diff options
Diffstat (limited to 'arch/um/kernel')
38 files changed, 528 insertions, 642 deletions
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index e36f92b463ce..87a4e4427d8d 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -97,6 +97,8 @@ SECTIONS .data : { . = ALIGN(KERNEL_STACK_SIZE); /* init_task */ *(.data.init_task) + . = ALIGN(KERNEL_STACK_SIZE); + *(.data.init_irqstack) *(.data .data.* .gnu.linkonce.d.*) SORT(CONSTRUCTORS) } diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 121166400e25..356e50f5aaed 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -10,8 +10,8 @@ #include "asm/pgtable.h" #include "asm/tlbflush.h" #include "asm/uaccess.h" -#include "user_util.h" #include "kern_util.h" +#include "as-layout.h" #include "mem_user.h" #include "kern.h" #include "irq_user.h" diff --git a/arch/um/kernel/init_task.c b/arch/um/kernel/init_task.c index 8cde431348cc..d4f1d1ab252b 100644 --- a/arch/um/kernel/init_task.c +++ b/arch/um/kernel/init_task.c @@ -1,5 +1,5 @@ -/* - * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) +/* + * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,intel.linux}.com) * Licensed under the GPL */ @@ -10,7 +10,6 @@ #include "linux/mqueue.h" #include "asm/uaccess.h" #include "asm/pgtable.h" -#include "user_util.h" #include "mem_user.h" #include "os.h" @@ -34,28 +33,20 @@ EXPORT_SYMBOL(init_task); /* * Initial thread structure. * - * We need to make sure that this is 16384-byte aligned due to the + * We need to make sure that this is aligned due to the * way process stacks are handled. This is done by having a special * "init_task" linker map entry.. */ -union thread_union init_thread_union -__attribute__((__section__(".data.init_task"))) = -{ INIT_THREAD_INFO(init_task) }; +union thread_union init_thread_union + __attribute__((__section__(".data.init_task"))) = + { INIT_THREAD_INFO(init_task) }; + +union thread_union cpu0_irqstack + __attribute__((__section__(".data.init_irqstack"))) = + { INIT_THREAD_INFO(init_task) }; void unprotect_stack(unsigned long stack) { - os_protect_memory((void *) stack, (1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE, - 1, 1, 0); + os_protect_memory((void *) stack, THREAD_SIZE, 1, 1, 0); } - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c index 82ecf904b09c..16dc43e9d940 100644 --- a/arch/um/kernel/initrd.c +++ b/arch/um/kernel/initrd.c @@ -7,7 +7,6 @@ #include "linux/bootmem.h" #include "linux/initrd.h" #include "asm/types.h" -#include "user_util.h" #include "kern_util.h" #include "initrd.h" #include "init.h" @@ -22,12 +21,20 @@ static int __init read_initrd(void) long long size; int err; - if(initrd == NULL) return 0; + if(initrd == NULL) + return 0; + err = os_file_size(initrd, &size); - if(err) return 0; + if(err) + return 0; + area = alloc_bootmem(size); - if(area == NULL) return 0; - if(load_initrd(initrd, area, size) == -1) return 0; + if(area == NULL) + return 0; + + if(load_initrd(initrd, area, size) == -1) + return 0; + initrd_start = (unsigned long) area; initrd_end = initrd_start + size; return 0; @@ -54,25 +61,15 @@ int load_initrd(char *filename, void *buf, int size) fd = os_open_file(filename, of_read(OPENFLAGS()), 0); if(fd < 0){ printk("Opening '%s' failed - err = %d\n", filename, -fd); - return(-1); + return -1; } n = os_read_file(fd, buf, size); if(n != size){ printk("Read of %d bytes from '%s' failed, err = %d\n", size, filename, -n); - return(-1); + return -1; } os_close_file(fd); - return(0); + return 0; } -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index dbf2f5bc842f..dba04d88b432 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) * Licensed under the GPL * Derived (i.e. mostly copied) from arch/i386/kernel/irq.c: @@ -25,7 +25,6 @@ #include "asm/system.h" #include "asm/errno.h" #include "asm/uaccess.h" -#include "user_util.h" #include "kern_util.h" #include "irq_user.h" #include "irq_kern.h" @@ -33,6 +32,7 @@ #include "sigio.h" #include "um_malloc.h" #include "misc_constants.h" +#include "as-layout.h" /* * Generic, controller-independent functions: @@ -54,7 +54,7 @@ int show_interrupts(struct seq_file *p, void *v) if (i < NR_IRQS) { spin_lock_irqsave(&irq_desc[i].lock, flags); action = irq_desc[i].action; - if (!action) + if (!action) goto skip; seq_printf(p, "%3d: ",i); #ifndef CONFIG_SMP @@ -79,6 +79,14 @@ skip: return 0; } +/* + * This list is accessed under irq_lock, except in sigio_handler, + * where it is safe from being modified. IRQ handlers won't change it - + * if an IRQ source has vanished, it will be freed by free_irqs just + * before returning from sigio_handler. That will process a separate + * list of irqs to free, with its own locking, coming back here to + * remove list elements, taking the irq_lock to do so. + */ static struct irq_fd *active_fds = NULL; static struct irq_fd **last_irq_ptr = &active_fds; @@ -244,6 +252,7 @@ void free_irq_by_fd(int fd) free_irq_by_cb(same_fd, &fd); } +/* Must be called with irq_lock held */ static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) { struct irq_fd *irq; @@ -309,6 +318,12 @@ void deactivate_fd(int fd, int irqnum) ignore_sigio_fd(fd); } +/* + * Called just before shutdown in order to provide a clean exec + * environment in case the system is rebooting. No locking because + * that would cause a pointless shutdown hang if something hadn't + * released the lock. + */ int deactivate_all_fds(void) { struct irq_fd *irq; @@ -454,3 +469,113 @@ int init_aio_irq(int irq, char *name, irq_handler_t handler) out: return err; } + +/* + * IRQ stack entry and exit: + * + * Unlike i386, UML doesn't receive IRQs on the normal kernel stack + * and switch over to the IRQ stack after some preparation. We use + * sigaltstack to receive signals on a separate stack from the start. + * These two functions make sure the rest of the kernel won't be too + * upset by being on a different stack. The IRQ stack has a + * thread_info structure at the bottom so that current et al continue + * to work. + * + * to_irq_stack copies the current task's thread_info to the IRQ stack + * thread_info and sets the tasks's stack to point to the IRQ stack. + * + * from_irq_stack copies the thread_info struct back (flags may have + * been modified) and resets the task's stack pointer. + * + * Tricky bits - + * + * What happens when two signals race each other? UML doesn't block + * signals with sigprocmask, SA_DEFER, or sa_mask, so a second signal + * could arrive while a previous one is still setting up the + * thread_info. + * + * There are three cases - + * The first interrupt on the stack - sets up the thread_info and + * handles the interrupt + * A nested interrupt interrupting the copying of the thread_info - + * can't handle the interrupt, as the stack is in an unknown state + * A nested interrupt not interrupting the copying of the + * thread_info - doesn't do any setup, just handles the interrupt + * + * The first job is to figure out whether we interrupted stack setup. + * This is done by xchging the signal mask with thread_info->pending. + * If the value that comes back is zero, then there is no setup in + * progress, and the interrupt can be handled. If the value is + * non-zero, then there is stack setup in progress. In order to have + * the interrupt handled, we leave our signal in the mask, and it will + * be handled by the upper handler