diff options
Diffstat (limited to 'arch')
125 files changed, 1716 insertions, 2366 deletions
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 9fee37e2596..32ca1b92730 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -981,27 +981,18 @@ asmlinkage int osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval32 __user *tvp) { - fd_set_bits fds; - char *bits; - size_t size; - long timeout; - int ret = -EINVAL; - struct fdtable *fdt; - int max_fds; - - timeout = MAX_SCHEDULE_TIMEOUT; + s64 timeout = MAX_SCHEDULE_TIMEOUT; if (tvp) { time_t sec, usec; if (!access_ok(VERIFY_READ, tvp, sizeof(*tvp)) || __get_user(sec, &tvp->tv_sec) || __get_user(usec, &tvp->tv_usec)) { - ret = -EFAULT; - goto out_nofds; + return -EFAULT; } if (sec < 0 || usec < 0) - goto out_nofds; + return -EINVAL; if ((unsigned long) sec < MAX_SELECT_SECONDS) { timeout = (usec + 1000000/HZ - 1) / (1000000/HZ); @@ -1009,60 +1000,8 @@ osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, } } - rcu_read_lock(); - fdt = files_fdtable(current->files); - max_fds = fdt->max_fds; - rcu_read_unlock(); - if (n < 0 || n > max_fds) - goto out_nofds; - - /* - * We need 6 bitmaps (in/out/ex for both incoming and outgoing), - * since we used fdset we need to allocate memory in units of - * long-words. - */ - ret = -ENOMEM; - size = FDS_BYTES(n); - bits = kmalloc(6 * size, GFP_KERNEL); - if (!bits) - goto out_nofds; - fds.in = (unsigned long *) bits; - fds.out = (unsigned long *) (bits + size); - fds.ex = (unsigned long *) (bits + 2*size); - fds.res_in = (unsigned long *) (bits + 3*size); - fds.res_out = (unsigned long *) (bits + 4*size); - fds.res_ex = (unsigned long *) (bits + 5*size); - - if ((ret = get_fd_set(n, inp->fds_bits, fds.in)) || - (ret = get_fd_set(n, outp->fds_bits, fds.out)) || - (ret = get_fd_set(n, exp->fds_bits, fds.ex))) - goto out; - zero_fd_set(n, fds.res_in); - zero_fd_set(n, fds.res_out); - zero_fd_set(n, fds.res_ex); - - ret = do_select(n, &fds, &timeout); - /* OSF does not copy back the remaining time. */ - - if (ret < 0) - goto out; - if (!ret) { - ret = -ERESTARTNOHAND; - if (signal_pending(current)) - goto out; - ret = 0; - } - - if (set_fd_set(n, inp->fds_bits, fds.res_in) || - set_fd_set(n, outp->fds_bits, fds.res_out) || - set_fd_set(n, exp->fds_bits, fds.res_ex)) - ret = -EFAULT; - - out: - kfree(bits); - out_nofds: - return ret; + return core_sys_select(n, inp, outp, exp, &timeout); } struct rusage32 { diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index 9bd1870d980..0128687ba0f 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -34,23 +34,6 @@ extern unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr); -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - /* common code for old and new mmaps */ inline long do_mmap2( unsigned long addr, unsigned long len, diff --git a/arch/avr32/kernel/sys_avr32.c b/arch/avr32/kernel/sys_avr32.c index 8deb6003ee6..8e8911e55c8 100644 --- a/arch/avr32/kernel/sys_avr32.c +++ b/arch/avr32/kernel/sys_avr32.c @@ -14,19 +14,6 @@ #include <asm/mman.h> #include <asm/uaccess.h> -asmlinkage int sys_pipe(unsigned long __user *filedes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(filedes, fd, sizeof(fd))) - error = -EFAULT; - } - return error; -} - asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, off_t offset) diff --git a/arch/blackfin/kernel/sys_bfin.c b/arch/blackfin/kernel/sys_bfin.c index efb7b25a263..fce49d7cf00 100644 --- a/arch/blackfin/kernel/sys_bfin.c +++ b/arch/blackfin/kernel/sys_bfin.c @@ -45,23 +45,6 @@ #include <asm/cacheflush.h> #include <asm/dma.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2 * sizeof(int))) - error = -EFAULT; - } - return error; -} - /* common code for old and new mmaps */ static inline long do_mmap2(unsigned long addr, unsigned long len, diff --git a/arch/cris/kernel/sys_cris.c b/arch/cris/kernel/sys_cris.c index 8b9984197ed..d124066e172 100644 --- a/arch/cris/kernel/sys_cris.c +++ b/arch/cris/kernel/sys_cris.c @@ -40,8 +40,11 @@ asmlinkage int sys_pipe(unsigned long __user * fildes) error = do_pipe(fd); unlock_kernel(); if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) + if (copy_to_user(fildes, fd, 2*sizeof(int))) { + sys_close(fd[0]); + sys_close(fd[1]); error = -EFAULT; + } } return error; } diff --git a/arch/frv/kernel/sys_frv.c b/arch/frv/kernel/sys_frv.c index 04c6b1677cc..49b2cf2c38f 100644 --- a/arch/frv/kernel/sys_frv.c +++ b/arch/frv/kernel/sys_frv.c @@ -28,23 +28,6 @@ #include <asm/setup.h> #include <asm/uaccess.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -asmlinkage long sys_pipe(unsigned long __user * fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/frv/mm/Makefile b/arch/frv/mm/Makefile index fb8b1d860f4..1bca5ab8a6a 100644 --- a/arch/frv/mm/Makefile +++ b/arch/frv/mm/Makefile @@ -6,4 +6,4 @@ obj-y := init.o kmap.o obj-$(CONFIG_MMU) += \ pgalloc.o highmem.o fault.o extable.o cache-page.o tlb-flush.o tlb-miss.o \ - mmu-context.o dma-alloc.o unaligned.o elf-fdpic.o + mmu-context.o dma-alloc.o elf-fdpic.o diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c index 00608be6d56..2745656dcc5 100644 --- a/arch/h8300/kernel/sys_h8300.c +++ b/arch/h8300/kernel/sys_h8300.c @@ -27,23 +27,6 @@ #include <asm/traps.h> #include <asm/unistd.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long * fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - /* common code for old and new mmaps */ static inline long do_mmap2( unsigned long addr, unsigned long len, diff --git a/arch/ia64/ia32/ia32_signal.c b/arch/ia64/ia32/ia32_signal.c index 256a7faeda0..b763ca19ef1 100644 --- a/arch/ia64/ia32/ia32_signal.c +++ b/arch/ia64/ia32/ia32_signal.c @@ -463,7 +463,7 @@ sys32_sigsuspend (int history0, int history1, old_sigset_t mask) current->state = TASK_INTERRUPTIBLE; schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); + set_restore_sigmask(); return -ERESTARTNOHAND; } diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index c7467f863c7..19709a07963 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -966,7 +966,7 @@ acpi_map_iosapics (void) fs_initcall(acpi_map_iosapics); #endif /* CONFIG_ACPI_NUMA */ -int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) +int __ref acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) { int err; diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index 6dee579f205..7fd18f54c05 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -183,10 +183,10 @@ void fixup_irqs(void) { unsigned int irq; extern void ia64_process_pending_intr(void); - extern void ia64_disable_timer(void); extern volatile int time_keeper_id; - ia64_disable_timer(); + /* Mask ITV to disable timer */ + ia64_set_itv(1 << 16); /* * Find a new timesync master diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 396004e8cd1..4547a2092af 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -1053,7 +1053,7 @@ static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block palinfo_cpu_notifier __cpuinitdata = +static struct notifier_block __refdata palinfo_cpu_notifier = { .notifier_call = palinfo_cpu_callback, .priority = 0, diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 7fbb51e10bb..c1ad27de2dd 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -867,7 +867,7 @@ pfm_rvfree(void *mem, unsigned long size) } static pfm_context_t * -pfm_context_alloc(void) +pfm_context_alloc(int ctx_flags) { pfm_context_t *ctx; @@ -878,6 +878,46 @@ pfm_context_alloc(void) ctx = kzalloc(sizeof(pfm_context_t), GFP_KERNEL); if (ctx) { DPRINT(("alloc ctx @%p\n", ctx)); + + /* + * init context protection lock + */ + spin_lock_init(&ctx->ctx_lock); + + /* + * context is unloaded + */ + ctx->ctx_state = PFM_CTX_UNLOADED; + + /* + * initialization of context's flags + */ + ctx->ctx_fl_block = (ctx_flags & PFM_FL_NOTIFY_BLOCK) ? 1 : 0; + ctx->ctx_fl_system = (ctx_flags & PFM_FL_SYSTEM_WIDE) ? 1: 0; + ctx->ctx_fl_no_msg = (ctx_flags & PFM_FL_OVFL_NO_MSG) ? 1: 0; + /* + * will move to set properties + * ctx->ctx_fl_excl_idle = (ctx_flags & PFM_FL_EXCL_IDLE) ? 1: 0; + */ + + /* + * init restart semaphore to locked + */ + init_completion(&ctx->ctx_restart_done); + + /* + * activation is used in SMP only + */ + ctx->ctx_last_activation = PFM_INVALID_ACTIVATION; + SET_LAST_CPU(ctx, -1); + + /* + * initialize notification message queue + */ + ctx->ctx_msgq_head = ctx->ctx_msgq_tail = 0; + init_waitqueue_head(&ctx->ctx_msgq_wait); + init_waitqueue_head(&ctx->ctx_zombieq); + } return ctx; } @@ -2165,28 +2205,21 @@ static struct dentry_operations pfmfs_dentry_operations = { }; -static int -pfm_alloc_fd(struct file **cfile) +static struct file * +pfm_alloc_file(pfm_context_t *ctx) { - int fd, ret = 0; - struct file *file = NULL; - struct inode * inode; + struct file *file; + struct inode *inode; + struct dentry *dentry; char name[32]; struct qstr this; - fd = get_unused_fd(); - if (fd < 0) return -ENFILE; - - ret = -ENFILE; - - file = get_empty_filp(); - if (!file) goto out; - /* * allocate a new inode */ inode = new_inode(pfmfs_mnt->mnt_sb); - if (!inode) goto out; + if (!inode) + return ERR_PTR(-ENOMEM); DPRINT(("new inode ino=%ld @%p\n", inode->i_ino, inode)); @@ -2199,59 +2232,28 @@ pfm_alloc_fd(struct file **cfile) this.len = strlen(name); this.hash = inode->i_ino; - ret = -ENOMEM; - /* * allocate a new dcache entry */ - file->f_path.dentry = d_alloc(pfmfs_mnt->mnt_sb->s_root, &this); - if (!file->f_path.dentry) goto out; + dentry = d_alloc(pfmfs_mnt->mnt_sb->s_root, &this); + if (!dentry) { + iput(inode); + return ERR_PTR(-ENOMEM); + } - file->f_path.dentry->d_op = &pfmfs_dentry_operations; + dentry->d_op = &pfmfs_dentry_operations; + d_add(dentry, inode); - d_add(file->f_path.dentry, inode); - file->f_path.mnt = mntget(pfmfs_mnt); - file->f_mapping = inode->i_mapping; + file = alloc_file(pfmfs_mnt, dentry, FMODE_READ, &pfm_file_ops); + if (!file) { + dput(dentry); + return ERR_PTR(-ENFILE); + } - file->f_op = &pfm_file_ops; - file->f_mode = FMODE_READ; file->f_flags = O_RDONLY; - file->f_pos = 0; - - /* - * may have to delay until context is attached? - */ - fd_install(fd, file); - - /* - * the file structure we will use - */ - *cfile = file; - - return fd; -out: - if (file) put_filp(file); - put_unused_fd(fd); - return ret; -} - -static void -pfm_free_fd(int fd, struct file *file) -{ - struct files_struct *files = current->files; - struct fdtable *fdt; + file->private_data = ctx; - /* - * there ie no fd_uninstall(), so we do it here - */ - spin_lock(&files->file_lock); - fdt = files_fdtable(files); - rcu_assign_pointer(fdt->fd[fd], NULL); - spin_unlock(&files->file_lock); - - if (file) - put_filp(file); - put_unused_fd(fd); + return file; } static int @@ -2475,6 +2477,7 @@ pfm_setup_buffer_fmt(struct task_struct *task, struct file *filp, pfm_context_t /* link buffer format and context */ ctx->ctx_buf_fmt = fmt; + ctx->ctx_fl_is_sampling = 1; /* assume record() is defined */ /* * check if buffer format wants to use perfmon buffer allocation/mapping service @@ -2669,78 +2672,45 @@ pfm_context_create(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg { pfarg_context_t *req = (pfarg_context_t *)arg; struct file *filp; + struct path path; int ctx_flags; + int fd; int ret; /* let's check the arguments first */ ret = pfarg_is_sane(current, req); - if (ret < 0) return ret; + if (ret < 0) + return ret; ctx_flags = req->ctx_flags; ret = -ENOMEM; - ctx = pfm_context_alloc(); - if (!ctx) goto error; + fd = get_unused_fd(); + if (fd < 0) + return fd; - ret = pfm_alloc_fd(&filp); - if (ret < 0) goto error_file; + ctx = pfm_context_alloc(ctx_flags); + if (!ctx) + goto error; - req->ctx_fd = ctx->ctx_fd = ret; + filp = pfm_alloc_file(ctx); + if (IS_ERR(filp)) { + ret = PTR_ERR(filp); + goto error_file; + } - /* - * attach context to file - */ - filp->private_data = ctx; + req->ctx_fd = ctx->ctx_fd = fd; /* * does the user want to sample? */ if (pfm_uuid_cmp(req->ctx_smpl_buf_id, pfm_null_uuid)) { ret = pfm_setup_buffer_fmt(current, filp, ctx, ctx_flags, 0, req); - if (ret) goto buffer_error; + if (ret) + goto buffer_error; } - /* - * init context protection lock - */ - spin_lock_init(&ctx->ctx_lock); - - /* - * context is unloaded - */ - ctx->ctx_state = PFM_CTX_UNLOADED; - - /* - * initialization of context's flags - */ - ctx->ctx_fl_block = (ctx_flags & PFM_FL_NOTIFY_BLOCK) ? 1 : 0; - ctx->ctx_fl_system = (ctx_flags & PFM_FL_SYSTEM_WIDE) ? 1: 0; - ctx->ctx_fl_is_sampling = ctx->ctx_buf_fmt ? 1 : 0; /* assume record() is defined */ - ctx->ctx_fl_no_msg = (ctx_flags & PFM_FL_OVFL_NO_MSG) ? 1: 0; - /* - * will move to set properties - * ctx->ctx_fl_excl_idle = (ctx_flags & PFM_FL_EXCL_IDLE) ? 1: 0; - */ - - /* - * init restart semaphore to locked - */ - init_completion(&ctx->ctx_restart_done); - - /* - * activation is used in SMP only - */ - ctx->ctx_last_activation = PFM_INVALID_ACTIVATION; - SET_LAST_CPU(ctx, -1); - - /* - * initialize notification message queue - */ - ctx->ctx_msgq_head = ctx->ctx_msgq_tail = 0; - init_waitqueue_head(&ctx->ctx_msgq_wait); - init_waitqueue_head(&ctx->ctx_zombieq); - DPRINT(("ctx=%p flags=0x%x system=%d notify_block=%d excl_idle=%d no_msg=%d ctx_fd=%d \n", ctx, ctx_flags, @@ -2755,10 +2725,14 @@ pfm_context_create(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg */ pfm_reset_pmu_state(ctx); + fd_install(fd, filp); + return 0; buffer_error: - pfm_free_fd(ctx->ctx_fd, filp); + path = filp->f_path; + put_filp(filp); + path_put(&path); if (ctx->ctx_buf_fmt) { pfm_buf_fmt_exit(ctx->ctx_buf_fmt, current, NULL, regs); @@ -2767,6 +2741,7 @@ error_file: pfm_context_free(ctx); error: + put_unused_fd(fd); return ret; } diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index 5740296c35a..19c5a78636f 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -464,7 +464,7 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) if (!user_mode(&scr->pt)) return; - if (test_thread_flag(TIF_RESTORE_SIGMASK)) + if (current_thread_info()->status & TS_RESTORE_SIGMASK) oldset = ¤t->saved_sigmask; else oldset = ¤t->blocked; @@ -530,12 +530,13 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) * continue to iterate in this loop so we can deliver the SIGSEGV... */ if (handle_signal(signr, &ka, &info, oldset, scr)) { - /* a signal was successfully delivered; the saved + /* + * A signal was successfully delivered; the saved * sigmask will have been stored in the signal frame, * and will be restored by sigreturn, so we can simply - * clear the TIF_RESTORE_SIGMASK flag */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - clear_thread_flag(TIF_RESTORE_SIGMASK); + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; return; } } @@ -566,8 +567,8 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) /* if there's no signal to deliver, we just put the saved sigmask * back */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) { - clear_thread_flag(TIF_RESTORE_SIGMASK); + if (current_thread_info()->status & TS_RESTORE_SIGMASK) { + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } } diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index 9a9d4c48933..983296f1c81 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -98,8 +98,33 @@ unlock_ipi_calllock(void) spin_unlock_irq(&call_lock); } +static inline void +handle_call_data(void) +{ + struct call_data_struct *data; + void (*func)(void *info); + void *info; + int wait; + + /* release the 'pointer lock' */ + data = (struct call_data_struct *)call_data; + func = data->func; + info = data->info; + wait = data->wait; + + mb(); + atomic_inc(&data->started); + /* At this point the structure may be gone unless wait is true. */ + (*func)(info); + + /* Notify the sending CPU that the task is done. */ + mb(); + if (wait) + atomic_inc(&data->finished); +} + static void -stop_this_cpu (void) +stop_this_cpu(void) { /* * Remove this CPU: @@ -138,44 +163,21 @@ handle_IPI (int irq, void *dev_id) ops &= ~(1 << which); switch (which) { - case IPI_CALL_FUNC: - { - struct call_data_struct *data; - void (*func)(void *info); - void *info; - int wait; - - /* release the 'pointer lock' */ - data = (struct call_data_struct *) call_data; - func = data->func; - info = data->info; - wait = data->wait; - - mb(); - atomic_inc(&data->started); - /* - * At this point the structure may be gone unless - * wait is true. - */ - (*func)(info); - - /* Notify the sending CPU that the task is done. */ - mb(); - if (wait) - atomic_inc(&data->finished); - } - break; - - case IPI_CPU_STOP: + case IPI_CALL_FUNC: + handle_call_data(); + break; + + case IPI_CPU_STOP: stop_this_cpu(); break; #ifdef CONFIG_KEXEC - case IPI_KDUMP_CPU_STOP: + case IPI_KDUMP_CPU_STOP: unw_init_running(kdump_cpu_freeze, NULL); break; #endif - default: - printk(KERN_CRIT "Unknown IPI on CPU %d: %lu\n", this_cpu, which); + default: + printk(KERN_CRIT "Unknown IPI on CPU %d: %lu\n", + this_cpu, which); break; } } while (ops); diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 48e15a51782..8c73643f2d6 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -379,11 +379,6 @@ static struct irqaction timer_irqaction = { .name = "timer" }; -void __devinit ia64_disable_timer(void) -{ - ia64_set_itv(1 << 16); -} - void __init time_init (void) { diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index abb17a613b1..26228e2d01a 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -36,9 +36,11 @@ void arch_fix_phys_package_id(int num, u32 slot) } EXPORT_SYMBOL_GPL(arch_fix_phys_package_id); -int arch_register_cpu(int num) + +#ifdef CONFIG_HOTPLUG_CPU +int __ref arch_register_cpu(int num) { -#if defined (CONFIG_ACPI) && defined (CONFIG_HOTPLUG_CPU) +#ifdef CONFIG_ACPI /* * If CPEI can be re-targetted or if this is not * CPEI target, then it is hotpluggable @@ -47,19 +49,21 @@ int arch_register_cpu(int num) sysfs_cpus[num].cpu.hotpluggable = 1; map_cpu_to_node(num, node_cpuid[num].nid); #endif - return register_cpu(&sysfs_cpus[num].cpu, num); } - -#ifdef CONFIG_HOTPLUG_CPU +EXPORT_SYMBOL(arch_register_cpu); void arch_unregister_cpu(int num) { unregister_cpu(&sysfs_cpus[num].cpu); unmap_cpu_from_node(num, cpu_to_node(num)); } -EXPORT_SYMBOL(arch_register_cpu); EXPORT_SYMBOL(arch_unregister_cpu); +#else +static int __init arch_register_cpu(int num) +{ + return register_cpu(&sysfs_cpus[num].cpu, num); +} #endif /*CONFIG_HOTPLUG_CPU*/ diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 6df07324013..318b8110062 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1,4 +1,3 @@ - /* * kvm_ia64.c: Basic KVM suppport On Itanium series processors * @@ -431,7 +430,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) if (itc_diff < 0) itc_diff = -itc_diff; - expires = div64_64(itc_diff, cyc_per_usec); + expires = div64_u64(itc_diff, cyc_per_usec); kt = ktime_set(0, 1000 * expires); vcpu->arch.ht_active = 1; hrtimer_start(p_ht, kt, HRTIMER_MODE_ABS); diff --git a/arch/m32r/Makefile b/arch/m32r/Makefile index 4072a07ebf8..469766b24e2 100644 --- a/arch/m32r/Makefile +++ b/arch/m32r/Makefile @@ -5,6 +5,8 @@ # architecture-specific flags and dependencies. # +KBUILD_DEFCONFIG := m32700ut.smp_defconfig + LDFLAGS := OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := diff --git a/arch/m32r/defconfig b/arch/m32r/defconfig deleted file mode 100644 index af3b9817911..00000000000 --- a/arch/m32r/defconfig +++ /dev/null @@ -1,863 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.23-rc1 -# Wed Aug 1 17:22:35 2007 -# -CONFIG_M32R=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_ZONE_DMA=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_NO_IOPORT=y -CONFIG_NO_DMA=y -CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_LOCALVERSION_AUTO=y -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -CONFIG_SYSVIPC_SYSCTL=y -# CONFIG_POSIX_MQUEUE is not set -CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -# CONFIG_TASKSTATS is not set -# CONFIG_USER_NS is not set -# CONFIG_AUDIT is not set -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=15 -# CONFIG_CPUSETS is not set -CONFIG_SYSFS_DEPRECATED=y -# CONFIG_RELAY is not set -# CONFIG_BLK_DEV_INITRD is not set -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_SYSCTL=y -CONFIG_EMBEDDED=y -CONFIG_SYSCTL_SYSCALL=y -# CONFIG_KALLSYMS is not set -CONFIG_HOTPLUG=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_ELF_CORE=y -CONFIG_BASE_FULL=y -# CONFIG_FUTEX is not set -CONFIG_ANON_INODES=y -# CONFIG_EPOLL is not set -CONFIG_SIGNALFD=y -CONFIG_TIMERFD=y -CONFIG_EVENTFD=y -CONFIG_SHMEM=y -CONFIG_VM_EVENT_COUNTERS=y -CONFIG_SLAB=y -# CONFIG_SLUB is not set -# CONFIG_SLOB is not set -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y -CONFIG_STOP_MACHINE=y -CONFIG_BLOCK=y -# CONFIG_LBD is not set -# CONFIG_BLK_DEV_IO_TRACE is not set -# CONFIG_LSF is not set -# CONFIG_BLK_DEV_BSG is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -# CONFIG_IOSCHED_AS is not set -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_DEFAULT_AS is not set -# CONFIG_DEFAULT_DEADLINE is not set -CONFIG_DEFAULT_CFQ=y -# CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="cfq" - -# -# Processor type and features -# -# CONFIG_PLAT_MAPPI is not set -# CONFIG_PLAT_USRV is not set -CONFIG_PLAT_M32700UT=y -# CONFIG_PLAT_OPSPUT is not set -# CONFIG_PLAT_OAKS32R is not set -# CONFIG_PLAT_MAPPI2 is not set -# CONFIG_PLAT_MAPPI3 is not set -# CONFIG_PLAT_M32104UT is not set -CONFIG_CHIP_M32700=y -# CONFIG_CHIP_M32102 is not set -# CONFIG_CHIP_M32104 is not set -# CONFIG_CHIP_VDEC2 is not set -# CONFIG_CHIP_OPSP is not set -CONFIG_MMU=y -CONFIG_TLB_ENTRIES=32 -CONFIG_ISA_M32R2=y -CONFIG_ISA_DSP_LEVEL2=y -CONFIG_ISA_DUAL_ISSUE=y -CONFIG_BUS_CLOCK=50000000 -CONFIG_TIMER_DIVIDE=128 -# CONFIG_CPU_LITTLE_ENDIAN is not set -CONFIG_MEMORY_START=0x08000000 -CONFIG_MEMORY_SIZE=0x01000000 -CONFIG_NOHIGHMEM=y -CONFIG_ARCH_DISCONTIGMEM_ENABLE=y -CONFIG_SELECT_MEMORY_MODEL=y -# CONFIG_FLATMEM_MANUAL is not set -CONFIG_DISCONTIGMEM_MANUAL=y -# CONFIG_SPARSEMEM_MANUAL is not set -CONFIG_DISCONTIGMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y -CONFIG_NEED_MULTIPLE_NODES=y -# CONFIG_SPARSEMEM_STATIC is not set -CONFIG_SPLIT_PTLOCK_CPUS=4 -# CONFIG_RESOURCES_64BIT is not set -CONFIG_ZONE_DMA_FLAG=1 -CONFIG_BOUNCE=y -CONFIG_VIRT_TO_BUS=y -CONFIG_IRAM_START=0x00f00000 -CONFIG_IRAM_SIZE=0x00080000 -CONFIG_RWSEM_GENERIC_SPINLOCK=y -# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set -# CONFIG_ARCH_HAS_ILOG2_U32 is not set -# CONFIG_ARCH_HAS_ILOG2_U64 is not set -CONFIG_GENERIC_FIND_NEXT_BIT=y -CONFIG_GENERIC_HWEIGHT=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y -CONFIG_PREEMPT=y -CONFIG_SMP=y -# CONFIG_CHIP_M32700_TS1 is not set -CONFIG_NR_CPUS=2 -CONFIG_NODES_SHIFT=1 - -# -# Bus options (PCI, PCMCIA, EISA, MCA, ISA) -# -# CONFIG_ARCH_SUPPORTS_MSI is not set -# CONFIG_ISA is not set - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -# CONFIG_BINFMT_MISC is not set - -# -# Networking -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -CONFIG_XFRM=y -# CONFIG_XFRM_USER is not set -# CONFIG_XFRM_SUB_POLICY is not set -# CONFIG_XFRM_MIGRATE is not set -# CONFIG_NET_KEY is not set -CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set -# CONFIG_IP_ADVANCED_ROUTER is not set -CONFIG_IP_FIB_HASH=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_XFRM_TUNNEL is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_INET_XFRM_MODE_TRANSPORT=y -CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_INET_XFRM_MODE_BEET=y -CONFIG_INET_DIAG=y -CONFIG_INET_TCP_DIAG=y -# CONFIG_TCP_CONG_ADVANCED is not set -CONFIG_TCP_CONG_CUBIC=y -CONFIG_DEFAULT_TCP_CONG="cubic" -# CONFIG_TCP_MD5SIG is not set -# CONFIG_IPV6 is not set -# CONFIG_INET6_XFRM_TUNNEL is not set -# CONFIG_INET6_TUNNEL is not set -# CONFIG_NETWORK_SECMARK is not set -# CONFIG_NETFILTER is not set -# CONFIG_IP_DCCP is not set -# CONFIG_IP_SCTP is not set -# CONFIG_TIPC is not set -# CONFIG_ATM is not set -# CONFIG_BRIDGE is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -# CONFIG_AF_RXRPC is not set - -# -# Wireless -# -# CONFIG_CFG80211 is not set -# CONFIG_WIRELESS_EXT is not set -# CONFIG_MAC80211 is not set -# CONFIG_IEEE80211 is not set -# CONFIG_RFKILL is not set -# CONFIG_NET_9P is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=y -# CONFIG_SYS_HYPERVISOR is not set -# CONFIG_CONNECTOR is not set -CONFIG_MTD=y -# CONFIG_MTD_DEBUG is not set -# CONFIG_MTD_CONCAT is not set -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_REDBOOT_PARTS=y -CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1 -# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set -# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set -# CONFIG_MTD_CMDLINE_PARTS is not set - -# -# User Modules And Translation Layers -# -# CONFIG_MTD_CHAR is not set -CONFIG_MTD_BLKDEVS=y -CONFIG_MTD_BLOCK=y -# CONFIG_FTL is not set -# CONFIG_NFTL is not set -# CONFIG_INFTL is not set -# CONFIG_RFD_FTL is not set -# CONFIG_SSFDC is not set - -# -# RAM/ROM/Flash chip drivers -# -CONFIG_MTD_CFI=m -CONFIG_MTD_JEDECPROBE=m -CONFIG_MTD_GEN_PROBE=m -CONFIG_MTD_CFI_ADV_OPTIONS=y -# CONFIG_MTD_CFI_NOSWAP is not set -CONFIG_MTD_CFI_BE_BYTE_SWAP=y -# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set -CONFIG_MTD_CFI_GEOMETRY=y -CONFIG_MTD_MAP_BANK_WIDTH_1=y -CONFIG_MTD_MAP_BANK_WIDTH_2=y -CONFIG_MTD_MAP_BANK_WIDTH_4=y -# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set -CONFIG_MTD_CFI_I1=y -# CONFIG_MTD_CFI_I2 is not set -# CONFIG_MTD_CFI_I4 is not set -# CONFIG_MTD_CFI_I8 is not set -# CONFIG_MTD_OTP is not set -# CONFIG_MTD_CFI_INTELEXT is not set -CONFIG_MTD_CFI_AMDSTD=m -# CONFIG_MTD_CFI_STAA is not set -CONFIG_MTD_CFI_UTIL=m -# CONFIG_MTD_RAM is not set -# CONFIG_MTD_ROM is not set -# CONFIG_MTD_ABSENT is not set - -# -# Mapping drivers for chip access -# -# CONFIG_MTD_COMPLEX_MAPPINGS is not set -# CONFIG_MTD_PHYSMAP is not set -# CONFIG_MTD_PLATRAM is not set - -# -# Self-contained MTD device drivers -# -# CONFIG_MTD_SLRAM is not set -# CONFIG_MTD_PHRAM is not set -# CONFIG_MTD_MTDRAM is not set -# CONFIG_MTD_BLOCK2MTD is not set - -# -# Disk-On-Chip Device Drivers -# -# CONFIG_MTD_DOC2000 is not set -# CONFIG_MTD_DOC2001 is not set -# CONFIG_MTD_DOC2001PLUS is not set -# CONFIG_MTD_NAND is not set -# CONFIG_MTD_ONENAND is not set - -# -# UBI - Unsorted block images -# -# CONFIG_MTD_UBI is not set -# CONFIG_PARPORT is not set -CONFIG_BLK_DEV=y -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=y -# CONFIG_BLK_DEV_CRYPTOLOOP is not set -CONFIG_BLK_DEV_NBD=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 -# CONFIG_CDROM_PKTCDVD is not set -CONFIG_ATA_OVER_ETH=m -CONFIG_MISC_DEVICES=y -# CONFIG_EEPROM_93CX6 is not set -CONFIG_IDE=y -CONFIG_IDE_MAX_HWIFS=4 -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -CONFIG_BLK_DEV_IDEDISK=y -# CONFIG_IDEDISK_MULTI_MODE is not set -CONFIG_BLK_DEV_IDECD=m -# CONFIG_BLK_DEV_IDETAPE is not set -# CONFIG_BLK_DEV_IDEFLOPPY is not set -# CONFIG_BLK_DEV_IDESCSI is not set -# CONFIG_IDE_TASK_IOCTL is not set -CONFIG_IDE_PROC_FS=y - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -# CONFIG_IDEPCI_PCIBUS_ORDER is not set -# CONFIG_IDE_ARM is not set -# CONFIG_BLK_DEV_IDEDMA is not set -# CONFIG_BLK_DEV_HD is not set - -# -# SCSI device support -# -# CONFIG_RAID_ATTRS is not set -CONFIG_SCSI=m -# CONFIG_SCSI_DMA is not set -# CONFIG_SCSI_TGT is not set -# CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=m -# CONFIG_CHR_DEV_ST is not set -# CONFIG_CHR_DEV_OSST is not set -CONFIG_BLK_DEV_SR=m -# CONFIG_BLK_DEV_SR_VENDOR is not set -CONFIG_CHR_DEV_SG=m -# CONFIG_CHR_DEV_SCH is not set - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -CONFIG_SCSI_MULTI_LUN=y -# CONFIG_SCSI_CONSTANTS is not set -# CONFIG_SCSI_LOGGING is not set -# CONFIG_SCSI_SCAN_ASYNC is not set -CONFIG_SCSI_WAIT_SCAN=m - -# -# SCSI Transports -# -# CONFIG_SCSI_SPI_ATTRS is not set -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set -# CONFIG_SCSI_SAS_LIBSAS is not set -CONFIG_SCSI_LOWLEVEL=y -# CONFIG_ISCSI_TCP is not set -# CONFIG_SCSI_DEBUG is not set -# CONFIG_MD is not set -CONFIG_NETDEVICES=y -# CONFIG_NETDEVICES_MULTIQUEUE is not set -# CONFIG_DUMMY is not set -# CONFIG_BONDING is not set -# CONFIG_MACVLAN is not set -# CONFIG_EQUALIZER is not set -# CONFIG_TUN is not set -# CONFIG_PHYLIB is not set -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -CONFIG_SMC91X=y -# CONFIG_NE2000 is not set -CONFIG_NETDEV_1000=y -CONFIG_NETDEV_10000=y - -# -# Wireless LAN -# -# CONFIG_WLAN_PRE80211 is not set -# CONFIG_WLAN_80211 is not set -# CONFIG_WAN is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_ISDN is not set -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y -# CONFIG_INPUT_FF_MEMLESS is not set -# CONFIG_INPUT_POLLDEV is not set - -# -# Userland interfaces -# -# CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TABLET is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -# CONFIG_SERIO_I8042 is not set -CONFIG_SERIO_SERPORT=y -# CONFIG_SERIO_LIBPS2 is not set -# CONFIG_SERIO_RAW is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# -CONFIG_VT=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_VT_HW_CONSOLE_BINDING is not set -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -CONFIG_SERIAL_CORE=y -CONFIG_SERIAL_CORE_CONSOLE=y -CONFIG_SERIAL_M32R_SIO=y -CONFIG_SERIAL_M32R_SIO_CONSOLE=y -CONFIG_SERIAL_M32R_PLDSIO=y -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 -# CONFIG_IPMI_HANDLER is not set -# CONFIG_WATCHDOG is not set -CONFIG_HW_RANDOM=y -# CONFIG_RTC is not set -CONFIG_DS1302=y -# CONFIG_R3964 is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_TCG_TPM is not set -# CONFIG_I2C is not set - -# -# SPI support -# -# CONFIG_SPI is not set -# CONFIG_SPI_MASTER is not set -# CONFIG_W1 is not set -# CONFIG_POWER_SUPPLY is not set -CONFIG_HWMON=y -# CONFIG_HWMON_VID is not set -# CONFIG_SENSORS_ABITUGURU is not set -# CONFIG_SENSORS_ABITUGURU3 is not set -# CONFIG_SENSORS_F71805F is not set -# CONFIG_SENSORS_IT87 is not set -# CONFIG_SENSORS_PC87360 is not set -# CONFIG_SENSORS_PC87427 is not set -# CONFIG_SENSORS_SMSC47M1 is not set -# CONFIG_SENSORS_SMSC47B397 is not set -# CONFIG_SENSORS_VT1211 is not set -# CONFIG_SENSORS_W83627HF is not set -# CONFIG_SENSORS_W83627EHF is not set -# CONFIG_HWMON_DEBUG_CHIP is not set - -# -# Multifunction device drivers -# -# CONFIG_MFD_SM501 is not set - -# -# Multimedia devices -# -CONFIG_VIDEO_DEV=m -CONFIG_VIDEO_V4L1=y -CONFIG_VIDEO_V4L1_COMPAT=y -CONFIG_VIDEO_V4L2=y -CONFIG_VIDEO_CAPTURE_DRIVERS=y -# CONFIG_VIDEO_ADV_DEBUG is not set -CONFIG_VIDEO_HELPER_CHIPS_AUTO=y -# CONFIG_VIDEO_CPIA is not set -CONFIG_VIDEO_M32R_AR=m -CONFIG_VIDEO_M32R_AR_M64278=m -CONFIG_RADIO_ADAPTERS=y -# CONFIG_DVB_CORE is not set -CONFIG_DAB=y - -# -# Graphics support -# -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set - -# -# Display device support -# -# CONFIG_DISPLAY_SUPPORT is not set -# CONFIG_VGASTATE is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m -CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y -# CONFIG_FB_DDC is not set -CONFIG_FB_CFB_FILLRECT=y -CONFIG_FB_CFB_COPYAREA=y -CONFIG_FB_CFB_IMAGEBLIT=y -# CONFIG_FB_SYS_FILLRECT is not set -# CONFIG_FB_SYS_COPYAREA is not set -# CONFIG_FB_SYS_IMAGEBLIT is not set -# CONFIG_FB_SYS_FOPS is not set -CONFIG_FB_DEFERRED_IO=y -# CONFIG_FB_SVGALIB is not set -# CONFIG_FB_MACMODES is not set -# CONFIG_FB_BACKLIGHT is not set -# CONFIG_FB_MODE_HELPERS is not set -# CONFIG_FB_TILEBLITTING is not set - -# -# Frame buffer hardware drivers -# -CONFIG_FB_S1D13XXX=y -# CONFIG_FB_VIRTUAL is not set - -# -# Console display driver support -# -# CONFIG_VGA_CONSOLE is not set -CONFIG_DUMMY_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE=y -# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set -# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set -# CONFIG_FONTS is not set -CONFIG_FONT_8x8=y -CONFIG_FONT_8x16=y -CONFIG_LOGO=y -CONFIG_LOGO_LINUX_MONO=y -CONFIG_LOGO_LINUX_VGA16=y -CONFIG_LOGO_LINUX_CLUT224=y -CONFIG_LOGO_M32R_CLUT224=y - -# -# Sound -# -# CONFIG_SOUND is not set -CONFIG_HID_SUPPORT=y -CONFIG_HID=y -# CONFIG_HID_DEBUG is not set -CONFIG_USB_SUPPORT=y -# CONFIG_USB_ARCH_HAS_HCD is not set -# CONFIG_USB_ARCH_HAS_OHCI is not set -# CONFIG_USB_ARCH_HAS_EHCI is not set - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' -# - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set -CONFIG_MMC=y -CONFIG_MMC_DEBUG=y -# CONFIG_MMC_UNSAFE_RESUME is not set - -# -# MMC/SD Card Drivers -# -CONFIG_MMC_BLOCK=y -CONFIG_MMC_BLOCK_BOUNCE=y - -# -# MMC/SD Host Controller Drivers -# -# CONFIG_NEW_LEDS is not set - -# -# Real Time Clock -# -# CONFIG_RTC_CLASS is not set - -# -# Userspace I/O -# -# CONFIG_UIO is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set -# CONFIG_EXT2_FS_XIP is not set -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set -# CONFIG_EXT4DEV_FS is not set -CONFIG_JBD=y -CONFIG_JBD_DEBUG=y -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=m -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -# CONFIG_REISERFS_FS_XATTR is not set -# CONFIG_JFS_FS is not set -# CONFIG_FS_POSIX_ACL is not set -# CONFIG_XFS_FS is not set -# CONFIG_GFS2_FS is not set -# CONFIG_OCFS2_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -CONFIG_INOTIFY=y -CONFIG_INOTIFY_USER=y -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -# CONFIG_AUTOFS_FS is not set -# CONFIG_AUTOFS4_FS is not set -# CONFIG_FUSE_FS is not set - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=m -CONFIG_JOLIET=y -# CONFIG_ZISOFS is not set -CONFIG_UDF_FS=m -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_PROC_SYSCTL=y -CONFIG_SYSFS=y -CONFIG_TMPFS=y -# CONFIG_TMPFS_POSIX_ACL is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y -# CONFIG_CONFIGFS_FS is not set - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_JFFS2_FS is not set -# CONFIG_CRAMFS is not set -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V3_ACL is not set -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -# CONFIG_NFSD is not set -CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_NFS_COMMON=y -CONFIG_SUNRPC=y -# CONFIG_SUNRPC_BIND34 is not set -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set -# CONFIG_SMB_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -# CONFIG_NLS_CODEPAGE_437 is not set -# CONFIG_NLS_CODEPAGE_737 is not set -# CONFIG_NLS_CODEPAGE_775 is not set -# CONFIG_NLS_CODEPAGE_850 is not set -# CONFIG_NLS_CODEPAGE_852 is not set -# CONFIG_NLS_CODEPAGE_855 is not set -# CONFIG_NLS_CODEPAGE_857 is not set -# CONFIG_NLS_CODEPAGE_860 is not set -# CONFIG_NLS_CODEPAGE_861 is not set -# CONFIG_NLS_CODEPAGE_862 is not set -# CONFIG_NLS_CODEPAGE_863 is not set -# CONFIG_NLS_CODEPAGE_864 is not set -# CONFIG_NLS_CODEPAGE_865 is not set -# CONFIG_NLS_CODEPAGE_866 is not set -# CONFIG_NLS_CODEPAGE_869 is not set -# CONFIG_NLS_CODEPAGE_936 is not set -# CONFIG_NLS_CODEPAGE_950 is not set -# CONFIG_NLS_CODEPAGE_932 is not set -# CONFIG_NLS_CODEPAGE_949 is not set -# CONFIG_NLS_CODEPAGE_874 is not set -# CONFIG_NLS_ISO8859_8 is not set -# CONFIG_NLS_CODEPAGE_1250 is not set -# CONFIG_NLS_CODEPAGE_1251 is not set -# CONFIG_NLS_ASCII is not set -# CONFIG_NLS_ISO8859_1 is not set -# CONFIG_NLS_ISO8859_2 is not set -# CONFIG_NLS_ISO8859_3 is not set -# CONFIG_NLS_ISO8859_4 is not set -# CONFIG_NLS_ISO8859_5 is not set -# CONFIG_NLS_ISO8859_6 is not set -# CONFIG_NLS_ISO8859_7 is not set -# CONFIG_NLS_ISO8859_9 is not set -# CONFIG_NLS_ISO8859_13 is not set -# CONFIG_NLS_ISO8859_14 is not set -# CONFIG_NLS_ISO8859_15 is not set -# CONFIG_NLS_KOI8_R is not set -# CONFIG_NLS_KOI8_U is not set -# CONFIG_NLS_UTF8 is not set - -# -# Distributed Lock Manager -# -# CONFIG_DLM is not set - -# -# Profiling support -# -CONFIG_PROFILING=y -CONFIG_OPROFILE=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_ENABLE_MUST_CHECK=y -# CONFIG_MAGIC_SYSRQ is not set -# CONFIG_UNUSED_SYMBOLS is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_HEADERS_CHECK is not set -# CONFIG_DEBUG_KERNEL is not set -# CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_FRAME_POINTER is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set -# CONFIG_CRYPTO is not set - -# -# Library routines -# -CONFIG_BITREVERSE=y -# CONFIG_CRC_CCITT is not set -# CONFIG_CRC16 is not set -# CONFIG_CRC_ITU_T is not set -CONFIG_CRC32=y -# CONFIG_CRC7 is not set -# CONFIG_LIBCRC32C is not set -CONFIG_HAS_IOMEM=y diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index 6d7a80fdad4..319c79720b8 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -90,8 +90,11 @@ sys_pipe(unsigned long r0, unsigned long r1, unsigned long r2, error = do_pipe(fd); if (!error) { - if (copy_to_user((void __user *)r0, fd, 2*sizeof(int))) + if (copy_to_user((void __user *)r0, fd, 2*sizeof(int))) { + sys_close(fd[0]); + sys_close(fd[1]); error = -EFAULT; + } } return error; } diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S index 41b07854fcc..15a6f36c06d 100644 --- a/arch/m32r/kernel/vmlinux.lds.S +++ b/arch/m32r/kernel/vmlinux.lds.S @@ -60,9 +60,6 @@ SECTIONS . = ALIGN(4096); __nosave_end = .; - . = ALIGN(4096); - .data.page_aligned : { *(.data.idt) } - . = ALIGN(32); .data.cacheline_aligned : { *(.data.cacheline_aligned) } diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index e892f17ba3f..7f54efaf60b 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -30,23 +30,6 @@ #include <asm/page.h> #include <asm/unistd.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long __user * fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - /* common code for old and new mmaps */ static inline long do_mmap2( unsigned long addr, unsigned long len, diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index fd4858e2dd6..75b8340b254 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -468,15 +468,26 @@ static inline void access_error040(struct frame *fp) * (if do_page_fault didn't fix the mapping, * the writeback won't do good) */ +disable_wb: #ifdef DEBUG printk(".. disabling wb2\n"); #endif if (fp->un.fmt7.wb2a == fp->un.fmt7.faddr) fp->un.fmt7.wb2s &= ~WBV_040; + if (fp->un.fmt7.wb3a == fp->un.fmt7.faddr) + fp->un.fmt7.wb3s &= ~WBV_040; } - } else if (send_fault_sig(&fp->ptregs) > 0) { - printk("68040 access error, ssw=%x\n", ssw); - trap_c(fp); + } else { + /* In case of a bus error we either kill the process or expect + * the kernel to catch the fault, which then is also responsible + * for cleaning up the mess. + */ + current->thread.signo = SIGBUS; + current->thread.faddr = fp->un.fmt7.faddr; + if (send_fault_sig(&fp->ptregs) >= 0) + printk("68040 bus error (ssw=%x, faddr=%lx)\n", ssw, + fp->un.fmt7.faddr); + goto disable_wb; } do_040writebacks(fp); diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 735a49b4b93..ad3e3bacae3 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -48,9 +48,6 @@ struct mac_booter_data mac_bi_data; int mac_bisize = sizeof mac_bi_data; -struct mac_hw_present mac_hw_present; -EXPORT_SYMBOL(mac_hw_present); - /* New m68k bootinfo stuff and videobase */ extern int m68k_num_memory; @@ -817,27 +814,6 @@ void __init mac_identify(void) m68k_ramdisk.addr, m68k_ramdisk.size); #endif - /* - * TODO: set the various fields in macintosh_config->hw_present here! - */ - switch (macintosh_config->scsi_type) { - case MAC_SCSI_OLD: - MACHW_SET(MAC_SCSI_80); - break; - case MAC_SCSI_QUADRA: - case MAC_SCSI_QUADRA2: - case MAC_SCSI_QUADRA3: - MACHW_SET(MAC_SCSI_96); - if ((macintosh_config->ident == MAC_MODEL_Q900) || - (macintosh_config->ident == MAC_MODEL_Q950)) - MACHW_SET(MAC_SCSI_96_2); - break; - default: - printk(KERN_WARNING "config.c: wtf: unknown scsi, using 53c80\n"); - MACHW_SET(MAC_SCSI_80); - break; - } - iop_init(); via_init(); oss_init(); diff --git a/arch/m68knommu/kernel/asm-offsets.c b/arch/m68knommu/kernel/asm-offsets.c index fd0c685a7f1..c785d07c02c 100644 --- a/arch/m68knommu/kernel/asm-offsets.c +++ b/arch/m68knommu/kernel/asm-offsets.c @@ -87,6 +87,7 @@ int main(void) DEFINE(TI_TASK, offsetof(struct thread_info, task)); DEFINE(TI_EXECDOMAIN, offsetof(struct thread_info, exec_domain)); DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPTCOUNT, offsetof(struct thread_info, preempt_count)); DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); return 0; diff --git a/arch/m68knommu/kernel/entry.S b/arch/m68knommu/kernel/entry.S index 1e7ea6a3e1a..f4782d2dce8 100644 --- a/arch/m68knommu/kernel/entry.S +++ b/arch/m68knommu/kernel/entry.S @@ -32,6 +32,7 @@ #include <asm/segment.h> #include <asm/asm-offsets.h> #include <asm/entry.h> +#include <asm/unistd.h> .text @@ -140,3 +141,11 @@ ENTRY(sys_rt_sigreturn) RESTORE_SWITCH_STACK rts +ENTRY(ret_from_user_signal) + moveq #__NR_sigreturn,%d0 + trap #0 + +ENTRY(ret_from_user_rt_signal) + move #__NR_rt_sigreturn,%d0 + trap #0 + diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c index d6f0200316f..03f4fe6a2fc 100644 --- a/arch/m68knommu/kernel/setup.c +++ b/arch/m68knommu/kernel/setup.c @@ -162,7 +162,7 @@ void __init setup_arch(char **cmdline_p) printk(KERN_INFO "DragonEngine II board support by Georges Menie\n"); #endif #ifdef CONFIG_M5235EVB - printk(KERN_INFO "Motorola M5235EVB support (C)2005 Syn-tech Systems, Inc. (Jate Sujjavanich)"); + printk(KERN_INFO "Motorola M5235EVB support (C)2005 Syn-tech Systems, Inc. (Jate Sujjavanich)\n"); #endif #ifdef DEBUG diff --git a/arch/m68knommu/kernel/signal.c b/arch/m68knommu/kernel/signal.c index 70371378db8..bbfcae9e52b 100644 --- a/arch/m68knommu/kernel/signal.c +++ b/arch/m68knommu/kernel/signal.c @@ -51,6 +51,8 @@ #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) +void ret_from_user_signal(void); +void ret_from_user_rt_signal(void); asmlinkage int do_signal(sigset_t *oldset, struct pt_regs *regs); /* @@ -539,10 +541,6 @@ static inline int rt_setup_ucontext(struct ucontext *uc, struct pt_regs *regs) return err; } -static inline void push_cache (unsigned long vaddr) -{ -} - static inline void * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size) { @@ -586,16 +584,11 @@ static void setup_frame (int sig, struct k_sigaction *ka, err |= copy_to_user (&frame->sc, &context, sizeof(context)); /* Set up to return from userspace. */ - err |= __put_user(frame->retcode, &frame->pretcode); - /* moveq #,d0; trap #0 */ - err |= __put_user(0x70004e40 + (__NR_sigreturn << 16), - (long *)(frame->retcode)); + err |= __put_user((void *) ret_from_user_signal, &frame->pretcode); if (err) goto give_sigsegv; - push_cache ((unsigned long) &frame->retcode); - /* Set up registers for signal handler */ wrusp ((unsigned long) frame); regs->pc = (unsigned long) ka->sa.sa_handler; @@ -655,17 +648,11 @@ static void setup_rt_frame (int sig, struct k_sigaction *ka, siginfo_t *info, err |= copy_to_user (&frame->uc.uc_sigmask, set, sizeof(*set)); /* Set up to return from userspace. */ - err |= __put_user(frame->retcode, &frame->pretcode); - /* moveq #,d0; notb d0; trap #0 */ - err |= __put_user(0x70004600 + ((__NR_rt_sigreturn ^ 0xff) << 16), - (long *)(frame->retcode + 0)); - err |= __put_user(0x4e40, (short *)(frame->retcode + 4)); + err |= __put_user((void *) ret_from_user_rt_signal, &frame->pretcode); if (err) goto give_sigsegv; - push_cache ((unsigned long) &frame->retcode); - /* Set up registers for signal handler */ wrusp ((unsigned long) frame); regs->pc = (unsigned long) ka->sa.sa_handler; diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c index 65f7a95f056..70028163862 100644 --- a/arch/m68knommu/kernel/sys_m68k.c +++ b/arch/m68knommu/kernel/sys_m68k.c @@ -28,23 +28,6 @@ #include <asm/cacheflush.h> #include <asm/unistd.