diff options
Diffstat (limited to 'arch/s390')
85 files changed, 3807 insertions, 1574 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index eba9c1d..b2d7ec1 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -66,6 +66,7 @@ config S390 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_SG_CHAIN select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH @@ -116,7 +117,6 @@ config S390 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 if 64BIT select HAVE_DYNAMIC_FTRACE_WITH_REGS if 64BIT @@ -152,7 +152,6 @@ config S390 select TTY select VIRT_CPU_ACCOUNTING select VIRT_TO_BUS - select ARCH_HAS_SG_CHAIN config SCHED_OMIT_FRAME_POINTER def_bool y @@ -188,6 +187,10 @@ config HAVE_MARCH_ZEC12_FEATURES def_bool n select HAVE_MARCH_Z196_FEATURES +config HAVE_MARCH_Z13_FEATURES + def_bool n + select HAVE_MARCH_ZEC12_FEATURES + choice prompt "Processor type" default MARCH_G5 @@ -247,6 +250,14 @@ config MARCH_ZEC12 2827 series). The kernel will be slightly faster but will not work on older machines. +config MARCH_Z13 + bool "IBM z13" + select HAVE_MARCH_Z13_FEATURES if 64BIT + help + Select this to enable optimizations for IBM z13 (2964 series). + The kernel will be slightly faster but will not work on older + machines. + endchoice config MARCH_G5_TUNE @@ -270,6 +281,9 @@ config MARCH_Z196_TUNE config MARCH_ZEC12_TUNE def_bool TUNE_ZEC12 || MARCH_ZEC12 && TUNE_DEFAULT +config MARCH_Z13_TUNE + def_bool TUNE_Z13 || MARCH_Z13 && TUNE_DEFAULT + choice prompt "Tune code generation" default TUNE_DEFAULT @@ -308,6 +322,9 @@ config TUNE_Z196 config TUNE_ZEC12 bool "IBM zBC12 and zEC12" +config TUNE_Z13 + bool "IBM z13" + endchoice config 64BIT @@ -359,14 +376,14 @@ config SMP Even if you don't know what to do here, say Y. config NR_CPUS - int "Maximum number of CPUs (2-256)" - range 2 256 + int "Maximum number of CPUs (2-512)" + range 2 512 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 256 and the + kernel will support. The maximum supported value is 512 and the minimum value which makes sense is 2. This is purely to save memory - each supported CPU adds @@ -381,17 +398,26 @@ config HOTPLUG_CPU can be controlled through /sys/devices/system/cpu/cpu#. Say N if you want to disable CPU hotplug. +config SCHED_SMT + def_bool n + config SCHED_MC def_bool n config SCHED_BOOK + def_bool n + +config SCHED_TOPOLOGY def_bool y - prompt "Book scheduler support" + prompt "Topology scheduler support" depends on SMP + select SCHED_SMT select SCHED_MC + select SCHED_BOOK help - Book scheduler support improves the CPU scheduler's decision making - when dealing with machines that have several books. + Topology scheduler support improves the CPU scheduler's decision + making when dealing with machines that have multi-threading, + multiple cores or multiple books. source kernel/Kconfig.preempt diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 878e679..acb6859 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -42,6 +42,7 @@ mflags-$(CONFIG_MARCH_Z9_109) := -march=z9-109 mflags-$(CONFIG_MARCH_Z10) := -march=z10 mflags-$(CONFIG_MARCH_Z196) := -march=z196 mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12 +mflags-$(CONFIG_MARCH_Z13) := -march=z13 aflags-y += $(mflags-y) cflags-y += $(mflags-y) @@ -53,6 +54,7 @@ cflags-$(CONFIG_MARCH_Z9_109_TUNE) += -mtune=z9-109 cflags-$(CONFIG_MARCH_Z10_TUNE) += -mtune=z10 cflags-$(CONFIG_MARCH_Z196_TUNE) += -mtune=z196 cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 +cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 #KBUILD_IMAGE is necessary for make rpm KBUILD_IMAGE :=arch/s390/boot/image @@ -85,6 +87,16 @@ ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y) cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack endif +ifdef CONFIG_FUNCTION_TRACER +# make use of hotpatch feature if the compiler supports it +cc_hotpatch := -mhotpatch=0,3 +ifeq ($(call cc-option-yn,$(cc_hotpatch)),y) +CC_FLAGS_FTRACE := $(cc_hotpatch) +KBUILD_AFLAGS += -DCC_USING_HOTPATCH +KBUILD_CFLAGS += -DCC_USING_HOTPATCH +endif +endif + KBUILD_CFLAGS += -mbackchain -msoft-float $(cflags-y) KBUILD_CFLAGS += -pipe -fno-strength-reduce -Wno-sign-compare KBUILD_AFLAGS += $(aflags-y) diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 57cbaff..42506b3 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -8,6 +8,7 @@ #include <asm/uaccess.h> #include <asm/page.h> +#include <asm/sclp.h> #include <asm/ipl.h> #include "sizes.h" @@ -63,8 +64,6 @@ static unsigned long free_mem_end_ptr; #include "../../../../lib/decompress_unxz.c" #endif -extern _sclp_print_early(const char *); - static int puts(const char *s) { _sclp_print_early(s); diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 9432d0f..6470775 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -555,7 +555,6 @@ 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 @@ -563,6 +562,7 @@ CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 219dca6..5c30972 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -540,6 +540,7 @@ CONFIG_UNUSED_SYMBOLS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m +CONFIG_PANIC_ON_OOPS=y CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 822c2f2..bda70f1 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -537,6 +537,7 @@ CONFIG_FRAME_WARN=1024 CONFIG_UNUSED_SYMBOLS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y +CONFIG_PANIC_ON_OOPS=y CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 9d63051..1b0184a 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -71,6 +71,7 @@ CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y +CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_FTRACE is not set diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 1f272b2..5566ce8 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -134,7 +134,7 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { - const struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); if (unlikely(need_fallback(sctx->key_len))) { crypto_cipher_encrypt_one(sctx->fallback.cip, out, in); @@ -159,7 +159,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { - const struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); if (unlikely(need_fallback(sctx->key_len))) { crypto_cipher_decrypt_one(sctx->fallback.cip, out, in); diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 785c5f2..83ef702 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -14,7 +14,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_CGROUPS=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y @@ -22,12 +21,8 @@ CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y CONFIG_NAMESPACES=y CONFIG_BLK_DEV_INITRD=y -CONFIG_RD_BZIP2=y -CONFIG_RD_LZMA=y -CONFIG_RD_XZ=y -CONFIG_RD_LZO=y -CONFIG_RD_LZ4=y CONFIG_EXPERT=y +CONFIG_BPF_SYSCALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/s390/hypfs/Makefile b/arch/s390/hypfs/Makefile index 06f8d95..2ee25ba 100644 --- a/arch/s390/hypfs/Makefile +++ b/arch/s390/hypfs/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_S390_HYPFS_FS) += s390_hypfs.o s390_hypfs-objs := inode.o hypfs_diag.o hypfs_vm.o hypfs_dbfs.o hypfs_sprp.o +s390_hypfs-objs += hypfs_diag0c.o diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h index b34b5ab..eecde50 100644 --- a/arch/s390/hypfs/hypfs.h +++ b/arch/s390/hypfs/hypfs.h @@ -37,6 +37,10 @@ extern int hypfs_vm_init(void); extern void hypfs_vm_exit(void); extern int hypfs_vm_create_files(struct dentry *root); +/* VM diagnose 0c */ +int hypfs_diag0c_init(void); +void hypfs_diag0c_exit(void); + /* Set Partition-Resource Parameter */ int hypfs_sprp_init(void); void hypfs_sprp_exit(void); @@ -49,7 +53,6 @@ struct hypfs_dbfs_data { void *buf_free_ptr; size_t size; struct hypfs_dbfs_file *dbfs_file; - struct kref kref; }; struct hypfs_dbfs_file { @@ -61,8 +64,6 @@ struct hypfs_dbfs_file { unsigned long); /* Private data for hypfs_dbfs.c */ - struct hypfs_dbfs_data *data; - struct delayed_work data_free_work; struct mutex lock; struct dentry *dentry; }; diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 47fe105..752f6df 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -17,33 +17,16 @@ static struct hypfs_dbfs_data *hypfs_dbfs_data_alloc(struct hypfs_dbfs_file *f) data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return NULL; - kref_init(&data->kref); data->dbfs_file = f; return data; } -static void hypfs_dbfs_data_free(struct kref *kref) +static void hypfs_dbfs_data_free(struct hypfs_dbfs_data *data) { - struct hypfs_dbfs_data *data; - - data = container_of(kref, struct hypfs_dbfs_data, kref); data->dbfs_file->data_free(data->buf_free_ptr); kfree(data); } -static void data_free_delayed(struct work_struct *work) -{ - struct hypfs_dbfs_data *data; - struct hypfs_dbfs_file *df; - - df = container_of(work, struct hypfs_dbfs_file, data_free_work.work); - mutex_lock(&df->lock); - data = df->data; - df->data = NULL; - mutex_unlock(&df->lock); - kref_put(&data->kref, hypfs_dbfs_data_free); -} - static ssize_t dbfs_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) { @@ -56,28 +39,21 @@ static ssize_t dbfs_read(struct file *file, char __user *buf, df = file_inode(file)->i_private; mutex_lock(&df->lock); - if (!df->data) { - data = hypfs_dbfs_data_alloc(df); - if (!data) { - mutex_unlock(&df->lock); - return -ENOMEM; - } - rc = df->data_create(&data->buf, &data->buf_free_ptr, - &data->size); - if (rc) { - mutex_unlock(&df->lock); - kfree(data); - return rc; - } - df->data = data; - schedule_delayed_work(&df->data_free_work, HZ); + data = hypfs_dbfs_data_alloc(df); + if (!data) { + mutex_unlock(&df->lock); + return -ENOMEM; + } + rc = df->data_create(&data->buf, &data->buf_free_ptr, &data->size); + if (rc) { + mutex_unlock(&df->lock); + kfree(data); + return rc; } - data = df->data; - kref_get(&data->kref); mutex_unlock(&df->lock); rc = simple_read_from_buffer(buf, size, ppos, data->buf, data->size); - kref_put(&data->kref, hypfs_dbfs_data_free); + hypfs_dbfs_data_free(data); return rc; } @@ -108,7 +84,6 @@ int hypfs_dbfs_create_file(struct hypfs_dbfs_file *df) if (IS_ERR(df->dentry)) return PTR_ERR(df->dentry); mutex_init(&df->lock); - INIT_DELAYED_WORK(&df->data_free_work, data_free_delayed); return 0; } diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c new file mode 100644 index 0000000..d4c0d37 --- /dev/null +++ b/arch/s390/hypfs/hypfs_diag0c.c @@ -0,0 +1,139 @@ +/* + * Hypervisor filesystem for Linux on s390 + * + * Diag 0C implementation + * + * Copyright IBM Corp. 2014 + */ + +#include <linux/slab.h> +#include <linux/cpu.h> +#include <asm/hypfs.h> +#include "hypfs.h" + +#define DBFS_D0C_HDR_VERSION 0 + +/* + * Execute diagnose 0c in 31 bit mode + */ +static void diag0c(struct hypfs_diag0c_entry *entry) +{ + asm volatile ( +#ifdef CONFIG_64BIT + " sam31\n" + " diag %0,%0,0x0c\n" + " sam64\n" +#else + " diag %0,%0,0x0c\n" +#endif + : /* no output register */ + : "a" (entry) + : "memory"); +} + +/* + * Get hypfs_diag0c_entry from CPU vector and store diag0c data + */ +static void diag0c_fn(void *data) +{ + diag0c(((void **) data)[smp_processor_id()]); +} + +/* + * Allocate buffer and store diag 0c data + */ +static void *diag0c_store(unsigned int *count) +{ + struct hypfs_diag0c_data *diag0c_data; + unsigned int cpu_count, cpu, i; + void **cpu_vec; + + get_online_cpus(); + cpu_count = num_online_cpus(); + cpu_vec = kmalloc(sizeof(*cpu_vec) * num_possible_cpus(), GFP_KERNEL); + if (!cpu_vec) + goto fail_put_online_cpus; + /* Note: Diag 0c needs 8 byte alignment and real storage */ + diag0c_data = kzalloc(sizeof(struct hypfs_diag0c_hdr) + + cpu_count * sizeof(struct hypfs_diag0c_entry), + GFP_KERNEL | GFP_DMA); + if (!diag0c_data) + goto fail_kfree_cpu_vec; + i = 0; + /* Fill CPU vector for each online CPU */ + for_each_online_cpu(cpu) { + diag0c_data->entry[i].cpu = cpu; + cpu_vec[cpu] = &diag0c_data->entry[i++]; + } + /* Collect data all CPUs */ + on_each_cpu(diag0c_fn, cpu_vec, 1); + *count = cpu_count; + kfree(cpu_vec); + put_online_cpus(); + return diag0c_data; + +fail_kfree_cpu_vec: + kfree(cpu_vec); +fail_put_online_cpus: + put_online_cpus(); + return ERR_PTR(-ENOMEM); +} + +/* + * Hypfs DBFS callback: Free diag 0c data + */ +static void dbfs_diag0c_free(const void *data) +{ + kfree(data); +} + +/* + * Hypfs DBFS callback: Create diag 0c data + */ +static int dbfs_diag0c_create(void **data, void **data_free_ptr, size_t *size) +{ + struct hypfs_diag0c_data *diag0c_data; + unsigned int count; + + diag0c_data = diag0c_store(&count); + if (IS_ERR(diag0c_data)) + return PTR_ERR(diag0c_data); + memset(&diag0c_data->hdr, 0, sizeof(diag0c_data->hdr)); + get_tod_clock_ext(diag0c_data->hdr.tod_ext); + diag0c_data->hdr.len = count * sizeof(struct hypfs_diag0c_entry); + diag0c_data->hdr.version = DBFS_D0C_HDR_VERSION; + diag0c_data->hdr.count = count; + *data = diag0c_data; + *data_free_ptr = diag0c_data; + *size = diag0c_data->hdr.len + sizeof(struct hypfs_diag0c_hdr); + return 0; +} + +/* + * Hypfs DBFS file structure + */ +static struct hypfs_dbfs_file dbfs_file_0c = { + .name = "diag_0c", + .data_create = dbfs_diag0c_create, + .data_free = dbfs_diag0c_free, +}; + +/* + * Initialize diag 0c interface for z/VM + */ +int __init hypfs_diag0c_init(void) +{ + if (!MACHINE_IS_VM) + return 0; + return hypfs_dbfs_create_file(&dbfs_file_0c); +} + +/* + * Shutdown diag 0c interface for z/VM + */ +void hypfs_diag0c_exit(void) +{ + if (!MACHINE_IS_VM) + return; + hypfs_dbfs_remove_file(&dbfs_file_0c); +} diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index c952b98..99824ff 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -74,7 +74,7 @@ static void hypfs_remove(struct dentry *dentry) parent = dentry->d_parent; mutex_lock(&parent->d_inode->i_mutex); if (hypfs_positive(dentry)) { - if (S_ISDIR(dentry->d_inode->i_mode)) + if (d_is_dir(dentry)) simple_rmdir(parent->d_inode, dentry); else simple_unlink(parent->d_inode, dentry); @@ -144,36 +144,32 @@ static int hypfs_open(struct inode *inode, struct file *filp) return nonseekable_open(inode, filp); } -static ssize_t hypfs_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t offset) +static ssize_t hypfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { - char *data; - ssize_t ret; - struct file *filp = iocb->ki_filp; - /* XXX: temporary */ - char __user *buf = iov[0].iov_base; - size_t count = iov[0].iov_len; - - if (nr_segs != 1) - return -EINVAL; - - data = filp->private_data; - ret = simple_read_from_buffer(buf, count, &offset, data, strlen(data)); - if (ret <= 0) - return ret; - - iocb->ki_pos += ret; - file_accessed(filp); + struct file *file = iocb->ki_filp; + char *data = file->private_data; + size_t available = strlen(data); + loff_t pos = iocb->ki_pos; + size_t count; - return ret; + if (pos < 0) + return -EINVAL; + if (pos >= available || !iov_iter_count(to)) + return 0; + count = copy_to_iter(data + pos, available - pos, to); + if (!count) + return -EFAULT; + iocb->ki_pos = pos + count; + file_accessed(file); + return count; } -static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t offset) + +static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from) { int rc; 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); + size_t count = iov_iter_count(from); /* * Currently we only allow one update per second for two reasons: @@ -202,6 +198,7 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov, } hypfs_update_update(sb); rc = count; + iov_iter_advance(from, count); out: mutex_unlock(&fs_info->lock); return rc; @@ -440,10 +437,10 @@ struct dentry *hypfs_create_str(struct dentry *dir, static const struct file_operations hypfs_file_ops = { .open = hypfs_open, .release = hypfs_release, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = hypfs_aio_read, - .aio_write = hypfs_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = hypfs_read_iter, + .write_iter = hypfs_write_iter, .llseek = no_llseek, }; @@ -482,10 +479,14 @@ static int __init hypfs_init(void) rc = -ENODATA; goto fail_hypfs_vm_exit; } + if (hypfs_diag0c_init()) { + rc = -ENODATA; + goto fail_hypfs_sprp_exit; + } s390_kobj = kobject_create_and_add("s390", hypervisor_kobj); if (!s390_kobj) { rc = -ENOMEM; - goto fail_hypfs_sprp_exit; + goto fail_hypfs_diag0c_exit; } rc = register_filesystem(&hypfs_type); if (rc) @@ -494,6 +495,8 @@ static int __init hypfs_init(void) fail_filesystem: kobject_put(s390_kobj); +fail_hypfs_diag0c_exit: + hypfs_diag0c_exit(); fail_hypfs_sprp_exit: hypfs_sprp_exit(); fail_hypfs_vm_exit: @@ -510,6 +513,7 @@ static void __exit hypfs_exit(void) { unregister_filesystem(&hypfs_type); kobject_put(s390_kobj); + hypfs_diag0c_exit(); hypfs_sprp_exit(); hypfs_vm_exit(); hypfs_diag_exit(); diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index cb700d5..5243a86 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -189,6 +189,20 @@ static inline int ecctr(u64 ctr, u64 *val) return cc; } +/* Store CPU counter multiple for the MT utilization counter set */ +static inline int stcctm5(u64 num, u64 *val) +{ + typedef struct { u64 _[num]; } addrtype; + int cc; + + asm volatile ( + " .insn rsy,0xeb0000000017,%2,5,%1\n" + " ipm %0\n" + " srl %0,28\n" + : "=d" (cc), "=Q" (*(addrtype *) val) : "d" (num) : "cc"); + return cc; +} + /* Query sampling information */ static inline int qsi(struct hws_qsi_info_block *info) { diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index f6e43d3..c9c875d 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -163,8 +163,8 @@ extern unsigned int vdso_enabled; the loader. We need to make sure that it is out of the way of the program that it will "exec", and that there is sufficient room for the brk. */ -extern unsigned long randomize_et_dyn(unsigned long base); -#define ELF_ET_DYN_BASE (randomize_et_dyn(STACK_TOP / 3 * 2)) +extern unsigned long randomize_et_dyn(void); +#define ELF_ET_DYN_BASE randomize_et_dyn() /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. */ @@ -209,7 +209,9 @@ do { \ } while (0) #endif /* CONFIG_COMPAT */ -#define STACK_RND_MASK 0x7ffUL +extern unsigned long mmap_rnd_mask; + +#define STACK_RND_MASK (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask) #define ARCH_DLINFO \ do { \ diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index abb618f..836c562 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -3,8 +3,12 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 +#ifdef CC_USING_HOTPATCH +#define MCOUNT_INSN_SIZE 6 +#else #define MCOUNT_INSN_SIZE 24 #define MCOUNT_RETURN_FIXUP 18 +#endif #ifndef __ASSEMBLY__ @@ -37,18 +41,29 @@ struct ftrace_insn { static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn) { #ifdef CONFIG_FUNCTION_TRACER +#ifdef CC_USING_HOTPATCH + /* brcl 0,0 */ + insn->opc = 0xc004; + insn->disp = 0; +#else /* jg .+24 */ insn->opc = 0xc0f4; insn->disp = MCOUNT_INSN_SIZE / 2; #endif +#endif } static inline int is_ftrace_nop(struct ftrace_insn *insn) { #ifdef CONFIG_FUNCTION_TRACER +#ifdef CC_USING_HOTPATCH + if (insn->disp == 0) + return 1; +#else if (insn->disp == MCOUNT_INSN_SIZE / 2) return 1; #endif +#endif return 0; } diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 346b1c8..2b77e23 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -1,9 +1,12 @@ #ifndef _ASM_S390_JUMP_LABEL_H #define _ASM_S390_JUMP_LABEL_H +#ifndef __ASSEMBLY__ + #include <linux/types.h> #define JUMP_LABEL_NOP_SIZE 6 +#define JUMP_LABEL_NOP_OFFSET 2 #ifdef CONFIG_64BIT #define ASM_PTR ".quad" @@ -13,9 +16,13 @@ #define ASM_ALIGN ".balign 4" #endif +/* + * We use a brcl 0,2 instruction for jump labels at compile time so it + * can be easily distinguished from a hotpatch generated instruction. + */ static __always_inline bool arch_static_branch(struct static_key *key) { - asm_volatile_goto("0: brcl 0,0\n" + asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n" ".pushsection __jump_table, \"aw\"\n" ASM_ALIGN "\n" ASM_PTR " 0b, %l[label], %0\n" @@ -34,4 +41,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 9cba74d5..d01fc58 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -35,11 +35,13 @@ #define KVM_NR_IRQCHIPS 1 #define KVM_IRQCHIP_NUM_PINS 4096 -#define SIGP_CTRL_C 0x00800000 +#define SIGP_CTRL_C 0x80 +#define SIGP_CTRL_SCN_MASK 0x3f struct sca_entry { - atomic_t ctrl; - __u32 reserved; + __u8 reserved0; + __u8 sigp_ctrl; + __u16 reserved[3]; __u64 sda; __u64 reserved2[2]; } __attribute__((packed)); @@ -87,7 +89,8 @@ struct kvm_s390_sie_block { atomic_t cpuflags; /* 0x0000 */ __u32 : 1; /* 0x0004 */ __u32 prefix : 18; - __u32 : 13; + __u32 : 1; + __u32 ibc : 12; __u8 reserved08[4]; /* 0x0008 */ #define PROG_IN_SIE (1<<0) __u32 prog0c; /* 0x000c */ @@ -132,7 +135,9 @@ struct kvm_s390_sie_block { __u8 reserved60; /* 0x0060 */ __u8 ecb; /* 0x0061 */ __u8 ecb2; /* 0x0062 */ - __u8 reserved63[1]; /* 0x0063 */ +#define ECB3_AES 0x04 +#define ECB3_DEA 0x08 + __u8 ecb3; /* 0x0063 */ __u32 scaol; /* 0x0064 */ __u8 reserved68[4]; /* 0x0068 */ __u32 todpr; /* 0x006c */ @@ -159,6 +164,7 @@ struct kvm_s390_sie_block { __u64 tecmc; /* 0x00e8 */ __u8 reservedf0[12]; /* 0x00f0 */ #define CRYCB_FORMAT1 0x00000001 +#define CRYCB_FORMAT2 0x00000003 __u32 crycbd; /* 0x00fc */ __u64 gcr[16]; /* 0x0100 */ __u64 gbea; /* 0x0180 */ @@ -166,7 +172,9 @@ struct kvm_s390_sie_block { __u32 fac; /* 0x01a0 */ __u8 reserved1a4[20]; /* 0x01a4 */ __u64 cbrlo; /* 0x01b8 */ - __u8 reserved1c0[30]; /* 0x01c0 */ + __u8 reserved1c0[8]; /* 0x01c0 */ + __u32 ecd; /* 0x01c8 */ + __u8 reserved1cc[18]; /* 0x01cc */ __u64 pp; /* 0x01de */ __u8 reserved1e6[2]; /* 0x01e6 */ __u64 itdba; /* 0x01e8 */ @@ -177,11 +185,17 @@ struct kvm_s390_itdb { __u8 data[256]; } __packed; +struct kvm_s390_vregs { + __vector128 vrs[32]; + __u8 reserved200[512]; /* for future vector expansion */ +} __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 */ + __u8 reserved700[1280]; /* 0x0700 */ + struct kvm_s390_vregs vregs; /* 0x0c00 */ } __packed; struct kvm_vcpu_stat { @@ -192,6 +206,7 @@ struct kvm_vcpu_stat { u32 exit_stop_request; u32 exit_validity; u32 exit_instruction; + u32 halt_successful_poll; u32 halt_wakeup; u32 instruction_lctl; u32 instruction_lctlg; @@ -231,6 +246,7 @@ struct kvm_vcpu_stat { u32 instruction_sigp_stop; u32 instruction_sigp_stop_store_status; u32 instruction_sigp_store_status; + u32 instruction_sigp_store_adtl_status; u32 instruction_sigp_arch; u32 instruction_sigp_prefix; u32 instruction_sigp_restart; @@ -263,6 +279,7 @@ struct kvm_vcpu_stat { #define PGM_SPECIAL_OPERATION 0x13 #define PGM_OPERAND 0x15 #define PGM_TRACE_TABEL 0x16 +#define PGM_VECTOR_PROCESSING 0x1b #define PGM_SPACE_SWITCH 0x1c #define PGM_HFP_SQUARE_ROOT 0x1d #define PGM_PC_TRANSLATION_SPEC 0x1f @@ -327,6 +344,11 @@ enum irq_types { IRQ_PEND_COUNT }; +/* We have 2M for virtio device descriptor pages. Smallest amount of + * memory per page is 24 bytes (1 queue), so (2048*1024) / 24 = 87381 + */ +#define KVM_S390_MAX_VIRTIO_IRQS 87381 + /* * Repressible (non-floating) machine check interrupts * subclass bits in MCIC @@ -378,14 +400,11 @@ 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_stop_info stop; 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) - struct kvm_s390_irq_payload { struct kvm_s390_io_info io; struct kvm_s390_ext_info ext; @@ -393,6 +412,7 @@ struct kvm_s390_irq_payload { struct kvm_s390_emerg_info emerg; struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; struct kvm_s390_mchk_info mchk; }; @@ -401,19 +421,37 @@ struct kvm_s390_local_interrupt { struct kvm_s390_float_interrupt *float_int; wait_queue_head_t *wq; atomic_t *cpuflags; - unsigned int action_bits; DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); struct kvm_s390_irq_payload irq; unsigned long pending_irqs; }; +#define FIRQ_LIST_IO_ISC_0 0 +#define FIRQ_LIST_IO_ISC_1 1 +#define FIRQ_LIST_IO_ISC_2 2 +#define FIRQ_LIST_IO_ISC_3 3 +#define FIRQ_LIST_IO_ISC_4 4 +#define FIRQ_LIST_IO_ISC_5 5 +#define FIRQ_LIST_IO_ISC_6 6 +#define FIRQ_LIST_IO_ISC_7 7 +#define FIRQ_LIST_PFAULT 8 +#define FIRQ_LIST_VIRTIO 9 +#define FIRQ_LIST_COUNT 10 +#define FIRQ_CNTR_IO 0 +#define FIRQ_CNTR_SERVICE 1 +#define FIRQ_CNTR_VIRTIO 2 +#define FIRQ_CNTR_PFAULT 3 +#define FIRQ_MAX_COUNT 4 + struct kvm_s390_float_interrupt { + unsigned long pending_irqs; spinlock_t lock; - struct list_head list; - atomic_t active; + struct list_head lists[FIRQ_LIST_COUNT]; + int counters[FIRQ_MAX_COUNT]; + struct kvm_s390_mchk_info mchk; + struct kvm_s390_ext_info srv_signal; int next_rr_cpu; unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; - unsigned int irq_count; }; struct kvm_hw_wp_info_arch { @@ -461,6 +499,7 @@ struct kvm_vcpu_arch { s390_fp_regs host_fpregs; unsigned int host_acrs[NUM_ACRS]; s390_fp_regs guest_fpregs; + struct kvm_s390_vregs *host_vregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; @@ -470,7 +509,6 @@ struct kvm_vcpu_arch { }; 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; @@ -504,13 +542,39 @@ struct s390_io_adapter { #define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8) #define MAX_S390_ADAPTER_MAPS 256 +/* maximum size of facilities and facility mask is 2k bytes */ +#define S390_ARCH_FAC_LIST_SIZE_BYTE (1<<11) +#define S390_ARCH_FAC_LIST_SIZE_U64 \ + (S390_ARCH_FAC_LIST_SIZE_BYTE / sizeof(u64)) +#define S390_ARCH_FAC_MASK_SIZE_BYTE S390_ARCH_FAC_LIST_SIZE_BYTE +#define S390_ARCH_FAC_MASK_SIZE_U64 \ + (S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64)) + +struct kvm_s390_fac { + /* facility list requested by guest */ + __u64 list[S390_ARCH_FAC_LIST_SIZE_U64]; + /* facility mask supported by kvm & hosting machine */ + __u64 mask[S390_ARCH_FAC_LIST_SIZE_U64]; +}; + +struct kvm_s390_cpu_model { + struct kvm_s390_fac *fac; + struct cpuid cpu_id; + unsigned short ibc; +}; + struct kvm_s390_crypto { struct kvm_s390_crypto_cb *crycb; __u32 crycbd; + __u8 aes_kw; + __u8 dea_kw; }; struct kvm_s390_crypto_cb { - __u8 reserved00[128]; /* 0x0000 */ + __u8 reserved00[72]; /* 0x0000 */ + __u8 dea_wrapping_key_mask[24]; /* 0x0048 */ + __u8 aes_wrapping_key_mask[32]; /* 0x0060 */ + __u8 reserved80[128]; /* 0x0080 */ }; struct kvm_arch{ @@ -523,12 +587,16 @@ struct kvm_arch{ int use_irqchip; int use_cmma; int user_cpu_state_ctrl; + int user_sigp; + int user_stsi; struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS]; wait_queue_head_t ipte_wq; int ipte_lock_count; struct mutex ipte_mutex; spinlock_t start_stop_lock; + struct kvm_s390_cpu_model model; struct kvm_s390_crypto crypto; + u64 epoch; }; #define KVM_HVA_ERR_BAD (-1UL) diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index f49b719..8fb3802 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -62,6 +62,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { int cpu = smp_processor_id(); + S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); if (prev == next) return; if (MACHINE_HAS_TLB_LC) @@ -73,7 +74,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *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 diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 7b2ac6e..53eacbd 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -37,16 +37,7 @@ static inline void storage_key_init_range(unsigned long start, unsigned long end #endif } -static inline void clear_page(void *page) -{ - 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"); -} +#define clear_page(page) memset((page), 0, PAGE_SIZE) /* * copy_page uses the mvcl instruction with 0xb0 padding byte in order to diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index f664e96..1a9a98d 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -16,6 +16,7 @@ struct zpci_iomap_entry { u32 fh; u8 bar; + u16 count; }; extern struct zpci_iomap_entry *zpci_iomap_start; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index ffb1d8c..e08ec38 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -91,7 +91,9 @@ extern unsigned long zero_page_mask; */ #define PTRS_PER_PTE 256 #ifndef CONFIG_64BIT +#define __PAGETABLE_PUD_FOLDED #define PTRS_PER_PMD 1 +#define __PAGETABLE_PMD_FOLDED #define PTRS_PER_PUD 1 #else /* CONFIG_64BIT */ #define PTRS_PER_PMD 2048 @@ -99,7 +101,7 @@ extern unsigned long zero_page_mask; #endif /* CONFIG_64BIT */ #define PTRS_PER_PGD 2048 -#define FIRST_USER_ADDRESS 0 +#define FIRST_USER_ADDRESS 0UL #define pte_ERROR(e) \ printk("%s:%d: bad pte %p.