diff options
Diffstat (limited to 'arch/um')
50 files changed, 713 insertions, 172 deletions
diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86 index 8aae429a56e2..21bebe63df66 100644 --- a/arch/um/Kconfig.x86 +++ b/arch/um/Kconfig.x86 @@ -1,3 +1,5 @@ +mainmenu "User Mode Linux/$SUBARCH $KERNELVERSION Kernel Configuration" + source "arch/um/Kconfig.common" menu "UML-specific options" @@ -8,6 +10,10 @@ config CMPXCHG_LOCAL bool default n +config CMPXCHG_DOUBLE + bool + default n + source "arch/x86/Kconfig.cpu" endmenu diff --git a/arch/um/Makefile b/arch/um/Makefile index fab8121d2b32..c0f712cc7c5f 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -41,7 +41,7 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH) KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\" \ $(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap \ -Din6addr_loopback=kernel_in6addr_loopback \ - -Din6addr_any=kernel_in6addr_any + -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr KBUILD_AFLAGS += $(ARCH_INCLUDE) diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c index 25e1965df7ce..d4191fe1cede 100644 --- a/arch/um/drivers/chan_kern.c +++ b/arch/um/drivers/chan_kern.c @@ -543,11 +543,10 @@ int parse_chan_pair(char *str, struct line *line, int device, const struct chan_opts *opts, char **error_out) { struct list_head *chans = &line->chan_list; - struct chan *new, *chan; + struct chan *new; char *in, *out; if (!list_empty(chans)) { - chan = list_entry(chans->next, struct chan, list); free_chan(chans, 0); INIT_LIST_HEAD(chans); } diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c index 93f227a25ba4..9cbb426c0b91 100644 --- a/arch/um/drivers/cow_user.c +++ b/arch/um/drivers/cow_user.c @@ -186,7 +186,11 @@ static int absolutize(char *to, int size, char *from) strcat(to, "/"); strcat(to, from); } - chdir(save_cwd); + if (chdir(save_cwd)) { + cow_printf("absolutize : Can't cd to '%s' - " + "errno = %d\n", save_cwd, errno); + return -1; + } return 0; } diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index b56f8e0196a9..84dce3fc590c 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -32,7 +32,7 @@ int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock) { struct dog_data data; int in_fds[2], out_fds[2], pid, n, err; - char pid_buf[sizeof("nnnnn\0")], c; + char pid_buf[sizeof("nnnnnnn\0")], c; char *pid_args[] = { "/usr/bin/uml_watchdog", "-pid", pid_buf, NULL }; char *mconsole_args[] = { "/usr/bin/uml_watchdog", "-mconsole", NULL, NULL }; diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 35dd0b86401a..364c8a15c4c3 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -176,10 +176,9 @@ void line_flush_buffer(struct tty_struct *tty) { struct line *line = tty->driver_data; unsigned long flags; - int err; spin_lock_irqsave(&line->lock, flags); - err = flush_buffer(line); + flush_buffer(line); spin_unlock_irqrestore(&line->lock, flags); } @@ -400,8 +399,8 @@ int line_setup_irq(int fd, int input, int output, struct line *line, void *data) * is done under a spinlock. Checking whether the device is in use is * line->tty->count > 1, also under the spinlock. * - * tty->count serves to decide whether the device should be enabled or - * disabled on the host. If it's equal to 1, then we are doing the + * line->count serves to decide whether the device should be enabled or + * disabled on the host. If it's equal to 0, then we are doing the * first open or last close. Otherwise, open and close just return. */ @@ -415,16 +414,16 @@ int line_open(struct line *lines, struct tty_struct *tty) goto out_unlock; err = 0; - if (tty->count > 1) + if (line->count++) goto out_unlock; - spin_unlock(&line->count_lock); - + BUG_ON(tty->driver_data); tty->driver_data = line; line->tty = tty; + spin_unlock(&line->count_lock); err = enable_chan(line); - if (err) + if (err) /* line_close() will be called by our caller */ return err; INIT_DELAYED_WORK(&line->task, line_timer_cb); @@ -437,7 +436,7 @@ int line_open(struct line *lines, struct tty_struct *tty) chan_window_size(&line->chan_list, &tty->winsize.ws_row, &tty->winsize.ws_col); - return err; + return 0; out_unlock: spin_unlock(&line->count_lock); @@ -461,17 +460,16 @@ void line_close(struct tty_struct *tty, struct file * filp) flush_buffer(line); spin_lock(&line->count_lock); - if (!line->valid) - goto out_unlock; + BUG_ON(!line->valid); - if (tty->count > 1) + if (--line->count) goto out_unlock; - spin_unlock(&line->count_lock); - line->tty = NULL; tty->driver_data = NULL; + spin_unlock(&line->count_lock); + if (line->sigio) { unregister_winch(tty); line->sigio = 0; @@ -499,7 +497,7 @@ static int setup_one_line(struct line *lines, int n, char *init, int init_prio, spin_lock(&line->count_lock); - if (line->tty != NULL) { + if (line->count) { *error_out = "Device is already open"; goto out; } @@ -723,41 +721,53 @@ struct winch { int pid; struct tty_struct *tty; unsigned long stack; + struct work_struct work; }; -static void free_winch(struct winch *winch, int free_irq_ok) +static void __free_winch(struct work_struct *work) { - if (free_irq_ok) - free_irq(WINCH_IRQ, winch); - - list_del(&winch->list); + struct winch *winch = container_of(work, struct winch, work); + free_irq(WINCH_IRQ, winch); if (winch->pid != -1) os_kill_process(winch->pid, 1); - if (winch->fd != -1) - os_close_file(winch->fd); if (winch->stack != 0) free_stack(winch->stack, 0); kfree(winch); } +static void free_winch(struct winch *winch) +{ + int fd = winch->fd; + winch->fd = -1; + if (fd != -1) + os_close_file(fd); + list_del(&winch->list); + __free_winch(&winch->work); +} + static irqreturn_t winch_interrupt(int irq, void *data) { struct winch *winch = data; struct tty_struct *tty; struct line *line; + int fd = winch->fd; int err; char c; - if (winch->fd != -1) { - err = generic_read(winch->fd, &c, NULL); + if (fd != -1) { + err = generic_read(fd, &c, NULL); if (err < 0) { if (err != -EAGAIN) { + winch->fd = -1; + list_del(&winch->list); + os_close_file(fd); printk(KERN_ERR "winch_interrupt : " "read failed, errno = %d\n", -err); printk(KERN_ERR "fd %d is losing SIGWINCH " "support\n", winch->tty_fd); - free_winch(winch, 0); + INIT_WORK(&winch->work, __free_winch); + schedule_work(&winch->work); return IRQ_HANDLED; } goto out; @@ -829,7 +839,7 @@ static void unregister_winch(struct tty_struct *tty) list_for_each_safe(ele, next, &winch_handlers) { winch = list_entry(ele, struct winch, list); if (winch->tty == tty) { - free_winch(winch, 1); + free_winch(winch); break; } } @@ -845,7 +855,7 @@ static void winch_cleanup(void) list_for_each_safe(ele, next, &winch_handlers) { winch = list_entry(ele, struct winch, list); - free_winch(winch, 1); + free_winch(winch); } spin_unlock(&winch_handler_lock); diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 47d0c37897d5..22745b47c829 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -262,6 +262,15 @@ static int uml_net_change_mtu(struct net_device *dev, int new_mtu) return 0; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void uml_net_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + uml_net_interrupt(dev->irq, dev); + enable_irq(dev->irq); +} +#endif + static void uml_net_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { @@ -364,6 +373,9 @@ static const struct net_device_ops uml_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = uml_net_change_mtu, .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = uml_net_poll_controller, +#endif }; /* diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c index 9415dd9e63ef..520118888f16 100644 --- a/arch/um/drivers/net_user.c +++ b/arch/um/drivers/net_user.c @@ -228,7 +228,10 @@ static void change(char *dev, char *what, unsigned char *addr, "buffer\n"); pid = change_tramp(argv, output, output_len); - if (pid < 0) return; + if (pid < 0) { + kfree(output); + return; + } if (output != NULL) { printk("%s", output); diff --git a/arch/um/drivers/slip_user.c b/arch/um/drivers/slip_user.c index a1c2d2c98a94..cbacfc4e63e6 100644 --- a/arch/um/drivers/slip_user.c +++ b/arch/um/drivers/slip_user.c @@ -102,7 +102,7 @@ static int slip_tramp(char **argv, int fd) "buffer\n"); os_kill_process(pid, 1); err = -ENOMEM; - goto out_free; + goto out_close; } close(fds[1]); @@ -112,7 +112,6 @@ static int slip_tramp(char **argv, int fd) err = helper_wait(pid); close(fds[0]); -out_free: kfree(output); return err; diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c index 8ac7146c237f..2e1de5728604 100644 --- a/arch/um/drivers/xterm.c +++ b/arch/um/drivers/xterm.c @@ -123,6 +123,7 @@ static int xterm_open(int input, int output, int primary, void *d, err = -errno; printk(UM_KERN_ERR "xterm_open : unlink failed, errno = %d\n", errno); + close(fd); return err; } close(fd); diff --git a/arch/um/include/asm/delay.h b/arch/um/include/asm/delay.h index c71e32b6741e..8a5576d8eda5 100644 --- a/arch/um/include/asm/delay.h +++ b/arch/um/include/asm/delay.h @@ -1,20 +1,18 @@ #ifndef __UM_DELAY_H #define __UM_DELAY_H -#define MILLION 1000000 - /* Undefined on purpose */ extern void __bad_udelay(void); +extern void __bad_ndelay(void); extern void __udelay(unsigned long usecs); +extern void __ndelay(unsigned long usecs); extern void __delay(unsigned long loops); #define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \ __bad_udelay() : __udelay(n)) -/* It appears that ndelay is not used at all for UML, and has never been - * implemented. */ -extern void __unimplemented_ndelay(void); -#define ndelay(n) __unimplemented_ndelay() +#define ndelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \ + __bad_ndelay() : __ndelay(n)) #endif diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h index b7c5bab9bd77..1a7d2757fe05 100644 --- a/arch/um/include/asm/ptrace-generic.h +++ b/arch/um/include/asm/ptrace-generic.h @@ -42,12 +42,6 @@ extern long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern unsigned long getreg(struct task_struct *child, int regno); extern int putreg(struct task_struct *child, int regno, unsigned long value); -extern int get_fpregs(struct user_i387_struct __user *buf, - struct task_struct *child); -extern int set_fpregs(struct user_i387_struct __user *buf, - struct task_struct *child); - -extern void show_regs(struct pt_regs *regs); extern int arch_copy_tls(struct task_struct *new); extern void clear_flushed_tls(struct task_struct *task); diff --git a/arch/um/include/shared/line.h b/arch/um/include/shared/line.h index 72f4f25af247..63df3ca02ac2 100644 --- a/arch/um/include/shared/line.h +++ b/arch/um/include/shared/line.h @@ -33,6 +33,7 @@ struct line_driver { struct line { struct tty_struct *tty; spinlock_t count_lock; + unsigned long count; int valid; char *init_str; diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h index b0b4589e0ebc..f1e0aa56c52a 100644 --- a/arch/um/include/shared/registers.h +++ b/arch/um/include/shared/registers.h @@ -16,7 +16,7 @@ extern int restore_fpx_registers(int pid, unsigned long *fp_regs); extern int save_registers(int pid, struct uml_pt_regs *regs); extern int restore_registers(int pid, struct uml_pt_regs *regs); extern int init_registers(int pid); -extern void get_safe_registers(unsigned long *regs); +extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs); extern unsigned long get_thread_reg(int reg, jmp_buf *buf); extern int get_fp_registers(int pid, unsigned long *regs); extern int put_fp_registers(int pid, unsigned long *regs); diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 09bd7b585726..939a4a67f0fd 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -38,7 +38,6 @@ void flush_thread(void) void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) { - set_fs(USER_DS); PT_REGS_IP(regs) = eip; PT_REGS_SP(regs) = esp; } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index fab4371184f6..21c1ae7c3d75 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -202,7 +202,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, arch_copy_thread(¤t->thread.arch, &p->thread.arch); } else { - get_safe_registers(p->thread.regs.regs.gp); + get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); p->thread.request.u.thread = current->thread.request.u.thread; handler = new_thread_handler; } diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c index 701b672c1122..c9da32b0c707 100644 --- a/arch/um/kernel/ptrace.c +++ b/arch/um/kernel/ptrace.c @@ -50,23 +50,11 @@ long arch_ptrace(struct task_struct *child, long request, void __user *vp = p; switch (request) { - /* read word at location addr. */ - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - ret = generic_ptrace_peekdata(child, addr, data); - break; - /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: ret = peek_user(child, addr, data); break; - /* write the word at location addr. */ - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - ret = generic_ptrace_pokedata(child, addr, data); - break; - /* write the word at location addr in the USER area */ case PTRACE_POKEUSR: ret = poke_user(child, addr, data); @@ -107,16 +95,6 @@ long arch_ptrace(struct task_struct *child, long request, break; } #endif -#ifdef PTRACE_GETFPREGS - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - ret = get_fpregs(vp, child); - break; -#endif -#ifdef PTRACE_SETFPREGS - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - ret = set_fpregs(vp, child); - break; -#endif case PTRACE_GET_THREAD_AREA: ret = ptrace_get_thread_area(child, addr, vp); break; @@ -154,12 +132,6 @@ long arch_ptrace(struct task_struct *child, long request, break; } #endif -#ifdef PTRACE_ARCH_PRCTL - case PTRACE_ARCH_PRCTL: - /* XXX Calls ptrace on the host - needs some SMP thinking */ - ret = arch_prctl(child, data, (void __user *) addr); - break; -#endif default: ret = ptrace_request(child, request, addr, data); if (ret == -EIO) diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 869bec9f2516..4d93dff6b371 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -20,9 +20,8 @@ static void kill_off_processes(void) os_kill_ptraced_process(userspace_pid[0], 1); else { struct task_struct *p; - int pid, me; + int pid; - me = os_getpid(); for_each_process(p) { if (p->mm == NULL) continue; diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index d66f0388f091..b33f4dfe7ae5 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -3,10 +3,12 @@ # Licensed under the GPL # -obj-y = aio.o elf_aux.o execvp.o file.o helper.o irq.o main.o mem.o process.o \ +obj-y = aio.o execvp.o file.o helper.o irq.o main.o mem.o process.o \ registers.o sigio.o signal.o start_up.o time.o tty.o uaccess.o \ umid.o tls.o user_syms.o util.o drivers/ sys-$(SUBARCH)/ skas/ +obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o + USER_OBJS := $(user-objs-y) aio.o elf_aux.o execvp.o file.o helper.o irq.o \ main.o mem.o process.o registers.o sigio.o signal.o start_up.o time.o \ tty.o tls.o uaccess.o umid.o util.o diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c index 608784d4ec57..953323799381 100644 --- a/arch/um/os-Linux/elf_aux.c +++ b/arch/um/os-Linux/elf_aux.c @@ -14,16 +14,11 @@ #include "mem_user.h" #include <kern_constants.h> -/* Use the one from the kernel - the host may miss it, if having old headers. */ -#if UM_ELF_CLASS == UM_ELFCLASS32 typedef Elf32_auxv_t elf_auxv_t; -#else -typedef Elf64_auxv_t elf_auxv_t; -#endif /* These are initialized very early in boot and never changed */ char * elf_aux_platform; -long elf_aux_hwcap; +extern long elf_aux_hwcap; unsigned long vsyscall_ehdr; unsigned long vsyscall_end; unsigned long __kernel_vsyscall; diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index b6b1096152aa..feff22d64672 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -28,14 +28,14 @@ static int helper_child(void *arg) { struct helper_data *data = arg; char **argv = data->argv; - int err; + int err, ret; if (data->pre_exec != NULL) (*data->pre_exec)(data->pre_data); err = execvp_noalloc(data->buf, argv[0], argv); /* If the exec succeeds, we