_rela_bits(loc, val, 1, 20, 0); else if (r_type == R_390_GOT32 || r_type == R_390_GOTPLT32) - *(unsigned int *) loc = val; - else if (r_type == R_390_GOTENT || - r_type == R_390_GOTPLTENT) - *(unsigned int *) loc = - (val + (Elf_Addr) me->module_core - loc) >> 1; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_GOT64 || r_type == R_390_GOTPLT64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); + else if (r_type == R_390_GOTENT || + r_type == R_390_GOTPLTENT) { + val += (Elf_Addr) me->module_core - loc; + rc = apply_rela_bits(loc, val, 1, 32, 1); + } break; case R_390_PLT16DBL: /* 16 bit PC rel. PLT shifted by 1. */ case R_390_PLT32DBL: /* 32 bit PC rel. PLT shifted by 1. */ @@ -321,17 +356,17 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val += rela->r_addend - loc; } if (r_type == R_390_PLT16DBL) - *(unsigned short *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 16, 1); else if (r_type == R_390_PLTOFF16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_PLT32DBL) - *(unsigned int *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 32, 1); else if (r_type == R_390_PLT32 || r_type == R_390_PLTOFF32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_PLT64 || r_type == R_390_PLTOFF64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); break; case R_390_GOTOFF16: /* 16 bit offset to GOT. */ case R_390_GOTOFF32: /* 32 bit offset to GOT. */ @@ -339,20 +374,20 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val = val + rela->r_addend - ((Elf_Addr) me->module_core + me->arch.got_offset); if (r_type == R_390_GOTOFF16) - *(unsigned short *) loc = val; + rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOTOFF32) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 0, 32, 0); else if (r_type == R_390_GOTOFF64) - *(unsigned long *) loc = val; + rc = apply_rela_bits(loc, val, 0, 64, 0); break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ val = (Elf_Addr) me->module_core + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) - *(unsigned int *) loc = val; + rc = apply_rela_bits(loc, val, 1, 32, 0); else if (r_type == R_390_GOTPCDBL) - *(unsigned int *) loc = val >> 1; + rc = apply_rela_bits(loc, val, 1, 32, 1); break; case R_390_COPY: case R_390_GLOB_DAT: /* Create GOT entry. */ @@ -360,19 +395,25 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_RELATIVE: /* Adjust by program base. */ /* Only needed if we want to support loading of modules linked with -shared. */ - break; + return -ENOEXEC; default: - printk(KERN_ERR "module %s: Unknown relocation: %u\n", + printk(KERN_ERR "module %s: unknown relocation: %u\n", me->name, r_type); return -ENOEXEC; } + if (rc) { + printk(KERN_ERR "module %s: relocation error for symbol %s " + "(r_type %i, value 0x%lx)\n", + me->name, strtab + symtab[r_sym].st_name, + r_type, (unsigned long) val); + return rc; + } return 0; } -int -apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, - unsigned int symindex, unsigned int relsec, - struct module *me) +int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) { Elf_Addr base; Elf_Sym *symtab; @@ -388,7 +429,7 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, n = sechdrs[relsec].sh_size / sizeof(Elf_Rela); for (i = 0; i < n; i++, rela++) { - rc = apply_rela(rela, base, symtab, me); + rc = apply_rela(rela, base, symtab, strtab, me); if (rc) return rc; } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 7918fbea36b..210e1285f75 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -55,7 +55,7 @@ void s390_handle_mcck(void) local_mcck_disable(); mcck = __get_cpu_var(cpu_mcck); memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct)); - clear_thread_flag(TIF_MCCK_PENDING); + clear_cpu_flag(CIF_MCCK_PENDING); local_mcck_enable(); local_irq_restore(flags); @@ -214,10 +214,7 @@ static int notrace s390_revalidate_registers(struct mci *mci) : "0", "cc"); #endif /* Revalidate clock comparator register */ - if (S390_lowcore.clock_comparator == -1) - set_clock_comparator(S390_lowcore.mcck_clock); - else - set_clock_comparator(S390_lowcore.clock_comparator); + set_clock_comparator(S390_lowcore.clock_comparator); /* Check if old PSW is valid */ if (!mci->wp) /* @@ -293,7 +290,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) * retry this instruction. */ spin_lock(&ipd_lock); - tmp = get_clock(); + tmp = get_tod_clock(); if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME) ipd_count++; else @@ -316,7 +313,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) */ mcck->kill_task = 1; mcck->mcck_code = *(unsigned long long *) mci; - set_thread_flag(TIF_MCCK_PENDING); + set_cpu_flag(CIF_MCCK_PENDING); } else { /* * Couldn't restore all register contents while in @@ -355,12 +352,12 @@ void notrace s390_do_machine_check(struct pt_regs *regs) if (mci->cp) { /* Channel report word pending */ mcck->channel_report = 1; - set_thread_flag(TIF_MCCK_PENDING); + set_cpu_flag(CIF_MCCK_PENDING); } if (mci->w) { /* Warning pending */ mcck->warning = 1; - set_thread_flag(TIF_MCCK_PENDING); + set_cpu_flag(CIF_MCCK_PENDING); } nmi_exit(); } diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 46480d81df0..d112fc66f99 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -10,6 +10,7 @@ #include <linux/crash_dump.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <asm/checksum.h> #include <asm/lowcore.h> #include <asm/os_info.h> diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 86ec7447e1f..ea75d011a6f 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -274,7 +274,7 @@ static int reserve_pmc_hardware(void) int flags = PMC_INIT; on_each_cpu(setup_pmc_cpu, &flags, 1); - measurement_alert_subclass_register(); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); return 0; } @@ -285,7 +285,7 @@ static void release_pmc_hardware(void) int flags = PMC_RELEASE; on_each_cpu(setup_pmc_cpu, &flags, 1); - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); } /* Release the PMU if event is the last perf event */ @@ -367,13 +367,6 @@ static int __hw_perf_event_init(struct perf_event *event) if (ev >= PERF_CPUM_CF_MAX_CTR) return -EINVAL; - /* The CPU measurement counter facility does not have any interrupts - * to do sampling. Sampling must be provided by external means, - * for example, by timers. - */ - if (hwc->sample_period) - return -EINVAL; - /* Use the hardware perf event structure to store the counter number * in 'config' member and the counter set to which the counter belongs * in the 'config_base'. The counter set (config_base) is then used @@ -418,6 +411,12 @@ static int cpumf_pmu_event_init(struct perf_event *event) case PERF_TYPE_HARDWARE: case PERF_TYPE_HW_CACHE: case PERF_TYPE_RAW: + /* The CPU measurement counter facility does not have overflow + * interrupts to do sampling. Sampling must be provided by + * external means, for example, by timers. + */ + if (is_sampling_event(event)) + return -ENOENT; err = __hw_perf_event_init(event); break; default: @@ -640,8 +639,8 @@ static struct pmu cpumf_pmu = { .cancel_txn = cpumf_pmu_cancel_txn, }; -static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self, - unsigned long action, void *hcpu) +static int cpumf_pmu_notifier(struct notifier_block *self, unsigned long action, + void *hcpu) { unsigned int cpu = (long) hcpu; int flags; @@ -674,17 +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(®s, 0, sizeof(regs)); + regs.int_code = 0x1407; + regs.int_parm = CPU_MF_INT_SF_PRA; + sde_regs = (struct perf_sf_sde_regs *) ®s.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, ®s, sde_regs)) + goto out; + if (perf_event_overflow(event, &data, ®s)) { + 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 f58f37f6682..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 @@ -13,17 +13,22 @@ #include <linux/kernel.h> #include <linux/perf_event.h> +#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); @@ -34,35 +39,189 @@ 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; } EXPORT_SYMBOL(perf_num_counters); -void perf_event_print_debug(void) +static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs) { - struct cpumf_ctr_info cf_info; + struct stack_frame *stack = (struct stack_frame *) regs->gprs[15]; + + if (!stack) + return NULL; + + return (struct kvm_s390_sie_block *) stack->empty1[0]; +} + +static bool is_in_guest(struct pt_regs *regs) +{ + if (user_mode(regs)) + return false; +#if IS_ENABLED(CONFIG_KVM) + return instruction_pointer(regs) == (unsigned long) &sie_exit; +#else + return false; +#endif +} + +static unsigned long guest_is_user_mode(struct pt_regs *regs) +{ + return sie_block(regs)->gpsw.mask & PSW_MASK_PSTATE; +} + +static unsigned long instruction_pointer_guest(struct pt_regs *regs) +{ + return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN; +} + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + return is_in_guest(regs) ? instruction_pointer_guest(regs) + : instruction_pointer(regs); +} + +static unsigned long perf_misc_guest_flags(struct pt_regs *regs) +{ + return guest_is_user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER + : 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; - int cpu; - if (!cpum_cf_avail()) - return; + sde_regs = (struct perf_sf_sde_regs *) ®s->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; +} - local_irq_save(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); + + return user_mode(regs) ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; +} + +static void print_debug_cf(void) +{ + struct cpumf_ctr_info cf_info; + int cpu = smp_processor_id(); - cpu = smp_processor_id(); memset(&cf_info, 0, sizeof(cf_info)); - if (!qctri(&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); - print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET, - &cf_info, sizeof(cf_info)); - } +} + +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, @@ -122,3 +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/pgm_check.S b/arch/s390/kernel/pgm_check.S index 14bdecb6192..813ec726087 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -78,7 +78,7 @@ PGM_CHECK_DEFAULT /* 34 */ PGM_CHECK_DEFAULT /* 35 */ PGM_CHECK_DEFAULT /* 36 */ PGM_CHECK_DEFAULT /* 37 */ -PGM_CHECK_64BIT(do_asce_exception) /* 38 */ +PGM_CHECK_64BIT(do_dat_exception) /* 38 */ PGM_CHECK_64BIT(do_dat_exception) /* 39 */ PGM_CHECK_64BIT(do_dat_exception) /* 3a */ PGM_CHECK_64BIT(do_dat_exception) /* 3b */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 536d64579d9..93b9ca42e5c 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -61,41 +61,28 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sf->gprs[8]; } -/* - * The idle loop on a S390... - */ -static void default_idle(void) +void arch_cpu_idle(void) { - if (cpu_is_offline(smp_processor_id())) - cpu_die(); - local_irq_disable(); - if (need_resched()) { - local_irq_enable(); - return; - } local_mcck_disable(); - if (test_thread_flag(TIF_MCCK_PENDING)) { + if (test_cpu_flag(CIF_MCCK_PENDING)) { local_mcck_enable(); local_irq_enable(); return; } /* Halt the cpu and keep track of cpu time accounting. */ vtime_stop_cpu(); + local_irq_enable(); } -void cpu_idle(void) +void arch_cpu_idle_exit(void) { - for (;;) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched() && !test_thread_flag(TIF_MCCK_PENDING)) - default_idle(); - rcu_idle_exit(); - tick_nohz_idle_exit(); - if (test_thread_flag(TIF_MCCK_PENDING)) - s390_handle_mcck(); - schedule_preempt_disabled(); - } + if (test_cpu_flag(CIF_MCCK_PENDING)) + s390_handle_mcck(); +} + +void arch_cpu_idle_dead(void) +{ + cpu_die(); } extern void __kprobes kernel_thread_starter(void); @@ -136,7 +123,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, memset(&p->thread.per_user, 0, sizeof(p->thread.per_user)); memset(&p->thread.per_event, 0, sizeof(p->thread.per_event)); clear_tsk_thread_flag(p, TIF_SINGLE_STEP); - clear_tsk_thread_flag(p, TIF_PER_TRAP); /* Initialize per thread user and system timer values */ ti = task_thread_info(p); ti->user_timer = 0; @@ -152,7 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(&frame->childregs, 0, sizeof(struct pt_regs)); - frame->childregs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | + frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; frame->childregs.psw.addr = PSW_ADDR_AMODE | (unsigned long) kernel_thread_starter; @@ -165,6 +151,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, } frame->childregs = *current_pt_regs(); frame->childregs.gprs[2] = 0; /* child returns 0 on fork. */ + frame->childregs.flags = 0; if (new_stackp) frame->childregs.gprs[15] = new_stackp; @@ -178,7 +165,8 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, * save fprs to current->thread.fp_regs to merge them with * the emulated registers and then copy the result to the child. */ - save_fp_regs(¤t->thread.fp_regs); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); memcpy(&p->thread.fp_regs, ¤t->thread.fp_regs, sizeof(s390_fp_regs)); /* Set a new TLS ? */ @@ -186,7 +174,9 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, p->thread.acrs[0] = frame->childregs.gprs[6]; #else /* CONFIG_64BIT */ /* Save the fpu registers to new thread structure. */ - save_fp_regs(&p->thread.fp_regs); + save_fp_ctl(&p->thread.fp_regs.fpc); + save_fp_regs(p->thread.fp_regs.fprs); + p->thread.fp_regs.pad = 0; /* Set a new TLS ? */ if (clone_flags & CLONE_SETTLS) { unsigned long tls = frame->childregs.gprs[6]; @@ -218,10 +208,12 @@ int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs) * save fprs to current->thread.fp_regs to merge them with * the emulated registers and then copy the result to the dump. */ - save_fp_regs(¤t->thread.fp_regs); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); memcpy(fpregs, ¤t->thread.fp_regs, sizeof(s390_fp_regs)); #else /* CONFIG_64BIT */ - save_fp_regs(fpregs); + save_fp_ctl(&fpregs->fpc); + save_fp_regs(fpregs->fprs); #endif /* CONFIG_64BIT */ return 1; } @@ -269,20 +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/processor.c b/arch/s390/kernel/processor.c index 753c41d0ffd..24612029f45 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -21,7 +21,7 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id); /* * cpu_init - initializes state that is per-CPU. */ -void __cpuinit cpu_init(void) +void cpu_init(void) { struct s390_idle_data *idle = &__get_cpu_var(s390_idle); struct cpuid *id = &__get_cpu_var(cpu_id); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a314c57f4e9..5dc7ad9e2fb 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -47,7 +47,7 @@ enum s390_regset { REGSET_GENERAL_EXTENDED, }; -void update_per_regs(struct task_struct *task) +void update_cr_regs(struct task_struct *task) { struct pt_regs *regs = task_pt_regs(task); struct thread_struct *thread = &task->thread; @@ -56,17 +56,26 @@ void update_per_regs(struct task_struct *task) #ifdef CONFIG_64BIT /* Take care of the enable/disable of transactional execution. */ if (MACHINE_HAS_TE) { - unsigned long cr0, cr0_new; + unsigned long cr, cr_new; - __ctl_store(cr0, 0, 0); - /* set or clear transaction execution bits 8 and 9. */ + __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) - cr0_new = cr0 & ~(3UL << 54); - else - cr0_new = cr0 | (3UL << 54); - /* Only load control register 0 if necessary. */ - if (cr0 != cr0_new) - __ctl_load(cr0_new, 0, 0); + cr_new &= ~(1UL << 55); + if (cr_new != cr) + __ctl_load(cr_new, 0, 0); + /* Set or clear transaction execution TDC bits 62 and 63. */ + __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 |= 1UL; + else + cr_new |= 2UL; + } + if (cr_new != cr) + __ctl_load(cr_new, 2, 2); } #endif /* Copy user specified PER registers */ @@ -76,7 +85,10 @@ void update_per_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; @@ -98,16 +110,20 @@ void update_per_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_per_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_per_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); } /* @@ -120,7 +136,7 @@ void ptrace_disable(struct task_struct *task) memset(&task->thread.per_user, 0, sizeof(task->thread.per_user)); memset(&task->thread.per_event, 0, sizeof(task->thread.per_event)); clear_tsk_thread_flag(task, TIF_SINGLE_STEP); - clear_tsk_thread_flag(task, TIF_PER_TRAP); + clear_pt_regs_flag(task_pt_regs(task), PIF_PER_TRAP); task->thread.per_flags = 0; } @@ -190,9 +206,11 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) * psw and gprs are stored on the stack */ tmp = *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr); - if (addr == (addr_t) &dummy->regs.psw.mask) + if (addr == (addr_t) &dummy->regs.psw.mask) { /* Return a clean psw mask. */ - tmp = psw_user_bits | (tmp & PSW_MASK_USER); + tmp &= PSW_MASK_USER | PSW_MASK_RI; + tmp |= PSW_USER_BITS; + } } else if (addr < (addr_t) &dummy->regs.orig_gpr2) { /* @@ -231,8 +249,7 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) offset = addr - (addr_t) &dummy->regs.fp_regs; tmp = *(addr_t *)((addr_t) &child->thread.fp_regs + offset); if (addr == (addr_t) &dummy->regs.fp_regs.fpc) - tmp &= (unsigned long) FPC_VALID_MASK - << (BITS_PER_LONG - 32); + tmp <<= BITS_PER_LONG - 32; } else if (addr < (addr_t) (&dummy->regs.per_info + 1)) { /* @@ -313,11 +330,20 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * psw and gprs are stored on the stack */ - if (addr == (addr_t) &dummy->regs.psw.mask && - ((data & ~PSW_MASK_USER) != psw_user_bits || - ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)))) - /* Invalid psw mask. */ - return -EINVAL; + if (addr == (addr_t) &dummy->regs.psw.mask) { + unsigned long mask = PSW_MASK_USER; + + mask |= is_ri_task(child) ? PSW_MASK_RI : 0; + if ((data ^ PSW_USER_BITS) & ~mask) + /* Invalid psw mask. */ + return -EINVAL; + if ((data & PSW_MASK_ASC) == PSW_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; + if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)) + /* Invalid addressing mode bits */ + return -EINVAL; + } *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { @@ -355,10 +381,10 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * floating point regs. are stored in the thread structure */ - if (addr == (addr_t) &dummy->regs.fp_regs.fpc && - (data & ~((unsigned long) FPC_VALID_MASK - << (BITS_PER_LONG - 32))) != 0) - return -EINVAL; + if (addr == (addr_t) &dummy->regs.fp_regs.fpc) + if ((unsigned int) data != 0 || + test_fp_ctl(data >> (BITS_PER_LONG - 32))) + return -EINVAL; offset = addr - (addr_t) &dummy->regs.fp_regs; *(addr_t *)((addr_t) &child->thread.fp_regs + offset) = data; @@ -447,6 +473,26 @@ long arch_ptrace(struct task_struct *child, long request, if (!MACHINE_HAS_TE) return -EIO; child->thread.per_flags |= PER_FLAG_NO_TE; + child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND; + return 0; + case PTRACE_TE_ABORT_RAND: + if (!MACHINE_HAS_TE || (child->thread.per_flags & PER_FLAG_NO_TE)) + return -EIO; + switch (data) { + case 0UL: + child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND; + break; + case 1UL: + child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND; + child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND_TEND; + break; + case 2UL: + child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND; + child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND_TEND; + break; + default: + return -EINVAL; + } return 0; default: /* Removing high order bit from addr (only for 31 bit). */ @@ -529,7 +575,8 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) if (addr == (addr_t) &dummy32->regs.psw.mask) { /* Fake a 31 bit psw mask. */ tmp = (__u32)(regs->psw.mask >> 32); - tmp = psw32_user_bits | (tmp & PSW32_MASK_USER); + tmp &= PSW32_MASK_USER | PSW32_MASK_RI; + tmp |= PSW32_USER_BITS; } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Fake a 31 bit psw address. */ tmp = (__u32) regs->psw.addr | @@ -626,13 +673,19 @@ static int __poke_user_compat(struct task_struct *child, * psw, gprs, acrs and orig_gpr2 are stored on the stack */ if (addr == (addr_t) &dummy32->regs.psw.mask) { + __u32 mask = PSW32_MASK_USER; + + mask |= is_ri_task(child) ? PSW32_MASK_RI : 0; /* Build a 64 bit psw mask from 31 bit mask. */ - if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits) + if ((tmp ^ PSW32_USER_BITS) & ~mask) /* Invalid psw mask. */ return -EINVAL; + if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME) + /* Invalid address-space-control bits */ + return -EINVAL; regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | (regs->psw.mask & PSW_MASK_BA) | - (__u64)(tmp & PSW32_MASK_USER) << 32; + (__u64)(tmp & mask) << 32; } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Build a 64 bit psw address from 31 bit address. */ regs->psw.addr = (__u64) tmp & PSW32_ADDR_INSN; @@ -668,8 +721,7 @@ static int __poke_user_compat(struct task_struct *child, * floating point regs. are stored in the thread structure */ if (addr == (addr_t) &dummy32->regs.fp_regs.fpc && - (tmp & ~FPC_VALID_MASK) != 0) - /* Invalid floating point control. */ + test_fp_ctl(tmp)) return -EINVAL; offset = addr - (addr_t) &dummy32->regs.fp_regs; *(__u32 *)((addr_t) &child->thread.fp_regs + offset) = tmp; @@ -769,7 +821,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) * debugger stored an invalid system call number. Skip * the system call and the system call restart handling. */ - clear_thread_flag(TIF_SYSCALL); + clear_pt_regs_flag(regs, PIF_SYSCALL); ret = -1; } @@ -867,8 +919,10 @@ static int s390_fpregs_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - if (target == current) - save_fp_regs(&target->thread.fp_regs); + if (target == current) { + save_fp_ctl(&target->thread.fp_regs.fpc); + save_fp_regs(target->thread.fp_regs.fprs); + } return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_regs, 0, -1); @@ -881,19 +935,21 @@ static int s390_fpregs_set(struct task_struct *target, { int rc = 0; - if (target == current) - save_fp_regs(&target->thread.fp_regs); + if (target == current) { + save_fp_ctl(&target->thread.fp_regs.fpc); + save_fp_regs(target->thread.fp_regs.fprs); + } /* If setting FPC, must validate it first. */ if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { - u32 fpc[2] = { target->thread.fp_regs.fpc, 0 }; - rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpc, + u32 ufpc[2] = { target->thread.fp_regs.fpc, 0 }; + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc, 0, offsetof(s390_fp_regs, fprs)); if (rc) return rc; - if ((fpc[0] & ~FPC_VALID_MASK) != 0 || fpc[1] != 0) + if (ufpc[1] != 0 || test_fp_ctl(ufpc[0])) return -EINVAL; - target->thread.fp_regs.fpc = fpc[0]; + target->thread.fp_regs.fpc = ufpc[0]; } if (rc == 0 && count > 0) @@ -901,8 +957,10 @@ static int s390_fpregs_set(struct task_struct *target, target->thread.fp_regs.fprs, offsetof(s390_fp_regs, fprs), -1); - if (rc == 0 && target == current) - restore_fp_regs(&target->thread.fp_regs); + if (rc == 0 && target == current) { + restore_fp_ctl(&target->thread.fp_regs.fpc); + restore_fp_regs(target->thread.fp_regs.fprs); + } return rc; } @@ -1271,7 +1329,7 @@ int regs_query_register_offset(const char *name) if (!name || *name != 'r') return -EINVAL; - if (strict_strtoul(name + 1, 10, &offset)) + if (kstrtoul(name + 1, 10, &offset)) return -EINVAL; if (offset >= NUM_GPRS) return -EINVAL; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 077a99389b0..26b4ae96fdd 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -40,8 +40,6 @@ static void disable_runtime_instr(void) static void init_runtime_instr_cb(struct runtime_instr_cb *cb) { cb->buf_limit = 0xfff; - if (s390_user_mode == HOME_SPACE_MODE) - cb->home_space = 1; cb->int_requested = 1; cb->pstate = 1; cb->pstate_set_buf = 1; @@ -139,10 +137,11 @@ static int __init runtime_instr_init(void) if (!runtime_instr_avail()) return 0; - measurement_alert_subclass_register(); - rc = register_external_interrupt(0x1407, runtime_instr_int_handler); + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); + rc = register_external_irq(EXT_IRQ_MEASURE_ALERT, + runtime_instr_int_handler); if (rc) - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); else pr_info("Runtime instrumentation facility initialized\n"); return rc; diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 9bdbcef1da9..9f60467938d 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -5,8 +5,9 @@ #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 EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index b6506ee32a3..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 @@ -225,7 +226,7 @@ _sclp_print: ahi %r2,1 ltr %r0,%r0 # end of string? jz .LfinalizemtoS4 - chi %r0,0x15 # end of line (NL)? + chi %r0,0x0a # end of line (NL)? jz .LfinalizemtoS4 stc %r0,0(%r6,%r7) # copy to mto la %r11,0(%r6,%r7) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a5360de85ec..1e2264b46e4 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> @@ -64,18 +63,6 @@ #include <asm/sclp.h> #include "entry.h" -long psw_kernel_bits = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY | - PSW_MASK_EA | PSW_MASK_BA; -long psw_user_bits = PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | - PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_ASC_HOME; - -/* - * User copy operations. - */ -struct uaccess_ops uaccess; -EXPORT_SYMBOL(uaccess); - /* * Machine setup.. */ @@ -91,10 +78,9 @@ EXPORT_SYMBOL(console_irq); unsigned long elf_hwcap = 0; char elf_platform[ELF_PLATFORM_SIZE]; -struct mem_chunk __initdata memory_chunk[MEMORY_CHUNKS]; - int __initdata memory_end_set; unsigned long __initdata memory_end; +unsigned long __initdata max_physmem_end; unsigned long VMALLOC_START; EXPORT_SYMBOL(VMALLOC_START); @@ -225,27 +211,19 @@ static void __init conmode_default(void) } } -#ifdef CONFIG_ZFCPDUMP -static void __init setup_zfcpdump(unsigned int console_devno) +#ifdef CONFIG_CRASH_DUMP +static void __init setup_zfcpdump(void) { - static char str[41]; - if (ipl_info.type != IPL_TYPE_FCP_DUMP) return; if (OLDMEM_BASE) return; - if (console_devno != -1) - sprintf(str, " cio_ignore=all,!0.0.%04x,!0.0.%04x", - ipl_info.data.fcp.dev_id.devno, console_devno); - else - sprintf(str, " cio_ignore=all,!0.0.%04x", - ipl_info.data.fcp.dev_id.devno); - strcat(boot_command_line, str); + strcat(boot_command_line, " cio_ignore=all,!ipldev,!condev"); console_loglevel = 2; } #else -static inline void setup_zfcpdump(unsigned int console_devno) {} -#endif /* CONFIG_ZFCPDUMP */ +static inline void setup_zfcpdump(void) {} +#endif /* CONFIG_CRASH_DUMP */ /* * Reboot, halt and power_off stubs. They just call _machine_restart, @@ -294,6 +272,7 @@ EXPORT_SYMBOL_GPL(pm_power_off); static int __init early_parse_mem(char *p) { memory_end = memparse(p, &p); + memory_end &= PAGE_MASK; memory_end_set = 1; return 0; } @@ -308,43 +287,6 @@ static int __init parse_vmalloc(char *arg) } early_param("vmalloc", parse_vmalloc); -unsigned int s390_user_mode = PRIMARY_SPACE_MODE; -EXPORT_SYMBOL_GPL(s390_user_mode); - -static void __init set_user_mode_primary(void) -{ - psw_kernel_bits = (psw_kernel_bits & ~PSW_MASK_ASC) | PSW_ASC_HOME; - psw_user_bits = (psw_user_bits & ~PSW_MASK_ASC) | PSW_ASC_PRIMARY; -#ifdef CONFIG_COMPAT - psw32_user_bits = - (psw32_user_bits & ~PSW32_MASK_ASC) | PSW32_ASC_PRIMARY; -#endif - uaccess = MACHINE_HAS_MVCOS ? uaccess_mvcos_switch : uaccess_pt; -} - -static int __init early_parse_user_mode(char *p) -{ - if (p && strcmp(p, "primary") == 0) - s390_user_mode = PRIMARY_SPACE_MODE; - else if (!p || strcmp(p, "home") == 0) - s390_user_mode = HOME_SPACE_MODE; - else - return 1; - return 0; -} -early_param("user_mode", early_parse_user_mode); - -static void __init setup_addressing_mode(void) -{ - if (s390_user_mode != PRIMARY_SPACE_MODE) - return; - set_user_mode_primary(); - if (MACHINE_HAS_MVCOS) - pr_info("Address spaces switched, mvcos available\n"); - else - pr_info("Address spaces switched, mvcos not available\n"); -} - void *restart_stack __attribute__((__section__(".data"))); static void __init setup_lowcore(void) @@ -356,32 +298,35 @@ static void __init setup_lowcore(void) */ BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096); lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0); - lc->restart_psw.mask = psw_kernel_bits; + lc->restart_psw.mask = PSW_KERNEL_BITS; lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) restart_int_handler; - lc->external_new_psw.mask = psw_kernel_bits | + lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; lc->external_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) ext_int_handler; - lc->svc_new_psw.mask = psw_kernel_bits | + lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call; - lc->program_new_psw.mask = psw_kernel_bits | + lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; lc->program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) pgm_check_handler; - lc->mcck_new_psw.mask = psw_kernel_bits; + lc->mcck_new_psw.mask = PSW_KERNEL_BITS; lc->mcck_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) mcck_int_handler; - lc->io_new_psw.mask = psw_kernel_bits | + lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; - lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; + lc->kernel_stack = ((unsigned long) &init_thread_union) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->async_stack = (unsigned long) - __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE; + __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + + ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->panic_stack = (unsigned long) - __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + PAGE_SIZE; + __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0) + + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; lc->machine_flags = S390_lowcore.machine_flags; @@ -413,7 +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; @@ -428,6 +373,10 @@ static void __init setup_lowcore(void) mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source); mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw); +#ifdef CONFIG_SMP + lc->spinlock_lockval = arch_spin_lockval(0); +#endif + set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; } @@ -456,7 +405,8 @@ static struct resource __initdata *standard_resources[] = { static void __init setup_resources(void) { struct resource *res, *std_res, *sub_res; - int i, j; + struct memblock_region *reg; + int j; code_resource.start = (unsigned long) &_text; code_resource.end = (unsigned long) &_etext - 1; @@ -465,28 +415,13 @@ static void __init setup_resources(void) bss_resource.start = (unsigned long) &__bss_start; bss_resource.end = (unsigned long) &__bss_stop - 1; - for (i = 0; i < MEMORY_CHUNKS; i++) { - if (!memory_chunk[i].size) - continue; - if (memory_chunk[i].type == CHUNK_OLDMEM || - memory_chunk[i].type == CHUNK_CRASHK) - continue; + for_each_memblock(memory, reg) { res = alloc_bootmem_low(sizeof(*res)); res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; - switch (memory_chunk[i].type) { - case CHUNK_READ_WRITE: - case CHUNK_CRASHK: - res->name = "System RAM"; - break; - case CHUNK_READ_ONLY: - res->name = "System ROM"; - res->flags |= IORESOURCE_READONLY; - break; - default: - res->name = "reserved"; - } - res->start = memory_chunk[i].addr; - res->end = res->start + memory_chunk[i].size - 1; + + res->name = "System RAM"; + res->start = reg->base; + res->end = reg->base + reg->size - 1; request_resource(&iomem_resource, res); for (j = 0; j < ARRAY_SIZE(standard_resources); j++) { @@ -507,51 +442,14 @@ static void __init setup_resources(void) } } -unsigned long real_memory_size; -EXPORT_SYMBOL_GPL(real_memory_size); - static void __init setup_memory_end(void) { unsigned long vmax, vmalloc_size, tmp; - int i; - - -#ifdef CONFIG_ZFCPDUMP - if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) { - memory_end = ZFCPDUMP_HSA_SIZE; - memory_end_set = 1; - } -#endif - real_memory_size = 0; - memory_end &= PAGE_MASK; - - /* - * Make sure all chunks are MAX_ORDER aligned so we don't need the - * extra checks that HOLES_IN_ZONE would require. - */ - for (i = 0; i < MEMORY_CHUNKS; i++) { - unsigned long start, end; - struct mem_chunk *chunk; - unsigned long align; - - chunk = &memory_chunk[i]; - align = 1UL << (MAX_ORDER + PAGE_SHIFT - 1); - start = (chunk->addr + align - 1) & ~(align - 1); - end = (chunk->addr + chunk->size) & ~(align - 1); - if (start >= end) - memset(chunk, 0, sizeof(*chunk)); - else { - chunk->addr = start; - chunk->size = end - start; - } - real_memory_size = max(real_memory_size, - chunk->addr + chunk->size); - } /* Choose kernel address space layout: 2, 3, or 4 levels. */ #ifdef CONFIG_64BIT vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN; - tmp = (memory_end ?: real_memory_size) / PAGE_SIZE; + tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE; tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size; if (tmp <= (1UL << 42)) vmax = 1UL << 42; /* 3-level kernel page table */ @@ -571,25 +469,19 @@ static void __init setup_memory_end(void) /* Split remaining virtual space between 1:1 mapping & vmemmap array */ tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page)); + /* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */ + tmp = SECTION_ALIGN_UP(tmp); tmp = VMALLOC_START - tmp * sizeof(struct page); tmp &= ~((vmax >> 11) - 1); /* align to page table level */ tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS); vmemmap = (struct page *) tmp; /* Take care that memory_end is set and <= vmemmap */ - memory_end = min(memory_end ?: real_memory_size, tmp); - - /* Fixup memory chunk array to fit into 0..memory_end */ - for (i = 0; i < MEMORY_CHUNKS; i++) { - struct mem_chunk *chunk = &memory_chunk[i]; + memory_end = min(memory_end ?: max_physmem_end, tmp); + max_pfn = max_low_pfn = PFN_DOWN(memory_end); + memblock_remove(memory_end, ULONG_MAX); - if (chunk->addr >= memory_end) { - memset(chunk, 0, sizeof(*chunk)); - continue; - } - if (chunk->addr + chunk->size > memory_end) - chunk->size = memory_end - chunk->addr; - } + pr_notice("Max memory size: %luMB\n", memory_end >> 20); } static void __init setup_vmcoreinfo(void) @@ -600,98 +492,6 @@ static void __init setup_vmcoreinfo(void) #ifdef CONFIG_CRASH_DUMP /* - * Find suitable location for crashkernel memory - */ -static unsigned long __init find_crash_base(unsigned long crash_size, - char **msg) -{ - unsigned long crash_base; - struct mem_chunk *chunk; - int i; - - if (memory_chunk[0].size < crash_size) { - *msg = "first memory chunk must be at least crashkernel size"; - return 0; - } - if (OLDMEM_BASE && crash_size == OLDMEM_SIZE) - return OLDMEM_BASE; - - for (i = MEMORY_CHUNKS - 1; i >= 0; i--) { - chunk = &memory_chunk[i]; - if (chunk->size == 0) - continue; - if (chunk->type != CHUNK_READ_WRITE) - continue; - if (chunk->size < crash_size) - continue; - crash_base = (chunk->addr + chunk->size) - crash_size; - if (crash_base < crash_size) - continue; - if (crash_base < ZFCPDUMP_HSA_SIZE_MAX) - continue; - if (crash_base < (unsigned long) INITRD_START + INITRD_SIZE) - continue; - return crash_base; - } - *msg = "no suitable area found"; - return 0; -} - -/* - * Check if crash_base and crash_size is valid - */ -static int __init verify_crash_base(unsigned long crash_base, - unsigned long crash_size, - char **msg) -{ - struct mem_chunk *chunk; - int i; - - /* - * Because we do the swap to zero, we must have at least 'crash_size' - * bytes free space before crash_base - */ - if (crash_size > crash_base) { - *msg = "crashkernel offset must be greater than size"; - return -EINVAL; - } - - /* First memory chunk must be at least crash_size */ - if (memory_chunk[0].size < crash_size) { - *msg = "first memory chunk must be at least crashkernel size"; - return -EINVAL; - } - /* Check if we fit into the respective memory chunk */ - for (i = 0; i < MEMORY_CHUNKS; i++) { - chunk = &memory_chunk[i]; - if (chunk->size == 0) - continue; - if (crash_base < chunk->addr) - continue; - if (crash_base >= chunk->addr + chunk->size) - continue; - /* we have found the memory chunk */ - if (crash_base + crash_size > chunk->addr + chunk->size) { - *msg = "selected memory chunk is too small for " - "crashkernel memory"; - return -EINVAL; - } - return 0; - } - *msg = "invalid memory range specified"; - return -EINVAL; -} - -/* - * Reserve kdump memory by creating a memory hole in the mem_chunk array - */ -static void __init reserve_kdump_bootmem(unsigned long addr, unsigned long size, - int type) -{ - create_mem_hole(memory_chunk, addr, size, type); -} - -/* * When kdump is enabled, we have to ensure that no memory from * the area [0 - crashkernel memory size] and * [crashk_res.start - crashk_res.end] is set offline. @@ -717,21 +517,44 @@ static struct notifier_block kdump_mem_nb = { #endif /* + * Make sure that the area behind memory_end is protected + */ +static void reserve_memory_end(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (ipl_info.type == IPL_TYPE_FCP_DUMP && + !OLDMEM_BASE && sclp_get_hsa_size()) { + memory_end = sclp_get_hsa_size(); + memory_end &= PAGE_MASK; + memory_end_set = 1; + } +#endif + if (!memory_end_set) + return; + memblock_reserve(memory_end, ULONG_MAX); +} + +/* * Make sure that oldmem, where the dump is stored, is protected */ static void reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP - if (!OLDMEM_BASE) - return; + if (OLDMEM_BASE) + /* Forget all memory above the running kdump system */ + memblock_reserve(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX); +#endif +} - reserve_kdump_bootmem(OLDMEM_BASE, OLDMEM_SIZE, CHUNK_OLDMEM); - reserve_kdump_bootmem(OLDMEM_SIZE, memory_end - OLDMEM_SIZE, - CHUNK_OLDMEM); - if (OLDMEM_BASE + OLDMEM_SIZE == real_memory_size) - saved_max_pfn = PFN_DOWN(OLDMEM_BASE) - 1; - else - saved_max_pfn = PFN_DOWN(real_memory_size) - 1; +/* + * Make sure that oldmem, where the dump is stored, is protected + */ +static void remove_oldmem(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE) + /* Forget all memory above the running kdump system */ + memblock_remove(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX); #endif } @@ -742,168 +565,132 @@ static void __init reserve_crashkernel(void) { #ifdef CONFIG_CRASH_DUMP unsigned long long crash_base, crash_size; - char *msg = NULL; + phys_addr_t low, high; int rc; rc = parse_crashkernel(boot_command_line, memory_end, &crash_size, &crash_base); - if (rc || crash_size == 0) - return; + crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN); crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN); - if (register_memory_notifier(&kdump_mem_nb)) + if (rc || crash_size == 0) return; - if (!crash_base) - crash_base = find_crash_base(crash_size, &msg); - if (!crash_base) { - pr_info("crashkernel reservation failed: %s\n", msg); - unregister_memory_notifier(&kdump_mem_nb); + + if (memblock.memory.regions[0].size < crash_size) { + pr_info("crashkernel reservation failed: %s\n", + "first memory chunk must be at least crashkernel size"); return; } - if (verify_crash_base(crash_base, crash_size, &msg)) { - pr_info("crashkernel reservation failed: %s\n", msg); - unregister_memory_notifier(&kdump_mem_nb); + + low = crash_base ?: OLDMEM_BASE; + high = low + crash_size; + if (low >= OLDMEM_BASE && high <= OLDMEM_BASE + OLDMEM_SIZE) { + /* The crashkernel fits into OLDMEM, reuse OLDMEM */ + crash_base = low; + } else { + /* Find suitable area in free memory */ + low = max_t(unsigned long, crash_size, sclp_get_hsa_size()); + high = crash_base ? crash_base + crash_size : ULONG_MAX; + + if (crash_base && crash_base < low) { + pr_info("crashkernel reservation failed: %s\n", + "crash_base too low"); + return; + } + low = crash_base ?: low; + crash_base = memblock_find_in_range(low, high, crash_size, + KEXEC_CRASH_MEM_ALIGN); + } + + if (!crash_base) { + pr_info("crashkernel reservation failed: %s\n", + "no suitable area found"); return; } + + if (register_memory_notifier(&kdump_mem_nb)) + return; + if (!OLDMEM_BASE && MACHINE_IS_VM) diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size)); crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; insert_resource(&iomem_resource, &crashk_res); - reserve_kdump_bootmem(crash_base, crash_size, CHUNK_CRASHK); + memblock_remove(crash_base, crash_size); pr_info("Reserving %lluMB of memory at %lluMB " "for crashkernel (System RAM: %luMB)\n", - crash_size >> 20, crash_base >> 20, memory_end >> 20); + crash_size >> 20, crash_base >> 20, + (unsigned long)memblock.memory.total_size >> 20); os_info_crashkernel_add(crash_base, crash_size); #endif } -static void __init setup_memory(void) +/* + * Reserve the initrd from being used by memblock + */ +static void __init reserve_initrd(void) { - unsigned long bootmap_size; - unsigned long start_pfn, end_pfn; - int i; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_start = INITRD_START; + initrd_end = initrd_start + INITRD_SIZE; + memblock_reserve(INITRD_START, INITRD_SIZE); +#endif +} - /* - * partially used pages are not usable - thus - * we are rounding upwards: - */ +/* + * Check for initrd being in usable memory + */ +static void __init check_initrd(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + if (INITRD_START && INITRD_SIZE && + !memblock_is_region_memory(INITRD_START, INITRD_SIZE)) { + pr_err("initrd does not fit memory.\n"); + memblock_free(INITRD_START, INITRD_SIZE); + initrd_start = initrd_end = 0; + } +#endif +} + +/* + * Reserve all kernel text + */ +static void __init reserve_kernel(void) +{ + unsigned long start_pfn; start_pfn = PFN_UP(__pa(&_end)); - end_pfn = max_pfn = PFN_DOWN(memory_end); -#ifdef CONFIG_BLK_DEV_INITRD /* - * Move the initrd in case the bitmap of the bootmem allocater - * would overwrite it. + * Reserve memory used for lowcore/command line/kernel image. */ + memblock_reserve(0, (unsigned long)_ehead); + memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn) + - (unsigned long)_stext); +} - if (INITRD_START && INITRD_SIZE) { - unsigned long bmap_size; - unsigned long start; - - bmap_size = bootmem_bootmap_pages(end_pfn - start_pfn + 1); - bmap_size = PFN_PHYS(bmap_size); - - if (PFN_PHYS(start_pfn) + bmap_size > INITRD_START) { - start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE; - +static void __init reserve_elfcorehdr(void) +{ #ifdef CONFIG_CRASH_DUMP - if (OLDMEM_BASE) { - /* Move initrd behind kdump oldmem */ - if (start + INITRD_SIZE > OLDMEM_BASE && - start < OLDMEM_BASE + OLDMEM_SIZE) - start = OLDMEM_BASE + OLDMEM_SIZE; - } -#endif - if (start + INITRD_SIZE > memory_end) { - pr_err("initrd extends beyond end of " - "memory (0x%08lx > 0x%08lx) " - "disabling initrd\n", - start + INITRD_SIZE, memory_end); - INITRD_START = INITRD_SIZE = 0; - } else { - pr_info("Moving initrd (0x%08lx -> " - "0x%08lx, size: %ld)\n", - INITRD_START, start, INITRD_SIZE); - memmove((void *) start, (void *) INITRD_START, - INITRD_SIZE); - INITRD_START = start; - } - } - } + if (is_kdump_kernel()) + memblock_reserve(elfcorehdr_addr - OLDMEM_BASE, + PAGE_ALIGN(elfcorehdr_size)); #endif +} - /* - * Initialize the boot-time allocator - */ - bootmap_size = init_bootmem(start_pfn, end_pfn); +static void __init setup_memory(void) +{ + struct memblock_region *reg; /* - * Register RAM areas with the bootmem allocator. + * Init storage key for present memory */ - - for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { - unsigned long start_chunk, end_chunk, pfn; - - if (memory_chunk[i].type != CHUNK_READ_WRITE && - memory_chunk[i].type != CHUNK_CRASHK) - continue; - start_chunk = PFN_DOWN(memory_chunk[i].addr); - end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size); - end_chunk = min(end_chunk, end_pfn); - if (start_chunk >= end_chunk) - continue; - memblock_add_node(PFN_PHYS(start_chunk), - PFN_PHYS(end_chunk - start_chunk), 0); - pfn = max(start_chunk, start_pfn); - storage_key_init_range(PFN_PHYS(pfn), PFN_PHYS(end_chunk)); + for_each_memblock(memory, reg) { + storage_key_init_range(reg->base, reg->base + reg->size); } - psw_set_key(PAGE_DEFAULT_KEY); - free_bootmem_with_active_regions(0, max_pfn); - - /* - * Reserve memory used for lowcore/command line/kernel image. - */ - reserve_bootmem(0, (unsigned long)_ehead, BOOTMEM_DEFAULT); - reserve_bootmem((unsigned long)_stext, - PFN_PHYS(start_pfn) - (unsigned long)_stext, - BOOTMEM_DEFAULT); - /* - * Reserve the bootmem bitmap itself as well. We do this in two - * steps (first step was init_bootmem()) because this catches - * the (very unlikely) case of us accidentally initializing the - * bootmem allocator with an invalid RAM area. - */ - reserve_bootmem(start_pfn << PAGE_SHIFT, bootmap_size, - BOOTMEM_DEFAULT); - -#ifdef CONFIG_CRASH_DUMP - if (crashk_res.start) - reserve_bootmem(crashk_res.start, - crashk_res.end - crashk_res.start + 1, - BOOTMEM_DEFAULT); - if (is_kdump_kernel()) - reserve_bootmem(elfcorehdr_addr - OLDMEM_BASE, - PAGE_ALIGN(elfcorehdr_size), BOOTMEM_DEFAULT); -#endif -#ifdef CONFIG_BLK_DEV_INITRD - if (INITRD_START && INITRD_SIZE) { - if (INITRD_START + INITRD_SIZE <= memory_end) { - reserve_bootmem(INITRD_START, INITRD_SIZE, - BOOTMEM_DEFAULT); - initrd_start = INITRD_START; - initrd_end = initrd_start + INITRD_SIZE; - } else { - pr_err("initrd extends beyond end of " - "memory (0x%08lx > 0x%08lx) " - "disabling initrd\n", - initrd_start + INITRD_SIZE, memory_end); - initrd_start = initrd_end = 0; - } - } -#endif + /* Only cosmetics */ + memblock_enforce_memory_limit(memblock_end_of_DRAM()); } /* @@ -1008,6 +795,7 @@ static void __init setup_hwcaps(void) strcpy(elf_platform, "z196"); break; case 0x2827: + case 0x2828: strcpy(elf_platform, "zEC12"); break; } @@ -1051,29 +839,47 @@ void __init setup_arch(char **cmdline_p) ROOT_DEV = Root_RAM0; + /* Is init_mm really needed? */ init_mm.start_code = PAGE_OFFSET; init_mm.end_code = (unsigned long) &_etext; init_mm.end_data = (unsigned long) &_edata; init_mm.brk = (unsigned long) &_end; - if (MACHINE_HAS_MVCOS) - memcpy(&uaccess, &uaccess_mvcos, sizeof(uaccess)); - else - memcpy(&uaccess, &uaccess_std, sizeof(uaccess)); - parse_early_param(); - os_info_init(); setup_ipl(); - setup_memory_end(); - setup_addressing_mode(); + + /* Do some memory reservations *before* memory is added to memblock */ + reserve_memory_end(); reserve_oldmem(); - reserve_crashkernel(); + reserve_kernel(); + reserve_initrd(); + reserve_elfcorehdr(); + memblock_allow_resize(); + + /* Get information about *all* installed memory */ + detect_memory_memblock(); + + remove_oldmem(); + + /* + * Make sure all chunks are MAX_ORDER aligned so we don't need the + * extra checks that HOLES_IN_ZONE would require. + * + * Is this still required? + */ + memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT)); + + setup_memory_end(); setup_memory(); + + check_initrd(); + reserve_crashkernel(); + setup_resources(); setup_vmcoreinfo(); setup_lowcore(); - + smp_fill_possible_mask(); cpu_init(); s390_init_cpu_topology(); @@ -1092,5 +898,37 @@ void __init setup_arch(char **cmdline_p) set_preferred_console(); /* Setup zfcpdump support */ - setup_zfcpdump(console_devno); + setup_zfcpdump(); +} + +#ifdef CONFIG_32BIT +static int no_removal_warning __initdata; + +static int __init parse_no_removal_warning(char *str) +{ + no_removal_warning = 1; + return 0; } +__setup("no_removal_warning", parse_no_removal_warning); + +static int __init removal_warning(void) +{ + if (no_removal_warning) + return 0; + printk(KERN_ALERT "\n\n"); + printk(KERN_CONT "Warning - you are using a 31 bit kernel!\n\n"); + printk(KERN_CONT "We plan to remove 31 bit kernel support from the kernel sources in March 2015.\n"); + printk(KERN_CONT "Currently we assume that nobody is using the 31 bit kernel on old 31 bit\n"); + printk(KERN_CONT "hardware anymore. If you think that the code should not be removed and also\n"); + printk(KERN_CONT "future versions of the Linux kernel should be able to run in 31 bit mode\n"); + printk(KERN_CONT "please let us know. Please write to:\n"); + printk(KERN_CONT "linux390@de.ibm.com (mail address) and/or\n"); + printk(KERN_CONT "linux-s390@vger.kernel.org (mailing list).\n\n"); + printk(KERN_CONT "Thank you!\n\n"); + printk(KERN_CONT "If this kernel runs on a 64 bit machine you may consider using a 64 bit kernel.\n"); + printk(KERN_CONT "This message can be disabled with the \"no_removal_warning\" kernel parameter.