\n", __FILE__, __LINE__, (void *) pte_val(e)) @@ -1758,6 +1760,10 @@ extern int s390_enable_sie(void); extern int s390_enable_skey(void); extern void s390_reset_cmma(struct mm_struct *mm); +/* s390 has a private copy of get unmapped area to deal with cache synonyms */ +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN + /* * No page table caches to initialise */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index bed05ea..e7cbbdc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -215,10 +215,7 @@ static inline unsigned short stap(void) /* * Give up the time slice of the virtual PU. */ -static inline void cpu_relax(void) -{ - barrier(); -} +void cpu_relax(void); #define cpu_relax_lowlatency() barrier() diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h index 8045785..7278606 100644 --- a/arch/s390/include/asm/reset.h +++ b/arch/s390/include/asm/reset.h @@ -15,5 +15,6 @@ struct reset_call { extern void register_reset_call(struct reset_call *reset); extern void unregister_reset_call(struct reset_call *reset); -extern void s390_reset_system(void (*func)(void *), void *data); +extern void s390_reset_system(void (*fn_pre)(void), + void (*fn_post)(void *), void *data); #endif /* _ASM_S390_RESET_H */ diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 1aba89b..f1096ba 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -27,11 +27,12 @@ struct sclp_ipl_info { }; struct sclp_cpu_entry { - u8 address; + u8 core_id; u8 reserved0[2]; u8 : 3; u8 siif : 1; - u8 : 4; + u8 sigpif : 1; + u8 : 3; u8 reserved2[10]; u8 type; u8 reserved1; @@ -51,6 +52,9 @@ int sclp_cpu_deconfigure(u8 cpu); unsigned long long sclp_get_rnmax(void); unsigned long long sclp_get_rzm(void); unsigned int sclp_get_max_cpu(void); +unsigned int sclp_get_mtid(u8 cpu_type); +unsigned int sclp_get_mtid_max(void); +unsigned int sclp_get_mtid_prev(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); @@ -66,6 +70,9 @@ 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); +int sclp_has_sigpif(void); unsigned int sclp_get_ibc(void); +long _sclp_print_early(const char *); + #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 7736fdd..b8d1e54 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -57,6 +57,7 @@ extern void detect_memory_memblock(void); #define MACHINE_FLAG_TE (1UL << 15) #define MACHINE_FLAG_TLB_LC (1UL << 17) #define MACHINE_FLAG_VX (1UL << 18) +#define MACHINE_FLAG_CAD (1UL << 19) #define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) #define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) @@ -80,6 +81,7 @@ extern void detect_memory_memblock(void); #define MACHINE_HAS_TE (0) #define MACHINE_HAS_TLB_LC (0) #define MACHINE_HAS_VX (0) +#define MACHINE_HAS_CAD (0) #else /* CONFIG_64BIT */ #define MACHINE_HAS_IEEE (1) #define MACHINE_HAS_CSP (1) @@ -93,6 +95,7 @@ extern void detect_memory_memblock(void); #define MACHINE_HAS_TE (S390_lowcore.machine_flags & MACHINE_FLAG_TE) #define MACHINE_HAS_TLB_LC (S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC) #define MACHINE_HAS_VX (S390_lowcore.machine_flags & MACHINE_FLAG_VX) +#define MACHINE_HAS_CAD (S390_lowcore.machine_flags & MACHINE_FLAG_CAD) #endif /* CONFIG_64BIT */ /* diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h index fad4ae2..ec60cf7 100644 --- a/arch/s390/include/asm/sigp.h +++ b/arch/s390/include/asm/sigp.h @@ -16,6 +16,7 @@ #define SIGP_SET_ARCHITECTURE 18 #define SIGP_COND_EMERGENCY_SIGNAL 19 #define SIGP_SENSE_RUNNING 21 +#define SIGP_SET_MULTI_THREADING 22 #define SIGP_STORE_ADDITIONAL_STATUS 23 /* SIGP condition codes */ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 762d4f8..b3bd028 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -16,6 +16,8 @@ #define raw_smp_processor_id() (S390_lowcore.cpu_nr) extern struct mutex smp_cpu_state_mutex; +extern unsigned int smp_cpu_mt_shift; +extern unsigned int smp_cpu_mtid; extern int __cpu_up(unsigned int cpu, struct task_struct *tidle); @@ -35,6 +37,8 @@ extern void smp_fill_possible_mask(void); #else /* CONFIG_SMP */ +#define smp_cpu_mtid 0 + static inline void smp_call_ipl_cpu(void (*func)(void *), void *data) { func(data); diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 7e2dcd7..8662f5c 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -44,7 +44,6 @@ extern char *strstr(const char *, const char *); #undef __HAVE_ARCH_STRCHR #undef __HAVE_ARCH_STRNCHR #undef __HAVE_ARCH_STRNCMP -#undef __HAVE_ARCH_STRNICMP #undef __HAVE_ARCH_STRPBRK #undef __HAVE_ARCH_STRSEP #undef __HAVE_ARCH_STRSPN diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index f92428e..f7054a8 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -15,6 +15,7 @@ #define __ASM_S390_SYSINFO_H #include <asm/bitsperlong.h> +#include <linux/uuid.h> struct sysinfo_1_1_1 { unsigned char p:1; @@ -90,7 +91,11 @@ struct sysinfo_2_2_2 { unsigned short cpus_reserved; char name[8]; unsigned int caf; - char reserved_2[16]; + char reserved_2[8]; + unsigned char mt_installed; + unsigned char mt_general; + unsigned char mt_psmtid; + char reserved_3[5]; unsigned short cpus_dedicated; unsigned short cpus_shared; }; @@ -112,34 +117,39 @@ struct sysinfo_3_2_2 { char name[8]; unsigned int caf; char cpi[16]; - char reserved_1[24]; - + char reserved_1[3]; + char ext_name_encoding; + unsigned int reserved_2; + uuid_be uuid; } vm[8]; - char reserved_544[3552]; + char reserved_3[1504]; + char ext_names[8][256]; }; extern int topology_max_mnest; -#define TOPOLOGY_CPU_BITS 64 +#define TOPOLOGY_CORE_BITS 64 #define TOPOLOGY_NR_MAG 6 -struct topology_cpu { - unsigned char reserved0[4]; +struct topology_core { + unsigned char nl; + unsigned char reserved0[3]; unsigned char :6; unsigned char pp:2; unsigned char reserved1; unsigned short origin; - unsigned long mask[TOPOLOGY_CPU_BITS / BITS_PER_LONG]; + unsigned long mask[TOPOLOGY_CORE_BITS / BITS_PER_LONG]; }; struct topology_container { - unsigned char reserved[7]; + unsigned char nl; + unsigned char reserved[6]; unsigned char id; }; union topology_entry { unsigned char nl; - struct topology_cpu cpu; + struct topology_core cpu; struct topology_container container; }; diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 4d62fd5..ef1df71 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -39,7 +39,6 @@ struct thread_info { 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; unsigned int system_call; __u64 user_timer; __u64 system_timer; @@ -56,9 +55,6 @@ struct thread_info { .flags = 0, \ .cpu = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ - .restart_block = { \ - .fn = do_no_restart_syscall, \ - }, \ } #define init_thread_info (init_thread_union.thread_info) diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 56af530..b1453a2 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -9,20 +9,24 @@ struct cpu; #ifdef CONFIG_SCHED_BOOK struct cpu_topology_s390 { + unsigned short thread_id; unsigned short core_id; unsigned short socket_id; unsigned short book_id; + cpumask_t thread_mask; cpumask_t core_mask; cpumask_t book_mask; }; -extern struct cpu_topology_s390 cpu_topology[NR_CPUS]; +DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology); -#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) -#define topology_core_id(cpu) (cpu_topology[cpu].core_id) -#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_mask) -#define topology_book_id(cpu) (cpu_topology[cpu].book_id) -#define topology_book_cpumask(cpu) (&cpu_topology[cpu].book_mask) +#define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id) +#define topology_thread_id(cpu) (per_cpu(cpu_topology, cpu).thread_id) +#define topology_thread_cpumask(cpu) (&per_cpu(cpu_topology, cpu).thread_mask) +#define topology_core_id(cpu) (per_cpu(cpu_topology, cpu).core_id) +#define topology_core_cpumask(cpu) (&per_cpu(cpu_topology, cpu).core_mask) +#define topology_book_id(cpu) (per_cpu(cpu_topology, cpu).book_id) +#define topology_book_cpumask(cpu) (&per_cpu(cpu_topology, cpu).book_mask) #define mc_capable() 1 @@ -47,14 +51,6 @@ static inline void topology_expect_change(void) { } #define POLARIZATION_VM (2) #define POLARIZATION_VH (3) -#ifdef CONFIG_SCHED_BOOK -void s390_init_cpu_topology(void); -#else -static inline void s390_init_cpu_topology(void) -{ -}; -#endif - #include <asm-generic/topology.h> #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/s390/include/uapi/asm/hypfs.h b/arch/s390/include/uapi/asm/hypfs.h index 37998b4..b3fe12d 100644 --- a/arch/s390/include/uapi/asm/hypfs.h +++ b/arch/s390/include/uapi/asm/hypfs.h @@ -1,16 +1,19 @@ /* - * IOCTL interface for hypfs + * Structures for hypfs interface * * Copyright IBM Corp. 2013 * * Author: Martin Schwidefsky <schwidefsky@de.ibm.com> */ -#ifndef _ASM_HYPFS_CTL_H -#define _ASM_HYPFS_CTL_H +#ifndef _ASM_HYPFS_H +#define _ASM_HYPFS_H #include <linux/types.h> +/* + * IOCTL for binary interface /sys/kernel/debug/diag_304 + */ struct hypfs_diag304 { __u32 args[2]; __u64 data; @@ -22,4 +25,30 @@ struct hypfs_diag304 { #define HYPFS_DIAG304 \ _IOWR(HYPFS_IOCTL_MAGIC, 0x20, struct hypfs_diag304) +/* + * Structures for binary interface /sys/kernel/debug/diag_0c + */ +struct hypfs_diag0c_hdr { + __u64 len; /* Length of diag0c buffer without header */ + __u16 version; /* Version of header */ + char reserved1[6]; /* Reserved */ + char tod_ext[16]; /* TOD clock for diag0c */ + __u64 count; /* Number of entries (CPUs) in diag0c array */ + char reserved2[24]; /* Reserved */ +}; + +struct hypfs_diag0c_entry { + char date[8]; /* MM/DD/YY in EBCDIC */ + char time[8]; /* HH:MM:SS in EBCDIC */ + __u64 virtcpu; /* Virtual time consumed by the virt CPU (us) */ + __u64 totalproc; /* Total of virtual and simulation time (us) */ + __u32 cpu; /* Linux logical CPU number */ + __u32 reserved; /* Align to 8 byte */ +}; + +struct hypfs_diag0c_data { + struct hypfs_diag0c_hdr hdr; /* 64 byte header */ + struct hypfs_diag0c_entry entry[]; /* diag0c entry array */ +}; + #endif diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 48eda3a..ef1a5fc 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -57,10 +57,44 @@ struct kvm_s390_io_adapter_req { /* kvm attr_group on vm fd */ #define KVM_S390_VM_MEM_CTRL 0 +#define KVM_S390_VM_TOD 1 +#define KVM_S390_VM_CRYPTO 2 +#define KVM_S390_VM_CPU_MODEL 3 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 #define KVM_S390_VM_MEM_CLR_CMMA 1 +#define KVM_S390_VM_MEM_LIMIT_SIZE 2 + +/* kvm attributes for KVM_S390_VM_TOD */ +#define KVM_S390_VM_TOD_LOW 0 +#define KVM_S390_VM_TOD_HIGH 1 + +/* kvm attributes for KVM_S390_VM_CPU_MODEL */ +/* processor related attributes are r/w */ +#define KVM_S390_VM_CPU_PROCESSOR 0 +struct kvm_s390_vm_cpu_processor { + __u64 cpuid; + __u16 ibc; + __u8 pad[6]; + __u64 fac_list[256]; +}; + +/* machine related attributes are r/o */ +#define KVM_S390_VM_CPU_MACHINE 1 +struct kvm_s390_vm_cpu_machine { + __u64 cpuid; + __u32 ibc; + __u8 pad[4]; + __u64 fac_mask[256]; + __u64 fac_list[256]; +}; + +/* kvm attributes for crypto */ +#define KVM_S390_VM_CRYPTO_ENABLE_AES_KW 0 +#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1 +#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2 +#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -107,12 +141,16 @@ struct kvm_guest_debug_arch { struct kvm_hw_breakpoint __user *hw_bp; }; +/* for KVM_SYNC_PFAULT and KVM_REG_S390_PFTOKEN */ +#define KVM_S390_PFAULT_TOKEN_INVALID 0xffffffffffffffffULL + #define KVM_SYNC_PREFIX (1UL << 0) #define KVM_SYNC_GPRS (1UL << 1) #define KVM_SYNC_ACRS (1UL << 2) #define KVM_SYNC_CRS (1UL << 3) #define KVM_SYNC_ARCH0 (1UL << 4) #define KVM_SYNC_PFAULT (1UL << 5) +#define KVM_SYNC_VRS (1UL << 6) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -127,6 +165,9 @@ struct kvm_sync_regs { __u64 pft; /* pfault token [PFAULT] */ __u64 pfs; /* pfault select [PFAULT] */ __u64 pfc; /* pfault compare [PFAULT] */ + __u64 vrs[32][2]; /* vector registers */ + __u8 reserved[512]; /* for future vector expansion */ + __u32 fpc; /* only valid with vector registers */ }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h index d4096fd..ee69c08 100644 --- a/arch/s390/include/uapi/asm/sie.h +++ b/arch/s390/include/uapi/asm/sie.h @@ -230,7 +230,7 @@ * 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) \ +#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) \ @@ -239,6 +239,6 @@ INSN_DECODE_IPA0(0xe5, insn, 48, 0xff) \ INSN_DECODE_IPA0(0xeb, insn, 16, 0xff) \ INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f) \ - INSN_DECODE(insn) + INSN_DECODE(insn)) #endif /* _UAPI_ASM_S390_SIE_H */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 204c43a..31fab26 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -4,8 +4,8 @@ ifdef CONFIG_FUNCTION_TRACER # Don't trace early setup code and tracing code -CFLAGS_REMOVE_early.o = -pg -CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) endif # diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index e07e916..8dc4db1 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -171,6 +171,7 @@ int main(void) #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_VX_SAVE_AREA_ADDR, offsetof(struct _lowcore, vector_save_area_addr)); 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)); diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index 797a823..f74a53d 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -97,7 +97,8 @@ ENTRY(diag308_reset) lg %r4,0(%r4) # Save PSW sturg %r4,%r3 # Use sturg, because of large pages lghi %r1,1 - diag %r1,%r1,0x308 + lghi %r0,0 + diag %r0,%r1,0x308 .Lrestart_part2: lhi %r0,0 # Load r0 with zero lhi %r1,2 # Use mode 2 = ESAME (dump) diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index c0b03c2..0969d113 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -5,37 +5,11 @@ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ -#include <linux/notifier.h> #include <linux/seq_file.h> -#include <linux/init.h> -#include <linux/list.h> -#include <linux/slab.h> #include <linux/cpu.h> +#include <linux/cacheinfo.h> #include <asm/facility.h> -struct cache { - unsigned long size; - unsigned int line_size; - unsigned int associativity; - unsigned int nr_sets; - unsigned int level : 3; - unsigned int type : 2; - unsigned int private : 1; - struct list_head list; -}; - -struct cache_dir { - struct kobject *kobj; - struct cache_index_dir *index; -}; - -struct cache_index_dir { - struct kobject kobj; - int cpu; - struct cache *cache; - struct cache_index_dir *next; -}; - enum { CACHE_SCOPE_NOTEXISTS, CACHE_SCOPE_PRIVATE, @@ -44,10 +18,10 @@ enum { }; enum { - CACHE_TYPE_SEPARATE, - CACHE_TYPE_DATA, - CACHE_TYPE_INSTRUCTION, - CACHE_TYPE_UNIFIED, + CTYPE_SEPARATE, + CTYPE_DATA, + CTYPE_INSTRUCTION, + CTYPE_UNIFIED, }; enum { @@ -70,37 +44,57 @@ struct cache_info { }; #define CACHE_MAX_LEVEL 8 - union cache_topology { struct cache_info ci[CACHE_MAX_LEVEL]; unsigned long long raw; }; static const char * const cache_type_string[] = { - "Data", + "", "Instruction", + "Data", + "", "Unified", }; -static struct cache_dir *cache_dir_cpu[NR_CPUS]; -static LIST_HEAD(cache_list); +static const enum cache_type cache_type_map[] = { + [CTYPE_SEPARATE] = CACHE_TYPE_SEPARATE, + [CTYPE_DATA] = CACHE_TYPE_DATA, + [CTYPE_INSTRUCTION] = CACHE_TYPE_INST, + [CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED, +}; void show_cacheinfo(struct seq_file *m) { - struct cache *cache; - int index = 0; + struct cpu_cacheinfo *this_cpu_ci; + struct cacheinfo *cache; + int idx; - list_for_each_entry(cache, &cache_list, list) { - seq_printf(m, "cache%-11d: ", index); + get_online_cpus(); + this_cpu_ci = get_cpu_cacheinfo(cpumask_any(cpu_online_mask)); + for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) { + cache = this_cpu_ci->info_list + idx; + seq_printf(m, "cache%-11d: ", idx); seq_printf(m, "level=%d ", cache->level); seq_printf(m, "type=%s ", cache_type_string[cache->type]); - seq_printf(m, "scope=%s ", cache->private ? "Private" : "Shared"); - seq_printf(m, "size=%luK ", cache->size >> 10); - seq_printf(m, "line_size=%u ", cache->line_size); - seq_printf(m, "associativity=%d", cache->associativity); + seq_printf(m, "scope=%s ", + cache->disable_sysfs ? "Shared" : "Private"); + seq_printf(m, "size=%dK ", cache->size >> 10); + seq_printf(m, "line_size=%u ", cache->coherency_line_size); + seq_printf(m, "associativity=%d", cache->ways_of_associativity); seq_puts(m, "\n"); - index++; } + put_online_cpus(); +} + +static inline enum cache_type get_cache_type(struct cache_info *ci, int level) +{ + if (level >= CACHE_MAX_LEVEL) + return CACHE_TYPE_NOCACHE; + ci += level; + if (ci->scope != CACHE_SCOPE_SHARED && ci->scope != CACHE_SCOPE_PRIVATE) + return CACHE_TYPE_NOCACHE; + return cache_type_map[ci->type]; } static inline unsigned long ecag(int ai, int li, int ti) @@ -113,277 +107,71 @@ static inline unsigned long ecag(int ai, int li, int ti) return val; } -static int __init cache_add(int level, int private, int type) +static void ci_leaf_init(struct cacheinfo *this_leaf, int private, + enum cache_type type, unsigned int level, int cpu) { - struct cache *cache; - int ti; + int ti, num_sets; - cache = kzalloc(sizeof(*cache), GFP_KERNEL); - if (!cache) - return -ENOMEM; - if (type == CACHE_TYPE_INSTRUCTION) + if (type == CACHE_TYPE_INST) ti = CACHE_TI_INSTRUCTION; else ti = CACHE_TI_UNIFIED; - cache->size = ecag(EXTRACT_SIZE, level, ti); - cache->line_size = ecag(EXTRACT_LINE_SIZE, level, ti); - cache->associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti); - cache->nr_sets = cache->size / cache->associativity; - cache->nr_sets /= cache->line_size; - cache->private = private; - cache->level = level + 1; - cache->type = type - 1; - list_add_tail(&cache->list, &cache_list); - return 0; -} - -static void __init cache_build_info(void) -{ - struct cache *cache, *next; + this_leaf->level = level + 1; + this_leaf->type = type; + this_leaf->coherency_line_size = ecag(EXTRACT_LINE_SIZE, level, ti); + this_leaf->ways_of_associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti); + this_leaf->size = ecag(EXTRACT_SIZE, level, ti); + num_sets = this_leaf->size / this_leaf->coherency_line_size; + num_sets /= this_leaf->ways_of_associativity; + this_leaf->number_of_sets = num_sets; + cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map); + if (!private) + this_leaf->disable_sysfs = true; +} + +int init_cache_level(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + unsigned int level = 0, leaves = 0; union cache_topology ct; - int level, private, rc; + enum cache_type ctype; + if (!this_cpu_ci) + return -EINVAL; ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); - for (level = 0; level < CACHE_MAX_LEVEL; level++) { - switch (ct.ci[level].scope) { - case CACHE_SCOPE_SHARED: - private = 0; - break; - case CACHE_SCOPE_PRIVATE: - private = 1; + do { + ctype = get_cache_type(&ct.ci[0], level); + if (ctype == CACHE_TYPE_NOCACHE) break; - default: - return; - } - if (ct.ci[level].type == CACHE_TYPE_SEPARATE) { - rc = cache_add(level, private, CACHE_TYPE_DATA); - rc |= cache_add(level, private, CACHE_TYPE_INSTRUCTION); - } else { - rc = cache_add(level, private, ct.ci[level].type); - } - if (rc) - goto error; - } - return; -error: - list_for_each_entry_safe(cache, next, &cache_list, list) { - list_del(&cache->list); - kfree(cache); - } -} - -static struct cache_dir *cache_create_cache_dir(int cpu) -{ - struct cache_dir *cache_dir; - struct kobject *kobj = NULL; - struct device *dev; - - dev = get_cpu_device(cpu); - if (!dev) - goto out; - kobj = kobject_create_and_add("cache", &dev->kobj); - if (!kobj) - goto out; - cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL); - if (!cache_dir) - goto out; - cache_dir->kobj = kobj; - cache_dir_cpu[cpu] = cache_dir; - return cache_dir; -out: - kobject_put(kobj); - return NULL; -} - -static struct cache_index_dir *kobj_to_cache_index_dir(struct kobject *kobj) -{ - return container_of(kobj, struct cache_index_dir, kobj); -} - -static void cache_index_release(struct kobject *kobj) -{ - struct cache_index_dir *index; - - index = kobj_to_cache_index_dir(kobj); - kfree(index); -} - -static ssize_t cache_index_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct kobj_attribute *kobj_attr; - - kobj_attr = container_of(attr, struct kobj_attribute, attr); - return kobj_attr->show(kobj, kobj_attr, buf); -} - -#define DEFINE_CACHE_ATTR(_name, _format, _value) \ -static ssize_t cache_##_name##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *buf) \ -{ \ - struct cache_index_dir *index; \ - \ - index = kobj_to_cache_index_dir(kobj); \ - return sprintf(buf, _format, _value); \ -} \ -static struct kobj_attribute cache_##_name##_attr = \ - __ATTR(_name, 0444, cache_##_name##_show, NULL); - -DEFINE_CACHE_ATTR(size, "%luK\n", index->cache->size >> 10); -DEFINE_CACHE_ATTR(coherency_line_size, "%u\n", index->cache->line_size); -DEFINE_CACHE_ATTR(number_of_sets, "%u\n", index->cache->nr_sets); -DEFINE_CACHE_ATTR(ways_of_associativity, "%u\n", index->cache->associativity); -DEFINE_CACHE_ATTR(type, "%s\n", cache_type_string[index->cache->type]); -DEFINE_CACHE_ATTR(level, "%d\n", index->cache->level); - -static ssize_t shared_cpu_map_func(struct kobject *kobj, int type, char *buf) -{ - struct cache_index_dir *index; - int len; - - index = kobj_to_cache_index_dir(kobj); - len = type ? - cpulist_scnprintf(buf, PAGE_SIZE - 2, cpumask_of(index->cpu)) : - cpumask_scnprintf(buf, PAGE_SIZE - 2, cpumask_of(index->cpu)); - len += sprintf(&buf[len], "\n"); - return len; -} - -static ssize_t shared_cpu_map_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return shared_cpu_map_func(kobj, 0, buf); -} -static struct kobj_attribute cache_shared_cpu_map_attr = - __ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL); - -static ssize_t shared_cpu_list_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return shared_cpu_map_func(kobj, 1, buf); -} -static struct kobj_attribute cache_shared_cpu_list_attr = - __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL); - -static struct attribute *cache_index_default_attrs[] = { - &cache_type_attr.attr, - &cache_size_attr.attr, - &cache_number_of_sets_attr.attr, - &cache_ways_of_associativity_attr.attr, - &cache_level_attr.attr, - &cache_coherency_line_size_attr.attr, - &cache_shared_cpu_map_attr.attr, - &cache_shared_cpu_list_attr.attr, - NULL, -}; - -static const struct sysfs_ops cache_index_ops = { - .show = cache_index_show, -}; - -static struct kobj_type cache_index_type = { - .sysfs_ops = &cache_index_ops, - .release = cache_index_release, - .default_attrs = cache_index_default_attrs, -}; - -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; - - index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL); - if (!index_dir) - return -ENOMEM; - index_dir->cache = cache; - index_dir->cpu = cpu; - rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type, - cache_dir->kobj, "index%d", index); - if (rc) - goto out; - index_dir->next = cache_dir->index; - cache_dir->index = index_dir; - return 0; -out: - kfree(index_dir); - return rc; -} - -static int cache_add_cpu(int cpu) -{ - struct cache_dir *cache_dir; - struct cache *cache; - int rc, index = 0; - - if (list_empty(&cache_list)) - return 0; - cache_dir = cache_create_cache_dir(cpu); - if (!cache_dir) - return -ENOMEM; - list_for_each_entry(cache, &cache_list, list) { - if (!cache->private) - break; - rc = cache_create_index_dir(cache_dir, cache, index, cpu); - if (rc) - return rc; - index++; - } + /* Separate instruction and data caches */ + leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; + } while (++level < CACHE_MAX_LEVEL); + this_cpu_ci->num_levels = level; + this_cpu_ci->num_leaves = leaves; return 0; } -static void cache_remove_cpu(int cpu) -{ - struct cache_index_dir *index, *next; - struct cache_dir *cache_dir; - - cache_dir = cache_dir_cpu[cpu]; - if (!cache_dir) - return; - index = cache_dir->index; - while (index) { - next = index->next; - kobject_put(&index->kobj); - index = next; - } - kobject_put(cache_dir->kobj); - kfree(cache_dir); - cache_dir_cpu[cpu] = NULL; -} - -static int cache_hotplug(struct notifier_block *nfb, unsigned long action, - void *hcpu) +int populate_cache_leaves(unsigned int cpu) { - int cpu = (long)hcpu; - int rc = 0; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf = this_cpu_ci->info_list; + unsigned int level, idx, pvt; + union cache_topology ct; + enum cache_type ctype; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - rc = cache_add_cpu(cpu); - if (rc) - cache_remove_cpu(cpu); - break; - case CPU_DEAD: - cache_remove_cpu(cpu); - break; + ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); + for (idx = 0, level = 0; level < this_cpu_ci->num_levels && + idx < this_cpu_ci->num_leaves; idx++, level++) { + if (!this_leaf) + return -EINVAL; + pvt = (ct.ci[level].scope == CACHE_SCOPE_PRIVATE) ? 