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long * fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - /* common code for old and new mmaps */ static inline long do_mmap2( unsigned long addr, unsigned long len, diff --git a/arch/m68knommu/kernel/traps.c b/arch/m68knommu/kernel/traps.c index 437a061d8b9..ec9aea652e7 100644 --- a/arch/m68knommu/kernel/traps.c +++ b/arch/m68knommu/kernel/traps.c @@ -28,6 +28,7 @@ #include <linux/linkage.h> #include <linux/init.h> #include <linux/ptrace.h> +#include <linux/kallsyms.h> #include <asm/setup.h> #include <asm/fpu.h> @@ -102,56 +103,47 @@ asmlinkage void buserr_c(struct frame *fp) force_sig(SIGSEGV, current); } - int kstack_depth_to_print = 48; -void show_stack(struct task_struct *task, unsigned long *stack) +static void __show_stack(struct task_struct *task, unsigned long *stack) { unsigned long *endstack, addr; - extern char _start, _etext; + unsigned long *last_stack; int i; - if (!stack) { - if (task) - stack = (unsigned long *)task->thread.ksp; - else - stack = (unsigned long *)&stack; - } + if (!stack) + stack = (unsigned long *)task->thread.ksp; addr = (unsigned long) stack; endstack = (unsigned long *) PAGE_ALIGN(addr); printk(KERN_EMERG "Stack from %08lx:", (unsigned long)stack); for (i = 0; i < kstack_depth_to_print; i++) { - if (stack + 1 > endstack) + if (stack + 1 + i > endstack) break; if (i % 8 == 0) printk("\n" KERN_EMERG " "); - printk(" %08lx", *stack++); + printk(" %08lx", *(stack + i)); } printk("\n"); - printk(KERN_EMERG "Call Trace:"); - i = 0; - while (stack + 1 <= endstack) { - addr = *stack++; - /* - * If the address is either in the text segment of the - * kernel, or in the region which contains vmalloc'ed - * memory, it *may* be the address of a calling - * routine; if so, print it so that someone tracing - * down the cause of the crash will be able to figure - * out the call path that was taken. - */ - if (((addr >= (unsigned long) &_start) && - (addr <= (unsigned long) &_etext))) { - if (i % 4 == 0) - printk("\n" KERN_EMERG " "); - printk(" [<%08lx>]", addr); - i++; - } +#ifdef CONFIG_FRAME_POINTER + printk(KERN_EMERG "Call Trace:\n"); + + last_stack = stack - 1; + while (stack <= endstack && stack > last_stack) { + + addr = *(stack + 1); + printk(KERN_EMERG " [%08lx] ", addr); + print_symbol(KERN_CONT "%s\n", addr); + + last_stack = stack; + stack = (unsigned long *)*stack; } printk("\n"); +#else + printk(KERN_EMERG "CONFIG_FRAME_POINTER disabled, no symbolic call trace\n"); +#endif } void bad_super_trap(struct frame *fp) @@ -298,19 +290,47 @@ asmlinkage void set_esp0(unsigned long ssp) current->thread.esp0 = ssp; } - /* * The architecture-independent backtrace generator */ void dump_stack(void) { - unsigned long stack; + /* + * We need frame pointers for this little trick, which works as follows: + * + * +------------+ 0x00 + * | Next SP | -> 0x0c + * +------------+ 0x04 + * | Caller | + * +------------+ 0x08 + * | Local vars | -> our stack var + * +------------+ 0x0c + * | Next SP | -> 0x18, that is what we pass to show_stack() + * +------------+ 0x10 + * | Caller | + * +------------+ 0x14 + * | Local vars | + * +------------+ 0x18 + * | ... | + * +------------+ + */ - show_stack(current, &stack); -} + unsigned long *stack; + stack = (unsigned long *)&stack; + stack++; + __show_stack(current, stack); +} EXPORT_SYMBOL(dump_stack); +void show_stack(struct task_struct *task, unsigned long *stack) +{ + if (!stack && !task) + dump_stack(); + else + __show_stack(task, stack); +} + #ifdef CONFIG_M68KFPU_EMU asmlinkage void fpemu_signal(int signal, int code, void *addr) { diff --git a/arch/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S index b44edb08e21..5592e0bf951 100644 --- a/arch/m68knommu/kernel/vmlinux.lds.S +++ b/arch/m68knommu/kernel/vmlinux.lds.S @@ -64,6 +64,7 @@ SECTIONS { _stext = . ; TEXT_TEXT SCHED_TEXT + LOCK_TEXT *(.text.lock) . = ALIGN(16); /* Exception table */ @@ -73,6 +74,7 @@ SECTIONS { *(.rodata) *(.rodata.*) *(__vermagic) /* Kernel version magic */ + *(__markers_strings) *(.rodata1) *(.rodata.str1.1) @@ -182,6 +184,7 @@ SECTIONS { *(COMMON) . = ALIGN(4) ; _ebss = . ; + _end = . ; } > BSS } diff --git a/arch/m68knommu/platform/5206e/config.c b/arch/m68knommu/platform/5206e/config.c index a6692e958f6..d01a5d2b755 100644 --- a/arch/m68knommu/platform/5206e/config.c +++ b/arch/m68knommu/platform/5206e/config.c @@ -48,7 +48,7 @@ static struct platform_device *m5206e_devices[] __initdata = { /***************************************************************************/ -static void __init m5206_uart_init_line(int line, int irq) +static void __init m5206e_uart_init_line(int line, int irq) { if (line == 0) { writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR); diff --git a/arch/m68knommu/platform/5272/config.c b/arch/m68knommu/platform/5272/config.c index 2aca599a1ca..230bae691a7 100644 --- a/arch/m68knommu/platform/5272/config.c +++ b/arch/m68knommu/platform/5272/config.c @@ -139,10 +139,6 @@ void __init config_BSP(char *commandp, int size) /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0xf0004000, size); commandp[size-1] = 0; -#elif defined(CONFIG_MTD_KeyTechnology) - /* Copy command line from FLASH to local buffer... */ - memcpy(commandp, (char *) 0xffe06000, size); - commandp[size-1] = 0; #elif defined(CONFIG_CANCam) /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0xf0010000, size); diff --git a/arch/m68knommu/platform/528x/config.c b/arch/m68knommu/platform/528x/config.c index 036e1b73d94..dfdb5c2ed8e 100644 --- a/arch/m68knommu/platform/528x/config.c +++ b/arch/m68knommu/platform/528x/config.c @@ -26,9 +26,240 @@ #include <asm/mcfuart.h> #include <asm/mcfqspi.h> +#ifdef CONFIG_MTD_PARTITIONS +#include <linux/mtd/partitions.h> +#endif + /***************************************************************************/ void coldfire_reset(void); +static void coldfire_qspi_cs_control(u8 cs, u8 command); + +/***************************************************************************/ + +#if defined(CONFIG_SPI) + +#if defined(CONFIG_WILDFIRE) +#define SPI_NUM_CHIPSELECTS 0x02 +#define SPI_PAR_VAL 0x07 /* Enable DIN, DOUT, CLK */ +#define SPI_CS_MASK 0x18 + +#define FLASH_BLOCKSIZE (1024*64) +#define FLASH_NUMBLOCKS 16 +#define FLASH_TYPE "m25p80" + +#define M25P80_CS 0 +#define MMC_CS 1 + +#ifdef CONFIG_MTD_PARTITIONS +static struct mtd_partition stm25p_partitions[] = { + /* sflash */ + [0] = { + .name = "stm25p80", + .offset = 0x00000000, + .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS, + .mask_flags = 0 + } +}; + +#endif + +#elif defined(CONFIG_WILDFIREMOD) + +#define SPI_NUM_CHIPSELECTS 0x08 +#define SPI_PAR_VAL 0x07 /* Enable DIN, DOUT, CLK */ +#define SPI_CS_MASK 0x78 + +#define FLASH_BLOCKSIZE (1024*64) +#define FLASH_NUMBLOCKS 64 +#define FLASH_TYPE "m25p32" +/* Reserve 1M for the kernel parition */ +#define FLASH_KERNEL_SIZE (1024 * 1024) + +#define M25P80_CS 5 +#define MMC_CS 6 + +#ifdef CONFIG_MTD_PARTITIONS +static struct mtd_partition stm25p_partitions[] = { + /* sflash */ + [0] = { + .name = "kernel", + .offset = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS - FLASH_KERNEL_SIZE, + .size = FLASH_KERNEL_SIZE, + .mask_flags = 0 + }, + [1] = { + .name = "image", + .offset = 0x00000000, + .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS - FLASH_KERNEL_SIZE, + .mask_flags = 0 + }, + [2] = { + .name = "all", + .offset = 0x00000000, + .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS, + .mask_flags = 0 + } +}; +#endif + +#else +#define SPI_NUM_CHIPSELECTS 0x04 +#define SPI_PAR_VAL 0x7F /* Enable DIN, DOUT, CLK, CS0 - CS4 */ +#endif + +#ifdef MMC_CS +static struct coldfire_spi_chip flash_chip_info = { + .mode = SPI_MODE_0, + .bits_per_word = 16, + .del_cs_to_clk = 17, + .del_after_trans = 1, + .void_write_data = 0 +}; + +static struct coldfire_spi_chip mmc_chip_info = { + .mode = SPI_MODE_0, + .bits_per_word = 16, + .del_cs_to_clk = 17, + .del_after_trans = 1, + .void_write_data = 0xFFFF +}; +#endif + +#ifdef M25P80_CS +static struct flash_platform_data stm25p80_platform_data = { + .name = "ST M25P80 SPI Flash chip", +#ifdef CONFIG_MTD_PARTITIONS + .parts = stm25p_partitions, + .nr_parts = sizeof(stm25p_partitions) / sizeof(*stm25p_partitions), +#endif + .type = FLASH_TYPE +}; +#endif + +static struct spi_board_info spi_board_info[] __initdata = { +#ifdef M25P80_CS + { + .modalias = "m25p80", + .max_speed_hz = 16000000, + .bus_num = 1, + .chip_select = M25P80_CS, + .platform_data = &stm25p80_platform_data, + .controller_data = &flash_chip_info + }, +#endif +#ifdef MMC_CS + { + .modalias = "mmc_spi", + .max_speed_hz = 16000000, + .bus_num = 1, + .chip_select = MMC_CS, + .controller_data = &mmc_chip_info + } +#endif +}; + +static struct coldfire_spi_master coldfire_master_info = { + .bus_num = 1, + .num_chipselect = SPI_NUM_CHIPSELECTS, + .irq_source = MCF5282_QSPI_IRQ_SOURCE, + .irq_vector = MCF5282_QSPI_IRQ_VECTOR, + .irq_mask = ((0x01 << MCF5282_QSPI_IRQ_SOURCE) | 0x01), + .irq_lp = 0x2B, /* Level 5 and Priority 3 */ + .par_val = SPI_PAR_VAL, + .cs_control = coldfire_qspi_cs_control, +}; + +static struct resource coldfire_spi_resources[] = { + [0] = { + .name = "qspi-par", + .start = MCF5282_QSPI_PAR, + .end = MCF5282_QSPI_PAR, + .flags = IORESOURCE_MEM + }, + + [1] = { + .name = "qspi-module", + .start = MCF5282_QSPI_QMR, + .end = MCF5282_QSPI_QMR + 0x18, + .flags = IORESOURCE_MEM + }, + + [2] = { + .name = "qspi-int-level", + .start = MCF5282_INTC0 + MCFINTC_ICR0 + MCF5282_QSPI_IRQ_SOURCE, + .end = MCF5282_INTC0 + MCFINTC_ICR0 + MCF5282_QSPI_IRQ_SOURCE, + .flags = IORESOURCE_MEM + }, + + [3] = { + .name = "qspi-int-mask", + .start = MCF5282_INTC0 + MCFINTC_IMRL, + .end = MCF5282_INTC0 + MCFINTC_IMRL, + .flags = IORESOURCE_MEM + } +}; + +static struct platform_device coldfire_spi = { + .name = "spi_coldfire", + .id = -1, + .resource = coldfire_spi_resources, + .num_resources = ARRAY_SIZE(coldfire_spi_resources), + .dev = { + .platform_data = &coldfire_master_info, + } +}; + +static void coldfire_qspi_cs_control(u8 cs, u8 command) +{ + u8 cs_bit = ((0x01 << cs) << 3) & SPI_CS_MASK; + +#if defined(CONFIG_WILDFIRE) + u8 cs_mask = ~(((0x01 << cs) << 3) & SPI_CS_MASK); +#endif +#if defined(CONFIG_WILDFIREMOD) + u8 cs_mask = (cs << 3) & SPI_CS_MASK; +#endif + + /* + * Don't do anything if the chip select is not + * one of the port qs pins. + */ + if (command & QSPI_CS_INIT) { +#if defined(CONFIG_WILDFIRE) + MCF5282_GPIO_DDRQS |= cs_bit; + MCF5282_GPIO_PQSPAR &= ~cs_bit; +#endif + +#if defined(CONFIG_WILDFIREMOD) + MCF5282_GPIO_DDRQS |= SPI_CS_MASK; + MCF5282_GPIO_PQSPAR &= ~SPI_CS_MASK; +#endif + } + + if (command & QSPI_CS_ASSERT) { + MCF5282_GPIO_PORTQS &= ~SPI_CS_MASK; + MCF5282_GPIO_PORTQS |= cs_mask; + } else if (command & QSPI_CS_DROP) { + MCF5282_GPIO_PORTQS |= SPI_CS_MASK; + } +} + +static int __init spi_dev_init(void) +{ + int retval; + + retval = platform_device_register(&coldfire_spi); + if (retval < 0) + return retval; + + if (ARRAY_SIZE(spi_board_info)) + retval = spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info)); + + return retval; +} + +#endif /* CONFIG_SPI */ /***************************************************************************/ @@ -111,10 +342,43 @@ void mcf_autovector(unsigned int vec) /***************************************************************************/ +#ifdef CONFIG_WILDFIRE +void wildfire_halt(void) +{ + writeb(0, 0x30000007); + writeb(0x2, 0x30000007); +} +#endif + +#ifdef CONFIG_WILDFIREMOD +void wildfiremod_halt(void) +{ + printk(KERN_INFO "WildFireMod hibernating...\n"); + + /* Set portE.5 to Digital IO */ + MCF5282_GPIO_PEPAR &= ~(1 << (5 * 2)); + + /* Make portE.5 an output */ + MCF5282_GPIO_DDRE |= (1 << 5); + + /* Now toggle portE.5 from low to high */ + MCF5282_GPIO_PORTE &= ~(1 << 5); + MCF5282_GPIO_PORTE |= (1 << 5); + + printk(KERN_EMERG "Failed to hibernate. Halting!\n"); +} +#endif + void __init config_BSP(char *commandp, int size) { mcf_disableall(); - mach_reset = coldfire_reset; + +#ifdef CONFIG_WILDFIRE + mach_halt = wildfire_halt; +#endif +#ifdef CONFIG_WILDFIREMOD + mach_halt = wildfiremod_halt; +#endif } /***************************************************************************/ diff --git a/arch/m68knommu/platform/5307/config.c b/arch/m68knommu/platform/5307/config.c index 92dc862fa82..11cff6625dc 100644 --- a/arch/m68knommu/platform/5307/config.c +++ b/arch/m68knommu/platform/5307/config.c @@ -124,8 +124,7 @@ void __init config_BSP(char *commandp, int size) mcf_setimr(MCFSIM_IMR_MASKALL); #if defined(CONFIG_NETtel) || defined(CONFIG_eLIA) || \ - defined(CONFIG_DISKtel) || defined(CONFIG_SECUREEDGEMP3) || \ - defined(CONFIG_CLEOPATRA) + defined(CONFIG_SECUREEDGEMP3) || defined(CONFIG_CLEOPATRA) /* Copy command line from FLASH to local buffer... */ memcpy(commandp, (char *) 0xf0004000, size); commandp[size-1] = 0; diff --git a/arch/m68knommu/platform/coldfire/entry.S b/arch/m68knommu/platform/coldfire/entry.S index 111b66dc737..1e3c0dcbd7a 100644 --- a/arch/m68knommu/platform/coldfire/entry.S +++ b/arch/m68knommu/platform/coldfire/entry.S @@ -103,9 +103,26 @@ ret_from_signal: addql #4,%sp ret_from_exception: + move #0x2700,%sr /* disable intrs */ btst #5,%sp@(PT_SR) /* check if returning to kernel */ jeq Luser_return /* if so, skip resched, signals */ +#ifdef CONFIG_PREEMPT + movel %sp,%d1 /* get thread_info pointer */ + andl #-THREAD_SIZE,%d1 /* at base of kernel stack */ + movel %d1,%a0 + movel %a0@(TI_FLAGS),%d1 /* get thread_info->flags */ + andl #_TIF_NEED_RESCHED,%d1 + jeq Lkernel_return + + movel %a0@(TI_PREEMPTCOUNT),%d1 + cmpl #0,%d1 + jne Lkernel_return + + pea Lkernel_return + jmp preempt_schedule_irq /* preempt the kernel */ +#endif + Lkernel_return: moveml %sp@,%d1-%d5/%a0-%a2 lea %sp@(32),%sp /* space for 8 regs */ @@ -140,6 +157,7 @@ Lreturn: Lwork_to_do: movel %a0@(TI_FLAGS),%d1 /* get thread_info->flags */ + move #0x2000,%sr /* enable intrs again */ btst #TIF_NEED_RESCHED,%d1 jne reschedule diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 77db3473dea..9fdd8bcdd21 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -54,6 +54,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; #include <linux/module.h> #include <linux/elfcore.h> #include <linux/compat.h> +#include <linux/math64.h> #define elf_prstatus elf_prstatus32 struct elf_prstatus32 @@ -102,8 +103,8 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) * one divide. */ u64 nsec = (u64)jiffies * TICK_NSEC; - long rem; - value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &rem); + u32 rem; + value->tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); value->tv_usec = rem / NSEC_PER_USEC; } diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 08f4cd781ee..e1333d7319e 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -56,6 +56,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; #include <linux/module.h> #include <linux/elfcore.h> #include <linux/compat.h> +#include <linux/math64.h> #define elf_prstatus elf_prstatus32 struct elf_prstatus32 @@ -104,8 +105,8 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) * one divide. */ u64 nsec = (u64)jiffies * TICK_NSEC; - long rem; - value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &rem); + u32 rem; + value->tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); value->tv_usec = rem / NSEC_PER_USEC; } diff --git a/arch/mips/kernel/irixioctl.c b/arch/mips/kernel/irixioctl.c index 2bde200d5ad..b39bdba82e0 100644 --- a/arch/mips/kernel/irixioctl.c +++ b/arch/mips/kernel/irixioctl.c @@ -27,33 +27,6 @@ struct irix_termios { cc_t c_cc[NCCS]; }; -extern void start_tty(struct tty_struct *tty); -static struct tty_struct *get_tty(int fd) -{ - struct file *filp; - struct tty_struct *ttyp = NULL; - - rcu_read_lock(); - filp = fcheck(fd); - if(filp && filp->private_data) { - ttyp = (struct tty_struct *) filp->private_data; - - if(ttyp->magic != TTY_MAGIC) - ttyp =NULL; - } - rcu_read_unlock(); - return ttyp; -} - -static struct tty_struct *get_real_tty(struct tty_struct *tp) -{ - if (tp->driver->type == TTY_DRIVER_TYPE_PTY && - tp->driver->subtype == PTY_TYPE_MASTER) - return tp->link; - else - return tp; -} - asmlinkage int irix_ioctl(int fd, unsigned long cmd, unsigned long arg) { struct tty_struct *tp, *rtp; @@ -146,34 +119,24 @@ asmlinkage int irix_ioctl(int fd, unsigned long cmd, unsigned long arg) error = sys_ioctl(fd, TIOCNOTTY, arg); break; - case 0x00007416: + case 0x00007416: { + pid_t pid; #ifdef DEBUG_IOCTLS printk("TIOCGSID, %08lx) ", arg); #endif - tp = get_tty(fd); - if(!tp) { - error = -EINVAL; - break; - } - rtp = get_real_tty(tp); -#ifdef DEBUG_IOCTLS - printk("rtp->session=%d ", rtp->session); -#endif - error = put_user(rtp->session, (unsigned long __user *) arg); + old_fs = get_fs(); set_fs(get_ds()); + error = sys_ioctl(fd, TIOCGSID, (unsigned long)&pid); + set_fs(old_fs); + if (!error) + error = put_user(pid, (unsigned long __user *) arg); break; - + } case 0x746e: /* TIOCSTART, same effect as hitting ^Q */ #ifdef DEBUG_IOCTLS printk("TIOCSTART, %08lx) ", arg); #endif - tp = get_tty(fd); - if(!tp) { - error = -EINVAL; - break; - } - rtp = get_real_tty(tp); - start_tty(rtp); + error = sys_ioctl(fd, TCXONC, TCOON); break; case 0x20006968: diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c index 998c4efcce8..ceb62dce1c9 100644 --- a/arch/mips/kernel/kspd.c +++ b/arch/mips/kernel/kspd.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/unistd.h> #include <linux/file.h> +#include <linux/fdtable.h> #include <linux/fs.h> #include <linux/syscalls.h> #include <linux/workqueue.h> diff --git a/arch/mn10300/kernel/sys_mn10300.c b/arch/mn10300/kernel/sys_mn10300.c index 5f17a1ebc82..bca5a84dc72 100644 --- a/arch/mn10300/kernel/sys_mn10300.c +++ b/arch/mn10300/kernel/sys_mn10300.c @@ -29,23 +29,6 @@ #define MIN_MAP_ADDR PAGE_SIZE /* minimum fixed mmap address */ /* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way Unix traditionally does this, though. - */ -asmlinkage long sys_pipe(unsigned long __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2 * sizeof(int))) - error = -EFAULT; - } - return error; -} - -/* * memory mapping syscall */ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 4f589216b39..71b31957c8f 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -33,19 +33,6 @@ #include <linux/utsname.h> #include <linux/personality.h> -int sys_pipe(int __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - static unsigned long get_unshared_area(unsigned long addr, unsigned long len) { struct vm_area_struct *vma; diff --git a/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/arch/powerpc/boot/dts/mpc8610_hpcd.dts index 1f2f1e0a557..bba234eb14a 100644 --- a/arch/powerpc/boot/dts/mpc8610_hpcd.dts +++ b/arch/powerpc/boot/dts/mpc8610_hpcd.dts @@ -21,6 +21,7 @@ serial1 = &serial1; pci0 = &pci0; pci1 = &pci1; + pci2 = &pci2; }; cpus { @@ -105,7 +106,7 @@ compatible = "ns16550"; reg = <0x4600 0x100>; clock-frequency = <0>; - interrupts = <28 2>; + interrupts = <42 2>; interrupt-parent = <&mpic>; }; @@ -322,4 +323,24 @@ }; }; }; + + pci2: pcie@e0009000 { + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + device_type = "pci"; + compatible = "fsl,mpc8641-pcie"; + reg = <0xe0009000 0x00001000>; + ranges = <0x02000000 0 0x90000000 0x90000000 0 0x10000000 + 0x01000000 0 0x00000000 0xe2000000 0 0x00100000>; + bus-range = <0 255>; + interrupt-map-mask = <0xf800 0 0 7>; + interrupt-map = <0x0000 0 0 1 &mpic 4 1 + 0x0000 0 0 2 &mpic 5 1 + 0x0000 0 0 3 &mpic 6 1 + 0x0000 0 0 4 &mpic 7 1>; + interrupt-parent = <&mpic>; + interrupts = <25 2>; + clock-frequency = <33333333>; + }; }; diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 7a64c564f6e..71d79e428d2 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.25-rc6 -# Thu Mar 20 11:07:04 2008 +# Linux kernel version: 2.6.25 +# Mon Apr 28 12:39:10 2008 # CONFIG_PPC64=y @@ -30,6 +30,9 @@ CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_GENERIC_HARDIRQS=y CONFIG_HAVE_SETUP_PER_CPU_AREA=y CONFIG_IRQ_PER_CPU=y +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +CONFIG_LOCKDEP_SUPPORT=y CONFIG_RWSEM_XCHGADD_ALGORITHM=y CONFIG_ARCH_HAS_ILOG2_U32=y CONFIG_ARCH_HAS_ILOG2_U64=y @@ -73,8 +76,6 @@ CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=17 # CONFIG_CGROUPS is not set # CONFIG_GROUP_SCHED is not set -# CONFIG_USER_SCHED is not set -# CONFIG_CGROUP_SCHED is not set CONFIG_SYSFS_DEPRECATED=y CONFIG_SYSFS_DEPRECATED_V2=y # CONFIG_RELAY is not set @@ -161,7 +162,6 @@ CONFIG_PPC_MULTIPLATFORM=y # CONFIG_PPC_PMAC is not set # CONFIG_PPC_MAPLE is not set # CONFIG_PPC_PASEMI is not set -# CONFIG_PPC_CELLEB is not set CONFIG_PPC_PS3=y # @@ -181,6 +181,7 @@ CONFIG_PS3_LPM=m CONFIG_PPC_CELL=y # CONFIG_PPC_CELL_NATIVE is not set # CONFIG_PPC_IBM_CELL_BLADE is not set +# CONFIG_PPC_CELLEB is not set # # Cell Broadband Engine options @@ -205,9 +206,9 @@ CONFIG_SPU_BASE=y # # Kernel options # -# CONFIG_TICK_ONESHOT is not set +CONFIG_TICK_ONESHOT=y # CONFIG_NO_HZ is not set -# CONFIG_HIGH_RES_TIMERS is not set +CONFIG_HIGH_RES_TIMERS=y CONFIG_GENERIC_CLOCKEVENTS_BUILD=y # CONFIG_HZ_100 is not set CONFIG_HZ_250=y @@ -221,7 +222,6 @@ CONFIG_PREEMPT_NONE=y CONFIG_BINFMT_ELF=y CONFIG_COMPAT_BINFMT_ELF=y CONFIG_BINFMT_MISC=y -CONFIG_FORCE_MAX_ZONEORDER=13 # CONFIG_IOMMU_VMERGE is not set CONFIG_IOMMU_HELPER=y CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y @@ -255,6 +255,7 @@ CONFIG_BOUNCE=y CONFIG_ARCH_MEMORY_PROBE=y # CONFIG_PPC_HAS_HASH_64K is not set # CONFIG_PPC_64K_PAGES is not set +CONFIG_FORCE_MAX_ZONEORDER=13 # CONFIG_SCHED_SMT is not set CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set @@ -272,7 +273,9 @@ CONFIG_GENERIC_ISA_DMA=y # CONFIG_PCI_SYSCALL is not set # CONFIG_ARCH_SUPPORTS_MSI is not set # CONFIG_PCCARD is not set +CONFIG_PAGE_OFFSET=0xc000000000000000 CONFIG_KERNEL_START=0xc000000000000000 +CONFIG_PHYSICAL_START=0x00000000 # # Networking @@ -292,7 +295,7 @@ CONFIG_XFRM=y # CONFIG_XFRM_STATISTICS is not set # CONFIG_NET_KEY is not set CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set +CONFIG_IP_MULTICAST=y # CONFIG_IP_ADVANCED_ROUTER is not set CONFIG_IP_FIB_HASH=y CONFIG_IP_PNP=y @@ -301,6 +304,7 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_IP_PNP_RARP is not set # CONFIG_NET_IPIP is not set # CONFIG_NET_IPGRE is not set +# CONFIG_IP_MROUTE is not set # CONFIG_ARPD is not set # CONFIG_SYN_COOKIES is not set # CONFIG_INET_AH is not set @@ -332,8 +336,10 @@ CONFIG_INET6_XFRM_MODE_TUNNEL=y CONFIG_INET6_XFRM_MODE_BEET=y # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set CONFIG_IPV6_SIT=y +CONFIG_IPV6_NDISC_NODETYPE=y # CONFIG_IPV6_TUNNEL is not set # CONFIG_IPV6_MULTIPLE_TABLES is not set +# CONFIG_IPV6_MROUTE is not set # CONFIG_NETWORK_SECMARK is not set # CONFIG_NETFILTER is not set # CONFIG_IP_DCCP is not set @@ -392,8 +398,6 @@ CONFIG_IEEE80211=m CONFIG_IEEE80211_CRYPT_WEP=m CONFIG_IEEE80211_CRYPT_CCMP=m CONFIG_IEEE80211_CRYPT_TKIP=m -CONFIG_IEEE80211_SOFTMAC=m -# CONFIG_IEEE80211_SOFTMAC_DEBUG is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -507,6 +511,7 @@ CONFIG_WLAN_80211=y # CONFIG_LIBERTAS is not set # CONFIG_USB_ZD1201 is not set # CONFIG_USB_NET_RNDIS_WLAN is not set +# CONFIG_IWLWIFI_LEDS is not set # CONFIG_HOSTAP is not set # @@ -578,6 +583,7 @@ CONFIG_INPUT_JOYSTICK=y # CONFIG_JOYSTICK_SPACEBALL is not set # CONFIG_JOYSTICK_STINGER is not set # CONFIG_JOYSTICK_TWIDJOY is not set +# CONFIG_JOYSTICK_ZHENHUA is not set # CONFIG_JOYSTICK_JOYDUMP is not set # CONFIG_JOYSTICK_XPAD