\n"); + schedule_timeout_uninterruptible(300 * HZ); + return 0; +} +early_initcall(removal_warning); +#endif diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index c3ff70a7b24..42b49f9e19b 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -48,54 +48,6 @@ typedef struct struct ucontext uc; } rt_sigframe; -/* - * Atomically swap in the new signal mask, and wait for a signal. - */ -SYSCALL_DEFINE3(sigsuspend, int, history0, int, history1, old_sigset_t, mask) -{ - sigset_t blocked; - siginitset(&blocked, mask); - return sigsuspend(&blocked); -} - -SYSCALL_DEFINE3(sigaction, int, sig, const struct old_sigaction __user *, act, - struct old_sigaction __user *, oact) -{ - struct k_sigaction new_ka, old_ka; - int ret; - - if (act) { - old_sigset_t mask; - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || - __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags) || - __get_user(mask, &act->sa_mask)) - return -EFAULT; - siginitset(&new_ka.sa.sa_mask, mask); - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || - __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) - return -EFAULT; - } - - return ret; -} - -SYSCALL_DEFINE2(sigaltstack, const stack_t __user *, uss, - stack_t __user *, uoss) -{ - struct pt_regs *regs = task_pt_regs(current); - return do_sigaltstack(uss, uoss, regs->gprs[15]); -} - /* Returns non-zero on fault. */ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) { @@ -105,40 +57,48 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) /* Copy a 'clean' PSW mask to the user to avoid leaking information about whether PER is currently on. */ - user_sregs.regs.psw.mask = psw_user_bits | - (regs->psw.mask & PSW_MASK_USER); + user_sregs.regs.psw.mask = PSW_USER_BITS | + (regs->psw.mask & (PSW_MASK_USER | PSW_MASK_RI)); user_sregs.regs.psw.addr = regs->psw.addr; memcpy(&user_sregs.regs.gprs, ®s->gprs, sizeof(sregs->regs.gprs)); memcpy(&user_sregs.regs.acrs, current->thread.acrs, - sizeof(sregs->regs.acrs)); + sizeof(user_sregs.regs.acrs)); /* * We have to store the fp registers to current->thread.fp_regs * to merge them with the emulated registers. */ - save_fp_regs(¤t->thread.fp_regs); + save_fp_ctl(¤t->thread.fp_regs.fpc); + save_fp_regs(current->thread.fp_regs.fprs); memcpy(&user_sregs.fpregs, ¤t->thread.fp_regs, - sizeof(s390_fp_regs)); - return __copy_to_user(sregs, &user_sregs, sizeof(_sigregs)); + sizeof(user_sregs.fpregs)); + if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs))) + return -EFAULT; + return 0; } -/* Returns positive number on error */ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) { - int err; _sigregs user_sregs; /* Alwys make any pending restarted system call return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; - err = __copy_from_user(&user_sregs, sregs, sizeof(_sigregs)); - if (err) - return err; - /* Use regs->psw.mask instead of psw_user_bits to preserve PER bit. */ - regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | - (user_sregs.regs.psw.mask & PSW_MASK_USER); + if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs))) + return -EFAULT; + + if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI)) + return -EINVAL; + + /* Loading the floating-point-control word can fail. Do that first. */ + if (restore_fp_ctl(&user_sregs.fpregs.fpc)) + return -EINVAL; + + /* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) | + (user_sregs.regs.psw.mask & (PSW_MASK_USER | PSW_MASK_RI)); /* Check for invalid user address space control. */ - if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC)) - regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) | + if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME) + regs->psw.mask = PSW_ASC_PRIMARY | (regs->psw.mask & ~PSW_MASK_ASC); /* Check for invalid amode */ if (regs->psw.mask & PSW_MASK_EA) @@ -146,15 +106,14 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) regs->psw.addr = user_sregs.regs.psw.addr; memcpy(®s->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs)); memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, - sizeof(sregs->regs.acrs)); + sizeof(current->thread.acrs)); restore_access_regs(current->thread.acrs); memcpy(¤t->thread.fp_regs, &user_sregs.fpregs, - sizeof(s390_fp_regs)); - current->thread.fp_regs.fpc &= FPC_VALID_MASK; + sizeof(current->thread.fp_regs)); - restore_fp_regs(¤t->thread.fp_regs); - clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ + restore_fp_regs(current->thread.fp_regs.fprs); + clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -164,8 +123,6 @@ SYSCALL_DEFINE0(sigreturn) sigframe __user *frame = (sigframe __user *)regs->gprs[15]; sigset_t set; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE)) goto badframe; set_current_blocked(&set); @@ -183,15 +140,12 @@ SYSCALL_DEFINE0(rt_sigreturn) rt_sigframe __user *frame = (rt_sigframe __user *)regs->gprs[15]; sigset_t set; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; set_current_blocked(&set); if (restore_sigregs(regs, &frame->uc.uc_mcontext)) goto badframe; - if (do_sigaltstack(&frame->uc.uc_stack, NULL, - regs->gprs[15]) == -EFAULT) + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; return regs->gprs[2]; badframe: @@ -244,8 +198,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigframe __user *frame; frame = get_sigframe(ka, regs, sizeof(sigframe)); - if (!access_ok(VERIFY_WRITE, frame, sizeof(sigframe))) - goto give_sigsegv; if (frame == (void __user *) -1UL) goto give_sigsegv; @@ -279,7 +231,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, regs->gprs[15] = (unsigned long) frame; /* Force default amode and default user address space control. */ regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; @@ -313,8 +265,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, rt_sigframe __user *frame; frame = get_sigframe(ka, regs, sizeof(rt_sigframe)); - if (!access_ok(VERIFY_WRITE, frame, sizeof(rt_sigframe))) - goto give_sigsegv; if (frame == (void __user *) -1UL) goto give_sigsegv; @@ -325,10 +275,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); err |= __put_user(NULL, &frame->uc.uc_link); - err |= __put_user((void __user *)current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->gprs[15]), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= __save_altstack(&frame->uc.uc_stack, regs->gprs[15]); err |= save_sigregs(regs, &frame->uc.uc_mcontext); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) @@ -355,7 +302,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[15] = (unsigned long) frame; /* Force default amode and default user address space control. */ regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | - (psw_user_bits & PSW_MASK_ASC) | + (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; @@ -409,7 +356,7 @@ void do_signal(struct pt_regs *regs) * call information. */ current_thread_info()->system_call = - test_thread_flag(TIF_SYSCALL) ? regs->int_code : 0; + test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0; signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { @@ -437,7 +384,7 @@ void do_signal(struct pt_regs *regs) } } /* No longer in a system call */ - clear_thread_flag(TIF_SYSCALL); + clear_pt_regs_flag(regs, PIF_SYSCALL); if (is_compat_task()) handle_signal32(signr, &ka, &info, oldset, regs); @@ -447,7 +394,7 @@ void do_signal(struct pt_regs *regs) } /* No handlers present - check for system call restart */ - clear_thread_flag(TIF_SYSCALL); + clear_pt_regs_flag(regs, PIF_SYSCALL); if (current_thread_info()->system_call) { regs->int_code = current_thread_info()->system_call; switch (regs->gprs[2]) { @@ -460,9 +407,9 @@ void do_signal(struct pt_regs *regs) case -ERESTARTNOINTR: /* Restart system call with magic TIF bit. */ regs->gprs[2] = regs->orig_gpr2; - set_thread_flag(TIF_SYSCALL); + set_pt_regs_flag(regs, PIF_SYSCALL); if (test_thread_flag(TIF_SINGLE_STEP)) - set_thread_flag(TIF_PER_TRAP); + clear_pt_regs_flag(regs, PIF_PER_TRAP); break; } } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 7433a2f9e5c..243c7e51260 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -49,7 +49,6 @@ enum { ec_schedule = 0, - ec_call_function, ec_call_function_single, ec_stop_cpu, }; @@ -60,7 +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 */ @@ -83,21 +82,6 @@ DEFINE_MUTEX(smp_cpu_state_mutex); /* * Signal processor helper functions. */ -static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status) -{ - register unsigned int reg1 asm ("1") = parm; - int cc; - - asm volatile( - " sigp %1,%2,0(%3)\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc"); - if (status && cc == 1) - *status = reg1; - return cc; -} - static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status) { int cc; @@ -160,13 +144,13 @@ 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); } -static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) +static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) { struct _lowcore *lc; @@ -181,9 +165,12 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc = pcpu->lowcore; memcpy(lc, &S390_lowcore, 512); memset((char *) lc + 512, 0, sizeof(*lc) - 512); - lc->async_stack = pcpu->async_stack + ASYNC_SIZE; - lc->panic_stack = pcpu->panic_stack + PAGE_SIZE; + lc->async_stack = pcpu->async_stack + ASYNC_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); + lc->panic_stack = pcpu->panic_stack + PAGE_SIZE + - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->cpu_nr = cpu; + lc->spinlock_lockval = arch_spin_lockval(cpu); #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { lc->extended_save_area_addr = get_zeroed_page(GFP_KERNEL); @@ -235,8 +222,12 @@ 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->spinlock_lockval = arch_spin_lockval(cpu); lc->percpu_offset = __per_cpu_offset[cpu]; lc->kernel_asce = S390_lowcore.kernel_asce; lc->machine_flags = S390_lowcore.machine_flags; @@ -253,7 +244,8 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) struct _lowcore *lc = pcpu->lowcore; struct thread_info *ti = task_thread_info(tsk); - lc->kernel_stack = (unsigned long) task_stack_page(tsk) + THREAD_SIZE; + lc->kernel_stack = (unsigned long) task_stack_page(tsk) + + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->thread_info = (unsigned long) task_thread_info(tsk); lc->current_task = (unsigned long) tsk; lc->user_timer = ti->user_timer; @@ -281,7 +273,7 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), struct _lowcore *lc = lowcore_ptr[pcpu - pcpu_devices]; unsigned long source_cpu = stap(); - __load_psw_mask(psw_kernel_bits); + __load_psw_mask(PSW_KERNEL_BITS); if (pcpu->address == source_cpu) func(data); /* should not return */ /* Stop target cpu (if func returns this stops the current cpu). */ @@ -360,21 +352,21 @@ void smp_yield_cpu(int cpu) * Send cpus emergency shutdown signal. This gives the cpus the * opportunity to complete outstanding interrupts. */ -void smp_emergency_stop(cpumask_t *cpumask) +static void smp_emergency_stop(cpumask_t *cpumask) { u64 end; int cpu; - end = get_clock() + (1000000UL << 12); + end = get_tod_clock() + (1000000UL << 12); for_each_cpu(cpu, cpumask) { struct pcpu *pcpu = pcpu_devices + cpu; set_bit(ec_stop_cpu, &pcpu->ec_mask); while (__pcpu_sigp(pcpu->address, SIGP_EMERGENCY_SIGNAL, 0, NULL) == SIGP_CC_BUSY && - get_clock() < end) + get_tod_clock() < end) cpu_relax(); } - while (get_clock() < end) { + while (get_tod_clock() < end) { for_each_cpu(cpu, cpumask) if (pcpu_stopped(pcpu_devices + cpu)) cpumask_clear_cpu(cpu, cpumask); @@ -393,7 +385,7 @@ void smp_send_stop(void) int cpu; /* Disable all interrupts/machine checks */ - __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); trace_hardirqs_off(); debug_set_critical(); @@ -413,46 +405,28 @@ void smp_send_stop(void) } /* - * Stop the current cpu. - */ -void smp_stop_cpu(void) -{ - pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); - for (;;) ; -} - -/* * This is the main routine where commands issued by other * cpus are handled. */ -static void do_ext_call_interrupt(struct ext_code ext_code, - unsigned int param32, unsigned long param64) +static void smp_handle_ext_call(void) { unsigned long bits; - int cpu; - - cpu = smp_processor_id(); - if (ext_code.code == 0x1202) - inc_irq_stat(IRQEXT_EXC); - else - inc_irq_stat(IRQEXT_EMS); - /* - * handle bit signal external calls - */ - bits = xchg(&pcpu_devices[cpu].ec_mask, 0); + /* handle bit signal external calls */ + bits = xchg(&pcpu_devices[smp_processor_id()].ec_mask, 0); if (test_bit(ec_stop_cpu, &bits)) smp_stop_cpu(); - if (test_bit(ec_schedule, &bits)) scheduler_ipi(); - - if (test_bit(ec_call_function, &bits)) - generic_smp_call_function_interrupt(); - if (test_bit(ec_call_function_single, &bits)) generic_smp_call_function_single_interrupt(); +} +static void do_ext_call_interrupt(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + inc_irq_stat(ext_code.code == 0x1202 ? IRQEXT_EXC : IRQEXT_EMS); + smp_handle_ext_call(); } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -460,7 +434,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) int cpu; for_each_cpu(cpu, mask) - pcpu_ec_call(pcpu_devices + cpu, ec_call_function); + pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single); } void arch_send_call_function_single_ipi(int cpu) @@ -538,10 +512,7 @@ void smp_ctl_clear_bit(int cr, int bit) } EXPORT_SYMBOL(smp_ctl_clear_bit); -#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_CRASH_DUMP) - -struct save_area *zfcpdump_save_areas[NR_CPUS + 1]; -EXPORT_SYMBOL_GPL(zfcpdump_save_areas); +#ifdef CONFIG_CRASH_DUMP static void __init smp_get_save_area(int cpu, u16 address) { @@ -553,23 +524,15 @@ static void __init smp_get_save_area(int cpu, u16 address) if (!OLDMEM_BASE && (address == boot_cpu_address || ipl_info.type != IPL_TYPE_FCP_DUMP)) return; - if (cpu >= NR_CPUS) { - pr_warning("CPU %i exceeds the maximum %i and is excluded " - "from the dump\n", cpu, NR_CPUS - 1); - return; - } - save_area = kmalloc(sizeof(struct save_area), GFP_KERNEL); + save_area = dump_save_area_create(cpu); if (!save_area) panic("could not allocate memory for save area\n"); - zfcpdump_save_areas[cpu] = save_area; -#ifdef CONFIG_CRASH_DUMP if (address == boot_cpu_address) { /* Copy the registers of the boot cpu. */ copy_oldmem_page(1, (void *) save_area, sizeof(*save_area), SAVE_AREA_BASE - PAGE_SIZE, 0); return; } -#endif /* Get the registers of a non-boot cpu. */ __pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL); memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area)); @@ -586,11 +549,11 @@ int smp_store_status(int cpu) return 0; } -#else /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ +#else /* CONFIG_CRASH_DUMP */ static inline void smp_get_save_area(int cpu, u16 address) { } -#endif /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ +#endif /* CONFIG_CRASH_DUMP */ void smp_cpu_set_polarization(int cpu, int val) { @@ -623,10 +586,9 @@ static struct sclp_cpu_info *smp_get_cpu_info(void) return info; } -static int __cpuinit smp_add_present_cpu(int cpu); +static int smp_add_present_cpu(int cpu); -static int __cpuinit __smp_rescan_cpus(struct sclp_cpu_info *info, - int sysfs_add) +static int __smp_rescan_cpus(struct sclp_cpu_info *info, int sysfs_add) { struct pcpu *pcpu; cpumask_t avail; @@ -642,7 +604,7 @@ static int __cpuinit __smp_rescan_cpus(struct sclp_cpu_info *info, continue; pcpu = pcpu_devices + cpu; pcpu->address = info->cpu[i].address; - pcpu->state = (cpu >= info->configured) ? + pcpu->state = (i >= info->configured) ? CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); set_cpu_present(cpu, true); @@ -692,16 +654,16 @@ static void __init smp_detect_cpus(void) /* * Activate a secondary processor. */ -static void __cpuinit smp_start_secondary(void *cpuvoid) +static void smp_start_secondary(void *cpuvoid) { - S390_lowcore.last_update_clock = get_clock(); + S390_lowcore.last_update_clock = get_tod_clock(); S390_lowcore.restart_stack = (unsigned long) restart_stack; S390_lowcore.restart_fn = (unsigned long) do_restart; S390_lowcore.restart_data = 0; S390_lowcore.restart_source = -1UL; restore_access_regs(S390_lowcore.access_regs_save_area); __ctl_load(S390_lowcore.cregs_save_area, 0, 15); - __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); cpu_init(); preempt_disable(); init_cpu_timer(); @@ -711,12 +673,11 @@ static void __cpuinit smp_start_secondary(void *cpuvoid) set_cpu_online(smp_processor_id(), true); inc_irq_stat(CPU_RST); local_irq_enable(); - /* cpu_idle will call schedule for us */ - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } /* Upping and downing of CPUs */ -int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) +int __cpu_up(unsigned int cpu, struct task_struct *tidle) { struct pcpu *pcpu; int rc; @@ -739,18 +700,14 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) return 0; } -static int __init setup_possible_cpus(char *s) -{ - int max, cpu; +static unsigned int setup_possible_cpus __initdata; - if (kstrtoint(s, 0, &max) < 0) - return 0; - init_cpu_possible(cpumask_of(0)); - for (cpu = 1; cpu < max && cpu < nr_cpu_ids; cpu++) - set_cpu_possible(cpu, true); +static int __init _setup_possible_cpus(char *s) +{ + get_option(&s, &setup_possible_cpus); return 0; } -early_param("possible_cpus", setup_possible_cpus); +early_param("possible_cpus", _setup_possible_cpus); #ifdef CONFIG_HOTPLUG_CPU @@ -758,6 +715,8 @@ int __cpu_disable(void) { unsigned long cregs[16]; + /* Handle possible pending IPIs */ + smp_handle_ext_call(); set_cpu_online(smp_processor_id(), false); /* Disable pseudo page faults on this cpu. */ pfault_fini(); @@ -780,6 +739,9 @@ 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) @@ -791,13 +753,24 @@ void __noreturn cpu_die(void) #endif /* CONFIG_HOTPLUG_CPU */ +void __init smp_fill_possible_mask(void) +{ + unsigned int possible, sclp, cpu; + + 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); +} + 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(); } @@ -810,8 +783,10 @@ void __init smp_prepare_boot_cpu(void) pcpu->state = CPU_STATE_CONFIGURED; pcpu->address = boot_cpu_address; pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix(); - pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE; - pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE; + pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE + + STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); S390_lowcore.percpu_offset = __per_cpu_offset[0]; smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); set_cpu_present(0, true); @@ -825,6 +800,7 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_setup_processor_id(void) { S390_lowcore.cpu_nr = 0; + S390_lowcore.spinlock_lockval = arch_spin_lockval(0); } /* @@ -934,7 +910,7 @@ static ssize_t show_idle_count(struct device *dev, idle_count = ACCESS_ONCE(idle->idle_count); if (ACCESS_ONCE(idle->clock_idle_enter)) idle_count++; - } while ((sequence & 1) || (idle->sequence != sequence)); + } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); return sprintf(buf, "%llu\n", idle_count); } static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); @@ -947,12 +923,12 @@ static ssize_t show_idle_time(struct device *dev, unsigned int sequence; do { - now = get_clock(); + now = get_tod_clock(); sequence = ACCESS_ONCE(idle->sequence); idle_time = ACCESS_ONCE(idle->idle_time); idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (idle->sequence != sequence)); + } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; return sprintf(buf, "%llu\n", idle_time >> 12); } @@ -968,11 +944,11 @@ static struct attribute_group cpu_online_attr_group = { .attrs = cpu_online_attrs, }; -static int __cpuinit smp_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +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; @@ -987,12 +963,17 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self, return notifier_from_errno(err); } -static int __cpuinit smp_add_present_cpu(int cpu) +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) @@ -1059,19 +1040,24 @@ 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/suspend.c b/arch/s390/kernel/suspend.c index aa1494d0e38..a7a7537ce1e 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -10,6 +10,10 @@ #include <linux/suspend.h> #include <linux/mm.h> #include <asm/ctl_reg.h> +#include <asm/ipl.h> +#include <asm/cio.h> +#include <asm/pci.h> +#include "entry.h" /* * References to section boundaries @@ -41,6 +45,7 @@ struct page_key_data { static struct page_key_data *page_key_data; static struct page_key_data *page_key_rp, *page_key_wp; static unsigned long page_key_rx, page_key_wx; +unsigned long suspend_zero_pages; /* * For each page in the hibernation image one additional byte is @@ -149,6 +154,36 @@ int pfn_is_nosave(unsigned long pfn) return 0; } +/* + * PM notifier callback for suspend + */ +static int suspend_pm_cb(struct notifier_block *nb, unsigned long action, + void *ptr) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + suspend_zero_pages = __get_free_pages(GFP_KERNEL, LC_ORDER); + if (!suspend_zero_pages) + return NOTIFY_BAD; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + free_pages(suspend_zero_pages, LC_ORDER); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int __init suspend_pm_init(void) +{ + pm_notifier(suspend_pm_cb, 0); + return 0; +} +arch_initcall(suspend_pm_init); + void save_processor_state(void) { /* swsusp_arch_suspend() actually saves all cpu register contents. @@ -180,3 +215,11 @@ void restore_processor_state(void) __ctl_set_bit(0,28); local_mcck_enable(); } + +/* Called at the end of swsusp_arch_resume */ +void s390_early_resume(void) +{ + lgr_info_log(); + channel_subsystem_reinit(); + zpci_rescan(); +} diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index d4ca4e0617b..6b09fdffbd2 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -36,8 +36,8 @@ ENTRY(swsusp_arch_suspend) /* Store prefix register on stack */ stpx __SF_EMPTY(%r15) - /* Save prefix register contents for lowcore */ - llgf %r4,__SF_EMPTY(%r15) + /* Save prefix register contents for lowcore copy */ + llgf %r10,__SF_EMPTY(%r15) /* Get pointer to save area */ lghi %r1,0x1000 @@ -91,7 +91,18 @@ ENTRY(swsusp_arch_suspend) xc __SF_EMPTY(4,%r15),__SF_EMPTY(%r15) spx __SF_EMPTY(%r15) + /* Save absolute zero pages */ + larl %r2,suspend_zero_pages + lg %r2,0(%r2) + lghi %r4,0 + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + + /* Copy lowcore to absolute zero lowcore */ lghi %r2,0 + lgr %r4,%r10 lghi %r3,2*PAGE_SIZE lghi %r5,2*PAGE_SIZE 1: mvcle %r2,%r4,0 @@ -248,8 +259,20 @@ restore_registers: /* Load old stack */ lg %r15,0x2f8(%r13) + /* Save prefix register */ + mvc __SF_EMPTY(4,%r15),0x318(%r13) + + /* Restore absolute zero pages */ + lghi %r2,0 + larl %r4,suspend_zero_pages + lg %r4,0(%r4) + lghi %r3,2*PAGE_SIZE + lghi %r5,2*PAGE_SIZE +1: mvcle %r2,%r4,0 + jo 1b + /* Restore prefix register */ - spx 0x318(%r13) + spx __SF_EMPTY(%r15) /* Activate DAT */ stosm __SF_EMPTY(%r15),0x04 @@ -258,11 +281,8 @@ restore_registers: lghi %r2,0 brasl %r14,arch_set_page_states - /* Log potential guest relocation */ - brasl %r14,lgr_info_log - - /* Reinitialize the channel subsystem */ - brasl %r14,channel_subsystem_reinit + /* Call arch specific early resume code */ + brasl %r14,s390_early_resume /* Return 0 */ lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index d0964d22adb..23eb222c165 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -132,19 +132,9 @@ SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args) * to * %r2: fd, %r3: mode, %r4/%r5: offset, 96(%r15)-103(%r15): len */ -SYSCALL_DEFINE(s390_fallocate)(int fd, int mode, loff_t offset, - u32 len_high, u32 len_low) +SYSCALL_DEFINE5(s390_fallocate, int, fd, int, mode, loff_t, offset, + u32, len_high, u32, len_low) { return sys_fallocate(fd, mode, offset, ((u64)len_high << 32) | len_low); } -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS -asmlinkage long SyS_s390_fallocate(long fd, long mode, loff_t offset, - long len_high, long len_low) -{ - return SYSC_s390_fallocate((int) fd, (int) mode, offset, - (u32) len_high, (u32) len_low); -} -SYSCALL_ALIAS(sys_s390_fallocate, SyS_s390_fallocate); -#endif - #endif diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 6a6c61f94dd..fe5cdf29a00 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -9,347 +9,350 @@ #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_open,sys_open,sys32_open_wrapper) /* 5 */ -SYSCALL(sys_close,sys_close,sys32_close_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,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,sys32_lseek_wrapper) +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,sys32_sigaction_wrapper) +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_getrusage,sys_getrusage,compat_sys_getrusage_wrapper) -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_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) +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_truncate,sys_truncate,sys32_truncate_wrapper) -SYSCALL(sys_ftruncate,sys_ftruncate,sys32_ftruncate_wrapper) -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_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,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_setitimer,sys_setitimer,compat_sys_setitimer_wrapper) -SYSCALL(sys_getitimer,sys_getitimer,compat_sys_getitimer_wrapper) /* 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_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) +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,sys32_lookup_dcookie_wrapper) /* 110 */ +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_wrapper) -SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper) /* 115 */ -SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) -SYSCALL(sys_s390_ipc,sys_s390_ipc,sys32_ipc_wrapper) -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_wait4,sys_wait4,compat_sys_wait4) +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,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_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask_wrapper) +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_sysctl,sys_sysctl,sys32_sysctl_wrapper) -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_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,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_rr_get_interval,sys_sched_rr_get_interval,sys32_sched_rr_get_interval_wrapper) -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_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) +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_rt_sigaction,sys_rt_sigaction,sys32_rt_sigaction_wrapper) -SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,sys32_rt_sigprocmask_wrapper) /* 175 */ -SYSCALL(sys_rt_sigpending,sys_rt_sigpending,sys32_rt_sigpending_wrapper) -SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait_wrapper) -SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,sys32_rt_sigqueueinfo_wrapper) -SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend_wrapper) -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_sigaltstack,sys_sigaltstack,sys32_sigaltstack_wrapper) -SYSCALL(sys_sendfile,sys_sendfile64,sys32_sendfile_wrapper) +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,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_sendfile64,sys_ni_syscall,sys32_sendfile64_wrapper) -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_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,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_futex,sys_futex,compat_sys_futex_wrapper) -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_tkill,sys_tkill,compat_sys_tkill) +SYSCALL(sys_futex,sys_futex,compat_sys_futex) +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_waitid,sys_waitid,compat_sys_waitid_wrapper) -SYSCALL(sys_ioprio_set,sys_ioprio_set,sys_ioprio_set_wrapper) -SYSCALL(sys_ioprio_get,sys_ioprio_get,sys_ioprio_get_wrapper) +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,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_wrapper) -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_set_robust_list,sys_set_robust_list,compat_sys_set_robust_list_wrapper) -SYSCALL(sys_get_robust_list,sys_get_robust_list,compat_sys_get_robust_list_wrapper) -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_vmsplice,sys_vmsplice,compat_sys_vmsplice_wrapper) +SYSCALL(sys_openat,sys_openat,compat_sys_openat) +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,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_epoll_pwait,sys_epoll_pwait,compat_sys_epoll_pwait_wrapper) -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_signalfd,sys_signalfd,compat_sys_signalfd_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) +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_timerfd_settime,sys_timerfd_settime,compat_sys_timerfd_settime_wrapper) /* 320 */ -SYSCALL(sys_timerfd_gettime,sys_timerfd_gettime,compat_sys_timerfd_gettime_wrapper) -SYSCALL(sys_signalfd4,sys_signalfd4,compat_sys_signalfd4_wrapper) -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_preadv,sys_preadv,compat_sys_preadv_wrapper) -SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev_wrapper) -SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo_wrapper) /* 330 */ -SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper) -SYSCALL(sys_fanotify_init,sys_fanotify_init,sys_fanotify_init_wrapper) -SYSCALL(sys_fanotify_mark,sys_fanotify_mark,sys_fanotify_mark_wrapper) -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_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at_wrapper) -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_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,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,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,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) +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) +SYSCALL(sys_renameat2,sys_renameat2,compat_sys_renameat2) diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 62f89d98e88..811f542b8ed 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -418,7 +418,7 @@ void s390_adjust_jiffies(void) /* * calibrate the delay loop */ -void __cpuinit calibrate_delay(void) +void calibrate_delay(void) { s390_adjust_jiffies(); /* Print the good old Bogomips line .. */ diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index a5f4f5a1d24..0931b110c82 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators); */ unsigned long long notrace __kprobes sched_clock(void) { - return tod_to_ns(get_clock_monotonic()); + return tod_to_ns(get_tod_clock_monotonic()); } /* @@ -92,7 +92,6 @@ void clock_comparator_work(void) struct clock_event_device *cd; S390_lowcore.clock_comparator = -1ULL; - set_clock_comparator(S390_lowcore.clock_comparator); cd = &__get_cpu_var(comparators); cd->event_handler(cd); } @@ -109,17 +108,10 @@ static void fixup_clock_comparator(unsigned long long delta) set_clock_comparator(S390_lowcore.clock_comparator); } -static int s390_next_ktime(ktime_t expires, +static int s390_next_event(unsigned long delta, struct clock_event_device *evt) { - struct timespec ts; - u64 nsecs; - - ts.tv_sec = ts.tv_nsec = 0; - monotonic_to_bootbased(&ts); - nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires)); - do_div(nsecs, 125); - S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9); + S390_lowcore.clock_comparator = get_tod_clock() + delta; set_clock_comparator(S390_lowcore.clock_comparator); return 0; } @@ -144,15 +136,14 @@ void init_cpu_timer(void) cpu = smp_processor_id(); cd = &per_cpu(comparators, cpu); cd->name = "comparator"; - cd->features = CLOCK_EVT_FEAT_ONESHOT | - CLOCK_EVT_FEAT_KTIME; + cd->features = CLOCK_EVT_FEAT_ONESHOT; cd->mult = 16777; cd->shift = 12; cd->min_delta_ns = 1; cd->max_delta_ns = LONG_MAX; cd->rating = 400; cd->cpumask = cpumask_of(cpu); - cd->set_next_ktime = s390_next_ktime; + cd->set_next_event = s390_next_event; cd->set_mode = s390_set_mode; clockevents_register_device(cd); @@ -191,7 +182,7 @@ static void stp_reset(void); void read_persistent_clock(struct timespec *ts) { - tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); + tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts); } void read_boot_clock(struct timespec *ts) @@ -201,7 +192,7 @@ void read_boot_clock(struct timespec *ts) static cycle_t read_tod_clock(struct clocksource *cs) { - return get_clock(); + return get_tod_clock(); } static struct clocksource clocksource_tod = { @@ -219,21 +210,30 @@ struct clocksource * __init clocksource_default_clock(void) return &clocksource_tod; } -void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) +void update_vsyscall(struct timekeeper *tk) { - if (clock != &clocksource_tod) + u64 nsecps; + + if (tk->clock != &clocksource_tod) return; /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = clock->cycle_last; - vdso_data->xtime_clock_sec = wall_time->tv_sec; - vdso_data->xtime_clock_nsec = wall_time->tv_nsec; - vdso_data->wtom_clock_sec = wtm->tv_sec; - vdso_data->wtom_clock_nsec = wtm->tv_nsec; - vdso_data->ntp_mult = mult; + vdso_data->xtime_tod_stamp = tk->clock->cycle_last; + vdso_data->xtime_clock_sec = tk->xtime_sec; + vdso_data->xtime_clock_nsec = tk->xtime_nsec; + vdso_data->wtom_clock_sec = + tk->xtime_sec + tk->wall_to_monotonic.tv_sec; + vdso_data->wtom_clock_nsec = tk->xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift); + nsecps = (u64) NSEC_PER_SEC << tk->shift; + while (vdso_data->wtom_clock_nsec >= nsecps) { + vdso_data->wtom_clock_nsec -= nsecps; + vdso_data->wtom_clock_sec++; + } + vdso_data->tk_mult = tk->mult; + vdso_data->tk_shift = tk->shift; smp_wmb(); ++vdso_data->tb_update_count; } @@ -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) @@ -339,7 +339,7 @@ int get_sync_clock(unsigned long long *clock) sw_ptr = &get_cpu_var(clock_sync_word); sw0 = atomic_read(sw_ptr); - *clock = get_clock(); + *clock = get_tod_clock(); sw1 = atomic_read(sw_ptr); put_cpu_var(clock_sync_word); if (sw0 == sw1 && (sw0 & 0x80000000U)) @@ -483,7 +483,7 @@ static void etr_reset(void) .p0 = 0, .p1 = 0, ._pad1 = 0, .ea = 0, .es = 0, .sl = 0 }; if (etr_setr(&etr_eacr) == 0) { - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags); if (etr_port0_online && etr_port1_online) set_bit(CLOCK_SYNC_ETR, &clock_sync_flags); @@ -765,8 +765,8 @@ static int etr_sync_clock(void *data) __ctl_set_bit(14, 21); __ctl_set_bit(0, 29); clock = ((unsigned long long) (aib->edf2.etv + 1)) << 32; - old_clock = get_clock(); - if (set_clock(clock) == 0) { + old_clock = get_tod_clock(); + if (set_tod_clock(clock) == 0) { __udelay(1); /* Wait for the clock to start. */ __ctl_clear_bit(0, 29); __ctl_clear_bit(14, 21); @@ -842,7 +842,7 @@ static struct etr_eacr etr_handle_events(struct etr_eacr eacr) * assume that this can have caused an stepping * port switch. */ - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); eacr.p0 = etr_port0_online; if (!eacr.p0) eacr.e0 = 0; @@ -855,7 +855,7 @@ static struct etr_eacr etr_handle_events(struct etr_eacr eacr) * assume that this can have caused an stepping * port switch. */ - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); eacr.p1 = etr_port1_online; if (!eacr.p1) eacr.e1 = 0; @@ -971,7 +971,7 @@ static void etr_update_eacr(struct etr_eacr eacr) etr_eacr = eacr; etr_setr(&etr_eacr); if (dp_changed) - etr_tolec = get_clock(); + etr_tolec = get_tod_clock(); } /* @@ -1009,7 +1009,7 @@ static void etr_work_fn(struct work_struct *work) /* Store aib to get the current ETR status word. */ BUG_ON(etr_stetr(&aib) != 0); etr_port0.esw = etr_port1.esw = aib.esw; /* Copy status word. */ - now = get_clock(); + now = get_tod_clock(); /* * Update the port information if the last stepping port change @@ -1534,10 +1534,10 @@ static int stp_sync_clock(void *data) if (stp_info.todoff[0] || stp_info.todoff[1] || stp_info.todoff[2] || stp_info.todoff[3] || stp_info.tmd != 2) { - old_clock = get_clock(); + old_clock = get_tod_clock(); rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0); if (rc == 0) { - delta = adjust_time(old_clock, get_clock(), 0); + delta = adjust_time(old_clock, get_tod_clock(), 0); fixup_clock_comparator(delta); rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4b2e3e31700..355a16c5570 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -333,7 +333,9 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info, nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i]; nr_masks = max(nr_masks, 1); for (i = 0; i < nr_masks; i++) { - mask->next = alloc_bootmem(sizeof(struct mask_info)); + mask->next = alloc_bootmem_align( + roundup_pow_of_two(sizeof(struct mask_info)), + roundup_pow_of_two(sizeof(struct mask_info))); mask = mask->next; } } @@ -443,6 +445,23 @@ int topology_cpu_init(struct cpu *cpu) return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group); } +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_mask; +} + +static const struct cpumask *cpu_book_mask(int cpu) +{ + return &cpu_topology[cpu].book_mask; +} + +static struct sched_domain_topology_level s390_topology[] = { + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_book_mask, SD_INIT_NAME(BOOK) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static int __init topology_init(void) { if (!MACHINE_HAS_TOPOLOGY) { @@ -451,7 +470,9 @@ static int __init topology_init(void) } set_topology_timer(); out: - update_cpu_masks(); + + set_sched_topology(s390_topology); + return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 70ecfc5fe8f..c5762324d9e 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -12,49 +12,16 @@ * 'Traps.c' handles hardware traps and faults after we have saved some * state in 'asm.s'. */ -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> +#include <linux/module.h> #include <linux/ptrace.h> -#include <linux/timer.h> +#include <linux/sched.h> #include <linux/mm.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/seq_file.h> -#include <linux/delay.h> -#include <linux/module.h> -#include <linux/kdebug.h> -#include <linux/kallsyms.h> -#include <linux/reboot.h> -#include <linux/kprobes.h> -#include <linux/bug.h> -#include <linux/utsname.h> -#include <asm/uaccess.h> -#include <asm/io.h> -#include <linux/atomic.h> -#include <asm/mathemu.h> -#include <asm/cpcmd.h> -#include <asm/lowcore.h> -#include <asm/debug.h> -#include <asm/ipl.h> #include "entry.h" int show_unhandled_signals = 1; -#define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; }) - -#ifndef CONFIG_64BIT -#define LONG "%08lx " -#define FOURLONG "%08lx %08lx %08lx %08lx\n" -static int kstack_depth_to_print = 12; -#else /* CONFIG_64BIT */ -#define LONG "%016lx " -#define FOURLONG "%016lx %016lx %016lx %016lx\n" -static int kstack_depth_to_print = 20; -#endif /* CONFIG_64BIT */ - static inline void __user *get_trap_ip(struct pt_regs *regs) { #ifdef CONFIG_64BIT @@ -72,215 +39,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) #endif } -/* - * For show_trace we have tree different stack to consider: - * - the panic stack which is used if the kernel stack has overflown - * - the asynchronous interrupt stack (cpu related) - * - the synchronous kernel stack (process related) - * The stack trace can start at any of the three stack and can potentially - * touch all of them. The order is: panic stack, async stack, sync stack. - */ -static unsigned long -__show_trace(unsigned long sp, unsigned long low, unsigned long high) -{ - struct stack_frame *sf; - struct pt_regs *regs; - - while (1) { - sp = sp & PSW_ADDR_INSN; - if (sp < low || sp > high - sizeof(*sf)) - return sp; - sf = (struct stack_frame *) sp; - printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN); - /* Follow the backchain. */ - while (1) { - low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; - if (!sp) - break; - if (sp <= low || sp > high - sizeof(*sf)) - return sp; - sf = (struct stack_frame *) sp; - printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN); - print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN); - } - /* Zero backchain detected, check for interrupt frame. */ - sp = (unsigned long) (sf + 1); - if (sp <= low || sp > high - sizeof(*regs)) - return sp; - regs = (struct pt_regs *) sp; - printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN); - print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN); - low = sp; - sp = regs->gprs[15]; - } -} - -static void show_trace(struct task_struct *task, unsigned long *stack) -{ - register unsigned long __r15 asm ("15"); - unsigned long sp; - - sp = (unsigned long) stack; - if (!sp) - sp = task ? task->thread.ksp : __r15; - printk("Call Trace:\n"); -#ifdef CONFIG_CHECK_STACK - sp = __show_trace(sp, S390_lowcore.panic_stack - 4096, - S390_lowcore.panic_stack); -#endif - sp = __show_trace(sp, S390_lowcore.async_stack - ASYNC_SIZE, - S390_lowcore.async_stack); - if (task) - __show_trace(sp, (unsigned long) task_stack_page(task), - (unsigned long) task_stack_page(task) + THREAD_SIZE); - else - __show_trace(sp, S390_lowcore.thread_info, - S390_lowcore.thread_info + THREAD_SIZE); - if (!task) - task = current; - debug_show_held_locks(task); -} - -void show_stack(struct task_struct *task, unsigned long *sp) -{ - register unsigned long * __r15 asm ("15"); - unsigned long *stack; - int i; - - if (!sp) - stack = task ? (unsigned long *) task->thread.ksp : __r15; - else - stack = sp; - - for (i = 0; i < kstack_depth_to_print; i++) { - if (((addr_t) stack & (THREAD_SIZE-1)) == 0) - break; - if ((i * sizeof(long) % 32) == 0) - printk("%s ", i == 0 ? "" : "\n"); - printk(LONG, *stack++); - } - printk("\n"); - show_trace(task, sp); -} - -static void show_last_breaking_event(struct pt_regs *regs) -{ -#ifdef CONFIG_64BIT - printk("Last Breaking-Event-Address:\n"); - printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); - print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); -#endif -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - -static inline int mask_bits(struct pt_regs *regs, unsigned long bits) -{ - return (regs->psw.mask & bits) / ((~bits + 1) & bits); -} - -void show_registers(struct pt_regs *regs) -{ - char *mode; - - mode = user_mode(regs) ? "User" : "Krnl"; - printk("%s PSW : %p %p", - mode, (void *) regs->psw.mask, - (void *) regs->psw.addr); - print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN); - printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " - "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER), - mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO), - mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY), - mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT), - mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), - mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); -#ifdef CONFIG_64BIT - printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); -#endif - printk("\n%s GPRS: " FOURLONG, mode, - regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); - printk(" " FOURLONG, - regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); - printk(" " FOURLONG, - regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]); - printk(" " FOURLONG, - regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]); - - show_code(regs); -} - -void show_regs(struct pt_regs *regs) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_registers(regs); - /* Show stack backtrace if pt_regs is from kernel mode */ - if (!user_mode(regs)) - show_trace(NULL, (unsigned long *) regs->gprs[15]); - show_last_breaking_event(regs); -} - -static DEFINE_SPINLOCK(die_lock); - -void die(struct pt_regs *regs, const char *str) -{ - static int die_counter; - - oops_enter(); - lgr_info_log(); - debug_stop_all(); - console_verbose(); - spin_lock_irq(&die_lock); - bust_spinlocks(1); - printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); -#endif - printk("\n"); - notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); - print_modules(); - show_regs(regs); - bust_spinlocks(0); - add_taint(TAINT_DIE); - spin_unlock_irq(&die_lock); - if (in_interrupt()) - panic("Fatal exception in interrupt"); - if (panic_on_oops) - panic("Fatal exception: panic_on_oops"); - oops_exit(); - do_exit(SIGSEGV); -} - static inline void report_user_fault(struct pt_regs *regs, int signr) { if ((task_pid_nr(current) > 1) && !show_unhandled_signals) diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index d7776281cb6..61364909678 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -63,7 +63,7 @@ static int __init vdso_setup(char *s) else if (strncmp(s, "off", 4) == 0) vdso_enabled = 0; else { - rc = strict_strtoul(s, 0, &val); + rc = kstrtoul(s, 0, &val); vdso_enabled = rc ? 0 : !!val; } return !rc; @@ -84,8 +84,7 @@ struct vdso_data *vdso_data = &vdso_data_store.data; */ static void vdso_init_data(struct vdso_data *vd) { - vd->ectg_available = - s390_user_mode != HOME_SPACE_MODE && test_facility(31); + vd->ectg_available = test_facility(31); } #ifdef CONFIG_64BIT @@ -102,7 +101,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) lowcore->vdso_per_cpu_data = __LC_PASTE; - if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (!vdso_enabled) return 0; segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); @@ -113,11 +112,11 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE << SEGMENT_ORDER); - clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) page_table, _PAGE_INVALID, 256*sizeof(unsigned long)); *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table; - *(unsigned long *) page_table = _PAGE_RO + page_frame; + *(unsigned long *) page_table = _PAGE_PROTECT + page_frame; psal = (u32 *) (page_table + 256*sizeof(unsigned long)); aste = psal + 32; @@ -126,7 +125,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) psal[i] = 0x80000000; lowcore->paste[4] = (u32)(addr_t) psal; - psal[0] = 0x20000000; + psal[0] = 0x02000000; psal[2] = (u32)(addr_t) aste; *(unsigned long *) (aste + 2) = segment_table + _ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT; @@ -147,7 +146,7 @@ void vdso_free_per_cpu(struct _lowcore *lowcore) unsigned long segment_table, page_table, page_frame; u32 *psal, *aste; - if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (!vdso_enabled) return; psal = (u32 *)(addr_t) lowcore->paste[4]; @@ -165,7 +164,7 @@ static void vdso_init_cr5(void) { unsigned long cr5; - if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) + if (!vdso_enabled) return; cr5 = offsetof(struct _lowcore, paste); __ctl_load(cr5, 5, 5); diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S index b2224e0b974..65fc3979c2f 100644 --- a/arch/s390/kernel/vdso32/clock_gettime.S +++ b/arch/s390/kernel/vdso32/clock_gettime.S @@ -38,25 +38,21 @@ __kernel_clock_gettime: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,2f ahi %r0,-1 -2: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ +2: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ lr %r2,%r0 - l %r0,__VDSO_NTP_MULT(%r5) + l %r0,__VDSO_TK_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 3f - a %r0,__VDSO_NTP_MULT(%r5) + a %r0,__VDSO_TK_MULT(%r5) 3: alr %r0,%r2 - srdl %r0,12 - al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ - al %r1,__VDSO_XTIME_NSEC+4(%r5) - brc 12,4f - ahi %r0,1 -4: l %r2,__VDSO_XTIME_SEC+4(%r5) - al %r0,__VDSO_WTOM_NSEC(%r5) /* + wall_to_monotonic */ + al %r0,__VDSO_WTOM_NSEC(%r5) al %r1,__VDSO_WTOM_NSEC+4(%r5) brc 12,5f ahi %r0,1 -5: al %r2,__VDSO_WTOM_SEC+4(%r5) +5: l %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srdl %r0,0(%r2) /* >> tk->shift */ + l %r2,__VDSO_WTOM_SEC+4(%r5) cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ jne 1b basr %r5,0 @@ -86,20 +82,21 @@ __kernel_clock_gettime: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,12f ahi %r0,-1 -12: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ +12: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ lr %r2,%r0 - l %r0,__VDSO_NTP_MULT(%r5) + l %r0,__VDSO_TK_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 13f - a %r0,__VDSO_NTP_MULT(%r5) + a %r0,__VDSO_TK_MULT(%r5) 13: alr %r0,%r2 - srdl %r0,12 - al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ + al %r0,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ al %r1,__VDSO_XTIME_NSEC+4(%r5) brc 12,14f ahi %r0,1 -14: l %r2,__VDSO_XTIME_SEC+4(%r5) +14: l %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srdl %r0,0(%r2) /* >> tk->shift */ + l %r2,__VDSO_XTIME_SEC+4(%r5) cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ jne 11b basr %r5,0 diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S index 2d3633175e3..fd621a950f7 100644 --- a/arch/s390/kernel/vdso32/gettimeofday.S +++ b/arch/s390/kernel/vdso32/gettimeofday.S @@ -35,15 +35,14 @@ __kernel_gettimeofday: sl %r1,__VDSO_XTIME_STAMP+4(%r5) brc 3,3f ahi %r0,-1 -3: ms %r0,__VDSO_NTP_MULT(%r5) /* cyc2ns(clock,cycle_delta) */ +3: ms %r0,__VDSO_TK_MULT(%r5) /* * tk->mult */ st %r0,24(%r15) - l %r0,__VDSO_NTP_MULT(%r5) + l %r0,__VDSO_TK_MULT(%r5) ltr %r1,%r1 mr %r0,%r0 jnm 4f - a %r0,__VDSO_NTP_MULT(%r5) + a %r0,__VDSO_TK_MULT(%r5) 4: al %r0,24(%r15) - srdl %r0,12 al %r0,__VDSO_XTIME_NSEC(%r5) /* + xtime */ al %r1,__VDSO_XTIME_NSEC+4(%r5) brc 12,5f @@ -51,6 +50,8 @@ __kernel_gettimeofday: 5: mvc 24(4,%r15),__VDSO_XTIME_SEC+4(%r5) cl %r4,__VDSO_UPD_COUNT+4(%r5) /* check update counter */ jne 1b + l %r4,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srdl %r0,0(%r4) /* >> tk->shift */ l %r4,24(%r15) /* get tv_sec from stack */ basr %r5,0 6: ltr %r0,%r0 diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S index 176e1f75f9a..34deba7c7ed 100644 --- a/arch/s390/kernel/vdso64/clock_getres.S +++ b/arch/s390/kernel/vdso64/clock_getres.S @@ -23,7 +23,9 @@ __kernel_clock_getres: je 0f cghi %r2,__CLOCK_MONOTONIC je 0f - cghi %r2,-2 /* CLOCK_THREAD_CPUTIME_ID for this thread */ + cghi %r2,__CLOCK_THREAD_CPUTIME_ID + je 0f + cghi %r2,-2 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ jne 2f larl %r5,_vdso_data icm %r0,15,__LC_ECTG_OK(%r5) diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S index d46c95ed5f1..91940ed33a4 100644 --- a/arch/s390/kernel/vdso64/clock_gettime.S +++ b/arch/s390/kernel/vdso64/clock_gettime.S @@ -22,7 +22,9 @@ __kernel_clock_gettime: larl %r5,_vdso_data cghi %r2,__CLOCK_REALTIME je 4f - cghi %r2,-2 /* CLOCK_THREAD_CPUTIME_ID for this thread */ + cghi %r2,__CLOCK_THREAD_CPUTIME_ID + je 9f + cghi %r2,-2 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ je 9f cghi %r2,__CLOCK_MONOTONIC jne 12f @@ -34,14 +36,13 @@ __kernel_clock_gettime: tmll %r4,0x0001 /* pending update ? loop */ jnz 0b stck 48(%r15) /* Store TOD clock */ + lgf %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + lg %r0,__VDSO_WTOM_SEC(%r5) lg %r1,48(%r15) sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ - srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ - alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime */ - lg %r0,__VDSO_XTIME_SEC(%r5) - alg %r1,__VDSO_WTOM_NSEC(%r5) /* + wall_to_monotonic */ - alg %r0,__VDSO_WTOM_SEC(%r5) + msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ + alg %r1,__VDSO_WTOM_NSEC(%r5) + srlg %r1,%r1,0(%r2) /* >> tk->shift */ clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ jne 0b larl %r5,13f @@ -62,12 +63,13 @@ __kernel_clock_gettime: tmll %r4,0x0001 /* pending update ? loop */ jnz 5b stck 48(%r15) /* Store TOD clock */ + lgf %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ lg %r1,48(%r15) sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ - srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ - alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime */ - lg %r0,__VDSO_XTIME_SEC(%r5) + msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ + srlg %r1,%r1,0(%r2) /* >> tk->shift */ + lg %r0,__VDSO_XTIME_SEC(%r5) /* tk->xtime_sec */ clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ jne 5b larl %r5,13f diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S index 36ee674722e..d0860d1d0cc 100644 --- a/arch/s390/kernel/vdso64/gettimeofday.S +++ b/arch/s390/kernel/vdso64/gettimeofday.S @@ -31,12 +31,13 @@ __kernel_gettimeofday: stck 48(%r15) /* Store TOD clock */ lg %r1,48(%r15) sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - msgf %r1,__VDSO_NTP_MULT(%r5) /* * NTP adjustment */ - srlg %r1,%r1,12 /* cyc2ns(clock,cycle_delta) */ - alg %r1,__VDSO_XTIME_NSEC(%r5) /* + xtime.tv_nsec */ - lg %r0,__VDSO_XTIME_SEC(%r5) /* xtime.tv_sec */ + msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ + alg %r1,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ + lg %r0,__VDSO_XTIME_SEC(%r5) /* tk->xtime_sec */ clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ jne 0b + lgf %r5,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ + srlg %r1,%r1,0(%r5) /* >> tk->shift */ larl %r5,5f 2: clg %r1,0(%r5) jl 3f diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 79cb51adc74..35b13ed0af5 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -75,6 +75,10 @@ SECTIONS EXIT_TEXT } + .exit.data : { + EXIT_DATA + } + /* early.c uses stsi, which requires page aligned data. */ . = ALIGN(PAGE_SIZE); INIT_DATA_SECTION(0x100) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index e84b8b68444..8c34363d6f1 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -19,6 +19,7 @@ #include <asm/irq_regs.h> #include <asm/cputime.h> #include <asm/vtimer.h> +#include <asm/vtime.h> #include <asm/irq.h> #include "entry.h" @@ -127,7 +128,7 @@ void vtime_account_user(struct task_struct *tsk) * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -void vtime_account(struct task_struct *tsk) +void vtime_account_irq_enter(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); u64 timer, system; @@ -145,10 +146,10 @@ void vtime_account(struct task_struct *tsk) virt_timer_forward(system); } -EXPORT_SYMBOL_GPL(vtime_account); +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); void vtime_account_system(struct task_struct *tsk) -__attribute__((alias("vtime_account"))); +__attribute__((alias("vtime_account_irq_enter"))); EXPORT_SYMBOL_GPL(vtime_account_system); void __kprobes vtime_stop_cpu(void) @@ -158,20 +159,15 @@ void __kprobes vtime_stop_cpu(void) unsigned long psw_mask; trace_hardirqs_on(); - /* Don't trace preempt off for idle. */ - stop_critical_timings(); /* Wait for external, I/O or machine check interrupt. */ - psw_mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_DAT | + psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; idle->nohz_delay = 0; /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - /* Reenable preemption tracer. */ - start_critical_timings(); - /* Account time spent with enabled wait psw loaded as idle time. */ idle->sequence++; smp_wmb(); @@ -191,11 +187,11 @@ cputime64_t s390_get_idle_time(int cpu) unsigned int sequence; do { - now = get_clock(); + now = get_tod_clock(); sequence = ACCESS_ONCE(idle->sequence); idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (idle->sequence != sequence)); + } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; } @@ -376,14 +372,14 @@ EXPORT_SYMBOL(del_virt_timer); /* * Start the virtual CPU timer on the current CPU. */ -void __cpuinit init_cpu_vtimer(void) +void init_cpu_vtimer(void) { /* set initial cpu timer */ set_vtimer(VTIMER_MAX_SLICE); } -static int __cpuinit s390_nohz_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int s390_nohz_notify(struct notifier_block *self, unsigned long action, + void *hcpu) { struct s390_idle_data *idle; long cpu = (long) hcpu; diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index b58dd869cb3..10d529ac982 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -18,10 +18,15 @@ if VIRTUALIZATION config KVM def_tristate y prompt "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM && EXPERIMENTAL + depends on HAVE_KVM select PREEMPT_NOTIFIERS 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 3975722bb19..b3b55346965 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -6,9 +6,12 @@ # it under the terms of the GNU General Public License (version 2 only) # as published by the Free Software Foundation. -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o) +KVM := ../../../virt/kvm +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o ccflags-y := -Ivirt/kvm -Iarch/s390/kvm -kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o +kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o +kvm-objs += diag.o gaccess.o guestdbg.o + obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index a390687feb1..0161675878a 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -13,14 +13,17 @@ #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) { unsigned long start, end; - unsigned long prefix = vcpu->arch.sie_block->prefix; + unsigned long prefix = kvm_s390_get_prefix(vcpu); start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096; @@ -45,6 +48,86 @@ 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); + + if (vcpu->run->s.regs.gprs[rx] & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + 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); + + if (kvm_is_error_gpa(vcpu->kvm, parm.token_addr)) + 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"); @@ -93,7 +176,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } - atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + kvm_s390_vcpu_stop(vcpu); vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL; vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT; @@ -104,9 +187,42 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) return -EREMOTE; } +static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) +{ + int ret; + + /* No virtio-ccw notification? Get out quickly. */ + if (!vcpu->kvm->arch.css_support || + (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY)) + return -EOPNOTSUPP; + + /* + * The layout is as follows: + * - gpr 2 contains the subchannel id (passed as addr) + * - gpr 3 contains the virtqueue index (passed as datamatch) + * - 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] & 0xffffffff, + 8, &vcpu->run->s.regs.gprs[3], + vcpu->run->s.regs.gprs[4]); + + /* + * Return cookie in gpr 2, but don't overwrite the register if the + * diagnose will be handled by userspace. + */ + if (ret != -EOPNOTSUPP) + vcpu->run->s.regs.gprs[2] = ret; + /* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */ + return ret < 0 ? ret : 0; +} + 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); trace_kvm_s390_handle_diag(vcpu, code); switch (code) { @@ -116,8 +232,12 @@ 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: + return __diag_virtio_hypercall(vcpu); default: return -EOPNOTSUPP; } diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c new file mode 100644 index 00000000000..4653ac6e182 --- /dev/null +++ b/arch/s390/kvm/gaccess.c @@ -0,0 +1,726 @@ +/* + * guest access functions + * + * Copyright IBM Corp. 2014 + * + */ + +#include <linux/vmalloc.h> +#include <linux/err.h> +#include <asm/pgtable.h> +#include "kvm-s390.h" +#include "gaccess.h" + +union asce { + unsigned long val; + struct { + unsigned long origin : 52; /* Region- or Segment-Table Origin */ + unsigned long : 2; + unsigned long g : 1; /* Subspace Group Control */ + unsigned long p : 1; /* Private Space Control */ + unsigned long s : 1; /* Storage-Alteration-Event Control */ + unsigned long x : 1; /* Space-Switch-Event Control */ + unsigned long r : 1; /* Real-Space Control */ + unsigned long : 1; + unsigned long dt : 2; /* Designation-Type Control */ + unsigned long tl : 2; /* Region- or Segment-Table Length */ + }; +}; + +enum { + ASCE_TYPE_SEGMENT = 0, + ASCE_TYPE_REGION3 = 1, + ASCE_TYPE_REGION2 = 2, + ASCE_TYPE_REGION1 = 3 +}; + +union region1_table_entry { + unsigned long val; + struct { + unsigned long rto: 52;/* Region-Table Origin */ + unsigned long : 2; + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 1; + unsigned long tf : 2; /* Region-Second-Table Offset */ + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long : 1; + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long tl : 2; /* Region-Second-Table Length */ + }; +}; + +union region2_table_entry { + unsigned long val; + struct { + unsigned long rto: 52;/* Region-Table Origin */ + unsigned long : 2; + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 1; + unsigned long tf : 2; /* Region-Third-Table Offset */ + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long : 1; + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long tl : 2; /* Region-Third-Table Length */ + }; +}; + +struct region3_table_entry_fc0 { + unsigned long sto: 52;/* Segment-Table Origin */ + unsigned long : 1; + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 1; + unsigned long tf : 2; /* Segment-Table Offset */ + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long cr : 1; /* Common-Region Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long tl : 2; /* Segment-Table Length */ +}; + +struct region3_table_entry_fc1 { + unsigned long rfaa : 33; /* Region-Frame Absolute Address */ + unsigned long : 14; + unsigned long av : 1; /* ACCF-Validity Control */ + unsigned long acc: 4; /* Access-Control Bits */ + unsigned long f : 1; /* Fetch-Protection Bit */ + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long co : 1; /* Change-Recording Override */ + unsigned long : 2; + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long cr : 1; /* Common-Region Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; +}; + +union region3_table_entry { + unsigned long val; + struct region3_table_entry_fc0 fc0; + struct region3_table_entry_fc1 fc1; + struct { + unsigned long : 53; + unsigned long fc : 1; /* Format-Control */ + unsigned long : 4; + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long cr : 1; /* Common-Region Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; + }; +}; + +struct segment_entry_fc0 { + unsigned long pto: 53;/* Page-Table Origin */ + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 3; + unsigned long i : 1; /* Segment-Invalid Bit */ + unsigned long cs : 1; /* Common-Segment Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; +}; + +struct segment_entry_fc1 { + unsigned long sfaa : 44; /* Segment-Frame Absolute Address */ + unsigned long : 3; + unsigned long av : 1; /* ACCF-Validity Control */ + unsigned long acc: 4; /* Access-Control Bits */ + unsigned long f : 1; /* Fetch-Protection