1 : 0; + ctype = get_cache_type(&ct.ci[0], level); + if (ctype == CACHE_TYPE_SEPARATE) { + ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_DATA, level, cpu); + ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_INST, level, cpu); + } else { + ci_leaf_init(this_leaf++, pvt, ctype, level, cpu); + } } - return rc ? NOTIFY_BAD : NOTIFY_OK; -} - -static int __init cache_init(void) -{ - int cpu; - - 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); - cpu_notifier_register_done(); return 0; } -device_initcall(cache_init); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 34d5fa7..bc1df12 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -209,7 +209,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) int i; /* Alwys make any pending restarted system call return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; + current->restart_block.fn = do_no_restart_syscall; if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs))) return -EFAULT; diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index f376293..5334303 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -137,7 +137,7 @@ enum { INSTR_RSI_RRP, INSTR_RSL_LRDFU, INSTR_RSL_R0RD, INSTR_RSY_AARD, INSTR_RSY_CCRD, INSTR_RSY_RRRD, INSTR_RSY_RURD, - INSTR_RSY_RDRM, + INSTR_RSY_RDRM, INSTR_RSY_RMRD, INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD, INSTR_RS_RRRD, INSTR_RS_RURD, INSTR_RXE_FRRD, INSTR_RXE_RRRD, INSTR_RXE_RRRDM, @@ -226,7 +226,6 @@ static const struct s390_operand operands[] = [U16_32] = { 16, 32, 0 }, [J16_16] = { 16, 16, OPERAND_PCREL }, [J16_32] = { 16, 32, OPERAND_PCREL }, - [I16_32] = { 16, 32, OPERAND_SIGNED }, [I24_24] = { 24, 24, OPERAND_SIGNED }, [J32_16] = { 32, 16, OPERAND_PCREL }, [I32_16] = { 32, 16, OPERAND_SIGNED }, @@ -308,6 +307,7 @@ static const unsigned char formats[][7] = { [INSTR_RSY_AARD] = { 0xff, A_8,A_12,D20_20,B_16,0,0 }, [INSTR_RSY_CCRD] = { 0xff, C_8,C_12,D20_20,B_16,0,0 }, [INSTR_RSY_RDRM] = { 0xff, R_8,D20_20,B_16,U4_12,0,0 }, + [INSTR_RSY_RMRD] = { 0xff, R_8,U4_12,D20_20,B_16,0,0 }, [INSTR_RSY_RRRD] = { 0xff, R_8,R_12,D20_20,B_16,0,0 }, [INSTR_RSY_RURD] = { 0xff, R_8,U4_12,D20_20,B_16,0,0 }, [INSTR_RS_AARD] = { 0xff, A_8,A_12,D_20,B_16,0,0 }, @@ -451,7 +451,8 @@ enum { LONG_INSN_VERLLV, LONG_INSN_VESRAV, LONG_INSN_VESRLV, - LONG_INSN_VSBCBI + LONG_INSN_VSBCBI, + LONG_INSN_STCCTM }; static char *long_insn_name[] = { @@ -531,6 +532,7 @@ static char *long_insn_name[] = { [LONG_INSN_VESRAV] = "vesrav", [LONG_INSN_VESRLV] = "vesrlv", [LONG_INSN_VSBCBI] = "vsbcbi", + [LONG_INSN_STCCTM] = "stcctm", }; static struct s390_insn opcode[] = { @@ -1656,6 +1658,7 @@ static struct s390_insn opcode_eb[] = { { "lric", 0x60, INSTR_RSY_RDRM }, { "stric", 0x61, INSTR_RSY_RDRM }, { "mric", 0x62, INSTR_RSY_RDRM }, + { { 0, LONG_INSN_STCCTM }, 0x17, INSTR_RSY_RMRD }, #endif { "rll", 0x1d, INSTR_RSY_RRRD }, { "mvclu", 0x8e, INSTR_RSY_RRRD }, diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 302ac1f7..4427ab7 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -396,6 +396,26 @@ static __init void detect_machine_facilities(void) #endif } +static int __init cad_setup(char *str) +{ + int val; + + get_option(&str, &val); + if (val && test_facility(128)) + S390_lowcore.machine_flags |= MACHINE_FLAG_CAD; + return 0; +} +early_param("cad", cad_setup); + +static int __init cad_init(void) +{ + if (MACHINE_HAS_CAD) + /* Enable problem state CAD. */ + __ctl_set_bit(2, 3); + return 0; +} +early_initcall(cad_init); + static __init void rescue_initrd(void) { #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 8e61393..834df04 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -71,9 +71,11 @@ struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; +long sys_rt_sigreturn(void); +long sys_sigreturn(void); + long sys_s390_personality(unsigned int personality); long sys_s390_runtime_instr(int command, int signum); - long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t); long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t); #endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index b86bb88..6c79f1b 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -46,10 +46,55 @@ * lg %r14,8(%r15) # offset 18 * The jg instruction branches to offset 24 to skip as many instructions * as possible. + * In case we use gcc's hotpatch feature the original and also the disabled + * function prologue contains only a single six byte instruction and looks + * like this: + * > brcl 0,0 # offset 0 + * To enable ftrace the code gets patched like above and afterwards looks + * like this: + * > brasl %r0,ftrace_caller # offset 0 */ unsigned long ftrace_plt; +static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn) +{ +#ifdef CC_USING_HOTPATCH + /* brcl 0,0 */ + insn->opc = 0xc004; + insn->disp = 0; +#else + /* stg r14,8(r15) */ + insn->opc = 0xe3e0; + insn->disp = 0xf0080024; +#endif +} + +static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + if (insn->opc == BREAKPOINT_INSTRUCTION) + return 1; +#endif + return 0; +} + +static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + insn->opc = BREAKPOINT_INSTRUCTION; + insn->disp = KPROBE_ON_FTRACE_NOP; +#endif +} + +static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_KPROBES + insn->opc = BREAKPOINT_INSTRUCTION; + insn->disp = KPROBE_ON_FTRACE_CALL; +#endif +} + int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { @@ -59,62 +104,62 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn insn; - unsigned short op; - void *from, *to; - size_t size; - - ftrace_generate_nop_insn(&insn); - size = sizeof(insn); - from = &insn; - to = (void *) rec->ip; - if (probe_kernel_read(&op, (void *) rec->ip, sizeof(op))) + struct ftrace_insn orig, new, old; + + if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - /* - * If we find a breakpoint instruction, a kprobe has been placed - * at the beginning of the function. We write the constant - * KPROBE_ON_FTRACE_NOP into the remaining four bytes of the original - * instruction so that the kprobes handler can execute a nop, if it - * reaches this breakpoint. - */ - if (op == BREAKPOINT_INSTRUCTION) { - size -= 2; - from += 2; - to += 2; - insn.disp = KPROBE_ON_FTRACE_NOP; + if (addr == MCOUNT_ADDR) { + /* Initial code replacement */ + ftrace_generate_orig_insn(&orig); + ftrace_generate_nop_insn(&new); + } else if (is_kprobe_on_ftrace(&old)) { + /* + * If we find a breakpoint instruction, a kprobe has been + * placed at the beginning of the function. We write the + * constant KPROBE_ON_FTRACE_NOP into the remaining four + * bytes of the original instruction so that the kprobes + * handler can execute a nop, if it reaches this breakpoint. + */ + ftrace_generate_kprobe_call_insn(&orig); + ftrace_generate_kprobe_nop_insn(&new); + } else { + /* Replace ftrace call with a nop. */ + ftrace_generate_call_insn(&orig, rec->ip); + ftrace_generate_nop_insn(&new); } - if (probe_kernel_write(to, from, size)) + /* Verify that the to be replaced code matches what we expect. */ + if (memcmp(&orig, &old, sizeof(old))) + return -EINVAL; + if (probe_kernel_write((void *) rec->ip, &new, sizeof(new))) return -EPERM; return 0; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn insn; - unsigned short op; - void *from, *to; - size_t size; - - ftrace_generate_call_insn(&insn, rec->ip); - size = sizeof(insn); - from = &insn; - to = (void *) rec->ip; - if (probe_kernel_read(&op, (void *) rec->ip, sizeof(op))) + struct ftrace_insn orig, new, old; + + if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - /* - * If we find a breakpoint instruction, a kprobe has been placed - * at the beginning of the function. We write the constant - * KPROBE_ON_FTRACE_CALL into the remaining four bytes of the original - * instruction so that the kprobes handler can execute a brasl if it - * reaches this breakpoint. - */ - if (op == BREAKPOINT_INSTRUCTION) { - size -= 2; - from += 2; - to += 2; - insn.disp = KPROBE_ON_FTRACE_CALL; + if (is_kprobe_on_ftrace(&old)) { + /* + * If we find a breakpoint instruction, a kprobe has been + * placed at the beginning of the function. We write the + * constant KPROBE_ON_FTRACE_CALL into the remaining four + * bytes of the original instruction so that the kprobes + * handler can execute a brasl if it reaches this breakpoint. + */ + ftrace_generate_kprobe_nop_insn(&orig); + ftrace_generate_kprobe_call_insn(&new); + } else { + /* Replace nop with an ftrace call. */ + ftrace_generate_nop_insn(&orig); + ftrace_generate_call_insn(&new, rec->ip); } - if (probe_kernel_write(to, from, size)) + /* Verify that the to be replaced code matches what we expect. */ + if (memcmp(&orig, &old, sizeof(old))) + return -EINVAL; + if (probe_kernel_write((void *) rec->ip, &new, sizeof(new))) return -EPERM; return 0; } diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index d62eee1..132f4c9 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -436,7 +436,9 @@ ENTRY(startup_kdump) # followed by the facility words. #if defined(CONFIG_64BIT) -#if defined(CONFIG_MARCH_ZEC12) +#if defined(CONFIG_MARCH_Z13) + .long 3, 0xc100eff2, 0xf46ce800, 0x00400000 +#elif defined(CONFIG_MARCH_ZEC12) .long 3, 0xc100eff2, 0xf46ce800, 0x00400000 #elif defined(CONFIG_MARCH_Z196) .long 2, 0xc100eff2, 0xf46c0000 diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 39badb9..5c8651f 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2074,7 +2074,8 @@ static void do_reset_calls(void) u32 dump_prefix_page; -void s390_reset_system(void (*func)(void *), void *data) +void s390_reset_system(void (*fn_pre)(void), + void (*fn_post)(void *), void *data) { struct _lowcore *lc; @@ -2112,7 +2113,11 @@ void s390_reset_system(void (*func)(void *), void *data) /* Store status at absolute zero */ store_status(); + /* Call function before reset */ + if (fn_pre) + fn_pre(); do_reset_calls(); - if (func) - func(data); + /* Call function after reset */ + if (fn_post) + fn_post(data); } diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index b987ab2..830066f 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -22,31 +22,70 @@ struct insn_args { enum jump_label_type type; }; +static void jump_label_make_nop(struct jump_entry *entry, struct insn *insn) +{ + /* brcl 0,0 */ + insn->opcode = 0xc004; + insn->offset = 0; +} + +static void jump_label_make_branch(struct jump_entry *entry, struct insn *insn) +{ + /* brcl 15,offset */ + insn->opcode = 0xc0f4; + insn->offset = (entry->target - entry->code) >> 1; +} + +static void jump_label_bug(struct jump_entry *entry, struct insn *expected, + struct insn *new) +{ + unsigned char *ipc = (unsigned char *)entry->code; + unsigned char *ipe = (unsigned char *)expected; + unsigned char *ipn = (unsigned char *)new; + + pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc); + pr_emerg("Found: %02x %02x %02x %02x %02x %02x\n", + ipc[0], ipc[1], ipc[2], ipc[3], ipc[4], ipc[5]); + pr_emerg("Expected: %02x %02x %02x %02x %02x %02x\n", + ipe[0], ipe[1], ipe[2], ipe[3], ipe[4], ipe[5]); + pr_emerg("New: %02x %02x %02x %02x %02x %02x\n", + ipn[0], ipn[1], ipn[2], ipn[3], ipn[4], ipn[5]); + panic("Corrupted kernel text"); +} + +static struct insn orignop = { + .opcode = 0xc004, + .offset = JUMP_LABEL_NOP_OFFSET >> 1, +}; + static void __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) + enum jump_label_type type, + int init) { - struct insn insn; - int rc; + struct insn old, new; if (type == JUMP_LABEL_ENABLE) { - /* brcl 15,offset */ - insn.opcode = 0xc0f4; - insn.offset = (entry->target - entry->code) >> 1; + jump_label_make_nop(entry, &old); + jump_label_make_branch(entry, &new); } else { - /* brcl 0,0 */ - insn.opcode = 0xc004; - insn.offset = 0; + jump_label_make_branch(entry, &old); + jump_label_make_nop(entry, &new); } - - rc = probe_kernel_write((void *)entry->code, &insn, JUMP_LABEL_NOP_SIZE); - WARN_ON_ONCE(rc < 0); + if (init) { + if (memcmp((void *)entry->code, &orignop, sizeof(orignop))) + jump_label_bug(entry, &orignop, &new); + } else { + if (memcmp((void *)entry->code, &old, sizeof(old))) + jump_label_bug(entry, &old, &new); + } + probe_kernel_write((void *)entry->code, &new, sizeof(new)); } static int __sm_arch_jump_label_transform(void *data) { struct insn_args *args = data; - __jump_label_transform(args->entry, args->type); + __jump_label_transform(args->entry, args->type, 0); return 0; } @@ -64,7 +103,7 @@ void arch_jump_label_transform(struct jump_entry *entry, void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { - __jump_label_transform(entry, type); + __jump_label_transform(entry, type, 1); } #endif diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 1e4c710..f516edc 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -69,7 +69,8 @@ static void copy_instruction(struct kprobe *p) /* * If kprobes patches the instruction that is morphed by * ftrace make sure that kprobes always sees the branch - * "jg .+24" that skips the mcount block + * "jg .+24" that skips the mcount block or the "brcl 0,0" + * in case of hotpatch. */ ftrace_generate_nop_insn((struct ftrace_insn *)p->ainsn.insn); p->ainsn.is_ftrace_insn = 1; diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 4685337..fb0901e 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -103,21 +103,18 @@ static int __init machine_kdump_pm_init(void) return 0; } arch_initcall(machine_kdump_pm_init); -#endif /* * Start kdump: We expect here that a store status has been done on our CPU */ static void __do_machine_kdump(void *image) { -#ifdef CONFIG_CRASH_DUMP int (*start_kdump)(int) = (void *)((struct kimage *) image)->start; - setup_regs(); __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); start_kdump(1); -#endif } +#endif /* * Check if kdump checksums are valid: We call purgatory with parameter "0" @@ -249,18 +246,18 @@ static void __do_machine_kexec(void *data) */ static void __machine_kexec(void *data) { - struct kimage *image = data; - __arch_local_irq_stosm(0x04); /* enable DAT */ pfault_fini(); tracing_off(); debug_locks_off(); - if (image->type == KEXEC_TYPE_CRASH) { +#ifdef CONFIG_CRASH_DUMP + if (((struct kimage *) data)->type == KEXEC_TYPE_CRASH) { + lgr_info_log(); - s390_reset_system(__do_machine_kdump, data); - } else { - s390_reset_system(__do_machine_kexec, data); - } + s390_reset_system(setup_regs, __do_machine_kdump, data); + } else +#endif + s390_reset_system(NULL, __do_machine_kexec, data); disabled_wait((unsigned long) __builtin_return_address(0)); } diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index b6dfc5b..e499370 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -27,7 +27,9 @@ ENTRY(ftrace_caller) .globl ftrace_regs_caller .set ftrace_regs_caller,ftrace_caller lgr %r1,%r15 +#ifndef CC_USING_HOTPATCH aghi %r0,MCOUNT_RETURN_FIXUP +#endif aghi %r15,-STACK_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 409d152..2ca9586 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, NUMA_NO_NODE, + GFP_KERNEL, PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); } #endif @@ -436,6 +436,7 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { + jump_label_apply_nops(me); vfree(me->arch.syminfo); me->arch.syminfo = NULL; return 0; diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index c3f8d15..e6a1578 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1415,7 +1415,7 @@ 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, NULL, }; @@ -1606,8 +1606,11 @@ static int __init init_cpum_sampling_pmu(void) return -EINVAL; } - if (si.ad) + if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); + cpumsf_pmu_events_attr[1] = + CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); + } sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80); if (!sfdbg) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index aa7a839..13fc097 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -79,6 +79,14 @@ void release_thread(struct task_struct *dead_task) { } +#ifdef CONFIG_64BIT +void arch_release_task_struct(struct task_struct *tsk) +{ + if (tsk->thread.vxrs) + kfree(tsk->thread.vxrs); +} +#endif + int copy_thread(unsigned long clone_flags, unsigned long new_stackp, unsigned long arg, struct task_struct *p) { @@ -243,13 +251,3 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) 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; - - if (!(current->flags & PF_RANDOMIZE)) - return base; - 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 dbdd33e..dc488e1 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -8,16 +8,24 @@ #include <linux/kernel.h> #include <linux/init.h> -#include <linux/smp.h> #include <linux/seq_file.h> #include <linux/delay.h> #include <linux/cpu.h> #include <asm/elf.h> #include <asm/lowcore.h> #include <asm/param.h> +#include <asm/smp.h> static DEFINE_PER_CPU(struct cpuid, cpu_id); +void notrace cpu_relax(void) +{ + if (!smp_cpu_mtid && MACHINE_HAS_DIAG44) + asm volatile("diag 0,0,0x44"); + barrier(); +} +EXPORT_SYMBOL(cpu_relax); + /* * cpu_init - initializes state that is per-CPU. */ diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index a41f2c9..7e77e03 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -294,7 +294,8 @@ ENTRY(_sclp_print_early) #ifdef CONFIG_64BIT tm LC_AR_MODE_ID,1 jno .Lesa3 - lmh %r6,%r15,96(%r15) # store upper register halves + lgfr %r2,%r2 # sign extend return value + lmh %r6,%r15,96(%r15) # restore upper register halves ahi %r15,80 .Lesa3: #endif diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 4e532c6..a5ea8bc 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -810,6 +810,9 @@ static void __init setup_hwcaps(void) case 0x2828: strcpy(elf_platform, "zEC12"); break; + case 0x2964: + strcpy(elf_platform, "z13"); + break; } } @@ -906,7 +909,6 @@ void __init setup_arch(char **cmdline_p) setup_lowcore(); smp_fill_possible_mask(); cpu_init(); - s390_init_cpu_topology(); /* * Setup capabilities (ELF_HWCAP & ELF_PLATFORM). diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 6a2ac25..b3ae6f7 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -162,7 +162,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) _sigregs user_sregs; /* Alwys make any pending restarted system call return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; + current->restart_block.fn = do_no_restart_syscall; if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs))) return -EFAULT; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 0b499f5..db8f1115 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -59,21 +59,41 @@ enum { CPU_STATE_CONFIGURED, }; +static DEFINE_PER_CPU(struct cpu *, cpu_device); + struct pcpu { - 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 */ unsigned long ec_mask; /* bit mask for ec_xxx functions */ - int state; /* physical cpu state */ - int polarization; /* physical polarization */ + signed char state; /* physical cpu state */ + signed char polarization; /* physical polarization */ u16 address; /* physical cpu address */ }; static u8 boot_cpu_type; -static u16 boot_cpu_address; static struct pcpu pcpu_devices[NR_CPUS]; +unsigned int smp_cpu_mt_shift; +EXPORT_SYMBOL(smp_cpu_mt_shift); + +unsigned int smp_cpu_mtid; +EXPORT_SYMBOL(smp_cpu_mtid); + +static unsigned int smp_max_threads __initdata = -1U; + +static int __init early_nosmt(char *s) +{ + smp_max_threads = 1; + return 0; +} +early_param("nosmt", early_nosmt); + +static int __init early_smt(char *s) +{ + get_option(&s, &smp_max_threads); + return 0; +} +early_param("smt", early_smt); + /* * The smp_cpu_state_mutex must be held when changing the state or polarization * member of a pcpu data structure within the pcpu_devices arreay. @@ -132,7 +152,7 @@ static inline int pcpu_running(struct pcpu *pcpu) /* * Find struct pcpu by cpu address. */ -static struct pcpu *pcpu_find_address(const struct cpumask *mask, int address) +static struct pcpu *pcpu_find_address(const struct cpumask *mask, u16 address) { int cpu; @@ -152,25 +172,30 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit) pcpu_sigp_retry(pcpu, order, 0); } +#define ASYNC_FRAME_OFFSET (ASYNC_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE) +#define PANIC_FRAME_OFFSET (PAGE_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE) + static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) { + unsigned long async_stack, panic_stack; struct _lowcore *lc; if (pcpu != &pcpu_devices[0]) { pcpu->lowcore = (struct _lowcore *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); - pcpu->async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); - pcpu->panic_stack = __get_free_page(GFP_KERNEL); - if (!pcpu->lowcore || !pcpu->panic_stack || !pcpu->async_stack) + async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER); + panic_stack = __get_free_page(GFP_KERNEL); + if (!pcpu->lowcore || !panic_stack || !async_stack) goto out; + } else { + async_stack = pcpu->lowcore->async_stack - ASYNC_FRAME_OFFSET; + panic_stack = pcpu->lowcore->panic_stack - PANIC_FRAME_OFFSET; } lc = pcpu->lowcore; memcpy(lc, &S390_lowcore, 512); memset((char *) lc + 512, 0, sizeof(*lc) - 512); - 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->async_stack = async_stack + ASYNC_FRAME_OFFSET; + lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET; lc->cpu_nr = cpu; lc->spinlock_lockval = arch_spin_lockval(cpu); #ifndef CONFIG_64BIT @@ -191,8 +216,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) return 0; out: if (pcpu != &pcpu_devices[0]) { - free_page(pcpu->panic_stack); - free_pages(pcpu->async_stack, ASYNC_ORDER); + free_page(panic_stack); + free_pages(async_stack, ASYNC_ORDER); free_pages((unsigned long) pcpu->lowcore, LC_ORDER); } return -ENOMEM; @@ -214,11 +239,11 @@ static void pcpu_free_lowcore(struct pcpu *pcpu) #else vdso_free_per_cpu(pcpu->lowcore); #endif - if (pcpu != &pcpu_devices[0]) { - free_page(pcpu->panic_stack); - free_pages(pcpu->async_stack, ASYNC_ORDER); - free_pages((unsigned long) pcpu->lowcore, LC_ORDER); - } + if (pcpu == &pcpu_devices[0]) + return; + free_page(pcpu->lowcore->panic_stack-PANIC_FRAME_OFFSET); + free_pages(pcpu->lowcore->async_stack-ASYNC_FRAME_OFFSET, ASYNC_ORDER); + free_pages((unsigned long) pcpu->lowcore, LC_ORDER); } #endif /* CONFIG_HOTPLUG_CPU */ @@ -299,6 +324,32 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), } /* + * Enable additional logical cpus for multi-threading. + */ +static int pcpu_set_smt(unsigned int mtid) +{ + register unsigned long reg1 asm ("1") = (unsigned long) mtid; + int cc; + + if (smp_cpu_mtid == mtid) + return 0; + asm volatile( + " sigp %1,0,%2 # sigp set multi-threading\n" + " ipm %0\n" + " srl %0,28\n" + : "=d" (cc) : "d" (reg1), "K" (SIGP_SET_MULTI_THREADING) + : "cc"); + if (cc == 0) { + smp_cpu_mtid = mtid; + smp_cpu_mt_shift = 0; + while (smp_cpu_mtid >= (1U << smp_cpu_mt_shift)) + smp_cpu_mt_shift++; + pcpu_devices[0].address = stap(); + } + return cc; +} + +/* * Call function on an online CPU. */ void smp_call_online_cpu(void (*func)(void *), void *data) @@ -319,7 +370,8 @@ void smp_call_online_cpu(void (*func)(void *), void *data) void smp_call_ipl_cpu(void (*func)(void *), void *data) { pcpu_delegate(&pcpu_devices[0], func, data, - pcpu_devices->panic_stack + PAGE_SIZE); + pcpu_devices->lowcore->panic_stack - + PANIC_FRAME_OFFSET + PAGE_SIZE); } int smp_find_processor_id(u16 address) @@ -512,22 +564,17 @@ EXPORT_SYMBOL(smp_ctl_clear_bit); #ifdef CONFIG_CRASH_DUMP -static void __init smp_get_save_area(int cpu, u16 address) +static inline void __smp_store_cpu_state(int cpu, u16 address, int is_boot_cpu) { void *lc = pcpu_devices[0].lowcore; struct save_area_ext *sa_ext; unsigned long vx_sa; - if (is_kdump_kernel()) - return; - if (!OLDMEM_BASE && (address == boot_cpu_address || - ipl_info.type != IPL_TYPE_FCP_DUMP)) - return; sa_ext = dump_save_area_create(cpu); if (!sa_ext) panic("could not allocate memory for save area\n"); - if (address == boot_cpu_address) { - /* Copy the registers of the boot cpu. */ + if (is_boot_cpu) { + /* Copy the registers of the boot CPU. */ copy_oldmem_page(1, (void *) &sa_ext->sa, sizeof(sa_ext->sa), SAVE_AREA_BASE - PAGE_SIZE, 0); if (MACHINE_HAS_VX) @@ -548,6 +595,64 @@ static void __init smp_get_save_area(int cpu, u16 address) free_page(vx_sa); } +/* + * Collect CPU state of the previous, crashed system. + * There are four cases: + * 1) standard zfcp dump + * condition: OLDMEM_BASE == NULL && ipl_info.type == IPL_TYPE_FCP_DUMP + * The state for all CPUs except the boot CPU needs to be collected + * with sigp stop-and-store-status. The boot CPU state is located in + * the absolute lowcore of the memory stored in the HSA. The zcore code + * will allocate the save area and copy the boot CPU state from the HSA. + * 2) stand-alone kdump for SCSI (zfcp dump with swapped memory) + * condition: OLDMEM_BASE != NULL && ipl_info.type == IPL_TYPE_FCP_DUMP + * The state for all CPUs except the boot CPU needs to be collected + * with sigp stop-and-store-status. The firmware or the boot-loader + * stored the registers of the boot CPU in the absolute lowcore in the + * memory of the old system. + * 3) kdump and the old kernel did not store the CPU state, + * or stand-alone kdump for DASD + * condition: OLDMEM_BASE != NULL && !is_kdump_kernel() + * The state for all CPUs except the boot CPU needs to be collected + * with sigp stop-and-store-status. The kexec code or the boot-loader + * stored the registers of the boot CPU in the memory of the old system. + * 4) kdump and the old kernel stored the CPU state + * condition: OLDMEM_BASE != NULL && is_kdump_kernel() + * The state of all CPUs is stored in ELF sections in the memory of the + * old system. The ELF sections are picked up by the crash_dump code + * via elfcorehdr_addr. + */ +static void __init smp_store_cpu_states(struct sclp_cpu_info *info) +{ + unsigned int cpu, address, i, j; + int is_boot_cpu; + + if (is_kdump_kernel()) + /* Previous system stored the CPU states. Nothing to do. */ + return; + if (!(OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP)) + /* No previous system present, normal boot. */ + return; + /* Set multi-threading state to the previous system. */ + pcpu_set_smt(sclp_get_mtid_prev()); + /* Collect CPU states. */ + cpu = 0; + for (i = 0; i < info->configured; i++) { + /* Skip CPUs with different CPU type. */ + if (info->has_cpu_type && info->cpu[i].type != boot_cpu_type) + continue; + for (j = 0; j <= smp_cpu_mtid; j++, cpu++) { + address = (info->cpu[i].core_id << smp_cpu_mt_shift) + j; + is_boot_cpu = (address == pcpu_devices[0].address); + if (is_boot_cpu && !OLDMEM_BASE) + /* Skip boot CPU for standard zfcp dump. */ + continue; + /* Get state for this CPu. */ + __smp_store_cpu_state(cpu, address, is_boot_cpu); + } + } +} + int smp_store_status(int cpu) { unsigned long vx_sa; @@ -565,10 +670,6 @@ int smp_store_status(int cpu) return 0; } -#else /* CONFIG_CRASH_DUMP */ - -static inline void smp_get_save_area(int cpu, u16 address) { } - #endif /* CONFIG_CRASH_DUMP */ void smp_cpu_set_polarization(int cpu, int val) @@ -590,11 +691,13 @@ static struct sclp_cpu_info *smp_get_cpu_info(void) info = kzalloc(sizeof(*info), GFP_KERNEL); if (info && (use_sigp_detection || sclp_get_cpu_info(info))) { use_sigp_detection = 1; - for (address = 0; address <= MAX_CPU_ADDRESS; address++) { + for (address = 0; address <= MAX_CPU_ADDRESS; + address += (1U << smp_cpu_mt_shift)) { if (__pcpu_sigp_relax(address, SIGP_SENSE, 0, NULL) == SIGP_CC_NOT_OPERATIONAL) continue; - info->cpu[info->configured].address = address; + info->cpu[info->configured].core_id = + address >> smp_cpu_mt_shift; info->configured++; } info->combined = info->configured; @@ -608,7 +711,8 @@ static int __smp_rescan_cpus(struct sclp_cpu_info *info, int sysfs_add) { struct pcpu *pcpu; cpumask_t avail; - int cpu, nr, i; + int cpu, nr, i, j; + u16 address; nr = 0; cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); @@ -616,51 +720,76 @@ static int __smp_rescan_cpus(struct sclp_cpu_info *info, int sysfs_add) for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) { if (info->has_cpu_type && info->cpu[i].type != boot_cpu_type) continue; - if (pcpu_find_address(cpu_present_mask, info->cpu[i].address)) - continue; - pcpu = pcpu_devices + cpu; - pcpu->address = info->cpu[i].address; - pcpu->state = (i >= info->configured) ? - CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - set_cpu_present(cpu, true); - if (sysfs_add && smp_add_present_cpu(cpu) != 0) - set_cpu_present(cpu, false); - else - nr++; - cpu = cpumask_next(cpu, &avail); + address = info->cpu[i].core_id << smp_cpu_mt_shift; + for (j = 0; j <= smp_cpu_mtid; j++) { + if (pcpu_find_address(cpu_present_mask, address + j)) + continue; + pcpu = pcpu_devices + cpu; + pcpu->address = address + j; + pcpu->state = + (cpu >= info->configured*(smp_cpu_mtid + 1)) ? + CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + set_cpu_present(cpu, true); + if (sysfs_add && smp_add_present_cpu(cpu) != 0) + set_cpu_present(cpu, false); + else + nr++; + cpu = cpumask_next(cpu, &avail); + if (cpu >= nr_cpu_ids) + break; + } } return nr; } static void __init smp_detect_cpus(void) { - unsigned int cpu, c_cpus, s_cpus; + unsigned int cpu, mtid, c_cpus, s_cpus; struct sclp_cpu_info *info; + u16 address; + /* Get CPU information */ info = smp_get_cpu_info(); if (!info) panic("smp_detect_cpus failed to allocate memory\n"); + + /* Find boot CPU type */ if (info->has_cpu_type) { - for (cpu = 0; cpu < info->combined; cpu++) { - if (info->cpu[cpu].address != boot_cpu_address) - continue; - /* The boot cpu dictates the cpu type. */ - boot_cpu_type = info->cpu[cpu].type; - break; - } + address = stap(); + for (cpu = 0; cpu < info->combined; cpu++) + if (info->cpu[cpu].core_id == address) { + /* The boot cpu dictates the cpu type. */ + boot_cpu_type = info->cpu[cpu].type; + break; + } + if (cpu >= info->combined) + panic("Could not find boot CPU type"); } + +#ifdef CONFIG_CRASH_DUMP + /* Collect CPU state of previous system */ + smp_store_cpu_states(info); +#endif + + /* Set multi-threading state for the current system */ + mtid = sclp_get_mtid(boot_cpu_type); + mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1; + pcpu_set_smt(mtid); + + /* Print number of CPUs */ c_cpus = s_cpus = 0; for (cpu = 0; cpu < info->combined; cpu++) { if (info->has_cpu_type && info->cpu[cpu].type != boot_cpu_type) continue; - if (cpu < info->configured) { - smp_get_save_area(c_cpus, info->cpu[cpu].address); - c_cpus++; - } else - s_cpus++; + if (cpu < info->configured) + c_cpus += smp_cpu_mtid + 1; + else + s_cpus += smp_cpu_mtid + 1; } pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus); + + /* Add CPUs present at boot */ get_online_cpus(); __smp_rescan_cpus(info, 0); put_online_cpus(); @@ -696,12 +825,23 @@ static void smp_start_secondary(void *cpuvoid) int __cpu_up(unsigned int cpu, struct task_struct *tidle) { struct pcpu *pcpu; - int rc; + int base, i, rc; pcpu = pcpu_devices + cpu; if (pcpu->state != CPU_STATE_CONFIGURED) return -EIO; - if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) != + base = cpu - (cpu % (smp_cpu_mtid + 1)); + for (i = 0; i <= smp_cpu_mtid; i++) { + if (base + i < nr_cpu_ids) + if (cpu_online(base + i)) + break; + } + /* + * If this