is not set # CONFIG_INPUT_TABLET is not set @@ -641,6 +647,7 @@ CONFIG_SSB_POSSIBLE=y # Multifunction device drivers # # CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set # # Multimedia devices @@ -761,10 +768,6 @@ CONFIG_SND_PS3_DEFAULT_START_DELAY=2000 # CONFIG_SND_SOC is not set # -# SoC Audio support for SuperH -# - -# # ALSA SoC audio for Freescale SOCs # @@ -849,6 +852,7 @@ CONFIG_USB_STORAGE=m # CONFIG_USB_STORAGE_ALAUDA is not set # CONFIG_USB_STORAGE_ONETOUCH is not set # CONFIG_USB_STORAGE_KARMA is not set +# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set # CONFIG_USB_LIBUSUAL is not set # @@ -893,10 +897,6 @@ CONFIG_USB_MON=y # CONFIG_EDAC is not set # CONFIG_RTC_CLASS is not set # CONFIG_DMADEVICES is not set - -# -# Userspace I/O -# # CONFIG_UIO is not set # @@ -986,7 +986,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3=y # CONFIG_NFS_V3_ACL is not set CONFIG_NFS_V4=y -# CONFIG_NFS_DIRECTIO is not set # CONFIG_NFSD is not set CONFIG_ROOT_NFS=y CONFIG_LOCKD=y @@ -1059,9 +1058,10 @@ CONFIG_NLS_ISO8859_1=y # Library routines # CONFIG_BITREVERSE=y +# CONFIG_GENERIC_FIND_FIRST_BIT is not set # CONFIG_CRC_CCITT is not set # CONFIG_CRC16 is not set -# CONFIG_CRC_ITU_T is not set +CONFIG_CRC_ITU_T=m CONFIG_CRC32=y # CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set @@ -1071,6 +1071,7 @@ CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y +CONFIG_HAVE_LMB=y # # Kernel hacking @@ -1078,6 +1079,7 @@ CONFIG_HAS_DMA=y # CONFIG_PRINTK_TIME is not set CONFIG_ENABLE_WARN_DEPRECATED=y CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set # CONFIG_DEBUG_FS is not set @@ -1093,12 +1095,16 @@ CONFIG_SCHED_DEBUG=y # CONFIG_RT_MUTEX_TESTER is not set CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set CONFIG_DEBUG_SPINLOCK_SLEEP=y # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set # CONFIG_DEBUG_KOBJECT is not set CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_INFO=y # CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set CONFIG_DEBUG_LIST=y # CONFIG_DEBUG_SG is not set # CONFIG_BOOT_PRINTK_DELAY is not set @@ -1121,51 +1127,81 @@ CONFIG_IRQSTACKS=y # CONFIG_SECURITY is not set # CONFIG_SECURITY_FILE_CAPABILITIES is not set CONFIG_CRYPTO=y + +# +# Crypto core or helper +# CONFIG_CRYPTO_ALGAPI=y CONFIG_CRYPTO_AEAD=m CONFIG_CRYPTO_BLKCIPHER=y -CONFIG_CRYPTO_SEQIV=m CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_GF128MUL=m +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +# CONFIG_CRYPTO_AUTHENC is not set +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +CONFIG_CRYPTO_CCM=m +CONFIG_CRYPTO_GCM=m +CONFIG_CRYPTO_SEQIV=m + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +CONFIG_CRYPTO_CTR=m +# CONFIG_CRYPTO_CTS is not set +CONFIG_CRYPTO_ECB=m +# CONFIG_CRYPTO_LRW is not set +CONFIG_CRYPTO_PCBC=m +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# # CONFIG_CRYPTO_HMAC is not set # CONFIG_CRYPTO_XCBC is not set -# CONFIG_CRYPTO_NULL is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set # CONFIG_CRYPTO_MD4 is not set CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_MICHAEL_MIC=m # CONFIG_CRYPTO_SHA1 is not set # CONFIG_CRYPTO_SHA256 is not set # CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set # CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_GF128MUL=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_CBC=y -CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_LRW is not set -# CONFIG_CRYPTO_XTS is not set -CONFIG_CRYPTO_CTR=m -CONFIG_CRYPTO_GCM=m -CONFIG_CRYPTO_CCM=m -# CONFIG_CRYPTO_CRYPTD is not set -CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_FCRYPT is not set -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# CONFIG_CRYPTO_AES=m +# CONFIG_CRYPTO_ANUBIS is not set +CONFIG_CRYPTO_ARC4=m +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set # CONFIG_CRYPTO_CAST5 is not set # CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_FCRYPT is not set # CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_SEED is not set CONFIG_CRYPTO_SALSA20=m +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set + +# +# Compression +# # CONFIG_CRYPTO_DEFLATE is not set -CONFIG_CRYPTO_MICHAEL_MIC=m -# CONFIG_CRYPTO_CRC32C is not set -# CONFIG_CRYPTO_CAMELLIA is not set -# CONFIG_CRYPTO_TEST is not set -# CONFIG_CRYPTO_AUTHENC is not set CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_HW=y # CONFIG_PPC_CLOCK is not set +# CONFIG_VIRTUALIZATION is not set diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index be35ffae10f..1457aa0a08f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -386,6 +386,8 @@ static void __init smp_create_idle(unsigned int cpu) panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p)); #ifdef CONFIG_PPC64 paca[cpu].__current = p; + paca[cpu].kstack = (unsigned long) task_thread_info(p) + + THREAD_SIZE - STACK_FRAME_OVERHEAD; #endif current_set[cpu] = task_thread_info(p); task_thread_info(p)->cpu = cpu; diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index e722a4eeb5d..4fe69ca2448 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -136,23 +136,6 @@ int sys_ipc(uint call, int first, unsigned long second, long third, return ret; } -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -int sys_pipe(int __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - static inline unsigned long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long off, int shift) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 3b26fbd6bec..73401e83739 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -149,7 +149,7 @@ EXPORT_SYMBOL(tb_ticks_per_sec); /* for cputime_t conversions */ u64 tb_to_xs; unsigned tb_to_us; -#define TICKLEN_SCALE TICK_LENGTH_SHIFT +#define TICKLEN_SCALE NTP_SCALE_SHIFT u64 last_tick_len; /* units are ns / 2^TICKLEN_SCALE */ u64 ticklen_to_xs; /* 0.64 fraction */ @@ -1007,8 +1007,6 @@ void __init time_init(void) vdso_data->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; vdso_data->tb_to_xs = tb_to_xs; - time_freq = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); /* Register the clocksource, if we're not running on iSeries */ diff --git a/arch/powerpc/kvm/booke_guest.c b/arch/powerpc/kvm/booke_guest.c index 6d9884a6884..712d89a28c4 100644 --- a/arch/powerpc/kvm/booke_guest.c +++ b/arch/powerpc/kvm/booke_guest.c @@ -49,6 +49,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "inst_emu", VCPU_STAT(emulated_inst_exits) }, { "dec", VCPU_STAT(dec_exits) }, { "ext_intr", VCPU_STAT(ext_intr_exits) }, + { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { NULL } }; @@ -338,6 +339,11 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, } break; + case BOOKE_INTERRUPT_FP_UNAVAIL: + kvmppc_queue_exception(vcpu, exit_nr); + r = RESUME_GUEST; + break; + case BOOKE_INTERRUPT_DATA_STORAGE: vcpu->arch.dear = vcpu->arch.fault_dear; vcpu->arch.esr = vcpu->arch.fault_esr; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index bad40bd2d3a..777e0f34e0e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -36,13 +36,12 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - /* XXX implement me */ - return 0; + return !!(v->arch.pending_exceptions); } int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { - return 1; + return !(v->arch.msr & MSR_WE); } @@ -214,6 +213,11 @@ static void kvmppc_decrementer_func(unsigned long data) struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_DECREMENTER); + + if (waitqueue_active(&vcpu->wq)) { + wake_up_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) @@ -339,6 +343,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) int r; sigset_t sigsaved; + vcpu_load(vcpu); + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -363,12 +369,20 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); + vcpu_put(vcpu); + return r; } int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_EXTERNAL); + + if (waitqueue_active(&vcpu->wq)) { + wake_up_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + return 0; } diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 4bb023f4c86..f1d2cdc5331 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_SMP) += locks.o endif obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o +obj-$(CONFIG_HAS_IOMEM) += devres.o diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c new file mode 100644 index 00000000000..292115d98ea --- /dev/null +++ b/arch/powerpc/lib/devres.c @@ -0,0 +1,42 @@ +/* + * Copyright (C) 2008 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/device.h> /* devres_*(), devm_ioremap_release() */ +#include <linux/io.h> /* ioremap_flags() */ +#include <linux/module.h> /* EXPORT_SYMBOL() */ + +/** + * devm_ioremap_prot - Managed ioremap_flags() + * @dev: Generic device to remap IO address for + * @offset: BUS offset to map + * @size: Size of map + * @flags: Page flags + * + * Managed ioremap_prot(). Map is automatically unmapped on driver + * detach. + */ +void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags) +{ + void __iomem **ptr, *addr; + + ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + addr = ioremap_flags(offset, size, flags); + if (addr) { + *ptr = addr; + devres_add(dev, ptr); + } else + devres_free(ptr); + + return addr; +} +EXPORT_SYMBOL(devm_ioremap_prot); diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 906daeda59a..cf8705e32d6 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -30,7 +30,7 @@ #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) #else -#define DBG(fmt...) +#define DBG pr_debug #endif extern void slb_allocate_realmode(unsigned long ea); @@ -44,13 +44,13 @@ static void slb_allocate(unsigned long ea) slb_allocate_realmode(ea); } +#define slb_esid_mask(ssize) \ + (((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T) + static inline unsigned long mk_esid_data(unsigned long ea, int ssize, unsigned long slot) { - unsigned long mask; - - mask = (ssize == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T; - return (ea & mask) | SLB_ESID_V | slot; + return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot; } #define slb_vsid_shift(ssize) \ @@ -279,8 +279,8 @@ void slb_initialize(void) patch_slb_encoding(slb_compare_rr_to_size, mmu_slb_size); - DBG("SLB: linear LLP = %04x\n", linear_llp); - DBG("SLB: io LLP = %04x\n", io_llp); + DBG("SLB: linear LLP = %04lx\n", linear_llp); + DBG("SLB: io LLP = %04lx\n", io_llp); } get_paca()->stab_rr = SLB_NUM_BOLTED; @@ -301,11 +301,16 @@ void slb_initialize(void) create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, 1); + /* For the boot cpu, we're running on the stack in init_thread_union, + * which is in the first segment of the linear mapping, and also + * get_paca()->kstack hasn't been initialized yet. + * For secondary cpus, we need to bolt the kernel stack entry now. + */ slb_shadow_clear(2); + if (raw_smp_processor_id() != boot_cpuid && + (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET) + create_shadowed_slbe(get_paca()->kstack, + mmu_kernel_ssize, lflags, 2); - /* We don't bolt the stack for the time being - we're in boot, - * so the stack is in the bolted segment. By the time it goes - * elsewhere, we'll call _switch() which will bolt in the new - * one. */ asm volatile("isync":::"memory"); } diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index b962c3ab470..af116aadba1 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -22,6 +22,7 @@ #include <linux/elf.h> #include <linux/file.h> +#include <linux/fdtable.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/module.h> diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index a14e5cdc2fe..e59634f7af9 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -167,8 +167,8 @@ static struct irq_chip ps3_irq_chip = { * ps3_private data. */ -int ps3_virq_setup(enum ps3_cpu_binding cpu, unsigned long outlet, - unsigned int *virq) +static int ps3_virq_setup(enum ps3_cpu_binding cpu, unsigned long outlet, + unsigned int *virq) { int result; struct ps3_private *pd; @@ -217,7 +217,7 @@ fail_create: * Clears chip data and calls irq_dispose_mapping() for the virq. */ -int ps3_virq_destroy(unsigned int virq) +static int ps3_virq_destroy(unsigned int virq) { const struct ps3_private *pd = get_irq_chip_data(virq); diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c index bec3803f061..417eca79df6 100644 --- a/arch/powerpc/platforms/pseries/scanlog.c +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -55,11 +55,6 @@ static ssize_t scanlog_read(struct file *file, char __user *buf, dp = PDE(inode); data = (unsigned int *)dp->data; - if (!data) { - printk(KERN_ERR "scanlog: read failed no data\n"); - return -EIO; - } - if (count > RTAS_DATA_BUF_SIZE) count = RTAS_DATA_BUF_SIZE; @@ -146,11 +141,6 @@ static int scanlog_open(struct inode * inode, struct file * file) struct proc_dir_entry *dp = PDE(inode); unsigned int *data = (unsigned int *)dp->data; - if (!data) { - printk(KERN_ERR "scanlog: open failed no data\n"); - return -EIO; - } - if (data[0] != 0) { /* This imperfect test stops a second copy of the * data (or a reset while data is being copied) @@ -168,10 +158,6 @@ static int scanlog_release(struct inode * inode, struct file * file) struct proc_dir_entry *dp = PDE(inode); unsigned int *data = (unsigned int *)dp->data; - if (!data) { - printk(KERN_ERR "scanlog: release failed no data\n"); - return -EIO; - } data[0] = 0; return 0; @@ -200,12 +186,11 @@ static int __init scanlog_init(void) if (!data) goto err; - ent = proc_create("ppc64/rtas/scan-log-dump", S_IRUSR, NULL, - &scanlog_fops); + ent = proc_create_data("ppc64/rtas/scan-log-dump", S_IRUSR, NULL, + &scanlog_fops, data); if (!ent) goto err; - ent->data = data; proc_ppc64_scan_log_dump = ent; return 0; diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 3d920376f58..a0fa4ebb39c 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -176,6 +176,7 @@ struct rio_priv { /** * fsl_rio_doorbell_send - Send a MPC85xx doorbell message + * @mport: RapidIO master port info * @index: ID of RapidIO interface * @destid: Destination ID of target device * @data: 16-bit info field of RapidIO doorbell message @@ -211,6 +212,7 @@ static int fsl_rio_doorbell_send(struct rio_mport *mport, /** * fsl_local_config_read - Generate a MPC85xx local config space read + * @mport: RapidIO master port info * @index: ID of RapdiIO interface * @offset: Offset into configuration space * @len: Length (in bytes) of the maintenance transaction @@ -232,6 +234,7 @@ static int fsl_local_config_read(struct rio_mport *mport, /** * fsl_local_config_write - Generate a MPC85xx local config space write + * @mport: RapidIO master port info * @index: ID of RapdiIO interface * @offset: Offset into configuration space * @len: Length (in bytes) of the maintenance transaction @@ -254,6 +257,7 @@ static int fsl_local_config_write(struct rio_mport *mport, /** * fsl_rio_config_read - Generate a MPC85xx read maintenance transaction + * @mport: RapidIO master port info * @index: ID of RapdiIO interface * @destid: Destination ID of transaction * @hopcount: Number of hops to target device @@ -295,6 +299,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, /** * fsl_rio_config_write - Generate a MPC85xx write maintenance transaction + * @mport: RapidIO master port info * @index: ID of RapdiIO interface * @destid: Destination ID of transaction * @hopcount: Number of hops to target device @@ -985,8 +990,8 @@ static inline void fsl_rio_info(struct device *dev, u32 ccsr) } /** - * fsl_rio_setup - Setup MPC85xx RapidIO interface - * @fsl_rio_setup - Setup Freescale PowerPC RapidIO interface + * fsl_rio_setup - Setup Freescale PowerPC RapidIO interface + * @dev: of_device pointer * * Initializes MPC85xx RapidIO hardware interface, configures * master port with system-specific info, and registers the diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index 324c01b70dd..3a7054e2bb7 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -389,8 +389,8 @@ static int __init gfar_of_init(void) } gfar_data.phy_id = *id; - snprintf(gfar_data.bus_id, MII_BUS_ID_SIZE, "%x", - res.start); + snprintf(gfar_data.bus_id, MII_BUS_ID_SIZE, "%llx", + (unsigned long long)res.start); of_node_put(phy); of_node_put(mdio); diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c index ba8eea2bcce..b7aefd0d45c 100644 --- a/arch/powerpc/sysdev/xilinx_intc.c +++ b/arch/powerpc/sysdev/xilinx_intc.c @@ -107,7 +107,7 @@ xilinx_intc_init(struct device_node *np) } regs = ioremap(res.start, 32); - printk(KERN_INFO "Xilinx intc at 0x%08X mapped to 0x%p\n", + printk(KERN_INFO "Xilinx intc at 0x%08LX mapped to 0x%p\n", res.start, regs); /* Setup interrupt controller */ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 29a7940f284..1d035082e78 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -430,6 +430,13 @@ config CMM_IUCV Select this option to enable the special message interface to the cooperative memory management. +config PAGE_STATES + bool "Unused page notification" + help + This enables the notification of unused pages to the + hypervisor. The ESSA instruction is used to do the states + changes between a page that has content and the unused state. + config VIRT_TIMER bool "Virtual CPU timer support" help diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 743d54f0b8d..d003a6e16af 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -121,7 +121,7 @@ sys32_ptrace_wrapper: lgfr %r3,%r3 # long llgtr %r4,%r4 # long llgfr %r5,%r5 # long - jg sys_ptrace # branch to system call + jg compat_sys_ptrace # branch to system call .globl sys32_alarm_wrapper sys32_alarm_wrapper: diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index bdbb3bcd78a..708cf9cf9a3 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -279,8 +279,6 @@ sysc_do_restart: st %r2,SP_R2(%r15) # store return value (change R2 on stack) sysc_return: - tm SP_PSW+1(%r15),0x01 # returning to user ? - bno BASED(sysc_restore) tm __TI_flags+3(%r9),_TIF_WORK_SVC bnz BASED(sysc_work) # there is work to do (signals etc.) sysc_restore: @@ -312,6 +310,8 @@ sysc_work_loop: # One of the work bits is on. Find out which one. # sysc_work: + tm SP_PSW+1(%r15),0x01 # returning to user ? + bno BASED(sysc_restore) tm __TI_flags+3(%r9),_TIF_MCCK_PENDING bo BASED(sysc_mcck_pending) tm __TI_flags+3(%r9),_TIF_NEED_RESCHED @@ -602,12 +602,6 @@ io_no_vtime: la %r2,SP_PTREGS(%r15) # address of register-save area basr %r14,%r1 # branch to standard irq handler io_return: - tm SP_PSW+1(%r15),0x01 # returning to user ? -#ifdef CONFIG_PREEMPT - bno BASED(io_preempt) # no -> check for preemptive scheduling -#else - bno BASED(io_restore) # no-> skip resched & signal -#endif tm __TI_flags+3(%r9),_TIF_WORK_INT bnz BASED(io_work) # there is work to do (signals etc.) io_restore: @@ -629,10 +623,18 @@ io_restore_trace_psw: .long 0, io_restore_trace + 0x80000000 #endif -#ifdef CONFIG_PREEMPT -io_preempt: +# +# switch to kernel stack, then check the TIF bits +# +io_work: + tm SP_PSW+1(%r15),0x01 # returning to user ? +#ifndef CONFIG_PREEMPT + bno BASED(io_restore) # no-> skip resched & signal +#else + bnz BASED(io_work_user) # no -> check for preemptive scheduling + # check for preemptive scheduling icm %r0,15,__TI_precount(%r9) - bnz BASED(io_restore) + bnz BASED(io_restore) # preemption disabled l %r1,SP_R15(%r15) s %r1,BASED(.Lc_spsize) mvc SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15) @@ -646,10 +648,7 @@ io_resume_loop: br %r1 # call schedule #endif -# -# switch to kernel stack, then check the TIF bits -# -io_work: +io_work_user: l %r1,__LC_KERNEL_STACK s %r1,BASED(.Lc_spsize) mvc SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15) diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 5a4a7bcd2bb..fee10177dbf 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -271,8 +271,6 @@ sysc_noemu: stg %r2,SP_R2(%r15) # store return value (change R2 on stack) sysc_return: - tm SP_PSW+1(%r15),0x01 # returning to user ? - jno sysc_restore tm __TI_flags+7(%r9),_TIF_WORK_SVC jnz sysc_work # there is work to do (signals etc.) sysc_restore: @@ -304,6 +302,8 @@ sysc_work_loop: # One of the work bits is on. Find out which one. # sysc_work: + tm SP_PSW+1(%r15),0x01 # returning to user ? + jno sysc_restore tm __TI_flags+7(%r9),_TIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+7(%r9),_TIF_NEED_RESCHED @@ -585,12 +585,6 @@ io_no_vtime: la %r2,SP_PTREGS(%r15) # address of register-save area brasl %r14,do_IRQ # call standard irq handler io_return: - tm SP_PSW+1(%r15),0x01 # returning to user ? -#ifdef CONFIG_PREEMPT - jno io_preempt # no -> check for preemptive scheduling -#else - jno io_restore # no-> skip resched & signal -#endif tm __TI_flags+7(%r9),_TIF_WORK_INT jnz io_work # there is work to do (signals etc.) io_restore: @@ -612,10 +606,41 @@ io_restore_trace_psw: .quad 0, io_restore_trace #endif -#ifdef CONFIG_PREEMPT -io_preempt: +# +# There is work todo, we need to check if we return to userspace, then +# check, if we are in SIE, if yes leave it +# +io_work: + tm SP_PSW+1(%r15),0x01 # returning to user ? +#ifndef CONFIG_PREEMPT +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + jnz io_work_user # yes -> no need to check for SIE + la %r1, BASED(sie_opcode) # we return to kernel here + lg %r2, SP_PSW+8(%r15) + clc 0(2,%r1), 0(%r2) # is current instruction = SIE? + jne io_restore # no-> return to kernel + lg %r1, SP_PSW+8(%r15) # yes-> add 4 bytes to leave SIE + aghi %r1, 4 + stg %r1, SP_PSW+8(%r15) + j io_restore # return to kernel +#else + jno io_restore # no-> skip resched & signal +#endif +#else + jnz io_work_user # yes -> do resched & signal +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) + la %r1, BASED(sie_opcode) + lg %r2, SP_PSW+8(%r15) + clc 0(2,%r1), 0(%r2) # is current instruction = SIE? + jne 0f # no -> leave PSW alone + lg %r1, SP_PSW+8(%r15) # yes-> add 4 bytes to leave SIE + aghi %r1, 4 + stg %r1, SP_PSW+8(%r15) +0: +#endif + # check for preemptive scheduling icm %r0,15,__TI_precount(%r9) - jnz io_restore + jnz io_restore # preemption is disabled # switch to kernel stack lg %r1,SP_R15(%r15) aghi %r1,-SP_SIZE @@ -629,10 +654,7 @@ io_resume_loop: jg preempt_schedule_irq #endif -# -# switch to kernel stack, then check TIF bits -# -io_work: +io_work_user: lg %r1,__LC_KERNEL_STACK aghi %r1,-SP_SIZE mvc SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15) @@ -653,6 +675,11 @@ io_work_loop: j io_restore io_work_done: +#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) +sie_opcode: + .long 0xb2140000 +#endif + # # _TIF_MCCK_PENDING is set, call handler # diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 7f427016374..35827b9bd4d 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -292,8 +292,7 @@ poke_user(struct task_struct *child, addr_t addr, addr_t data) return 0; } -static int -do_ptrace_normal(struct task_struct *child, long request, long addr, long data) +long arch_ptrace(struct task_struct *child, long request, long addr, long data) { ptrace_area parea; int copied, ret; @@ -529,35 +528,19 @@ poke_user_emu31(struct task_struct *child, addr_t addr, addr_t data) return 0; } -static int -do_ptrace_emu31(struct task_struct *child, long request, long addr, long data) +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) { - unsigned int tmp; /* 4 bytes !! */ + unsigned long addr = caddr; + unsigned long data = cdata; ptrace_area_emu31 parea; int copied, ret; switch (request) { - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - /* read word at location addr. */ - copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0); - if (copied != sizeof(tmp)) - return -EIO; - return put_user(tmp, (unsigned int __force __user *) data); - case PTRACE_PEEKUSR: /* read the word at location addr in the USER area. */ return peek_user_emu31(child, addr, data); - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - /* write the word at location addr. */ - tmp = data; - copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 1); - if (copied != sizeof(tmp)) - return -EIO; - return 0; - case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ return poke_user_emu31(child, addr, data); @@ -587,82 +570,11 @@ do_ptrace_emu31(struct task_struct *child, long request, long addr, long data) copied += sizeof(unsigned int); } return 0; - case PTRACE_GETEVENTMSG: - return put_user((__u32) child->ptrace_message, - (unsigned int __force __user *) data); - case PTRACE_GETSIGINFO: - if (child->last_siginfo == NULL) - return -EINVAL; - return copy_siginfo_to_user32((compat_siginfo_t - __force __user *) data, - child->last_siginfo); - case PTRACE_SETSIGINFO: - if (child->last_siginfo == NULL) - return -EINVAL; - return copy_siginfo_from_user32(child->last_siginfo, - (compat_siginfo_t - __force __user *) data); } - return ptrace_request(child, request, addr, data); + return compat_ptrace_request(child, request, addr, data); } #endif -long arch_ptrace(struct task_struct *child, long request, long addr, long data) -{ - switch (request) { - case PTRACE_SYSCALL: - /* continue and stop at next (return from) syscall */ - case PTRACE_CONT: - /* restart after signal. */ - if (!valid_signal(data)) - return -EIO; - if (request == PTRACE_SYSCALL) - set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - else - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - child->exit_code = data; - /* make sure the single step bit is not set. */ - user_disable_single_step(child); - wake_up_process(child); - return 0; - - case PTRACE_KILL: - /* - * make the child exit. Best I can do is send it a sigkill. - * perhaps it should be put in the status that it wants to - * exit. - */ - if (child->exit_state == EXIT_ZOMBIE) /* already dead */ - return 0; - child->exit_code = SIGKILL; - /* make sure the single step bit is not set. */ - user_disable_single_step(child); - wake_up_process(child); - return 0; - - case PTRACE_SINGLESTEP: - /* set the trap flag. */ - if (!valid_signal(data)) - return -EIO; - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - child->exit_code = data; - user_enable_single_step(child); - /* give it a chance to run. */ - wake_up_process(child); - return 0; - - /* Do requests that differ for 31/64 bit */ - default: -#ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_31BIT)) - return do_ptrace_emu31(child, request, addr, data); -#endif - return do_ptrace_normal(child, request, addr, data); - } - /* Not reached. */ - return -EIO; -} - asmlinkage void syscall_trace(struct pt_regs *regs, int entryexit) { diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index 988d0d64c2c..5fdb799062b 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -32,23 +32,6 @@ #include <asm/uaccess.h> #include "entry.h" -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way Unix traditionally does this, though. - */ -asmlinkage long sys_pipe(unsigned long __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - /* common code for old and new mmaps */ static inline long do_mmap2( unsigned long addr, unsigned long len, diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 1761b74d639..e051cad1f1e 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -22,7 +22,6 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select S390_SWITCH_AMODE - select PREEMPT ---help--- Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 349581a2610..47a0b642174 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -105,6 +105,9 @@ static intercept_handler_t instruction_handlers[256] = { static int handle_noop(struct kvm_vcpu *vcpu) { switch (vcpu->arch.sie_block->icptcode) { + case 0x0: + vcpu->stat.exit_null++; + break; case 0x10: vcpu->stat.exit_external_request++; break; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 98d1e73e01f..0ac36a649eb 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -31,6 +31,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "userspace_handled", VCPU_STAT(exit_userspace) }, + { "exit_null", VCPU_STAT(exit_null) }, { "exit_validity", VCPU_STAT(exit_validity) }, { "exit_stop_request", VCPU_STAT(exit_stop_request) }, { "exit_external_request", VCPU_STAT(exit_external_request) }, @@ -221,10 +222,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK; restore_fp_regs(&vcpu->arch.guest_fpregs); restore_access_regs(vcpu->arch.guest_acrs); - - if (signal_pending(current)) - atomic_set_mask(CPUSTAT_STOP_INT, - &vcpu->arch.sie_block->cpuflags); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index fb988a48a75..2a745813454 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -5,3 +5,4 @@ obj-y := init.o fault.o extmem.o mmap.o vmem.o pgtable.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +obj-$(CONFIG_PAGE_STATES) += page-states.o diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index fa31de6ae97..29f3a63806b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -126,6 +126,9 @@ void __init mem_init(void) /* clear the zero-page */ memset(empty_zero_page, 0, PAGE_SIZE); + /* Setup guest page hinting */ + cmma_init(); + /* this will put all low memory onto the freelists */ totalram_pages += free_all_bootmem(); diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c new file mode 100644 index 00000000000..fc0ad73ffd9 --- /dev/null +++ b/arch/s390/mm/page-states.c @@ -0,0 +1,79 @@ +/* + * arch/s390/mm/page-states.c + * + * Copyright IBM Corp. 2008 + * + * Guest page hinting for unused pages. + * + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + */ + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/init.h> + +#define ESSA_SET_STABLE 1 +#define ESSA_SET_UNUSED 2 + +static int cmma_flag; + +static int __init cmma(char *str) +{ + char *parm; + parm = strstrip(str); + if (strcmp(parm, "yes") == 0 || strcmp(parm, "on") == 0) { + cmma_flag = 1; + return 1; + } + cmma_flag = 0; + if (strcmp(parm, "no") == 0 || strcmp(parm, "off") == 0) + return 1; + return 0; +} + +__setup("cmma=", cmma); + +void __init cmma_init(void) +{ + register unsigned long tmp asm("0") = 0; + register int rc asm("1") = -EOPNOTSUPP; + + if (!cmma_flag) + return; + asm volatile( + " .insn rrf,0xb9ab0000,%1,%1,0,0\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "+&d" (rc), "+&d" (tmp)); + if (rc) + cmma_flag = 0; +} + +void arch_free_page(struct page *page, int order) +{ + int i, rc; + + if (!cmma_flag) + return; + for (i = 0; i < (1 << order); i++) + asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" + : "=&d" (rc) + : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT), + "i" (ESSA_SET_UNUSED)); +} + +void arch_alloc_page(struct page *page, int order) +{ + int i, rc; + + if (!cmma_flag) + return; + for (i = 0; i < (1 << order); i++) + asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" + : "=&d" (rc) + : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT), + "i" (ESSA_SET_STABLE)); +} diff --git a/arch/sh/kernel/sys_sh64.c b/arch/sh/kernel/sys_sh64.c index 578004d71e0..91fb8445a5a 100644 --- a/arch/sh/kernel/sys_sh64.c +++ b/arch/sh/kernel/sys_sh64.c @@ -31,23 +31,6 @@ #include <asm/unistd.h> /* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way Unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long * fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - -/* * Do a system call from kernel instead of calling sys_execve so we * end up with proper pt_regs. */ diff --git a/arch/sparc/kernel/process.c b/arch/sparc/kernel/process.c index e7f35198ae3..36431f377de 100644 --- a/arch/sparc/kernel/process.c +++ b/arch/sparc/kernel/process.c @@ -419,14 +419,26 @@ asmlinkage int sparc_do_fork(unsigned long clone_flags, unsigned long stack_size) { unsigned long parent_tid_ptr, child_tid_ptr; + unsigned long orig_i1 = regs->u_regs[UREG_I1]; + long ret; parent_tid_ptr = regs->u_regs[UREG_I2]; child_tid_ptr = regs->u_regs[UREG_I4]; - return do_fork(clone_flags, stack_start, - regs, stack_size, - (int __user *) parent_tid_ptr, - (int __user *) child_tid_ptr); + ret = do_fork(clone_flags, stack_start, + regs, stack_size, + (int __user *) parent_tid_ptr, + (int __user *) child_tid_ptr); + + /* If we get an error and potentially restart the system + * call, we're screwed because copy_thread() clobbered + * the parent's %o1. So detect that case and restore it + * here. + */ + if ((unsigned long)ret >= -ERESTART_RESTARTBLOCK) + regs->u_regs[UREG_I1] = orig_i1; + + return ret; } /* Copy a Sparc thread. The fork() return value conventions diff --git a/arch/sparc/kernel/setup.c b/arch/sparc/kernel/setup.c index 3c13137685d..8a55c4f0df8 100644 --- a/arch/sparc/kernel/setup.c +++ b/arch/sparc/kernel/setup.c @@ -180,11 +180,9 @@ static void __init boot_flags_init(char *commands) /* This routine will in the future do all the nasty prom stuff * to probe for the mmu type and its parameters, etc. This will - * also be where SMP things happen plus the Sparc specific memory - * physical memory probe as on the alpha. + * also be where SMP things happen. */ -extern int prom_probe_memory(void); extern void sun4c_probe_vac(void); extern char cputypval; extern unsigned long start, end; @@ -268,7 +266,6 @@ void __init setup_arch(char **cmdline_p) if (ARCH_SUN4C_SUN4) sun4c_probe_vac(); load_mmu(); - (void) prom_probe_memory(); phys_base = 0xffffffffUL; highest_paddr = 0UL; diff --git a/arch/sparc/kernel/signal.c b/arch/sparc/kernel/signal.c index 3c312290c3c..368157926d2 100644 --- a/arch/sparc/kernel/signal.c +++ b/arch/sparc/kernel/signal.c @@ -245,15 +245,29 @@ static inline int invalid_frame_pointer(void __user *fp, int fplen) static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, unsigned long framesize) { - unsigned long sp; + unsigned long sp = regs->u_regs[UREG_FP]; - sp = regs->u_regs[UREG_FP]; + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user *) -1L; /* This is the X/Open sanctioned signal stack switching. */ if (sa->sa_flags & SA_ONSTACK) { - if (!on_sig_stack(sp) && !((current->sas_ss_sp + current->sas_ss_size) & 7)) + if (sas_ss_flags(sp) == 0) sp = current->sas_ss_sp + current->sas_ss_size; } + + /* Always align the stack frame. This handles two cases. First, + * sigaltstack need not be mindful of platform specific stack + * alignment. Second, if we took this signal because the stack + * is not aligned properly, we'd like to take the signal cleanly + * and report that. + */ + sp &= ~7UL; + return (void __user *)(sp - framesize); } diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc.c index f188b5dc9fd..e995491c443 100644 --- a/arch/sparc/kernel/sys_sparc.c +++ b/arch/sparc/kernel/sys_sparc.c @@ -223,8 +223,7 @@ int sparc_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) { if (ARCH_SUN4C_SUN4 && (len > 0x20000000 || - ((flags & MAP_FIXED) && - addr < 0xe0000000 && addr + len > 0x20000000))) + (addr < 0xe0000000 && addr + len > 0x20000000))) return -EINVAL; /* See asm-sparc/uaccess.h */ diff --git a/arch/sparc/mm/fault.c b/arch/sparc/mm/fault.c index e4d9c8e19df..abd50795a7b 100644 --- a/arch/sparc/mm/fault.c +++ b/arch/sparc/mm/fault.c @@ -47,64 +47,15 @@ int vac_size, vac_linesize, vac_do_hw_vac_flushes; int vac_entries_per_context, vac_entries_per_segment; int vac_entries_per_page; -/* Nice, simple, prom library does all the sweating for us. ;) */ -int prom_probe_memory (void) +/* Return how much physical memory we have. */ +unsigned long probe_memory(void) { - register struct linux_mlist_v0 *mlist; - register unsigned long bytes, base_paddr, tally; - register int i; - - i = 0; - mlist= *prom_meminfo()->v0_available; - bytes = tally = mlist->num_bytes; - base_paddr = (unsigned long) mlist->start_adr; - - sp_banks[0].base_addr = base_paddr; - sp_banks[0].num_bytes = bytes; - - while (mlist->theres_more != (void *) 0){ - i++; - mlist = mlist->theres_more; - bytes = mlist->num_bytes; - tally += bytes; - if (i > SPARC_PHYS_BANKS-1) { - printk ("The machine has more banks than " - "this kernel can support\n" - "Increase the SPARC_PHYS_BANKS " - "setting (currently %d)\n", - SPARC_PHYS_BANKS); - i = SPARC_PHYS_BANKS-1; - break; - } - - sp_banks[i].base_addr = (unsigned long) mlist->start_adr; - sp_banks[i].num_bytes = mlist->num_bytes; - } - - i++; - sp_banks[i].base_addr = 0xdeadbeef; - sp_banks[i].num_bytes = 0; - - /* Now mask all bank sizes on a page boundary, it is all we can - * use anyways. - */ - for(i=0; sp_banks[i].num_bytes != 0; i++) - sp_banks[i].num_bytes &= PAGE_MASK; - - return tally; -} - -/* Traverse the memory lists in the prom to see how much physical we - * have. - */ -unsigned long -probe_memory(void) -{ - int total; + unsigned long total = 0; + int i; - total = prom_probe_memory(); + for (i = 0; sp_banks[i].num_bytes; i++) + total += sp_banks[i].num_bytes; - /* Oh man, much nicer, keep the dirt in promlib. */ return total; } diff --git a/arch/sparc/prom/init.c b/arch/sparc/prom/init.c index 50abfb1b880..2fa3a474e3a 100644 --- a/arch/sparc/prom/init.c +++ b/arch/sparc/prom/init.c @@ -21,8 +21,6 @@ linux_sun4_romvec *sun4_romvec; /* The root node of the prom device tree. */ int prom_root_node; -int prom_stdin, prom_stdout; - /* Pointer to the device tree operations structure. */ struct linux_nodeops *prom_nodeops; @@ -74,11 +72,6 @@ void __init prom_init(struct linux_romvec *rp) (((unsigned long) prom_nodeops) == -1)) prom_halt(); - if(prom_vers == PROM_V2 || prom_vers == PROM_V3) { - prom_stdout = *romvec->pv_v2bootargs.fd_stdout; - prom_stdin = *romvec->pv_v2bootargs.fd_stdin; - } - prom_meminit(); prom_ranges_init(); diff --git a/arch/sparc/prom/memory.c b/arch/sparc/prom/memory.c index b0c0f9c4fc1..947f047dc95 100644 --- a/arch/sparc/prom/memory.c +++ b/arch/sparc/prom/memory.c @@ -1,215 +1,100 @@ -/* $Id: memory.c,v 1.15 2000/01/29 01:09:12 anton Exp $ - * memory.c: Prom routine for acquiring various bits of information +/* memory.c: Prom routine for acquiring various bits of information * about RAM on the machine, both virtual and physical. * - * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu) + * Copyright (C) 1995, 2008 David S. Miller (davem@davemloft.net) * Copyright (C) 1997 Michael A. Griffith (grif@acm.org) */ #include <linux/kernel.h> +#include <linux/sort.h> #include <linux/init.h> #include <asm/openprom.h> #include <asm/sun4prom.h> #include <asm/oplib.h> +#include <asm/page.h> -/* This routine, for consistency, returns the ram parameters in the - * V0 prom memory descriptor format. I choose this format because I - * think it was the easiest to work with. I feel the religious - * arguments now... ;) Also, I return the linked lists sorted to - * prevent paging_init() upset stomach as I have not yet written - * the pepto-bismol kernel module yet. - */ +static int __init prom_meminit_v0(void) +{ + struct linux_mlist_v0 *p; + int index; + + index = 0; + for (p = *(romvec->pv_v0mem.v0_available); p; p = p->theres_more) { + sp_banks[index].base_addr = (unsigned long) p->start_adr; + sp_banks[index].num_bytes = p->num_bytes; + index++; + } -struct linux_prom_registers prom_reg_memlist[64]; -struct linux_prom_registers prom_reg_tmp[64]; + return index; +} -struct linux_mlist_v0 prom_phys_total[64]; -struct linux_mlist_v0 prom_prom_taken[64]; -struct linux_mlist_v0 prom_phys_avail[64]; +static int __init prom_meminit_v2(void) +{ + struct linux_prom_registers reg[64]; + int node, size, num_ents, i; -struct linux_mlist_v0 *prom_ptot_ptr = prom_phys_total; -struct linux_mlist_v0 *prom_ptak_ptr = prom_prom_taken; -struct linux_mlist_v0 *prom_pavl_ptr = prom_phys_avail; + node = prom_searchsiblings(prom_getchild(prom_root_node), "memory"); + size = prom_getproperty(node, "available", (char *) reg, sizeof(reg)); + num_ents = size / sizeof(struct linux_prom_registers); -struct linux_mem_v0 prom_memlist; + for (i = 0; i < num_ents; i++) { + sp_banks[i].base_addr = reg[i].phys_addr; + sp_banks[i].num_bytes = reg[i].reg_size; + } + return num_ents; +} -/* Internal Prom library routine to sort a linux_mlist_v0 memory - * list. Used below in initialization. - */ -static void __init -prom_sortmemlist(struct linux_mlist_v0 *thislist) +static int __init prom_meminit_sun4(void) { - int swapi = 0; - int i, mitr, tmpsize; - char *tmpaddr; - char *lowest; - - for(i=0; thislist[i].theres_more; i++) { - lowest = thislist[i].start_adr; - for(mitr = i+1; thislist[mitr-1].theres_more; mitr++) - if(thislist[mitr].start_adr < lowest) { - lowest = thislist[mitr].start_adr; - swapi = mitr; - } - if(lowest == thislist[i].start_adr) continue; - tmpaddr = thislist[swapi].start_adr; - tmpsize = thislist[swapi].num_bytes; - for(mitr = swapi; mitr > i; mitr--) { - thislist[mitr].start_adr = thislist[mitr-1].start_adr; - thislist[mitr].num_bytes = thislist[mitr-1].num_bytes; - } - thislist[i].start_adr = tmpaddr; - thislist[i].num_bytes = tmpsize; - } +#ifdef CONFIG_SUN4 + sp_banks[0].base_addr = 0; + sp_banks[0].num_bytes = *(sun4_romvec->memoryavail); +#endif + return 1; +} + +static int sp_banks_cmp(const void *a, const void *b) +{ + const struct sparc_phys_banks *x = a, *y = b; - return; + if (x->base_addr > y->base_addr) + return 1; + if (x->base_addr < y->base_addr) + return -1; + return 0; } /* Initialize the memory lists based upon the prom version. */ void __init prom_meminit(void) { - int node = 0; - unsigned int iter, num_regs; - struct linux_mlist_v0 *mptr; /* ptr for traversal */ + int i, num_ents = 0; - switch(prom_vers) { + switch (prom_vers) { case PROM_V0: - /* Nice, kind of easier to do in this case. */ - /* First, the total physical descriptors. */ - for(mptr = (*(romvec->pv_v0mem.v0_totphys)), iter=0; - mptr; mptr=mptr->theres_more, iter++) { - prom_phys_total[iter].start_adr = mptr->start_adr; - prom_phys_total[iter].num_bytes = mptr->num_bytes; - prom_phys_total[iter].theres_more = &prom_phys_total[iter+1]; - } - prom_phys_total[iter-1].theres_more = NULL; - /* Second, the total prom taken descriptors. */ - for(mptr = (*(romvec->pv_v0mem.v0_prommap)), iter=0; - mptr; mptr=mptr->theres_more, iter++) { - prom_prom_taken[iter].start_adr = mptr->start_adr; - prom_prom_taken[iter].num_bytes = mptr->num_bytes; - prom_prom_taken[iter].theres_more = &prom_prom_taken[iter+1]; - } - prom_prom_taken[iter-1].theres_more = NULL; - /* Last, the available physical descriptors. */ - for(mptr = (*(romvec->pv_v0mem.v0_available)), iter=0; - mptr; mptr=mptr->theres_more, iter++) { - prom_phys_avail[iter].start_adr = mptr->start_adr; - prom_phys_avail[iter].num_bytes = mptr->num_bytes; - prom_phys_avail[iter].theres_more = &prom_phys_avail[iter+1]; - } - prom_phys_avail[iter-1].theres_more = NULL; - /* Sort all the lists. */ - prom_sortmemlist(prom_phys_total); - prom_sortmemlist(prom_prom_taken); - prom_sortmemlist(prom_phys_avail); + num_ents = prom_meminit_v0(); break; + case PROM_V2: case PROM_V3: - /* Grrr, have to traverse the prom device tree ;( */ - node = prom_getchild(prom_root_node); - node = prom_searchsiblings(node, "memory"); - num_regs = prom_getproperty(node, "available", - (char *) prom_reg_memlist, - sizeof(prom_reg_memlist)); - num_regs = (num_regs/sizeof(struct linux_prom_registers)); - for(iter=0; iter<num_regs; iter++) { - prom_phys_avail[iter].start_adr = - (char *) prom_reg_memlist[iter].phys_addr; - prom_phys_avail[iter].num_bytes = - (unsigned long) prom_reg_memlist[iter].reg_size; - prom_phys_avail[iter].theres_more = - &prom_phys_avail[iter+1]; - } - prom_phys_avail[iter-1].theres_more = NULL; - - num_regs = prom_getproperty(node, "reg", - (char *) prom_reg_memlist, - sizeof(prom_reg_memlist)); - num_regs = (num_regs/sizeof(struct linux_prom_registers)); - for(iter=0; iter<num_regs; iter++) { - prom_phys_total[iter].start_adr = - (char *) prom_reg_memlist[iter].phys_addr; - prom_phys_total[iter].num_bytes = - (unsigned long) prom_reg_memlist[iter].reg_size; - prom_phys_total[iter].theres_more = - &prom_phys_total[iter+1]; - } - prom_phys_total[iter-1].theres_more = NULL; - - node = prom_getchild(prom_root_node); - node = prom_searchsiblings(node, "virtual-memory"); - num_regs = prom_getproperty(node, "available", - (char *) prom_reg_memlist, - sizeof(prom_reg_memlist)); - num_regs = (num_regs/sizeof(struct linux_prom_registers)); - - /* Convert available virtual areas to taken virtual - * areas. First sort, then convert. - */ - for(iter=0; iter<num_regs; iter++) { - prom_prom_taken[iter].start_adr = - (char *) prom_reg_memlist[iter].phys_addr; - prom_prom_taken[iter].num_bytes = - (unsigned long) prom_reg_memlist[iter].reg_size; - prom_prom_taken[iter].theres_more = - &prom_prom_taken[iter+1]; - } - prom_prom_taken[iter-1].theres_more = NULL; - - prom_sortmemlist(prom_prom_taken); - - /* Finally, convert. */ - for(iter=0; iter<num_regs; iter++) { - prom_prom_taken[iter].start_adr = - prom_prom_taken[iter].start_adr + - prom_prom_taken[iter].num_bytes; - prom_prom_taken[iter].num_bytes = - prom_prom_taken[iter+1].start_adr - - prom_prom_taken[iter].start_adr; - } - prom_prom_taken[iter-1].num_bytes = - 0xffffffff - (unsigned long) prom_prom_taken[iter-1].start_adr; - - /* Sort