Bit */ + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long co : 1; /* Change-Recording Override */ + unsigned long : 2; + unsigned long i : 1; /* Segment-Invalid Bit */ + unsigned long cs : 1; /* Common-Segment Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; +}; + +union segment_table_entry { + unsigned long val; + struct segment_entry_fc0 fc0; + struct segment_entry_fc1 fc1; + struct { + unsigned long : 53; + unsigned long fc : 1; /* Format-Control */ + unsigned long : 4; + unsigned long i : 1; /* Segment-Invalid Bit */ + unsigned long cs : 1; /* Common-Segment Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; + }; +}; + +enum { + TABLE_TYPE_SEGMENT = 0, + TABLE_TYPE_REGION3 = 1, + TABLE_TYPE_REGION2 = 2, + TABLE_TYPE_REGION1 = 3 +}; + +union page_table_entry { + unsigned long val; + struct { + unsigned long pfra : 52; /* Page-Frame Real Address */ + unsigned long z : 1; /* Zero Bit */ + unsigned long i : 1; /* Page-Invalid Bit */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long co : 1; /* Change-Recording Override */ + unsigned long : 8; + }; +}; + +/* + * vaddress union in order to easily decode a virtual address into its + * region first index, region second index etc. parts. + */ +union vaddress { + unsigned long addr; + struct { + unsigned long rfx : 11; + unsigned long rsx : 11; + unsigned long rtx : 11; + unsigned long sx : 11; + unsigned long px : 8; + unsigned long bx : 12; + }; + struct { + unsigned long rfx01 : 2; + unsigned long : 9; + unsigned long rsx01 : 2; + unsigned long : 9; + unsigned long rtx01 : 2; + unsigned long : 9; + unsigned long sx01 : 2; + unsigned long : 29; + }; +}; + +/* + * raddress union which will contain the result (real or absolute address) + * after a page table walk. The rfaa, sfaa and pfra members are used to + * simply assign them the value of a region, segment or page table entry. + */ +union raddress { + unsigned long addr; + unsigned long rfaa : 33; /* Region-Frame Absolute Address */ + unsigned long sfaa : 44; /* Segment-Frame Absolute Address */ + unsigned long pfra : 52; /* Page-Frame Real Address */ +}; + +static int ipte_lock_count; +static DEFINE_MUTEX(ipte_mutex); + +int ipte_lock_held(struct kvm_vcpu *vcpu) +{ + union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control; + + if (vcpu->arch.sie_block->eca & 1) + return ic->kh != 0; + return ipte_lock_count != 0; +} + +static void ipte_lock_simple(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + mutex_lock(&ipte_mutex); + ipte_lock_count++; + if (ipte_lock_count > 1) + goto out; + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + old = ACCESS_ONCE(*ic); + while (old.k) { + cond_resched(); + old = ACCESS_ONCE(*ic); + } + new = old; + new.k = 1; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); +out: + mutex_unlock(&ipte_mutex); +} + +static void ipte_unlock_simple(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + mutex_lock(&ipte_mutex); + ipte_lock_count--; + if (ipte_lock_count) + goto out; + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + new = old = ACCESS_ONCE(*ic); + new.k = 0; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + if (!ipte_lock_count) + wake_up(&vcpu->kvm->arch.ipte_wq); +out: + mutex_unlock(&ipte_mutex); +} + +static void ipte_lock_siif(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + old = ACCESS_ONCE(*ic); + while (old.kg) { + cond_resched(); + old = ACCESS_ONCE(*ic); + } + new = old; + new.k = 1; + new.kh++; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); +} + +static void ipte_unlock_siif(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + new = old = ACCESS_ONCE(*ic); + new.kh--; + if (!new.kh) + new.k = 0; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + if (!new.kh) + wake_up(&vcpu->kvm->arch.ipte_wq); +} + +void ipte_lock(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->eca & 1) + ipte_lock_siif(vcpu); + else + ipte_lock_simple(vcpu); +} + +void ipte_unlock(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->eca & 1) + ipte_unlock_siif(vcpu); + else + ipte_unlock_simple(vcpu); +} + +static unsigned long get_vcpu_asce(struct kvm_vcpu *vcpu) +{ + switch (psw_bits(vcpu->arch.sie_block->gpsw).as) { + case PSW_AS_PRIMARY: + return vcpu->arch.sie_block->gcr[1]; + case PSW_AS_SECONDARY: + return vcpu->arch.sie_block->gcr[7]; + case PSW_AS_HOME: + return vcpu->arch.sie_block->gcr[13]; + } + return 0; +} + +static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) +{ + return kvm_read_guest(kvm, gpa, val, sizeof(*val)); +} + +/** + * guest_translate - translate a guest virtual into a guest absolute address + * @vcpu: virtual cpu + * @gva: guest virtual address + * @gpa: points to where guest physical (absolute) address should be stored + * @write: indicates if access is a write access + * + * Translate a guest virtual address into a guest absolute address by means + * of dynamic address translation as specified by the architecuture. + * If the resulting absolute address is not available in the configuration + * an addressing exception is indicated and @gpa will not be changed. + * + * Returns: - zero on success; @gpa contains the resulting absolute address + * - a negative value if guest access failed due to e.g. broken + * guest mapping + * - a positve value if an access exception happened. In this case + * the returned value is the program interruption code as defined + * by the architecture + */ +static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, + unsigned long *gpa, int write) +{ + union vaddress vaddr = {.addr = gva}; + union raddress raddr = {.addr = gva}; + union page_table_entry pte; + int dat_protection = 0; + union ctlreg0 ctlreg0; + unsigned long ptr; + int edat1, edat2; + union asce asce; + + ctlreg0.val = vcpu->arch.sie_block->gcr[0]; + edat1 = ctlreg0.edat && test_vfacility(8); + edat2 = edat1 && test_vfacility(78); + asce.val = get_vcpu_asce(vcpu); + if (asce.r) + goto real_address; + ptr = asce.origin * 4096; + switch (asce.dt) { + case ASCE_TYPE_REGION1: + if (vaddr.rfx01 > asce.tl) + return PGM_REGION_FIRST_TRANS; + ptr += vaddr.rfx * 8; + break; + case ASCE_TYPE_REGION2: + if (vaddr.rfx) + return PGM_ASCE_TYPE; + if (vaddr.rsx01 > asce.tl) + return PGM_REGION_SECOND_TRANS; + ptr += vaddr.rsx * 8; + break; + case ASCE_TYPE_REGION3: + if (vaddr.rfx || vaddr.rsx) + return PGM_ASCE_TYPE; + if (vaddr.rtx01 > asce.tl) + return PGM_REGION_THIRD_TRANS; + ptr += vaddr.rtx * 8; + break; + case ASCE_TYPE_SEGMENT: + if (vaddr.rfx || vaddr.rsx || vaddr.rtx) + return PGM_ASCE_TYPE; + if (vaddr.sx01 > asce.tl) + return PGM_SEGMENT_TRANSLATION; + ptr += vaddr.sx * 8; + break; + } + switch (asce.dt) { + case ASCE_TYPE_REGION1: { + union region1_table_entry rfte; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &rfte.val)) + return -EFAULT; + if (rfte.i) + return PGM_REGION_FIRST_TRANS; + if (rfte.tt != TABLE_TYPE_REGION1) + return PGM_TRANSLATION_SPEC; + if (vaddr.rsx01 < rfte.tf || vaddr.rsx01 > rfte.tl) + return PGM_REGION_SECOND_TRANS; + if (edat1) + dat_protection |= rfte.p; + ptr = rfte.rto * 4096 + vaddr.rsx * 8; + } + /* fallthrough */ + case ASCE_TYPE_REGION2: { + union region2_table_entry rste; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &rste.val)) + return -EFAULT; + if (rste.i) + return PGM_REGION_SECOND_TRANS; + if (rste.tt != TABLE_TYPE_REGION2) + return PGM_TRANSLATION_SPEC; + if (vaddr.rtx01 < rste.tf || vaddr.rtx01 > rste.tl) + return PGM_REGION_THIRD_TRANS; + if (edat1) + dat_protection |= rste.p; + ptr = rste.rto * 4096 + vaddr.rtx * 8; + } + /* fallthrough */ + case ASCE_TYPE_REGION3: { + union region3_table_entry rtte; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &rtte.val)) + return -EFAULT; + if (rtte.i) + return PGM_REGION_THIRD_TRANS; + if (rtte.tt != TABLE_TYPE_REGION3) + return PGM_TRANSLATION_SPEC; + if (rtte.cr && asce.p && edat2) + return PGM_TRANSLATION_SPEC; + if (rtte.fc && edat2) { + dat_protection |= rtte.fc1.p; + raddr.rfaa = rtte.fc1.rfaa; + goto absolute_address; + } + if (vaddr.sx01 < rtte.fc0.tf) + return PGM_SEGMENT_TRANSLATION; + if (vaddr.sx01 > rtte.fc0.tl) + return PGM_SEGMENT_TRANSLATION; + if (edat1) + dat_protection |= rtte.fc0.p; + ptr = rtte.fc0.sto * 4096 + vaddr.sx * 8; + } + /* fallthrough */ + case ASCE_TYPE_SEGMENT: { + union segment_table_entry ste; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &ste.val)) + return -EFAULT; + if (ste.i) + return PGM_SEGMENT_TRANSLATION; + if (ste.tt != TABLE_TYPE_SEGMENT) + return PGM_TRANSLATION_SPEC; + if (ste.cs && asce.p) + return PGM_TRANSLATION_SPEC; + if (ste.fc && edat1) { + dat_protection |= ste.fc1.p; + raddr.sfaa = ste.fc1.sfaa; + goto absolute_address; + } + dat_protection |= ste.fc0.p; + ptr = ste.fc0.pto * 2048 + vaddr.px * 8; + } + } + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &pte.val)) + return -EFAULT; + if (pte.i) + return PGM_PAGE_TRANSLATION; + if (pte.z) + return PGM_TRANSLATION_SPEC; + if (pte.co && !edat1) + return PGM_TRANSLATION_SPEC; + dat_protection |= pte.p; + raddr.pfra = pte.pfra; +real_address: + raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr); +absolute_address: + if (write && dat_protection) + return PGM_PROTECTION; + if (kvm_is_error_gpa(vcpu->kvm, raddr.addr)) + return PGM_ADDRESSING; + *gpa = raddr.addr; + return 0; +} + +static inline int is_low_address(unsigned long ga) +{ + /* Check for address ranges 0..511 and 4096..4607 */ + return (ga & ~0x11fful) == 0; +} + +static int low_address_protection_enabled(struct kvm_vcpu *vcpu) +{ + union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + union asce asce; + + if (!ctlreg0.lap) + return 0; + asce.val = get_vcpu_asce(vcpu); + if (psw_bits(*psw).t && asce.p) + return 0; + return 1; +} + +struct trans_exc_code_bits { + unsigned long addr : 52; /* Translation-exception Address */ + unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ + unsigned long : 7; + unsigned long b61 : 1; + unsigned long as : 2; /* ASCE Identifier */ +}; + +enum { + FSI_UNKNOWN = 0, /* Unknown wether fetch or store */ + FSI_STORE = 1, /* Exception was due to store operation */ + FSI_FETCH = 2 /* Exception was due to fetch operation */ +}; + +static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, + unsigned long *pages, unsigned long nr_pages, + int write) +{ + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct trans_exc_code_bits *tec_bits; + int lap_enabled, rc; + + memset(pgm, 0, sizeof(*pgm)); + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; + tec_bits->as = psw_bits(*psw).as; + lap_enabled = low_address_protection_enabled(vcpu); + while (nr_pages) { + ga = kvm_s390_logical_to_effective(vcpu, ga); + tec_bits->addr = ga >> PAGE_SHIFT; + if (write && lap_enabled && is_low_address(ga)) { + pgm->code = PGM_PROTECTION; + return pgm->code; + } + ga &= PAGE_MASK; + if (psw_bits(*psw).t) { + rc = guest_translate(vcpu, ga, pages, write); + if (rc < 0) + return rc; + if (rc == PGM_PROTECTION) + tec_bits->b61 = 1; + if (rc) + pgm->code = rc; + } else { + *pages = kvm_s390_real_to_abs(vcpu, ga); + if (kvm_is_error_gpa(vcpu->kvm, *pages)) + pgm->code = PGM_ADDRESSING; + } + if (pgm->code) + return pgm->code; + ga += PAGE_SIZE; + pages++; + nr_pages--; + } + return 0; +} + +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, + unsigned long len, int write) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + unsigned long _len, nr_pages, gpa, idx; + unsigned long pages_array[2]; + unsigned long *pages; + int need_ipte_lock; + union asce asce; + int rc; + + if (!len) + return 0; + /* Access register mode is not supported yet. */ + if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG) + return -EOPNOTSUPP; + nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1; + pages = pages_array; + if (nr_pages > ARRAY_SIZE(pages_array)) + pages = vmalloc(nr_pages * sizeof(unsigned long)); + if (!pages) + return -ENOMEM; + asce.val = get_vcpu_asce(vcpu); + need_ipte_lock = psw_bits(*psw).t && !asce.r; + if (need_ipte_lock) + ipte_lock(vcpu); + rc = guest_page_range(vcpu, ga, pages, nr_pages, write); + for (idx = 0; idx < nr_pages && !rc; idx++) { + gpa = *(pages + idx) + (ga & ~PAGE_MASK); + _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); + if (write) + rc = kvm_write_guest(vcpu->kvm, gpa, data, _len); + else + rc = kvm_read_guest(vcpu->kvm, gpa, data, _len); + len -= _len; + ga += _len; + data += _len; + } + if (need_ipte_lock) + ipte_unlock(vcpu); + if (nr_pages > ARRAY_SIZE(pages_array)) + vfree(pages); + return rc; +} + +int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, + void *data, unsigned long len, int write) +{ + unsigned long _len, gpa; + int rc = 0; + + while (len && !rc) { + gpa = kvm_s390_real_to_abs(vcpu, gra); + _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); + if (write) + rc = write_guest_abs(vcpu, gpa, data, _len); + else + rc = read_guest_abs(vcpu, gpa, data, _len); + len -= _len; + gra += _len; + data += _len; + } + return rc; +} + +/** + * guest_translate_address - translate guest logical into guest absolute address + * + * Parameter semantics are the same as the ones from guest_translate. + * The memory contents at the guest address are not changed. + * + * Note: The IPTE lock is not taken during this function, so the caller + * has to take care of this. + */ +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, + unsigned long *gpa, int write) +{ + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct trans_exc_code_bits *tec; + union asce asce; + int rc; + + /* Access register mode is not supported yet. */ + if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG) + return -EOPNOTSUPP; + + gva = kvm_s390_logical_to_effective(vcpu, gva); + memset(pgm, 0, sizeof(*pgm)); + tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec->as = psw_bits(*psw).as; + tec->fsi = write ? FSI_STORE : FSI_FETCH; + tec->addr = gva >> PAGE_SHIFT; + if (is_low_address(gva) && low_address_protection_enabled(vcpu)) { + if (write) { + rc = pgm->code = PGM_PROTECTION; + return rc; + } + } + + asce.val = get_vcpu_asce(vcpu); + if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ + rc = guest_translate(vcpu, gva, gpa, write); + if (rc > 0) { + if (rc == PGM_PROTECTION) + tec->b61 = 1; + pgm->code = rc; + } + } else { + rc = 0; + *gpa = kvm_s390_real_to_abs(vcpu, gva); + if (kvm_is_error_gpa(vcpu->kvm, *gpa)) + rc = pgm->code = PGM_ADDRESSING; + } + + return rc; +} + +/** + * kvm_s390_check_low_addr_protection - check for low-address protection + * @ga: Guest address + * + * Checks whether an address is subject to low-address protection and set + * up vcpu->arch.pgm accordingly if necessary. + * + * Return: 0 if no protection exception, or PGM_PROTECTION if protected. + */ +int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga) +{ + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct trans_exc_code_bits *tec_bits; + + if (!is_low_address(ga) || !low_address_protection_enabled(vcpu)) + return 0; + + memset(pgm, 0, sizeof(*pgm)); + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec_bits->fsi = FSI_STORE; + tec_bits->as = psw_bits(*psw).as; + tec_bits->addr = ga >> PAGE_SHIFT; + pgm->code = PGM_PROTECTION; + + return pgm->code; +} diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 4703f129e95..0149cf15058 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,7 +1,7 @@ /* * access guest memory * - * Copyright IBM Corp. 2008, 2009 + * 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) @@ -15,372 +15,321 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> +#include <linux/ptrace.h> #include "kvm-s390.h" -static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu, - unsigned long guestaddr) -{ - unsigned long prefix = vcpu->arch.sie_block->prefix; - - if (guestaddr < 2 * PAGE_SIZE) - guestaddr += prefix; - else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE)) - guestaddr -= prefix; - - return (void __user *) gmap_fault(guestaddr, vcpu->arch.gmap); -} - -static inline int get_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u64 *result) -{ - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - BUG_ON(guestaddr & 7); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - return get_user(*result, (unsigned long __user *) uptr); -} - -static inline int get_guest_u32(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u32 *result) -{ - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - BUG_ON(guestaddr & 3); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - return get_user(*result, (u32 __user *) uptr); -} - -static inline int get_guest_u16(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u16 *result) +/** + * kvm_s390_real_to_abs - convert guest real address to guest absolute address + * @vcpu - guest virtual cpu + * @gra - guest real address + * + * Returns the guest absolute address that corresponds to the passed guest real + * address @gra of a virtual guest cpu by applying its prefix. + */ +static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, + unsigned long gra) { - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - BUG_ON(guestaddr & 1); - - if (IS_ERR(uptr)) - return PTR_ERR(uptr); + unsigned long prefix = kvm_s390_get_prefix(vcpu); - return get_user(*result, (u16 __user *) uptr); + if (gra < 2 * PAGE_SIZE) + gra += prefix; + else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE) + gra -= prefix; + return gra; } -static inline int get_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u8 *result) +/** + * kvm_s390_logical_to_effective - convert guest logical to effective address + * @vcpu: guest virtual cpu + * @ga: guest logical address + * + * Convert a guest vcpu logical address to a guest vcpu effective address by + * applying the rules of the vcpu's addressing mode defined by PSW bits 31 + * and 32 (extendended/basic addressing mode). + * + * Depending on the vcpu's addressing mode the upper 40 bits (24 bit addressing + * mode), 33 bits (31 bit addressing mode) or no bits (64 bit addressing mode) + * of @ga will be zeroed and the remaining bits will be returned. + */ +static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu, + unsigned long ga) { - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); + psw_t *psw = &vcpu->arch.sie_block->gpsw; - return get_user(*result, (u8 __user *) uptr); + if (psw_bits(*psw).eaba == PSW_AMODE_64BIT) + return ga; + if (psw_bits(*psw).eaba == PSW_AMODE_31BIT) + return ga & ((1UL << 31) - 1); + return ga & ((1UL << 24) - 1); } -static inline int put_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u64 value) -{ - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - BUG_ON(guestaddr & 7); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - return put_user(value, (u64 __user *) uptr); -} +/* + * put_guest_lc, read_guest_lc and write_guest_lc are guest access functions + * which shall only be used to access the lowcore of a vcpu. + * These functions should be used for e.g. interrupt handlers where no + * guest memory access protection facilities, like key or low address + * protection, are applicable. + * At a later point guest vcpu lowcore access should happen via pinned + * prefix pages, so that these pages can be accessed directly via the + * kernel mapping. All of these *_lc functions can be removed then. + */ -static inline int put_guest_u32(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u32 value) +/** + * put_guest_lc - write a simple variable to a guest vcpu's lowcore + * @vcpu: virtual cpu + * @x: value to copy to guest + * @gra: vcpu's destination guest real address + * + * Copies a simple value from kernel space to a guest vcpu's lowcore. + * The size of the variable may be 1, 2, 4 or 8 bytes. The destination + * must be located in the vcpu's lowcore. Otherwise the result is undefined. + * + * Returns zero on success or -EFAULT on error. + * + * Note: an error indicates that either the kernel is out of memory or + * the guest memory mapping is broken. In any case the best solution + * would be to terminate the guest. + * It is wrong to inject a guest exception. + */ +#define put_guest_lc(vcpu, x, gra) \ +({ \ + struct kvm_vcpu *__vcpu = (vcpu); \ + __typeof__(*(gra)) __x = (x); \ + unsigned long __gpa; \ + \ + __gpa = (unsigned long)(gra); \ + __gpa += kvm_s390_get_prefix(__vcpu); \ + kvm_write_guest(__vcpu->kvm, __gpa, &__x, sizeof(__x)); \ +}) + +/** + * write_guest_lc - copy data from kernel space to guest vcpu's lowcore + * @vcpu: virtual cpu + * @gra: vcpu's source guest real address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy data from kernel space to guest vcpu's lowcore. The entire range must + * be located within the vcpu's lowcore, otherwise the result is undefined. + * + * Returns zero on success or -EFAULT on error. + * + * Note: an error indicates that either the kernel is out of memory or + * the guest memory mapping is broken. In any case the best solution + * would be to terminate the guest. + * It is wrong to inject a guest exception. + */ +static inline __must_check +int write_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) { - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - BUG_ON(guestaddr & 3); + unsigned long gpa = gra + kvm_s390_get_prefix(vcpu); - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - return put_user(value, (u32 __user *) uptr); + return kvm_write_guest(vcpu->kvm, gpa, data, len); } -static inline int put_guest_u16(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u16 value) +/** + * read_guest_lc - copy data from guest vcpu's lowcore to kernel space + * @vcpu: virtual cpu + * @gra: vcpu's source guest real address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy data from guest vcpu's lowcore to kernel space. The entire range must + * be located within the vcpu's lowcore, otherwise the result is undefined. + * + * Returns zero on success or -EFAULT on error. + * + * Note: an error indicates that either the kernel is out of memory or + * the guest memory mapping is broken. In any case the best solution + * would be to terminate the guest. + * It is wrong to inject a guest exception. + */ +static inline __must_check +int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) { - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - BUG_ON(guestaddr & 1); + unsigned long gpa = gra + kvm_s390_get_prefix(vcpu); - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - return put_user(value, (u16 __user *) uptr); + return kvm_read_guest(vcpu->kvm, gpa, data, len); } -static inline int put_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr, - u8 value) -{ - void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, + unsigned long *gpa, int write); - return put_user(value, (u8 __user *) uptr); -} +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, + unsigned long len, int write); +int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, + void *data, unsigned long len, int write); -static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, - unsigned long guestdest, - void *from, unsigned long n) +/** + * write_guest - copy data from kernel space to guest space + * @vcpu: virtual cpu + * @ga: guest address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @data (kernel space) to @ga (guest address). + * In order to copy data to guest space the PSW of the vcpu is inspected: + * If DAT is off data will be copied to guest real or absolute memory. + * If DAT is on data will be copied to the address space as specified by + * the address space bits of the PSW: + * Primary, secondory or home space (access register mode is currently not + * implemented). + * The addressing mode of the PSW is also inspected, so that address wrap + * around is taken into account for 24-, 31- and 64-bit addressing mode, + * if the to be copied data crosses page boundaries in guest address space. + * In addition also low address and DAT protection are inspected before + * copying any data (key protection is currently not implemented). + * + * This function modifies the 'struct kvm_s390_pgm_info pgm' member of @vcpu. + * In case of an access exception (e.g. protection exception) pgm will contain + * all data necessary so that a subsequent call to 'kvm_s390_inject_prog_vcpu()' + * will inject a correct exception into the guest. + * If no access exception happened, the contents of pgm are undefined when + * this function returns. + * + * Returns: - zero on success + * - a negative value if e.g. the guest mapping is broken or in + * case of out-of-memory. In this case the contents of pgm are + * undefined. Also parts of @data may have been copied to guest + * space. + * - a positive value if an access exception happened. In this case + * the returned value is the program interruption code and the + * contents of pgm may be used to inject an exception into the + * guest. No data has been copied to guest space. + * + * Note: in case an access exception is recognized no data has been copied to + * guest space (this is also true, if the to be copied data would cross + * one or more page boundaries in guest space). + * Therefore this function may be used for nullifying and suppressing + * instruction emulation. + * It may also be used for terminating instructions, if it is undefined + * if data has been changed in guest space in case of an exception. + */ +static inline __must_check +int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, + unsigned long len) { - int rc; - unsigned long i; - u8 *data = from; - - for (i = 0; i < n; i++) { - rc = put_guest_u8(vcpu, guestdest++, *(data++)); - if (rc < 0) - return rc; - } - return 0; + return access_guest(vcpu, ga, data, len, 1); } -static inline int __copy_to_guest_fast(struct kvm_vcpu *vcpu, - unsigned long guestdest, - void *from, unsigned long n) -{ - int r; - void __user *uptr; - unsigned long size; - - if (guestdest + n < guestdest) - return -EFAULT; - - /* simple case: all within one segment table entry? */ - if ((guestdest & PMD_MASK) == ((guestdest+n) & PMD_MASK)) { - uptr = (void __user *) gmap_fault(guestdest, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - r = copy_to_user(uptr, from, n); - - if (r) - r = -EFAULT; - - goto out; - } - - /* copy first segment */ - uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - size = PMD_SIZE - (guestdest & ~PMD_MASK); - - r = copy_to_user(uptr, from, size); - - if (r) { - r = -EFAULT; - goto out; - } - from += size; - n -= size; - guestdest += size; - - /* copy full segments */ - while (n >= PMD_SIZE) { - uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - r = copy_to_user(uptr, from, PMD_SIZE); - - if (r) { - r = -EFAULT; - goto out; - } - from += PMD_SIZE; - n -= PMD_SIZE; - guestdest += PMD_SIZE; - } - - /* copy the tail segment */ - if (n) { - uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - r = copy_to_user(uptr, from, n); - - if (r) - r = -EFAULT; - } -out: - return r; -} - -static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, - unsigned long guestdest, - void *from, unsigned long n) +/** + * read_guest - copy data from guest space to kernel space + * @vcpu: virtual cpu + * @ga: guest address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @ga (guest address) to @data (kernel space). + * + * The behaviour of read_guest is identical to write_guest, except that + * data will be copied from guest space to kernel space. + */ +static inline __must_check +int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, + unsigned long len) { - return __copy_to_guest_fast(vcpu, guestdest, from, n); + return access_guest(vcpu, ga, data, len, 0); } -static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest, - void *from, unsigned long n) +/** + * write_guest_abs - copy data from kernel space to guest space absolute + * @vcpu: virtual cpu + * @gpa: guest physical (absolute) address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @data (kernel space) to @gpa (guest absolute address). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest low address and key protection are not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to guest memory. + */ +static inline __must_check +int write_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, + unsigned long len) { - unsigned long prefix = vcpu->arch.sie_block->prefix; - - if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE)) - goto slowpath; - - if ((guestdest < prefix) && (guestdest + n > prefix)) - goto slowpath; - - if ((guestdest < prefix + 2 * PAGE_SIZE) - && (guestdest + n > prefix + 2 * PAGE_SIZE)) - goto slowpath; - - if (guestdest < 2 * PAGE_SIZE) - guestdest += prefix; - else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE)) - guestdest -= prefix; - - return __copy_to_guest_fast(vcpu, guestdest, from, n); -slowpath: - return __copy_to_guest_slow(vcpu, guestdest, from, n); + return kvm_write_guest(vcpu->kvm, gpa, data, len); } -static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to, - unsigned long guestsrc, - unsigned long n) +/** + * read_guest_abs - copy data from guest space absolute to kernel space + * @vcpu: virtual cpu + * @gpa: guest physical (absolute) address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @gpa (guest absolute address) to @data (kernel space). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest key protection is not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to kernel space. + */ +static inline __must_check +int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, + unsigned long len) { - int rc; - unsigned long i; - u8 *data = to; - - for (i = 0; i < n; i++) { - rc = get_guest_u8(vcpu, guestsrc++, data++); - if (rc < 0) - return rc; - } - return 0; + return kvm_read_guest(vcpu->kvm, gpa, data, len); } -static inline int __copy_from_guest_fast(struct kvm_vcpu *vcpu, void *to, - unsigned long guestsrc, - unsigned long n) +/** + * write_guest_real - copy data from kernel space to guest space real + * @vcpu: virtual cpu + * @gra: guest real address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @data (kernel space) to @gra (guest real address). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest low address and key protection are not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to guest memory. + */ +static inline __must_check +int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) { - int r; - void __user *uptr; - unsigned long size; - - if (guestsrc + n < guestsrc) - return -EFAULT; - - /* simple case: all within one segment table entry? */ - if ((guestsrc & PMD_MASK) == ((guestsrc+n) & PMD_MASK)) { - uptr = (void __user *) gmap_fault(guestsrc, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - r = copy_from_user(to, uptr, n); - - if (r) - r = -EFAULT; - - goto out; - } - - /* copy first segment */ - uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - size = PMD_SIZE - (guestsrc & ~PMD_MASK); - - r = copy_from_user(to, uptr, size); - - if (r) { - r = -EFAULT; - goto out; - } - to += size; - n -= size; - guestsrc += size; - - /* copy full segments */ - while (n >= PMD_SIZE) { - uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - r = copy_from_user(to, uptr, PMD_SIZE); - - if (r) { - r = -EFAULT; - goto out; - } - to += PMD_SIZE; - n -= PMD_SIZE; - guestsrc += PMD_SIZE; - } - - /* copy the tail segment */ - if (n) { - uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap); - - if (IS_ERR((void __force *) uptr)) - return PTR_ERR((void __force *) uptr); - - r = copy_from_user(to, uptr, n); - - if (r) - r = -EFAULT; - } -out: - return r; + return access_guest_real(vcpu, gra, data, len, 1); } -static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to, - unsigned long guestsrc, - unsigned long n) +/** + * read_guest_real - copy data from guest space real to kernel space + * @vcpu: virtual cpu + * @gra: guest real address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @gra (guest real address) to @data (kernel space). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest key protection is not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to kernel space. + */ +static inline __must_check +int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) { - return __copy_from_guest_fast(vcpu, to, guestsrc, n); + return access_guest_real(vcpu, gra, data, len, 0); } -static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to, - unsigned long guestsrc, unsigned long n) -{ - unsigned long prefix = vcpu->arch.sie_block->prefix; - - if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) - goto slowpath; +void ipte_lock(struct kvm_vcpu *vcpu); +void ipte_unlock(struct kvm_vcpu *vcpu); +int ipte_lock_held(struct kvm_vcpu *vcpu); +int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga); - if ((guestsrc < prefix) && (guestsrc + n > prefix)) - goto slowpath; - - if ((guestsrc < prefix + 2 * PAGE_SIZE) - && (guestsrc + n > prefix + 2 * PAGE_SIZE)) - goto slowpath; - - if (guestsrc < 2 * PAGE_SIZE) - guestsrc += prefix; - else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE)) - guestsrc -= prefix; - - return __copy_from_guest_fast(vcpu, to, guestsrc, n); -slowpath: - return __copy_from_guest_slow(vcpu, to, guestsrc, n); -} -#endif +#endif /* __KVM_S390_GACCESS_H */ diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c new file mode 100644 index 00000000000..3e8d4092ce3 --- /dev/null +++ b/arch/s390/kvm/guestdbg.c @@ -0,0 +1,482 @@ +/* + * kvm guest debug support + * + * 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): David Hildenbrand <dahi@linux.vnet.ibm.com> + */ +#include <linux/kvm_host.h> +#include <linux/errno.h> +#include "kvm-s390.h" +#include "gaccess.h" + +/* + * Extends the address range given by *start and *stop to include the address + * range starting with estart and the length len. Takes care of overflowing + * intervals and tries to minimize the overall intervall size. + */ +static void extend_address_range(u64 *start, u64 *stop, u64 estart, int len) +{ + u64 estop; + + if (len > 0) + len--; + else + len = 0; + + estop = estart + len; + + /* 0-0 range represents "not set" */ + if ((*start == 0) && (*stop == 0)) { + *start = estart; + *stop = estop; + } else if (*start <= *stop) { + /* increase the existing range */ + if (estart < *start) + *start = estart; + if (estop > *stop) + *stop = estop; + } else { + /* "overflowing" interval, whereby *stop > *start */ + if (estart <= *stop) { + if (estop > *stop) + *stop = estop; + } else if (estop > *start) { + if (estart < *start) + *start = estart; + } + /* minimize the range */ + else if ((estop - *stop) < (*start - estart)) + *stop = estop; + else + *start = estart; + } +} + +#define MAX_INST_SIZE 6 + +static void enable_all_hw_bp(struct kvm_vcpu *vcpu) +{ + unsigned long start, len; + u64 *cr9 = &vcpu->arch.sie_block->gcr[9]; + u64 *cr10 = &vcpu->arch.sie_block->gcr[10]; + u64 *cr11 = &vcpu->arch.sie_block->gcr[11]; + int i; + + if (vcpu->arch.guestdbg.nr_hw_bp <= 0 || + vcpu->arch.guestdbg.hw_bp_info == NULL) + return; + + /* + * If the guest is not interrested in branching events, we can savely + * limit them to the PER address range. + */ + if (!(*cr9 & PER_EVENT_BRANCH)) + *cr9 |= PER_CONTROL_BRANCH_ADDRESS; + *cr9 |= PER_EVENT_IFETCH | PER_EVENT_BRANCH; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_bp; i++) { + start = vcpu->arch.guestdbg.hw_bp_info[i].addr; + len = vcpu->arch.guestdbg.hw_bp_info[i].len; + + /* + * The instruction in front of the desired bp has to + * report instruction-fetching events + */ + if (start < MAX_INST_SIZE) { + len += start; + start = 0; + } else { + start -= MAX_INST_SIZE; + len += MAX_INST_SIZE; + } + + extend_address_range(cr10, cr11, start, len); + } +} + +static void enable_all_hw_wp(struct kvm_vcpu *vcpu) +{ + unsigned long start, len; + u64 *cr9 = &vcpu->arch.sie_block->gcr[9]; + u64 *cr10 = &vcpu->arch.sie_block->gcr[10]; + u64 *cr11 = &vcpu->arch.sie_block->gcr[11]; + int i; + + if (vcpu->arch.guestdbg.nr_hw_wp <= 0 || + vcpu->arch.guestdbg.hw_wp_info == NULL) + return; + + /* if host uses storage alternation for special address + * spaces, enable all events and give all to the guest */ + if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) { + *cr9 &= ~PER_CONTROL_ALTERATION; + *cr10 = 0; + *cr11 = PSW_ADDR_INSN; + } else { + *cr9 &= ~PER_CONTROL_ALTERATION; + *cr9 |= PER_EVENT_STORE; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) { + start = vcpu->arch.guestdbg.hw_wp_info[i].addr; + len = vcpu->arch.guestdbg.hw_wp_info[i].len; + + extend_address_range(cr10, cr11, start, len); + } + } +} + +void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu) +{ + vcpu->arch.guestdbg.cr0 = vcpu->arch.sie_block->gcr[0]; + vcpu->arch.guestdbg.cr9 = vcpu->arch.sie_block->gcr[9]; + vcpu->arch.guestdbg.cr10 = vcpu->arch.sie_block->gcr[10]; + vcpu->arch.guestdbg.cr11 = vcpu->arch.sie_block->gcr[11]; +} + +void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu) +{ + vcpu->arch.sie_block->gcr[0] = vcpu->arch.guestdbg.cr0; + vcpu->arch.sie_block->gcr[9] = vcpu->arch.guestdbg.cr9; + vcpu->arch.sie_block->gcr[10] = vcpu->arch.guestdbg.cr10; + vcpu->arch.sie_block->gcr[11] = vcpu->arch.guestdbg.cr11; +} + +void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu) +{ + /* + * TODO: if guest psw has per enabled, otherwise 0s! + * This reduces the amount of reported events. + * Need to intercept all psw changes! + */ + + if (guestdbg_sstep_enabled(vcpu)) { + /* disable timer (clock-comparator) interrupts */ + vcpu->arch.sie_block->gcr[0] &= ~0x800ul; + vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH; + vcpu->arch.sie_block->gcr[10] = 0; + vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN; + } + + if (guestdbg_hw_bp_enabled(vcpu)) { + enable_all_hw_bp(vcpu); + enable_all_hw_wp(vcpu); + } + + /* TODO: Instruction-fetching-nullification not allowed for now */ + if (vcpu->arch.sie_block->gcr[9] & PER_EVENT_NULLIFICATION) + vcpu->arch.sie_block->gcr[9] &= ~PER_EVENT_NULLIFICATION; +} + +#define MAX_WP_SIZE 100 + +static int __import_wp_info(struct kvm_vcpu *vcpu, + struct kvm_hw_breakpoint *bp_data, + struct kvm_hw_wp_info_arch *wp_info) +{ + int ret = 0; + wp_info->len = bp_data->len; + wp_info->addr = bp_data->addr; + wp_info->phys_addr = bp_data->phys_addr; + wp_info->old_data = NULL; + + if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE) + return -EINVAL; + + wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL); + if (!wp_info->old_data) + return -ENOMEM; + /* try to backup the original value */ + ret = read_guest(vcpu, wp_info->phys_addr, wp_info->old_data, + wp_info->len); + if (ret) { + kfree(wp_info->old_data); + wp_info->old_data = NULL; + } + + return ret; +} + +#define MAX_BP_COUNT 50 + +int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + int ret = 0, nr_wp = 0, nr_bp = 0, i, size; + struct kvm_hw_breakpoint *bp_data = NULL; + struct kvm_hw_wp_info_arch *wp_info = NULL; + struct kvm_hw_bp_info_arch *bp_info = NULL; + + if (dbg->arch.nr_hw_bp <= 0 || !dbg->arch.hw_bp) + return 0; + else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT) + return -EINVAL; + + size = dbg->arch.nr_hw_bp * sizeof(struct kvm_hw_breakpoint); + bp_data = kmalloc(size, GFP_KERNEL); + if (!bp_data) { + ret = -ENOMEM; + goto error; + } + + if (copy_from_user(bp_data, dbg->arch.hw_bp, size)) { + ret = -EFAULT; + goto error; + } + + for (i = 0; i < dbg->arch.nr_hw_bp; i++) { + switch (bp_data[i].type) { + case KVM_HW_WP_WRITE: + nr_wp++; + break; + case KVM_HW_BP: + nr_bp++; + break; + default: + break; + } + } + + size = nr_wp * sizeof(struct kvm_hw_wp_info_arch); + if (size > 0) { + wp_info = kmalloc(size, GFP_KERNEL); + if (!wp_info) { + ret = -ENOMEM; + goto error; + } + } + size = nr_bp * sizeof(struct kvm_hw_bp_info_arch); + if (size > 0) { + bp_info = kmalloc(size, GFP_KERNEL); + if (!bp_info) { + ret = -ENOMEM; + goto error; + } + } + + for (nr_wp = 0, nr_bp = 0, i = 0; i < dbg->arch.nr_hw_bp; i++) { + switch (bp_data[i].type) { + case KVM_HW_WP_WRITE: + ret = __import_wp_info(vcpu, &bp_data[i], + &wp_info[nr_wp]); + if (ret) + goto error; + nr_wp++; + break; + case KVM_HW_BP: + bp_info[nr_bp].len = bp_data[i].len; + bp_info[nr_bp].addr = bp_data[i].addr; + nr_bp++; + break; + } + } + + vcpu->arch.guestdbg.nr_hw_bp = nr_bp; + vcpu->arch.guestdbg.hw_bp_info = bp_info; + vcpu->arch.guestdbg.nr_hw_wp = nr_wp; + vcpu->arch.guestdbg.hw_wp_info = wp_info; + return 0; +error: + kfree(bp_data); + kfree(wp_info); + kfree(bp_info); + return ret; +} + +void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_hw_wp_info_arch *hw_wp_info = NULL; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) { + hw_wp_info = &vcpu->arch.guestdbg.hw_wp_info[i]; + kfree(hw_wp_info->old_data); + hw_wp_info->old_data = NULL; + } + kfree(vcpu->arch.guestdbg.hw_wp_info); + vcpu->arch.guestdbg.hw_wp_info = NULL; + + kfree(vcpu->arch.guestdbg.hw_bp_info); + vcpu->arch.guestdbg.hw_bp_info = NULL; + + vcpu->arch.guestdbg.nr_hw_wp = 0; + vcpu->arch.guestdbg.nr_hw_bp = 0; +} + +static inline int in_addr_range(u64 addr, u64 a, u64 b) +{ + if (a <= b) + return (addr >= a) && (addr <= b); + else + /* "overflowing" interval */ + return (addr <= a) && (addr >= b); +} + +#define end_of_range(bp_info) (bp_info->addr + bp_info->len - 1) + +static struct kvm_hw_bp_info_arch *find_hw_bp(struct kvm_vcpu *vcpu, + unsigned long addr) +{ + struct kvm_hw_bp_info_arch *bp_info = vcpu->arch.guestdbg.hw_bp_info; + int i; + + if (vcpu->arch.guestdbg.nr_hw_bp == 0) + return NULL; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_bp; i++) { + /* addr is directly the start or in the range of a bp */ + if (addr == bp_info->addr) + goto found; + if (bp_info->len > 0 && + in_addr_range(addr, bp_info->addr, end_of_range(bp_info))) + goto found; + + bp_info++; + } + + return NULL; +found: + return bp_info; +} + +static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_hw_wp_info_arch *wp_info = NULL; + void *temp = NULL; + + if (vcpu->arch.guestdbg.nr_hw_wp == 0) + return NULL; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) { + wp_info = &vcpu->arch.guestdbg.hw_wp_info[i]; + if (!wp_info || !wp_info->old_data || wp_info->len <= 0) + continue; + + temp = kmalloc(wp_info->len, GFP_KERNEL); + if (!temp) + continue; + + /* refetch the wp data and compare it to the old value */ + if (!read_guest(vcpu, wp_info->phys_addr, temp, + wp_info->len)) { + if (memcmp(temp, wp_info->old_data, wp_info->len)) { + kfree(temp); + return wp_info; + } + } + kfree(temp); + temp = NULL; + } + + return NULL; +} + +void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu) +{ + vcpu->run->exit_reason = KVM_EXIT_DEBUG; + vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING; +} + +#define per_bp_event(code) \ + (code & (PER_EVENT_IFETCH | PER_EVENT_BRANCH)) +#define per_write_wp_event(code) \ + (code & (PER_EVENT_STORE | PER_EVENT_STORE_REAL)) + +static int debug_exit_required(struct kvm_vcpu *vcpu) +{ + u32 perc = (vcpu->arch.sie_block->perc << 24); + struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch; + struct kvm_hw_wp_info_arch *wp_info = NULL; + struct kvm_hw_bp_info_arch *bp_info = NULL; + unsigned long addr = vcpu->arch.sie_block->gpsw.addr; + unsigned long peraddr = vcpu->arch.sie_block->peraddr; + + if (guestdbg_hw_bp_enabled(vcpu)) { + if (per_write_wp_event(perc) && + vcpu->arch.guestdbg.nr_hw_wp > 0) { + wp_info = any_wp_changed(vcpu); + if (wp_info) { + debug_exit->addr = wp_info->addr; + debug_exit->type = KVM_HW_WP_WRITE; + goto exit_required; + } + } + if (per_bp_event(perc) && + vcpu->arch.guestdbg.nr_hw_bp > 0) { + bp_info = find_hw_bp(vcpu, addr); + /* remove duplicate events if PC==PER address */ + if (bp_info && (addr != peraddr)) { + debug_exit->addr = addr; + debug_exit->type = KVM_HW_BP; + vcpu->arch.guestdbg.last_bp = addr; + goto exit_required; + } + /* breakpoint missed */ + bp_info = find_hw_bp(vcpu, peraddr); + if (bp_info && vcpu->arch.guestdbg.last_bp != peraddr) { + debug_exit->addr = peraddr; + debug_exit->type = KVM_HW_BP; + goto exit_required; + } + } + } + if (guestdbg_sstep_enabled(vcpu) && per_bp_event(perc)) { + debug_exit->addr = addr; + debug_exit->type = KVM_SINGLESTEP; + goto exit_required; + } + + return 0; +exit_required: + return 1; +} + +#define guest_per_enabled(vcpu) \ + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) + +static void filter_guest_per_event(struct kvm_vcpu *vcpu) +{ + u32 perc = vcpu->arch.sie_block->perc << 24; + u64 peraddr = vcpu->arch.sie_block->peraddr; + u64 addr = vcpu->arch.sie_block->gpsw.addr; + u64 cr9 = vcpu->arch.sie_block->gcr[9]; + u64 cr10 = vcpu->arch.sie_block->gcr[10]; + u64 cr11 = vcpu->arch.sie_block->gcr[11]; + /* filter all events, demanded by the guest */ + u32 guest_perc = perc & cr9 & PER_EVENT_MASK; + + if (!guest_per_enabled(vcpu)) + guest_perc = 0; + + /* filter "successful-branching" events */ + if (guest_perc & PER_EVENT_BRANCH && + cr9 & PER_CONTROL_BRANCH_ADDRESS && + !in_addr_range(addr, cr10, cr11)) + guest_perc &= ~PER_EVENT_BRANCH; + + /* filter "instruction-fetching" events */ + if (guest_perc & PER_EVENT_IFETCH && + !in_addr_range(peraddr, cr10, cr11)) + guest_perc &= ~PER_EVENT_IFETCH; + + /* All other PER events will be given to the guest */ + /* TODO: Check alterated address/address space */ + + vcpu->arch.sie_block->perc = guest_perc >> 24; + + if (!guest_perc) + vcpu->arch.sie_block->iprcc &= ~PGM_PER; +} + +void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu) +{ + if (debug_exit_required(vcpu)) + vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING; + + filter_guest_per_event(vcpu); +} diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 22798ec33fd..a0b586c1913 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -1,7 +1,7 @@ /* * in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008, 2009 + * 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) @@ -16,102 +16,26 @@ #include <linux/pagemap.h> #include <asm/kvm_host.h> +#include <asm/asm-offsets.h> +#include <asm/irq.h> #include "kvm-s390.h" #include "gaccess.h" #include "trace.h" #include "trace-s390.h" -static int handle_lctlg(struct kvm_vcpu *vcpu) -{ - int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; - int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + - ((vcpu->arch.sie_block->ipb & 0xff00) << 4); - u64 useraddr; - int reg, rc; - - vcpu->stat.instruction_lctlg++; - if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f) - return -EOPNOTSUPP; - - useraddr = disp2; - if (base2) - useraddr += vcpu->run->s.regs.gprs[base2]; - - if (useraddr & 7) - return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - - reg = reg1; - - VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, - disp2); - trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr); - - do { - rc = get_guest_u64(vcpu, useraddr, - &vcpu->arch.sie_block->gcr[reg]); - if (rc == -EFAULT) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - break; - } - useraddr += 8; - if (reg == reg3) - break; - reg = (reg + 1) % 16; - } while (1); - return 0; -} - -static int handle_lctl(struct kvm_vcpu *vcpu) -{ - int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; - int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); - u64 useraddr; - u32 val = 0; - int reg, rc; - - vcpu->stat.instruction_lctl++; - - useraddr = disp2; - if (base2) - useraddr += vcpu->run->s.regs.gprs[base2]; - - if (useraddr & 3) - return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - - VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, - disp2); - trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr); - - reg = reg1; - do { - rc = get_guest_u32(vcpu, useraddr, &val); - if (rc == -EFAULT) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - break; - } - vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; - vcpu->arch.sie_block->gcr[reg] |= val; - useraddr += 4; - if (reg == reg3) - break; - reg = (reg + 1) % 16; - } while (1); - return 0; -} -static intercept_handler_t instruction_handlers[256] = { +static const intercept_handler_t instruction_handlers[256] = { [0x01] = kvm_s390_handle_01, + [0x82] = kvm_s390_handle_lpsw, [0x83] = kvm_s390_handle_diag, [0xae] = kvm_s390_handle_sigp, [0xb2] = kvm_s390_handle_b2, - [0xb7] = handle_lctl, + [0xb6] = kvm_s390_handle_stctl, + [0xb7] = kvm_s390_handle_lctl, + [0xb9] = kvm_s390_handle_b9, [0xe5] = kvm_s390_handle_e5, - [0xeb] = handle_lctlg, + [0xeb] = kvm_s390_handle_eb, }; static int handle_noop(struct kvm_vcpu *vcpu) @@ -123,9 +47,6 @@ static int handle_noop(struct kvm_vcpu *vcpu) case 0x10: vcpu->stat.exit_external_request++; break; - case 0x14: - vcpu->stat.exit_external_interrupt++; - break; default: break; /* nothing */ } @@ -141,15 +62,8 @@ static int handle_stop(struct kvm_vcpu *vcpu) trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits); - if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) { - vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP; - rc = SIE_INTERCEPT_RERUNVCPU; - vcpu->run->exit_reason = KVM_EXIT_INTR; - } - if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) { - atomic_set_mask(CPUSTAT_STOPPED, - &vcpu->arch.sie_block->cpuflags); + kvm_s390_vcpu_stop(vcpu); vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP; VCPU_EVENT(vcpu, 3, "%s", "cpu stopped"); rc = -EOPNOTSUPP; @@ -172,47 +86,12 @@ static int handle_stop(struct kvm_vcpu *vcpu) static int handle_validity(struct kvm_vcpu *vcpu) { - unsigned long vmaddr; int viwhy = vcpu->arch.sie_block->ipb >> 16; - int rc; vcpu->stat.exit_validity++; trace_kvm_s390_intercept_validity(vcpu, viwhy); - if (viwhy == 0x37) { - vmaddr = gmap_fault(vcpu->arch.sie_block->prefix, - vcpu->arch.gmap); - if (IS_ERR_VALUE(vmaddr)) { - rc = -EOPNOTSUPP; - goto out; - } - rc = fault_in_pages_writeable((char __user *) vmaddr, - PAGE_SIZE); - if (rc) { - /* user will receive sigsegv, exit to user */ - rc = -EOPNOTSUPP; - goto out; - } - vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE, - vcpu->arch.gmap); - if (IS_ERR_VALUE(vmaddr)) { - rc = -EOPNOTSUPP; - goto out; - } - rc = fault_in_pages_writeable((char __user *) vmaddr, - PAGE_SIZE); - if (rc) { - /* user will receive sigsegv, exit to user */ - rc = -EOPNOTSUPP; - goto out; - } - } else - rc = -EOPNOTSUPP; - -out: - if (rc) - VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", - viwhy); - return rc; + WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy); + return -EOPNOTSUPP; } static int handle_instruction(struct kvm_vcpu *vcpu) @@ -229,11 +108,120 @@ static int handle_instruction(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } +static void __extract_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info) +{ + memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info)); + pgm_info->code = vcpu->arch.sie_block->iprcc; + + switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) { + case PGM_AFX_TRANSLATION: + case PGM_ASX_TRANSLATION: + case PGM_EX_TRANSLATION: + case PGM_LFX_TRANSLATION: + case PGM_LSTE_SEQUENCE: + case PGM_LSX_TRANSLATION: + case PGM_LX_TRANSLATION: + case PGM_PRIMARY_AUTHORITY: + case PGM_SECONDARY_AUTHORITY: + case PGM_SPACE_SWITCH: + pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + break; + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_INSTANCE: + case PGM_ASTE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_EXTENDED_AUTHORITY: + pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + break; + case PGM_ASCE_TYPE: + case PGM_PAGE_TRANSLATION: + case PGM_REGION_FIRST_TRANS: + case PGM_REGION_SECOND_TRANS: + case PGM_REGION_THIRD_TRANS: + case PGM_SEGMENT_TRANSLATION: + pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + pgm_info->op_access_id = vcpu->arch.sie_block->oai; + break; + case PGM_MONITOR: + pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn; + pgm_info->mon_code = vcpu->arch.sie_block->tecmc; + break; + case PGM_DATA: + pgm_info->data_exc_code = vcpu->arch.sie_block->dxc; + break; + case PGM_PROTECTION: + pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + break; + default: + break; + } + + if (vcpu->arch.sie_block->iprcc & PGM_PER) { + pgm_info->per_code = vcpu->arch.sie_block->perc; + pgm_info->per_atmid = vcpu->arch.sie_block->peratmid; + pgm_info->per_address = vcpu->arch.sie_block->peraddr; + pgm_info->per_access_id = vcpu->arch.sie_block->peraid; + } +} + +/* + * restore ITDB to program-interruption TDB in guest lowcore + * and set TX abort indication if required +*/ +static int handle_itdb(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_itdb *itdb; + int rc; + + if (!IS_TE_ENABLED(vcpu) || !IS_ITDB_VALID(vcpu)) + return 0; + if (current->thread.per_flags & PER_FLAG_NO_TE) + return 0; + itdb = (struct kvm_s390_itdb *)vcpu->arch.sie_block->itdba; + rc = write_guest_lc(vcpu, __LC_PGM_TDB, itdb, sizeof(*itdb)); + if (rc) + return rc; + memset(itdb, 0, sizeof(*itdb)); + + return 0; +} + +#define per_event(vcpu) (vcpu->arch.sie_block->iprcc & PGM_PER) + static int handle_prog(struct kvm_vcpu *vcpu) { + struct kvm_s390_pgm_info pgm_info; + psw_t psw; + int rc; + vcpu->stat.exit_program_interruption++; + + if (guestdbg_enabled(vcpu) && per_event(vcpu)) { + kvm_s390_handle_per_event(vcpu); + /* the interrupt might have been filtered out completely */ + if (vcpu->arch.sie_block->iprcc == 0) + return 0; + } + trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc); - return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc); + if (vcpu->arch.sie_block->iprcc == PGM_SPECIFICATION) { + rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &psw, sizeof(psw_t)); + if (rc) + return rc; + /* Avoid endless loops of specification exceptions */ + if (!is_valid_psw(&psw)) + return -EOPNOTSUPP; + } + rc = handle_itdb(vcpu); + if (rc) + return rc; + + __extract_prog_irq(vcpu, &pgm_info); + return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } static int handle_instruction_and_prog(struct kvm_vcpu *vcpu) @@ -251,16 +239,110 @@ static int handle_instruction_and_prog(struct kvm_vcpu *vcpu) return rc2; } +/** + * handle_external_interrupt - used for external interruption interceptions + * + * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if + * the new PSW does not have external interrupts disabled. In the first case, + * we've got to deliver the interrupt manually, and in the second case, we + * drop to userspace to handle the situation there. + */ +static int handle_external_interrupt(struct kvm_vcpu *vcpu) +{ + u16 eic = vcpu->arch.sie_block->eic; + struct kvm_s390_interrupt irq; + psw_t newpsw; + int rc; + + vcpu->stat.exit_external_interrupt++; + + rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t)); + if (rc) + return rc; + /* We can not handle clock comparator or timer interrupt with bad PSW */ + if ((eic == EXT_IRQ_CLK_COMP || eic == EXT_IRQ_CPU_TIMER) && + (newpsw.mask & PSW_MASK_EXT)) + return -EOPNOTSUPP; + + switch (eic) { + case EXT_IRQ_CLK_COMP: + irq.type = KVM_S390_INT_CLOCK_COMP; + break; + case EXT_IRQ_CPU_TIMER: + irq.type = KVM_S390_INT_CPU_TIMER; + break; + case EXT_IRQ_EXTERNAL_CALL: + if (kvm_s390_si_ext_call_pending(vcpu)) + return 0; + irq.type = KVM_S390_INT_EXTERNAL_CALL; + irq.parm = vcpu->arch.sie_block->extcpuaddr; + break; + default: + return -EOPNOTSUPP; + } + + return kvm_s390_inject_vcpu(vcpu, &irq); +} + +/** + * Handle MOVE PAGE partial execution interception. + * + * This interception can only happen for guests with DAT disabled and + * addresses that are currently not mapped in the host. Thus we try to + * set up the mappings for the corresponding user pages here (or throw + * addressing exceptions in case of illegal guest addresses). + */ +static int handle_mvpg_pei(struct kvm_vcpu *vcpu) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + unsigned long srcaddr, dstaddr; + int reg1, reg2, rc; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + /* Make sure that the source is paged-in */ + srcaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg2]); + if (kvm_is_error_gpa(vcpu->kvm, srcaddr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0); + if (rc != 0) + return rc; + + /* Make sure that the destination is paged-in */ + dstaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg1]); + if (kvm_is_error_gpa(vcpu->kvm, dstaddr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); + if (rc != 0) + return rc; + + psw->addr = __rewind_psw(*psw, 4); + + return 0; +} + +static int handle_partial_execution(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->ipa == 0xb254) /* MVPG */ + return handle_mvpg_pei(vcpu); + if (vcpu->arch.sie_block->ipa >> 8 == 0xae) /* SIGP */ + return kvm_s390_handle_sigp_pei(vcpu); + + return -EOPNOTSUPP; +} + static const intercept_handler_t intercept_funcs[] = { [0x00 >> 2] = handle_noop, [0x04 >> 2] = handle_instruction, [0x08 >> 2] = handle_prog, [0x0C >> 2] = handle_instruction_and_prog, [0x10 >> 2] = handle_noop, - [0x14 >> 2] = handle_noop, + [0x14 >> 2] = handle_external_interrupt, + [0x18 >> 2] = handle_noop, [0x1C >> 2] = kvm_s390_handle_wait, [0x20 >> 2] = handle_validity, [0x28 >> 2] = handle_stop, + [0x38 >> 2] = handle_partial_execution, }; int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 82c481ddef7..90c8de22a2a 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> @@ -21,11 +22,33 @@ #include "gaccess.h" #include "trace-s390.h" -static int psw_extint_disabled(struct kvm_vcpu *vcpu) +#define IOINT_SCHID_MASK 0x0000ffff +#define IOINT_SSID_MASK 0x00030000 +#define IOINT_CSSID_MASK 0x03fc0000 +#define IOINT_AI_MASK 0x04000000 + +static void deliver_ckc_interrupt(struct kvm_vcpu *vcpu); + +static int is_ioint(u64 type) +{ + return ((type & 0xfffe0000u) != 0xfffe0000u); +} + +int psw_extint_disabled(struct kvm_vcpu *vcpu) { return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); } +static int psw_ioint_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO); +} + +static int psw_mchk_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK); +} + static int psw_interrupts_disabled(struct kvm_vcpu *vcpu) { if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) || @@ -35,6 +58,24 @@ static int psw_interrupts_disabled(struct kvm_vcpu *vcpu) return 1; } +static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) +{ + if (psw_extint_disabled(vcpu) || + !