is the first CPU of the core to get online + * do an initial CPU reset. + */ + if (i > smp_cpu_mtid && + pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) != SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; @@ -774,7 +914,8 @@ void __init smp_fill_possible_mask(void) { unsigned int possible, sclp, cpu; - sclp = sclp_get_max_cpu() ?: nr_cpu_ids; + sclp = min(smp_max_threads, sclp_get_mtid_max() + 1); + sclp = sclp_get_max_cpu()*sclp ?: nr_cpu_ids; possible = setup_possible_cpus ?: nr_cpu_ids; possible = min(possible, sclp); for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++) @@ -796,14 +937,9 @@ void __init smp_prepare_boot_cpu(void) { struct pcpu *pcpu = pcpu_devices; - boot_cpu_address = stap(); pcpu->state = CPU_STATE_CONFIGURED; - pcpu->address = boot_cpu_address; + pcpu->address = stap(); pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix(); - 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); @@ -848,7 +984,7 @@ static ssize_t cpu_configure_store(struct device *dev, const char *buf, size_t count) { struct pcpu *pcpu; - int cpu, val, rc; + int cpu, val, rc, i; char delim; if (sscanf(buf, "%d %c", &val, &delim) != 1) @@ -860,29 +996,43 @@ static ssize_t cpu_configure_store(struct device *dev, rc = -EBUSY; /* disallow configuration changes of online cpus and cpu 0 */ cpu = dev->id; - if (cpu_online(cpu) || cpu == 0) + cpu -= cpu % (smp_cpu_mtid + 1); + if (cpu == 0) goto out; + for (i = 0; i <= smp_cpu_mtid; i++) + if (cpu_online(cpu + i)) + goto out; pcpu = pcpu_devices + cpu; rc = 0; switch (val) { case 0: if (pcpu->state != CPU_STATE_CONFIGURED) break; - rc = sclp_cpu_deconfigure(pcpu->address); + rc = sclp_cpu_deconfigure(pcpu->address >> smp_cpu_mt_shift); if (rc) break; - pcpu->state = CPU_STATE_STANDBY; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + for (i = 0; i <= smp_cpu_mtid; i++) { + if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i)) + continue; + pcpu[i].state = CPU_STATE_STANDBY; + smp_cpu_set_polarization(cpu + i, + POLARIZATION_UNKNOWN); + } topology_expect_change(); break; case 1: if (pcpu->state != CPU_STATE_STANDBY) break; - rc = sclp_cpu_configure(pcpu->address); + rc = sclp_cpu_configure(pcpu->address >> smp_cpu_mt_shift); if (rc) break; - pcpu->state = CPU_STATE_CONFIGURED; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + for (i = 0; i <= smp_cpu_mtid; i++) { + if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i)) + continue; + pcpu[i].state = CPU_STATE_CONFIGURED; + smp_cpu_set_polarization(cpu + i, + POLARIZATION_UNKNOWN); + } topology_expect_change(); break; default: @@ -929,8 +1079,7 @@ static int smp_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned int)(long)hcpu; - struct cpu *c = pcpu_devices[cpu].cpu; - struct device *s = &c->dev; + struct device *s = &per_cpu(cpu_device, cpu)->dev; int err = 0; switch (action & ~CPU_TASKS_FROZEN) { @@ -953,7 +1102,7 @@ static int smp_add_present_cpu(int cpu) c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; - pcpu_devices[cpu].cpu = c; + per_cpu(cpu_device, cpu) = c; s = &c->dev; c->hotpluggable = 1; rc = register_cpu(c, cpu); diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index 6b09fdf..ca62946 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -177,6 +177,17 @@ restart_entry: lhi %r1,1 sigp %r1,%r0,SIGP_SET_ARCHITECTURE sam64 +#ifdef CONFIG_SMP + larl %r1,smp_cpu_mt_shift + icm %r1,15,0(%r1) + jz smt_done + llgfr %r1,%r1 +smt_loop: + sigp %r1,%r0,SIGP_SET_MULTI_THREADING + brc 8,smt_done /* accepted */ + brc 2,smt_loop /* busy, try again */ +smt_done: +#endif larl %r1,.Lnew_pgm_check_psw lpswe 0(%r1) pgm_check_entry: diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 811f542..99babea 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -194,6 +194,41 @@ static void stsi_2_2_2(struct seq_file *m, struct sysinfo_2_2_2 *info) seq_printf(m, "LPAR CPUs Reserved: %d\n", info->cpus_reserved); seq_printf(m, "LPAR CPUs Dedicated: %d\n", info->cpus_dedicated); seq_printf(m, "LPAR CPUs Shared: %d\n", info->cpus_shared); + if (info->mt_installed & 0x80) { + seq_printf(m, "LPAR CPUs G-MTID: %d\n", + info->mt_general & 0x1f); + seq_printf(m, "LPAR CPUs S-MTID: %d\n", + info->mt_installed & 0x1f); + seq_printf(m, "LPAR CPUs PS-MTID: %d\n", + info->mt_psmtid & 0x1f); + } +} + +static void print_ext_name(struct seq_file *m, int lvl, + struct sysinfo_3_2_2 *info) +{ + if (info->vm[lvl].ext_name_encoding == 0) + return; + if (info->ext_names[lvl][0] == 0) + return; + switch (info->vm[lvl].ext_name_encoding) { + case 1: /* EBCDIC */ + EBCASC(info->ext_names[lvl], sizeof(info->ext_names[lvl])); + break; + case 2: /* UTF-8 */ + break; + default: + return; + } + seq_printf(m, "VM%02d Extended Name: %-.256s\n", lvl, + info->ext_names[lvl]); +} + +static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info) +{ + if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be))) + return; + seq_printf(m, "VM%02d UUID: %pUb\n", i, &info->vm[i].uuid); } static void stsi_3_2_2(struct seq_file *m, struct sysinfo_3_2_2 *info) @@ -213,6 +248,8 @@ static void stsi_3_2_2(struct seq_file *m, struct sysinfo_3_2_2 *info) seq_printf(m, "VM%02d CPUs Configured: %d\n", i, info->vm[i].cpus_configured); seq_printf(m, "VM%02d CPUs Standby: %d\n", i, info->vm[i].cpus_standby); seq_printf(m, "VM%02d CPUs Reserved: %d\n", i, info->vm[i].cpus_reserved); + print_ext_name(m, i, info); + print_uuid(m, i, info); } } diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 20660dd..170ddd2 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -215,20 +215,20 @@ void update_vsyscall(struct timekeeper *tk) { u64 nsecps; - if (tk->tkr.clock != &clocksource_tod) + if (tk->tkr_mono.clock != &clocksource_tod) return; /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; + vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; + vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; vdso_data->wtom_clock_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec + - + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift); - nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift; + vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); + nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift; while (vdso_data->wtom_clock_nsec >= nsecps) { vdso_data->wtom_clock_nsec -= nsecps; vdso_data->wtom_clock_sec++; @@ -236,7 +236,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->xtime_coarse_sec = tk->xtime_sec; vdso_data->xtime_coarse_nsec = - (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); vdso_data->wtom_coarse_sec = vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec; vdso_data->wtom_coarse_nsec = @@ -246,8 +246,8 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_coarse_sec++; } - vdso_data->tk_mult = tk->tkr.mult; - vdso_data->tk_shift = tk->tkr.shift; + vdso_data->tk_mult = tk->tkr_mono.mult; + vdso_data->tk_shift = tk->tkr_mono.shift; smp_wmb(); ++vdso_data->tb_update_count; } @@ -283,7 +283,7 @@ void __init time_init(void) if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt)) panic("Couldn't request external interrupt 0x1406"); - if (clocksource_register(&clocksource_tod) != 0) + if (__clocksource_register(&clocksource_tod) != 0) panic("Could not register TOD clock source"); /* Enable TOD clock interrupts on the boot cpu. */ diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index b93bed7..14da43b 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -7,14 +7,14 @@ #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/workqueue.h> -#include <linux/bootmem.h> #include <linux/cpuset.h> #include <linux/device.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> -#include <linux/init.h> #include <linux/delay.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> #include <linux/smp.h> #include <linux/mm.h> @@ -42,8 +42,8 @@ static DEFINE_SPINLOCK(topology_lock); static struct mask_info socket_info; static struct mask_info book_info; -struct cpu_topology_s390 cpu_topology[NR_CPUS]; -EXPORT_SYMBOL_GPL(cpu_topology); +DEFINE_PER_CPU(struct cpu_topology_s390, cpu_topology); +EXPORT_PER_CPU_SYMBOL_GPL(cpu_topology); static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) { @@ -59,32 +59,50 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) return mask; } -static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu, +static cpumask_t cpu_thread_map(unsigned int cpu) +{ + cpumask_t mask; + int i; + + cpumask_copy(&mask, cpumask_of(cpu)); + if (!topology_enabled || !MACHINE_HAS_TOPOLOGY) + return mask; + cpu -= cpu % (smp_cpu_mtid + 1); + for (i = 0; i <= smp_cpu_mtid; i++) + if (cpu_present(cpu + i)) + cpumask_set_cpu(cpu + i, &mask); + return mask; +} + +static struct mask_info *add_cpus_to_mask(struct topology_core *tl_core, struct mask_info *book, struct mask_info *socket, int one_socket_per_cpu) { - unsigned int cpu; + unsigned int core; - for_each_set_bit(cpu, &tl_cpu->mask[0], TOPOLOGY_CPU_BITS) { - unsigned int rcpu; - int lcpu; + for_each_set_bit(core, &tl_core->mask[0], TOPOLOGY_CORE_BITS) { + unsigned int rcore; + int lcpu, i; - rcpu = TOPOLOGY_CPU_BITS - 1 - cpu + tl_cpu->origin; - lcpu = smp_find_processor_id(rcpu); + rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin; + lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); if (lcpu < 0) continue; - cpumask_set_cpu(lcpu, &book->mask); - cpu_topology[lcpu].book_id = book->id; - cpumask_set_cpu(lcpu, &socket->mask); - cpu_topology[lcpu].core_id = rcpu; - if (one_socket_per_cpu) { - cpu_topology[lcpu].socket_id = rcpu; - socket = socket->next; - } else { - cpu_topology[lcpu].socket_id = socket->id; + for (i = 0; i <= smp_cpu_mtid; i++) { + per_cpu(cpu_topology, lcpu + i).book_id = book->id; + per_cpu(cpu_topology, lcpu + i).core_id = rcore; + per_cpu(cpu_topology, lcpu + i).thread_id = lcpu + i; + cpumask_set_cpu(lcpu + i, &book->mask); + cpumask_set_cpu(lcpu + i, &socket->mask); + if (one_socket_per_cpu) + per_cpu(cpu_topology, lcpu + i).socket_id = rcore; + else + per_cpu(cpu_topology, lcpu + i).socket_id = socket->id; + smp_cpu_set_polarization(lcpu + i, tl_core->pp); } - smp_cpu_set_polarization(lcpu, tl_cpu->pp); + if (one_socket_per_cpu) + socket = socket->next; } return socket; } @@ -108,7 +126,7 @@ static void clear_masks(void) static union topology_entry *next_tle(union topology_entry *tle) { if (!tle->nl) - return (union topology_entry *)((struct topology_cpu *)tle + 1); + return (union topology_entry *)((struct topology_core *)tle + 1); return (union topology_entry *)((struct topology_container *)tle + 1); } @@ -231,12 +249,14 @@ static void update_cpu_masks(void) spin_lock_irqsave(&topology_lock, flags); for_each_possible_cpu(cpu) { - cpu_topology[cpu].core_mask = cpu_group_map(&socket_info, cpu); - cpu_topology[cpu].book_mask = cpu_group_map(&book_info, cpu); + per_cpu(cpu_topology, cpu).thread_mask = cpu_thread_map(cpu); + per_cpu(cpu_topology, cpu).core_mask = cpu_group_map(&socket_info, cpu); + per_cpu(cpu_topology, cpu).book_mask = cpu_group_map(&book_info, cpu); if (!MACHINE_HAS_TOPOLOGY) { - cpu_topology[cpu].core_id = cpu; - cpu_topology[cpu].socket_id = cpu; - cpu_topology[cpu].book_id = cpu; + per_cpu(cpu_topology, cpu).thread_id = cpu; + per_cpu(cpu_topology, cpu).core_id = cpu; + per_cpu(cpu_topology, cpu).socket_id = cpu; + per_cpu(cpu_topology, cpu).book_id = cpu; } } spin_unlock_irqrestore(&topology_lock, flags); @@ -314,50 +334,6 @@ void topology_expect_change(void) set_topology_timer(); } -static int __init early_parse_topology(char *p) -{ - if (strncmp(p, "off", 3)) - return 0; - topology_enabled = 0; - return 0; -} -early_param("topology", early_parse_topology); - -static void __init alloc_masks(struct sysinfo_15_1_x *info, - struct mask_info *mask, int offset) -{ - int i, nr_masks; - - nr_masks = info->mag[TOPOLOGY_NR_MAG - offset]; - for (i = 0; i < info->mnest - offset; i++) - 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_align( - roundup_pow_of_two(sizeof(struct mask_info)), - roundup_pow_of_two(sizeof(struct mask_info))); - mask = mask->next; - } -} - -void __init s390_init_cpu_topology(void) -{ - struct sysinfo_15_1_x *info; - int i; - - if (!MACHINE_HAS_TOPOLOGY) - return; - tl_info = alloc_bootmem_pages(PAGE_SIZE); - info = tl_info; - store_topology(info); - pr_info("The CPU configuration topology of the machine is:"); - for (i = 0; i < TOPOLOGY_NR_MAG; i++) - printk(KERN_CONT " %d", info->mag[i]); - printk(KERN_CONT " / %d\n", info->mnest); - alloc_masks(info, &socket_info, 1); - alloc_masks(info, &book_info, 2); -} - static int cpu_management; static ssize_t dispatching_show(struct device *dev, @@ -445,23 +421,75 @@ int topology_cpu_init(struct cpu *cpu) return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group); } +const struct cpumask *cpu_thread_mask(int cpu) +{ + return &per_cpu(cpu_topology, cpu).thread_mask; +} + + const struct cpumask *cpu_coregroup_mask(int cpu) { - return &cpu_topology[cpu].core_mask; + return &per_cpu(cpu_topology, cpu).core_mask; } static const struct cpumask *cpu_book_mask(int cpu) { - return &cpu_topology[cpu].book_mask; + return &per_cpu(cpu_topology, cpu).book_mask; +} + +static int __init early_parse_topology(char *p) +{ + if (strncmp(p, "off", 3)) + return 0; + topology_enabled = 0; + return 0; } +early_param("topology", early_parse_topology); static struct sched_domain_topology_level s390_topology[] = { + { cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, { 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 void __init alloc_masks(struct sysinfo_15_1_x *info, + struct mask_info *mask, int offset) +{ + int i, nr_masks; + + nr_masks = info->mag[TOPOLOGY_NR_MAG - offset]; + for (i = 0; i < info->mnest - offset; i++) + 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 = kzalloc(sizeof(*mask->next), GFP_KERNEL); + mask = mask->next; + } +} + +static int __init s390_topology_init(void) +{ + struct sysinfo_15_1_x *info; + int i; + + if (!MACHINE_HAS_TOPOLOGY) + return 0; + tl_info = (struct sysinfo_15_1_x *)__get_free_page(GFP_KERNEL); + info = tl_info; + store_topology(info); + pr_info("The CPU configuration topology of the machine is:"); + for (i = 0; i < TOPOLOGY_NR_MAG; i++) + printk(KERN_CONT " %d", info->mag[i]); + printk(KERN_CONT " / %d\n", info->mnest); + alloc_masks(info, &socket_info, 1); + alloc_masks(info, &book_info, 2); + set_sched_topology(s390_topology); + return 0; +} +early_initcall(s390_topology_init); + static int __init topology_init(void) { if (MACHINE_HAS_TOPOLOGY) @@ -471,10 +499,3 @@ static int __init topology_init(void) return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); - -static int __init early_topology_init(void) -{ - set_sched_topology(s390_topology); - return 0; -} -early_initcall(early_topology_init); diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S index 7699e73..61541fb 100644 --- a/arch/s390/kernel/vdso64/clock_gettime.S +++ b/arch/s390/kernel/vdso64/clock_gettime.S @@ -25,9 +25,7 @@ __kernel_clock_gettime: je 4f cghi %r2,__CLOCK_REALTIME je 5f - cghi %r2,__CLOCK_THREAD_CPUTIME_ID - je 9f - cghi %r2,-2 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ + cghi %r2,-3 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ je 9f cghi %r2,__CLOCK_MONOTONIC_COARSE je 3f @@ -106,7 +104,7 @@ __kernel_clock_gettime: aghi %r15,16 br %r14 - /* CLOCK_THREAD_CPUTIME_ID for this thread */ + /* CPUCLOCK_VIRT for this thread */ 9: icm %r0,15,__VDSO_ECTG_OK(%r5) jz 12f ear %r2,%a4 diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index e34122e5..e53d359 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -15,6 +15,8 @@ #include <asm/cputime.h> #include <asm/vtimer.h> #include <asm/vtime.h> +#include <asm/cpu_mf.h> +#include <asm/smp.h> static void virt_timer_expire(void); @@ -23,6 +25,10 @@ static DEFINE_SPINLOCK(virt_timer_lock); static atomic64_t virt_timer_current; static atomic64_t virt_timer_elapsed; +static DEFINE_PER_CPU(u64, mt_cycles[32]); +static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 }; +static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 }; + static inline u64 get_vtimer(void) { u64 timer; @@ -61,6 +67,8 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) { struct thread_info *ti = task_thread_info(tsk); u64 timer, clock, user, system, steal; + u64 user_scaled, system_scaled; + int i; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; @@ -76,15 +84,49 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; + /* Do MT utilization calculation */ + if (smp_cpu_mtid) { + u64 cycles_new[32], *cycles_old; + u64 delta, mult, div; + + cycles_old = this_cpu_ptr(mt_cycles); + if (stcctm5(smp_cpu_mtid + 1, cycles_new) < 2) { + mult = div = 0; + for (i = 0; i <= smp_cpu_mtid; i++) { + delta = cycles_new[i] - cycles_old[i]; + mult += delta; + div += (i + 1) * delta; + } + if (mult > 0) { + /* Update scaling factor */ + __this_cpu_write(mt_scaling_mult, mult); + __this_cpu_write(mt_scaling_div, div); + memcpy(cycles_old, cycles_new, + sizeof(u64) * (smp_cpu_mtid + 1)); + } + } + } + user = S390_lowcore.user_timer - ti->user_timer; S390_lowcore.steal_timer -= user; ti->user_timer = S390_lowcore.user_timer; - account_user_time(tsk, user, user); system = S390_lowcore.system_timer - ti->system_timer; S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; - account_system_time(tsk, hardirq_offset, system, system); + + user_scaled = user; + system_scaled = system; + /* Do MT utilization scaling */ + if (smp_cpu_mtid) { + u64 mult = __this_cpu_read(mt_scaling_mult); + u64 div = __this_cpu_read(mt_scaling_div); + + user_scaled = (user_scaled * mult) / div; + system_scaled = (system_scaled * mult) / div; + } + account_user_time(tsk, user, user_scaled); + account_system_time(tsk, hardirq_offset, system, system_scaled); steal = S390_lowcore.steal_timer; if ((s64) steal > 0) { @@ -126,7 +168,7 @@ void vtime_account_user(struct task_struct *tsk) void vtime_account_irq_enter(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - u64 timer, system; + u64 timer, system, system_scaled; timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); @@ -135,7 +177,15 @@ void vtime_account_irq_enter(struct task_struct *tsk) system = S390_lowcore.system_timer - ti->system_timer; S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; - account_system_time(tsk, 0, system, system); + system_scaled = system; + /* Do MT utilization scaling */ + if (smp_cpu_mtid) { + u64 mult = __this_cpu_read(mt_scaling_mult); + u64 div = __this_cpu_read(mt_scaling_div); + + system_scaled = (system_scaled * mult) / div; + } + account_system_time(tsk, 0, system, system_scaled); virt_timer_forward(system); } diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 9254aff..fc7ec95 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) 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)); + rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], 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) @@ -213,7 +213,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * - 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, + ret = kvm_io_bus_write_cookie(vcpu, 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]); @@ -230,7 +230,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) { - int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff; + int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 8a1be90..a7559f7 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -10,6 +10,7 @@ #include <asm/pgtable.h> #include "kvm-s390.h" #include "gaccess.h" +#include <asm/switch_to.h> union asce { unsigned long val; @@ -207,6 +208,54 @@ union raddress { unsigned long pfra : 52; /* Page-Frame Real Address */ }; +union alet { + u32 val; + struct { + u32 reserved : 7; + u32 p : 1; + u32 alesn : 8; + u32 alen : 16; + }; +}; + +union ald { + u32 val; + struct { + u32 : 1; + u32 alo : 24; + u32 all : 7; + }; +}; + +struct ale { + unsigned long i : 1; /* ALEN-Invalid Bit */ + unsigned long : 5; + unsigned long fo : 1; /* Fetch-Only Bit */ + unsigned long p : 1; /* Private Bit */ + unsigned long alesn : 8; /* Access-List-Entry Sequence Number */ + unsigned long aleax : 16; /* Access-List-Entry Authorization Index */ + unsigned long : 32; + unsigned long : 1; + unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */ + unsigned long : 6; + unsigned long astesn : 32; /* ASTE Sequence Number */ +} __packed; + +struct aste { + unsigned long i : 1; /* ASX-Invalid Bit */ + unsigned long ato : 29; /* Authority-Table Origin */ + unsigned long : 1; + unsigned long b : 1; /* Base-Space Bit */ + unsigned long ax : 16; /* Authorization Index */ + unsigned long atl : 12; /* Authority-Table Length */ + unsigned long : 2; + unsigned long ca : 1; /* Controlled-ASN Bit */ + unsigned long ra : 1; /* Reusable-ASN Bit */ + unsigned long asce : 64; /* Address-Space-Control Element */ + unsigned long ald : 32; + unsigned long astesn : 32; + /* .. more fields there */ +} __packed; int ipte_lock_held(struct kvm_vcpu *vcpu) { @@ -307,15 +356,157 @@ void ipte_unlock(struct kvm_vcpu *vcpu) ipte_unlock_simple(vcpu); } -static unsigned long get_vcpu_asce(struct kvm_vcpu *vcpu) +static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, + int write) +{ + union alet alet; + struct ale ale; + struct aste aste; + unsigned long ald_addr, authority_table_addr; + union ald ald; + int eax, rc; + u8 authority_table; + + if (ar >= NUM_ACRS) + return -EINVAL; + + save_access_regs(vcpu->run->s.regs.acrs); + alet.val = vcpu->run->s.regs.acrs[ar]; + + if (ar == 0 || alet.val == 0) { + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; + } else if (alet.val == 1) { + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; + } + + if (alet.reserved) + return PGM_ALET_SPECIFICATION; + + if (alet.p) + ald_addr = vcpu->arch.sie_block->gcr[5]; + else + ald_addr = vcpu->arch.sie_block->gcr[2]; + ald_addr &= 0x7fffffc0; + + rc = read_guest_real(vcpu, ald_addr + 16, &ald.val, sizeof(union ald)); + if (rc) + return rc; + + if (alet.alen / 8 > ald.all) + return PGM_ALEN_TRANSLATION; + + if (0x7fffffff - ald.alo * 128 < alet.alen * 16) + return PGM_ADDRESSING; + + rc = read_guest_real(vcpu, ald.alo * 128 + alet.alen * 16, &ale, + sizeof(struct ale)); + if (rc) + return rc; + + if (ale.i == 1) + return PGM_ALEN_TRANSLATION; + if (ale.alesn != alet.alesn) + return PGM_ALE_SEQUENCE; + + rc = read_guest_real(vcpu, ale.asteo * 64, &aste, sizeof(struct aste)); + if (rc) + return rc; + + if (aste.i) + return PGM_ASTE_VALIDITY; + if (aste.astesn != ale.astesn) + return PGM_ASTE_SEQUENCE; + + if (ale.p == 1) { + eax = (vcpu->arch.sie_block->gcr[8] >> 16) & 0xffff; + if (ale.aleax != eax) { + if (eax / 16 > aste.atl) + return PGM_EXTENDED_AUTHORITY; + + authority_table_addr = aste.ato * 4 + eax / 4; + + rc = read_guest_real(vcpu, authority_table_addr, + &authority_table, + sizeof(u8)); + if (rc) + return rc; + + if ((authority_table & (0x40 >> ((eax & 3) * 2))) == 0) + return PGM_EXTENDED_AUTHORITY; + } + } + + if (ale.fo == 1 && write) + return PGM_PROTECTION; + + asce->val = aste.asce; + return 0; +} + +struct trans_exc_code_bits { + unsigned long addr : 52; /* Translation-exception Address */ + unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ + unsigned long : 6; + unsigned long b60 : 1; + 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 get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, + ar_t ar, int write) { + int rc; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + struct trans_exc_code_bits *tec_bits; + + 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; + + if (!psw_bits(*psw).t) { + asce->val = 0; + asce->r = 1; + return 0; + } + switch (psw_bits(vcpu->arch.sie_block->gpsw).as) { case PSW_AS_PRIMARY: - return vcpu->arch.sie_block->gcr[1]; + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; case PSW_AS_SECONDARY: - return vcpu->arch.sie_block->gcr[7]; + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; case PSW_AS_HOME: - return vcpu->arch.sie_block->gcr[13]; + asce->val = vcpu->arch.sie_block->gcr[13]; + return 0; + case PSW_AS_ACCREG: + rc = ar_translation(vcpu, asce, ar, write); + switch (rc) { + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_ASTE_SEQUENCE: + case PGM_EXTENDED_AUTHORITY: + vcpu->arch.pgm.exc_access_id = ar; + break; + case PGM_PROTECTION: + tec_bits->b60 = 1; + tec_bits->b61 = 1; + break; + } + if (rc > 0) + pgm->code = rc; + return rc; } return 0; } @@ -330,10 +521,11 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * @vcpu: virtual cpu * @gva: guest virtual address * @gpa: points to where guest physical (absolute) address should be stored + * @asce: effective asce * @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. + * of dynamic address translation as specified by the architecture. * If the resulting absolute address is not available in the configuration * an addressing exception is indicated and @gpa will not be changed. * @@ -345,7 +537,8 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * by the architecture */ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, - unsigned long *gpa, int write) + unsigned long *gpa, const union asce asce, + int write) { union vaddress vaddr = {.addr = gva}; union raddress raddr = {.addr = gva}; @@ -354,12 +547,10 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, 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); + edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8); + edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78); if (asce.r) goto real_address; ptr = asce.origin * 4096; @@ -506,48 +697,30 @@ static inline int is_low_address(unsigned long ga) return (ga & ~0x11fful) == 0; } -static int low_address_protection_enabled(struct kvm_vcpu *vcpu) +static int low_address_protection_enabled(struct kvm_vcpu *vcpu, + const union asce asce) { 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) + const union asce asce, 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); + lap_enabled = low_address_protection_enabled(vcpu, asce); while (nr_pages) { ga = kvm_s390_logical_to_effective(vcpu, ga); tec_bits->addr = ga >> PAGE_SHIFT; @@ -557,7 +730,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, } ga &= PAGE_MASK; if (psw_bits(*psw).t) { - rc = guest_translate(vcpu, ga, pages, write); + rc = guest_translate(vcpu, ga, pages, asce, write); if (rc < 0) return rc; if (rc == PGM_PROTECTION) @@ -578,7 +751,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, return 0; } -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len, int write) { psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -591,20 +764,19 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, 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; + rc = get_vcpu_asce(vcpu, &asce, ar, write); + if (rc) + return rc; 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); + rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write); for (idx = 0; idx < nr_pages && !rc; idx++) { gpa = *(pages + idx) + (ga & ~PAGE_MASK); _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); @@ -652,7 +824,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * 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, +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, unsigned long *gpa, int write) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; @@ -661,26 +833,21 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, 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; + rc = get_vcpu_asce(vcpu, &asce, ar, write); tec->addr = gva >> PAGE_SHIFT; - if (is_low_address(gva) && low_address_protection_enabled(vcpu)) { + if (rc) + return rc; + if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) { 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); + rc = guest_translate(vcpu, gva, gpa, asce, write); if (rc > 0) { if (rc == PGM_PROTECTION) tec->b61 = 1; @@ -697,28 +864,51 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, } /** - * kvm_s390_check_low_addr_protection - check for low-address protection - * @ga: Guest address + * check_gva_range - test a range of guest virtual addresses for