From 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 16 Apr 2005 15:20:36 -0700 Subject: Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip! --- kernel/Makefile | 53 + kernel/acct.c | 561 +++++ kernel/audit.c | 839 ++++++++ kernel/auditsc.c | 1015 +++++++++ kernel/capability.c | 220 ++ kernel/compat.c | 860 ++++++++ kernel/configs.c | 118 ++ kernel/cpu.c | 193 ++ kernel/cpuset.c | 1564 ++++++++++++++ kernel/dma.c | 158 ++ kernel/exec_domain.c | 209 ++ kernel/exit.c | 1527 ++++++++++++++ kernel/extable.c | 67 + kernel/fork.c | 1274 ++++++++++++ kernel/futex.c | 798 ++++++++ kernel/intermodule.c | 182 ++ kernel/irq/Makefile | 5 + kernel/irq/autoprobe.c | 189 ++ kernel/irq/handle.c | 193 ++ kernel/irq/internals.h | 18 + kernel/irq/manage.c | 349 ++++ kernel/irq/proc.c | 159 ++ kernel/irq/spurious.c | 96 + kernel/itimer.c | 241 +++ kernel/kallsyms.c | 411 ++++ kernel/kfifo.c | 168 ++ kernel/kmod.c | 256 +++ kernel/kprobes.c | 157 ++ kernel/ksysfs.c | 57 + kernel/kthread.c | 202 ++ kernel/module.c | 2108 +++++++++++++++++++ kernel/panic.c | 157 ++ kernel/params.c | 721 +++++++ kernel/pid.c | 292 +++ kernel/posix-cpu-timers.c | 1559 ++++++++++++++ kernel/posix-timers.c | 1584 ++++++++++++++ kernel/power/Kconfig | 74 + kernel/power/Makefile | 11 + kernel/power/console.c | 58 + kernel/power/disk.c | 431 ++++ kernel/power/main.c | 269 +++ kernel/power/pm.c | 265 +++ kernel/power/power.h | 52 + kernel/power/poweroff.c | 45 + kernel/power/process.c | 121 ++ kernel/power/smp.c | 85 + kernel/power/swsusp.c | 1433 +++++++++++++ kernel/printk.c | 996 +++++++++ kernel/profile.c | 563 +++++ kernel/ptrace.c | 389 ++++ kernel/rcupdate.c | 470 +++++ kernel/resource.c | 551 +++++ kernel/sched.c | 5004 +++++++++++++++++++++++++++++++++++++++++++++ kernel/seccomp.c | 56 + kernel/signal.c | 2662 ++++++++++++++++++++++++ kernel/softirq.c | 496 +++++ kernel/spinlock.c | 371 ++++ kernel/stop_machine.c | 212 ++ kernel/sys.c | 1725 ++++++++++++++++ kernel/sys_ni.c | 86 + kernel/sysctl.c | 2337 +++++++++++++++++++++ kernel/time.c | 599 ++++++ kernel/timer.c | 1611 +++++++++++++++ kernel/uid16.c | 196 ++ kernel/user.c | 189 ++ kernel/wait.c | 246 +++ kernel/workqueue.c | 555 +++++ 67 files changed, 40718 insertions(+) create mode 100644 kernel/Makefile create mode 100644 kernel/acct.c create mode 100644 kernel/audit.c create mode 100644 kernel/auditsc.c create mode 100644 kernel/capability.c create mode 100644 kernel/compat.c create mode 100644 kernel/configs.c create mode 100644 kernel/cpu.c create mode 100644 kernel/cpuset.c create mode 100644 kernel/dma.c create mode 100644 kernel/exec_domain.c create mode 100644 kernel/exit.c create mode 100644 kernel/extable.c create mode 100644 kernel/fork.c create mode 100644 kernel/futex.c create mode 100644 kernel/intermodule.c create mode 100644 kernel/irq/Makefile create mode 100644 kernel/irq/autoprobe.c create mode 100644 kernel/irq/handle.c create mode 100644 kernel/irq/internals.h create mode 100644 kernel/irq/manage.c create mode 100644 kernel/irq/proc.c create mode 100644 kernel/irq/spurious.c create mode 100644 kernel/itimer.c create mode 100644 kernel/kallsyms.c create mode 100644 kernel/kfifo.c create mode 100644 kernel/kmod.c create mode 100644 kernel/kprobes.c create mode 100644 kernel/ksysfs.c create mode 100644 kernel/kthread.c create mode 100644 kernel/module.c create mode 100644 kernel/panic.c create mode 100644 kernel/params.c create mode 100644 kernel/pid.c create mode 100644 kernel/posix-cpu-timers.c create mode 100644 kernel/posix-timers.c create mode 100644 kernel/power/Kconfig create mode 100644 kernel/power/Makefile create mode 100644 kernel/power/console.c create mode 100644 kernel/power/disk.c create mode 100644 kernel/power/main.c create mode 100644 kernel/power/pm.c create mode 100644 kernel/power/power.h create mode 100644 kernel/power/poweroff.c create mode 100644 kernel/power/process.c create mode 100644 kernel/power/smp.c create mode 100644 kernel/power/swsusp.c create mode 100644 kernel/printk.c create mode 100644 kernel/profile.c create mode 100644 kernel/ptrace.c create mode 100644 kernel/rcupdate.c create mode 100644 kernel/resource.c create mode 100644 kernel/sched.c create mode 100644 kernel/seccomp.c create mode 100644 kernel/signal.c create mode 100644 kernel/softirq.c create mode 100644 kernel/spinlock.c create mode 100644 kernel/stop_machine.c create mode 100644 kernel/sys.c create mode 100644 kernel/sys_ni.c create mode 100644 kernel/sysctl.c create mode 100644 kernel/time.c create mode 100644 kernel/timer.c create mode 100644 kernel/uid16.c create mode 100644 kernel/user.c create mode 100644 kernel/wait.c create mode 100644 kernel/workqueue.c (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile new file mode 100644 index 000000000000..eb88b446c2cc --- /dev/null +++ b/kernel/Makefile @@ -0,0 +1,53 @@ +# +# Makefile for the linux kernel. +# + +obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ + exit.o itimer.o time.o softirq.o resource.o \ + sysctl.o capability.o ptrace.o timer.o user.o \ + signal.o sys.o kmod.o workqueue.o pid.o \ + rcupdate.o intermodule.o extable.o params.o posix-timers.o \ + kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o + +obj-$(CONFIG_FUTEX) += futex.o +obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o +obj-$(CONFIG_SMP) += cpu.o spinlock.o +obj-$(CONFIG_UID16) += uid16.o +obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_KALLSYMS) += kallsyms.o +obj-$(CONFIG_PM) += power/ +obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o +obj-$(CONFIG_COMPAT) += compat.o +obj-$(CONFIG_CPUSETS) += cpuset.o +obj-$(CONFIG_IKCONFIG) += configs.o +obj-$(CONFIG_IKCONFIG_PROC) += configs.o +obj-$(CONFIG_STOP_MACHINE) += stop_machine.o +obj-$(CONFIG_AUDIT) += audit.o +obj-$(CONFIG_AUDITSYSCALL) += auditsc.o +obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_SYSFS) += ksysfs.o +obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ +obj-$(CONFIG_SECCOMP) += seccomp.o + +ifneq ($(CONFIG_IA64),y) +# According to Alan Modra , the -fno-omit-frame-pointer is +# needed for x86 only. Why this used to be enabled for all architectures is beyond +# me. I suspect most platforms don't need this, but until we know that for sure +# I turn this off for IA-64 only. Andreas Schwab says it's also needed on m68k +# to get a correct value for the wait-channel (WCHAN in ps). --davidm +CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer +endif + +$(obj)/configs.o: $(obj)/config_data.h + +# config_data.h contains the same information as ikconfig.h but gzipped. +# Info from config_data can be extracted from /proc/config* +targets += config_data.gz +$(obj)/config_data.gz: .config FORCE + $(call if_changed,gzip) + +quiet_cmd_ikconfiggz = IKCFG $@ + cmd_ikconfiggz = (echo "static const char kernel_config_data[] = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@ +targets += config_data.h +$(obj)/config_data.h: $(obj)/config_data.gz FORCE + $(call if_changed,ikconfiggz) diff --git a/kernel/acct.c b/kernel/acct.c new file mode 100644 index 000000000000..4168f631868e --- /dev/null +++ b/kernel/acct.c @@ -0,0 +1,561 @@ +/* + * linux/kernel/acct.c + * + * BSD Process Accounting for Linux + * + * Author: Marco van Wieringen + * + * Some code based on ideas and code from: + * Thomas K. Dyas + * + * This file implements BSD-style process accounting. Whenever any + * process exits, an accounting record of type "struct acct" is + * written to the file specified with the acct() system call. It is + * up to user-level programs to do useful things with the accounting + * log. The kernel just provides the raw accounting information. + * + * (C) Copyright 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V. + * + * Plugged two leaks. 1) It didn't return acct_file into the free_filps if + * the file happened to be read-only. 2) If the accounting was suspended + * due to the lack of space it happily allowed to reopen it and completely + * lost the old acct_file. 3/10/98, Al Viro. + * + * Now we silently close acct_file on attempt to reopen. Cleaned sys_acct(). + * XTerms and EMACS are manifestations of pure evil. 21/10/98, AV. + * + * Fixed a nasty interaction with with sys_umount(). If the accointing + * was suspeneded we failed to stop it on umount(). Messy. + * Another one: remount to readonly didn't stop accounting. + * Question: what should we do if we have CAP_SYS_ADMIN but not + * CAP_SYS_PACCT? Current code does the following: umount returns -EBUSY + * unless we are messing with the root. In that case we are getting a + * real mess with do_remount_sb(). 9/11/98, AV. + * + * Fixed a bunch of races (and pair of leaks). Probably not the best way, + * but this one obviously doesn't introduce deadlocks. Later. BTW, found + * one race (and leak) in BSD implementation. + * OK, that's better. ANOTHER race and leak in BSD variant. There always + * is one more bug... 10/11/98, AV. + * + * Oh, fsck... Oopsable SMP race in do_process_acct() - we must hold + * ->mmap_sem to walk the vma list of current->mm. Nasty, since it leaks + * a struct file opened for write. Fixed. 2/6/2000, AV. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* sector_div */ + +/* + * These constants control the amount of freespace that suspend and + * resume the process accounting system, and the time delay between + * each check. + * Turned into sysctl-controllable parameters. AV, 12/11/98 + */ + +int acct_parm[3] = {4, 2, 30}; +#define RESUME (acct_parm[0]) /* >foo% free space - resume */ +#define SUSPEND (acct_parm[1]) /* f_dentry->d_inode->i_sb, &sbuf)) + return res; + suspend = sbuf.f_blocks * SUSPEND; + resume = sbuf.f_blocks * RESUME; + + sector_div(suspend, 100); + sector_div(resume, 100); + + if (sbuf.f_bavail <= suspend) + act = -1; + else if (sbuf.f_bavail >= resume) + act = 1; + else + act = 0; + + /* + * If some joker switched acct_globals.file under us we'ld better be + * silent and _not_ touch anything. + */ + spin_lock(&acct_globals.lock); + if (file != acct_globals.file) { + if (act) + res = act>0; + goto out; + } + + if (acct_globals.active) { + if (act < 0) { + acct_globals.active = 0; + printk(KERN_INFO "Process accounting paused\n"); + } + } else { + if (act > 0) { + acct_globals.active = 1; + printk(KERN_INFO "Process accounting resumed\n"); + } + } + + del_timer(&acct_globals.timer); + acct_globals.needcheck = 0; + acct_globals.timer.expires = jiffies + ACCT_TIMEOUT*HZ; + add_timer(&acct_globals.timer); + res = acct_globals.active; +out: + spin_unlock(&acct_globals.lock); + return res; +} + +/* + * Close the old accouting file (if currently open) and then replace + * it with file (if non-NULL). + * + * NOTE: acct_globals.lock MUST be held on entry and exit. + */ +static void acct_file_reopen(struct file *file) +{ + struct file *old_acct = NULL; + + if (acct_globals.file) { + old_acct = acct_globals.file; + del_timer(&acct_globals.timer); + acct_globals.active = 0; + acct_globals.needcheck = 0; + acct_globals.file = NULL; + } + if (file) { + acct_globals.file = file; + acct_globals.needcheck = 0; + acct_globals.active = 1; + /* It's been deleted if it was used before so this is safe */ + init_timer(&acct_globals.timer); + acct_globals.timer.function = acct_timeout; + acct_globals.timer.expires = jiffies + ACCT_TIMEOUT*HZ; + add_timer(&acct_globals.timer); + } + if (old_acct) { + spin_unlock(&acct_globals.lock); + do_acct_process(0, old_acct); + filp_close(old_acct, NULL); + spin_lock(&acct_globals.lock); + } +} + +/* + * sys_acct() is the only system call needed to implement process + * accounting. It takes the name of the file where accounting records + * should be written. If the filename is NULL, accounting will be + * shutdown. + */ +asmlinkage long sys_acct(const char __user *name) +{ + struct file *file = NULL; + char *tmp; + int error; + + if (!capable(CAP_SYS_PACCT)) + return -EPERM; + + if (name) { + tmp = getname(name); + if (IS_ERR(tmp)) { + return (PTR_ERR(tmp)); + } + /* Difference from BSD - they don't do O_APPEND */ + file = filp_open(tmp, O_WRONLY|O_APPEND, 0); + putname(tmp); + if (IS_ERR(file)) { + return (PTR_ERR(file)); + } + if (!S_ISREG(file->f_dentry->d_inode->i_mode)) { + filp_close(file, NULL); + return (-EACCES); + } + + if (!file->f_op->write) { + filp_close(file, NULL); + return (-EIO); + } + } + + error = security_acct(file); + if (error) { + if (file) + filp_close(file, NULL); + return error; + } + + spin_lock(&acct_globals.lock); + acct_file_reopen(file); + spin_unlock(&acct_globals.lock); + + return (0); +} + +/* + * If the accouting is turned on for a file in the filesystem pointed + * to by sb, turn accouting off. + */ +void acct_auto_close(struct super_block *sb) +{ + spin_lock(&acct_globals.lock); + if (acct_globals.file && + acct_globals.file->f_dentry->d_inode->i_sb == sb) { + acct_file_reopen((struct file *)NULL); + } + spin_unlock(&acct_globals.lock); +} + +/* + * encode an unsigned long into a comp_t + * + * This routine has been adopted from the encode_comp_t() function in + * the kern_acct.c file of the FreeBSD operating system. The encoding + * is a 13-bit fraction with a 3-bit (base 8) exponent. + */ + +#define MANTSIZE 13 /* 13 bit mantissa. */ +#define EXPSIZE 3 /* Base 8 (3 bit) exponent. */ +#define MAXFRACT ((1 << MANTSIZE) - 1) /* Maximum fractional value. */ + +static comp_t encode_comp_t(unsigned long value) +{ + int exp, rnd; + + exp = rnd = 0; + while (value > MAXFRACT) { + rnd = value & (1 << (EXPSIZE - 1)); /* Round up? */ + value >>= EXPSIZE; /* Base 8 exponent == 3 bit shift. */ + exp++; + } + + /* + * If we need to round up, do it (and handle overflow correctly). + */ + if (rnd && (++value > MAXFRACT)) { + value >>= EXPSIZE; + exp++; + } + + /* + * Clean it up and polish it off. + */ + exp <<= MANTSIZE; /* Shift the exponent into place */ + exp += value; /* and add on the mantissa. */ + return exp; +} + +#if ACCT_VERSION==1 || ACCT_VERSION==2 +/* + * encode an u64 into a comp2_t (24 bits) + * + * Format: 5 bit base 2 exponent, 20 bits mantissa. + * The leading bit of the mantissa is not stored, but implied for + * non-zero exponents. + * Largest encodable value is 50 bits. + */ + +#define MANTSIZE2 20 /* 20 bit mantissa. */ +#define EXPSIZE2 5 /* 5 bit base 2 exponent. */ +#define MAXFRACT2 ((1ul << MANTSIZE2) - 1) /* Maximum fractional value. */ +#define MAXEXP2 ((1 < (MAXFRACT2>>1)); + rnd = 0; + while (value > MAXFRACT2) { + rnd = value & 1; + value >>= 1; + exp++; + } + + /* + * If we need to round up, do it (and handle overflow correctly). + */ + if (rnd && (++value > MAXFRACT2)) { + value >>= 1; + exp++; + } + + if (exp > MAXEXP2) { + /* Overflow. Return largest representable number instead. */ + return (1ul << (MANTSIZE2+EXPSIZE2-1)) - 1; + } else { + return (value & (MAXFRACT2>>1)) | (exp << (MANTSIZE2-1)); + } +} +#endif + +#if ACCT_VERSION==3 +/* + * encode an u64 into a 32 bit IEEE float + */ +static u32 encode_float(u64 value) +{ + unsigned exp = 190; + unsigned u; + + if (value==0) return 0; + while ((s64)value > 0){ + value <<= 1; + exp--; + } + u = (u32)(value >> 40) & 0x7fffffu; + return u | (exp << 23); +} +#endif + +/* + * Write an accounting entry for an exiting process + * + * The acct_process() call is the workhorse of the process + * accounting system. The struct acct is built here and then written + * into the accounting file. This function should only be called from + * do_exit(). + */ + +/* + * do_acct_process does all actual work. Caller holds the reference to file. + */ +static void do_acct_process(long exitcode, struct file *file) +{ + acct_t ac; + mm_segment_t fs; + unsigned long vsize; + unsigned long flim; + u64 elapsed; + u64 run_time; + struct timespec uptime; + + /* + * First check to see if there is enough free_space to continue + * the process accounting system. + */ + if (!check_free_space(file)) + return; + + /* + * Fill the accounting struct with the needed info as recorded + * by the different kernel functions. + */ + memset((caddr_t)&ac, 0, sizeof(acct_t)); + + ac.ac_version = ACCT_VERSION | ACCT_BYTEORDER; + strlcpy(ac.ac_comm, current->comm, sizeof(ac.ac_comm)); + + /* calculate run_time in nsec*/ + do_posix_clock_monotonic_gettime(&uptime); + run_time = (u64)uptime.tv_sec*NSEC_PER_SEC + uptime.tv_nsec; + run_time -= (u64)current->start_time.tv_sec*NSEC_PER_SEC + + current->start_time.tv_nsec; + /* convert nsec -> AHZ */ + elapsed = nsec_to_AHZ(run_time); +#if ACCT_VERSION==3 + ac.ac_etime = encode_float(elapsed); +#else + ac.ac_etime = encode_comp_t(elapsed < (unsigned long) -1l ? + (unsigned long) elapsed : (unsigned long) -1l); +#endif +#if ACCT_VERSION==1 || ACCT_VERSION==2 + { + /* new enlarged etime field */ + comp2_t etime = encode_comp2_t(elapsed); + ac.ac_etime_hi = etime >> 16; + ac.ac_etime_lo = (u16) etime; + } +#endif + do_div(elapsed, AHZ); + ac.ac_btime = xtime.tv_sec - elapsed; + ac.ac_utime = encode_comp_t(jiffies_to_AHZ( + current->signal->utime + + current->group_leader->utime)); + ac.ac_stime = encode_comp_t(jiffies_to_AHZ( + current->signal->stime + + current->group_leader->stime)); + /* we really need to bite the bullet and change layout */ + ac.ac_uid = current->uid; + ac.ac_gid = current->gid; +#if ACCT_VERSION==2 + ac.ac_ahz = AHZ; +#endif +#if ACCT_VERSION==1 || ACCT_VERSION==2 + /* backward-compatible 16 bit fields */ + ac.ac_uid16 = current->uid; + ac.ac_gid16 = current->gid; +#endif +#if ACCT_VERSION==3 + ac.ac_pid = current->tgid; + ac.ac_ppid = current->parent->tgid; +#endif + + read_lock(&tasklist_lock); /* pin current->signal */ + ac.ac_tty = current->signal->tty ? + old_encode_dev(tty_devnum(current->signal->tty)) : 0; + read_unlock(&tasklist_lock); + + ac.ac_flag = 0; + if (current->flags & PF_FORKNOEXEC) + ac.ac_flag |= AFORK; + if (current->flags & PF_SUPERPRIV) + ac.ac_flag |= ASU; + if (current->flags & PF_DUMPCORE) + ac.ac_flag |= ACORE; + if (current->flags & PF_SIGNALED) + ac.ac_flag |= AXSIG; + + vsize = 0; + if (current->mm) { + struct vm_area_struct *vma; + down_read(¤t->mm->mmap_sem); + vma = current->mm->mmap; + while (vma) { + vsize += vma->vm_end - vma->vm_start; + vma = vma->vm_next; + } + up_read(¤t->mm->mmap_sem); + } + vsize = vsize / 1024; + ac.ac_mem = encode_comp_t(vsize); + ac.ac_io = encode_comp_t(0 /* current->io_usage */); /* %% */ + ac.ac_rw = encode_comp_t(ac.ac_io / 1024); + ac.ac_minflt = encode_comp_t(current->signal->min_flt + + current->group_leader->min_flt); + ac.ac_majflt = encode_comp_t(current->signal->maj_flt + + current->group_leader->maj_flt); + ac.ac_swaps = encode_comp_t(0); + ac.ac_exitcode = exitcode; + + /* + * Kernel segment override to datasegment and write it + * to the accounting file. + */ + fs = get_fs(); + set_fs(KERNEL_DS); + /* + * Accounting records are not subject to resource limits. + */ + flim = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; + file->f_op->write(file, (char *)&ac, + sizeof(acct_t), &file->f_pos); + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; + set_fs(fs); +} + +/* + * acct_process - now just a wrapper around do_acct_process + */ +void acct_process(long exitcode) +{ + struct file *file = NULL; + + /* + * accelerate the common fastpath: + */ + if (!acct_globals.file) + return; + + spin_lock(&acct_globals.lock); + file = acct_globals.file; + if (unlikely(!file)) { + spin_unlock(&acct_globals.lock); + return; + } + get_file(file); + spin_unlock(&acct_globals.lock); + + do_acct_process(exitcode, file); + fput(file); +} + + +/* + * acct_update_integrals + * - update mm integral fields in task_struct + */ +void acct_update_integrals(struct task_struct *tsk) +{ + if (likely(tsk->mm)) { + long delta = tsk->stime - tsk->acct_stimexpd; + + if (delta == 0) + return; + tsk->acct_stimexpd = tsk->stime; + tsk->acct_rss_mem1 += delta * get_mm_counter(tsk->mm, rss); + tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; + } +} + +/* + * acct_clear_integrals + * - clear the mm integral fields in task_struct + */ +void acct_clear_integrals(struct task_struct *tsk) +{ + if (tsk) { + tsk->acct_stimexpd = 0; + tsk->acct_rss_mem1 = 0; + tsk->acct_vm_mem1 = 0; + } +} diff --git a/kernel/audit.c b/kernel/audit.c new file mode 100644 index 000000000000..0f84dd7af2c8 --- /dev/null +++ b/kernel/audit.c @@ -0,0 +1,839 @@ +/* audit.c -- Auditing support -*- linux-c -*- + * Gateway between the kernel (e.g., selinux) and the user-space audit daemon. + * System-call specific features have moved to auditsc.c + * + * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Written by Rickard E. (Rik) Faith + * + * Goals: 1) Integrate fully with SELinux. + * 2) Minimal run-time overhead: + * a) Minimal when syscall auditing is disabled (audit_enable=0). + * b) Small when syscall auditing is enabled and no audit record + * is generated (defer as much work as possible to record + * generation time): + * i) context is allocated, + * ii) names from getname are stored without a copy, and + * iii) inode information stored from path_lookup. + * 3) Ability to disable syscall auditing at boot time (audit=0). + * 4) Usable by other parts of the kernel (if audit_log* is called, + * then a syscall record will be generated automatically for the + * current syscall). + * 5) Netlink interface to user-space. + * 6) Support low-overhead kernel-based filtering to minimize the + * information that must be passed to user-space. + * + * Example user-space utilities: http://people.redhat.com/faith/audit/ + */ + +#include +#include +#include +#include +#include + +#include + +#include +#include +#include + +/* No auditing will take place until audit_initialized != 0. + * (Initialization happens after skb_init is called.) */ +static int audit_initialized; + +/* No syscall auditing will take place unless audit_enabled != 0. */ +int audit_enabled; + +/* Default state when kernel boots without any parameters. */ +static int audit_default; + +/* If auditing cannot proceed, audit_failure selects what happens. */ +static int audit_failure = AUDIT_FAIL_PRINTK; + +/* If audit records are to be written to the netlink socket, audit_pid + * contains the (non-zero) pid. */ +static int audit_pid; + +/* If audit_limit is non-zero, limit the rate of sending audit records + * to that number per second. This prevents DoS attacks, but results in + * audit records being dropped. */ +static int audit_rate_limit; + +/* Number of outstanding audit_buffers allowed. */ +static int audit_backlog_limit = 64; +static atomic_t audit_backlog = ATOMIC_INIT(0); + +/* Records can be lost in several ways: + 0) [suppressed in audit_alloc] + 1) out of memory in audit_log_start [kmalloc of struct audit_buffer] + 2) out of memory in audit_log_move [alloc_skb] + 3) suppressed due to audit_rate_limit + 4) suppressed due to audit_backlog_limit +*/ +static atomic_t audit_lost = ATOMIC_INIT(0); + +/* The netlink socket. */ +static struct sock *audit_sock; + +/* There are two lists of audit buffers. The txlist contains audit + * buffers that cannot be sent immediately to the netlink device because + * we are in an irq context (these are sent later in a tasklet). + * + * The second list is a list of pre-allocated audit buffers (if more + * than AUDIT_MAXFREE are in use, the audit buffer is freed instead of + * being placed on the freelist). */ +static DEFINE_SPINLOCK(audit_txlist_lock); +static DEFINE_SPINLOCK(audit_freelist_lock); +static int audit_freelist_count = 0; +static LIST_HEAD(audit_txlist); +static LIST_HEAD(audit_freelist); + +/* There are three lists of rules -- one to search at task creation + * time, one to search at syscall entry time, and another to search at + * syscall exit time. */ +static LIST_HEAD(audit_tsklist); +static LIST_HEAD(audit_entlist); +static LIST_HEAD(audit_extlist); + +/* The netlink socket is only to be read by 1 CPU, which lets us assume + * that list additions and deletions never happen simultaneiously in + * auditsc.c */ +static DECLARE_MUTEX(audit_netlink_sem); + +/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting + * audit records. Since printk uses a 1024 byte buffer, this buffer + * should be at least that large. */ +#define AUDIT_BUFSIZ 1024 + +/* AUDIT_MAXFREE is the number of empty audit_buffers we keep on the + * audit_freelist. Doing so eliminates many kmalloc/kfree calls. */ +#define AUDIT_MAXFREE (2*NR_CPUS) + +/* The audit_buffer is used when formatting an audit record. The caller + * locks briefly to get the record off the freelist or to allocate the + * buffer, and locks briefly to send the buffer to the netlink layer or + * to place it on a transmit queue. Multiple audit_buffers can be in + * use simultaneously. */ +struct audit_buffer { + struct list_head list; + struct sk_buff_head sklist; /* formatted skbs ready to send */ + struct audit_context *ctx; /* NULL or associated context */ + int len; /* used area of tmp */ + char tmp[AUDIT_BUFSIZ]; + + /* Pointer to header and contents */ + struct nlmsghdr *nlh; + int total; + int type; + int pid; + int count; /* Times requeued */ +}; + +void audit_set_type(struct audit_buffer *ab, int type) +{ + ab->type = type; +} + +struct audit_entry { + struct list_head list; + struct audit_rule rule; +}; + +static void audit_log_end_irq(struct audit_buffer *ab); +static void audit_log_end_fast(struct audit_buffer *ab); + +static void audit_panic(const char *message) +{ + switch (audit_failure) + { + case AUDIT_FAIL_SILENT: + break; + case AUDIT_FAIL_PRINTK: + printk(KERN_ERR "audit: %s\n", message); + break; + case AUDIT_FAIL_PANIC: + panic("audit: %s\n", message); + break; + } +} + +static inline int audit_rate_check(void) +{ + static unsigned long last_check = 0; + static int messages = 0; + static DEFINE_SPINLOCK(lock); + unsigned long flags; + unsigned long now; + unsigned long elapsed; + int retval = 0; + + if (!audit_rate_limit) return 1; + + spin_lock_irqsave(&lock, flags); + if (++messages < audit_rate_limit) { + retval = 1; + } else { + now = jiffies; + elapsed = now - last_check; + if (elapsed > HZ) { + last_check = now; + messages = 0; + retval = 1; + } + } + spin_unlock_irqrestore(&lock, flags); + + return retval; +} + +/* Emit at least 1 message per second, even if audit_rate_check is + * throttling. */ +void audit_log_lost(const char *message) +{ + static unsigned long last_msg = 0; + static DEFINE_SPINLOCK(lock); + unsigned long flags; + unsigned long now; + int print; + + atomic_inc(&audit_lost); + + print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit); + + if (!print) { + spin_lock_irqsave(&lock, flags); + now = jiffies; + if (now - last_msg > HZ) { + print = 1; + last_msg = now; + } + spin_unlock_irqrestore(&lock, flags); + } + + if (print) { + printk(KERN_WARNING + "audit: audit_lost=%d audit_backlog=%d" + " audit_rate_limit=%d audit_backlog_limit=%d\n", + atomic_read(&audit_lost), + atomic_read(&audit_backlog), + audit_rate_limit, + audit_backlog_limit); + audit_panic(message); + } + +} + +static int audit_set_rate_limit(int limit) +{ + int old = audit_rate_limit; + audit_rate_limit = limit; + audit_log(current->audit_context, "audit_rate_limit=%d old=%d", + audit_rate_limit, old); + return old; +} + +static int audit_set_backlog_limit(int limit) +{ + int old = audit_backlog_limit; + audit_backlog_limit = limit; + audit_log(current->audit_context, "audit_backlog_limit=%d old=%d", + audit_backlog_limit, old); + return old; +} + +static int audit_set_enabled(int state) +{ + int old = audit_enabled; + if (state != 0 && state != 1) + return -EINVAL; + audit_enabled = state; + audit_log(current->audit_context, "audit_enabled=%d old=%d", + audit_enabled, old); + return old; +} + +static int audit_set_failure(int state) +{ + int old = audit_failure; + if (state != AUDIT_FAIL_SILENT + && state != AUDIT_FAIL_PRINTK + && state != AUDIT_FAIL_PANIC) + return -EINVAL; + audit_failure = state; + audit_log(current->audit_context, "audit_failure=%d old=%d", + audit_failure, old); + return old; +} + +#ifdef CONFIG_NET +void audit_send_reply(int pid, int seq, int type, int done, int multi, + void *payload, int size) +{ + struct sk_buff *skb; + struct nlmsghdr *nlh; + int len = NLMSG_SPACE(size); + void *data; + int flags = multi ? NLM_F_MULTI : 0; + int t = done ? NLMSG_DONE : type; + + skb = alloc_skb(len, GFP_KERNEL); + if (!skb) + goto nlmsg_failure; + + nlh = NLMSG_PUT(skb, pid, seq, t, len - sizeof(*nlh)); + nlh->nlmsg_flags = flags; + data = NLMSG_DATA(nlh); + memcpy(data, payload, size); + netlink_unicast(audit_sock, skb, pid, MSG_DONTWAIT); + return; + +nlmsg_failure: /* Used by NLMSG_PUT */ + if (skb) + kfree_skb(skb); +} + +/* + * Check for appropriate CAP_AUDIT_ capabilities on incoming audit + * control messages. + */ +static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type) +{ + int err = 0; + + switch (msg_type) { + case AUDIT_GET: + case AUDIT_LIST: + case AUDIT_SET: + case AUDIT_ADD: + case AUDIT_DEL: + if (!cap_raised(eff_cap, CAP_AUDIT_CONTROL)) + err = -EPERM; + break; + case AUDIT_USER: + if (!cap_raised(eff_cap, CAP_AUDIT_WRITE)) + err = -EPERM; + break; + default: /* bad msg */ + err = -EINVAL; + } + + return err; +} + +static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + u32 uid, pid, seq; + void *data; + struct audit_status *status_get, status_set; + int err; + struct audit_buffer *ab; + u16 msg_type = nlh->nlmsg_type; + + err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type); + if (err) + return err; + + pid = NETLINK_CREDS(skb)->pid; + uid = NETLINK_CREDS(skb)->uid; + seq = nlh->nlmsg_seq; + data = NLMSG_DATA(nlh); + + switch (msg_type) { + case AUDIT_GET: + status_set.enabled = audit_enabled; + status_set.failure = audit_failure; + status_set.pid = audit_pid; + status_set.rate_limit = audit_rate_limit; + status_set.backlog_limit = audit_backlog_limit; + status_set.lost = atomic_read(&audit_lost); + status_set.backlog = atomic_read(&audit_backlog); + audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_GET, 0, 0, + &status_set, sizeof(status_set)); + break; + case AUDIT_SET: + if (nlh->nlmsg_len < sizeof(struct audit_status)) + return -EINVAL; + status_get = (struct audit_status *)data; + if (status_get->mask & AUDIT_STATUS_ENABLED) { + err = audit_set_enabled(status_get->enabled); + if (err < 0) return err; + } + if (status_get->mask & AUDIT_STATUS_FAILURE) { + err = audit_set_failure(status_get->failure); + if (err < 0) return err; + } + if (status_get->mask & AUDIT_STATUS_PID) { + int old = audit_pid; + audit_pid = status_get->pid; + audit_log(current->audit_context, + "audit_pid=%d old=%d", audit_pid, old); + } + if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) + audit_set_rate_limit(status_get->rate_limit); + if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT) + audit_set_backlog_limit(status_get->backlog_limit); + break; + case AUDIT_USER: + ab = audit_log_start(NULL); + if (!ab) + break; /* audit_panic has been called */ + audit_log_format(ab, + "user pid=%d uid=%d length=%d msg='%.1024s'", + pid, uid, + (int)(nlh->nlmsg_len + - ((char *)data - (char *)nlh)), + (char *)data); + ab->type = AUDIT_USER; + ab->pid = pid; + audit_log_end(ab); + break; + case AUDIT_ADD: + case AUDIT_DEL: + if (nlh->nlmsg_len < sizeof(struct audit_rule)) + return -EINVAL; + /* fallthrough */ + case AUDIT_LIST: +#ifdef CONFIG_AUDITSYSCALL + err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid, + uid, seq, data); +#else + err = -EOPNOTSUPP; +#endif + break; + default: + err = -EINVAL; + break; + } + + return err < 0 ? err : 0; +} + +/* Get message from skb (based on rtnetlink_rcv_skb). Each message is + * processed by audit_receive_msg. Malformed skbs with wrong length are + * discarded silently. */ +static int audit_receive_skb(struct sk_buff *skb) +{ + int err; + struct nlmsghdr *nlh; + u32 rlen; + + while (skb->len >= NLMSG_SPACE(0)) { + nlh = (struct nlmsghdr *)skb->data; + if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) + return 0; + rlen = NLMSG_ALIGN(nlh->nlmsg_len); + if (rlen > skb->len) + rlen = skb->len; + if ((err = audit_receive_msg(skb, nlh))) { + netlink_ack(skb, nlh, err); + } else if (nlh->nlmsg_flags & NLM_F_ACK) + netlink_ack(skb, nlh, 0); + skb_pull(skb, rlen); + } + return 0; +} + +/* Receive messages from netlink socket. */ +static void audit_receive(struct sock *sk, int length) +{ + struct sk_buff *skb; + + if (down_trylock(&audit_netlink_sem)) + return; + + /* FIXME: this must not cause starvation */ + while ((skb = skb_dequeue(&sk->sk_receive_queue))) { + if (audit_receive_skb(skb) && skb->len) + skb_queue_head(&sk->sk_receive_queue, skb); + else + kfree_skb(skb); + } + up(&audit_netlink_sem); +} + +/* Move data from tmp buffer into an skb. This is an extra copy, and + * that is unfortunate. However, the copy will only occur when a record + * is being written to user space, which is already a high-overhead + * operation. (Elimination of the copy is possible, for example, by + * writing directly into a pre-allocated skb, at the cost of wasting + * memory. */ +static void audit_log_move(struct audit_buffer *ab) +{ + struct sk_buff *skb; + char *start; + int extra = ab->nlh ? 0 : NLMSG_SPACE(0); + + /* possible resubmission */ + if (ab->len == 0) + return; + + skb = skb_peek(&ab->sklist); + if (!skb || skb_tailroom(skb) <= ab->len + extra) { + skb = alloc_skb(2 * ab->len + extra, GFP_ATOMIC); + if (!skb) { + ab->len = 0; /* Lose information in ab->tmp */ + audit_log_lost("out of memory in audit_log_move"); + return; + } + __skb_queue_tail(&ab->sklist, skb); + if (!ab->nlh) + ab->nlh = (struct nlmsghdr *)skb_put(skb, + NLMSG_SPACE(0)); + } + start = skb_put(skb, ab->len); + memcpy(start, ab->tmp, ab->len); + ab->len = 0; +} + +/* Iterate over the skbuff in the audit_buffer, sending their contents + * to user space. */ +static inline int audit_log_drain(struct audit_buffer *ab) +{ + struct sk_buff *skb; + + while ((skb = skb_dequeue(&ab->sklist))) { + int retval = 0; + + if (audit_pid) { + if (ab->nlh) { + ab->nlh->nlmsg_len = ab->total; + ab->nlh->nlmsg_type = ab->type; + ab->nlh->nlmsg_flags = 0; + ab->nlh->nlmsg_seq = 0; + ab->nlh->nlmsg_pid = ab->pid; + } + skb_get(skb); /* because netlink_* frees */ + retval = netlink_unicast(audit_sock, skb, audit_pid, + MSG_DONTWAIT); + } + if (retval == -EAGAIN && ab->count < 5) { + ++ab->count; + skb_queue_tail(&ab->sklist, skb); + audit_log_end_irq(ab); + return 1; + } + if (retval < 0) { + if (retval == -ECONNREFUSED) { + printk(KERN_ERR + "audit: *NO* daemon at audit_pid=%d\n", + audit_pid); + audit_pid = 0; + } else + audit_log_lost("netlink socket too busy"); + } + if (!audit_pid) { /* No daemon */ + int offset = ab->nlh ? NLMSG_SPACE(0) : 0; + int len = skb->len - offset; + printk(KERN_ERR "%*.*s\n", + len, len, skb->data + offset); + } + kfree_skb(skb); + ab->nlh = NULL; + } + return 0; +} + +/* Initialize audit support at boot time. */ +static int __init audit_init(void) +{ + printk(KERN_INFO "audit: initializing netlink socket (%s)\n", + audit_default ? "enabled" : "disabled"); + audit_sock = netlink_kernel_create(NETLINK_AUDIT, audit_receive); + if (!audit_sock) + audit_panic("cannot initialize netlink socket"); + + audit_initialized = 1; + audit_enabled = audit_default; + audit_log(NULL, "initialized"); + return 0; +} + +#else +/* Without CONFIG_NET, we have no skbuffs. For now, print what we have + * in the buffer. */ +static void audit_log_move(struct audit_buffer *ab) +{ + printk(KERN_ERR "%*.*s\n", ab->len, ab->len, ab->tmp); + ab->len = 0; +} + +static inline int audit_log_drain(struct audit_buffer *ab) +{ + return 0; +} + +/* Initialize audit support at boot time. */ +int __init audit_init(void) +{ + printk(KERN_INFO "audit: initializing WITHOUT netlink support\n"); + audit_sock = NULL; + audit_pid = 0; + + audit_initialized = 1; + audit_enabled = audit_default; + audit_log(NULL, "initialized"); + return 0; +} +#endif + +__initcall(audit_init); + +/* Process kernel command-line parameter at boot time. audit=0 or audit=1. */ +static int __init audit_enable(char *str) +{ + audit_default = !!simple_strtol(str, NULL, 0); + printk(KERN_INFO "audit: %s%s\n", + audit_default ? "enabled" : "disabled", + audit_initialized ? "" : " (after initialization)"); + if (audit_initialized) + audit_enabled = audit_default; + return 0; +} + +__setup("audit=", audit_enable); + + +/* Obtain an audit buffer. This routine does locking to obtain the + * audit buffer, but then no locking is required for calls to + * audit_log_*format. If the tsk is a task that is currently in a + * syscall, then the syscall is marked as auditable and an audit record + * will be written at syscall exit. If there is no associated task, tsk + * should be NULL. */ +struct audit_buffer *audit_log_start(struct audit_context *ctx) +{ + struct audit_buffer *ab = NULL; + unsigned long flags; + struct timespec t; + int serial = 0; + + if (!audit_initialized) + return NULL; + + if (audit_backlog_limit + && atomic_read(&audit_backlog) > audit_backlog_limit) { + if (audit_rate_check()) + printk(KERN_WARNING + "audit: audit_backlog=%d > " + "audit_backlog_limit=%d\n", + atomic_read(&audit_backlog), + audit_backlog_limit); + audit_log_lost("backlog limit exceeded"); + return NULL; + } + + spin_lock_irqsave(&audit_freelist_lock, flags); + if (!list_empty(&audit_freelist)) { + ab = list_entry(audit_freelist.next, + struct audit_buffer, list); + list_del(&ab->list); + --audit_freelist_count; + } + spin_unlock_irqrestore(&audit_freelist_lock, flags); + + if (!ab) + ab = kmalloc(sizeof(*ab), GFP_ATOMIC); + if (!ab) { + audit_log_lost("out of memory in audit_log_start"); + return NULL; + } + + atomic_inc(&audit_backlog); + skb_queue_head_init(&ab->sklist); + + ab->ctx = ctx; + ab->len = 0; + ab->nlh = NULL; + ab->total = 0; + ab->type = AUDIT_KERNEL; + ab->pid = 0; + ab->count = 0; + +#ifdef CONFIG_AUDITSYSCALL + if (ab->ctx) + audit_get_stamp(ab->ctx, &t, &serial); + else +#endif + t = CURRENT_TIME; + + audit_log_format(ab, "audit(%lu.%03lu:%u): ", + t.tv_sec, t.tv_nsec/1000000, serial); + return ab; +} + + +/* Format an audit message into the audit buffer. If there isn't enough + * room in the audit buffer, more room will be allocated and vsnprint + * will be called a second time. Currently, we assume that a printk + * can't format message larger than 1024 bytes, so we don't either. */ +static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, + va_list args) +{ + int len, avail; + + if (!ab) + return; + + avail = sizeof(ab->tmp) - ab->len; + if (avail <= 0) { + audit_log_move(ab); + avail = sizeof(ab->tmp) - ab->len; + } + len = vsnprintf(ab->tmp + ab->len, avail, fmt, args); + if (len >= avail) { + /* The printk buffer is 1024 bytes long, so if we get + * here and AUDIT_BUFSIZ is at least 1024, then we can + * log everything that printk could have logged. */ + audit_log_move(ab); + avail = sizeof(ab->tmp) - ab->len; + len = vsnprintf(ab->tmp + ab->len, avail, fmt, args); + } + ab->len += (len < avail) ? len : avail; + ab->total += (len < avail) ? len : avail; +} + +/* Format a message into the audit buffer. All the work is done in + * audit_log_vformat. */ +void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) +{ + va_list args; + + if (!ab) + return; + va_start(args, fmt); + audit_log_vformat(ab, fmt, args); + va_end(args); +} + +/* This is a helper-function to print the d_path without using a static + * buffer or allocating another buffer in addition to the one in + * audit_buffer. */ +void audit_log_d_path(struct audit_buffer *ab, const char *prefix, + struct dentry *dentry, struct vfsmount *vfsmnt) +{ + char *p; + int len, avail; + + if (prefix) audit_log_format(ab, " %s", prefix); + + if (ab->len > 128) + audit_log_move(ab); + avail = sizeof(ab->tmp) - ab->len; + p = d_path(dentry, vfsmnt, ab->tmp + ab->len, avail); + if (IS_ERR(p)) { + /* FIXME: can we save some information here? */ + audit_log_format(ab, ""); + } else { + /* path isn't at start of buffer */ + len = (ab->tmp + sizeof(ab->tmp) - 1) - p; + memmove(ab->tmp + ab->len, p, len); + ab->len += len; + ab->total += len; + } +} + +/* Remove queued messages from the audit_txlist and send them to userspace. */ +static void audit_tasklet_handler(unsigned long arg) +{ + LIST_HEAD(list); + struct audit_buffer *ab; + unsigned long flags; + + spin_lock_irqsave(&audit_txlist_lock, flags); + list_splice_init(&audit_txlist, &list); + spin_unlock_irqrestore(&audit_txlist_lock, flags); + + while (!list_empty(&list)) { + ab = list_entry(list.next, struct audit_buffer, list); + list_del(&ab->list); + audit_log_end_fast(ab); + } +} + +static DECLARE_TASKLET(audit_tasklet, audit_tasklet_handler, 0); + +/* The netlink_* functions cannot be called inside an irq context, so + * the audit buffer is places on a queue and a tasklet is scheduled to + * remove them from the queue outside the irq context. May be called in + * any context. */ +static void audit_log_end_irq(struct audit_buffer *ab) +{ + unsigned long flags; + + if (!ab) + return; + spin_lock_irqsave(&audit_txlist_lock, flags); + list_add_tail(&ab->list, &audit_txlist); + spin_unlock_irqrestore(&audit_txlist_lock, flags); + + tasklet_schedule(&audit_tasklet); +} + +/* Send the message in the audit buffer directly to user space. May not + * be called in an irq context. */ +static void audit_log_end_fast(struct audit_buffer *ab) +{ + unsigned long flags; + + BUG_ON(in_irq()); + if (!ab) + return; + if (!audit_rate_check()) { + audit_log_lost("rate limit exceeded"); + } else { + audit_log_move(ab); + if (audit_log_drain(ab)) + return; + } + + atomic_dec(&audit_backlog); + spin_lock_irqsave(&audit_freelist_lock, flags); + if (++audit_freelist_count > AUDIT_MAXFREE) + kfree(ab); + else + list_add(&ab->list, &audit_freelist); + spin_unlock_irqrestore(&audit_freelist_lock, flags); +} + +/* Send or queue the message in the audit buffer, depending on the + * current context. (A convenience function that may be called in any + * context.) */ +void audit_log_end(struct audit_buffer *ab) +{ + if (in_irq()) + audit_log_end_irq(ab); + else + audit_log_end_fast(ab); +} + +/* Log an audit record. This is a convenience function that calls + * audit_log_start, audit_log_vformat, and audit_log_end. It may be + * called in any context. */ +void audit_log(struct audit_context *ctx, const char *fmt, ...) +{ + struct audit_buffer *ab; + va_list args; + + ab = audit_log_start(ctx); + if (ab) { + va_start(args, fmt); + audit_log_vformat(ab, fmt, args); + va_end(args); + audit_log_end(ab); + } +} diff --git a/kernel/auditsc.c b/kernel/auditsc.c new file mode 100644 index 000000000000..8c454852d6a5 --- /dev/null +++ b/kernel/auditsc.c @@ -0,0 +1,1015 @@ +/* auditsc.c -- System-call auditing support -*- linux-c -*- + * Handles all system-call specific auditing features. + * + * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Written by Rickard E. (Rik) Faith + * + * Many of the ideas implemented here are from Stephen C. Tweedie, + * especially the idea of avoiding a copy by using getname. + * + * The method for actual interception of syscall entry and exit (not in + * this file -- see entry.S) is based on a GPL'd patch written by + * okir@suse.de and Copyright 2003 SuSE Linux AG. + * + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* 0 = no checking + 1 = put_count checking + 2 = verbose put_count checking +*/ +#define AUDIT_DEBUG 0 + +/* No syscall auditing will take place unless audit_enabled != 0. */ +extern int audit_enabled; + +/* AUDIT_NAMES is the number of slots we reserve in the audit_context + * for saving names from getname(). */ +#define AUDIT_NAMES 20 + +/* AUDIT_NAMES_RESERVED is the number of slots we reserve in the + * audit_context from being used for nameless inodes from + * path_lookup. */ +#define AUDIT_NAMES_RESERVED 7 + +/* At task start time, the audit_state is set in the audit_context using + a per-task filter. At syscall entry, the audit_state is augmented by + the syscall filter. */ +enum audit_state { + AUDIT_DISABLED, /* Do not create per-task audit_context. + * No syscall-specific audit records can + * be generated. */ + AUDIT_SETUP_CONTEXT, /* Create the per-task audit_context, + * but don't necessarily fill it in at + * syscall entry time (i.e., filter + * instead). */ + AUDIT_BUILD_CONTEXT, /* Create the per-task audit_context, + * and always fill it in at syscall + * entry time. This makes a full + * syscall record available if some + * other part of the kernel decides it + * should be recorded. */ + AUDIT_RECORD_CONTEXT /* Create the per-task audit_context, + * always fill it in at syscall entry + * time, and always write out the audit + * record at syscall exit time. */ +}; + +/* When fs/namei.c:getname() is called, we store the pointer in name and + * we don't let putname() free it (instead we free all of the saved + * pointers at syscall exit time). + * + * Further, in fs/namei.c:path_lookup() we store the inode and device. */ +struct audit_names { + const char *name; + unsigned long ino; + dev_t dev; + umode_t mode; + uid_t uid; + gid_t gid; + dev_t rdev; +}; + +struct audit_aux_data { + struct audit_aux_data *next; + int type; +}; + +#define AUDIT_AUX_IPCPERM 0 + +struct audit_aux_data_ipcctl { + struct audit_aux_data d; + struct ipc_perm p; + unsigned long qbytes; + uid_t uid; + gid_t gid; + mode_t mode; +}; + + +/* The per-task audit context. */ +struct audit_context { + int in_syscall; /* 1 if task is in a syscall */ + enum audit_state state; + unsigned int serial; /* serial number for record */ + struct timespec ctime; /* time of syscall entry */ + uid_t loginuid; /* login uid (identity) */ + int major; /* syscall number */ + unsigned long argv[4]; /* syscall arguments */ + int return_valid; /* return code is valid */ + int return_code;/* syscall return code */ + int auditable; /* 1 if record should be written */ + int name_count; + struct audit_names names[AUDIT_NAMES]; + struct audit_context *previous; /* For nested syscalls */ + struct audit_aux_data *aux; + + /* Save things to print about task_struct */ + pid_t pid; + uid_t uid, euid, suid, fsuid; + gid_t gid, egid, sgid, fsgid; + unsigned long personality; + +#if AUDIT_DEBUG + int put_count; + int ino_count; +#endif +}; + + /* Public API */ +/* There are three lists of rules -- one to search at task creation + * time, one to search at syscall entry time, and another to search at + * syscall exit time. */ +static LIST_HEAD(audit_tsklist); +static LIST_HEAD(audit_entlist); +static LIST_HEAD(audit_extlist); + +struct audit_entry { + struct list_head list; + struct rcu_head rcu; + struct audit_rule rule; +}; + +/* Check to see if two rules are identical. It is called from + * audit_del_rule during AUDIT_DEL. */ +static int audit_compare_rule(struct audit_rule *a, struct audit_rule *b) +{ + int i; + + if (a->flags != b->flags) + return 1; + + if (a->action != b->action) + return 1; + + if (a->field_count != b->field_count) + return 1; + + for (i = 0; i < a->field_count; i++) { + if (a->fields[i] != b->fields[i] + || a->values[i] != b->values[i]) + return 1; + } + + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) + if (a->mask[i] != b->mask[i]) + return 1; + + return 0; +} + +/* Note that audit_add_rule and audit_del_rule are called via + * audit_receive() in audit.c, and are protected by + * audit_netlink_sem. */ +static inline int audit_add_rule(struct audit_entry *entry, + struct list_head *list) +{ + if (entry->rule.flags & AUDIT_PREPEND) { + entry->rule.flags &= ~AUDIT_PREPEND; + list_add_rcu(&entry->list, list); + } else { + list_add_tail_rcu(&entry->list, list); + } + return 0; +} + +static void audit_free_rule(struct rcu_head *head) +{ + struct audit_entry *e = container_of(head, struct audit_entry, rcu); + kfree(e); +} + +/* Note that audit_add_rule and audit_del_rule are called via + * audit_receive() in audit.c, and are protected by + * audit_netlink_sem. */ +static inline int audit_del_rule(struct audit_rule *rule, + struct list_head *list) +{ + struct audit_entry *e; + + /* Do not use the _rcu iterator here, since this is the only + * deletion routine. */ + list_for_each_entry(e, list, list) { + if (!audit_compare_rule(rule, &e->rule)) { + list_del_rcu(&e->list); + call_rcu(&e->rcu, audit_free_rule); + return 0; + } + } + return -EFAULT; /* No matching rule */ +} + +#ifdef CONFIG_NET +/* Copy rule from user-space to kernel-space. Called during + * AUDIT_ADD. */ +static int audit_copy_rule(struct audit_rule *d, struct audit_rule *s) +{ + int i; + + if (s->action != AUDIT_NEVER + && s->action != AUDIT_POSSIBLE + && s->action != AUDIT_ALWAYS) + return -1; + if (s->field_count < 0 || s->field_count > AUDIT_MAX_FIELDS) + return -1; + + d->flags = s->flags; + d->action = s->action; + d->field_count = s->field_count; + for (i = 0; i < d->field_count; i++) { + d->fields[i] = s->fields[i]; + d->values[i] = s->values[i]; + } + for (i = 0; i < AUDIT_BITMASK_SIZE; i++) d->mask[i] = s->mask[i]; + return 0; +} + +int audit_receive_filter(int type, int pid, int uid, int seq, void *data) +{ + u32 flags; + struct audit_entry *entry; + int err = 0; + + switch (type) { + case AUDIT_LIST: + /* The *_rcu iterators not needed here because we are + always called with audit_netlink_sem held. */ + list_for_each_entry(entry, &audit_tsklist, list) + audit_send_reply(pid, seq, AUDIT_LIST, 0, 1, + &entry->rule, sizeof(entry->rule)); + list_for_each_entry(entry, &audit_entlist, list) + audit_send_reply(pid, seq, AUDIT_LIST, 0, 1, + &entry->rule, sizeof(entry->rule)); + list_for_each_entry(entry, &audit_extlist, list) + audit_send_reply(pid, seq, AUDIT_LIST, 0, 1, + &entry->rule, sizeof(entry->rule)); + audit_send_reply(pid, seq, AUDIT_LIST, 1, 1, NULL, 0); + break; + case AUDIT_ADD: + if (!(entry = kmalloc(sizeof(*entry), GFP_KERNEL))) + return -ENOMEM; + if (audit_copy_rule(&entry->rule, data)) { + kfree(entry); + return -EINVAL; + } + flags = entry->rule.flags; + if (!err && (flags & AUDIT_PER_TASK)) + err = audit_add_rule(entry, &audit_tsklist); + if (!err && (flags & AUDIT_AT_ENTRY)) + err = audit_add_rule(entry, &audit_entlist); + if (!err && (flags & AUDIT_AT_EXIT)) + err = audit_add_rule(entry, &audit_extlist); + break; + case AUDIT_DEL: + flags =((struct audit_rule *)data)->flags; + if (!err && (flags & AUDIT_PER_TASK)) + err = audit_del_rule(data, &audit_tsklist); + if (!err && (flags & AUDIT_AT_ENTRY)) + err = audit_del_rule(data, &audit_entlist); + if (!err && (flags & AUDIT_AT_EXIT)) + err = audit_del_rule(data, &audit_extlist); + break; + default: + return -EINVAL; + } + + return err; +} +#endif + +/* Compare a task_struct with an audit_rule. Return 1 on match, 0 + * otherwise. */ +static int audit_filter_rules(struct task_struct *tsk, + struct audit_rule *rule, + struct audit_context *ctx, + enum audit_state *state) +{ + int i, j; + + for (i = 0; i < rule->field_count; i++) { + u32 field = rule->fields[i] & ~AUDIT_NEGATE; + u32 value = rule->values[i]; + int result = 0; + + switch (field) { + case AUDIT_PID: + result = (tsk->pid == value); + break; + case AUDIT_UID: + result = (tsk->uid == value); + break; + case AUDIT_EUID: + result = (tsk->euid == value); + break; + case AUDIT_SUID: + result = (tsk->suid == value); + break; + case AUDIT_FSUID: + result = (tsk->fsuid == value); + break; + case AUDIT_GID: + result = (tsk->gid == value); + break; + case AUDIT_EGID: + result = (tsk->egid == value); + break; + case AUDIT_SGID: + result = (tsk->sgid == value); + break; + case AUDIT_FSGID: + result = (tsk->fsgid == value); + break; + case AUDIT_PERS: + result = (tsk->personality == value); + break; + + case AUDIT_EXIT: + if (ctx && ctx->return_valid) + result = (ctx->return_code == value); + break; + case AUDIT_SUCCESS: + if (ctx && ctx->return_valid) + result = (ctx->return_code >= 0); + break; + case AUDIT_DEVMAJOR: + if (ctx) { + for (j = 0; j < ctx->name_count; j++) { + if (MAJOR(ctx->names[j].dev)==value) { + ++result; + break; + } + } + } + break; + case AUDIT_DEVMINOR: + if (ctx) { + for (j = 0; j < ctx->name_count; j++) { + if (MINOR(ctx->names[j].dev)==value) { + ++result; + break; + } + } + } + break; + case AUDIT_INODE: + if (ctx) { + for (j = 0; j < ctx->name_count; j++) { + if (ctx->names[j].ino == value) { + ++result; + break; + } + } + } + break; + case AUDIT_LOGINUID: + result = 0; + if (ctx) + result = (ctx->loginuid == value); + break; + case AUDIT_ARG0: + case AUDIT_ARG1: + case AUDIT_ARG2: + case AUDIT_ARG3: + if (ctx) + result = (ctx->argv[field-AUDIT_ARG0]==value); + break; + } + + if (rule->fields[i] & AUDIT_NEGATE) + result = !result; + if (!result) + return 0; + } + switch (rule->action) { + case AUDIT_NEVER: *state = AUDIT_DISABLED; break; + case AUDIT_POSSIBLE: *state = AUDIT_BUILD_CONTEXT; break; + case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; + } + return 1; +} + +/* At process creation time, we can determine if system-call auditing is + * completely disabled for this task. Since we only have the task + * structure at this point, we can only check uid and gid. + */ +static enum audit_state audit_filter_task(struct task_struct *tsk) +{ + struct audit_entry *e; + enum audit_state state; + + rcu_read_lock(); + list_for_each_entry_rcu(e, &audit_tsklist, list) { + if (audit_filter_rules(tsk, &e->rule, NULL, &state)) { + rcu_read_unlock(); + return state; + } + } + rcu_read_unlock(); + return AUDIT_BUILD_CONTEXT; +} + +/* At syscall entry and exit time, this filter is called if the + * audit_state is not low enough that auditing cannot take place, but is + * also not high enough that we already know we have to write and audit + * record (i.e., the state is AUDIT_SETUP_CONTEXT or AUDIT_BUILD_CONTEXT). + */ +static enum audit_state audit_filter_syscall(struct task_struct *tsk, + struct audit_context *ctx, + struct list_head *list) +{ + struct audit_entry *e; + enum audit_state state; + int word = AUDIT_WORD(ctx->major); + int bit = AUDIT_BIT(ctx->major); + + rcu_read_lock(); + list_for_each_entry_rcu(e, list, list) { + if ((e->rule.mask[word] & bit) == bit + && audit_filter_rules(tsk, &e->rule, ctx, &state)) { + rcu_read_unlock(); + return state; + } + } + rcu_read_unlock(); + return AUDIT_BUILD_CONTEXT; +} + +/* This should be called with task_lock() held. */ +static inline struct audit_context *audit_get_context(struct task_struct *tsk, + int return_valid, + int return_code) +{ + struct audit_context *context = tsk->audit_context; + + if (likely(!context)) + return NULL; + context->return_valid = return_valid; + context->return_code = return_code; + + if (context->in_syscall && !context->auditable) { + enum audit_state state; + state = audit_filter_syscall(tsk, context, &audit_extlist); + if (state == AUDIT_RECORD_CONTEXT) + context->auditable = 1; + } + + context->pid = tsk->pid; + context->uid = tsk->uid; + context->gid = tsk->gid; + context->euid = tsk->euid; + context->suid = tsk->suid; + context->fsuid = tsk->fsuid; + context->egid = tsk->egid; + context->sgid = tsk->sgid; + context->fsgid = tsk->fsgid; + context->personality = tsk->personality; + tsk->audit_context = NULL; + return context; +} + +static inline void audit_free_names(struct audit_context *context) +{ + int i; + +#if AUDIT_DEBUG == 2 + if (context->auditable + ||context->put_count + context->ino_count != context->name_count) { + printk(KERN_ERR "audit.c:%d(:%d): major=%d in_syscall=%d" + " name_count=%d put_count=%d" + " ino_count=%d [NOT freeing]\n", + __LINE__, + context->serial, context->major, context->in_syscall, + context->name_count, context->put_count, + context->ino_count); + for (i = 0; i < context->name_count; i++) + printk(KERN_ERR "names[%d] = %p = %s\n", i, + context->names[i].name, + context->names[i].name); + dump_stack(); + return; + } +#endif +#if AUDIT_DEBUG + context->put_count = 0; + context->ino_count = 0; +#endif + + for (i = 0; i < context->name_count; i++) + if (context->names[i].name) + __putname(context->names[i].name); + context->name_count = 0; +} + +static inline void audit_free_aux(struct audit_context *context) +{ + struct audit_aux_data *aux; + + while ((aux = context->aux)) { + context->aux = aux->next; + kfree(aux); + } +} + +static inline void audit_zero_context(struct audit_context *context, + enum audit_state state) +{ + uid_t loginuid = context->loginuid; + + memset(context, 0, sizeof(*context)); + context->state = state; + context->loginuid = loginuid; +} + +static inline struct audit_context *audit_alloc_context(enum audit_state state) +{ + struct audit_context *context; + + if (!(context = kmalloc(sizeof(*context), GFP_KERNEL))) + return NULL; + audit_zero_context(context, state); + return context; +} + +/* Filter on the task information and allocate a per-task audit context + * if necessary. Doing so turns on system call auditing for the + * specified task. This is called from copy_process, so no lock is + * needed. */ +int audit_alloc(struct task_struct *tsk) +{ + struct audit_context *context; + enum audit_state state; + + if (likely(!audit_enabled)) + return 0; /* Return if not auditing. */ + + state = audit_filter_task(tsk); + if (likely(state == AUDIT_DISABLED)) + return 0; + + if (!