(vcpu->arch.sie_block->gcr[0] & 0x800ul)) + return 0; + if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu)) + /* No timer interrupts when single stepping */ + return 0; + return 1; +} + +static u64 int_word_to_isc_bits(u32 int_word) +{ + u8 isc = (int_word & 0x38000000) >> 27; + + return (0x80 >> isc) << 24; +} + static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { @@ -50,12 +91,17 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, if (vcpu->arch.sie_block->gcr[0] & 0x4000ul) return 1; return 0; - case KVM_S390_INT_SERVICE: + case KVM_S390_INT_CLOCK_COMP: + return ckc_interrupts_enabled(vcpu); + case KVM_S390_INT_CPU_TIMER: if (psw_extint_disabled(vcpu)) return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x200ul) + if (vcpu->arch.sie_block->gcr[0] & 0x400ul) return 1; return 0; + 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)) return 0; @@ -67,7 +113,22 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, case KVM_S390_SIGP_SET_PREFIX: case KVM_S390_RESTART: return 1; + case KVM_S390_MCHK: + if (psw_mchk_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14) + return 1; + return 0; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + if (psw_ioint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[6] & + int_word_to_isc_bits(inti->io.io_int_word)) + return 1; + return 0; default: + printk(KERN_WARNING "illegal interrupt type %llx\n", + inti->type); BUG(); } return 0; @@ -75,24 +136,28 @@ 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); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) { - atomic_clear_mask(CPUSTAT_ECALL_PEND | - CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT, - &vcpu->arch.sie_block->cpuflags); + atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT, + &vcpu->arch.sie_block->cpuflags); vcpu->arch.sie_block->lctl = 0x0000; + vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT); + + if (guestdbg_enabled(vcpu)) { + vcpu->arch.sie_block->lctl |= (LCTL_CR0 | LCTL_CR9 | + LCTL_CR10 | LCTL_CR11); + vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT); + } } static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) @@ -107,7 +172,11 @@ 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: + case KVM_S390_INT_CLOCK_COMP: + case KVM_S390_INT_CPU_TIMER: if (psw_extint_disabled(vcpu)) __set_cpuflag(vcpu, CPUSTAT_EXT_INT); else @@ -116,16 +185,128 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu, case KVM_S390_SIGP_STOP: __set_cpuflag(vcpu, CPUSTAT_STOP_INT); break; + case KVM_S390_MCHK: + if (psw_mchk_disabled(vcpu)) + vcpu->arch.sie_block->ictl |= ICTL_LPSW; + else + vcpu->arch.sie_block->lctl |= LCTL_CR14; + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + if (psw_ioint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_IO_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR6; + break; default: BUG(); } } +static int __deliver_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info) +{ + const unsigned short table[] = { 2, 4, 4, 6 }; + int rc = 0; + + switch (pgm_info->code & ~PGM_PER) { + case PGM_AFX_TRANSLATION: + case PGM_ASX_TRANSLATION: + case PGM_EX_TRANSLATION: + case PGM_LFX_TRANSLATION: + case PGM_LSTE_SEQUENCE: + case PGM_LSX_TRANSLATION: + case PGM_LX_TRANSLATION: + case PGM_PRIMARY_AUTHORITY: + case PGM_SECONDARY_AUTHORITY: + case PGM_SPACE_SWITCH: + rc = put_guest_lc(vcpu, pgm_info->trans_exc_code, + (u64 *)__LC_TRANS_EXC_CODE); + break; + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_INSTANCE: + case PGM_ASTE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_EXTENDED_AUTHORITY: + rc = put_guest_lc(vcpu, pgm_info->exc_access_id, + (u8 *)__LC_EXC_ACCESS_ID); + break; + case PGM_ASCE_TYPE: + case PGM_PAGE_TRANSLATION: + case PGM_REGION_FIRST_TRANS: + case PGM_REGION_SECOND_TRANS: + case PGM_REGION_THIRD_TRANS: + case PGM_SEGMENT_TRANSLATION: + rc = put_guest_lc(vcpu, pgm_info->trans_exc_code, + (u64 *)__LC_TRANS_EXC_CODE); + rc |= put_guest_lc(vcpu, pgm_info->exc_access_id, + (u8 *)__LC_EXC_ACCESS_ID); + rc |= put_guest_lc(vcpu, pgm_info->op_access_id, + (u8 *)__LC_OP_ACCESS_ID); + break; + case PGM_MONITOR: + rc = put_guest_lc(vcpu, pgm_info->mon_class_nr, + (u64 *)__LC_MON_CLASS_NR); + rc |= put_guest_lc(vcpu, pgm_info->mon_code, + (u64 *)__LC_MON_CODE); + break; + case PGM_DATA: + rc = put_guest_lc(vcpu, pgm_info->data_exc_code, + (u32 *)__LC_DATA_EXC_CODE); + break; + case PGM_PROTECTION: + rc = put_guest_lc(vcpu, pgm_info->trans_exc_code, + (u64 *)__LC_TRANS_EXC_CODE); + rc |= put_guest_lc(vcpu, pgm_info->exc_access_id, + (u8 *)__LC_EXC_ACCESS_ID); + break; + } + + if (pgm_info->code & PGM_PER) { + rc |= put_guest_lc(vcpu, pgm_info->per_code, + (u8 *) __LC_PER_CODE); + rc |= put_guest_lc(vcpu, pgm_info->per_atmid, + (u8 *)__LC_PER_ATMID); + rc |= put_guest_lc(vcpu, pgm_info->per_address, + (u64 *) __LC_PER_ADDRESS); + rc |= put_guest_lc(vcpu, pgm_info->per_access_id, + (u8 *) __LC_PER_ACCESS_ID); + } + + switch (vcpu->arch.sie_block->icptcode) { + case ICPT_INST: + case ICPT_INSTPROGI: + case ICPT_OPEREXC: + case ICPT_PARTEXEC: + case ICPT_IOINST: + /* last instruction only stored for these icptcodes */ + rc |= put_guest_lc(vcpu, table[vcpu->arch.sie_block->ipa >> 14], + (u16 *) __LC_PGM_ILC); + break; + case ICPT_PROGI: + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->pgmilc, + (u16 *) __LC_PGM_ILC); + break; + default: + rc |= put_guest_lc(vcpu, 0, + (u16 *) __LC_PGM_ILC); + } + + rc |= put_guest_lc(vcpu, pgm_info->code, + (u16 *)__LC_PGM_INT_CODE); + rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + + return rc; +} + static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { const unsigned short table[] = { 2, 4, 4, 6 }; - int rc, exception = 0; + int rc = 0; switch (inti->type) { case KVM_S390_INT_EMERGENCY: @@ -133,74 +314,87 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, vcpu->stat.deliver_emergency_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, inti->emerg.code, 0); - rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1201); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u16(vcpu, __LC_EXT_CPU_ADDR, inti->emerg.code); - if (rc == -EFAULT) - exception = 1; - - rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - __LC_EXT_NEW_PSW, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; + rc = put_guest_lc(vcpu, 0x1201, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, inti->emerg.code, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); break; - case KVM_S390_INT_EXTERNAL_CALL: VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call"); vcpu->stat.deliver_external_call++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, inti->extcall.code, 0); - rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1202); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u16(vcpu, __LC_EXT_CPU_ADDR, inti->extcall.code); - if (rc == -EFAULT) - exception = 1; - - rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - __LC_EXT_NEW_PSW, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; + rc = put_guest_lc(vcpu, 0x1202, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, inti->extcall.code, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + break; + case KVM_S390_INT_CLOCK_COMP: + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + inti->ext.ext_params, 0); + deliver_ckc_interrupt(vcpu); + break; + case KVM_S390_INT_CPU_TIMER: + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + inti->ext.ext_params, 0); + rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, + (u16 *)__LC_EXT_INT_CODE); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); break; - case KVM_S390_INT_SERVICE: VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", inti->ext.ext_params); vcpu->stat.deliver_service_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, inti->ext.ext_params, 0); - rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2401); - if (rc == -EFAULT) - exception = 1; - - rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - __LC_EXT_NEW_PSW, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params); - if (rc == -EFAULT) - exception = 1; + rc = put_guest_lc(vcpu, 0x2401, (u16 *)__LC_EXT_INT_CODE); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__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_lc(vcpu, 0x2603, (u16 *) __LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0x0600, (u16 *) __LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *) __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_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0x0680, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__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); @@ -208,34 +402,18 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, inti->ext.ext_params, inti->ext.ext_params2); - rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2603); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u16(vcpu, __LC_EXT_CPU_ADDR, 0x0d00); - if (rc == -EFAULT) - exception = 1; - - rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - __LC_EXT_NEW_PSW, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u64(vcpu, __LC_EXT_PARAMS2, - inti->ext.ext_params2); - if (rc == -EFAULT) - exception = 1; + rc = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0x0d00, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); break; - case KVM_S390_SIGP_STOP: VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop"); vcpu->stat.deliver_stop_signal++; @@ -258,18 +436,13 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, vcpu->stat.deliver_restart_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0, 0); - rc = copy_to_guest(vcpu, offsetof(struct _lowcore, - restart_old_psw), &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - offsetof(struct _lowcore, restart_psw), sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + rc = write_guest_lc(vcpu, + offsetof(struct _lowcore, restart_old_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw), + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); break; - case KVM_S390_PROGRAM_INT: VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x", inti->pgm.code, @@ -277,64 +450,93 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, vcpu->stat.deliver_program_int++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, inti->pgm.code, 0); - rc = put_guest_u16(vcpu, __LC_PGM_INT_CODE, inti->pgm.code); - if (rc == -EFAULT) - exception = 1; - - rc = put_guest_u16(vcpu, __LC_PGM_ILC, - table[vcpu->arch.sie_block->ipa >> 14]); - if (rc == -EFAULT) - exception = 1; - - rc = copy_to_guest(vcpu, __LC_PGM_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; + rc = __deliver_prog_irq(vcpu, &inti->pgm); + break; - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - __LC_PGM_NEW_PSW, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; + case KVM_S390_MCHK: + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + inti->mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + inti->mchk.cr14, + inti->mchk.mcic); + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_PREFIXED); + rc |= put_guest_lc(vcpu, inti->mchk.mcic, (u64 *)__LC_MCCK_CODE); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + { + __u32 param0 = ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr; + __u64 param1 = ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word; + VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + param0, param1); + rc = put_guest_lc(vcpu, inti->io.subchannel_id, + (u16 *)__LC_SUBCHANNEL_ID); + rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, + (u16 *)__LC_SUBCHANNEL_NR); + rc |= put_guest_lc(vcpu, inti->io.io_int_parm, + (u32 *)__LC_IO_INT_PARM); + rc |= put_guest_lc(vcpu, inti->io.io_int_word, + (u32 *)__LC_IO_INT_WORD); + rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + break; + } default: BUG(); } - if (exception) { + if (rc) { printk("kvm: The guest lowcore is not mapped during interrupt " - "delivery, killing userspace\n"); + "delivery, killing userspace\n"); do_exit(SIGKILL); } } -static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu) +static void deliver_ckc_interrupt(struct kvm_vcpu *vcpu) { - int rc, exception = 0; - - if (psw_extint_disabled(vcpu)) - return 0; - if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul)) - return 0; - rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1004); - if (rc == -EFAULT) - exception = 1; - rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, - __LC_EXT_NEW_PSW, sizeof(psw_t)); - if (rc == -EFAULT) - exception = 1; - if (exception) { + int rc; + + rc = put_guest_lc(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + if (rc) { printk("kvm: The guest lowcore is not mapped during interrupt " "delivery, killing userspace\n"); do_exit(SIGKILL); } - return 1; } -static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) +/* Check whether SIGP interpretation facility has an external call pending */ +int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu) +{ + atomic_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl; + + if (!psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x2000ul) && + (atomic_read(sigp_ctrl) & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND)) + return 1; + + return 0; +} + +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; @@ -361,19 +563,23 @@ static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) spin_unlock(&fi->lock); } - if ((!rc) && (vcpu->arch.sie_block->ckc < - get_clock() + vcpu->arch.sie_block->epoch)) { - if ((!psw_extint_disabled(vcpu)) && - (vcpu->arch.sie_block->gcr[0] & 0x800ul)) - rc = 1; - } + if (!rc && kvm_cpu_has_pending_timer(vcpu)) + rc = 1; + + if (!rc && kvm_s390_si_ext_call_pending(vcpu)) + rc = 1; return rc; } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return 0; + if (!(vcpu->arch.sie_block->ckc < + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) + return 0; + if (!ckc_interrupts_enabled(vcpu)) + return 0; + return 1; } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) @@ -396,13 +602,12 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; /* disabled wait */ } - if (psw_extint_disabled(vcpu) || - (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) { + if (!ckc_interrupts_enabled(vcpu)) { VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer"); goto no_timer; } - now = get_clock() + vcpu->arch.sie_block->epoch; + now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch; if (vcpu->arch.sie_block->ckc < now) { __unset_cpu_idle(vcpu); return 0; @@ -413,13 +618,15 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); no_timer: + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); spin_lock(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); - add_wait_queue(&vcpu->arch.local_int.wq, &wait); + add_wait_queue(&vcpu->wq, &wait); while (list_empty(&vcpu->arch.local_int.list) && list_empty(&vcpu->arch.local_int.float_int->list) && (!vcpu->arch.local_int.timer_due) && - !signal_pending(current)) { + !signal_pending(current) && + !kvm_s390_si_ext_call_pending(vcpu)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_bh(&vcpu->arch.local_int.lock); spin_unlock(&vcpu->arch.local_int.float_int->lock); @@ -429,9 +636,11 @@ no_timer: } __unset_cpu_idle(vcpu); __set_current_state(TASK_RUNNING); - remove_wait_queue(&vcpu->arch.local_int.wq, &wait); + remove_wait_queue(&vcpu->wq, &wait); spin_unlock_bh(&vcpu->arch.local_int.lock); spin_unlock(&vcpu->arch.local_int.float_int->lock); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); return 0; } @@ -442,8 +651,8 @@ void kvm_s390_tasklet(unsigned long parm) spin_lock(&vcpu->arch.local_int.lock); vcpu->arch.local_int.timer_due = 1; - if (waitqueue_active(&vcpu->arch.local_int.wq)) - wake_up_interruptible(&vcpu->arch.local_int.wq); + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); spin_unlock(&vcpu->arch.local_int.lock); } @@ -456,11 +665,31 @@ 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); + + /* clear pending external calls set by sigp interpretation facility */ + atomic_clear_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); + atomic_clear_mask(SIGP_CTRL_C, + &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl); +} + void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -491,9 +720,8 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } while (deliver); } - if ((vcpu->arch.sie_block->ckc < - get_clock() + vcpu->arch.sie_block->epoch)) - __try_deliver_ckc_interrupt(vcpu); + if (kvm_cpu_has_pending_timer(vcpu)) + deliver_ckc_interrupt(vcpu); if (atomic_read(&fi->active)) { do { @@ -502,6 +730,63 @@ 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; + } + __set_intercept_indicator(vcpu, inti); + } + if (list_empty(&fi->list)) + atomic_set(&fi->active, 0); + spin_unlock(&fi->lock); + if (deliver) { + __do_deliver_interrupt(vcpu, inti); + kfree(inti); + } + } while (deliver); + } +} + +void kvm_s390_deliver_pending_machine_checks(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; + struct kvm_s390_interrupt_info *n, *inti = NULL; + int deliver; + + __reset_intercept_indicators(vcpu); + if (atomic_read(&li->active)) { + do { + deliver = 0; + spin_lock_bh(&li->lock); + list_for_each_entry_safe(inti, n, &li->list, list) { + if ((inti->type == KVM_S390_MCHK) && + __interrupt_is_deliverable(vcpu, inti)) { + list_del(&inti->list); + deliver = 1; + break; + } + __set_intercept_indicator(vcpu, inti); + } + if (list_empty(&li->list)) + atomic_set(&li->active, 0); + spin_unlock_bh(&li->lock); + if (deliver) { + __do_deliver_interrupt(vcpu, inti); + kfree(inti); + } + } while (deliver); + } + + if (atomic_read(&fi->active)) { + do { + deliver = 0; + spin_lock(&fi->lock); + list_for_each_entry_safe(inti, n, &fi->list, list) { + if ((inti->type == KVM_S390_MCHK) && + __interrupt_is_deliverable(vcpu, inti)) { + list_del(&inti->list); + fi->irq_count--; deliver = 1; break; } @@ -535,51 +820,109 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) spin_lock_bh(&li->lock); list_add(&inti->list, &li->list); atomic_set(&li->active, 1); - BUG_ON(waitqueue_active(&li->wq)); + BUG_ON(waitqueue_active(li->wq)); spin_unlock_bh(&li->lock); return 0; } -int kvm_s390_inject_vm(struct kvm *kvm, - struct kvm_s390_interrupt *s390int) +int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info) { - struct kvm_s390_local_interrupt *li; - struct kvm_s390_float_interrupt *fi; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_interrupt_info *inti; - int sigcpu; inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) return -ENOMEM; - switch (s390int->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; + VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)", + pgm_info->code); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, + pgm_info->code, 0, 1); + + inti->type = KVM_S390_PROGRAM_INT; + memcpy(&inti->pgm, pgm_info, sizeof(inti->pgm)); + spin_lock_bh(&li->lock); + list_add(&inti->list, &li->list); + atomic_set(&li->active, 1); + BUG_ON(waitqueue_active(li->wq)); + spin_unlock_bh(&li->lock); + return 0; +} + +struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, + u64 cr6, u64 schid) +{ + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_interrupt_info *inti, *iter; + + if ((!schid && !cr6) || (schid && cr6)) + return NULL; + mutex_lock(&kvm->lock); + fi = &kvm->arch.float_int; + spin_lock(&fi->lock); + inti = NULL; + list_for_each_entry(iter, &fi->list, list) { + if (!is_ioint(iter->type)) + continue; + if (cr6 && + ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0)) + continue; + if (schid) { + if (((schid & 0x00000000ffff0000) >> 16) != + iter->io.subchannel_id) + continue; + if ((schid & 0x000000000000ffff) != + iter->io.subchannel_nr) + continue; + } + inti = iter; break; - case KVM_S390_PROGRAM_INT: - case KVM_S390_SIGP_STOP: - case KVM_S390_INT_EXTERNAL_CALL: - case KVM_S390_INT_EMERGENCY: - default: - kfree(inti); - return -EINVAL; } - trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64, - 2); + if (inti) { + list_del_init(&inti->list); + fi->irq_count--; + } + if (list_empty(&fi->list)) + atomic_set(&fi->active, 0); + spin_unlock(&fi->lock); + mutex_unlock(&kvm->lock); + return inti; +} + +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 *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); - list_add_tail(&inti->list, &fi->list); + 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) { @@ -587,17 +930,80 @@ int kvm_s390_inject_vm(struct kvm *kvm, sigcpu = fi->next_rr_cpu++; if (sigcpu == KVM_MAX_VCPUS) sigcpu = fi->next_rr_cpu = 0; - } while (fi->local_int[sigcpu] == NULL); + } while (kvm_get_vcpu(kvm, sigcpu) == NULL); } - li = fi->local_int[sigcpu]; + 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); + 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 0; + 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; + + 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->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->ext.ext_params = s390int->parm; + break; + 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->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 (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->io.subchannel_id = s390int->parm >> 16; + inti->io.subchannel_nr = s390int->parm & 0x0000ffffu; + inti->io.io_int_parm = s390int->parm64 >> 32; + inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull; + break; + default: + kfree(inti); + return -EINVAL; + } + trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64, + 2); + + return __inject_vm(kvm, inti); +} + +void kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + __inject_vm(kvm, inti); } int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, @@ -629,6 +1035,8 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, break; case KVM_S390_SIGP_STOP: case KVM_S390_RESTART: + case KVM_S390_INT_CLOCK_COMP: + case KVM_S390_INT_CPU_TIMER: VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type); inti->type = s390int->type; break; @@ -651,8 +1059,19 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, inti->type = s390int->type; inti->emerg.code = s390int->parm; break; + case KVM_S390_MCHK: + VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx", + s390int->parm64); + 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: default: kfree(inti); return -EINVAL; @@ -671,9 +1090,530 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, if (inti->type == KVM_S390_SIGP_STOP) li->action_bits |= ACTION_STOP_ON_STOP; atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&vcpu->arch.local_int.wq); + 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; } + +void kvm_s390_clear_float_irqs(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; + kvm_s390_clear_float_irqs(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 f090e819bf7..2f3e14fe91a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -11,6 +11,7 @@ * Christian Borntraeger <borntraeger@de.ibm.com> * Heiko Carstens <heiko.carstens@de.ibm.com> * Christian Ehrhardt <ehrhardt@de.ibm.com> + * Jason J. Herne <jjherne@us.ibm.com> */ #include <linux/compiler.h> @@ -28,6 +29,7 @@ #include <asm/pgtable.h> #include <asm/nmi.h> #include <asm/switch_to.h> +#include <asm/facility.h> #include <asm/sclp.h> #include "kvm-s390.h" #include "gaccess.h" @@ -50,6 +52,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, { "instruction_lctl", VCPU_STAT(instruction_lctl) }, + { "instruction_stctl", VCPU_STAT(instruction_stctl) }, + { "instruction_stctg", VCPU_STAT(instruction_stctg) }, { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, { "deliver_external_call", VCPU_STAT(deliver_external_call) }, { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, @@ -59,13 +63,16 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, { "exit_wait_state", VCPU_STAT(exit_wait_state) }, + { "instruction_pfmf", VCPU_STAT(instruction_pfmf) }, { "instruction_stidp", VCPU_STAT(instruction_stidp) }, { "instruction_spx", VCPU_STAT(instruction_spx) }, { "instruction_stpx", VCPU_STAT(instruction_stpx) }, { "instruction_stap", VCPU_STAT(instruction_stap) }, { "instruction_storage_key", VCPU_STAT(instruction_storage_key) }, + { "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) }, { "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) }, @@ -83,7 +90,14 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -static unsigned long long *facilities; +unsigned long *vfacilities; +static struct gmap_notifier gmap_notifier; + +/* test availability of vfacility */ +int test_vfacility(unsigned long nr) +{ + return __test_facility(nr, (void *) vfacilities); +} /* Section: not file related */ int kvm_arch_hardware_enable(void *garbage) @@ -96,13 +110,18 @@ void kvm_arch_hardware_disable(void *garbage) { } +static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address); + int kvm_arch_hardware_setup(void) { + gmap_notifier.notifier_call = kvm_gmap_notifier; + gmap_register_ipte_notifier(&gmap_notifier); return 0; } void kvm_arch_hardware_unsetup(void) { + gmap_unregister_ipte_notifier(&gmap_notifier); } void kvm_arch_check_processor_compat(void *rtn) @@ -138,16 +157,27 @@ 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_IRQFD: + case KVM_CAP_IOEVENTFD: + case KVM_CAP_DEVICE_CTRL: + case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_VM_ATTRIBUTES: r = 1; break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_USER_MEM_SLOTS; + break; case KVM_CAP_S390_COW: - r = sclp_get_fac85() & 0x2; + r = MACHINE_HAS_ESOP; break; default: r = 0; @@ -155,6 +185,25 @@ int kvm_dev_ioctl_check_extension(long ext) return r; } +static void kvm_s390_sync_dirty_log(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + gfn_t cur_gfn, last_gfn; + unsigned long address; + struct gmap *gmap = kvm->arch.gmap; + + down_read(&gmap->mm->mmap_sem); + /* Loop over all guest pages */ + last_gfn = memslot->base_gfn + memslot->npages; + for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) { + address = gfn_to_hva_memslot(memslot, cur_gfn); + + if (gmap_test_and_clear_dirty(address, gmap)) + mark_page_dirty(kvm, cur_gfn); + } + up_read(&gmap->mm->mmap_sem); +} + /* Section: vm related */ /* * Get (and clear) the dirty memory log for a memory slot. @@ -162,7 +211,129 @@ int kvm_dev_ioctl_check_extension(long ext) int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - return 0; + int r; + unsigned long n; + struct kvm_memory_slot *memslot; + int is_dirty = 0; + + mutex_lock(&kvm->slots_lock); + + r = -EINVAL; + if (log->slot >= KVM_USER_MEM_SLOTS) + goto out; + + memslot = id_to_memslot(kvm->memslots, log->slot); + r = -ENOENT; + if (!memslot->dirty_bitmap) + goto out; + + kvm_s390_sync_dirty_log(kvm, memslot); + r = kvm_get_dirty_log(kvm, log, &is_dirty); + if (r) + goto out; + + /* Clear the dirty log */ + if (is_dirty) { + n = kvm_dirty_bitmap_bytes(memslot); + memset(memslot->dirty_bitmap, 0, n); + } + r = 0; +out: + mutex_unlock(&kvm->slots_lock); + return r; +} + +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; +} + +static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + unsigned int idx; + switch (attr->attr) { + case KVM_S390_VM_MEM_ENABLE_CMMA: + ret = -EBUSY; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) == 0) { + kvm->arch.use_cmma = 1; + ret = 0; + } + mutex_unlock(&kvm->lock); + break; + case KVM_S390_VM_MEM_CLR_CMMA: + mutex_lock(&kvm->lock); + idx = srcu_read_lock(&kvm->srcu); + page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false); + srcu_read_unlock(&kvm->srcu, idx); + mutex_unlock(&kvm->lock); + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->group) { + case KVM_S390_VM_MEM_CTRL: + ret = kvm_s390_mem_control(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + + return ret; +} + +static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + return -ENXIO; +} + +static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->group) { + case KVM_S390_VM_MEM_CTRL: + switch (attr->attr) { + case KVM_S390_VM_MEM_ENABLE_CMMA: + case KVM_S390_VM_MEM_CLR_CMMA: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + default: + ret = -ENXIO; + break; + } + + return ret; } long kvm_arch_vm_ioctl(struct file *filp, @@ -170,6 +341,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; + struct kvm_device_attr attr; int r; switch (ioctl) { @@ -182,6 +354,47 @@ 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; + } + case KVM_SET_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_s390_vm_set_attr(kvm, &attr); + break; + } + case KVM_GET_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_s390_vm_get_attr(kvm, &attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_s390_vm_has_attr(kvm, &attr); + break; + } default: r = -ENOTTY; } @@ -193,6 +406,7 @@ 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 @@ -214,6 +428,10 @@ 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); @@ -223,6 +441,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) spin_lock_init(&kvm->arch.float_int.lock); INIT_LIST_HEAD(&kvm->arch.float_int.list); + init_waitqueue_head(&kvm->arch.ipte_wq); debug_register_view(kvm->arch.dbf, &debug_sprintf_view); VM_EVENT(kvm, 3, "%s", "vm created"); @@ -233,7 +452,15 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.gmap = gmap_alloc(current->mm); 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; + + spin_lock_init(&kvm->arch.start_stop_lock); + return 0; out_nogmap: debug_unregister(kvm->arch.dbf); @@ -247,6 +474,8 @@ 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_s390_clear_local_irqs(vcpu); + 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); @@ -259,9 +488,12 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) if (kvm_is_ucontrol(vcpu->kvm)) gmap_free(vcpu->arch.gmap); + if (kvm_s390_cmma_enabled(vcpu->kvm)) + kvm_s390_vcpu_unsetup_cmma(vcpu); free_page((unsigned long)(vcpu->arch.sie_block)); + kvm_vcpu_uninit(vcpu); - kfree(vcpu); + kmem_cache_free(kvm_vcpu_cache, vcpu); } static void kvm_free_vcpus(struct kvm *kvm) @@ -291,15 +523,20 @@ 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); + kvm_s390_clear_float_irqs(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) return -ENOMEM; + vcpu->arch.gmap->private = vcpu->kvm; return 0; } @@ -318,10 +555,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - save_fp_regs(&vcpu->arch.host_fpregs); + save_fp_ctl(&vcpu->arch.host_fpregs.fpc); + save_fp_regs(vcpu->arch.host_fpregs.fprs); save_access_regs(vcpu->arch.host_acrs); - vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK; - restore_fp_regs(&vcpu->arch.guest_fpregs); + restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + restore_fp_regs(vcpu->arch.guest_fpregs.fprs); restore_access_regs(vcpu->run->s.regs.acrs); gmap_enable(vcpu->arch.gmap); atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); @@ -331,9 +569,11 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); - save_fp_regs(&vcpu->arch.guest_fpregs); + save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + save_fp_regs(vcpu->arch.guest_fpregs.fprs); save_access_regs(vcpu->run->s.regs.acrs); - restore_fp_regs(&vcpu->arch.host_fpregs); + restore_fp_ctl(&vcpu->arch.host_fpregs.fpc); + restore_fp_regs(vcpu->arch.host_fpregs.fprs); restore_access_regs(vcpu->arch.host_acrs); } @@ -352,7 +592,11 @@ 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; - atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + vcpu->arch.sie_block->pp = 0; + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + kvm_clear_async_pf_completion_queue(vcpu); + kvm_s390_vcpu_stop(vcpu); + kvm_s390_clear_local_irqs(vcpu); } int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -360,27 +604,62 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) return 0; } +void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu) +{ + free_page(vcpu->arch.sie_block->cbrlo); + vcpu->arch.sie_block->cbrlo = 0; +} + +int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) +{ + vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL); + if (!vcpu->arch.sie_block->cbrlo) + return -ENOMEM; + + vcpu->arch.sie_block->ecb2 |= 0x80; + vcpu->arch.sie_block->ecb2 &= ~0x08; + return 0; +} + int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { + int rc = 0; + atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | - CPUSTAT_STOPPED); + CPUSTAT_STOPPED | + CPUSTAT_GED); vcpu->arch.sie_block->ecb = 6; - vcpu->arch.sie_block->eca = 0xC1002001U; - vcpu->arch.sie_block->fac = (int) (long) facilities; + if (test_vfacility(50) && test_vfacility(73)) + vcpu->arch.sie_block->ecb |= 0x10; + + vcpu->arch.sie_block->ecb2 = 8; + vcpu->arch.sie_block->eca = 0xD1002000U; + if (sclp_has_siif()) + vcpu->arch.sie_block->eca |= 1; + vcpu->arch.sie_block->fac = (int) (long) vfacilities; + vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE | + ICTL_TPROT; + + if (kvm_s390_cmma_enabled(vcpu->kvm)) { + rc = kvm_s390_vcpu_setup_cmma(vcpu); + if (rc) + return rc; + } hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, (unsigned long) vcpu); vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; get_cpu_id(&vcpu->arch.cpu_id); vcpu->arch.cpu_id.version = 0xff; - return 0; + return rc; } 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) @@ -388,16 +667,17 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, rc = -ENOMEM; - vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); 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) { @@ -416,11 +696,8 @@ 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; - init_waitqueue_head(&vcpu->arch.local_int.wq); + 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) @@ -433,16 +710,58 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, out_free_sie_block: free_page((unsigned long)(vcpu->arch.sie_block)); out_free_cpu: - kfree(vcpu); + kmem_cache_free(kvm_vcpu_cache, vcpu); out: return ERR_PTR(rc); } 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) +{ + atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); +} + +void s390_vcpu_unblock(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); +} + +/* + * Kick a guest cpu out of SIE and wait until SIE is not running. + * If the CPU is not running (e.g. waiting as idle) the function will + * return immediately. */ +void exit_sie(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags); + while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE) + cpu_relax(); +} + +/* Kick a guest cpu out of SIE and prevent SIE-reentry */ +void exit_sie_sync(struct kvm_vcpu *vcpu) +{ + s390_vcpu_block(vcpu); + exit_sie(vcpu); +} + +static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address) +{ + int i; + struct kvm *kvm = gmap->private; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + /* match against both prefix pages */ + if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) { + VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address); + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + exit_sie_sync(vcpu); + } + } } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) @@ -474,6 +793,26 @@ 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; } @@ -503,6 +842,26 @@ 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; } @@ -547,9 +906,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + if (test_fp_ctl(fpu->fpc)) + return -EINVAL; memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - vcpu->arch.guest_fpregs.fpc = fpu->fpc & FPC_VALID_MASK; - restore_fp_regs(&vcpu->arch.guest_fpregs); + vcpu->arch.guest_fpregs.fpc = fpu->fpc; + restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + restore_fp_regs(vcpu->arch.guest_fpregs.fprs); return 0; } @@ -579,10 +941,40 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, return -EINVAL; /* not implemented yet */ } +#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \ + KVM_GUESTDBG_USE_HW_BP | \ + KVM_GUESTDBG_ENABLE) + int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - return -EINVAL; /* not implemented yet */ + int rc = 0; + + vcpu->guest_debug = 0; + kvm_s390_clear_bp_data(vcpu); + + if (dbg->control & ~VALID_GUESTDBG_FLAGS) + return -EINVAL; + + if (dbg->control & KVM_GUESTDBG_ENABLE) { + vcpu->guest_debug = dbg->control; + /* enforce guest PER */ + atomic_set_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + + if (dbg->control & KVM_GUESTDBG_USE_HW_BP) + rc = kvm_s390_import_bp_data(vcpu, dbg); + } else { + atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + vcpu->arch.guestdbg.last_bp = 0; + } + + if (rc) { + vcpu->guest_debug = 0; + kvm_s390_clear_bp_data(vcpu); + atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + } + + return rc; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, @@ -597,46 +989,285 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return -EINVAL; /* not implemented yet */ } -static int __vcpu_run(struct kvm_vcpu *vcpu) +bool kvm_s390_cmma_enabled(struct kvm *kvm) +{ + if (!MACHINE_IS_LPAR) + return false; + /* only enable for z10 and later */ + if (!MACHINE_HAS_EDAT1) + return false; + if (!kvm->arch.use_cmma) + return false; + return true; +} + +static bool ibs_enabled(struct kvm_vcpu *vcpu) +{ + return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS; +} + +static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) { +retry: + s390_vcpu_unblock(vcpu); + /* + * We use MMU_RELOAD just to re-arm the ipte notifier for the + * guest prefix page. gmap_ipte_notify will wait on the ptl lock. + * This ensures that the ipte instruction for this request has + * already finished. We might race against a second unmapper that + * wants to set the blocking bit. Lets just retry the request loop. + */ + if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) { + int rc; + rc = gmap_ipte_notify(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu), + PAGE_SIZE * 2); + if (rc) + return rc; + goto retry; + } + + if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) { + if (!ibs_enabled(vcpu)) { + trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1); + atomic_set_mask(CPUSTAT_IBS, + &vcpu->arch.sie_block->cpuflags); + } + goto retry; + } + + if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) { + if (ibs_enabled(vcpu)) { + trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0); + atomic_clear_mask(CPUSTAT_IBS, + &vcpu->arch.sie_block->cpuflags); + } + goto retry; + } + + return 0; +} + +/** + * kvm_arch_fault_in_page - fault-in guest page if necessary + * @vcpu: The corresponding virtual cpu + * @gpa: Guest physical address + * @writable: Whether the page should be writable or not + * + * Make sure that a guest page has been faulted-in on the host. + * + * Return: Zero on success, negative error code otherwise. + */ +long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable) +{ + struct mm_struct *mm = current->mm; + hva_t hva; + long rc; + + hva = gmap_fault(gpa, vcpu->arch.gmap); + if (IS_ERR_VALUE(hva)) + return (long)hva; + down_read(&mm->mmap_sem); + rc = get_user_pages(current, mm, hva, 1, writable, 0, NULL, NULL); + up_read(&mm->mmap_sem); + + return rc < 0 ? rc : 0; +} + +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 = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr)); + hva += current->thread.gmap_addr & ~PAGE_MASK; + if (read_guest_real(vcpu, vcpu->arch.pfault_token, &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()) schedule(); - if (test_thread_flag(TIF_MCCK_PENDING)) + if (test_cpu_flag(CIF_MCCK_PENDING)) s390_handle_mcck(); if (!kvm_is_ucontrol(vcpu->kvm)) kvm_s390_deliver_pending_interrupts(vcpu); - vcpu->arch.sie_block->icptcode = 0; - preempt_disable(); - kvm_guest_enter(); - preempt_enable(); - VCPU_EVENT(vcpu, 6, "entering sie flags %x", - atomic_read(&vcpu->arch.sie_block->cpuflags)); - trace_kvm_s390_sie_enter(vcpu, - atomic_read(&vcpu->arch.sie_block->cpuflags)); - rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); - if (rc) { - 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); - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - rc = 0; - } + rc = kvm_s390_handle_requests(vcpu); + if (rc) + return rc; + + if (guestdbg_enabled(vcpu)) { + kvm_s390_backup_guest_per_regs(vcpu); + kvm_s390_patch_guest_per_regs(vcpu); } + + vcpu->arch.sie_block->icptcode = 0; + cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); + VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags); + trace_kvm_s390_sie_enter(vcpu, cpuflags); + + return 0; +} + +static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) +{ + int rc = -1; + VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode); - kvm_guest_exit(); + + if (guestdbg_enabled(vcpu)) + kvm_s390_restore_guest_per_regs(vcpu); + + if (exit_reason >= 0) { + rc = 0; + } 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)) { + rc = 0; + } else { + gpa_t gpa = current->thread.gmap_addr; + rc = kvm_arch_fault_in_page(vcpu, gpa, 1); + } + } + + 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)) + /* Don't exit for host interrupts. */ + rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0; + else + rc = kvm_handle_sie_intercept(vcpu); + } + + return rc; +} + +static int __vcpu_run(struct kvm_vcpu *vcpu) +{ + int rc, exit_reason; + + /* + * We try to hold kvm->srcu during most of vcpu_run (except when run- + * ning the guest), so that memslots (and other stuff) are protected + */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + do { + rc = vcpu_pre_run(vcpu); + if (rc) + break; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + /* + * As PF_VCPU will be used in fault handler, between + * guest_enter and guest_exit should be no uaccess. + */ + preempt_disable(); + kvm_guest_enter(); + preempt_enable(); + exit_reason = sie64a(vcpu->arch.sie_block, + vcpu->run->s.regs.gprs); + kvm_guest_exit(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + rc = vcpu_post_run(vcpu, exit_reason); + } while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc); + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); return rc; } @@ -645,13 +1276,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int rc; sigset_t sigsaved; -rerun_vcpu: + if (guestdbg_exit_pending(vcpu)) { + kvm_s390_prepare_debug_exit(vcpu); + return 0; + } + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); - atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); - - BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL); + kvm_s390_vcpu_start(vcpu); switch (kvm_run->exit_reason) { case KVM_EXIT_S390_SIEIC: @@ -659,6 +1292,8 @@ rerun_vcpu: case KVM_EXIT_INTR: case KVM_EXIT_S390_RESET: case KVM_EXIT_S390_UCONTROL: + case KVM_EXIT_S390_TSCH: + case KVM_EXIT_DEBUG: break; default: BUG(); @@ -677,34 +1312,17 @@ rerun_vcpu: } might_fault(); - - do { - rc = __vcpu_run(vcpu); - if (rc) - break; - if (kvm_is_ucontrol(vcpu->kvm)) - rc = -EOPNOTSUPP; - else - rc = kvm_handle_sie_intercept(vcpu); - } while (!signal_pending(current) && !rc); - - if (rc == SIE_INTERCEPT_RERUNVCPU) - goto rerun_vcpu; + rc = __vcpu_run(vcpu); if (signal_pending(current) && !rc) { kvm_run->exit_reason = KVM_EXIT_INTR; 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; + if (guestdbg_exit_pending(vcpu) && !rc) { + kvm_s390_prepare_debug_exit(vcpu); rc = 0; } -#endif if (rc == -EOPNOTSUPP) { /* intercept cannot be handled in-kernel, prepare kvm-run */ @@ -723,7 +1341,7 @@ rerun_vcpu: kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask; kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr; - kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix; + kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu); memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128); if (vcpu->sigset_active) @@ -733,81 +1351,192 @@ rerun_vcpu: return rc; } -static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from, - unsigned long n, int prefix) -{ - if (prefix) - return copy_to_guest(vcpu, guestdest, from, n); - else - return copy_to_guest_absolute(vcpu, guestdest, from, n); -} - /* * store status at address * we use have two special cases: * 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 gpa) { unsigned char archmode = 1; - int prefix; + unsigned int px; + u64 clkcomp; + int rc; - if (addr == KVM_S390_STORE_STATUS_NOADDR) { - if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1)) + if (gpa == KVM_S390_STORE_STATUS_NOADDR) { + if (write_guest_abs(vcpu, 163, &archmode, 1)) return -EFAULT; - addr = SAVE_AREA_BASE; - prefix = 0; - } else if (addr == KVM_S390_STORE_STATUS_PREFIXED) { - if (copy_to_guest(vcpu, 163ul, &archmode, 1)) + gpa = SAVE_AREA_BASE; + } else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) { + if (write_guest_real(vcpu, 163, &archmode, 1)) return -EFAULT; - addr = SAVE_AREA_BASE; - prefix = 1; - } else - prefix = 0; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs), - vcpu->arch.guest_fpregs.fprs, 128, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs), - vcpu->run->s.regs.gprs, 128, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw), - &vcpu->arch.sie_block->gpsw, 16, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg), - &vcpu->arch.sie_block->prefix, 4, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, - addr + offsetof(struct save_area, fp_ctrl_reg), - &vcpu->arch.guest_fpregs.fpc, 4, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg), - &vcpu->arch.sie_block->todpr, 4, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer), - &vcpu->arch.sie_block->cputm, 8, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp), - &vcpu->arch.sie_block->ckc, 8, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs), - &vcpu->run->s.regs.acrs, 64, prefix)) - return -EFAULT; - - if (__guestcopy(vcpu, - addr + offsetof(struct save_area, ctrl_regs), - &vcpu->arch.sie_block->gcr, 128, prefix)) - return -EFAULT; - return 0; + gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE); + } + rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs), + vcpu->arch.guest_fpregs.fprs, 128); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs), + vcpu->run->s.regs.gprs, 128); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw), + &vcpu->arch.sie_block->gpsw, 16); + px = kvm_s390_get_prefix(vcpu); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg), + &px, 4); + rc |= write_guest_abs(vcpu, + gpa + offsetof(struct save_area, fp_ctrl_reg), + &vcpu->arch.guest_fpregs.fpc, 4); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg), + &vcpu->arch.sie_block->todpr, 4); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer), + &vcpu->arch.sie_block->cputm, 8); + clkcomp = vcpu->arch.sie_block->ckc >> 8; + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp), + &clkcomp, 8); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs), + &vcpu->run->s.regs.acrs, 64); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs), + &vcpu->arch.sie_block->gcr, 128); + return rc ? -EFAULT : 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 inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) +{ + return atomic_read(&(vcpu)->arch.sie_block->cpuflags) & CPUSTAT_STOPPED; +} + +static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) +{ + kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); + kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu); + exit_sie_sync(vcpu); +} + +static void __disable_ibs_on_all_vcpus(struct kvm *kvm) +{ + unsigned int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + __disable_ibs_on_vcpu(vcpu); + } +} + +static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu) +{ + kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu); + kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu); + exit_sie_sync(vcpu); +} + +void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) +{ + int i, online_vcpus, started_vcpus = 0; + + if (!is_vcpu_stopped(vcpu)) + return; + + trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1); + /* Only one cpu at a time may enter/leave the STOPPED state. */ + spin_lock_bh(&vcpu->kvm->arch.start_stop_lock); + online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + + for (i = 0; i < online_vcpus; i++) { + if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) + started_vcpus++; + } + + if (started_vcpus == 0) { + /* we're the only active VCPU -> speed it up */ + __enable_ibs_on_vcpu(vcpu); + } else if (started_vcpus == 1) { + /* + * As we are starting a second VCPU, we have to disable + * the IBS facility on all VCPUs to remove potentially + * oustanding ENABLE requests. + */ + __disable_ibs_on_all_vcpus(vcpu->kvm); + } + + atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + /* + * Another VCPU might have used IBS while we were offline. + * Let's play safe and flush the VCPU at startup. + */ + vcpu->arch.sie_block->ihcpu = 0xffff; + spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock); + return; +} + +void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) +{ + int i, online_vcpus, started_vcpus = 0; + struct kvm_vcpu *started_vcpu = NULL; + + if (is_vcpu_stopped(vcpu)) + return; + + trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0); + /* Only one cpu at a time may enter/leave the STOPPED state. */ + spin_lock_bh(&vcpu->kvm->arch.start_stop_lock); + online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + + atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + __disable_ibs_on_vcpu(vcpu); + + for (i = 0; i < online_vcpus; i++) { + if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) { + started_vcpus++; + started_vcpu = vcpu->kvm->vcpus[i]; + } + } + + if (started_vcpus == 1) { + /* + * As we only have one VCPU left, we want to enable the + * IBS facility for that VCPU to speed it up. + */ + __enable_ibs_on_vcpu(started_vcpu); + } + + spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock); + return; +} + +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_S390_CSS_SUPPORT: + if (!vcpu->kvm->arch.css_support) { + vcpu->kvm->arch.css_support = 1; + trace_kvm_s390_enable_css(vcpu->kvm); + } + r = 0; + break; + default: + r = -EINVAL; + break; + } + return r; } long kvm_arch_vcpu_ioctl(struct file *filp, @@ -815,6 +1544,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; + int idx; long r; switch (ioctl) { @@ -828,7 +1558,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_S390_STORE_STATUS: + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_s390_vcpu_store_status(vcpu, arg); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; case KVM_S390_SET_INITIAL_PSW: { psw_t psw; @@ -896,6 +1628,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = 0; break; } + case KVM_ENABLE_CAP: + { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + break; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -ENOTTY; } @@ -915,35 +1656,31 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc) + enum kvm_mr_change change) { - /* A few sanity checks. We can have exactly one memory slot which has - to start at guest virtual zero and which has to be located at a - page boundary in userland and which has to end at a page boundary. - The memory in userland is ok to be fragmented into various different - vmas. It is okay to mmap() and munmap() stuff in this slot after - doing this call at any time */ - - if (mem->slot) - return -EINVAL; - - if (mem->guest_phys_addr) - return -EINVAL; + /* A few sanity checks. We can have memory slots which have to be + located/ended at a segment boundary (1MB). The memory in userland is + ok to be fragmented into various different vmas. It is okay to mmap() + and munmap() stuff in this slot after doing this call at any time */ if (mem->userspace_addr & 0xffffful) return -EINVAL; @@ -951,19 +1688,26 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (mem->memory_size & 0xffffful) return -EINVAL; - if (!user_alloc) - return -EINVAL; - return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - int user_alloc) + const struct kvm_memory_slot *old, + enum kvm_mr_change change) { int rc; + /* If the basics of the memslot do not change, we do not want + * to update the gmap. Every update causes several unnecessary + * segment translation exceptions. This is usually handled just + * fine by the normal fault handler + gmap, but it will also + * cause faults on the prefix page of running guest CPUs. + */ + if (old->userspace_addr == mem->userspace_addr && + old->base_gfn * PAGE_SIZE == mem->guest_phys_addr && + old->npages * PAGE_SIZE == mem->memory_size) + return; rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, mem->guest_phys_addr, mem->memory_size); @@ -993,22 +1737,31 @@ static int __init kvm_s390_init(void) * to hold the maximum amount of facilities. On the other hand, we * only set facilities that are known to work in KVM. */ - facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); - if (!facilities) { + vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); + if (!vfacilities) { kvm_exit(); return -ENOMEM; } - memcpy(facilities, S390_lowcore.stfle_fac_list, 16); - facilities[0] &= 0xff00fff3f47c0000ULL; - facilities[1] &= 0x001c000000000000ULL; + memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16); + vfacilities[0] &= 0xff82fff3f4fc2000UL; + vfacilities[1] &= 0x005c000000000000UL; return 0; } static void __exit kvm_s390_exit(void) { - free_page((unsigned long) facilities); + free_page((unsigned long) vfacilities); kvm_exit(); } module_init(kvm_s390_init); module_exit(kvm_s390_exit); + +/* + * Enable autoloading of the kvm module. + * Note that we add the module alias here instead of virt/kvm/kvm_main.c + * since x86 takes a different approach. + */ +#include <linux/miscdevice.h> +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index d75bc5e92c5..a8655ed3161 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -19,16 +19,18 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> -/* The current code can have up to 256 pages for virtio */ -#define VIRTIODESCSPACE (256ul * 4096ul) - typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); -/* negativ values are error codes, positive values for internal conditions */ -#define SIE_INTERCEPT_RERUNVCPU (1<<0) -#define SIE_INTERCEPT_UCONTROL (1<<1) +/* declare vfacilities extern */ +extern unsigned long *vfacilities; + 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_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", \ @@ -59,35 +61,176 @@ static inline int kvm_is_ucontrol(struct kvm *kvm) #endif } +#define GUEST_PREFIX_SHIFT 13 +static inline u32 kvm_s390_get_prefix(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.sie_block->prefix << GUEST_PREFIX_SHIFT; +} + static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) { - vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u; + vcpu->arch.sie_block->prefix = prefix >> GUEST_PREFIX_SHIFT; vcpu->arch.sie_block->ihcpu = 0xffff; + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); +} + +static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu) +{ + u32 base2 = vcpu->arch.sie_block->ipb >> 28; + u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; +} + +static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, + u64 *address1, u64 *address2) +{ + u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; + u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; + u32 base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12; + u32 disp2 = vcpu->arch.sie_block->ipb & 0x0fff; + + *address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; + *address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; +} + +static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) +{ + if (r1) + *r1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 20; + if (r2) + *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; +} + +static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) +{ + u32 base2 = vcpu->arch.sie_block->ipb >> 28; + u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + + ((vcpu->arch.sie_block->ipb & 0xff00) << 4); + /* The displacement is a 20bit _SIGNED_ value */ + if (disp2 & 0x80000) + disp2+=0xfff00000; + + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2; +} + +static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu) +{ + u32 base2 = vcpu->arch.sie_block->ipb >> 28; + u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; +} + +/* Set the condition code in the guest program status word */ +static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) +{ + vcpu->arch.sie_block->gpsw.mask &= ~(3UL << 44); + vcpu->arch.sie_block->gpsw.mask |= cc << 44; } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); 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); -int kvm_s390_inject_vm(struct kvm *kvm, - struct kvm_s390_interrupt *s390int); -int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt *s390int); -int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); -int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action); +void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu); +void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu); +void kvm_s390_clear_float_irqs(struct kvm *kvm); +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); +struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, + u64 cr6, u64 schid); +void kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti); +int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); /* implemented in priv.c */ +int is_valid_psw(psw_t *psw); int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); int kvm_s390_handle_e5(struct kvm_vcpu *vcpu); int kvm_s390_handle_01(struct kvm_vcpu *vcpu); +int kvm_s390_handle_b9(struct kvm_vcpu *vcpu); +int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu); +int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu); +int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu); +int kvm_s390_handle_eb(struct kvm_vcpu *vcpu); /* implemented in sigp.c */ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); +int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ -int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, - unsigned long addr); +long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); +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 kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); +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); +int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); +/* is cmma enabled */ +bool kvm_s390_cmma_enabled(struct kvm *kvm); +int test_vfacility(unsigned long nr); + /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); +/* implemented in interrupt.c */ +int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info); + +/** + * kvm_s390_inject_prog_cond - conditionally inject a program check + * @vcpu: virtual cpu + * @rc: original return/error code + * + * This function is supposed to be used after regular guest access functions + * failed, to conditionally inject a program check to a vcpu. The typical + * pattern would look like + * + * rc = write_guest(vcpu, addr, data, len); + * if (rc) + * return kvm_s390_inject_prog_cond(vcpu, rc); + * + * A negative return code from guest access functions implies an internal error + * like e.g. out of memory. In these cases no program check should be injected + * to the guest. + * A positive value implies that an exception happened while accessing a guest's + * memory. In this case all data belonging to the corresponding program check + * has been stored in vcpu->arch.pgm and can be injected with + * kvm_s390_inject_prog_irq(). + * + * Returns: - the original @rc value if @rc was negative (internal error) + * - zero if @rc was already zero + * - zero or error code from injecting if @rc was positive + * (program check injected to @vcpu) + */ +static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc) +{ + if (rc <= 0) + return rc; + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); +} + +/* 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); +int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu); + +/* implemented in guestdbg.c */ +void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); +void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu); +void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu); +int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); +void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu); +void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu); +void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu); #endif diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d768906f15c..f89c1cd6775 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1,7 +1,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008 + * 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) @@ -14,207 +14,453 @@ #include <linux/kvm.h> #include <linux/gfp.h> #include <linux/errno.h> +#include <linux/compat.h> +#include <asm/asm-offsets.h> +#include <asm/facility.h> #include <asm/current.h> #include <asm/debug.h> #include <asm/ebcdic.h> #include <asm/sysinfo.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/io.h> +#include <asm/ptrace.h> +#include <asm/compat.h> #include "gaccess.h" #include "kvm-s390.h" #include "trace.h" +/* Handle SCK (SET CLOCK) interception */ +static int handle_set_clock(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *cpup; + s64 hostclk, val; + int i, rc; + u64 op2; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + op2 = kvm_s390_get_base_disp_s(vcpu); + if (op2 & 7) /* Operand must be on a doubleword boundary */ + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + rc = read_guest(vcpu, op2, &val, sizeof(val)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + if (store_tod_clock(&hostclk)) { + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } + val = (val - hostclk) & ~0x3fUL; + + mutex_lock(&vcpu->kvm->lock); + kvm_for_each_vcpu(i, cpup, vcpu->kvm) + cpup->arch.sie_block->epoch = val; + mutex_unlock(&vcpu->kvm->lock); + + kvm_s390_set_psw_cc(vcpu, 0); + return 0; +} + static int handle_set_prefix(struct kvm_vcpu *vcpu) { - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); u64 operand2; - u32 address = 0; - u8 tmp; + u32 address; + int rc; vcpu->stat.instruction_spx++; - operand2 = disp2; - if (base2) - operand2 += vcpu->run->s.regs.gprs[base2]; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + operand2 = kvm_s390_get_base_disp_s(vcpu); /* must be word boundary */ - if (operand2 & 3) { - kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - goto out; - } + if (operand2 & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); /* get the value */ - if (get_guest_u32(vcpu, operand2, &address)) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - goto out; - } + rc = read_guest(vcpu, operand2, &address, sizeof(address)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); - address = address & 0x7fffe000u; + address &= 0x7fffe000u; - /* make sure that the new value is valid memory */ - if (copy_from_guest_absolute(vcpu, &tmp, address, 1) || - (copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1))) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - goto out; - } + /* + * Make sure the new value is valid memory. We only need to check the + * first page, since address is 8k aligned and memory pieces are always + * at least 1MB aligned and have at least a size of 1MB. + */ + if (kvm_is_error_gpa(vcpu->kvm, address)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); kvm_s390_set_prefix(vcpu, address); VCPU_EVENT(vcpu, 5, "setting prefix to %x", address); trace_kvm_s390_handle_prefix(vcpu, 1, address); -out: return 0; } static int handle_store_prefix(struct kvm_vcpu *vcpu) { - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); u64 operand2; u32 address; + int rc; vcpu->stat.instruction_stpx++; - operand2 = disp2; - if (base2) - operand2 += vcpu->run->s.regs.gprs[base2]; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + operand2 = kvm_s390_get_base_disp_s(vcpu); /* must be word boundary */ - if (operand2 & 3) { - kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - goto out; - } + if (operand2 & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - address = vcpu->arch.sie_block->prefix; - address = address & 0x7fffe000u; + address = kvm_s390_get_prefix(vcpu); /* get the value */ - if (put_guest_u32(vcpu, operand2, address)) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - goto out; - } + rc = write_guest(vcpu, operand2, &address, sizeof(address)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); VCPU_EVENT(vcpu, 5, "storing prefix to %x", address); trace_kvm_s390_handle_prefix(vcpu, 0, address); -out: return 0; } static int handle_store_cpu_address(struct kvm_vcpu *vcpu) { - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); - u64 useraddr; + u16 vcpu_id = vcpu->vcpu_id; + u64 ga; int rc; vcpu->stat.instruction_stap++; - useraddr = disp2; - if (base2) - useraddr += vcpu->run->s.regs.gprs[base2]; - if (useraddr & 1) { - kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - goto out; - } + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - rc = put_guest_u16(vcpu, useraddr, vcpu->vcpu_id); - if (rc == -EFAULT) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - goto out; - } + ga = kvm_s390_get_base_disp_s(vcpu); - VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", useraddr); - trace_kvm_s390_handle_stap(vcpu, useraddr); -out: + if (ga & 1) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = write_guest(vcpu, ga, &vcpu_id, sizeof(vcpu_id)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", ga); + trace_kvm_s390_handle_stap(vcpu, ga); return 0; } +static void __skey_check_enable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE))) + return; + + s390_enable_skey(); + trace_kvm_s390_skey_related_inst(vcpu); + vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE); +} + + static int handle_skey(struct kvm_vcpu *vcpu) { + __skey_check_enable(vcpu); + vcpu->stat.instruction_storage_key++; - vcpu->arch.sie_block->gpsw.addr -= 4; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + vcpu->arch.sie_block->gpsw.addr = + __rewind_psw(vcpu->arch.sie_block->gpsw, 4); VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); return 0; } -static int handle_stsch(struct kvm_vcpu *vcpu) +static int handle_ipte_interlock(struct kvm_vcpu *vcpu) { - vcpu->stat.instruction_stsch++; - VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3"); - /* condition code 3 */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + + vcpu->stat.instruction_ipte_interlock++; + if (psw_bits(*psw).p) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); + psw->addr = __rewind_psw(*psw, 4); + VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation"); return 0; } -static int handle_chsc(struct kvm_vcpu *vcpu) +static int handle_test_block(struct kvm_vcpu *vcpu) { - vcpu->stat.instruction_chsc++; - VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3"); - /* condition code 3 */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + gpa_t addr; + int reg2; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + kvm_s390_get_regs_rre(vcpu, NULL, ®2); + addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + addr = kvm_s390_logical_to_effective(vcpu, addr); + if (kvm_s390_check_low_addr_protection(vcpu, addr)) + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + addr = kvm_s390_real_to_abs(vcpu, addr); + + if (kvm_is_error_gpa(vcpu->kvm, addr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + /* + * We don't expect errors on modern systems, and do not care + * about storage keys (yet), so let's just clear the page. + */ + if (kvm_clear_guest(vcpu->kvm, addr, PAGE_SIZE)) + return -EFAULT; + kvm_s390_set_psw_cc(vcpu, 0); + vcpu->run->s.regs.gprs[0] = 0; return 0; } +static int handle_tpi(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_interrupt_info *inti; + unsigned long len; + u32 tpi_data[3]; + int cc, rc; + u64 addr; + + rc = 0; + addr = kvm_s390_get_base_disp_s(vcpu); + if (addr & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + cc = 0; + inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0); + if (!inti) + goto no_interrupt; + cc = 1; + tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr; + tpi_data[1] = inti->io.io_int_parm; + tpi_data[2] = inti->io.io_int_word; + if (addr) { + /* + * Store the two-word I/O interruption code into the + * provided area. + */ + len = sizeof(tpi_data) - 4; + rc = write_guest(vcpu, addr, &tpi_data, len); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + } else { + /* + * Store the three-word I/O interruption code into + * the appropriate lowcore area. + */ + len = sizeof(tpi_data); + if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) + rc = -EFAULT; + } + /* + * If we encounter a problem storing the interruption code, the + * instruction is suppressed from the guest's view: reinject the + * interrupt. + */ + if (!rc) + kfree(inti); + else + kvm_s390_reinject_io_int(vcpu->kvm, inti); +no_interrupt: + /* Set condition code and we're done. */ + if (!rc) + kvm_s390_set_psw_cc(vcpu, cc); + return rc ? -EFAULT : 0; +} + +static int handle_tsch(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_interrupt_info *inti; + + inti = kvm_s390_get_io_int(vcpu->kvm, 0, + vcpu->run->s.regs.gprs[1]); + + /* + * Prepare exit to userspace. + * We indicate whether we dequeued a pending I/O interrupt + * so that userspace can re-inject it if the instruction gets + * a program check. While this may re-order the pending I/O + * interrupts, this is no problem since the priority is kept + * intact. + */ + vcpu->run->exit_reason = KVM_EXIT_S390_TSCH; + vcpu->run->s390_tsch.dequeued = !!inti; + if (inti) { + vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id; + vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr; + vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm; + vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word; + } + vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb; + kfree(inti); + return -EREMOTE; +} + +static int handle_io_inst(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 4, "%s", "I/O instruction"); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (vcpu->kvm->arch.css_support) { + /* + * Most I/O instructions will be handled by userspace. + * Exceptions are tpi and the interrupt portion of tsch. + */ + if (vcpu->arch.sie_block->ipa == 0xb236) + return handle_tpi(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb235) + return handle_tsch(vcpu); + /* Handle in userspace. */ + return -EOPNOTSUPP; + } else { + /* + * Set condition code 3 to stop the guest from issuing channel + * I/O instructions. + */ + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } +} + static int handle_stfl(struct kvm_vcpu *vcpu) { - unsigned int facility_list; int rc; vcpu->stat.instruction_stfl++; - /* only pass the facility bits, which we can handle */ - facility_list = S390_lowcore.stfl_fac_list & 0xff00fff3; - - rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), - &facility_list, sizeof(facility_list)); - if (rc == -EFAULT) - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - else { - VCPU_EVENT(vcpu, 5, "store facility list value %x", - facility_list); - trace_kvm_s390_handle_stfl(vcpu, facility_list); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list), + vfacilities, 4); + if (rc) + return rc; + VCPU_EVENT(vcpu, 5, "store facility list value %x", + *(unsigned int *) vfacilities); + trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities); + return 0; +} + +static void handle_new_psw(struct kvm_vcpu *vcpu) +{ + /* Check whether the new psw is enabled for machine checks. */ + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK) + kvm_s390_deliver_pending_machine_checks(vcpu); +} + +#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA) +#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL +#define PSW_ADDR_24 0x0000000000ffffffUL +#define PSW_ADDR_31 0x000000007fffffffUL + +int is_valid_psw(psw_t *psw) +{ + if (psw->mask & PSW_MASK_UNASSIGNED) + return 0; + if ((psw->mask & PSW_MASK_ADDR_MODE) == PSW_MASK_BA) { + if (psw->addr & ~PSW_ADDR_31) + return 0; } + if (!(psw->mask & PSW_MASK_ADDR_MODE) && (psw->addr & ~PSW_ADDR_24)) + return 0; + if ((psw->mask & PSW_MASK_ADDR_MODE) == PSW_MASK_EA) + return 0; + if (psw->addr & 1) + return 0; + return 1; +} + +int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) +{ + psw_t *gpsw = &vcpu->arch.sie_block->gpsw; + psw_compat_t new_psw; + u64 addr; + int rc; + + if (gpsw->mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_s(vcpu); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + if (!(new_psw.mask & PSW32_MASK_BASE)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + gpsw->mask = (new_psw.mask & ~PSW32_MASK_BASE) << 32; + gpsw->mask |= new_psw.addr & PSW32_ADDR_AMODE; + gpsw->addr = new_psw.addr & ~PSW32_ADDR_AMODE; + if (!is_valid_psw(gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + handle_new_psw(vcpu); + return 0; +} + +static int handle_lpswe(struct kvm_vcpu *vcpu) +{ + psw_t new_psw; + u64 addr; + int rc; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_s(vcpu); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + vcpu->arch.sie_block->gpsw = new_psw; + if (!is_valid_psw(&vcpu->arch.sie_block->gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + handle_new_psw(vcpu); return 0; } static int handle_stidp(struct kvm_vcpu *vcpu) { - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 stidp_data = vcpu->arch.stidp_data; u64 operand2; int rc; vcpu->stat.instruction_stidp++; - operand2 = disp2; - if (base2) - operand2 += vcpu->run->s.regs.gprs[base2]; - if (operand2 & 7) { - kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - goto out; - } + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - rc = put_guest_u64(vcpu, operand2, vcpu->arch.stidp_data); - if (rc == -EFAULT) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - goto out; - } + operand2 = kvm_s390_get_base_disp_s(vcpu); + + if (operand2 & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = write_guest(vcpu, operand2, &stidp_data, sizeof(stidp_data)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); VCPU_EVENT(vcpu, 5, "%s", "store cpu id"); -out: return 0; } 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)) @@ -240,75 +486,103 @@ static int handle_stsi(struct kvm_vcpu *vcpu) int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28; int sel1 = vcpu->run->s.regs.gprs[0] & 0xff; int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff; - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + unsigned long mem = 0; u64 operand2; - unsigned long mem; + int rc = 0; vcpu->stat.instruction_stsi++; VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); - operand2 = disp2; - if (base2) - operand2 += vcpu->run->s.regs.gprs[base2]; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - if (operand2 & 0xfff && fc > 0) + if (fc > 3) { + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } + + if (vcpu->run->s.regs.gprs[0] & 0x0fffff00 + || vcpu->run->s.regs.gprs[1] & 0xffff0000) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - switch (fc) { - case 0: + if (fc == 0) { vcpu->run->s.regs.gprs[0] = 3 << 28; - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + kvm_s390_set_psw_cc(vcpu, 0); return 0; + } + + operand2 = kvm_s390_get_base_disp_s(vcpu); + + if (operand2 & 0xfff) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + switch (fc) { case 1: /* same handling for 1 and 2 */ case 2: mem = get_zeroed_page(GFP_KERNEL); if (!mem) - goto out_fail; + goto out_no_data; if (stsi((void *) mem, fc, sel1, sel2)) - goto out_mem; + goto out_no_data; break; case 3: if (sel1 != 2 || sel2 != 2) - goto out_fail; + goto out_no_data; mem = get_zeroed_page(GFP_KERNEL); if (!mem) - goto out_fail; + goto out_no_data; handle_stsi_3_2_2(vcpu, (void *) mem); break; - default: - goto out_fail; } - if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) { - kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - goto out_mem; + rc = write_guest(vcpu, operand2, (void *)mem, PAGE_SIZE); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto out; } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; return 0; -out_mem: +out_no_data: + kvm_s390_set_psw_cc(vcpu, 3); +out: free_page(mem); -out_fail: - /* condition code 3 */ - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; - return 0; + return rc; } -static intercept_handler_t priv_handlers[256] = { +static const intercept_handler_t b2_handlers[256] = { [0x02] = handle_stidp, + [0x04] = handle_set_clock, [0x10] = handle_set_prefix, [0x11] = handle_store_prefix, [0x12] = handle_store_cpu_address, + [0x21] = handle_ipte_interlock, [0x29] = handle_skey, [0x2a] = handle_skey, [0x2b] = handle_skey, - [0x34] = handle_stsch, - [0x5f] = handle_chsc, + [0x2c] = handle_test_block, + [0x30] = handle_io_inst, + [0x31] = handle_io_inst, + [0x32] = handle_io_inst, + [0x33] = handle_io_inst, + [0x34] = handle_io_inst, + [0x35] = handle_io_inst, + [0x36] = handle_io_inst, + [0x37] = handle_io_inst, + [0x38] = handle_io_inst, + [0x39] = handle_io_inst, + [0x3a] = handle_io_inst, + [0x3b] = handle_io_inst, + [0x3c] = handle_io_inst, + [0x50] = handle_ipte_interlock, + [0x5f] = handle_io_inst, + [0x74] = handle_io_inst, + [0x76] = handle_io_inst, [0x7d] = handle_stsi, [0xb1] = handle_stfl, + [0xb2] = handle_lpswe, }; int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) @@ -316,67 +590,394 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) intercept_handler_t handler; /* - * a lot of B2 instructions are priviledged. We first check for - * the privileged ones, that we can handle in the kernel. If the - * kernel can handle this instruction, we check for the problem - * state bit and (a) handle the instruction or (b) send a code 2 - * program check. - * Anything else goes to userspace.*/ - handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) { - if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); + * A lot of B2 instructions are priviledged. Here we check for + * the privileged ones, that we can handle in the kernel. + * Anything else goes to userspace. + */ + handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) + return handler(vcpu); + + return -EOPNOTSUPP; +} + +static int handle_epsw(struct kvm_vcpu *vcpu) +{ + int reg1, reg2; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + /* This basically extracts the mask half of the psw. */ + vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000UL; + vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32; + if (reg2) { + vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000UL; + vcpu->run->s.regs.gprs[reg2] |= + vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffffUL; + } + return 0; +} + +#define PFMF_RESERVED 0xfffc0101UL +#define PFMF_SK 0x00020000UL +#define PFMF_CF 0x00010000UL +#define PFMF_UI 0x00008000UL +#define PFMF_FSC 0x00007000UL +#define PFMF_NQ 0x00000800UL +#define PFMF_MR 0x00000400UL +#define PFMF_MC 0x00000200UL +#define PFMF_KEY 0x000000feUL + +static int handle_pfmf(struct kvm_vcpu *vcpu) +{ + int reg1, reg2; + unsigned long start, end; + + vcpu->stat.instruction_pfmf++; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + if (!MACHINE_HAS_PFMF) + 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->run->s.regs.gprs[reg1] & PFMF_RESERVED) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* Only provide non-quiescing support if the host supports it */ + if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ && !test_facility(14)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* No support for conditional-SSKE */ + if (vcpu->run->s.regs.gprs[reg1] & (PFMF_MR | PFMF_MC)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { + if (kvm_s390_check_low_addr_protection(vcpu, start)) + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + } + + switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { + case 0x00000000: + end = (start + (1UL << 12)) & ~((1UL << 12) - 1); + break; + case 0x00001000: + end = (start + (1UL << 20)) & ~((1UL << 20) - 1); + break; + /* We dont support EDAT2 + case 0x00002000: + end = (start + (1UL << 31)) & ~((1UL << 31) - 1); + break;*/ + default: + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + } + while (start < end) { + unsigned long useraddr, abs_addr; + + /* Translate guest address to host address */ + if ((vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) == 0) + abs_addr = kvm_s390_real_to_abs(vcpu, start); else - return handler(vcpu); + abs_addr = start; + useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(abs_addr)); + if (kvm_is_error_hva(useraddr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { + if (clear_user((void __user *)useraddr, PAGE_SIZE)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) { + __skey_check_enable(vcpu); + if (set_guest_storage_key(current->mm, useraddr, + vcpu->run->s.regs.gprs[reg1] & PFMF_KEY, + vcpu->run->s.regs.gprs[reg1] & PFMF_NQ)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + start += PAGE_SIZE; } + if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) + vcpu->run->s.regs.gprs[reg2] = end; + 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_s390_cmma_enabled(vcpu->kvm)) + 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] = { + [0x8a] = handle_ipte_interlock, + [0x8d] = handle_epsw, + [0x8e] = handle_ipte_interlock, + [0x8f] = handle_ipte_interlock, + [0xab] = handle_essa, + [0xaf] = handle_pfmf, +}; + +int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + /* This is handled just as for the B2 instructions. */ + handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) + return handler(vcpu); + + return -EOPNOTSUPP; +} + +int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + u32 val = 0; + int reg, rc; + u64 ga; + + vcpu->stat.instruction_lctl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rs(vcpu); + + if (ga & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga); + + reg = reg1; + do { + rc = read_guest(vcpu, ga, &val, sizeof(val)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; + vcpu->arch.sie_block->gcr[reg] |= val; + ga += 4; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + + return 0; +} + +int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + u64 ga; + u32 val; + int reg, rc; + + vcpu->stat.instruction_stctl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rs(vcpu); + + if (ga & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "stctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga); + + reg = reg1; + do { + val = vcpu->arch.sie_block->gcr[reg] & 0x00000000fffffffful; + rc = write_guest(vcpu, ga, &val, sizeof(val)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + ga += 4; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + + return 0; +} + +static int handle_lctlg(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + u64 ga, val; + int reg, rc; + + vcpu->stat.instruction_lctlg++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rsy(vcpu); + + if (ga & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + reg = reg1; + + VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga); + + do { + rc = read_guest(vcpu, ga, &val, sizeof(val)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + vcpu->arch.sie_block->gcr[reg] = val; + ga += 8; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + + return 0; +} + +static int handle_stctg(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + u64 ga, val; + int reg, rc; + + vcpu->stat.instruction_stctg++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rsy(vcpu); + + if (ga & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + reg = reg1; + + VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga); + + do { + val = vcpu->arch.sie_block->gcr[reg]; + rc = write_guest(vcpu, ga, &val, sizeof(val)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + ga += 8; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + + return 0; +} + +static const intercept_handler_t eb_handlers[256] = { + [0x2f] = handle_lctlg, + [0x25] = handle_stctg, +}; + +int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; + if (handler) + return handler(vcpu); return -EOPNOTSUPP; } static int handle_tprot(struct kvm_vcpu *vcpu) { - int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; - int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; - int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12; - int disp2 = vcpu->arch.sie_block->ipb & 0x0fff; - u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0; - u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0; - struct vm_area_struct *vma; - unsigned long user_address; + u64 address1, address2; + unsigned long hva, gpa; + int ret = 0, cc = 0; + bool writable; vcpu->stat.instruction_tprot++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + kvm_s390_get_base_disp_sse(vcpu, &address1, &address2); + /* we only handle the Linux memory detection case: * access key == 0 - * guest DAT == off * everything else goes to userspace. */ if (address2 & 0xf0) return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) - return -EOPNOTSUPP; - - - /* we must resolve the address without holding the mmap semaphore. - * This is ok since the userspace hypervisor is not supposed to change - * the mapping while the guest queries the memory. Otherwise the guest - * might crash or get wrong info anyway. */ - user_address = (unsigned long) __guestaddr_to_user(vcpu, address1); - - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, user_address); - if (!vma) { - up_read(¤t->mm->mmap_sem); - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + ipte_lock(vcpu); + ret = guest_translate_address(vcpu, address1, &gpa, 1); + if (ret == PGM_PROTECTION) { + /* Write protected? Try again with read-only... */ + cc = 1; + ret = guest_translate_address(vcpu, address1, &gpa, 0); + } + if (ret) { + if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { + ret = kvm_s390_inject_program_int(vcpu, ret); + } else if (ret > 0) { + /* Translation not available */ + kvm_s390_set_psw_cc(vcpu, 3); + ret = 0; + } + goto out_unlock; } - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ)) - vcpu->arch.sie_block->gpsw.mask |= (1ul << 44); - if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ)) - vcpu->arch.sie_block->gpsw.mask |= (2ul << 44); - - up_read(¤t->mm->mmap_sem); - return 0; + hva = gfn_to_hva_prot(vcpu->kvm, gpa_to_gfn(gpa), &writable); + if (kvm_is_error_hva(hva)) { + ret = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } else { + if (!writable) + cc = 1; /* Write not permitted ==> read-only */ + kvm_s390_set_psw_cc(vcpu, cc); + /* Note: CC2 only occurs for storage keys (not supported yet) */ + } +out_unlock: + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) + ipte_unlock(vcpu); + return ret; } int kvm_s390_handle_e5(struct kvm_vcpu *vcpu) @@ -392,8 +993,7 @@ static int handle_sckpf(struct kvm_vcpu *vcpu) u32 value; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); if (vcpu->run->s.regs.gprs[0] & 0x00000000ffff0000) return kvm_s390_inject_program_int(vcpu, @@ -405,7 +1005,7 @@ static int handle_sckpf(struct kvm_vcpu *vcpu) return 0; } -static intercept_handler_t x01_handlers[256] = { +static const intercept_handler_t x01_handlers[256] = { [0x07] = handle_sckpf, }; diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 566ddf6e8df..43079a48cc9 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; @@ -53,83 +54,81 @@ 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_s390_interrupt s390int = { + .type = KVM_S390_INT_EMERGENCY, + .parm = vcpu->vcpu_id, + }; + struct kvm_vcpu *dst_vcpu = NULL; + int rc = 0; - 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); - if (!inti) - return -ENOMEM; + rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int); + if (!rc) + VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); - inti->type = KVM_S390_INT_EMERGENCY; - inti->emerg.code = vcpu->vcpu_id; + return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; +} - spin_lock(&fi->lock); - li = fi->local_int[cpu_addr]; - if (li == NULL) { - rc = SIGP_CC_NOT_OPERATIONAL; - kfree(inti); - goto unlock; +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; } - spin_lock_bh(&li->lock); - list_add_tail(&inti->list, &li->list); - atomic_set(&li->active, 1); - atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); - spin_unlock_bh(&li->lock); - rc = SIGP_CC_ORDER_CODE_ACCEPTED; - VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); -unlock: - spin_unlock(&fi->lock); - return rc; } static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) { - struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; - struct kvm_s390_local_interrupt *li; - struct kvm_s390_interrupt_info *inti; + struct kvm_s390_interrupt s390int = { + .type = KVM_S390_INT_EXTERNAL_CALL, + .parm = vcpu->vcpu_id, + }; + struct kvm_vcpu *dst_vcpu = NULL; int rc; - 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); - if (!inti) - return -ENOMEM; - - inti->type = KVM_S390_INT_EXTERNAL_CALL; - inti->extcall.code = vcpu->vcpu_id; + rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int); + if (!rc) + VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); - spin_lock(&fi->lock); - li = fi->local_int[cpu_addr]; - if (li == NULL) { - rc = SIGP_CC_NOT_OPERATIONAL; - kfree(inti); - goto unlock; - } - spin_lock_bh(&li->lock); - list_add_tail(&inti->list, &li->list); - atomic_set(&li->active, 1); - atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); - spin_unlock_bh(&li->lock); - rc = 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 rc ? rc : 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) @@ -137,53 +136,58 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action) inti->type = KVM_S390_SIGP_STOP; spin_lock_bh(&li->lock); - if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) + 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); atomic_set(&li->active, 1); atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); li->action_bits |= action; - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); 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: @@ -191,6 +195,11 @@ 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: @@ -202,16 +211,24 @@ 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; - /* make sure that the new value is valid memory */ - address = address & 0x7fffe000u; - if (copy_from_guest_absolute(vcpu, &tmp, address, 1) || - copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) { + 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 the new value is valid memory. We only need to check the + * first page, since address is 8k aligned and memory pieces are always + * at least 1MB aligned and have at least a size of 1MB. + */ + address &= 0x7fffe000u; + if (kvm_is_error_gpa(vcpu->kvm, address)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INVALID_PARAMETER; return SIGP_CC_STATUS_STORED; @@ -221,18 +238,6 @@ 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)) { @@ -248,43 +253,70 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, list_add_tail(&inti->list, &li->list); atomic_set(&li->active, 1); - if (waitqueue_active(&li->wq)) - wake_up_interruptible(&li->wq); + if (waitqueue_active(li->wq)) + wake_up_interruptible(li->wq); rc = SIGP_CC_ORDER_CODE_ACCEPTED; 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); @@ -292,31 +324,25 @@ 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; } @@ -324,8 +350,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) { int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; int r3 = vcpu->arch.sie_block->ipa & 0x000f; - int base2 = vcpu->arch.sie_block->ipb >> 28; - int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); u32 parameter; u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; u8 order_code; @@ -333,12 +357,9 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) /* sigp in userspace can exit */ if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, - PGM_PRIVILEGED_OPERATION); + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - order_code = disp2; - if (base2) - order_code += vcpu->run->s.regs.gprs[base2]; + order_code = kvm_s390_get_base_disp_rs(vcpu); if (r1 % 2) parameter = vcpu->run->s.regs.gprs[r1]; @@ -369,6 +390,10 @@ 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); @@ -378,17 +403,31 @@ 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; } @@ -396,7 +435,41 @@ 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; } + +/* + * Handle SIGP partial execution interception. + * + * This interception will occur at the source cpu when a source cpu sends an + * external call to a target cpu and the target cpu has the WAIT bit set in + * its cpuflags. Interception will occurr after the interrupt indicator bits at + * the target cpu have been set. All error cases will lead to instruction + * interception, therefore nothing is to be checked or prepared. + */ +int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) +{ + int r3 = vcpu->arch.sie_block->ipa & 0x000f; + u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; + struct kvm_vcpu *dest_vcpu; + u8 order_code = kvm_s390_get_base_disp_rs(vcpu); + + trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); + + if (order_code == SIGP_EXTERNAL_CALL) { + dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + BUG_ON(dest_vcpu == NULL); + + spin_lock_bh(&dest_vcpu->arch.local_int.lock); + if (waitqueue_active(&dest_vcpu->wq)) + wake_up_interruptible(&dest_vcpu->wq); + dest_vcpu->preempted = true; + spin_unlock_bh(&dest_vcpu->arch.local_int.lock); + + kvm_s390_set_psw_cc(vcpu, SIGP_CC_ORDER_CODE_ACCEPTED); + return 0; + } + + return -EOPNOTSUPP; +} diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h index 90fdf85b5ff..647e9d6a481 100644 --- a/arch/s390/kvm/trace-s390.h +++ b/arch/s390/kvm/trace-s390.h @@ -68,6 +68,27 @@ TRACE_EVENT(kvm_s390_destroy_vcpu, ); /* + * Trace point for start and stop of vpcus. + */ +TRACE_EVENT(kvm_s390_vcpu_start_stop, + TP_PROTO(unsigned int id, int state), + TP_ARGS(id, state), + + TP_STRUCT__entry( + __field(unsigned int, id) + __field(int, state) + ), + + TP_fast_assign( + __entry->id = id; + __entry->state = state; + ), + + TP_printk("%s cpu %d", __entry->state ? "starting" : "stopping", + __entry->id) + ); + +/* * Trace points for injection of interrupts, either per machine or * per vcpu. */ @@ -141,13 +162,13 @@ TRACE_EVENT(kvm_s390_inject_vcpu, * Trace point for the actual delivery of interrupts. */ TRACE_EVENT(kvm_s390_deliver_interrupt, - TP_PROTO(unsigned int id, __u64 type, __u32 data0, __u64 data1), + TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1), TP_ARGS(id, type, data0, data1), TP_STRUCT__entry( __field(int, id) __field(__u32, inttype) - __field(__u32, data0) + __field(__u64, data0) __field(__u64, data1) ), @@ -159,7 +180,7 @@ TRACE_EVENT(kvm_s390_deliver_interrupt, ), TP_printk("deliver interrupt (vcpu %d): type:%x (%s) " \ - "data:%08x %016llx", + "data:%08llx %016llx", __entry->id, __entry->inttype, __print_symbolic(__entry->inttype, kvm_s390_int_type), __entry->data0, __entry->data1) @@ -204,6 +225,48 @@ TRACE_EVENT(kvm_s390_stop_request, ); +/* + * Trace point for enabling channel I/O instruction support. + */ +TRACE_EVENT(kvm_s390_enable_css, + TP_PROTO(void *kvm), + TP_ARGS(kvm), + + TP_STRUCT__entry( + __field(void *, kvm) + ), + + TP_fast_assign( + __entry->kvm = kvm; + ), + + TP_printk("enabling channel I/O support (kvm @ %p)\n", + __entry->kvm) + ); + +/* + * Trace point for enabling and disabling interlocking-and-broadcasting + * suppression. + */ +TRACE_EVENT(kvm_s390_enable_disable_ibs, + TP_PROTO(unsigned int id, int state), + TP_ARGS(id, state), + + TP_STRUCT__entry( + __field(unsigned int, id) + __field(int, state) + ), + + TP_fast_assign( + __entry->id = id; + __entry->state = state; + ), + + TP_printk("%s ibs on cpu %d", + __entry->state ? "enabling" : "disabling", __entry->id) + ); + + #endif /* _TRACE_KVMS390_H */ /* This part must be outside protection */ diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h index 2b29e62351d..916834d7a73 100644 --- a/arch/s390/kvm/trace.h +++ b/arch/s390/kvm/trace.h @@ -2,8 +2,9 @@ #define _TRACE_KVM_H #include <linux/tracepoint.h> -#include <asm/sigp.h> +#include <asm/sie.h> #include <asm/debug.h> +#include <asm/dis.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm @@ -29,6 +30,66 @@ TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id, \ __entry->pswmask, __entry->pswaddr, p_args) +TRACE_EVENT(kvm_s390_skey_related_inst, + 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", "first instruction related to skeys on vcpu") + ); + +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. */ @@ -64,17 +125,6 @@ TRACE_EVENT(kvm_s390_sie_fault, VCPU_TP_PRINTK("%s", "fault in sie instruction") ); -#define sie_intercept_code \ - {0x04, "Instruction"}, \ - {0x08, "Program interruption"}, \ - {0x0C, "Instruction and program interuption"}, \ - {0x10, "External request"}, \ - {0x14, "External interruption"}, \ - {0x18, "I/O request"}, \ - {0x1C, "Wait state"}, \ - {0x20, "Validity"}, \ - {0x28, "Stop request"} - TRACE_EVENT(kvm_s390_sie_exit, TP_PROTO(VCPU_PROTO_COMMON, u8 icptcode), TP_ARGS(VCPU_ARGS_COMMON, icptcode), @@ -104,7 +154,6 @@ TRACE_EVENT(kvm_s390_intercept_instruction, TP_STRUCT__entry( VCPU_FIELD_COMMON __field(__u64, instruction) - __field(char, insn[8]) ), TP_fast_assign( @@ -115,10 +164,8 @@ TRACE_EVENT(kvm_s390_intercept_instruction, VCPU_TP_PRINTK("intercepted instruction %016llx (%s)", __entry->instruction, - insn_to_mnemonic((unsigned char *) - &__entry->instruction, - __entry->insn) ? - "unknown" : __entry->insn) + __print_symbolic(icpt_insn_decoder(__entry->instruction), + icpt_insn_codes)) ); /* @@ -166,17 +213,6 @@ TRACE_EVENT(kvm_s390_intercept_validity, * Trace points for instructions that are of special interest. */ -#define sigp_order_codes \ - {SIGP_SENSE, "sense"}, \ - {SIGP_EXTERNAL_CALL, "external call"}, \ - {SIGP_EMERGENCY_SIGNAL, "emergency signal"}, \ - {SIGP_STOP, "stop"}, \ - {SIGP_STOP_AND_STORE_STATUS, "stop and store status"}, \ - {SIGP_SET_ARCHITECTURE, "set architecture"}, \ - {SIGP_SET_PREFIX, "set prefix"}, \ - {SIGP_SENSE_RUNNING, "sense running"}, \ - {SIGP_RESTART, "restart"} - TRACE_EVENT(kvm_s390_handle_sigp, TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr, \ __u32 parameter), @@ -203,12 +239,28 @@ TRACE_EVENT(kvm_s390_handle_sigp, __entry->cpu_addr, __entry->parameter) ); -#define diagnose_codes \ - {0x10, "release pages"}, \ - {0x44, "time slice end"}, \ - {0x308, "ipl functions"}, \ - {0x500, "kvm hypercall"}, \ - {0x501, "kvm breakpoint"} +TRACE_EVENT(kvm_s390_handle_sigp_pei, + TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr), + TP_ARGS(VCPU_ARGS_COMMON, order_code, cpu_addr), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u8, order_code) + __field(__u16, cpu_addr) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->order_code = order_code; + __entry->cpu_addr = cpu_addr; + ), + + VCPU_TP_PRINTK("handle sigp pei order %02x (%s), cpu address %04x", + __entry->order_code, + __print_symbolic(__entry->order_code, + sigp_order_codes), + __entry->cpu_addr) + ); TRACE_EVENT(kvm_s390_handle_diag, TP_PROTO(VCPU_PROTO_COMMON, __u16 code), @@ -253,6 +305,31 @@ TRACE_EVENT(kvm_s390_handle_lctl, __entry->reg1, __entry->reg3, __entry->addr) ); +TRACE_EVENT(kvm_s390_handle_stctl, + TP_PROTO(VCPU_PROTO_COMMON, int g, int reg1, int reg3, u64 addr), + TP_ARGS(VCPU_ARGS_COMMON, g, reg1, reg3, addr), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(int, g) + __field(int, reg1) + __field(int, reg3) + __field(u64, addr) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->g = g; + __entry->reg1 = reg1; + __entry->reg3 = reg3; + __entry->addr = addr; + ), + + VCPU_TP_PRINTK("%s: storing cr %x-%x to %016llx", + __entry->g ? "stctg" : "stctl", + __entry->reg1, __entry->reg3, __entry->addr) + ); + TRACE_EVENT(kvm_s390_handle_prefix, TP_PROTO(VCPU_PROTO_COMMON, int set, u32 address), TP_ARGS(VCPU_ARGS_COMMON, set, address), diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 6ab0d0b5cec..c6d752e8bf2 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -2,9 +2,7 @@ # Makefile for s390-specific library files.. # -lib-y += delay.o string.o uaccess_std.o uaccess_pt.o -obj-y += usercopy.