after it has set up the stack. + * + * Next is to figure out whether we are the outer handler or a nested + * one. As part of setting up the stack, thread_info->real_thread is + * set to non-NULL (and is reset to NULL on exit). This is the + * nesting indicator. If it is non-NULL, then the stack is already + * set up and the handler can run. + */ + +static unsigned long pending_mask; + +unsigned long to_irq_stack(int sig, unsigned long *mask_out) +{ + struct thread_info *ti; + unsigned long mask, old; + int nested; + + mask = xchg(&pending_mask, 1 << sig); + if(mask != 0){ + /* If any interrupts come in at this point, we want to + * make sure that their bits aren't lost by our + * putting our bit in. So, this loop accumulates bits + * until xchg returns the same value that we put in. + * When that happens, there were no new interrupts, + * and pending_mask contains a bit for each interrupt + * that came in. + */ + old = 1 << sig; + do { + old |= mask; + mask = xchg(&pending_mask, old); + } while(mask != old); + return 1; + } + + ti = current_thread_info(); + nested = (ti->real_thread != NULL); + if(!nested){ + struct task_struct *task; + struct thread_info *tti; + + task = cpu_tasks[ti->cpu].task; + tti = task_thread_info(task); + *ti = *tti; + ti->real_thread = tti; + task->stack = ti; + } + + mask = xchg(&pending_mask, 0); + *mask_out |= mask | nested; + return 0; +} + +unsigned long from_irq_stack(int nested) +{ + struct thread_info *ti, *to; + unsigned long mask; + + ti = current_thread_info(); + + pending_mask = 1; + + to = ti->real_thread; + current->stack = to; + ti->real_thread = NULL; + *to = *ti; + + mask = xchg(&pending_mask, 0); + return mask & ~1; +} + diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c index 0e00cf93f900..7b3e53fb8070 100644 --- a/arch/um/kernel/ksyms.c +++ b/arch/um/kernel/ksyms.c @@ -16,7 +16,7 @@ #include "asm/page.h" #include "asm/tlbflush.h" #include "kern_util.h" -#include "user_util.h" +#include "as-layout.h" #include "mem_user.h" #include "os.h" diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index df7d662b98ce..72ff85693a39 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -13,8 +13,8 @@ #include "asm/page.h" #include "asm/fixmap.h" #include "asm/pgalloc.h" -#include "user_util.h" #include "kern_util.h" +#include "as-layout.h" #include "kern.h" #include "mem_user.h" #include "uml_uaccess.h" @@ -216,7 +216,7 @@ static void __init fixaddr_user_init( void) #endif } -void paging_init(void) +void __init paging_init(void) { unsigned long zones_size[MAX_NR_ZONES], vaddr; int i; diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 638f3b5f6094..3ba6e4c841da 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -13,7 +13,7 @@ #include "asm/types.h" #include "asm/pgtable.h" #include "kern_util.h" -#include "user_util.h" +#include "as-layout.h" #include "mode_kern.h" #include "mem.h" #include "mem_user.h" @@ -21,229 +21,8 @@ #include "kern.h" #include "init.h" -struct phys_desc { - struct rb_node rb; - int fd; - __u64 offset; - void *virt; - unsigned long phys; - struct list_head list; -}; - -static struct rb_root phys_mappings = RB_ROOT; - -static struct rb_node **find_rb(void *virt) -{ - struct rb_node **n = &phys_mappings.rb_node; - struct phys_desc *d; - - while(*n != NULL){ - d = rb_entry(*n, struct phys_desc, rb); - if(d->virt == virt) - return n; - - if(d->virt > virt) - n = &(*n)->rb_left; - else - n = &(*n)->rb_right; - } - - return n; -} - -static struct phys_desc *find_phys_mapping(void *virt) -{ - struct rb_node **n = find_rb(virt); - - if(*n == NULL) - return NULL; - - return rb_entry(*n, struct phys_desc, rb); -} - -static void insert_phys_mapping(struct phys_desc *desc) -{ - struct rb_node **n = find_rb(desc->virt); - - if(*n != NULL) - panic("Physical remapping for %p already present", - desc->virt); - - rb_link_node(&desc->rb, rb_parent(*n), n); - rb_insert_color(&desc->rb, &phys_mappings); -} - -LIST_HEAD(descriptor_mappings); - -struct desc_mapping { - int fd; - struct list_head list; - struct list_head pages; -}; - -static struct desc_mapping *find_mapping(int fd) -{ - struct desc_mapping *desc; - struct list_head *ele; - - list_for_each(ele, &descriptor_mappings){ - desc = list_entry(ele, struct desc_mapping, list); - if(desc->fd == fd) - return desc; - } - - return NULL; -} - -static struct desc_mapping *descriptor_mapping(int fd) -{ - struct desc_mapping *desc; - - desc = find_mapping(fd); - if(desc != NULL) - return desc; - - desc = kmalloc(sizeof(*desc), GFP_ATOMIC); - if(desc == NULL) - return NULL; - - *desc = ((struct desc_mapping) - { .fd = fd, - .list = LIST_HEAD_INIT(desc->list), - .pages = LIST_HEAD_INIT(desc->pages) }); - list_add(&desc->list, &descriptor_mappings); - - return desc; -} - -int physmem_subst_mapping(void *virt, int fd, __u64 offset, int w) -{ - struct desc_mapping *fd_maps; - struct phys_desc *desc; - unsigned long phys; - int err; - - fd_maps = descriptor_mapping(fd); - if(fd_maps == NULL) - return -ENOMEM; - - phys = __pa(virt); - desc = find_phys_mapping(virt); - if(desc != NULL) - panic("Address 0x%p is already substituted\n", virt); - - err = -ENOMEM; - desc = kmalloc(sizeof(*desc), GFP_ATOMIC); - if(desc == NULL) - goto out; - - *desc = ((struct phys_desc) - { .fd = fd, - .offset = offset, - .virt = virt, - .phys = __pa(virt), - .list = LIST_HEAD_INIT(desc->list) }); - insert_phys_mapping(desc); - - list_add(&desc->list, &fd_maps->pages); - - virt = (void *) ((unsigned long) virt & PAGE_MASK); - err = os_map_memory(virt, fd, offset, PAGE_SIZE, 1, w, 0); - if(!err) - goto out; - - rb_erase(&desc->rb, &phys_mappings); - kfree(desc); - out: - return err; -} - static int physmem_fd = -1; -static void remove_mapping(struct phys_desc *desc) -{ - void *virt = desc->virt; - int err; - - rb_erase(&desc->rb, &phys_mappings); - list_del(&desc->list); - kfree(desc); - - err = os_map_memory(virt, physmem_fd, __pa(virt), PAGE_SIZE, 1, 1, 0); - if(err) - panic("Failed to unmap block device page from physical memory, " - "errno = %d", -err); -} - -int physmem_remove_mapping(void *virt) -{ - struct phys_desc *desc; - - virt = (void *) ((unsigned long) virt & PAGE_MASK); - desc = find_phys_mapping(virt); - if(desc == NULL) - return 0; - - remove_mapping(desc); - return 1; -} - -void physmem_forget_descriptor(int fd) -{ - struct desc_mapping *desc; - struct phys_desc *page; - struct list_head *ele, *next; - __u64 offset; - void *addr; - int err; - - desc = find_mapping(fd); - if(desc == NULL) - return; - - list_for_each_safe(ele, next, &desc->pages){ - page = list_entry(ele, struct phys_desc, list); - offset = page->offset; - addr = page->virt; - remove_mapping(page); - err = os_seek_file(fd, offset); - if(err) - panic("physmem_forget_descriptor - failed to seek " - "to %lld in fd %d, error = %d\n", - offset, fd, -err); - err = os_read_file(fd, addr, PAGE_SIZE); - if(err < 0) - panic("physmem_forget_descriptor - failed to read " - "from fd %d to 0x%p, error = %d\n", - fd, addr, -err); - } - - list_del(&desc->list); - kfree(desc); -} - -EXPORT_SYMBOL(physmem_forget_descriptor); -EXPORT_SYMBOL(physmem_remove_mapping); -EXPORT_SYMBOL(physmem_subst_mapping); - -void arch_free_page(struct page *page, int order) -{ - void *virt; - int i; - - for(i = 0; i < (1 << order); i++){ - virt = __va(page_to_phys(page + i)); - physmem_remove_mapping(virt); - } -} - -int