(context = audit_alloc_context(state))) { + audit_log_lost("out of memory in audit_alloc"); + return -ENOMEM; + } + + /* Preserve login uid */ + context->loginuid = -1; + if (current->audit_context) + context->loginuid = current->audit_context->loginuid; + + tsk->audit_context = context; + set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); + return 0; +} + +static inline void audit_free_context(struct audit_context *context) +{ + struct audit_context *previous; + int count = 0; + + do { + previous = context->previous; + if (previous || (count && count < 10)) { + ++count; + printk(KERN_ERR "audit(:%d): major=%d name_count=%d:" + " freeing multiple contexts (%d)\n", + context->serial, context->major, + context->name_count, count); + } + audit_free_names(context); + audit_free_aux(context); + kfree(context); + context = previous; + } while (context); + if (count >= 10) + printk(KERN_ERR "audit: freed %d contexts\n", count); +} + +static void audit_log_exit(struct audit_context *context) +{ + int i; + struct audit_buffer *ab; + + ab = audit_log_start(context); + if (!ab) + return; /* audit_panic has been called */ + audit_log_format(ab, "syscall=%d", context->major); + if (context->personality != PER_LINUX) + audit_log_format(ab, " per=%lx", context->personality); + if (context->return_valid) + audit_log_format(ab, " exit=%d", context->return_code); + audit_log_format(ab, + " a0=%lx a1=%lx a2=%lx a3=%lx items=%d" + " pid=%d loginuid=%d uid=%d gid=%d" + " euid=%d suid=%d fsuid=%d" + " egid=%d sgid=%d fsgid=%d", + context->argv[0], + context->argv[1], + context->argv[2], + context->argv[3], + context->name_count, + context->pid, + context->loginuid, + context->uid, + context->gid, + context->euid, context->suid, context->fsuid, + context->egid, context->sgid, context->fsgid); + audit_log_end(ab); + while (context->aux) { + struct audit_aux_data *aux; + + ab = audit_log_start(context); + if (!ab) + continue; /* audit_panic has been called */ + + aux = context->aux; + context->aux = aux->next; + + audit_log_format(ab, "auxitem=%d", aux->type); + switch (aux->type) { + case AUDIT_AUX_IPCPERM: { + struct audit_aux_data_ipcctl *axi = (void *)aux; + audit_log_format(ab, + " qbytes=%lx uid=%d gid=%d mode=%x", + axi->qbytes, axi->uid, axi->gid, axi->mode); + } + } + audit_log_end(ab); + kfree(aux); + } + + for (i = 0; i < context->name_count; i++) { + ab = audit_log_start(context); + if (!ab) + continue; /* audit_panic has been called */ + audit_log_format(ab, "item=%d", i); + if (context->names[i].name) + audit_log_format(ab, " name=%s", + context->names[i].name); + if (context->names[i].ino != (unsigned long)-1) + audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#o" + " uid=%d gid=%d rdev=%02x:%02x", + context->names[i].ino, + MAJOR(context->names[i].dev), + MINOR(context->names[i].dev), + context->names[i].mode, + context->names[i].uid, + context->names[i].gid, + MAJOR(context->names[i].rdev), + MINOR(context->names[i].rdev)); + audit_log_end(ab); + } +} + +/* Free a per-task audit context. Called from copy_process and + * __put_task_struct. */ +void audit_free(struct task_struct *tsk) +{ + struct audit_context *context; + + task_lock(tsk); + context = audit_get_context(tsk, 0, 0); + task_unlock(tsk); + + if (likely(!context)) + return; + + /* Check for system calls that do not go through the exit + * function (e.g., exit_group), then free context block. */ + if (context->in_syscall && context->auditable) + audit_log_exit(context); + + audit_free_context(context); +} + +/* Compute a serial number for the audit record. Audit records are + * written to user-space as soon as they are generated, so a complete + * audit record may be written in several pieces. The timestamp of the + * record and this serial number are used by the user-space daemon to + * determine which pieces belong to the same audit record. The + * (timestamp,serial) tuple is unique for each syscall and is live from + * syscall entry to syscall exit. + * + * Atomic values are only guaranteed to be 24-bit, so we count down. + * + * NOTE: Another possibility is to store the formatted records off the + * audit context (for those records that have a context), and emit them + * all at syscall exit. However, this could delay the reporting of + * significant errors until syscall exit (or never, if the system + * halts). */ +static inline unsigned int audit_serial(void) +{ + static atomic_t serial = ATOMIC_INIT(0xffffff); + unsigned int a, b; + + do { + a = atomic_read(&serial); + if (atomic_dec_and_test(&serial)) + atomic_set(&serial, 0xffffff); + b = atomic_read(&serial); + } while (b != a - 1); + + return 0xffffff - b; +} + +/* Fill in audit context at syscall entry. This only happens if the + * audit context was created when the task was created and the state or + * filters demand the audit context be built. If the state from the + * per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT, + * then the record will be written at syscall exit time (otherwise, it + * will only be written if another part of the kernel requests that it + * be written). */ +void audit_syscall_entry(struct task_struct *tsk, int major, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4) +{ + struct audit_context *context = tsk->audit_context; + enum audit_state state; + + BUG_ON(!context); + + /* This happens only on certain architectures that make system + * calls in kernel_thread via the entry.S interface, instead of + * with direct calls. (If you are porting to a new + * architecture, hitting this condition can indicate that you + * got the _exit/_leave calls backward in entry.S.) + * + * i386 no + * x86_64 no + * ppc64 yes (see arch/ppc64/kernel/misc.S) + * + * This also happens with vm86 emulation in a non-nested manner + * (entries without exits), so this case must be caught. + */ + if (context->in_syscall) { + struct audit_context *newctx; + +#if defined(__NR_vm86) && defined(__NR_vm86old) + /* vm86 mode should only be entered once */ + if (major == __NR_vm86 || major == __NR_vm86old) + return; +#endif +#if AUDIT_DEBUG + printk(KERN_ERR + "audit(:%d) pid=%d in syscall=%d;" + " entering syscall=%d\n", + context->serial, tsk->pid, context->major, major); +#endif + newctx = audit_alloc_context(context->state); + if (newctx) { + newctx->previous = context; + context = newctx; + tsk->audit_context = newctx; + } else { + /* If we can't alloc a new context, the best we + * can do is to leak memory (any pending putname + * will be lost). The only other alternative is + * to abandon auditing. */ + audit_zero_context(context, context->state); + } + } + BUG_ON(context->in_syscall || context->name_count); + + if (!audit_enabled) + return; + + context->major = major; + context->argv[0] = a1; + context->argv[1] = a2; + context->argv[2] = a3; + context->argv[3] = a4; + + state = context->state; + if (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT) + state = audit_filter_syscall(tsk, context, &audit_entlist); + if (likely(state == AUDIT_DISABLED)) + return; + + context->serial = audit_serial(); + context->ctime = CURRENT_TIME; + context->in_syscall = 1; + context->auditable = !!(state == AUDIT_RECORD_CONTEXT); +} + +/* Tear down after system call. If the audit context has been marked as + * auditable (either because of the AUDIT_RECORD_CONTEXT state from + * filtering, or because some other part of the kernel write an audit + * message), then write out the syscall information. In call cases, + * free the names stored from getname(). */ +void audit_syscall_exit(struct task_struct *tsk, int return_code) +{ + struct audit_context *context; + + get_task_struct(tsk); + task_lock(tsk); + context = audit_get_context(tsk, 1, return_code); + task_unlock(tsk); + + /* Not having a context here is ok, since the parent may have + * called __put_task_struct. */ + if (likely(!context)) + return; + + if (context->in_syscall && context->auditable) + audit_log_exit(context); + + context->in_syscall = 0; + context->auditable = 0; + if (context->previous) { + struct audit_context *new_context = context->previous; + context->previous = NULL; + audit_free_context(context); + tsk->audit_context = new_context; + } else { + audit_free_names(context); + audit_free_aux(context); + audit_zero_context(context, context->state); + tsk->audit_context = context; + } + put_task_struct(tsk); +} + +/* Add a name to the list. Called from fs/namei.c:getname(). */ +void audit_getname(const char *name) +{ + struct audit_context *context = current->audit_context; + + if (!context || IS_ERR(name) || !name) + return; + + if (!context->in_syscall) { +#if AUDIT_DEBUG == 2 + printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n", + __FILE__, __LINE__, context->serial, name); + dump_stack(); +#endif + return; + } + BUG_ON(context->name_count >= AUDIT_NAMES); + context->names[context->name_count].name = name; + context->names[context->name_count].ino = (unsigned long)-1; + ++context->name_count; +} + +/* Intercept a putname request. Called from + * include/linux/fs.h:putname(). If we have stored the name from + * getname in the audit context, then we delay the putname until syscall + * exit. */ +void audit_putname(const char *name) +{ + struct audit_context *context = current->audit_context; + + BUG_ON(!context); + if (!context->in_syscall) { +#if AUDIT_DEBUG == 2 + printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n", + __FILE__, __LINE__, context->serial, name); + if (context->name_count) { + int i; + for (i = 0; i < context->name_count; i++) + printk(KERN_ERR "name[%d] = %p = %s\n", i, + context->names[i].name, + context->names[i].name); + } +#endif + __putname(name); + } +#if AUDIT_DEBUG + else { + ++context->put_count; + if (context->put_count > context->name_count) { + printk(KERN_ERR "%s:%d(:%d): major=%d" + " in_syscall=%d putname(%p) name_count=%d" + " put_count=%d\n", + __FILE__, __LINE__, + context->serial, context->major, + context->in_syscall, name, context->name_count, + context->put_count); + dump_stack(); + } + } +#endif +} + +/* Store the inode and device from a lookup. Called from + * fs/namei.c:path_lookup(). */ +void audit_inode(const char *name, const struct inode *inode) +{ + int idx; + struct audit_context *context = current->audit_context; + + if (!context->in_syscall) + return; + if (context->name_count + && context->names[context->name_count-1].name + && context->names[context->name_count-1].name == name) + idx = context->name_count - 1; + else if (context->name_count > 1 + && context->names[context->name_count-2].name + && context->names[context->name_count-2].name == name) + idx = context->name_count - 2; + else { + /* FIXME: how much do we care about inodes that have no + * associated name? */ + if (context->name_count >= AUDIT_NAMES - AUDIT_NAMES_RESERVED) + return; + idx = context->name_count++; + context->names[idx].name = NULL; +#if AUDIT_DEBUG + ++context->ino_count; +#endif + } + context->names[idx].ino = inode->i_ino; + context->names[idx].dev = inode->i_sb->s_dev; + context->names[idx].mode = inode->i_mode; + context->names[idx].uid = inode->i_uid; + context->names[idx].gid = inode->i_gid; + context->names[idx].rdev = inode->i_rdev; +} + +void audit_get_stamp(struct audit_context *ctx, + struct timespec *t, int *serial) +{ + if (ctx) { + t->tv_sec = ctx->ctime.tv_sec; + t->tv_nsec = ctx->ctime.tv_nsec; + *serial = ctx->serial; + ctx->auditable = 1; + } else { + *t = CURRENT_TIME; + *serial = 0; + } +} + +extern int audit_set_type(struct audit_buffer *ab, int type); + +int audit_set_loginuid(struct audit_context *ctx, uid_t loginuid) +{ + if (ctx) { + struct audit_buffer *ab; + + ab = audit_log_start(NULL); + if (ab) { + audit_log_format(ab, "login pid=%d uid=%u " + "old loginuid=%u new loginuid=%u", + ctx->pid, ctx->uid, ctx->loginuid, loginuid); + audit_set_type(ab, AUDIT_LOGIN); + audit_log_end(ab); + } + ctx->loginuid = loginuid; + } + return 0; +} + +uid_t audit_get_loginuid(struct audit_context *ctx) +{ + return ctx ? ctx->loginuid : -1; +} + +int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) +{ + struct audit_aux_data_ipcctl *ax; + struct audit_context *context = current->audit_context; + + if (likely(!context)) + return 0; + + ax = kmalloc(sizeof(*ax), GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->qbytes = qbytes; + ax->uid = uid; + ax->gid = gid; + ax->mode = mode; + + ax->d.type = AUDIT_AUX_IPCPERM; + ax->d.next = context->aux; + context->aux = (void *)ax; + return 0; +} diff --git a/kernel/capability.c b/kernel/capability.c new file mode 100644 index 000000000000..64db1ee820c2 --- /dev/null +++ b/kernel/capability.c @@ -0,0 +1,220 @@ +/* + * linux/kernel/capability.c + * + * Copyright (C) 1997 Andrew Main + * + * Integrated into 2.1.97+, Andrew G. Morgan + * 30 May 2002: Cleanup, Robert M. Love + */ + +#include +#include +#include +#include +#include + +unsigned securebits = SECUREBITS_DEFAULT; /* systemwide security settings */ +kernel_cap_t cap_bset = CAP_INIT_EFF_SET; + +EXPORT_SYMBOL(securebits); +EXPORT_SYMBOL(cap_bset); + +/* + * This lock protects task->cap_* for all tasks including current. + * Locking rule: acquire this prior to tasklist_lock. + */ +static DEFINE_SPINLOCK(task_capability_lock); + +/* + * For sys_getproccap() and sys_setproccap(), any of the three + * capability set pointers may be NULL -- indicating that that set is + * uninteresting and/or not to be changed. + */ + +/* + * sys_capget - get the capabilities of a given process. + */ +asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) +{ + int ret = 0; + pid_t pid; + __u32 version; + task_t *target; + struct __user_cap_data_struct data; + + if (get_user(version, &header->version)) + return -EFAULT; + + if (version != _LINUX_CAPABILITY_VERSION) { + if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) + return -EFAULT; + return -EINVAL; + } + + if (get_user(pid, &header->pid)) + return -EFAULT; + + if (pid < 0) + return -EINVAL; + + spin_lock(&task_capability_lock); + read_lock(&tasklist_lock); + + if (pid && pid != current->pid) { + target = find_task_by_pid(pid); + if (!target) { + ret = -ESRCH; + goto out; + } + } else + target = current; + + ret = security_capget(target, &data.effective, &data.inheritable, &data.permitted); + +out: + read_unlock(&tasklist_lock); + spin_unlock(&task_capability_lock); + + if (!ret && copy_to_user(dataptr, &data, sizeof data)) + return -EFAULT; + + return ret; +} + +/* + * cap_set_pg - set capabilities for all processes in a given process + * group. We call this holding task_capability_lock and tasklist_lock. + */ +static inline int cap_set_pg(int pgrp, kernel_cap_t *effective, + kernel_cap_t *inheritable, + kernel_cap_t *permitted) +{ + task_t *g, *target; + int ret = -EPERM; + int found = 0; + + do_each_task_pid(pgrp, PIDTYPE_PGID, g) { + target = g; + while_each_thread(g, target) { + if (!security_capset_check(target, effective, + inheritable, + permitted)) { + security_capset_set(target, effective, + inheritable, + permitted); + ret = 0; + } + found = 1; + } + } while_each_task_pid(pgrp, PIDTYPE_PGID, g); + + if (!found) + ret = 0; + return ret; +} + +/* + * cap_set_all - set capabilities for all processes other than init + * and self. We call this holding task_capability_lock and tasklist_lock. + */ +static inline int cap_set_all(kernel_cap_t *effective, + kernel_cap_t *inheritable, + kernel_cap_t *permitted) +{ + task_t *g, *target; + int ret = -EPERM; + int found = 0; + + do_each_thread(g, target) { + if (target == current || target->pid == 1) + continue; + found = 1; + if (security_capset_check(target, effective, inheritable, + permitted)) + continue; + ret = 0; + security_capset_set(target, effective, inheritable, permitted); + } while_each_thread(g, target); + + if (!found) + ret = 0; + return ret; +} + +/* + * sys_capset - set capabilities for a given process, all processes, or all + * processes in a given process group. + * + * The restrictions on setting capabilities are specified as: + * + * [pid is for the 'target' task. 'current' is the calling task.] + * + * I: any raised capabilities must be a subset of the (old current) permitted + * P: any raised capabilities must be a subset of the (old current) permitted + * E: must be set to a subset of (new target) permitted + */ +asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) +{ + kernel_cap_t inheritable, permitted, effective; + __u32 version; + task_t *target; + int ret; + pid_t pid; + + if (get_user(version, &header->version)) + return -EFAULT; + + if (version != _LINUX_CAPABILITY_VERSION) { + if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) + return -EFAULT; + return -EINVAL; + } + + if (get_user(pid, &header->pid)) + return -EFAULT; + + if (pid && pid != current->pid && !capable(CAP_SETPCAP)) + return -EPERM; + + if (copy_from_user(&effective, &data->effective, sizeof(effective)) || + copy_from_user(&inheritable, &data->inheritable, sizeof(inheritable)) || + copy_from_user(&permitted, &data->permitted, sizeof(permitted))) + return -EFAULT; + + spin_lock(&task_capability_lock); + read_lock(&tasklist_lock); + + if (pid > 0 && pid != current->pid) { + target = find_task_by_pid(pid); + if (!target) { + ret = -ESRCH; + goto out; + } + } else + target = current; + + ret = 0; + + /* having verified that the proposed changes are legal, + we now put them into effect. */ + if (pid < 0) { + if (pid == -1) /* all procs other than current and init */ + ret = cap_set_all(&effective, &inheritable, &permitted); + + else /* all procs in process group */ + ret = cap_set_pg(-pid, &effective, &inheritable, + &permitted); + } else { + ret = security_capset_check(target, &effective, &inheritable, + &permitted); + if (!ret) + security_capset_set(target, &effective, &inheritable, + &permitted); + } + +out: + read_unlock(&tasklist_lock); + spin_unlock(&task_capability_lock); + + return ret; +} diff --git a/kernel/compat.c b/kernel/compat.c new file mode 100644 index 000000000000..dad10656bf14 --- /dev/null +++ b/kernel/compat.c @@ -0,0 +1,860 @@ +/* + * linux/kernel/compat.c + * + * Kernel compatibililty routines for e.g. 32 bit syscall support + * on 64 bit kernels. + * + * Copyright (C) 2002-2003 Stephen Rothwell, IBM Corporation + * + * 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 +#include +#include +#include +#include +#include /* for MAX_SCHEDULE_TIMEOUT */ +#include /* for FUTEX_WAIT */ +#include +#include +#include + +#include +#include + +int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) +{ + return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || + __get_user(ts->tv_sec, &cts->tv_sec) || + __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; +} + +int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts) +{ + return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) || + __put_user(ts->tv_sec, &cts->tv_sec) || + __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; +} + +static long compat_nanosleep_restart(struct restart_block *restart) +{ + unsigned long expire = restart->arg0, now = jiffies; + struct compat_timespec __user *rmtp; + + /* Did it expire while we handled signals? */ + if (!time_after(expire, now)) + return 0; + + current->state = TASK_INTERRUPTIBLE; + expire = schedule_timeout(expire - now); + if (expire == 0) + return 0; + + rmtp = (struct compat_timespec __user *)restart->arg1; + if (rmtp) { + struct compat_timespec ct; + struct timespec t; + + jiffies_to_timespec(expire, &t); + ct.tv_sec = t.tv_sec; + ct.tv_nsec = t.tv_nsec; + if (copy_to_user(rmtp, &ct, sizeof(ct))) + return -EFAULT; + } + /* The 'restart' block is already filled in */ + return -ERESTART_RESTARTBLOCK; +} + +asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp, + struct compat_timespec __user *rmtp) +{ + struct timespec t; + struct restart_block *restart; + unsigned long expire; + + if (get_compat_timespec(&t, rqtp)) + return -EFAULT; + + if ((t.tv_nsec >= 1000000000L) || (t.tv_nsec < 0) || (t.tv_sec < 0)) + return -EINVAL; + + expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec); + current->state = TASK_INTERRUPTIBLE; + expire = schedule_timeout(expire); + if (expire == 0) + return 0; + + if (rmtp) { + jiffies_to_timespec(expire, &t); + if (put_compat_timespec(&t, rmtp)) + return -EFAULT; + } + restart = ¤t_thread_info()->restart_block; + restart->fn = compat_nanosleep_restart; + restart->arg0 = jiffies + expire; + restart->arg1 = (unsigned long) rmtp; + return -ERESTART_RESTARTBLOCK; +} + +static inline long get_compat_itimerval(struct itimerval *o, + struct compat_itimerval __user *i) +{ + return (!access_ok(VERIFY_READ, i, sizeof(*i)) || + (__get_user(o->it_interval.tv_sec, &i->it_interval.tv_sec) | + __get_user(o->it_interval.tv_usec, &i->it_interval.tv_usec) | + __get_user(o->it_value.tv_sec, &i->it_value.tv_sec) | + __get_user(o->it_value.tv_usec, &i->it_value.tv_usec))); +} + +static inline long put_compat_itimerval(struct compat_itimerval __user *o, + struct itimerval *i) +{ + return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || + (__put_user(i->it_interval.tv_sec, &o->it_interval.tv_sec) | + __put_user(i->it_interval.tv_usec, &o->it_interval.tv_usec) | + __put_user(i->it_value.tv_sec, &o->it_value.tv_sec) | + __put_user(i->it_value.tv_usec, &o->it_value.tv_usec))); +} + +asmlinkage long compat_sys_getitimer(int which, + struct compat_itimerval __user *it) +{ + struct itimerval kit; + int error; + + error = do_getitimer(which, &kit); + if (!error && put_compat_itimerval(it, &kit)) + error = -EFAULT; + return error; +} + +asmlinkage long compat_sys_setitimer(int which, + struct compat_itimerval __user *in, + struct compat_itimerval __user *out) +{ + struct itimerval kin, kout; + int error; + + if (in) { + if (get_compat_itimerval(&kin, in)) + return -EFAULT; + } else + memset(&kin, 0, sizeof(kin)); + + error = do_setitimer(which, &kin, out ? &kout : NULL); + if (error || !out) + return error; + if (put_compat_itimerval(out, &kout)) + return -EFAULT; + return 0; +} + +asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) +{ + /* + * In the SMP world we might just be unlucky and have one of + * the times increment as we use it. Since the value is an + * atomically safe type this is just fine. Conceptually its + * as if the syscall took an instant longer to occur. + */ + if (tbuf) { + struct compat_tms tmp; + struct task_struct *tsk = current; + struct task_struct *t; + cputime_t utime, stime, cutime, cstime; + + read_lock(&tasklist_lock); + utime = tsk->signal->utime; + stime = tsk->signal->stime; + t = tsk; + do { + utime = cputime_add(utime, t->utime); + stime = cputime_add(stime, t->stime); + t = next_thread(t); + } while (t != tsk); + + /* + * While we have tasklist_lock read-locked, no dying thread + * can be updating current->signal->[us]time. Instead, + * we got their counts included in the live thread loop. + * However, another thread can come in right now and + * do a wait call that updates current->signal->c[us]time. + * To make sure we always see that pair updated atomically, + * we take the siglock around fetching them. + */ + spin_lock_irq(&tsk->sighand->siglock); + cutime = tsk->signal->cutime; + cstime = tsk->signal->cstime; + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + + tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime)); + tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime)); + tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime)); + tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime)); + if (copy_to_user(tbuf, &tmp, sizeof(tmp))) + return -EFAULT; + } + return compat_jiffies_to_clock_t(jiffies); +} + +/* + * Assumption: old_sigset_t and compat_old_sigset_t are both + * types that can be passed to put_user()/get_user(). + */ + +asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set) +{ + old_sigset_t s; + long ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_sigpending((old_sigset_t __user *) &s); + set_fs(old_fs); + if (ret == 0) + ret = put_user(s, set); + return ret; +} + +asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set, + compat_old_sigset_t __user *oset) +{ + old_sigset_t s; + long ret; + mm_segment_t old_fs; + + if (set && get_user(s, set)) + return -EFAULT; + old_fs = get_fs(); + set_fs(KERNEL_DS); + ret = sys_sigprocmask(how, + set ? (old_sigset_t __user *) &s : NULL, + oset ? (old_sigset_t __user *) &s : NULL); + set_fs(old_fs); + if (ret == 0) + if (oset) + ret = put_user(s, oset); + return ret; +} + +#ifdef CONFIG_FUTEX +asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, int val, + struct compat_timespec __user *utime, u32 __user *uaddr2, + int val3) +{ + struct timespec t; + unsigned long timeout = MAX_SCHEDULE_TIMEOUT; + int val2 = 0; + + if ((op == FUTEX_WAIT) && utime) { + if (get_compat_timespec(&t, utime)) + return -EFAULT; + timeout = timespec_to_jiffies(&t) + 1; + } + if (op >= FUTEX_REQUEUE) + val2 = (int) (unsigned long) utime; + + return do_futex((unsigned long)uaddr, op, val, timeout, + (unsigned long)uaddr2, val2, val3); +} +#endif + +asmlinkage long compat_sys_setrlimit(unsigned int resource, + struct compat_rlimit __user *rlim) +{ + struct rlimit r; + int ret; + mm_segment_t old_fs = get_fs (); + + if (resource >= RLIM_NLIMITS) + return -EINVAL; + + if (!access_ok(VERIFY_READ, rlim, sizeof(*rlim)) || + __get_user(r.rlim_cur, &rlim->rlim_cur) || + __get_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + + if (r.rlim_cur == COMPAT_RLIM_INFINITY) + r.rlim_cur = RLIM_INFINITY; + if (r.rlim_max == COMPAT_RLIM_INFINITY) + r.rlim_max = RLIM_INFINITY; + set_fs(KERNEL_DS); + ret = sys_setrlimit(resource, (struct rlimit __user *) &r); + set_fs(old_fs); + return ret; +} + +#ifdef COMPAT_RLIM_OLD_INFINITY + +asmlinkage long compat_sys_old_getrlimit(unsigned int resource, + struct compat_rlimit __user *rlim) +{ + struct rlimit r; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_old_getrlimit(resource, &r); + set_fs(old_fs); + + if (!ret) { + if (r.rlim_cur > COMPAT_RLIM_OLD_INFINITY) + r.rlim_cur = COMPAT_RLIM_INFINITY; + if (r.rlim_max > COMPAT_RLIM_OLD_INFINITY) + r.rlim_max = COMPAT_RLIM_INFINITY; + + if (!access_ok(VERIFY_WRITE, rlim, sizeof(*rlim)) || + __put_user(r.rlim_cur, &rlim->rlim_cur) || + __put_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + } + return ret; +} + +#endif + +asmlinkage long compat_sys_getrlimit (unsigned int resource, + struct compat_rlimit __user *rlim) +{ + struct rlimit r; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_getrlimit(resource, (struct rlimit __user *) &r); + set_fs(old_fs); + if (!ret) { + if (r.rlim_cur > COMPAT_RLIM_INFINITY) + r.rlim_cur = COMPAT_RLIM_INFINITY; + if (r.rlim_max > COMPAT_RLIM_INFINITY) + r.rlim_max = COMPAT_RLIM_INFINITY; + + if (!access_ok(VERIFY_WRITE, rlim, sizeof(*rlim)) || + __put_user(r.rlim_cur, &rlim->rlim_cur) || + __put_user(r.rlim_max, &rlim->rlim_max)) + return -EFAULT; + } + return ret; +} + +int put_compat_rusage(const struct rusage *r, struct compat_rusage __user *ru) +{ + if (!access_ok(VERIFY_WRITE, ru, sizeof(*ru)) || + __put_user(r->ru_utime.tv_sec, &ru->ru_utime.tv_sec) || + __put_user(r->ru_utime.tv_usec, &ru->ru_utime.tv_usec) || + __put_user(r->ru_stime.tv_sec, &ru->ru_stime.tv_sec) || + __put_user(r->ru_stime.tv_usec, &ru->ru_stime.tv_usec) || + __put_user(r->ru_maxrss, &ru->ru_maxrss) || + __put_user(r->ru_ixrss, &ru->ru_ixrss) || + __put_user(r->ru_idrss, &ru->ru_idrss) || + __put_user(r->ru_isrss, &ru->ru_isrss) || + __put_user(r->ru_minflt, &ru->ru_minflt) || + __put_user(r->ru_majflt, &ru->ru_majflt) || + __put_user(r->ru_nswap, &ru->ru_nswap) || + __put_user(r->ru_inblock, &ru->ru_inblock) || + __put_user(r->ru_oublock, &ru->ru_oublock) || + __put_user(r->ru_msgsnd, &ru->ru_msgsnd) || + __put_user(r->ru_msgrcv, &ru->ru_msgrcv) || + __put_user(r->ru_nsignals, &ru->ru_nsignals) || + __put_user(r->ru_nvcsw, &ru->ru_nvcsw) || + __put_user(r->ru_nivcsw, &ru->ru_nivcsw)) + return -EFAULT; + return 0; +} + +asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru) +{ + struct rusage r; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + ret = sys_getrusage(who, (struct rusage __user *) &r); + set_fs(old_fs); + + if (ret) + return ret; + + if (put_compat_rusage(&r, ru)) + return -EFAULT; + + return 0; +} + +asmlinkage long +compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, + struct compat_rusage __user *ru) +{ + if (!ru) { + return sys_wait4(pid, stat_addr, options, NULL); + } else { + struct rusage r; + int ret; + unsigned int status; + mm_segment_t old_fs = get_fs(); + + set_fs (KERNEL_DS); + ret = sys_wait4(pid, + (stat_addr ? + (unsigned int __user *) &status : NULL), + options, (struct rusage __user *) &r); + set_fs (old_fs); + + if (ret > 0) { + if (put_compat_rusage(&r, ru)) + return -EFAULT; + if (stat_addr && put_user(status, stat_addr)) + return -EFAULT; + } + return ret; + } +} + +asmlinkage long compat_sys_waitid(int which, compat_pid_t pid, + struct compat_siginfo __user *uinfo, int options, + struct compat_rusage __user *uru) +{ + siginfo_t info; + struct rusage ru; + long ret; + mm_segment_t old_fs = get_fs(); + + memset(&info, 0, sizeof(info)); + + set_fs(KERNEL_DS); + ret = sys_waitid(which, pid, (siginfo_t __user *)&info, options, + uru ? (struct rusage __user *)&ru : NULL); + set_fs(old_fs); + + if ((ret < 0) || (info.si_signo == 0)) + return ret; + + if (uru) { + ret = put_compat_rusage(&ru, uru); + if (ret) + return ret; + } + + BUG_ON(info.si_code & __SI_MASK); + info.si_code |= __SI_CHLD; + return copy_siginfo_to_user32(uinfo, &info); +} + +static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr, + unsigned len, cpumask_t *new_mask) +{ + unsigned long *k; + + if (len < sizeof(cpumask_t)) + memset(new_mask, 0, sizeof(cpumask_t)); + else if (len > sizeof(cpumask_t)) + len = sizeof(cpumask_t); + + k = cpus_addr(*new_mask); + return compat_get_bitmap(k, user_mask_ptr, len * 8); +} + +asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, + unsigned int len, + compat_ulong_t __user *user_mask_ptr) +{ + cpumask_t new_mask; + int retval; + + retval = compat_get_user_cpu_mask(user_mask_ptr, len, &new_mask); + if (retval) + return retval; + + return sched_setaffinity(pid, new_mask); +} + +asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, + compat_ulong_t __user *user_mask_ptr) +{ + int ret; + cpumask_t mask; + unsigned long *k; + unsigned int min_length = sizeof(cpumask_t); + + if (NR_CPUS <= BITS_PER_COMPAT_LONG) + min_length = sizeof(compat_ulong_t); + + if (len < min_length) + return -EINVAL; + + ret = sched_getaffinity(pid, &mask); + if (ret < 0) + return ret; + + k = cpus_addr(mask); + ret = compat_put_bitmap(user_mask_ptr, k, min_length * 8); + if (ret) + return ret; + + return min_length; +} + +static int get_compat_itimerspec(struct itimerspec *dst, + struct compat_itimerspec __user *src) +{ + if (get_compat_timespec(&dst->it_interval, &src->it_interval) || + get_compat_timespec(&dst->it_value, &src->it_value)) + return -EFAULT; + return 0; +} + +static int put_compat_itimerspec(struct compat_itimerspec __user *dst, + struct itimerspec *src) +{ + if (put_compat_timespec(&src->it_interval, &dst->it_interval) || + put_compat_timespec(&src->it_value, &dst->it_value)) + return -EFAULT; + return 0; +} + +long compat_sys_timer_settime(timer_t timer_id, int flags, + struct compat_itimerspec __user *new, + struct compat_itimerspec __user *old) +{ + long err; + mm_segment_t oldfs; + struct itimerspec newts, oldts; + + if (!new) + return -EINVAL; + if (get_compat_itimerspec(&newts, new)) + return -EFAULT; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_timer_settime(timer_id, flags, + (struct itimerspec __user *) &newts, + (struct itimerspec __user *) &oldts); + set_fs(oldfs); + if (!err && old && put_compat_itimerspec(old, &oldts)) + return -EFAULT; + return err; +} + +long compat_sys_timer_gettime(timer_t timer_id, + struct compat_itimerspec __user *setting) +{ + long err; + mm_segment_t oldfs; + struct itimerspec ts; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_timer_gettime(timer_id, + (struct itimerspec __user *) &ts); + set_fs(oldfs); + if (!err && put_compat_itimerspec(setting, &ts)) + return -EFAULT; + return err; +} + +long compat_sys_clock_settime(clockid_t which_clock, + struct compat_timespec __user *tp) +{ + long err; + mm_segment_t oldfs; + struct timespec ts; + + if (get_compat_timespec(&ts, tp)) + return -EFAULT; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_settime(which_clock, + (struct timespec __user *) &ts); + set_fs(oldfs); + return err; +} + +long compat_sys_clock_gettime(clockid_t which_clock, + struct compat_timespec __user *tp) +{ + long err; + mm_segment_t oldfs; + struct timespec ts; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_gettime(which_clock, + (struct timespec __user *) &ts); + set_fs(oldfs); + if (!err && put_compat_timespec(&ts, tp)) + return -EFAULT; + return err; +} + +long compat_sys_clock_getres(clockid_t which_clock, + struct compat_timespec __user *tp) +{ + long err; + mm_segment_t oldfs; + struct timespec ts; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_getres(which_clock, + (struct timespec __user *) &ts); + set_fs(oldfs); + if (!err && tp && put_compat_timespec(&ts, tp)) + return -EFAULT; + return err; +} + +long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, + struct compat_timespec __user *rqtp, + struct compat_timespec __user *rmtp) +{ + long err; + mm_segment_t oldfs; + struct timespec in, out; + + if (get_compat_timespec(&in, rqtp)) + return -EFAULT; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = sys_clock_nanosleep(which_clock, flags, + (struct timespec __user *) &in, + (struct timespec __user *) &out); + set_fs(oldfs); + if ((err == -ERESTART_RESTARTBLOCK) && rmtp && + put_compat_timespec(&out, rmtp)) + return -EFAULT; + return err; +} + +/* + * We currently only need the following fields from the sigevent + * structure: sigev_value, sigev_signo, sig_notify and (sometimes + * sigev_notify_thread_id). The others are handled in user mode. + * We also assume that copying sigev_value.sival_int is sufficient + * to keep all the bits of sigev_value.sival_ptr intact. + */ +int get_compat_sigevent(struct sigevent *event, + const struct compat_sigevent __user *u_event) +{ + memset(&event, 0, sizeof(*event)); + return (!access_ok(VERIFY_READ, u_event, sizeof(*u_event)) || + __get_user(event->sigev_value.sival_int, + &u_event->sigev_value.sival_int) || + __get_user(event->sigev_signo, &u_event->sigev_signo) || + __get_user(event->sigev_notify, &u_event->sigev_notify) || + __get_user(event->sigev_notify_thread_id, + &u_event->sigev_notify_thread_id)) + ? -EFAULT : 0; +} + +/* timer_create is architecture specific because it needs sigevent conversion */ + +long compat_get_bitmap(unsigned long *mask, compat_ulong_t __user *umask, + unsigned long bitmap_size) +{ + int i, j; + unsigned long m; + compat_ulong_t um; + unsigned long nr_compat_longs; + + /* align bitmap up to nearest compat_long_t boundary */ + bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); + + if (!access_ok(VERIFY_READ, umask, bitmap_size / 8)) + return -EFAULT; + + nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); + + for (i = 0; i < BITS_TO_LONGS(bitmap_size); i++) { + m = 0; + + for (j = 0; j < sizeof(m)/sizeof(um); j++) { + /* + * We dont want to read past the end of the userspace + * bitmap. We must however ensure the end of the + * kernel bitmap is zeroed. + */ + if (nr_compat_longs-- > 0) { + if (__get_user(um, umask)) + return -EFAULT; + } else { + um = 0; + } + + umask++; + m |= (long)um << (j * BITS_PER_COMPAT_LONG); + } + *mask++ = m; + } + + return 0; +} + +long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, + unsigned long bitmap_size) +{ + int i, j; + unsigned long m; + compat_ulong_t um; + unsigned long nr_compat_longs; + + /* align bitmap up to nearest compat_long_t boundary */ + bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); + + if (!access_ok(VERIFY_WRITE, umask, bitmap_size / 8)) + return -EFAULT; + + nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); + + for (i = 0; i < BITS_TO_LONGS(bitmap_size); i++) { + m = *mask++; + + for (j = 0; j < sizeof(m)/sizeof(um); j++) { + um = m; + + /* + * We dont want to write past the end of the userspace + * bitmap. + */ + if (nr_compat_longs-- > 0) { + if (__put_user(um, umask)) + return -EFAULT; + } + + umask++; + m >>= 4*sizeof(um); + m >>= 4*sizeof(um); + } + } + + return 0; +} + +void +sigset_from_compat (sigset_t *set, compat_sigset_t *compat) +{ + switch (_NSIG_WORDS) { +#if defined (__COMPAT_ENDIAN_SWAP__) + case 4: set->sig[3] = compat->sig[7] | (((long)compat->sig[6]) << 32 ); + case 3: set->sig[2] = compat->sig[5] | (((long)compat->sig[4]) << 32 ); + case 2: set->sig[1] = compat->sig[3] | (((long)compat->sig[2]) << 32 ); + case 1: set->sig[0] = compat->sig[1] | (((long)compat->sig[0]) << 32 ); +#else + case 4: set->sig[3] = compat->sig[6] | (((long)compat->sig[7]) << 32 ); + case 3: set->sig[2] = compat->sig[4] | (((long)compat->sig[5]) << 32 ); + case 2: set->sig[1] = compat->sig[2] | (((long)compat->sig[3]) << 32 ); + case 1: set->sig[0] = compat->sig[0] | (((long)compat->sig[1]) << 32 ); +#endif + } +} + +asmlinkage long +compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese, + struct compat_siginfo __user *uinfo, + struct compat_timespec __user *uts, compat_size_t sigsetsize) +{ + compat_sigset_t s32; + sigset_t s; + int sig; + struct timespec t; + siginfo_t info; + long ret, timeout = 0; + + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&s32, uthese, sizeof(compat_sigset_t))) + return -EFAULT; + sigset_from_compat(&s, &s32); + sigdelsetmask(&s,sigmask(SIGKILL)|sigmask(SIGSTOP)); + signotset(&s); + + if (uts) { + if (get_compat_timespec (&t, uts)) + return -EFAULT; + if (t.tv_nsec >= 1000000000L || t.tv_nsec < 0 + || t.tv_sec < 0) + return -EINVAL; + } + + spin_lock_irq(¤t->sighand->siglock); + sig = dequeue_signal(current, &s, &info); + if (!sig) { + timeout = MAX_SCHEDULE_TIMEOUT; + if (uts) + timeout = timespec_to_jiffies(&t) + +(t.tv_sec || t.tv_nsec); + if (timeout) { + current->real_blocked = current->blocked; + sigandsets(¤t->blocked, ¤t->blocked, &s); + + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + current->state = TASK_INTERRUPTIBLE; + timeout = schedule_timeout(timeout); + + spin_lock_irq(¤t->sighand->siglock); + sig = dequeue_signal(current, &s, &info); + current->blocked = current->real_blocked; + siginitset(¤t->real_blocked, 0); + recalc_sigpending(); + } + } + spin_unlock_irq(¤t->sighand->siglock); + + if (sig) { + ret = sig; + if (uinfo) { + if (copy_siginfo_to_user32(uinfo, &info)) + ret = -EFAULT; + } + }else { + ret = timeout?-EINTR:-EAGAIN; + } + return ret; + +} + +#ifdef __ARCH_WANT_COMPAT_SYS_TIME + +/* compat_time_t is a 32 bit "long" and needs to get converted. */ + +asmlinkage long compat_sys_time(compat_time_t __user * tloc) +{ + compat_time_t i; + struct timeval tv; + + do_gettimeofday(&tv); + i = tv.tv_sec; + + if (tloc) { + if (put_user(i,tloc)) + i = -EFAULT; + } + return i; +} + +asmlinkage long compat_sys_stime(compat_time_t __user *tptr) +{ + struct timespec tv; + int err; + + if (get_user(tv.tv_sec, tptr)) + return -EFAULT; + + tv.tv_nsec = 0; + + err = security_settime(&tv, NULL); + if (err) + return err; + + do_settimeofday(&tv); + return 0; +} + +#endif /* __ARCH_WANT_COMPAT_SYS_TIME */ diff --git a/kernel/configs.c b/kernel/configs.c new file mode 100644 index 000000000000..986f7af31e0a --- /dev/null +++ b/kernel/configs.c @@ -0,0 +1,118 @@ +/* + * kernel/configs.c + * Echo the kernel .config file used to build the kernel + * + * Copyright (C) 2002 Khalid Aziz + * Copyright (C) 2002 Randy Dunlap + * Copyright (C) 2002 Al Stone + * Copyright (C) 2002 Hewlett-Packard Company + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include +#include +#include +#include +#include +#include +#include + +/**************************************************/ +/* the actual current config file */ + +/* + * Define kernel_config_data and kernel_config_data_size, which contains the + * wrapped and compressed configuration file. The file is first compressed + * with gzip and then bounded by two eight byte magic numbers to allow + * extraction from a binary kernel image: + * + * IKCFG_ST + * + * IKCFG_ED + */ +#define MAGIC_START "IKCFG_ST" +#define MAGIC_END "IKCFG_ED" +#include "config_data.h" + + +#define MAGIC_SIZE (sizeof(MAGIC_START) - 1) +#define kernel_config_data_size \ + (sizeof(kernel_config_data) - 1 - MAGIC_SIZE * 2) + +#ifdef CONFIG_IKCONFIG_PROC + +/**************************************************/ +/* globals and useful constants */ + +static ssize_t +ikconfig_read_current(struct file *file, char __user *buf, + size_t len, loff_t * offset) +{ + loff_t pos = *offset; + ssize_t count; + + if (pos >= kernel_config_data_size) + return 0; + + count = min(len, (size_t)(kernel_config_data_size - pos)); + if (copy_to_user(buf, kernel_config_data + MAGIC_SIZE + pos, count)) + return -EFAULT; + + *offset += count; + return count; +} + +static struct file_operations ikconfig_file_ops = { + .owner = THIS_MODULE, + .read = ikconfig_read_current, +}; + +/***************************************************/ +/* ikconfig_init: start up everything we need to */ + +static int __init ikconfig_init(void) +{ + struct proc_dir_entry *entry; + + /* create the current config file */ + entry = create_proc_entry("config.gz", S_IFREG | S_IRUGO, + &proc_root); + if (!entry) + return -ENOMEM; + + entry->proc_fops = &ikconfig_file_ops; + entry->size = kernel_config_data_size; + + return 0; +} + +/***************************************************/ +/* ikconfig_cleanup: clean up our mess */ + +static void __exit ikconfig_cleanup(void) +{ + remove_proc_entry("config.gz", &proc_root); +} + +module_init(ikconfig_init); +module_exit(ikconfig_cleanup); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Randy Dunlap"); +MODULE_DESCRIPTION("Echo the kernel .config file used to build the kernel"); + +#endif /* CONFIG_IKCONFIG_PROC */ diff --git a/kernel/cpu.c b/kernel/cpu.c new file mode 100644 index 000000000000..628f4ccda127 --- /dev/null +++ b/kernel/cpu.c @@ -0,0 +1,193 @@ +/* CPU control. + * (C) 2001, 2002, 2003, 2004 Rusty Russell + * + * This code is licenced under the GPL. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* This protects CPUs going up and down... */ +DECLARE_MUTEX(cpucontrol); + +static struct notifier_block *cpu_chain; + +/* Need to know about CPUs going up/down? */ +int register_cpu_notifier(struct notifier_block *nb) +{ + int ret; + + if ((ret = down_interruptible(&cpucontrol)) != 0) + return ret; + ret = notifier_chain_register(&cpu_chain, nb); + up(&cpucontrol); + return ret; +} +EXPORT_SYMBOL(register_cpu_notifier); + +void unregister_cpu_notifier(struct notifier_block *nb) +{ + down(&cpucontrol); + notifier_chain_unregister(&cpu_chain, nb); + up(&cpucontrol); +} +EXPORT_SYMBOL(unregister_cpu_notifier); + +#ifdef CONFIG_HOTPLUG_CPU +static inline void check_for_tasks(int cpu) +{ + struct task_struct *p; + + write_lock_irq(&tasklist_lock); + for_each_process(p) { + if (task_cpu(p) == cpu && + (!cputime_eq(p->utime, cputime_zero) || + !cputime_eq(p->stime, cputime_zero))) + printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\ + (state = %ld, flags = %lx) \n", + p->comm, p->pid, cpu, p->state, p->flags); + } + write_unlock_irq(&tasklist_lock); +} + +/* Take this CPU down. */ +static int take_cpu_down(void *unused) +{ + int err; + + /* Take offline: makes arch_cpu_down somewhat easier. */ + cpu_clear(smp_processor_id(), cpu_online_map); + + /* Ensure this CPU doesn't handle any more interrupts. */ + err = __cpu_disable(); + if (err < 0) + cpu_set(smp_processor_id(), cpu_online_map); + else + /* Force idle task to run as soon as we yield: it should + immediately notice cpu is offline and die quickly. */ + sched_idle_next(); + + return err; +} + +int cpu_down(unsigned int cpu) +{ + int err; + struct task_struct *p; + cpumask_t old_allowed, tmp; + + if ((err = lock_cpu_hotplug_interruptible()) != 0) + return err; + + if (num_online_cpus() == 1) { + err = -EBUSY; + goto out; + } + + if (!cpu_online(cpu)) { + err = -EINVAL; + goto out; + } + + err = notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE, + (void *)(long)cpu); + if (err == NOTIFY_BAD) { + printk("%s: attempt to take down CPU %u failed\n", + __FUNCTION__, cpu); + err = -EINVAL; + goto out; + } + + /* Ensure that we are not runnable on dying cpu */ + old_allowed = current->cpus_allowed; + tmp = CPU_MASK_ALL; + cpu_clear(cpu, tmp); + set_cpus_allowed(current, tmp); + + p = __stop_machine_run(take_cpu_down, NULL, cpu); + if (IS_ERR(p)) { + /* CPU didn't die: tell everyone. Can't complain. */ + if (notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED, + (void *)(long)cpu) == NOTIFY_BAD) + BUG(); + + err = PTR_ERR(p); + goto out_allowed; + } + + if (cpu_online(cpu)) + goto out_thread; + + /* Wait for it to sleep (leaving idle task). */ + while (!idle_cpu(cpu)) + yield(); + + /* This actually kills the CPU. */ + __cpu_die(cpu); + + /* Move it here so it can run. */ + kthread_bind(p, get_cpu()); + put_cpu(); + + /* CPU is completely dead: tell everyone. Too late to complain. */ + if (notifier_call_chain(&cpu_chain, CPU_DEAD, (void *)(long)cpu) + == NOTIFY_BAD) + BUG(); + + check_for_tasks(cpu); + +out_thread: + err = kthread_stop(p); +out_allowed: + set_cpus_allowed(current, old_allowed); +out: + unlock_cpu_hotplug(); + return err; +} +#endif /*CONFIG_HOTPLUG_CPU*/ + +int __devinit cpu_up(unsigned int cpu) +{ + int ret; + void *hcpu = (void *)(long)cpu; + + if ((ret = down_interruptible(&cpucontrol)) != 0) + return ret; + + if (cpu_online(cpu) || !cpu_present(cpu)) { + ret = -EINVAL; + goto out; + } + ret = notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu); + if (ret == NOTIFY_BAD) { + printk("%s: attempt to bring up CPU %u failed\n", + __FUNCTION__, cpu); + ret = -EINVAL; + goto out_notify; + } + + /* Arch-specific enabling code. */ + ret = __cpu_up(cpu); + if (ret != 0) + goto out_notify; + if (!cpu_online(cpu)) + BUG(); + + /* Now call notifier in preparation. */ + notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu); + +out_notify: + if (ret != 0) + notifier_call_chain(&cpu_chain, CPU_UP_CANCELED, hcpu); +out: + up(&cpucontrol); + return ret; +} diff --git a/kernel/cpuset.c b/kernel/cpuset.c new file mode 100644 index 000000000000..69792bbe2281 --- /dev/null +++ b/kernel/cpuset.c @@ -0,0 +1,1564 @@ +/* + * kernel/cpuset.c + * + * Processor and Memory placement constraints for sets of tasks. + * + * Copyright (C) 2003 BULL SA. + * Copyright (C) 2004 Silicon Graphics, Inc. + * + * Portions derived from Patrick Mochel's sysfs code. + * sysfs is Copyright (c) 2001-3 Patrick Mochel + * Portions Copyright (c) 2004 Silicon Graphics, Inc. + * + * 2003-10-10 Written by Simon Derr + * 2003-10-22 Updates by Stephen Hemminger. + * 2004 May-July Rework by Paul Jackson + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of the Linux + * distribution for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define CPUSET_SUPER_MAGIC 0x27e0eb + +struct cpuset { + unsigned long flags; /* "unsigned long" so bitops work */ + cpumask_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ + nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */ + + atomic_t count; /* count tasks using this cpuset */ + + /* + * We link our 'sibling' struct into our parents 'children'. + * Our children link their 'sibling' into our 'children'. + */ + struct list_head sibling; /* my parents children */ + struct list_head children; /* my children */ + + struct cpuset *parent; /* my parent */ + struct dentry *dentry; /* cpuset fs entry */ + + /* + * Copy of global cpuset_mems_generation as of the most + * recent time this cpuset changed its mems_allowed. + */ + int mems_generation; +}; + +/* bits in struct cpuset flags field */ +typedef enum { + CS_CPU_EXCLUSIVE, + CS_MEM_EXCLUSIVE, + CS_REMOVED, + CS_NOTIFY_ON_RELEASE +} cpuset_flagbits_t; + +/* convenient tests for these bits */ +static inline int is_cpu_exclusive(const struct cpuset *cs) +{ + return !!test_bit(CS_CPU_EXCLUSIVE, &cs->flags); +} + +static inline int is_mem_exclusive(const struct cpuset *cs) +{ + return !!test_bit(CS_MEM_EXCLUSIVE, &cs->flags); +} + +static inline int is_removed(const struct cpuset *cs) +{ + return !!test_bit(CS_REMOVED, &cs->flags); +} + +static inline int notify_on_release(const struct cpuset *cs) +{ + return !!test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags); +} + +/* + * Increment this atomic integer everytime any cpuset changes its + * mems_allowed value. Users of cpusets can track this generation + * number, and avoid having to lock and reload mems_allowed unless + * the cpuset they're using changes generation. + * + * A single, global generation is needed because attach_task() could + * reattach a task to a different cpuset, which must not have its + * generation numbers aliased with those of that tasks previous cpuset. + * + * Generations are needed for mems_allowed because one task cannot + * modify anothers memory placement. So we must enable every task, + * on every visit to __alloc_pages(), to efficiently check whether + * its current->cpuset->mems_allowed has changed, requiring an update + * of its current->mems_allowed. + */ +static atomic_t cpuset_mems_generation = ATOMIC_INIT(1); + +static struct cpuset top_cpuset = { + .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), + .cpus_allowed = CPU_MASK_ALL, + .mems_allowed = NODE_MASK_ALL, + .count = ATOMIC_INIT(0), + .sibling = LIST_HEAD_INIT(top_cpuset.sibling), + .children = LIST_HEAD_INIT(top_cpuset.children), + .parent = NULL, + .dentry = NULL, + .mems_generation = 0, +}; + +static struct vfsmount *cpuset_mount; +static struct super_block *cpuset_sb = NULL; + +/* + * cpuset_sem should be held by anyone who is depending on the children + * or sibling lists of any cpuset, or performing non-atomic operations + * on the flags or *_allowed values of a cpuset, such as raising the + * CS_REMOVED flag bit iff it is not already raised, or reading and + * conditionally modifying the *_allowed values. One kernel global + * cpuset semaphore should be sufficient - these things don't change + * that much. + * + * The code that modifies cpusets holds cpuset_sem across the entire + * operation, from cpuset_common_file_write() down, single threading + * all cpuset modifications (except for counter manipulations from + * fork and exit) across the system. This presumes that cpuset + * modifications are rare - better kept simple and safe, even if slow. + * + * The code that reads cpusets, such as in cpuset_common_file_read() + * and below, only holds cpuset_sem across small pieces of code, such + * as when reading out possibly multi-word cpumasks and nodemasks, as + * the risks are less, and the desire for performance a little greater. + * The proc_cpuset_show() routine needs to hold cpuset_sem to insure + * that no cs->dentry is NULL, as it walks up the cpuset tree to root. + * + * The hooks from fork and exit, cpuset_fork() and cpuset_exit(), don't + * (usually) grab cpuset_sem. These are the two most performance + * critical pieces of code here. The exception occurs on exit(), + * if the last task using a cpuset exits, and the cpuset was marked + * notify_on_release. In that case, the cpuset_sem is taken, the + * path to the released cpuset calculated, and a usermode call made + * to /sbin/cpuset_release_agent with the name of the cpuset (path + * relative to the root of cpuset file system) as the argument. + * + * A cpuset can only be deleted if both its 'count' of using tasks is + * zero, and its list of 'children' cpusets is empty. Since all tasks + * in the system use _some_ cpuset, and since there is always at least + * one task in the system (init, pid == 1), therefore, top_cpuset + * always has either children cpusets and/or using tasks. So no need + * for any special hack to ensure that top_cpuset cannot be deleted. + */ + +static DECLARE_MUTEX(cpuset_sem); + +/* + * A couple of forward declarations required, due to cyclic reference loop: + * cpuset_mkdir -> cpuset_create -> cpuset_populate_dir -> cpuset_add_file + * -> cpuset_create_file -> cpuset_dir_inode_operations -> cpuset_mkdir. + */ + +static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode); +static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry); + +static struct backing_dev_info cpuset_backing_dev_info = { + .ra_pages = 0, /* No readahead */ + .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, +}; + +static struct inode *cpuset_new_inode(mode_t mode) +{ + struct inode *inode = new_inode(cpuset_sb); + + if (inode) { + inode->i_mode = mode; + inode->i_uid = current->fsuid; + inode->i_gid = current->fsgid; + inode->i_blksize = PAGE_CACHE_SIZE; + inode->i_blocks = 0; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info; + } + return inode; +} + +static void cpuset_diput(struct dentry *dentry, struct inode *inode) +{ + /* is dentry a directory ? if so, kfree() associated cpuset */ + if (S_ISDIR(inode->i_mode)) { + struct cpuset *cs = dentry->d_fsdata; + BUG_ON(!