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/delay.c b/arch/s390/lib/delay.c index 42d0cf89121..a9f3d0042d5 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -32,7 +32,7 @@ static void __udelay_disabled(unsigned long long usecs) unsigned long cr0, cr6, new; u64 clock_saved, end; - end = get_clock() + (usecs << 12); + end = get_tod_clock() + (usecs << 12); clock_saved = local_tick_disable(); __ctl_store(cr0, 0, 0); __ctl_store(cr6, 6, 6); @@ -44,8 +44,7 @@ static void __udelay_disabled(unsigned long long usecs) do { set_clock_comparator(end); vtime_stop_cpu(); - local_irq_disable(); - } while (get_clock() < end); + } while (get_tod_clock_fast() < end); lockdep_on(); __ctl_load(cr0, 0, 0); __ctl_load(cr6, 6, 6); @@ -56,7 +55,7 @@ static void __udelay_enabled(unsigned long long usecs) { u64 clock_saved, end; - end = get_clock() + (usecs << 12); + end = get_tod_clock_fast() + (usecs << 12); do { clock_saved = 0; if (end < S390_lowcore.clock_comparator) { @@ -64,10 +63,9 @@ static void __udelay_enabled(unsigned long long usecs) set_clock_comparator(end); } vtime_stop_cpu(); - local_irq_disable(); if (clock_saved) local_tick_enable(clock_saved); - } while (get_clock() < end); + } while (get_tod_clock_fast() < end); } /* @@ -111,8 +109,8 @@ void udelay_simple(unsigned long long usecs) { u64 end; - end = get_clock() + (usecs << 12); - while (get_clock() < end) + end = get_tod_clock_fast() + (usecs << 12); + while (get_tod_clock_fast() < end) cpu_relax(); } @@ -122,10 +120,10 @@ void __ndelay(unsigned long long nsecs) nsecs <<= 9; do_div(nsecs, 125); - end = get_clock() + nsecs; + end = get_tod_clock_fast() + nsecs; if (nsecs & ~0xfffUL) __udelay(nsecs >> 12); - while (get_clock() < end) + while (get_tod_clock_fast() < end) barrier(); } EXPORT_SYMBOL(__ndelay); diff --git a/arch/s390/lib/find.c b/arch/s390/lib/find.c new file mode 100644 index 00000000000..922003c1b90 --- /dev/null +++ b/arch/s390/lib/find.c @@ -0,0 +1,77 @@ +/* + * MSB0 numbered special bitops handling. + * + * On s390x the bits are numbered: + * |0..............63|64............127|128...........191|192...........255| + * and on s390: + * |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 + * from the 'wrong end'. + */ + +#include <linux/compiler.h> +#include <linux/bitops.h> +#include <linux/export.h> + +unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size) +{ + const unsigned long *p = addr; + unsigned long result = 0; + unsigned long tmp; + + while (size & ~(BITS_PER_LONG - 1)) { + if ((tmp = *(p++))) + goto found; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = (*p) & (~0UL << (BITS_PER_LONG - size)); + if (!tmp) /* Are any bits set? */ + return result + size; /* Nope. */ +found: + return result + (__fls(tmp) ^ (BITS_PER_LONG - 1)); +} +EXPORT_SYMBOL(find_first_bit_inv); + +unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + const unsigned long *p = addr + (offset / BITS_PER_LONG); + unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long tmp; + + if (offset >= size) + return size; + size -= result; + offset %= BITS_PER_LONG; + if (offset) { + tmp = *(p++); + tmp &= (~0UL >> offset); + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + size -= BITS_PER_LONG; + result += BITS_PER_LONG; + } + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; +found_first: + tmp &= (~0UL << (BITS_PER_LONG - size)); + if (!tmp) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + (__fls(tmp) ^ (BITS_PER_LONG - 1)); +} +EXPORT_SYMBOL(find_next_bit_inv); diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index f709983f41f..5b0e445bc3f 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -26,83 +26,81 @@ __setup("spin_retry=", spin_retry_setup); void arch_spin_lock_wait(arch_spinlock_t *lp) { - int count = spin_retry; - unsigned int cpu = ~smp_processor_id(); + unsigned int cpu = SPINLOCK_LOCKVAL; unsigned int owner; + int count; while (1) { - owner = lp->owner_cpu; - if (!owner || smp_vcpu_scheduled(~owner)) { - for (count = spin_retry; count > 0; count--) { - if (arch_spin_is_locked(lp)) - continue; - if (_raw_compare_and_swap(&lp->owner_cpu, 0, - cpu) == 0) - return; - } - if (MACHINE_IS_LPAR) - continue; + owner = ACCESS_ONCE(lp->lock); + /* Try to get the lock if it is free. */ + if (!owner) { + if (_raw_compare_and_swap(&lp->lock, 0, cpu)) + return; + continue; } - owner = lp->owner_cpu; - if (owner) + /* Check if the lock owner is running. */ + if (!smp_vcpu_scheduled(~owner)) { + smp_yield_cpu(~owner); + continue; + } + /* Loop for a while on the lock value. */ + count = spin_retry; + do { + owner = ACCESS_ONCE(lp->lock); + } while (owner && count-- > 0); + if (!owner) + continue; + /* + * For multiple layers of hypervisors, e.g. z/VM + LPAR + * yield the CPU if the lock is still unavailable. + */ + if (!MACHINE_IS_LPAR) smp_yield_cpu(~owner); - if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) - return; } } EXPORT_SYMBOL(arch_spin_lock_wait); void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags) { - int count = spin_retry; - unsigned int cpu = ~smp_processor_id(); + unsigned int cpu = SPINLOCK_LOCKVAL; unsigned int owner; + int count; local_irq_restore(flags); while (1) { - owner = lp->owner_cpu; - if (!owner || smp_vcpu_scheduled(~owner)) { - for (count = spin_retry; count > 0; count--) { - if (arch_spin_is_locked(lp)) - continue; - local_irq_disable(); - if (_raw_compare_and_swap(&lp->owner_cpu, 0, - cpu) == 0) - return; - local_irq_restore(flags); - } - if (MACHINE_IS_LPAR) - continue; + owner = ACCESS_ONCE(lp->lock); + /* Try to get the lock if it is free. */ + if (!owner) { + local_irq_disable(); + if (_raw_compare_and_swap(&lp->lock, 0, cpu)) + return; + local_irq_restore(flags); } - owner = lp->owner_cpu; - if (owner) + /* Check if the lock owner is running. */ + if (!smp_vcpu_scheduled(~owner)) { smp_yield_cpu(~owner); - local_irq_disable(); - if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) - return; - local_irq_restore(flags); - } -} -EXPORT_SYMBOL(arch_spin_lock_wait_flags); - -int arch_spin_trylock_retry(arch_spinlock_t *lp) -{ - unsigned int cpu = ~smp_processor_id(); - int count; - - for (count = spin_retry; count > 0; count--) { - if (arch_spin_is_locked(lp)) continue; - if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) - return 1; + } + /* Loop for a while on the lock value. */ + count = spin_retry; + do { + owner = ACCESS_ONCE(lp->lock); + } while (owner && count-- > 0); + if (!owner) + continue; + /* + * For multiple layers of hypervisors, e.g. z/VM + LPAR + * yield the CPU if the lock is still unavailable. + */ + if (!MACHINE_IS_LPAR) + smp_yield_cpu(~owner); } - return 0; } -EXPORT_SYMBOL(arch_spin_trylock_retry); +EXPORT_SYMBOL(arch_spin_lock_wait_flags); -void arch_spin_relax(arch_spinlock_t *lock) +void arch_spin_relax(arch_spinlock_t *lp) { - unsigned int cpu = lock->owner_cpu; + unsigned int cpu = lp->lock; if (cpu != 0) { if (MACHINE_IS_VM || MACHINE_IS_KVM || !smp_vcpu_scheduled(~cpu)) @@ -111,6 +109,17 @@ void arch_spin_relax(arch_spinlock_t *lock) } EXPORT_SYMBOL(arch_spin_relax); +int arch_spin_trylock_retry(arch_spinlock_t *lp) +{ + int count; + + for (count = spin_retry; count > 0; count--) + if (arch_spin_trylock_once(lp)) + return 1; + return 0; +} +EXPORT_SYMBOL(arch_spin_trylock_retry); + void _raw_read_lock_wait(arch_rwlock_t *rw) { unsigned int old; @@ -121,10 +130,10 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) smp_yield(); count = spin_retry; } - if (!arch_read_can_lock(rw)) + old = ACCESS_ONCE(rw->lock); + if ((int) old < 0) continue; - old = rw->lock & 0x7fffffffU; - if (_raw_compare_and_swap(&rw->lock, old, old + 1) == old) + if (_raw_compare_and_swap(&rw->lock, old, old + 1)) return; } } @@ -141,12 +150,13 @@ void _raw_read_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags) smp_yield(); count = spin_retry; } - if (!arch_read_can_lock(rw)) + old = ACCESS_ONCE(rw->lock); + if ((int) old < 0) continue; - old = rw->lock & 0x7fffffffU; local_irq_disable(); - if (_raw_compare_and_swap(&rw->lock, old, old + 1) == old) + if (_raw_compare_and_swap(&rw->lock, old, old + 1)) return; + local_irq_restore(flags); } } EXPORT_SYMBOL(_raw_read_lock_wait_flags); @@ -157,10 +167,10 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw) int count = spin_retry; while (count-- > 0) { - if (!arch_read_can_lock(rw)) + old = ACCESS_ONCE(rw->lock); + if ((int) old < 0) continue; - old = rw->lock & 0x7fffffffU; - if (_raw_compare_and_swap(&rw->lock, old, old + 1) == old) + if (_raw_compare_and_swap(&rw->lock, old, old + 1)) return 1; } return 0; @@ -169,6 +179,7 @@ EXPORT_SYMBOL(_raw_read_trylock_retry); void _raw_write_lock_wait(arch_rwlock_t *rw) { + unsigned int old; int count = spin_retry; while (1) { @@ -176,9 +187,10 @@ void _raw_write_lock_wait(arch_rwlock_t *rw) smp_yield(); count = spin_retry; } - if (!arch_write_can_lock(rw)) + old = ACCESS_ONCE(rw->lock); + if (old) continue; - if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) + if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000)) return; } } @@ -186,6 +198,7 @@ EXPORT_SYMBOL(_raw_write_lock_wait); void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags) { + unsigned int old; int count = spin_retry; local_irq_restore(flags); @@ -194,23 +207,27 @@ void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags) smp_yield(); count = spin_retry; } - if (!arch_write_can_lock(rw)) + old = ACCESS_ONCE(rw->lock); + if (old) continue; local_irq_disable(); - if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) + if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000)) return; + local_irq_restore(flags); } } EXPORT_SYMBOL(_raw_write_lock_wait_flags); int _raw_write_trylock_retry(arch_rwlock_t *rw) { + unsigned int old; int count = spin_retry; while (count-- > 0) { - if (!arch_write_can_lock(rw)) + old = ACCESS_ONCE(rw->lock); + if (old) continue; - if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0) + if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000)) return 1; } return 0; diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c new file mode 100644 index 00000000000..53dd5d7a0c9 --- /dev/null +++ b/arch/s390/lib/uaccess.c @@ -0,0 +1,406 @@ +/* + * 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; + + load_kernel_asce(); + 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; + + load_kernel_asce(); + 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; + + load_kernel_asce(); + 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; + + load_kernel_asce(); + 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; + + 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) +{ + if (unlikely(!size)) + return 0; + load_kernel_asce(); + 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 2443ae476e3..00000000000 --- a/arch/s390/lib/uaccess_mvcos.c +++ /dev/null @@ -1,225 +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_from_user_mvcos_check(size_t size, const void __user *ptr, void *x) -{ - if (size <= 256) - return copy_from_user_std(size, ptr, x); - return copy_from_user_mvcos(size, ptr, x); -} - -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_to_user_mvcos_check(size_t size, void __user *ptr, - const void *x) -{ - if (size <= 256) - return copy_to_user_std(size, ptr, x); - return copy_to_user_mvcos(size, ptr, x); -} - -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) -{ - char buf[256]; - int rc; - size_t done, len, len_str; - - done = 0; - do { - len = min(count - done, (size_t) 256); - rc = uaccess.copy_from_user(len, src + done, buf); - if (unlikely(rc == len)) - return 0; - len -= rc; - len_str = strnlen(buf, len); - done += 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) -{ - int rc; - size_t done, len, len_str; - - done = 0; - do { - len = min(count - done, (size_t) 4096); - rc = uaccess.copy_from_user(len, src + done, dst); - if (unlikely(rc == len)) - return -EFAULT; - len -= rc; - len_str = strnlen(dst, len); - done += len_str; - } while ((len_str == len) && (done < count)); - return done; -} - -struct uaccess_ops uaccess_mvcos = { - .copy_from_user = copy_from_user_mvcos_check, - .copy_from_user_small = copy_from_user_std, - .copy_to_user = copy_to_user_mvcos_check, - .copy_to_user_small = copy_to_user_std, - .copy_in_user = copy_in_user_mvcos, - .clear_user = clear_user_mvcos, - .strnlen_user = strnlen_user_std, - .strncpy_from_user = strncpy_from_user_std, - .futex_atomic_op = futex_atomic_op_std, - .futex_atomic_cmpxchg = futex_atomic_cmpxchg_std, -}; - -struct uaccess_ops uaccess_mvcos_switch = { - .copy_from_user = copy_from_user_mvcos, - .copy_from_user_small = copy_from_user_mvcos, - .copy_to_user = copy_to_user_mvcos, - .copy_to_user_small = 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 9017a63dda3..00000000000 --- a/arch/s390/lib/uaccess_pt.c +++ /dev/null @@ -1,388 +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" - - -/* - * 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. - */ -static __always_inline unsigned long follow_table(struct mm_struct *mm, - unsigned long addr, int write) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; - - pgd = pgd_offset(mm, addr); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return -0x3aUL; - - pud = pud_offset(pgd, addr); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return -0x3bUL; - - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) - return -0x10UL; - if (pmd_large(*pmd)) { - if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO)) - return -0x04UL; - return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK); - } - if (unlikely(pmd_bad(*pmd))) - return -0x10UL; - - ptep = pte_offset_map(pmd, addr); - if (!pte_present(*ptep)) - return -0x11UL; - if (write && !pte_write(*ptep)) - return -0x04UL; - - return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK); -} - -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)) { - memcpy(to, (void __kernel __force *) from, n); - return 0; - } - 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)) { - memcpy((void __kernel __force *) to, from, n); - return 0; - } - return __user_copy_pt((unsigned long) to, (void *) from, n, 1); -} - -static size_t clear_user_pt(size_t n, void __user *to) -{ - long done, size, ret; - - if (segment_eq(get_fs(), KERNEL_DS)) { - memset((void __kernel __force *) to, 0, n); - return 0; - } - done = 0; - do { - if (n - done > PAGE_SIZE) - size = PAGE_SIZE; - else - size = n - done; - ret = __user_copy_pt((unsigned long) to + done, - &empty_zero_page, size, 1); - done += 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 (segment_eq(get_fs(), KERNEL_DS)) - return strnlen((const char __kernel __force *) src, count) + 1; - 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 n = strnlen_user_pt(count, src); - - if (!n) - return -EFAULT; - if (n > count) - n = count; - if (segment_eq(get_fs(), KERNEL_DS)) { - memcpy(dst, (const char __kernel __force *) src, n); - if (dst[n-1] == '\0') - return n-1; - else - return n; - } - if (__user_copy_pt((unsigned long) src, dst, n, 0)) - return -EFAULT; - if (dst[n-1] == '\0') - return n-1; - else - return n; -} - -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)) { - memcpy((void __force *) to, (void __force *) from, n); - return 0; - } - 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(¤t->mm->page_table_lock); - uaddr = (u32 __force __user *) - __dat_user_addr((__force unsigned long) uaddr, 1); - if (!uaddr) { - spin_unlock(¤t->mm->page_table_lock); - return -EFAULT; - } - get_page(virt_to_page(uaddr)); - spin_unlock(¤t->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(¤t->mm->page_table_lock); - uaddr = (u32 __force __user *) - __dat_user_addr((__force unsigned long) uaddr, 1); - if (!uaddr) { - spin_unlock(¤t->mm->page_table_lock); - return -EFAULT; - } - get_page(virt_to_page(uaddr)); - spin_unlock(¤t->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_from_user_small = copy_from_user_pt, - .copy_to_user = copy_to_user_pt, - .copy_to_user_small = 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/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c deleted file mode 100644 index 6fbd0633827..00000000000 --- a/arch/s390/lib/uaccess_std.c +++ /dev/null @@ -1,317 +0,0 @@ -/* - * Standard user space access functions based on mvcp/mvcs and doing - * interesting things in the secondary space mode. - * - * 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 <linux/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 - -size_t copy_from_user_std(size_t size, const void __user *ptr, void *x) -{ - unsigned long tmp1, tmp2; - - tmp1 = -256UL; - asm volatile( - "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: \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; -} - -static size_t copy_from_user_std_check(size_t size, const void __user *ptr, - void *x) -{ - if (size <= 1024) - return copy_from_user_std(size, ptr, x); - return copy_from_user_pt(size, ptr, x); -} - -size_t copy_to_user_std(size_t size, void __user *ptr, const void *x) -{ - unsigned long tmp1, tmp2; - - tmp1 = -256UL; - asm volatile( - "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: \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; -} - -static size_t copy_to_user_std_check(size_t size, void __user *ptr, - const void *x) -{ - if (size <= 1024) - return copy_to_user_std(size, ptr, x); - return copy_to_user_pt(size, ptr, x); -} - -static size_t copy_in_user_std(size_t size, void __user *to, - const void __user *from) -{ - unsigned long tmp1; - - 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 0\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; -} - -static size_t clear_user_std(size_t size, void __user *to) -{ - unsigned long tmp1, tmp2; - - 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 0\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; -} - -size_t strnlen_user_std(size_t size, 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" - " 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 0\n" - EX_TABLE(0b,1b) - : "+a" (size), "+a" (src), "=a" (tmp1), "=a" (tmp2) - : "d" (reg0) : "cc", "memory"); - return size; -} - -size_t strncpy_from_user_std(size_t size, const char __user *src, char *dst) -{ - register unsigned long reg0 asm("0") = 0UL; - unsigned long tmp1, tmp2; - - asm volatile( - " la %3,0(%1)\n" - " la %4,0(%0,%1)\n" - " sacf 256\n" - "0: srst %4,%3\n" - " jo 0b\n" - " sacf 0\n" - " la %0,0(%4)\n" - " jh 1f\n" /* found \0 in string ? */ - " "AHI" %4,1\n" /* include \0 in copy */ - "1:"SLR" %0,%1\n" /* %0 = return length (without \0) */ - " "SLR" %4,%1\n" /* %4 = copy length (including \0) */ - "2: mvcp 0(%4,%2),0(%1),%5\n" - " jz 9f\n" - "3:"AHI" %4,-256\n" - " la %1,256(%1)\n" - " la %2,256(%2)\n" - "4: mvcp 0(%4,%2),0(%1),%5\n" - " jnz 3b\n" - " j 9f\n" - "7: sacf 0\n" - "8:"LHI" %0,%6\n" - "9:\n" - EX_TABLE(0b,7b) EX_TABLE(2b,8b) EX_TABLE(4b,8b) - : "+a" (size), "+a" (src), "+d" (dst), "=a" (tmp1), "=a" (tmp2) - : "d" (reg0), "K" (-EFAULT) : "cc", "memory"); - return size; -} - -#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 0\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"); - -int futex_atomic_op_std(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; - } - *old = oldval; - return ret; -} - -int futex_atomic_cmpxchg_std(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) -{ - int ret; - - asm volatile( - " sacf 256\n" - "0: cs %1,%4,0(%5)\n" - "1: la %0,0\n" - "2: sacf 0\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; -} - -struct uaccess_ops uaccess_std = { - .copy_from_user = copy_from_user_std_check, - .copy_from_user_small = copy_from_user_std, - .copy_to_user = copy_to_user_std_check, - .copy_to_user_small = copy_to_user_std, - .copy_in_user = copy_in_user_std, - .clear_user = clear_user_std, - .strnlen_user = strnlen_user_std, - .strncpy_from_user = strncpy_from_user_std, - .futex_atomic_op = futex_atomic_op_std, - .futex_atomic_cmpxchg = futex_atomic_cmpxchg_std, -}; diff --git a/arch/s390/lib/usercopy.c b/arch/s390/lib/usercopy.c deleted file mode 100644 index 14b363fec8a..00000000000 --- a/arch/s390/lib/usercopy.c +++ /dev/null @@ -1,8 +0,0 @@ -#include <linux/module.h> -#include <linux/bug.h> - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); diff --git a/arch/s390/math-emu/math.c b/arch/s390/math-emu/math.c index 58bff541fde..a6ba0d72433 100644 --- a/arch/s390/math-emu/math.c +++ b/arch/s390/math-emu/math.c @@ -19,6 +19,8 @@ #include <math-emu/double.h> #include <math-emu/quad.h> +#define FPC_VALID_MASK 0xF8F8FF03 + /* * I miss a macro to round a floating point number to the * nearest integer in the same floating point format. diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index 640bea12303..839592ca265 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -3,7 +3,7 @@ # obj-y := init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o -obj-y += page-states.o gup.o extable.o pageattr.o +obj-y += page-states.o gup.o extable.o pageattr.o mem_detect.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 479e9428291..79ddd580d60 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -253,12 +253,12 @@ static int cmm_skip_blanks(char *cp, char **endp) static struct ctl_table cmm_table[]; -static int cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int cmm_pages_handler(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[16], *p; + unsigned int len; long nr; - int len; if (!*lenp || (*ppos && !write)) { *lenp = 0; @@ -293,12 +293,12 @@ static int cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer, return 0; } -static int cmm_timeout_handler(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int cmm_timeout_handler(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[64], *p; long nr, seconds; - int len; + unsigned int len; if (!*lenp || (*ppos && !write)) { *lenp = 0; @@ -458,12 +458,10 @@ static int __init cmm_init(void) if (rc) goto out_pm; cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); - rc = IS_ERR(cmm_thread_ptr) ? PTR_ERR(cmm_thread_ptr) : 0; - if (rc) - goto out_kthread; - return 0; + if (!IS_ERR(cmm_thread_ptr)) + return 0; -out_kthread: + rc = PTR_ERR(cmm_thread_ptr); unregister_pm_notifier(&cmm_power_notifier); out_pm: unregister_oom_notifier(&cmm_oom_nb); diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 04e4892247d..46d517c3c76 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -49,10 +49,13 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level) { "ASCE", "PGD", "PUD", "PMD", "PTE" }; seq_printf(m, "%s ", level_name[level]); - if (pr & _PAGE_INVALID) + if (pr & _PAGE_INVALID) { seq_printf(m, "I\n"); - else - seq_printf(m, "%s\n", pr & _PAGE_RO ? "RO" : "RW"); + return; + } + seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW "); + seq_printf(m, "%s", pr & _PAGE_CO ? "CO " : " "); + seq_putc(m, '\n'); } static void note_page(struct seq_file *m, struct pg_state *st, @@ -102,12 +105,12 @@ static void note_page(struct seq_file *m, struct pg_state *st, } /* - * The actual page table walker functions. In order to keep the implementation - * of print_prot() short, we only check and pass _PAGE_INVALID and _PAGE_RO - * flags to note_page() if a region, segment or page table entry is invalid or - * read-only. - * After all it's just a hint that the current level being walked contains an - * invalid or read-only entry. + * The actual page table walker functions. In order to keep the + * implementation of print_prot() short, we only check and pass + * _PAGE_INVALID and _PAGE_PROTECT flags to note_page() if a region, + * segment or page table entry is invalid or read-only. + * After all it's just a hint that the current level being walked + * contains an invalid or read-only entry. */ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t *pmd, unsigned long addr) @@ -119,12 +122,18 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) { st->current_address = addr; pte = pte_offset_kernel(pmd, addr); - prot = pte_val(*pte) & (_PAGE_RO | _PAGE_INVALID); + prot = pte_val(*pte) & (_PAGE_PROTECT | _PAGE_INVALID); note_page(m, st, prot, 4); addr += PAGE_SIZE; } } +#ifdef CONFIG_64BIT +#define _PMD_PROT_MASK (_SEGMENT_ENTRY_PROTECT | _SEGMENT_ENTRY_CO) +#else +#define _PMD_PROT_MASK 0 +#endif + static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t *pud, unsigned long addr) { @@ -137,7 +146,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pmd = pmd_offset(pud, addr); if (!pmd_none(*pmd)) { if (pmd_large(*pmd)) { - prot = pmd_val(*pmd) & _SEGMENT_ENTRY_RO; + prot = pmd_val(*pmd) & _PMD_PROT_MASK; note_page(m, st, prot, 3); } else walk_pte_level(m, st, pmd, addr); @@ -147,6 +156,12 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, } } +#ifdef CONFIG_64BIT +#define _PUD_PROT_MASK (_REGION3_ENTRY_RO | _REGION3_ENTRY_CO) +#else +#define _PUD_PROT_MASK 0 +#endif + static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t *pgd, unsigned long addr) { @@ -159,7 +174,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pud = pud_offset(pgd, addr); if (!pud_none(*pud)) if (pud_large(*pud)) { - prot = pud_val(*pud) & _PAGE_RO; + prot = pud_val(*pud) & _PUD_PROT_MASK; note_page(m, st, prot, 2); } else walk_pmd_level(m, st, pud, addr); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 2fb9e63b8fc..3f3b35403d0 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; @@ -105,26 +106,151 @@ 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; - if (s390_user_mode == HOME_SPACE_MODE) - /* User space if the access has been done via home space. */ - return trans_exc_code == 3; - /* - * If the user space is not the home space the kernel runs in home - * space. Access via secondary space has already been covered, - * 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 int bad_address(void *p) +{ + unsigned long dummy; + + return probe_kernel_address((unsigned long *)p, dummy); +} + +#ifdef CONFIG_64BIT +static void dump_pagetable(unsigned long asce, unsigned long address) +{ + unsigned long *table = __va(asce & PAGE_MASK); + + pr_alert("AS:%016lx ", asce); + switch (asce & _ASCE_TYPE_MASK) { + case _ASCE_TYPE_REGION1: + table = table + ((address >> 53) & 0x7ff); + if (bad_address(table)) + goto bad; + pr_cont("R1:%016lx ", *table); + if (*table & _REGION_ENTRY_INVALID) + goto out; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + /* fallthrough */ + case _ASCE_TYPE_REGION2: + table = table + ((address >> 42) & 0x7ff); + if (bad_address(table)) + goto bad; + pr_cont("R2:%016lx ", *table); + if (*table & _REGION_ENTRY_INVALID) + goto out; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + /* fallthrough */ + case _ASCE_TYPE_REGION3: + table = table + ((address >> 31) & 0x7ff); + if (bad_address(table)) + goto bad; + pr_cont("R3:%016lx ", *table); + if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE)) + goto out; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + /* fallthrough */ + case _ASCE_TYPE_SEGMENT: + table = table + ((address >> 20) & 0x7ff); + if (bad_address(table)) + goto bad; + pr_cont(KERN_CONT "S:%016lx ", *table); + if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE)) + goto out; + table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); + } + table = table + ((address >> 12) & 0xff); + if (bad_address(table)) + goto bad; + pr_cont("P:%016lx ", *table); +out: + pr_cont("\n"); + return; +bad: + pr_cont("BAD\n"); +} + +#else /* CONFIG_64BIT */ + +static void dump_pagetable(unsigned long asce, unsigned long address) +{ + unsigned long *table = __va(asce & PAGE_MASK); + + pr_alert("AS:%08lx ", asce); + table = table + ((address >> 20) & 0x7ff); + if (bad_address(table)) + goto bad; + pr_cont("S:%08lx ", *table); + if (*table & _SEGMENT_ENTRY_INVALID) + goto out; + table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); + table = table + ((address >> 12) & 0xff); + if (bad_address(table)) + goto bad; + pr_cont("P:%08lx ", *table); +out: + pr_cont("\n"); + return; +bad: + pr_cont("BAD\n"); +} + +#endif /* CONFIG_64BIT */ + +static void dump_fault_info(struct pt_regs *regs) +{ + unsigned long asce; + + pr_alert("Fault in "); + switch (regs->int_parm_long & 3) { + case 3: + pr_cont("home space "); + break; + case 2: + pr_cont("secondary space "); + break; + case 1: + pr_cont("access register "); + break; + case 0: + pr_cont("primary space "); + break; + } + pr_cont("mode while using "); + if (!user_space_fault(regs)) { + asce = S390_lowcore.kernel_asce; + pr_cont("kernel "); + } +#ifdef CONFIG_PGSTE + else if ((current->flags & PF_VCPU) && S390_lowcore.gmap) { + struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; + asce = gmap->asce; + pr_cont("gmap "); + } +#endif + else { + asce = S390_lowcore.user_asce; + pr_cont("user "); + } + pr_cont("ASCE.\n"); + dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK); } static inline void report_user_fault(struct pt_regs *regs, long signr) @@ -139,8 +265,9 @@ static inline void report_user_fault(struct pt_regs *regs, long signr) regs->int_code); print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN); printk(KERN_CONT "\n"); - printk(KERN_ALERT "failing address: %lX\n", - regs->int_parm_long & __FAIL_ADDR_MASK); + printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n", + regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long); + dump_fault_info(regs); show_regs(regs); } @@ -176,13 +303,15 @@ 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); + " in virtual kernel address space\n"); else printk(KERN_ALERT "Unable to handle kernel paging request" - " at virtual user address %p\n", (void *)address); - + " in virtual user address space\n"); + printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n", + regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long); + dump_fault_info(regs); die(regs, "Oops"); do_exit(SIGKILL); } @@ -232,6 +361,7 @@ 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: @@ -269,6 +399,9 @@ 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; @@ -282,7 +415,7 @@ static inline int do_exception(struct pt_regs *regs, int access) * The instruction that caused the program check has * been nullified. Don't signal single step via SIGTRAP. */ - clear_tsk_thread_flag(tsk, TIF_PER_TRAP); + clear_pt_regs_flag(regs, PIF_PER_TRAP); if (notify_page_fault(regs)) return 0; @@ -296,20 +429,23 @@ 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; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) flags |= FAULT_FLAG_WRITE; 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; @@ -318,6 +454,8 @@ 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 @@ -374,9 +512,19 @@ 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; @@ -395,8 +543,13 @@ void __kprobes do_protection_exception(struct pt_regs *regs) int fault; trans_exc_code = regs->int_parm_long; - /* Protection exception is suppressing, decrement psw address. */ - regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16); + /* + * Protection exceptions are suppressing, decrement psw address. + * The exception to this rule are aborted transactions, for these + * the PSW already points to the correct location. + */ + if (!(regs->int_code & 0x200)) + regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16); /* * Check for low-address protection. This needs to be treated * as a special case because the translation exception code @@ -421,67 +574,6 @@ void __kprobes do_dat_exception(struct pt_regs *regs) do_fault_error(regs, fault); } -#ifdef CONFIG_64BIT -void __kprobes do_asce_exception(struct pt_regs *regs) -{ - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - unsigned long trans_exc_code; - - /* - * The instruction that caused the program check has - * been nullified. Don't signal single step via SIGTRAP. - */ - clear_tsk_thread_flag(current, TIF_PER_TRAP); - - trans_exc_code = regs->int_parm_long; - if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) - goto no_context; - - down_read(&mm->mmap_sem); - vma = find_vma(mm, trans_exc_code & __FAIL_ADDR_MASK); - up_read(&mm->mmap_sem); - - if (vma) { - update_mm(mm, current); - return; - } - - /* User mode accesses just cause a SIGSEGV */ - if (user_mode(regs)) { - do_sigsegv(regs, SEGV_MAPERR); - return; - } - -no_context: - do_no_context(regs); -} -#endif - -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(®s, 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. @@ -634,8 +726,8 @@ out: put_task_struct(tsk); } -static int __cpuinit pfault_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int pfault_cpu_notify(struct notifier_block *self, unsigned long action, + void *hcpu) { struct thread_struct *thread, *next; struct task_struct *tsk; @@ -662,18 +754,18 @@ 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; if (rc) goto out_pfault; - service_subclass_irq_register(); + irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); hotcpu_notifier(pfault_cpu_notify, 0); 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/gup.c b/arch/s390/mm/gup.c index 1f5315d1215..639fce46400 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -24,7 +24,7 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, pte_t *ptep, pte; struct page *page; - mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL; + mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL; ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr); do { @@ -55,8 +55,8 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, struct page *head, *page, *tail; int refs; - result = write ? 0 : _SEGMENT_ENTRY_RO; - mask = result | _SEGMENT_ENTRY_INV; + result = write ? 0 : _SEGMENT_ENTRY_PROTECT; + mask = result | _SEGMENT_ENTRY_INVALID; if ((pmd_val(pmd) & mask) != result) return 0; VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT)); @@ -180,9 +180,15 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, addr = start; len = (unsigned long) nr_pages << PAGE_SHIFT; end = start + len; - if ((end < start) || (end > TASK_SIZE)) + if ((end <= start) || (end > TASK_SIZE)) return 0; - + /* + * local_irq_save() doesn't prevent pagetable teardown, but does + * prevent the pagetables from being freed on s390. + * + * So long as we atomically load page table pointers versus teardown, + * we can follow the address down to the the page and take a ref on it. + */ local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { @@ -219,63 +225,22 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp, pgd; - int nr = 0; + int nr, ret; start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if ((end < start) || (end > TASK_SIZE)) - goto slow_irqon; - - /* - * local_irq_disable() doesn't prevent pagetable teardown, but does - * prevent the pagetables from being freed on s390. - * - * So long as we atomically load page table pointers versus teardown, - * we can follow the address down to the the page and take a ref on it. - */ - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd = *pgdp; - barrier(); - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgdp, pgd, addr, next, write, pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; -slow: - local_irq_enable(); -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, start, - (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); - up_read(&mm->mmap_sem); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } + nr = __get_user_pages_fast(start, nr_pages, write, pages); + if (nr == nr_pages) + return nr; + + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + nr_pages - nr, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + /* Have to be a bit careful with return values */ + if (nr > 0) + ret = (ret < 0) ? nr : ret + nr; + return ret; } diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 532525ec88c..0ff66a7e29b 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -8,21 +8,124 @@ #include <linux/mm.h> #include <linux/hugetlb.h> +static inline pmd_t __pte_to_pmd(pte_t pte) +{ + int none, young, prot; + pmd_t pmd; + + /* + * Convert encoding pte bits pmd bits + * .IR...wrdytp ..R...I...y. + * empty .10...000000 -> ..0...1...0. + * prot-none, clean, old .11...000001 -> ..0...1...1. + * prot-none, clean, young .11...000101 -> ..1...1...1. + * prot-none, dirty, old .10...001001 -> ..0...1...1. + * prot-none, dirty, young .10...001101 -> ..1...1...1. + * read-only, clean, old .11...010001 -> ..1...1...0. + * read-only, clean, young .01...010101 -> ..1...0...1. + * read-only, dirty, old .11...011001 -> ..1...1...0. + * read-only, dirty, young .01...011101 -> ..1...0...1. + * read-write, clean, old .11...110001 -> ..0...1...0. + * read-write, clean, young .01...110101 -> ..0...0...1. + * read-write, dirty, old .10...111001 -> ..0...1...0. + * read-write, dirty, young .00...111101 -> ..0...0...1. + * Huge ptes are dirty by definition, a clean pte is made dirty + * by the conversion. + */ + if (pte_present(pte)) { + pmd_val(pmd) = pte_val(pte) & PAGE_MASK; + if (pte_val(pte) & _PAGE_INVALID) + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; + none = (pte_val(pte) & _PAGE_PRESENT) && + !(pte_val(pte) & _PAGE_READ) && + !(pte_val(pte) & _PAGE_WRITE); + prot = (pte_val(pte) & _PAGE_PROTECT) && + !(pte_val(pte) & _PAGE_WRITE); + young = pte_val(pte) & _PAGE_YOUNG; + if (none || young) + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + if (prot || (none && young)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + } else + pmd_val(pmd) = _SEGMENT_ENTRY_INVALID; + return pmd; +} + +static inline pte_t __pmd_to_pte(pmd_t pmd) +{ + pte_t pte; + + /* + * Convert encoding pmd bits pte bits + * ..R...I...y. .IR...wrdytp + * empty ..0...1...0. -> .10...000000 + * prot-none, old ..0...1...1. -> .10...001001 + * prot-none, young ..1...1...1. -> .10...001101 + * read-only, old ..1...1...0. -> .11...011001 + * read-only, young ..1...0...1. -> .01...011101 + * read-write, old ..0...1...0. -> .10...111001 + * read-write, young ..0...0...1. -> .00...111101 + * Huge ptes are dirty by definition + */ + if (pmd_present(pmd)) { + pte_val(pte) = _PAGE_PRESENT | _PAGE_LARGE | _PAGE_DIRTY | + (pmd_val(pmd) & PAGE_MASK); + if (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) + pte_val(pte) |= _PAGE_INVALID; + if (pmd_prot_none(pmd)) { + if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) + pte_val(pte) |= _PAGE_YOUNG; + } else { + pte_val(pte) |= _PAGE_READ; + if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) + pte_val(pte) |= _PAGE_PROTECT; + else + pte_val(pte) |= _PAGE_WRITE; + if (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) + pte_val(pte) |= _PAGE_YOUNG; + } + } else + pte_val(pte) = _PAGE_INVALID; + return pte; +} void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *pteptr, pte_t pteval) + pte_t *ptep, pte_t pte) { - pmd_t *pmdp = (pmd_t *) pteptr; - unsigned long mask; + pmd_t pmd; + pmd = __pte_to_pmd(pte); if (!MACHINE_HAS_HPAGE) { - pteptr = (pte_t *) pte_page(pteval)[1].index; - mask = pte_val(pteval) & - (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO); - pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) |= pte_page(pte)[1].index; + } else + pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO; + *(pmd_t *) ptep = pmd; +} + +pte_t huge_ptep_get(pte_t *ptep) +{ + unsigned long origin; + pmd_t pmd; + + pmd = *(pmd_t *) ptep; + if (!MACHINE_HAS_HPAGE && pmd_present(pmd)) { + origin = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) |= *(unsigned long *) origin; } + return __pmd_to_pte(pmd); +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *) ptep; + pte_t pte = huge_ptep_get(ptep); - pmd_val(*pmdp) = pte_val(pteval); + pmdp_flush_direct(mm, addr, pmdp); + pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY; + return pte; } int arch_prepare_hugepage(struct page *page) @@ -39,7 +142,7 @@ int arch_prepare_hugepage(struct page *page) if (!ptep) return -ENOMEM; - pte = mk_pte(page, PAGE_RW); + pte_val(pte) = addr; for (i = 0; i < PTRS_PER_PTE; i++) { set_pte_at(&init_mm, addr + i * PAGE_SIZE, ptep + i, pte); pte_val(pte) += PAGE_SIZE; @@ -58,7 +161,7 @@ void arch_release_hugepage(struct page *page) ptep = (pte_t *) page[1].index; if (!ptep) return; - clear_table((unsigned long *) ptep, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) ptep, _PAGE_INVALID, PTRS_PER_PTE * sizeof(pte_t)); page_table_free(&init_mm, (unsigned long *) ptep); page[1].index = 0; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index ae672f41c46..0c1073ed1e8 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/pagemap.h> #include <linux/bootmem.h> +#include <linux/memory.h> #include <linux/pfn.h> #include <linux/poison.h> #include <linux/initrd.h> @@ -36,17 +37,17 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/ctl_reg.h> +#include <asm/sclp.h> pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE))); unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); -static unsigned long __init setup_zero_pages(void) +static void __init setup_zero_pages(void) { struct cpuid cpu_id; unsigned int order; - unsigned long size; struct page *page; int i; @@ -63,10 +64,19 @@ static unsigned long __init setup_zero_pages(void) break; case 0x2097: /* z10 */ case 0x2098: /* z10 */ - default: + case 0x2817: /* z196 */ + case 0x2818: /* z196 */ order = 2; break; + case 0x2827: /* zEC12 */ + case 0x2828: /* zEC12 */ + default: + order = 5; + break; } + /* Limit number of empty zero pages for small memory sizes */ + if (order > 2 && totalram_pages <= 16384) + order = 2; empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!empty_zero_page) @@ -75,14 +85,11 @@ static unsigned long __init setup_zero_pages(void) page = virt_to_page((void *) empty_zero_page); split_page(page, order); for (i = 1 << order; i > 0; i--) { - SetPageReserved(page); + mark_page_reserved(page); page++; } - size = PAGE_SIZE << order; - zero_page_mask = (size - 1) & PAGE_MASK; - - return 1UL << order; + zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; } /* @@ -117,8 +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)); @@ -129,63 +134,37 @@ void __init paging_init(void) void __init mem_init(void) { - unsigned long codesize, reservedpages, datasize, initsize; + 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 = num_physpages = max_low_pfn; + max_mapnr = max_low_pfn; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); /* Setup guest page hinting */ cmma_init(); /* this will put all low memory onto the freelists */ - totalram_pages += free_all_bootmem(); - totalram_pages -= setup_zero_pages(); /* Setup zeroed pages. */ - - reservedpages = 0; - - codesize = (unsigned long) &_etext - (unsigned long) &_text; - datasize = (unsigned long) &_edata - (unsigned long) &_etext; - initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n", - nr_free_pages() << (PAGE_SHIFT-10), - max_mapnr << (PAGE_SHIFT-10), - codesize >> 10, - reservedpages << (PAGE_SHIFT-10), - datasize >>10, - initsize >> 10); + free_all_bootmem(); + setup_zero_pages(); /* Setup zeroed pages. */ + + mem_init_print_info(NULL); printk("Write protected kernel read-only data: %#lx - %#lx\n", (unsigned long)&_stext, PFN_ALIGN((unsigned long)&_eshared) - 1); } -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ - unsigned long addr = begin; - - if (begin >= end) - return; - for (; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)(addr & PAGE_MASK), POISON_FREE_INITMEM, - PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); -} - void free_initmem(void) { - free_init_pages("unused kernel memory", - (unsigned long)&__init_begin, - (unsigned long)&__init_end); + free_initmem_default(POISON_FREE_INITMEM); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", start, end); + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); } #endif @@ -228,4 +207,25 @@ int arch_add_memory(int nid, u64 start, u64 size) vmem_remove_mapping(start, size); return rc; } + +unsigned long memory_block_size_bytes(void) +{ + /* + * Make sure the memory block size is always greater + * or equal than the memory increment size. + */ + return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp_get_rzm()); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + /* + * There is no hardware or firmware interface which could trigger a + * hot memory remove on s390. So there is nothing that needs to be + * implemented. + */ + return -EBUSY; +} +#endif #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 921fa541dc0..2a2e35416d2 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -14,6 +14,7 @@ #include <linux/gfp.h> #include <linux/cpu.h> #include <asm/ctl_reg.h> +#include <asm/io.h> /* * This function writes to kernel memory bypassing DAT and possible @@ -127,7 +128,7 @@ void memcpy_absolute(void *dest, void *src, size_t count) /* * Copy memory from kernel (real) to user (virtual) */ -int copy_to_user_real(void __user *dest, void *src, size_t count) +int copy_to_user_real(void __user *dest, void *src, unsigned long count) { int offs = 0, size, rc; char *buf; @@ -151,32 +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/mem_detect.c b/arch/s390/mm/mem_detect.c new file mode 100644 index 00000000000..5535cfe0ee1 --- /dev/null +++ b/arch/s390/mm/mem_detect.c @@ -0,0 +1,65 @@ +/* + * Copyright IBM Corp. 2008, 2009 + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/memblock.h> +#include <linux/init.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <asm/ipl.h> +#include <asm/sclp.h> +#include <asm/setup.h> + +#define ADDR2G (1ULL << 31) + +#define CHUNK_READ_WRITE 0 +#define CHUNK_READ_ONLY 1 + +static inline void memblock_physmem_add(phys_addr_t start, phys_addr_t size) +{ + memblock_add_range(&memblock.memory, start, size, 0, 0); + memblock_add_range(&memblock.physmem, start, size, 0, 0); +} + +void __init detect_memory_memblock(void) +{ + unsigned long long memsize, rnmax, rzm; + unsigned long addr, size; + int type; + + rzm = sclp_get_rzm(); + rnmax = sclp_get_rnmax(); + memsize = rzm * rnmax; + if (!rzm) + rzm = 1ULL << 17; + if (IS_ENABLED(CONFIG_32BIT)) { + rzm = min(ADDR2G, rzm); + memsize = min(ADDR2G, memsize); + } + max_physmem_end = memsize; + addr = 0; + /* keep memblock lists close to the kernel */ + memblock_set_bottom_up(true); + do { + size = 0; + type = tprot(addr); + do { + size += rzm; + if (max_physmem_end && addr + size >= max_physmem_end) + break; + } while (type == tprot(addr + size)); + if (type == CHUNK_READ_WRITE || type == CHUNK_READ_ONLY) { + if (max_physmem_end && (addr + size > max_physmem_end)) + size = max_physmem_end - addr; + memblock_physmem_add(addr, size); + } + addr += size; + } while (addr < max_physmem_end); + memblock_set_bottom_up(false); + if (!max_physmem_end) + max_physmem_end = memblock_end_of_DRAM(); +} diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index c59a5efa58b..9b436c21195 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -64,6 +64,11 @@ static unsigned long mmap_rnd(void) return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; } +static unsigned long mmap_base_legacy(void) +{ + return TASK_UNMAPPED_BASE + mmap_rnd(); +} + static inline unsigned long mmap_base(void) { unsigned long gap = rlimit(RLIMIT_STACK); @@ -89,29 +94,24 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * bit is set, or if the expected stack growth is unlimited: */ if (mmap_is_legacy()) { - mm->mmap_base = TASK_UNMAPPED_BASE; + mm->mmap_base = mmap_base_legacy(); mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } #else -int s390_mmap_check(unsigned long addr, unsigned long len) +int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) { - int rc; - - if (!is_compat_task() && - len >= TASK_SIZE && TASK_SIZE < (1UL << 53)) { - rc = crst_table_upgrade(current->mm, 1UL << 53); - if (rc) - return rc; - update_mm(current->mm, current); - } + if (is_compat_task() || (TASK_SIZE >= (1UL << 53))) + return 0; + if (!(flags & MAP_FIXED)) + addr = 0; + if ((addr + len) >= TASK_SIZE) + return crst_table_upgrade(current->mm, 1UL << 53); return 0; } @@ -131,7 +131,6 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, rc = crst_table_upgrade(mm, 1UL << 53); if (rc) return (unsigned long) rc; - update_mm(mm, current); area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); } return area; @@ -154,7 +153,6 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, rc = crst_table_upgrade(mm, 1UL << 53); if (rc) return (unsigned long) rc; - update_mm(mm, current); area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } @@ -171,13 +169,11 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * bit is set, or if the expected stack growth is unlimited: */ if (mmap_is_legacy()) { - mm->mmap_base = TASK_UNMAPPED_BASE; + mm->mmap_base = mmap_base_legacy(); mm->get_unmapped_area = s390_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = s390_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 29ccee3651f..8400f494623 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -9,31 +9,26 @@ #include <asm/pgtable.h> #include <asm/page.h> -void storage_key_init_range(unsigned long start, unsigned long end) +#if PAGE_DEFAULT_KEY +static inline unsigned long sske_frame(unsigned long addr, unsigned char skey) { - unsigned long boundary, function, size; + asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0" + : [addr] "+a" (addr) : [skey] "d" (skey)); + return addr; +} + +void __storage_key_init_range(unsigned long start, unsigned long end) +{ + unsigned long boundary, size; while (start < end) { - if (MACHINE_HAS_EDAT2) { - /* set storage keys for a 2GB frame */ - function = 0x22000 | PAGE_DEFAULT_KEY; - size = 1UL << 31; - boundary = (start + size) & ~(size - 1); - if (boundary <= end) { - do { - start = pfmf(function, start); - } while (start < boundary); - continue; - } - } if (MACHINE_HAS_EDAT1) { /* set storage keys for a 1MB frame */ - function = 0x21000 | PAGE_DEFAULT_KEY; size = 1UL << 20; boundary = (start + size) & ~(size - 1); if (boundary <= end) { do { - start = pfmf(function, start); + start = sske_frame(start, PAGE_DEFAULT_KEY); } while (start < boundary); continue; } @@ -42,6 +37,7 @@ void storage_key_init_range(unsigned long start, unsigned long end) start += PAGE_SIZE; } } +#endif static pte_t *walk_page_table(unsigned long addr) { @@ -124,10 +120,10 @@ void kernel_map_pages(struct page *page, int numpages, int enable) pte = pte_offset_kernel(pmd, address); if (!enable) { __ptep_ipte(address, pte); - pte_val(*pte) = _PAGE_TYPE_EMPTY; + pte_val(*pte) = _PAGE_INVALID; continue; } - *pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW)); + pte_val(*pte) = __pa(address); } } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index ae44d2a3431..37b8241ec78 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> @@ -48,12 +49,25 @@ void crst_table_free(struct mm_struct *mm, unsigned long *table) } #ifdef CONFIG_64BIT +static void __crst_table_upgrade(void *arg) +{ + struct mm_struct *mm = arg; + + if (current->active_mm == mm) { + clear_user_asce(); + set_user_asce(mm); + } + __tlb_flush_local(); +} + int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) { unsigned long *table, *pgd; unsigned long entry; + int flush; BUG_ON(limit > (1UL << 53)); + flush = 0; repeat: table = crst_table_alloc(mm); if (!table) @@ -79,12 +93,15 @@ repeat: mm->pgd = (pgd_t *) table; mm->task_size = mm->context.asce_limit; table = NULL; + flush = 1; } spin_unlock_bh(&mm->page_table_lock); if (table) crst_table_free(mm, table); if (mm->context.asce_limit < limit) goto repeat; + if (flush) + on_each_cpu(__crst_table_upgrade, mm, 0); return 0; } @@ -92,6 +109,10 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) { pgd_t *pgd; + if (current->active_mm == mm) { + clear_user_asce(); + __tlb_flush_mm(mm); + } while (mm->context.asce_limit > limit) { pgd = mm->pgd; switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) { @@ -114,6 +135,8 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) mm->task_size = mm->context.asce_limit; crst_table_free(mm, (unsigned long *) pgd); } + if (current->active_mm == mm) + set_user_asce(mm); } #endif @@ -161,7 +184,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table) struct gmap_rmap *rmap; struct page *page; - if (*table & _SEGMENT_ENTRY_INV) + if (*table & _SEGMENT_ENTRY_INVALID) return 0; page = pfn_to_page(*table >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; @@ -172,14 +195,14 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table) kfree(rmap); break; } - *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + *table = mp->vmaddr | _SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_PROTECT; return 1; } 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(); @@ -198,7 +221,7 @@ 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(); @@ -245,7 +268,9 @@ EXPORT_SYMBOL_GPL(gmap_disable); * gmap_alloc_table is assumed to be called with mmap_sem held */ static int gmap_alloc_table(struct gmap *gmap, - unsigned long *table, unsigned long init) + unsigned long *table, unsigned long init) + __releases(&gmap->mm->page_table_lock) + __acquires(&gmap->mm->page_table_lock) { struct page *page; unsigned long *new; @@ -258,7 +283,7 @@ static int gmap_alloc_table(struct gmap *gmap, return -ENOMEM; new = (unsigned long *) page_to_phys(page); crst_table_init(new, init); - if (*table & _REGION_ENTRY_INV) { + if (*table & _REGION_ENTRY_INVALID) { list_add(&page->lru, &gmap->crst_list); *table = (unsigned long) new | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); @@ -273,7 +298,7 @@ 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) { @@ -292,22 +317,22 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) for (off = 0; off < len; off += PMD_SIZE) { /* Walk the guest addr space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); - if (*table & _REGION_ENTRY_INV) + if (*table & _REGION_ENTRY_INVALID) goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 42) & 0x7ff); - if (*table & _REGION_ENTRY_INV) + if (*table & _REGION_ENTRY_INVALID) goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 31) & 0x7ff); - if (*table & _REGION_ENTRY_INV) + if (*table & _REGION_ENTRY_INVALID) goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 20) & 0x7ff); /* Clear segment table entry in guest address space. */ flush |= gmap_unlink_segment(gmap, table); - *table = _SEGMENT_ENTRY_INV; + *table = _SEGMENT_ENTRY_INVALID; } out: spin_unlock(&gmap->mm->page_table_lock); @@ -324,7 +349,7 @@ 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) @@ -335,7 +360,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, if ((from | to | len) & (PMD_SIZE - 1)) return -EINVAL; - if (len == 0 || from + len > PGDIR_SIZE || + if (len == 0 || from + len > TASK_MAX_SIZE || from + len < from || to + len < to) return -EINVAL; @@ -345,17 +370,17 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, for (off = 0; off < len; off += PMD_SIZE) { /* Walk the gmap address space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); - if ((*table & _REGION_ENTRY_INV) && + if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY)) goto out_unmap; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 42) & 0x7ff); - if ((*table & _REGION_ENTRY_INV) && + if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY)) goto out_unmap; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 31) & 0x7ff); - if ((*table & _REGION_ENTRY_INV) && + if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY)) goto out_unmap; table = (unsigned long *) (*table & _REGION_ENTRY_ORIGIN); @@ -363,7 +388,8 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, /* Store 'from' address in an invalid segment table entry. */ flush |= gmap_unlink_segment(gmap, table); - *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off); + *table = (from + off) | (_SEGMENT_ENTRY_INVALID | + _SEGMENT_ENTRY_PROTECT); } spin_unlock(&gmap->mm->page_table_lock); up_read(&gmap->mm->mmap_sem); @@ -379,75 +405,187 @@ out_unmap: } EXPORT_SYMBOL_GPL(gmap_map_segment); -/* - * this function is assumed to be called with mmap_sem held - */ -unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap) { - unsigned long *table, vmaddr, segment; - struct mm_struct *mm; - struct gmap_pgtable *mp; - struct gmap_rmap *rmap; - struct vm_area_struct *vma; - struct page *page; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + unsigned long *table; - current->thread.gmap_addr = address; - mm = gmap->mm; - /* Walk the gmap address space page table */ table = gmap->table + ((address >> 53) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + if (unlikely(*table & _REGION_ENTRY_INVALID)) + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 42) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + if (unlikely(*table & _REGION_ENTRY_INVALID)) + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 31) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) - return -EFAULT; + if (unlikely(*table & _REGION_ENTRY_INVALID)) + return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 20) & 0x7ff); + return table; +} +/** + * __gmap_translate - translate a guest address to a user space address + * @address: guest address + * @gmap: pointer to guest mapping meta data structure + * + * Returns user space address which corresponds to the guest address or + * -EFAULT if no such mapping exists. + * This function does not establish potentially missing page table entries. + * The mmap_sem of the mm that belongs to the address space must be held + * when this function gets called. + */ +unsigned long __gmap_translate(unsigned long address, struct gmap *gmap) +{ + unsigned long *segment_ptr, vmaddr, segment; + struct gmap_pgtable *mp; + struct page *page; + + current->thread.gmap_addr = address; + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return PTR_ERR(segment_ptr); /* Convert the gmap address to an mm address. */ - segment = *table; - if (likely(!(segment & _SEGMENT_ENTRY_INV))) { + segment = *segment_ptr; + if (!(segment & _SEGMENT_ENTRY_INVALID)) { page = pfn_to_page(segment >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; return mp->vmaddr | (address & ~PMD_MASK); - } else if (segment & _SEGMENT_ENTRY_RO) { + } else if (segment & _SEGMENT_ENTRY_PROTECT) { vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; - vma = find_vma(mm, vmaddr); - if (!vma || vma->vm_start > vmaddr) - return -EFAULT; - - /* Walk the parent mm page table */ - pgd = pgd_offset(mm, vmaddr); - pud = pud_alloc(mm, pgd, vmaddr); - if (!pud) - return -ENOMEM; - pmd = pmd_alloc(mm, pud, vmaddr); - if (!pmd) - return -ENOMEM; - if (!pmd_present(*pmd) && - __pte_alloc(mm, vma, pmd, vmaddr)) - return -ENOMEM; - /* pmd now points to a valid segment table entry. */ - rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT); - if (!rmap) - return -ENOMEM; - /* Link gmap segment table entry location to page table. */ - page = pmd_page(*pmd); - mp = (struct gmap_pgtable *) page->index; - rmap->entry = table; - spin_lock(&mm->page_table_lock); + return vmaddr | (address & ~PMD_MASK); + } + return -EFAULT; +} +EXPORT_SYMBOL_GPL(__gmap_translate); + +/** + * gmap_translate - translate a guest address to a user space address + * @address: guest address + * @gmap: pointer to guest mapping meta data structure + * + * Returns user space address which corresponds to the guest address or + * -EFAULT if no such mapping exists. + * This function does not establish potentially missing page table entries. + */ +unsigned long gmap_translate(unsigned long address, struct gmap *gmap) +{ + unsigned long rc; + + down_read(&gmap->mm->mmap_sem); + rc = __gmap_translate(address, gmap); + up_read(&gmap->mm->mmap_sem); + return rc; +} +EXPORT_SYMBOL_GPL(gmap_translate); + +static int gmap_connect_pgtable(unsigned long address, unsigned long segment, + unsigned long *segment_ptr, struct gmap *gmap) +{ + unsigned long vmaddr; + struct vm_area_struct *vma; + struct gmap_pgtable *mp; + struct gmap_rmap *rmap; + struct mm_struct *mm; + struct page *page; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + mm = gmap->mm; + vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; + vma = find_vma(mm, vmaddr); + if (!vma || vma->vm_start > vmaddr) + return -EFAULT; + /* Walk the parent mm page table */ + pgd = pgd_offset(mm, vmaddr); + pud = pud_alloc(mm, pgd, vmaddr); + if (!pud) + return -ENOMEM; + pmd = pmd_alloc(mm, pud, vmaddr); + if (!pmd) + return -ENOMEM; + if (!pmd_present(*pmd) && + __pte_alloc(mm, vma, pmd, vmaddr)) + return -ENOMEM; + /* 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) + return -ENOMEM; + /* Link gmap segment table entry location to page table. */ + page = pmd_page(*pmd); + mp = (struct gmap_pgtable *) page->index; + rmap->gmap = gmap; + rmap->entry = segment_ptr; + rmap->vmaddr = address & PMD_MASK; + spin_lock(&mm->page_table_lock); + if (*segment_ptr == segment) { list_add(&rmap->list, &mp->mapper); - spin_unlock(&mm->page_table_lock); /* Set gmap segment table entry to page table. */ - *table = pmd_val(*pmd) & PAGE_MASK; - return vmaddr | (address & ~PMD_MASK); + *segment_ptr = pmd_val(*pmd) & PAGE_MASK; + rmap = NULL; + } + spin_unlock(&mm->page_table_lock); + kfree(rmap); + return 0; +} + +static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table) +{ + struct gmap_rmap *rmap, *next; + struct gmap_pgtable *mp; + struct page *page; + int flush; + + flush = 0; + spin_lock(&mm->page_table_lock); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + list_for_each_entry_safe(rmap, next, &mp->mapper, list) { + *rmap->entry = mp->vmaddr | (_SEGMENT_ENTRY_INVALID | + _SEGMENT_ENTRY_PROTECT); + list_del(&rmap->list); + kfree(rmap); + flush = 1; + } + spin_unlock(&mm->page_table_lock); + if (flush) + __tlb_flush_global(); +} + +/* + * this function is assumed to be called with mmap_sem held + */ +unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) +{ + unsigned long *segment_ptr, segment; + struct gmap_pgtable *mp; + struct page *page; + int rc; + + current->thread.gmap_addr = address; + segment_ptr = gmap_table_walk(address, gmap); + if (IS_ERR(segment_ptr)) + return -EFAULT; + /* Convert the gmap address to an mm address. */ + while (1) { + segment = *segment_ptr; + if (!(segment & _SEGMENT_ENTRY_INVALID)) { + /* Page table is present */ + page = pfn_to_page(segment >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + return mp->vmaddr | (address & ~PMD_MASK); + } + if (!