is_remapped(void *virt) -{ - struct phys_desc *desc = find_phys_mapping(virt); - - return desc != NULL; -} - /* Changed during early boot */ unsigned long high_physmem; @@ -350,14 +129,9 @@ void setup_physmem(unsigned long start, unsigned long reserve_end, int phys_mapping(unsigned long phys, __u64 *offset_out) { - struct phys_desc *desc = find_phys_mapping(__va(phys & PAGE_MASK)); int fd = -1; - if(desc != NULL){ - fd = desc->fd; - *offset_out = desc->offset; - } - else if(phys < physmem_size){ + if(phys < physmem_size){ fd = physmem_fd; *offset_out = phys; } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 348b272bb766..8d2c5496532b 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -32,8 +32,8 @@ #include "asm/tlbflush.h" #include "asm/uaccess.h" #include "asm/user.h" -#include "user_util.h" #include "kern_util.h" +#include "as-layout.h" #include "kern.h" #include "signal_kern.h" #include "init.h" @@ -54,11 +54,9 @@ */ struct cpu_task cpu_tasks[NR_CPUS] = { [0 ... NR_CPUS - 1] = { -1, NULL } }; -int external_pid(void *t) +static inline int external_pid(struct task_struct *task) { - struct task_struct *task = t ? t : current; - - return(CHOOSE_MODE_PROC(external_pid_tt, external_pid_skas, task)); + return CHOOSE_MODE_PROC(external_pid_tt, external_pid_skas, task); } int pid_to_processor_id(int pid) @@ -66,9 +64,10 @@ int pid_to_processor_id(int pid) int i; for(i = 0; i < ncpus; i++){ - if(cpu_tasks[i].pid == pid) return(i); + if(cpu_tasks[i].pid == pid) + return i; } - return(-1); + return -1; } void free_stack(unsigned long stack, int order) @@ -85,9 +84,9 @@ unsigned long alloc_stack(int order, int atomic) flags = GFP_ATOMIC; page = __get_free_pages(flags, order); if(page == 0) - return(0); + return 0; stack_protections(page); - return(page); + return page; } int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) @@ -98,15 +97,11 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) current->thread.request.u.thread.arg = arg; pid = do_fork(CLONE_VM | CLONE_UNTRACED | flags, 0, ¤t->thread.regs, 0, NULL, NULL); - if(pid < 0) - panic("do_fork failed in kernel_thread, errno = %d", pid); - return(pid); + return pid; } -void set_current(void *t) +static inline void set_current(struct task_struct *task) { - struct task_struct *task = t; - cpu_tasks[task_thread_info(task)->cpu] = ((struct cpu_task) { external_pid(task), task }); } @@ -128,14 +123,16 @@ void *_switch_to(void *prev, void *next, void *last) prev= current; } while(current->thread.saved_task); - return(current->thread.prev_sched); + return current->thread.prev_sched; } void interrupt_end(void) { - if(need_resched()) schedule(); - if(test_tsk_thread_flag(current, TIF_SIGPENDING)) do_signal(); + if(need_resched()) + schedule(); + if(test_tsk_thread_flag(current, TIF_SIGPENDING)) + do_signal(); } void release_thread(struct task_struct *task) @@ -150,7 +147,7 @@ void exit_thread(void) void *get_current(void) { - return(current); + return current; } int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, @@ -188,15 +185,12 @@ void initial_thread_cb(void (*proc)(void *), void *arg) kmalloc_ok = save_kmalloc_ok; } +#ifdef CONFIG_MODE_TT unsigned long stack_sp(unsigned long page) { - return(page + PAGE_SIZE - sizeof(void *)); -} - -int current_pid(void) -{ - return(current->pid); + return page + PAGE_SIZE - sizeof(void *); } +#endif void default_idle(void) { @@ -221,11 +215,6 @@ void cpu_idle(void) CHOOSE_MODE(init_idle_tt(), init_idle_skas()); } -int page_size(void) -{ - return(PAGE_SIZE); -} - void *um_virt_to_phys(struct task_struct *task, unsigned long addr, pte_t *pte_out) { @@ -236,68 +225,43 @@ void *um_virt_to_phys(struct task_struct *task, unsigned long addr, pte_t ptent; if(task->mm == NULL) - return(ERR_PTR(-EINVAL)); + return ERR_PTR(-EINVAL); pgd = pgd_offset(task->mm, addr); if(!pgd_present(*pgd)) - return(ERR_PTR(-EINVAL)); + return ERR_PTR(-EINVAL); pud = pud_offset(pgd, addr); if(!pud_present(*pud)) - return(ERR_PTR(-EINVAL)); + return ERR_PTR(-EINVAL); pmd = pmd_offset(pud, addr); if(!pmd_present(*pmd)) - return(ERR_PTR(-EINVAL)); + return ERR_PTR(-EINVAL); pte = pte_offset_kernel(pmd, addr); ptent = *pte; if(!pte_present(ptent)) - return(ERR_PTR(-EINVAL)); + return ERR_PTR(-EINVAL); if(pte_out != NULL) *pte_out = ptent; - return((void *) (pte_val(ptent) & PAGE_MASK) + (addr & ~PAGE_MASK)); + return (void *) (pte_val(ptent) & PAGE_MASK) + (addr & ~PAGE_MASK); } char *current_cmd(void) { #if defined(CONFIG_SMP) || defined(CONFIG_HIGHMEM) - return("(Unknown)"); + return "(Unknown)"; #else void *addr = um_virt_to_phys(current, current->mm->arg_start, NULL); return IS_ERR(addr) ? "(Unknown)": __va((unsigned long) addr); #endif } -void force_sigbus(void) -{ - printk(KERN_ERR "Killing pid %d because of a lack of memory\n", - current->pid); - lock_kernel(); - sigaddset(¤t->pending.signal, SIGBUS); - recalc_sigpending(); - current->flags |= PF_SIGNALED; - do_exit(SIGBUS | 0x80); -} - void dump_thread(struct pt_regs *regs, struct user *u) { } -void enable_hlt(void) -{ - panic("enable_hlt"); -} - -EXPORT_SYMBOL(enable_hlt); - -void disable_hlt(void) -{ - panic("disable_hlt"); -} - -EXPORT_SYMBOL(disable_hlt); - void *um_kmalloc(int size) { return kmalloc(size, GFP_KERNEL); @@ -313,36 +277,17 @@ void *um_vmalloc(int size) return vmalloc(size); } -void *um_vmalloc_atomic(int size) -{ - return __vmalloc(size, GFP_ATOMIC | __GFP_HIGHMEM, PAGE_KERNEL); -} - int __cant_sleep(void) { return in_atomic() || irqs_disabled() || in_interrupt(); /* Is in_interrupt() really needed? */ } -unsigned long get_fault_addr(void) -{ - return((unsigned long) current->thread.fault_addr); -} - -EXPORT_SYMBOL(get_fault_addr); - -void not_implemented(void) -{ - printk(KERN_DEBUG "Something isn't implemented in here\n"); -} - -EXPORT_SYMBOL(not_implemented); - int user_context(unsigned long sp) { unsigned long stack; stack = sp & (PAGE_MASK << CONFIG_KERNEL_STACK_ORDER); - return(stack != (unsigned long) current_thread); + return stack != (unsigned long) current_thread; } extern exitcall_t __uml_exitcall_begin, __uml_exitcall_end; @@ -363,22 +308,22 @@ char *uml_strdup(char *string) int copy_to_user_proc(void __user *to, void *from, int size) { - return(copy_to_user(to, from, size)); + return copy_to_user(to, from, size); } int copy_from_user_proc(void *to, void __user *from, int size) { - return(copy_from_user(to, from, size)); + return copy_from_user(to, from, size); } int clear_user_proc(void __user *buf, int size) { - return(clear_user(buf, size)); + return clear_user(buf, size); } int strlen_user_proc(char __user *str) { - return(strlen_user(str)); + return strlen_user(str); } int smp_sigio_handler(void) @@ -387,14 +332,14 @@ int smp_sigio_handler(void) int cpu = current_thread->cpu; IPI_handler(cpu); if(cpu != 0) - return(1); + return 1; #endif - return(0); + return 0; } int cpu(void) { - return(current_thread->cpu); + return current_thread->cpu; } static atomic_t using_sysemu = ATOMIC_INIT(0); @@ -443,7 +388,7 @@ int __init make_proc_sysemu(void) if (ent == NULL) { printk(KERN_WARNING "Failed to register /proc/sysemu\n"); - return(0); + return 0; } ent->read_proc = proc_read_sysemu; diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index f602623644aa..7e4305a1fd3c 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -6,7 +6,6 @@ #include "linux/module.h" #include "linux/sched.h" #include "asm/smp.h" -#include "user_util.h" #include "kern_util.h" #include "kern.h" #include "os.h" diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 3c798cdde550..c4020c3d7857 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -17,7 +17,6 @@ #include "asm/signal.h" #include "asm/uaccess.h" #include "asm/unistd.h" -#include "user_util.h" #include "asm/ucontext.h" #include "kern_util.h" #include "signal_kern.h" diff --git a/arch/um/kernel/skas/exec.c b/arch/um/kernel/skas/exec.c index 54b795951372..580eb6468949 100644 --- a/arch/um/kernel/skas/exec.c +++ b/arch/um/kernel/skas/exec.c @@ -17,7 +17,17 @@ void flush_thread_skas(void) { - force_flush_all(); + void *data = NULL; + unsigned long end = proc_mm ? task_size : CONFIG_STUB_START; + int ret; + + ret = unmap(¤t->mm->context.skas.id, 0, end, 1, &data); + if(ret){ + printk("flush_thread_skas - clearing address space failed, " + "err = %d\n", ret); + force_sig(SIGKILL, current); + } + switch_mm_skas(¤t->mm->context.skas.id); } diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c index ae4fa71d3b8b..2a69a7ce5792 100644 --- a/arch/um/kernel/skas/process.c +++ b/arch/um/kernel/skas/process.c @@ -13,9 +13,9 @@ #include "asm/uaccess.h" #include "asm/atomic.h" #include "kern_util.h" +#include "as-layout.h" #include "skas.h" #include "os.h" -#include "user_util.h" #include "tlb.h" #include "kern.h" #include "mode.h" @@ -163,8 +163,12 @@ static int start_kernel_proc(void *unused) extern int userspace_pid[]; +extern char cpu0_irqstack[]; + int start_uml_skas(void) { + stack_protections((unsigned long) &cpu0_irqstack); + set_sigstack(cpu0_irqstack, THREAD_SIZE); if(proc_mm) userspace_pid[0] = start_userspace(0); @@ -178,20 +182,23 @@ int start_uml_skas(void) int external_pid_skas(struct task_struct *task) { -#warning Need to look up userspace_pid by cpu + /* FIXME: Need to look up userspace_pid by cpu */ return(userspace_pid[0]); } int thread_pid_skas(struct task_struct *task) { -#warning Need to look up userspace_pid by cpu + /* FIXME: Need to look up userspace_pid by cpu */ return(userspace_pid[0]); } void kill_off_processes_skas(void) { if(proc_mm) -#warning need to loop over userspace_pids in kill_off_processes_skas + /* + * FIXME: need to loop over userspace_pids in + * kill_off_processes_skas + */ os_kill_ptraced_process(userspace_pid[0], 1); else { struct task_struct *p; diff --git a/arch/um/kernel/skas/tlb.c b/arch/um/kernel/skas/tlb.c index 27eb29ce666b..c0f0693743ba 100644 --- a/arch/um/kernel/skas/tlb.c +++ b/arch/um/kernel/skas/tlb.c @@ -10,7 +10,6 @@ #include "asm/page.h" #include "asm/pgtable.h" #include "asm/mmu.h" -#include "user_util.h" #include "mem_user.h" #include "mem.h" #include "skas.h" @@ -28,19 +27,17 @@ static int do_ops(union mm_context *mmu, struct host_vm_op *ops, int last, switch(op->type){ case MMAP: ret = map(&mmu->skas.id, op->u.mmap.addr, - op->u.mmap.len, op->u.mmap.r, op->u.mmap.w, - op->u.mmap.x, op->u.mmap.fd, - op->u.mmap.offset, finished, flush); + op->u.mmap.len, op->u.mmap.prot, + op->u.mmap.fd, op->u.mmap.offset, finished, + flush); break; case MUNMAP: - ret = unmap(&mmu->skas.id, - (void *) op->u.munmap.addr, + ret = unmap(&mmu->skas.id, op->u.munmap.addr, op->u.munmap.len, finished, flush); break; case MPROTECT: ret = protect(&mmu->skas.id, op->u.mprotect.addr, - op->u.mprotect.len, op->u.mprotect.r, - op->u.mprotect.w, op->u.mprotect.x, + op->u.mprotect.len, op->u.mprotect.prot, finished, flush); break; default: @@ -92,6 +89,76 @@ void flush_tlb_mm_skas(struct mm_struct *mm) void force_flush_all_skas(void) { - unsigned long end = proc_mm ? task_size : CONFIG_STUB_START; - fix_range(current->mm, 0, end, 1); + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = mm->mmap; + + while(vma != NULL) { + fix_range(mm, vma->vm_start, vma->vm_end, 1); + vma = vma->vm_next; + } +} + +void flush_tlb_page_skas(struct vm_area_struct *vma, unsigned long address) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + struct mm_struct *mm = vma->vm_mm; + void *flush = NULL; + int r, w, x, prot, err = 0; + struct mm_id *mm_id; + + pgd = pgd_offset(mm, address); + if(!pgd_present(*pgd)) + goto kill; + + pud = pud_offset(pgd, address); + if(!pud_present(*pud)) + goto kill; + + pmd = pmd_offset(pud, address); + if(!pmd_present(*pmd)) + goto kill; + + pte = pte_offset_kernel(pmd, address); + + r = pte_read(*pte); + w = pte_write(*pte); + x = pte_exec(*pte); + if (!pte_young(*pte)) { + r = 0; + w = 0; + } else if (!pte_dirty(*pte)) { + w = 0; + } + + mm_id = &mm->context.skas.id; + prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) | + (x ? UM_PROT_EXEC : 0)); + if(pte_newpage(*pte)){ + if(pte_present(*pte)){ + unsigned long long offset; + int fd; + + fd = phys_mapping(pte_val(*pte) & PAGE_MASK, &offset); + err = map(mm_id, address, PAGE_SIZE, prot, fd, offset, + 1, &flush); + } + else err = unmap(mm_id, address, PAGE_SIZE, 1, &flush); + } + else if(pte_newprot(*pte)) + err = protect(mm_id, address, PAGE_SIZE, prot, 1, &flush); + + if(err) + goto kill; + + *pte = pte_mkuptodate(*pte); + + return; + +kill: + printk("Failed to flush page for address 0x%lx\n", address); + force_sig(SIGKILL, current); } + diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 759b07053160..e6a7778006ad 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -21,7 +21,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); #include "asm/smp.h" #include "asm/processor.h" #include "asm/spinlock.h" -#include "user_util.h" #include "kern_util.h" #include "kern.h" #include "irq_user.h" @@ -90,7 +89,7 @@ static int idle_proc(void *cpup) cpu_set(cpu, cpu_online_map); default_idle(); - return(0); + return 0; } static struct task_struct *idle_thread(int cpu) @@ -98,8 +97,8 @@ static struct task_struct *idle_thread(int cpu) struct task_struct *new_task; unsigned char c; - current->thread.request.u.thread.proc = idle_proc; - current->thread.request.u.thread.arg = (void *) cpu; + current->thread.request.u.thread.proc = idle_proc; + current->thread.request.u.thread.arg = (void *) cpu; new_task = fork_idle(cpu); if(IS_ERR(new_task)) panic("copy_process failed in idle_thread, error = %ld", @@ -110,9 +109,9 @@ static struct task_struct *idle_thread(int cpu) .task = new_task } ); idle_threads[cpu] = new_task; CHOOSE_MODE(os_write_file(new_task->thread.mode.tt.switch_pipe[1], &c, - sizeof(c)), + sizeof(c)), ({ panic("skas mode doesn't support SMP"); })); - return(new_task); + return new_task; } void smp_prepare_cpus(unsigned int maxcpus) @@ -163,13 +162,13 @@ int __cpu_up(unsigned int cpu) cpu_set(cpu, smp_commenced_mask); while (!cpu_isset(cpu, cpu_online_map)) mb(); - return(0); + return 0; } int setup_profiling_timer(unsigned int multiplier) { printk(KERN_INFO "setup_profiling_timer\n"); - return(0); + return 0; } void smp_call_function_slave(int cpu); @@ -205,7 +204,7 @@ void IPI_handler(int cpu) int hard_smp_processor_id(void) { - return(pid_to_processor_id(os_getpid())); + return pid_to_processor_id(os_getpid()); } static DEFINE_SPINLOCK(call_lock); @@ -254,14 +253,3 @@ int smp_call_function(void (*_func)(void *info), void *_info, int nonatomic, } #endif - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 2828c5283227..237c4eab7cfd 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -18,7 +18,6 @@ #include "asm/mman.h" #include "asm/uaccess.h" #include "kern_util.h" -#include "user_util.h" #include "sysdep/syscalls.h" #include "mode_kern.h" #include "choose-mode.h" diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index f9e02b31a97a..93263571d813 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -10,7 +10,6 @@ #include "asm/page.h" #include "asm/processor.h" #include "sysrq.h" -#include "user_util.h" /* Catch non-i386 SUBARCH's. */ #if !defined(CONFIG_UML_X86) || defined(CONFIG_64BIT) diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index b1f8b0752419..259c49da7ff5 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -18,7 +18,6 @@ #include "asm/param.h" #include "asm/current.h" #include "kern_util.h" -#include "user_util.h" #include "mode.h" #include "os.h" @@ -35,8 +34,8 @@ unsigned long long sched_clock(void) return (unsigned long long)jiffies_64 * (1000000000 / HZ); } -static unsigned long long prev_nsecs[NR_CPUS]; #ifdef CONFIG_UML_REAL_TIME_CLOCK +static unsigned long long prev_nsecs[NR_CPUS]; static long long delta[NR_CPUS]; /* Deviation per interval */ #endif @@ -95,7 +94,12 @@ irqreturn_t um_timer(int irq, void *dev) do_timer(1); +#ifdef CONFIG_UML_REAL_TIME_CLOCK nsecs = get_time(); +#else + nsecs = (unsigned long long) xtime.tv_sec * BILLION + xtime.tv_nsec + + BILLION / HZ; +#endif xtime.tv_sec = nsecs / NSEC_PER_SEC; xtime.tv_nsec = nsecs - xtime.tv_sec * NSEC_PER_SEC; @@ -128,13 +132,18 @@ void time_init(void) nsecs = os_nsecs(); set_normalized_timespec(&wall_to_monotonic, -nsecs / BILLION, -nsecs % BILLION); + set_normalized_timespec(&xtime, nsecs / BILLION, nsecs % BILLION); late_time_init = register_timer; } void do_gettimeofday(struct timeval *tv) { +#ifdef CONFIG_UML_REAL_TIME_CLOCK unsigned long long nsecs = get_time(); - +#else + unsigned long long nsecs = (unsigned long long) xtime.tv_sec * BILLION + + xtime.tv_nsec; +#endif tv->tv_sec = nsecs / NSEC_PER_SEC; /* Careful about calculations here - this was originally done as * (nsecs - tv->tv_sec * NSEC_PER_SEC) / NSEC_PER_USEC @@ -168,6 +177,8 @@ int do_settimeofday(struct timespec *tv) void timer_handler(int sig, union uml_pt_regs *regs) { + if(current_thread->cpu == 0) + timer_irq(regs); local_irq_disable(); irq_enter(); update_process_times(CHOOSE_MODE( @@ -175,6 +186,4 @@ void timer_handler(int sig, union uml_pt_regs *regs) (regs)->skas.is_user)); irq_exit(); local_irq_enable(); - if(current_thread->cpu == 0) - timer_irq(regs); } diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 54a5ff25645a..8a8d52851443 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -6,17 +6,18 @@ #include "linux/mm.h" #include "asm/page.h" #include "asm/pgalloc.h" +#include "asm/pgtable.h" #include "asm/tlbflush.h" #include "choose-mode.h" #include "mode_kern.h" -#include "user_util.h" +#include "as-layout.h" #include "tlb.h" #include "mem.h" #include "mem_user.h" #include "os.h" static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, - int r, int w, int x, struct host_vm_op *ops, int *index, + unsigned int prot, struct host_vm_op *ops, int *index, int last_filled, union mm_context *mmu, void **flush, int (*do_ops)(union mm_context *, struct host_vm_op *, int, int, void **)) @@ -30,8 +31,7 @@ static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, last = &ops[*index]; if((last->type == MMAP) && (last->u.mmap.addr + last->u.mmap.len == virt) && - (last->u.mmap.r == r) && (last->u.mmap.w == w) && - (last->u.mmap.x == x) && (last->u.mmap.fd == fd) && + (last->u.mmap.prot == prot) && (last->u.mmap.fd == fd) && (last->u.mmap.offset + last->u.mmap.len == offset)){ last->u.mmap.len += len; return 0; @@ -47,9 +47,7 @@ static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, .u = { .mmap = { .addr = virt, .len = len, - .r = r, - .w = w, - .x = x, + .prot = prot, .fd = fd, .offset = offset } } }); @@ -86,8 +84,8 @@ static int add_munmap(unsigned long addr, unsigned long len, return ret; } -static int add_mprotect(unsigned long addr, unsigned long len, int r, int w, - int x, struct host_vm_op *ops, int *index, +static int add_mprotect(unsigned long addr, unsigned long len, + unsigned int prot, struct host_vm_op *ops, int *index, int last_filled, union mm_context *mmu, void **flush, int (*do_ops)(union mm_context *, struct host_vm_op *, int, int, void **)) @@ -99,8 +97,7 @@ static int add_mprotect(unsigned long addr, unsigned long len, int r, int w, last = &ops[*index]; if((last->type == MPROTECT) && (last->u.mprotect.addr + last->u.mprotect.len == addr) && - (last->u.mprotect.r == r) && (last->u.mprotect.w == w) && - (last->u.mprotect.x == x)){ + (last->u.mprotect.prot == prot)){ last->u.mprotect.len += len; return 0; } @@ -115,114 +112,145 @@ static int add_mprotect(unsigned long addr, unsigned long len, int r, int w, .u = { .mprotect = { .addr = addr, .len = len, - .r = r, - .w = w, - .x = x } } }); + .prot = prot } } }); return ret; } #define ADD_ROUND(n, inc) (((n) + (inc)) & ~((inc) - 1)) +static inline int update_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct host_vm_op *ops, + int last_op, int *op_index, int force, + union mm_context *mmu, void **flush, + int (*do_ops)(union mm_context *, + struct host_vm_op *, int, int, + void **)) +{ + pte_t *pte; + int r, w, x, prot, ret = 0; + + pte = pte_offset_kernel(pmd, addr); + do { + r = pte_read(*pte); + w = pte_write(*pte); + x = pte_exec(*pte); + if (!pte_young(*pte)) { + r = 0; + w = 0; + } else if (!pte_dirty(*pte)) { + w = 0; + } + prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) | + (x ? UM_PROT_EXEC : 0)); + if(force || pte_newpage(*pte)){ + if(pte_present(*pte)) + ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK, + PAGE_SIZE, prot, ops, op_index, + last_op, mmu, flush, do_ops); + else ret = add_munmap(addr, PAGE_SIZE, ops, op_index, + last_op, mmu, flush, do_ops); + } + else if(pte_newprot(*pte)) + ret = add_mprotect(addr, PAGE_SIZE, prot, ops, op_index, + last_op, mmu, flush, do_ops); + *pte = pte_mkuptodate(*pte); + } while (pte++, addr += PAGE_SIZE, ((addr != end) && !ret)); + return ret; +} + +static inline int update_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, struct host_vm_op *ops, + int last_op, int *op_index, int force, + union mm_context *mmu, void **flush, + int (*do_ops)(union mm_context *, + struct host_vm_op *, int, int, + void **)) +{ + pmd_t *pmd; + unsigned long next; + int ret = 0; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if(!pmd_present(*pmd)){ + if(force || pmd_newpage(*pmd)){ + ret = add_munmap(addr, next - addr, ops, + op_index, last_op, mmu, + flush, do_ops); + pmd_mkuptodate(*pmd); + } + } + else ret = update_pte_range(pmd, addr, next, ops, last_op, + op_index, force, mmu, flush, + do_ops); + } while (pmd++, addr = next, ((addr != end) && !ret)); + return ret; +} + +static inline int update_pud_range(pgd_t *pgd, unsigned long addr, + unsigned long end, struct host_vm_op *ops, + int last_op, int *op_index, int force, + union mm_context *mmu, void **flush, + int (*do_ops)(union mm_context *, + struct host_vm_op *, int, int, + void **)) +{ + pud_t *pud; + unsigned long next; + int ret = 0; + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if(!pud_present(*pud)){ + if(force || pud_newpage(*pud)){ + ret = add_munmap(addr, next - addr, ops, + op_index, last_op, mmu, + flush, do_ops); + pud_mkuptodate(*pud); + } + } + else