(is_removed(cs))); + kfree(cs); + } + iput(inode); +} + +static struct dentry_operations cpuset_dops = { + .d_iput = cpuset_diput, +}; + +static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name) +{ + struct qstr qstr; + struct dentry *d; + + qstr.name = name; + qstr.len = strlen(name); + qstr.hash = full_name_hash(name, qstr.len); + d = lookup_hash(&qstr, parent); + if (!IS_ERR(d)) + d->d_op = &cpuset_dops; + return d; +} + +static void remove_dir(struct dentry *d) +{ + struct dentry *parent = dget(d->d_parent); + + d_delete(d); + simple_rmdir(parent->d_inode, d); + dput(parent); +} + +/* + * NOTE : the dentry must have been dget()'ed + */ +static void cpuset_d_remove_dir(struct dentry *dentry) +{ + struct list_head *node; + + spin_lock(&dcache_lock); + node = dentry->d_subdirs.next; + while (node != &dentry->d_subdirs) { + struct dentry *d = list_entry(node, struct dentry, d_child); + list_del_init(node); + if (d->d_inode) { + d = dget_locked(d); + spin_unlock(&dcache_lock); + d_delete(d); + simple_unlink(dentry->d_inode, d); + dput(d); + spin_lock(&dcache_lock); + } + node = dentry->d_subdirs.next; + } + list_del_init(&dentry->d_child); + spin_unlock(&dcache_lock); + remove_dir(dentry); +} + +static struct super_operations cpuset_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, +}; + +static int cpuset_fill_super(struct super_block *sb, void *unused_data, + int unused_silent) +{ + struct inode *inode; + struct dentry *root; + + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_magic = CPUSET_SUPER_MAGIC; + sb->s_op = &cpuset_ops; + cpuset_sb = sb; + + inode = cpuset_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR); + if (inode) { + inode->i_op = &simple_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + /* directories start off with i_nlink == 2 (for "." entry) */ + inode->i_nlink++; + } else { + return -ENOMEM; + } + + root = d_alloc_root(inode); + if (!root) { + iput(inode); + return -ENOMEM; + } + sb->s_root = root; + return 0; +} + +static struct super_block *cpuset_get_sb(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data) +{ + return get_sb_single(fs_type, flags, data, cpuset_fill_super); +} + +static struct file_system_type cpuset_fs_type = { + .name = "cpuset", + .get_sb = cpuset_get_sb, + .kill_sb = kill_litter_super, +}; + +/* struct cftype: + * + * The files in the cpuset filesystem mostly have a very simple read/write + * handling, some common function will take care of it. Nevertheless some cases + * (read tasks) are special and therefore I define this structure for every + * kind of file. + * + * + * When reading/writing to a file: + * - the cpuset to use in file->f_dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_dentry->d_fsdata + */ + +struct cftype { + char *name; + int private; + int (*open) (struct inode *inode, struct file *file); + ssize_t (*read) (struct file *file, char __user *buf, size_t nbytes, + loff_t *ppos); + int (*write) (struct file *file, const char __user *buf, size_t nbytes, + loff_t *ppos); + int (*release) (struct inode *inode, struct file *file); +}; + +static inline struct cpuset *__d_cs(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +static inline struct cftype *__d_cft(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +/* + * Call with cpuset_sem held. Writes path of cpuset into buf. + * Returns 0 on success, -errno on error. + */ + +static int cpuset_path(const struct cpuset *cs, char *buf, int buflen) +{ + char *start; + + start = buf + buflen; + + *--start = '\0'; + for (;;) { + int len = cs->dentry->d_name.len; + if ((start -= len) < buf) + return -ENAMETOOLONG; + memcpy(start, cs->dentry->d_name.name, len); + cs = cs->parent; + if (!cs) + break; + if (!cs->parent) + continue; + if (--start < buf) + return -ENAMETOOLONG; + *start = '/'; + } + memmove(buf, start, buf + buflen - start); + return 0; +} + +/* + * Notify userspace when a cpuset is released, by running + * /sbin/cpuset_release_agent with the name of the cpuset (path + * relative to the root of cpuset file system) as the argument. + * + * Most likely, this user command will try to rmdir this cpuset. + * + * This races with the possibility that some other task will be + * attached to this cpuset before it is removed, or that some other + * user task will 'mkdir' a child cpuset of this cpuset. That's ok. + * The presumed 'rmdir' will fail quietly if this cpuset is no longer + * unused, and this cpuset will be reprieved from its death sentence, + * to continue to serve a useful existence. Next time it's released, + * we will get notified again, if it still has 'notify_on_release' set. + * + * Note final arg to call_usermodehelper() is 0 - that means + * don't wait. Since we are holding the global cpuset_sem here, + * and we are asking another thread (started from keventd) to rmdir a + * cpuset, we can't wait - or we'd deadlock with the removing thread + * on cpuset_sem. + */ + +static int cpuset_release_agent(char *cpuset_str) +{ + char *argv[3], *envp[3]; + int i; + + i = 0; + argv[i++] = "/sbin/cpuset_release_agent"; + argv[i++] = cpuset_str; + argv[i] = NULL; + + i = 0; + /* minimal command environment */ + envp[i++] = "HOME=/"; + envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[i] = NULL; + + return call_usermodehelper(argv[0], argv, envp, 0); +} + +/* + * Either cs->count of using tasks transitioned to zero, or the + * cs->children list of child cpusets just became empty. If this + * cs is notify_on_release() and now both the user count is zero and + * the list of children is empty, send notice to user land. + */ + +static void check_for_release(struct cpuset *cs) +{ + if (notify_on_release(cs) && atomic_read(&cs->count) == 0 && + list_empty(&cs->children)) { + char *buf; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return; + if (cpuset_path(cs, buf, PAGE_SIZE) < 0) + goto out; + cpuset_release_agent(buf); +out: + kfree(buf); + } +} + +/* + * Return in *pmask the portion of a cpusets's cpus_allowed that + * are online. If none are online, walk up the cpuset hierarchy + * until we find one that does have some online cpus. If we get + * all the way to the top and still haven't found any online cpus, + * return cpu_online_map. Or if passed a NULL cs from an exit'ing + * task, return cpu_online_map. + * + * One way or another, we guarantee to return some non-empty subset + * of cpu_online_map. + * + * Call with cpuset_sem held. + */ + +static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask) +{ + while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map)) + cs = cs->parent; + if (cs) + cpus_and(*pmask, cs->cpus_allowed, cpu_online_map); + else + *pmask = cpu_online_map; + BUG_ON(!cpus_intersects(*pmask, cpu_online_map)); +} + +/* + * Return in *pmask the portion of a cpusets's mems_allowed that + * are online. If none are online, walk up the cpuset hierarchy + * until we find one that does have some online mems. If we get + * all the way to the top and still haven't found any online mems, + * return node_online_map. + * + * One way or another, we guarantee to return some non-empty subset + * of node_online_map. + * + * Call with cpuset_sem held. + */ + +static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) +{ + while (cs && !nodes_intersects(cs->mems_allowed, node_online_map)) + cs = cs->parent; + if (cs) + nodes_and(*pmask, cs->mems_allowed, node_online_map); + else + *pmask = node_online_map; + BUG_ON(!nodes_intersects(*pmask, node_online_map)); +} + +/* + * Refresh current tasks mems_allowed and mems_generation from + * current tasks cpuset. Call with cpuset_sem held. + * + * Be sure to call refresh_mems() on any cpuset operation which + * (1) holds cpuset_sem, and (2) might possibly alloc memory. + * Call after obtaining cpuset_sem lock, before any possible + * allocation. Otherwise one risks trying to allocate memory + * while the task cpuset_mems_generation is not the same as + * the mems_generation in its cpuset, which would deadlock on + * cpuset_sem in cpuset_update_current_mems_allowed(). + * + * Since we hold cpuset_sem, once refresh_mems() is called, the + * test (current->cpuset_mems_generation != cs->mems_generation) + * in cpuset_update_current_mems_allowed() will remain false, + * until we drop cpuset_sem. Anyone else who would change our + * cpusets mems_generation needs to lock cpuset_sem first. + */ + +static void refresh_mems(void) +{ + struct cpuset *cs = current->cpuset; + + if (current->cpuset_mems_generation != cs->mems_generation) { + guarantee_online_mems(cs, ¤t->mems_allowed); + current->cpuset_mems_generation = cs->mems_generation; + } +} + +/* + * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? + * + * One cpuset is a subset of another if all its allowed CPUs and + * Memory Nodes are a subset of the other, and its exclusive flags + * are only set if the other's are set. + */ + +static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) +{ + return cpus_subset(p->cpus_allowed, q->cpus_allowed) && + nodes_subset(p->mems_allowed, q->mems_allowed) && + is_cpu_exclusive(p) <= is_cpu_exclusive(q) && + is_mem_exclusive(p) <= is_mem_exclusive(q); +} + +/* + * validate_change() - Used to validate that any proposed cpuset change + * follows the structural rules for cpusets. + * + * If we replaced the flag and mask values of the current cpuset + * (cur) with those values in the trial cpuset (trial), would + * our various subset and exclusive rules still be valid? Presumes + * cpuset_sem held. + * + * 'cur' is the address of an actual, in-use cpuset. Operations + * such as list traversal that depend on the actual address of the + * cpuset in the list must use cur below, not trial. + * + * 'trial' is the address of bulk structure copy of cur, with + * perhaps one or more of the fields cpus_allowed, mems_allowed, + * or flags changed to new, trial values. + * + * Return 0 if valid, -errno if not. + */ + +static int validate_change(const struct cpuset *cur, const struct cpuset *trial) +{ + struct cpuset *c, *par; + + /* Each of our child cpusets must be a subset of us */ + list_for_each_entry(c, &cur->children, sibling) { + if (!is_cpuset_subset(c, trial)) + return -EBUSY; + } + + /* Remaining checks don't apply to root cpuset */ + if ((par = cur->parent) == NULL) + return 0; + + /* We must be a subset of our parent cpuset */ + if (!is_cpuset_subset(trial, par)) + return -EACCES; + + /* If either I or some sibling (!= me) is exclusive, we can't overlap */ + list_for_each_entry(c, &par->children, sibling) { + if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && + c != cur && + cpus_intersects(trial->cpus_allowed, c->cpus_allowed)) + return -EINVAL; + if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && + c != cur && + nodes_intersects(trial->mems_allowed, c->mems_allowed)) + return -EINVAL; + } + + return 0; +} + +static int update_cpumask(struct cpuset *cs, char *buf) +{ + struct cpuset trialcs; + int retval; + + trialcs = *cs; + retval = cpulist_parse(buf, trialcs.cpus_allowed); + if (retval < 0) + return retval; + cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map); + if (cpus_empty(trialcs.cpus_allowed)) + return -ENOSPC; + retval = validate_change(cs, &trialcs); + if (retval == 0) + cs->cpus_allowed = trialcs.cpus_allowed; + return retval; +} + +static int update_nodemask(struct cpuset *cs, char *buf) +{ + struct cpuset trialcs; + int retval; + + trialcs = *cs; + retval = nodelist_parse(buf, trialcs.mems_allowed); + if (retval < 0) + return retval; + nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map); + if (nodes_empty(trialcs.mems_allowed)) + return -ENOSPC; + retval = validate_change(cs, &trialcs); + if (retval == 0) { + cs->mems_allowed = trialcs.mems_allowed; + atomic_inc(&cpuset_mems_generation); + cs->mems_generation = atomic_read(&cpuset_mems_generation); + } + return retval; +} + +/* + * update_flag - read a 0 or a 1 in a file and update associated flag + * bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, + * CS_NOTIFY_ON_RELEASE) + * cs: the cpuset to update + * buf: the buffer where we read the 0 or 1 + */ + +static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf) +{ + int turning_on; + struct cpuset trialcs; + int err; + + turning_on = (simple_strtoul(buf, NULL, 10) != 0); + + trialcs = *cs; + if (turning_on) + set_bit(bit, &trialcs.flags); + else + clear_bit(bit, &trialcs.flags); + + err = validate_change(cs, &trialcs); + if (err == 0) { + if (turning_on) + set_bit(bit, &cs->flags); + else + clear_bit(bit, &cs->flags); + } + return err; +} + +static int attach_task(struct cpuset *cs, char *buf) +{ + pid_t pid; + struct task_struct *tsk; + struct cpuset *oldcs; + cpumask_t cpus; + + if (sscanf(buf, "%d", &pid) != 1) + return -EIO; + if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) + return -ENOSPC; + + if (pid) { + read_lock(&tasklist_lock); + + tsk = find_task_by_pid(pid); + if (!tsk) { + read_unlock(&tasklist_lock); + return -ESRCH; + } + + get_task_struct(tsk); + read_unlock(&tasklist_lock); + + if ((current->euid) && (current->euid != tsk->uid) + && (current->euid != tsk->suid)) { + put_task_struct(tsk); + return -EACCES; + } + } else { + tsk = current; + get_task_struct(tsk); + } + + task_lock(tsk); + oldcs = tsk->cpuset; + if (!oldcs) { + task_unlock(tsk); + put_task_struct(tsk); + return -ESRCH; + } + atomic_inc(&cs->count); + tsk->cpuset = cs; + task_unlock(tsk); + + guarantee_online_cpus(cs, &cpus); + set_cpus_allowed(tsk, cpus); + + put_task_struct(tsk); + if (atomic_dec_and_test(&oldcs->count)) + check_for_release(oldcs); + return 0; +} + +/* The various types of files and directories in a cpuset file system */ + +typedef enum { + FILE_ROOT, + FILE_DIR, + FILE_CPULIST, + FILE_MEMLIST, + FILE_CPU_EXCLUSIVE, + FILE_MEM_EXCLUSIVE, + FILE_NOTIFY_ON_RELEASE, + FILE_TASKLIST, +} cpuset_filetype_t; + +static ssize_t cpuset_common_file_write(struct file *file, const char __user *userbuf, + size_t nbytes, loff_t *unused_ppos) +{ + struct cpuset *cs = __d_cs(file->f_dentry->d_parent); + struct cftype *cft = __d_cft(file->f_dentry); + cpuset_filetype_t type = cft->private; + char *buffer; + int retval = 0; + + /* Crude upper limit on largest legitimate cpulist user might write. */ + if (nbytes > 100 + 6 * NR_CPUS) + return -E2BIG; + + /* +1 for nul-terminator */ + if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0) + return -ENOMEM; + + if (copy_from_user(buffer, userbuf, nbytes)) { + retval = -EFAULT; + goto out1; + } + buffer[nbytes] = 0; /* nul-terminate */ + + down(&cpuset_sem); + + if (is_removed(cs)) { + retval = -ENODEV; + goto out2; + } + + switch (type) { + case FILE_CPULIST: + retval = update_cpumask(cs, buffer); + break; + case FILE_MEMLIST: + retval = update_nodemask(cs, buffer); + break; + case FILE_CPU_EXCLUSIVE: + retval = update_flag(CS_CPU_EXCLUSIVE, cs, buffer); + break; + case FILE_MEM_EXCLUSIVE: + retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer); + break; + case FILE_NOTIFY_ON_RELEASE: + retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer); + break; + case FILE_TASKLIST: + retval = attach_task(cs, buffer); + break; + default: + retval = -EINVAL; + goto out2; + } + + if (retval == 0) + retval = nbytes; +out2: + up(&cpuset_sem); +out1: + kfree(buffer); + return retval; +} + +static ssize_t cpuset_file_write(struct file *file, const char __user *buf, + size_t nbytes, loff_t *ppos) +{ + ssize_t retval = 0; + struct cftype *cft = __d_cft(file->f_dentry); + if (!cft) + return -ENODEV; + + /* special function ? */ + if (cft->write) + retval = cft->write(file, buf, nbytes, ppos); + else + retval = cpuset_common_file_write(file, buf, nbytes, ppos); + + return retval; +} + +/* + * These ascii lists should be read in a single call, by using a user + * buffer large enough to hold the entire map. If read in smaller + * chunks, there is no guarantee of atomicity. Since the display format + * used, list of ranges of sequential numbers, is variable length, + * and since these maps can change value dynamically, one could read + * gibberish by doing partial reads while a list was changing. + * A single large read to a buffer that crosses a page boundary is + * ok, because the result being copied to user land is not recomputed + * across a page fault. + */ + +static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs) +{ + cpumask_t mask; + + down(&cpuset_sem); + mask = cs->cpus_allowed; + up(&cpuset_sem); + + return cpulist_scnprintf(page, PAGE_SIZE, mask); +} + +static int cpuset_sprintf_memlist(char *page, struct cpuset *cs) +{ + nodemask_t mask; + + down(&cpuset_sem); + mask = cs->mems_allowed; + up(&cpuset_sem); + + return nodelist_scnprintf(page, PAGE_SIZE, mask); +} + +static ssize_t cpuset_common_file_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + struct cftype *cft = __d_cft(file->f_dentry); + struct cpuset *cs = __d_cs(file->f_dentry->d_parent); + cpuset_filetype_t type = cft->private; + char *page; + ssize_t retval = 0; + char *s; + char *start; + size_t n; + + if (!(page = (char *)__get_free_page(GFP_KERNEL))) + return -ENOMEM; + + s = page; + + switch (type) { + case FILE_CPULIST: + s += cpuset_sprintf_cpulist(s, cs); + break; + case FILE_MEMLIST: + s += cpuset_sprintf_memlist(s, cs); + break; + case FILE_CPU_EXCLUSIVE: + *s++ = is_cpu_exclusive(cs) ? '1' : '0'; + break; + case FILE_MEM_EXCLUSIVE: + *s++ = is_mem_exclusive(cs) ? '1' : '0'; + break; + case FILE_NOTIFY_ON_RELEASE: + *s++ = notify_on_release(cs) ? '1' : '0'; + break; + default: + retval = -EINVAL; + goto out; + } + *s++ = '\n'; + *s = '\0'; + + start = page + *ppos; + n = s - start; + retval = n - copy_to_user(buf, start, min(n, nbytes)); + *ppos += retval; +out: + free_page((unsigned long)page); + return retval; +} + +static ssize_t cpuset_file_read(struct file *file, char __user *buf, size_t nbytes, + loff_t *ppos) +{ + ssize_t retval = 0; + struct cftype *cft = __d_cft(file->f_dentry); + if (!cft) + return -ENODEV; + + /* special function ? */ + if (cft->read) + retval = cft->read(file, buf, nbytes, ppos); + else + retval = cpuset_common_file_read(file, buf, nbytes, ppos); + + return retval; +} + +static int cpuset_file_open(struct inode *inode, struct file *file) +{ + int err; + struct cftype *cft; + + err = generic_file_open(inode, file); + if (err) + return err; + + cft = __d_cft(file->f_dentry); + if (!cft) + return -ENODEV; + if (cft->open) + err = cft->open(inode, file); + else + err = 0; + + return err; +} + +static int cpuset_file_release(struct inode *inode, struct file *file) +{ + struct cftype *cft = __d_cft(file->f_dentry); + if (cft->release) + return cft->release(inode, file); + return 0; +} + +static struct file_operations cpuset_file_operations = { + .read = cpuset_file_read, + .write = cpuset_file_write, + .llseek = generic_file_llseek, + .open = cpuset_file_open, + .release = cpuset_file_release, +}; + +static struct inode_operations cpuset_dir_inode_operations = { + .lookup = simple_lookup, + .mkdir = cpuset_mkdir, + .rmdir = cpuset_rmdir, +}; + +static int cpuset_create_file(struct dentry *dentry, int mode) +{ + struct inode *inode; + + if (!dentry) + return -ENOENT; + if (dentry->d_inode) + return -EEXIST; + + inode = cpuset_new_inode(mode); + if (!inode) + return -ENOMEM; + + if (S_ISDIR(mode)) { + inode->i_op = &cpuset_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + + /* start off with i_nlink == 2 (for "." entry) */ + inode->i_nlink++; + } else if (S_ISREG(mode)) { + inode->i_size = 0; + inode->i_fop = &cpuset_file_operations; + } + + d_instantiate(dentry, inode); + dget(dentry); /* Extra count - pin the dentry in core */ + return 0; +} + +/* + * cpuset_create_dir - create a directory for an object. + * cs: the cpuset we create the directory for. + * It must have a valid ->parent field + * And we are going to fill its ->dentry field. + * name: The name to give to the cpuset directory. Will be copied. + * mode: mode to set on new directory. + */ + +static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode) +{ + struct dentry *dentry = NULL; + struct dentry *parent; + int error = 0; + + parent = cs->parent->dentry; + dentry = cpuset_get_dentry(parent, name); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + error = cpuset_create_file(dentry, S_IFDIR | mode); + if (!error) { + dentry->d_fsdata = cs; + parent->d_inode->i_nlink++; + cs->dentry = dentry; + } + dput(dentry); + + return error; +} + +static int cpuset_add_file(struct dentry *dir, const struct cftype *cft) +{ + struct dentry *dentry; + int error; + + down(&dir->d_inode->i_sem); + dentry = cpuset_get_dentry(dir, cft->name); + if (!IS_ERR(dentry)) { + error = cpuset_create_file(dentry, 0644 | S_IFREG); + if (!error) + dentry->d_fsdata = (void *)cft; + dput(dentry); + } else + error = PTR_ERR(dentry); + up(&dir->d_inode->i_sem); + return error; +} + +/* + * Stuff for reading the 'tasks' file. + * + * Reading this file can return large amounts of data if a cpuset has + * *lots* of attached tasks. So it may need several calls to read(), + * but we cannot guarantee that the information we produce is correct + * unless we produce it entirely atomically. + * + * Upon tasks file open(), a struct ctr_struct is allocated, that + * will have a pointer to an array (also allocated here). The struct + * ctr_struct * is stored in file->private_data. Its resources will + * be freed by release() when the file is closed. The array is used + * to sprintf the PIDs and then used by read(). + */ + +/* cpusets_tasks_read array */ + +struct ctr_struct { + char *buf; + int bufsz; +}; + +/* + * Load into 'pidarray' up to 'npids' of the tasks using cpuset 'cs'. + * Return actual number of pids loaded. + */ +static inline int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs) +{ + int n = 0; + struct task_struct *g, *p; + + read_lock(&tasklist_lock); + + do_each_thread(g, p) { + if (p->cpuset == cs) { + pidarray[n++] = p->pid; + if (unlikely(n == npids)) + goto array_full; + } + } while_each_thread(g, p); + +array_full: + read_unlock(&tasklist_lock); + return n; +} + +static int cmppid(const void *a, const void *b) +{ + return *(pid_t *)a - *(pid_t *)b; +} + +/* + * Convert array 'a' of 'npids' pid_t's to a string of newline separated + * decimal pids in 'buf'. Don't write more than 'sz' chars, but return + * count 'cnt' of how many chars would be written if buf were large enough. + */ +static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids) +{ + int cnt = 0; + int i; + + for (i = 0; i < npids; i++) + cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]); + return cnt; +} + +static int cpuset_tasks_open(struct inode *unused, struct file *file) +{ + struct cpuset *cs = __d_cs(file->f_dentry->d_parent); + struct ctr_struct *ctr; + pid_t *pidarray; + int npids; + char c; + + if (!(file->f_mode & FMODE_READ)) + return 0; + + ctr = kmalloc(sizeof(*ctr), GFP_KERNEL); + if (!ctr) + goto err0; + + /* + * If cpuset gets more users after we read count, we won't have + * enough space - tough. This race is indistinguishable to the + * caller from the case that the additional cpuset users didn't + * show up until sometime later on. + */ + npids = atomic_read(&cs->count); + pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL); + if (!pidarray) + goto err1; + + npids = pid_array_load(pidarray, npids, cs); + sort(pidarray, npids, sizeof(pid_t), cmppid, NULL); + + /* Call pid_array_to_buf() twice, first just to get bufsz */ + ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1; + ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL); + if (!ctr->buf) + goto err2; + ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids); + + kfree(pidarray); + file->private_data = ctr; + return 0; + +err2: + kfree(pidarray); +err1: + kfree(ctr); +err0: + return -ENOMEM; +} + +static ssize_t cpuset_tasks_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + struct ctr_struct *ctr = file->private_data; + + if (*ppos + nbytes > ctr->bufsz) + nbytes = ctr->bufsz - *ppos; + if (copy_to_user(buf, ctr->buf + *ppos, nbytes)) + return -EFAULT; + *ppos += nbytes; + return nbytes; +} + +static int cpuset_tasks_release(struct inode *unused_inode, struct file *file) +{ + struct ctr_struct *ctr; + + if (file->f_mode & FMODE_READ) { + ctr = file->private_data; + kfree(ctr->buf); + kfree(ctr); + } + return 0; +} + +/* + * for the common functions, 'private' gives the type of file + */ + +static struct cftype cft_tasks = { + .name = "tasks", + .open = cpuset_tasks_open, + .read = cpuset_tasks_read, + .release = cpuset_tasks_release, + .private = FILE_TASKLIST, +}; + +static struct cftype cft_cpus = { + .name = "cpus", + .private = FILE_CPULIST, +}; + +static struct cftype cft_mems = { + .name = "mems", + .private = FILE_MEMLIST, +}; + +static struct cftype cft_cpu_exclusive = { + .name = "cpu_exclusive", + .private = FILE_CPU_EXCLUSIVE, +}; + +static struct cftype cft_mem_exclusive = { + .name = "mem_exclusive", + .private = FILE_MEM_EXCLUSIVE, +}; + +static struct cftype cft_notify_on_release = { + .name = "notify_on_release", + .private = FILE_NOTIFY_ON_RELEASE, +}; + +static int cpuset_populate_dir(struct dentry *cs_dentry) +{ + int err; + + if ((err = cpuset_add_file(cs_dentry, &cft_cpus)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_mems)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_cpu_exclusive)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_mem_exclusive)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_notify_on_release)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0) + return err; + return 0; +} + +/* + * cpuset_create - create a cpuset + * parent: cpuset that will be parent of the new cpuset. + * name: name of the new cpuset. Will be strcpy'ed. + * mode: mode to set on new inode + * + * Must be called with the semaphore on the parent inode held + */ + +static long cpuset_create(struct cpuset *parent, const char *name, int mode) +{ + struct cpuset *cs; + int err; + + cs = kmalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return -ENOMEM; + + down(&cpuset_sem); + refresh_mems(); + cs->flags = 0; + if (notify_on_release(parent)) + set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags); + cs->cpus_allowed = CPU_MASK_NONE; + cs->mems_allowed = NODE_MASK_NONE; + atomic_set(&cs->count, 0); + INIT_LIST_HEAD(&cs->sibling); + INIT_LIST_HEAD(&cs->children); + atomic_inc(&cpuset_mems_generation); + cs->mems_generation = atomic_read(&cpuset_mems_generation); + + cs->parent = parent; + + list_add(&cs->sibling, &cs->parent->children); + + err = cpuset_create_dir(cs, name, mode); + if (err < 0) + goto err; + + /* + * Release cpuset_sem before cpuset_populate_dir() because it + * will down() this new directory's i_sem and if we race with + * another mkdir, we might deadlock. + */ + up(&cpuset_sem); + + err = cpuset_populate_dir(cs->dentry); + /* If err < 0, we have a half-filled directory - oh well ;) */ + return 0; +err: + list_del(&cs->sibling); + up(&cpuset_sem); + kfree(cs); + return err; +} + +static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode) +{ + struct cpuset *c_parent = dentry->d_parent->d_fsdata; + + /* the vfs holds inode->i_sem already */ + return cpuset_create(c_parent, dentry->d_name.name, mode | S_IFDIR); +} + +static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry) +{ + struct cpuset *cs = dentry->d_fsdata; + struct dentry *d; + struct cpuset *parent; + + /* the vfs holds both inode->i_sem already */ + + down(&cpuset_sem); + refresh_mems(); + if (atomic_read(&cs->count) > 0) { + up(&cpuset_sem); + return -EBUSY; + } + if (!list_empty(&cs->children)) { + up(&cpuset_sem); + return -EBUSY; + } + spin_lock(&cs->dentry->d_lock); + parent = cs->parent; + set_bit(CS_REMOVED, &cs->flags); + list_del(&cs->sibling); /* delete my sibling from parent->children */ + if (list_empty(&parent->children)) + check_for_release(parent); + d = dget(cs->dentry); + cs->dentry = NULL; + spin_unlock(&d->d_lock); + cpuset_d_remove_dir(d); + dput(d); + up(&cpuset_sem); + return 0; +} + +/** + * cpuset_init - initialize cpusets at system boot + * + * Description: Initialize top_cpuset and the cpuset internal file system, + **/ + +int __init cpuset_init(void) +{ + struct dentry *root; + int err; + + top_cpuset.cpus_allowed = CPU_MASK_ALL; + top_cpuset.mems_allowed = NODE_MASK_ALL; + + atomic_inc(&cpuset_mems_generation); + top_cpuset.mems_generation = atomic_read(&cpuset_mems_generation); + + init_task.cpuset = &top_cpuset; + + err = register_filesystem(&cpuset_fs_type); + if (err < 0) + goto out; + cpuset_mount = kern_mount(&cpuset_fs_type); + if (IS_ERR(cpuset_mount)) { + printk(KERN_ERR "cpuset: could not mount!\n"); + err = PTR_ERR(cpuset_mount); + cpuset_mount = NULL; + goto out; + } + root = cpuset_mount->mnt_sb->s_root; + root->d_fsdata = &top_cpuset; + root->d_inode->i_nlink++; + top_cpuset.dentry = root; + root->d_inode->i_op = &cpuset_dir_inode_operations; + err = cpuset_populate_dir(root); +out: + return err; +} + +/** + * cpuset_init_smp - initialize cpus_allowed + * + * Description: Finish top cpuset after cpu, node maps are initialized + **/ + +void __init cpuset_init_smp(void) +{ + top_cpuset.cpus_allowed = cpu_online_map; + top_cpuset.mems_allowed = node_online_map; +} + +/** + * cpuset_fork - attach newly forked task to its parents cpuset. + * @p: pointer to task_struct of forking parent process. + * + * Description: By default, on fork, a task inherits its + * parents cpuset. The pointer to the shared cpuset is + * automatically copied in fork.c by dup_task_struct(). + * This cpuset_fork() routine need only increment the usage + * counter in that cpuset. + **/ + +void cpuset_fork(struct task_struct *tsk) +{ + atomic_inc(&tsk->cpuset->count); +} + +/** + * cpuset_exit - detach cpuset from exiting task + * @tsk: pointer to task_struct of exiting process + * + * Description: Detach cpuset from @tsk and release it. + * + **/ + +void cpuset_exit(struct task_struct *tsk) +{ + struct cpuset *cs; + + task_lock(tsk); + cs = tsk->cpuset; + tsk->cpuset = NULL; + task_unlock(tsk); + + if (atomic_dec_and_test(&cs->count)) { + down(&cpuset_sem); + check_for_release(cs); + up(&cpuset_sem); + } +} + +/** + * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. + * + * Description: Returns the cpumask_t cpus_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of cpu_online_map, even if this means going outside the + * tasks cpuset. + **/ + +const cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk) +{ + cpumask_t mask; + + down(&cpuset_sem); + task_lock((struct task_struct *)tsk); + guarantee_online_cpus(tsk->cpuset, &mask); + task_unlock((struct task_struct *)tsk); + up(&cpuset_sem); + + return mask; +} + +void cpuset_init_current_mems_allowed(void) +{ + current->mems_allowed = NODE_MASK_ALL; +} + +/* + * If the current tasks cpusets mems_allowed changed behind our backs, + * update current->mems_allowed and mems_generation to the new value. + * Do not call this routine if in_interrupt(). + */ + +void cpuset_update_current_mems_allowed(void) +{ + struct cpuset *cs = current->cpuset; + + if (!cs) + return; /* task is exiting */ + if (current->cpuset_mems_generation != cs->mems_generation) { + down(&cpuset_sem); + refresh_mems(); + up(&cpuset_sem); + } +} + +void cpuset_restrict_to_mems_allowed(unsigned long *nodes) +{ + bitmap_and(nodes, nodes, nodes_addr(current->mems_allowed), + MAX_NUMNODES); +} + +/* + * Are any of the nodes on zonelist zl allowed in current->mems_allowed? + */ +int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl) +{ + int i; + + for (i = 0; zl->zones[i]; i++) { + int nid = zl->zones[i]->zone_pgdat->node_id; + + if (node_isset(nid, current->mems_allowed)) + return 1; + } + return 0; +} + +/* + * Is 'current' valid, and is zone z allowed in current->mems_allowed? + */ +int cpuset_zone_allowed(struct zone *z) +{ + return in_interrupt() || + node_isset(z->zone_pgdat->node_id, current->mems_allowed); +} + +/* + * proc_cpuset_show() + * - Print tasks cpuset path into seq_file. + * - Used for /proc//cpuset. + */ + +static int proc_cpuset_show(struct seq_file *m, void *v) +{ + struct cpuset *cs; + struct task_struct *tsk; + char *buf; + int retval = 0; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + tsk = m->private; + down(&cpuset_sem); + task_lock(tsk); + cs = tsk->cpuset; + task_unlock(tsk); + if (!cs) { + retval = -EINVAL; + goto out; + } + + retval = cpuset_path(cs, buf, PAGE_SIZE); + if (retval < 0) + goto out; + seq_puts(m, buf); + seq_putc(m, '\n'); +out: + up(&cpuset_sem); + kfree(buf); + return retval; +} + +static int cpuset_open(struct inode *inode, struct file *file) +{ + struct task_struct *tsk = PROC_I(inode)->task; + return single_open(file, proc_cpuset_show, tsk); +} + +struct file_operations proc_cpuset_operations = { + .open = cpuset_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/* Display task cpus_allowed, mems_allowed in /proc//status file. */ +char *cpuset_task_status_allowed(struct task_struct *task, char *buffer) +{ + buffer += sprintf(buffer, "Cpus_allowed:\t"); + buffer += cpumask_scnprintf(buffer, PAGE_SIZE, task->cpus_allowed); + buffer += sprintf(buffer, "\n"); + buffer += sprintf(buffer, "Mems_allowed:\t"); + buffer += nodemask_scnprintf(buffer, PAGE_SIZE, task->mems_allowed); + buffer += sprintf(buffer, "\n"); + return buffer; +} diff --git a/kernel/dma.c b/kernel/dma.c new file mode 100644 index 000000000000..aef0a45b7893 --- /dev/null +++ b/kernel/dma.c @@ -0,0 +1,158 @@ +/* $Id: dma.c,v 1.7 1994/12/28 03:35:33 root Exp root $ + * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c. + * + * Written by Hennus Bergman, 1992. + * + * 1994/12/26: Changes by Alex Nash to fix a minor bug in /proc/dma. + * In the previous version the reported device could end up being wrong, + * if a device requested a DMA channel that was already in use. + * [It also happened to remove the sizeof(char *) == sizeof(int) + * assumption introduced because of those /proc/dma patches. -- Hennus] + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +/* A note on resource allocation: + * + * All drivers needing DMA channels, should allocate and release them + * through the public routines `request_dma()' and `free_dma()'. + * + * In order to avoid problems, all processes should allocate resources in + * the same sequence and release them in the reverse order. + * + * So, when allocating DMAs and IRQs, first allocate the IRQ, then the DMA. + * When releasing them, first release the DMA, then release the IRQ. + * If you don't, you may cause allocation requests to fail unnecessarily. + * This doesn't really matter now, but it will once we get real semaphores + * in the kernel. + */ + + +DEFINE_SPINLOCK(dma_spin_lock); + +/* + * If our port doesn't define this it has no PC like DMA + */ + +#ifdef MAX_DMA_CHANNELS + + +/* Channel n is busy iff dma_chan_busy[n].lock != 0. + * DMA0 used to be reserved for DRAM refresh, but apparently not any more... + * DMA4 is reserved for cascading. + */ + +struct dma_chan { + int lock; + const char *device_id; +}; + +static struct dma_chan dma_chan_busy[MAX_DMA_CHANNELS] = { + [4] = { 1, "cascade" }, +}; + + +int request_dma(unsigned int dmanr, const char * device_id) +{ + if (dmanr >= MAX_DMA_CHANNELS) + return -EINVAL; + + if (xchg(&dma_chan_busy[dmanr].lock, 1) != 0) + return -EBUSY; + + dma_chan_busy[dmanr].device_id = device_id; + + /* old flag was 0, now contains 1 to indicate busy */ + return 0; +} /* request_dma */ + + +void free_dma(unsigned int dmanr) +{ + if (dmanr >= MAX_DMA_CHANNELS) { + printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); + return; + } + + if (xchg(&dma_chan_busy[dmanr].lock, 0) == 0) { + printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); + return; + } + +} /* free_dma */ + +#else + +int request_dma(unsigned int dmanr, const char *device_id) +{ + return -EINVAL; +} + +void free_dma(unsigned int dmanr) +{ +} + +#endif + +#ifdef CONFIG_PROC_FS + +#ifdef MAX_DMA_CHANNELS +static int proc_dma_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0 ; i < MAX_DMA_CHANNELS ; i++) { + if (dma_chan_busy[i].lock) { + seq_printf(m, "%2d: %s\n", i, + dma_chan_busy[i].device_id); + } + } + return 0; +} +#else +static int proc_dma_show(struct seq_file *m, void *v) +{ + seq_puts(m, "No DMA\n"); + return 0; +} +#endif /* MAX_DMA_CHANNELS */ + +static int proc_dma_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_dma_show, NULL); +} + +static struct file_operations proc_dma_operations = { + .open = proc_dma_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_dma_init(void) +{ + struct proc_dir_entry *e; + + e = create_proc_entry("dma", 0, NULL); + if (e) + e->proc_fops = &proc_dma_operations; + + return 0; +} + +__initcall(proc_dma_init); +#endif + +EXPORT_SYMBOL(request_dma); +EXPORT_SYMBOL(free_dma); +EXPORT_SYMBOL(dma_spin_lock); diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c new file mode 100644 index 000000000000..867d6dbeb574 --- /dev/null +++ b/kernel/exec_domain.c @@ -0,0 +1,209 @@ +/* + * Handling of different ABIs (personalities). + * + * We group personalities into execution domains which have their + * own handlers for kernel entry points, signal mapping, etc... + * + * 2001-05-06 Complete rewrite, Christoph Hellwig (hch@infradead.org) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +static void default_handler(int, struct pt_regs *); + +static struct exec_domain *exec_domains = &default_exec_domain; +static DEFINE_RWLOCK(exec_domains_lock); + + +static u_long ident_map[32] = { + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31 +}; + +struct exec_domain default_exec_domain = { + .name = "Linux", /* name */ + .handler = default_handler, /* lcall7 causes a seg fault. */ + .pers_low = 0, /* PER_LINUX personality. */ + .pers_high = 0, /* PER_LINUX personality. */ + .signal_map = ident_map, /* Identity map signals. */ + .signal_invmap = ident_map, /* - both ways. */ +}; + + +static void +default_handler(int segment, struct pt_regs *regp) +{ + set_personality(0); + + if (current_thread_info()->exec_domain->handler != default_handler) + current_thread_info()->exec_domain->handler(segment, regp); + else + send_sig(SIGSEGV, current, 1); +} + +static struct exec_domain * +lookup_exec_domain(u_long personality) +{ + struct exec_domain * ep; + u_long pers = personality(personality); + + read_lock(&exec_domains_lock); + for (ep = exec_domains; ep; ep = ep->next) { + if (pers >= ep->pers_low && pers <= ep->pers_high) + if (try_module_get(ep->module)) + goto out; + } + +#ifdef CONFIG_KMOD + read_unlock(&exec_domains_lock); + request_module("personality-%ld", pers); + read_lock(&exec_domains_lock); + + for (ep = exec_domains; ep; ep = ep->next) { + if (pers >= ep->pers_low && pers <= ep->pers_high) + if (try_module_get(ep->module)) + goto out; + } +#endif + + ep = &default_exec_domain; +out: + read_unlock(&exec_domains_lock); + return (ep); +} + +int +register_exec_domain(struct exec_domain *ep) +{ + struct exec_domain *tmp; + int err = -EBUSY; + + if (ep == NULL) + return -EINVAL; + + if (ep->next != NULL) + return -EBUSY; + + write_lock(&exec_domains_lock); + for (tmp = exec_domains; tmp; tmp = tmp->next) { + if (tmp == ep) + goto out; + } + + ep->next = exec_domains; + exec_domains = ep; + err = 0; + +out: + write_unlock(&exec_domains_lock); + return (err); +} + +int +unregister_exec_domain(struct exec_domain *ep) +{ + struct exec_domain **epp; + + epp = &exec_domains; + write_lock(&exec_domains_lock); + for (epp = &exec_domains; *epp; epp = &(*epp)->next) { + if (ep == *epp) + goto unregister; + } + write_unlock(&exec_domains_lock); + return -EINVAL; + +unregister: + *epp = ep->next; + ep->next = NULL; + write_unlock(&exec_domains_lock); + return 0; +} + +int +__set_personality(u_long personality) +{ + struct exec_domain *ep, *oep; + + ep = lookup_exec_domain(personality); + if (ep == current_thread_info()->exec_domain) { + current->personality = personality; + return 0; + } + + if (atomic_read(¤t->fs->count) != 1) { + struct fs_struct *fsp, *ofsp; + + fsp = copy_fs_struct(current->fs); + if (fsp == NULL) { + module_put(ep->module); + return -ENOMEM; + } + + task_lock(current); + ofsp = current->fs; + current->fs = fsp; + task_unlock(current); + + put_fs_struct(ofsp); + } + + /* + * At that point we are guaranteed to be the sole owner of + * current->fs. + */ + + current->personality = personality; + oep = current_thread_info()->exec_domain; + current_thread_info()->exec_domain = ep; + set_fs_altroot(); + + module_put(oep->module); + return 0; +} + +int +get_exec_domain_list(char *page) +{ + struct exec_domain *ep; + int len = 0; + + read_lock(&exec_domains_lock); + for (ep = exec_domains; ep && len < PAGE_SIZE - 80; ep = ep->next) + len += sprintf(page + len, "%d-%d\t%-16s\t[%s]\n", + ep->pers_low, ep->pers_high, ep->name, + module_name(ep->module)); + read_unlock(&exec_domains_lock); + return (len); +} + +asmlinkage long +sys_personality(u_long personality) +{ + u_long old = current->personality; + + if (personality != 0xffffffff) { + set_personality(personality); + if (current->personality != personality) + return -EINVAL; + } + + return (long)old; +} + + +EXPORT_SYMBOL(register_exec_domain); +EXPORT_SYMBOL(unregister_exec_domain); +EXPORT_SYMBOL(__set_personality); diff --git a/kernel/exit.c b/kernel/exit.c new file mode 100644 index 000000000000..6dd4ebe1dd90 --- /dev/null +++ b/kernel/exit.c @@ -0,0 +1,1527 @@ +/* + * linux/kernel/exit.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +extern void sem_exit (void); +extern struct task_struct *child_reaper; + +int getrusage(struct task_struct *, int, struct rusage __user *); + +static void __unhash_process(struct task_struct *p) +{ + nr_threads--; + detach_pid(p, PIDTYPE_PID); + detach_pid(p, PIDTYPE_TGID); + if (thread_group_leader(p)) { + detach_pid(p, PIDTYPE_PGID); + detach_pid(p, PIDTYPE_SID); + if (p->pid) + __get_cpu_var(process_counts)--; + } + + REMOVE_LINKS(p); +} + +void release_task(struct task_struct * p) +{ + int zap_leader; + task_t *leader; + struct dentry *proc_dentry; + +repeat: + atomic_dec(&p->user->processes); + spin_lock(&p->proc_lock); + proc_dentry = proc_pid_unhash(p); + write_lock_irq(&tasklist_lock); + if (unlikely(p->ptrace)) + __ptrace_unlink(p); + BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); + __exit_signal(p); + __exit_sighand(p); + __unhash_process(p); + + /* + * If we are the last non-leader member of the thread + * group, and the leader is zombie, then notify the + * group leader's parent process. (if it wants notification.) + */ + zap_leader = 0; + leader = p->group_leader; + if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { + BUG_ON(leader->exit_signal == -1); + do_notify_parent(leader, leader->exit_signal); + /* + * If we were the last child thread and the leader has + * exited already, and the leader's parent ignores SIGCHLD, + * then we are the one who should release the leader. + * + * do_notify_parent() will have marked it self-reaping in + * that case. + */ + zap_leader = (leader->exit_signal == -1); + } + + sched_exit(p); + write_unlock_irq(&tasklist_lock); + spin_unlock(&p->proc_lock); + proc_pid_flush(proc_dentry); + release_thread(p); + put_task_struct(p); + + p = leader; + if (unlikely(zap_leader)) + goto repeat; +} + +/* we are using it only for SMP init */ + +void unhash_process(struct task_struct *p) +{ + struct dentry *proc_dentry; + + spin_lock(&p->proc_lock); + proc_dentry = proc_pid_unhash(p); + write_lock_irq(&tasklist_lock); + __unhash_process(p); + write_unlock_irq(&tasklist_lock); + spin_unlock(&p->proc_lock); + proc_pid_flush(proc_dentry); +} + +/* + * This checks not only the pgrp, but falls back on the pid if no + * satisfactory pgrp is found. I dunno - gdb doesn't work correctly + * without this... + */ +int session_of_pgrp(int pgrp) +{ + struct task_struct *p; + int sid = -1; + + read_lock(&tasklist_lock); + do_each_task_pid(pgrp, PIDTYPE_PGID, p) { + if (p->signal->session > 0) { + sid = p->signal->session; + goto out; + } + } while_each_task_pid(pgrp, PIDTYPE_PGID, p); + p = find_task_by_pid(pgrp); + if (p) + sid = p->signal->session; +out: + read_unlock(&tasklist_lock); + + return sid; +} + +/* + * Determine if a process group is "orphaned", according to the POSIX + * definition in 2.2.2.52. Orphaned process groups are not to be affected + * by terminal-generated stop signals. Newly orphaned process groups are + * to receive a SIGHUP and a SIGCONT. + * + * "I ask you, have you ever known what it is to be an orphan?" + */ +static int will_become_orphaned_pgrp(int pgrp, task_t *ignored_task) +{ + struct task_struct *p; + int ret = 1; + + do_each_task_pid(pgrp, PIDTYPE_PGID, p) { + if (p == ignored_task + || p->exit_state + || p->real_parent->pid == 1) + continue; + if (process_group(p->real_parent) != pgrp + && p->real_parent->signal->session == p->signal->session) { + ret = 0; + break; + } + } while_each_task_pid(pgrp, PIDTYPE_PGID, p); + return ret; /* (sighing) "Often!" */ +} + +int is_orphaned_pgrp(int pgrp) +{ + int retval; + + read_lock(&tasklist_lock); + retval = will_become_orphaned_pgrp(pgrp, NULL); + read_unlock(&tasklist_lock); + + return retval; +} + +static inline int has_stopped_jobs(int pgrp) +{ + int retval = 0; + struct task_struct *p; + + do_each_task_pid(pgrp, PIDTYPE_PGID, p) { + if (p->state != TASK_STOPPED) + continue; + + /* If p is stopped by a debugger on a signal that won't + stop it, then don't count p as stopped. This isn't + perfect but it's a good approximation. */ + if (unlikely (p->ptrace) + && p->exit_code != SIGSTOP + && p->exit_code != SIGTSTP + && p->exit_code != SIGTTOU + && p->exit_code != SIGTTIN) + continue; + + retval = 1; + break; + } while_each_task_pid(pgrp, PIDTYPE_PGID, p); + return retval; +} + +/** + * reparent_to_init() - Reparent the calling kernel thread to the init task. + * + * If a kernel thread is launched as a result of a system call, or if + * it ever exits, it should generally reparent itself to init so that + * it is correctly cleaned up on exit. + * + * The various task state such as scheduling policy and priority may have + * been inherited from a user process, so we reset them to sane values here. + * + * NOTE that reparent_to_init() gives the caller full capabilities. + */ +void reparent_to_init(void) +{ + write_lock_irq(&tasklist_lock); + + ptrace_unlink(current); + /* Reparent to init */ + REMOVE_LINKS(current); + current->parent = child_reaper; + current->real_parent = child_reaper; + SET_LINKS(current); + + /* Set the exit signal to SIGCHLD so we signal init on exit */ + current->exit_signal = SIGCHLD; + + if ((current->policy == SCHED_NORMAL) && (task_nice(current) < 0)) + set_user_nice(current, 0); + /* cpus_allowed? */ + /* rt_priority? */ + /* signals? */ + security_task_reparent_to_init(current); + memcpy(current->signal->rlim, init_task.signal->rlim, + sizeof(current->signal->rlim)); + atomic_inc(&(INIT_USER->__count)); + write_unlock_irq(&tasklist_lock); + switch_uid(INIT_USER); +} + +void __set_special_pids(pid_t session, pid_t pgrp) +{ + struct task_struct *curr = current; + + if (curr->signal->session != session) { + detach_pid(curr, PIDTYPE_SID); + curr->signal->session = session; + attach_pid(curr, PIDTYPE_SID, session); + } + if (process_group(curr) != pgrp) { + detach_pid(curr, PIDTYPE_PGID); + curr->signal->pgrp = pgrp; + attach_pid(curr, PIDTYPE_PGID, pgrp); + } +} + +void set_special_pids(pid_t session, pid_t pgrp) +{ + write_lock_irq(&tasklist_lock); + __set_special_pids(session, pgrp); + write_unlock_irq(&tasklist_lock); +} + +/* + * Let kernel threads use this to say that they + * allow a certain signal (since daemonize() will + * have disabled all of them by default). + */ +int allow_signal(int sig) +{ + if (sig < 1 || sig > _NSIG) + return -EINVAL; + + spin_lock_irq(¤t->sighand->siglock); + sigdelset(¤t->blocked, sig); + if (!current->mm) { + /* Kernel threads handle their own signals. + Let the signal code know it'll be handled, so + that they don't get converted to SIGKILL or + just silently dropped */ + current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2; + } + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + return 0; +} + +EXPORT_SYMBOL(allow_signal); + +int disallow_signal(int sig) +{ + if (sig < 1 || sig > _NSIG) + return -EINVAL; + + spin_lock_irq(¤t->sighand->siglock); + sigaddset(¤t->blocked, sig); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + return 0; +} + +EXPORT_SYMBOL(disallow_signal); + +/* + * Put all the gunge required to become a kernel thread without + * attached user resources in one place where it belongs. + */ + +void daemonize(const char *name, ...) +{ + va_list args; + struct fs_struct *fs; + sigset_t blocked; + + va_start(args, name); + vsnprintf(current->comm, sizeof(current->comm), name, args); + va_end(args); + + /* + * If we were started as result of loading a module, close all of the + * user space pages. We don't need them, and if we didn't close them + * they would be locked into memory. + */ + exit_mm(current); + + set_special_pids(1, 1); + down(&tty_sem); + current->signal->tty = NULL; + up(&tty_sem); + + /* Block and flush all signals */ + sigfillset(&blocked); + sigprocmask(SIG_BLOCK, &blocked, NULL); + flush_signals(current); + + /* Become as one with the init task */ + + exit_fs(current); /* current->fs->count--; */ + fs = init_task.fs; + current->fs = fs; + atomic_inc(&fs->count); + exit_files(current); + current->files = init_task.files; + atomic_inc(¤t->files->count); + + reparent_to_init(); +} + +EXPORT_SYMBOL(daemonize); + +static inline void close_files(struct files_struct * files) +{ + int i, j; + + j = 0; + for (;;) { + unsigned long set; + i = j * __NFDBITS; + if (i >= files->max_fdset || i >= files->max_fds) + break; + set = files->open_fds->fds_bits[j++]; + while (set) { + if (set & 1) { + struct file * file = xchg(&files->fd[i], NULL); + if (file) + filp_close(file, files); + } + i++; + set >>= 1; + } + } +} + +struct files_struct *get_files_struct(struct task_struct *task) +{ + struct files_struct *files; + + task_lock(task); + files = task->files; + if (files) + atomic_inc(&files->count); + task_unlock(task); + + return files; +} + +void fastcall put_files_struct(struct files_struct *files) +{ + if (atomic_dec_and_test(&files->count)) { + close_files(files); + /* + * Free the fd and fdset arrays if we expanded them. + */ + if (files->fd != &files->fd_array[0]) + free_fd_array(files->fd, files->max_fds); + if (files->max_fdset > __FD_SETSIZE) { + free_fdset(files->open_fds, files->max_fdset); + free_fdset(files->close_on_exec, files->max_fdset); + } + kmem_cache_free(files_cachep, files); + } +} + +EXPORT_SYMBOL(put_files_struct); + +static inline void __exit_files(struct task_struct *tsk) +{ + struct files_struct * files = tsk->files; + + if (files) { + task_lock(tsk); + tsk->files = NULL; + task_unlock(tsk); + put_files_struct(files); + } +} + +void exit_files(struct task_struct *tsk) +{ + __exit_files(tsk); +} + +static inline void __put_fs_struct(struct fs_struct *fs) +{ + /* No need to hold fs->lock if we are killing it */ + if (atomic_dec_and_test(&fs->count)) { + dput(fs->root); + mntput(fs->rootmnt); + dput(fs->pwd); + mntput(fs->pwdmnt); + if (fs->altroot) { + dput(fs->altroot); + mntput(fs->altrootmnt); + } + kmem_cache_free(fs_cachep, fs); + } +} + +void put_fs_struct(struct fs_struct *fs) +{ + __put_fs_struct(fs); +} + +static inline void __exit_fs(struct task_struct *tsk) +{ + struct fs_struct * fs = tsk->fs; + + if (fs) { + task_lock(tsk); + tsk->fs = NULL; + task_unlock(tsk); + __put_fs_struct(fs); + } +} + +void exit_fs(struct task_struct *tsk) +{ + __exit_fs(tsk); +} + +EXPORT_SYMBOL_GPL(exit_fs); + +/* + * Turn us into a lazy TLB process if we + * aren't already.. + */ +void exit_mm(struct task_struct * tsk) +{ + struct mm_struct *mm = tsk->mm; + + mm_release(tsk, mm); + if (!mm) + return; + /* + * Serialize with any possible pending coredump. + * We must hold mmap_sem around checking core_waiters + * and clearing tsk->mm. The core-inducing thread + * will increment core_waiters for each thread in the + * group with ->mm != NULL. + */ + down_read(&mm->mmap_sem); + if (mm->core_waiters) { + up_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); + if (!--mm->core_waiters) + complete(mm->core_startup_done); + up_write(&mm->mmap_sem); + + wait_for_completion(&mm->core_done); + down_read(&mm->mmap_sem); + } + atomic_inc(&mm->mm_count); + if (mm != tsk->active_mm) BUG(); + /* more a memory barrier than a real lock */ + task_lock(tsk); + tsk->mm = NULL; + up_read(&mm->mmap_sem); + enter_lazy_tlb(mm, current); + task_unlock(tsk); + mmput(mm); +} + +static inline void choose_new_parent(task_t *p, task_t *reaper, task_t *child_reaper) +{ + /* + * Make sure we're not reparenting to ourselves and that + * the parent is not a zombie. + */ + BUG_ON(p == reaper || reaper->exit_state >= EXIT_ZOMBIE); + p->real_parent = reaper; + if (p->parent == p->real_parent) + BUG(); +} + +static inline void reparent_thread(task_t *p, task_t *father, int traced) +{ + /* We don't want people slaying init. */ + if (p->exit_signal != -1) + p->exit_signal = SIGCHLD; + + if (p->pdeath_signal) + /* We already hold the tasklist_lock here. */ + group_send_sig_info(p->pdeath_signal, (void *) 0, p); + + /* Move the child from its dying parent to the new one. */ + if (unlikely(traced)) { + /* Preserve ptrace links if someone else is tracing this child. */ + list_del_init(&p->ptrace_list); + if (p->parent != p->real_parent) + list_add(&p->ptrace_list, &p->real_parent->ptrace_children); + } else { + /* If this child is being traced, then we're the one tracing it + * anyway, so let go of it. + */ + p->ptrace = 0; + list_del_init(&p->sibling); + p->parent = p->real_parent; + list_add_tail(&p->sibling, &p->parent->children); + + /* If we'd notified the old parent about this child's death, + * also notify the new parent. + */ + if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 && + thread_group_empty(p)) + do_notify_parent(p, p->exit_signal); + else if (p->state == TASK_TRACED) { + /* + * If it was at a trace stop, turn it into + * a normal stop since it's no longer being + * traced. + */ + ptrace_untrace(p); + } + } + + /* + * process group orphan check + * Case ii: Our child is in a different pgrp + * than we are, and it was the only connection + * outside, so the child pgrp is now orphaned. + */ + if ((process_group(p) != process_group(father)) && + (p->signal->session == father->signal->session)) { + int pgrp = process_group(p); + + if (will_become_orphaned_pgrp(pgrp, NULL) && has_stopped_jobs(pgrp)) { + __kill_pg_info(SIGHUP, (void *)1, pgrp); + __kill_pg_info(SIGCONT, (void *)1, pgrp); + } + } +} + +/* + * When we die, we re-parent all our children. + * Try to give them to another thread in our thread + * group, and if no such member exists, give it to + * the global child reaper process (ie "init") + */ +static inline void forget_original_parent(struct task_struct * father, + struct list_head *to_release) +{ + struct task_struct *p, *reaper = father; + struct list_head *_p, *_n; + + do { + reaper = next_thread(reaper); + if (reaper == father) { + reaper = child_reaper; + break; + } + } while (reaper->exit_state); + + /* + * There are only two places where our children can be: + * + * - in our child list + * - in our ptraced child list + * + * Search them and reparent children. + */ + list_for_each_safe(_p, _n, &father->children) { + int ptrace; + p = list_entry(_p,struct task_struct,sibling); + + ptrace = p->ptrace; + + /* if father isn't the real parent, then ptrace must be enabled */ + BUG_ON(father != p->real_parent && !ptrace); + + if (father == p->real_parent) { + /* reparent with a reaper, real father it's us */ + choose_new_parent(p, reaper, child_reaper); + reparent_thread(p, father, 0); + } else { + /* reparent ptraced task to its real parent */ + __ptrace_unlink (p); + if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 && + thread_group_empty(p)) + do_notify_parent(p, p->exit_signal); + } + + /* + * if the ptraced child is a zombie with exit_signal == -1 + * we must collect it before we exit, or it will remain + * zombie forever since we prevented it from self-reap itself + * while it was being traced by us, to be able to see it in wait4. + */ + if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && p->exit_signal == -1)) + list_add(&p->ptrace_list, to_release); + } + list_for_each_safe(_p, _n, &father->ptrace_children) { + p = list_entry(_p,struct task_struct,ptrace_list); + choose_new_parent(p, reaper, child_reaper); + reparent_thread(p, father, 1); + } +} + +/* + * Send signals to all our closest relatives so that they know + * to properly mourn us.. + */ +static void exit_notify(struct task_struct *tsk) +{ + int state; + struct task_struct *t; + struct list_head ptrace_dead, *_p, *_n; + + if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT) + && !thread_group_empty(tsk)) { + /* + * This occurs when there was a race between our exit + * syscall and a group signal choosing us as the one to + * wake up. It could be that we are the only thread + * alerted to check for pending signals, but another thread + * should be woken now to take the signal since we will not. + * Now we'll wake all the threads in the group just to make + * sure someone gets all the pending signals. + */ + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + for (t = next_thread(tsk); t != tsk; t = next_thread(t)) + if (!signal_pending(t) && !(t->flags & PF_EXITING)) { + recalc_sigpending_tsk(t); + if (signal_pending(t)) + signal_wake_up(t, 0); + } + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + } + + write_lock_irq(&tasklist_lock); + + /* + * This does two things: + * + * A. Make init inherit all the child processes + * B. Check to see if any process groups have become orphaned + * as a result of our exiting, and if they have any stopped + * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) + */ + + INIT_LIST_HEAD(&ptrace_dead); + forget_original_parent(tsk, &ptrace_dead); + BUG_ON(!list_empty(&tsk->children)); + BUG_ON(!list_empty(&tsk->ptrace_children)); + + /* + * Check to see if any process groups have become orphaned + * as a result of our exiting, and if they have any stopped + * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) + * + * Case i: Our father is in a different pgrp than we are + * and we were the only connection outside, so our pgrp + * is about to become orphaned. + */ + + t = tsk->real_parent; + + if ((process_group(t) != process_group(tsk)) && + (t->signal->session == tsk->signal->session) && + will_become_orphaned_pgrp(process_group(tsk), tsk) && + has_stopped_jobs(process_group(tsk))) { + __kill_pg_info(SIGHUP, (void *)1, process_group(tsk)); + __kill_pg_info(SIGCONT, (void *)1, process_group(tsk)); + } + + /* Let father know we died + * + * Thread signals are configurable, but you aren't going to use + * that to send signals to arbitary processes. + * That stops right now. + * + * If the parent exec id doesn't match the exec id we saved + * when we started then we know the parent has changed security + * domain. + * + * If our self_exec id doesn't match our parent_exec_id then + * we have changed execution domain as these two values started + * the same after a fork. + * + */ + + if (tsk->exit_signal != SIGCHLD && tsk->exit_signal != -1 && + ( tsk->parent_exec_id != t->self_exec_id || + tsk->self_exec_id != tsk->parent_exec_id) + && !capable(CAP_KILL)) + tsk->exit_signal = SIGCHLD; + + + /* If something other than our normal parent is ptracing us, then + * send it a SIGCHLD instead of honoring exit_signal. exit_signal + * only has special meaning to our real parent. + */ + if (tsk->exit_signal != -1 && thread_group_empty(tsk)) { + int signal = tsk->parent == tsk->real_parent ? tsk->exit_signal : SIGCHLD; + do_notify_parent(tsk, signal); + } else if (tsk->ptrace) { + do_notify_parent(tsk, SIGCHLD); + } + + state = EXIT_ZOMBIE; + if (tsk->exit_signal == -1 && + (likely(tsk->ptrace == 0) || + unlikely(tsk->parent->signal->flags & SIGNAL_GROUP_EXIT))) + state = EXIT_DEAD; + tsk->exit_state = state; + + write_unlock_irq(&tasklist_lock); + + list_for_each_safe(_p, _n, &ptrace_dead) { + list_del_init(_p); + t = list_entry(_p,struct task_struct,ptrace_list); + release_task(t); + } + + /* If the process is dead, release it - nobody will wait for it */ + if (state == EXIT_DEAD) + release_task(tsk); + + /* PF_DEAD causes final put_task_struct after we schedule. */ + preempt_disable(); + tsk->flags |= PF_DEAD; +} + +fastcall NORET_TYPE void do_exit(long code) +{ + struct task_struct *tsk = current; + int group_dead; + + profile_task_exit(tsk); + + if (unlikely(in_interrupt())) + panic("Aiee, killing interrupt handler!"); + if (unlikely(!tsk->pid)) + panic("Attempted to kill the idle task!"); + if (unlikely(tsk->pid == 1)) + panic("Attempted to kill init!"); + if (tsk->io_context) + exit_io_context(); + + if (unlikely(current->ptrace & PT_TRACE_EXIT)) { + current->ptrace_message = code; + ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP); + } + + tsk->flags |= PF_EXITING; + + /* + * Make sure we don't try to process any timer firings + * while we are already exiting. + */ + tsk->it_virt_expires = cputime_zero; + tsk->it_prof_expires = cputime_zero; + tsk->it_sched_expires = 0; + + if (unlikely(in_atomic())) + printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", + current->comm, current->pid, + preempt_count()); + + acct_update_integrals(tsk); + update_mem_hiwater(tsk); + group_dead = atomic_dec_and_test(&tsk->signal->live); + if (group_dead) { + del_timer_sync(&tsk->signal->real_timer); + acct_process(code); + } + exit_mm(tsk); + + exit_sem(tsk); + __exit_files(tsk); + __exit_fs(tsk); + exit_namespace(tsk); + exit_thread(); + cpuset_exit(tsk); + exit_keys(tsk); + + if (group_dead && tsk->signal->leader) + disassociate_ctty(1); + + module_put(tsk->thread_info->exec_domain->module); + if (tsk->binfmt) + module_put(tsk->binfmt->module); + + tsk->exit_code = code; + exit_notify(tsk); +#ifdef CONFIG_NUMA + mpol_free(tsk->mempolicy); + tsk->mempolicy = NULL; +#endif + + BUG_ON(!