(segment & _SEGMENT_ENTRY_PROTECT)) + /* Nothing mapped in the gmap address space. */ + break; + rc = gmap_connect_pgtable(address, segment, segment_ptr, gmap); + if (rc) + return rc; } return -EFAULT; } @@ -464,6 +602,82 @@ 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) { @@ -477,25 +691,25 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) while (address < to) { /* Walk the gmap address space page table */ table = gmap->table + ((address >> 53) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) { + if (unlikely(*table & _REGION_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 42) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) { + if (unlikely(*table & _REGION_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 31) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) { + if (unlikely(*table & _REGION_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 20) & 0x7ff); - if (unlikely(*table & _SEGMENT_ENTRY_INV)) { + if (unlikely(*table & _SEGMENT_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } @@ -511,27 +725,120 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) } EXPORT_SYMBOL_GPL(gmap_discard); -void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table) +static LIST_HEAD(gmap_notifier_list); +static DEFINE_SPINLOCK(gmap_notifier_lock); + +/** + * gmap_register_ipte_notifier - register a pte invalidation callback + * @nb: pointer to the gmap notifier block + */ +void gmap_register_ipte_notifier(struct gmap_notifier *nb) { - struct gmap_rmap *rmap, *next; + spin_lock(&gmap_notifier_lock); + list_add(&nb->list, &gmap_notifier_list); + spin_unlock(&gmap_notifier_lock); +} +EXPORT_SYMBOL_GPL(gmap_register_ipte_notifier); + +/** + * gmap_unregister_ipte_notifier - remove a pte invalidation callback + * @nb: pointer to the gmap notifier block + */ +void gmap_unregister_ipte_notifier(struct gmap_notifier *nb) +{ + spin_lock(&gmap_notifier_lock); + list_del_init(&nb->list); + spin_unlock(&gmap_notifier_lock); +} +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 + * @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 + * the invalidation notification could be set. If the gmap mapping is missing + * for one or more pages -EFAULT is returned. If no memory could be allocated + * -ENOMEM is returned. This function establishes missing page table entries. + */ +int gmap_ipte_notify(struct gmap *gmap, unsigned long start, unsigned long len) +{ + unsigned long addr; + spinlock_t *ptl; + pte_t *ptep, entry; + pgste_t pgste; + int rc = 0; + + if ((start & ~PAGE_MASK) || (len & ~PAGE_MASK)) + return -EINVAL; + down_read(&gmap->mm->mmap_sem); + while (len) { + /* Convert gmap address and connect the page tables */ + addr = __gmap_fault(start, gmap); + if (IS_ERR_VALUE(addr)) { + rc = addr; + break; + } + /* Get the page mapped */ + if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) { + rc = -EFAULT; + break; + } + /* Walk the process page table, lock and get pte pointer */ + ptep = get_locked_pte(gmap->mm, addr, &ptl); + if (unlikely(!ptep)) + continue; + /* Set notification bit in the pgste of the pte */ + entry = *ptep; + if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) { + pgste = pgste_get_lock(ptep); + pgste_val(pgste) |= PGSTE_IN_BIT; + pgste_set_unlock(ptep, pgste); + start += PAGE_SIZE; + len -= PAGE_SIZE; + } + spin_unlock(ptl); + } + up_read(&gmap->mm->mmap_sem); + return rc; +} +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 + * @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, pte_t *pte) +{ + unsigned long segment_offset; + struct gmap_notifier *nb; struct gmap_pgtable *mp; + struct gmap_rmap *rmap; struct page *page; - int flush; - flush = 0; - spin_lock(&mm->page_table_lock); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + segment_offset = ((unsigned long) pte) & (255 * sizeof(pte_t)); + segment_offset = segment_offset * (4096 / sizeof(pte_t)); + page = pfn_to_page(__pa(pte) >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; - list_for_each_entry_safe(rmap, next, &mp->mapper, list) { - *rmap->entry = - _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; - list_del(&rmap->list); - kfree(rmap); - flush = 1; + spin_lock(&gmap_notifier_lock); + list_for_each_entry(rmap, &mp->mapper, list) { + list_for_each_entry(nb, &gmap_notifier_list, list) + nb->notifier_call(rmap->gmap, + rmap->vmaddr + segment_offset); } - spin_unlock(&mm->page_table_lock); - if (flush) - __tlb_flush_global(); + spin_unlock(&gmap_notifier_lock); +} +EXPORT_SYMBOL_GPL(gmap_do_ipte_notify); + +static inline int page_table_with_pgste(struct page *page) +{ + return atomic_read(&page->_mapcount) == 0; } static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, @@ -549,13 +856,17 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, __free_page(page); return NULL; } - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + kfree(mp); + __free_page(page); + return NULL; + } mp->vmaddr = vmaddr & PMD_MASK; INIT_LIST_HEAD(&mp->mapper); page->index = (unsigned long) mp; - atomic_set(&page->_mapcount, 3); + atomic_set(&page->_mapcount, 0); table = (unsigned long *) page_to_phys(page); - clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2); + clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2); return table; } @@ -574,20 +885,166 @@ 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, bool init_skey) +{ + 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; + if (init_skey) { + unsigned long address; + + pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT | + PGSTE_GR_BIT | PGSTE_GC_BIT); + + /* skip invalid and not writable pages */ + if (pte_val(*pte) & _PAGE_INVALID || + !(pte_val(*pte) & _PAGE_WRITE)) { + pgste_set_unlock(pte, pgste); + continue; + } + + address = pte_val(*pte) & PAGE_MASK; + page_set_storage_key(address, PAGE_DEFAULT_KEY, 1); + } + 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, bool init_skey) +{ + 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, init_skey); + } 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, bool init_skey) +{ + 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, init_skey); + } while (pud++, addr = next, addr != end); + + return addr; +} + +void page_table_reset_pgste(struct mm_struct *mm, unsigned long start, + unsigned long end, bool init_skey) +{ + unsigned long addr, next; + pgd_t *pgd; + + down_write(&mm->mmap_sem); + if (init_skey && mm_use_skey(mm)) + goto out_up; + addr = start; + 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, init_skey); + } while (pgd++, addr = next, addr != end); + if (init_skey) + current->mm->context.use_skey = 1; +out_up: + up_write(&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) +{ + spinlock_t *ptl; + pgste_t old, new; + pte_t *ptep; + + down_read(&mm->mmap_sem); + ptep = get_locked_pte(current->mm, addr, &ptl); + if (unlikely(!ptep)) { + up_read(&mm->mmap_sem); + return -EFAULT; + } + + new = old = pgste_get_lock(ptep); + pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | + PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48; + pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; + if (!(pte_val(*ptep) & _PAGE_INVALID)) { + unsigned long address, bits, skey; + + address = pte_val(*ptep) & PAGE_MASK; + skey = (unsigned long) page_get_storage_key(address); + bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); + skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT); + /* Set storage key ACC and FP */ + page_set_storage_key(address, skey, !nq); + /* Merge host changed & referenced into pgste */ + pgste_val(new) |= bits << 52; + } + /* changing the guest storage key is considered a change of the page */ + if ((pgste_val(new) ^ pgste_val(old)) & + (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT)) + pgste_val(new) |= PGSTE_UC_BIT; + + pgste_set_unlock(ptep, new); + pte_unmap_unlock(*ptep, ptl); + up_read(&mm->mmap_sem); + return 0; +} +EXPORT_SYMBOL(set_guest_storage_key); + #else /* CONFIG_PGSTE */ +static inline int page_table_with_pgste(struct page *page) +{ + return 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { return NULL; } +void page_table_reset_pgste(struct mm_struct *mm, unsigned long start, + unsigned long end, bool init_skey) +{ +} + static inline void page_table_free_pgste(unsigned long *table) { } -static inline void gmap_unmap_notifier(struct mm_struct *mm, - unsigned long *table) +static inline void gmap_disconnect_pgtable(struct mm_struct *mm, + unsigned long *table) { } @@ -630,10 +1087,13 @@ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr) page = alloc_page(GFP_KERNEL|__GFP_REPEAT); if (!page) return NULL; - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } atomic_set(&page->_mapcount, 1); table = (unsigned long *) page_to_phys(page); - clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE); + clear_table(table, _PAGE_INVALID, PAGE_SIZE); spin_lock_bh(&mm->context.list_lock); list_add(&page->lru, &mm->context.pgtable_list); } else { @@ -652,12 +1112,12 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) struct page *page; unsigned int bit, mask; - if (mm_has_pgste(mm)) { - gmap_unmap_notifier(mm, table); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { + gmap_disconnect_pgtable(mm, table); return page_table_free_pgste(table); } /* Free 1K/2K page table fragment of a 4K page */ - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t))); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) @@ -695,14 +1155,14 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) unsigned int bit, mask; mm = tlb->mm; - if (mm_has_pgste(mm)) { - gmap_unmap_notifier(mm, table); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { + gmap_disconnect_pgtable(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; } bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t))); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) list_del(&page->lru); @@ -714,7 +1174,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) tlb_remove_table(tlb, table); } -void __tlb_remove_table(void *_table) +static void __tlb_remove_table(void *_table) { const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK; void *table = (void *)((unsigned long) _table & ~mask); @@ -762,7 +1222,6 @@ void tlb_table_flush(struct mmu_gather *tlb) struct mmu_table_batch **batch = &tlb->batch; if (*batch) { - __tlb_flush_mm(tlb->mm); call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); *batch = NULL; } @@ -772,11 +1231,12 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct mmu_table_batch **batch = &tlb->batch; + tlb->mm->context.flush_mm = 1; if (*batch == NULL) { *batch = (struct mmu_table_batch *) __get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { - __tlb_flush_mm(tlb->mm); + __tlb_flush_mm_lazy(tlb->mm); tlb_remove_table_one(table); return; } @@ -784,102 +1244,177 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) } (*batch)->tables[(*batch)->nr++] = table; if ((*batch)->nr == MAX_TABLE_BATCH) - tlb_table_flush(tlb); + tlb_flush_mmu(tlb); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void thp_split_vma(struct vm_area_struct *vma) +static inline void thp_split_vma(struct vm_area_struct *vma) { unsigned long addr; - struct page *page; - for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) { - page = follow_page(vma, addr, FOLL_SPLIT); - } + for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) + follow_page(vma, addr, FOLL_SPLIT); } -void thp_split_mm(struct mm_struct *mm) +static inline void thp_split_mm(struct mm_struct *mm) { - struct vm_area_struct *vma = mm->mmap; + struct vm_area_struct *vma; - while (vma != NULL) { + for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) { thp_split_vma(vma); vma->vm_flags &= ~VM_HUGEPAGE; vma->vm_flags |= VM_NOHUGEPAGE; - vma = vma->vm_next; } + mm->def_flags |= VM_NOHUGEPAGE; +} +#else +static inline void thp_split_mm(struct mm_struct *mm) +{ } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb, + struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end) +{ + unsigned long next, *table, *new; + struct page *page; + pmd_t *pmd; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); +again: + if (pmd_none_or_clear_bad(pmd)) + continue; + table = (unsigned long *) pmd_deref(*pmd); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) + continue; + /* Allocate new page table with pgstes */ + new = page_table_alloc_pgste(mm, addr); + if (!new) + return -ENOMEM; + + spin_lock(&mm->page_table_lock); + if (likely((unsigned long *) pmd_deref(*pmd) == table)) { + /* Nuke pmd entry pointing to the "short" page table */ + pmdp_flush_lazy(mm, addr, pmd); + pmd_clear(pmd); + /* Copy ptes from old table to new table */ + memcpy(new, table, PAGE_SIZE/2); + clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); + /* Establish new table */ + pmd_populate(mm, pmd, (pte_t *) new); + /* Free old table with rcu, there might be a walker! */ + page_table_free_rcu(tlb, table); + new = NULL; + } + spin_unlock(&mm->page_table_lock); + if (new) { + page_table_free_pgste(new); + goto again; + } + } while (pmd++, addr = next, addr != end); + + return addr; +} + +static unsigned long page_table_realloc_pud(struct mmu_gather *tlb, + 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_realloc_pmd(tlb, mm, pud, addr, next); + if (unlikely(IS_ERR_VALUE(next))) + return next; + } while (pud++, addr = next, addr != end); + + return addr; +} + +static unsigned long page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + unsigned long next; + pgd_t *pgd; + + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + next = page_table_realloc_pud(tlb, mm, pgd, addr, next); + if (unlikely(IS_ERR_VALUE(next))) + return next; + } while (pgd++, addr = next, addr != end); + + return 0; +} + /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { struct task_struct *tsk = current; - struct mm_struct *mm, *old_mm; - - /* Do we have switched amode? If no, we cannot do sie */ - if (s390_user_mode == HOME_SPACE_MODE) - return -EINVAL; + struct mm_struct *mm = tsk->mm; + struct mmu_gather tlb; /* Do we have pgstes? if yes, we are done */ if (mm_has_pgste(tsk->mm)) return 0; - /* lets check if we are allowed to replace the mm */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - task_unlock(tsk); - return -EINVAL; - } - task_unlock(tsk); - - /* we copy the mm and let dup_mm create the page tables with_pgstes */ - tsk->mm->context.alloc_pgste = 1; - /* make sure that both mms have a correct rss state */ - sync_mm_rss(tsk->mm); - mm = dup_mm(tsk); - tsk->mm->context.alloc_pgste = 0; - if (!mm) - return -ENOMEM; - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE + down_write(&mm->mmap_sem); /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - mm->def_flags |= VM_NOHUGEPAGE; -#endif + /* Reallocate the page tables with pgstes */ + tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE); + if (!page_table_realloc(&tlb, mm, 0, TASK_SIZE)) + mm->context.has_pgste = 1; + tlb_finish_mmu(&tlb, 0, TASK_SIZE); + up_write(&mm->mmap_sem); + return mm->context.has_pgste ? 0 : -ENOMEM; +} +EXPORT_SYMBOL_GPL(s390_enable_sie); - /* Now lets check again if something happened */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - mmput(mm); - task_unlock(tsk); - return -EINVAL; - } +/* + * Enable storage key handling from now on and initialize the storage + * keys with the default key. + */ +void s390_enable_skey(void) +{ + page_table_reset_pgste(current->mm, 0, TASK_SIZE, true); +} +EXPORT_SYMBOL_GPL(s390_enable_skey); - /* ok, we are alone. No ptrace, no threads, etc. */ - old_mm = tsk->mm; - tsk->mm = tsk->active_mm = mm; - preempt_disable(); - update_mm(mm, tsk); - atomic_inc(&mm->context.attach_count); - atomic_dec(&old_mm->context.attach_count); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - preempt_enable(); - task_unlock(tsk); - mmput(old_mm); - return 0; +/* + * Test and reset if a guest page is dirty + */ +bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap) +{ + pte_t *pte; + spinlock_t *ptl; + bool dirty = false; + + pte = get_locked_pte(gmap->mm, address, &ptl); + if (unlikely(!pte)) + return false; + + if (ptep_test_and_clear_user_dirty(gmap->mm, address, pte)) + dirty = true; + + spin_unlock(ptl); + return dirty; } -EXPORT_SYMBOL_GPL(s390_enable_sie); +EXPORT_SYMBOL_GPL(gmap_test_and_clear_dirty); #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, @@ -920,41 +1455,42 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, } } -void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) { struct list_head *lh = (struct list_head *) pgtable; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ - if (!mm->pmd_huge_pte) + if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(lh); else - list_add(lh, (struct list_head *) mm->pmd_huge_pte); - mm->pmd_huge_pte = pgtable; + list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp)); + pmd_huge_pte(mm, pmdp) = pgtable; } -pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { struct list_head *lh; pgtable_t pgtable; pte_t *ptep; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ - pgtable = mm->pmd_huge_pte; + pgtable = pmd_huge_pte(mm, pmdp); lh = (struct list_head *) pgtable; if (list_empty(lh)) - mm->pmd_huge_pte = NULL; + pmd_huge_pte(mm, pmdp) = NULL; else { - mm->pmd_huge_pte = (pgtable_t) lh->next; + pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next; list_del(lh); } ptep = (pte_t *) pgtable; - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; ptep++; - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; return pgtable; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6ed1426d27c..fe9012a49aa 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -10,6 +10,7 @@ #include <linux/list.h> #include <linux/hugetlb.h> #include <linux/slab.h> +#include <linux/memblock.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/setup.h> @@ -66,10 +67,11 @@ static pte_t __ref *vmem_pte_alloc(unsigned long address) if (slab_is_available()) pte = (pte_t *) page_table_alloc(&init_mm, address); else - pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t)); + pte = alloc_bootmem_align(PTRS_PER_PTE * sizeof(pte_t), + PTRS_PER_PTE * sizeof(pte_t)); if (!pte) return NULL; - clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) pte, _PAGE_INVALID, PTRS_PER_PTE * sizeof(pte_t)); return pte; } @@ -85,11 +87,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; - pte_t pte; int ret = -ENOMEM; while (address < end) { - pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0)); pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { pu_dir = vmem_pud_alloc(); @@ -101,9 +101,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC) if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address && !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) { - pte_val(pte) |= _REGION3_ENTRY_LARGE; - pte_val(pte) |= _REGION_ENTRY_TYPE_R3; - pud_val(*pu_dir) = pte_val(pte); + pud_val(*pu_dir) = __pa(address) | + _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE | + (ro ? _REGION_ENTRY_PROTECT : 0); address += PUD_SIZE; continue; } @@ -118,8 +118,10 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC) if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address && !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) { - pte_val(pte) |= _SEGMENT_ENTRY_LARGE; - pmd_val(*pm_dir) = pte_val(pte); + pmd_val(*pm_dir) = __pa(address) | + _SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE | + _SEGMENT_ENTRY_YOUNG | + (ro ? _SEGMENT_ENTRY_PROTECT : 0); address += PMD_SIZE; continue; } @@ -132,12 +134,12 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) } pt_dir = pte_offset_kernel(pm_dir, address); - *pt_dir = pte; + pte_val(*pt_dir) = __pa(address) | + pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL); address += PAGE_SIZE; } ret = 0; out: - flush_tlb_kernel_range(start, end); return ret; } @@ -155,7 +157,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size) pte_t *pt_dir; pte_t pte; - pte_val(pte) = _PAGE_TYPE_EMPTY; + pte_val(pte) = _PAGE_INVALID; while (address < end) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { @@ -192,20 +194,16 @@ static void vmem_remove_range(unsigned long start, unsigned long size) /* * Add a backed mem_map array to the virtual mem_map array. */ -int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { - unsigned long address, start_addr, end_addr; + unsigned long address = start; pgd_t *pg_dir; pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; - pte_t pte; int ret = -ENOMEM; - start_addr = (unsigned long) start; - end_addr = (unsigned long) (start + nr); - - for (address = start_addr; address < end_addr;) { + for (address = start; address < end;) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { pu_dir = vmem_pud_alloc(); @@ -237,9 +235,9 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) new_page = vmemmap_alloc_block(PMD_SIZE, node); if (!new_page) goto out; - pte = mk_pte_phys(__pa(new_page), PAGE_RW); - pte_val(pte) |= _SEGMENT_ENTRY_LARGE; - pmd_val(*pm_dir) = pte_val(pte); + pmd_val(*pm_dir) = __pa(new_page) | + _SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE | + _SEGMENT_ENTRY_CO; address = (address + PMD_SIZE) & PMD_MASK; continue; } @@ -260,18 +258,21 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) new_page =__pa(vmem_alloc_pages(0)); if (!new_page) goto out; - pte = pfn_pte(new_page >> PAGE_SHIFT, PAGE_KERNEL); - *pt_dir = pte; + pte_val(*pt_dir) = + __pa(new_page) | pgprot_val(PAGE_KERNEL); } address += PAGE_SIZE; } - memset(start, 0, nr * sizeof(struct page)); + memset((void *)start, 0, end - start); ret = 0; out: - flush_tlb_kernel_range(start_addr, end_addr); return ret; } +void vmemmap_free(unsigned long start, unsigned long end) +{ +} + /* * Add memory segment to the segment list if it doesn't overlap with * an already present segment. @@ -372,17 +373,14 @@ out: void __init vmem_map_init(void) { unsigned long ro_start, ro_end; - unsigned long start, end; - int i; + struct memblock_region *reg; + phys_addr_t start, end; ro_start = PFN_ALIGN((unsigned long)&_stext); ro_end = (unsigned long)&_eshared & PAGE_MASK; - for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { - if (memory_chunk[i].type == CHUNK_CRASHK || - memory_chunk[i].type == CHUNK_OLDMEM) - continue; - start = memory_chunk[i].addr; - end = memory_chunk[i].addr + memory_chunk[i].size; + for_each_memblock(memory, reg) { + start = reg->base; + end = reg->base + reg->size - 1; if (start >= ro_end || end <= ro_start) vmem_add_mem(start, end - start, 0); else if (start >= ro_start && end <= ro_end) @@ -402,26 +400,21 @@ void __init vmem_map_init(void) } /* - * Convert memory chunk array to a memory segment list so there is a single - * list that contains both r/w memory and shared memory segments. + * Convert memblock.memory to a memory segment list so there is a single + * list that contains all memory segments. */ static int __init vmem_convert_memory_chunk(void) { + struct memblock_region *reg; struct memory_segment *seg; - int i; mutex_lock(&vmem_mutex); - for (i = 0; i < MEMORY_CHUNKS; i++) { - if (!memory_chunk[i].size) - continue; - if (memory_chunk[i].type == CHUNK_CRASHK || - memory_chunk[i].type == CHUNK_OLDMEM) - continue; + for_each_memblock(memory, reg) { seg = kzalloc(sizeof(*seg), GFP_KERNEL); if (!seg) panic("Out of memory...\n"); - seg->start = memory_chunk[i].addr; - seg->size = memory_chunk[i].size; + seg->start = reg->base; + seg->size = reg->size; insert_memory_segment(seg); } mutex_unlock(&vmem_mutex); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index bb284419b0f..a2cbd875543 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -7,10 +7,13 @@ */ #include <linux/moduleloader.h> #include <linux/netdevice.h> +#include <linux/if_vlan.h> #include <linux/filter.h> +#include <linux/random.h> +#include <linux/init.h> #include <asm/cacheflush.h> -#include <asm/processor.h> #include <asm/facility.h> +#include <asm/dis.h> /* * Conventions: @@ -153,8 +156,8 @@ static void bpf_jit_prologue(struct bpf_jit *jit) EMIT6(0xeb8ff058, 0x0024); /* lgr %r14,%r15 */ EMIT4(0xb90400ef); - /* ahi %r15,<offset> */ - EMIT4_IMM(0xa7fa0000, (jit->seen & SEEN_MEM) ? -112 : -80); + /* aghi %r15,<offset> */ + EMIT4_IMM(0xa7fb0000, (jit->seen & SEEN_MEM) ? -112 : -80); /* stg %r14,152(%r15) */ EMIT6(0xe3e0f098, 0x0024); } else if ((jit->seen & SEEN_XREG) && (jit->seen & SEEN_LITERAL)) @@ -220,6 +223,37 @@ static void bpf_jit_epilogue(struct bpf_jit *jit) EMIT2(0x07fe); } +/* Helper to find the offset of pkt_type in sk_buff + * Make sure its still a 3bit field starting at the MSBs within a byte. + */ +#define PKT_TYPE_MAX 0xe0 +static int pkt_type_offset; + +static int __init bpf_pkt_type_offset_init(void) +{ + struct sk_buff skb_probe = { + .pkt_type = ~0, + }; + char *ct = (char *)&skb_probe; + int off; + + pkt_type_offset = -1; + for (off = 0; off < sizeof(struct sk_buff); off++) { + if (!ct[off]) + continue; + if (ct[off] == PKT_TYPE_MAX) + pkt_type_offset = off; + else { + /* Found non matching bit pattern, fix needed. */ + WARN_ON_ONCE(1); + pkt_type_offset = -1; + return -1; + } + } + return 0; +} +device_initcall(bpf_pkt_type_offset_init); + /* * make sure we dont leak kernel information to user */ @@ -235,26 +269,17 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter) EMIT4(0xa7c80000); /* Clear A if the first register does not set it. */ switch (filter[0].code) { - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: - case BPF_S_LD_W_LEN: - case BPF_S_LD_W_IND: - case BPF_S_LD_H_IND: - case BPF_S_LD_B_IND: - case BPF_S_LDX_B_MSH: - case BPF_S_LD_IMM: - case BPF_S_LD_MEM: - case BPF_S_MISC_TXA: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_PKTTYPE: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_QUEUE: - case BPF_S_ANC_HATYPE: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_CPU: - case BPF_S_RET_K: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LD | BPF_W | BPF_IND: + case BPF_LD | BPF_H | BPF_IND: + case BPF_LD | BPF_B | BPF_IND: + case BPF_LD | BPF_IMM: + case BPF_LD | BPF_MEM: + case BPF_MISC | BPF_TXA: + case BPF_RET | BPF_K: /* first instruction sets A register */ break; default: /* A = 0 */ @@ -269,15 +294,18 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, unsigned int K; int offset; unsigned int mask; + u16 code; K = filter->k; - switch (filter->code) { - case BPF_S_ALU_ADD_X: /* A += X */ + code = bpf_anc_helper(filter); + + switch (code) { + case BPF_ALU | BPF_ADD | BPF_X: /* A += X */ jit->seen |= SEEN_XREG; /* ar %r5,%r12 */ EMIT2(0x1a5c); break; - case BPF_S_ALU_ADD_K: /* A += K */ + case BPF_ALU | BPF_ADD | BPF_K: /* A += K */ if (!K) break; if (K <= 16383) @@ -290,12 +318,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* a %r5,<d(K)>(%r13) */ EMIT4_DISP(0x5a50d000, EMIT_CONST(K)); break; - case BPF_S_ALU_SUB_X: /* A -= X */ + case BPF_ALU | BPF_SUB | BPF_X: /* A -= X */ jit->seen |= SEEN_XREG; /* sr %r5,%r12 */ EMIT2(0x1b5c); break; - case BPF_S_ALU_SUB_K: /* A -= K */ + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ if (!K) break; if (K <= 16384) @@ -308,12 +336,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* s %r5,<d(K)>(%r13) */ EMIT4_DISP(0x5b50d000, EMIT_CONST(K)); break; - case BPF_S_ALU_MUL_X: /* A *= X */ + case BPF_ALU | BPF_MUL | BPF_X: /* A *= X */ jit->seen |= SEEN_XREG; /* msr %r5,%r12 */ EMIT4(0xb252005c); break; - case BPF_S_ALU_MUL_K: /* A *= K */ + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ if (K <= 16383) /* mhi %r5,K */ EMIT4_IMM(0xa75c0000, K); @@ -324,7 +352,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* ms %r5,<d(K)>(%r13) */ EMIT4_DISP(0x7150d000, EMIT_CONST(K)); break; - case BPF_S_ALU_DIV_X: /* A /= X */ + case BPF_ALU | BPF_DIV | BPF_X: /* A /= X */ jit->seen |= SEEN_XREG | SEEN_RET0; /* ltr %r12,%r12 */ EMIT2(0x12cc); @@ -332,16 +360,18 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg)); /* lhi %r4,0 */ EMIT4(0xa7480000); - /* dr %r4,%r12 */ - EMIT2(0x1d4c); + /* dlr %r4,%r12 */ + EMIT4(0xb997004c); break; - case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */ - /* m %r4,<d(K)>(%r13) */ - EMIT4_DISP(0x5c40d000, EMIT_CONST(K)); - /* lr %r5,%r4 */ - EMIT2(0x1854); + case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */ + if (K == 1) + break; + /* lhi %r4,0 */ + EMIT4(0xa7480000); + /* dl %r4,<d(K)>(%r13) */ + EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K)); break; - case BPF_S_ALU_MOD_X: /* A %= X */ + case BPF_ALU | BPF_MOD | BPF_X: /* A %= X */ jit->seen |= SEEN_XREG | SEEN_RET0; /* ltr %r12,%r12 */ EMIT2(0x12cc); @@ -349,25 +379,30 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg)); /* lhi %r4,0 */ EMIT4(0xa7480000); - /* dr %r4,%r12 */ - EMIT2(0x1d4c); + /* dlr %r4,%r12 */ + EMIT4(0xb997004c); /* lr %r5,%r4 */ EMIT2(0x1854); break; - case BPF_S_ALU_MOD_K: /* A %= K */ + case BPF_ALU | BPF_MOD | BPF_K: /* A %= K */ + if (K == 1) { + /* lhi %r5,0 */ + EMIT4(0xa7580000); + break; + } /* lhi %r4,0 */ EMIT4(0xa7480000); - /* d %r4,<d(K)>(%r13) */ - EMIT4_DISP(0x5d40d000, EMIT_CONST(K)); + /* dl %r4,<d(K)>(%r13) */ + EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K)); /* lr %r5,%r4 */ EMIT2(0x1854); break; - case BPF_S_ALU_AND_X: /* A &= X */ + case BPF_ALU | BPF_AND | BPF_X: /* A &= X */ jit->seen |= SEEN_XREG; /* nr %r5,%r12 */ EMIT2(0x145c); break; - case BPF_S_ALU_AND_K: /* A &= K */ + case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ if (test_facility(21)) /* nilf %r5,<K> */ EMIT6_IMM(0xc05b0000, K); @@ -375,12 +410,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* n %r5,<d(K)>(%r13) */ EMIT4_DISP(0x5450d000, EMIT_CONST(K)); break; - case BPF_S_ALU_OR_X: /* A |= X */ + case BPF_ALU | BPF_OR | BPF_X: /* A |= X */ jit->seen |= SEEN_XREG; /* or %r5,%r12 */ EMIT2(0x165c); break; - case BPF_S_ALU_OR_K: /* A |= K */ + case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ if (test_facility(21)) /* oilf %r5,<K> */ EMIT6_IMM(0xc05d0000, K); @@ -388,55 +423,55 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, /* o %r5,<d(K)>(%r13) */ EMIT4_DISP(0x5650d000, EMIT_CONST(K)); break; - case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ - case BPF_S_ALU_XOR_X: + case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */ + case BPF_ALU | BPF_XOR | BPF_X: jit->seen |= SEEN_XREG; /* xr %r5,%r12 */ EMIT2(0x175c); break; - case BPF_S_ALU_XOR_K: /* A ^= K */ + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ if (!K) break; /* x %r5,<d(K)>(%r13) */ EMIT4_DISP(0x5750d000, EMIT_CONST(K)); break; - case BPF_S_ALU_LSH_X: /* A <<= X; */ + case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */ jit->seen |= SEEN_XREG; /* sll %r5,0(%r12) */ EMIT4(0x8950c000); break; - case BPF_S_ALU_LSH_K: /* A <<= K */ + case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */ if (K == 0) break; /* sll %r5,K */ EMIT4_DISP(0x89500000, K); break; - case BPF_S_ALU_RSH_X: /* A >>= X; */ + case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */ jit->seen |= SEEN_XREG; /* srl %r5,0(%r12) */ EMIT4(0x8850c000); break; - case BPF_S_ALU_RSH_K: /* A >>= K; */ + case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */ if (K == 0) break; /* srl %r5,K */ EMIT4_DISP(0x88500000, K); break; - case BPF_S_ALU_NEG: /* A = -A */ + case BPF_ALU | BPF_NEG: /* A = -A */ /* lnr %r5,%r5 */ EMIT2(0x1155); break; - case BPF_S_JMP_JA: /* ip += K */ + case BPF_JMP | BPF_JA: /* ip += K */ offset = addrs[i + K] + jit->start - jit->prg; EMIT4_PCREL(0xa7f40000, offset); break; - case BPF_S_JMP_JGT_K: /* ip += (A > K) ? jt : jf */ + case BPF_JMP | BPF_JGT | BPF_K: /* ip += (A > K) ? jt : jf */ mask = 0x200000; /* jh */ goto kbranch; - case BPF_S_JMP_JGE_K: /* ip += (A >= K) ? jt : jf */ + case BPF_JMP | BPF_JGE | BPF_K: /* ip += (A >= K) ? jt : jf */ mask = 0xa00000; /* jhe */ goto kbranch; - case BPF_S_JMP_JEQ_K: /* ip += (A == K) ? jt : jf */ + case BPF_JMP | BPF_JEQ | BPF_K: /* ip += (A == K) ? jt : jf */ mask = 0x800000; /* je */ kbranch: /* Emit compare if the branch targets are different */ if (filter->jt != filter->jf) { @@ -469,7 +504,7 @@ branch: if (filter->jt == filter->jf) { EMIT4_PCREL(0xa7040000 | (mask ^ 0xf00000), offset); } break; - case BPF_S_JMP_JSET_K: /* ip += (A & K) ? jt : jf */ + case BPF_JMP | BPF_JSET | BPF_K: /* ip += (A & K) ? jt : jf */ mask = 0x700000; /* jnz */ /* Emit test if the branch targets are different */ if (filter->jt != filter->jf) { @@ -483,13 +518,13 @@ branch: if (filter->jt == filter->jf) { EMIT4_IMM(0xa7510000, K); } goto branch; - case BPF_S_JMP_JGT_X: /* ip += (A > X) ? jt : jf */ + case BPF_JMP | BPF_JGT | BPF_X: /* ip += (A > X) ? jt : jf */ mask = 0x200000; /* jh */ goto xbranch; - case BPF_S_JMP_JGE_X: /* ip += (A >= X) ? jt : jf */ + case BPF_JMP | BPF_JGE | BPF_X: /* ip += (A >= X) ? jt : jf */ mask = 0xa00000; /* jhe */ goto xbranch; - case BPF_S_JMP_JEQ_X: /* ip += (A == X) ? jt : jf */ + case BPF_JMP | BPF_JEQ | BPF_X: /* ip += (A == X) ? jt : jf */ mask = 0x800000; /* je */ xbranch: /* Emit compare if the branch targets are different */ if (filter->jt != filter->jf) { @@ -498,7 +533,7 @@ xbranch: /* Emit compare if the branch targets are different */ EMIT2(0x195c); } goto branch; - case BPF_S_JMP_JSET_X: /* ip += (A & X) ? jt : jf */ + case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */ mask = 0x700000; /* jnz */ /* Emit test if the branch targets are different */ if (filter->jt != filter->jf) { @@ -509,15 +544,15 @@ xbranch: /* Emit compare if the branch targets are different */ EMIT2(0x144c); } goto branch; - case BPF_S_LD_W_ABS: /* A = *(u32 *) (skb->data+K) */ + case BPF_LD | BPF_W | BPF_ABS: /* A = *(u32 *) (skb->data+K) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_WORD; offset = jit->off_load_word; goto load_abs; - case BPF_S_LD_H_ABS: /* A = *(u16 *) (skb->data+K) */ + case BPF_LD | BPF_H | BPF_ABS: /* A = *(u16 *) (skb->data+K) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_HALF; offset = jit->off_load_half; goto load_abs; - case BPF_S_LD_B_ABS: /* A = *(u8 *) (skb->data+K) */ + case BPF_LD | BPF_B | BPF_ABS: /* A = *(u8 *) (skb->data+K) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_BYTE; offset = jit->off_load_byte; load_abs: if ((int) K < 0) @@ -531,19 +566,19 @@ call_fn: /* lg %r1,<d(function)>(%r13) */ /* jnz <ret0> */ EMIT4_PCREL(0xa7740000, (jit->ret0_ip - jit->prg)); break; - case BPF_S_LD_W_IND: /* A = *(u32 *) (skb->data+K+X) */ + case BPF_LD | BPF_W | BPF_IND: /* A = *(u32 *) (skb->data+K+X) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IWORD; offset = jit->off_load_iword; goto call_fn; - case BPF_S_LD_H_IND: /* A = *(u16 *) (skb->data+K+X) */ + case BPF_LD | BPF_H | BPF_IND: /* A = *(u16 *) (skb->data+K+X) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IHALF; offset = jit->off_load_ihalf; goto call_fn; - case BPF_S_LD_B_IND: /* A = *(u8 *) (skb->data+K+X) */ + case BPF_LD | BPF_B | BPF_IND: /* A = *(u8 *) (skb->data+K+X) */ jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IBYTE; offset = jit->off_load_ibyte; goto call_fn; - case BPF_S_LDX_B_MSH: + case BPF_LDX | BPF_B | BPF_MSH: /* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */ jit->seen |= SEEN_RET0; if ((int) K < 0) { @@ -554,17 +589,17 @@ call_fn: /* lg %r1,<d(function)>(%r13) */ jit->seen |= SEEN_DATAREF | SEEN_LOAD_BMSH; offset = jit->off_load_bmsh; goto call_fn; - case BPF_S_LD_W_LEN: /* A = skb->len; */ + case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); /* l %r5,<d(len)>(%r2) */ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, len)); break; - case BPF_S_LDX_W_LEN: /* X = skb->len; */ + case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ jit->seen |= SEEN_XREG; /* l %r12,<d(len)>(%r2) */ EMIT4_DISP(0x58c02000, offsetof(struct sk_buff, len)); break; - case BPF_S_LD_IMM: /* A = K */ + case BPF_LD | BPF_IMM: /* A = K */ if (K <= 16383) /* lhi %r5,K */ EMIT4_IMM(0xa7580000, K); @@ -575,7 +610,7 @@ call_fn: /* lg %r1,<d(function)>(%r13) */ /* l %r5,<d(K)>(%r13) */ EMIT4_DISP(0x5850d000, EMIT_CONST(K)); break; - case BPF_S_LDX_IMM: /* X = K */ + case BPF_LDX | BPF_IMM: /* X = K */ jit->seen |= SEEN_XREG; if (K <= 16383) /* lhi %r12,<K> */ @@ -587,29 +622,29 @@ call_fn: /* lg %r1,<d(function)>(%r13) */ /* l %r12,<d(K)>(%r13) */ EMIT4_DISP(0x58c0d000, EMIT_CONST(K)); break; - case BPF_S_LD_MEM: /* A = mem[K] */ + case BPF_LD | BPF_MEM: /* A = mem[K] */ jit->seen |= SEEN_MEM; /* l %r5,<K>(%r15) */ EMIT4_DISP(0x5850f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_LDX_MEM: /* X = mem[K] */ + case BPF_LDX | BPF_MEM: /* X = mem[K] */ jit->seen |= SEEN_XREG | SEEN_MEM; /* l %r12,<K>(%r15) */ EMIT4_DISP(0x58c0f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_MISC_TAX: /* X = A */ + case BPF_MISC | BPF_TAX: /* X = A */ jit->seen |= SEEN_XREG; /* lr %r12,%r5 */ EMIT2(0x18c5); break; - case BPF_S_MISC_TXA: /* A = X */ + case BPF_MISC | BPF_TXA: /* A = X */ jit->seen |= SEEN_XREG; /* lr %r5,%r12 */ EMIT2(0x185c); break; - case BPF_S_RET_K: + case BPF_RET | BPF_K: if (K == 0) { jit->seen |= SEEN_RET0; if (last) @@ -629,33 +664,33 @@ call_fn: /* lg %r1,<d(function)>(%r13) */ EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); } break; - case BPF_S_RET_A: + case BPF_RET | BPF_A: /* llgfr %r2,%r5 */ EMIT4(0xb9160025); /* j <exit> */ EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); break; - case BPF_S_ST: /* mem[K] = A */ + case BPF_ST: /* mem[K] = A */ jit->seen |= SEEN_MEM; /* st %r5,<K>(%r15) */ EMIT4_DISP(0x5050f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ + case BPF_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ jit->seen |= SEEN_XREG | SEEN_MEM; /* st %r12,<K>(%r15) */ EMIT4_DISP(0x50c0f000, (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); break; - case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); /* lhi %r5,0 */ EMIT4(0xa7580000); /* icm %r5,3,<d(protocol)>(%r2) */ EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, protocol)); break; - case BPF_S_ANC_IFINDEX: /* if (!skb->dev) return 0; - * A = skb->dev->ifindex */ + case BPF_ANC | SKF_AD_IFINDEX: /* if (!skb->dev) return 0; + * A = skb->dev->ifindex */ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); jit->seen |= SEEN_RET0; /* lg %r1,<d(dev)>(%r2) */ @@ -667,20 +702,20 @@ call_fn: /* lg %r1,<d(function)>(%r13) */ /* l %r5,<d(ifindex)>(%r1) */ EMIT4_DISP(0x58501000, offsetof(struct net_device, ifindex)); break; - case BPF_S_ANC_MARK: /* A = skb->mark */ + case BPF_ANC | SKF_AD_MARK: /* A = skb->mark */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); /* l %r5,<d(mark)>(%r2) */ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, mark)); break; - case BPF_S_ANC_QUEUE: /* A = skb->queue_mapping */ + case BPF_ANC | SKF_AD_QUEUE: /* A = skb->queue_mapping */ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); /* lhi %r5,0 */ EMIT4(0xa7580000); /* icm %r5,3,<d(queue_mapping)>(%r2) */ EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, queue_mapping)); break; - case BPF_S_ANC_HATYPE: /* if (!skb->dev) return 0; - * A = skb->dev->type */ + case BPF_ANC | SKF_AD_HATYPE: /* if (!skb->dev) return 0; + * A = skb->dev->type */ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); jit->seen |= SEEN_RET0; /* lg %r1,<d(dev)>(%r2) */ @@ -694,12 +729,40 @@ 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_ANC | SKF_AD_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_ANC | SKF_AD_VLAN_TAG: + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + /* lhi %r5,0 */ + EMIT4(0xa7580000); + /* icm %r5,3,<d(vlan_tci)>(%r2) */ + EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, vlan_tci)); + if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) { + /* nill %r5,0xefff */ + EMIT4_IMM(0xa5570000, ~VLAN_TAG_PRESENT); + } else { + /* nill %r5,0x1000 */ + EMIT4_IMM(0xa5570000, VLAN_TAG_PRESENT); + /* srl %r5,12 */ + EMIT4_DISP(0x88500000, 12); + } + break; + case BPF_ANC | SKF_AD_PKTTYPE: + if (pkt_type_offset < 0) + goto out; + /* lhi %r5,0 */ + EMIT4(0xa7580000); + /* ic %r5,<d(pkt_type_offset)>(%r2) */ + EMIT4_DISP(0x43502000, pkt_type_offset); + /* srl %r5,5 */ + EMIT4_DISP(0x88500000, 5); break; - case BPF_S_ANC_CPU: /* A = smp_processor_id() */ + case BPF_ANC | SKF_AD_CPU: /* A = smp_processor_id() */ #ifdef CONFIG_SMP /* l %r5,<d(cpu_nr)> */ EMIT4_DISP(0x58500000, offsetof(struct _lowcore, cpu_nr)); @@ -717,8 +780,41 @@ out: return -1; } +/* + * Note: for security reasons, bpf code will follow a randomly + * sized amount of illegal instructions. + */ +struct bpf_binary_header { + unsigned int pages; + u8 image[]; +}; + +static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize, + u8 **image_ptr) +{ + struct bpf_binary_header *header; + unsigned int sz, hole; + + /* Most BPF filters are really small, but if some of them fill a page, + * allow at least 128 extra bytes for illegal instructions. + */ + sz = round_up(bpfsize + sizeof(*header) + 128, PAGE_SIZE); + header = module_alloc(sz); + if (!header) + return NULL; + memset(header, 0, sz); + header->pages = sz / PAGE_SIZE; + hole = min(sz - (bpfsize + sizeof(*header)), PAGE_SIZE - sizeof(*header)); + /* Insert random number of illegal instructions before BPF code + * and make sure the first instruction starts at an even address. + */ + *image_ptr = &header->image[(prandom_u32() % hole) & -2]; + return header; +} + void bpf_jit_compile(struct sk_filter *fp) { + struct bpf_binary_header *header = NULL; unsigned long size, prg_len, lit_len; struct bpf_jit jit, cjit; unsigned int *addrs; @@ -726,10 +822,9 @@ void bpf_jit_compile(struct sk_filter *fp) if (!bpf_jit_enable) return; - addrs = kmalloc(fp->len * sizeof(*addrs), GFP_KERNEL); + addrs = kcalloc(fp->len, sizeof(*addrs), GFP_KERNEL); if (addrs == NULL) return; - memset(addrs, 0, fp->len * sizeof(*addrs)); memset(&jit, 0, sizeof(cjit)); memset(&cjit, 0, sizeof(cjit)); @@ -752,12 +847,11 @@ void bpf_jit_compile(struct sk_filter *fp) } else if (jit.prg == cjit.prg && jit.lit == cjit.lit) { prg_len = jit.prg - jit.start; lit_len = jit.lit - jit.mid; - size = max_t(unsigned long, prg_len + lit_len, - sizeof(struct work_struct)); + size = prg_len + lit_len; if (size >= BPF_SIZE_MAX) goto out; - jit.start = module_alloc(size); - if (!jit.start) + header = bpf_alloc_binary(size, &jit.start); + if (!header) goto out; jit.prg = jit.mid = jit.start + prg_len; jit.lit = jit.end = jit.start + prg_len + lit_len; @@ -768,37 +862,30 @@ void bpf_jit_compile(struct sk_filter *fp) cjit = jit; } if (bpf_jit_enable > 1) { - pr_err("flen=%d proglen=%lu pass=%d image=%p\n", - fp->len, jit.end - jit.start, pass, jit.start); - if (jit.start) { - printk(KERN_ERR "JIT code:\n"); + bpf_jit_dump(fp->len, jit.end - jit.start, pass, jit.start); + if (jit.start) print_fn_code(jit.start, jit.mid - jit.start); - print_hex_dump(KERN_ERR, "JIT literals:\n", - DUMP_PREFIX_ADDRESS, 16, 1, - jit.mid, jit.end - jit.mid, false); - } } - if (jit.start) + if (jit.start) { + set_memory_ro((unsigned long)header, header->pages); fp->bpf_func = (void *) jit.start; + fp->jited = 1; + } out: kfree(addrs); } -static void jit_free_defer(struct work_struct *arg) -{ - module_free(NULL, arg); -} - -/* run from softirq, we must use a work_struct to call - * module_free() from process context - */ void bpf_jit_free(struct sk_filter *fp) { - struct work_struct *work; + unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; + struct bpf_binary_header *header = (void *)addr; - if (fp->bpf_func == sk_run_filter) - return; - work = (struct work_struct *)fp->bpf_func; - INIT_WORK(work, jit_free_defer); - schedule_work(work); + 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 b5b2916895e..e53c6f26880 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); @@ -256,23 +209,11 @@ static void init_all_cpu_buffers(void) } } -static int is_link_entry(unsigned long *s) +static void prepare_cpu_buffers(void) { - 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; - int rc; struct hws_cpu_buffer *cb; + int cpu; - rc = 0; for_each_online_cpu(cpu) { cb = &per_cpu(sampler_cpu_buffer, cpu); atomic_set(&cb->ext_params, 0); @@ -287,8 +228,6 @@ static int prepare_cpu_buffers(void) cb->oom = 0; cb->stop_mode = 0; } - - return rc; } /* @@ -353,7 +292,7 @@ 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 +768,7 @@ 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 +795,7 @@ 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 +805,7 @@ 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; @@ -1001,7 +940,8 @@ int hwsampler_deallocate(void) if (hws_state != HWS_STOPPED) goto deallocate_exit; - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); + hws_alert = 0; deallocate_sdbt(); hws_state = HWS_DEALLOCATED; @@ -1089,7 +1029,7 @@ 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; @@ -1115,7 +1055,8 @@ int hwsampler_shutdown(void) mutex_lock(&hws_sem); if (hws_state == HWS_STOPPED) { - measurement_alert_subclass_unregister(); + irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); + hws_alert = 0; deallocate_sdbt(); } if (hws_wq) { @@ -1123,7 +1064,7 @@ 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; } @@ -1162,9 +1103,7 @@ int hwsampler_start_all(unsigned long rate) if (rc) goto start_all_exit; - rc = prepare_cpu_buffers(); - if (rc) - goto start_all_exit; + prepare_cpu_buffers(); for_each_online_cpu(cpu) { rc = start_sampling(cpu); @@ -1190,7 +1129,8 @@ start_all_exit: hws_oom = 1; hws_flush_all = 0; /* now let them in, 1407 CPUMF external interrupts */ - measurement_alert_subclass_register(); + hws_alert = 1; + irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); return 0; } @@ -1210,7 +1150,7 @@ int hwsampler_stop_all(void) rc = 0; if (hws_state == HWS_INIT) { mutex_unlock(&hws_sem); - return rc; + return 0; } hws_state = HWS_STOPPING; mutex_unlock(&hws_sem); diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h index 1912f3bb190..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 lpp; /* Logical-Partition Program Param. */ - unsigned long long vpp; /* Virtual-Machine Program Param. */ -}; - -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 584b93674ea..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; } @@ -346,16 +363,15 @@ static const struct file_operations timer_enabled_fops = { }; -static int oprofile_create_hwsampling_files(struct super_block *sb, - struct dentry *root) +static int oprofile_create_hwsampling_files(struct dentry *root) { struct dentry *dir; - dir = oprofilefs_mkdir(sb, root, "timer"); + dir = oprofilefs_mkdir(root, "timer"); if (!dir) return -EINVAL; - oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops); + oprofilefs_create_file(dir, "enabled", &timer_enabled_fops); if (!hwsampler_available) return 0; @@ -376,17 +392,17 @@ static int oprofile_create_hwsampling_files(struct super_block *sb, * and can only be set to 0. */ - dir = oprofilefs_mkdir(sb, root, "0"); + dir = oprofilefs_mkdir(root, "0"); if (!dir) return -EINVAL; - oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops); - oprofilefs_create_file(sb, dir, "event", &zero_fops); - oprofilefs_create_file(sb, dir, "count", &hw_interval_fops); - oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops); - oprofilefs_create_file(sb, dir, "kernel", &kernel_fops); - oprofilefs_create_file(sb, dir, "user", &user_fops); - oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks", + oprofilefs_create_file(dir, "enabled", &hwsampler_fops); + oprofilefs_create_file(dir, "event", &zero_fops); + oprofilefs_create_file(dir, "count", &hw_interval_fops); + oprofilefs_create_file(dir, "unit_mask", &zero_fops); + oprofilefs_create_file(dir, "kernel", &kernel_fops); + oprofilefs_create_file(dir, "user", &user_fops); + oprofilefs_create_ulong(dir, "hw_sdbt_blocks", &oprofile_sdbt_blocks); } else { @@ -396,19 +412,19 @@ static int oprofile_create_hwsampling_files(struct super_block *sb, * space tools. The /dev/oprofile/hwsampling fs is * provided in that case. */ - dir = oprofilefs_mkdir(sb, root, "hwsampling"); + dir = oprofilefs_mkdir(root, "hwsampling"); if (!dir) return -EINVAL; - oprofilefs_create_file(sb, dir, "hwsampler", + oprofilefs_create_file(dir, "hwsampler", &hwsampler_fops); - oprofilefs_create_file(sb, dir, "hw_interval", + oprofilefs_create_file(dir, "hw_interval", &hw_interval_fops); - oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval", + oprofilefs_create_ro_ulong(dir, "hw_min_interval", &oprofile_min_interval); - oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval", + oprofilefs_create_ro_ulong(dir, "hw_max_interval", &oprofile_max_interval); - oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks", + oprofilefs_create_ulong(dir, "hw_sdbt_blocks", &oprofile_sdbt_blocks); } return 0; @@ -440,6 +456,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops) switch (id.machine) { case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break; case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break; + case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break; default: return -ENODEV; } } diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index f0f426a113c..a9e1dc4ae44 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -2,5 +2,5 @@ # Makefile for the s390 PCI subsystem. # -obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_msi.o \ - pci_sysfs.o pci_event.o pci_debug.o +obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_sysfs.o \ + pci_event.o pci_debug.o pci_insn.