don't get here */ - write(data->fd, &err, sizeof(err)); + CATCH_EINTR(ret = write(data->fd, &err, sizeof(err))); return 0; } diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index fb2a97a75fb1..8471b817d94f 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -21,6 +21,8 @@ #define STACKSIZE (8 * 1024 * 1024) #define THREAD_NAME_LEN (256) +long elf_aux_hwcap; + static void set_stklim(void) { struct rlimit lim; @@ -143,7 +145,9 @@ int __init main(int argc, char **argv, char **envp) install_fatal_handler(SIGINT); install_fatal_handler(SIGTERM); +#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA scan_elf_aux(envp); +#endif do_uml_initcalls(); ret = linux_main(argc, argv); diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index e696144d2be3..62878cf1d33f 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -176,7 +176,7 @@ static int __init make_tempfile(const char *template, char **out_tempname, find_tempdir(); if ((tempdir == NULL) || (strlen(tempdir) >= MAXPATHLEN)) - return -1; + goto out; if (template[0] != '/') strcpy(tempname, tempdir); @@ -191,13 +191,15 @@ static int __init make_tempfile(const char *template, char **out_tempname, } if (do_unlink && (unlink(tempname) < 0)) { perror("unlink"); - goto out; + goto close; } if (out_tempname) { *out_tempname = tempname; } else free(tempname); return fd; +close: + close(fd); out: free(tempname); return -1; diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c index 830fe6a1518a..b866b9e3bef9 100644 --- a/arch/um/os-Linux/registers.c +++ b/arch/um/os-Linux/registers.c @@ -8,6 +8,8 @@ #include <string.h> #include <sys/ptrace.h> #include "sysdep/ptrace.h" +#include "sysdep/ptrace_user.h" +#include "registers.h" int save_registers(int pid, struct uml_pt_regs *regs) { @@ -32,6 +34,7 @@ int restore_registers(int pid, struct uml_pt_regs *regs) /* This is set once at boot time and not changed thereafter */ static unsigned long exec_regs[MAX_REG_NR]; +static unsigned long exec_fp_regs[FP_SIZE]; int init_registers(int pid) { @@ -42,10 +45,14 @@ int init_registers(int pid) return -errno; arch_init_registers(pid); + get_fp_registers(pid, exec_fp_regs); return 0; } -void get_safe_registers(unsigned long *regs) +void get_safe_registers(unsigned long *regs, unsigned long *fp_regs) { memcpy(regs, exec_regs, sizeof(exec_regs)); + + if (fp_regs) + memcpy(fp_regs, exec_fp_regs, sizeof(exec_fp_regs)); } diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index d261f170d120..e771398be5f3 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -39,7 +39,7 @@ static unsigned long syscall_regs[MAX_REG_NR]; static int __init init_syscall_regs(void) { - get_safe_registers(syscall_regs); + get_safe_registers(syscall_regs, NULL); syscall_regs[REGS_IP_INDEX] = STUB_CODE + ((unsigned long) &batch_syscall_stub - (unsigned long) &__syscall_stub_start); diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index d6e0a2234b86..dee0e8cf8ad0 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -373,6 +373,9 @@ void userspace(struct uml_pt_regs *regs) if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) fatal_sigsegv(); + if (put_fp_registers(pid, regs->fp)) + fatal_sigsegv(); + /* Now we set local_using_sysemu to be used for one loop */ local_using_sysemu = get_using_sysemu(); @@ -399,6 +402,12 @@ void userspace(struct uml_pt_regs *regs) fatal_sigsegv(); } + if (get_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "userspace - get_fp_registers failed, " + "errno = %d\n", errno); + fatal_sigsegv(); + } + UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */ if (WIFSTOPPED(status)) { @@ -457,10 +466,11 @@ void userspace(struct uml_pt_regs *regs) } static unsigned long thread_regs[MAX_REG_NR]; +static unsigned long thread_fp_regs[FP_SIZE]; static int __init init_thread_regs(void) { - get_safe_registers(thread_regs); + get_safe_registers(thread_regs, thread_fp_regs); /* Set parent's instruction pointer to start of clone-stub */ thread_regs[REGS_IP_INDEX] = STUB_CODE + (unsigned long) stub_clone_handler - @@ -503,6 +513,13 @@ int copy_context_skas0(unsigned long new_stack, int pid) return err; } + err = put_fp_registers(pid, thread_fp_regs); + if (err < 0) { + printk(UM_KERN_ERR "copy_context_skas0 : put_fp_registers " + "failed, pid = %d, err = %d\n", pid, err); + return err; + } + /* set a well known return code for detection of child write failure */ child_data->err = 12345678; diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index 05f5ea8e83d2..45ffe46871e0 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -113,3 +113,8 @@ EXPORT_SYMBOL(__stack_smash_handler); extern long __guard __attribute__((weak)); EXPORT_SYMBOL(__guard); + +#ifdef _FORTIFY_SOURCE +extern int __sprintf_chk(char *str, int flag, size_t strlen, const char *format); +EXPORT_SYMBOL(__sprintf_chk); +#endif diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile index b1da91c1b200..3923cfb87649 100644 --- a/arch/um/sys-i386/Makefile +++ b/arch/um/sys-i386/Makefile @@ -4,11 +4,12 @@ obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \ ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \ - sys_call_table.o tls.o atomic64_cx8_32.o + sys_call_table.o tls.o atomic64_cx8_32.o mem.