(current->flags & PF_DEAD)); + schedule(); + BUG(); + /* Avoid "noreturn function does return". */ + for (;;) ; +} + +NORET_TYPE void complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + do_exit(code); +} + +EXPORT_SYMBOL(complete_and_exit); + +asmlinkage long sys_exit(int error_code) +{ + do_exit((error_code&0xff)<<8); +} + +task_t fastcall *next_thread(const task_t *p) +{ + return pid_task(p->pids[PIDTYPE_TGID].pid_list.next, PIDTYPE_TGID); +} + +EXPORT_SYMBOL(next_thread); + +/* + * Take down every thread in the group. This is called by fatal signals + * as well as by sys_exit_group (below). + */ +NORET_TYPE void +do_group_exit(int exit_code) +{ + BUG_ON(exit_code & 0x80); /* core dumps don't get here */ + + if (current->signal->flags & SIGNAL_GROUP_EXIT) + exit_code = current->signal->group_exit_code; + else if (!thread_group_empty(current)) { + struct signal_struct *const sig = current->signal; + struct sighand_struct *const sighand = current->sighand; + read_lock(&tasklist_lock); + spin_lock_irq(&sighand->siglock); + if (sig->flags & SIGNAL_GROUP_EXIT) + /* Another thread got here before we took the lock. */ + exit_code = sig->group_exit_code; + else { + sig->flags = SIGNAL_GROUP_EXIT; + sig->group_exit_code = exit_code; + zap_other_threads(current); + } + spin_unlock_irq(&sighand->siglock); + read_unlock(&tasklist_lock); + } + + do_exit(exit_code); + /* NOTREACHED */ +} + +/* + * this kills every thread in the thread group. Note that any externally + * wait4()-ing process will get the correct exit code - even if this + * thread is not the thread group leader. + */ +asmlinkage void sys_exit_group(int error_code) +{ + do_group_exit((error_code & 0xff) << 8); +} + +static int eligible_child(pid_t pid, int options, task_t *p) +{ + if (pid > 0) { + if (p->pid != pid) + return 0; + } else if (!pid) { + if (process_group(p) != process_group(current)) + return 0; + } else if (pid != -1) { + if (process_group(p) != -pid) + return 0; + } + + /* + * Do not consider detached threads that are + * not ptraced: + */ + if (p->exit_signal == -1 && !p->ptrace) + return 0; + + /* Wait for all children (clone and not) if __WALL is set; + * otherwise, wait for clone children *only* if __WCLONE is + * set; otherwise, wait for non-clone children *only*. (Note: + * A "clone" child here is one that reports to its parent + * using a signal other than SIGCHLD.) */ + if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0)) + && !(options & __WALL)) + return 0; + /* + * Do not consider thread group leaders that are + * in a non-empty thread group: + */ + if (current->tgid != p->tgid && delay_group_leader(p)) + return 2; + + if (security_task_wait(p)) + return 0; + + return 1; +} + +static int wait_noreap_copyout(task_t *p, pid_t pid, uid_t uid, + int why, int status, + struct siginfo __user *infop, + struct rusage __user *rusagep) +{ + int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + put_task_struct(p); + if (!retval) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval) + retval = put_user(0, &infop->si_errno); + if (!retval) + retval = put_user((short)why, &infop->si_code); + if (!retval) + retval = put_user(pid, &infop->si_pid); + if (!retval) + retval = put_user(uid, &infop->si_uid); + if (!retval) + retval = put_user(status, &infop->si_status); + if (!retval) + retval = pid; + return retval; +} + +/* + * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold + * read_lock(&tasklist_lock) on entry. If we return zero, we still hold + * the lock and this task is uninteresting. If we return nonzero, we have + * released the lock and the system call should return. + */ +static int wait_task_zombie(task_t *p, int noreap, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) +{ + unsigned long state; + int retval; + int status; + + if (unlikely(noreap)) { + pid_t pid = p->pid; + uid_t uid = p->uid; + int exit_code = p->exit_code; + int why, status; + + if (unlikely(p->exit_state != EXIT_ZOMBIE)) + return 0; + if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) + return 0; + get_task_struct(p); + read_unlock(&tasklist_lock); + if ((exit_code & 0x7f) == 0) { + why = CLD_EXITED; + status = exit_code >> 8; + } else { + why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; + status = exit_code & 0x7f; + } + return wait_noreap_copyout(p, pid, uid, why, + status, infop, ru); + } + + /* + * Try to move the task's state to DEAD + * only one thread is allowed to do this: + */ + state = xchg(&p->exit_state, EXIT_DEAD); + if (state != EXIT_ZOMBIE) { + BUG_ON(state != EXIT_DEAD); + return 0; + } + if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) { + /* + * This can only happen in a race with a ptraced thread + * dying on another processor. + */ + return 0; + } + + if (likely(p->real_parent == p->parent) && likely(p->signal)) { + /* + * The resource counters for the group leader are in its + * own task_struct. Those for dead threads in the group + * are in its signal_struct, as are those for the child + * processes it has previously reaped. All these + * accumulate in the parent's signal_struct c* fields. + * + * We don't bother to take a lock here to protect these + * p->signal fields, because they are only touched by + * __exit_signal, which runs with tasklist_lock + * write-locked anyway, and so is excluded here. We do + * need to protect the access to p->parent->signal fields, + * as other threads in the parent group can be right + * here reaping other children at the same time. + */ + spin_lock_irq(&p->parent->sighand->siglock); + p->parent->signal->cutime = + cputime_add(p->parent->signal->cutime, + cputime_add(p->utime, + cputime_add(p->signal->utime, + p->signal->cutime))); + p->parent->signal->cstime = + cputime_add(p->parent->signal->cstime, + cputime_add(p->stime, + cputime_add(p->signal->stime, + p->signal->cstime))); + p->parent->signal->cmin_flt += + p->min_flt + p->signal->min_flt + p->signal->cmin_flt; + p->parent->signal->cmaj_flt += + p->maj_flt + p->signal->maj_flt + p->signal->cmaj_flt; + p->parent->signal->cnvcsw += + p->nvcsw + p->signal->nvcsw + p->signal->cnvcsw; + p->parent->signal->cnivcsw += + p->nivcsw + p->signal->nivcsw + p->signal->cnivcsw; + spin_unlock_irq(&p->parent->sighand->siglock); + } + + /* + * Now we are sure this task is interesting, and no other + * thread can reap it because we set its state to EXIT_DEAD. + */ + read_unlock(&tasklist_lock); + + retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + status = (p->signal->flags & SIGNAL_GROUP_EXIT) + ? p->signal->group_exit_code : p->exit_code; + if (!retval && stat_addr) + retval = put_user(status, stat_addr); + if (!retval && infop) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval && infop) + retval = put_user(0, &infop->si_errno); + if (!retval && infop) { + int why; + + if ((status & 0x7f) == 0) { + why = CLD_EXITED; + status >>= 8; + } else { + why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; + status &= 0x7f; + } + retval = put_user((short)why, &infop->si_code); + if (!retval) + retval = put_user(status, &infop->si_status); + } + if (!retval && infop) + retval = put_user(p->pid, &infop->si_pid); + if (!retval && infop) + retval = put_user(p->uid, &infop->si_uid); + if (retval) { + // TODO: is this safe? + p->exit_state = EXIT_ZOMBIE; + return retval; + } + retval = p->pid; + if (p->real_parent != p->parent) { + write_lock_irq(&tasklist_lock); + /* Double-check with lock held. */ + if (p->real_parent != p->parent) { + __ptrace_unlink(p); + // TODO: is this safe? + p->exit_state = EXIT_ZOMBIE; + /* + * If this is not a detached task, notify the parent. + * If it's still not detached after that, don't release + * it now. + */ + if (p->exit_signal != -1) { + do_notify_parent(p, p->exit_signal); + if (p->exit_signal != -1) + p = NULL; + } + } + write_unlock_irq(&tasklist_lock); + } + if (p != NULL) + release_task(p); + BUG_ON(!retval); + return retval; +} + +/* + * Handle sys_wait4 work for one task in state TASK_STOPPED. We hold + * read_lock(&tasklist_lock) on entry. If we return zero, we still hold + * the lock and this task is uninteresting. If we return nonzero, we have + * released the lock and the system call should return. + */ +static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) +{ + int retval, exit_code; + + if (!p->exit_code) + return 0; + if (delayed_group_leader && !(p->ptrace & PT_PTRACED) && + p->signal && p->signal->group_stop_count > 0) + /* + * A group stop is in progress and this is the group leader. + * We won't report until all threads have stopped. + */ + return 0; + + /* + * Now we are pretty sure this task is interesting. + * Make sure it doesn't get reaped out from under us while we + * give up the lock and then examine it below. We don't want to + * keep holding onto the tasklist_lock while we call getrusage and + * possibly take page faults for user memory. + */ + get_task_struct(p); + read_unlock(&tasklist_lock); + + if (unlikely(noreap)) { + pid_t pid = p->pid; + uid_t uid = p->uid; + int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED; + + exit_code = p->exit_code; + if (unlikely(!exit_code) || + unlikely(p->state > TASK_STOPPED)) + goto bail_ref; + return wait_noreap_copyout(p, pid, uid, + why, (exit_code << 8) | 0x7f, + infop, ru); + } + + write_lock_irq(&tasklist_lock); + + /* + * This uses xchg to be atomic with the thread resuming and setting + * it. It must also be done with the write lock held to prevent a + * race with the EXIT_ZOMBIE case. + */ + exit_code = xchg(&p->exit_code, 0); + if (unlikely(p->exit_state)) { + /* + * The task resumed and then died. Let the next iteration + * catch it in EXIT_ZOMBIE. Note that exit_code might + * already be zero here if it resumed and did _exit(0). + * The task itself is dead and won't touch exit_code again; + * other processors in this function are locked out. + */ + p->exit_code = exit_code; + exit_code = 0; + } + if (unlikely(exit_code == 0)) { + /* + * Another thread in this function got to it first, or it + * resumed, or it resumed and then died. + */ + write_unlock_irq(&tasklist_lock); +bail_ref: + put_task_struct(p); + /* + * We are returning to the wait loop without having successfully + * removed the process and having released the lock. We cannot + * continue, since the "p" task pointer is potentially stale. + * + * Return -EAGAIN, and do_wait() will restart the loop from the + * beginning. Do _not_ re-acquire the lock. + */ + return -EAGAIN; + } + + /* move to end of parent's list to avoid starvation */ + remove_parent(p); + add_parent(p, p->parent); + + write_unlock_irq(&tasklist_lock); + + retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + if (!retval && stat_addr) + retval = put_user((exit_code << 8) | 0x7f, stat_addr); + if (!retval && infop) + retval = put_user(SIGCHLD, &infop->si_signo); + if (!retval && infop) + retval = put_user(0, &infop->si_errno); + if (!retval && infop) + retval = put_user((short)((p->ptrace & PT_PTRACED) + ? CLD_TRAPPED : CLD_STOPPED), + &infop->si_code); + if (!retval && infop) + retval = put_user(exit_code, &infop->si_status); + if (!retval && infop) + retval = put_user(p->pid, &infop->si_pid); + if (!retval && infop) + retval = put_user(p->uid, &infop->si_uid); + if (!retval) + retval = p->pid; + put_task_struct(p); + + BUG_ON(!retval); + return retval; +} + +/* + * Handle do_wait work for one task in a live, non-stopped state. + * read_lock(&tasklist_lock) on entry. If we return zero, we still hold + * the lock and this task is uninteresting. If we return nonzero, we have + * released the lock and the system call should return. + */ +static int wait_task_continued(task_t *p, int noreap, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) +{ + int retval; + pid_t pid; + uid_t uid; + + if (unlikely(!p->signal)) + return 0; + + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) + return 0; + + spin_lock_irq(&p->sighand->siglock); + /* Re-check with the lock held. */ + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { + spin_unlock_irq(&p->sighand->siglock); + return 0; + } + if (!noreap) + p->signal->flags &= ~SIGNAL_STOP_CONTINUED; + spin_unlock_irq(&p->sighand->siglock); + + pid = p->pid; + uid = p->uid; + get_task_struct(p); + read_unlock(&tasklist_lock); + + if (!infop) { + retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + put_task_struct(p); + if (!retval && stat_addr) + retval = put_user(0xffff, stat_addr); + if (!retval) + retval = p->pid; + } else { + retval = wait_noreap_copyout(p, pid, uid, + CLD_CONTINUED, SIGCONT, + infop, ru); + BUG_ON(retval == 0); + } + + return retval; +} + + +static inline int my_ptrace_child(struct task_struct *p) +{ + if (!(p->ptrace & PT_PTRACED)) + return 0; + if (!(p->ptrace & PT_ATTACHED)) + return 1; + /* + * This child was PTRACE_ATTACH'd. We should be seeing it only if + * we are the attacher. If we are the real parent, this is a race + * inside ptrace_attach. It is waiting for the tasklist_lock, + * which we have to switch the parent links, but has already set + * the flags in p->ptrace. + */ + return (p->parent != p->real_parent); +} + +static long do_wait(pid_t pid, int options, struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) +{ + DECLARE_WAITQUEUE(wait, current); + struct task_struct *tsk; + int flag, retval; + + add_wait_queue(¤t->signal->wait_chldexit,&wait); +repeat: + /* + * We will set this flag if we see any child that might later + * match our criteria, even if we are not able to reap it yet. + */ + flag = 0; + current->state = TASK_INTERRUPTIBLE; + read_lock(&tasklist_lock); + tsk = current; + do { + struct task_struct *p; + struct list_head *_p; + int ret; + + list_for_each(_p,&tsk->children) { + p = list_entry(_p,struct task_struct,sibling); + + ret = eligible_child(pid, options, p); + if (!ret) + continue; + + switch (p->state) { + case TASK_TRACED: + if (!my_ptrace_child(p)) + continue; + /*FALLTHROUGH*/ + case TASK_STOPPED: + /* + * It's stopped now, so it might later + * continue, exit, or stop again. + */ + flag = 1; + if (!(options & WUNTRACED) && + !my_ptrace_child(p)) + continue; + retval = wait_task_stopped(p, ret == 2, + (options & WNOWAIT), + infop, + stat_addr, ru); + if (retval == -EAGAIN) + goto repeat; + if (retval != 0) /* He released the lock. */ + goto end; + break; + default: + // case EXIT_DEAD: + if (p->exit_state == EXIT_DEAD) + continue; + // case EXIT_ZOMBIE: + if (p->exit_state == EXIT_ZOMBIE) { + /* + * Eligible but we cannot release + * it yet: + */ + if (ret == 2) + goto check_continued; + if (!likely(options & WEXITED)) + continue; + retval = wait_task_zombie( + p, (options & WNOWAIT), + infop, stat_addr, ru); + /* He released the lock. */ + if (retval != 0) + goto end; + break; + } +check_continued: + /* + * It's running now, so it might later + * exit, stop, or stop and then continue. + */ + flag = 1; + if (!unlikely(options & WCONTINUED)) + continue; + retval = wait_task_continued( + p, (options & WNOWAIT), + infop, stat_addr, ru); + if (retval != 0) /* He released the lock. */ + goto end; + break; + } + } + if (!flag) { + list_for_each(_p, &tsk->ptrace_children) { + p = list_entry(_p, struct task_struct, + ptrace_list); + if (!eligible_child(pid, options, p)) + continue; + flag = 1; + break; + } + } + if (options & __WNOTHREAD) + break; + tsk = next_thread(tsk); + if (tsk->signal != current->signal) + BUG(); + } while (tsk != current); + + read_unlock(&tasklist_lock); + if (flag) { + retval = 0; + if (options & WNOHANG) + goto end; + retval = -ERESTARTSYS; + if (signal_pending(current)) + goto end; + schedule(); + goto repeat; + } + retval = -ECHILD; +end: + current->state = TASK_RUNNING; + remove_wait_queue(¤t->signal->wait_chldexit,&wait); + if (infop) { + if (retval > 0) + retval = 0; + else { + /* + * For a WNOHANG return, clear out all the fields + * we would set so the user can easily tell the + * difference. + */ + if (!retval) + retval = put_user(0, &infop->si_signo); + if (!retval) + retval = put_user(0, &infop->si_errno); + if (!retval) + retval = put_user(0, &infop->si_code); + if (!retval) + retval = put_user(0, &infop->si_pid); + if (!retval) + retval = put_user(0, &infop->si_uid); + if (!retval) + retval = put_user(0, &infop->si_status); + } + } + return retval; +} + +asmlinkage long sys_waitid(int which, pid_t pid, + struct siginfo __user *infop, int options, + struct rusage __user *ru) +{ + long ret; + + if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED)) + return -EINVAL; + if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) + return -EINVAL; + + switch (which) { + case P_ALL: + pid = -1; + break; + case P_PID: + if (pid <= 0) + return -EINVAL; + break; + case P_PGID: + if (pid <= 0) + return -EINVAL; + pid = -pid; + break; + default: + return -EINVAL; + } + + ret = do_wait(pid, options, infop, NULL, ru); + + /* avoid REGPARM breakage on x86: */ + prevent_tail_call(ret); + return ret; +} + +asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, + int options, struct rusage __user *ru) +{ + long ret; + + if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| + __WNOTHREAD|__WCLONE|__WALL)) + return -EINVAL; + ret = do_wait(pid, options | WEXITED, NULL, stat_addr, ru); + + /* avoid REGPARM breakage on x86: */ + prevent_tail_call(ret); + return ret; +} + +#ifdef __ARCH_WANT_SYS_WAITPID + +/* + * sys_waitpid() remains for compatibility. waitpid() should be + * implemented by calling sys_wait4() from libc.a. + */ +asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options) +{ + return sys_wait4(pid, stat_addr, options, NULL); +} + +#endif diff --git a/kernel/extable.c b/kernel/extable.c new file mode 100644 index 000000000000..7501b531ceed --- /dev/null +++ b/kernel/extable.c @@ -0,0 +1,67 @@ +/* Rewritten by Rusty Russell, on the backs of many others... + Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include + +extern struct exception_table_entry __start___ex_table[]; +extern struct exception_table_entry __stop___ex_table[]; + +/* Sort the kernel's built-in exception table */ +void __init sort_main_extable(void) +{ + sort_extable(__start___ex_table, __stop___ex_table); +} + +/* Given an address, look for it in the exception tables. */ +const struct exception_table_entry *search_exception_tables(unsigned long addr) +{ + const struct exception_table_entry *e; + + e = search_extable(__start___ex_table, __stop___ex_table-1, addr); + if (!e) + e = search_module_extables(addr); + return e; +} + +static int core_kernel_text(unsigned long addr) +{ + if (addr >= (unsigned long)_stext && + addr <= (unsigned long)_etext) + return 1; + + if (addr >= (unsigned long)_sinittext && + addr <= (unsigned long)_einittext) + return 1; + return 0; +} + +int __kernel_text_address(unsigned long addr) +{ + if (core_kernel_text(addr)) + return 1; + return __module_text_address(addr) != NULL; +} + +int kernel_text_address(unsigned long addr) +{ + if (core_kernel_text(addr)) + return 1; + return module_text_address(addr) != NULL; +} diff --git a/kernel/fork.c b/kernel/fork.c new file mode 100644 index 000000000000..f42a17f88699 --- /dev/null +++ b/kernel/fork.c @@ -0,0 +1,1274 @@ +/* + * linux/kernel/fork.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * 'fork.c' contains the help-routines for the 'fork' system call + * (see also entry.S and others). + * Fork is rather simple, once you get the hang of it, but the memory + * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* + * Protected counters by write_lock_irq(&tasklist_lock) + */ +unsigned long total_forks; /* Handle normal Linux uptimes. */ +int nr_threads; /* The idle threads do not count.. */ + +int max_threads; /* tunable limit on nr_threads */ + +DEFINE_PER_CPU(unsigned long, process_counts) = 0; + + __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ + +EXPORT_SYMBOL(tasklist_lock); + +int nr_processes(void) +{ + int cpu; + int total = 0; + + for_each_online_cpu(cpu) + total += per_cpu(process_counts, cpu); + + return total; +} + +#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR +# define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL) +# define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk)) +static kmem_cache_t *task_struct_cachep; +#endif + +/* SLAB cache for signal_struct structures (tsk->signal) */ +kmem_cache_t *signal_cachep; + +/* SLAB cache for sighand_struct structures (tsk->sighand) */ +kmem_cache_t *sighand_cachep; + +/* SLAB cache for files_struct structures (tsk->files) */ +kmem_cache_t *files_cachep; + +/* SLAB cache for fs_struct structures (tsk->fs) */ +kmem_cache_t *fs_cachep; + +/* SLAB cache for vm_area_struct structures */ +kmem_cache_t *vm_area_cachep; + +/* SLAB cache for mm_struct structures (tsk->mm) */ +static kmem_cache_t *mm_cachep; + +void free_task(struct task_struct *tsk) +{ + free_thread_info(tsk->thread_info); + free_task_struct(tsk); +} +EXPORT_SYMBOL(free_task); + +void __put_task_struct(struct task_struct *tsk) +{ + WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE))); + WARN_ON(atomic_read(&tsk->usage)); + WARN_ON(tsk == current); + + if (unlikely(tsk->audit_context)) + audit_free(tsk); + security_task_free(tsk); + free_uid(tsk->user); + put_group_info(tsk->group_info); + + if (!profile_handoff_task(tsk)) + free_task(tsk); +} + +void __init fork_init(unsigned long mempages) +{ +#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR +#ifndef ARCH_MIN_TASKALIGN +#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES +#endif + /* create a slab on which task_structs can be allocated */ + task_struct_cachep = + kmem_cache_create("task_struct", sizeof(struct task_struct), + ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL, NULL); +#endif + + /* + * The default maximum number of threads is set to a safe + * value: the thread structures can take up at most half + * of memory. + */ + max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE); + + /* + * we need to allow at least 20 threads to boot a system + */ + if(max_threads < 20) + max_threads = 20; + + init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; + init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; + init_task.signal->rlim[RLIMIT_SIGPENDING] = + init_task.signal->rlim[RLIMIT_NPROC]; +} + +static struct task_struct *dup_task_struct(struct task_struct *orig) +{ + struct task_struct *tsk; + struct thread_info *ti; + + prepare_to_copy(orig); + + tsk = alloc_task_struct(); + if (!tsk) + return NULL; + + ti = alloc_thread_info(tsk); + if (!ti) { + free_task_struct(tsk); + return NULL; + } + + *ti = *orig->thread_info; + *tsk = *orig; + tsk->thread_info = ti; + ti->task = tsk; + + /* One for us, one for whoever does the "release_task()" (usually parent) */ + atomic_set(&tsk->usage,2); + return tsk; +} + +#ifdef CONFIG_MMU +static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) +{ + struct vm_area_struct * mpnt, *tmp, **pprev; + struct rb_node **rb_link, *rb_parent; + int retval; + unsigned long charge; + struct mempolicy *pol; + + down_write(&oldmm->mmap_sem); + flush_cache_mm(current->mm); + mm->locked_vm = 0; + mm->mmap = NULL; + mm->mmap_cache = NULL; + mm->free_area_cache = oldmm->mmap_base; + mm->map_count = 0; + set_mm_counter(mm, rss, 0); + set_mm_counter(mm, anon_rss, 0); + cpus_clear(mm->cpu_vm_mask); + mm->mm_rb = RB_ROOT; + rb_link = &mm->mm_rb.rb_node; + rb_parent = NULL; + pprev = &mm->mmap; + + for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) { + struct file *file; + + if (mpnt->vm_flags & VM_DONTCOPY) { + __vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, + -vma_pages(mpnt)); + continue; + } + charge = 0; + if (mpnt->vm_flags & VM_ACCOUNT) { + unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT; + if (security_vm_enough_memory(len)) + goto fail_nomem; + charge = len; + } + tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + if (!tmp) + goto fail_nomem; + *tmp = *mpnt; + pol = mpol_copy(vma_policy(mpnt)); + retval = PTR_ERR(pol); + if (IS_ERR(pol)) + goto fail_nomem_policy; + vma_set_policy(tmp, pol); + tmp->vm_flags &= ~VM_LOCKED; + tmp->vm_mm = mm; + tmp->vm_next = NULL; + anon_vma_link(tmp); + file = tmp->vm_file; + if (file) { + struct inode *inode = file->f_dentry->d_inode; + get_file(file); + if (tmp->vm_flags & VM_DENYWRITE) + atomic_dec(&inode->i_writecount); + + /* insert tmp into the share list, just after mpnt */ + spin_lock(&file->f_mapping->i_mmap_lock); + tmp->vm_truncate_count = mpnt->vm_truncate_count; + flush_dcache_mmap_lock(file->f_mapping); + vma_prio_tree_add(tmp, mpnt); + flush_dcache_mmap_unlock(file->f_mapping); + spin_unlock(&file->f_mapping->i_mmap_lock); + } + + /* + * Link in the new vma and copy the page table entries: + * link in first so that swapoff can see swap entries, + * and try_to_unmap_one's find_vma find the new vma. + */ + spin_lock(&mm->page_table_lock); + *pprev = tmp; + pprev = &tmp->vm_next; + + __vma_link_rb(mm, tmp, rb_link, rb_parent); + rb_link = &tmp->vm_rb.rb_right; + rb_parent = &tmp->vm_rb; + + mm->map_count++; + retval = copy_page_range(mm, current->mm, tmp); + spin_unlock(&mm->page_table_lock); + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + + if (retval) + goto out; + } + retval = 0; + +out: + flush_tlb_mm(current->mm); + up_write(&oldmm->mmap_sem); + return retval; +fail_nomem_policy: + kmem_cache_free(vm_area_cachep, tmp); +fail_nomem: + retval = -ENOMEM; + vm_unacct_memory(charge); + goto out; +} + +static inline int mm_alloc_pgd(struct mm_struct * mm) +{ + mm->pgd = pgd_alloc(mm); + if (unlikely(!mm->pgd)) + return -ENOMEM; + return 0; +} + +static inline void mm_free_pgd(struct mm_struct * mm) +{ + pgd_free(mm->pgd); +} +#else +#define dup_mmap(mm, oldmm) (0) +#define mm_alloc_pgd(mm) (0) +#define mm_free_pgd(mm) +#endif /* CONFIG_MMU */ + + __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); + +#define allocate_mm() (kmem_cache_alloc(mm_cachep, SLAB_KERNEL)) +#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) + +#include + +static struct mm_struct * mm_init(struct mm_struct * mm) +{ + atomic_set(&mm->mm_users, 1); + atomic_set(&mm->mm_count, 1); + init_rwsem(&mm->mmap_sem); + INIT_LIST_HEAD(&mm->mmlist); + mm->core_waiters = 0; + mm->nr_ptes = 0; + spin_lock_init(&mm->page_table_lock); + rwlock_init(&mm->ioctx_list_lock); + mm->ioctx_list = NULL; + mm->default_kioctx = (struct kioctx)INIT_KIOCTX(mm->default_kioctx, *mm); + mm->free_area_cache = TASK_UNMAPPED_BASE; + + if (likely(!mm_alloc_pgd(mm))) { + mm->def_flags = 0; + return mm; + } + free_mm(mm); + return NULL; +} + +/* + * Allocate and initialize an mm_struct. + */ +struct mm_struct * mm_alloc(void) +{ + struct mm_struct * mm; + + mm = allocate_mm(); + if (mm) { + memset(mm, 0, sizeof(*mm)); + mm = mm_init(mm); + } + return mm; +} + +/* + * Called when the last reference to the mm + * is dropped: either by a lazy thread or by + * mmput. Free the page directory and the mm. + */ +void fastcall __mmdrop(struct mm_struct *mm) +{ + BUG_ON(mm == &init_mm); + mm_free_pgd(mm); + destroy_context(mm); + free_mm(mm); +} + +/* + * Decrement the use count and release all resources for an mm. + */ +void mmput(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + exit_aio(mm); + exit_mmap(mm); + if (!list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + list_del(&mm->mmlist); + spin_unlock(&mmlist_lock); + } + put_swap_token(mm); + mmdrop(mm); + } +} +EXPORT_SYMBOL_GPL(mmput); + +/** + * get_task_mm - acquire a reference to the task's mm + * + * Returns %NULL if the task has no mm. Checks PF_BORROWED_MM (meaning + * this kernel workthread has transiently adopted a user mm with use_mm, + * to do its AIO) is not set and if so returns a reference to it, after + * bumping up the use count. User must release the mm via mmput() + * after use. Typically used by /proc and ptrace. + */ +struct mm_struct *get_task_mm(struct task_struct *task) +{ + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) { + if (task->flags & PF_BORROWED_MM) + mm = NULL; + else + atomic_inc(&mm->mm_users); + } + task_unlock(task); + return mm; +} +EXPORT_SYMBOL_GPL(get_task_mm); + +/* Please note the differences between mmput and mm_release. + * mmput is called whenever we stop holding onto a mm_struct, + * error success whatever. + * + * mm_release is called after a mm_struct has been removed + * from the current process. + * + * This difference is important for error handling, when we + * only half set up a mm_struct for a new process and need to restore + * the old one. Because we mmput the new mm_struct before + * restoring the old one. . . + * Eric Biederman 10 January 1998 + */ +void mm_release(struct task_struct *tsk, struct mm_struct *mm) +{ + struct completion *vfork_done = tsk->vfork_done; + + /* Get rid of any cached register state */ + deactivate_mm(tsk, mm); + + /* notify parent sleeping on vfork() */ + if (vfork_done) { + tsk->vfork_done = NULL; + complete(vfork_done); + } + if (tsk->clear_child_tid && atomic_read(&mm->mm_users) > 1) { + u32 __user * tidptr = tsk->clear_child_tid; + tsk->clear_child_tid = NULL; + + /* + * We don't check the error code - if userspace has + * not set up a proper pointer then tough luck. + */ + put_user(0, tidptr); + sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0); + } +} + +static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) +{ + struct mm_struct * mm, *oldmm; + int retval; + + tsk->min_flt = tsk->maj_flt = 0; + tsk->nvcsw = tsk->nivcsw = 0; + + tsk->mm = NULL; + tsk->active_mm = NULL; + + /* + * Are we cloning a kernel thread? + * + * We need to steal a active VM for that.. + */ + oldmm = current->mm; + if (!oldmm) + return 0; + + if (clone_flags & CLONE_VM) { + atomic_inc(&oldmm->mm_users); + mm = oldmm; + /* + * There are cases where the PTL is held to ensure no + * new threads start up in user mode using an mm, which + * allows optimizing out ipis; the tlb_gather_mmu code + * is an example. + */ + spin_unlock_wait(&oldmm->page_table_lock); + goto good_mm; + } + + retval = -ENOMEM; + mm = allocate_mm(); + if (!mm) + goto fail_nomem; + + /* Copy the current MM stuff.. */ + memcpy(mm, oldmm, sizeof(*mm)); + if (!mm_init(mm)) + goto fail_nomem; + + if (init_new_context(tsk,mm)) + goto fail_nocontext; + + retval = dup_mmap(mm, oldmm); + if (retval) + goto free_pt; + + mm->hiwater_rss = get_mm_counter(mm,rss); + mm->hiwater_vm = mm->total_vm; + +good_mm: + tsk->mm = mm; + tsk->active_mm = mm; + return 0; + +free_pt: + mmput(mm); +fail_nomem: + return retval; + +fail_nocontext: + /* + * If init_new_context() failed, we cannot use mmput() to free the mm + * because it calls destroy_context() + */ + mm_free_pgd(mm); + free_mm(mm); + return retval; +} + +static inline struct fs_struct *__copy_fs_struct(struct fs_struct *old) +{ + struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); + /* We don't need to lock fs - think why ;-) */ + if (fs) { + atomic_set(&fs->count, 1); + rwlock_init(&fs->lock); + fs->umask = old->umask; + read_lock(&old->lock); + fs->rootmnt = mntget(old->rootmnt); + fs->root = dget(old->root); + fs->pwdmnt = mntget(old->pwdmnt); + fs->pwd = dget(old->pwd); + if (old->altroot) { + fs->altrootmnt = mntget(old->altrootmnt); + fs->altroot = dget(old->altroot); + } else { + fs->altrootmnt = NULL; + fs->altroot = NULL; + } + read_unlock(&old->lock); + } + return fs; +} + +struct fs_struct *copy_fs_struct(struct fs_struct *old) +{ + return __copy_fs_struct(old); +} + +EXPORT_SYMBOL_GPL(copy_fs_struct); + +static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk) +{ + if (clone_flags & CLONE_FS) { + atomic_inc(¤t->fs->count); + return 0; + } + tsk->fs = __copy_fs_struct(current->fs); + if (!tsk->fs) + return -ENOMEM; + return 0; +} + +static int count_open_files(struct files_struct *files, int size) +{ + int i; + + /* Find the last open fd */ + for (i = size/(8*sizeof(long)); i > 0; ) { + if (files->open_fds->fds_bits[--i]) + break; + } + i = (i+1) * 8 * sizeof(long); + return i; +} + +static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +{ + struct files_struct *oldf, *newf; + struct file **old_fds, **new_fds; + int open_files, size, i, error = 0, expand; + + /* + * A background process may not have any files ... + */ + oldf = current->files; + if (!oldf) + goto out; + + if (clone_flags & CLONE_FILES) { + atomic_inc(&oldf->count); + goto out; + } + + /* + * Note: we may be using current for both targets (See exec.c) + * This works because we cache current->files (old) as oldf. Don't + * break this. + */ + tsk->files = NULL; + error = -ENOMEM; + newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL); + if (!newf) + goto out; + + atomic_set(&newf->count, 1); + + spin_lock_init(&newf->file_lock); + newf->next_fd = 0; + newf->max_fds = NR_OPEN_DEFAULT; + newf->max_fdset = __FD_SETSIZE; + newf->close_on_exec = &newf->close_on_exec_init; + newf->open_fds = &newf->open_fds_init; + newf->fd = &newf->fd_array[0]; + + spin_lock(&oldf->file_lock); + + open_files = count_open_files(oldf, oldf->max_fdset); + expand = 0; + + /* + * Check whether we need to allocate a larger fd array or fd set. + * Note: we're not a clone task, so the open count won't change. + */ + if (open_files > newf->max_fdset) { + newf->max_fdset = 0; + expand = 1; + } + if (open_files > newf->max_fds) { + newf->max_fds = 0; + expand = 1; + } + + /* if the old fdset gets grown now, we'll only copy up to "size" fds */ + if (expand) { + spin_unlock(&oldf->file_lock); + spin_lock(&newf->file_lock); + error = expand_files(newf, open_files-1); + spin_unlock(&newf->file_lock); + if (error < 0) + goto out_release; + spin_lock(&oldf->file_lock); + } + + old_fds = oldf->fd; + new_fds = newf->fd; + + memcpy(newf->open_fds->fds_bits, oldf->open_fds->fds_bits, open_files/8); + memcpy(newf->close_on_exec->fds_bits, oldf->close_on_exec->fds_bits, open_files/8); + + for (i = open_files; i != 0; i--) { + struct file *f = *old_fds++; + if (f) { + get_file(f); + } else { + /* + * The fd may be claimed in the fd bitmap but not yet + * instantiated in the files array if a sibling thread + * is partway through open(). So make sure that this + * fd is available to the new process. + */ + FD_CLR(open_files - i, newf->open_fds); + } + *new_fds++ = f; + } + spin_unlock(&oldf->file_lock); + + /* compute the remainder to be cleared */ + size = (newf->max_fds - open_files) * sizeof(struct file *); + + /* This is long word aligned thus could use a optimized version */ + memset(new_fds, 0, size); + + if (newf->max_fdset > open_files) { + int left = (newf->max_fdset-open_files)/8; + int start = open_files / (8 * sizeof(unsigned long)); + + memset(&newf->open_fds->fds_bits[start], 0, left); + memset(&newf->close_on_exec->fds_bits[start], 0, left); + } + + tsk->files = newf; + error = 0; +out: + return error; + +out_release: + free_fdset (newf->close_on_exec, newf->max_fdset); + free_fdset (newf->open_fds, newf->max_fdset); + free_fd_array(newf->fd, newf->max_fds); + kmem_cache_free(files_cachep, newf); + goto out; +} + +/* + * Helper to unshare the files of the current task. + * We don't want to expose copy_files internals to + * the exec layer of the kernel. + */ + +int unshare_files(void) +{ + struct files_struct *files = current->files; + int rc; + + if(!files) + BUG(); + + /* This can race but the race causes us to copy when we don't + need to and drop the copy */ + if(atomic_read(&files->count) == 1) + { + atomic_inc(&files->count); + return 0; + } + rc = copy_files(0, current); + if(rc) + current->files = files; + return rc; +} + +EXPORT_SYMBOL(unshare_files); + +static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk) +{ + struct sighand_struct *sig; + + if (clone_flags & (CLONE_SIGHAND | CLONE_THREAD)) { + atomic_inc(¤t->sighand->count); + return 0; + } + sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); + tsk->sighand = sig; + if (!sig) + return -ENOMEM; + spin_lock_init(&sig->siglock); + atomic_set(&sig->count, 1); + memcpy(sig->action, current->sighand->action, sizeof(sig->action)); + return 0; +} + +static inline int copy_signal(unsigned long clone_flags, struct task_struct * tsk) +{ + struct signal_struct *sig; + int ret; + + if (clone_flags & CLONE_THREAD) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + return 0; + } + sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); + tsk->signal = sig; + if (!sig) + return -ENOMEM; + + ret = copy_thread_group_keys(tsk); + if (ret < 0) { + kmem_cache_free(signal_cachep, sig); + return ret; + } + + atomic_set(&sig->count, 1); + atomic_set(&sig->live, 1); + init_waitqueue_head(&sig->wait_chldexit); + sig->flags = 0; + sig->group_exit_code = 0; + sig->group_exit_task = NULL; + sig->group_stop_count = 0; + sig->curr_target = NULL; + init_sigpending(&sig->shared_pending); + INIT_LIST_HEAD(&sig->posix_timers); + + sig->it_real_value = sig->it_real_incr = 0; + sig->real_timer.function = it_real_fn; + sig->real_timer.data = (unsigned long) tsk; + init_timer(&sig->real_timer); + + sig->it_virt_expires = cputime_zero; + sig->it_virt_incr = cputime_zero; + sig->it_prof_expires = cputime_zero; + sig->it_prof_incr = cputime_zero; + + sig->tty = current->signal->tty; + sig->pgrp = process_group(current); + sig->session = current->signal->session; + sig->leader = 0; /* session leadership doesn't inherit */ + sig->tty_old_pgrp = 0; + + sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; + sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; + sig->sched_time = 0; + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); + + task_lock(current->group_leader); + memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); + task_unlock(current->group_leader); + + if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { + /* + * New sole thread in the process gets an expiry time + * of the whole CPU time limit. + */ + tsk->it_prof_expires = + secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); + } + + return 0; +} + +static inline void copy_flags(unsigned long clone_flags, struct task_struct *p) +{ + unsigned long new_flags = p->flags; + + new_flags &= ~PF_SUPERPRIV; + new_flags |= PF_FORKNOEXEC; + if (!(clone_flags & CLONE_PTRACE)) + p->ptrace = 0; + p->flags = new_flags; +} + +asmlinkage long sys_set_tid_address(int __user *tidptr) +{ + current->clear_child_tid = tidptr; + + return current->pid; +} + +/* + * This creates a new process as a copy of the old one, + * but does not actually start it yet. + * + * It copies the registers, and all the appropriate + * parts of the process environment (as per the clone + * flags). The actual kick-off is left to the caller. + */ +static task_t *copy_process(unsigned long clone_flags, + unsigned long stack_start, + struct pt_regs *regs, + unsigned long stack_size, + int __user *parent_tidptr, + int __user *child_tidptr, + int pid) +{ + int retval; + struct task_struct *p = NULL; + + if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) + return ERR_PTR(-EINVAL); + + /* + * Thread groups must share signals as well, and detached threads + * can only be started up within the thread group. + */ + if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) + return ERR_PTR(-EINVAL); + + /* + * Shared signal handlers imply shared VM. By way of the above, + * thread groups also imply shared VM. Blocking this case allows + * for various simplifications in other code. + */ + if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) + return ERR_PTR(-EINVAL); + + retval = security_task_create(clone_flags); + if (retval) + goto fork_out; + + retval = -ENOMEM; + p = dup_task_struct(current); + if (!p) + goto fork_out; + + retval = -EAGAIN; + if (atomic_read(&p->user->processes) >= + p->signal->rlim[RLIMIT_NPROC].rlim_cur) { + if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && + p->user != &root_user) + goto bad_fork_free; + } + + atomic_inc(&p->user->__count); + atomic_inc(&p->user->processes); + get_group_info(p->group_info); + + /* + * If multiple threads are within copy_process(), then this check + * triggers too late. This doesn't hurt, the check is only there + * to stop root fork bombs. + */ + if (nr_threads >= max_threads) + goto bad_fork_cleanup_count; + + if (!try_module_get(p->thread_info->exec_domain->module)) + goto bad_fork_cleanup_count; + + if (p->binfmt && !try_module_get(p->binfmt->module)) + goto bad_fork_cleanup_put_domain; + + p->did_exec = 0; + copy_flags(clone_flags, p); + p->pid = pid; + retval = -EFAULT; + if (clone_flags & CLONE_PARENT_SETTID) + if (put_user(p->pid, parent_tidptr)) + goto bad_fork_cleanup; + + p->proc_dentry = NULL; + + INIT_LIST_HEAD(&p->children); + INIT_LIST_HEAD(&p->sibling); + p->vfork_done = NULL; + spin_lock_init(&p->alloc_lock); + spin_lock_init(&p->proc_lock); + + clear_tsk_thread_flag(p, TIF_SIGPENDING); + init_sigpending(&p->pending); + + p->utime = cputime_zero; + p->stime = cputime_zero; + p->sched_time = 0; + p->rchar = 0; /* I/O counter: bytes read */ + p->wchar = 0; /* I/O counter: bytes written */ + p->syscr = 0; /* I/O counter: read syscalls */ + p->syscw = 0; /* I/O counter: write syscalls */ + acct_clear_integrals(p); + + p->it_virt_expires = cputime_zero; + p->it_prof_expires = cputime_zero; + p->it_sched_expires = 0; + INIT_LIST_HEAD(&p->cpu_timers[0]); + INIT_LIST_HEAD(&p->cpu_timers[1]); + INIT_LIST_HEAD(&p->cpu_timers[2]); + + p->lock_depth = -1; /* -1 = no lock */ + do_posix_clock_monotonic_gettime(&p->start_time); + p->security = NULL; + p->io_context = NULL; + p->io_wait = NULL; + p->audit_context = NULL; +#ifdef CONFIG_NUMA + p->mempolicy = mpol_copy(p->mempolicy); + if (IS_ERR(p->mempolicy)) { + retval = PTR_ERR(p->mempolicy); + p->mempolicy = NULL; + goto bad_fork_cleanup; + } +#endif + + p->tgid = p->pid; + if (clone_flags & CLONE_THREAD) + p->tgid = current->tgid; + + if ((retval = security_task_alloc(p))) + goto bad_fork_cleanup_policy; + if ((retval = audit_alloc(p))) + goto bad_fork_cleanup_security; + /* copy all the process information */ + if ((retval = copy_semundo(clone_flags, p))) + goto bad_fork_cleanup_audit; + if ((retval = copy_files(clone_flags, p))) + goto bad_fork_cleanup_semundo; + if ((retval = copy_fs(clone_flags, p))) + goto bad_fork_cleanup_files; + if ((retval = copy_sighand(clone_flags, p))) + goto bad_fork_cleanup_fs; + if ((retval = copy_signal(clone_flags, p))) + goto bad_fork_cleanup_sighand; + if ((retval = copy_mm(clone_flags, p))) + goto bad_fork_cleanup_signal; + if ((retval = copy_keys(clone_flags, p))) + goto bad_fork_cleanup_mm; + if ((retval = copy_namespace(clone_flags, p))) + goto bad_fork_cleanup_keys; + retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); + if (retval) + goto bad_fork_cleanup_namespace; + + p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; + /* + * Clear TID on mm_release()? + */ + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; + + /* + * Syscall tracing should be turned off in the child regardless + * of CLONE_PTRACE. + */ + clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); + + /* Our parent execution domain becomes current domain + These must match for thread signalling to apply */ + + p->parent_exec_id = p->self_exec_id; + + /* ok, now we should be set up.. */ + p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); + p->pdeath_signal = 0; + p->exit_state = 0; + + /* Perform scheduler related setup */ + sched_fork(p); + + /* + * Ok, make it visible to the rest of the system. + * We dont wake it up yet. + */ + p->group_leader = p; + INIT_LIST_HEAD(&p->ptrace_children); + INIT_LIST_HEAD(&p->ptrace_list); + + /* Need tasklist lock for parent etc handling! */ + write_lock_irq(&tasklist_lock); + + /* + * The task hasn't been attached yet, so cpus_allowed mask cannot + * have changed. The cpus_allowed mask of the parent may have + * changed after it was copied first time, and it may then move to + * another CPU - so we re-copy it here and set the child's CPU to + * the parent's CPU. This avoids alot of nasty races. + */ + p->cpus_allowed = current->cpus_allowed; + set_task_cpu(p, smp_processor_id()); + + /* + * Check for pending SIGKILL! The new thread should not be allowed + * to slip out of an OOM kill. (or normal SIGKILL.) + */ + if (sigismember(¤t->pending.signal, SIGKILL)) { + write_unlock_irq(&tasklist_lock); + retval = -EINTR; + goto bad_fork_cleanup_namespace; + } + + /* CLONE_PARENT re-uses the old parent */ + if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) + p->real_parent = current->real_parent; + else + p->real_parent = current; + p->parent = p->real_parent; + + if (clone_flags & CLONE_THREAD) { + spin_lock(¤t->sighand->siglock); + /* + * Important: if an exit-all has been started then + * do not create this new thread - the whole thread + * group is supposed to exit anyway. + */ + if (current->signal->flags & SIGNAL_GROUP_EXIT) { + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); + retval = -EAGAIN; + goto bad_fork_cleanup_namespace; + } + p->group_leader = current->group_leader; + + if (current->signal->group_stop_count > 0) { + /* + * There is an all-stop in progress for the group. + * We ourselves will stop as soon as we check signals. + * Make the new thread part of that group stop too. + */ + current->signal->group_stop_count++; + set_tsk_thread_flag(p, TIF_SIGPENDING); + } + + if (!cputime_eq(current->signal->it_virt_expires, + cputime_zero) || + !cputime_eq(current->signal->it_prof_expires, + cputime_zero) || + current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || + !list_empty(¤t->signal->cpu_timers[0]) || + !list_empty(¤t->signal->cpu_timers[1]) || + !list_empty(¤t->signal->cpu_timers[2])) { + /* + * Have child wake up on its first tick to check + * for process CPU timers. + */ + p->it_prof_expires = jiffies_to_cputime(1); + } + + spin_unlock(¤t->sighand->siglock); + } + + SET_LINKS(p); + if (unlikely(p->ptrace & PT_PTRACED)) + __ptrace_link(p, current->parent); + + cpuset_fork(p); + + attach_pid(p, PIDTYPE_PID, p->pid); + attach_pid(p, PIDTYPE_TGID, p->tgid); + if (thread_group_leader(p)) { + attach_pid(p, PIDTYPE_PGID, process_group(p)); + attach_pid(p, PIDTYPE_SID, p->signal->session); + if (p->pid) + __get_cpu_var(process_counts)++; + } + + nr_threads++; + total_forks++; + write_unlock_irq(&tasklist_lock); + retval = 0; + +fork_out: + if (retval) + return ERR_PTR(retval); + return p; + +bad_fork_cleanup_namespace: + exit_namespace(p); +bad_fork_cleanup_keys: + exit_keys(p); +bad_fork_cleanup_mm: + if (p->mm) + mmput(p->mm); +bad_fork_cleanup_signal: + exit_signal(p); +bad_fork_cleanup_sighand: + exit_sighand(p); +bad_fork_cleanup_fs: + exit_fs(p); /* blocking */ +bad_fork_cleanup_files: + exit_files(p); /* blocking */ +bad_fork_cleanup_semundo: + exit_sem(p); +bad_fork_cleanup_audit: + audit_free(p); +bad_fork_cleanup_security: + security_task_free(p); +bad_fork_cleanup_policy: +#ifdef CONFIG_NUMA + mpol_free(p->mempolicy); +#endif +bad_fork_cleanup: + if (p->binfmt) + module_put(p->binfmt->module); +bad_fork_cleanup_put_domain: + module_put(p->thread_info->exec_domain->module); +bad_fork_cleanup_count: + put_group_info(p->group_info); + atomic_dec(&p->user->processes); + free_uid(p->user); +bad_fork_free: + free_task(p); + goto fork_out; +} + +struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs) +{ + memset(regs, 0, sizeof(struct pt_regs)); + return regs; +} + +task_t * __devinit fork_idle(int cpu) +{ + task_t *task; + struct pt_regs regs; + + task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, NULL, 0); + if (!task) + return ERR_PTR(-ENOMEM); + init_idle(task, cpu); + unhash_process(task); + return task; +} + +static inline int fork_traceflag (unsigned clone_flags) +{ + if (clone_flags & CLONE_UNTRACED) + return 0; + else if (clone_flags & CLONE_VFORK) { + if (current->ptrace & PT_TRACE_VFORK) + return PTRACE_EVENT_VFORK; + } else if ((clone_flags & CSIGNAL) != SIGCHLD) { + if (current->ptrace & PT_TRACE_CLONE) + return PTRACE_EVENT_CLONE; + } else if (current->ptrace & PT_TRACE_FORK) + return PTRACE_EVENT_FORK; + + return 0; +} + +/* + * Ok, this is the main fork-routine. + * + * It copies the process, and if successful kick-starts + * it and waits for it to finish using the VM if required. + */ +long do_fork(unsigned long clone_flags, + unsigned long stack_start, + struct pt_regs *regs, + unsigned long stack_size, + int __user *parent_tidptr, + int __user *child_tidptr) +{ + struct task_struct *p; + int trace = 0; + long pid = alloc_pidmap(); + + if (pid < 0) + return -EAGAIN; + if (unlikely(current->ptrace)) { + trace = fork_traceflag (clone_flags); + if (trace) + clone_flags |= CLONE_PTRACE; + } + + p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, pid); + /* + * Do this prior waking up the new thread - the thread pointer + * might get invalid after that point, if the thread exits quickly. + */ + if (!IS_ERR(p)) { + struct completion vfork; + + if (clone_flags & CLONE_VFORK) { + p->vfork_done = &vfork; + init_completion(&vfork); + } + + if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) { + /* + * We'll start up with an immediate SIGSTOP. + */ + sigaddset(&p->pending.signal, SIGSTOP); + set_tsk_thread_flag(p, TIF_SIGPENDING); + } + + if (!(clone_flags & CLONE_STOPPED)) + wake_up_new_task(p, clone_flags); + else + p->state = TASK_STOPPED; + + if (unlikely (trace)) { + current->ptrace_message = pid; + ptrace_notify ((trace << 8) | SIGTRAP); + } + + if (clone_flags & CLONE_VFORK) { + wait_for_completion(&vfork); + if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) + ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); + } + } else { + free_pidmap(pid); + pid = PTR_ERR(p); + } + return pid; +} + +void __init proc_caches_init(void) +{ + sighand_cachep = kmem_cache_create("sighand_cache", + sizeof(struct sighand_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + signal_cachep = kmem_cache_create("signal_cache", + sizeof(struct signal_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + files_cachep = kmem_cache_create("files_cache", + sizeof(struct files_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + fs_cachep = kmem_cache_create("fs_cache", + sizeof(struct fs_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL, NULL); + mm_cachep = kmem_cache_create("mm_struct", + sizeof(struct mm_struct), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); +} diff --git a/kernel/futex.c b/kernel/futex.c new file mode 100644 index 000000000000..7b54a672d0ad --- /dev/null +++ b/kernel/futex.c @@ -0,0 +1,798 @@ +/* + * Fast Userspace Mutexes (which I call "Futexes!"). + * (C) Rusty Russell, IBM 2002 + * + * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar + * (C) Copyright 2003 Red Hat Inc, All Rights Reserved + * + * Removed page pinning, fix privately mapped COW pages and other cleanups + * (C) Copyright 2003, 2004 Jamie Lokier + * + * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly + * enough at me, Linus for the original (flawed) idea, Matthew + * Kirkwood for proof-of-concept implementation. + * + * "The futexes are also cursed." + * "But they come in a choice of three flavours!" + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8) + +/* + * Futexes are matched on equal values of this key. + * The key type depends on whether it's a shared or private mapping. + * Don't rearrange members without looking at hash_futex(). + * + * offset is aligned to a multiple of sizeof(u32) (== 4) by definition. + * We set bit 0 to indicate if it's an inode-based key. + */ +union futex_key { + struct { + unsigned long pgoff; + struct inode *inode; + int offset; + } shared; + struct { + unsigned long uaddr; + struct mm_struct *mm; + int offset; + } private; + struct { + unsigned long word; + void *ptr; + int offset; + } both; +}; + +/* + * We use this hashed waitqueue instead of a normal wait_queue_t, so + * we can wake only the relevant ones (hashed queues may be shared). + * + * A futex_q has a woken state, just like tasks have TASK_RUNNING. + * It is considered woken when list_empty(&q->list) || q->lock_ptr == 0. + * The order of wakup is always to make the first condition true, then + * wake up q->waiters, then make the second condition true. + */ +struct futex_q { + struct list_head list; + wait_queue_head_t waiters; + + /* Which hash list lock to use. */ + spinlock_t *lock_ptr; + + /* Key which the futex is hashed on. */ + union futex_key key; + + /* For fd, sigio sent using these. */ + int fd; + struct file *filp; +}; + +/* + * Split the global futex_lock into every hash list lock. + */ +struct futex_hash_bucket { + spinlock_t lock; + struct list_head chain; +}; + +static struct futex_hash_bucket futex_queues[1<both.word, + (sizeof(key->both.word)+sizeof(key->both.ptr))/4, + key->both.offset); + return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)]; +} + +/* + * Return 1 if two futex_keys are equal, 0 otherwise. + */ +static inline int match_futex(union futex_key *key1, union futex_key *key2) +{ + return (key1->both.word == key2->both.word + && key1->both.ptr == key2->both.ptr + && key1->both.offset == key2->both.offset); +} + +/* + * Get parameters which are the keys for a futex. + * + * For shared mappings, it's (page->index, vma->vm_file->f_dentry->d_inode, + * offset_within_page). For private mappings, it's (uaddr, current->mm). + * We can usually work out the index without swapping in the page. + * + * Returns: 0, or negative error code. + * The key words are stored in *key on success. + * + * Should be called with ¤t->mm->mmap_sem but NOT any spinlocks. + */ +static int get_futex_key(unsigned long uaddr, union futex_key *key) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + struct page *page; + int err; + + /* + * The futex address must be "naturally" aligned. + */ + key->both.offset = uaddr % PAGE_SIZE; + if (unlikely((key->both.offset % sizeof(u32)) != 0)) + return -EINVAL; + uaddr -= key->both.offset; + + /* + * The futex is hashed differently depending on whether + * it's in a shared or private mapping. So check vma first. + */ + vma = find_extend_vma(mm, uaddr); + if (unlikely(!vma)) + return -EFAULT; + + /* + * Permissions. + */ + if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) + return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; + + /* + * Private mappings are handled in a simple way. + * + * NOTE: When userspace waits on a MAP_SHARED mapping, even if + * it's a read-only handle, it's expected that futexes attach to + * the object not the particular process. Therefore we use + * VM_MAYSHARE here, not VM_SHARED which is restricted to shared + * mappings of _writable_ handles. + */ + if (likely(!(vma->vm_flags & VM_MAYSHARE))) { + key->private.mm = mm; + key->private.uaddr = uaddr; + return 0; + } + + /* + * Linear file mappings are also simple. + */ + key->shared.inode = vma->vm_file->f_dentry->d_inode; + key->both.offset++; /* Bit 0 of offset indicates inode-based key. */ + if (likely(!