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 60e0372545d..30de42730b2 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -42,82 +42,40 @@ #define SIC_IRQ_MODE_SINGLE 1 #define ZPCI_NR_DMA_SPACES 1 -#define ZPCI_MSI_VEC_BITS 6 #define ZPCI_NR_DEVICES CONFIG_PCI_NR_FUNCTIONS /* list of all detected zpci devices */ -LIST_HEAD(zpci_list); -EXPORT_SYMBOL_GPL(zpci_list); -DEFINE_MUTEX(zpci_list_lock); -EXPORT_SYMBOL_GPL(zpci_list_lock); +static LIST_HEAD(zpci_list); +static DEFINE_SPINLOCK(zpci_list_lock); -struct pci_hp_callback_ops hotplug_ops; -EXPORT_SYMBOL_GPL(hotplug_ops); +static struct irq_chip zpci_irq_chip = { + .name = "zPCI", + .irq_unmask = unmask_msi_irq, + .irq_mask = mask_msi_irq, +}; static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); static DEFINE_SPINLOCK(zpci_domain_lock); -struct callback { - irq_handler_t handler; - void *data; -}; +static struct airq_iv *zpci_aisb_iv; +static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES]; -struct zdev_irq_map { - unsigned long aibv; /* AI bit vector */ - int msi_vecs; /* consecutive MSI-vectors used */ - int __unused; - struct callback cb[ZPCI_NR_MSI_VECS]; /* callback handler array */ - spinlock_t lock; /* protect callbacks against de-reg */ -}; +/* Adapter interrupt definitions */ +static void zpci_irq_handler(struct airq_struct *airq); -struct intr_bucket { - /* amap of adapters, one bit per dev, corresponds to one irq nr */ - unsigned long *alloc; - /* AI summary bit, global page for all devices */ - unsigned long *aisb; - /* pointer to aibv and callback data in zdev */ - struct zdev_irq_map *imap[ZPCI_NR_DEVICES]; - /* protects the whole bucket struct */ - spinlock_t lock; +static struct airq_struct zpci_airq = { + .handler = zpci_irq_handler, + .isc = PCI_ISC, }; -static struct intr_bucket *bucket; - -/* Adapter local summary indicator */ -static u8 *zpci_irq_si; - -static atomic_t irq_retries = ATOMIC_INIT(0); - /* I/O Map */ static DEFINE_SPINLOCK(zpci_iomap_lock); static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES); struct zpci_iomap_entry *zpci_iomap_start; EXPORT_SYMBOL_GPL(zpci_iomap_start); -/* highest irq summary bit */ -static int __read_mostly aisb_max; - -static struct kmem_cache *zdev_irq_cache; static struct kmem_cache *zdev_fmb_cache; -debug_info_t *pci_debug_msg_id; -debug_info_t *pci_debug_err_id; - -static inline int irq_to_msi_nr(unsigned int irq) -{ - return irq & ZPCI_MSI_MASK; -} - -static inline int irq_to_dev_nr(unsigned int irq) -{ - return irq >> ZPCI_MSI_VEC_BITS; -} - -static inline struct zdev_irq_map *get_imap(unsigned int irq) -{ - return bucket->imap[irq_to_dev_nr(irq)]; -} - struct zpci_dev *get_zdev(struct pci_dev *pdev) { return (struct zpci_dev *) pdev->sysdata; @@ -127,22 +85,17 @@ struct zpci_dev *get_zdev_by_fid(u32 fid) { struct zpci_dev *tmp, *zdev = NULL; - mutex_lock(&zpci_list_lock); + spin_lock(&zpci_list_lock); list_for_each_entry(tmp, &zpci_list, entry) { if (tmp->fid == fid) { zdev = tmp; break; } } - mutex_unlock(&zpci_list_lock); + spin_unlock(&zpci_list_lock); return zdev; } -bool zpci_fid_present(u32 fid) -{ - return (get_zdev_by_fid(fid) != NULL) ? true : false; -} - static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus) { return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL; @@ -161,30 +114,20 @@ int pci_proc_domain(struct pci_bus *bus) EXPORT_SYMBOL_GPL(pci_proc_domain); /* Modify PCI: Register adapter interruptions */ -static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb, - u64 aibv) +static int zpci_set_airq(struct zpci_dev *zdev) { u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT); - struct zpci_fib *fib; - int rc; - - fib = (void *) get_zeroed_page(GFP_KERNEL); - if (!fib) - return -ENOMEM; + struct zpci_fib fib = {0}; - fib->isc = PCI_ISC; - fib->noi = zdev->irq_map->msi_vecs; - fib->sum = 1; /* enable summary notifications */ - fib->aibv = aibv; - fib->aibvo = 0; /* every function has its own page */ - fib->aisb = (u64) bucket->aisb + aisb / 8; - fib->aisbo = aisb & ZPCI_MSI_MASK; + fib.isc = PCI_ISC; + fib.sum = 1; /* enable summary notifications */ + fib.noi = airq_iv_end(zdev->aibv); + fib.aibv = (unsigned long) zdev->aibv->vector; + fib.aibvo = 0; /* each zdev has its own interrupt vector */ + fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8; + fib.aisbo = zdev->aisb & 63; - rc = mpcifc_instr(req, fib); - pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi); - - free_page((unsigned long) fib); - return rc; + return zpci_mod_fc(req, &fib); } struct mod_pci_args { @@ -197,22 +140,14 @@ struct mod_pci_args { static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args *args) { u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, fn); - struct zpci_fib *fib; - int rc; + struct zpci_fib fib = {0}; - /* The FIB must be available even if it's not used */ - fib = (void *) get_zeroed_page(GFP_KERNEL); - if (!fib) - return -ENOMEM; - - fib->pba = args->base; - fib->pal = args->limit; - fib->iota = args->iota; - fib->fmb_addr = args->fmb_addr; + fib.pba = args->base; + fib.pal = args->limit; + fib.iota = args->iota; + fib.fmb_addr = args->fmb_addr; - rc = mpcifc_instr(req, fib); - free_page((unsigned long) fib); - return rc; + return zpci_mod_fc(req, &fib); } /* Modify PCI: Register I/O address translation parameters */ @@ -235,7 +170,7 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) } /* Modify PCI: Unregister adapter interruptions */ -static int zpci_unregister_airq(struct zpci_dev *zdev) +static int zpci_clear_airq(struct zpci_dev *zdev) { struct mod_pci_args args = { 0, 0, 0, 0 }; @@ -250,10 +185,9 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) if (zdev->fmb) return -EINVAL; - zdev->fmb = kmem_cache_alloc(zdev_fmb_cache, GFP_KERNEL); + zdev->fmb = kmem_cache_zalloc(zdev_fmb_cache, GFP_KERNEL); if (!zdev->fmb) return -ENOMEM; - memset(zdev->fmb, 0, sizeof(*zdev->fmb)); WARN_ON((u64) zdev->fmb & 0xf); args.fmb_addr = virt_to_phys(zdev->fmb); @@ -285,12 +219,12 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len) u64 data; int rc; - rc = pcilg_instr(&data, req, offset); - data = data << ((8 - len) * 8); - data = le64_to_cpu(data); - if (!rc) + rc = zpci_load(&data, req, offset); + if (!rc) { + data = data << ((8 - len) * 8); + data = le64_to_cpu(data); *val = (u32) data; - else + } else *val = 0xffffffff; return rc; } @@ -303,59 +237,10 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len) data = cpu_to_le64(data); data = data >> ((8 - len) * 8); - rc = pcistg_instr(data, req, offset); + rc = zpci_store(data, req, offset); return rc; } -void synchronize_irq(unsigned int irq) -{ - /* - * Not needed, the handler is protected by a lock and IRQs that occur - * after the handler is deleted are just NOPs. - */ -} -EXPORT_SYMBOL_GPL(synchronize_irq); - -void enable_irq(unsigned int irq) -{ - struct msi_desc *msi = irq_get_msi_desc(irq); - - zpci_msi_set_mask_bits(msi, 1, 0); -} -EXPORT_SYMBOL_GPL(enable_irq); - -void disable_irq(unsigned int irq) -{ - struct msi_desc *msi = irq_get_msi_desc(irq); - - zpci_msi_set_mask_bits(msi, 1, 1); -} -EXPORT_SYMBOL_GPL(disable_irq); - -void disable_irq_nosync(unsigned int irq) -{ - disable_irq(irq); -} -EXPORT_SYMBOL_GPL(disable_irq_nosync); - -unsigned long probe_irq_on(void) -{ - return 0; -} -EXPORT_SYMBOL_GPL(probe_irq_on); - -int probe_irq_off(unsigned long val) -{ - return 0; -} -EXPORT_SYMBOL_GPL(probe_irq_off); - -unsigned int probe_irq_mask(unsigned long val) -{ - return val; -} -EXPORT_SYMBOL_GPL(probe_irq_mask); - void pcibios_fixup_bus(struct pci_bus *bus) { } @@ -410,20 +295,28 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { struct zpci_dev *zdev = get_zdev_by_bus(bus); + int ret; if (!zdev || devfn != ZPCI_DEVFN) - return 0; - return zpci_cfg_load(zdev, where, val, size); + ret = -ENODEV; + else + ret = zpci_cfg_load(zdev, where, val, size); + + return ret; } static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { struct zpci_dev *zdev = get_zdev_by_bus(bus); + int ret; if (!zdev || devfn != ZPCI_DEVFN) - return 0; - return zpci_cfg_store(zdev, where, val, size); + ret = -ENODEV; + else + ret = zpci_cfg_store(zdev, where, val, size); + + return ret; } static struct pci_ops pci_root_ops = { @@ -431,153 +324,144 @@ static struct pci_ops pci_root_ops = { .write = pci_write, }; -/* store the last handled bit to implement fair scheduling of devices */ -static DEFINE_PER_CPU(unsigned long, next_sbit); - -static void zpci_irq_handler(void *dont, void *need) +static void zpci_irq_handler(struct airq_struct *airq) { - unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit); - int rescan = 0, max = aisb_max; - struct zdev_irq_map *imap; + unsigned long si, ai; + struct airq_iv *aibv; + int irqs_on = 0; inc_irq_stat(IRQIO_PCI); - sbit = start; - -scan: - /* find summary_bit */ - for_each_set_bit_left_cont(sbit, bucket->aisb, max) { - clear_bit(63 - (sbit & 63), bucket->aisb + (sbit >> 6)); - last = sbit; + for (si = 0;;) { + /* Scan adapter summary indicator bit vector */ + si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv)); + if (si == -1UL) { + if (irqs_on++) + /* End of second scan with interrupts on. */ + break; + /* First scan complete, reenable interrupts. */ + zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + si = 0; + continue; + } - /* find vector bit */ - imap = bucket->imap[sbit]; - for_each_set_bit_left(mbit, &imap->aibv, imap->msi_vecs) { + /* Scan the adapter interrupt vector for this device. */ + aibv = zpci_aibv[si]; + for (ai = 0;;) { + ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv)); + if (ai == -1UL) + break; inc_irq_stat(IRQIO_MSI); - clear_bit(63 - mbit, &imap->aibv); - - spin_lock(&imap->lock); - if (imap->cb[mbit].handler) - imap->cb[mbit].handler(mbit, - imap->cb[mbit].data); - spin_unlock(&imap->lock); + airq_iv_lock(aibv, ai); + generic_handle_irq(airq_iv_get_data(aibv, ai)); + airq_iv_unlock(aibv, ai); } } - - if (rescan) - goto out; - - /* scan the skipped bits */ - if (start > 0) { - sbit = 0; - max = start; - start = 0; - goto scan; - } - - /* enable interrupts again */ - sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); - - /* check again to not lose initiative */ - rmb(); - max = aisb_max; - sbit = find_first_bit_left(bucket->aisb, max); - if (sbit != max) { - atomic_inc(&irq_retries); - rescan++; - goto scan; - } -out: - /* store next device bit to scan */ - __get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last; } -/* msi_vecs - number of requested interrupts, 0 place function to error state */ -static int zpci_setup_msi(struct pci_dev *pdev, int msi_vecs) +int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { struct zpci_dev *zdev = get_zdev(pdev); - unsigned int aisb, msi_nr; + unsigned int hwirq, msi_vecs; + unsigned long aisb; struct msi_desc *msi; - int rc; - - /* store the number of used MSI vectors */ - zdev->irq_map->msi_vecs = min(msi_vecs, ZPCI_NR_MSI_VECS); - - spin_lock(&bucket->lock); - aisb = find_first_zero_bit(bucket->alloc, PAGE_SIZE); - /* alloc map exhausted? */ - if (aisb == PAGE_SIZE) { - spin_unlock(&bucket->lock); - return -EIO; - } - set_bit(aisb, bucket->alloc); - spin_unlock(&bucket->lock); - + struct msi_msg msg; + int rc, irq; + + 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); + + /* Allocate adapter summary indicator bit */ + rc = -EIO; + aisb = airq_iv_alloc_bit(zpci_aisb_iv); + if (aisb == -1UL) + goto out; zdev->aisb = aisb; - if (aisb + 1 > aisb_max) - aisb_max = aisb + 1; - /* wire up IRQ shortcut pointer */ - bucket->imap[zdev->aisb] = zdev->irq_map; - pr_debug("%s: imap[%u] linked to %p\n", __func__, zdev->aisb, zdev->irq_map); + /* Create adapter interrupt vector */ + rc = -ENOMEM; + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); + if (!zdev->aibv) + goto out_si; - /* TODO: irq number 0 wont be found if we return less than requested MSIs. - * ignore it for now and fix in common code. - */ - msi_nr = aisb << ZPCI_MSI_VEC_BITS; + /* Wire up shortcut pointer */ + zpci_aibv[aisb] = zdev->aibv; + /* Request MSI interrupts */ + hwirq = 0; list_for_each_entry(msi, &pdev->msi_list, list) { - rc = zpci_setup_msi_irq(zdev, msi, msi_nr, - aisb << ZPCI_MSI_VEC_BITS); + rc = -EIO; + irq = irq_alloc_desc(0); /* Alloc irq on node 0 */ + if (irq < 0) + goto out_msi; + rc = irq_set_msi_desc(irq, msi); if (rc) - return rc; - msi_nr++; + goto out_msi; + irq_set_chip_and_handler(irq, &zpci_irq_chip, + handle_simple_irq); + msg.data = hwirq; + msg.address_lo = zdev->msi_addr & 0xffffffff; + msg.address_hi = zdev->msi_addr >> 32; + write_msi_msg(irq, &msg); + airq_iv_set_data(zdev->aibv, hwirq, irq); + hwirq++; } - rc = zpci_register_airq(zdev, aisb, (u64) &zdev->irq_map->aibv); - if (rc) { - clear_bit(aisb, bucket->alloc); - dev_err(&pdev->dev, "register MSI failed with: %d\n", rc); - return rc; + /* Enable adapter interrupts */ + rc = zpci_set_airq(zdev); + if (rc) + goto out_msi; + + return (msi_vecs == nvec) ? 0 : msi_vecs; + +out_msi: + list_for_each_entry(msi, &pdev->msi_list, list) { + if (hwirq-- == 0) + break; + irq_set_msi_desc(msi->irq, NULL); + irq_free_desc(msi->irq); + msi->msg.address_lo = 0; + msi->msg.address_hi = 0; + msi->msg.data = 0; + msi->irq = 0; } - return (zdev->irq_map->msi_vecs == msi_vecs) ? - 0 : zdev->irq_map->msi_vecs; + zpci_aibv[aisb] = NULL; + airq_iv_release(zdev->aibv); +out_si: + airq_iv_free_bit(zpci_aisb_iv, aisb); +out: + return rc; } -static void zpci_teardown_msi(struct pci_dev *pdev) +void arch_teardown_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = get_zdev(pdev); struct msi_desc *msi; - int aisb, rc; + int rc; - rc = zpci_unregister_airq(zdev); - if (rc) { - dev_err(&pdev->dev, "deregister MSI failed with: %d\n", rc); + /* Disable adapter interrupts */ + rc = zpci_clear_airq(zdev); + if (rc) return; - } - - msi = list_first_entry(&pdev->msi_list, struct msi_desc, list); - aisb = irq_to_dev_nr(msi->irq); - list_for_each_entry(msi, &pdev->msi_list, list) - zpci_teardown_msi_irq(zdev, msi); - - clear_bit(aisb, bucket->alloc); - if (aisb + 1 == aisb_max) - aisb_max--; -} - -int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) -{ - pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec); - if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI) - return -EINVAL; - return zpci_setup_msi(pdev, nvec); -} + /* Release MSI interrupts */ + list_for_each_entry(msi, &pdev->msi_list, list) { + if (msi->msi_attrib.is_msix) + default_msix_mask_irq(msi, 1); + else + default_msi_mask_irq(msi, 1, 1); + irq_set_msi_desc(msi->irq, NULL); + irq_free_desc(msi->irq); + msi->msg.address_lo = 0; + msi->msg.address_hi = 0; + msi->msg.data = 0; + msi->irq = 0; + } -void arch_teardown_msi_irqs(struct pci_dev *pdev) -{ - pr_info("%s: on pdev: %p\n", __func__, pdev); - zpci_teardown_msi(pdev); + zpci_aibv[zdev->aisb] = NULL; + airq_iv_release(zdev->aibv); + airq_iv_free_bit(zpci_aisb_iv, zdev->aisb); } static void zpci_map_resources(struct zpci_dev *zdev) @@ -592,13 +476,12 @@ static void zpci_map_resources(struct zpci_dev *zdev) continue; pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0); pdev->resource[i].end = pdev->resource[i].start + len - 1; - pr_debug("BAR%i: -> start: %Lx end: %Lx\n", - i, pdev->resource[i].start, pdev->resource[i].end); } -}; +} -static void zpci_unmap_resources(struct pci_dev *pdev) +static void zpci_unmap_resources(struct zpci_dev *zdev) { + struct pci_dev *pdev = zdev->pdev; resource_size_t len; int i; @@ -608,246 +491,36 @@ static void zpci_unmap_resources(struct pci_dev *pdev) continue; pci_iounmap(pdev, (void *) pdev->resource[i].start); } -}; - -struct zpci_dev *zpci_alloc_device(void) -{ - struct zpci_dev *zdev; - - /* Alloc memory for our private pci device data */ - zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); - if (!zdev) - return ERR_PTR(-ENOMEM); - - /* Alloc aibv & callback space */ - zdev->irq_map = kmem_cache_zalloc(zdev_irq_cache, GFP_KERNEL); - if (!zdev->irq_map) - goto error; - WARN_ON((u64) zdev->irq_map & 0xff); - return zdev; - -error: - kfree(zdev); - return ERR_PTR(-ENOMEM); -} - -void zpci_free_device(struct zpci_dev *zdev) -{ - kmem_cache_free(zdev_irq_cache, zdev->irq_map); - kfree(zdev); -} - -/* Called on removal of pci_dev, leaves zpci and bus device */ -static void zpci_remove_device(struct pci_dev *pdev) -{ - struct zpci_dev *zdev = get_zdev(pdev); - - dev_info(&pdev->dev, "Removing device %u\n", zdev->domain); - zdev->state = ZPCI_FN_STATE_CONFIGURED; - zpci_dma_exit_device(zdev); - zpci_fmb_disable_device(zdev); - zpci_sysfs_remove_device(&pdev->dev); - zpci_unmap_resources(pdev); - list_del(&zdev->entry); /* can be called from init */ - zdev->pdev = NULL; -} - -static void zpci_scan_devices(void) -{ - struct zpci_dev *zdev; - - mutex_lock(&zpci_list_lock); - list_for_each_entry(zdev, &zpci_list, entry) - if (zdev->state == ZPCI_FN_STATE_CONFIGURED) - zpci_scan_device(zdev); - mutex_unlock(&zpci_list_lock); -} - -/* - * Too late for any s390 specific setup, since interrupts must be set up - * already which requires DMA setup too and the pci scan will access the - * config space, which only works if the function handle is enabled. - */ -int pcibios_enable_device(struct pci_dev *pdev, int mask) -{ - struct resource *res; - u16 cmd; - int i; - - 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; -} - -void pcibios_disable_device(struct pci_dev *pdev) -{ - zpci_remove_device(pdev); - pdev->sysdata = NULL; -} - -int pcibios_add_platform_entries(struct pci_dev *pdev) -{ - return zpci_sysfs_add_device(&pdev->dev); -} - -int zpci_request_irq(unsigned int irq, irq_handler_t handler, void *data) -{ - int msi_nr = irq_to_msi_nr(irq); - struct zdev_irq_map *imap; - struct msi_desc *msi; - - msi = irq_get_msi_desc(irq); - if (!msi) - return -EIO; - - imap = get_imap(irq); - spin_lock_init(&imap->lock); - - pr_debug("%s: register handler for IRQ:MSI %d:%d\n", __func__, irq >> 6, msi_nr); - imap->cb[msi_nr].handler = handler; - imap->cb[msi_nr].data = data; - - /* - * The generic MSI code returns with the interrupt disabled on the - * card, using the MSI mask bits. Firmware doesn't appear to unmask - * at that level, so we do it here by hand. - */ - zpci_msi_set_mask_bits(msi, 1, 0); - return 0; -} - -void zpci_free_irq(unsigned int irq) -{ - struct zdev_irq_map *imap = get_imap(irq); - int msi_nr = irq_to_msi_nr(irq); - unsigned long flags; - - pr_debug("%s: for irq: %d\n", __func__, irq); - - spin_lock_irqsave(&imap->lock, flags); - imap->cb[msi_nr].handler = NULL; - imap->cb[msi_nr].data = NULL; - spin_unlock_irqrestore(&imap->lock, flags); -} - -int request_irq(unsigned int irq, irq_handler_t handler, - unsigned long irqflags, const char *devname, void *dev_id) -{ - pr_debug("%s: irq: %d handler: %p flags: %lx dev: %s\n", - __func__, irq, handler, irqflags, devname); - - return zpci_request_irq(irq, handler, dev_id); -} -EXPORT_SYMBOL_GPL(request_irq); - -void free_irq(unsigned int irq, void *dev_id) -{ - zpci_free_irq(irq); } -EXPORT_SYMBOL_GPL(free_irq); static int __init zpci_irq_init(void) { - int cpu, rc; - - bucket = kzalloc(sizeof(*bucket), GFP_KERNEL); - if (!bucket) - return -ENOMEM; - - bucket->aisb = (unsigned long *) get_zeroed_page(GFP_KERNEL); - if (!bucket->aisb) { - rc = -ENOMEM; - goto out_aisb; - } - - bucket->alloc = (unsigned long *) get_zeroed_page(GFP_KERNEL); - if (!bucket->alloc) { - rc = -ENOMEM; - goto out_alloc; - } + int rc; - isc_register(PCI_ISC); - zpci_irq_si = s390_register_adapter_interrupt(&zpci_irq_handler, NULL, PCI_ISC); - if (IS_ERR(zpci_irq_si)) { - rc = PTR_ERR(zpci_irq_si); - zpci_irq_si = NULL; - goto out_ai; - } + rc = register_adapter_interrupt(&zpci_airq); + if (rc) + goto out; + /* Set summary to 1 to be called every time for the ISC. */ + *zpci_airq.lsi_ptr = 1; - for_each_online_cpu(cpu) - per_cpu(next_sbit, cpu) = 0; + rc = -ENOMEM; + zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC); + if (!zpci_aisb_iv) + goto out_airq; - spin_lock_init(&bucket->lock); - /* set summary to 1 to be called every time for the ISC */ - *zpci_irq_si = 1; - sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); return 0; -out_ai: - isc_unregister(PCI_ISC); - free_page((unsigned long) bucket->alloc); -out_alloc: - free_page((unsigned long) bucket->aisb); -out_aisb: - kfree(bucket); +out_airq: + unregister_adapter_interrupt(&zpci_airq); +out: return rc; } static void zpci_irq_exit(void) { - free_page((unsigned long) bucket->alloc); - free_page((unsigned long) bucket->aisb); - s390_unregister_adapter_interrupt(zpci_irq_si, PCI_ISC); - isc_unregister(PCI_ISC); - kfree(bucket); -} - -void zpci_debug_info(struct zpci_dev *zdev, struct seq_file *m) -{ - if (!zdev) - return; - - seq_printf(m, "global irq retries: %u\n", atomic_read(&irq_retries)); - seq_printf(m, "aibv[0]:%016lx aibv[1]:%016lx aisb:%016lx\n", - get_imap(0)->aibv, get_imap(1)->aibv, *bucket->aisb); -} - -static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size, - unsigned long flags, int domain) -{ - struct resource *r; - char *name; - int rc; - - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return ERR_PTR(-ENOMEM); - r->start = start; - r->end = r->start + size - 1; - r->flags = flags; - r->parent = &iomem_resource; - name = kmalloc(18, GFP_KERNEL); - if (!name) { - kfree(r); - return ERR_PTR(-ENOMEM); - } - sprintf(name, "PCI Bus: %04x:%02x", domain, ZPCI_BUS_NR); - r->name = name; - - rc = request_resource(&iomem_resource, r); - if (rc) - pr_debug("request resource %pR failed\n", r); - return r; + airq_iv_release(zpci_aisb_iv); + unregister_adapter_interrupt(&zpci_airq); } static int zpci_alloc_iomap(struct zpci_dev *zdev) @@ -873,17 +546,38 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } -static int zpci_create_device_bus(struct zpci_dev *zdev) +static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, + unsigned long size, unsigned long flags) { + struct resource *r; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return NULL; + + r->start = start; + r->end = r->start + size - 1; + r->flags = flags; + r->name = zdev->res_name; + + if (request_resource(&iomem_resource, r)) { + kfree(r); + return NULL; + } + return r; +} + +static int zpci_setup_bus_resources(struct zpci_dev *zdev, + struct list_head *resources) +{ + unsigned long addr, size, flags; struct resource *res; - LIST_HEAD(resources); - int i; + int i, entry; - /* allocate mapping entry for each used bar */ - for (i = 0; i < PCI_BAR_COUNT; i++) { - unsigned long addr, size, flags; - int entry; + snprintf(zdev->res_name, sizeof(zdev->res_name), + "PCI Bus %04x:%02x", zdev->domain, ZPCI_BUS_NR); + for (i = 0; i < PCI_BAR_COUNT; i++) { if (!zdev->bars[i].size) continue; entry = zpci_alloc_iomap(zdev); @@ -902,23 +596,115 @@ static int zpci_create_device_bus(struct zpci_dev *zdev) size = 1UL << zdev->bars[i].size; - res = zpci_alloc_bus_resource(addr, size, flags, zdev->domain); - if (IS_ERR(res)) { + res = __alloc_res(zdev, addr, size, flags); + if (!res) { zpci_free_iomap(zdev, entry); - return PTR_ERR(res); + return -ENOMEM; } - pci_add_resource(&resources, res); + zdev->bars[i].res = res; + pci_add_resource(resources, res); } - zdev->bus = pci_create_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, - zdev, &resources); - if (!zdev->bus) - return -EIO; + return 0; +} + +static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) +{ + int i; + + for (i = 0; i < PCI_BAR_COUNT; i++) { + if (!zdev->bars[i].size) + continue; + + zpci_free_iomap(zdev, zdev->bars[i].map_idx); + release_resource(zdev->bars[i].res); + kfree(zdev->bars[i].res); + } +} + +int pcibios_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = get_zdev(pdev); + struct resource *res; + int i; + + zdev->pdev = pdev; + pdev->dev.groups = zpci_attr_groups; + zpci_map_resources(zdev); + + for (i = 0; i < PCI_BAR_COUNT; i++) { + res = &pdev->resource[i]; + if (res->parent || !res->flags) + continue; + pci_claim_resource(pdev, i); + } - zdev->bus->max_bus_speed = zdev->max_bus_speed; return 0; } +int pcibios_enable_device(struct pci_dev *pdev, int mask) +{ + struct zpci_dev *zdev = get_zdev(pdev); + + zdev->pdev = pdev; + zpci_debug_init_device(zdev); + zpci_fmb_enable_device(zdev); + zpci_map_resources(zdev); + + return pci_enable_resources(pdev, mask); +} + +void pcibios_disable_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = get_zdev(pdev); + + zpci_unmap_resources(zdev); + zpci_fmb_disable_device(zdev); + zpci_debug_exit_device(zdev); + zdev->pdev = NULL; +} + +#ifdef CONFIG_HIBERNATE_CALLBACKS +static int zpci_restore(struct device *dev) +{ + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); + int ret = 0; + + if (zdev->state != ZPCI_FN_STATE_ONLINE) + goto out; + + ret = clp_enable_fh(zdev, ZPCI_NR_DMA_SPACES); + if (ret) + goto out; + + zpci_map_resources(zdev); + zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET, + zdev->start_dma + zdev->iommu_size - 1, + (u64) zdev->dma_table); + +out: + return ret; +} + +static int zpci_freeze(struct device *dev) +{ + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); + + if (zdev->state != ZPCI_FN_STATE_ONLINE) + return 0; + + zpci_unregister_ioat(zdev, 0); + return clp_disable_fh(zdev); +} + +struct dev_pm_ops pcibios_pm_ops = { + .thaw_noirq = zpci_restore, + .freeze_noirq = zpci_freeze, + .restore_noirq = zpci_restore, + .poweroff_noirq = zpci_freeze, +}; +#endif /* CONFIG_HIBERNATE_CALLBACKS */ + static int zpci_alloc_domain(struct zpci_dev *zdev) { spin_lock(&zpci_domain_lock); @@ -939,6 +725,41 @@ static void zpci_free_domain(struct zpci_dev *zdev) spin_unlock(&zpci_domain_lock); } +void pcibios_remove_bus(struct pci_bus *bus) +{ + struct zpci_dev *zdev = get_zdev_by_bus(bus); + + zpci_exit_slot(zdev); + zpci_cleanup_bus_resources(zdev); + zpci_free_domain(zdev); + + spin_lock(&zpci_list_lock); + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); + + kfree(zdev); +} + +static int zpci_scan_bus(struct zpci_dev *zdev) +{ + LIST_HEAD(resources); + int ret; + + ret = zpci_setup_bus_resources(zdev, &resources); + if (ret) + return ret; + + zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, + zdev, &resources); + if (!zdev->bus) { + zpci_cleanup_bus_resources(zdev); + return -EIO; + } + + zdev->bus->max_bus_speed = zdev->max_bus_speed; + return 0; +} + int zpci_enable_device(struct zpci_dev *zdev) { int rc; @@ -946,11 +767,12 @@ int zpci_enable_device(struct zpci_dev *zdev) rc = clp_enable_fh(zdev, ZPCI_NR_DMA_SPACES); if (rc) goto out; - pr_info("Enabled fh: 0x%x fid: 0x%x\n", zdev->fh, zdev->fid); rc = zpci_dma_init_device(zdev); if (rc) goto out_dma; + + zdev->state = ZPCI_FN_STATE_ONLINE; return 0; out_dma: @@ -960,6 +782,13 @@ out: } EXPORT_SYMBOL_GPL(zpci_enable_device); +int zpci_disable_device(struct zpci_dev *zdev) +{ + zpci_dma_exit_device(zdev); + return clp_disable_fh(zdev); +} +EXPORT_SYMBOL_GPL(zpci_disable_device); + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -968,31 +797,27 @@ int zpci_create_device(struct zpci_dev *zdev) if (rc) goto out; - rc = zpci_create_device_bus(zdev); + if (zdev->state == ZPCI_FN_STATE_CONFIGURED) { + rc = zpci_enable_device(zdev); + if (rc) + goto out_free; + } + rc = zpci_scan_bus(zdev); if (rc) - goto out_bus; + goto out_disable; - mutex_lock(&zpci_list_lock); + spin_lock(&zpci_list_lock); list_add_tail(&zdev->entry, &zpci_list); - if (hotplug_ops.create_slot) - hotplug_ops.create_slot(zdev); - mutex_unlock(&zpci_list_lock); + spin_unlock(&zpci_list_lock); - if (zdev->state == ZPCI_FN_STATE_STANDBY) - return 0; + zpci_init_slot(zdev); - rc = zpci_enable_device(zdev); - if (rc) - goto out_start; return 0; -out_start: - mutex_lock(&zpci_list_lock); - list_del(&zdev->entry); - if (hotplug_ops.remove_slot) - hotplug_ops.remove_slot(zdev); - mutex_unlock(&zpci_list_lock); -out_bus: +out_disable: + if (zdev->state == ZPCI_FN_STATE_ONLINE) + zpci_disable_device(zdev); +out_free: zpci_free_domain(zdev); out: return rc; @@ -1008,31 +833,6 @@ void zpci_stop_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_stop_device); -int zpci_scan_device(struct zpci_dev *zdev) -{ - zdev->pdev = pci_scan_single_device(zdev->bus, ZPCI_DEVFN); - if (!zdev->pdev) { - pr_err("pci_scan_single_device failed for fid: 0x%x\n", - zdev->fid); - goto out; - } - - zpci_debug_init_device(zdev); - zpci_fmb_enable_device(zdev); - zpci_map_resources(zdev); - pci_bus_add_devices(zdev->bus); - - /* now that pdev was added to the bus mark it as used */ - zdev->state = ZPCI_FN_STATE_ONLINE; - return 0; - -out: - zpci_dma_exit_device(zdev); - clp_disable_fh(zdev); - return -EIO; -} -EXPORT_SYMBOL_GPL(zpci_scan_device); - static inline int barsize(u8 size) { return (size) ? (1 << size) >> 10 : 0; @@ -1040,15 +840,10 @@ static inline int barsize(u8 size) static int zpci_mem_init(void) { - zdev_irq_cache = kmem_cache_create("PCI_IRQ_cache", sizeof(struct zdev_irq_map), - L1_CACHE_BYTES, SLAB_HWCACHE_ALIGN, NULL); - if (!zdev_irq_cache) - goto error_zdev; - zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), 16, 0, NULL); if (!zdev_fmb_cache) - goto error_fmb; + goto error_zdev; /* TODO: use realloc */ zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start), @@ -1059,8 +854,6 @@ static int zpci_mem_init(void) error_iomap: kmem_cache_destroy(zdev_fmb_cache); -error_fmb: - kmem_cache_destroy(zdev_irq_cache); error_zdev: return -ENOMEM; } @@ -1068,49 +861,45 @@ error_zdev: static void zpci_mem_exit(void) { kfree(zpci_iomap_start); - kmem_cache_destroy(zdev_irq_cache); kmem_cache_destroy(zdev_fmb_cache); } -unsigned int pci_probe = 1; -EXPORT_SYMBOL_GPL(pci_probe); +static unsigned int s390_pci_probe = 1; +static unsigned int s390_pci_initialized; char * __init pcibios_setup(char *str) { if (!strcmp(str, "off")) { - pci_probe = 0; + 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; - if (!pci_probe) + if (!s390_pci_probe) return 0; if (!test_facility(2) || !test_facility(69) || !test_facility(71) || !test_facility(72)) return 0; - pr_info("Probing PCI hardware: PCI:%d SID:%d AEN:%d\n", - test_facility(69), test_facility(70), - test_facility(71)); - rc = zpci_debug_init(); if (rc) - return rc; + goto out; rc = zpci_mem_init(); if (rc) goto out_mem; - rc = zpci_msihash_init(); - if (rc) - goto out_hash; - rc = zpci_irq_init(); if (rc) goto out_irq; @@ -1119,11 +908,11 @@ static int __init pci_base_init(void) if (rc) goto out_dma; - rc = clp_find_pci_devices(); + rc = clp_scan_pci_devices(); if (rc) goto out_find; - zpci_scan_devices(); + s390_pci_initialized = 1; return 0; out_find: @@ -1131,11 +920,16 @@ out_find: out_dma: zpci_irq_exit(); out_irq: - zpci_msihash_exit(); -out_hash: zpci_mem_exit(); out_mem: zpci_debug_exit(); +out: return rc; } -subsys_initcall(pci_base_init); +subsys_initcall_sync(pci_base_init); + +void zpci_rescan(void) +{ + if (zpci_is_enabled()) + clp_rescan_pci_devices_simple(); +} diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 2c847143cbd..96545d7659f 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -13,31 +13,42 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/pci.h> +#include <asm/pci_debug.h> #include <asm/pci_clp.h> +static inline void zpci_err_clp(unsigned int rsp, int rc) +{ + struct { + unsigned int rsp; + int rc; + } __packed data = {rsp, rc}; + + zpci_err_hex(&data, sizeof(data)); +} + /* * Call Logical Processor * Retry logic is handled by the caller. */ -static inline u8 clp_instr(void *req) +static inline u8 clp_instr(void *data) { - u64 ilpm; + struct { u8 _[CLP_BLK_SIZE]; } *req = data; + u64 ignored; u8 cc; asm volatile ( - " .insn rrf,0xb9a00000,%[ilpm],%[req],0x0,0x2\n" + " .insn rrf,0xb9a00000,%[ign],%[req],0x0,0x2\n" " ipm %[cc]\n" " srl %[cc],28\n" - : [cc] "=d" (cc), [ilpm] "=d" (ilpm) + : [cc] "=d" (cc), [ign] "=d" (ignored), "+m" (*req) : [req] "a" (req) - : "cc", "memory"); + : "cc"); return cc; } -static void *clp_alloc_block(void) +static void *clp_alloc_block(gfp_t gfp_mask) { - struct page *page = alloc_pages(GFP_KERNEL, get_order(CLP_BLK_SIZE)); - return (page) ? page_address(page) : NULL; + return (void *) __get_free_pages(gfp_mask, get_order(CLP_BLK_SIZE)); } static void clp_free_block(void *ptr) @@ -53,7 +64,6 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev, zdev->msi_addr = response->msia; zdev->fmb_update = response->mui; - pr_debug("Supported number of MSI vectors: %u\n", response->noi); switch (response->version) { case 1: zdev->max_bus_speed = PCIE_SPEED_5_0GT; @@ -69,7 +79,7 @@ static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid) struct clp_req_rsp_query_pci_grp *rrb; int rc; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; @@ -83,8 +93,8 @@ static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid) if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) clp_store_query_pci_fngrp(zdev, &rrb->response); else { - pr_err("Query PCI FNGRP failed with response: %x cc: %d\n", - rrb->response.hdr.rsp, rc); + zpci_err("Q PCI FGRP:\n"); + zpci_err_clp(rrb->response.hdr.rsp, rc); rc = -EIO; } clp_free_block(rrb); @@ -104,6 +114,16 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, zdev->end_dma = response->edma; zdev->pchid = response->pchid; zdev->pfgid = response->pfgid; + zdev->pft = response->pft; + zdev->vfn = response->vfn; + zdev->uid = response->uid; + + memcpy(zdev->pfip, response->pfip, sizeof(zdev->pfip)); + if (response->util_str_avail) { + memcpy(zdev->util_str, response->util_str, + sizeof(zdev->util_str)); + } + return 0; } @@ -112,7 +132,7 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh) struct clp_req_rsp_query_pci *rrb; int rc; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; @@ -130,8 +150,8 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh) if (rrb->response.pfgid) rc = clp_query_pci_fngrp(zdev, rrb->response.pfgid); } else { - pr_err("Query PCI failed with response: %x cc: %d\n", - rrb->response.hdr.rsp, rc); + zpci_err("Q PCI FN:\n"); + zpci_err_clp(rrb->response.hdr.rsp, rc); rc = -EIO; } out: @@ -144,9 +164,10 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) struct zpci_dev *zdev; int rc; - zdev = zpci_alloc_device(); - if (IS_ERR(zdev)) - return PTR_ERR(zdev); + zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured); + zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); + if (!zdev) + return -ENOMEM; zdev->fh = fh; zdev->fid = fid; @@ -167,7 +188,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) return 0; error: - zpci_free_device(zdev); + kfree(zdev); return rc; } @@ -177,9 +198,9 @@ error: static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) { struct clp_req_rsp_set_pci *rrb; - int rc, retries = 1000; + int rc, retries = 100; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; @@ -197,15 +218,15 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) retries--; if (retries < 0) break; - msleep(1); + msleep(20); } } while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY); if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) *fh = rrb->response.fh; else { - pr_err("Set PCI FN failed with response: %x cc: %d\n", - rrb->response.hdr.rsp, rc); + zpci_err("Set PCI FN:\n"); + zpci_err_clp(rrb->response.hdr.rsp, rc); rc = -EIO; } clp_free_block(rrb); @@ -221,6 +242,8 @@ int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as) if (!rc) /* Success -> store enabled handle in zdev */ zdev->fh = fh; + + zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); return rc; } @@ -232,94 +255,138 @@ int clp_disable_fh(struct zpci_dev *zdev) if (!zdev_enabled(zdev)) return 0; - dev_info(&zdev->pdev->dev, "disabling fn handle: 0x%x\n", fh); rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN); if (!rc) /* Success -> store disabled handle in zdev */ zdev->fh = fh; - else - dev_err(&zdev->pdev->dev, - "Failed to disable fn handle: 0x%x\n", fh); + + zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc); return rc; } -static void clp_check_pcifn_entry(struct clp_fh_list_entry *entry) +static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, + void (*cb)(struct clp_fh_list_entry *entry)) { - int present, rc; + u64 resume_token = 0; + int entries, i, rc; + + do { + memset(rrb, 0, sizeof(*rrb)); + rrb->request.hdr.len = sizeof(rrb->request); + rrb->request.hdr.cmd = CLP_LIST_PCI; + /* store as many entries as possible */ + rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN; + rrb->request.resume_token = resume_token; + /* Get PCI function handle list */ + rc = clp_instr(rrb); + if (rc || rrb->response.hdr.rsp != CLP_RC_OK) { + zpci_err("List PCI FN:\n"); + zpci_err_clp(rrb->response.hdr.rsp, rc); + rc = -EIO; + goto out; + } + + WARN_ON_ONCE(rrb->response.entry_size != + sizeof(struct clp_fh_list_entry)); + + entries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) / + rrb->response.entry_size; + + resume_token = rrb->response.resume_token; + for (i = 0; i < entries; i++) + cb(&rrb->response.fh_list[i]); + } while (resume_token); +out: + return rc; +} + +static void __clp_add(struct clp_fh_list_entry *entry) +{ if (!entry->vendor_id) return; - /* TODO: be a little bit more scalable */ - present = zpci_fid_present(entry->fid); + clp_add_pci_device(entry->fid, entry->fh, entry->config_state); +} + +static void __clp_rescan(struct clp_fh_list_entry *entry) +{ + struct zpci_dev *zdev; - if (present) - pr_debug("%s: device %x already present\n", __func__, entry->fid); + if (!entry->vendor_id) + return; - /* skip already used functions */ - if (present && entry->config_state) + zdev = get_zdev_by_fid(entry->fid); + if (!zdev) { + clp_add_pci_device(entry->fid, entry->fh, entry->config_state); return; + } - /* aev 306: function moved to stand-by state */ - if (present && !entry->config_state) { + if (!entry->config_state) { /* * The handle is already disabled, that means no iota/irq freeing via * the firmware interfaces anymore. Need to free resources manually * (DMA memory, debug, sysfs)... */ - zpci_stop_device(get_zdev_by_fid(entry->fid)); - return; + zpci_stop_device(zdev); } +} - rc = clp_add_pci_device(entry->fid, entry->fh, entry->config_state); - if (rc) - pr_err("Failed to add fid: 0x%x\n", entry->fid); +static void __clp_update(struct clp_fh_list_entry *entry) +{ + struct zpci_dev *zdev; + + if (!entry->vendor_id) + return; + + zdev = get_zdev_by_fid(entry->fid); + if (!zdev) + return; + + zdev->fh = entry->fh; } -int clp_find_pci_devices(void) +int clp_scan_pci_devices(void) { struct clp_req_rsp_list_pci *rrb; - u64 resume_token = 0; - int entries, i, rc; + int rc; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; - do { - memset(rrb, 0, sizeof(*rrb)); - rrb->request.hdr.len = sizeof(rrb->request); - rrb->request.hdr.cmd = CLP_LIST_PCI; - /* store as many entries as possible */ - rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN; - rrb->request.resume_token = resume_token; + rc = clp_list_pci(rrb, __clp_add); - /* Get PCI function handle list */ - rc = clp_instr(rrb); - if (rc || rrb->response.hdr.rsp != CLP_RC_OK) { - pr_err("List PCI failed with response: 0x%x cc: %d\n", - rrb->response.hdr.rsp, rc); - rc = -EIO; - goto out; - } + clp_free_block(rrb); + return rc; +} - WARN_ON_ONCE(rrb->response.entry_size != - sizeof(struct clp_fh_list_entry)); +int clp_rescan_pci_devices(void) +{ + struct clp_req_rsp_list_pci *rrb; + int rc; - entries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) / - rrb->response.entry_size; - pr_info("Detected number of PCI functions: %u\n", entries); + rrb = clp_alloc_block(GFP_KERNEL); + if (!rrb) + return -ENOMEM; - /* Store the returned resume token as input for the next call */ - resume_token = rrb->response.resume_token; + rc = clp_list_pci(rrb, __clp_rescan); - for (i = 0; i < entries; i++) - clp_check_pcifn_entry(&rrb->response.fh_list[i]); - } while (resume_token); + clp_free_block(rrb); + return rc; +} + +int clp_rescan_pci_devices_simple(void) +{ + struct clp_req_rsp_list_pci *rrb; + int rc; + + rrb = clp_alloc_block(GFP_NOWAIT); + if (!rrb) + return -ENOMEM; + + rc = clp_list_pci(rrb, __clp_update); - pr_debug("Maximum number of supported PCI functions: %u\n", - rrb->response.max_fn); -out: clp_free_block(rrb); return rc; } diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index a303c95346c..c5c66840ac0 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -11,12 +11,17 @@ #include <linux/kernel.h> #include <linux/seq_file.h> #include <linux/debugfs.h> +#include <linux/export.h> #include <linux/pci.h> #include <asm/debug.h> #include <asm/pci_dma.h> static struct dentry *debugfs_root; +debug_info_t *pci_debug_msg_id; +EXPORT_SYMBOL_GPL(pci_debug_msg_id); +debug_info_t *pci_debug_err_id; +EXPORT_SYMBOL_GPL(pci_debug_err_id); static char *pci_perf_names[] = { /* hardware counters */ @@ -99,7 +104,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf, static int pci_perf_seq_open(struct inode *inode, struct file *filp) { return single_open(filp, pci_perf_show, - filp->f_path.dentry->d_inode->i_private); + file_inode(filp)->i_private); } static const struct file_operations debugfs_pci_perf_fops = { @@ -110,27 +115,6 @@ static const struct file_operations debugfs_pci_perf_fops = { .release = single_release, }; -static int pci_debug_show(struct seq_file *m, void *v) -{ - struct zpci_dev *zdev = m->private; - - zpci_debug_info(zdev, m); - return 0; -} - -static int pci_debug_seq_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, pci_debug_show, - filp->f_path.dentry->d_inode->i_private); -} - -static const struct file_operations debugfs_pci_debug_fops = { - .open = pci_debug_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - void zpci_debug_init_device(struct zpci_dev *zdev) { zdev->debugfs_dev = debugfs_create_dir(dev_name(&zdev->pdev->dev), @@ -144,31 +128,22 @@ void zpci_debug_init_device(struct zpci_dev *zdev) &debugfs_pci_perf_fops); if (IS_ERR(zdev->debugfs_perf)) zdev->debugfs_perf = NULL; - - zdev->debugfs_debug = debugfs_create_file("debug", - S_IFREG | S_IRUGO | S_IWUSR, - zdev->debugfs_dev, zdev, - &debugfs_pci_debug_fops); - if (IS_ERR(zdev->debugfs_debug)) - zdev->debugfs_debug = NULL; } void zpci_debug_exit_device(struct zpci_dev *zdev) { debugfs_remove(zdev->debugfs_perf); - debugfs_remove(zdev->debugfs_debug); debugfs_remove(zdev->debugfs_dev); } 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); debug_set_level(pci_debug_msg_id, 3); - zpci_dbg("Debug view initialized\n"); /* error log */ pci_debug_err_id = debug_register("pci_error", 2, 1, 16); @@ -176,7 +151,6 @@ int __init zpci_debug_init(void) return -EINVAL; debug_register_view(pci_debug_err_id, &debug_hex_ascii_view); debug_set_level(pci_debug_err_id, 6); - zpci_err("Debug view initialized\n"); debugfs_root = debugfs_create_dir("pci", NULL); return 0; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index a547419907c..f91c0311980 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -10,6 +10,7 @@ #include <linux/export.h> #include <linux/iommu-helper.h> #include <linux/dma-mapping.h> +#include <linux/vmalloc.h> #include <linux/pci.h> #include <asm/pci_dma.h> @@ -144,10 +145,8 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, return -EINVAL; spin_lock_irqsave(&zdev->dma_table_lock, irq_flags); - if (!zdev->dma_table) { - dev_err(&zdev->pdev->dev, "Missing DMA table\n"); + if (!zdev->dma_table) goto no_refresh; - } for (i = 0; i < nr_pages; i++) { dma_update_cpu_trans(zdev, page_addr, dma_addr, flags); @@ -169,8 +168,9 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, * needs to be redone! */ goto no_refresh; - rc = rpcit_instr((u64) zdev->fh << 32, start_dma_addr, - nr_pages * PAGE_SIZE); + + rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, + nr_pages * PAGE_SIZE); no_refresh: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); @@ -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); } @@ -262,14 +264,12 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, enum dma_data_direction direction, struct dma_attrs *attrs) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); unsigned long nr_pages, iommu_page_index; unsigned long pa = page_to_phys(page) + offset; int flags = ZPCI_PTE_VALID; dma_addr_t dma_addr; - WARN_ON_ONCE(offset > PAGE_SIZE); - /* This rounds up number of pages based on size and offset */ nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); iommu_page_index = dma_alloc_iommu(zdev, nr_pages); @@ -280,24 +280,22 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, size = nr_pages * PAGE_SIZE; dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE; - if (dma_addr + size > zdev->end_dma) { - dev_err(dev, "(dma_addr: 0x%16.16LX + size: 0x%16.16lx) > end_dma: 0x%16.16Lx\n", - dma_addr, size, zdev->end_dma); + if (dma_addr + size > zdev->end_dma) goto out_free; - } if (direction == DMA_NONE || direction == DMA_TO_DEVICE) flags |= ZPCI_TABLE_PROTECTED; if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) { - atomic64_add(nr_pages, (atomic64_t *) &zdev->fmb->mapped_pages); - return dma_addr + offset; + atomic64_add(nr_pages, &zdev->fmb->mapped_pages); + return dma_addr + (offset & ~PAGE_MASK); } out_free: dma_free_iommu(zdev, iommu_page_index, nr_pages); out_err: - dev_err(dev, "Failed to map addr: %lx\n", pa); + zpci_err("map error:\n"); + zpci_err_hex(&pa, sizeof(pa)); return DMA_ERROR_CODE; } @@ -305,17 +303,19 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, struct dma_attrs *attrs) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); unsigned long iommu_page_index; int npages; npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); dma_addr = dma_addr & PAGE_MASK; if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, - ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) - dev_err(dev, "Failed to unmap addr: %Lx\n", dma_addr); + ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) { + zpci_err("unmap error:\n"); + 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); } @@ -324,7 +324,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); struct page *page; unsigned long pa; dma_addr_t map; @@ -334,7 +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); @@ -345,6 +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; @@ -354,8 +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)); } @@ -408,7 +411,6 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int zpci_dma_init_device(struct zpci_dev *zdev) { - unsigned int bitmap_order; int rc; spin_lock_init(&zdev->iommu_bitmap_lock); @@ -422,12 +424,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET; zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; - bitmap_order = get_order(zdev->iommu_pages / 8); - pr_info("iommu_size: 0x%lx iommu_pages: 0x%lx bitmap_order: %i\n", - zdev->iommu_size, zdev->iommu_pages, bitmap_order); - - zdev->iommu_bitmap = (void *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, - bitmap_order); + zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); if (!zdev->iommu_bitmap) { rc = -ENOMEM; goto out_reg; @@ -452,8 +449,7 @@ void zpci_dma_exit_device(struct zpci_dev *zdev) { zpci_unregister_ioat(zdev, 0); dma_cleanup_tables(zdev); - free_pages((unsigned long) zdev->iommu_bitmap, - get_order(zdev->iommu_pages / 8)); + vfree(zdev->iommu_bitmap); zdev->iommu_bitmap = NULL; zdev->next_bit = 0; } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index ec62e3a0dc0..6d7f5a3016c 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -10,6 +10,8 @@ #include <linux/kernel.h> #include <linux/pci.h> +#include <asm/pci_debug.h> +#include <asm/sclp.h> /* Content Code Description for PCI Function Error */ struct zpci_ccdf_err { @@ -41,55 +43,94 @@ struct zpci_ccdf_avail { u16 pec; /* PCI event code */ } __packed; -static void zpci_event_log_err(struct zpci_ccdf_err *ccdf) +static void __zpci_event_error(struct zpci_ccdf_err *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); - zpci_err("SEI error CCD:\n"); + zpci_err("error CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); - dev_err(&zdev->pdev->dev, "event code: 0x%x\n", ccdf->pec); + + if (!zdev) + return; + + pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", + pci_name(zdev->pdev), ccdf->pec, ccdf->fid); } -static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf) +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_dev *zdev = get_zdev_by_fid(ccdf->fid); + struct pci_dev *pdev = zdev ? zdev->pdev : NULL; + int ret; - pr_err("%s%s: availability event: fh: 0x%x fid: 0x%x event code: 0x%x reason:", - (zdev) ? dev_driver_string(&zdev->pdev->dev) : "?", - (zdev) ? dev_name(&zdev->pdev->dev) : "?", - ccdf->fh, ccdf->fid, ccdf->pec); - print_hex_dump(KERN_CONT, "ccdf", DUMP_PREFIX_OFFSET, - 16, 1, ccdf, sizeof(*ccdf), false); + pr_info("%s: Event 0x%x reconfigured PCI function 0x%x\n", + pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); + zpci_err("avail CCDF:\n"); + zpci_err_hex(ccdf, sizeof(*ccdf)); switch (ccdf->pec) { - case 0x0301: - zpci_enable_device(zdev); + case 0x0301: /* Standby -> Configured */ + if (!zdev || zdev->state != ZPCI_FN_STATE_STANDBY) + break; + zdev->state = ZPCI_FN_STATE_CONFIGURED; + zdev->fh = ccdf->fh; + ret = zpci_enable_device(zdev); + if (ret) + break; + pci_rescan_bus(zdev->bus); + break; + case 0x0302: /* Reserved -> Standby */ + if (!zdev) + clp_add_pci_device(ccdf->fid, ccdf->fh, 0); + break; + case 0x0303: /* Deconfiguration requested */ + if (pdev) + pci_stop_and_remove_bus_device(pdev); + + ret = zpci_disable_device(zdev); + if (ret) + break; + + ret = sclp_pci_deconfigure(zdev->fid); + zpci_dbg(3, "deconf fid:%x, rc:%d\n", zdev->fid, ret); + if (!ret) + zdev->state = ZPCI_FN_STATE_STANDBY; + + break; + case 0x0304: /* Configured -> Standby */ + 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); + zdev->state = ZPCI_FN_STATE_STANDBY; break; - case 0x0302: - clp_add_pci_device(ccdf->fid, ccdf->fh, 0); + case 0x0306: /* 0x308 or 0x302 for multiple devices */ + clp_rescan_pci_devices(); break; - case 0x0306: - clp_find_pci_devices(); + case 0x0308: /* Standby -> Reserved */ + if (!zdev) + break; + pci_stop_root_bus(zdev->bus); + pci_remove_root_bus(zdev->bus); break; default: break; } } -void zpci_event_error(void *data) -{ - struct zpci_ccdf_err *ccdf = data; - struct zpci_dev *zdev; - - zpci_event_log_err(ccdf); - zdev = get_zdev_by_fid(ccdf->fid); - if (!zdev) { - pr_err("Error event for unknown fid: %x", ccdf->fid); - return; - } -} - void zpci_event_availability(void *data) { - zpci_event_log_avail(data); + if (zpci_is_enabled()) + __zpci_event_availability(data); } diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c new file mode 100644 index 00000000000..85267c058af --- /dev/null +++ b/arch/s390/pci/pci_insn.c @@ -0,0 +1,202 @@ +/* + * s390 specific pci instructions + * + * Copyright IBM Corp. 2013 + */ + +#include <linux/export.h> +#include <linux/errno.h> +#include <linux/delay.h> +#include <asm/pci_insn.h> +#include <asm/processor.h> + +#define ZPCI_INSN_BUSY_DELAY 1 /* 1 microsecond */ + +/* Modify PCI Function Controls */ +static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) +{ + u8 cc; + + asm volatile ( + " .insn rxy,0xe300000000d0,%[req],%[fib]\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib) + : : "cc"); + *status = req >> 24 & 0xff; + return cc; +} + +int zpci_mod_fc(u64 req, struct zpci_fib *fib) +{ + u8 cc, status; + + do { + cc = __mpcifc(req, fib, &status); + if (cc == 2) + msleep(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d\n", + __func__, cc, status); + return (cc) ? -EIO : 0; +} + +/* Refresh PCI Translations */ +static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) +{ + register u64 __addr asm("2") = addr; + register u64 __range asm("3") = range; + u8 cc; + + asm volatile ( + " .insn rre,0xb9d30000,%[fn],%[addr]\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=d" (cc), [fn] "+d" (fn) + : [addr] "d" (__addr), "d" (__range) + : "cc"); + *status = fn >> 24 & 0xff; + return cc; +} + +int zpci_refresh_trans(u64 fn, u64 addr, u64 range) +{ + u8 cc, status; + + do { + cc = __rpcit(fn, addr, range, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d dma_addr: %Lx size: %Lx\n", + __func__, cc, status, addr, range); + return (cc) ? -EIO : 0; +} + +/* Set Interruption Controls */ +void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc) +{ + asm volatile ( + " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" + : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); +} + +/* PCI Load */ +static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status) +{ + register u64 __req asm("2") = req; + register u64 __offset asm("3") = offset; + int cc = -ENXIO; + u64 __data; + + asm volatile ( + " .insn rre,0xb9d20000,%[data],%[req]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [data] "=d" (__data), [req] "+d" (__req) + : "d" (__offset) + : "cc"); + *status = __req >> 24 & 0xff; + if (!cc) + *data = __data; + + return cc; +} + +int zpci_load(u64 *data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcilg(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(zpci_load); + +/* PCI Store */ +static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) +{ + register u64 __req asm("2") = req; + register u64 __offset asm("3") = offset; + int cc = -ENXIO; + + asm volatile ( + " .insn rre,0xb9d00000,%[data],%[req]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [req] "+d" (__req) + : "d" (__offset), [data] "d" (data) + : "cc"); + *status = __req >> 24 & 0xff; + return cc; +} + +int zpci_store(u64 data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcistg(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(zpci_store); + +/* PCI Store Block */ +static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) +{ + int cc = -ENXIO; + + asm volatile ( + " .insn rsy,0xeb00000000d0,%[req],%[offset],%[data]\n" + "0: ipm %[cc]\n" + " srl %[cc],28\n" + "1:\n" + EX_TABLE(0b, 1b) + : [cc] "+d" (cc), [req] "+d" (req) + : [offset] "d" (offset), [data] "Q" (*data) + : "cc"); + *status = req >> 24 & 0xff; + return cc; +} + +int zpci_store_block(const u64 *data, u64 req, u64 offset) +{ + u8 status; + int cc; + + do { + cc = __pcistb(data, req, offset, &status); + if (cc == 2) + udelay(ZPCI_INSN_BUSY_DELAY); + } while (cc == 2); + + if (cc) + printk_once(KERN_ERR "%s: error cc: %d status: %d req: %Lx offset: %Lx\n", + __func__, cc, status, req, offset); + return (cc > 0) ? -EIO : cc; +} +EXPORT_SYMBOL_GPL(zpci_store_block); diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c deleted file mode 100644 index 90fd3482b9e..00000000000 --- a/arch/s390/pci/pci_msi.c +++ /dev/null @@ -1,141 +0,0 @@ -/* - * Copyright IBM Corp. 2012 - * - * Author(s): - * Jan Glauber <jang@linux.vnet.ibm.com> - */ - -#define COMPONENT "zPCI" -#define pr_fmt(fmt) COMPONENT ": " fmt - -#include <linux/kernel.h> -#include <linux/err.h> -#include <linux/rculist.h> -#include <linux/hash.h> -#include <linux/pci.h> -#include <linux/msi.h> -#include <asm/hw_irq.h> - -/* mapping of irq numbers to msi_desc */ -static struct hlist_head *msi_hash; -static unsigned int msihash_shift = 6; -#define msi_hashfn(nr) hash_long(nr, msihash_shift) - -static DEFINE_SPINLOCK(msi_map_lock); - -struct msi_desc *__irq_get_msi_desc(unsigned int irq) -{ - struct hlist_node *entry; - struct msi_map *map; - - hlist_for_each_entry_rcu(map, entry, - &msi_hash[msi_hashfn(irq)], msi_chain) - if (map->irq == irq) - return map->msi; - return NULL; -} - -int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag) -{ - if (msi->msi_attrib.is_msix) { - int offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL; - msi->masked = readl(msi->mask_base + offset); - writel(flag, msi->mask_base + offset); - } else { - if (msi->msi_attrib.maskbit) { - int pos; - u32 mask_bits; - - pos = (long) msi->mask_base; - pci_read_config_dword(msi->dev, pos, &mask_bits); - mask_bits &= ~(mask); - mask_bits |= flag & mask; - pci_write_config_dword(msi->dev, pos, mask_bits); - } else { - return 0; - } - } - - msi->msi_attrib.maskbit = !!flag; - return 1; -} - -int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi, - unsigned int nr, int offset) -{ - struct msi_map *map; - struct msi_msg msg; - int rc; - - map = kmalloc(sizeof(*map), GFP_KERNEL); - if (map == NULL) - return -ENOMEM; - - map->irq = nr; - map->msi = msi; - zdev->msi_map[nr & ZPCI_MSI_MASK] = map; - - pr_debug("%s hashing irq: %u to bucket nr: %llu\n", - __func__, nr, msi_hashfn(nr)); - hlist_add_head_rcu(&map->msi_chain, &msi_hash[msi_hashfn(nr)]); - - spin_lock(&msi_map_lock); - rc = irq_set_msi_desc(nr, msi); - if (rc) { - spin_unlock(&msi_map_lock); - hlist_del_rcu(&map->msi_chain); - kfree(map); - zdev->msi_map[nr & ZPCI_MSI_MASK] = NULL; - return rc; - } - spin_unlock(&msi_map_lock); - - msg.data = nr - offset; - msg.address_lo = zdev->msi_addr & 0xffffffff; - msg.address_hi = zdev->msi_addr >> 32; - write_msi_msg(nr, &msg); - return 0; -} - -void zpci_teardown_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi) -{ - int irq = msi->irq & ZPCI_MSI_MASK; - struct msi_map *map; - - msi->msg.address_lo = 0; - msi->msg.address_hi = 0; - msi->msg.data = 0; - msi->irq = 0; - zpci_msi_set_mask_bits(msi, 1, 1); - - spin_lock(&msi_map_lock); - map = zdev->msi_map[irq]; - hlist_del_rcu(&map->msi_chain); - kfree(map); - zdev->msi_map[irq] = NULL; - spin_unlock(&msi_map_lock); -} - -/* - * The msi hash table has 256 entries which is good for 4..20 - * devices (a typical device allocates 10 + CPUs MSI's). Maybe make - * the hash table size adjustable later. - */ -int __init zpci_msihash_init(void) -{ - unsigned int i; - - msi_hash = kmalloc(256 * sizeof(*msi_hash), GFP_KERNEL); - if (!msi_hash) - return -ENOMEM; - - for (i = 0; i < (1U << msihash_shift); i++) - INIT_HLIST_HEAD(&msi_hash[i]); - return 0; -} - -void __init zpci_msihash_exit(void) -{ - kfree(msi_hash); -} diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index a42cce69d0a..9190214b870 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -12,75 +12,99 @@ #include <linux/stat.h> #include <linux/pci.h> -static ssize_t show_fid(struct device *dev, struct device_attribute *attr, - char *buf) +#define zpci_attr(name, fmt, member) \ +static ssize_t name##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); \ + \ + return sprintf(buf, fmt, zdev->member); \ +} \ +static DEVICE_ATTR_RO(name) + +zpci_attr(function_id, "0x%08x\n", fid); +zpci_attr(function_handle, "0x%08x\n", fh); +zpci_attr(pchid, "0x%04x\n", pchid); +zpci_attr(pfgid, "0x%02x\n", pfgid); +zpci_attr(vfn, "0x%04x\n", vfn); +zpci_attr(pft, "0x%02x\n", pft); +zpci_attr(uid, "0x%x\n", uid); +zpci_attr(segment0, "0x%02x\n", pfip[0]); +zpci_attr(segment1, "0x%02x\n", pfip[1]); +zpci_attr(segment2, "0x%02x\n", pfip[2]); +zpci_attr(segment3, "0x%02x\n", pfip[3]); + +static ssize_t recover_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); + int ret; - sprintf(buf, "0x%08x\n", zdev->fid); - return strlen(buf); -} -static DEVICE_ATTR(function_id, S_IRUGO, show_fid, NULL); + if (!device_remove_file_self(dev, attr)) + return count; -static ssize_t show_fh(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + pci_stop_and_remove_bus_device(pdev); + ret = zpci_disable_device(zdev); + if (ret) + return ret; - sprintf(buf, "0x%08x\n", zdev->fh); - return strlen(buf); -} -static DEVICE_ATTR(function_handle, S_IRUGO, show_fh, NULL); - -static ssize_t show_pchid(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + ret = zpci_enable_device(zdev); + if (ret) + return ret; - sprintf(buf, "0x%04x\n", zdev->pchid); - return strlen(buf); + pci_rescan_bus(zdev->bus); + return count; } -static DEVICE_ATTR(pchid, S_IRUGO, show_pchid, NULL); +static DEVICE_ATTR_WO(recover); -static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t util_string_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { - struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev)); + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); - sprintf(buf, "0x%02x\n", zdev->pfgid); - return strlen(buf); + return memory_read_from_buffer(buf, count, &off, zdev->util_str, + sizeof(zdev->util_str)); } -static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL); - -static struct device_attribute *zpci_dev_attrs[] = { - &dev_attr_function_id, - &dev_attr_function_handle, - &dev_attr_pchid, - &dev_attr_pfgid, +static BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); +static struct bin_attribute *zpci_bin_attrs[] = { + &bin_attr_util_string, NULL, }; -int zpci_sysfs_add_device(struct device *dev) -{ - int i, rc = 0; - - for (i = 0; zpci_dev_attrs[i]; i++) { - rc = device_create_file(dev, zpci_dev_attrs[i]); - if (rc) - goto error; - } - return 0; - -error: - while (--i >= 0) - device_remove_file(dev, zpci_dev_attrs[i]); - return rc; -} +static struct attribute *zpci_dev_attrs[] = { + &dev_attr_function_id.attr, + &dev_attr_function_handle.attr, + &dev_attr_pchid.attr, + &dev_attr_pfgid.attr, + &dev_attr_pft.attr, + &dev_attr_vfn.attr, + &dev_attr_uid.attr, + &dev_attr_recover.attr, + NULL, +}; +static struct attribute_group zpci_attr_group = { + .attrs = zpci_dev_attrs, + .bin_attrs = zpci_bin_attrs, +}; -void zpci_sysfs_remove_device(struct device *dev) -{ - int i; +static struct attribute *pfip_attrs[] = { + &dev_attr_segment0.attr, + &dev_attr_segment1.attr, + &dev_attr_segment2.attr, + &dev_attr_segment3.attr, + NULL, +}; +static struct attribute_group pfip_attr_group = { + .name = "pfip", + .attrs = pfip_attrs, +}; - for (i = 0; zpci_dev_attrs[i]; i++) - device_remove_file(dev, zpci_dev_attrs[i]); -} +const struct attribute_group *zpci_attr_groups[] = { + &zpci_attr_group, + &pfip_attr_group, + NULL, +}; |