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o -subarch-obj-y = lib/semaphore_32.o lib/string_32.o +subarch-obj-y = lib/string_32.o +subarch-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += lib/rwsem.o subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem_32.o subarch-obj-$(CONFIG_MODULES) += kernel/module.o diff --git a/arch/um/sys-i386/asm/elf.h b/arch/um/sys-i386/asm/elf.h index d964a4111ac6..42305551d204 100644 --- a/arch/um/sys-i386/asm/elf.h +++ b/arch/um/sys-i386/asm/elf.h @@ -105,6 +105,8 @@ extern unsigned long __kernel_vsyscall; #define FIXADDR_USER_START VSYSCALL_BASE #define FIXADDR_USER_END VSYSCALL_END +#define __HAVE_ARCH_GATE_AREA 1 + /* * Architecture-neutral AT_ values in 0-17, leave some room * for more of them, start the x86-specific ones at 32. diff --git a/arch/um/sys-i386/asm/ptrace.h b/arch/um/sys-i386/asm/ptrace.h index 0273e4d09af7..5d2a59112537 100644 --- a/arch/um/sys-i386/asm/ptrace.h +++ b/arch/um/sys-i386/asm/ptrace.h @@ -42,11 +42,6 @@ */ struct user_desc; -extern int get_fpxregs(struct user_fxsr_struct __user *buf, - struct task_struct *child); -extern int set_fpxregs(struct user_fxsr_struct __user *buf, - struct task_struct *tsk); - extern int ptrace_get_thread_area(struct task_struct *child, int idx, struct user_desc __user *user_desc); diff --git a/arch/um/sys-i386/delay.c b/arch/um/sys-i386/delay.c index d623e074f41d..f3fe1a688f7e 100644 --- a/arch/um/sys-i386/delay.c +++ b/arch/um/sys-i386/delay.c @@ -1,29 +1,60 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * Mostly copied from arch/x86/lib/delay.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + #include <linux/module.h> #include <linux/kernel.h> #include <linux/delay.h> #include <asm/param.h> -void __delay(unsigned long time) +void __delay(unsigned long loops) { - /* Stolen from the i386 __loop_delay */ - int d0; - __asm__ __volatile__( - "\tjmp 1f\n" + asm volatile( + "test %0,%0\n" + "jz 3f\n" + "jmp 1f\n" + ".align 16\n" - "1:\tjmp 2f\n" + "1: jmp 2f\n" + ".align 16\n" - "2:\tdecl %0\n\tjns 2b" - :"=&a" (d0) - :"0" (time)); + "2: dec %0\n" + " jnz 2b\n" + "3: dec %0\n" + + : /* we don't need output */ + : "a" (loops) + ); } +EXPORT_SYMBOL(__delay); -void __udelay(unsigned long usecs) +inline void __const_udelay(unsigned long xloops) { - int i, n; + int d0; - n = (loops_per_jiffy * HZ * usecs) / MILLION; - for(i=0;i<n;i++) - cpu_relax(); + xloops *= 4; + asm("mull %%edx" + : "=d" (xloops), "=&a" (d0) + : "1" (xloops), "0" + (loops_per_jiffy * (HZ/4))); + + __delay(++xloops); } +EXPORT_SYMBOL(__const_udelay); +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ +} EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); diff --git a/arch/um/sys-i386/mem.c b/arch/um/sys-i386/mem.c new file mode 100644 index 000000000000..639900a6fde9 --- /dev/null +++ b/arch/um/sys-i386/mem.c @@ -0,0 +1,62 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/mm.h> +#include <asm/page.h> +#include <asm/mman.h> + +static struct vm_area_struct gate_vma; + +static int __init gate_vma_init(void) +{ + if (!FIXADDR_USER_START) + return 0; + + gate_vma.vm_mm = NULL; + gate_vma.vm_start = FIXADDR_USER_START; + gate_vma.vm_end = FIXADDR_USER_END; + gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + gate_vma.vm_page_prot = __P101; + + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + gate_vma.vm_flags |= VM_ALWAYSDUMP; + + return 0; +} +__initcall(gate_vma_init); + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return FIXADDR_USER_START ? &gate_vma : NULL; +} + +int in_gate_area_no_mm(unsigned long addr) +{ + if (!FIXADDR_USER_START) + return 0; + + if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) + return 1; + + return 0; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = get_gate_vma(mm); + + if (!vma) + return 0; + + return (addr >= vma->vm_start) && (addr < vma->vm_end); +} diff --git a/arch/um/sys-i386/ptrace.c b/arch/um/sys-i386/ptrace.c index d23b2d3ea384..3375c2717851 100644 --- a/arch/um/sys-i386/ptrace.c +++ b/arch/um/sys-i386/ptrace.c @@ -145,7 +145,7 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long __user *) data); } -int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_i387_struct fpregs; @@ -161,7 +161,7 @@ int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) return n; } -int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_i387_struct fpregs; @@ -174,7 +174,7 @@ int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) (unsigned long *) &fpregs); } -int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) +static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_fxsr_struct fpregs; @@ -190,7 +190,7 @@ int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) return n; } -int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) +static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_fxsr_struct fpregs; @@ -206,5 +206,23 @@ int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { - return -EIO; + int ret = -EIO; + void __user *datap = (void __user *) data; + switch (request) { + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + ret = get_fpregs(datap, child); + break; + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + ret = set_fpregs(datap, child); + break; + case PTRACE_GETFPXREGS: /* Get the child FPU state. */ + ret = get_fpxregs(datap, child); + break; + case PTRACE_SETFPXREGS: /* Set the child FPU state. */ + ret = set_fpxregs(datap, child); + break; + default: + ret = -EIO; + } + return ret; } diff --git a/arch/um/sys-i386/shared/sysdep/ptrace.h b/arch/um/sys-i386/shared/sysdep/ptrace.h index d50e62e07070..c398a5076111 100644 --- a/arch/um/sys-i386/shared/sysdep/ptrace.h +++ b/arch/um/sys-i386/shared/sysdep/ptrace.h @@ -53,6 +53,7 @@ extern int sysemu_supported; struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; + unsigned long fp[HOST_FPX_SIZE]; struct faultinfo faultinfo; long syscall; int is_user; diff --git a/arch/um/sys-i386/signal.c b/arch/um/sys-i386/signal.c index 129647375a6c..89a46626bfd8 100644 --- a/arch/um/sys-i386/signal.c +++ b/arch/um/sys-i386/signal.c @@ -58,7 +58,7 @@ static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave) unsigned long ret = 0xffff0000; int i; -#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16); +#define FPREG_ADDR(f, n) ((char *)&(f)->st_space + (n) * 16) for (i = 0; i < 8; i++) { if (twd & 0x1) { diff --git a/arch/um/sys-x86_64/Makefile b/arch/um/sys-x86_64/Makefile index c1ea9eb04466..bd4d1d3ba919 100644 --- a/arch/um/sys-x86_64/Makefile +++ b/arch/um/sys-x86_64/Makefile @@ -4,12 +4,14 @@ # Licensed under the GPL # -obj-y = bug.o bugs.o delay.o fault.o ldt.o mem.o ptrace.o ptrace_user.o \ +obj-y = bug.o bugs.o delay.o fault.o ldt.o ptrace.o ptrace_user.o mem.o \ setjmp.o signal.o stub.o stub_segv.o syscalls.o syscall_table.o \ sysrq.o ksyms.o tls.o +obj-y += vdso/ + subarch-obj-y = lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o \ - lib/rwsem_64.o + lib/rwsem.o subarch-obj-$(CONFIG_MODULES) += kernel/module.o ldt-y = ../sys-i386/ldt.o diff --git a/arch/um/sys-x86_64/asm/elf.h b/arch/um/sys-x86_64/asm/elf.h index d6d5af376251..11a2bfb38859 100644 --- a/arch/um/sys-x86_64/asm/elf.h +++ b/arch/um/sys-x86_64/asm/elf.h @@ -119,4 +119,14 @@ extern long elf_aux_hwcap; #define SET_PERSONALITY(ex) do ; while(0) +#define __HAVE_ARCH_GATE_AREA 1 +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 +struct linux_binprm; +extern int arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); + +extern unsigned long um_vdso_addr; +#define AT_SYSINFO_EHDR 33 +#define ARCH_DLINFO NEW_AUX_ENT(AT_SYSINFO_EHDR, um_vdso_addr) + #endif diff --git a/arch/um/sys-x86_64/delay.c b/arch/um/sys-x86_64/delay.c index dee5be66da82..f3fe1a688f7e 100644 --- a/arch/um/sys-x86_64/delay.c +++ b/arch/um/sys-x86_64/delay.c @@ -1,30 +1,60 @@ /* - * Copyright 2003 PathScale, Inc. - * Copied from arch/x86_64 + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * Mostly copied from arch/x86/lib/delay.c * - * Licensed under the GPL + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. */ #include <linux/module.h> +#include <linux/kernel.h> #include <linux/delay.h> -#include <asm/processor.h> #include <asm/param.h> void __delay(unsigned long loops) { - unsigned long i; + asm volatile( + "test %0,%0\n" + "jz 3f\n" + "jmp 1f\n" - for(i = 0; i < loops; i++) - cpu_relax(); + ".align 16\n" + "1: jmp 2f\n" + + ".align 16\n" + "2: dec %0\n" + " jnz 2b\n" + "3: dec %0\n" + + : /* we don't need output */ + : "a" (loops) + ); } +EXPORT_SYMBOL(__delay); -void __udelay(unsigned long usecs) +inline void __const_udelay(unsigned long xloops) { - unsigned long i, n; + int d0; - n = (loops_per_jiffy * HZ * usecs) / MILLION; - for(i=0;i<n;i++) - cpu_relax(); + xloops *= 4; + asm("mull %%edx" + : "=d" (xloops), "=&a" (d0) + : "1" (xloops), "0" + (loops_per_jiffy * (HZ/4))); + + __delay(++xloops); } +EXPORT_SYMBOL(__const_udelay); +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ +} EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); diff --git a/arch/um/sys-x86_64/mem.c b/arch/um/sys-x86_64/mem.c index 3f8df8abf347..546518727a73 100644 --- a/arch/um/sys-x86_64/mem.c +++ b/arch/um/sys-x86_64/mem.c @@ -1,16 +1,26 @@ -/* - * Copyright 2003 PathScale, Inc. - * - * Licensed under the GPL - */ - #include "linux/mm.h" #include "asm/page.h" #include "asm/mman.h" -unsigned long vm_stack_flags = __VM_STACK_FLAGS; -unsigned long vm_stack_flags32 = __VM_STACK_FLAGS; -unsigned long vm_data_default_flags = __VM_DATA_DEFAULT_FLAGS; -unsigned long vm_data_default_flags32 = __VM_DATA_DEFAULT_FLAGS; -unsigned long vm_force_exec32 = PROT_EXEC; +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_mm && vma->vm_start == um_vdso_addr) + return "[vdso]"; + + return NULL; +} + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return NULL; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + return 0; +} +int in_gate_area_no_mm(unsigned long addr) +{ + return 0; +} diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/um/sys-x86_64/ptrace.c index f43613643cdb..4005506834fd 100644 --- a/arch/um/sys-x86_64/ptrace.c +++ b/arch/um/sys-x86_64/ptrace.c @@ -145,7 +145,7 @@ int is_syscall(unsigned long addr) return instr == 0x050f; } -int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; long fpregs[HOST_FP_SIZE]; @@ -162,7 +162,7 @@ int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) return n; } -int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; long fpregs[HOST_FP_SIZE]; @@ -182,12 +182,16 @@ long subarch_ptrace(struct task_struct *child, long request, void __user *datap = (void __user *) data; switch (request) { - case PTRACE_GETFPXREGS: /* Get the child FPU state. */ + case PTRACE_GETFPREGS: /* Get