(vma->vm_flags & VM_NONLINEAR))) { + key->shared.pgoff = (((uaddr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff); + return 0; + } + + /* + * We could walk the page table to read the non-linear + * pte, and get the page index without fetching the page + * from swap. But that's a lot of code to duplicate here + * for a rare case, so we simply fetch the page. + */ + + /* + * Do a quick atomic lookup first - this is the fastpath. + */ + spin_lock(¤t->mm->page_table_lock); + page = follow_page(mm, uaddr, 0); + if (likely(page != NULL)) { + key->shared.pgoff = + page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + spin_unlock(¤t->mm->page_table_lock); + return 0; + } + spin_unlock(¤t->mm->page_table_lock); + + /* + * Do it the general way. + */ + err = get_user_pages(current, mm, uaddr, 1, 0, 0, &page, NULL); + if (err >= 0) { + key->shared.pgoff = + page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + put_page(page); + return 0; + } + return err; +} + +/* + * Take a reference to the resource addressed by a key. + * Can be called while holding spinlocks. + * + * NOTE: mmap_sem MUST be held between get_futex_key() and calling this + * function, if it is called at all. mmap_sem keeps key->shared.inode valid. + */ +static inline void get_key_refs(union futex_key *key) +{ + if (key->both.ptr != 0) { + if (key->both.offset & 1) + atomic_inc(&key->shared.inode->i_count); + else + atomic_inc(&key->private.mm->mm_count); + } +} + +/* + * Drop a reference to the resource addressed by a key. + * The hash bucket spinlock must not be held. + */ +static void drop_key_refs(union futex_key *key) +{ + if (key->both.ptr != 0) { + if (key->both.offset & 1) + iput(key->shared.inode); + else + mmdrop(key->private.mm); + } +} + +static inline int get_futex_value_locked(int *dest, int __user *from) +{ + int ret; + + inc_preempt_count(); + ret = __copy_from_user_inatomic(dest, from, sizeof(int)); + dec_preempt_count(); + + return ret ? -EFAULT : 0; +} + +/* + * The hash bucket lock must be held when this is called. + * Afterwards, the futex_q must not be accessed. + */ +static void wake_futex(struct futex_q *q) +{ + list_del_init(&q->list); + if (q->filp) + send_sigio(&q->filp->f_owner, q->fd, POLL_IN); + /* + * The lock in wake_up_all() is a crucial memory barrier after the + * list_del_init() and also before assigning to q->lock_ptr. + */ + wake_up_all(&q->waiters); + /* + * The waiting task can free the futex_q as soon as this is written, + * without taking any locks. This must come last. + */ + q->lock_ptr = NULL; +} + +/* + * Wake up all waiters hashed on the physical page that is mapped + * to this virtual address: + */ +static int futex_wake(unsigned long uaddr, int nr_wake) +{ + union futex_key key; + struct futex_hash_bucket *bh; + struct list_head *head; + struct futex_q *this, *next; + int ret; + + down_read(¤t->mm->mmap_sem); + + ret = get_futex_key(uaddr, &key); + if (unlikely(ret != 0)) + goto out; + + bh = hash_futex(&key); + spin_lock(&bh->lock); + head = &bh->chain; + + list_for_each_entry_safe(this, next, head, list) { + if (match_futex (&this->key, &key)) { + wake_futex(this); + if (++ret >= nr_wake) + break; + } + } + + spin_unlock(&bh->lock); +out: + up_read(¤t->mm->mmap_sem); + return ret; +} + +/* + * Requeue all waiters hashed on one physical page to another + * physical page. + */ +static int futex_requeue(unsigned long uaddr1, unsigned long uaddr2, + int nr_wake, int nr_requeue, int *valp) +{ + union futex_key key1, key2; + struct futex_hash_bucket *bh1, *bh2; + struct list_head *head1; + struct futex_q *this, *next; + int ret, drop_count = 0; + + retry: + down_read(¤t->mm->mmap_sem); + + ret = get_futex_key(uaddr1, &key1); + if (unlikely(ret != 0)) + goto out; + ret = get_futex_key(uaddr2, &key2); + if (unlikely(ret != 0)) + goto out; + + bh1 = hash_futex(&key1); + bh2 = hash_futex(&key2); + + if (bh1 < bh2) + spin_lock(&bh1->lock); + spin_lock(&bh2->lock); + if (bh1 > bh2) + spin_lock(&bh1->lock); + + if (likely(valp != NULL)) { + int curval; + + ret = get_futex_value_locked(&curval, (int __user *)uaddr1); + + if (unlikely(ret)) { + spin_unlock(&bh1->lock); + if (bh1 != bh2) + spin_unlock(&bh2->lock); + + /* If we would have faulted, release mmap_sem, fault + * it in and start all over again. + */ + up_read(¤t->mm->mmap_sem); + + ret = get_user(curval, (int __user *)uaddr1); + + if (!ret) + goto retry; + + return ret; + } + if (curval != *valp) { + ret = -EAGAIN; + goto out_unlock; + } + } + + head1 = &bh1->chain; + list_for_each_entry_safe(this, next, head1, list) { + if (!match_futex (&this->key, &key1)) + continue; + if (++ret <= nr_wake) { + wake_futex(this); + } else { + list_move_tail(&this->list, &bh2->chain); + this->lock_ptr = &bh2->lock; + this->key = key2; + get_key_refs(&key2); + drop_count++; + + if (ret - nr_wake >= nr_requeue) + break; + /* Make sure to stop if key1 == key2 */ + if (head1 == &bh2->chain && head1 != &next->list) + head1 = &this->list; + } + } + +out_unlock: + spin_unlock(&bh1->lock); + if (bh1 != bh2) + spin_unlock(&bh2->lock); + + /* drop_key_refs() must be called outside the spinlocks. */ + while (--drop_count >= 0) + drop_key_refs(&key1); + +out: + up_read(¤t->mm->mmap_sem); + return ret; +} + +/* The key must be already stored in q->key. */ +static inline struct futex_hash_bucket * +queue_lock(struct futex_q *q, int fd, struct file *filp) +{ + struct futex_hash_bucket *bh; + + q->fd = fd; + q->filp = filp; + + init_waitqueue_head(&q->waiters); + + get_key_refs(&q->key); + bh = hash_futex(&q->key); + q->lock_ptr = &bh->lock; + + spin_lock(&bh->lock); + return bh; +} + +static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *bh) +{ + list_add_tail(&q->list, &bh->chain); + spin_unlock(&bh->lock); +} + +static inline void +queue_unlock(struct futex_q *q, struct futex_hash_bucket *bh) +{ + spin_unlock(&bh->lock); + drop_key_refs(&q->key); +} + +/* + * queue_me and unqueue_me must be called as a pair, each + * exactly once. They are called with the hashed spinlock held. + */ + +/* The key must be already stored in q->key. */ +static void queue_me(struct futex_q *q, int fd, struct file *filp) +{ + struct futex_hash_bucket *bh; + bh = queue_lock(q, fd, filp); + __queue_me(q, bh); +} + +/* Return 1 if we were still queued (ie. 0 means we were woken) */ +static int unqueue_me(struct futex_q *q) +{ + int ret = 0; + spinlock_t *lock_ptr; + + /* In the common case we don't take the spinlock, which is nice. */ + retry: + lock_ptr = q->lock_ptr; + if (lock_ptr != 0) { + spin_lock(lock_ptr); + /* + * q->lock_ptr can change between reading it and + * spin_lock(), causing us to take the wrong lock. This + * corrects the race condition. + * + * Reasoning goes like this: if we have the wrong lock, + * q->lock_ptr must have changed (maybe several times) + * between reading it and the spin_lock(). It can + * change again after the spin_lock() but only if it was + * already changed before the spin_lock(). It cannot, + * however, change back to the original value. Therefore + * we can detect whether we acquired the correct lock. + */ + if (unlikely(lock_ptr != q->lock_ptr)) { + spin_unlock(lock_ptr); + goto retry; + } + WARN_ON(list_empty(&q->list)); + list_del(&q->list); + spin_unlock(lock_ptr); + ret = 1; + } + + drop_key_refs(&q->key); + return ret; +} + +static int futex_wait(unsigned long uaddr, int val, unsigned long time) +{ + DECLARE_WAITQUEUE(wait, current); + int ret, curval; + struct futex_q q; + struct futex_hash_bucket *bh; + + retry: + down_read(¤t->mm->mmap_sem); + + ret = get_futex_key(uaddr, &q.key); + if (unlikely(ret != 0)) + goto out_release_sem; + + bh = queue_lock(&q, -1, NULL); + + /* + * Access the page AFTER the futex is queued. + * Order is important: + * + * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); + * Userspace waker: if (cond(var)) { var = new; futex_wake(&var); } + * + * The basic logical guarantee of a futex is that it blocks ONLY + * if cond(var) is known to be true at the time of blocking, for + * any cond. If we queued after testing *uaddr, that would open + * a race condition where we could block indefinitely with + * cond(var) false, which would violate the guarantee. + * + * A consequence is that futex_wait() can return zero and absorb + * a wakeup when *uaddr != val on entry to the syscall. This is + * rare, but normal. + * + * We hold the mmap semaphore, so the mapping cannot have changed + * since we looked it up in get_futex_key. + */ + + ret = get_futex_value_locked(&curval, (int __user *)uaddr); + + if (unlikely(ret)) { + queue_unlock(&q, bh); + + /* If we would have faulted, release mmap_sem, fault it in and + * start all over again. + */ + up_read(¤t->mm->mmap_sem); + + ret = get_user(curval, (int __user *)uaddr); + + if (!ret) + goto retry; + return ret; + } + if (curval != val) { + ret = -EWOULDBLOCK; + queue_unlock(&q, bh); + goto out_release_sem; + } + + /* Only actually queue if *uaddr contained val. */ + __queue_me(&q, bh); + + /* + * Now the futex is queued and we have checked the data, we + * don't want to hold mmap_sem while we sleep. + */ + up_read(¤t->mm->mmap_sem); + + /* + * There might have been scheduling since the queue_me(), as we + * cannot hold a spinlock across the get_user() in case it + * faults, and we cannot just set TASK_INTERRUPTIBLE state when + * queueing ourselves into the futex hash. This code thus has to + * rely on the futex_wake() code removing us from hash when it + * wakes us up. + */ + + /* add_wait_queue is the barrier after __set_current_state. */ + __set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&q.waiters, &wait); + /* + * !list_empty() is safe here without any lock. + * q.lock_ptr != 0 is not safe, because of ordering against wakeup. + */ + if (likely(!list_empty(&q.list))) + time = schedule_timeout(time); + __set_current_state(TASK_RUNNING); + + /* + * NOTE: we don't remove ourselves from the waitqueue because + * we are the only user of it. + */ + + /* If we were woken (and unqueued), we succeeded, whatever. */ + if (!unqueue_me(&q)) + return 0; + if (time == 0) + return -ETIMEDOUT; + /* We expect signal_pending(current), but another thread may + * have handled it for us already. */ + return -EINTR; + + out_release_sem: + up_read(¤t->mm->mmap_sem); + return ret; +} + +static int futex_close(struct inode *inode, struct file *filp) +{ + struct futex_q *q = filp->private_data; + + unqueue_me(q); + kfree(q); + return 0; +} + +/* This is one-shot: once it's gone off you need a new fd */ +static unsigned int futex_poll(struct file *filp, + struct poll_table_struct *wait) +{ + struct futex_q *q = filp->private_data; + int ret = 0; + + poll_wait(filp, &q->waiters, wait); + + /* + * list_empty() is safe here without any lock. + * q->lock_ptr != 0 is not safe, because of ordering against wakeup. + */ + if (list_empty(&q->list)) + ret = POLLIN | POLLRDNORM; + + return ret; +} + +static struct file_operations futex_fops = { + .release = futex_close, + .poll = futex_poll, +}; + +/* + * Signal allows caller to avoid the race which would occur if they + * set the sigio stuff up afterwards. + */ +static int futex_fd(unsigned long uaddr, int signal) +{ + struct futex_q *q; + struct file *filp; + int ret, err; + + ret = -EINVAL; + if (signal < 0 || signal > _NSIG) + goto out; + + ret = get_unused_fd(); + if (ret < 0) + goto out; + filp = get_empty_filp(); + if (!filp) { + put_unused_fd(ret); + ret = -ENFILE; + goto out; + } + filp->f_op = &futex_fops; + filp->f_vfsmnt = mntget(futex_mnt); + filp->f_dentry = dget(futex_mnt->mnt_root); + filp->f_mapping = filp->f_dentry->d_inode->i_mapping; + + if (signal) { + int err; + err = f_setown(filp, current->pid, 1); + if (err < 0) { + put_unused_fd(ret); + put_filp(filp); + ret = err; + goto out; + } + filp->f_owner.signum = signal; + } + + q = kmalloc(sizeof(*q), GFP_KERNEL); + if (!q) { + put_unused_fd(ret); + put_filp(filp); + ret = -ENOMEM; + goto out; + } + + down_read(¤t->mm->mmap_sem); + err = get_futex_key(uaddr, &q->key); + + if (unlikely(err != 0)) { + up_read(¤t->mm->mmap_sem); + put_unused_fd(ret); + put_filp(filp); + kfree(q); + return err; + } + + /* + * queue_me() must be called before releasing mmap_sem, because + * key->shared.inode needs to be referenced while holding it. + */ + filp->private_data = q; + + queue_me(q, ret, filp); + up_read(¤t->mm->mmap_sem); + + /* Now we map fd to filp, so userspace can access it */ + fd_install(ret, filp); +out: + return ret; +} + +long do_futex(unsigned long uaddr, int op, int val, unsigned long timeout, + unsigned long uaddr2, int val2, int val3) +{ + int ret; + + switch (op) { + case FUTEX_WAIT: + ret = futex_wait(uaddr, val, timeout); + break; + case FUTEX_WAKE: + ret = futex_wake(uaddr, val); + break; + case FUTEX_FD: + /* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */ + ret = futex_fd(uaddr, val); + break; + case FUTEX_REQUEUE: + ret = futex_requeue(uaddr, uaddr2, val, val2, NULL); + break; + case FUTEX_CMP_REQUEUE: + ret = futex_requeue(uaddr, uaddr2, val, val2, &val3); + break; + default: + ret = -ENOSYS; + } + return ret; +} + + +asmlinkage long sys_futex(u32 __user *uaddr, int op, int val, + struct timespec __user *utime, u32 __user *uaddr2, + int val3) +{ + struct timespec t; + unsigned long timeout = MAX_SCHEDULE_TIMEOUT; + int val2 = 0; + + if ((op == FUTEX_WAIT) && utime) { + if (copy_from_user(&t, utime, sizeof(t)) != 0) + return -EFAULT; + timeout = timespec_to_jiffies(&t) + 1; + } + /* + * requeue parameter in 'utime' if op == FUTEX_REQUEUE. + */ + if (op >= FUTEX_REQUEUE) + val2 = (int) (unsigned long) utime; + + return do_futex((unsigned long)uaddr, op, val, timeout, + (unsigned long)uaddr2, val2, val3); +} + +static struct super_block * +futexfs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return get_sb_pseudo(fs_type, "futex", NULL, 0xBAD1DEA); +} + +static struct file_system_type futex_fs_type = { + .name = "futexfs", + .get_sb = futexfs_get_sb, + .kill_sb = kill_anon_super, +}; + +static int __init init(void) +{ + unsigned int i; + + register_filesystem(&futex_fs_type); + futex_mnt = kern_mount(&futex_fs_type); + + for (i = 0; i < ARRAY_SIZE(futex_queues); i++) { + INIT_LIST_HEAD(&futex_queues[i].chain); + spin_lock_init(&futex_queues[i].lock); + } + return 0; +} +__initcall(init); diff --git a/kernel/intermodule.c b/kernel/intermodule.c new file mode 100644 index 000000000000..388977f3e9b7 --- /dev/null +++ b/kernel/intermodule.c @@ -0,0 +1,182 @@ +/* Deprecated, do not use. Moved from module.c to here. --RR */ + +/* Written by Keith Owens Oct 2000 */ +#include +#include +#include +#include +#include + +/* inter_module functions are always available, even when the kernel is + * compiled without modules. Consumers of inter_module_xxx routines + * will always work, even when both are built into the kernel, this + * approach removes lots of #ifdefs in mainline code. + */ + +static struct list_head ime_list = LIST_HEAD_INIT(ime_list); +static DEFINE_SPINLOCK(ime_lock); +static int kmalloc_failed; + +struct inter_module_entry { + struct list_head list; + const char *im_name; + struct module *owner; + const void *userdata; +}; + +/** + * inter_module_register - register a new set of inter module data. + * @im_name: an arbitrary string to identify the data, must be unique + * @owner: module that is registering the data, always use THIS_MODULE + * @userdata: pointer to arbitrary userdata to be registered + * + * Description: Check that the im_name has not already been registered, + * complain if it has. For new data, add it to the inter_module_entry + * list. + */ +void inter_module_register(const char *im_name, struct module *owner, const void *userdata) +{ + struct list_head *tmp; + struct inter_module_entry *ime, *ime_new; + + if (!(ime_new = kmalloc(sizeof(*ime), GFP_KERNEL))) { + /* Overloaded kernel, not fatal */ + printk(KERN_ERR + "Aiee, inter_module_register: cannot kmalloc entry for '%s'\n", + im_name); + kmalloc_failed = 1; + return; + } + memset(ime_new, 0, sizeof(*ime_new)); + ime_new->im_name = im_name; + ime_new->owner = owner; + ime_new->userdata = userdata; + + spin_lock(&ime_lock); + list_for_each(tmp, &ime_list) { + ime = list_entry(tmp, struct inter_module_entry, list); + if (strcmp(ime->im_name, im_name) == 0) { + spin_unlock(&ime_lock); + kfree(ime_new); + /* Program logic error, fatal */ + printk(KERN_ERR "inter_module_register: duplicate im_name '%s'", im_name); + BUG(); + } + } + list_add(&(ime_new->list), &ime_list); + spin_unlock(&ime_lock); +} + +/** + * inter_module_unregister - unregister a set of inter module data. + * @im_name: an arbitrary string to identify the data, must be unique + * + * Description: Check that the im_name has been registered, complain if + * it has not. For existing data, remove it from the + * inter_module_entry list. + */ +void inter_module_unregister(const char *im_name) +{ + struct list_head *tmp; + struct inter_module_entry *ime; + + spin_lock(&ime_lock); + list_for_each(tmp, &ime_list) { + ime = list_entry(tmp, struct inter_module_entry, list); + if (strcmp(ime->im_name, im_name) == 0) { + list_del(&(ime->list)); + spin_unlock(&ime_lock); + kfree(ime); + return; + } + } + spin_unlock(&ime_lock); + if (kmalloc_failed) { + printk(KERN_ERR + "inter_module_unregister: no entry for '%s', " + "probably caused by previous kmalloc failure\n", + im_name); + return; + } + else { + /* Program logic error, fatal */ + printk(KERN_ERR "inter_module_unregister: no entry for '%s'", im_name); + BUG(); + } +} + +/** + * inter_module_get - return arbitrary userdata from another module. + * @im_name: an arbitrary string to identify the data, must be unique + * + * Description: If the im_name has not been registered, return NULL. + * Try to increment the use count on the owning module, if that fails + * then return NULL. Otherwise return the userdata. + */ +static const void *inter_module_get(const char *im_name) +{ + struct list_head *tmp; + struct inter_module_entry *ime; + const void *result = NULL; + + spin_lock(&ime_lock); + list_for_each(tmp, &ime_list) { + ime = list_entry(tmp, struct inter_module_entry, list); + if (strcmp(ime->im_name, im_name) == 0) { + if (try_module_get(ime->owner)) + result = ime->userdata; + break; + } + } + spin_unlock(&ime_lock); + return(result); +} + +/** + * inter_module_get_request - im get with automatic request_module. + * @im_name: an arbitrary string to identify the data, must be unique + * @modname: module that is expected to register im_name + * + * Description: If inter_module_get fails, do request_module then retry. + */ +const void *inter_module_get_request(const char *im_name, const char *modname) +{ + const void *result = inter_module_get(im_name); + if (!result) { + request_module("%s", modname); + result = inter_module_get(im_name); + } + return(result); +} + +/** + * inter_module_put - release use of data from another module. + * @im_name: an arbitrary string to identify the data, must be unique + * + * Description: If the im_name has not been registered, complain, + * otherwise decrement the use count on the owning module. + */ +void inter_module_put(const char *im_name) +{ + struct list_head *tmp; + struct inter_module_entry *ime; + + spin_lock(&ime_lock); + list_for_each(tmp, &ime_list) { + ime = list_entry(tmp, struct inter_module_entry, list); + if (strcmp(ime->im_name, im_name) == 0) { + if (ime->owner) + module_put(ime->owner); + spin_unlock(&ime_lock); + return; + } + } + spin_unlock(&ime_lock); + printk(KERN_ERR "inter_module_put: no entry for '%s'", im_name); + BUG(); +} + +EXPORT_SYMBOL(inter_module_register); +EXPORT_SYMBOL(inter_module_unregister); +EXPORT_SYMBOL(inter_module_get_request); +EXPORT_SYMBOL(inter_module_put); diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile new file mode 100644 index 000000000000..49378738ff5e --- /dev/null +++ b/kernel/irq/Makefile @@ -0,0 +1,5 @@ + +obj-y := handle.o manage.o spurious.o +obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o +obj-$(CONFIG_PROC_FS) += proc.o + diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c new file mode 100644 index 000000000000..98d62d8efeaf --- /dev/null +++ b/kernel/irq/autoprobe.c @@ -0,0 +1,189 @@ +/* + * linux/kernel/irq/autoprobe.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains the interrupt probing code and driver APIs. + */ + +#include +#include +#include + +/* + * Autodetection depends on the fact that any interrupt that + * comes in on to an unassigned handler will get stuck with + * "IRQ_WAITING" cleared and the interrupt disabled. + */ +static DECLARE_MUTEX(probe_sem); + +/** + * probe_irq_on - begin an interrupt autodetect + * + * Commence probing for an interrupt. The interrupts are scanned + * and a mask of potential interrupt lines is returned. + * + */ +unsigned long probe_irq_on(void) +{ + unsigned long val, delay; + irq_desc_t *desc; + unsigned int i; + + down(&probe_sem); + /* + * something may have generated an irq long ago and we want to + * flush such a longstanding irq before considering it as spurious. + */ + for (i = NR_IRQS-1; i > 0; i--) { + desc = irq_desc + i; + + spin_lock_irq(&desc->lock); + if (!irq_desc[i].action) + irq_desc[i].handler->startup(i); + spin_unlock_irq(&desc->lock); + } + + /* Wait for longstanding interrupts to trigger. */ + for (delay = jiffies + HZ/50; time_after(delay, jiffies); ) + /* about 20ms delay */ barrier(); + + /* + * enable any unassigned irqs + * (we must startup again here because if a longstanding irq + * happened in the previous stage, it may have masked itself) + */ + for (i = NR_IRQS-1; i > 0; i--) { + desc = irq_desc + i; + + spin_lock_irq(&desc->lock); + if (!desc->action) { + desc->status |= IRQ_AUTODETECT | IRQ_WAITING; + if (desc->handler->startup(i)) + desc->status |= IRQ_PENDING; + } + spin_unlock_irq(&desc->lock); + } + + /* + * Wait for spurious interrupts to trigger + */ + for (delay = jiffies + HZ/10; time_after(delay, jiffies); ) + /* about 100ms delay */ barrier(); + + /* + * Now filter out any obviously spurious interrupts + */ + val = 0; + for (i = 0; i < NR_IRQS; i++) { + irq_desc_t *desc = irq_desc + i; + unsigned int status; + + spin_lock_irq(&desc->lock); + status = desc->status; + + if (status & IRQ_AUTODETECT) { + /* It triggered already - consider it spurious. */ + if (!(status & IRQ_WAITING)) { + desc->status = status & ~IRQ_AUTODETECT; + desc->handler->shutdown(i); + } else + if (i < 32) + val |= 1 << i; + } + spin_unlock_irq(&desc->lock); + } + + return val; +} + +EXPORT_SYMBOL(probe_irq_on); + +/** + * probe_irq_mask - scan a bitmap of interrupt lines + * @val: mask of interrupts to consider + * + * Scan the interrupt lines and return a bitmap of active + * autodetect interrupts. The interrupt probe logic state + * is then returned to its previous value. + * + * Note: we need to scan all the irq's even though we will + * only return autodetect irq numbers - just so that we reset + * them all to a known state. + */ +unsigned int probe_irq_mask(unsigned long val) +{ + unsigned int mask; + int i; + + mask = 0; + for (i = 0; i < NR_IRQS; i++) { + irq_desc_t *desc = irq_desc + i; + unsigned int status; + + spin_lock_irq(&desc->lock); + status = desc->status; + + if (status & IRQ_AUTODETECT) { + if (i < 16 && !(status & IRQ_WAITING)) + mask |= 1 << i; + + desc->status = status & ~IRQ_AUTODETECT; + desc->handler->shutdown(i); + } + spin_unlock_irq(&desc->lock); + } + up(&probe_sem); + + return mask & val; +} +EXPORT_SYMBOL(probe_irq_mask); + +/** + * probe_irq_off - end an interrupt autodetect + * @val: mask of potential interrupts (unused) + * + * Scans the unused interrupt lines and returns the line which + * appears to have triggered the interrupt. If no interrupt was + * found then zero is returned. If more than one interrupt is + * found then minus the first candidate is returned to indicate + * their is doubt. + * + * The interrupt probe logic state is returned to its previous + * value. + * + * BUGS: When used in a module (which arguably shouldn't happen) + * nothing prevents two IRQ probe callers from overlapping. The + * results of this are non-optimal. + */ +int probe_irq_off(unsigned long val) +{ + int i, irq_found = 0, nr_irqs = 0; + + for (i = 0; i < NR_IRQS; i++) { + irq_desc_t *desc = irq_desc + i; + unsigned int status; + + spin_lock_irq(&desc->lock); + status = desc->status; + + if (status & IRQ_AUTODETECT) { + if (!(status & IRQ_WAITING)) { + if (!nr_irqs) + irq_found = i; + nr_irqs++; + } + desc->status = status & ~IRQ_AUTODETECT; + desc->handler->shutdown(i); + } + spin_unlock_irq(&desc->lock); + } + up(&probe_sem); + + if (nr_irqs > 1) + irq_found = -irq_found; + return irq_found; +} + +EXPORT_SYMBOL(probe_irq_off); + diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c new file mode 100644 index 000000000000..2fb0e46e11f3 --- /dev/null +++ b/kernel/irq/handle.c @@ -0,0 +1,193 @@ +/* + * linux/kernel/irq/handle.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains the core interrupt handling code. + */ + +#include +#include +#include +#include +#include + +#include "internals.h" + +/* + * Linux has a controller-independent interrupt architecture. + * Every controller has a 'controller-template', that is used + * by the main code to do the right thing. Each driver-visible + * interrupt source is transparently wired to the apropriate + * controller. Thus drivers need not be aware of the + * interrupt-controller. + * + * The code is designed to be easily extended with new/different + * interrupt controllers, without having to do assembly magic or + * having to touch the generic code. + * + * Controller mappings for all interrupt sources: + */ +irq_desc_t irq_desc[NR_IRQS] __cacheline_aligned = { + [0 ... NR_IRQS-1] = { + .handler = &no_irq_type, + .lock = SPIN_LOCK_UNLOCKED + } +}; + +/* + * Generic 'no controller' code + */ +static void end_none(unsigned int irq) { } +static void enable_none(unsigned int irq) { } +static void disable_none(unsigned int irq) { } +static void shutdown_none(unsigned int irq) { } +static unsigned int startup_none(unsigned int irq) { return 0; } + +static void ack_none(unsigned int irq) +{ + /* + * 'what should we do if we get a hw irq event on an illegal vector'. + * each architecture has to answer this themself. + */ + ack_bad_irq(irq); +} + +struct hw_interrupt_type no_irq_type = { + .typename = "none", + .startup = startup_none, + .shutdown = shutdown_none, + .enable = enable_none, + .disable = disable_none, + .ack = ack_none, + .end = end_none, + .set_affinity = NULL +}; + +/* + * Special, empty irq handler: + */ +irqreturn_t no_action(int cpl, void *dev_id, struct pt_regs *regs) +{ + return IRQ_NONE; +} + +/* + * Have got an event to handle: + */ +fastcall int handle_IRQ_event(unsigned int irq, struct pt_regs *regs, + struct irqaction *action) +{ + int ret, retval = 0, status = 0; + + if (!(action->flags & SA_INTERRUPT)) + local_irq_enable(); + + do { + ret = action->handler(irq, action->dev_id, regs); + if (ret == IRQ_HANDLED) + status |= action->flags; + retval |= ret; + action = action->next; + } while (action); + + if (status & SA_SAMPLE_RANDOM) + add_interrupt_randomness(irq); + local_irq_disable(); + + return retval; +} + +/* + * do_IRQ handles all normal device IRQ's (the special + * SMP cross-CPU interrupts have their own specific + * handlers). + */ +fastcall unsigned int __do_IRQ(unsigned int irq, struct pt_regs *regs) +{ + irq_desc_t *desc = irq_desc + irq; + struct irqaction * action; + unsigned int status; + + kstat_this_cpu.irqs[irq]++; + if (desc->status & IRQ_PER_CPU) { + irqreturn_t action_ret; + + /* + * No locking required for CPU-local interrupts: + */ + desc->handler->ack(irq); + action_ret = handle_IRQ_event(irq, regs, desc->action); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret); + desc->handler->end(irq); + return 1; + } + + spin_lock(&desc->lock); + desc->handler->ack(irq); + /* + * REPLAY is when Linux resends an IRQ that was dropped earlier + * WAITING is used by probe to mark irqs that are being tested + */ + status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING); + status |= IRQ_PENDING; /* we _want_ to handle it */ + + /* + * If the IRQ is disabled for whatever reason, we cannot + * use the action we have. + */ + action = NULL; + if (likely(!(status & (IRQ_DISABLED | IRQ_INPROGRESS)))) { + action = desc->action; + status &= ~IRQ_PENDING; /* we commit to handling */ + status |= IRQ_INPROGRESS; /* we are handling it */ + } + desc->status = status; + + /* + * If there is no IRQ handler or it was disabled, exit early. + * Since we set PENDING, if another processor is handling + * a different instance of this same irq, the other processor + * will take care of it. + */ + if (unlikely(!action)) + goto out; + + /* + * Edge triggered interrupts need to remember + * pending events. + * This applies to any hw interrupts that allow a second + * instance of the same irq to arrive while we are in do_IRQ + * or in the handler. But the code here only handles the _second_ + * instance of the irq, not the third or fourth. So it is mostly + * useful for irq hardware that does not mask cleanly in an + * SMP environment. + */ + for (;;) { + irqreturn_t action_ret; + + spin_unlock(&desc->lock); + + action_ret = handle_IRQ_event(irq, regs, action); + + spin_lock(&desc->lock); + if (!noirqdebug) + note_interrupt(irq, desc, action_ret); + if (likely(!(desc->status & IRQ_PENDING))) + break; + desc->status &= ~IRQ_PENDING; + } + desc->status &= ~IRQ_INPROGRESS; + +out: + /* + * The ->end() handler has to deal with interrupts which got + * disabled while the handler was running. + */ + desc->handler->end(irq); + spin_unlock(&desc->lock); + + return 1; +} + diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h new file mode 100644 index 000000000000..46feba630266 --- /dev/null +++ b/kernel/irq/internals.h @@ -0,0 +1,18 @@ +/* + * IRQ subsystem internal functions and variables: + */ + +extern int noirqdebug; + +#ifdef CONFIG_PROC_FS +extern void register_irq_proc(unsigned int irq); +extern void register_handler_proc(unsigned int irq, struct irqaction *action); +extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); +#else +static inline void register_irq_proc(unsigned int irq) { } +static inline void register_handler_proc(unsigned int irq, + struct irqaction *action) { } +static inline void unregister_handler_proc(unsigned int irq, + struct irqaction *action) { } +#endif + diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c new file mode 100644 index 000000000000..5202e4c4a5b6 --- /dev/null +++ b/kernel/irq/manage.c @@ -0,0 +1,349 @@ +/* + * linux/kernel/irq/manage.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains driver APIs to the irq subsystem. + */ + +#include +#include +#include +#include + +#include "internals.h" + +#ifdef CONFIG_SMP + +cpumask_t irq_affinity[NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_ALL }; + +/** + * synchronize_irq - wait for pending IRQ handlers (on other CPUs) + * + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_desc + irq; + + while (desc->status & IRQ_INPROGRESS) + cpu_relax(); +} + +EXPORT_SYMBOL(synchronize_irq); + +#endif + +/** + * disable_irq_nosync - disable an irq without waiting + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Disables and Enables are + * nested. + * Unlike disable_irq(), this function does not ensure existing + * instances of the IRQ handler have completed before returning. + * + * This function may be called from IRQ context. + */ +void disable_irq_nosync(unsigned int irq) +{ + irq_desc_t *desc = irq_desc + irq; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + if (!desc->depth++) { + desc->status |= IRQ_DISABLED; + desc->handler->disable(irq); + } + spin_unlock_irqrestore(&desc->lock, flags); +} + +EXPORT_SYMBOL(disable_irq_nosync); + +/** + * disable_irq - disable an irq and wait for completion + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Enables and Disables are + * nested. + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void disable_irq(unsigned int irq) +{ + irq_desc_t *desc = irq_desc + irq; + + disable_irq_nosync(irq); + if (desc->action) + synchronize_irq(irq); +} + +EXPORT_SYMBOL(disable_irq); + +/** + * enable_irq - enable handling of an irq + * @irq: Interrupt to enable + * + * Undoes the effect of one call to disable_irq(). If this + * matches the last disable, processing of interrupts on this + * IRQ line is re-enabled. + * + * This function may be called from IRQ context. + */ +void enable_irq(unsigned int irq) +{ + irq_desc_t *desc = irq_desc + irq; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + switch (desc->depth) { + case 0: + WARN_ON(1); + break; + case 1: { + unsigned int status = desc->status & ~IRQ_DISABLED; + + desc->status = status; + if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) { + desc->status = status | IRQ_REPLAY; + hw_resend_irq(desc->handler,irq); + } + desc->handler->enable(irq); + /* fall-through */ + } + default: + desc->depth--; + } + spin_unlock_irqrestore(&desc->lock, flags); +} + +EXPORT_SYMBOL(enable_irq); + +/* + * Internal function that tells the architecture code whether a + * particular irq has been exclusively allocated or is available + * for driver use. + */ +int can_request_irq(unsigned int irq, unsigned long irqflags) +{ + struct irqaction *action; + + if (irq >= NR_IRQS) + return 0; + + action = irq_desc[irq].action; + if (action) + if (irqflags & action->flags & SA_SHIRQ) + action = NULL; + + return !action; +} + +/* + * Internal function to register an irqaction - typically used to + * allocate special interrupts that are part of the architecture. + */ +int setup_irq(unsigned int irq, struct irqaction * new) +{ + struct irq_desc *desc = irq_desc + irq; + struct irqaction *old, **p; + unsigned long flags; + int shared = 0; + + if (desc->handler == &no_irq_type) + return -ENOSYS; + /* + * Some drivers like serial.c use request_irq() heavily, + * so we have to be careful not to interfere with a + * running system. + */ + if (new->flags & SA_SAMPLE_RANDOM) { + /* + * This function might sleep, we want to call it first, + * outside of the atomic block. + * Yes, this might clear the entropy pool if the wrong + * driver is attempted to be loaded, without actually + * installing a new handler, but is this really a problem, + * only the sysadmin is able to do this. + */ + rand_initialize_irq(irq); + } + + /* + * The following block of code has to be executed atomically + */ + spin_lock_irqsave(&desc->lock,flags); + p = &desc->action; + if ((old = *p) != NULL) { + /* Can't share interrupts unless both agree to */ + if (!(old->flags & new->flags & SA_SHIRQ)) { + spin_unlock_irqrestore(&desc->lock,flags); + return -EBUSY; + } + + /* add new interrupt at end of irq queue */ + do { + p = &old->next; + old = *p; + } while (old); + shared = 1; + } + + *p = new; + + if (!shared) { + desc->depth = 0; + desc->status &= ~(IRQ_DISABLED | IRQ_AUTODETECT | + IRQ_WAITING | IRQ_INPROGRESS); + if (desc->handler->startup) + desc->handler->startup(irq); + else + desc->handler->enable(irq); + } + spin_unlock_irqrestore(&desc->lock,flags); + + new->irq = irq; + register_irq_proc(irq); + new->dir = NULL; + register_handler_proc(irq, new); + + return 0; +} + +/** + * free_irq - free an interrupt + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove an interrupt handler. The handler is removed and if the + * interrupt line is no longer in use by any driver it is disabled. + * On a shared IRQ the caller must ensure the interrupt is disabled + * on the card it drives before calling this function. The function + * does not return until any executing interrupts for this IRQ + * have completed. + * + * This function must not be called from interrupt context. + */ +void free_irq(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc; + struct irqaction **p; + unsigned long flags; + + if (irq >= NR_IRQS) + return; + + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock,flags); + p = &desc->action; + for (;;) { + struct irqaction * action = *p; + + if (action) { + struct irqaction **pp = p; + + p = &action->next; + if (action->dev_id != dev_id) + continue; + + /* Found it - now remove it from the list of entries */ + *pp = action->next; + if (!desc->action) { + desc->status |= IRQ_DISABLED; + if (desc->handler->shutdown) + desc->handler->shutdown(irq); + else + desc->handler->disable(irq); + } + spin_unlock_irqrestore(&desc->lock,flags); + unregister_handler_proc(irq, action); + + /* Make sure it's not being used on another CPU */ + synchronize_irq(irq); + kfree(action); + return; + } + printk(KERN_ERR "Trying to free free IRQ%d\n",irq); + spin_unlock_irqrestore(&desc->lock,flags); + return; + } +} + +EXPORT_SYMBOL(free_irq); + +/** + * request_irq - allocate an interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * This call allocates interrupt resources and enables the + * interrupt line and IRQ handling. From the point this + * call is made your handler function may be invoked. Since + * your handler function must clear any interrupt the board + * raises, you must take care both to initialise your hardware + * and to set up the interrupt handler in the right order. + * + * Dev_id must be globally unique. Normally the address of the + * device data structure is used as the cookie. Since the handler + * receives this value it makes sense to use it. + * + * If your interrupt is shared you must pass a non NULL dev_id + * as this is required when freeing the interrupt. + * + * Flags: + * + * SA_SHIRQ Interrupt is shared + * SA_INTERRUPT Disable local interrupts while processing + * SA_SAMPLE_RANDOM The interrupt can be used for entropy + * + */ +int request_irq(unsigned int irq, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, const char * devname, void *dev_id) +{ + struct irqaction * action; + int retval; + + /* + * Sanity-check: shared interrupts must pass in a real dev-ID, + * otherwise we'll have trouble later trying to figure out + * which interrupt is which (messes up the interrupt freeing + * logic etc). + */ + if ((irqflags & SA_SHIRQ) && !dev_id) + return -EINVAL; + if (irq >= NR_IRQS) + return -EINVAL; + if (!handler) + return -EINVAL; + + action = kmalloc(sizeof(struct irqaction), GFP_ATOMIC); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->flags = irqflags; + cpus_clear(action->mask); + action->name = devname; + action->next = NULL; + action->dev_id = dev_id; + + retval = setup_irq(irq, action); + if (retval) + kfree(action); + + return retval; +} + +EXPORT_SYMBOL(request_irq); + diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c new file mode 100644 index 000000000000..85d08daa6600 --- /dev/null +++ b/kernel/irq/proc.c @@ -0,0 +1,159 @@ +/* + * linux/kernel/irq/proc.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains the /proc/irq/ handling code. + */ + +#include +#include +#include + +static struct proc_dir_entry *root_irq_dir, *irq_dir[NR_IRQS]; + +#ifdef CONFIG_SMP + +/* + * The /proc/irq//smp_affinity values: + */ +static struct proc_dir_entry *smp_affinity_entry[NR_IRQS]; + +void __attribute__((weak)) +proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val) +{ + irq_affinity[irq] = mask_val; + irq_desc[irq].handler->set_affinity(irq, mask_val); +} + +static int irq_affinity_read_proc(char *page, char **start, off_t off, + int count, int *eof, void *data) +{ + int len = cpumask_scnprintf(page, count, irq_affinity[(long)data]); + + if (count - len < 2) + return -EINVAL; + len += sprintf(page + len, "\n"); + return len; +} + +int no_irq_affinity; +static int irq_affinity_write_proc(struct file *file, const char __user *buffer, + unsigned long count, void *data) +{ + unsigned int irq = (int)(long)data, full_count = count, err; + cpumask_t new_value, tmp; + + if (!irq_desc[irq].handler->set_affinity || no_irq_affinity) + return -EIO; + + err = cpumask_parse(buffer, count, new_value); + if (err) + return err; + + /* + * Do not allow disabling IRQs completely - it's a too easy + * way to make the system unusable accidentally :-) At least + * one online CPU still has to be targeted. + */ + cpus_and(tmp, new_value, cpu_online_map); + if (cpus_empty(tmp)) + return -EINVAL; + + proc_set_irq_affinity(irq, new_value); + + return full_count; +} + +#endif + +#define MAX_NAMELEN 128 + +static int name_unique(unsigned int irq, struct irqaction *new_action) +{ + struct irq_desc *desc = irq_desc + irq; + struct irqaction *action; + + for (action = desc->action ; action; action = action->next) + if ((action != new_action) && action->name && + !strcmp(new_action->name, action->name)) + return 0; + return 1; +} + +void register_handler_proc(unsigned int irq, struct irqaction *action) +{ + char name [MAX_NAMELEN]; + + if (!irq_dir[irq] || action->dir || !action->name || + !name_unique(irq, action)) + return; + + memset(name, 0, MAX_NAMELEN); + snprintf(name, MAX_NAMELEN, "%s", action->name); + + /* create /proc/irq/1234/handler/ */ + action->dir = proc_mkdir(name, irq_dir[irq]); +} + +#undef MAX_NAMELEN + +#define MAX_NAMELEN 10 + +void register_irq_proc(unsigned int irq) +{ + char name [MAX_NAMELEN]; + + if (!root_irq_dir || + (irq_desc[irq].handler == &no_irq_type) || + irq_dir[irq]) + return; + + memset(name, 0, MAX_NAMELEN); + sprintf(name, "%d", irq); + + /* create /proc/irq/1234 */ + irq_dir[irq] = proc_mkdir(name, root_irq_dir); + +#ifdef CONFIG_SMP + { + struct proc_dir_entry *entry; + + /* create /proc/irq//smp_affinity */ + entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]); + + if (entry) { + entry->nlink = 1; + entry->data = (void *)(long)irq; + entry->read_proc = irq_affinity_read_proc; + entry->write_proc = irq_affinity_write_proc; + } + smp_affinity_entry[irq] = entry; + } +#endif +} + +#undef MAX_NAMELEN + +void unregister_handler_proc(unsigned int irq, struct irqaction *action) +{ + if (action->dir) + remove_proc_entry(action->dir->name, irq_dir[irq]); +} + +void init_irq_proc(void) +{ + int i; + + /* create /proc/irq */ + root_irq_dir = proc_mkdir("irq", NULL); + if (!root_irq_dir) + return; + + /* + * Create entries for all existing IRQs. + */ + for (i = 0; i < NR_IRQS; i++) + register_irq_proc(i); +} + diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c new file mode 100644 index 000000000000..f6297c306905 --- /dev/null +++ b/kernel/irq/spurious.c @@ -0,0 +1,96 @@ +/* + * linux/kernel/irq/spurious.c + * + * Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar + * + * This file contains spurious interrupt handling. + */ + +#include +#include +#include +#include + +/* + * If 99,900 of the previous 100,000 interrupts have not been handled + * then assume that the IRQ is stuck in some manner. Drop a diagnostic + * and try to turn the IRQ off. + * + * (The other 100-of-100,000 interrupts may have been a correctly + * functioning device sharing an IRQ with the failing one) + * + * Called under desc->lock + */ + +static void +__report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) +{ + struct irqaction *action; + + if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) { + printk(KERN_ERR "irq event %d: bogus return value %x\n", + irq, action_ret); + } else { + printk(KERN_ERR "irq %d: nobody cared!\n", irq); + } + dump_stack(); + printk(KERN_ERR "handlers:\n"); + action = desc->action; + while (action) { + printk(KERN_ERR "[<%p>]", action->handler); + print_symbol(" (%s)", + (unsigned long)action->handler); + printk("\n"); + action = action->next; + } +} + +void report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) +{ + static int count = 100; + + if (count > 0) { + count--; + __report_bad_irq(irq, desc, action_ret); + } +} + +void note_interrupt(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret) +{ + if (action_ret != IRQ_HANDLED) { + desc->irqs_unhandled++; + if (action_ret != IRQ_NONE) + report_bad_irq(irq, desc, action_ret); + } + + desc->irq_count++; + if (desc->irq_count < 100000) + return; + + desc->irq_count = 0; + if (desc->irqs_unhandled > 99900) { + /* + * The interrupt is stuck + */ + __report_bad_irq(irq, desc, action_ret); + /* + * Now kill the IRQ + */ + printk(KERN_EMERG "Disabling IRQ #%d\n", irq); + desc->status |= IRQ_DISABLED; + desc->handler->disable(irq); + } + desc->irqs_unhandled = 0; +} + +int noirqdebug; + +int __init noirqdebug_setup(char *str) +{ + noirqdebug = 1; + printk(KERN_INFO "IRQ lockup detection disabled\n"); + return 1; +} + +__setup("noirqdebug", noirqdebug_setup); + diff --git a/kernel/itimer.c b/kernel/itimer.c new file mode 100644 index 000000000000..e9a40e947e07 --- /dev/null +++ b/kernel/itimer.c @@ -0,0 +1,241 @@ +/* + * linux/kernel/itimer.c + * + * Copyright (C) 1992 Darren Senn + */ + +/* These are all the functions necessary to implement itimers */ + +#include +#include +#include +#include +#include +#include + +#include + +static unsigned long it_real_value(struct signal_struct *sig) +{ + unsigned long val = 0; + if (timer_pending(&sig->real_timer)) { + val = sig->real_timer.expires - jiffies; + + /* look out for negative/zero itimer.. */ + if ((long) val <= 0) + val = 1; + } + return val; +} + +int do_getitimer(int which, struct itimerval *value) +{ + struct task_struct *tsk = current; + unsigned long interval, val; + cputime_t cinterval, cval; + + switch (which) { + case ITIMER_REAL: + spin_lock_irq(&tsk->sighand->siglock); + interval = tsk->signal->it_real_incr; + val = it_real_value(tsk->signal); + spin_unlock_irq(&tsk->sighand->siglock); + jiffies_to_timeval(val, &value->it_value); + jiffies_to_timeval(interval, &value->it_interval); + break; + case ITIMER_VIRTUAL: + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + cval = tsk->signal->it_virt_expires; + cinterval = tsk->signal->it_virt_incr; + if (!cputime_eq(cval, cputime_zero)) { + struct task_struct *t = tsk; + cputime_t utime = tsk->signal->utime; + do { + utime = cputime_add(utime, t->utime); + t = next_thread(t); + } while (t != tsk); + if (cputime_le(cval, utime)) { /* about to fire */ + cval = jiffies_to_cputime(1); + } else { + cval = cputime_sub(cval, utime); + } + } + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + cputime_to_timeval(cval, &value->it_value); + cputime_to_timeval(cinterval, &value->it_interval); + break; + case ITIMER_PROF: + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + cval = tsk->signal->it_prof_expires; + cinterval = tsk->signal->it_prof_incr; + if (!cputime_eq(cval, cputime_zero)) { + struct task_struct *t = tsk; + cputime_t ptime = cputime_add(tsk->signal->utime, + tsk->signal->stime); + do { + ptime = cputime_add(ptime, + cputime_add(t->utime, + t->stime)); + t = next_thread(t); + } while (t != tsk); + if (cputime_le(cval, ptime)) { /* about to fire */ + cval = jiffies_to_cputime(1); + } else { + cval = cputime_sub(cval, ptime); + } + } + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + cputime_to_timeval(cval, &value->it_value); + cputime_to_timeval(cinterval, &value->it_interval); + break; + default: + return(-EINVAL); + } + return 0; +} + +asmlinkage long sys_getitimer(int which, struct itimerval __user *value) +{ + int error = -EFAULT; + struct itimerval get_buffer; + + if (value) { + error = do_getitimer(which, &get_buffer); + if (!error && + copy_to_user(value, &get_buffer, sizeof(get_buffer))) + error = -EFAULT; + } + return error; +} + +/* + * Called with P->sighand->siglock held and P->signal->real_timer inactive. + * If interval is nonzero, arm the timer for interval ticks from now. + */ +static inline void it_real_arm(struct task_struct *p, unsigned long interval) +{ + p->signal->it_real_value = interval; /* XXX unnecessary field?? */ + if (interval == 0) + return; + if (interval > (unsigned long) LONG_MAX) + interval = LONG_MAX; + p->signal->real_timer.expires = jiffies + interval; + add_timer(&p->signal->real_timer); +} + +void it_real_fn(unsigned long __data) +{ + struct task_struct * p = (struct task_struct *) __data; + + send_group_sig_info(SIGALRM, SEND_SIG_PRIV, p); + + /* + * Now restart the timer if necessary. We don't need any locking + * here because do_setitimer makes sure we have finished running + * before it touches anything. + */ + it_real_arm(p, p->signal->it_real_incr); +} + +int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) +{ + struct task_struct *tsk = current; + unsigned long val, interval; + cputime_t cval, cinterval, nval, ninterval; + + switch (which) { + case ITIMER_REAL: + spin_lock_irq(&tsk->sighand->siglock); + interval = tsk->signal->it_real_incr; + val = it_real_value(tsk->signal); + if (val) + del_timer_sync(&tsk->signal->real_timer); + tsk->signal->it_real_incr = + timeval_to_jiffies(&value->it_interval); + it_real_arm(tsk, timeval_to_jiffies(&value->it_value)); + spin_unlock_irq(&tsk->sighand->siglock); + if (ovalue) { + jiffies_to_timeval(val, &ovalue->it_value); + jiffies_to_timeval(interval, + &ovalue->it_interval); + } + break; + case ITIMER_VIRTUAL: + nval = timeval_to_cputime(&value->it_value); + ninterval = timeval_to_cputime(&value->it_interval); + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + cval = tsk->signal->it_virt_expires; + cinterval = tsk->signal->it_virt_incr; + if (!cputime_eq(cval, cputime_zero) || + !cputime_eq(nval, cputime_zero)) { + if (cputime_gt(nval, cputime_zero)) + nval = cputime_add(nval, + jiffies_to_cputime(1)); + set_process_cpu_timer(tsk, CPUCLOCK_VIRT, + &nval, &cval); + } + tsk->signal->it_virt_expires = nval; + tsk->signal->it_virt_incr = ninterval; + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + if (ovalue) { + cputime_to_timeval(cval, &ovalue->it_value); + cputime_to_timeval(cinterval, &ovalue->it_interval); + } + break; + case ITIMER_PROF: + nval = timeval_to_cputime(&value->it_value); + ninterval = timeval_to_cputime(&value->it_interval); + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + cval = tsk->signal->it_prof_expires; + cinterval = tsk->signal->it_prof_incr; + if (!cputime_eq(cval, cputime_zero) || + !cputime_eq(nval, cputime_zero)) { + if (cputime_gt(nval, cputime_zero)) + nval = cputime_add(nval, + jiffies_to_cputime(1)); + set_process_cpu_timer(tsk, CPUCLOCK_PROF, + &nval, &cval); + } + tsk->signal->it_prof_expires = nval; + tsk->signal->it_prof_incr = ninterval; + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + if (ovalue) { + cputime_to_timeval(cval, &ovalue->it_value); + cputime_to_timeval(cinterval, &ovalue->it_interval); + } + break; + default: + return -EINVAL; + } + return 0; +} + +asmlinkage long sys_setitimer(int which, + struct itimerval __user *value, + struct itimerval __user *ovalue) +{ + struct itimerval set_buffer, get_buffer; + int error; + + if (value) { + if(copy_from_user(&set_buffer, value, sizeof(set_buffer))) + return -EFAULT; + } else + memset((char *) &set_buffer, 0, sizeof(set_buffer)); + + error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL); + if (error || !ovalue) + return error; + + if (copy_to_user(ovalue, &get_buffer, sizeof(get_buffer))) + return -EFAULT; + return 0; +} diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c new file mode 100644 index 000000000000..1627f8d6e0cd --- /dev/null +++ b/kernel/kallsyms.c @@ -0,0 +1,411 @@ +/* + * kallsyms.c: in-kernel printing of symbolic oopses and stack traces. + * + * Rewritten and vastly simplified by Rusty Russell for in-kernel + * module loader: + * Copyright 2002 Rusty Russell IBM Corporation + * + * ChangeLog: + * + * (25/Aug/2004) Paulo Marques + * Changed the compression method from stem compression to "table lookup" + * compression (see scripts/kallsyms.c for a more complete description) + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#ifdef CONFIG_KALLSYMS_ALL +#define all_var 1 +#else +#define all_var 0 +#endif + +/* These will be re-linked against their real values during the second link stage */ +extern unsigned long kallsyms_addresses[] __attribute__((weak)); +extern unsigned long kallsyms_num_syms __attribute__((weak,section("data"))); +extern u8 kallsyms_names[] __attribute__((weak)); + +extern u8 kallsyms_token_table[] __attribute__((weak)); +extern u16 kallsyms_token_index[] __attribute__((weak)); + +extern unsigned long kallsyms_markers[] __attribute__((weak)); + +static inline int is_kernel_inittext(unsigned long addr) +{ + if (addr >= (unsigned long)_sinittext + && addr <= (unsigned long)_einittext) + return 1; + return 0; +} + +static inline int is_kernel_text(unsigned long addr) +{ + if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) + return 1; + return in_gate_area_no_task(addr); +} + +static inline int is_kernel(unsigned long addr) +{ + if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) + return 1; + return in_gate_area_no_task(addr); +} + +/* expand a compressed symbol data into the resulting uncompressed string, + given the offset to where the symbol is in the compressed stream */ +static unsigned int kallsyms_expand_symbol(unsigned int off, char *result) +{ + int len, skipped_first = 0; + u8 *tptr, *data; + + /* get the compressed symbol length from the first symbol byte */ + data = &kallsyms_names[off]; + len = *data; + data++; + + /* update the offset to return the offset for the next symbol on + * the compressed stream */ + off += len + 1; + + /* for every byte on the compressed symbol data, copy the table + entry for that byte */ + while(len) { + tptr = &kallsyms_token_table[ kallsyms_token_index[*data] ]; + data++; + len--; + + while (*tptr) { + if(skipped_first) { + *result = *tptr; + result++; + } else + skipped_first = 1; + tptr++; + } + } + + *result = '\0'; + + /* return to offset to the next symbol */ + return off; +} + +/* get symbol type information. This is encoded as a single char at the + * begining of the symbol name */ +static char kallsyms_get_symbol_type(unsigned int off) +{ + /* get just the first code, look it up in the token table, and return the + * first char from this token */ + return kallsyms_token_table[ kallsyms_token_index[ kallsyms_names[off+1] ] ]; +} + + +/* find the offset on the compressed stream given and index in the + * kallsyms array */ +static unsigned int get_symbol_offset(unsigned long pos) +{ + u8 *name; + int i; + + /* use the closest marker we have. We have markers every 256 positions, + * so that should be close enough */ + name = &kallsyms_names[ kallsyms_markers[pos>>8] ]; + + /* sequentially scan all the symbols up to the point we're searching for. + * Every symbol is stored in a [][ bytes of data] format, so we + * just need to add the len to the current pointer for every symbol we + * wish to skip */ + for(i = 0; i < (pos&0xFF); i++) + name = name + (*name) + 1; + + return name - kallsyms_names; +} + +/* Lookup the address for this symbol. Returns 0 if not found. */ +unsigned long kallsyms_lookup_name(const char *name) +{ + char namebuf[KSYM_NAME_LEN+1]; + unsigned long i; + unsigned int off; + + for (i = 0, off = 0; i < kallsyms_num_syms; i++) { + off = kallsyms_expand_symbol(off, namebuf); + + if (strcmp(namebuf, name) == 0) + return kallsyms_addresses[i]; + } + return module_kallsyms_lookup_name(name); +} +EXPORT_SYMBOL_GPL(kallsyms_lookup_name); + +/* + * Lookup an address + * - modname is set to NULL if it's in the kernel + * - we guarantee that the returned name is valid until we reschedule even if + * it resides in a module + * - we also guarantee that modname will be valid until rescheduled + */ +const char *kallsyms_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, char *namebuf) +{ + unsigned long i, low, high, mid; + const char *msym; + + /* This kernel should never had been booted. */ + BUG_ON(!kallsyms_addresses); + + namebuf[KSYM_NAME_LEN] = 0; + namebuf[0] = 0; + + if ((all_var && is_kernel(addr)) || + (!all_var && (is_kernel_text(addr) || is_kernel_inittext(addr)))) { + unsigned long symbol_end=0; + + /* do a binary search on the sorted kallsyms_addresses array */ + low = 0; + high = kallsyms_num_syms; + + while (high-low > 1) { + mid = (low + high) / 2; + if (kallsyms_addresses[mid] <= addr) low = mid; + else high = mid; + } + + /* search for the first aliased symbol. Aliased symbols are + symbols with the same address */ + while (low && kallsyms_addresses[low - 1] == kallsyms_addresses[low]) + --low; + + /* Grab name */ + kallsyms_expand_symbol(get_symbol_offset(low), namebuf); + + /* Search for next non-aliased symbol */ + for (i = low + 1; i < kallsyms_num_syms; i++) { + if (kallsyms_addresses[i] > kallsyms_addresses[low]) { + symbol_end = kallsyms_addresses[i]; + break; + } + } + + /* if we found no next symbol, we use the end of the section */ + if (!symbol_end) { + if (is_kernel_inittext(addr)) + symbol_end = (unsigned long)_einittext; + else + symbol_end = all_var ? (unsigned long)_end : (unsigned long)_etext; + } + + *symbolsize = symbol_end - kallsyms_addresses[low]; + *modname = NULL; + *offset = addr - kallsyms_addresses[low]; + return namebuf; + } + + /* see if it's in a module */ + msym = module_address_lookup(addr, symbolsize, offset, modname); + if (msym) + return strncpy(namebuf, msym, KSYM_NAME_LEN); + + return NULL; +} + +/* Replace "%s" in format with address, or returns -errno. */ +void __print_symbol(const char *fmt, unsigned long address) +{ + char *modname; + const char *name; + unsigned long offset, size; + char namebuf[KSYM_NAME_LEN+1]; + char buffer[sizeof("%s+%#lx/%#lx [%s]") + KSYM_NAME_LEN + + 2*(BITS_PER_LONG*3/10) + MODULE_NAME_LEN + 1]; + + name = kallsyms_lookup(address, &size, &offset, &modname, namebuf); + + if (!name) + sprintf(buffer, "0x%lx", address); + else { + if (modname) + sprintf(buffer, "%s+%#lx/%#lx [%s]", name, offset, + size, modname); + else + sprintf(buffer, "%s+%#lx/%#lx", name, offset, size); + } + printk(fmt, buffer); +} + +/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */ +struct kallsym_iter +{ + loff_t pos; + struct module *owner; + unsigned long value; + unsigned int nameoff; /* If iterating in core kernel symbols */ + char type; + char name[KSYM_NAME_LEN+1]; +}; + +/* Only label it "global" if it is exported. */ +static void upcase_if_global(struct kallsym_iter *iter) +{ + if (is_exported(iter->name, iter->owner)) + iter->type += 'A' - 'a'; +} + +static int get_ksymbol_mod(struct kallsym_iter *iter) +{ + iter->owner = module_get_kallsym(iter->pos - kallsyms_num_syms, + &iter->value, + &iter->type, iter->name); + if (iter->owner == NULL) + return 0; + + upcase_if_global(iter); + return 1; +} + +/* Returns space to next name. */ +static unsigned long get_ksymbol_core(struct kallsym_iter *iter) +{ + unsigned off = iter->nameoff; + + iter->owner = NULL; + iter->value = kallsyms_addresses[iter->pos]; + + iter->type = kallsyms_get_symbol_type(off); + + off = kallsyms_expand_symbol(off, iter->name); + + return off - iter->nameoff; +} + +static void reset_iter(struct kallsym_iter *iter, loff_t new_pos) +{ + iter->name[0] = '\0'; + iter->nameoff = get_symbol_offset(new_pos); + iter->pos = new_pos; +} + +/* Returns false if pos at or past end of file. */ +static int update_iter(struct kallsym_iter *iter, loff_t pos) +{ + /* Module symbols can be accessed randomly. */ + if (pos >= kallsyms_num_syms) { + iter->pos = pos; + return get_ksymbol_mod(iter); + } + + /* If we're not on the desired position, reset to new position. */ + if (pos != iter->pos) + reset_iter(iter, pos); + + iter->nameoff += get_ksymbol_core(iter); + iter->pos++; + + return 1; +} + +static void *s_next(struct seq_file *m, void *p, loff_t *pos) +{ + (*pos)++; + + if (!update_iter(m->private, *pos)) + return NULL; + return p; +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + if (!update_iter(m->private, *pos)) + return NULL; + return m->private; +} + +static void s_stop(struct seq_file *m, void *p) +{ +} + +static int s_show(struct seq_file *m, void *p) +{ + struct kallsym_iter *iter = m->private; + + /* Some debugging symbols have no name. Ignore them. */ + if (!iter->name[0]) + return 0; + + if (iter->owner) + seq_printf(m, "%0*lx %c %s\t[%s]\n", + (int)(2*sizeof(void*)), + iter->value, iter->type, iter->name, + module_name(iter->owner)); + else + seq_printf(m, "%0*lx %c %s\n", + (int)(2*sizeof(void*)), + iter->value, iter->type, iter->name); + return 0; +} + +static struct seq_operations kallsyms_op = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show +}; + +static int kallsyms_open(struct inode *inode, struct file *file) +{ + /* We keep iterator in m->private, since normal case is to + * s_start from where we left off, so we avoid doing + * using get_symbol_offset for every symbol */ + struct kallsym_iter *iter; + int ret; + + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + reset_iter(iter, 0); + + ret = seq_open(file, &kallsyms_op); + if (ret == 0) + ((struct seq_file *)file->private_data)->private = iter; + else + kfree(iter); + return ret; +} + +static int kallsyms_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + kfree(m->private); + return seq_release(inode, file); +} + +static struct file_operations kallsyms_operations = { + .open = kallsyms_open, + .read = seq_read, + .llseek = seq_lseek, + .release = kallsyms_release, +}; + +static int __init kallsyms_init(void) +{ + struct proc_dir_entry *entry; + + entry = create_proc_entry("kallsyms", 0444, NULL); + if (entry) + entry->proc_fops = &kallsyms_operations; + return 0; +} +__initcall(kallsyms_init); + +EXPORT_SYMBOL(__print_symbol); diff --git a/kernel/kfifo.c b/kernel/kfifo.c new file mode 100644 index 000000000000..179baafcdd96 --- /dev/null +++ b/kernel/kfifo.c @@ -0,0 +1,168 @@ +/* + * A simple kernel FIFO implementation. + * + * Copyright (C) 2004 Stelian Pop + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#include +#include +#include +#include +#include + +/** + * kfifo_init - allocates a new FIFO using a preallocated buffer + * @buffer: the preallocated buffer to be used. + * @size: the size of the internal buffer, this have to be a power of 2. + * @gfp_mask: get_free_pages mask, passed to kmalloc() + * @lock: the lock to be used to protect the fifo buffer + * + * Do NOT pass the kfifo to kfifo_free() after use ! Simply free the + * struct kfifo with kfree(). + */ +struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size, + unsigned int __nocast gfp_mask, spinlock_t *lock) +{ + struct kfifo *fifo; + + /* size must be a power of 2 */ + BUG_ON(size & (size - 1)); + + fifo = kmalloc(sizeof(struct kfifo), gfp_mask); + if (!fifo) + return ERR_PTR(-ENOMEM); + + fifo->buffer = buffer; + fifo->size = size; + fifo->in = fifo->out = 0; + fifo->lock = lock; + + return fifo; +} +EXPORT_SYMBOL(kfifo_init); + +/** + * kfifo_alloc - allocates a new FIFO and its internal buffer + * @size: the size of the internal buffer to be allocated. + * @gfp_mask: get_free_pages mask, passed to kmalloc() + * @lock: the lock to be used to protect the fifo buffer + * + * The size will be rounded-up to a power of 2. + */ +struct kfifo *kfifo_alloc(unsigned int size, unsigned int __nocast gfp_mask, spinlock_t *lock) +{ + unsigned char *buffer; + struct kfifo *ret; + + /* + * round up to the next power of 2, since our 'let the indices + * wrap' tachnique works only in this case. + */ + if (size & (size - 1)) { + BUG_ON(size > 0x80000000); + size = roundup_pow_of_two(size); + } + + buffer = kmalloc(size, gfp_mask); + if (!buffer) + return ERR_PTR(-ENOMEM); + + ret = kfifo_init(buffer, size, gfp_mask, lock); + + if (IS_ERR(ret)) + kfree(buffer); + + return ret; +} +EXPORT_SYMBOL(kfifo_alloc); + +/** + * kfifo_free - frees the FIFO + * @fifo: the fifo to be freed. + */ +void kfifo_free(struct kfifo *fifo) +{ + kfree(fifo->buffer); + kfree(fifo); +} +EXPORT_SYMBOL(kfifo_free); + +/** + * __kfifo_put - puts some data into the FIFO, no locking version + * @fifo: the fifo to be used. + * @buffer: the data to be added. + * @len: the length of the data to be added. + * + * This function copies at most 'len' bytes from the 'buffer' into + * the FIFO depending on the free space, and returns the number of + * bytes copied. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these functions. + */ +unsigned int __kfifo_put(struct kfifo *fifo, + unsigned char *buffer, unsigned int len) +{ + unsigned int l; + + len = min(len, fifo->size - fifo->in + fifo->out); + + /* first put the data starting from fifo->in to buffer end */ + l = min(len, fifo->size - (fifo->in & (fifo->size - 1))); + memcpy(fifo->buffer + (fifo->in & (fifo->size - 1)), buffer, l); + + /* then put the rest (if any) at the beginning of the buffer */ + memcpy(fifo->buffer, buffer + l, len - l); + + fifo->in += len; + + return len; +} +EXPORT_SYMBOL(__kfifo_put); + +/** + * __kfifo_get - gets some data from the FIFO, no locking version + * @fifo: the fifo to be used. + * @buffer: where the data must be copied. + * @len: the size of the destination buffer. + * + * This function copies at most 'len' bytes from the FIFO into the + * 'buffer' and returns the number of copied bytes. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these functions. + */ +unsigned int __kfifo_get(struct kfifo *fifo, + unsigned char *buffer, unsigned int len) +{ + unsigned int l; + + len = min(len, fifo->in - fifo->out); + + /* first get the data from fifo->out until the end of the buffer */ + l = min(len, fifo->size - (fifo->out & (fifo->size - 1))); + memcpy(buffer, fifo->buffer + (fifo->out & (fifo->size - 1)), l); + + /* then get the rest (if any) from the beginning of the buffer */ + memcpy(buffer + l, fifo->buffer, len - l); + + fifo->out += len; + + return len; +} +EXPORT_SYMBOL(__kfifo_get); diff --git a/kernel/kmod.c b/kernel/kmod.c new file mode 100644 index 000000000000..eed53d4f5230 --- /dev/null +++ b/kernel/kmod.c @@ -0,0 +1,256 @@ +/* + kmod, the new module loader (replaces kerneld) + Kirk Petersen + + Reorganized not to be a daemon by Adam Richter, with guidance + from Greg Zornetzer. + + Modified to avoid chroot and file sharing problems. + Mikael Pettersson + + Limit the concurrent number of kmod modprobes to catch loops from + "modprobe needs a service that is in a module". + Keith Owens December 1999 + + Unblock all signals when we exec a usermode process. + Shuu Yamaguchi December 2000 + + call_usermodehelper wait flag, and remove exec_usermodehelper. + Rusty Russell Jan 2003 +*/ +#define __KERNEL_SYSCALLS__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern int max_threads; + +static struct workqueue_struct *khelper_wq; + +#ifdef CONFIG_KMOD + +/* + modprobe_path is set via /proc/sys. +*/ +char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; + +/** + * request_module - try to load a kernel module + * @fmt: printf style format string for the name of the module + * @varargs: arguements as specified in the format string + * + * Load a module using the user mode module loader. The function returns + * zero on success or a negative errno code on failure. Note that a + * successful module load does not mean the module did not then unload + * and exit on an error of its own. Callers must check that the service + * they requested is now available not blindly invoke it. + * + * If module auto-loading support is disabled then this function + * becomes a no-operation. + */ +int request_module(const char *fmt, ...) +{ + va_list args; + char module_name[MODULE_NAME_LEN]; + unsigned int max_modprobes; + int ret; + char *argv[] = { modprobe_path, "-q", "--", module_name, NULL }; + static char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL }; + static atomic_t kmod_concurrent = ATOMIC_INIT(0); +#define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */ + static int kmod_loop_msg; + + va_start(args, fmt); + ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); + va_end(args); + if (ret >= MODULE_NAME_LEN) + return -ENAMETOOLONG; + + /* If modprobe needs a service that is in a module, we get a recursive + * loop. Limit the number of running kmod threads to max_threads/2 or + * MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method + * would be to run the parents of this process, counting how many times + * kmod was invoked. That would mean accessing the internals of the + * process tables to get the command line, proc_pid_cmdline is static + * and it is not worth changing the proc code just to handle this case. + * KAO. + * + * "trace the ppid" is simple, but will fail if someone's + * parent exits. I think this is as good as it gets. --RR + */ + max_modprobes = min(max_threads/2, MAX_KMOD_CONCURRENT); + atomic_inc(&kmod_concurrent); + if (atomic_read(&kmod_concurrent) > max_modprobes) { + /* We may be blaming an innocent here, but unlikely */ + if (kmod_loop_msg++ < 5) + printk(KERN_ERR + "request_module: runaway loop modprobe %s\n", + module_name); + atomic_dec(&kmod_concurrent); + return -ENOMEM; + } + + ret = call_usermodehelper(modprobe_path, argv, envp, 1); + atomic_dec(&kmod_concurrent); + return ret; +} +EXPORT_SYMBOL(request_module); +#endif /* CONFIG_KMOD */ + +struct subprocess_info { + struct completion *complete; + char *path; + char **argv; + char **envp; + int wait; + int retval; +}; + +/* + * This is the task which runs the usermode application + */ +static int ____call_usermodehelper(void *data) +{ + struct subprocess_info *sub_info = data; + int retval; + + /* Unblock all signals. */ + flush_signals(current); + spin_lock_irq(¤t->sighand->siglock); + flush_signal_handlers(current, 1); + sigemptyset(¤t->blocked); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + /* We can run anywhere, unlike our parent keventd(). */ + set_cpus_allowed(current, CPU_MASK_ALL); + + retval = -EPERM; + if (current->fs->root) + retval = execve(sub_info->path, sub_info->argv,sub_info->envp); + + /* Exec failed? */ + sub_info->retval = retval; + do_exit(0); +} + +/* Keventd can't block, but this (a child) can. */ +static int wait_for_helper(void *data) +{ + struct subprocess_info *sub_info = data; + pid_t pid; + struct k_sigaction sa; + + /* Install a handler: if SIGCLD isn't handled sys_wait4 won't + * populate the status, but will return -ECHILD. */ + sa.sa.sa_handler = SIG_IGN; + sa.sa.sa_flags = 0; + siginitset(&sa.sa.sa_mask, sigmask(SIGCHLD)); + do_sigaction(SIGCHLD, &sa, (struct k_sigaction *)0); + allow_signal(SIGCHLD); + + pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD); + if (pid < 0) { + sub_info->retval = pid; + } else { + /* + * Normally it is bogus to call wait4() from in-kernel because + * wait4() wants to write the exit code to a userspace address. + * But wait_for_helper() always runs as keventd, and put_user() + * to a kernel address works OK for kernel threads, due to their + * having an mm_segment_t which spans the entire address space. + * + * Thus the __user pointer cast is valid here. + */ + sys_wait4(pid, (int __user *) &sub_info->retval, 0, NULL); + } + + complete(sub_info->complete); + return 0; +} + +/* This is run by khelper thread */ +static void __call_usermodehelper(void *data) +{ + struct subprocess_info *sub_info = data; + pid_t pid; + + /* CLONE_VFORK: wait until the usermode helper has execve'd + * successfully We need the data structures to stay around + * until that is done. */ + if (sub_info->wait) + pid = kernel_thread(wait_for_helper, sub_info, + CLONE_FS | CLONE_FILES | SIGCHLD); + else + pid = kernel_thread(____call_usermodehelper, sub_info, + CLONE_VFORK | SIGCHLD); + + if (pid < 0) { + sub_info->retval = pid; + complete(sub_info->complete); + } else if (!sub_info->wait) + complete(sub_info->complete); +} + +/** + * call_usermodehelper - start a usermode application + * @path: pathname for the application + * @argv: null-terminated argument list + * @envp: null-terminated environment list + * @wait: wait for the application to finish and return status. + * + * Runs a user-space application. The application is started + * asynchronously if wait is not set, and runs as a child of keventd. + * (ie. it runs with full root capabilities). + * + * Must be called from process context. Returns a negative error code + * if program was not execed successfully, or 0. + */ +int call_usermodehelper(char *path, char **argv, char **envp, int wait) +{ + DECLARE_COMPLETION(done); + struct subprocess_info sub_info = { + .complete = &done, + .path = path, + .argv = argv, + .envp = envp, + .wait = wait, + .retval = 0, + }; + DECLARE_WORK(work, __call_usermodehelper, &sub_info); + + if (!khelper_wq) + return -EBUSY; + + if (path[0] == '\0') + return 0; + + queue_work(khelper_wq, &work); + wait_for_completion(&done); + return sub_info.retval; +} +EXPORT_SYMBOL(call_usermodehelper); + +void __init usermodehelper_init(void) +{ + khelper_wq = create_singlethread_workqueue("khelper"); + BUG_ON(!khelper_wq); +} diff --git a/kernel/kprobes.c b/kernel/kprobes.c new file mode 100644 index 000000000000..1d5dd1337bd1 --- /dev/null +++ b/kernel/kprobes.c @@ -0,0 +1,157 @@ +/* + * Kernel Probes (KProbes) + * kernel/kprobes.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * + * 2002-Oct Created by Vamsi Krishna S Kernel + * Probes initial implementation (includes suggestions from + * Rusty Russell). + * 2004-Aug Updated by Prasanna S Panchamukhi with + * hlists and exceptions notifier as suggested by Andi Kleen. + * 2004-July Suparna Bhattacharya added jumper probes + * interface to access function arguments. + * 2004-Sep Prasanna S Panchamukhi Changed Kprobes + * exceptions notifier to be first on the priority list. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#define KPROBE_HASH_BITS 6 +#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) + +static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; + +unsigned int kprobe_cpu = NR_CPUS; +static DEFINE_SPINLOCK(kprobe_lock); + +/* Locks kprobe: irqs must be disabled */ +void lock_kprobes(void) +{ + spin_lock(&kprobe_lock); + kprobe_cpu = smp_processor_id(); +} + +void unlock_kprobes(void) +{ + kprobe_cpu = NR_CPUS; + spin_unlock(&kprobe_lock); +} + +/* You have to be holding the kprobe_lock */ +struct kprobe *get_kprobe(void *addr) +{ + struct hlist_head *head; + struct hlist_node *node; + + head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; + hlist_for_each(node, head) { + struct kprobe *p = hlist_entry(node, struct kprobe, hlist); + if (p->addr == addr) + return p; + } + return NULL; +} + +int register_kprobe(struct kprobe *p) +{ + int ret = 0; + unsigned long flags = 0; + + if ((ret = arch_prepare_kprobe(p)) != 0) { + goto rm_kprobe; + } + spin_lock_irqsave(&kprobe_lock, flags); + INIT_HLIST_NODE(&p->hlist); + if (get_kprobe(p->addr)) { + ret = -EEXIST; + goto out; + } + arch_copy_kprobe(p); + + hlist_add_head(&p->hlist, + &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); + + p->opcode = *p->addr; + *p->addr = BREAKPOINT_INSTRUCTION; + flush_icache_range((unsigned long) p->addr, + (unsigned long) p->addr + sizeof(kprobe_opcode_t)); +out: + spin_unlock_irqrestore(&kprobe_lock, flags); +rm_kprobe: + if (ret == -EEXIST) + arch_remove_kprobe(p); + return ret; +} + +void unregister_kprobe(struct kprobe *p) +{ + unsigned long flags; + arch_remove_kprobe(p); + spin_lock_irqsave(&kprobe_lock, flags); + *p->addr = p->opcode; + hlist_del(&p->hlist); + flush_icache_range((unsigned long) p->addr, + (unsigned long) p->addr + sizeof(kprobe_opcode_t)); + spin_unlock_irqrestore(&kprobe_lock, flags); +} + +static struct notifier_block kprobe_exceptions_nb = { + .notifier_call = kprobe_exceptions_notify, + .priority = 0x7fffffff /* we need to notified first */ +}; + +int register_jprobe(struct jprobe *jp) +{ + /* Todo: Verify probepoint is a function entry point */ + jp->kp.pre_handler = setjmp_pre_handler; + jp->kp.break_handler = longjmp_break_handler; + + return register_kprobe(&jp->kp); +} + +void unregister_jprobe(struct jprobe *jp) +{ + unregister_kprobe(&jp->kp); +} + +static int __init init_kprobes(void) +{ + int i, err = 0; + + /* FIXME allocate the probe table, currently defined statically */ + /* initialize all list heads */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) + INIT_HLIST_HEAD(&kprobe_table[i]); + + err = register_die_notifier(&kprobe_exceptions_nb); + return err; +} + +__initcall(init_kprobes); + +EXPORT_SYMBOL_GPL(register_kprobe); +EXPORT_SYMBOL_GPL(unregister_kprobe); +EXPORT_SYMBOL_GPL(register_jprobe); +EXPORT_SYMBOL_GPL(unregister_jprobe); +EXPORT_SYMBOL_GPL(jprobe_return); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c new file mode 100644 index 000000000000..1f064a63f8cf --- /dev/null +++ b/kernel/ksysfs.c @@ -0,0 +1,57 @@ +/* + * kernel/ksysfs.c - sysfs attributes in /sys/kernel, which + * are not related to any other subsystem + * + * Copyright (C) 2004 Kay Sievers + * + * This file is release under the GPLv2 + * + */ + +#include +#include +#include +#include +#include +#include + +#define KERNEL_ATTR_RO(_name) \ +static struct subsys_attribute _name##_attr = __ATTR_RO(_name) + +#define KERNEL_ATTR_RW(_name) \ +static struct subsys_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +#ifdef CONFIG_HOTPLUG +static ssize_t hotplug_seqnum_show(struct subsystem *subsys, char *page) +{ + return sprintf(page, "%llu\n", (unsigned long long)hotplug_seqnum); +} +KERNEL_ATTR_RO(hotplug_seqnum); +#endif + +decl_subsys(kernel, NULL, NULL); +EXPORT_SYMBOL_GPL(kernel_subsys); + +static struct attribute * kernel_attrs[] = { +#ifdef CONFIG_HOTPLUG + &hotplug_seqnum_attr.attr, +#endif + NULL +}; + +static struct attribute_group kernel_attr_group = { + .attrs = kernel_attrs, +}; + +static int __init ksysfs_init(void) +{ + int error = subsystem_register(&kernel_subsys); + if (!error) + error = sysfs_create_group(&kernel_subsys.kset.kobj, + &kernel_attr_group); + + return error; +} + +core_initcall(ksysfs_init); diff --git a/kernel/kthread.c b/kernel/kthread.c new file mode 100644 index 000000000000..e377e2244103 --- /dev/null +++ b/kernel/kthread.c @@ -0,0 +1,202 @@ +/* Kernel thread helper functions. + * Copyright (C) 2004 IBM Corporation, Rusty Russell. + * + * Creation is done via keventd, so that we get a clean environment + * even if we're invoked from userspace (think modprobe, hotplug cpu, + * etc.). + */ +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * We dont want to execute off keventd since it might + * hold a semaphore our callers hold too: + */ +static struct workqueue_struct *helper_wq; + +struct kthread_create_info +{ + /* Information passed to kthread() from keventd. */ + int (*threadfn)(void *data); + void *data; + struct completion started; + + /* Result passed back to kthread_create() from keventd. */ + struct task_struct *result; + struct completion done; +}; + +struct kthread_stop_info +{ + struct task_struct *k; + int err; + struct completion done; +}; + +/* Thread stopping is done by setthing this var: lock serializes + * multiple kthread_stop calls. */ +static DECLARE_MUTEX(kthread_stop_lock); +static struct kthread_stop_info kthread_stop_info; + +int kthread_should_stop(void) +{ + return (kthread_stop_info.k == current); +} +EXPORT_SYMBOL(kthread_should_stop); + +static void kthread_exit_files(void) +{ + struct fs_struct *fs; + struct task_struct *tsk = current; + + exit_fs(tsk); /* current->fs->count--; */ + fs = init_task.fs; + tsk->fs = fs; + atomic_inc(&fs->count); + exit_files(tsk); + current->files = init_task.files; + atomic_inc(&tsk->files->count); +} + +static int kthread(void *_create) +{ + struct kthread_create_info *create = _create; + int (*threadfn)(void *data); + void *data; + sigset_t blocked; + int ret = -EINTR; + + kthread_exit_files(); + + /* Copy data: it's on keventd's stack */ + threadfn = create->threadfn; + data = create->data; + + /* Block and flush all signals (in case we're not from keventd). */ + sigfillset(&blocked); + sigprocmask(SIG_BLOCK, &blocked, NULL); + flush_signals(current); + + /* By default we can run anywhere, unlike keventd. */ + set_cpus_allowed(current, CPU_MASK_ALL); + + /* OK, tell user we're spawned, wait for stop or wakeup */ + __set_current_state(TASK_INTERRUPTIBLE); + complete(&create->started); + schedule(); + + if (!kthread_should_stop()) + ret = threadfn(data); + + /* It might have exited on its own, w/o kthread_stop. Check. */ + if (kthread_should_stop()) { + kthread_stop_info.err = ret; + complete(&kthread_stop_info.done); + } + return 0; +} + +/* We are keventd: create a thread. */ +static void keventd_create_kthread(void *_create) +{ + struct kthread_create_info *create = _create; + int pid; + + /* We want our own signal handler (we take no signals by default). */ + pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); + if (pid < 0) { + create->result = ERR_PTR(pid); + } else { + wait_for_completion(&create->started); + create->result = find_task_by_pid(pid); + } + complete(&create->done); +} + +struct task_struct *kthread_create(int (*threadfn)(void *data), + void *data, + const char namefmt[], + ...) +{ + struct kthread_create_info create; + DECLARE_WORK(work, keventd_create_kthread, &create); + + create.threadfn = threadfn; + create.data = data; + init_completion(&create.started); + init_completion(&create.done); + + /* + * The workqueue needs to start up first: + */ + if (!helper_wq) + work.func(work.data); + else { + queue_work(helper_wq, &work); + wait_for_completion(&create.done); + } + if (!IS_ERR(create.result)) { + va_list args; + va_start(args, namefmt); + vsnprintf(create.result->comm, sizeof(create.result->comm), + namefmt, args); + va_end(args); + } + + return create.result; +} +EXPORT_SYMBOL(kthread_create); + +void kthread_bind(struct task_struct *k, unsigned int cpu) +{ + BUG_ON(k->state != TASK_INTERRUPTIBLE); + /* Must have done schedule() in kthread() before we set_task_cpu */ + wait_task_inactive(k); + set_task_cpu(k, cpu); + k->cpus_allowed = cpumask_of_cpu(cpu); +} +EXPORT_SYMBOL(kthread_bind); + +int kthread_stop(struct task_struct *k) +{ + int ret; + + down(&kthread_stop_lock); + + /* It could exit after stop_info.k set, but before wake_up_process. */ + get_task_struct(k); + + /* Must init completion *before* thread sees kthread_stop_info.k */ + init_completion(&kthread_stop_info.done); + wmb(); + + /* Now set kthread_should_stop() to true, and wake it up. */ + kthread_stop_info.k = k; + wake_up_process(k); + put_task_struct(k); + + /* Once it dies, reset stop ptr, gather result and we're done. */ + wait_for_completion(&kthread_stop_info.done); + kthread_stop_info.k = NULL; + ret = kthread_stop_info.err; + up(&kthread_stop_lock); + + return ret; +} +EXPORT_SYMBOL(kthread_stop); + +static __init int helper_init(void) +{ + helper_wq = create_singlethread_workqueue("kthread"); + BUG_ON(!helper_wq); + + return 0; +} +core_initcall(helper_init); + diff --git a/kernel/module.c b/kernel/module.c new file mode 100644 index 000000000000..2dbfa0773faf --- /dev/null +++ b/kernel/module.c @@ -0,0 +1,2108 @@ +/* Rewritten by Rusty Russell, on the backs of many others... + Copyright (C) 2002 Richard Henderson + Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt , a...) +#endif + +#ifndef ARCH_SHF_SMALL +#define ARCH_SHF_SMALL 0 +#endif + +/* If this is set, the section belongs in the init part of the module */ +#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) + +/* Protects module list */ +static DEFINE_SPINLOCK(modlist_lock); + +/* List of modules, protected by module_mutex AND modlist_lock */ +static DECLARE_MUTEX(module_mutex); +static LIST_HEAD(modules); + +static DECLARE_MUTEX(notify_mutex); +static struct notifier_block * module_notify_list; + +int register_module_notifier(struct notifier_block * nb) +{ + int err; + down(¬ify_mutex); + err = notifier_chain_register(&module_notify_list, nb); + up(¬ify_mutex); + return err; +} +EXPORT_SYMBOL(register_module_notifier); + +int unregister_module_notifier(struct notifier_block * nb) +{ + int err; + down(¬ify_mutex); + err = notifier_chain_unregister(&module_notify_list, nb); + up(¬ify_mutex); + return err; +} +EXPORT_SYMBOL(unregister_module_notifier); + +/* We require a truly strong try_module_get() */ +static inline int strong_try_module_get(struct module *mod) +{ + if (mod && mod->state == MODULE_STATE_COMING) + return 0; + return try_module_get(mod); +} + +/* A thread that wants to hold a reference to a module only while it + * is running can call ths to safely exit. + * nfsd and lockd use this. + */ +void __module_put_and_exit(struct module *mod, long code) +{ + module_put(mod); + do_exit(code); +} +EXPORT_SYMBOL(__module_put_and_exit); + +/* Find a module section: 0 means not found. */ +static unsigned int find_sec(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings, + const char *name) +{ + unsigned int i; + + for (i = 1; i < hdr->e_shnum; i++) + /* Alloc bit cleared means "ignore it." */ + if ((sechdrs[i].sh_flags & SHF_ALLOC) + && strcmp(secstrings+sechdrs[i].sh_name, name) == 0) + return i; + return 0; +} + +/* Provided by the linker */ +extern const struct kernel_symbol __start___ksymtab[]; +extern const struct kernel_symbol __stop___ksymtab[]; +extern const struct kernel_symbol __start___ksymtab_gpl[]; +extern const struct kernel_symbol __stop___ksymtab_gpl[]; +extern const unsigned long __start___kcrctab[]; +extern const unsigned long __start___kcrctab_gpl[]; + +#ifndef CONFIG_MODVERSIONS +#define symversion(base, idx) NULL +#else +#define symversion(base, idx) ((base) ? ((base) + (idx)) : NULL) +#endif + +/* Find a symbol, return value, crc and module which owns it */ +static unsigned long __find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + int gplok) +{ + struct module *mod; + unsigned int i; + + /* Core kernel first. */ + *owner = NULL; + for (i = 0; __start___ksymtab+i < __stop___ksymtab; i++) { + if (strcmp(__start___ksymtab[i].name, name) == 0) { + *crc = symversion(__start___kcrctab, i); + return __start___ksymtab[i].value; + } + } + if (gplok) { + for (i = 0; __start___ksymtab_gpl+i<__stop___ksymtab_gpl; i++) + if (strcmp(__start___ksymtab_gpl[i].name, name) == 0) { + *crc = symversion(__start___kcrctab_gpl, i); + return __start___ksymtab_gpl[i].value; + } + } + + /* Now try modules. */ + list_for_each_entry(mod, &modules, list) { + *owner = mod; + for (i = 0; i < mod->num_syms; i++) + if (strcmp(mod->syms[i].name, name) == 0) { + *crc = symversion(mod->crcs, i); + return mod->syms[i].value; + } + + if (gplok) { + for (i = 0; i < mod->num_gpl_syms; i++) { + if (strcmp(mod->gpl_syms[i].name, name) == 0) { + *crc = symversion(mod->gpl_crcs, i); + return mod->gpl_syms[i].value; + } + } + } + } + DEBUGP("Failed to find symbol %s\n", name); + return 0; +} + +/* Find a symbol in this elf symbol table */ +static unsigned long find_local_symbol(Elf_Shdr *sechdrs, + unsigned int symindex, + const char *strtab, + const char *name) +{ + unsigned int i; + Elf_Sym *sym = (void *)sechdrs[symindex].sh_addr; + + /* Search (defined) internal symbols first. */ + for (i = 1; i < sechdrs[symindex].sh_size/sizeof(*sym); i++) { + if (sym[i].st_shndx != SHN_UNDEF + && strcmp(name, strtab + sym[i].st_name) == 0) + return sym[i].st_value; + } + return 0; +} + +/* Search for module by name: must hold module_mutex. */ +static struct module *find_module(const char *name) +{ + struct module *mod; + + list_for_each_entry(mod, &modules, list) { + if (strcmp(mod->name, name) == 0) + return mod; + } + return NULL; +} + +#ifdef CONFIG_SMP +/* Number of blocks used and allocated. */ +static unsigned int pcpu_num_used, pcpu_num_allocated; +/* Size of each block. -ve means used. */ +static int *pcpu_size; + +static int split_block(unsigned int i, unsigned short size) +{ + /* Reallocation required? */ + if (pcpu_num_used + 1 > pcpu_num_allocated) { + int *new = kmalloc(sizeof(new[0]) * pcpu_num_allocated*2, + GFP_KERNEL); + if (!new) + return 0; + + memcpy(new, pcpu_size, sizeof(new[0])*pcpu_num_allocated); + pcpu_num_allocated *= 2; + kfree(pcpu_size); + pcpu_size = new; + } + + /* Insert a new subblock */ + memmove(&pcpu_size[i+1], &pcpu_size[i], + sizeof(pcpu_size[0]) * (pcpu_num_used - i)); + pcpu_num_used++; + + pcpu_size[i+1] -= size; + pcpu_size[i] = size; + return 1; +} + +static inline unsigned int block_size(int val) +{ + if (val < 0) + return -val; + return val; +} + +/* Created by linker magic */ +extern char __per_cpu_start[], __per_cpu_end[]; + +static void *percpu_modalloc(unsigned long size, unsigned long align) +{ + unsigned long extra; + unsigned int i; + void *ptr; + + BUG_ON(align > SMP_CACHE_BYTES); + + ptr = __per_cpu_start; + for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) { + /* Extra for alignment requirement. */ + extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr; + BUG_ON(i == 0 && extra != 0); + + if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size) + continue; + + /* Transfer extra to previous block. */ + if (pcpu_size[i-1] < 0) + pcpu_size[i-1] -= extra; + else + pcpu_size[i-1] += extra; + pcpu_size[i] -= extra; + ptr += extra; + + /* Split block if warranted */ + if (pcpu_size[i] - size > sizeof(unsigned long)) + if (!split_block(i, size)) + return NULL; + + /* Mark allocated */ + pcpu_size[i] = -pcpu_size[i]; + return ptr; + } + + printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n", + size); + return NULL; +} + +static void percpu_modfree(void *freeme) +{ + unsigned int i; + void *ptr = __per_cpu_start + block_size(pcpu_size[0]); + + /* First entry is core kernel percpu data. */ + for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) { + if (ptr == freeme) { + pcpu_size[i] = -pcpu_size[i]; + goto free; + } + } + BUG(); + + free: + /* Merge with previous? */ + if (pcpu_size[i-1] >= 0) { + pcpu_size[i-1] += pcpu_size[i]; + pcpu_num_used--; + memmove(&pcpu_size[i], &pcpu_size[i+1], + (pcpu_num_used - i) * sizeof(pcpu_size[0])); + i--; + } + /* Merge with next? */ + if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) { + pcpu_size[i] += pcpu_size[i+1]; + pcpu_num_used--; + memmove(&pcpu_size[i+1], &pcpu_size[i+2], + (pcpu_num_used - (i+1)) * sizeof(pcpu_size[0])); + } +} + +static unsigned int find_pcpusec(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings) +{ + return find_sec(hdr, sechdrs, secstrings, ".data.percpu"); +} + +static int percpu_modinit(void) +{ + pcpu_num_used = 2; + pcpu_num_allocated = 2; + pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated, + GFP_KERNEL); + /* Static in-kernel percpu data (used). */ + pcpu_size[0] = -ALIGN(__per_cpu_end-__per_cpu_start, SMP_CACHE_BYTES); + /* Free room. */ + pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0]; + if (pcpu_size[1] < 0) { + printk(KERN_ERR "No per-cpu room for modules.\n"); + pcpu_num_used = 1; + } + + return 0; +} +__initcall(percpu_modinit); +#else /* ... !CONFIG_SMP */ +static inline void *percpu_modalloc(unsigned long size, unsigned long align) +{ + return NULL; +} +static inline void percpu_modfree(void *pcpuptr) +{ + BUG(); +} +static inline unsigned int find_pcpusec(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings) +{ + return 0; +} +static inline void percpu_modcopy(void *pcpudst, const void *src, + unsigned long size) +{ + /* pcpusec should be 0, and size of that section should be 0. */ + BUG_ON(size != 0); +} +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_MODULE_UNLOAD +/* Init the unload section of the module. */ +static void module_unload_init(struct module *mod) +{ + unsigned int i; + + INIT_LIST_HEAD(&mod->modules_which_use_me); + for (i = 0; i < NR_CPUS; i++) + local_set(&mod->ref[i].count, 0); + /* Hold reference count during initialization. */ + local_set(&mod->ref[_smp_processor_id()].count, 1); + /* Backwards compatibility macros put refcount during init. */ + mod->waiter = current; +} + +/* modules using other modules */ +struct module_use +{ + struct list_head list; + struct module *module_which_uses; +}; + +/* Does a already use b? */ +static int already_uses(struct module *a, struct module *b) +{ + struct module_use *use; + + list_for_each_entry(use, &b->modules_which_use_me, list) { + if (use->module_which_uses == a) { + DEBUGP("%s uses %s!\n", a->name, b->name); + return 1; + } + } + DEBUGP("%s does not use %s!\n", a->name, b->name); + return 0; +} + +/* Module a uses b */ +static int use_module(struct module *a, struct module *b) +{ + struct module_use *use; + if (b == NULL || already_uses(a, b)) return 1; + + if (!strong_try_module_get(b)) + return 0; + + DEBUGP("Allocating new usage for %s.\n", a->name); + use = kmalloc(sizeof(*use), GFP_ATOMIC); + if (!use) { + printk("%s: out of memory loading\n", a->name); + module_put(b); + return 0; + } + + use->module_which_uses = a; + list_add(&use->list, &b->modules_which_use_me); + return 1; +} + +/* Clear the unload stuff of the module. */ +static void module_unload_free(struct module *mod) +{ + struct module *i; + + list_for_each_entry(i, &modules, list) { + struct module_use *use; + + list_for_each_entry(use, &i->modules_which_use_me, list) { + if (use->module_which_uses == mod) { + DEBUGP("%s unusing %s\n", mod->name, i->name); + module_put(i); + list_del(&use->list); + kfree(use); + /* There can be at most one match. */ + break; + } + } + } +} + +#ifdef CONFIG_MODULE_FORCE_UNLOAD +static inline int try_force(unsigned int flags) +{ + int ret = (flags & O_TRUNC); + if (ret) + tainted |= TAINT_FORCED_MODULE; + return ret; +} +#else +static inline int try_force(unsigned int flags) +{ + return 0; +} +#endif /* CONFIG_MODULE_FORCE_UNLOAD */ + +struct stopref +{ + struct module *mod; + int flags; + int *forced; +}; + +/* Whole machine is stopped with interrupts off when this runs. */ +static int __try_stop_module(void *_sref) +{ + struct stopref *sref = _sref; + + /* If it's not unused, quit unless we are told to block. */ + if ((sref->flags & O_NONBLOCK) && module_refcount(sref->mod) != 0) { + if (!(*sref->forced = try_force(sref->flags))) + return -EWOULDBLOCK; + } + + /* Mark it as dying. */ + sref->mod->state = MODULE_STATE_GOING; + return 0; +} + +static int try_stop_module(struct module *mod, int flags, int *forced) +{ + struct stopref sref = { mod, flags, forced }; + + return stop_machine_run(__try_stop_module, &sref, NR_CPUS); +} + +unsigned int module_refcount(struct module *mod) +{ + unsigned int i, total = 0; + + for (i = 0; i < NR_CPUS; i++) + total += local_read(&mod->ref[i].count); + return total; +} +EXPORT_SYMBOL(module_refcount); + +/* This exists whether we can unload or not */ +static void free_module(struct module *mod); + +static void wait_for_zero_refcount(struct module *mod) +{ + /* Since we might sleep for some time, drop the semaphore first */ + up(&module_mutex); + for (;;) { + DEBUGP("Looking at refcount...\n"); + set_current_state(TASK_UNINTERRUPTIBLE); + if (module_refcount(mod) == 0) + break; + schedule(); + } + current->state = TASK_RUNNING; + down(&module_mutex); +} + +asmlinkage long +sys_delete_module(const char __user *name_user, unsigned int flags) +{ + struct module *mod; + char name[MODULE_NAME_LEN]; + int ret, forced = 0; + + if (!capable(CAP_SYS_MODULE)) + return -EPERM; + + if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0) + return -EFAULT; + name[MODULE_NAME_LEN-1] = '\0'; + + if (down_interruptible(&module_mutex) != 0) + return -EINTR; + + mod = find_module(name); + if (!mod) { + ret = -ENOENT; + goto out; + } + + if (!list_empty(&mod->modules_which_use_me)) { + /* Other modules depend on us: get rid of them first. */ + ret = -EWOULDBLOCK; + goto out; + } + + /* Doing init or already dying? */ + if (mod->state != MODULE_STATE_LIVE) { + /* FIXME: if (force), slam module count and wake up + waiter --RR */ + DEBUGP("%s already dying\n", mod->name); + ret = -EBUSY; + goto out; + } + + /* If it has an init func, it must have an exit func to unload */ + if ((mod->init != NULL && mod->exit == NULL) + || mod->unsafe) { + forced = try_force(flags); + if (!forced) { + /* This module can't be removed */ + ret = -EBUSY; + goto out; + } + } + + /* Set this up before setting mod->state */ + mod->waiter = current; + + /* Stop the machine so refcounts can't move and disable module. */ + ret = try_stop_module(mod, flags, &forced); + if (ret != 0) + goto out; + + /* Never wait if forced. */ + if (!forced && module_refcount(mod) != 0) + wait_for_zero_refcount(mod); + + /* Final destruction now noone is using it. */ + if (mod->exit != NULL) { + up(&module_mutex); + mod->exit(); + down(&module_mutex); + } + free_module(mod); + + out: + up(&module_mutex); + return ret; +} + +static void print_unload_info(struct seq_file *m, struct module *mod) +{ + struct module_use *use; + int printed_something = 0; + + seq_printf(m, " %u ", module_refcount(mod)); + + /* Always include a trailing , so userspace can differentiate + between this and the old multi-field proc format. */ + list_for_each_entry(use, &mod->modules_which_use_me, list) { + printed_something = 1; + seq_printf(m, "%s,", use->module_which_uses->name); + } + + if (mod->unsafe) { + printed_something = 1; + seq_printf(m, "[unsafe],"); + } + + if (mod->init != NULL && mod->exit == NULL) { + printed_something = 1; + seq_printf(m, "[permanent],"); + } + + if (!printed_something) + seq_printf(m, "-"); +} + +void __symbol_put(const char *symbol) +{ + struct module *owner; + unsigned long flags; + const unsigned long *crc; + + spin_lock_irqsave(&modlist_lock, flags); + if (!__find_symbol(symbol, &owner, &crc, 1)) + BUG(); + module_put(owner); + spin_unlock_irqrestore(&modlist_lock, flags); +} +EXPORT_SYMBOL(__symbol_put); + +void symbol_put_addr(void *addr) +{ + unsigned long flags; + + spin_lock_irqsave(&modlist_lock, flags); + if (!kernel_text_address((unsigned long)addr)) + BUG(); + + module_put(module_text_address((unsigned long)addr)); + spin_unlock_irqrestore(&modlist_lock, flags); +} +EXPORT_SYMBOL_GPL(symbol_put_addr); + +static ssize_t show_refcnt(struct module_attribute *mattr, + struct module *mod, char *buffer) +{ + /* sysfs holds a reference */ + return sprintf(buffer, "%u\n", module_refcount(mod)-1); +} + +static struct module_attribute refcnt = { + .attr = { .name = "refcnt", .mode = 0444, .owner = THIS_MODULE }, + .show = show_refcnt, +}; + +#else /* !CONFIG_MODULE_UNLOAD */ +static void print_unload_info(struct seq_file *m, struct module *mod) +{ + /* We don't know the usage count, or what modules are using. */ + seq_printf(m, " - -"); +} + +static inline void module_unload_free(struct module *mod) +{ +} + +static inline int use_module(struct module *a, struct module *b) +{ + return strong_try_module_get(b); +} + +static inline void module_unload_init(struct module *mod) +{ +} +#endif /* CONFIG_MODULE_UNLOAD */ + +#ifdef CONFIG_OBSOLETE_MODPARM +/* Bounds checking done below */ +static int obsparm_copy_string(const char *val, struct kernel_param *kp) +{ + strcpy(kp->arg, val); + return 0; +} + +int set_obsolete(const char *val, struct kernel_param *kp) +{ + unsigned int min, max; + unsigned int size, maxsize; + int dummy; + char *endp; + const char *p; + struct obsolete_modparm *obsparm = kp->arg; + + if (!val) { + printk(KERN_ERR "Parameter %s needs an argument\n", kp->name); + return -EINVAL; + } + + /* type is: [min[-max]]{b,h,i,l,s} */ + p = obsparm->type; + min = simple_strtol(p, &endp, 10); + if (endp == obsparm->type) + min = max = 1; + else if (*endp == '-') { + p = endp+1; + max = simple_strtol(p, &endp, 10); + } else + max = min; + switch (*endp) { + case 'b': + return param_array(kp->name, val, min, max, obsparm->addr, + 1, param_set_byte, &dummy); + case 'h': + return param_array(kp->name, val, min, max, obsparm->addr, + sizeof(short), param_set_short, &dummy); + case 'i': + return param_array(kp->name, val, min, max, obsparm->addr, + sizeof(int), param_set_int, &dummy); + case 'l': + return param_array(kp->name, val, min, max, obsparm->addr, + sizeof(long), param_set_long, &dummy); + case 's': + return param_array(kp->name, val, min, max, obsparm->addr, + sizeof(char *), param_set_charp, &dummy); + + case 'c': + /* Undocumented: 1-5c50 means 1-5 strings of up to 49 chars, + and the decl is "char xxx[5][50];" */ + p = endp+1; + maxsize = simple_strtol(p, &endp, 10); + /* We check lengths here (yes, this is a hack). */ + p = val; + while (p[size = strcspn(p, ",")]) { + if (size >= maxsize) + goto oversize; + p += size+1; + } + if (size >= maxsize) + goto oversize; + return param_array(kp->name, val, min, max, obsparm->addr, + maxsize, obsparm_copy_string, &dummy); + } + printk(KERN_ERR "Unknown obsolete parameter type %s\n", obsparm->type); + return -EINVAL; + oversize: + printk(KERN_ERR + "Parameter %s doesn't fit in %u chars.\n", kp->name, maxsize); + return -EINVAL; +} + +static int obsolete_params(const char *name, + char *args, + struct obsolete_modparm obsparm[], + unsigned int num, + Elf_Shdr *sechdrs, + unsigned int symindex, + const char *strtab) +{ + struct kernel_param *kp; + unsigned int i; + int ret; + + kp = kmalloc(sizeof(kp[0]) * num, GFP_KERNEL); + if (!kp) + return -ENOMEM; + + for (i = 0; i < num; i++) { + char sym_name[128 + sizeof(MODULE_SYMBOL_PREFIX)]; + + snprintf(sym_name, sizeof(sym_name), "%s%s", + MODULE_SYMBOL_PREFIX, obsparm[i].name); + + kp[i].name = obsparm[i].name; + kp[i].perm = 000; + kp[i].set = set_obsolete; + kp[i].get = NULL; + obsparm[i].addr + = (void *)find_local_symbol(sechdrs, symindex, strtab, + sym_name); + if (!obsparm[i].addr) { + printk("%s: falsely claims to have parameter %s\n", + name, obsparm[i].name); + ret = -EINVAL; + goto out; + } + kp[i].arg = &obsparm[i]; + } + + ret = parse_args(name, args, kp, num, NULL); + out: + kfree(kp); + return ret; +} +#else +static int obsolete_params(const char *name, + char *args, + struct obsolete_modparm obsparm[], + unsigned int num, + Elf_Shdr *sechdrs, + unsigned int symindex, + const char *strtab) +{ + if (num != 0) + printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", + name); + return 0; +} +#endif /* CONFIG_OBSOLETE_MODPARM */ + +static const char vermagic[] = VERMAGIC_STRING; + +#ifdef CONFIG_MODVERSIONS +static int check_version(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *symname, + struct module *mod, + const unsigned long *crc) +{ + unsigned int i, num_versions; + struct modversion_info *versions; + + /* Exporting module didn't supply crcs? OK, we're already tainted. */ + if (!crc) + return 1; + + versions = (void *) sechdrs[versindex].sh_addr; + num_versions = sechdrs[versindex].sh_size + / sizeof(struct modversion_info); + + for (i = 0; i < num_versions; i++) { + if (strcmp(versions[i].name, symname) != 0) + continue; + + if (versions[i].crc == *crc) + return 1; + printk("%s: disagrees about version of symbol %s\n", + mod->name, symname); + DEBUGP("Found checksum %lX vs module %lX\n", + *crc, versions[i].crc); + return 0; + } + /* Not in module's version table. OK, but that taints the kernel. */ + if (!(tainted & TAINT_FORCED_MODULE)) { + printk("%s: no version for \"%s\" found: kernel tainted.\n", + mod->name, symname); + tainted |= TAINT_FORCED_MODULE; + } + return 1; +} + +static inline int check_modstruct_version(Elf_Shdr *sechdrs, + unsigned int versindex, + struct module *mod) +{ + const unsigned long *crc; + struct module *owner; + + if (!__find_symbol("struct_module", &owner, &crc, 1)) + BUG(); + return check_version(sechdrs, versindex, "struct_module", mod, + crc); +} + +/* First part is kernel version, which we ignore. */ +static inline int same_magic(const char *amagic, const char *bmagic) +{ + amagic += strcspn(amagic, " "); + bmagic += strcspn(bmagic, " "); + return strcmp(amagic, bmagic) == 0; +} +#else +static inline int check_version(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *symname, + struct module *mod, + const unsigned long *crc) +{ + return 1; +} + +static inline int check_modstruct_version(Elf_Shdr *sechdrs, + unsigned int versindex, + struct module *mod) +{ + return 1; +} + +static inline int same_magic(const char *amagic, const char *bmagic) +{ + return strcmp(amagic, bmagic) == 0; +} +#endif /* CONFIG_MODVERSIONS */ + +/* Resolve a symbol for this module. I.e. if we find one, record usage. + Must be holding module_mutex. */ +static unsigned long resolve_symbol(Elf_Shdr *sechdrs, + unsigned int versindex, + const char *name, + struct module *mod) +{ + struct module *owner; + unsigned long ret; + const unsigned long *crc; + + spin_lock_irq(&modlist_lock); + ret = __find_symbol(name, &owner, &crc, mod->license_gplok); + if (ret) { + /* use_module can fail due to OOM, or module unloading */ + if (!check_version(sechdrs, versindex, name, mod, crc) || + !use_module(mod, owner)) + ret = 0; + } + spin_unlock_irq(&modlist_lock); + return ret; +} + + +/* + * /sys/module/foo/sections stuff + * J. Corbet + */ +#ifdef CONFIG_KALLSYMS +static ssize_t module_sect_show(struct module_attribute *mattr, + struct module *mod, char *buf) +{ + struct module_sect_attr *sattr = + container_of(mattr, struct module_sect_attr, mattr); + return sprintf(buf, "0x%lx\n", sattr->address); +} + +static void add_sect_attrs(struct module *mod, unsigned int nsect, + char *secstrings, Elf_Shdr *sechdrs) +{ + unsigned int nloaded = 0, i, size[2]; + struct module_sect_attrs *sect_attrs; + struct module_sect_attr *sattr; + struct attribute **gattr; + + /* Count loaded sections and allocate structures */ + for (i = 0; i < nsect; i++) + if (sechdrs[i].sh_flags & SHF_ALLOC) + nloaded++; + size[0] = ALIGN(sizeof(*sect_attrs) + + nloaded * sizeof(sect_attrs->attrs[0]), + sizeof(sect_attrs->grp.attrs[0])); + size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]); + if (! (sect_attrs = kmalloc(size[0] + size[1], GFP_KERNEL))) + return; + + /* Setup section attributes. */ + sect_attrs->grp.name = "sections"; + sect_attrs->grp.attrs = (void *)sect_attrs + size[0]; + + sattr = §_attrs->attrs[0]; + gattr = §_attrs->grp.attrs[0]; + for (i = 0; i < nsect; i++) { + if (! (sechdrs[i].sh_flags & SHF_ALLOC)) + continue; + sattr->address = sechdrs[i].sh_addr; + strlcpy(sattr->name, secstrings + sechdrs[i].sh_name, + MODULE_SECT_NAME_LEN); + sattr->mattr.show = module_sect_show; + sattr->mattr.store = NULL; + sattr->mattr.attr.name = sattr->name; + sattr->mattr.attr.owner = mod; + sattr->mattr.attr.mode = S_IRUGO; + *(gattr++) = &(sattr++)->mattr.attr; + } + *gattr = NULL; + + if (sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp)) + goto out; + + mod->sect_attrs = sect_attrs; + return; + out: + kfree(sect_attrs); +} + +static void remove_sect_attrs(struct module *mod) +{ + if (mod->sect_attrs) { + sysfs_remove_group(&mod->mkobj.kobj, + &mod->sect_attrs->grp); + /* We are positive that no one is using any sect attrs + * at this point. Deallocate immediately. */ + kfree(mod->sect_attrs); + mod->sect_attrs = NULL; + } +} + + +#else +static inline void add_sect_attrs(struct module *mod, unsigned int nsect, + char *sectstrings, Elf_Shdr *sechdrs) +{ +} + +static inline void remove_sect_attrs(struct module *mod) +{ +} +#endif /* CONFIG_KALLSYMS */ + + +#ifdef CONFIG_MODULE_UNLOAD +static inline int module_add_refcnt_attr(struct module *mod) +{ + return sysfs_create_file(&mod->mkobj.kobj, &refcnt.attr); +} +static void module_remove_refcnt_attr(struct module *mod) +{ + return sysfs_remove_file(&mod->mkobj.kobj, &refcnt.attr); +} +#else +static inline int module_add_refcnt_attr(struct module *mod) +{ + return 0; +} +static void module_remove_refcnt_attr(struct module *mod) +{ +} +#endif + + +static int mod_sysfs_setup(struct module *mod, + struct kernel_param *kparam, + unsigned int num_params) +{ + int err; + + memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); + err = kobject_set_name(&mod->mkobj.kobj, "%s", mod->name); + if (err) + goto out; + kobj_set_kset_s(&mod->mkobj, module_subsys); + mod->mkobj.mod = mod; + err = kobject_register(&mod->mkobj.kobj); + if (err) + goto out; + + err = module_add_refcnt_attr(mod); + if (err) + goto out_unreg; + + err = module_param_sysfs_setup(mod, kparam, num_params); + if (err) + goto out_unreg; + + return 0; + +out_unreg: + kobject_unregister(&mod->mkobj.kobj); +out: + return err; +} + +static void mod_kobject_remove(struct module *mod) +{ + module_remove_refcnt_attr(mod); + module_param_sysfs_remove(mod); + + kobject_unregister(&mod->mkobj.kobj); +} + +/* + * unlink the module with the whole machine is stopped with interrupts off + * - this defends against kallsyms not taking locks + */ +static int __unlink_module(void *_mod) +{ + struct module *mod = _mod; + list_del(&mod->list); + return 0; +} + +/* Free a module, remove from lists, etc (must hold module mutex). */ +static void free_module(struct module *mod) +{ + /* Delete from various lists */ + stop_machine_run(__unlink_module, mod, NR_CPUS); + remove_sect_attrs(mod); + mod_kobject_remove(mod); + + /* Arch-specific cleanup. */ + module_arch_cleanup(mod); + + /* Module unload stuff */ + module_unload_free(mod); + + /* This may be NULL, but that's OK */ + module_free(mod, mod->module_init); + kfree(mod->args); + if (mod->percpu) + percpu_modfree(mod->percpu); + + /* Finally, free the core (containing the module structure) */ + module_free(mod, mod->module_core); +} + +void *__symbol_get(const char *symbol) +{ + struct module *owner; + unsigned long value, flags; + const unsigned long *crc; + + spin_lock_irqsave(&modlist_lock, flags); + value = __find_symbol(symbol, &owner, &crc, 1); + if (value && !strong_try_module_get(owner)) + value = 0; + spin_unlock_irqrestore(&modlist_lock, flags); + + return (void *)value; +} +EXPORT_SYMBOL_GPL(__symbol_get); + +/* Change all symbols so that sh_value encodes the pointer directly. */ +static int simplify_symbols(Elf_Shdr *sechdrs, + unsigned int symindex, + const char *strtab, + unsigned int versindex, + unsigned int pcpuindex, + struct module *mod) +{ + Elf_Sym *sym = (void *)sechdrs[symindex].sh_addr; + unsigned long secbase; + unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym); + int ret = 0; + + for (i = 1; i < n; i++) { + switch (sym[i].st_shndx) { + case SHN_COMMON: + /* We compiled with -fno-common. These are not + supposed to happen. */ + DEBUGP("Common symbol: %s\n", strtab + sym[i].st_name); + printk("%s: please compile with -fno-common\n", + mod->name); + ret = -ENOEXEC; + break; + + case SHN_ABS: + /* Don't need to do anything */ + DEBUGP("Absolute symbol: 0x%08lx\n", + (long)sym[i].st_value); + break; + + case SHN_UNDEF: + sym[i].st_value + = resolve_symbol(sechdrs, versindex, + strtab + sym[i].st_name, mod); + + /* Ok if resolved. */ + if (sym[i].st_value != 0) + break; + /* Ok if weak. */ + if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK) + break; + + printk(KERN_WARNING "%s: Unknown symbol %s\n", + mod->name, strtab + sym[i].st_name); + ret = -ENOENT; + break; + + default: + /* Divert to percpu allocation if a percpu var. */ + if (sym[i].st_shndx == pcpuindex) + secbase = (unsigned long)mod->percpu; + else + secbase = sechdrs[sym[i].st_shndx].sh_addr; + sym[i].st_value += secbase; + break; + } + } + + return ret; +} + +/* Update size with this section: return offset. */ +static long get_offset(unsigned long *size, Elf_Shdr *sechdr) +{ + long ret; + + ret = ALIGN(*size, sechdr->sh_addralign ?: 1); + *size = ret + sechdr->sh_size; + return ret; +} + +/* Lay out the SHF_ALLOC sections in a way not dissimilar to how ld + might -- code, read-only data, read-write data, small data. Tally + sizes, and place the offsets into sh_entsize fields: high bit means it + belongs in init. */ +static void layout_sections(struct module *mod, + const Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings) +{ + static unsigned long const masks[][2] = { + /* NOTE: all executable code must be the first section + * in this array; otherwise modify the text_size + * finder in the two loops below */ + { SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL }, + { SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL }, + { SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL }, + { ARCH_SHF_SMALL | SHF_ALLOC, 0 } + }; + unsigned int m, i; + + for (i = 0; i < hdr->e_shnum; i++) + sechdrs[i].sh_entsize = ~0UL; + + DEBUGP("Core section allocation order:\n"); + for (m = 0; m < ARRAY_SIZE(masks); ++m) { + for (i = 0; i < hdr->e_shnum; ++i) { + Elf_Shdr *s = &sechdrs[i]; + + if ((s->sh_flags & masks[m][0]) != masks[m][0] + || (s->sh_flags & masks[m][1]) + || s->sh_entsize != ~0UL + || strncmp(secstrings + s->sh_name, + ".init", 5) == 0) + continue; + s->sh_entsize = get_offset(&mod->core_size, s); + DEBUGP("\t%s\n", secstrings + s->sh_name); + } + if (m == 0) + mod->core_text_size = mod->core_size; + } + + DEBUGP("Init section allocation order:\n"); + for (m = 0; m < ARRAY_SIZE(masks); ++m) { + for (i = 0; i < hdr->e_shnum; ++i) { + Elf_Shdr *s = &sechdrs[i]; + + if ((s->sh_flags & masks[m][0]) != masks[m][0] + || (s->sh_flags & masks[m][1]) + || s->sh_entsize != ~0UL + || strncmp(secstrings + s->sh_name, + ".init", 5) != 0) + continue; + s->sh_entsize = (get_offset(&mod->init_size, s) + | INIT_OFFSET_MASK); + DEBUGP("\t%s\n", secstrings + s->sh_name); + } + if (m == 0) + mod->init_text_size = mod->init_size; + } +} + +static inline int license_is_gpl_compatible(const char *license) +{ + return (strcmp(license, "GPL") == 0 + || strcmp(license, "GPL v2") == 0 + || strcmp(license, "GPL and additional rights") == 0 + || strcmp(license, "Dual BSD/GPL") == 0 + || strcmp(license, "Dual MPL/GPL") == 0); +} + +static void set_license(struct module *mod, const char *license) +{ + if (!license) + license = "unspecified"; + + mod->license_gplok = license_is_gpl_compatible(license); + if (!mod->license_gplok && !(tainted & TAINT_PROPRIETARY_MODULE)) { + printk(KERN_WARNING "%s: module license '%s' taints kernel.