ret = update_pmd_range(pud, addr, next, ops, last_op, + op_index, force, mmu, flush, + do_ops); + } while (pud++, addr = next, ((addr != end) && !ret)); + return ret; +} + void fix_range_common(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr, int force, int (*do_ops)(union mm_context *, struct host_vm_op *, int, int, void **)) { - pgd_t *npgd; - pud_t *npud; - pmd_t *npmd; - pte_t *npte; + pgd_t *pgd; union mm_context *mmu = &mm->context; - unsigned long addr, end; - int r, w, x; struct host_vm_op ops[1]; + unsigned long addr = start_addr, next; + int ret = 0, last_op = ARRAY_SIZE(ops) - 1, op_index = -1; void *flush = NULL; - int op_index = -1, last_op = ARRAY_SIZE(ops) - 1; - int ret = 0; - - if(mm == NULL) - return; ops[0].type = NONE; - for(addr = start_addr; addr < end_addr && !ret;){ - npgd = pgd_offset(mm, addr); - if(!pgd_present(*npgd)){ - end = ADD_ROUND(addr, PGDIR_SIZE); - if(end > end_addr) - end = end_addr; - if(force || pgd_newpage(*npgd)){ - ret = add_munmap(addr, end - addr, ops, - &op_index, last_op, mmu, - &flush, do_ops); - pgd_mkuptodate(*npgd); - } - addr = end; - continue; - } - - npud = pud_offset(npgd, addr); - if(!pud_present(*npud)){ - end = ADD_ROUND(addr, PUD_SIZE); - if(end > end_addr) - end = end_addr; - if(force || pud_newpage(*npud)){ - ret = add_munmap(addr, end - addr, ops, - &op_index, last_op, mmu, - &flush, do_ops); - pud_mkuptodate(*npud); - } - addr = end; - continue; - } - - npmd = pmd_offset(npud, addr); - if(!pmd_present(*npmd)){ - end = ADD_ROUND(addr, PMD_SIZE); - if(end > end_addr) - end = end_addr; - if(force || pmd_newpage(*npmd)){ - ret = add_munmap(addr, end - addr, ops, + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end_addr); + if(!pgd_present(*pgd)){ + if (force || pgd_newpage(*pgd)){ + ret = add_munmap(addr, next - addr, ops, &op_index, last_op, mmu, &flush, do_ops); - pmd_mkuptodate(*npmd); + pgd_mkuptodate(*pgd); } - addr = end; - continue; - } - - npte = pte_offset_kernel(npmd, addr); - r = pte_read(*npte); - w = pte_write(*npte); - x = pte_exec(*npte); - if (!pte_young(*npte)) { - r = 0; - w = 0; - } else if (!pte_dirty(*npte)) { - w = 0; - } - if(force || pte_newpage(*npte)){ - if(pte_present(*npte)) - ret = add_mmap(addr, - pte_val(*npte) & PAGE_MASK, - PAGE_SIZE, r, w, x, ops, - &op_index, last_op, mmu, - &flush, do_ops); - else ret = add_munmap(addr, PAGE_SIZE, ops, - &op_index, last_op, mmu, - &flush, do_ops); } - else if(pte_newprot(*npte)) - ret = add_mprotect(addr, PAGE_SIZE, r, w, x, ops, - &op_index, last_op, mmu, - &flush, do_ops); + else ret = update_pud_range(pgd, addr, next, ops, last_op, + &op_index, force, mmu, &flush, + do_ops); + } while (pgd++, addr = next, ((addr != end_addr) && !ret)); - *npte = pte_mkuptodate(*npte); - addr += PAGE_SIZE; - } if(!ret) ret = (*do_ops)(mmu, ops, op_index, 1, &flush); -/* This is not an else because ret is modified above */ + /* This is not an else because ret is modified above */ if(ret) { printk("fix_range_common: failed, killing current process\n"); force_sig(SIGKILL, current); @@ -343,12 +371,6 @@ pte_t *addr_pte(struct task_struct *task, unsigned long addr) return(pte_offset_map(pmd, addr)); } -void flush_tlb_page(struct vm_area_struct *vma, unsigned long address) -{ - address &= PAGE_MASK; - flush_tlb_range(vma, address, address + PAGE_SIZE); -} - void flush_tlb_all(void) { flush_tlb_mm(current->mm); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 26f15c458574..abab90c3803f 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -18,8 +18,9 @@ #include "asm/current.h" #include "asm/irq.h" #include "sysdep/sigcontext.h" -#include "user_util.h" #include "kern_util.h" +#include "as-layout.h" +#include "arch.h" #include "kern.h" #include "chan_kern.h" #include "mconsole_kern.h" @@ -71,8 +72,8 @@ good_area: goto out; /* Don't require VM_READ|VM_EXEC for write faults! */ - if(!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC))) - goto out; + if(!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC))) + goto out; do { survive: @@ -156,20 +157,23 @@ static void segv_handler(int sig, union uml_pt_regs *regs) * the info in the regs. A pointer to the info then would * give us bad data! */ -unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, void *sc) +unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, + union uml_pt_regs *regs) { struct siginfo si; void *catcher; int err; - int is_write = FAULT_WRITE(fi); - unsigned long address = FAULT_ADDRESS(fi); + int is_write = FAULT_WRITE(fi); + unsigned long address = FAULT_ADDRESS(fi); - if(!is_user && (address >= start_vm) && (address < end_vm)){ - flush_tlb_kernel_vm(); - return(0); - } - else if(current->mm == NULL) - panic("Segfault with no mm"); + if(!is_user && (address >= start_vm) && (address < end_vm)){ + flush_tlb_kernel_vm(); + return 0; + } + else if(current->mm == NULL) { + show_regs(container_of(regs, struct pt_regs, regs)); + panic("Segfault with no mm"); + } if (SEGV_IS_FIXABLE(&fi) || SEGV_MAYBE_FIXABLE(&fi)) err = handle_page_fault(address, ip, is_write, is_user, &si.si_code); @@ -182,26 +186,28 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, void *sc) catcher = current->thread.fault_catcher; if(!err) - return(0); + return 0; else if(catcher != NULL){ current->thread.fault_addr = (void *) address; do_longjmp(catcher, 1); } else if(current->thread.fault_addr != NULL) panic("fault_addr set but no fault catcher"); - else if(!is_user && arch_fixup(ip, sc)) - return(0); + else if(!is_user && arch_fixup(ip, regs)) + return 0; - if(!is_user) + if(!is_user) { + show_regs(container_of(regs, struct pt_regs, regs)); panic("Kernel mode fault at addr 0x%lx, ip 0x%lx", address, ip); + } if (err == -EACCES) { si.si_signo = SIGBUS; si.si_errno = 0; si.si_code = BUS_ADRERR; si.si_addr = (void __user *)address; - current->thread.arch.faultinfo = fi; + current->thread.arch.faultinfo = fi; force_sig_info(SIGBUS, &si, current); } else if (err == -ENOMEM) { printk("VM: killing process %s\n", current->comm); @@ -210,10 +216,10 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, void *sc) BUG_ON(err != -EFAULT); si.si_signo = SIGSEGV; si.si_addr = (void __user *) address; - current->thread.arch.faultinfo = fi; + current->thread.arch.faultinfo = fi; force_sig_info(SIGSEGV, &si, current); } - return(0); + return 0; } void relay_signal(int sig, union uml_pt_regs *regs) @@ -223,12 +229,12 @@ void relay_signal(int sig, union uml_pt_regs *regs) if(!UPT_IS_USER(regs)){ if(sig == SIGBUS) - printk("Bus error - the /dev/shm or /tmp mount likely " - "just ran out of space\n"); + printk("Bus error - the host /dev/shm or /tmp mount " + "likely just ran out of space\n"); panic("Kernel mode signal %d", sig); } - current->thread.arch.faultinfo = *UPT_FAULTINFO(regs); + current->thread.arch.faultinfo = *UPT_FAULTINFO(regs); force_sig(sig, current); } diff --git a/arch/um/kernel/tt/exec_kern.c b/arch/um/kernel/tt/exec_kern.c index ad66df17d9d7..40126cb51801 100644 --- a/arch/um/kernel/tt/exec_kern.c +++ b/arch/um/kernel/tt/exec_kern.c @@ -10,7 +10,6 @@ #include "asm/uaccess.h" #include "asm/pgalloc.h" #include "asm/tlbflush.h" -#include "user_util.h" #include "kern_util.h" #include "irq_user.h" #include "mem_user.h" @@ -58,7 +57,7 @@ void flush_thread_tt(void) enable_timer(); free_page(stack); protect_memory(uml_reserved, high_physmem - uml_reserved, 1, 1, 0, 1); - task_protections((unsigned long) current_thread); + stack_protections((unsigned long) current_thread); force_flush_all(); unblock_signals(); } diff --git a/arch/um/kernel/tt/exec_user.c b/arch/um/kernel/tt/exec_user.c index a92c02ff2ce3..7b5f2181cf51 100644 --- a/arch/um/kernel/tt/exec_user.c +++ b/arch/um/kernel/tt/exec_user.c @@ -10,7 +10,6 @@ #include <errno.h> #include <sys/wait.h> #include <signal.h> -#include "user_util.h" #include "kern_util.h" #include "user.h" #include "ptrace_user.h" diff --git a/arch/um/kernel/tt/gdb.c b/arch/um/kernel/tt/gdb.c index 8eba8f7dca68..030e4658f36b 100644 --- a/arch/um/kernel/tt/gdb.c +++ b/arch/um/kernel/tt/gdb.c @@ -17,7 +17,6 @@ #include "user.h" #include "debug.h" #include "kern_util.h" -#include "user_util.h" #include "tt.h" #include "sysdep/thread.h" #include "os.h" @@ -115,6 +114,8 @@ struct gdb_data { int err; }; +extern char *linux_prog; + static void config_gdb_cb(void *arg) { struct gdb_data *data = arg; diff --git a/arch/um/kernel/tt/include/mode_kern-tt.h b/arch/um/kernel/tt/include/mode_kern-tt.h deleted file mode 100644 index 2a35b15c5fef..000000000000 --- a/arch/um/kernel/tt/include/mode_kern-tt.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) - * Licensed under the GPL - */ - -#ifndef __TT_MODE_KERN_H__ -#define __TT_MODE_KERN_H__ - -#include "linux/sched.h" -#include "asm/page.h" -#include "asm/ptrace.h" -#include "asm/uaccess.h" - -extern void switch_to_tt(void *prev, void *next); -extern void flush_thread_tt(void); -extern void start_thread_tt(struct pt_regs *regs, unsigned long eip, - unsigned long esp); -extern int copy_thread_tt(int nr, unsigned long clone_flags, unsigned long sp, - unsigned long stack_top, struct task_struct *p, - struct pt_regs *regs); -extern void release_thread_tt(struct task_struct *task); -extern void initial_thread_cb_tt(void (*proc)(void *), void *arg); -extern void init_idle_tt(void); -extern void flush_tlb_kernel_range_tt(unsigned long start, unsigned long end); -extern void flush_tlb_kernel_vm_tt(void); -extern void __flush_tlb_one_tt(unsigned long addr); -extern void flush_tlb_range_tt(struct vm_area_struct *vma, - unsigned long start, unsigned long end); -extern void flush_tlb_mm_tt(struct mm_struct *mm); -extern void force_flush_all_tt(void); -extern long execute_syscall_tt(void *r); -extern void before_mem_tt(unsigned long brk_start); -extern unsigned long set_task_sizes_tt(int arg, unsigned long *host_size_out, - unsigned long *task_size_out); -extern int start_uml_tt(void); -extern int external_pid_tt(struct task_struct *task); -extern int thread_pid_tt(struct task_struct *task); - -#define kmem_end_tt (host_task_size - ABOVE_KMEM) - -#endif - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/kernel/tt/mem.c b/arch/um/kernel/tt/mem.c index 4d1929dfa285..d0c3c4975f28 100644 --- a/arch/um/kernel/tt/mem.c +++ b/arch/um/kernel/tt/mem.c @@ -8,7 +8,6 @@ #include "asm/uaccess.h" #include "mem_user.h" #include "kern_util.h" -#include "user_util.h" #include "kern.h" #include "tt.h" diff --git a/arch/um/kernel/tt/mem_user.c b/arch/um/kernel/tt/mem_user.c index 03e589895388..9774f6360c32 100644 --- a/arch/um/kernel/tt/mem_user.c +++ b/arch/um/kernel/tt/mem_user.c @@ -11,7 +11,6 @@ #include <sys/mman.h> #include "tt.h" #include "mem_user.h" -#include "user_util.h" #include "os.h" void remap_data(void *segment_start, void *segment_end, int w) diff --git a/arch/um/kernel/tt/process_kern.c b/arch/um/kernel/tt/process_kern.c index 1e86f0bfef72..74347adf81bf 100644 --- a/arch/um/kernel/tt/process_kern.c +++ b/arch/um/kernel/tt/process_kern.c @@ -14,7 +14,6 @@ #include "asm/tlbflush.h" #include "irq_user.h" #include "kern_util.h" -#include "user_util.h" #include "os.h" #include "kern.h" #include "sigcontext.h" @@ -65,7 +64,8 @@ void switch_to_tt(void *prev, void *next) if(from->thread.mode.tt.switch_pipe[0] == -1) os_kill_process(os_getpid(), 0); - err = os_read_file(from->thread.mode.tt.switch_pipe[0], &c, sizeof(c)); + err = os_read_file(from->thread.mode.tt.switch_pipe[0], &c, + sizeof(c)); if(err != sizeof(c)) panic("read of switch_pipe failed, errno = %d", -err); @@ -209,7 +209,7 @@ void finish_fork_handler(int sig) if(current->mm != current->parent->mm) protect_memory(uml_reserved, high_physmem - uml_reserved, 1, 1, 0, 1); - task_protections((unsigned long) current_thread); + stack_protections((unsigned long) current_thread); free_page(current->thread.temp_stack); local_irq_disable(); diff --git a/arch/um/kernel/tt/ptproxy/proxy.c b/arch/um/kernel/tt/ptproxy/proxy.c index 58800c50b10e..420c23f311f3 100644 --- a/arch/um/kernel/tt/ptproxy/proxy.c +++ b/arch/um/kernel/tt/ptproxy/proxy.c @@ -26,7 +26,6 @@ Jeff Dike (jdike@karaya.com) : Modified for integration into uml #include "sysdep.h" #include "wait.h" -#include "user_util.h" #include "user.h" #include "os.h" #include "tempfile.h" @@ -339,11 +338,12 @@ int start_debugger(char *prog, int startup, int stop, int *fd_out) "err = %d\n", -fd); exit(1); } - os_write_file(fd, gdb_init_string, sizeof(gdb_init_string) - 1); + os_write_file(fd, gdb_init_string, + sizeof(gdb_init_string) - 1); if(startup){ if(stop){ os_write_file(fd, "b start_kernel\n", - strlen("b start_kernel\n")); + strlen("b start_kernel\n")); } os_write_file(fd, "c\n", strlen("c\n")); } diff --git a/arch/um/kernel/tt/ptproxy/ptrace.c b/arch/um/kernel/tt/ptproxy/ptrace.c index 03774427d468..4b4f6179b212 100644 --- a/arch/um/kernel/tt/ptproxy/ptrace.c +++ b/arch/um/kernel/tt/ptproxy/ptrace.c @@ -16,7 +16,6 @@ Jeff Dike (jdike@karaya.com) : Modified for integration into uml #include "ptproxy.h" #include "debug.h" -#include "user_util.h" #include "kern_util.h" #include "ptrace_user.h" #include "tt.h" diff --git a/arch/um/kernel/tt/ptproxy/sysdep.c b/arch/um/kernel/tt/ptproxy/sysdep.c index 99f178319d03..e0e1ab0588ad 100644 --- a/arch/um/kernel/tt/ptproxy/sysdep.c +++ b/arch/um/kernel/tt/ptproxy/sysdep.c @@ -13,7 +13,6 @@ terms and conditions. #include <sys/types.h> #include <linux/unistd.h> #include "ptrace_user.h" -#include "user_util.h" #include "user.h" #include "os.h" diff --git a/arch/um/kernel/tt/ptproxy/wait.c b/arch/um/kernel/tt/ptproxy/wait.c index 12f6319d8d76..bdd4af4b65fc 100644 --- a/arch/um/kernel/tt/ptproxy/wait.c +++ b/arch/um/kernel/tt/ptproxy/wait.c @@ -13,7 +13,6 @@ terms and conditions. #include "ptproxy.h" #include "sysdep.h" #include "wait.h" -#include "user_util.h" #include "ptrace_user.h" #include "sysdep/ptrace.h" #include "sysdep/sigcontext.h" diff --git a/arch/um/kernel/tt/syscall_user.c b/arch/um/kernel/tt/syscall_user.c index 902987bf379b..f52b47aff1d2 100644 --- a/arch/um/kernel/tt/syscall_user.c +++ b/arch/um/kernel/tt/syscall_user.c @@ -11,7 +11,6 @@ #include "sigcontext.h" #include "ptrace_user.h" #include "task.h" -#include "user_util.h" #include "kern_util.h" #include "syscall.h" #include "tt.h" diff --git a/arch/um/kernel/tt/tlb.c b/arch/um/kernel/tt/tlb.c index ae6217c86135..7caa24fe05df 100644 --- a/arch/um/kernel/tt/tlb.c +++ b/arch/um/kernel/tt/tlb.c @@ -12,7 +12,6 @@ #include "asm/pgtable.h" #include "asm/uaccess.h" #include "asm/tlbflush.h" -#include "user_util.h" #include "mem_user.h" #include "os.h" #include "tlb.h" diff --git a/arch/um/kernel/tt/tracer.c b/arch/um/kernel/tt/tracer.c index b9195355075a..c23588393f6e 100644 --- a/arch/um/kernel/tt/tracer.c +++ b/arch/um/kernel/tt/tracer.c @@ -19,7 +19,6 @@ #include "sigcontext.h" #include "sysdep/sigcontext.h" #include "os.h" -#include "user_util.h" #include "mem_user.h" #include "process.h" #include "kern_util.h" diff --git a/arch/um/kernel/tt/trap_user.c b/arch/um/kernel/tt/trap_user.c index b5d9d64d91e4..3032eb5e2467 100644 --- a/arch/um/kernel/tt/trap_user.c +++ b/arch/um/kernel/tt/trap_user.c @@ -8,7 +8,6 @@ #include <signal.h> #include "sysdep/ptrace.h" #include "sysdep/sigcontext.h" -#include "user_util.h" #include "kern_util.h" #include "task.h" #include "tt.h" diff --git a/arch/um/kernel/tt/uaccess_user.c b/arch/um/kernel/tt/uaccess_user.c index ed1abcf4d057..0e5c82c5e5b7 100644 --- a/arch/um/kernel/tt/uaccess_user.c +++ b/arch/um/kernel/tt/uaccess_user.c @@ -5,7 +5,6 @@ */ #include <string.h> -#include "user_util.h" #include "uml_uaccess.h" #include "task.h" #include "kern_util.h" diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 89c6dba731f8..ecc458fe51b9 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -17,6 +17,7 @@ #include "linux/seq_file.h" #include "linux/delay.h" #include "linux/module.h" +#include "linux/utsname.h" #include "asm/page.h" #include "asm/pgtable.h" #include "asm/ptrace.h" @@ -25,8 +26,9 @@ #include "asm/setup.h" #include "ubd_user.h" #include "asm/current.h" -#include "user_util.h" #include "kern_util.h" +#include "as-layout.h" +#include "arch.h" #include "kern.h" #include "mem_user.h" #include "mem.h" @@ -42,7 +44,7 @@ #define DEFAULT_COMMAND_LINE "root=98:0" -/* Changed in linux_main and setup_arch, which run before SMP is started */ +/* Changed in add_arg and setup_arch, which run before SMP is started */ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 }; static void __init add_arg(char *arg) @@ -56,17 +58,25 @@ static void __init add_arg(char *arg) strcat(command_line, arg); } -struct cpuinfo_um boot_cpu_data = { +/* + * These fields are initialized at boot time and not changed. + * XXX This structure is used only in the non-SMP case. Maybe this + * should be moved to smp.c. + */ +struct cpuinfo_um boot_cpu_data = { .loops_per_jiffy = 0, .ipi_pipe = { -1, -1 } }; unsigned long thread_saved_pc(struct task_struct *task) { - return(os_process_pc(CHOOSE_MODE_PROC(thread_pid_tt, thread_pid_skas, - task))); + return os_process_pc(CHOOSE_MODE_PROC(thread_pid_tt, thread_pid_skas, + task)); } +/* Changed in setup_arch, which is called in early boot */ +static char host_info[(__NEW_UTS_LEN + 1) * 5]; + static int show_cpuinfo(struct seq_file *m, void *v) { int index = 0; @@ -86,7 +96,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) loops_per_jiffy/(500000/HZ), (loops_per_jiffy/(5000/HZ)) % 100); - return(0); + return 0; } static void *c_start(struct seq_file *m, loff_t *pos) @@ -114,14 +124,12 @@ const struct seq_operations cpuinfo_op = { /* Set in linux_main */ unsigned long host_task_size; unsigned long task_size; - -unsigned long uml_start; - -/* Set in early boot */ unsigned long uml_physmem; -unsigned long uml_reserved; +unsigned long uml_reserved; /* Also modified in mem_init */ unsigned long start_vm; unsigned long end_vm; + +/* Set in uml_ncpus_setup */ int ncpus = 1; #ifdef CONFIG_CMDLINE_ON_HOST @@ -135,6 +143,8 @@ static char *argv1_end = NULL; /* Set in early boot */ static int have_root __initdata = 0; + +/* Set in uml_mem_setup and modified in linux_main */ long long physmem_size = 32 * 1024 * 1024; void set_cmdline(char *cmd) @@ -212,12 +222,12 @@ __uml_setup("debug", no_skas_debug_setup, #ifdef CONFIG_SMP static int __init uml_ncpus_setup(char *line, int *add) { - if (!sscanf(line, "%d", &ncpus)) { - printf("Couldn't parse [%s]\n", line); - return -1; - } + if (!sscanf(line, "%d", &ncpus)) { + printf("Couldn't parse [%s]\n", line); + return -1; + } - return 0; + return 0; } __uml_setup("ncpus=", uml_ncpus_setup, @@ -234,7 +244,7 @@ static int force_tt = 0; static int __init mode_tt_setup(char *line, int *add) { force_tt = 1; - return(0); + return 0; } #else @@ -245,7 +255,7 @@ static int __init mode_tt_setup(char *line, int *add) static int __init mode_tt_setup(char *line, int *add) { printf("CONFIG_MODE_TT disabled - 'mode=tt' ignored\n"); - return(0); + return 0; } #else @@ -256,7 +266,7 @@ static int __init mode_tt_setup(char *line, int *add) static int __init mode_tt_setup(char *line, int *add) { printf("CONFIG_MODE_SKAS disabled - 'mode=tt' redundant\n"); - return(0); + return 0; } #endif @@ -274,16 +284,15 @@ int mode_tt = DEFAULT_TT; static int __init Usage(char *line, int *add) { - const char **p; + const char **p; printf(usage_string, init_utsname()->release); - p = &__uml_help_start; - while (p < &__uml_help_end) { - printf("%s", *p); - p++; - } + p = &__uml_help_start; + while (p < &__uml_help_end) { + printf("%s", *p); + p++; + } exit(0); - return 0; } @@ -374,13 +383,12 @@ int __init linux_main(int argc, char **argv) printf("UML running in %s mode\n", mode); - uml_start = (unsigned long) &__binary_start; host_task_size = CHOOSE_MODE_PROC(set_task_sizes_tt, set_task_sizes_skas, &task_size); /* - * Setting up handlers to 'sig_info' struct - */ + * Setting up handlers to 'sig_info' struct + */ os_fill_handlinfo(handlinfo_kern); brk_start = (unsigned long) sbrk(0); @@ -396,7 +404,7 @@ int __init linux_main(int argc, char **argv) physmem_size += UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end); } - uml_physmem = uml_start & PAGE_MASK; + uml_physmem = (unsigned long) &__binary_start & PAGE_MASK; /* Reserve up to 4M after the current brk */ uml_reserved = ROUND_4M(brk_start) + (1 << 22); @@ -407,7 +415,7 @@ int __init linux_main(int argc, char **argv) argv1_begin = argv[1]; argv1_end = &argv[1][strlen(argv[1])]; #endif - + highmem = 0; iomem_size = (iomem_size + PAGE_SIZE - 1) & PAGE_MASK; max_physmem = get_kmem_end() - uml_physmem - iomem_size - MIN_VMALLOC; @@ -449,12 +457,12 @@ int __init linux_main(int argc, char **argv) printf("Kernel virtual memory size shrunk to %lu bytes\n", virtmem_size); - uml_postsetup(); + uml_postsetup(); - task_protections((unsigned long) &init_thread_info); + stack_protections((unsigned long) &init_thread_info); os_flush_stdout(); - return(CHOOSE_MODE(start_uml_tt(), start_uml_skas())); + return CHOOSE_MODE(start_uml_tt(), start_uml_skas()); } extern int uml_exitcode; @@ -466,8 +474,8 @@ static int panic_exit(struct notifier_block *self, unsigned long unused1, show_regs(&(current->thread.regs)); bust_spinlocks(0); uml_exitcode = 1; - machine_halt(); - return(0); + os_dump_core(); + return 0; } static struct notifier_block panic_exit_notifier = { @@ -482,14 +490,14 @@ void __init setup_arch(char **cmdline_p) &panic_exit_notifier); paging_init(); strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - setup_hostinfo(); + *cmdline_p = command_line; + setup_hostinfo(host_info, sizeof host_info); } void __init check_bugs(void) { arch_check_bugs(); - os_check_bugs(); + os_check_bugs(); } void apply_alternatives(struct alt_instr *start, struct alt_instr *end) diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index f6301274cf3c..bc59f97e34d0 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -59,6 +59,8 @@ SECTIONS { . = ALIGN(KERNEL_STACK_SIZE); /* init_task */ *(.data.init_task) + . = ALIGN(KERNEL_STACK_SIZE); + *(.data.init_irqstack) *(.data) *(.gnu.linkonce.d*) CONSTRUCTORS |