the child FPU state. */ ret = get_fpregs(datap, child); break; - case PTRACE_SETFPXREGS: /* Set the child FPU state. */ + case PTRACE_SETFPREGS: /* Set the child FPU state. */ ret = set_fpregs(datap, child); break; + case PTRACE_ARCH_PRCTL: + /* XXX Calls ptrace on the host - needs some SMP thinking */ + ret = arch_prctl(child, data, (void __user *) addr); + break; } return ret; diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace.h b/arch/um/sys-x86_64/shared/sysdep/ptrace.h index fdba5457947a..8ee8f8e12af1 100644 --- a/arch/um/sys-x86_64/shared/sysdep/ptrace.h +++ b/arch/um/sys-x86_64/shared/sysdep/ptrace.h @@ -85,6 +85,7 @@ struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; + unsigned long fp[HOST_FP_SIZE]; struct faultinfo faultinfo; long syscall; int is_user; diff --git a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h b/arch/um/sys-x86_64/shared/sysdep/vm-flags.h index 3213edfa7888..3978e55132d2 100644 --- a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h +++ b/arch/um/sys-x86_64/shared/sysdep/vm-flags.h @@ -7,27 +7,9 @@ #ifndef __VM_FLAGS_X86_64_H #define __VM_FLAGS_X86_64_H -#define __VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define __VM_STACK_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \ - VM_EXEC | VM_MAYREAD | VM_MAYWRITE | \ - VM_MAYEXEC) - -extern unsigned long vm_stack_flags, vm_stack_flags32; -extern unsigned long vm_data_default_flags, vm_data_default_flags32; -extern unsigned long vm_force_exec32; - -#ifdef TIF_IA32 -#define VM_DATA_DEFAULT_FLAGS \ - (test_thread_flag(TIF_IA32) ? vm_data_default_flags32 : \ - vm_data_default_flags) - -#define VM_STACK_DEFAULT_FLAGS \ - (test_thread_flag(TIF_IA32) ? vm_stack_flags32 : vm_stack_flags) -#endif - -#define VM_DATA_DEFAULT_FLAGS vm_data_default_flags - -#define VM_STACK_DEFAULT_FLAGS vm_stack_flags +#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \ + VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #endif diff --git a/arch/um/sys-x86_64/vdso/Makefile b/arch/um/sys-x86_64/vdso/Makefile new file mode 100644 index 000000000000..5dffe6d46686 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/Makefile @@ -0,0 +1,90 @@ +# +# Building vDSO images for x86. +# + +VDSO64-y := y + +vdso-install-$(VDSO64-y) += vdso.so + + +# files to link into the vdso +vobjs-y := vdso-note.o um_vdso.o + +# files to link into kernel +obj-$(VDSO64-y) += vdso.o vma.o + +vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) + +$(obj)/vdso.o: $(obj)/vdso.so + +targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) + +export CPPFLAGS_vdso.lds += -P -C + +VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ + -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 + +$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so + +$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE + $(call if_changed,vdso) + +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# +# Don't omit frame pointers for ease of userspace debugging, but do +# optimize sibling calls. +# +CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ + $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + -fno-omit-frame-pointer -foptimize-sibling-calls + +$(vobjs): KBUILD_CFLAGS += $(CFL) + +# +# vDSO code runs in userspace and -pg doesn't help with profiling anyway. +# +CFLAGS_REMOVE_vdso-note.o = -pg +CFLAGS_REMOVE_um_vdso.o = -pg + +targets += vdso-syms.lds +obj-$(VDSO64-y) += vdso-syms.lds + +# +# Match symbols in the DSO that look like VDSO*; produce a file of constants. +# +sed-vdsosym := -e 's/^00*/0/' \ + -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' +quiet_cmd_vdsosym = VDSOSYM $@ +define cmd_vdsosym + $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ +endef + +$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE + $(call if_changed,vdsosym) + +# +# The DSO images are built using a special linker script. +# +quiet_cmd_vdso = VDSO $@ + cmd_vdso = $(CC) -nostdlib -o $@ \ + $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ + -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' + +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +GCOV_PROFILE := n + +# +# Install the unstripped copy of vdso*.so listed in $(vdso-install-y). +# +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ +$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) + +PHONY += vdso_install $(vdso-install-y) +vdso_install: $(vdso-install-y) diff --git a/arch/um/sys-x86_64/vdso/checkundef.sh b/arch/um/sys-x86_64/vdso/checkundef.sh new file mode 100644 index 000000000000..7ee90a9b549d --- /dev/null +++ b/arch/um/sys-x86_64/vdso/checkundef.sh @@ -0,0 +1,10 @@ +#!