the other two lists. */ - prom_sortmemlist(prom_phys_total); - prom_sortmemlist(prom_phys_avail); + num_ents = prom_meminit_v2(); break; case PROM_SUN4: -#ifdef CONFIG_SUN4 - /* how simple :) */ - prom_phys_total[0].start_adr = NULL; - prom_phys_total[0].num_bytes = *(sun4_romvec->memorysize); - prom_phys_total[0].theres_more = NULL; - prom_prom_taken[0].start_adr = NULL; - prom_prom_taken[0].num_bytes = 0x0; - prom_prom_taken[0].theres_more = NULL; - prom_phys_avail[0].start_adr = NULL; - prom_phys_avail[0].num_bytes = *(sun4_romvec->memoryavail); - prom_phys_avail[0].theres_more = NULL; -#endif + num_ents = prom_meminit_sun4(); break; default: break; - }; - - /* Link all the lists into the top-level descriptor. */ - prom_memlist.v0_totphys=&prom_ptot_ptr; - prom_memlist.v0_prommap=&prom_ptak_ptr; - prom_memlist.v0_available=&prom_pavl_ptr; + } + sort(sp_banks, num_ents, sizeof(struct sparc_phys_banks), + sp_banks_cmp, NULL); - return; -} + /* Sentinel. */ + sp_banks[num_ents].base_addr = 0xdeadbeef; + sp_banks[num_ents].num_bytes = 0; -/* This returns a pointer to our libraries internal v0 format - * memory descriptor. - */ -struct linux_mem_v0 * -prom_meminfo(void) -{ - return &prom_memlist; + for (i = 0; i < num_ents; i++) + sp_banks[i].num_bytes &= PAGE_MASK; } diff --git a/arch/sparc64/kernel/pci.c b/arch/sparc64/kernel/pci.c index dbf2fc2f4d8..112b09f16f3 100644 --- a/arch/sparc64/kernel/pci.c +++ b/arch/sparc64/kernel/pci.c @@ -350,8 +350,7 @@ static void pci_parse_of_addrs(struct of_device *op, struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, struct device_node *node, - struct pci_bus *bus, int devfn, - int host_controller) + struct pci_bus *bus, int devfn) { struct dev_archdata *sd; struct pci_dev *dev; @@ -390,43 +389,28 @@ struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->devfn = devfn; dev->multifunction = 0; /* maybe a lie? */ - if (host_controller) { - if (tlb_type != hypervisor) { - pci_read_config_word(dev, PCI_VENDOR_ID, - &dev->vendor); - pci_read_config_word(dev, PCI_DEVICE_ID, - &dev->device); - } else { - dev->vendor = PCI_VENDOR_ID_SUN; - dev->device = 0x80f0; - } - dev->cfg_size = 256; - dev->class = PCI_CLASS_BRIDGE_HOST << 8; - sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus), - 0x00, PCI_SLOT(devfn), PCI_FUNC(devfn)); - } else { - dev->vendor = of_getintprop_default(node, "vendor-id", 0xffff); - dev->device = of_getintprop_default(node, "device-id", 0xffff); - dev->subsystem_vendor = - of_getintprop_default(node, "subsystem-vendor-id", 0); - dev->subsystem_device = - of_getintprop_default(node, "subsystem-id", 0); - - dev->cfg_size = pci_cfg_space_size(dev); - - /* We can't actually use the firmware value, we have - * to read what is in the register right now. One - * reason is that in the case of IDE interfaces the - * firmware can sample the value before the the IDE - * interface is programmed into native mode. - */ - pci_read_config_dword(dev, PCI_CLASS_REVISION, &class); - dev->class = class >> 8; - dev->revision = class & 0xff; + dev->vendor = of_getintprop_default(node, "vendor-id", 0xffff); + dev->device = of_getintprop_default(node, "device-id", 0xffff); + dev->subsystem_vendor = + of_getintprop_default(node, "subsystem-vendor-id", 0); + dev->subsystem_device = + of_getintprop_default(node, "subsystem-id", 0); + + dev->cfg_size = pci_cfg_space_size(dev); + + /* We can't actually use the firmware value, we have + * to read what is in the register right now. One + * reason is that in the case of IDE interfaces the + * firmware can sample the value before the the IDE + * interface is programmed into native mode. + */ + pci_read_config_dword(dev, PCI_CLASS_REVISION, &class); + dev->class = class >> 8; + dev->revision = class & 0xff; + + sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus), + dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn)); - sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus), - dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn)); - } if (ofpci_verbose) printk(" class: 0x%x device name: %s\n", dev->class, pci_name(dev)); @@ -441,26 +425,21 @@ struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->current_state = 4; /* unknown power state */ dev->error_state = pci_channel_io_normal; - if (host_controller) { + if (!strcmp(type, "pci") || !strcmp(type, "pciex")) { + /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; dev->rom_base_reg = PCI_ROM_ADDRESS1; - dev->irq = PCI_IRQ_NONE; + } else if (!strcmp(type, "cardbus")) { + dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; } else { - if (!strcmp(type, "pci") || !strcmp(type, "pciex")) { - /* a PCI-PCI bridge */ - dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; - dev->rom_base_reg = PCI_ROM_ADDRESS1; - } else if (!strcmp(type, "cardbus")) { - dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; - } else { - dev->hdr_type = PCI_HEADER_TYPE_NORMAL; - dev->rom_base_reg = PCI_ROM_ADDRESS; + dev->hdr_type = PCI_HEADER_TYPE_NORMAL; + dev->rom_base_reg = PCI_ROM_ADDRESS; - dev->irq = sd->op->irqs[0]; - if (dev->irq == 0xffffffff) - dev->irq = PCI_IRQ_NONE; - } + dev->irq = sd->op->irqs[0]; + if (dev->irq == 0xffffffff) + dev->irq = PCI_IRQ_NONE; } + pci_parse_of_addrs(sd->op, node, dev); if (ofpci_verbose) @@ -749,7 +728,7 @@ static void __devinit pci_of_scan_bus(struct pci_pbm_info *pbm, prev_devfn = devfn; /* create a new pci_dev for this device */ - dev = of_create_pci_dev(pbm, child, bus, devfn, 0); + dev = of_create_pci_dev(pbm, child, bus, devfn); if (!dev) continue; if (ofpci_verbose) @@ -796,48 +775,9 @@ static void __devinit pci_bus_register_of_sysfs(struct pci_bus *bus) pci_bus_register_of_sysfs(child_bus); } -int pci_host_bridge_read_pci_cfg(struct pci_bus *bus_dev, - unsigned int devfn, - int where, int size, - u32 *value) -{ - static u8 fake_pci_config[] = { - 0x8e, 0x10, /* Vendor: 0x108e (Sun) */ - 0xf0, 0x80, /* Device: 0x80f0 (Fire) */ - 0x46, 0x01, /* Command: 0x0146 (SERR, PARITY, MASTER, MEM) */ - 0xa0, 0x22, /* Status: 0x02a0 (DEVSEL_MED, FB2B, 66MHZ) */ - 0x00, 0x00, 0x00, 0x06, /* Class: 0x06000000 host bridge */ - 0x00, /* Cacheline: 0x00 */ - 0x40, /* Latency: 0x40 */ - 0x00, /* Header-Type: 0x00 normal */ - }; - - *value = 0; - if (where >= 0 && where < sizeof(fake_pci_config) && - (where + size) >= 0 && - (where + size) < sizeof(fake_pci_config) && - size <= sizeof(u32)) { - while (size--) { - *value <<= 8; - *value |= fake_pci_config[where + size]; - } - } - - return PCIBIOS_SUCCESSFUL; -} - -int pci_host_bridge_write_pci_cfg(struct pci_bus *bus_dev, - unsigned int devfn, - int where, int size, - u32 value) -{ - return PCIBIOS_SUCCESSFUL; -} - struct pci_bus * __devinit pci_scan_one_pbm(struct pci_pbm_info *pbm) { struct device_node *node = pbm->prom_node; - struct pci_dev *host_pdev; struct pci_bus *bus; printk("PCI: Scanning PBM %s\n", node->full_name); @@ -855,10 +795,6 @@ struct pci_bus * __devinit pci_scan_one_pbm(struct pci_pbm_info *pbm) bus->resource[0] = &pbm->io_space; bus->resource[1] = &pbm->mem_space; - /* Create the dummy host bridge and link it in. */ - host_pdev = of_create_pci_dev(pbm, node, bus, 0x00, 1); - bus->self = host_pdev; - pci_of_scan_bus(pbm, node, bus); pci_bus_add_devices(bus); pci_bus_register_of_sysfs(bus); diff --git a/arch/sparc64/kernel/pci_common.c b/arch/sparc64/kernel/pci_common.c index 923e0bcc3bf..19fa621d6a6 100644 --- a/arch/sparc64/kernel/pci_common.c +++ b/arch/sparc64/kernel/pci_common.c @@ -264,9 +264,6 @@ static int sun4v_read_pci_cfg(struct pci_bus *bus_dev, unsigned int devfn, unsigned int func = PCI_FUNC(devfn); unsigned long ret; - if (!bus && devfn == 0x00) - return pci_host_bridge_read_pci_cfg(bus_dev, devfn, where, - size, value); if (config_out_of_range(pbm, bus, devfn, where)) { ret = ~0UL; } else { @@ -300,9 +297,6 @@ static int sun4v_write_pci_cfg(struct pci_bus *bus_dev, unsigned int devfn, unsigned int func = PCI_FUNC(devfn); unsigned long ret; - if (!bus && devfn == 0x00) - return pci_host_bridge_write_pci_cfg(bus_dev, devfn, where, - size, value); if (config_out_of_range(pbm, bus, devfn, where)) { /* Do nothing. */ } else { diff --git a/arch/sparc64/kernel/pci_impl.h b/arch/sparc64/kernel/pci_impl.h index 218bac4ff79..c385d126be1 100644 --- a/arch/sparc64/kernel/pci_impl.h +++ b/arch/sparc64/kernel/pci_impl.h @@ -167,15 +167,6 @@ extern void pci_get_pbm_props(struct pci_pbm_info *pbm); extern struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm); extern void pci_determine_mem_io_space(struct pci_pbm_info *pbm); -extern int pci_host_bridge_read_pci_cfg(struct pci_bus *bus_dev, - unsigned int devfn, - int where, int size, - u32 *value); -extern int pci_host_bridge_write_pci_cfg(struct pci_bus *bus_dev, - unsigned int devfn, - int where, int size, - u32 value); - /* Error reporting support. */ extern void pci_scan_for_target_abort(struct pci_pbm_info *, struct pci_bus *); extern void pci_scan_for_master_abort(struct pci_pbm_info *, struct pci_bus *); diff --git a/arch/sparc64/kernel/process.c b/arch/sparc64/kernel/process.c index 05601374915..4129c044985 100644 --- a/arch/sparc64/kernel/process.c +++ b/arch/sparc64/kernel/process.c @@ -503,6 +503,8 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags, unsigned long stack_size) { int __user *parent_tid_ptr, *child_tid_ptr; + unsigned long orig_i1 = regs->u_regs[UREG_I1]; + long ret; #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) { @@ -515,9 +517,19 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags, child_tid_ptr = (int __user *) regs->u_regs[UREG_I4]; } - return do_fork(clone_flags, stack_start, - regs, stack_size, - parent_tid_ptr, child_tid_ptr); + ret = do_fork(clone_flags, stack_start, + regs, stack_size, + parent_tid_ptr, child_tid_ptr); + + /* If we get an error and potentially restart the system + * call, we're screwed because copy_thread() clobbered + * the parent's %o1. So detect that case and restore it + * here. + */ + if ((unsigned long)ret >= -ERESTART_RESTARTBLOCK) + regs->u_regs[UREG_I1] = orig_i1; + + return ret; } /* Copy a Sparc thread. The fork() return value conventions @@ -591,12 +603,6 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, if (clone_flags & CLONE_SETTLS) t->kregs->u_regs[UREG_G7] = regs->u_regs[UREG_I3]; - /* We do not want to accidently trigger system call restart - * handling in the new thread. Therefore, clear out the trap - * type, which will make pt_regs_regs_is_syscall() return false. - */ - pt_regs_clear_trap_type(t->kregs); - return 0; } diff --git a/arch/sparc64/kernel/signal.c b/arch/sparc64/kernel/signal.c index f2d88d8f7a4..07c0443ea3f 100644 --- a/arch/sparc64/kernel/signal.c +++ b/arch/sparc64/kernel/signal.c @@ -332,6 +332,9 @@ void do_rt_sigreturn(struct pt_regs *regs) regs->tpc = tpc; regs->tnpc = tnpc; + /* Prevent syscall restart. */ + pt_regs_clear_trap_type(regs); + sigdelsetmask(&set, ~_BLOCKABLE); spin_lock_irq(¤t->sighand->siglock); current->blocked = set; @@ -373,16 +376,29 @@ save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, unsigned long framesize) { - unsigned long sp; + unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; - sp = regs->u_regs[UREG_FP] + STACK_BIAS; + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user *) -1L; /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { - if (!on_sig_stack(sp) && - !((current->sas_ss_sp + current->sas_ss_size) & 7)) + if (sas_ss_flags(sp) == 0) sp = current->sas_ss_sp + current->sas_ss_size; } + + /* Always align the stack frame. This handles two cases. First, + * sigaltstack need not be mindful of platform specific stack + * alignment. Second, if we took this signal because the stack + * is not aligned properly, we'd like to take the signal cleanly + * and report that. + */ + sp &= ~7UL; + return (void __user *)(sp - framesize); } @@ -515,7 +531,8 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) siginfo_t info; int signr; - if (pt_regs_is_syscall(regs)) { + if (pt_regs_is_syscall(regs) && + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { pt_regs_clear_trap_type(regs); cookie.restart_syscall = 1; } else diff --git a/arch/sparc64/kernel/signal32.c b/arch/sparc64/kernel/signal32.c index 91f8d0826db..0f6b7b156ef 100644 --- a/arch/sparc64/kernel/signal32.c +++ b/arch/sparc64/kernel/signal32.c @@ -268,6 +268,9 @@ void do_sigreturn32(struct pt_regs *regs) regs->tstate &= ~(TSTATE_ICC|TSTATE_XCC); regs->tstate |= psr_to_tstate_icc(psr); + /* Prevent syscall restart. */ + pt_regs_clear_trap_type(regs); + err |= __get_user(fpu_save, &sf->fpu_save); if (fpu_save) err |= restore_fpu_state32(regs, &sf->fpu_state); @@ -351,6 +354,9 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) regs->tstate &= ~(TSTATE_ICC|TSTATE_XCC); regs->tstate |= psr_to_tstate_icc(psr); + /* Prevent syscall restart. */ + pt_regs_clear_trap_type(regs); + err |= __get_user(fpu_save, &sf->fpu_save); if (fpu_save) err |= restore_fpu_state32(regs, &sf->fpu_state); @@ -400,11 +406,27 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL; sp = regs->u_regs[UREG_FP]; + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user *) -1L; + /* This is the X/Open sanctioned signal stack switching. */ if (sa->sa_flags & SA_ONSTACK) { - if (!on_sig_stack(sp) && !((current->sas_ss_sp + current->sas_ss_size) & 7)) + if (sas_ss_flags(sp) == 0) sp = current->sas_ss_sp + current->sas_ss_size; } + + /* Always align the stack frame. This handles two cases. First, + * sigaltstack need not be mindful of platform specific stack + * alignment. Second, if we took this signal because the stack + * is not aligned properly, we'd like to take the signal cleanly + * and report that. + */ + sp &= ~7UL; + return (void __user *)(sp - framesize); } diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c index 3aba47624df..0d6403a630a 100644 --- a/arch/sparc64/kernel/smp.c +++ b/arch/sparc64/kernel/smp.c @@ -865,21 +865,14 @@ void smp_call_function_client(int irq, struct pt_regs *regs) void *info = call_data->info; clear_softint(1 << irq); - - irq_enter(); - - if (!call_data->wait) { - /* let initiator proceed after getting data */ - atomic_inc(&call_data->finished); - } - - func(info); - - irq_exit(); - if (call_data->wait) { /* let initiator proceed only after completion */ + func(info); atomic_inc(&call_data->finished); + } else { + /* let initiator proceed after getting data */ + atomic_inc(&call_data->finished); + func(info); } } @@ -1041,9 +1034,7 @@ void smp_receive_signal(int cpu) void smp_receive_signal_client(int irq, struct pt_regs *regs) { - irq_enter(); clear_softint(1 << irq); - irq_exit(); } void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) @@ -1051,8 +1042,6 @@ void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) struct mm_struct *mm; unsigned long flags; - irq_enter(); - clear_softint(1 << irq); /* See if we need to allocate a new TLB context because @@ -1072,8 +1061,6 @@ void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) load_secondary_context(mm); __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT); - - irq_exit(); } void smp_new_mmu_context_version(void) @@ -1239,8 +1226,6 @@ void smp_penguin_jailcell(int irq, struct pt_regs *regs) { clear_softint(1 << irq); - irq_enter(); - preempt_disable(); __asm__ __volatile__("flushw"); @@ -1253,8 +1238,6 @@ void smp_penguin_jailcell(int irq, struct pt_regs *regs) prom_world(0); preempt_enable(); - - irq_exit(); } /* /proc/profile writes can call this, don't __init it please. */ diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc64/kernel/sys_sparc.c index 8d4761f15fa..0dbc941f130 100644 --- a/arch/sparc64/kernel/sys_sparc.c +++ b/arch/sparc64/kernel/sys_sparc.c @@ -549,13 +549,13 @@ int sparc64_mmap_check(unsigned long addr, unsigned long len, if (len >= STACK_TOP32) return -EINVAL; - if ((flags & MAP_FIXED) && addr > STACK_TOP32 - len) + if (addr > STACK_TOP32 - len) return -EINVAL; } else { if (len >= VA_EXCLUDE_START) return -EINVAL; - if ((flags & MAP_FIXED) && invalid_64bit_range(addr, len)) + if (invalid_64bit_range(addr, len)) return -EINVAL; } diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c index 161ce4710fe..1aa4288125f 100644 --- a/arch/sparc64/kernel/sys_sparc32.c +++ b/arch/sparc64/kernel/sys_sparc32.c @@ -236,13 +236,6 @@ asmlinkage long sys32_getegid16(void) /* 32-bit timeval and related flotsam. */ -static long get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - return (!access_ok(VERIFY_READ, i, sizeof(*i)) || - (__get_user(o->tv_sec, &i->tv_sec) | - __get_user(o->tv_usec, &i->tv_usec))); -} - static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) { return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || @@ -757,30 +750,6 @@ asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); } -asmlinkage long sys32_utimes(char __user *filename, - struct compat_timeval __user *tvs) -{ - struct timespec tv[2]; - - if (tvs) { - struct timeval ktvs[2]; - if (get_tv32(&ktvs[0], tvs) || - get_tv32(&ktvs[1], 1+tvs)) - return -EFAULT; - - if (ktvs[0].tv_usec < 0 || ktvs[0].tv_usec >= 1000000 || - ktvs[1].tv_usec < 0 || ktvs[1].tv_usec >= 1000000) - return -EINVAL; - - tv[0].tv_sec = ktvs[0].tv_sec; - tv[0].tv_nsec = 1000 * ktvs[0].tv_usec; - tv[1].tv_sec = ktvs[1].tv_sec; - tv[1].tv_nsec = 1000 * ktvs[1].tv_usec; - } - - return do_utimes(AT_FDCWD, filename, tvs ? tv : NULL, 0); -} - /* These are here just in case some old sparc32 binary calls it. */ asmlinkage long sys32_pause(void) { diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc64/kernel/systbls.S index a4fef2ba1ae..8b5282d433c 100644 --- a/arch/sparc64/kernel/systbls.S +++ b/arch/sparc64/kernel/systbls.S @@ -45,7 +45,7 @@ sys_call_table32: /*120*/ .word compat_sys_readv, compat_sys_writev, sys32_settimeofday, sys32_fchown16, sys_fchmod .word sys_nis_syscall, sys32_setreuid16, sys32_setregid16, sys_rename, sys_truncate /*130*/ .word sys_ftruncate, sys_flock, compat_sys_lstat64, sys_nis_syscall, sys_nis_syscall - .word sys_nis_syscall, sys32_mkdir, sys_rmdir, sys32_utimes, compat_sys_stat64 + .word sys_nis_syscall, sys32_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 /*140*/ .word sys32_sendfile64, sys_nis_syscall, sys32_futex, sys_gettid, compat_sys_getrlimit .word compat_sys_setrlimit, sys_pivot_root, sys32_prctl, sys_pciconfig_read, sys_pciconfig_write /*150*/ .word sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 diff --git a/arch/sparc64/mm/init.c b/arch/sparc64/mm/init.c index 4cad0b32b0a..ec3e2c72302 100644 --- a/arch/sparc64/mm/init.c +++ b/arch/sparc64/mm/init.c @@ -771,6 +771,9 @@ static void __init find_ramdisk(unsigned long phys_base) initrd_end = ramdisk_image + sparc_ramdisk_size; lmb_reserve(initrd_start, initrd_end); + + initrd_start += PAGE_OFFSET; + initrd_end += PAGE_OFFSET; } #endif } @@ -2362,16 +2365,3 @@ void __flush_tlb_all(void) __asm__ __volatile__("wrpr %0, 0, %%pstate" : : "r" (pstate)); } - -#ifdef CONFIG_MEMORY_HOTPLUG - -void online_page(struct page *page) -{ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalram_pages++; - num_physpages++; -} - -#endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 10b86e1cc65..5047490fc29 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -191,9 +191,9 @@ void line_flush_chars(struct tty_struct *tty) line_flush_buffer(tty); } -void line_put_char(struct tty_struct *tty, unsigned char ch) +int line_put_char(struct tty_struct *tty, unsigned char ch) { - line_write(tty, &ch, sizeof(ch)); + return line_write(tty, &ch, sizeof(ch)); } int line_write(struct tty_struct *tty, const unsigned char *buf, int len) diff --git a/arch/um/include/line.h b/arch/um/include/line.h index 1223f2c844b..979b73e6352 100644 --- a/arch/um/include/line.h +++ b/arch/um/include/line.h @@ -71,7 +71,7 @@ extern int line_setup(struct line *lines, unsigned int sizeof_lines, char *init, char **error_out); extern int line_write(struct tty_struct *tty, const unsigned char *buf, int len); -extern void line_put_char(struct tty_struct *tty, unsigned char ch); +extern int line_put_char(struct tty_struct *tty, unsigned char ch); extern void line_set_termios(struct tty_struct *tty, struct ktermios * old); extern int line_chars_in_buffer(struct tty_struct *tty); extern void line_flush_buffer(struct tty_struct *tty); diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 9cffc628a37..128ee85bc8d 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -73,23 +73,6 @@ long old_mmap(unsigned long addr, unsigned long len, out: return err; } -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -long sys_pipe(unsigned long __user * fildes) -{ - int fd[2]; - long error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, sizeof(fd))) - error = -EFAULT; - } - return error; -} - long sys_uname(struct old_utsname __user * name) { diff --git a/arch/v850/kernel/syscalls.c b/arch/v850/kernel/syscalls.c index 003db9c8c44..1a83daf8e24 100644 --- a/arch/v850/kernel/syscalls.c +++ b/arch/v850/kernel/syscalls.c @@ -132,23 +132,6 @@ sys_ipc (uint call, int first, int second, int third, void *ptr, long fifth) return ret; } -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way unix traditionally does this, though. - */ -int sys_pipe (int *fildes) -{ - int fd[2]; - int error; - - error = do_pipe (fd); - if (!error) { - if (copy_to_user (fildes, fd, 2*sizeof (int))) - error = -EFAULT; - } - return error; -} - static inline unsigned long do_mmap2 (unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c3f880902d6..bbcafaa160c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -18,6 +18,7 @@ config X86_64 ### Arch settings config X86 def_bool y + select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE select HAVE_KPROBES @@ -1661,6 +1662,7 @@ config GEODE_MFGPT_TIMER config OLPC bool "One Laptop Per Child support" + depends on MGEODE_LX default n help Add support for detecting the unique features of the OLPC diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index d01ea42187e..edaadea90aa 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -191,7 +191,7 @@ static void read_ehdr(FILE *fp) die("Cannot read ELF header: %s\n", strerror(errno)); } - if (memcmp(ehdr.e_ident, ELFMAG, 4) != 0) { + if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) { die("No ELF magic\n"); } if (ehdr.e_ident[EI_CLASS] != ELFCLASS32) { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index bbdacb398d4..5e618c3b472 