accessibility + */ +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write) +{ + unsigned long gpa; + unsigned long currlen; + int rc = 0; + + ipte_lock(vcpu); + while (length > 0 && !rc) { + currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE)); + rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write); + gva += currlen; + length -= currlen; + } + ipte_unlock(vcpu); + + return rc; +} + +/** + * kvm_s390_check_low_addr_prot_real - check for low-address protection + * @gra: Guest real 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) +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; struct trans_exc_code_bits *tec_bits; + union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; - if (!is_low_address(ga) || !low_address_protection_enabled(vcpu)) + if (!ctlreg0.lap || !is_low_address(gra)) 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; + tec_bits->addr = gra >> PAGE_SHIFT; pgm->code = PGM_PROTECTION; return pgm->code; diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 0149cf1..ef03726 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -156,9 +156,11 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, } int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, - unsigned long *gpa, int write); + ar_t ar, unsigned long *gpa, int write); +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write); -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len, int write); int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, @@ -168,6 +170,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * write_guest - copy data from kernel space to guest space * @vcpu: virtual cpu * @ga: guest address + * @ar: access register * @data: source address in kernel space * @len: number of bytes to copy * @@ -176,8 +179,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * 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). + * Primary, secondary, home space or access register mode. * 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. @@ -210,16 +212,17 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * 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, +int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, data, len, 1); + return access_guest(vcpu, ga, ar, data, len, 1); } /** * read_guest - copy data from guest space to kernel space * @vcpu: virtual cpu * @ga: guest address + * @ar: access register * @data: destination address in kernel space * @len: number of bytes to copy * @@ -229,10 +232,10 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, * 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, +int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, data, len, 0); + return access_guest(vcpu, ga, ar, data, len, 0); } /** @@ -330,6 +333,6 @@ int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, 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); +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra); #endif /* __KVM_S390_GACCESS_H */ diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 3e8d409..e97b345 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -191,8 +191,8 @@ static int __import_wp_info(struct kvm_vcpu *vcpu, 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); + ret = read_guest_abs(vcpu, wp_info->phys_addr, wp_info->old_data, + wp_info->len); if (ret) { kfree(wp_info->old_data); wp_info->old_data = NULL; @@ -362,8 +362,8 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu) 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 (!read_guest_abs(vcpu, wp_info->phys_addr, temp, + wp_info->len)) { if (memcmp(temp, wp_info->old_data, wp_info->len)) { kfree(temp); return wp_info; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 81c77ab..9e3779e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -68,18 +68,27 @@ static int handle_noop(struct kvm_vcpu *vcpu) static int handle_stop(struct kvm_vcpu *vcpu) { + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; int rc = 0; - unsigned int action_bits; + uint8_t flags, stop_pending; vcpu->stat.exit_stop_request++; - trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits); - action_bits = vcpu->arch.local_int.action_bits; + /* delay the stop if any non-stop irq is pending */ + if (kvm_s390_vcpu_has_irq(vcpu, 1)) + return 0; + + /* avoid races with the injection/SIGP STOP code */ + spin_lock(&li->lock); + flags = li->irq.stop.flags; + stop_pending = kvm_s390_is_stop_irq_pending(vcpu); + spin_unlock(&li->lock); - if (!(action_bits & ACTION_STOP_ON_STOP)) + trace_kvm_s390_stop_request(stop_pending, flags); + if (!stop_pending) return 0; - if (action_bits & ACTION_STORE_ON_STOP) { + if (flags & KVM_S390_STOP_FLAG_STORE_STATUS) { rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_NOADDR); if (rc) @@ -156,6 +165,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu, pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn; pgm_info->mon_code = vcpu->arch.sie_block->tecmc; break; + case PGM_VECTOR_PROCESSING: case PGM_DATA: pgm_info->data_exc_code = vcpu->arch.sie_block->dxc; break; @@ -279,11 +289,13 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu) 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.u.extcall.code = vcpu->arch.sie_block->extcpuaddr; - break; + rc = kvm_s390_inject_vcpu(vcpu, &irq); + /* ignore if another external call is already pending */ + if (rc == -EBUSY) + return 0; + return rc; default: return -EOPNOTSUPP; } @@ -307,17 +319,19 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) 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 = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2], + reg2, &srcaddr, 0); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); 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 = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1], + reg1, &dstaddr, 1); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); if (rc != 0) return rc; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index f00f31e..9de4726 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1,7 +1,7 @@ /* * handling kvm guest interrupts * - * Copyright IBM Corp. 2008,2014 + * Copyright IBM Corp. 2008, 2015 * * 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) @@ -17,8 +17,12 @@ #include <linux/signal.h> #include <linux/slab.h> #include <linux/bitmap.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> +#include <asm/dis.h> #include <asm/uaccess.h> +#include <asm/sclp.h> +#include <asm/isc.h> #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" @@ -31,11 +35,6 @@ #define PFAULT_DONE 0x0680 #define VIRTIO_PARAM 0x0d00 -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); @@ -71,70 +70,45 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) return 1; } -static u64 int_word_to_isc_bits(u32 int_word) +static int ckc_irq_pending(struct kvm_vcpu *vcpu) { - u8 isc = (int_word & 0x38000000) >> 27; + if (!(vcpu->arch.sie_block->ckc < + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) + return 0; + return ckc_interrupts_enabled(vcpu); +} +static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu) +{ + return !psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x400ul); +} + +static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.sie_block->cputm >> 63) && + cpu_timer_interrupts_enabled(vcpu); +} + +static inline int is_ioirq(unsigned long irq_type) +{ + return ((irq_type >= IRQ_PEND_IO_ISC_0) && + (irq_type <= IRQ_PEND_IO_ISC_7)); +} + +static uint64_t isc_to_isc_bits(int isc) +{ return (0x80 >> isc) << 24; } -static int __must_check __interrupt_is_deliverable(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static inline u8 int_word_to_isc(u32 int_word) { - switch (inti->type) { - case KVM_S390_INT_EXTERNAL_CALL: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) - return 1; - return 0; - case KVM_S390_INT_EMERGENCY: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x4000ul) - return 1; - return 0; - 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] & 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; - if (vcpu->arch.sie_block->gcr[0] & 0x200ul) - return 1; - return 0; - case KVM_S390_PROGRAM_INT: - case KVM_S390_SIGP_STOP: - 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; + return (int_word & 0x38000000) >> 27; +} + +static inline unsigned long pending_floating_irqs(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.float_int.pending_irqs; } static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) @@ -142,12 +116,31 @@ static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) return vcpu->arch.local_int.pending_irqs; } -static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) +static unsigned long disable_iscs(struct kvm_vcpu *vcpu, + unsigned long active_mask) { - unsigned long active_mask = pending_local_irqs(vcpu); + int i; + + for (i = 0; i <= MAX_ISC; i++) + if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i))) + active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i)); + + return active_mask; +} + +static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) +{ + unsigned long active_mask; + + active_mask = pending_local_irqs(vcpu); + active_mask |= pending_floating_irqs(vcpu); if (psw_extint_disabled(vcpu)) active_mask &= ~IRQ_PEND_EXT_MASK; + if (psw_ioint_disabled(vcpu)) + active_mask &= ~IRQ_PEND_IO_MASK; + else + active_mask = disable_iscs(vcpu, active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul)) __clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul)) @@ -156,8 +149,19 @@ static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul)) __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul)) + __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; + if (!(vcpu->arch.sie_block->gcr[14] & + vcpu->kvm->arch.float_int.mchk.cr14)) + __clear_bit(IRQ_PEND_MCHK_REP, &active_mask); + + /* + * STOP irqs will never be actively delivered. They are triggered via + * intercept requests and cleared when the stop intercept is performed. + */ + __clear_bit(IRQ_PEND_SIGP_STOP, &active_mask); return active_mask; } @@ -186,9 +190,6 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) LCTL_CR10 | LCTL_CR11); vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT); } - - if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) - atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags); } static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) @@ -196,6 +197,16 @@ static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags); } +static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) +{ + if (!(pending_floating_irqs(vcpu) & IRQ_PEND_IO_MASK)) + return; + else if (psw_ioint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_IO_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR6; +} + static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) { if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK)) @@ -216,46 +227,23 @@ static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->lctl |= LCTL_CR14; } -/* Set interception request for non-deliverable local interrupts */ -static void set_intercept_indicators_local(struct kvm_vcpu *vcpu) +static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu) { - set_intercept_indicators_ext(vcpu); - set_intercept_indicators_mchk(vcpu); + if (kvm_s390_is_stop_irq_pending(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_STOP_INT); } -static void __set_intercept_indicator(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +/* Set interception request for non-deliverable interrupts */ +static void set_intercept_indicators(struct kvm_vcpu *vcpu) { - switch (inti->type) { - case KVM_S390_INT_SERVICE: - case KVM_S390_INT_PFAULT_DONE: - case KVM_S390_INT_VIRTIO: - if (psw_extint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_EXT_INT); - else - vcpu->arch.sie_block->lctl |= LCTL_CR0; - 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(); - } + set_intercept_indicators_io(vcpu); + set_intercept_indicators_ext(vcpu); + set_intercept_indicators_mchk(vcpu); + set_intercept_indicators_stop(vcpu); } static u16 get_ilc(struct kvm_vcpu *vcpu) { - const unsigned short table[] = { 2, 4, 4, 6 }; - switch (vcpu->arch.sie_block->icptcode) { case ICPT_INST: case ICPT_INSTPROGI: @@ -263,7 +251,7 @@ static u16 get_ilc(struct kvm_vcpu *vcpu) case ICPT_PARTEXEC: case ICPT_IOINST: /* last instruction only stored for these icptcodes */ - return table[vcpu->arch.sie_block->ipa >> 14]; + return insn_length(vcpu->arch.sie_block->ipa >> 8); case ICPT_PROGI: return vcpu->arch.sie_block->pgmilc; default: @@ -339,38 +327,72 @@ static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu) static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) { + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_mchk_info mchk; - int rc; + struct kvm_s390_mchk_info mchk = {}; + unsigned long adtl_status_addr; + int deliver = 0; + int rc = 0; + spin_lock(&fi->lock); spin_lock(&li->lock); - mchk = li->irq.mchk; + if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) || + test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) { + /* + * If there was an exigent machine check pending, then any + * repressible machine checks that might have been pending + * are indicated along with it, so always clear bits for + * repressible and exigent interrupts + */ + mchk = li->irq.mchk; + clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + memset(&li->irq.mchk, 0, sizeof(mchk)); + deliver = 1; + } /* - * If there was an exigent machine check pending, then any repressible - * machine checks that might have been pending are indicated along - * with it, so always clear both bits + * We indicate floating repressible conditions along with + * other pending conditions. Channel Report Pending and Channel + * Subsystem damage are the only two and and are indicated by + * bits in mcic and masked in cr14. */ - clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); - clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); - memset(&li->irq.mchk, 0, sizeof(mchk)); + if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + mchk.mcic |= fi->mchk.mcic; + mchk.cr14 |= fi->mchk.cr14; + memset(&fi->mchk, 0, sizeof(mchk)); + deliver = 1; + } spin_unlock(&li->lock); + spin_unlock(&fi->lock); - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - mchk.mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, - mchk.cr14, mchk.mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, mchk.mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk.failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk.fixed_logout, sizeof(mchk.fixed_logout)); - 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)); + if (deliver) { + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_MCHK, + mchk.cr14, mchk.mcic); + + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_PREFIXED); + rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, + &adtl_status_addr, + sizeof(unsigned long)); + rc |= kvm_s390_vcpu_store_adtl_status(vcpu, + adtl_status_addr); + rc |= put_guest_lc(vcpu, mchk.mcic, + (u64 __user *) __LC_MCCK_CODE); + rc |= put_guest_lc(vcpu, mchk.failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, + &mchk.fixed_logout, + sizeof(mchk.fixed_logout)); + 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)); + } return rc ? -EFAULT : 0; } @@ -392,18 +414,6 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } -static int __must_check __deliver_stop(struct kvm_vcpu *vcpu) -{ - VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop"); - vcpu->stat.deliver_stop_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_SIGP_STOP, - 0, 0); - - __set_cpuflag(vcpu, CPUSTAT_STOP_INT); - clear_bit(IRQ_PEND_SIGP_STOP, &vcpu->arch.local_int.pending_irqs); - return 0; -} - static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -485,7 +495,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_pgm_info pgm_info; - int rc = 0; + int rc = 0, nullifying = false; u16 ilc = get_ilc(vcpu); spin_lock(&li->lock); @@ -510,6 +520,8 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_LX_TRANSLATION: case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: + nullifying = true; + /* fall through */ case PGM_SPACE_SWITCH: rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); @@ -522,6 +534,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_EXTENDED_AUTHORITY: rc = put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); + nullifying = true; break; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: @@ -535,6 +548,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *)__LC_EXC_ACCESS_ID); rc |= put_guest_lc(vcpu, pgm_info.op_access_id, (u8 *)__LC_OP_ACCESS_ID); + nullifying = true; break; case PGM_MONITOR: rc = put_guest_lc(vcpu, pgm_info.mon_class_nr, @@ -542,6 +556,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) rc |= put_guest_lc(vcpu, pgm_info.mon_code, (u64 *)__LC_MON_CODE); break; + case PGM_VECTOR_PROCESSING: case PGM_DATA: rc = put_guest_lc(vcpu, pgm_info.data_exc_code, (u32 *)__LC_DATA_EXC_CODE); @@ -552,6 +567,15 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); break; + case PGM_STACK_FULL: + case PGM_STACK_EMPTY: + case PGM_STACK_SPECIFICATION: + case PGM_STACK_TYPE: + case PGM_STACK_OPERATION: + case PGM_TRACE_TABEL: + case PGM_CRYPTO_OPERATION: + nullifying = true; + break; } if (pgm_info.code & PGM_PER) { @@ -565,7 +589,12 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *) __LC_PER_ACCESS_ID); } + if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST) + kvm_s390_rewind_psw(vcpu, ilc); + rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC); + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea, + (u64 *) __LC_LAST_BREAK); rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_INT_CODE); rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, @@ -575,16 +604,27 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } -static int __must_check __deliver_service(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_service(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + int rc = 0; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + memset(&fi->srv_signal, 0, sizeof(ext)); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", - inti->ext.ext_params); + ext.ext_params); vcpu->stat.deliver_service_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, 0); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); @@ -592,106 +632,146 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu, &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, + rc |= put_guest_lc(vcpu, ext.ext_params, (u32 *)__LC_EXT_PARAMS); + return rc ? -EFAULT : 0; } -static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, - KVM_S390_INT_PFAULT_DONE, 0, - inti->ext.ext_params2); + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT], + struct kvm_s390_interrupt_info, + list); + if (inti) { + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_DONE, 0, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_PFAULT] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_PFAULT])) + clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, PFAULT_DONE, (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); + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_DONE, + (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); + kfree(inti); + } return rc ? -EFAULT : 0; } -static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; - VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx", - inti->ext.ext_params, inti->ext.ext_params2); - vcpu->stat.deliver_virtio_interrupt++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, - inti->ext.ext_params2); + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO], + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, + "interrupt: virtio parm:%x,parm64:%llx", + inti->ext.ext_params, inti->ext.ext_params2); + vcpu->stat.deliver_virtio_interrupt++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + inti->ext.ext_params, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_VIRTIO] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO])) + clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, VIRTIO_PARAM, (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); + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, VIRTIO_PARAM, + (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); + kfree(inti); + } return rc ? -EFAULT : 0; } static int __must_check __deliver_io(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) + unsigned long irq_type) { - int rc; + struct list_head *isc_list; + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_interrupt_info *inti = NULL; + int rc = 0; - 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, - ((__u32)inti->io.subchannel_id << 16) | - inti->io.subchannel_nr, - ((__u64)inti->io.io_int_parm << 32) | - inti->io.io_int_word); - - 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)); - return rc ? -EFAULT : 0; -} + fi = &vcpu->kvm->arch.float_int; -static int __must_check __deliver_mchk_floating(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - struct kvm_s390_mchk_info *mchk = &inti->mchk; - int rc; + spin_lock(&fi->lock); + isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0]; + inti = list_first_entry_or_null(isc_list, + struct kvm_s390_interrupt_info, + list); + if (inti) { + 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, + ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr, + ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + } + if (list_empty(isc_list)) + clear_bit(irq_type, &fi->pending_irqs); + spin_unlock(&fi->lock); + + if (inti) { + 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)); + kfree(inti); + } - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - mchk->mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, - mchk->cr14, mchk->mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, mchk->mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk->failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk->fixed_logout, sizeof(mchk->fixed_logout)); - 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)); return rc ? -EFAULT : 0; } @@ -699,81 +779,49 @@ typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); static const deliver_irq_t deliver_irq_funcs[] = { [IRQ_PEND_MCHK_EX] = __deliver_machine_check, + [IRQ_PEND_MCHK_REP] = __deliver_machine_check, [IRQ_PEND_PROG] = __deliver_prog, [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc, [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer, [IRQ_PEND_RESTART] = __deliver_restart, - [IRQ_PEND_SIGP_STOP] = __deliver_stop, [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, + [IRQ_PEND_EXT_SERVICE] = __deliver_service, + [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, + [IRQ_PEND_VIRTIO] = __deliver_virtio, }; -static int __must_check __deliver_floating_interrupt(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +/* Check whether an external call is pending (deliverable or not) */ +int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { - int rc; - - switch (inti->type) { - case KVM_S390_INT_SERVICE: - rc = __deliver_service(vcpu, inti); - break; - case KVM_S390_INT_PFAULT_DONE: - rc = __deliver_pfault_done(vcpu, inti); - break; - case KVM_S390_INT_VIRTIO: - rc = __deliver_virtio(vcpu, inti); - break; - case KVM_S390_MCHK: - rc = __deliver_mchk_floating(vcpu, inti); - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - rc = __deliver_io(vcpu, inti); - break; - default: - BUG(); - } - - return rc; -} - -/* 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; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_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; + if (!sclp_has_sigpif()) + return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); - return 0; + return (sigp_ctrl & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND); } -int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) { - struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; - struct kvm_s390_interrupt_info *inti; int rc; - rc = !!deliverable_local_irqs(vcpu); - - if ((!rc) && atomic_read(&fi->active)) { - spin_lock(&fi->lock); - list_for_each_entry(inti, &fi->list, list) - if (__interrupt_is_deliverable(vcpu, inti)) { - rc = 1; - break; - } - spin_unlock(&fi->lock); - } + rc = !!deliverable_irqs(vcpu); if (!rc && kvm_cpu_has_pending_timer(vcpu)) rc = 1; - if (!rc && kvm_s390_si_ext_call_pending(vcpu)) + /* external call pending and deliverable */ + if (!rc && kvm_s390_ext_call_pending(vcpu) && + !psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x2000ul)) + rc = 1; + + if (!rc && !exclude_stop && kvm_s390_is_stop_irq_pending(vcpu)) rc = 1; return rc; @@ -781,12 +829,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - 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; + return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu); } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) @@ -804,14 +847,20 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; /* disabled wait */ } - __set_cpu_idle(vcpu); if (!ckc_interrupts_enabled(vcpu)) { VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer"); + __set_cpu_idle(vcpu); goto no_timer; } now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch; sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); + + /* underflow */ + if (vcpu->arch.sie_block->ckc < now) + return 0; + + __set_cpu_idle(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: @@ -820,7 +869,7 @@ no_timer: __unset_cpu_idle(vcpu); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); + hrtimer_cancel(&vcpu->arch.ckc_timer); return 0; } @@ -840,10 +889,20 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer) { struct kvm_vcpu *vcpu; + u64 now, sltime; vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer); - kvm_s390_vcpu_wakeup(vcpu); + now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch; + sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); + /* + * If the monotonic clock runs faster than the tod clock we might be + * woken up too early and have to go back to sleep to avoid deadlocks. + */ + if (vcpu->arch.sie_block->ckc > now && + hrtimer_forward_now(timer, ns_to_ktime(sltime))) + return HRTIMER_RESTART; + kvm_s390_vcpu_wakeup(vcpu); return HRTIMER_NORESTART; } @@ -859,67 +918,51 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) /* clear pending external calls set by sigp interpretation facility */ atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags); - atomic_clear_mask(SIGP_CTRL_C, - &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl); + vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0; } int __must_check kvm_s390_deliver_pending_interrupts(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; deliver_irq_t func; - int deliver; int rc = 0; unsigned long irq_type; - unsigned long deliverable_irqs; + unsigned long irqs; __reset_intercept_indicators(vcpu); /* pending ckc conditions might have been invalidated */ clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); - if (kvm_cpu_has_pending_timer(vcpu)) + if (ckc_irq_pending(vcpu)) set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + /* pending cpu timer conditions might have been invalidated */ + clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + if (cpu_timer_irq_pending(vcpu)) + set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + do { - deliverable_irqs = deliverable_local_irqs(vcpu); + irqs = deliverable_irqs(vcpu); /* bits are in the order of interrupt priority */ - irq_type = find_first_bit(&deliverable_irqs, IRQ_PEND_COUNT); + irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT); if (irq_type == IRQ_PEND_COUNT) break; - func = deliver_irq_funcs[irq_type]; - if (!func) { - WARN_ON_ONCE(func == NULL); - clear_bit(irq_type, &li->pending_irqs); - continue; + if (is_ioirq(irq_type)) { + rc = __deliver_io(vcpu, irq_type); + } else { + func = deliver_irq_funcs[irq_type]; + if (!func) { + WARN_ON_ONCE(func == NULL); + clear_bit(irq_type, &li->pending_irqs); + continue; + } + rc = func(vcpu); } - rc = func(vcpu); - } while (!rc && irq_type != IRQ_PEND_COUNT); - - set_intercept_indicators_local(vcpu); + if (rc) + break; + } while (!rc); - if (!rc && atomic_read(&fi->active)) { - do { - deliver = 0; - spin_lock(&fi->lock); - 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) { - rc = __deliver_floating_interrupt(vcpu, inti); - kfree(inti); - } - } while (!rc && deliver); - } + set_intercept_indicators(vcpu); return rc; } @@ -984,18 +1027,43 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) return 0; } -int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id) +{ + unsigned char new_val, old_val; + uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + + new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK); + old_val = *sigp_ctrl & ~SIGP_CTRL_C; + if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) { + /* another external call is pending */ + return -EBUSY; + } + atomic_set_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); + return 0; +} + +static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_extcall_info *extcall = &li->irq.extcall; + uint16_t src_id = irq->u.extcall.code; VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u", - irq->u.extcall.code); + src_id); trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL, - irq->u.extcall.code, 0, 2); + src_id, 0, 2); + + /* sending vcpu invalid */ + if (src_id >= KVM_MAX_VCPUS || + kvm_get_vcpu(vcpu->kvm, src_id) == NULL) + return -EINVAL; + + if (sclp_has_sigpif()) + return __inject_extcall_sigpif(vcpu, src_id); + if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) + return -EBUSY; *extcall = irq->u.extcall; - set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); return 0; } @@ -1006,23 +1074,41 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) struct kvm_s390_prefix_info *prefix = &li->irq.prefix; VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)", - prefix->address); + irq->u.prefix.address); trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX, - prefix->address, 0, 2); + irq->u.prefix.address, 0, 2); + + if (!is_vcpu_stopped(vcpu)) + return -EBUSY; *prefix = irq->u.prefix; set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); return 0; } +#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS) static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_stop_info *stop = &li->irq.stop; + int rc = 0; trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2); - li->action_bits |= ACTION_STOP_ON_STOP; - set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); + if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS) + return -EINVAL; + + if (is_vcpu_stopped(vcpu)) { + if (irq->u.stop.flags & KVM_S390_STOP_FLAG_STORE_STATUS) + rc = kvm_s390_store_status_unloaded(vcpu, + KVM_S390_STORE_STATUS_NOADDR); + return rc; + } + + if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs)) + return -EBUSY; + stop->flags = irq->u.stop.flags; + __set_cpuflag(vcpu, CPUSTAT_STOP_INT); return 0; } @@ -1042,14 +1128,13 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_emerg_info *emerg = &li->irq.emerg; VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", irq->u.emerg.code); trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, - emerg->code, 0, 2); + irq->u.emerg.code, 0, 2); - set_bit(emerg->code, li->sigp_emerg_pending); + set_bit(irq->u.emerg.code, li->sigp_emerg_pending); set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); return 0; @@ -1061,9 +1146,9 @@ static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) struct kvm_s390_mchk_info *mchk = &li->irq.mchk; VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx", - mchk->mcic); + irq->u.mchk.mcic); trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0, - mchk->mcic, 2); + irq->u.mchk.mcic, 2); /* * Because repressible machine checks can be indicated along with @@ -1112,81 +1197,182 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu) return 0; } +static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm, + int isc, u32 schid) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + struct list_head *isc_list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + struct kvm_s390_interrupt_info *iter; + u16 id = (schid & 0xffff0000U) >> 16; + u16 nr = schid & 0x0000ffffU; + spin_lock(&fi->lock); + list_for_each_entry(iter, isc_list, list) { + if (schid && (id != iter->io.subchannel_id || + nr != iter->io.subchannel_nr)) + continue; + /* found an appropriate entry */ + list_del_init(&iter->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + if (list_empty(isc_list)) + clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); + spin_unlock(&fi->lock); + return iter; + } + spin_unlock(&fi->lock); + return NULL; +} + +/* + * Dequeue and return an I/O interrupt matching any of the interruption + * subclasses as designated by the isc mask in cr6 and the schid (if != 0). + */ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, - u64 cr6, u64 schid) + u64 isc_mask, u32 schid) +{ + struct kvm_s390_interrupt_info *inti = NULL; + int isc; + + for (isc = 0; isc <= MAX_ISC && !inti; isc++) { + if (isc_mask & isc_to_isc_bits(isc)) + inti = get_io_int(kvm, isc, schid); + } + return inti; +} + +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int __inject_service(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + /* + * Early versions of the QEMU s390 bios will inject several + * service interrupts after another without handling a + * condition code indicating busy. + * We will silently ignore those superfluous sccb values. + * A future version of QEMU will take care of serialization + * of servc requests + */ + if (fi->srv_signal.ext_params & SCCB_MASK) + goto out; + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_MASK; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); +out: + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_virtio(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_VIRTIO] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_VIRTIO]); + set_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int __inject_pfault_done(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_PFAULT] >= + (ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_PFAULT] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_PFAULT]); + set_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +#define CR_PENDING_SUBCLASS 28 +static int __inject_float_mchk(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS); + fi->mchk.mcic |= inti->mchk.mcic; + set_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs); + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *inti, *iter; + struct list_head *list; + int isc; - 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; - } - if (inti) { - list_del_init(&inti->list); - fi->irq_count--; + if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; } - if (list_empty(&fi->list)) - atomic_set(&fi->active, 0); + fi->counters[FIRQ_CNTR_IO] += 1; + + isc = int_word_to_isc(inti->io.io_int_word); + list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + list_add_tail(&inti->list, list); + set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); - return inti; + return 0; } 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; + u64 type = READ_ONCE(inti->type); + int rc; - mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; - spin_lock(&fi->lock); - if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) { + + switch (type) { + case KVM_S390_MCHK: + rc = __inject_float_mchk(kvm, inti); + break; + case KVM_S390_INT_VIRTIO: + rc = __inject_virtio(kvm, inti); + break; + case KVM_S390_INT_SERVICE: + rc = __inject_service(kvm, inti); + break; + case KVM_S390_INT_PFAULT_DONE: + rc = __inject_pfault_done(kvm, inti); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + rc = __inject_io(kvm, inti); + break; + default: 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); + if (rc) + return rc; - /* Keep I/O interrupts sorted in isc order. */ - list_for_each_entry(iter, &fi->list, list) { - if (!is_ioint(iter->type)) - continue; - if (int_word_to_isc_bits(iter->io.io_int_word) - <= isc_bits) - continue; - break; - } - list_add_tail(&inti->list, &iter->list); - } - atomic_set(&fi->active, 1); sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); if (sigcpu == KVM_MAX_VCPUS) { do { @@ -1198,7 +1384,7 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) dst_vcpu = kvm_get_vcpu(kvm, sigcpu); li = &dst_vcpu->arch.local_int; spin_lock(&li->lock); - switch (inti->type) { + switch (type) { case KVM_S390_MCHK: atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); break; @@ -1211,16 +1397,15 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) } spin_unlock(&li->lock); kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); -unlock_fi: - spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); - return rc; + return 0; + } int kvm_s390_inject_vm(struct kvm *kvm, struct kvm_s390_interrupt *s390int) { struct kvm_s390_interrupt_info *inti; + int rc; inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) @@ -1239,7 +1424,6 @@ int kvm_s390_inject_vm(struct kvm *kvm, 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: @@ -1268,13 +1452,16 @@ int kvm_s390_inject_vm(struct kvm *kvm, trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64, 2); - return __inject_vm(kvm, inti); + rc = __inject_vm(kvm, inti); + if (rc) + kfree(inti); + return rc; } -void kvm_s390_reinject_io_int(struct kvm *kvm, +int kvm_s390_reinject_io_int(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { - __inject_vm(kvm, inti); + return __inject_vm(kvm, inti); } int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, @@ -1290,13 +1477,16 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, case KVM_S390_SIGP_SET_PREFIX: irq->u.prefix.address = s390int->parm; break; + case KVM_S390_SIGP_STOP: + irq->u.stop.flags = s390int->parm; + break; case KVM_S390_INT_EXTERNAL_CALL: - if (irq->u.extcall.code & 0xffff0000) + if (s390int->parm & 0xffff0000) return -EINVAL; irq->u.extcall.code = s390int->parm; break; case KVM_S390_INT_EMERGENCY: - if (irq->u.emerg.code & 0xffff0000) + if (s390int->parm & 0xffff0000) return -EINVAL; irq->u.emerg.code = s390int->parm; break; @@ -1307,12 +1497,27 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, return 0; } -int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); +} + +void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; spin_lock(&li->lock); + li->irq.stop.flags = 0; + clear_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); + spin_unlock(&li->lock); +} + +static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + int rc; + switch (irq->type) { case KVM_S390_PROGRAM_INT: VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)", @@ -1352,87 +1557,130 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) default: rc = -EINVAL; } + + return rc; +} + +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + spin_lock(&li->lock); + rc = do_inject_vcpu(vcpu, irq); spin_unlock(&li->lock); if (!rc) kvm_s390_vcpu_wakeup(vcpu); return rc; } -void kvm_s390_clear_float_irqs(struct kvm *kvm) +static inline void clear_irq_list(struct list_head *_list) { - struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *n, *inti = NULL; + struct kvm_s390_interrupt_info *inti, *n; - mutex_lock(&kvm->lock); - fi = &kvm->arch.float_int; - spin_lock(&fi->lock); - list_for_each_entry_safe(inti, n, &fi->list, list) { + list_for_each_entry_safe(inti, n, _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) +static void inti_to_irq(struct kvm_s390_interrupt_info *inti, + struct kvm_s390_irq *irq) { - struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr; - struct kvm_s390_irq irq = {0}; - - irq.type = inti->type; + 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; + irq->u.ext = inti->ext; break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - irq.u.io = inti->io; + 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; +void kvm_s390_clear_float_irqs(struct kvm *kvm) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + int i; - return 0; -} + spin_lock(&fi->lock); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + clear_irq_list(&fi->lists[i]); + for (i = 0; i < FIRQ_MAX_COUNT; i++) + fi->counters[i] = 0; + spin_unlock(&fi->lock); +}; -static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len) +static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) { struct kvm_s390_interrupt_info *inti; struct kvm_s390_float_interrupt *fi; + struct kvm_s390_irq *buf; + struct kvm_s390_irq *irq; + int max_irqs; int ret = 0; int n = 0; + int i; + + if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0) + return -EINVAL; + + /* + * We are already using -ENOMEM to signal + * userspace it may retry with a bigger buffer, + * so we need to use something else for this case + */ + buf = vzalloc(len); + if (!buf) + return -ENOBUFS; + + max_irqs = len / sizeof(struct kvm_s390_irq); - 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)) { + for (i = 0; i < FIRQ_LIST_COUNT; i++) { + list_for_each_entry(inti, &fi->lists[i], list) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + inti_to_irq(inti, &buf[n]); + n++; + } + } + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; - break; + goto out; } - ret = copy_irq_to_user(inti, buf); - if (ret) - break; - buf += sizeof(struct kvm_s390_irq); - len -= sizeof(struct kvm_s390_irq); + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_INT_SERVICE; + irq->u.ext = fi->srv_signal; n++; } + if (test_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_MCHK; + irq->u.mchk = fi->mchk; + n++; +} +out: spin_unlock(&fi->lock); - mutex_unlock(&kvm->lock); + if (!ret && n > 0) { + if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) + ret = -EFAULT; + } + vfree(buf); return ret < 0 ? ret : n; } @@ -1443,7 +1691,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) switch (attr->group) { case KVM_DEV_FLIC_GET_ALL_IRQS: - r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr, + r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, attr->attr); break; default: @@ -1875,3 +2123,143 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, { return -EINVAL; } + +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq *buf; + int r = 0; + int n; + + buf = vmalloc(len); + if (!buf) + return -ENOMEM; + + if (copy_from_user((void *) buf, irqstate, len)) { + r = -EFAULT; + goto out_free; + } + + /* + * Don't allow setting the interrupt state + * when there are already interrupts pending + */ + spin_lock(&li->lock); + if (li->pending_irqs) { + r = -EBUSY; + goto out_unlock; + } + + for (n = 0; n < len / sizeof(*buf); n++) { + r = do_inject_vcpu(vcpu, &buf[n]); + if (r) + break; + } + +out_unlock: + spin_unlock(&li->lock); +out_free: + vfree(buf); + + return r; +} + +static void store_local_irq(struct kvm_s390_local_interrupt *li, + struct kvm_s390_irq *irq, + unsigned long irq_type) +{ + switch (irq_type) { + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + irq->type = KVM_S390_MCHK; + irq->u.mchk = li->irq.mchk; + break; + case IRQ_PEND_PROG: + irq->type = KVM_S390_PROGRAM_INT; + irq->u.pgm = li->irq.pgm; + break; + case IRQ_PEND_PFAULT_INIT: + irq->type = KVM_S390_INT_PFAULT_INIT; + irq->u.ext = li->irq.ext; + break; + case IRQ_PEND_EXT_EXTERNAL: + irq->type = KVM_S390_INT_EXTERNAL_CALL; + irq->u.extcall = li->irq.extcall; + break; + case IRQ_PEND_EXT_CLOCK_COMP: + irq->type = KVM_S390_INT_CLOCK_COMP; + break; + case IRQ_PEND_EXT_CPU_TIMER: + irq->type = KVM_S390_INT_CPU_TIMER; + break; + case IRQ_PEND_SIGP_STOP: + irq->type = KVM_S390_SIGP_STOP; + irq->u.stop = li->irq.stop; + break; + case IRQ_PEND_RESTART: + irq->type = KVM_S390_RESTART; + break; + case IRQ_PEND_SET_PREFIX: + irq->type = KVM_S390_SIGP_SET_PREFIX; + irq->u.prefix = li->irq.prefix; + break; + } +} + +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) +{ + uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + unsigned long pending_irqs; + struct kvm_s390_irq irq; + unsigned long irq_type; + int cpuaddr; + int n = 0; + + spin_lock(&li->lock); + pending_irqs = li->pending_irqs; + memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending, + sizeof(sigp_emerg_pending)); + spin_unlock(&li->lock); + + for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) { + memset(&irq, 0, sizeof(irq)); + if (irq_type == IRQ_PEND_EXT_EMERGENCY) + continue; + if (n + sizeof(irq) > len) + return -ENOBUFS; + store_local_irq(&vcpu->arch.local_int, &irq, irq_type); + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) { + for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) { + memset(&irq, 0, sizeof(irq)); + if (n + sizeof(irq) > len) + return -ENOBUFS; + irq.type = KVM_S390_INT_EMERGENCY; + irq.u.emerg.code = cpuaddr; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + } + + if ((sigp_ctrl & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & + CPUSTAT_ECALL_PEND)) { + if (n + sizeof(irq) > len) + return -ENOBUFS; + memset(&irq, 0, sizeof(irq)); + irq.type = KVM_S390_INT_EXTERNAL_CALL; + irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + return n; +} diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3e09801..afa2bd7 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -22,14 +22,16 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/module.h> +#include <linux/random.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> #include <asm/pgtable.h> #include <asm/nmi.h> #include <asm/switch_to.h> -#include <asm/facility.h> +#include <asm/isc.h> #include <asm/sclp.h> #include "kvm-s390.h" #include "gaccess.h" @@ -38,6 +40,11 @@ #include "trace.h" #include "trace-s390.h" +#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */ +#define LOCAL_IRQS 32 +#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ + (KVM_MAX_VCPUS + LOCAL_IRQS)) + #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU struct kvm_stats_debugfs_item debugfs_entries[] = { @@ -50,6 +57,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exit_instruction", VCPU_STAT(exit_instruction) }, { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, + { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, { "instruction_lctl", VCPU_STAT(instruction_lctl) }, @@ -86,6 +94,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) }, { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) }, + { "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) }, { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, @@ -98,15 +107,20 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -unsigned long *vfacilities; -static struct gmap_notifier gmap_notifier; +/* upper facilities limit for kvm */ +unsigned long kvm_s390_fac_list_mask[] = { + 0xffe6fffbfcfdfc40UL, + 0x205c800000000000UL, +}; -/* test availability of vfacility */ -int test_vfacility(unsigned long nr) +unsigned long kvm_s390_fac_list_mask_size(void) { - return __test_facility(nr, (void *) vfacilities); + BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64); + return ARRAY_SIZE(kvm_s390_fac_list_mask); } +static struct gmap_notifier gmap_notifier; + /* Section: not file related */ int kvm_arch_hardware_enable(void) { @@ -159,15 +173,22 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 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_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: + case KVM_CAP_S390_INJECT_IRQ: + case KVM_CAP_S390_USER_SIGP: + case KVM_CAP_S390_USER_STSI: + case KVM_CAP_S390_SKEYS: + case KVM_CAP_S390_IRQ_STATE: r = 1; break; + case KVM_CAP_S390_MEM_OP: + r = MEM_OP_MAX_SIZE; + break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -178,6 +199,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_COW: r = MACHINE_HAS_ESOP; break; + case KVM_CAP_S390_VECTOR_REGISTERS: + r = MACHINE_HAS_VX; + break; default: r = 0; } @@ -254,6 +278,22 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) kvm->arch.use_irqchip = 1; r = 0; break; + case KVM_CAP_S390_USER_SIGP: + kvm->arch.user_sigp = 1; + r = 0; + break; + case KVM_CAP_S390_VECTOR_REGISTERS: + if (MACHINE_HAS_VX) { + set_kvm_facility(kvm->arch.model.fac->mask, 129); + set_kvm_facility(kvm->arch.model.fac->list, 129); + r = 0; + } else + r = -EINVAL; + break; + case KVM_CAP_S390_USER_STSI: + kvm->arch.user_stsi = 1; + r = 0; + break; default: r = -EINVAL; break; @@ -261,7 +301,24 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) return r; } -static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) +static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->attr) { + case KVM_S390_VM_MEM_LIMIT_SIZE: + ret = 0; + if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr)) + ret = -EFAULT; + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) { int ret; unsigned int idx; @@ -283,6 +340,190 @@ static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) mutex_unlock(&kvm->lock); ret = 0; break; + case KVM_S390_VM_MEM_LIMIT_SIZE: { + unsigned long new_limit; + + if (kvm_is_ucontrol(kvm)) + return -EINVAL; + + if (get_user(new_limit, (u64 __user *)attr->addr)) + return -EFAULT; + + if (new_limit > kvm->arch.gmap->asce_end) + return -E2BIG; + + ret = -EBUSY; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) == 0) { + /* gmap_alloc will round the limit up */ + struct gmap *new = gmap_alloc(current->mm, new_limit); + + if (!new) { + ret = -ENOMEM; + } else { + gmap_free(kvm->arch.gmap); + new->private = kvm; + kvm->arch.gmap = new; + ret = 0; + } + } + mutex_unlock(&kvm->lock); + break; + } + default: + ret = -ENXIO; + break; + } + return ret; +} + +static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); + +static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_vcpu *vcpu; + int i; + + if (!test_kvm_facility(kvm, 76)) + return -EINVAL; + + mutex_lock(&kvm->lock); + switch (attr->attr) { + case KVM_S390_VM_CRYPTO_ENABLE_AES_KW: + get_random_bytes( + kvm->arch.crypto.crycb->aes_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask)); + kvm->arch.crypto.aes_kw = 1; + break; + case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW: + get_random_bytes( + kvm->arch.crypto.crycb->dea_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask)); + kvm->arch.crypto.dea_kw = 1; + break; + case KVM_S390_VM_CRYPTO_DISABLE_AES_KW: + kvm->arch.crypto.aes_kw = 0; + memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0, + sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask)); + break; + case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW: + kvm->arch.crypto.dea_kw = 0; + memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0, + sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask)); + break; + default: + mutex_unlock(&kvm->lock); + return -ENXIO; + } + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_s390_vcpu_crypto_setup(vcpu); + exit_sie(vcpu); + } + mutex_unlock(&kvm->lock); + return 0; +} + +static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) +{ + u8 gtod_high; + + if (copy_from_user(>od_high, (void __user *)attr->addr, + sizeof(gtod_high))) + return -EFAULT; + + if (gtod_high != 0) + return -EINVAL; + + return 0; +} + +static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_vcpu *cur_vcpu; + unsigned int vcpu_idx; + u64 host_tod, gtod; + int r; + + if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) + return -EFAULT; + + r = store_tod_clock(&host_tod); + if (r) + return r; + + mutex_lock(&kvm->lock); + kvm->arch.epoch = gtod - host_tod; + kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) { + cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch; + exit_sie(cur_vcpu); + } + mutex_unlock(&kvm->lock); + return 0; +} + +static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + if (attr->flags) + return -EINVAL; + + switch (attr->attr) { + case KVM_S390_VM_TOD_HIGH: + ret = kvm_s390_set_tod_high(kvm, attr); + break; + case KVM_S390_VM_TOD_LOW: + ret = kvm_s390_set_tod_low(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) +{ + u8 gtod_high = 0; + + if (copy_to_user((void __user *)attr->addr, >od_high, + sizeof(gtod_high))) + return -EFAULT; + + return 0; +} + +static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) +{ + u64 host_tod, gtod; + int r; + + r = store_tod_clock(&host_tod); + if (r) + return r; + + gtod = host_tod + kvm->arch.epoch; + if (copy_to_user((void __user *)attr->addr, >od, sizeof(gtod))) + return -EFAULT; + + return 0; +} + +static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + if (attr->flags) + return -EINVAL; + + switch (attr->attr) { + case KVM_S390_VM_TOD_HIGH: + ret = kvm_s390_get_tod_high(kvm, attr); + break; + case KVM_S390_VM_TOD_LOW: + ret = kvm_s390_get_tod_low(kvm, attr); + break; default: ret = -ENXIO; break; @@ -290,13 +531,122 @@ static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } +static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_processor *proc; + int ret = 0; + + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus)) { + ret = -EBUSY; + goto out; + } + proc = kzalloc(sizeof(*proc), GFP_KERNEL); + if (!proc) { + ret = -ENOMEM; + goto out; + } + if (!copy_from_user(proc, (void __user *)attr->addr, + sizeof(*proc))) { + memcpy(&kvm->arch.model.cpu_id, &proc->cpuid, + sizeof(struct cpuid)); + kvm->arch.model.ibc = proc->ibc; + memcpy(kvm->arch.model.fac->list, proc->fac_list, + S390_ARCH_FAC_LIST_SIZE_BYTE); + } else + ret = -EFAULT; + kfree(proc); +out: + mutex_unlock(&kvm->lock); + return ret; +} + +static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->attr) { + case KVM_S390_VM_CPU_PROCESSOR: + ret = kvm_s390_set_processor(kvm, attr); + break; + } + return ret; +} + +static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_processor *proc; + int ret = 0; + + proc = kzalloc(sizeof(*proc), GFP_KERNEL); + if (!proc) { + ret = -ENOMEM; + goto out; + } + memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid)); + proc->ibc = kvm->arch.model.ibc; + memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE); + if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc))) + ret = -EFAULT; + kfree(proc); +out: + return ret; +} + +static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_machine *mach; + int ret = 0; + + mach = kzalloc(sizeof(*mach), GFP_KERNEL); + if (!mach) { + ret = -ENOMEM; + goto out; + } + get_cpu_id((struct cpuid *) &mach->cpuid); + mach->ibc = sclp_get_ibc(); + memcpy(&mach->fac_mask, kvm->arch.model.fac->mask, + S390_ARCH_FAC_LIST_SIZE_BYTE); + memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list, + S390_ARCH_FAC_LIST_SIZE_BYTE); + if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach))) + ret = -EFAULT; + kfree(mach); +out: + return ret; +} + +static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->attr) { + case KVM_S390_VM_CPU_PROCESSOR: + ret = kvm_s390_get_processor(kvm, attr); + break; + case KVM_S390_VM_CPU_MACHINE: + ret = kvm_s390_get_machine(kvm, attr); + 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); + ret = kvm_s390_set_mem_control(kvm, attr); + break; + case KVM_S390_VM_TOD: + ret = kvm_s390_set_tod(kvm, attr); + break; + case KVM_S390_VM_CPU_MODEL: + ret = kvm_s390_set_cpu_model(kvm, attr); + break; + case KVM_S390_VM_CRYPTO: + ret = kvm_s390_vm_set_crypto(kvm, attr); break; default: ret = -ENXIO; @@ -308,7 +658,24 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) { - return -ENXIO; + int ret; + + switch (attr->group) { + case KVM_S390_VM_MEM_CTRL: + ret = kvm_s390_get_mem_control(kvm, attr); + break; + case KVM_S390_VM_TOD: + ret = kvm_s390_get_tod(kvm, attr); + break; + case KVM_S390_VM_CPU_MODEL: + ret = kvm_s390_get_cpu_model(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + + return ret; } static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) @@ -320,6 +687,42 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) switch (attr->attr) { case KVM_S390_VM_MEM_ENABLE_CMMA: case KVM_S390_VM_MEM_CLR_CMMA: + case KVM_S390_VM_MEM_LIMIT_SIZE: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + case KVM_S390_VM_TOD: + switch (attr->attr) { + case KVM_S390_VM_TOD_LOW: + case KVM_S390_VM_TOD_HIGH: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + case KVM_S390_VM_CPU_MODEL: + switch (attr->attr) { + case KVM_S390_VM_CPU_PROCESSOR: + case KVM_S390_VM_CPU_MACHINE: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + case KVM_S390_VM_CRYPTO: + switch (attr->attr) { + case KVM_S390_VM_CRYPTO_ENABLE_AES_KW: + case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW: + case KVM_S390_VM_CRYPTO_DISABLE_AES_KW: + case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW: ret = 0; break; default: @@ -335,6 +738,108 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } +static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + unsigned long curkey; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Is this guest using storage keys? */ + if (!mm_use_skey(current->mm)) + return KVM_S390_GET_SKEYS_NONE; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + curkey = get_guest_storage_key(current->mm, hva); + if (IS_ERR_VALUE(curkey)) { + r = curkey; + goto out; + } + keys[i] = curkey; + } + + r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys, + sizeof(uint8_t) * args->count); + if (r) + r = -EFAULT; +out: + kvfree(keys); + return r; +} + +static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr, + sizeof(uint8_t) * args->count); + if (r) { + r = -EFAULT; + goto out; + } + + /* Enable storage key handling for the guest */ + s390_enable_skey(); + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + /* Lowest order bit is reserved */ + if (keys[i] & 0x01) { + r = -EINVAL; + goto out; + } + + r = set_guest_storage_key(current->mm, hva, + (unsigned long)keys[i], 0); + if (r) + goto out; + } +out: + kvfree(keys); + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -394,6 +899,26 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_s390_vm_has_attr(kvm, &attr); break; } + case KVM_S390_GET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_get_skeys(kvm, &args); + break; + } + case KVM_S390_SET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_set_skeys(kvm, &args); + break; + } default: r = -ENOTTY; } @@ -401,9 +926,64 @@ long kvm_arch_vm_ioctl(struct file *filp, return r; } +static int kvm_s390_query_ap_config(u8 *config) +{ + u32 fcn_code = 0x04000000UL; + u32 cc = 0; + + memset(config, 0, 128); + asm volatile( + "lgr 0,%1\n" + "lgr 2,%2\n" + ".long 0xb2af0000\n" /* PQAP(QCI) */ + "0: ipm %0\n" + "srl %0,28\n" + "1:\n" + EX_TABLE(0b, 1b) + : "+r" (cc) + : "r" (fcn_code), "r" (config) + : "cc", "0", "2", "memory" + ); + + return cc; +} + +static int kvm_s390_apxa_installed(void) +{ + u8 config[128]; + int cc; + + if (test_facility(2) && test_facility(12)) { + cc = kvm_s390_query_ap_config(config); + + if (cc) + pr_err("PQAP(QCI) failed with cc=%d", cc); + else + return config[0] & 0x40; + } + + return 0; +} + +static void kvm_s390_set_crycb_format(struct kvm *kvm) +{ + kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb; + + if (kvm_s390_apxa_installed()) + kvm->arch.crypto.crycbd |= CRYCB_FORMAT2; + else + kvm->arch.crypto.crycbd |= CRYCB_FORMAT1; +} + +static void kvm_s390_get_cpu_id(struct cpuid *cpu_id) +{ + get_cpu_id(cpu_id); + cpu_id->version = 0xff; +} + static int kvm_s390_crypto_init(struct kvm *kvm) { - if (!test_vfacility(76)) + if (!test_kvm_facility(kvm, 76)) return 0; kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb), @@ -411,15 +991,22 @@ static int kvm_s390_crypto_init(struct kvm *kvm) if (!kvm->arch.crypto.crycb) return -ENOMEM; - kvm->arch.crypto.crycbd = (__u32) (unsigned long) kvm->arch.crypto.crycb | - CRYCB_FORMAT1; + kvm_s390_set_crycb_format(kvm); + + /* Enable AES/DEA protected key functions by default */ + kvm->arch.crypto.aes_kw = 1; + kvm->arch.crypto.dea_kw = 1; + get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask)); + get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask)); return 0; } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - int rc; + int i, rc; char debug_name[16]; static unsigned long sca_offset; @@ -452,13 +1039,43 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long)); if (!kvm->arch.dbf) - goto out_nodbf; + goto out_err; + + /* + * The architectural maximum amount of facilities is 16 kbit. To store + * this amount, 2 kbyte of memory is required. Thus we need a full + * page to hold the guest facility list (arch.model.fac->list) and the + * facility mask (arch.model.fac->mask). Its address size has to be + * 31 bits and word aligned. + */ + kvm->arch.model.fac = + (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!kvm->arch.model.fac) + goto out_err; + + /* Populate the facility mask initially. */ + memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list, + S390_ARCH_FAC_LIST_SIZE_BYTE); + for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) { + if (i < kvm_s390_fac_list_mask_size()) + kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i]; + else + kvm->arch.model.fac->mask[i] = 0UL; + } + + /* Populate the facility list initially. */ + memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask, + S390_ARCH_FAC_LIST_SIZE_BYTE); + + kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id); + kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff; if (kvm_s390_crypto_init(kvm) < 0) - goto out_crypto; + goto out_err; spin_lock_init(&kvm->arch.float_int.lock); - INIT_LIST_HEAD(&kvm->arch.float_int.list); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]); init_waitqueue_head(&kvm->arch.ipte_wq); mutex_init(&kvm->arch.ipte_mutex); @@ -470,24 +1087,23 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) } else { kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1); if (!kvm->arch.gmap) - goto out_nogmap; + goto out_err; kvm->arch.gmap->private = kvm; kvm->arch.gmap->pfault_enabled = 0; } kvm->arch.css_support = 0; kvm->arch.use_irqchip = 0; + kvm->arch.epoch = 0; spin_lock_init(&kvm->arch.start_stop_lock); return 0; -out_nogmap: +out_err: kfree(kvm->arch.crypto.crycb); -out_crypto: + free_page((unsigned long)kvm->arch.model.fac); debug_unregister(kvm->arch.dbf); -out_nodbf: free_page((unsigned long)(kvm->arch.sca)); -out_err: return rc; } @@ -536,6 +1152,7 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { kvm_free_vcpus(kvm); + free_page((unsigned long)kvm->arch.model.fac); free_page((unsigned long)(kvm->arch.sca)); debug_unregister(kvm->arch.dbf); kfree(kvm->arch.crypto.crycb); @@ -546,35 +1163,50 @@ void kvm_arch_destroy_vm(struct kvm *kvm) } /* Section: vcpu related */ +static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu) +{ + vcpu->arch.gmap = gmap_alloc(current->mm, -1UL); + if (!vcpu->arch.gmap) + return -ENOMEM; + vcpu->arch.gmap->private = vcpu->kvm; + + return 0; +} + 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, -1UL); - if (!vcpu->arch.gmap) - return -ENOMEM; - vcpu->arch.gmap->private = vcpu->kvm; - return 0; - } - - vcpu->arch.gmap = vcpu->kvm->arch.gmap; vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + if (test_kvm_facility(vcpu->kvm, 129)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + + if (kvm_is_ucontrol(vcpu->kvm)) + return __kvm_ucontrol_vcpu_init(vcpu); + return 0; } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { save_fp_ctl(&vcpu->arch.host_fpregs.fpc); - save_fp_regs(vcpu->arch.host_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) + save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + save_fp_regs(vcpu->arch.host_fpregs.fprs); save_access_regs(vcpu->arch.host_acrs); - restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); - restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) { + restore_fp_ctl(&vcpu->run->s.regs.fpc); + restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + 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); @@ -584,11 +1216,19 @@ 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_ctl(&vcpu->arch.guest_fpregs.fpc); - save_fp_regs(vcpu->arch.guest_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) { + save_fp_ctl(&vcpu->run->s.regs.fpc); + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + 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_ctl(&vcpu->arch.host_fpregs.fpc); - restore_fp_regs(vcpu->arch.host_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) + restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + restore_fp_regs(vcpu->arch.host_fpregs.fprs); restore_access_regs(vcpu->arch.host_acrs); } @@ -615,16 +1255,27 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) kvm_s390_clear_local_irqs(vcpu); } -int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { - return 0; + mutex_lock(&vcpu->kvm->lock); + vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch; + mutex_unlock(&vcpu->kvm->lock); + if (!kvm_is_ucontrol(vcpu->kvm)) + vcpu->arch.gmap = vcpu->kvm->arch.gmap; } static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) { - if (!test_vfacility(76)) + if (!test_kvm_facility(vcpu->kvm, 76)) return; + vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA); + + if (vcpu->kvm->arch.crypto.aes_kw) + vcpu->arch.sie_block->ecb3 |= ECB3_AES; + if (vcpu->kvm->arch.crypto.dea_kw) + vcpu->arch.sie_block->ecb3 |= ECB3_DEA; + vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd; } @@ -645,6 +1296,15 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) return 0; } +static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model; + + vcpu->arch.cpu_id = model->cpu_id; + vcpu->arch.sie_block->ibc = model->ibc; + vcpu->arch.sie_block->fac = (int) (long) model->fac->list; +} + int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; @@ -653,27 +1313,31 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) CPUSTAT_SM | CPUSTAT_STOPPED | CPUSTAT_GED); + kvm_s390_vcpu_setup_model(vcpu); + vcpu->arch.sie_block->ecb = 6; - if (test_vfacility(50) && test_vfacility(73)) + if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73)) vcpu->arch.sie_block->ecb |= 0x10; vcpu->arch.sie_block->ecb2 = 8; - vcpu->arch.sie_block->eca = 0xD1002000U; + vcpu->arch.sie_block->eca = 0xC1002000U; 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 (sclp_has_sigpif()) + vcpu->arch.sie_block->eca |= 0x10000000U; + if (test_kvm_facility(vcpu->kvm, 129)) { + vcpu->arch.sie_block->eca |= 0x00020000; + vcpu->arch.sie_block->ecd |= 0x20000000; + } + vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; 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); + hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; - get_cpu_id(&vcpu->arch.cpu_id); - vcpu->arch.cpu_id.version = 0xff; kvm_s390_vcpu_crypto_setup(vcpu); @@ -702,6 +1366,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; + vcpu->arch.host_vregs = &sie_page->vregs; vcpu->arch.sie_block->icpua = id; if (!kvm_is_ucontrol(kvm)) { @@ -741,7 +1406,7 @@ out: int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - return kvm_cpu_has_interrupt(vcpu); + return kvm_s390_vcpu_has_irq(vcpu, 0); } void s390_vcpu_block(struct kvm_vcpu *vcpu) @@ -869,6 +1534,8 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, case KVM_REG_S390_PFTOKEN: r = get_user(vcpu->arch.pfault_token, (u64 __user *)reg->addr); + if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) + kvm_clear_async_pf_completion_queue(vcpu); break; case KVM_REG_S390_PFCOMPARE: r = get_user(vcpu->arch.pfault_compare, @@ -1176,7 +1843,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu) return 0; if (psw_extint_disabled(vcpu)) return 0; - if (kvm_cpu_has_interrupt(vcpu)) + if (kvm_s390_vcpu_has_irq(vcpu, 0)) return 0; if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul)) return 0; @@ -1234,6 +1901,31 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) return 0; } +static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + u8 opcode; + int rc; + + VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); + trace_kvm_s390_sie_fault(vcpu); + + /* + * We want to inject an addressing exception, which is defined as a + * suppressing or terminating exception. However, since we came here + * by a DAT access exception, the PSW still points to the faulting + * instruction since DAT exceptions are nullifying. So we've got + * to look up the current opcode to get the length of the instruction + * to be able to forward the PSW. + */ + rc = read_guest(vcpu, psw->addr, 0, &opcode, 1); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + psw->addr = __rewind_psw(*psw, -insn_length(opcode)); + + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); +} + static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) { int rc = -1; @@ -1265,11 +1957,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) } } - 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); - } + if (rc == -1) + rc = vcpu_post_run_fault_in_sie(vcpu); memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16); @@ -1341,6 +2030,8 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.pfault_token = kvm_run->s.regs.pft; vcpu->arch.pfault_select = kvm_run->s.regs.pfs; vcpu->arch.pfault_compare = kvm_run->s.regs.pfc; + if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) + kvm_clear_async_pf_completion_queue(vcpu); } kvm_run->kvm_dirty_regs = 0; } @@ -1483,6 +2174,35 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) return kvm_s390_store_status_unloaded(vcpu, addr); } +/* + * store additional status at address + */ +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long gpa) +{ + /* Only bits 0-53 are used for address formation */ + if (!(gpa & ~0x3ff)) + return 0; + + return write_guest_abs(vcpu, gpa & ~0x3ff, + (void *)&vcpu->run->s.regs.vrs, 512); +} + +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + if (!test_kvm_facility(vcpu->kvm, 129)) + return 0; + + /* + * The guest VXRS are in the host VXRs due to the lazy + * copying in vcpu load/put. Let's update our copies before we save + * it into the save area. + */ + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + + return kvm_s390_store_adtl_status_unloaded(vcpu, addr); +} + static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) { kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); @@ -1559,15 +2279,10 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->arch.start_stop_lock); online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); - /* Need to lock access to action_bits to avoid a SIGP race condition */ - spin_lock(&vcpu->arch.local_int.lock); - atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); - /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ - vcpu->arch.local_int.action_bits &= - ~(ACTION_STOP_ON_STOP | ACTION_STORE_ON_STOP); - spin_unlock(&vcpu->arch.local_int.lock); + kvm_s390_clear_stop_irq(vcpu); + atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); __disable_ibs_on_vcpu(vcpu); for (i = 0; i < online_vcpus; i++) { @@ -1612,6 +2327,65 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void *tmpbuf = NULL; + int r, srcu_idx; + const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION + | KVM_S390_MEMOP_F_CHECK_ONLY; + + if (mop->flags & ~supported_flags) + return -EINVAL; + + if (mop->size > MEM_OP_MAX_SIZE) + return -E2BIG; + + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { + tmpbuf = vmalloc(mop->size); + if (!tmpbuf) + return -ENOMEM; + } + + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (mop->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false); + break; + } + r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + if (r == 0) { + if (copy_to_user(uaddr, tmpbuf, mop->size)) + r = -EFAULT; + } + break; + case KVM_S390_MEMOP_LOGICAL_WRITE: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true); + break; + } + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + break; + } + r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + + if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) + kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + + vfree(tmpbuf); + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1621,6 +2395,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, long r; switch (ioctl) { + case KVM_S390_IRQ: { + struct kvm_s390_irq s390irq; + + r = -EFAULT; + if (copy_from_user(&s390irq, argp, sizeof(s390irq))) + break; + r = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; + } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; struct kvm_s390_irq s390irq; @@ -1711,6 +2494,47 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } + case KVM_S390_MEM_OP: { + struct kvm_s390_mem_op mem_op; + + if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0) + r = kvm_s390_guest_mem_op(vcpu, &mem_op); + else + r = -EFAULT; + break; + } + case KVM_S390_SET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len > VCPU_IRQS_MAX_BUF || + irq_state.len == 0 || + irq_state.len % sizeof(struct kvm_s390_irq) > 0) { + r = -EINVAL; + break; + } + r = kvm_s390_set_irq_state(vcpu, + (void __user *) irq_state.buf, + irq_state.len); + break; + } + case KVM_S390_GET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len == 0) { + r = -EINVAL; + break; + } + r = kvm_s390_get_irq_state(vcpu, + (__u8 __user *) irq_state.buf, + irq_state.len); + break; + } default: r = -ENOTTY; } @@ -1783,30 +2607,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, static int __init kvm_s390_init(void) { - int ret; - ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); - if (ret) - return ret; - - /* - * guests can ask for up to 255+1 double words, we need a full page - * to hold the maximum amount of facilities. On the other hand, we - * only set facilities that are known to work in KVM. - */ - vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); - if (!vfacilities) { - kvm_exit(); - return -ENOMEM; - } - memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16); - vfacilities[0] &= 0xff82fffbf47c2000UL; - vfacilities[1] &= 0x005c000000000000UL; - return 0; + return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); } static void __exit kvm_s390_exit(void) { - free_page((unsigned long) vfacilities); kvm_exit(); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a8f3d9b..ca108b9 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -18,12 +18,10 @@ #include <linux/hrtimer.h> #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <asm/facility.h> typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); -/* declare vfacilities extern */ -extern unsigned long *vfacilities; - /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & 0x10)) #define TDB_FORMAT1 1 @@ -72,16 +70,22 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); } -static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu) +typedef u8 __bitwise ar_t; + +static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + if (ar) + *ar = base2; + 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) + u64 *address1, u64 *address2, + ar_t *ar_b1, ar_t *ar_b2) { u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; @@ -90,6 +94,11 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, *address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; *address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; + + if (ar_b1) + *ar_b1 = base1; + if (ar_b2) + *ar_b2 = base2; } static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) @@ -100,7 +109,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2 *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; } -static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) +static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + @@ -109,14 +118,20 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) if (disp2 & 0x80000) disp2+=0xfff00000; + if (ar) + *ar = base2; + 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) +static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } @@ -127,6 +142,24 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) vcpu->arch.sie_block->gpsw.mask |= cc << 44; } +/* test availability of facility in a kvm instance */ +static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr) +{ + return __test_facility(nr, kvm->arch.model.fac->mask) && + __test_facility(nr, kvm->arch.model.fac->list); +} + +static inline int set_kvm_facility(u64 *fac_list, unsigned long nr) +{ + unsigned char *ptr; + + if (nr >= MAX_FACILITY_BIT) + return -EINVAL; + ptr = (unsigned char *) fac_list + (nr >> 3); + *ptr |= (0x80UL >> (nr & 7)); + return 0; +} + /* are cpu states controlled by user space */ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) { @@ -145,9 +178,9 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq); 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); + u64 isc_mask, u32 schid); +int 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 intercept.c */ @@ -172,7 +205,10 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ 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_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_vcpu_store_adtl_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); @@ -183,7 +219,8 @@ 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); +unsigned long kvm_s390_fac_list_mask_size(void); +extern unsigned long kvm_s390_fac_list_mask[]; /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); @@ -228,11 +265,17 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, struct kvm_s390_irq *s390irq); /* implemented in interrupt.c */ -int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop); 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); +int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu); extern struct kvm_device_ops kvm_flic_ops; +int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu); +void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu); +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, + void __user *buf, int len); +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, + __u8 __user *buf, int len); /* implemented in guestdbg.c */ void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 1be578d..d22d8ee 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -36,15 +36,16 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) struct kvm_vcpu *cpup; s64 hostclk, val; int i, rc; + ar_t ar; 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); + op2 = kvm_s390_get_base_disp_s(vcpu, &ar); 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)); + rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -68,20 +69,21 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; + ar_t ar; vcpu->stat.instruction_spx++; 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); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); /* must be word boundary */ if (operand2 & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); /* get the value */ - rc = read_guest(vcpu, operand2, &address, sizeof(address)); + rc = read_guest(vcpu, operand2, ar, &address, sizeof(address)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -107,13 +109,14 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; + ar_t ar; vcpu->stat.instruction_stpx++; 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); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); /* must be word boundary */ if (operand2 & 3) @@ -122,7 +125,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) address = kvm_s390_get_prefix(vcpu); /* get the value */ - rc = write_guest(vcpu, operand2, &address, sizeof(address)); + rc = write_guest(vcpu, operand2, ar, &address, sizeof(address)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -136,18 +139,19 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) u16 vcpu_id = vcpu->vcpu_id; u64 ga; int rc; + ar_t ar; vcpu->stat.instruction_stap++; 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_s(vcpu); + ga = kvm_s390_get_base_disp_s(vcpu, &ar); if (ga & 1) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = write_guest(vcpu, ga, &vcpu_id, sizeof(vcpu_id)); + rc = write_guest(vcpu, ga, ar, &vcpu_id, sizeof(vcpu_id)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -207,7 +211,7 @@ static int handle_test_block(struct kvm_vcpu *vcpu) 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)) + if (kvm_s390_check_low_addr_prot_real(vcpu, addr)) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); addr = kvm_s390_real_to_abs(vcpu, addr); @@ -229,18 +233,20 @@ static int handle_tpi(struct kvm_vcpu *vcpu) struct kvm_s390_interrupt_info *inti; unsigned long len; u32 tpi_data[3]; - int cc, rc; + int rc; u64 addr; + ar_t ar; - rc = 0; - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); 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; + if (!inti) { + kvm_s390_set_psw_cc(vcpu, 0); + return 0; + } + 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; @@ -250,40 +256,51 @@ static int handle_tpi(struct kvm_vcpu *vcpu) * 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); + rc = write_guest(vcpu, addr, ar, &tpi_data, len); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto reinject_interrupt; + } } 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)) + if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) { + /* failed writes to the low core are not recoverable */ rc = -EFAULT; + goto reinject_interrupt; + } } + + /* irq was successfully handed to the guest */ + kfree(inti); + kvm_s390_set_psw_cc(vcpu, 1); + return 0; +reinject_interrupt: /* * If we encounter a problem storing the interruption code, the * instruction is suppressed from the guest's view: reinject the * interrupt. */ - if (!rc) + if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) { 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); + rc = -EFAULT; + } + /* don't set the cc, a pgm irq was injected or we drop to user space */ return rc ? -EFAULT : 0; } static int handle_tsch(struct kvm_vcpu *vcpu) { - struct kvm_s390_interrupt_info *inti; + struct kvm_s390_interrupt_info *inti = NULL; + const u64 isc_mask = 0xffUL << 24; /* all iscs set */ - inti = kvm_s390_get_io_int(vcpu->kvm, 0, - vcpu->run->s.regs.gprs[1]); + /* a valid schid has at least one bit set */ + if (vcpu->run->s.regs.gprs[1]) + inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask, + vcpu->run->s.regs.gprs[1]); /* * Prepare exit to userspace. @@ -337,19 +354,24 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) static int handle_stfl(struct kvm_vcpu *vcpu) { int rc; + unsigned int fac; vcpu->stat.instruction_stfl++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + /* + * We need to shift the lower 32 facility bits (bit 0-31) from a u64 + * into a u32 memory representation. They will remain bits 0-31. + */ + fac = *vcpu->kvm->arch.model.fac->list >> 32; rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list), - vfacilities, 4); + &fac, sizeof(fac)); 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); + VCPU_EVENT(vcpu, 5, "store facility list value %x", fac); + trace_kvm_s390_handle_stfl(vcpu, fac); return 0; } @@ -381,15 +403,16 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) psw_compat_t new_psw; u64 addr; int rc; + ar_t ar; if (gpsw->mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (!(new_psw.mask & PSW32_MASK_BASE)) @@ -407,14 +430,15 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) psw_t new_psw; u64 addr; int rc; + ar_t ar; 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); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); vcpu->arch.sie_block->gpsw = new_psw; @@ -428,18 +452,19 @@ static int handle_stidp(struct kvm_vcpu *vcpu) u64 stidp_data = vcpu->arch.stidp_data; u64 operand2; int rc; + ar_t ar; vcpu->stat.instruction_stidp++; 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); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (operand2 & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = write_guest(vcpu, operand2, &stidp_data, sizeof(stidp_data)); + rc = write_guest(vcpu, operand2, ar, &stidp_data, sizeof(stidp_data)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -462,6 +487,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) for (n = mem->count - 1; n > 0 ; n--) memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + memset(&mem->vm[0], 0, sizeof(mem->vm[0])); mem->vm[0].cpus_total = cpus; mem->vm[0].cpus_configured = cpus; mem->vm[0].cpus_standby = 0; @@ -473,6 +499,17 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) ASCEBC(mem->vm[0].cpi, 16); } +static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar, + u8 fc, u8 sel1, u16 sel2) +{ + vcpu->run->exit_reason = KVM_EXIT_S390_STSI; + vcpu->run->s390_stsi.addr = addr; + vcpu->run->s390_stsi.ar = ar; + vcpu->run->s390_stsi.fc = fc; + vcpu->run->s390_stsi.sel1 = sel1; + vcpu->run->s390_stsi.sel2 = sel2; +} + static int handle_stsi(struct kvm_vcpu *vcpu) { int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28; @@ -481,6 +518,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) unsigned long mem = 0; u64 operand2; int rc = 0; + ar_t ar; vcpu->stat.instruction_stsi++; VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); @@ -503,7 +541,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) return 0; } - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (operand2 & 0xfff) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -527,16 +565,20 @@ static int handle_stsi(struct kvm_vcpu *vcpu) break; } - rc = write_guest(vcpu, operand2, (void *)mem, PAGE_SIZE); + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; } + if (vcpu->kvm->arch.user_stsi) { + insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2); + rc = -EREMOTE; + } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; - return 0; + return rc; out_no_data: kvm_s390_set_psw_cc(vcpu, 3); out: @@ -665,7 +707,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) } if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { - if (kvm_s390_check_low_addr_protection(vcpu, start)) + if (kvm_s390_check_low_addr_prot_real(vcpu, start)) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); } @@ -771,13 +813,14 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; + ar_t ar; 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); + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); if (ga & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -786,7 +829,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga); nr_regs = ((reg3 - reg1) & 0xf) + 1; - rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; @@ -809,13 +852,14 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; + ar_t ar; 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); + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); if (ga & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -831,7 +875,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) break; reg = (reg + 1) % 16; } while (1); - rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } @@ -842,13 +886,14 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; + ar_t ar; 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); + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -857,7 +902,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga); nr_regs = ((reg3 - reg1) & 0xf) + 1; - rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; @@ -879,13 +924,14 @@ static int handle_stctg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; + ar_t ar; 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); + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -901,7 +947,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu) break; reg = (reg + 1) % 16; } while (1); - rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } @@ -926,13 +972,14 @@ static int handle_tprot(struct kvm_vcpu *vcpu) unsigned long hva, gpa; int ret = 0, cc = 0; bool writable; + ar_t ar; 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); + kvm_s390_get_base_disp_sse(vcpu, &address1, &address2, &ar, NULL); /* we only handle the Linux memory detection case: * access key == 0 @@ -941,11 +988,11 @@ static int handle_tprot(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) ipte_lock(vcpu); - ret = guest_translate_address(vcpu, address1, &gpa, 1); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 1); if (ret == PGM_PROTECTION) { /* Write protected? Try again with read-only... */ cc = 1; - ret = guest_translate_address(vcpu, address1, &gpa, 0); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 0); } if (ret) { if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 6651f9f..72e58bd 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -26,15 +26,17 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, struct kvm_s390_local_interrupt *li; int cpuflags; int rc; + int ext_call_pending; li = &dst_vcpu->arch.local_int; cpuflags = atomic_read(li->cpuflags); - if (!(cpuflags & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED))) + ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu); + if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending) rc = SIGP_CC_ORDER_CODE_ACCEPTED; else { *reg &= 0xffffffff00000000UL; - if (cpuflags & CPUSTAT_ECALL_PEND) + if (ext_call_pending) *reg |= SIGP_STATUS_EXT_CALL_PENDING; if (cpuflags & CPUSTAT_STOPPED) *reg |= SIGP_STATUS_STOPPED; @@ -96,7 +98,7 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, } static int __sigp_external_call(struct kvm_vcpu *vcpu, - struct kvm_vcpu *dst_vcpu) + struct kvm_vcpu *dst_vcpu, u64 *reg) { struct kvm_s390_irq irq = { .type = KVM_S390_INT_EXTERNAL_CALL, @@ -105,45 +107,31 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, int rc; rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); - if (!rc) + if (rc == -EBUSY) { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_EXT_CALL_PENDING; + return SIGP_CC_STATUS_STORED; + } else if (rc == 0) { VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", dst_vcpu->vcpu_id); - - return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; -} - -static int __inject_sigp_stop(struct kvm_vcpu *dst_vcpu, int action) -{ - struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int; - int rc = SIGP_CC_ORDER_CODE_ACCEPTED; - - spin_lock(&li->lock); - if (li->action_bits & ACTION_STOP_ON_STOP) { - /* another SIGP STOP is pending */ - rc = SIGP_CC_BUSY; - goto out; - } - if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { - if ((action & ACTION_STORE_ON_STOP) != 0) - rc = -ESHUTDOWN; - goto out; } - set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); - li->action_bits |= action; - atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); - kvm_s390_vcpu_wakeup(dst_vcpu); -out: - spin_unlock(&li->lock); - return rc; + return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; } static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu) { + struct kvm_s390_irq irq = { + .type = KVM_S390_SIGP_STOP, + }; int rc; - rc = __inject_sigp_stop(dst_vcpu, ACTION_STOP_ON_STOP); - VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", dst_vcpu->vcpu_id); + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) + rc = SIGP_CC_BUSY; + else if (rc == 0) + VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", + dst_vcpu->vcpu_id); return rc; } @@ -151,20 +139,18 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu) static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, u64 *reg) { + struct kvm_s390_irq irq = { + .type = KVM_S390_SIGP_STOP, + .u.stop.flags = KVM_S390_STOP_FLAG_STORE_STATUS, + }; int rc; - rc = __inject_sigp_stop(dst_vcpu, ACTION_STOP_ON_STOP | - ACTION_STORE_ON_STOP); - VCPU_EVENT(vcpu, 4, "sent sigp stop and store status to cpu %x", - dst_vcpu->vcpu_id); - - if (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); - } + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) + rc = SIGP_CC_BUSY; + else if (rc == 0) + VCPU_EVENT(vcpu, 4, "sent sigp stop and store status to cpu %x", + dst_vcpu->vcpu_id); return rc; } @@ -197,41 +183,33 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, u32 address, u64 *reg) { - struct kvm_s390_local_interrupt *li; + struct kvm_s390_irq irq = { + .type = KVM_S390_SIGP_SET_PREFIX, + .u.prefix.address = address & 0x7fffe000u, + }; int rc; - 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)) { + if (kvm_is_error_gpa(vcpu->kvm, irq.u.prefix.address)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INVALID_PARAMETER; return SIGP_CC_STATUS_STORED; } - spin_lock(&li->lock); - /* cpu must be in stopped state */ - if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INCORRECT_STATE; - rc = SIGP_CC_STATUS_STORED; - goto out_li; + return SIGP_CC_STATUS_STORED; + } else if (rc == 0) { + VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", + dst_vcpu->vcpu_id, irq.u.prefix.address); } - li->irq.prefix.address = address; - set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); - kvm_s390_vcpu_wakeup(dst_vcpu); - rc = SIGP_CC_ORDER_CODE_ACCEPTED; - - VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", dst_vcpu->vcpu_id, - address); -out_li: - spin_unlock(&li->lock); return rc; } @@ -242,9 +220,7 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, int flags; int rc; - spin_lock(&dst_vcpu->arch.local_int.lock); flags = atomic_read(dst_vcpu->arch.local_int.cpuflags); - spin_unlock(&dst_vcpu->arch.local_int.lock); if (!(flags & CPUSTAT_STOPPED)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INCORRECT_STATE; @@ -291,8 +267,9 @@ static int __prepare_sigp_re_start(struct kvm_vcpu *vcpu, /* handle (RE)START in user space */ int rc = -EOPNOTSUPP; + /* make sure we don't race with STOP irq injection */ spin_lock(&li->lock); - if (li->action_bits & ACTION_STOP_ON_STOP) + if (kvm_s390_is_stop_irq_pending(dst_vcpu)) rc = SIGP_CC_BUSY; spin_unlock(&li->lock); @@ -333,7 +310,7 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, break; case SIGP_EXTERNAL_CALL: vcpu->stat.instruction_sigp_external_call++; - rc = __sigp_external_call(vcpu, dst_vcpu); + rc = __sigp_external_call(vcpu, dst_vcpu, status_reg); break; case SIGP_EMERGENCY_SIGNAL: vcpu->stat.instruction_sigp_emergency++; @@ -394,6 +371,56 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, return rc; } +static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code) +{ + if (!vcpu->kvm->arch.user_sigp) + return 0; + + switch (order_code) { + case SIGP_SENSE: + case SIGP_EXTERNAL_CALL: + case SIGP_EMERGENCY_SIGNAL: + case SIGP_COND_EMERGENCY_SIGNAL: + case SIGP_SENSE_RUNNING: + return 0; + /* update counters as we're directly dropping to user space */ + case SIGP_STOP: + vcpu->stat.instruction_sigp_stop++; + break; + case SIGP_STOP_AND_STORE_STATUS: + vcpu->stat.instruction_sigp_stop_store_status++; + break; + case SIGP_STORE_STATUS_AT_ADDRESS: + vcpu->stat.instruction_sigp_store_status++; + break; + case SIGP_STORE_ADDITIONAL_STATUS: + vcpu->stat.instruction_sigp_store_adtl_status++; + break; + case SIGP_SET_PREFIX: + vcpu->stat.instruction_sigp_prefix++; + break; + case SIGP_START: + vcpu->stat.instruction_sigp_start++; + break; + case SIGP_RESTART: + vcpu->stat.instruction_sigp_restart++; + break; + case SIGP_INITIAL_CPU_RESET: + vcpu->stat.instruction_sigp_init_cpu_reset++; + break; + case SIGP_CPU_RESET: + vcpu->stat.instruction_sigp_cpu_reset++; + break; + default: + vcpu->stat.instruction_sigp_unknown++; + } + + VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space", + order_code); + + return 1; +} + int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) { int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; @@ -407,7 +434,9 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - order_code = kvm_s390_get_base_disp_rs(vcpu); + order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); + if (handle_sigp_order_in_user_space(vcpu, order_code)) + return -EOPNOTSUPP; if (r1 % 2) parameter = vcpu->run->s.regs.gprs[r1]; @@ -447,7 +476,7 @@ 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); + u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h index 647e9d6..653a7ec 100644 --- a/arch/s390/kvm/trace-s390.h +++ b/arch/s390/kvm/trace-s390.h @@ -209,19 +209,21 @@ TRACE_EVENT(kvm_s390_request_resets, * Trace point for a vcpu's stop requests. */ TRACE_EVENT(kvm_s390_stop_request, - TP_PROTO(unsigned int action_bits), - TP_ARGS(action_bits), + TP_PROTO(unsigned char stop_irq, unsigned char flags), + TP_ARGS(stop_irq, flags), TP_STRUCT__entry( - __field(unsigned int, action_bits) + __field(unsigned char, stop_irq) + __field(unsigned char, flags) ), TP_fast_assign( - __entry->action_bits = action_bits; + __entry->stop_irq = stop_irq; + __entry->flags = flags; ), - TP_printk("stop request, action_bits = %08x", - __entry->action_bits) + TP_printk("stop request, stop irq = %u, flags = %08x", + __entry->stop_irq, __entry->flags) ); diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 034a35a..d6c9991 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -12,7 +12,15 @@ #include <linux/smp.h> #include <asm/io.h> -int spin_retry = 1000; +int spin_retry = -1; + +static int __init spin_retry_init(void) +{ + if (spin_retry < 0) + spin_retry = MACHINE_HAS_CAD ? 10 : 1000; + return 0; +} +early_initcall(spin_retry_init); /** * spin_retry= parameter @@ -24,6 +32,11 @@ static int __init spin_retry_setup(char *str) } __setup("spin_retry=", spin_retry_setup); +static inline void _raw_compare_and_delay(unsigned int *lock, unsigned int old) +{ + asm(".insn rsy,0xeb0000000022,%0,0,%1" : : "d" (old), "Q" (*lock)); +} + void arch_spin_lock_wait(arch_spinlock_t *lp) { unsigned int cpu = SPINLOCK_LOCKVAL; @@ -46,6 +59,8 @@ void arch_spin_lock_wait(arch_spinlock_t *lp) /* Loop for a while on the lock value. */ count = spin_retry; do { + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&lp->lock, owner); owner = ACCESS_ONCE(lp->lock); } while (owner && count-- > 0); if (!owner) @@ -84,6 +99,8 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags) /* Loop for a while on the lock value. */ count = spin_retry; do { + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&lp->lock, owner); owner = ACCESS_ONCE(lp->lock); } while (owner && count-- > 0); if (!owner) @@ -100,11 +117,19 @@ EXPORT_SYMBOL(arch_spin_lock_wait_flags); int arch_spin_trylock_retry(arch_spinlock_t *lp) { + unsigned int cpu = SPINLOCK_LOCKVAL; + unsigned int owner; int count; - for (count = spin_retry; count > 0; count--) - if (arch_spin_trylock_once(lp)) - return 1; + for (count = spin_retry; count > 0; count--) { + 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 1; + } else if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&lp->lock, owner); + } return 0; } EXPORT_SYMBOL(arch_spin_trylock_retry); @@ -126,8 +151,11 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) } old = ACCESS_ONCE(rw->lock); owner = ACCESS_ONCE(rw->owner); - if ((int) old < 0) + if ((int) old < 0) { + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&rw->lock, old); continue; + } if (_raw_compare_and_swap(&rw->lock, old, old + 1)) return; } @@ -141,8 +169,11 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw) while (count-- > 0) { old = ACCESS_ONCE(rw->lock); - if ((int) old < 0) + if ((int) old < 0) { + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&rw->lock, old); continue; + } if (_raw_compare_and_swap(&rw->lock, old, old + 1)) return 1; } @@ -173,6 +204,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev) } if ((old & 0x7fffffff) == 0 && (int) prev >= 0) break; + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&rw->lock, old); } } EXPORT_SYMBOL(_raw_write_lock_wait); @@ -201,6 +234,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw) smp_rmb(); if ((old & 0x7fffffff) == 0 && (int) prev >= 0) break; + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&rw->lock, old); } } EXPORT_SYMBOL(_raw_write_lock_wait); @@ -214,8 +249,11 @@ int _raw_write_trylock_retry(arch_rwlock_t *rw) while (count-- > 0) { old = ACCESS_ONCE(rw->lock); - if (old) + if (old) { + if (MACHINE_HAS_CAD) + _raw_compare_and_delay(&rw->lock, old); continue; + } if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000)) return 1; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 9065d5a..3ff8653 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -171,7 +171,7 @@ static void dump_pagetable(unsigned long asce, unsigned long address) table = table + ((address >> 20) & 0x7ff); if (bad_address(table)) goto bad; - pr_cont(KERN_CONT "S:%016lx ", *table); + pr_cont("S:%016lx ", *table); if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE)) goto out; table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); @@ -261,7 +261,7 @@ static inline void report_user_fault(struct pt_regs *regs, long signr) return; if (!printk_ratelimit()) return; - printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d", + printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ", regs->int_code & 0xffff, regs->int_code >> 17); print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN); printk(KERN_CONT "\n"); diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 639fce46..5c586c7 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -235,10 +235,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, /* 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); + ret = get_user_pages_unlocked(current, mm, start, + nr_pages - nr, write, 0, pages); /* Have to be a bit careful with return values */ if (nr > 0) ret = (ret < 0) ? nr : ret + nr; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 3c80d2e..210ffed 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -192,12 +192,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, - int write) -{ - return ERR_PTR(-EINVAL); -} - int pmd_huge(pmd_t pmd) { if (!MACHINE_HAS_HPAGE) @@ -210,17 +204,3 @@ int pud_huge(pud_t pud) { return 0; } - -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmdp, int write) -{ - struct page *page; - - if (!MACHINE_HAS_HPAGE) - return NULL; - - page = pmd_page(*pmdp); - if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); - return page; -} diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c7235e0..d35b151 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -71,13 +71,16 @@ static void __init setup_zero_pages(void) break; case 0x2827: /* zEC12 */ case 0x2828: /* zEC12 */ - default: order = 5; break; + case 0x2964: /* z13 */ + default: + order = 7; + break; } /* Limit number of empty zero pages for small memory sizes */ - if (order > 2 && totalram_pages <= 16384) - order = 2; + while (order > 2 && (totalram_pages >> 10) < (1UL << order)) + order--; empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!empty_zero_page) diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 9b436c2..179a2c2 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -28,8 +28,12 @@ #include <linux/module.h> #include <linux/random.h> #include <linux/compat.h> +#include <linux/security.h> #include <asm/pgalloc.h> +unsigned long mmap_rnd_mask; +unsigned long mmap_align_mask; + static unsigned long stack_maxrandom_size(void) { if (!(current->flags & PF_RANDOMIZE)) @@ -60,8 +64,10 @@ static unsigned long mmap_rnd(void) { if (!(current->flags & PF_RANDOMIZE)) return 0; - /* 8MB randomization for mmap_base */ - return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; + if (is_32bit_task()) + return (get_random_int() & 0x7ff) << PAGE_SHIFT; + else + return (get_random_int() & mmap_rnd_mask) << PAGE_SHIFT; } static unsigned long mmap_base_legacy(void) @@ -81,6 +87,109 @@ static inline unsigned long mmap_base(void) return STACK_TOP - stack_maxrandom_size() - mmap_rnd() - gap; } +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + struct vm_unmapped_area_info info; + int do_color_align; + + if (len > TASK_SIZE - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) + return addr; + + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vma->vm_start)) + return addr; + } + + do_color_align = 0; + if (filp || (flags & MAP_SHARED)) + do_color_align = !is_32bit_task(); + + info.flags = 0; + info.length = len; + info.low_limit = mm->mmap_base; + info.high_limit = TASK_SIZE; + info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0; + info.align_offset = pgoff << PAGE_SHIFT; + return vm_unmapped_area(&info); +} + +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) +{ + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + unsigned long addr = addr0; + struct vm_unmapped_area_info info; + int do_color_align; + + /* requested length too big for entire address space */ + if (len > TASK_SIZE - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) + return addr; + + /* requesting a specific address */ + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vma->vm_start)) + return addr; + } + + do_color_align = 0; + if (filp || (flags & MAP_SHARED)) + do_color_align = !is_32bit_task(); + + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.high_limit = mm->mmap_base; + info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0; + info.align_offset = pgoff << PAGE_SHIFT; + addr = vm_unmapped_area(&info); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + if (addr & ~PAGE_MASK) { + VM_BUG_ON(addr != -ENOMEM); + info.flags = 0; + info.low_limit = TASK_UNMAPPED_BASE; + info.high_limit = TASK_SIZE; + addr = vm_unmapped_area(&info); + } + + return addr; +} + +unsigned long randomize_et_dyn(void) +{ + unsigned long base; + + base = STACK_TOP / 3 * 2; + if (!is_32bit_task()) + /* Align to 4GB */ + base &= ~((1UL << 32) - 1); + return base + mmap_rnd(); +} + #ifndef CONFIG_64BIT /* @@ -177,4 +286,36 @@ void arch_pick_mmap_layout(struct mm_struct *mm) } } +static int __init setup_mmap_rnd(void) +{ + struct cpuid cpu_id; + + get_cpu_id(&cpu_id); + switch (cpu_id.machine) { + case 0x9672: + case 0x2064: + case 0x2066: + case 0x2084: + case 0x2086: + case 0x2094: + case 0x2096: + case 0x2097: + case 0x2098: + case 0x2817: + case 0x2818: + case 0x2827: + case 0x2828: + mmap_rnd_mask = 0x7ffUL; + mmap_align_mask = 0UL; + break; + case 0x2964: /* z13 */ + default: + mmap_rnd_mask = 0x3ff80UL; + mmap_align_mask = 0x7fUL; + break; + } + return 0; +} +early_initcall(setup_mmap_rnd); + #endif diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3cf8cc0..b2c1542 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -527,7 +527,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) table += (gaddr >> 53) & 0x7ff; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY, - gaddr & 0xffe0000000000000)) + gaddr & 0xffe0000000000000UL)) return -ENOMEM; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); } @@ -535,7 +535,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) table += (gaddr >> 42) & 0x7ff; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY, - gaddr & 0xfffffc0000000000)) + gaddr & 0xfffffc0000000000UL)) return -ENOMEM; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); } @@ -543,7 +543,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) table += (gaddr >> 31) & 0x7ff; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY, - gaddr & 0xffffffff80000000)) + gaddr & 0xffffffff80000000UL)) return -ENOMEM; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 3290f11..b2c76f6 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -259,7 +259,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) } /* Create a virtual mapping cookie for a PCI BAR */ -void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max) +void __iomem *pci_iomap_range(struct pci_dev *pdev, + int bar, + unsigned long offset, + unsigned long max) { struct zpci_dev *zdev = get_zdev(pdev); u64 addr; @@ -270,14 +273,27 @@ void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max) idx = zdev->bars[bar].map_idx; spin_lock(&zpci_iomap_lock); - zpci_iomap_start[idx].fh = zdev->fh; - zpci_iomap_start[idx].bar = bar; + if (zpci_iomap_start[idx].count++) { + BUG_ON(zpci_iomap_start[idx].fh != zdev->fh || + zpci_iomap_start[idx].bar != bar); + } else { + zpci_iomap_start[idx].fh = zdev->fh; + zpci_iomap_start[idx].bar = bar; + } + /* Detect overrun */ + BUG_ON(!zpci_iomap_start[idx].count); spin_unlock(&zpci_iomap_lock); addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48); - return (void __iomem *) addr; + return (void __iomem *) addr + offset; +} +EXPORT_SYMBOL(pci_iomap_range); + +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) +{ + return pci_iomap_range(dev, bar, 0, maxlen); } -EXPORT_SYMBOL_GPL(pci_iomap); +EXPORT_SYMBOL(pci_iomap); void pci_iounmap(struct pci_dev *pdev, void __iomem *addr) { @@ -285,11 +301,15 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr) idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48; spin_lock(&zpci_iomap_lock); - zpci_iomap_start[idx].fh = 0; - zpci_iomap_start[idx].bar = 0; + /* Detect underrun */ + BUG_ON(!zpci_iomap_start[idx].count); + if (!--zpci_iomap_start[idx].count) { + zpci_iomap_start[idx].fh = 0; + zpci_iomap_start[idx].bar = 0; + } spin_unlock(&zpci_iomap_lock); } -EXPORT_SYMBOL_GPL(pci_iounmap); +EXPORT_SYMBOL(pci_iounmap); static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) @@ -463,9 +483,8 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) airq_iv_free_bit(zpci_aisb_iv, zdev->aisb); } -static void zpci_map_resources(struct zpci_dev *zdev) +static void zpci_map_resources(struct pci_dev *pdev) { - struct pci_dev *pdev = zdev->pdev; resource_size_t len; int i; @@ -479,9 +498,8 @@ static void zpci_map_resources(struct zpci_dev *zdev) } } -static void zpci_unmap_resources(struct zpci_dev *zdev) +static void zpci_unmap_resources(struct pci_dev *pdev) { - struct pci_dev *pdev = zdev->pdev; resource_size_t len; int i; @@ -631,7 +649,7 @@ int pcibios_add_device(struct pci_dev *pdev) zdev->pdev = pdev; pdev->dev.groups = zpci_attr_groups; - zpci_map_resources(zdev); + zpci_map_resources(pdev); for (i = 0; i < PCI_BAR_COUNT; i++) { res = &pdev->resource[i]; @@ -643,6 +661,11 @@ int pcibios_add_device(struct pci_dev *pdev) return 0; } +void pcibios_release_device(struct pci_dev *pdev) +{ + zpci_unmap_resources(pdev); +} + int pcibios_enable_device(struct pci_dev *pdev, int mask) { struct zpci_dev *zdev = get_zdev(pdev); @@ -650,7 +673,6 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask) zdev->pdev = pdev; zpci_debug_init_device(zdev); zpci_fmb_enable_device(zdev); - zpci_map_resources(zdev); return pci_enable_resources(pdev, mask); } @@ -659,7 +681,6 @@ 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; @@ -668,7 +689,8 @@ void pcibios_disable_device(struct pci_dev *pdev) #ifdef CONFIG_HIBERNATE_CALLBACKS static int zpci_restore(struct device *dev) { - struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); int ret = 0; if (zdev->state != ZPCI_FN_STATE_ONLINE) @@ -678,7 +700,7 @@ static int zpci_restore(struct device *dev) if (ret) goto out; - zpci_map_resources(zdev); + zpci_map_resources(pdev); zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET, zdev->start_dma + zdev->iommu_size - 1, (u64) zdev->dma_table); @@ -689,12 +711,14 @@ out: static int zpci_freeze(struct device *dev) { - struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); if (zdev->state != ZPCI_FN_STATE_ONLINE) return 0; zpci_unregister_ioat(zdev, 0); + zpci_unmap_resources(pdev); return clp_disable_fh(zdev); } @@ -756,8 +780,8 @@ static int zpci_scan_bus(struct zpci_dev *zdev) zpci_cleanup_bus_resources(zdev); return -EIO; } - zdev->bus->max_bus_speed = zdev->max_bus_speed; + pci_bus_add_devices(zdev->bus); return 0; } diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 62c5ea6..b1bb2b7 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -55,7 +55,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, ret = get_pfn(mmio_addr, VM_WRITE, &pfn); if (ret) goto out; - io_addr = (void *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); + io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); ret = -EFAULT; if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) @@ -64,8 +64,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, if (copy_from_user(buf, user_buffer, length)) goto out; - memcpy_toio(io_addr, buf, length); - ret = 0; + ret = zpci_memcpy_toio(io_addr, buf, length); out: if (buf != local_buf) kfree(buf); @@ -96,18 +95,18 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, ret = get_pfn(mmio_addr, VM_READ, &pfn); if (ret) goto out; - io_addr = (void *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); + io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); - ret = -EFAULT; - if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) + if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) { + ret = -EFAULT; goto out; - - memcpy_fromio(buf, io_addr, length); - - if (copy_to_user(user_buffer, buf, length)) + } + ret = zpci_memcpy_fromio(buf, io_addr, length); + if (ret) goto out; + if (copy_to_user(user_buffer, buf, length)) + ret = -EFAULT; - ret = 0; out: if (buf != local_buf) kfree(buf); |