/bin/sh +nm="$1" +file="$2" +$nm "$file" | grep '^ *U' > /dev/null 2>&1 +if [ $? -eq 1 ]; then + exit 0 +else + echo "$file: undefined symbols found" >&2 + exit 1 +fi diff --git a/arch/um/sys-x86_64/vdso/um_vdso.c b/arch/um/sys-x86_64/vdso/um_vdso.c new file mode 100644 index 000000000000..7c441b59d375 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/um_vdso.c @@ -0,0 +1,71 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This vDSO turns all calls into a syscall so that UML can trap them. + */ + + +/* Disable profiling for userspace code */ +#define DISABLE_BRANCH_PROFILING + +#include <linux/time.h> +#include <linux/getcpu.h> +#include <asm/unistd.h> + +int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + + return ret; +} +int clock_gettime(clockid_t, struct timespec *) + __attribute__((weak, alias("__vdso_clock_gettime"))); + +int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + + return ret; +} +int gettimeofday(struct timeval *, struct timezone *) + __attribute__((weak, alias("__vdso_gettimeofday"))); + +time_t __vdso_time(time_t *t) +{ + long secs; + + asm volatile("syscall" + : "=a" (secs) + : "0" (__NR_time), "D" (t) : "cc", "r11", "cx", "memory"); + + return secs; +} +int time(time_t *t) __attribute__((weak, alias("__vdso_time"))); + +long +__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +{ + /* + * UML does not support SMP, we can cheat here. :) + */ + + if (cpu) + *cpu = 0; + if (node) + *node = 0; + + return 0; +} + +long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) + __attribute__((weak, alias("__vdso_getcpu"))); diff --git a/arch/um/sys-x86_64/vdso/vdso-layout.lds.S b/arch/um/sys-x86_64/vdso/vdso-layout.lds.S new file mode 100644 index 000000000000..634a2cf62046 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso-layout.lds.S @@ -0,0 +1,64 @@ +/* + * Linker script for vDSO. This is an ELF shared object prelinked to + * its virtual address, and with only one read-only segment. + * This script controls its layout. + */ + +SECTIONS +{ + . = VDSO_PRELINK + SIZEOF_HEADERS; + + .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + + .dynamic : { *(.dynamic) } :text :dynamic + + .rodata : { *(.rodata*) } :text + .data : { + *(.data*) + *(.sdata*) + *(.got.plt) *(.got) + *(.gnu.linkonce.d.*) + *(.bss*) + *(.dynbss*) + *(.gnu.linkonce.b.*) + } + + .altinstructions : { *(.altinstructions) } + .altinstr_replacement : { *(.altinstr_replacement) } + + /* + * Align the actual code well away from the non-instruction data. + * This is the best thing for the I-cache. + */ + . = ALIGN(0x100); + + .text : { *(.text*) } :text =0x90909090 +} + +/* + * Very old versions of ld do not recognize this name token; use the constant. + */ +#define PT_GNU_EH_FRAME 0x6474e550 + +/* + * We must supply the ELF program headers explicitly to get just one + * PT_LOAD segment, and set the flags explicitly to make segments read-only. + */ +PHDRS +{ + text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + note PT_NOTE FLAGS(4); /* PF_R */ + eh_frame_hdr PT_GNU_EH_FRAME; +} diff --git a/arch/um/sys-x86_64/vdso/vdso-note.S b/arch/um/sys-x86_64/vdso/vdso-note.S new file mode 100644 index 000000000000..79a071e4357e --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso-note.S @@ -0,0 +1,12 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> +#include <linux/elfnote.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/um/sys-x86_64/vdso/vdso.S b/arch/um/sys-x86_64/vdso/vdso.S new file mode 100644 index 000000000000..ec82c1686bd6 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso.S @@ -0,0 +1,10 @@ +#include <linux/init.h> + +__INITDATA + + .globl vdso_start, vdso_end +vdso_start: + .incbin "arch/um/sys-x86_64/vdso/vdso.so" +vdso_end: + +__FINIT diff --git a/arch/um/sys-x86_64/vdso/vdso.lds.S b/arch/um/sys-x86_64/vdso/vdso.lds.S new file mode 100644 index 000000000000..b96b2677cad8 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vdso.lds.S @@ -0,0 +1,32 @@ +/* + * Linker script for 64-bit vDSO. + * We #include the file to define the layout details. + * Here we only choose the prelinked virtual address. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. We can define local symbols here called VDSO* to make their + * values visible using the asm-x86/vdso.h macros from the kernel proper. + */ + +#define VDSO_PRELINK 0xffffffffff700000 +#include "vdso-layout.lds.S" + +/* + * This controls what userland symbols we export from the vDSO. + */ +VERSION { + LINUX_2.6 { + global: + clock_gettime; + __vdso_clock_gettime; + gettimeofday; + __vdso_gettimeofday; + getcpu; + __vdso_getcpu; + time; + __vdso_time; + local: *; + }; +} + +VDSO64_PRELINK = VDSO_PRELINK; diff --git a/arch/um/sys-x86_64/vdso/vma.c b/arch/um/sys-x86_64/vdso/vma.c new file mode 100644 index 000000000000..9495c8d0ce37 --- /dev/null +++ b/arch/um/sys-x86_64/vdso/vma.c @@ -0,0 +1,74 @@ +/* + * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <asm/page.h> +#include <linux/init.h> + +unsigned int __read_mostly vdso_enabled = 1; +unsigned long um_vdso_addr; + +extern unsigned long task_size; +extern char vdso_start[], vdso_end[]; + +static struct page **vdsop; + +static int __init init_vdso(void) +{ + struct page *um_vdso; + + BUG_ON(vdso_end - vdso_start > PAGE_SIZE); + + um_vdso_addr = task_size - PAGE_SIZE; + + vdsop = kmalloc(GFP_KERNEL, sizeof(struct page *)); + if (!vdsop) + goto oom; + + um_vdso = alloc_page(GFP_KERNEL); + if (!um_vdso) { + kfree(vdsop); + + goto oom; + } + + copy_page(page_address(um_vdso), vdso_start); + *vdsop = um_vdso; + + return 0; + +oom: + printk(KERN_ERR "Cannot allocate vdso\n"); + vdso_enabled = 0; + + return -ENOMEM; +} +subsys_initcall(init_vdso); + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + int err; + struct mm_struct *mm = current->mm; + + if (!vdso_enabled) + return 0; + + down_write(&mm->mmap_sem); + + err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| + VM_ALWAYSDUMP, + vdsop); + + up_write(&mm->mmap_sem); + + return err; +} |