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -83,9 +83,7 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o -ifdef CONFIG_INPUT_PCSPKR -obj-y += pcspeaker.o -endif +obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o obj-$(CONFIG_SCx200) += scx200.o scx200-y += scx200_32.o diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 7335959b6af..fd5ca97a2ad 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -10,5 +10,5 @@ endif $(obj)/wakeup_rm.o: $(obj)/realmode/wakeup.bin $(obj)/realmode/wakeup.bin: FORCE - $(Q)$(MAKE) $(build)=$(obj)/realmode $@ + $(Q)$(MAKE) $(build)=$(obj)/realmode diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile index 092900854ac..1c31cc0e9de 100644 --- a/arch/x86/kernel/acpi/realmode/Makefile +++ b/arch/x86/kernel/acpi/realmode/Makefile @@ -6,7 +6,8 @@ # for more details. # -targets := wakeup.bin wakeup.elf +always := wakeup.bin +targets := wakeup.elf wakeup.lds wakeup-y += wakeup.o wakemain.o video-mode.o copy.o @@ -48,7 +49,7 @@ LDFLAGS_wakeup.elf := -T CPPFLAGS_wakeup.lds += -P -C -$(obj)/wakeup.elf: $(src)/wakeup.lds $(WAKEUP_OBJS) FORCE +$(obj)/wakeup.elf: $(obj)/wakeup.lds $(WAKEUP_OBJS) FORCE $(call if_changed,ld) OBJCOPYFLAGS_wakeup.bin := -O binary diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ddee04043ae..4bc1be5d547 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -133,6 +133,7 @@ static int kvm_register_clock(void) return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high); } +#ifdef CONFIG_X86_LOCAL_APIC static void kvm_setup_secondary_clock(void) { /* @@ -143,6 +144,7 @@ static void kvm_setup_secondary_clock(void) /* ok, done with our trickery, call native */ setup_secondary_APIC_clock(); } +#endif /* * After the clock is registered, the host will keep writing to the @@ -177,7 +179,9 @@ void __init kvmclock_init(void) pv_time_ops.get_wallclock = kvm_get_wallclock; pv_time_ops.set_wallclock = kvm_set_wallclock; pv_time_ops.sched_clock = kvm_clock_read; +#ifdef CONFIG_X86_LOCAL_APIC pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock; +#endif machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 3e2c54dc8b2..404683b94e7 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -794,6 +794,11 @@ void __init find_smp_config(void) ACPI-based MP Configuration -------------------------------------------------------------------------- */ +/* + * Keep this outside and initialized to 0, for !CONFIG_ACPI builds: + */ +int es7000_plat; + #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC @@ -909,8 +914,6 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) MP_intsrc_info(&intsrc); } -int es7000_plat; - void __init mp_config_acpi_legacy_irqs(void) { struct mpc_config_intsrc intsrc; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 07c6d42ab5f..f6be7d5f82f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -149,7 +149,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), - DMI_MATCH(DMI_BOARD_NAME, "0WF810"), }, }, { /* Handle problems with rebooting on Dell Optiplex 745's DFF*/ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c0c68c18a78..cc6f5eb20b2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -95,7 +95,7 @@ void __init setup_per_cpu_areas(void) /* Copy section for each CPU (we discard the original) */ size = PERCPU_ENOUGH_ROOM; - printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n", + printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n", size); for_each_possible_cpu(i) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 84241a256dc..6b087ab6cd8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -299,7 +299,7 @@ static void __cpuinit smp_callin(void) /* * Activate a secondary processor. */ -void __cpuinit start_secondary(void *unused) +static void __cpuinit start_secondary(void *unused) { /* * Don't put *anything* before cpu_init(), SMP booting is too @@ -1306,7 +1306,7 @@ static void remove_siblinginfo(int cpu) cpu_clear(cpu, cpu_sibling_setup_map); } -int additional_cpus __initdata = -1; +static int additional_cpus __initdata = -1; static __init int setup_additional_cpus(char *s) { diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index a86d26f036e..d2ab52cc1d6 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -22,23 +22,6 @@ #include <asm/uaccess.h> #include <asm/unistd.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way Unix traditionally does this, though. - */ -asmlinkage int sys_pipe(unsigned long __user * fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index bd802a5e1aa..3b360ef3381 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -17,23 +17,6 @@ #include <asm/uaccess.h> #include <asm/ia32.h> -/* - * sys_pipe() is the normal C calling standard for creating - * a pipe. It's not the way Unix traditionally does this, though. - */ -asmlinkage long sys_pipe(int __user *fildes) -{ - int fd[2]; - int error; - - error = do_pipe(fd); - if (!error) { - if (copy_to_user(fildes, fd, 2*sizeof(int))) - error = -EFAULT; - } - return error; -} - asmlinkage long sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long off) { diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 361e3161127..3324d90038e 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -35,7 +35,7 @@ #include "i8254.h" #ifndef CONFIG_X86_64 -#define mod_64(x, y) ((x) - (y) * div64_64(x, y)) +#define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) #else #define mod_64(x, y) ((x) % (y)) #endif @@ -60,8 +60,8 @@ static u64 muldiv64(u64 a, u32 b, u32 c) rl = (u64)u.l.low * (u64)b; rh = (u64)u.l.high * (u64)b; rh += (rl >> 32); - res.l.high = div64_64(rh, c); - res.l.low = div64_64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c); + res.l.high = div64_u64(rh, c); + res.l.low = div64_u64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c); return res.ll; } @@ -288,6 +288,8 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) * mode 1 is one shot, mode 2 is period, otherwise del timer */ switch (ps->channels[0].mode) { case 1: + /* FIXME: enhance mode 4 precision */ + case 4: create_pit_timer(&ps->pit_timer, val, 0); break; case 2: diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 57ac4e4c556..36809d79788 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -25,13 +25,13 @@ #include <linux/hrtimer.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/math64.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/page.h> #include <asm/current.h> #include <asm/apicdef.h> #include <asm/atomic.h> -#include <asm/div64.h> #include "irq.h" #define PRId64 "d" @@ -526,8 +526,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) } else passed = ktime_sub(now, apic->timer.last_update); - counter_passed = div64_64(ktime_to_ns(passed), - (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); + counter_passed = div64_u64(ktime_to_ns(passed), + (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); if (counter_passed > tmcct) { if (unlikely(!apic_lvtt_period(apic))) { diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2ad6f548167..36c5406b181 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -79,36 +79,6 @@ static int dbg = 1; } #endif -#define PT64_PT_BITS 9 -#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS) -#define PT32_PT_BITS 10 -#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS) - -#define PT_WRITABLE_SHIFT 1 - -#define PT_PRESENT_MASK (1ULL << 0) -#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT) -#define PT_USER_MASK (1ULL << 2) -#define PT_PWT_MASK (1ULL << 3) -#define PT_PCD_MASK (1ULL << 4) -#define PT_ACCESSED_MASK (1ULL << 5) -#define PT_DIRTY_MASK (1ULL << 6) -#define PT_PAGE_SIZE_MASK (1ULL << 7) -#define PT_PAT_MASK (1ULL << 7) -#define PT_GLOBAL_MASK (1ULL << 8) -#define PT64_NX_SHIFT 63 -#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT) - -#define PT_PAT_SHIFT 7 -#define PT_DIR_PAT_SHIFT 12 -#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT) - -#define PT32_DIR_PSE36_SIZE 4 -#define PT32_DIR_PSE36_SHIFT 13 -#define PT32_DIR_PSE36_MASK \ - (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT) - - #define PT_FIRST_AVAIL_BITS_SHIFT 9 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 @@ -154,10 +124,6 @@ static int dbg = 1; #define PFERR_USER_MASK (1U << 2) #define PFERR_FETCH_MASK (1U << 4) -#define PT64_ROOT_LEVEL 4 -#define PT32_ROOT_LEVEL 2 -#define PT32E_ROOT_LEVEL 3 - #define PT_DIRECTORY_LEVEL 2 #define PT_PAGE_TABLE_LEVEL 1 @@ -186,6 +152,12 @@ static struct kmem_cache *mmu_page_header_cache; static u64 __read_mostly shadow_trap_nonpresent_pte; static u64 __read_mostly shadow_notrap_nonpresent_pte; +static u64 __read_mostly shadow_base_present_pte; +static u64 __read_mostly shadow_nx_mask; +static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */ +static u64 __read_mostly shadow_user_mask; +static u64 __read_mostly shadow_accessed_mask; +static u64 __read_mostly shadow_dirty_mask; void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte) { @@ -194,6 +166,23 @@ void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte) } EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes); +void kvm_mmu_set_base_ptes(u64 base_pte) +{ + shadow_base_present_pte = base_pte; +} +EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes); + +void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, + u64 dirty_mask, u64 nx_mask, u64 x_mask) +{ + shadow_user_mask = user_mask; + shadow_accessed_mask = accessed_mask; + shadow_dirty_mask = dirty_mask; + shadow_nx_mask = nx_mask; + shadow_x_mask = x_mask; +} +EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); + static int is_write_protection(struct kvm_vcpu *vcpu) { return vcpu->arch.cr0 & X86_CR0_WP; @@ -232,7 +221,7 @@ static int is_writeble_pte(unsigned long pte) static int is_dirty_pte(unsigned long pte) { - return pte & PT_DIRTY_MASK; + return pte & shadow_dirty_mask; } static int is_rmap_pte(u64 pte) @@ -387,7 +376,6 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn) write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn)); *write_count += 1; - WARN_ON(*write_count > KVM_PAGES_PER_HPAGE); } static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) @@ -547,7 +535,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) return; sp = page_header(__pa(spte)); pfn = spte_to_pfn(*spte); - if (*spte & PT_ACCESSED_MASK) + if (*spte & shadow_accessed_mask) kvm_set_pfn_accessed(pfn); if (is_writeble_pte(*spte)) kvm_release_pfn_dirty(pfn); @@ -1073,17 +1061,17 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, * whether the guest actually used the pte (in order to detect * demand paging). */ - spte = PT_PRESENT_MASK | PT_DIRTY_MASK; + spte = shadow_base_present_pte | shadow_dirty_mask; if (!speculative) pte_access |= PT_ACCESSED_MASK; if (!dirty) pte_access &= ~ACC_WRITE_MASK; - if (!(pte_access & ACC_EXEC_MASK)) - spte |= PT64_NX_MASK; - - spte |= PT_PRESENT_MASK; + if (pte_access & ACC_EXEC_MASK) + spte |= shadow_x_mask; + else + spte |= shadow_nx_mask; if (pte_access & ACC_USER_MASK) - spte |= PT_USER_MASK; + spte |= shadow_user_mask; if (largepage) spte |= PT_PAGE_SIZE_MASK; @@ -1188,8 +1176,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, return -ENOMEM; } - table[index] = __pa(new_table->spt) | PT_PRESENT_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; + table[index] = __pa(new_table->spt) + | PT_PRESENT_MASK | PT_WRITABLE_MASK + | shadow_user_mask | shadow_x_mask; } table_addr = table[index] & PT64_BASE_ADDR_MASK; } @@ -1244,7 +1233,6 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; spin_lock(&vcpu->kvm->mmu_lock); -#ifdef CONFIG_X86_64 if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; @@ -1256,7 +1244,6 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) spin_unlock(&vcpu->kvm->mmu_lock); return; } -#endif for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -1282,7 +1269,6 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; -#ifdef CONFIG_X86_64 if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; @@ -1297,7 +1283,6 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) vcpu->arch.mmu.root_hpa = root; return; } -#endif metaphysical = !is_paging(vcpu); if (tdp_enabled) metaphysical = 1; @@ -1377,7 +1362,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK, - largepage, gfn, pfn, TDP_ROOT_LEVEL); + largepage, gfn, pfn, kvm_x86_ops->get_tdp_level()); spin_unlock(&vcpu->kvm->mmu_lock); return r; @@ -1484,7 +1469,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->page_fault = tdp_page_fault; context->free = nonpaging_free; context->prefetch_page = nonpaging_prefetch_page; - context->shadow_root_level = TDP_ROOT_LEVEL; + context->shadow_root_level = kvm_x86_ops->get_tdp_level(); context->root_hpa = INVALID_PAGE; if (!is_paging(vcpu)) { @@ -1633,7 +1618,7 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) { u64 *spte = vcpu->arch.last_pte_updated; - return !!(spte && (*spte & PT_ACCESSED_MASK)); + return !!(spte && (*spte & shadow_accessed_mask)); } static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e64e9f56a65..1730757bbc7 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -3,11 +3,38 @@ #include <linux/kvm_host.h> -#ifdef CONFIG_X86_64 -#define TDP_ROOT_LEVEL PT64_ROOT_LEVEL -#else -#define TDP_ROOT_LEVEL PT32E_ROOT_LEVEL -#endif +#define PT64_PT_BITS 9 +#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS) +#define PT32_PT_BITS 10 +#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS) + +#define PT_WRITABLE_SHIFT 1 + +#define PT_PRESENT_MASK (1ULL << 0) +#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT) +#define PT_USER_MASK (1ULL << 2) +#define PT_PWT_MASK (1ULL << 3) +#define PT_PCD_MASK (1ULL << 4) +#define PT_ACCESSED_MASK (1ULL << 5) +#define PT_DIRTY_MASK (1ULL << 6) +#define PT_PAGE_SIZE_MASK (1ULL << 7) +#define PT_PAT_MASK (1ULL << 7) +#define PT_GLOBAL_MASK (1ULL << 8) +#define PT64_NX_SHIFT 63 +#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT) + +#define PT_PAT_SHIFT 7 +#define PT_DIR_PAT_SHIFT 12 +#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT) + +#define PT32_DIR_PSE36_SIZE 4 +#define PT32_DIR_PSE36_SHIFT 13 +#define PT32_DIR_PSE36_MASK \ + (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT) + +#define PT64_ROOT_LEVEL 4 +#define PT32_ROOT_LEVEL 2 +#define PT32E_ROOT_LEVEL 3 static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 89e0be2c10d..ab22615eee8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1863,6 +1863,15 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } +static int get_npt_level(void) +{ +#ifdef CONFIG_X86_64 + return PT64_ROOT_LEVEL; +#else + return PT32E_ROOT_LEVEL; +#endif +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -1920,6 +1929,7 @@ static struct kvm_x86_ops svm_x86_ops = { .inject_pending_vectors = do_interrupt_requests, .set_tss_addr = svm_set_tss_addr, + .get_tdp_level = get_npt_level, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8e5d6645b90..bfe4db11989 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -42,6 +42,9 @@ module_param(enable_vpid, bool, 0); static int flexpriority_enabled = 1; module_param(flexpriority_enabled, bool, 0); +static int enable_ept = 1; +module_param(enable_ept, bool, 0); + struct vmcs { u32 revision_id; u32 abort; @@ -84,7 +87,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } -static int init_rmode_tss(struct kvm *kvm); +static int init_rmode(struct kvm *kvm); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -107,6 +110,11 @@ static struct vmcs_config { u32 vmentry_ctrl; } vmcs_config; +struct vmx_capability { + u32 ept; + u32 vpid; +} vmx_capability; + #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ .selector = GUEST_##seg##_SELECTOR, \ @@ -214,6 +222,32 @@ static inline bool cpu_has_vmx_virtualize_apic_accesses(void) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); } +static inline int cpu_has_vmx_invept_individual_addr(void) +{ + return (!!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT)); +} + +static inline int cpu_has_vmx_invept_context(void) +{ + return (!!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT)); +} + +static inline int cpu_has_vmx_invept_global(void) +{ + return (!!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT)); +} + +static inline int cpu_has_vmx_ept(void) +{ + return (vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_EPT); +} + +static inline int vm_need_ept(void) +{ + return (cpu_has_vmx_ept() && enable_ept); +} + static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) { return ((cpu_has_vmx_virtualize_apic_accesses()) && @@ -250,6 +284,18 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva) : : "a"(&operand), "c"(ext) : "cc", "memory"); } +static inline void __invept(int ext, u64 eptp, gpa_t gpa) +{ + struct { + u64 eptp, gpa; + } operand = {eptp, gpa}; + + asm volatile (ASM_VMX_INVEPT + /* CF==1 or ZF==1 --> rc = -1 */ + "; ja 1f ; ud2 ; 1:\n" + : : "a" (&operand), "c" (ext) : "cc", "memory"); +} + static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -301,6 +347,33 @@ static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx) __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); } +static inline void ept_sync_global(void) +{ + if (cpu_has_vmx_invept_global()) + __invept(VMX_EPT_EXTENT_GLOBAL, 0, 0); +} + +static inline void ept_sync_context(u64 eptp) +{ + if (vm_need_ept()) { + if (cpu_has_vmx_invept_context()) + __invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0); + else + ept_sync_global(); + } +} + +static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa) +{ + if (vm_need_ept()) { + if (cpu_has_vmx_invept_individual_addr()) + __invept(VMX_EPT_EXTENT_INDIVIDUAL_ADDR, + eptp, gpa); + else + ept_sync_context(eptp); + } +} + static unsigned long vmcs_readl(unsigned long field) { unsigned long value; @@ -388,6 +461,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb |= 1u << 1; if (vcpu->arch.rmode.active) eb = ~0; + if (vm_need_ept()) + eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -985,7 +1060,7 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) { u32 vmx_msr_low, vmx_msr_high; - u32 min, opt; + u32 min, opt, min2, opt2; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; @@ -1003,6 +1078,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif + CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MOV_DR_EXITING | CPU_BASED_USE_TSC_OFFSETING; @@ -1018,11 +1095,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) ~CPU_BASED_CR8_STORE_EXITING; #endif if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { - min = 0; - opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + min2 = 0; + opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_ENABLE_VPID; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2, + SECONDARY_EXEC_ENABLE_VPID | + SECONDARY_EXEC_ENABLE_EPT; + if (adjust_vmx_controls(min2, opt2, + MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) return -EIO; } @@ -1031,6 +1110,16 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; #endif + if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { + /* CR3 accesses don't need to cause VM Exits when EPT enabled */ + min &= ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING); + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, + &_cpu_based_exec_control) < 0) + return -EIO; + rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, + vmx_capability.ept, vmx_capability.vpid); + } min = 0; #ifdef CONFIG_X86_64 @@ -1256,7 +1345,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) fix_rmode_seg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); kvm_mmu_reset_context(vcpu); - init_rmode_tss(vcpu->kvm); + init_rmode(vcpu->kvm); } #ifdef CONFIG_X86_64 @@ -1304,8 +1393,64 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK; } +static void ept_load_pdptrs(struct kvm_vcpu *vcpu) +{ + if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + if (!load_pdptrs(vcpu, vcpu->arch.cr3)) { + printk(KERN_ERR "EPT: Fail to load pdptrs!\n"); + return; + } + vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]); + vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]); + vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]); + vmcs_write64(GUEST_PDPTR3, vcpu->arch.pdptrs[3]); + } +} + +static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); + +static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, + unsigned long cr0, + struct kvm_vcpu *vcpu) +{ + if (!(cr0 & X86_CR0_PG)) { + /* From paging/starting to nonpaging */ + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, + vmcs_config.cpu_based_exec_ctrl | + (CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING)); + vcpu->arch.cr0 = cr0; + vmx_set_cr4(vcpu, vcpu->arch.cr4); + *hw_cr0 |= X86_CR0_PE | X86_CR0_PG; + *hw_cr0 &= ~X86_CR0_WP; + } else if (!is_paging(vcpu)) { + /* From nonpaging to paging */ + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, + vmcs_config.cpu_based_exec_ctrl & + ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING)); + vcpu->arch.cr0 = cr0; + vmx_set_cr4(vcpu, vcpu->arch.cr4); + if (!(vcpu->arch.cr0 & X86_CR0_WP)) + *hw_cr0 &= ~X86_CR0_WP; + } +} + +static void ept_update_paging_mode_cr4(unsigned long *hw_cr4, + struct kvm_vcpu *vcpu) +{ + if (!is_paging(vcpu)) { + *hw_cr4 &= ~X86_CR4_PAE; + *hw_cr4 |= X86_CR4_PSE; + } else if (!(vcpu->arch.cr4 & X86_CR4_PAE)) + *hw_cr4 &= ~X86_CR4_PAE; +} + static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { + unsigned long hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | + KVM_VM_CR0_ALWAYS_ON; + vmx_fpu_deactivate(vcpu); if (vcpu->arch.rmode.active && (cr0 & X86_CR0_PE)) @@ -1323,29 +1468,61 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif + if (vm_need_ept()) + ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); + vmcs_writel(CR0_READ_SHADOW, cr0); - vmcs_writel(GUEST_CR0, - (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON); + vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE)) vmx_fpu_activate(vcpu); } +static u64 construct_eptp(unsigned long root_hpa) +{ + u64 eptp; + + /* TODO write the value reading from MSR */ + eptp = VMX_EPT_DEFAULT_MT | + VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; + eptp |= (root_hpa & PAGE_MASK); + + return eptp; +} + static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { + unsigned long guest_cr3; + u64 eptp; + + guest_cr3 = cr3; + if (vm_need_ept()) { + eptp = construct_eptp(cr3); + vmcs_write64(EPT_POINTER, eptp); + ept_sync_context(eptp); + ept_load_pdptrs(vcpu); + guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 : + VMX_EPT_IDENTITY_PAGETABLE_ADDR; + } + vmx_flush_tlb(vcpu); - vmcs_writel(GUEST_CR3, cr3); + vmcs_writel(GUEST_CR3, guest_cr3); if (vcpu->arch.cr0 & X86_CR0_PE) vmx_fpu_deactivate(vcpu); } static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - vmcs_writel(CR4_READ_SHADOW, cr4); - vmcs_writel(GUEST_CR4, cr4 | (vcpu->arch.rmode.active ? - KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON)); + unsigned long hw_cr4 = cr4 | (vcpu->arch.rmode.active ? + KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); + vcpu->arch.cr4 = cr4; + if (vm_need_ept()) + ept_update_paging_mode_cr4(&hw_cr4, vcpu); + + vmcs_writel(CR4_READ_SHADOW, cr4); + vmcs_writel(GUEST_CR4, hw_cr4); } static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -1530,6 +1707,41 @@ out: return ret; } +static int init_rmode_identity_map(struct kvm *kvm) +{ + int i, r, ret; + pfn_t identity_map_pfn; + u32 tmp; + + if (!vm_need_ept()) + return 1; + if (unlikely(!kvm->arch.ept_identity_pagetable)) { + printk(KERN_ERR "EPT: identity-mapping pagetable " + "haven't been allocated!\n"); + return 0; + } + if (likely(kvm->arch.ept_identity_pagetable_done)) + return 1; + ret = 0; + identity_map_pfn = VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT; + r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); + if (r < 0) + goto out; + /* Set up identity-mapping pagetable for EPT in real mode */ + for (i = 0; i < PT32_ENT_PER_PAGE; i++) { + tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | + _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); + r = kvm_write_guest_page(kvm, identity_map_pfn, + &tmp, i * sizeof(tmp), sizeof(tmp)); + if (r < 0) + goto out; + } + kvm->arch.ept_identity_pagetable_done = true; + ret = 1; +out: + return ret; +} + static void seg_setup(int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -1564,6 +1776,31 @@ out: return r; } +static int alloc_identity_pagetable(struct kvm *kvm) +{ + struct kvm_userspace_memory_region kvm_userspace_mem; + int r = 0; + + down_write(&kvm->slots_lock); + if (kvm->arch.ept_identity_pagetable) + goto out; + kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; + kvm_userspace_mem.flags = 0; + kvm_userspace_mem.guest_phys_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; + kvm_userspace_mem.memory_size = PAGE_SIZE; + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); + if (r) + goto out; + + down_read(¤t->mm->mmap_sem); + kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, + VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); +out: + up_write(&kvm->slots_lock); + return r; +} + static void allocate_vpid(struct vcpu_vmx *vmx) { int vpid; @@ -1638,6 +1875,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) CPU_BASED_CR8_LOAD_EXITING; #endif } + if (!vm_need_ept()) + exec_control |= CPU_BASED_CR3_STORE_EXITING | + CPU_BASED_CR3_LOAD_EXITING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control); if (cpu_has_secondary_exec_ctrls()) { @@ -1647,6 +1887,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; + if (!vm_need_ept()) + exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } @@ -1722,6 +1964,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } +static int init_rmode(struct kvm *kvm) +{ + if (!init_rmode_tss(kvm)) + return 0; + if (!init_rmode_identity_map(kvm)) + return 0; + return 1; +} + static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1729,7 +1980,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) int ret; down_read(&vcpu->kvm->slots_lock); - if (!init_rmode_tss(vmx->vcpu.kvm)) { + if (!init_rmode(vmx->vcpu.kvm)) { ret = -ENOMEM; goto out; } @@ -1994,6 +2245,9 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { + /* EPT won't cause page fault directly */ + if (vm_need_ept()) + BUG(); cr2 = vmcs_readl(EXIT_QUALIFICATION); KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2, (u32)((u64)cr2 >> 32), handler); @@ -2323,6 +2577,64 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return kvm_task_switch(vcpu, tss_selector, reason); } +static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + u64 exit_qualification; + enum emulation_result er; + gpa_t gpa; + unsigned long hva; + int gla_validity; + int r; + + exit_qualification = vmcs_read64(EXIT_QUALIFICATION); + + if (exit_qualification & (1 << 6)) { + printk(KERN_ERR "EPT: GPA exceeds GAW!\n"); + return -ENOTSUPP; + } + + gla_validity = (exit_qualification >> 7) & 0x3; + if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) { + printk(KERN_ERR "EPT: Handling EPT violation failed!\n"); + printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", + (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), + (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS)); + printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", + (long unsigned int)exit_qualification); + kvm_run->exit_reason = KVM_EXIT_UNKNOWN; + kvm_run->hw.hardware_exit_reason = 0; + return -ENOTSUPP; + } + + gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT); + if (!kvm_is_error_hva(hva)) { + r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); + if (r < 0) { + printk(KERN_ERR "EPT: Not enough memory!\n"); + return -ENOMEM; + } + return 1; + } else { + /* must be MMIO */ + er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + + if (er == EMULATE_FAIL) { + printk(KERN_ERR + "EPT: Fail to handle EPT violation vmexit!er is %d\n", + er); + printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", + (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), + (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS)); + printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", + (long unsigned int)exit_qualification); + return -ENOTSUPP; + } else if (er == EMULATE_DO_MMIO) + return 0; + } + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -2346,6 +2658,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_WBINVD] = handle_wbinvd, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, + [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, }; static const int kvm_vmx_max_exit_handlers = @@ -2364,6 +2677,13 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)vmcs_readl(GUEST_RIP), (u32)((u64)vmcs_readl(GUEST_RIP) >> 32), entryexit); + /* Access CR3 don't cause VMExit in paging mode, so we need + * to sync with guest real CR3. */ + if (vm_need_ept() && is_paging(vcpu)) { + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + ept_load_pdptrs(vcpu); + } + if (unlikely(vmx->fail)) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason @@ -2372,7 +2692,8 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) } if ((vectoring_info & VECTORING_INFO_VALID_MASK) && - exit_reason != EXIT_REASON_EXCEPTION_NMI) + (exit_reason != EXIT_REASON_EXCEPTION_NMI && + exit_reason != EXIT_REASON_EPT_VIOLATION)) printk(KERN_WARNING "%s: unexpected, valid vectoring info and " "exit reason is 0x%x\n", __func__, exit_reason); if (exit_reason < kvm_vmx_max_exit_handlers @@ -2674,6 +2995,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return ERR_PTR(-ENOMEM); allocate_vpid(vmx); + if (id == 0 && vm_need_ept()) { + kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | + VMX_EPT_WRITABLE_MASK | + VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); + kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK, + VMX_EPT_FAKE_DIRTY_MASK, 0ull, + VMX_EPT_EXECUTABLE_MASK); + kvm_enable_tdp(); + } err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) @@ -2706,6 +3036,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (alloc_apic_access_page(kvm) != 0) goto free_vmcs; + if (vm_need_ept()) + if (alloc_identity_pagetable(kvm) != 0) + goto free_vmcs; + return &vmx->vcpu; free_vmcs: @@ -2735,6 +3069,11 @@ static void __init vmx_check_processor_compat(void *rtn) } } +static int get_ept_level(void) +{ + return VMX_EPT_DEFAULT_GAW + 1; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -2791,6 +3130,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .inject_pending_vectors = do_interrupt_requests, .set_tss_addr = vmx_set_tss_addr, + .get_tdp_level = get_ept_level, }; static int __init vmx_init(void) @@ -2843,9 +3183,14 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP); + if (cpu_has_vmx_ept()) + bypass_guest_pf = 0; + if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); + ept_sync_global(); + return 0; out2: diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h index 5dff4606b98..79d94c610df 100644 --- a/arch/x86/kvm/vmx.h +++ b/arch/x86/kvm/vmx.h @@ -35,6 +35,8 @@ #define CPU_BASED_MWAIT_EXITING 0x00000400 #define CPU_BASED_RDPMC_EXITING 0x00000800 #define CPU_BASED_RDTSC_EXITING 0x00001000 +#define CPU_BASED_CR3_LOAD_EXITING 0x00008000 +#define CPU_BASED_CR3_STORE_EXITING 0x00010000 #define CPU_BASED_CR8_LOAD_EXITING 0x00080000 #define CPU_BASED_CR8_STORE_EXITING 0x00100000 #define CPU_BASED_TPR_SHADOW 0x00200000 @@ -49,6 +51,7 @@ * Definitions of Secondary Processor-Based VM-Execution Controls. */ #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001 +#define SECONDARY_EXEC_ENABLE_EPT 0x00000002 #define SECONDARY_EXEC_ENABLE_VPID 0x00000020 #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 @@ -100,10 +103,22 @@ enum vmcs_field { VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013, APIC_ACCESS_ADDR = 0x00002014, APIC_ACCESS_ADDR_HIGH = 0x00002015, + EPT_POINTER = 0x0000201a, + EPT_POINTER_HIGH = 0x0000201b, + GUEST_PHYSICAL_ADDRESS = 0x00002400, + GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401, VMCS_LINK_POINTER = 0x00002800, VMCS_LINK_POINTER_HIGH = 0x00002801, GUEST_IA32_DEBUGCTL = 0x00002802, GUEST_IA32_DEBUGCTL_HIGH = 0x00002803, + GUEST_PDPTR0 = 0x0000280a, + GUEST_PDPTR0_HIGH = 0x0000280b, + GUEST_PDPTR1 = 0x0000280c, + GUEST_PDPTR1_HIGH = 0x0000280d, + GUEST_PDPTR2 = 0x0000280e, + GUEST_PDPTR2_HIGH = 0x0000280f, + GUEST_PDPTR3 = 0x00002810, + GUEST_PDPTR3_HIGH = 0x00002811, PIN_BASED_VM_EXEC_CONTROL = 0x00004000, CPU_BASED_VM_EXEC_CONTROL = 0x00004002, EXCEPTION_BITMAP = 0x00004004, @@ -226,6 +241,8 @@ enum vmcs_field { #define EXIT_REASON_MWAIT_INSTRUCTION 36 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 +#define EXIT_REASON_EPT_VIOLATION 48 +#define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_WBINVD 54 /* @@ -316,15 +333,36 @@ enum vmcs_field { #define MSR_IA32_VMX_CR4_FIXED1 0x489 #define MSR_IA32_VMX_VMCS_ENUM 0x48a #define MSR_IA32_VMX_PROCBASED_CTLS2 0x48b +#define MSR_IA32_VMX_EPT_VPID_CAP 0x48c #define MSR_IA32_FEATURE_CONTROL 0x3a #define MSR_IA32_FEATURE_CONTROL_LOCKED 0x1 #define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED 0x4 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT 9 +#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT 10 #define VMX_NR_VPIDS (1 << 16) #define VMX_VPID_EXTENT_SINGLE_CONTEXT 1 #define VMX_VPID_EXTENT_ALL_CONTEXT 2 +#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR 0 +#define VMX_EPT_EXTENT_CONTEXT 1 +#define VMX_EPT_EXTENT_GLOBAL 2 +#define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24) +#define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) +#define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) +#define VMX_EPT_DEFAULT_GAW 3 +#define VMX_EPT_MAX_GAW 0x4 +#define VMX_EPT_MT_EPTE_SHIFT 3 +#define VMX_EPT_GAW_EPTP_SHIFT 3 +#define VMX_EPT_DEFAULT_MT 0x6ull +#define VMX_EPT_READABLE_MASK 0x1ull +#define VMX_EPT_WRITABLE_MASK 0x2ull +#define VMX_EPT_EXECUTABLE_MASK 0x4ull +#define VMX_EPT_FAKE_ACCESSED_MASK (1ull << 62) +#define VMX_EPT_FAKE_DIRTY_MASK (1ull << 63) + +#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul + #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ce556372a4..21338bdb28f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2417,6 +2417,9 @@ int kvm_arch_init(void *opaque) kvm_x86_ops = ops; kvm_mmu_set_nonpresent_ptes(0ull, 0ull); + kvm_mmu_set_base_ptes(PT_PRESENT_MASK); + kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, + PT_DIRTY_MASK, PT64_NX_MASK, 0); return 0; out: @@ -3019,6 +3022,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_x86_ops->decache_regs(vcpu); + vcpu->arch.exception.pending = false; + vcpu_put(vcpu); return 0; @@ -3481,7 +3486,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { - cseg_desc.type &= ~(1 << 8); //clear the B flag + cseg_desc.type &= ~(1 << 1); //clear the B flag save_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc); } @@ -3507,7 +3512,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } if (reason != TASK_SWITCH_IRET) { - nseg_desc.type |= (1 << 8); + nseg_desc.type |= (1 << 1); save_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc); } @@ -3698,10 +3703,19 @@ void fx_init(struct kvm_vcpu *vcpu) { unsigned after_mxcsr_mask; + /* + * Touch the fpu the first time in non atomic context as if + * this is the first fpu instruction the exception handler + * will fire before the instruction returns and it'll have to + * allocate ram with GFP_KERNEL. + */ + if (!used_math()) + fx_save(&vcpu->arch.host_fx_image); + /* Initialize guest FPU by resetting ours and saving into guest's */ preempt_disable(); fx_save(&vcpu->arch.host_fx_image); - fpu_init(); + fx_finit(); fx_save(&vcpu->arch.guest_fx_image); fx_restore(&vcpu->arch.host_fx_image); preempt_enable(); @@ -3906,6 +3920,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_free_physmem(kvm); if (kvm->arch.apic_access_page) put_page(kvm->arch.apic_access_page); + if (kvm->arch.ept_identity_pagetable) + put_page(kvm->arch.ept_identity_pagetable); kfree(kvm); } diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index 2ca08386f99..f2a696d6a24 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -1761,6 +1761,7 @@ twobyte_insn: case 6: /* lmsw */ realmode_lmsw(ctxt->vcpu, (u16)c->src.val, &ctxt->eflags); + c->dst.type = OP_NONE; break; case 7: /* invlpg*/ emulate_invlpg(ctxt->vcpu, memop); diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 18378850e25..914ccf98368 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -476,29 +476,3 @@ int memory_add_physaddr_to_nid(u64 addr) EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif - -#ifndef CONFIG_HAVE_ARCH_PARSE_SRAT -/* - * XXX FIXME: Make SLIT table parsing available to 32-bit NUMA - * - * These stub functions are needed to compile 32-bit NUMA when SRAT is - * not set. There are functions in srat_64.c for parsing this table - * and it may be possible to make them common functions. - */ -void acpi_numa_slit_init (struct acpi_table_slit *slit) -{ - printk(KERN_INFO "ACPI: No support for parsing SLIT table\n"); -} - -void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa) -{ -} - -void acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma) -{ -} - -void acpi_numa_arch_fixup(void) -{ -} -#endif /* CONFIG_HAVE_ARCH_PARSE_SRAT */ diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 9ee007be914..369cf065b6a 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -172,10 +172,3 @@ void reserve_top_address(unsigned long reserve) __FIXADDR_TOP = -reserve - PAGE_SIZE; __VMALLOC_RESERVE += reserve; } - -int pmd_bad(pmd_t pmd) -{ - WARN_ON_ONCE(pmd_bad_v1(pmd) != pmd_bad_v2(pmd)); - - return pmd_bad_v1(pmd); -} diff --git a/arch/x86/pci/Makefile_32 b/arch/x86/pci/Makefile_32 index 7fa519868d7..89ec35d00ef 100644 --- a/arch/x86/pci/Makefile_32 +++ b/arch/x86/pci/Makefile_32 @@ -6,11 +6,19 @@ obj-$(CONFIG_PCI_DIRECT) += direct.o obj-$(CONFIG_PCI_OLPC) += olpc.o pci-y := fixup.o + +# Do not change the ordering here. There is a nasty init function +# ordering dependency which breaks when you move acpi.o below +# legacy/irq.o pci-$(CONFIG_ACPI) += acpi.o pci-y += legacy.o irq.o -pci-$(CONFIG_X86_VISWS) += visws.o fixup.o -pci-$(CONFIG_X86_NUMAQ) += numa.o irq.o +# Careful: VISWS and NUMAQ overrule the pci-y above. The colons are +# therefor correct. This needs a proper fix by distangling the code. +pci-$(CONFIG_X86_VISWS) := visws.o fixup.o +pci-$(CONFIG_X86_NUMAQ) := numa.o irq.o + +# Necessary for NUMAQ as well pci-$(CONFIG_NUMA) += mp_bus_to_node.o obj-y += $(pci-y) common.o early.o diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 1a9c0c6a1a1..d95de2f199c 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -6,45 +6,6 @@ #include <asm/numa.h> #include "pci.h" -static int __devinit can_skip_ioresource_align(const struct dmi_system_id *d) -{ - pci_probe |= PCI_CAN_SKIP_ISA_ALIGN; - printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident); - return 0; -} - -static struct dmi_system_id acpi_pciprobe_dmi_table[] __devinitdata = { -/* - * Systems where PCI IO resource ISA alignment can be skipped - * when the ISA enable bit in the bridge control is not set - */ - { - .callback = can_skip_ioresource_align, - .ident = "IBM System x3800", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "x3800"), - }, - }, - { - .callback = can_skip_ioresource_align, - .ident = "IBM System x3850", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "x3850"), - }, - }, - { - .callback = can_skip_ioresource_align, - .ident = "IBM System x3950", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "x3950"), - }, - }, - {} -}; - struct pci_root_info { char *name; unsigned int res_num; @@ -196,8 +157,6 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do int pxm; #endif - dmi_check_system(acpi_pciprobe_dmi_table); - if (domain && !pci_domains_supported) { printk(KERN_WARNING "PCI: Multiple domains not supported " "(dom %d, bus %d)\n", domain, busnum); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2a4d751818b..8545c8a9d10 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -77,17 +77,48 @@ int pcibios_scanned; */ DEFINE_SPINLOCK(pci_config_lock); -static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) +static int __devinit can_skip_ioresource_align(const struct dmi_system_id *d) { - struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE]; - - if (rom_r->parent) - return; - if (rom_r->start) - /* we deal with BIOS assigned ROM later */ - return; - if (!(pci_probe & PCI_ASSIGN_ROMS)) - rom_r->start = rom_r->end = rom_r->flags = 0; + pci_probe |= PCI_CAN_SKIP_ISA_ALIGN; + printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident); + return 0; +} + +static struct dmi_system_id can_skip_pciprobe_dmi_table[] __devinitdata = { +/* + * Systems where PCI IO resource ISA alignment can be skipped + * when the ISA enable bit in the bridge control is not set + */ + { + .callback = can_skip_ioresource_align, + .ident = "IBM System x3800", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "x3800"), + }, + }, + { + .callback = can_skip_ioresource_align, + .ident = "IBM System x3850", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "x3850"), + }, + }, + { + .callback = can_skip_ioresource_align, + .ident = "IBM System x3950", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "x3950"), + }, + }, + {} +}; + +void __init dmi_check_skip_isa_align(void) +{ + dmi_check_system(can_skip_pciprobe_dmi_table); } /* @@ -97,11 +128,7 @@ static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) void __devinit pcibios_fixup_bus(struct pci_bus *b) { - struct pci_dev *dev; - pci_read_bridge_bases(b); - list_for_each_entry(dev, &b->devices, bus_list) - pcibios_fixup_device_resources(dev); } /* @@ -318,13 +345,16 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = { {} }; +void __init dmi_check_pciprobe(void) +{ + dmi_check_system(pciprobe_dmi_table); +} + struct pci_bus * __devinit pcibios_scan_root(int busnum) { struct pci_bus *bus = NULL; struct pci_sysdata *sd; - dmi_check_system(pciprobe_dmi_table); - while ((bus = pci_find_next_bus(bus)) != NULL) { if (bus->number == busnum) { /* Already scanned */ @@ -462,6 +492,9 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "routeirq")) { pci_routeirq = 1; return NULL; + } else if (!strcmp(str, "skip_isa_align")) { + pci_probe |= PCI_CAN_SKIP_ISA_ALIGN; + return NULL; } return str; } @@ -489,7 +522,7 @@ void pcibios_disable_device (struct pci_dev *dev) pcibios_disable_irq(dev); } -struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) +struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) { struct pci_bus *bus = NULL; struct pci_sysdata *sd; @@ -512,7 +545,7 @@ struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) return bus; } -struct pci_bus *pci_scan_bus_with_sysdata(int busno) +struct pci_bus * __devinit pci_scan_bus_with_sysdata(int busno) { return pci_scan_bus_on_node(busno, &pci_root_ops, -1); } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index b60b2abd480..ff3a6a33634 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -502,7 +502,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015, */ static void fam10h_pci_cfg_space_size(struct pci_dev *dev) { - dev->cfg_size = pci_cfg_space_size_ext(dev, 0); + dev->cfg_size = pci_cfg_space_size_ext(dev); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, fam10h_pci_cfg_space_size); diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index dd30c6076b5..e70b9c57b88 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -33,6 +33,10 @@ static __init int pci_access_init(void) printk(KERN_ERR "PCI: Fatal: No config space access function found\n"); + dmi_check_pciprobe(); + + dmi_check_skip_isa_align(); + return 0; } arch_initcall(pci_access_init); diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h index c58805a92db..f3972b12c60 100644 --- a/arch/x86/pci/pci.h +++ b/arch/x86/pci/pci.h @@ -38,6 +38,9 @@ enum pci_bf_sort_state { pci_dmi_bf, }; +extern void __init dmi_check_pciprobe(void); +extern void __init dmi_check_skip_isa_align(void); + /* pci-i386.c */ extern unsigned int pcibios_max_latency; diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 4dceeb1fc5e..cf058fecfce 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -162,7 +162,7 @@ static __init void relocate_vdso(Elf32_Ehdr *ehdr) Elf32_Shdr *shdr; int i; - BUG_ON(memcmp(ehdr->e_ident, ELFMAG, 4) != 0 || + BUG_ON(memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0 || !elf_check_arch_ia32(ehdr) || ehdr->e_type != ET_DYN); diff --git a/arch/x86/video/fbdev.c b/arch/x86/video/fbdev.c index 4db42bff8c6..69527688f79 100644 --- a/arch/x86/video/fbdev.c +++ b/arch/x86/video/fbdev.c @@ -1,5 +1,4 @@ /* - * * Copyright (C) 2007 Antonino Daplas <adaplas@gmail.com> * * This file is subject to the terms and conditions of the GNU General Public @@ -29,3 +28,4 @@ int fb_is_primary_device(struct fb_info *info) return retval; } EXPORT_SYMBOL(fb_is_primary_device); +MODULE_LICENSE("GPL"); |