\n", + mod->name, license); + tainted |= TAINT_PROPRIETARY_MODULE; + } +} + +/* Parse tag=value strings from .modinfo section */ +static char *next_string(char *string, unsigned long *secsize) +{ + /* Skip non-zero chars */ + while (string[0]) { + string++; + if ((*secsize)-- <= 1) + return NULL; + } + + /* Skip any zero padding. */ + while (!string[0]) { + string++; + if ((*secsize)-- <= 1) + return NULL; + } + return string; +} + +static char *get_modinfo(Elf_Shdr *sechdrs, + unsigned int info, + const char *tag) +{ + char *p; + unsigned int taglen = strlen(tag); + unsigned long size = sechdrs[info].sh_size; + + for (p = (char *)sechdrs[info].sh_addr; p; p = next_string(p, &size)) { + if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') + return p + taglen + 1; + } + return NULL; +} + +#ifdef CONFIG_KALLSYMS +int is_exported(const char *name, const struct module *mod) +{ + unsigned int i; + + if (!mod) { + for (i = 0; __start___ksymtab+i < __stop___ksymtab; i++) + if (strcmp(__start___ksymtab[i].name, name) == 0) + return 1; + return 0; + } + for (i = 0; i < mod->num_syms; i++) + if (strcmp(mod->syms[i].name, name) == 0) + return 1; + return 0; +} + +/* As per nm */ +static char elf_type(const Elf_Sym *sym, + Elf_Shdr *sechdrs, + const char *secstrings, + struct module *mod) +{ + if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { + if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) + return 'v'; + else + return 'w'; + } + if (sym->st_shndx == SHN_UNDEF) + return 'U'; + if (sym->st_shndx == SHN_ABS) + return 'a'; + if (sym->st_shndx >= SHN_LORESERVE) + return '?'; + if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR) + return 't'; + if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC + && sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) { + if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE)) + return 'r'; + else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) + return 'g'; + else + return 'd'; + } + if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { + if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) + return 's'; + else + return 'b'; + } + if (strncmp(secstrings + sechdrs[sym->st_shndx].sh_name, + ".debug", strlen(".debug")) == 0) + return 'n'; + return '?'; +} + +static void add_kallsyms(struct module *mod, + Elf_Shdr *sechdrs, + unsigned int symindex, + unsigned int strindex, + const char *secstrings) +{ + unsigned int i; + + mod->symtab = (void *)sechdrs[symindex].sh_addr; + mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym); + mod->strtab = (void *)sechdrs[strindex].sh_addr; + + /* Set types up while we still have access to sections. */ + for (i = 0; i < mod->num_symtab; i++) + mod->symtab[i].st_info + = elf_type(&mod->symtab[i], sechdrs, secstrings, mod); +} +#else +static inline void add_kallsyms(struct module *mod, + Elf_Shdr *sechdrs, + unsigned int symindex, + unsigned int strindex, + const char *secstrings) +{ +} +#endif /* CONFIG_KALLSYMS */ + +/* Allocate and load the module: note that size of section 0 is always + zero, and we rely on this for optional sections. */ +static struct module *load_module(void __user *umod, + unsigned long len, + const char __user *uargs) +{ + Elf_Ehdr *hdr; + Elf_Shdr *sechdrs; + char *secstrings, *args, *modmagic, *strtab = NULL; + unsigned int i, symindex = 0, strindex = 0, setupindex, exindex, + exportindex, modindex, obsparmindex, infoindex, gplindex, + crcindex, gplcrcindex, versindex, pcpuindex; + long arglen; + struct module *mod; + long err = 0; + void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ + struct exception_table_entry *extable; + + DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", + umod, len, uargs); + if (len < sizeof(*hdr)) + return ERR_PTR(-ENOEXEC); + + /* Suck in entire file: we'll want most of it. */ + /* vmalloc barfs on "unusual" numbers. Check here */ + if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) + return ERR_PTR(-ENOMEM); + if (copy_from_user(hdr, umod, len) != 0) { + err = -EFAULT; + goto free_hdr; + } + + /* Sanity checks against insmoding binaries or wrong arch, + weird elf version */ + if (memcmp(hdr->e_ident, ELFMAG, 4) != 0 + || hdr->e_type != ET_REL + || !elf_check_arch(hdr) + || hdr->e_shentsize != sizeof(*sechdrs)) { + err = -ENOEXEC; + goto free_hdr; + } + + if (len < hdr->e_shoff + hdr->e_shnum * sizeof(Elf_Shdr)) + goto truncated; + + /* Convenience variables */ + sechdrs = (void *)hdr + hdr->e_shoff; + secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + sechdrs[0].sh_addr = 0; + + for (i = 1; i < hdr->e_shnum; i++) { + if (sechdrs[i].sh_type != SHT_NOBITS + && len < sechdrs[i].sh_offset + sechdrs[i].sh_size) + goto truncated; + + /* Mark all sections sh_addr with their address in the + temporary image. */ + sechdrs[i].sh_addr = (size_t)hdr + sechdrs[i].sh_offset; + + /* Internal symbols and strings. */ + if (sechdrs[i].sh_type == SHT_SYMTAB) { + symindex = i; + strindex = sechdrs[i].sh_link; + strtab = (char *)hdr + sechdrs[strindex].sh_offset; + } +#ifndef CONFIG_MODULE_UNLOAD + /* Don't load .exit sections */ + if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0) + sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; +#endif + } + + modindex = find_sec(hdr, sechdrs, secstrings, + ".gnu.linkonce.this_module"); + if (!modindex) { + printk(KERN_WARNING "No module found in object\n"); + err = -ENOEXEC; + goto free_hdr; + } + mod = (void *)sechdrs[modindex].sh_addr; + + if (symindex == 0) { + printk(KERN_WARNING "%s: module has no symbols (stripped?)\n", + mod->name); + err = -ENOEXEC; + goto free_hdr; + } + + /* Optional sections */ + exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); + gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); + crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); + gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); + setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); + exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); + obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); + versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); + infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); + pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); + + /* Don't keep modinfo section */ + sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; +#ifdef CONFIG_KALLSYMS + /* Keep symbol and string tables for decoding later. */ + sechdrs[symindex].sh_flags |= SHF_ALLOC; + sechdrs[strindex].sh_flags |= SHF_ALLOC; +#endif + + /* Check module struct version now, before we try to use module. */ + if (!check_modstruct_version(sechdrs, versindex, mod)) { + err = -ENOEXEC; + goto free_hdr; + } + + modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); + /* This is allowed: modprobe --force will invalidate it. */ + if (!modmagic) { + tainted |= TAINT_FORCED_MODULE; + printk(KERN_WARNING "%s: no version magic, tainting kernel.\n", + mod->name); + } else if (!same_magic(modmagic, vermagic)) { + printk(KERN_ERR "%s: version magic '%s' should be '%s'\n", + mod->name, modmagic, vermagic); + err = -ENOEXEC; + goto free_hdr; + } + + /* Now copy in args */ + arglen = strlen_user(uargs); + if (!arglen) { + err = -EFAULT; + goto free_hdr; + } + args = kmalloc(arglen, GFP_KERNEL); + if (!args) { + err = -ENOMEM; + goto free_hdr; + } + if (copy_from_user(args, uargs, arglen) != 0) { + err = -EFAULT; + goto free_mod; + } + + if (find_module(mod->name)) { + err = -EEXIST; + goto free_mod; + } + + mod->state = MODULE_STATE_COMING; + + /* Allow arches to frob section contents and sizes. */ + err = module_frob_arch_sections(hdr, sechdrs, secstrings, mod); + if (err < 0) + goto free_mod; + + if (pcpuindex) { + /* We have a special allocation for this section. */ + percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size, + sechdrs[pcpuindex].sh_addralign); + if (!percpu) { + err = -ENOMEM; + goto free_mod; + } + sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; + mod->percpu = percpu; + } + + /* Determine total sizes, and put offsets in sh_entsize. For now + this is done generically; there doesn't appear to be any + special cases for the architectures. */ + layout_sections(mod, hdr, sechdrs, secstrings); + + /* Do the allocs. */ + ptr = module_alloc(mod->core_size); + if (!ptr) { + err = -ENOMEM; + goto free_percpu; + } + memset(ptr, 0, mod->core_size); + mod->module_core = ptr; + + ptr = module_alloc(mod->init_size); + if (!ptr && mod->init_size) { + err = -ENOMEM; + goto free_core; + } + memset(ptr, 0, mod->init_size); + mod->module_init = ptr; + + /* Transfer each section which specifies SHF_ALLOC */ + DEBUGP("final section addresses:\n"); + for (i = 0; i < hdr->e_shnum; i++) { + void *dest; + + if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + continue; + + if (sechdrs[i].sh_entsize & INIT_OFFSET_MASK) + dest = mod->module_init + + (sechdrs[i].sh_entsize & ~INIT_OFFSET_MASK); + else + dest = mod->module_core + sechdrs[i].sh_entsize; + + if (sechdrs[i].sh_type != SHT_NOBITS) + memcpy(dest, (void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size); + /* Update sh_addr to point to copy in image. */ + sechdrs[i].sh_addr = (unsigned long)dest; + DEBUGP("\t0x%lx %s\n", sechdrs[i].sh_addr, secstrings + sechdrs[i].sh_name); + } + /* Module has been moved. */ + mod = (void *)sechdrs[modindex].sh_addr; + + /* Now we've moved module, initialize linked lists, etc. */ + module_unload_init(mod); + + /* Set up license info based on the info section */ + set_license(mod, get_modinfo(sechdrs, infoindex, "license")); + + /* Fix up syms, so that st_value is a pointer to location. */ + err = simplify_symbols(sechdrs, symindex, strtab, versindex, pcpuindex, + mod); + if (err < 0) + goto cleanup; + + /* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */ + mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms); + mod->syms = (void *)sechdrs[exportindex].sh_addr; + if (crcindex) + mod->crcs = (void *)sechdrs[crcindex].sh_addr; + mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms); + mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr; + if (gplcrcindex) + mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; + +#ifdef CONFIG_MODVERSIONS + if ((mod->num_syms && !crcindex) || + (mod->num_gpl_syms && !gplcrcindex)) { + printk(KERN_WARNING "%s: No versions for exported symbols." + " Tainting kernel.\n", mod->name); + tainted |= TAINT_FORCED_MODULE; + } +#endif + + /* Now do relocations. */ + for (i = 1; i < hdr->e_shnum; i++) { + const char *strtab = (char *)sechdrs[strindex].sh_addr; + unsigned int info = sechdrs[i].sh_info; + + /* Not a valid relocation section? */ + if (info >= hdr->e_shnum) + continue; + + /* Don't bother with non-allocated sections */ + if (!(sechdrs[info].sh_flags & SHF_ALLOC)) + continue; + + if (sechdrs[i].sh_type == SHT_REL) + err = apply_relocate(sechdrs, strtab, symindex, i,mod); + else if (sechdrs[i].sh_type == SHT_RELA) + err = apply_relocate_add(sechdrs, strtab, symindex, i, + mod); + if (err < 0) + goto cleanup; + } + + /* Set up and sort exception table */ + mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable); + mod->extable = extable = (void *)sechdrs[exindex].sh_addr; + sort_extable(extable, extable + mod->num_exentries); + + /* Finally, copy percpu area over. */ + percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, + sechdrs[pcpuindex].sh_size); + + add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); + + err = module_finalize(hdr, sechdrs, mod); + if (err < 0) + goto cleanup; + + mod->args = args; + if (obsparmindex) { + err = obsolete_params(mod->name, mod->args, + (struct obsolete_modparm *) + sechdrs[obsparmindex].sh_addr, + sechdrs[obsparmindex].sh_size + / sizeof(struct obsolete_modparm), + sechdrs, symindex, + (char *)sechdrs[strindex].sh_addr); + if (setupindex) + printk(KERN_WARNING "%s: Ignoring new-style " + "parameters in presence of obsolete ones\n", + mod->name); + } else { + /* Size of section 0 is 0, so this works well if no params */ + err = parse_args(mod->name, mod->args, + (struct kernel_param *) + sechdrs[setupindex].sh_addr, + sechdrs[setupindex].sh_size + / sizeof(struct kernel_param), + NULL); + } + if (err < 0) + goto arch_cleanup; + + err = mod_sysfs_setup(mod, + (struct kernel_param *) + sechdrs[setupindex].sh_addr, + sechdrs[setupindex].sh_size + / sizeof(struct kernel_param)); + if (err < 0) + goto arch_cleanup; + add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); + + /* Get rid of temporary copy */ + vfree(hdr); + + /* Done! */ + return mod; + + arch_cleanup: + module_arch_cleanup(mod); + cleanup: + module_unload_free(mod); + module_free(mod, mod->module_init); + free_core: + module_free(mod, mod->module_core); + free_percpu: + if (percpu) + percpu_modfree(percpu); + free_mod: + kfree(args); + free_hdr: + vfree(hdr); + if (err < 0) return ERR_PTR(err); + else return ptr; + + truncated: + printk(KERN_ERR "Module len %lu truncated\n", len); + err = -ENOEXEC; + goto free_hdr; +} + +/* + * link the module with the whole machine is stopped with interrupts off + * - this defends against kallsyms not taking locks + */ +static int __link_module(void *_mod) +{ + struct module *mod = _mod; + list_add(&mod->list, &modules); + return 0; +} + +/* This is where the real work happens */ +asmlinkage long +sys_init_module(void __user *umod, + unsigned long len, + const char __user *uargs) +{ + struct module *mod; + int ret = 0; + + /* Must have permission */ + if (!capable(CAP_SYS_MODULE)) + return -EPERM; + + /* Only one module load at a time, please */ + if (down_interruptible(&module_mutex) != 0) + return -EINTR; + + /* Do all the hard work */ + mod = load_module(umod, len, uargs); + if (IS_ERR(mod)) { + up(&module_mutex); + return PTR_ERR(mod); + } + + /* Flush the instruction cache, since we've played with text */ + if (mod->module_init) + flush_icache_range((unsigned long)mod->module_init, + (unsigned long)mod->module_init + + mod->init_size); + flush_icache_range((unsigned long)mod->module_core, + (unsigned long)mod->module_core + mod->core_size); + + /* Now sew it into the lists. They won't access us, since + strong_try_module_get() will fail. */ + stop_machine_run(__link_module, mod, NR_CPUS); + + /* Drop lock so they can recurse */ + up(&module_mutex); + + down(¬ify_mutex); + notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); + up(¬ify_mutex); + + /* Start the module */ + if (mod->init != NULL) + ret = mod->init(); + if (ret < 0) { + /* Init routine failed: abort. Try to protect us from + buggy refcounters. */ + mod->state = MODULE_STATE_GOING; + synchronize_kernel(); + if (mod->unsafe) + printk(KERN_ERR "%s: module is now stuck!\n", + mod->name); + else { + module_put(mod); + down(&module_mutex); + free_module(mod); + up(&module_mutex); + } + return ret; + } + + /* Now it's a first class citizen! */ + down(&module_mutex); + mod->state = MODULE_STATE_LIVE; + /* Drop initial reference. */ + module_put(mod); + module_free(mod, mod->module_init); + mod->module_init = NULL; + mod->init_size = 0; + mod->init_text_size = 0; + up(&module_mutex); + + return 0; +} + +static inline int within(unsigned long addr, void *start, unsigned long size) +{ + return ((void *)addr >= start && (void *)addr < start + size); +} + +#ifdef CONFIG_KALLSYMS +/* + * This ignores the intensely annoying "mapping symbols" found + * in ARM ELF files: $a, $t and $d. + */ +static inline int is_arm_mapping_symbol(const char *str) +{ + return str[0] == '$' && strchr("atd", str[1]) + && (str[2] == '\0' || str[2] == '.'); +} + +static const char *get_ksymbol(struct module *mod, + unsigned long addr, + unsigned long *size, + unsigned long *offset) +{ + unsigned int i, best = 0; + unsigned long nextval; + + /* At worse, next value is at end of module */ + if (within(addr, mod->module_init, mod->init_size)) + nextval = (unsigned long)mod->module_init+mod->init_text_size; + else + nextval = (unsigned long)mod->module_core+mod->core_text_size; + + /* Scan for closest preceeding symbol, and next symbol. (ELF + starts real symbols at 1). */ + for (i = 1; i < mod->num_symtab; i++) { + if (mod->symtab[i].st_shndx == SHN_UNDEF) + continue; + + /* We ignore unnamed symbols: they're uninformative + * and inserted at a whim. */ + if (mod->symtab[i].st_value <= addr + && mod->symtab[i].st_value > mod->symtab[best].st_value + && *(mod->strtab + mod->symtab[i].st_name) != '\0' + && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + best = i; + if (mod->symtab[i].st_value > addr + && mod->symtab[i].st_value < nextval + && *(mod->strtab + mod->symtab[i].st_name) != '\0' + && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + nextval = mod->symtab[i].st_value; + } + + if (!best) + return NULL; + + *size = nextval - mod->symtab[best].st_value; + *offset = addr - mod->symtab[best].st_value; + return mod->strtab + mod->symtab[best].st_name; +} + +/* For kallsyms to ask for address resolution. NULL means not found. + We don't lock, as this is used for oops resolution and races are a + lesser concern. */ +const char *module_address_lookup(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char **modname) +{ + struct module *mod; + + list_for_each_entry(mod, &modules, list) { + if (within(addr, mod->module_init, mod->init_size) + || within(addr, mod->module_core, mod->core_size)) { + *modname = mod->name; + return get_ksymbol(mod, addr, size, offset); + } + } + return NULL; +} + +struct module *module_get_kallsym(unsigned int symnum, + unsigned long *value, + char *type, + char namebuf[128]) +{ + struct module *mod; + + down(&module_mutex); + list_for_each_entry(mod, &modules, list) { + if (symnum < mod->num_symtab) { + *value = mod->symtab[symnum].st_value; + *type = mod->symtab[symnum].st_info; + strncpy(namebuf, + mod->strtab + mod->symtab[symnum].st_name, + 127); + up(&module_mutex); + return mod; + } + symnum -= mod->num_symtab; + } + up(&module_mutex); + return NULL; +} + +static unsigned long mod_find_symname(struct module *mod, const char *name) +{ + unsigned int i; + + for (i = 0; i < mod->num_symtab; i++) + if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0) + return mod->symtab[i].st_value; + return 0; +} + +/* Look for this name: can be of form module:name. */ +unsigned long module_kallsyms_lookup_name(const char *name) +{ + struct module *mod; + char *colon; + unsigned long ret = 0; + + /* Don't lock: we're in enough trouble already. */ + if ((colon = strchr(name, ':')) != NULL) { + *colon = '\0'; + if ((mod = find_module(name)) != NULL) + ret = mod_find_symname(mod, colon+1); + *colon = ':'; + } else { + list_for_each_entry(mod, &modules, list) + if ((ret = mod_find_symname(mod, name)) != 0) + break; + } + return ret; +} +#endif /* CONFIG_KALLSYMS */ + +/* Called by the /proc file system to return a list of modules. */ +static void *m_start(struct seq_file *m, loff_t *pos) +{ + struct list_head *i; + loff_t n = 0; + + down(&module_mutex); + list_for_each(i, &modules) { + if (n++ == *pos) + break; + } + if (i == &modules) + return NULL; + return i; +} + +static void *m_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct list_head *i = p; + (*pos)++; + if (i->next == &modules) + return NULL; + return i->next; +} + +static void m_stop(struct seq_file *m, void *p) +{ + up(&module_mutex); +} + +static int m_show(struct seq_file *m, void *p) +{ + struct module *mod = list_entry(p, struct module, list); + seq_printf(m, "%s %lu", + mod->name, mod->init_size + mod->core_size); + print_unload_info(m, mod); + + /* Informative for users. */ + seq_printf(m, " %s", + mod->state == MODULE_STATE_GOING ? "Unloading": + mod->state == MODULE_STATE_COMING ? "Loading": + "Live"); + /* Used by oprofile and other similar tools. */ + seq_printf(m, " 0x%p", mod->module_core); + + seq_printf(m, "\n"); + return 0; +} + +/* Format: modulename size refcount deps address + + Where refcount is a number or -, and deps is a comma-separated list + of depends or -. +*/ +struct seq_operations modules_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = m_show +}; + +/* Given an address, look for it in the module exception tables. */ +const struct exception_table_entry *search_module_extables(unsigned long addr) +{ + unsigned long flags; + const struct exception_table_entry *e = NULL; + struct module *mod; + + spin_lock_irqsave(&modlist_lock, flags); + list_for_each_entry(mod, &modules, list) { + if (mod->num_exentries == 0) + continue; + + e = search_extable(mod->extable, + mod->extable + mod->num_exentries - 1, + addr); + if (e) + break; + } + spin_unlock_irqrestore(&modlist_lock, flags); + + /* Now, if we found one, we are running inside it now, hence + we cannot unload the module, hence no refcnt needed. */ + return e; +} + +/* Is this a valid kernel address? We don't grab the lock: we are oopsing. */ +struct module *__module_text_address(unsigned long addr) +{ + struct module *mod; + + list_for_each_entry(mod, &modules, list) + if (within(addr, mod->module_init, mod->init_text_size) + || within(addr, mod->module_core, mod->core_text_size)) + return mod; + return NULL; +} + +struct module *module_text_address(unsigned long addr) +{ + struct module *mod; + unsigned long flags; + + spin_lock_irqsave(&modlist_lock, flags); + mod = __module_text_address(addr); + spin_unlock_irqrestore(&modlist_lock, flags); + + return mod; +} + +/* Don't grab lock, we're oopsing. */ +void print_modules(void) +{ + struct module *mod; + + printk("Modules linked in:"); + list_for_each_entry(mod, &modules, list) + printk(" %s", mod->name); + printk("\n"); +} + +void module_add_driver(struct module *mod, struct device_driver *drv) +{ + if (!mod || !drv) + return; + + /* Don't check return code; this call is idempotent */ + sysfs_create_link(&drv->kobj, &mod->mkobj.kobj, "module"); +} +EXPORT_SYMBOL(module_add_driver); + +void module_remove_driver(struct device_driver *drv) +{ + if (!drv) + return; + sysfs_remove_link(&drv->kobj, "module"); +} +EXPORT_SYMBOL(module_remove_driver); + +#ifdef CONFIG_MODVERSIONS +/* Generate the signature for struct module here, too, for modversions. */ +void struct_module(struct module *mod) { return; } +EXPORT_SYMBOL(struct_module); +#endif diff --git a/kernel/panic.c b/kernel/panic.c new file mode 100644 index 000000000000..0fa3f3a66fb6 --- /dev/null +++ b/kernel/panic.c @@ -0,0 +1,157 @@ +/* + * linux/kernel/panic.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * This function is used through-out the kernel (including mm and fs) + * to indicate a major problem. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int panic_timeout; +int panic_on_oops; +int tainted; + +EXPORT_SYMBOL(panic_timeout); + +struct notifier_block *panic_notifier_list; + +EXPORT_SYMBOL(panic_notifier_list); + +static int __init panic_setup(char *str) +{ + panic_timeout = simple_strtoul(str, NULL, 0); + return 1; +} +__setup("panic=", panic_setup); + +static long no_blink(long time) +{ + return 0; +} + +/* Returns how long it waited in ms */ +long (*panic_blink)(long time); +EXPORT_SYMBOL(panic_blink); + +/** + * panic - halt the system + * @fmt: The text string to print + * + * Display a message, then perform cleanups. + * + * This function never returns. + */ + +NORET_TYPE void panic(const char * fmt, ...) +{ + long i; + static char buf[1024]; + va_list args; +#if defined(CONFIG_ARCH_S390) + unsigned long caller = (unsigned long) __builtin_return_address(0); +#endif + + bust_spinlocks(1); + va_start(args, fmt); + vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf); + bust_spinlocks(0); + +#ifdef CONFIG_SMP + smp_send_stop(); +#endif + + notifier_call_chain(&panic_notifier_list, 0, buf); + + if (!panic_blink) + panic_blink = no_blink; + + if (panic_timeout > 0) + { + /* + * Delay timeout seconds before rebooting the machine. + * We can't use the "normal" timers since we just panicked.. + */ + printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout); + for (i = 0; i < panic_timeout*1000; ) { + touch_nmi_watchdog(); + i += panic_blink(i); + mdelay(1); + i++; + } + /* + * Should we run the reboot notifier. For the moment Im + * choosing not too. It might crash, be corrupt or do + * more harm than good for other reasons. + */ + machine_restart(NULL); + } +#ifdef __sparc__ + { + extern int stop_a_enabled; + /* Make sure the user can actually press L1-A */ + stop_a_enabled = 1; + printk(KERN_EMERG "Press L1-A to return to the boot prom\n"); + } +#endif +#if defined(CONFIG_ARCH_S390) + disabled_wait(caller); +#endif + local_irq_enable(); + for (i = 0;;) { + i += panic_blink(i); + mdelay(1); + i++; + } +} + +EXPORT_SYMBOL(panic); + +/** + * print_tainted - return a string to represent the kernel taint state. + * + * 'P' - Proprietary module has been loaded. + * 'F' - Module has been forcibly loaded. + * 'S' - SMP with CPUs not designed for SMP. + * 'R' - User forced a module unload. + * 'M' - Machine had a machine check experience. + * 'B' - System has hit bad_page. + * + * The string is overwritten by the next call to print_taint(). + */ + +const char *print_tainted(void) +{ + static char buf[20]; + if (tainted) { + snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c", + tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G', + tainted & TAINT_FORCED_MODULE ? 'F' : ' ', + tainted & TAINT_UNSAFE_SMP ? 'S' : ' ', + tainted & TAINT_FORCED_RMMOD ? 'R' : ' ', + tainted & TAINT_MACHINE_CHECK ? 'M' : ' ', + tainted & TAINT_BAD_PAGE ? 'B' : ' '); + } + else + snprintf(buf, sizeof(buf), "Not tainted"); + return(buf); +} + +void add_taint(unsigned flag) +{ + tainted |= flag; +} +EXPORT_SYMBOL(add_taint); diff --git a/kernel/params.c b/kernel/params.c new file mode 100644 index 000000000000..5538608bd339 --- /dev/null +++ b/kernel/params.c @@ -0,0 +1,721 @@ +/* Helpers for initial module or kernel cmdline parsing + Copyright (C) 2001 Rusty Russell. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ +#include +#include +#include +#include +#include +#include +#include +#include + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt, a...) +#endif + +static inline int dash2underscore(char c) +{ + if (c == '-') + return '_'; + return c; +} + +static inline int parameq(const char *input, const char *paramname) +{ + unsigned int i; + for (i = 0; dash2underscore(input[i]) == paramname[i]; i++) + if (input[i] == '\0') + return 1; + return 0; +} + +static int parse_one(char *param, + char *val, + struct kernel_param *params, + unsigned num_params, + int (*handle_unknown)(char *param, char *val)) +{ + unsigned int i; + + /* Find parameter */ + for (i = 0; i < num_params; i++) { + if (parameq(param, params[i].name)) { + DEBUGP("They are equal! Calling %p\n", + params[i].set); + return params[i].set(val, ¶ms[i]); + } + } + + if (handle_unknown) { + DEBUGP("Unknown argument: calling %p\n", handle_unknown); + return handle_unknown(param, val); + } + + DEBUGP("Unknown argument `%s'\n", param); + return -ENOENT; +} + +/* You can use " around spaces, but can't escape ". */ +/* Hyphens and underscores equivalent in parameter names. */ +static char *next_arg(char *args, char **param, char **val) +{ + unsigned int i, equals = 0; + int in_quote = 0, quoted = 0; + char *next; + + /* Chew any extra spaces */ + while (*args == ' ') args++; + if (*args == '"') { + args++; + in_quote = 1; + quoted = 1; + } + + for (i = 0; args[i]; i++) { + if (args[i] == ' ' && !in_quote) + break; + if (equals == 0) { + if (args[i] == '=') + equals = i; + } + if (args[i] == '"') + in_quote = !in_quote; + } + + *param = args; + if (!equals) + *val = NULL; + else { + args[equals] = '\0'; + *val = args + equals + 1; + + /* Don't include quotes in value. */ + if (**val == '"') { + (*val)++; + if (args[i-1] == '"') + args[i-1] = '\0'; + } + if (quoted && args[i-1] == '"') + args[i-1] = '\0'; + } + + if (args[i]) { + args[i] = '\0'; + next = args + i + 1; + } else + next = args + i; + return next; +} + +/* Args looks like "foo=bar,bar2 baz=fuz wiz". */ +int parse_args(const char *name, + char *args, + struct kernel_param *params, + unsigned num, + int (*unknown)(char *param, char *val)) +{ + char *param, *val; + + DEBUGP("Parsing ARGS: %s\n", args); + + while (*args) { + int ret; + + args = next_arg(args, ¶m, &val); + ret = parse_one(param, val, params, num, unknown); + switch (ret) { + case -ENOENT: + printk(KERN_ERR "%s: Unknown parameter `%s'\n", + name, param); + return ret; + case -ENOSPC: + printk(KERN_ERR + "%s: `%s' too large for parameter `%s'\n", + name, val ?: "", param); + return ret; + case 0: + break; + default: + printk(KERN_ERR + "%s: `%s' invalid for parameter `%s'\n", + name, val ?: "", param); + return ret; + } + } + + /* All parsed OK. */ + return 0; +} + +/* Lazy bastard, eh? */ +#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn) \ + int param_set_##name(const char *val, struct kernel_param *kp) \ + { \ + char *endp; \ + tmptype l; \ + \ + if (!val) return -EINVAL; \ + l = strtolfn(val, &endp, 0); \ + if (endp == val || ((type)l != l)) \ + return -EINVAL; \ + *((type *)kp->arg) = l; \ + return 0; \ + } \ + int param_get_##name(char *buffer, struct kernel_param *kp) \ + { \ + return sprintf(buffer, format, *((type *)kp->arg)); \ + } + +STANDARD_PARAM_DEF(byte, unsigned char, "%c", unsigned long, simple_strtoul); +STANDARD_PARAM_DEF(short, short, "%hi", long, simple_strtol); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, simple_strtoul); +STANDARD_PARAM_DEF(int, int, "%i", long, simple_strtol); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, simple_strtoul); +STANDARD_PARAM_DEF(long, long, "%li", long, simple_strtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, simple_strtoul); + +int param_set_charp(const char *val, struct kernel_param *kp) +{ + if (!val) { + printk(KERN_ERR "%s: string parameter expected\n", + kp->name); + return -EINVAL; + } + + if (strlen(val) > 1024) { + printk(KERN_ERR "%s: string parameter too long\n", + kp->name); + return -ENOSPC; + } + + *(char **)kp->arg = (char *)val; + return 0; +} + +int param_get_charp(char *buffer, struct kernel_param *kp) +{ + return sprintf(buffer, "%s", *((char **)kp->arg)); +} + +int param_set_bool(const char *val, struct kernel_param *kp) +{ + /* No equals means "set"... */ + if (!val) val = "1"; + + /* One of =[yYnN01] */ + switch (val[0]) { + case 'y': case 'Y': case '1': + *(int *)kp->arg = 1; + return 0; + case 'n': case 'N': case '0': + *(int *)kp->arg = 0; + return 0; + } + return -EINVAL; +} + +int param_get_bool(char *buffer, struct kernel_param *kp) +{ + /* Y and N chosen as being relatively non-coder friendly */ + return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'Y' : 'N'); +} + +int param_set_invbool(const char *val, struct kernel_param *kp) +{ + int boolval, ret; + struct kernel_param dummy = { .arg = &boolval }; + + ret = param_set_bool(val, &dummy); + if (ret == 0) + *(int *)kp->arg = !boolval; + return ret; +} + +int param_get_invbool(char *buffer, struct kernel_param *kp) +{ + int val; + struct kernel_param dummy = { .arg = &val }; + + val = !*(int *)kp->arg; + return param_get_bool(buffer, &dummy); +} + +/* We cheat here and temporarily mangle the string. */ +int param_array(const char *name, + const char *val, + unsigned int min, unsigned int max, + void *elem, int elemsize, + int (*set)(const char *, struct kernel_param *kp), + int *num) +{ + int ret; + struct kernel_param kp; + char save; + + /* Get the name right for errors. */ + kp.name = name; + kp.arg = elem; + + /* No equals sign? */ + if (!val) { + printk(KERN_ERR "%s: expects arguments\n", name); + return -EINVAL; + } + + *num = 0; + /* We expect a comma-separated list of values. */ + do { + int len; + + if (*num == max) { + printk(KERN_ERR "%s: can only take %i arguments\n", + name, max); + return -EINVAL; + } + len = strcspn(val, ","); + + /* nul-terminate and parse */ + save = val[len]; + ((char *)val)[len] = '\0'; + ret = set(val, &kp); + + if (ret != 0) + return ret; + kp.arg += elemsize; + val += len+1; + (*num)++; + } while (save == ','); + + if (*num < min) { + printk(KERN_ERR "%s: needs at least %i arguments\n", + name, min); + return -EINVAL; + } + return 0; +} + +int param_array_set(const char *val, struct kernel_param *kp) +{ + struct kparam_array *arr = kp->arg; + + return param_array(kp->name, val, 1, arr->max, arr->elem, + arr->elemsize, arr->set, arr->num ?: &arr->max); +} + +int param_array_get(char *buffer, struct kernel_param *kp) +{ + int i, off, ret; + struct kparam_array *arr = kp->arg; + struct kernel_param p; + + p = *kp; + for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + if (i) + buffer[off++] = ','; + p.arg = arr->elem + arr->elemsize * i; + ret = arr->get(buffer + off, &p); + if (ret < 0) + return ret; + off += ret; + } + buffer[off] = '\0'; + return off; +} + +int param_set_copystring(const char *val, struct kernel_param *kp) +{ + struct kparam_string *kps = kp->arg; + + if (strlen(val)+1 > kps->maxlen) { + printk(KERN_ERR "%s: string doesn't fit in %u chars.\n", + kp->name, kps->maxlen-1); + return -ENOSPC; + } + strcpy(kps->string, val); + return 0; +} + +int param_get_string(char *buffer, struct kernel_param *kp) +{ + struct kparam_string *kps = kp->arg; + return strlcpy(buffer, kps->string, kps->maxlen); +} + +/* sysfs output in /sys/modules/XYZ/parameters/ */ + +extern struct kernel_param __start___param[], __stop___param[]; + +#define MAX_KBUILD_MODNAME KOBJ_NAME_LEN + +struct param_attribute +{ + struct module_attribute mattr; + struct kernel_param *param; +}; + +struct module_param_attrs +{ + struct attribute_group grp; + struct param_attribute attrs[0]; +}; + +#define to_param_attr(n) container_of(n, struct param_attribute, mattr); + +static ssize_t param_attr_show(struct module_attribute *mattr, + struct module *mod, char *buf) +{ + int count; + struct param_attribute *attribute = to_param_attr(mattr); + + if (!attribute->param->get) + return -EPERM; + + count = attribute->param->get(buf, attribute->param); + if (count > 0) { + strcat(buf, "\n"); + ++count; + } + return count; +} + +/* sysfs always hands a nul-terminated string in buf. We rely on that. */ +static ssize_t param_attr_store(struct module_attribute *mattr, + struct module *owner, + const char *buf, size_t len) +{ + int err; + struct param_attribute *attribute = to_param_attr(mattr); + + if (!attribute->param->set) + return -EPERM; + + err = attribute->param->set(buf, attribute->param); + if (!err) + return len; + return err; +} + +#ifdef CONFIG_MODULES +#define __modinit +#else +#define __modinit __init +#endif + +/* + * param_sysfs_setup - setup sysfs support for one module or KBUILD_MODNAME + * @mk: struct module_kobject (contains parent kobject) + * @kparam: array of struct kernel_param, the actual parameter definitions + * @num_params: number of entries in array + * @name_skip: offset where the parameter name start in kparam[].name. Needed for built-in "modules" + * + * Create a kobject for a (per-module) group of parameters, and create files + * in sysfs. A pointer to the param_kobject is returned on success, + * NULL if there's no parameter to export, or other ERR_PTR(err). + */ +static __modinit struct module_param_attrs * +param_sysfs_setup(struct module_kobject *mk, + struct kernel_param *kparam, + unsigned int num_params, + unsigned int name_skip) +{ + struct module_param_attrs *mp; + unsigned int valid_attrs = 0; + unsigned int i, size[2]; + struct param_attribute *pattr; + struct attribute **gattr; + int err; + + for (i=0; iattrs[0]), + sizeof(mp->grp.attrs[0])); + size[1] = (valid_attrs + 1) * sizeof(mp->grp.attrs[0]); + + mp = kmalloc(size[0] + size[1], GFP_KERNEL); + if (!mp) + return ERR_PTR(-ENOMEM); + + mp->grp.name = "parameters"; + mp->grp.attrs = (void *)mp + size[0]; + + pattr = &mp->attrs[0]; + gattr = &mp->grp.attrs[0]; + for (i = 0; i < num_params; i++) { + struct kernel_param *kp = &kparam[i]; + if (kp->perm) { + pattr->param = kp; + pattr->mattr.show = param_attr_show; + pattr->mattr.store = param_attr_store; + pattr->mattr.attr.name = (char *)&kp->name[name_skip]; + pattr->mattr.attr.owner = mk->mod; + pattr->mattr.attr.mode = kp->perm; + *(gattr++) = &(pattr++)->mattr.attr; + } + } + *gattr = NULL; + + if ((err = sysfs_create_group(&mk->kobj, &mp->grp))) { + kfree(mp); + return ERR_PTR(err); + } + return mp; +} + + +#ifdef CONFIG_MODULES + +/* + * module_param_sysfs_setup - setup sysfs support for one module + * @mod: module + * @kparam: module parameters (array) + * @num_params: number of module parameters + * + * Adds sysfs entries for module parameters, and creates a link from + * /sys/module/[mod->name]/parameters to /sys/parameters/[mod->name]/ + */ +int module_param_sysfs_setup(struct module *mod, + struct kernel_param *kparam, + unsigned int num_params) +{ + struct module_param_attrs *mp; + + mp = param_sysfs_setup(&mod->mkobj, kparam, num_params, 0); + if (IS_ERR(mp)) + return PTR_ERR(mp); + + mod->param_attrs = mp; + return 0; +} + +/* + * module_param_sysfs_remove - remove sysfs support for one module + * @mod: module + * + * Remove sysfs entries for module parameters and the corresponding + * kobject. + */ +void module_param_sysfs_remove(struct module *mod) +{ + if (mod->param_attrs) { + sysfs_remove_group(&mod->mkobj.kobj, + &mod->param_attrs->grp); + /* We are positive that no one is using any param + * attrs at this point. Deallocate immediately. */ + kfree(mod->param_attrs); + mod->param_attrs = NULL; + } +} +#endif + +/* + * kernel_param_sysfs_setup - wrapper for built-in params support + */ +static void __init kernel_param_sysfs_setup(const char *name, + struct kernel_param *kparam, + unsigned int num_params, + unsigned int name_skip) +{ + struct module_kobject *mk; + + mk = kmalloc(sizeof(struct module_kobject), GFP_KERNEL); + memset(mk, 0, sizeof(struct module_kobject)); + + mk->mod = THIS_MODULE; + kobj_set_kset_s(mk, module_subsys); + kobject_set_name(&mk->kobj, name); + kobject_register(&mk->kobj); + + /* no need to keep the kobject if no parameter is exported */ + if (!param_sysfs_setup(mk, kparam, num_params, name_skip)) { + kobject_unregister(&mk->kobj); + kfree(mk); + } +} + +/* + * param_sysfs_builtin - add contents in /sys/parameters for built-in modules + * + * Add module_parameters to sysfs for "modules" built into the kernel. + * + * The "module" name (KBUILD_MODNAME) is stored before a dot, the + * "parameter" name is stored behind a dot in kernel_param->name. So, + * extract the "module" name for all built-in kernel_param-eters, + * and for all who have the same, call kernel_param_sysfs_setup. + */ +static void __init param_sysfs_builtin(void) +{ + struct kernel_param *kp, *kp_begin = NULL; + unsigned int i, name_len, count = 0; + char modname[MAX_KBUILD_MODNAME + 1] = ""; + + for (i=0; i < __stop___param - __start___param; i++) { + char *dot; + + kp = &__start___param[i]; + + /* We do not handle args without periods. */ + dot = memchr(kp->name, '.', MAX_KBUILD_MODNAME); + if (!dot) { + DEBUGP("couldn't find period in %s\n", kp->name); + continue; + } + name_len = dot - kp->name; + + /* new kbuild_modname? */ + if (strlen(modname) != name_len + || strncmp(modname, kp->name, name_len) != 0) { + /* add a new kobject for previous kernel_params. */ + if (count) + kernel_param_sysfs_setup(modname, + kp_begin, + count, + strlen(modname)+1); + + strncpy(modname, kp->name, name_len); + modname[name_len] = '\0'; + count = 0; + kp_begin = kp; + } + count++; + } + + /* last kernel_params need to be registered as well */ + if (count) + kernel_param_sysfs_setup(modname, kp_begin, count, + strlen(modname)+1); +} + + +/* module-related sysfs stuff */ +#ifdef CONFIG_MODULES + +#define to_module_attr(n) container_of(n, struct module_attribute, attr); +#define to_module_kobject(n) container_of(n, struct module_kobject, kobj); + +static ssize_t module_attr_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct module_attribute *attribute; + struct module_kobject *mk; + int ret; + + attribute = to_module_attr(attr); + mk = to_module_kobject(kobj); + + if (!attribute->show) + return -EPERM; + + if (!try_module_get(mk->mod)) + return -ENODEV; + + ret = attribute->show(attribute, mk->mod, buf); + + module_put(mk->mod); + + return ret; +} + +static ssize_t module_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct module_attribute *attribute; + struct module_kobject *mk; + int ret; + + attribute = to_module_attr(attr); + mk = to_module_kobject(kobj); + + if (!attribute->store) + return -EPERM; + + if (!try_module_get(mk->mod)) + return -ENODEV; + + ret = attribute->store(attribute, mk->mod, buf, len); + + module_put(mk->mod); + + return ret; +} + +static struct sysfs_ops module_sysfs_ops = { + .show = module_attr_show, + .store = module_attr_store, +}; + +#else +static struct sysfs_ops module_sysfs_ops = { + .show = NULL, + .store = NULL, +}; +#endif + +static struct kobj_type module_ktype = { + .sysfs_ops = &module_sysfs_ops, +}; + +decl_subsys(module, &module_ktype, NULL); + +/* + * param_sysfs_init - wrapper for built-in params support + */ +static int __init param_sysfs_init(void) +{ + subsystem_register(&module_subsys); + + param_sysfs_builtin(); + + return 0; +} +__initcall(param_sysfs_init); + +EXPORT_SYMBOL(param_set_byte); +EXPORT_SYMBOL(param_get_byte); +EXPORT_SYMBOL(param_set_short); +EXPORT_SYMBOL(param_get_short); +EXPORT_SYMBOL(param_set_ushort); +EXPORT_SYMBOL(param_get_ushort); +EXPORT_SYMBOL(param_set_int); +EXPORT_SYMBOL(param_get_int); +EXPORT_SYMBOL(param_set_uint); +EXPORT_SYMBOL(param_get_uint); +EXPORT_SYMBOL(param_set_long); +EXPORT_SYMBOL(param_get_long); +EXPORT_SYMBOL(param_set_ulong); +EXPORT_SYMBOL(param_get_ulong); +EXPORT_SYMBOL(param_set_charp); +EXPORT_SYMBOL(param_get_charp); +EXPORT_SYMBOL(param_set_bool); +EXPORT_SYMBOL(param_get_bool); +EXPORT_SYMBOL(param_set_invbool); +EXPORT_SYMBOL(param_get_invbool); +EXPORT_SYMBOL(param_array_set); +EXPORT_SYMBOL(param_array_get); +EXPORT_SYMBOL(param_set_copystring); +EXPORT_SYMBOL(param_get_string); diff --git a/kernel/pid.c b/kernel/pid.c new file mode 100644 index 000000000000..edba31c681ac --- /dev/null +++ b/kernel/pid.c @@ -0,0 +1,292 @@ +/* + * Generic pidhash and scalable, time-bounded PID allocator + * + * (C) 2002-2003 William Irwin, IBM + * (C) 2004 William Irwin, Oracle + * (C) 2002-2004 Ingo Molnar, Red Hat + * + * pid-structures are backing objects for tasks sharing a given ID to chain + * against. There is very little to them aside from hashing them and + * parking tasks using given ID's on a list. + * + * The hash is always changed with the tasklist_lock write-acquired, + * and the hash is only accessed with the tasklist_lock at least + * read-acquired, so there's no additional SMP locking needed here. + * + * We have a list of bitmap pages, which bitmaps represent the PID space. + * Allocating and freeing PIDs is completely lockless. The worst-case + * allocation scenario when all but one out of 1 million PIDs possible are + * allocated already: the scanning of 32 list entries and at most PAGE_SIZE + * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). + */ + +#include +#include +#include +#include +#include +#include + +#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift) +static struct hlist_head *pid_hash[PIDTYPE_MAX]; +static int pidhash_shift; + +int pid_max = PID_MAX_DEFAULT; +int last_pid; + +#define RESERVED_PIDS 300 + +int pid_max_min = RESERVED_PIDS + 1; +int pid_max_max = PID_MAX_LIMIT; + +#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) +#define BITS_PER_PAGE (PAGE_SIZE*8) +#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) +#define mk_pid(map, off) (((map) - pidmap_array)*BITS_PER_PAGE + (off)) +#define find_next_offset(map, off) \ + find_next_zero_bit((map)->page, BITS_PER_PAGE, off) + +/* + * PID-map pages start out as NULL, they get allocated upon + * first use and are never deallocated. This way a low pid_max + * value does not cause lots of bitmaps to be allocated, but + * the scheme scales to up to 4 million PIDs, runtime. + */ +typedef struct pidmap { + atomic_t nr_free; + void *page; +} pidmap_t; + +static pidmap_t pidmap_array[PIDMAP_ENTRIES] = + { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } }; + +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); + +fastcall void free_pidmap(int pid) +{ + pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE; + int offset = pid & BITS_PER_PAGE_MASK; + + clear_bit(offset, map->page); + atomic_inc(&map->nr_free); +} + +int alloc_pidmap(void) +{ + int i, offset, max_scan, pid, last = last_pid; + pidmap_t *map; + + pid = last + 1; + if (pid >= pid_max) + pid = RESERVED_PIDS; + offset = pid & BITS_PER_PAGE_MASK; + map = &pidmap_array[pid/BITS_PER_PAGE]; + max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset; + for (i = 0; i <= max_scan; ++i) { + if (unlikely(!map->page)) { + unsigned long page = get_zeroed_page(GFP_KERNEL); + /* + * Free the page if someone raced with us + * installing it: + */ + spin_lock(&pidmap_lock); + if (map->page) + free_page(page); + else + map->page = (void *)page; + spin_unlock(&pidmap_lock); + if (unlikely(!map->page)) + break; + } + if (likely(atomic_read(&map->nr_free))) { + do { + if (!test_and_set_bit(offset, map->page)) { + atomic_dec(&map->nr_free); + last_pid = pid; + return pid; + } + offset = find_next_offset(map, offset); + pid = mk_pid(map, offset); + /* + * find_next_offset() found a bit, the pid from it + * is in-bounds, and if we fell back to the last + * bitmap block and the final block was the same + * as the starting point, pid is before last_pid. + */ + } while (offset < BITS_PER_PAGE && pid < pid_max && + (i != max_scan || pid < last || + !((last+1) & BITS_PER_PAGE_MASK))); + } + if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) { + ++map; + offset = 0; + } else { + map = &pidmap_array[0]; + offset = RESERVED_PIDS; + if (unlikely(last == offset)) + break; + } + pid = mk_pid(map, offset); + } + return -1; +} + +struct pid * fastcall find_pid(enum pid_type type, int nr) +{ + struct hlist_node *elem; + struct pid *pid; + + hlist_for_each_entry(pid, elem, + &pid_hash[type][pid_hashfn(nr)], pid_chain) { + if (pid->nr == nr) + return pid; + } + return NULL; +} + +int fastcall attach_pid(task_t *task, enum pid_type type, int nr) +{ + struct pid *pid, *task_pid; + + task_pid = &task->pids[type]; + pid = find_pid(type, nr); + if (pid == NULL) { + hlist_add_head(&task_pid->pid_chain, + &pid_hash[type][pid_hashfn(nr)]); + INIT_LIST_HEAD(&task_pid->pid_list); + } else { + INIT_HLIST_NODE(&task_pid->pid_chain); + list_add_tail(&task_pid->pid_list, &pid->pid_list); + } + task_pid->nr = nr; + + return 0; +} + +static fastcall int __detach_pid(task_t *task, enum pid_type type) +{ + struct pid *pid, *pid_next; + int nr = 0; + + pid = &task->pids[type]; + if (!hlist_unhashed(&pid->pid_chain)) { + hlist_del(&pid->pid_chain); + + if (list_empty(&pid->pid_list)) + nr = pid->nr; + else { + pid_next = list_entry(pid->pid_list.next, + struct pid, pid_list); + /* insert next pid from pid_list to hash */ + hlist_add_head(&pid_next->pid_chain, + &pid_hash[type][pid_hashfn(pid_next->nr)]); + } + } + + list_del(&pid->pid_list); + pid->nr = 0; + + return nr; +} + +void fastcall detach_pid(task_t *task, enum pid_type type) +{ + int tmp, nr; + + nr = __detach_pid(task, type); + if (!nr) + return; + + for (tmp = PIDTYPE_MAX; --tmp >= 0; ) + if (tmp != type && find_pid(tmp, nr)) + return; + + free_pidmap(nr); +} + +task_t *find_task_by_pid_type(int type, int nr) +{ + struct pid *pid; + + pid = find_pid(type, nr); + if (!pid) + return NULL; + + return pid_task(&pid->pid_list, type); +} + +EXPORT_SYMBOL(find_task_by_pid_type); + +/* + * This function switches the PIDs if a non-leader thread calls + * sys_execve() - this must be done without releasing the PID. + * (which a detach_pid() would eventually do.) + */ +void switch_exec_pids(task_t *leader, task_t *thread) +{ + __detach_pid(leader, PIDTYPE_PID); + __detach_pid(leader, PIDTYPE_TGID); + __detach_pid(leader, PIDTYPE_PGID); + __detach_pid(leader, PIDTYPE_SID); + + __detach_pid(thread, PIDTYPE_PID); + __detach_pid(thread, PIDTYPE_TGID); + + leader->pid = leader->tgid = thread->pid; + thread->pid = thread->tgid; + + attach_pid(thread, PIDTYPE_PID, thread->pid); + attach_pid(thread, PIDTYPE_TGID, thread->tgid); + attach_pid(thread, PIDTYPE_PGID, thread->signal->pgrp); + attach_pid(thread, PIDTYPE_SID, thread->signal->session); + list_add_tail(&thread->tasks, &init_task.tasks); + + attach_pid(leader, PIDTYPE_PID, leader->pid); + attach_pid(leader, PIDTYPE_TGID, leader->tgid); + attach_pid(leader, PIDTYPE_PGID, leader->signal->pgrp); + attach_pid(leader, PIDTYPE_SID, leader->signal->session); +} + +/* + * The pid hash table is scaled according to the amount of memory in the + * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or + * more. + */ +void __init pidhash_init(void) +{ + int i, j, pidhash_size; + unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT); + + pidhash_shift = max(4, fls(megabytes * 4)); + pidhash_shift = min(12, pidhash_shift); + pidhash_size = 1 << pidhash_shift; + + printk("PID hash table entries: %d (order: %d, %Zd bytes)\n", + pidhash_size, pidhash_shift, + PIDTYPE_MAX * pidhash_size * sizeof(struct hlist_head)); + + for (i = 0; i < PIDTYPE_MAX; i++) { + pid_hash[i] = alloc_bootmem(pidhash_size * + sizeof(*(pid_hash[i]))); + if (!pid_hash[i]) + panic("Could not alloc pidhash!\n"); + for (j = 0; j < pidhash_size; j++) + INIT_HLIST_HEAD(&pid_hash[i][j]); + } +} + +void __init pidmap_init(void) +{ + int i; + + pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL); + set_bit(0, pidmap_array->page); + atomic_dec(&pidmap_array->nr_free); + + /* + * Allocate PID 0, and hash it via all PID types: + */ + + for (i = 0; i < PIDTYPE_MAX; i++) + attach_pid(current, i, 0); +} diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c new file mode 100644 index 000000000000..ad85d3f0dcc4 --- /dev/null +++ b/kernel/posix-cpu-timers.c @@ -0,0 +1,1559 @@ +/* + * Implement CPU time clocks for the POSIX clock interface. + */ + +#include +#include +#include +#include + +static int check_clock(clockid_t which_clock) +{ + int error = 0; + struct task_struct *p; + const pid_t pid = CPUCLOCK_PID(which_clock); + + if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX) + return -EINVAL; + + if (pid == 0) + return 0; + + read_lock(&tasklist_lock); + p = find_task_by_pid(pid); + if (!p || (CPUCLOCK_PERTHREAD(which_clock) ? + p->tgid != current->tgid : p->tgid != pid)) { + error = -EINVAL; + } + read_unlock(&tasklist_lock); + + return error; +} + +static inline union cpu_time_count +timespec_to_sample(clockid_t which_clock, const struct timespec *tp) +{ + union cpu_time_count ret; + ret.sched = 0; /* high half always zero when .cpu used */ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + ret.sched = tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; + } else { + ret.cpu = timespec_to_cputime(tp); + } + return ret; +} + +static void sample_to_timespec(clockid_t which_clock, + union cpu_time_count cpu, + struct timespec *tp) +{ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + tp->tv_sec = div_long_long_rem(cpu.sched, + NSEC_PER_SEC, &tp->tv_nsec); + } else { + cputime_to_timespec(cpu.cpu, tp); + } +} + +static inline int cpu_time_before(clockid_t which_clock, + union cpu_time_count now, + union cpu_time_count then) +{ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + return now.sched < then.sched; + } else { + return cputime_lt(now.cpu, then.cpu); + } +} +static inline void cpu_time_add(clockid_t which_clock, + union cpu_time_count *acc, + union cpu_time_count val) +{ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + acc->sched += val.sched; + } else { + acc->cpu = cputime_add(acc->cpu, val.cpu); + } +} +static inline union cpu_time_count cpu_time_sub(clockid_t which_clock, + union cpu_time_count a, + union cpu_time_count b) +{ + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + a.sched -= b.sched; + } else { + a.cpu = cputime_sub(a.cpu, b.cpu); + } + return a; +} + +/* + * Update expiry time from increment, and increase overrun count, + * given the current clock sample. + */ +static inline void bump_cpu_timer(struct k_itimer *timer, + union cpu_time_count now) +{ + int i; + + if (timer->it.cpu.incr.sched == 0) + return; + + if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) { + unsigned long long delta, incr; + + if (now.sched < timer->it.cpu.expires.sched) + return; + incr = timer->it.cpu.incr.sched; + delta = now.sched + incr - timer->it.cpu.expires.sched; + /* Don't use (incr*2 < delta), incr*2 might overflow. */ + for (i = 0; incr < delta - incr; i++) + incr = incr << 1; + for (; i >= 0; incr >>= 1, i--) { + if (delta <= incr) + continue; + timer->it.cpu.expires.sched += incr; + timer->it_overrun += 1 << i; + delta -= incr; + } + } else { + cputime_t delta, incr; + + if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu)) + return; + incr = timer->it.cpu.incr.cpu; + delta = cputime_sub(cputime_add(now.cpu, incr), + timer->it.cpu.expires.cpu); + /* Don't use (incr*2 < delta), incr*2 might overflow. */ + for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++) + incr = cputime_add(incr, incr); + for (; i >= 0; incr = cputime_halve(incr), i--) { + if (cputime_le(delta, incr)) + continue; + timer->it.cpu.expires.cpu = + cputime_add(timer->it.cpu.expires.cpu, incr); + timer->it_overrun += 1 << i; + delta = cputime_sub(delta, incr); + } + } +} + +static inline cputime_t prof_ticks(struct task_struct *p) +{ + return cputime_add(p->utime, p->stime); +} +static inline cputime_t virt_ticks(struct task_struct *p) +{ + return p->utime; +} +static inline unsigned long long sched_ns(struct task_struct *p) +{ + return (p == current) ? current_sched_time(p) : p->sched_time; +} + +int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +{ + int error = check_clock(which_clock); + if (!error) { + tp->tv_sec = 0; + tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ); + if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { + /* + * If sched_clock is using a cycle counter, we + * don't have any idea of its true resolution + * exported, but it is much more than 1s/HZ. + */ + tp->tv_nsec = 1; + } + } + return error; +} + +int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp) +{ + /* + * You can never reset a CPU clock, but we check for other errors + * in the call before failing with EPERM. + */ + int error = check_clock(which_clock); + if (error == 0) { + error = -EPERM; + } + return error; +} + + +/* + * Sample a per-thread clock for the given task. + */ +static int cpu_clock_sample(clockid_t which_clock, struct task_struct *p, + union cpu_time_count *cpu) +{ + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + cpu->cpu = prof_ticks(p); + break; + case CPUCLOCK_VIRT: + cpu->cpu = virt_ticks(p); + break; + case CPUCLOCK_SCHED: + cpu->sched = sched_ns(p); + break; + } + return 0; +} + +/* + * Sample a process (thread group) clock for the given group_leader task. + * Must be called with tasklist_lock held for reading. + * Must be called with tasklist_lock held for reading, and p->sighand->siglock. + */ +static int cpu_clock_sample_group_locked(unsigned int clock_idx, + struct task_struct *p, + union cpu_time_count *cpu) +{ + struct task_struct *t = p; + switch (clock_idx) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + cpu->cpu = cputime_add(p->signal->utime, p->signal->stime); + do { + cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t)); + t = next_thread(t); + } while (t != p); + break; + case CPUCLOCK_VIRT: + cpu->cpu = p->signal->utime; + do { + cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t)); + t = next_thread(t); + } while (t != p); + break; + case CPUCLOCK_SCHED: + cpu->sched = p->signal->sched_time; + /* Add in each other live thread. */ + while ((t = next_thread(t)) != p) { + cpu->sched += t->sched_time; + } + if (p->tgid == current->tgid) { + /* + * We're sampling ourselves, so include the + * cycles not yet banked. We still omit + * other threads running on other CPUs, + * so the total can always be behind as + * much as max(nthreads-1,ncpus) * (NSEC_PER_SEC/HZ). + */ + cpu->sched += current_sched_time(current); + } else { + cpu->sched += p->sched_time; + } + break; + } + return 0; +} + +/* + * Sample a process (thread group) clock for the given group_leader task. + * Must be called with tasklist_lock held for reading. + */ +static int cpu_clock_sample_group(clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) +{ + int ret; + unsigned long flags; + spin_lock_irqsave(&p->sighand->siglock, flags); + ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p, + cpu); + spin_unlock_irqrestore(&p->sighand->siglock, flags); + return ret; +} + + +int posix_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +{ + const pid_t pid = CPUCLOCK_PID(which_clock); + int error = -EINVAL; + union cpu_time_count rtn; + + if (pid == 0) { + /* + * Special case constant value for our own clocks. + * We don't have to do any lookup to find ourselves. + */ + if (CPUCLOCK_PERTHREAD(which_clock)) { + /* + * Sampling just ourselves we can do with no locking. + */ + error = cpu_clock_sample(which_clock, + current, &rtn); + } else { + read_lock(&tasklist_lock); + error = cpu_clock_sample_group(which_clock, + current, &rtn); + read_unlock(&tasklist_lock); + } + } else { + /* + * Find the given PID, and validate that the caller + * should be able to see it. + */ + struct task_struct *p; + read_lock(&tasklist_lock); + p = find_task_by_pid(pid); + if (p) { + if (CPUCLOCK_PERTHREAD(which_clock)) { + if (p->tgid == current->tgid) { + error = cpu_clock_sample(which_clock, + p, &rtn); + } + } else if (p->tgid == pid && p->signal) { + error = cpu_clock_sample_group(which_clock, + p, &rtn); + } + } + read_unlock(&tasklist_lock); + } + + if (error) + return error; + sample_to_timespec(which_clock, rtn, tp); + return 0; +} + + +/* + * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. + * This is called from sys_timer_create with the new timer already locked. + */ +int posix_cpu_timer_create(struct k_itimer *new_timer) +{ + int ret = 0; + const pid_t pid = CPUCLOCK_PID(new_timer->it_clock); + struct task_struct *p; + + if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX) + return -EINVAL; + + INIT_LIST_HEAD(&new_timer->it.cpu.entry); + new_timer->it.cpu.incr.sched = 0; + new_timer->it.cpu.expires.sched = 0; + + read_lock(&tasklist_lock); + if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) { + if (pid == 0) { + p = current; + } else { + p = find_task_by_pid(pid); + if (p && p->tgid != current->tgid) + p = NULL; + } + } else { + if (pid == 0) { + p = current->group_leader; + } else { + p = find_task_by_pid(pid); + if (p && p->tgid != pid) + p = NULL; + } + } + new_timer->it.cpu.task = p; + if (p) { + get_task_struct(p); + } else { + ret = -EINVAL; + } + read_unlock(&tasklist_lock); + + return ret; +} + +/* + * Clean up a CPU-clock timer that is about to be destroyed. + * This is called from timer deletion with the timer already locked. + * If we return TIMER_RETRY, it's necessary to release the timer's lock + * and try again. (This happens when the timer is in the middle of firing.) + */ +int posix_cpu_timer_del(struct k_itimer *timer) +{ + struct task_struct *p = timer->it.cpu.task; + + if (timer->it.cpu.firing) + return TIMER_RETRY; + + if (unlikely(p == NULL)) + return 0; + + if (!list_empty(&timer->it.cpu.entry)) { + read_lock(&tasklist_lock); + if (unlikely(p->signal == NULL)) { + /* + * We raced with the reaping of the task. + * The deletion should have cleared us off the list. + */ + BUG_ON(!list_empty(&timer->it.cpu.entry)); + } else { + /* + * Take us off the task's timer list. + */ + spin_lock(&p->sighand->siglock); + list_del(&timer->it.cpu.entry); + spin_unlock(&p->sighand->siglock); + } + read_unlock(&tasklist_lock); + } + put_task_struct(p); + + return 0; +} + +/* + * Clean out CPU timers still ticking when a thread exited. The task + * pointer is cleared, and the expiry time is replaced with the residual + * time for later timer_gettime calls to return. + * This must be called with the siglock held. + */ +static void cleanup_timers(struct list_head *head, + cputime_t utime, cputime_t stime, + unsigned long long sched_time) +{ + struct cpu_timer_list *timer, *next; + cputime_t ptime = cputime_add(utime, stime); + + list_for_each_entry_safe(timer, next, head, entry) { + timer->task = NULL; + list_del_init(&timer->entry); + if (cputime_lt(timer->expires.cpu, ptime)) { + timer->expires.cpu = cputime_zero; + } else { + timer->expires.cpu = cputime_sub(timer->expires.cpu, + ptime); + } + } + + ++head; + list_for_each_entry_safe(timer, next, head, entry) { + timer->task = NULL; + list_del_init(&timer->entry); + if (cputime_lt(timer->expires.cpu, utime)) { + timer->expires.cpu = cputime_zero; + } else { + timer->expires.cpu = cputime_sub(timer->expires.cpu, + utime); + } + } + + ++head; + list_for_each_entry_safe(timer, next, head, entry) { + timer->task = NULL; + list_del_init(&timer->entry); + if (timer->expires.sched < sched_time) { + timer->expires.sched = 0; + } else { + timer->expires.sched -= sched_time; + } + } +} + +/* + * These are both called with the siglock held, when the current thread + * is being reaped. When the final (leader) thread in the group is reaped, + * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit. + */ +void posix_cpu_timers_exit(struct task_struct *tsk) +{ + cleanup_timers(tsk->cpu_timers, + tsk->utime, tsk->stime, tsk->sched_time); + +} +void posix_cpu_timers_exit_group(struct task_struct *tsk) +{ + cleanup_timers(tsk->signal->cpu_timers, + cputime_add(tsk->utime, tsk->signal->utime), + cputime_add(tsk->stime, tsk->signal->stime), + tsk->sched_time + tsk->signal->sched_time); +} + + +/* + * Set the expiry times of all the threads in the process so one of them + * will go off before the process cumulative expiry total is reached. + */ +static void process_timer_rebalance(struct task_struct *p, + unsigned int clock_idx, + union cpu_time_count expires, + union cpu_time_count val) +{ + cputime_t ticks, left; + unsigned long long ns, nsleft; + struct task_struct *t = p; + unsigned int nthreads = atomic_read(&p->signal->live); + + switch (clock_idx) { + default: + BUG(); + break; + case CPUCLOCK_PROF: + left = cputime_div(cputime_sub(expires.cpu, val.cpu), + nthreads); + do { + if (!unlikely(t->exit_state)) { + ticks = cputime_add(prof_ticks(t), left); + if (cputime_eq(t->it_prof_expires, + cputime_zero) || + cputime_gt(t->it_prof_expires, ticks)) { + t->it_prof_expires = ticks; + } + } + t = next_thread(t); + } while (t != p); + break; + case CPUCLOCK_VIRT: + left = cputime_div(cputime_sub(expires.cpu, val.cpu), + nthreads); + do { + if (!unlikely(t->exit_state)) { + ticks = cputime_add(virt_ticks(t), left); + if (cputime_eq(t->it_virt_expires, + cputime_zero) || + cputime_gt(t->it_virt_expires, ticks)) { + t->it_virt_expires = ticks; + } + } + t = next_thread(t); + } while (t != p); + break; + case CPUCLOCK_SCHED: + nsleft = expires.sched - val.sched; + do_div(nsleft, nthreads); + do { + if (!unlikely(t->exit_state)) { + ns = t->sched_time + nsleft; + if (t->it_sched_expires == 0 || + t->it_sched_expires > ns) { + t->it_sched_expires = ns; + } + } + t = next_thread(t); + } while (t != p); + break; + } +} + +static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) +{ + /* + * That's all for this thread or process. + * We leave our residual in expires to be reported. + */ + put_task_struct(timer->it.cpu.task); + timer->it.cpu.task = NULL; + timer->it.cpu.expires = cpu_time_sub(timer->it_clock, + timer->it.cpu.expires, + now); +} + +/* + * Insert the timer on the appropriate list before any timers that + * expire later. This must be called with the tasklist_lock held + * for reading, and interrupts disabled. + */ +static void arm_timer(struct k_itimer *timer, union cpu_time_count now) +{ + struct task_struct *p = timer->it.cpu.task; + struct list_head *head, *listpos; + struct cpu_timer_list *const nt = &timer->it.cpu; + struct cpu_timer_list *next; + unsigned long i; + + head = (CPUCLOCK_PERTHREAD(timer->it_clock) ? + p->cpu_timers : p->signal->cpu_timers); + head += CPUCLOCK_WHICH(timer->it_clock); + + BUG_ON(!irqs_disabled()); + spin_lock(&p->sighand->siglock); + + listpos = head; + if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) { + list_for_each_entry(next, head, entry) { + if (next->expires.sched > nt->expires.sched) { + listpos = &next->entry; + break; + } + } + } else { + list_for_each_entry(next, head, entry) { + if (cputime_gt(next->expires.cpu, nt->expires.cpu)) { + listpos = &next->entry; + break; + } + } + } + list_add(&nt->entry, listpos); + + if (listpos == head) { + /* + * We are the new earliest-expiring timer. + * If we are a thread timer, there can always + * be a process timer telling us to stop earlier. + */ + + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + switch (CPUCLOCK_WHICH(timer->it_clock)) { + default: + BUG(); + case CPUCLOCK_PROF: + if (cputime_eq(p->it_prof_expires, + cputime_zero) || + cputime_gt(p->it_prof_expires, + nt->expires.cpu)) + p->it_prof_expires = nt->expires.cpu; + break; + case CPUCLOCK_VIRT: + if (cputime_eq(p->it_virt_expires, + cputime_zero) || + cputime_gt(p->it_virt_expires, + nt->expires.cpu)) + p->it_virt_expires = nt->expires.cpu; + break; + case CPUCLOCK_SCHED: + if (p->it_sched_expires == 0 || + p->it_sched_expires > nt->expires.sched) + p->it_sched_expires = nt->expires.sched; + break; + } + } else { + /* + * For a process timer, we must balance + * all the live threads' expirations. + */ + switch (CPUCLOCK_WHICH(timer->it_clock)) { + default: + BUG(); + case CPUCLOCK_VIRT: + if (!cputime_eq(p->signal->it_virt_expires, + cputime_zero) && + cputime_lt(p->signal->it_virt_expires, + timer->it.cpu.expires.cpu)) + break; + goto rebalance; + case CPUCLOCK_PROF: + if (!cputime_eq(p->signal->it_prof_expires, + cputime_zero) && + cputime_lt(p->signal->it_prof_expires, + timer->it.cpu.expires.cpu)) + break; + i = p->signal->rlim[RLIMIT_CPU].rlim_cur; + if (i != RLIM_INFINITY && + i <= cputime_to_secs(timer->it.cpu.expires.cpu)) + break; + goto rebalance; + case CPUCLOCK_SCHED: + rebalance: + process_timer_rebalance( + timer->it.cpu.task, + CPUCLOCK_WHICH(timer->it_clock), + timer->it.cpu.expires, now); + break; + } + } + } + + spin_unlock(&p->sighand->siglock); +} + +/* + * The timer is locked, fire it and arrange for its reload. + */ +static void cpu_timer_fire(struct k_itimer *timer) +{ + if (unlikely(timer->sigq == NULL)) { + /* + * This a special case for clock_nanosleep, + * not a normal timer from sys_timer_create. + */ + wake_up_process(timer->it_process); + timer->it.cpu.expires.sched = 0; + } else if (timer->it.cpu.incr.sched == 0) { + /* + * One-shot timer. Clear it as soon as it's fired. + */ + posix_timer_event(timer, 0); + timer->it.cpu.expires.sched = 0; + } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { + /* + * The signal did not get queued because the signal + * was ignored, so we won't get any callback to + * reload the timer. But we need to keep it + * ticking in case the signal is deliverable next time. + */ + posix_cpu_timer_schedule(timer); + } +} + +/* + * Guts of sys_timer_settime for CPU timers. + * This is called with the timer locked and interrupts disabled. + * If we return TIMER_RETRY, it's necessary to release the timer's lock + * and try again. (This happens when the timer is in the middle of firing.) + */ +int posix_cpu_timer_set(struct k_itimer *timer, int flags, + struct itimerspec *new, struct itimerspec *old) +{ + struct task_struct *p = timer->it.cpu.task; + union cpu_time_count old_expires, new_expires, val; + int ret; + + if (unlikely(p == NULL)) { + /* + * Timer refers to a dead task's clock. + */ + return -ESRCH; + } + + new_expires = timespec_to_sample(timer->it_clock, &new->it_value); + + read_lock(&tasklist_lock); + /* + * We need the tasklist_lock to protect against reaping that + * clears p->signal. If p has just been reaped, we can no + * longer get any information about it at all. + */ + if (unlikely(p->signal == NULL)) { + read_unlock(&tasklist_lock); + put_task_struct(p); + timer->it.cpu.task = NULL; + return -ESRCH; + } + + /* + * Disarm any old timer after extracting its expiry time. + */ + BUG_ON(!irqs_disabled()); + spin_lock(&p->sighand->siglock); + old_expires = timer->it.cpu.expires; + list_del_init(&timer->it.cpu.entry); + spin_unlock(&p->sighand->siglock); + + /* + * We need to sample the current value to convert the new + * value from to relative and absolute, and to convert the + * old value from absolute to relative. To set a process + * timer, we need a sample to balance the thread expiry + * times (in arm_timer). With an absolute time, we must + * check if it's already passed. In short, we need a sample. + */ + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + cpu_clock_sample(timer->it_clock, p, &val); + } else { + cpu_clock_sample_group(timer->it_clock, p, &val); + } + + if (old) { + if (old_expires.sched == 0) { + old->it_value.tv_sec = 0; + old->it_value.tv_nsec = 0; + } else { + /* + * Update the timer in case it has + * overrun already. If it has, + * we'll report it as having overrun + * and with the next reloaded timer + * already ticking, though we are + * swallowing that pending + * notification here to install the + * new setting. + */ + bump_cpu_timer(timer, val); + if (cpu_time_before(timer->it_clock, val, + timer->it.cpu.expires)) { + old_expires = cpu_time_sub( + timer->it_clock, + timer->it.cpu.expires, val); + sample_to_timespec(timer->it_clock, + old_expires, + &old->it_value); + } else { + old->it_value.tv_nsec = 1; + old->it_value.tv_sec = 0; + } + } + } + + if (unlikely(timer->it.cpu.firing)) { + /* + * We are colliding with the timer actually firing. + * Punt after filling in the timer's old value, and + * disable this firing since we are already reporting + * it as an overrun (thanks to bump_cpu_timer above). + */ + read_unlock(&tasklist_lock); + timer->it.cpu.firing = -1; + ret = TIMER_RETRY; + goto out; + } + + if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) { + cpu_time_add(timer->it_clock, &new_expires, val); + } + + /* + * Install the new expiry time (or zero). + * For a timer with no notification action, we don't actually + * arm the timer (we'll just fake it for timer_gettime). + */ + timer->it.cpu.expires = new_expires; + if (new_expires.sched != 0 && + (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE && + cpu_time_before(timer->it_clock, val, new_expires)) { + arm_timer(timer, val); + } + + read_unlock(&tasklist_lock); + + /* + * Install the new reload setting, and + * set up the signal and overrun bookkeeping. + */ + timer->it.cpu.incr = timespec_to_sample(timer->it_clock, + &new->it_interval); + + /* + * This acts as a modification timestamp for the timer, + * so any automatic reload attempt will punt on seeing + * that we have reset the timer manually. + */ + timer->it_requeue_pending = (timer->it_requeue_pending + 2) & + ~REQUEUE_PENDING; + timer->it_overrun_last = 0; + timer->it_overrun = -1; + + if (new_expires.sched != 0 && + (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE && + !cpu_time_before(timer->it_clock, val, new_expires)) { + /* + * The designated time already passed, so we notify + * immediately, even if the thread never runs to + * accumulate more time on this clock. + */ + cpu_timer_fire(timer); + } + + ret = 0; + out: + if (old) { + sample_to_timespec(timer->it_clock, + timer->it.cpu.incr, &old->it_interval); + } + return ret; +} + +void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) +{ + union cpu_time_count now; + struct task_struct *p = timer->it.cpu.task; + int clear_dead; + + /* + * Easy part: convert the reload time. + */ + sample_to_timespec(timer->it_clock, + timer->it.cpu.incr, &itp->it_interval); + + if (timer->it.cpu.expires.sched == 0) { /* Timer not armed at all. */ + itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; + return; + } + + if (unlikely(p == NULL)) { + /* + * This task already died and the timer will never fire. + * In this case, expires is actually the dead value. + */ + dead: + sample_to_timespec(timer->it_clock, timer->it.cpu.expires, + &itp->it_value); + return; + } + + /* + * Sample the clock to take the difference with the expiry time. + */ + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + cpu_clock_sample(timer->it_clock, p, &now); + clear_dead = p->exit_state; + } else { + read_lock(&tasklist_lock); + if (unlikely(p->signal == NULL)) { + /* + * The process has been reaped. + * We can't even collect a sample any more. + * Call the timer disarmed, nothing else to do. + */ + put_task_struct(p); + timer->it.cpu.task = NULL; + timer->it.cpu.expires.sched = 0; + read_unlock(&tasklist_lock); + goto dead; + } else { + cpu_clock_sample_group(timer->it_clock, p, &now); + clear_dead = (unlikely(p->exit_state) && + thread_group_empty(p)); + } + read_unlock(&tasklist_lock); + } + + if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { + if (timer->it.cpu.incr.sched == 0 && + cpu_time_before(timer->it_clock, + timer->it.cpu.expires, now)) { + /* + * Do-nothing timer expired and has no reload, + * so it's as if it was never set. + */ + timer->it.cpu.expires.sched = 0; + itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; + return; + } + /* + * Account for any expirations and reloads that should + * have happened. + */ + bump_cpu_timer(timer, now); + } + + if (unlikely(clear_dead)) { + /* + * We've noticed that the thread is dead, but + * not yet reaped. Take this opportunity to + * drop our task ref. + */ + clear_dead_task(timer, now); + goto dead; + } + + if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) { + sample_to_timespec(timer->it_clock, + cpu_time_sub(timer->it_clock, + timer->it.cpu.expires, now), + &itp->it_value); + } else { + /* + * The timer should have expired already, but the firing + * hasn't taken place yet. Say it's just about to expire. + */ + itp->it_value.tv_nsec = 1; + itp->it_value.tv_sec = 0; + } +} + +/* + * Check for any per-thread CPU timers that have fired and move them off + * the tsk->cpu_timers[N] list onto the firing list. Here we update the + * tsk->it_*_expires values to reflect the remaining thread CPU timers. + */ +static void check_thread_timers(struct task_struct *tsk, + struct list_head *firing) +{ + struct list_head *timers = tsk->cpu_timers; + + tsk->it_prof_expires = cputime_zero; + while (!list_empty(timers)) { + struct cpu_timer_list *t = list_entry(timers->next, + struct cpu_timer_list, + entry); + if (cputime_lt(prof_ticks(tsk), t->expires.cpu)) { + tsk->it_prof_expires = t->expires.cpu; + break; + } + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + ++timers; + tsk->it_virt_expires = cputime_zero; + while (!list_empty(timers)) { + struct cpu_timer_list *t = list_entry(timers->next, + struct cpu_timer_list, + entry); + if (cputime_lt(virt_ticks(tsk), t->expires.cpu)) { + tsk->it_virt_expires = t->expires.cpu; + break; + } + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + ++timers; + tsk->it_sched_expires = 0; + while (!list_empty(timers)) { + struct cpu_timer_list *t = list_entry(timers->next, + struct cpu_timer_list, + entry); + if (tsk->sched_time < t->expires.sched) { + tsk->it_sched_expires = t->expires.sched; + break; + } + t->firing = 1; + list_move_tail(&t->entry, firing); + } +} + +/* + * Check for any per-thread CPU timers that have fired and move them + * off the tsk->*_timers list onto the firing list. Per-thread timers + * have already been taken off. + */ +static void check_process_timers(struct task_struct *tsk, + struct list_head *firing) +{ + struct signal_struct *const sig = tsk->signal; + cputime_t utime, stime, ptime, virt_expires, prof_expires; + unsigned long long sched_time, sched_expires; + struct task_struct *t; + struct list_head *timers = sig->cpu_timers; + + /* + * Don't sample the current process CPU clocks if there are no timers. + */ + if (list_empty(&timers[CPUCLOCK_PROF]) && + cputime_eq(sig->it_prof_expires, cputime_zero) && + sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY && + list_empty(&timers[CPUCLOCK_VIRT]) && + cputime_eq(sig->it_virt_expires, cputime_zero) && + list_empty(&timers[CPUCLOCK_SCHED])) + return; + + /* + * Collect the current process totals. + */ + utime = sig->utime; + stime = sig->stime; + sched_time = sig->sched_time; + t = tsk; + do { + utime = cputime_add(utime, t->utime); + stime = cputime_add(stime, t->stime); + sched_time += t->sched_time; + t = next_thread(t); + } while (t != tsk); + ptime = cputime_add(utime, stime); + + prof_expires = cputime_zero; + while (!list_empty(timers)) { + struct cpu_timer_list *t = list_entry(timers->next, + struct cpu_timer_list, + entry); + if (cputime_lt(ptime, t->expires.cpu)) { + prof_expires = t->expires.cpu; + break; + } + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + ++timers; + virt_expires = cputime_zero; + while (!list_empty(timers)) { + struct cpu_timer_list *t = list_entry(timers->next, + struct cpu_timer_list, + entry); + if (cputime_lt(utime, t->expires.cpu)) { + virt_expires = t->expires.cpu; + break; + } + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + ++timers; + sched_expires = 0; + while (!list_empty(timers)) { + struct cpu_timer_list *t = list_entry(timers->next, + struct cpu_timer_list, + entry); + if (sched_time < t->expires.sched) { + sched_expires = t->expires.sched; + break; + } + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + /* + * Check for the special case process timers. + */ + if (!cputime_eq(sig->it_prof_expires, cputime_zero)) { + if (cputime_ge(ptime, sig->it_prof_expires)) { + /* ITIMER_PROF fires and reloads. */ + sig->it_prof_expires = sig->it_prof_incr; + if (!cputime_eq(sig->it_prof_expires, cputime_zero)) { + sig->it_prof_expires = cputime_add( + sig->it_prof_expires, ptime); + } + __group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk); + } + if (!cputime_eq(sig->it_prof_expires, cputime_zero) && + (cputime_eq(prof_expires, cputime_zero) || + cputime_lt(sig->it_prof_expires, prof_expires))) { + prof_expires = sig->it_prof_expires; + } + } + if (!cputime_eq(sig->it_virt_expires, cputime_zero)) { + if (cputime_ge(utime, sig->it_virt_expires)) { + /* ITIMER_VIRTUAL fires and reloads. */ + sig->it_virt_expires = sig->it_virt_incr; + if (!cputime_eq(sig->it_virt_expires, cputime_zero)) { + sig->it_virt_expires = cputime_add( + sig->it_virt_expires, utime); + } + __group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk); + } + if (!cputime_eq(sig->it_virt_expires, cputime_zero) && + (cputime_eq(virt_expires, cputime_zero) || + cputime_lt(sig->it_virt_expires, virt_expires))) { + virt_expires = sig->it_virt_expires; + } + } + if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { + unsigned long psecs = cputime_to_secs(ptime); + cputime_t x; + if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) { + /* + * At the hard limit, we just die. + * No need to calculate anything else now. + */ + __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); + return; + } + if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) { + /* + * At the soft limit, send a SIGXCPU every second. + */ + __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); + if (sig->rlim[RLIMIT_CPU].rlim_cur + < sig->rlim[RLIMIT_CPU].rlim_max) { + sig->rlim[RLIMIT_CPU].rlim_cur++; + } + } + x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); + if (cputime_eq(prof_expires, cputime_zero) || + cputime_lt(x, prof_expires)) { + prof_expires = x; + } + } + + if (!cputime_eq(prof_expires, cputime_zero) || + !cputime_eq(virt_expires, cputime_zero) || + sched_expires != 0) { + /* + * Rebalance the threads' expiry times for the remaining + * process CPU timers. + */ + + cputime_t prof_left, virt_left, ticks; + unsigned long long sched_left, sched; + const unsigned int nthreads = atomic_read(&sig->live); + + prof_left = cputime_sub(prof_expires, utime); + prof_left = cputime_sub(prof_left, stime); + prof_left = cputime_div(prof_left, nthreads); + virt_left = cputime_sub(virt_expires, utime); + virt_left = cputime_div(virt_left, nthreads); + if (sched_expires) { + sched_left = sched_expires - sched_time; + do_div(sched_left, nthreads); + } else { + sched_left = 0; + } + t = tsk; + do { + ticks = cputime_add(cputime_add(t->utime, t->stime), + prof_left); + if (!cputime_eq(prof_expires, cputime_zero) && + (cputime_eq(t->it_prof_expires, cputime_zero) || + cputime_gt(t->it_prof_expires, ticks))) { + t->it_prof_expires = ticks; + } + + ticks = cputime_add(t->utime, virt_left); + if (!cputime_eq(virt_expires, cputime_zero) && + (cputime_eq(t->it_virt_expires, cputime_zero) || + cputime_gt(t->it_virt_expires, ticks))) { + t->it_virt_expires = ticks; + } + + sched = t->sched_time + sched_left; + if (sched_expires && (t->it_sched_expires == 0 || + t->it_sched_expires > sched)) { + t->it_sched_expires = sched; + } + + do { + t = next_thread(t); + } while (unlikely(t->exit_state)); + } while (t != tsk); + } +} + +/* + * This is called from the signal code (via do_schedule_next_timer) + * when the last timer signal was delivered and we have to reload the timer. + */ +void posix_cpu_timer_schedule(struct k_itimer *timer) +{ + struct task_struct *p = timer->it.cpu.task; + union cpu_time_count now; + + if (unlikely(p == NULL)) + /* + * The task was cleaned up already, no future firings. + */ + return; + + /* + * Fetch the current sample and update the timer's expiry time. + */ + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + cpu_clock_sample(timer->it_clock, p, &now); + bump_cpu_timer(timer, now); + if (unlikely(p->exit_state)) { + clear_dead_task(timer, now); + return; + } + read_lock(&tasklist_lock); /* arm_timer needs it. */ + } else { + read_lock(&tasklist_lock); + if (unlikely(p->signal == NULL)) { + /* + * The process has been reaped. + * We can't even collect a sample any more. + */ + put_task_struct(p); + timer->it.cpu.task = p = NULL; + timer->it.cpu.expires.sched = 0; + read_unlock(&tasklist_lock); + return; + } else if (unlikely(p->exit_state) && thread_group_empty(p)) { + /* + * We've noticed that the thread is dead, but + * not yet reaped. Take this opportunity to + * drop our task ref. + */ + clear_dead_task(timer, now); + read_unlock(&tasklist_lock); + return; + } + cpu_clock_sample_group(timer->it_clock, p, &now); + bump_cpu_timer(timer, now); + /* Leave the tasklist_lock locked for the call below. */ + } + + /* + * Now re-arm for the new expiry time. + */ + arm_timer(timer, now); + + read_unlock(&tasklist_lock); +} + +/* + * This is called from the timer interrupt handler. The irq handler has + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +void run_posix_cpu_timers(struct task_struct *tsk) +{ + LIST_HEAD(firing); + struct k_itimer *timer, *next; + + BUG_ON(!irqs_disabled()); + +#define UNEXPIRED(clock) \ + (cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \ + cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires)) + + if (UNEXPIRED(prof) && UNEXPIRED(virt) && + (tsk->it_sched_expires == 0 || + tsk->sched_time < tsk->it_sched_expires)) + return; + +#undef UNEXPIRED + + BUG_ON(tsk->exit_state); + + /* + * Double-check with locks held. + */ + read_lock(&tasklist_lock); + spin_lock(&tsk->sighand->siglock); + + /* + * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] + * all the timers that are firing, and put them on the firing list. + */ + check_thread_timers(tsk, &firing); + check_process_timers(tsk, &firing); + + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + spin_unlock(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + + /* + * Now that all the timers on our list have the firing flag, + * noone will touch their list entries but us. We'll take + * each timer's lock before clearing its firing flag, so no + * timer call will interfere. + */ + list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) { + int firing; + spin_lock(&timer->it_lock); + list_del_init(&timer->it.cpu.entry); + firing = timer->it.cpu.firing; + timer->it.cpu.firing = 0; + /* + * The firing flag is -1 if we collided with a reset + * of the timer, which already reported this + * almost-firing as an overrun. So don't generate an event. + */ + if (likely(firing >= 0)) { + cpu_timer_fire(timer); + } + spin_unlock(&timer->it_lock); + } +} + +/* + * Set one of the process-wide special case CPU timers. + * The tasklist_lock and tsk->sighand->siglock must be held by the caller. + * The oldval argument is null for the RLIMIT_CPU timer, where *newval is + * absolute; non-null for ITIMER_*, where *newval is relative and we update + * it to be absolute, *oldval is absolute and we update it to be relative. + */ +void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, + cputime_t *newval, cputime_t *oldval) +{ + union cpu_time_count now; + struct list_head *head; + + BUG_ON(clock_idx == CPUCLOCK_SCHED); + cpu_clock_sample_group_locked(clock_idx, tsk, &now); + + if (oldval) { + if (!cputime_eq(*oldval, cputime_zero)) { + if (cputime_le(*oldval, now.cpu)) { + /* Just about to fire. */ + *oldval = jiffies_to_cputime(1); + } else { + *oldval = cputime_sub(*oldval, now.cpu); + } + } + + if (cputime_eq(*newval, cputime_zero)) + return; + *newval = cputime_add(*newval, now.cpu); + + /* + * If the RLIMIT_CPU timer will expire before the + * ITIMER_PROF timer, we have nothing else to do. + */ + if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur + < cputime_to_secs(*newval)) + return; + } + + /* + * Check whether there are any process timers already set to fire + * before this one. If so, we don't have anything more to do. + */ + head = &tsk->signal->cpu_timers[clock_idx]; + if (list_empty(head) || + cputime_ge(list_entry(head->next, + struct cpu_timer_list, entry)->expires.cpu, + *newval)) { + /* + * Rejigger each thread's expiry time so that one will + * notice before we hit the process-cumulative expiry time. + */ + union cpu_time_count expires = { .sched = 0 }; + expires.cpu = *newval; + process_timer_rebalance(tsk, clock_idx, expires, now); + } +} + +static long posix_cpu_clock_nanosleep_restart(struct restart_block *); + +int posix_cpu_nsleep(clockid_t which_clock, int flags, + struct timespec *rqtp) +{ + struct restart_block *restart_block = + ¤t_thread_info()->restart_block; + struct k_itimer timer; + int error; + + /* + * Diagnose required errors first. + */ + if (CPUCLOCK_PERTHREAD(which_clock) && + (CPUCLOCK_PID(which_clock) == 0 || + CPUCLOCK_PID(which_clock) == current->pid)) + return -EINVAL; + + /* + * Set up a temporary timer and then wait for it to go off. + */ + memset(&timer, 0, sizeof timer); + spin_lock_init(&timer.it_lock); + timer.it_clock = which_clock; + timer.it_overrun = -1; + error = posix_cpu_timer_create(&timer); + timer.it_process = current; + if (!error) { + struct timespec __user *rmtp; + static struct itimerspec zero_it; + struct itimerspec it = { .it_value = *rqtp, + .it_interval = {} }; + + spin_lock_irq(&timer.it_lock); + error = posix_cpu_timer_set(&timer, flags, &it, NULL); + if (error) { + spin_unlock_irq(&timer.it_lock); + return error; + } + + while (!signal_pending(current)) { + if (timer.it.cpu.expires.sched == 0) { + /* + * Our timer fired and was reset. + */ + spin_unlock_irq(&timer.it_lock); + return 0; + } + + /* + * Block until cpu_timer_fire (or a signal) wakes us. + */ + __set_current_state(TASK_INTERRUPTIBLE); + spin_unlock_irq(&timer.it_lock); + schedule(); + spin_lock_irq(&timer.it_lock); + } + + /* + * We were interrupted by a signal. + */ + sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp); + posix_cpu_timer_set(&timer, 0, &zero_it, &it); + spin_unlock_irq(&timer.it_lock); + + if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { + /* + * It actually did fire already. + */ + return 0; + } + + /* + * Report back to the user the time still remaining. + */ + rmtp = (struct timespec __user *) restart_block->arg1; + if (rmtp != NULL && !(flags & TIMER_ABSTIME) && + copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) + return -EFAULT; + + restart_block->fn = posix_cpu_clock_nanosleep_restart; + /* Caller already set restart_block->arg1 */ + restart_block->arg0 = which_clock; + restart_block->arg2 = rqtp->tv_sec; + restart_block->arg3 = rqtp->tv_nsec; + + error = -ERESTART_RESTARTBLOCK; + } + + return error; +} + +static long +posix_cpu_clock_nanosleep_restart(struct restart_block *restart_block) +{ + clockid_t which_clock = restart_block->arg0; + struct timespec t = { .tv_sec = restart_block->arg2, + .tv_nsec = restart_block->arg3 }; + restart_block->fn = do_no_restart_syscall; + return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t); +} + + +#define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED) +#define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED) + +static int process_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +{ + return posix_cpu_clock_getres(PROCESS_CLOCK, tp); +} +static int process_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +{ + return posix_cpu_clock_get(PROCESS_CLOCK, tp); +} +static int process_cpu_timer_create(struct k_itimer *timer) +{ + timer->it_clock = PROCESS_CLOCK; + return posix_cpu_timer_create(timer); +} +static int process_cpu_nsleep(clockid_t which_clock, int flags, + struct timespec *rqtp) +{ + return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp); +} +static int thread_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +{ + return posix_cpu_clock_getres(THREAD_CLOCK, tp); +} +static int thread_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +{ + return posix_cpu_clock_get(THREAD_CLOCK, tp); +} +static int thread_cpu_timer_create(struct k_itimer *timer) +{ + timer->it_clock = THREAD_CLOCK; + return posix_cpu_timer_create(timer); +} +static int thread_cpu_nsleep(clockid_t which_clock, int flags, + struct timespec *rqtp) +{ + return -EINVAL; +} + +static __init int init_posix_cpu_timers(void) +{ + struct k_clock process = { + .clock_getres = process_cpu_clock_getres, + .clock_get = process_cpu_clock_get, + .clock_set = do_posix_clock_nosettime, + .timer_create = process_cpu_timer_create, + .nsleep = process_cpu_nsleep, + }; + struct k_clock thread = { + .clock_getres = thread_cpu_clock_getres, + .clock_get = thread_cpu_clock_get, + .clock_set = do_posix_clock_nosettime, + .timer_create = thread_cpu_timer_create, + .nsleep = thread_cpu_nsleep, + }; + + register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process); + register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread); + + return 0; +} +__initcall(init_posix_cpu_timers); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c new file mode 100644 index 000000000000..fd316c272260 --- /dev/null +++ b/kernel/posix-timers.c @@ -0,0 +1,1584 @@ +/* + * linux/kernel/posix_timers.c + * + * + * 2002-10-15 Posix Clocks & timers + * by George Anzinger george@mvista.com + * + * Copyright (C) 2002 2003 by MontaVista Software. + * + * 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug. + * Copyright (C) 2004 Boris Hu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA + */ + +/* These are all the functions necessary to implement + * POSIX clocks & timers + */ +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef div_long_long_rem +#include + +#define div_long_long_rem(dividend,divisor,remainder) ({ \ + u64 result = dividend; \ + *remainder = do_div(result,divisor); \ + result; }) + +#endif +#define CLOCK_REALTIME_RES TICK_NSEC /* In nano seconds. */ + +static inline u64 mpy_l_X_l_ll(unsigned long mpy1,unsigned long mpy2) +{ + return (u64)mpy1 * mpy2; +} +/* + * Management arrays for POSIX timers. Timers are kept in slab memory + * Timer ids are allocated by an external routine that keeps track of the + * id and the timer. The external interface is: + * + * void *idr_find(struct idr *idp, int id); to find timer_id + * int idr_get_new(struct idr *idp, void *ptr); to get a new id and + * related it to + * void idr_remove(struct idr *idp, int id); to release + * void idr_init(struct idr *idp); to initialize + * which we supply. + * The idr_get_new *may* call slab for more memory so it must not be + * called under a spin lock. Likewise idr_remore may release memory + * (but it may be ok to do this under a lock...). + * idr_find is just a memory look up and is quite fast. A -1 return + * indicates that the requested id does not exist. + */ + +/* + * Lets keep our timers in a slab cache :-) + */ +static kmem_cache_t *posix_timers_cache; +static struct idr posix_timers_id; +static DEFINE_SPINLOCK(idr_lock); + +/* + * Just because the timer is not in the timer list does NOT mean it is + * inactive. It could be in the "fire" routine getting a new expire time. + */ +#define TIMER_INACTIVE 1 + +#ifdef CONFIG_SMP +# define timer_active(tmr) \ + ((tmr)->it.real.timer.entry.prev != (void *)TIMER_INACTIVE) +# define set_timer_inactive(tmr) \ + do { \ + (tmr)->it.real.timer.entry.prev = (void *)TIMER_INACTIVE; \ + } while (0) +#else +# define timer_active(tmr) BARFY // error to use outside of SMP +# define set_timer_inactive(tmr) do { } while (0) +#endif +/* + * we assume that the new SIGEV_THREAD_ID shares no bits with the other + * SIGEV values. Here we put out an error if this assumption fails. + */ +#if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \ + ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) +#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!" +#endif + + +/* + * The timer ID is turned into a timer address by idr_find(). + * Verifying a valid ID consists of: + * + * a) checking that idr_find() returns other than -1. + * b) checking that the timer id matches the one in the timer itself. + * c) that the timer owner is in the callers thread group. + */ + +/* + * CLOCKs: The POSIX standard calls for a couple of clocks and allows us + * to implement others. This structure defines the various + * clocks and allows the possibility of adding others. We + * provide an interface to add clocks to the table and expect + * the "arch" code to add at least one clock that is high + * resolution. Here we define the standard CLOCK_REALTIME as a + * 1/HZ resolution clock. + * + * RESOLUTION: Clock resolution is used to round up timer and interval + * times, NOT to report clock times, which are reported with as + * much resolution as the system can muster. In some cases this + * resolution may depend on the underlying clock hardware and + * may not be quantifiable until run time, and only then is the + * necessary code is written. The standard says we should say + * something about this issue in the documentation... + * + * FUNCTIONS: The CLOCKs structure defines possible functions to handle + * various clock functions. For clocks that use the standard + * system timer code these entries should be NULL. This will + * allow dispatch without the overhead of indirect function + * calls. CLOCKS that depend on other sources (e.g. WWV or GPS) + * must supply functions here, even if the function just returns + * ENOSYS. The standard POSIX timer management code assumes the + * following: 1.) The k_itimer struct (sched.h) is used for the + * timer. 2.) The list, it_lock, it_clock, it_id and it_process + * fields are not modified by timer code. + * + * At this time all functions EXCEPT clock_nanosleep can be + * redirected by the CLOCKS structure. Clock_nanosleep is in + * there, but the code ignores it. + * + * Permissions: It is assumed that the clock_settime() function defined + * for each clock will take care of permission checks. Some + * clocks may be set able by any user (i.e. local process + * clocks) others not. Currently the only set able clock we + * have is CLOCK_REALTIME and its high res counter part, both of + * which we beg off on and pass to do_sys_settimeofday(). + */ + +static struct k_clock posix_clocks[MAX_CLOCKS]; +/* + * We only have one real clock that can be set so we need only one abs list, + * even if we should want to have several clocks with differing resolutions. + */ +static struct k_clock_abs abs_list = {.list = LIST_HEAD_INIT(abs_list.list), + .lock = SPIN_LOCK_UNLOCKED}; + +static void posix_timer_fn(unsigned long); +static u64 do_posix_clock_monotonic_gettime_parts( + struct timespec *tp, struct timespec *mo); +int do_posix_clock_monotonic_gettime(struct timespec *tp); +static int do_posix_clock_monotonic_get(clockid_t, struct timespec *tp); + +static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags); + +static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) +{ + spin_unlock_irqrestore(&timr->it_lock, flags); +} + +/* + * Call the k_clock hook function if non-null, or the default function. + */ +#define CLOCK_DISPATCH(clock, call, arglist) \ + ((clock) < 0 ? posix_cpu_##call arglist : \ + (posix_clocks[clock].call != NULL \ + ? (*posix_clocks[clock].call) arglist : common_##call arglist)) + +/* + * Default clock hook functions when the struct k_clock passed + * to register_posix_clock leaves a function pointer null. + * + * The function common_CALL is the default implementation for + * the function pointer CALL in struct k_clock. + */ + +static inline int common_clock_getres(clockid_t which_clock, + struct timespec *tp) +{ + tp->tv_sec = 0; + tp->tv_nsec = posix_clocks[which_clock].res; + return 0; +} + +static inline int common_clock_get(clockid_t which_clock, struct timespec *tp) +{ + getnstimeofday(tp); + return 0; +} + +static inline int common_clock_set(clockid_t which_clock, struct timespec *tp) +{ + return do_sys_settimeofday(tp, NULL); +} + +static inline int common_timer_create(struct k_itimer *new_timer) +{ + INIT_LIST_HEAD(&new_timer->it.real.abs_timer_entry); + init_timer(&new_timer->it.real.timer); + new_timer->it.real.timer.data = (unsigned long) new_timer; + new_timer->it.real.timer.function = posix_timer_fn; + set_timer_inactive(new_timer); + return 0; +} + +/* + * These ones are defined below. + */ +static int common_nsleep(clockid_t, int flags, struct timespec *t); +static void common_timer_get(struct k_itimer *, struct itimerspec *); +static int common_timer_set(struct k_itimer *, int, + struct itimerspec *, struct itimerspec *); +static int common_timer_del(struct k_itimer *timer); + +/* + * Return nonzero iff we know a priori this clockid_t value is bogus. + */ +static inline int invalid_clockid(clockid_t which_clock) +{ + if (which_clock < 0) /* CPU clock, posix_cpu_* will check it */ + return 0; + if ((unsigned) which_clock >= MAX_CLOCKS) + return 1; + if (posix_clocks[which_clock].clock_getres != NULL) + return 0; +#ifndef CLOCK_DISPATCH_DIRECT + if (posix_clocks[which_clock].res != 0) + return 0; +#endif + return 1; +} + + +/* + * Initialize everything, well, just everything in Posix clocks/timers ;) + */ +static __init int init_posix_timers(void) +{ + struct k_clock clock_realtime = {.res = CLOCK_REALTIME_RES, + .abs_struct = &abs_list + }; + struct k_clock clock_monotonic = {.res = CLOCK_REALTIME_RES, + .abs_struct = NULL, + .clock_get = do_posix_clock_monotonic_get, + .clock_set = do_posix_clock_nosettime + }; + + register_posix_clock(CLOCK_REALTIME, &clock_realtime); + register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic); + + posix_timers_cache = kmem_cache_create("posix_timers_cache", + sizeof (struct k_itimer), 0, 0, NULL, NULL); + idr_init(&posix_timers_id); + return 0; +} + +__initcall(init_posix_timers); + +static void tstojiffie(struct timespec *tp, int res, u64 *jiff) +{ + long sec = tp->tv_sec; + long nsec = tp->tv_nsec + res - 1; + + if (nsec > NSEC_PER_SEC) { + sec++; + nsec -= NSEC_PER_SEC; + } + + /* + * The scaling constants are defined in + * The difference between there and here is that we do the + * res rounding and compute a 64-bit result (well so does that + * but it then throws away the high bits). + */ + *jiff = (mpy_l_X_l_ll(sec, SEC_CONVERSION) + + (mpy_l_X_l_ll(nsec, NSEC_CONVERSION) >> + (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; +} + +/* + * This function adjusts the timer as needed as a result of the clock + * being set. It should only be called for absolute timers, and then + * under the abs_list lock. It computes the time difference and sets + * the new jiffies value in the timer. It also updates the timers + * reference wall_to_monotonic value. It is complicated by the fact + * that tstojiffies() only handles positive times and it needs to work + * with both positive and negative times. Also, for negative offsets, + * we need to defeat the res round up. + * + * Return is true if there is a new time, else false. + */ +static long add_clockset_delta(struct k_itimer *timr, + struct timespec *new_wall_to) +{ + struct timespec delta; + int sign = 0; + u64 exp; + + set_normalized_timespec(&delta, + new_wall_to->tv_sec - + timr->it.real.wall_to_prev.tv_sec, + new_wall_to->tv_nsec - + timr->it.real.wall_to_prev.tv_nsec); + if (likely(!(delta.tv_sec | delta.tv_nsec))) + return 0; + if (delta.tv_sec < 0) { + set_normalized_timespec(&delta, + -delta.tv_sec, + 1 - delta.tv_nsec - + posix_clocks[timr->it_clock].res); + sign++; + } + tstojiffie(&delta, posix_clocks[timr->it_clock].res, &exp); + timr->it.real.wall_to_prev = *new_wall_to; + timr->it.real.timer.expires += (sign ? -exp : exp); + return 1; +} + +static void remove_from_abslist(struct k_itimer *timr) +{ + if (!list_empty(&timr->it.real.abs_timer_entry)) { + spin_lock(&abs_list.lock); + list_del_init(&timr->it.real.abs_timer_entry); + spin_unlock(&abs_list.lock); + } +} + +static void schedule_next_timer(struct k_itimer *timr) +{ + struct timespec new_wall_to; + struct now_struct now; + unsigned long seq; + + /* + * Set up the timer for the next interval (if there is one). + * Note: this code uses the abs_timer_lock to protect + * it.real.wall_to_prev and must hold it until exp is set, not exactly + * obvious... + + * This function is used for CLOCK_REALTIME* and + * CLOCK_MONOTONIC* timers. If we ever want to handle other + * CLOCKs, the calling code (do_schedule_next_timer) would need + * to pull the "clock" info from the timer and dispatch the + * "other" CLOCKs "next timer" code (which, I suppose should + * also be added to the k_clock structure). + */ + if (!timr->it.real.incr) + return; + + do { + seq = read_seqbegin(&xtime_lock); + new_wall_to = wall_to_monotonic; + posix_get_now(&now); + } while (read_seqretry(&xtime_lock, seq)); + + if (!list_empty(&timr->it.real.abs_timer_entry)) { + spin_lock(&abs_list.lock); + add_clockset_delta(timr, &new_wall_to); + + posix_bump_timer(timr, now); + + spin_unlock(&abs_list.lock); + } else { + posix_bump_timer(timr, now); + } + timr->it_overrun_last = timr->it_overrun; + timr->it_overrun = -1; + ++timr->it_requeue_pending; + add_timer(&timr->it.real.timer); +} + +/* + * This function is exported for use by the signal deliver code. It is + * called just prior to the info block being released and passes that + * block to us. It's function is to update the overrun entry AND to + * restart the timer. It should only be called if the timer is to be + * restarted (i.e. we have flagged this in the sys_private entry of the + * info block). + * + * To protect aginst the timer going away while the interrupt is queued, + * we require that the it_requeue_pending flag be set. + */ +void do_schedule_next_timer(struct siginfo *info) +{ + struct k_itimer *timr; + unsigned long flags; + + timr = lock_timer(info->si_tid, &flags); + + if (!timr || timr->it_requeue_pending != info->si_sys_private) + goto exit; + + if (timr->it_clock < 0) /* CPU clock */ + posix_cpu_timer_schedule(timr); + else + schedule_next_timer(timr); + info->si_overrun = timr->it_overrun_last; +exit: + if (timr) + unlock_timer(timr, flags); +} + +int posix_timer_event(struct k_itimer *timr,int si_private) +{ + memset(&timr->sigq->info, 0, sizeof(siginfo_t)); + timr->sigq->info.si_sys_private = si_private; + /* + * Send signal to the process that owns this timer. + + * This code assumes that all the possible abs_lists share the + * same lock (there is only one list at this time). If this is + * not the case, the CLOCK info would need to be used to find + * the proper abs list lock. + */ + + timr->sigq->info.si_signo = timr->it_sigev_signo; + timr->sigq->info.si_errno = 0; + timr->sigq->info.si_code = SI_TIMER; + timr->sigq->info.si_tid = timr->it_id; + timr->sigq->info.si_value = timr->it_sigev_value; + if (timr->it_sigev_notify & SIGEV_THREAD_ID) { + if (unlikely(timr->it_process->flags & PF_EXITING)) { + timr->it_sigev_notify = SIGEV_SIGNAL; + put_task_struct(timr->it_process); + timr->it_process = timr->it_process->group_leader; + goto group; + } + return send_sigqueue(timr->it_sigev_signo, timr->sigq, + timr->it_process); + } + else { + group: + return send_group_sigqueue(timr->it_sigev_signo, timr->sigq, + timr->it_process); + } +} +EXPORT_SYMBOL_GPL(posix_timer_event); + +/* + * This function gets called when a POSIX.1b interval timer expires. It + * is used as a callback from the kernel internal timer. The + * run_timer_list code ALWAYS calls with interrupts on. + + * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers. + */ +static void posix_timer_fn(unsigned long __data) +{ + struct k_itimer *timr = (struct k_itimer *) __data; + unsigned long flags; + unsigned long seq; + struct timespec delta, new_wall_to; + u64 exp = 0; + int do_notify = 1; + + spin_lock_irqsave(&timr->it_lock, flags); + set_timer_inactive(timr); + if (!list_empty(&timr->it.real.abs_timer_entry)) { + spin_lock(&abs_list.lock); + do { + seq = read_seqbegin(&xtime_lock); + new_wall_to = wall_to_monotonic; + } while (read_seqretry(&xtime_lock, seq)); + set_normalized_timespec(&delta, + new_wall_to.tv_sec - + timr->it.real.wall_to_prev.tv_sec, + new_wall_to.tv_nsec - + timr->it.real.wall_to_prev.tv_nsec); + if (likely((delta.tv_sec | delta.tv_nsec ) == 0)) { + /* do nothing, timer is on time */ + } else if (delta.tv_sec < 0) { + /* do nothing, timer is already late */ + } else { + /* timer is early due to a clock set */ + tstojiffie(&delta, + posix_clocks[timr->it_clock].res, + &exp); + timr->it.real.wall_to_prev = new_wall_to; + timr->it.real.timer.expires += exp; + add_timer(&timr->it.real.timer); + do_notify = 0; + } + spin_unlock(&abs_list.lock); + + } + if (do_notify) { + int si_private=0; + + if (timr->it.real.incr) + si_private = ++timr->it_requeue_pending; + else { + remove_from_abslist(timr); + } + + if (posix_timer_event(timr, si_private)) + /* + * signal was not sent because of sig_ignor + * we will not get a call back to restart it AND + * it should be restarted. + */ + schedule_next_timer(timr); + } + unlock_timer(timr, flags); /* hold thru abs lock to keep irq off */ +} + + +static inline struct task_struct * good_sigevent(sigevent_t * event) +{ + struct task_struct *rtn = current->group_leader; + + if ((event->sigev_notify & SIGEV_THREAD_ID ) && + (!(rtn = find_task_by_pid(event->sigev_notify_thread_id)) || + rtn->tgid != current->tgid || + (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL)) + return NULL; + + if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && + ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) + return NULL; + + return rtn; +} + +void register_posix_clock(clockid_t clock_id, struct k_clock *new_clock) +{ + if ((unsigned) clock_id >= MAX_CLOCKS) { + printk("POSIX clock register failed for clock_id %d\n", + clock_id); + return; + } + + posix_clocks[clock_id] = *new_clock; +} +EXPORT_SYMBOL_GPL(register_posix_clock); + +static struct k_itimer * alloc_posix_timer(void) +{ + struct k_itimer *tmr; + tmr = kmem_cache_alloc(posix_timers_cache, GFP_KERNEL); + if (!tmr) + return tmr; + memset(tmr, 0, sizeof (struct k_itimer)); + if (unlikely(!(tmr->sigq = sigqueue_alloc()))) { + kmem_cache_free(posix_timers_cache, tmr); + tmr = NULL; + } + return tmr; +} + +#define IT_ID_SET 1 +#define IT_ID_NOT_SET 0 +static void release_posix_timer(struct k_itimer *tmr, int it_id_set) +{ + if (it_id_set) { + unsigned long flags; + spin_lock_irqsave(&idr_lock, flags); + idr_remove(&posix_timers_id, tmr->it_id); + spin_unlock_irqrestore(&idr_lock, flags); + } + sigqueue_free(tmr->sigq); + if (unlikely(tmr->it_process) && + tmr->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) + put_task_struct(tmr->it_process); + kmem_cache_free(posix_timers_cache, tmr); +} + +/* Create a POSIX.1b interval timer. */ + +asmlinkage long +sys_timer_create(clockid_t which_clock, + struct sigevent __user *timer_event_spec, + timer_t __user * created_timer_id) +{ + int error = 0; + struct k_itimer *new_timer = NULL; + int new_timer_id; + struct task_struct *process = NULL; + unsigned long flags; + sigevent_t event; + int it_id_set = IT_ID_NOT_SET; + + if (invalid_clockid(which_clock)) + return -EINVAL; + + new_timer = alloc_posix_timer(); + if (unlikely(!new_timer)) + return -EAGAIN; + + spin_lock_init(&new_timer->it_lock); + retry: + if (unlikely(!idr_pre_get(&posix_timers_id, GFP_KERNEL))) { + error = -EAGAIN; + goto out; + } + spin_lock_irq(&idr_lock); + error = idr_get_new(&posix_timers_id, + (void *) new_timer, + &new_timer_id); + spin_unlock_irq(&idr_lock); + if (error == -EAGAIN) + goto retry; + else if (error) { + /* + * Wierd looking, but we return EAGAIN if the IDR is + * full (proper POSIX return value for this) + */ + error = -EAGAIN; + goto out; + } + + it_id_set = IT_ID_SET; + new_timer->it_id = (timer_t) new_timer_id; + new_timer->it_clock = which_clock; + new_timer->it_overrun = -1; + error = CLOCK_DISPATCH(which_clock, timer_create, (new_timer)); + if (error) + goto out; + + /* + * return the timer_id now. The next step is hard to + * back out if there is an error. + */ + if (copy_to_user(created_timer_id, + &new_timer_id, sizeof (new_timer_id))) { + error = -EFAULT; + goto out; + } + if (timer_event_spec) { + if (copy_from_user(&event, timer_event_spec, sizeof (event))) { + error = -EFAULT; + goto out; + } + new_timer->it_sigev_notify = event.sigev_notify; + new_timer->it_sigev_signo = event.sigev_signo; + new_timer->it_sigev_value = event.sigev_value; + + read_lock(&tasklist_lock); + if ((process = good_sigevent(&event))) { + /* + * We may be setting up this process for another + * thread. It may be exiting. To catch this + * case the we check the PF_EXITING flag. If + * the flag is not set, the siglock will catch + * him before it is too late (in exit_itimers). + * + * The exec case is a bit more invloved but easy + * to code. If the process is in our thread + * group (and it must be or we would not allow + * it here) and is doing an exec, it will cause + * us to be killed. In this case it will wait + * for us to die which means we can finish this + * linkage with our last gasp. I.e. no code :) + */ + spin_lock_irqsave(&process->sighand->siglock, flags); + if (!(process->flags & PF_EXITING)) { + new_timer->it_process = process; + list_add(&new_timer->list, + &process->signal->posix_timers); + spin_unlock_irqrestore(&process->sighand->siglock, flags); + if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) + get_task_struct(process); + } else { + spin_unlock_irqrestore(&process->sighand->siglock, flags); + process = NULL; + } + } + read_unlock(&tasklist_lock); + if (!process) { + error = -EINVAL; + goto out; + } + } else { + new_timer->it_sigev_notify = SIGEV_SIGNAL; + new_timer->it_sigev_signo = SIGALRM; + new_timer->it_sigev_value.sival_int = new_timer->it_id; + process = current->group_leader; + spin_lock_irqsave(&process->sighand->siglock, flags); + new_timer->it_process = process; + list_add(&new_timer->list, &process->signal->posix_timers); + spin_unlock_irqrestore(&process->sighand->siglock, flags); + } + + /* + * In the case of the timer belonging to another task, after + * the task is unlocked, the timer is owned by the other task + * and may cease to exist at any time. Don't use or modify + * new_timer after the unlock call. + */ + +out: + if (error) + release_posix_timer(new_timer, it_id_set); + + return error; +} + +/* + * good_timespec + * + * This function checks the elements of a timespec structure. + * + * Arguments: + * ts : Pointer to the timespec structure to check + * + * Return value: + * If a NULL pointer was passed in, or the tv_nsec field was less than 0 + * or greater than NSEC_PER_SEC, or the tv_sec field was less than 0, + * this function returns 0. Otherwise it returns 1. + */ +static int good_timespec(const struct timespec *ts) +{ + if ((!ts) || (ts->tv_sec < 0) || + ((unsigned) ts->tv_nsec >= NSEC_PER_SEC)) + return 0; + return 1; +} + +/* + * Locking issues: We need to protect the result of the id look up until + * we get the timer locked down so it is not deleted under us. The + * removal is done under the idr spinlock so we use that here to bridge + * the find to the timer lock. To avoid a dead lock, the timer id MUST + * be release with out holding the timer lock. + */ +static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) +{ + struct k_itimer *timr; + /* + * Watch out here. We do a irqsave on the idr_lock and pass the + * flags part over to the timer lock. Must not let interrupts in + * while we are moving the lock. + */ + + spin_lock_irqsave(&idr_lock, *flags); + timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id); + if (timr) { + spin_lock(&timr->it_lock); + spin_unlock(&idr_lock); + + if ((timr->it_id != timer_id) || !(timr->it_process) || + timr->it_process->tgid != current->tgid) { + unlock_timer(timr, *flags); + timr = NULL; + } + } else + spin_unlock_irqrestore(&idr_lock, *flags); + + return timr; +} + +/* + * Get the time remaining on a POSIX.1b interval timer. This function + * is ALWAYS called with spin_lock_irq on the timer, thus it must not + * mess with irq. + * + * We have a couple of messes to clean up here. First there is the case + * of a timer that has a requeue pending. These timers should appear to + * be in the timer list with an expiry as if we were to requeue them + * now. + * + * The second issue is the SIGEV_NONE timer which may be active but is + * not really ever put in the timer list (to save system resources). + * This timer may be expired, and if so, we will do it here. Otherwise + * it is the same as a requeue pending timer WRT to what we should + * report. + */ +static void +common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) +{ + unsigned long expires; + struct now_struct now; + + do + expires = timr->it.real.timer.expires; + while ((volatile long) (timr->it.real.timer.expires) != expires); + + posix_get_now(&now); + + if (expires && + ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) && + !timr->it.real.incr && + posix_time_before(&timr->it.real.timer, &now)) + timr->it.real.timer.expires = expires = 0; + if (expires) { + if (timr->it_requeue_pending & REQUEUE_PENDING || + (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { + posix_bump_timer(timr, now); + expires = timr->it.real.timer.expires; + } + else + if (!timer_pending(&timr->it.real.timer)) + expires = 0; + if (expires) + expires -= now.jiffies; + } + jiffies_to_timespec(expires, &cur_setting->it_value); + jiffies_to_timespec(timr->it.real.incr, &cur_setting->it_interval); + + if (cur_setting->it_value.tv_sec < 0) { + cur_setting->it_value.tv_nsec = 1; + cur_setting->it_value.tv_sec = 0; + } +} + +/* Get the time remaining on a POSIX.1b interval timer. */ +asmlinkage long +sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting) +{ + struct k_itimer *timr; + struct itimerspec cur_setting; + unsigned long flags; + + timr = lock_timer(timer_id, &flags); + if (!timr) + return -EINVAL; + + CLOCK_DISPATCH(timr->it_clock, timer_get, (timr, &cur_setting)); + + unlock_timer(timr, flags); + + if (copy_to_user(setting, &cur_setting, sizeof (cur_setting))) + return -EFAULT; + + return 0; +} +/* + * Get the number of overruns of a POSIX.1b interval timer. This is to + * be the overrun of the timer last delivered. At the same time we are + * accumulating overruns on the next timer. The overrun is frozen when + * the signal is delivered, either at the notify time (if the info block + * is not queued) or at the actual delivery time (as we are informed by + * the call back to do_schedule_next_timer(). So all we need to do is + * to pick up the frozen overrun. + */ + +asmlinkage long +sys_timer_getoverrun(timer_t timer_id) +{ + struct k_itimer *timr; + int overrun; + long flags; + + timr = lock_timer(timer_id, &flags); + if (!timr) + return -EINVAL; + + overrun = timr->it_overrun_last; + unlock_timer(timr, flags); + + return overrun; +} +/* + * Adjust for absolute time + * + * If absolute time is given and it is not CLOCK_MONOTONIC, we need to + * adjust for the offset between the timer clock (CLOCK_MONOTONIC) and + * what ever clock he is using. + * + * If it is relative time, we need to add the current (CLOCK_MONOTONIC) + * time to it to get the proper time for the timer. + */ +static int adjust_abs_time(struct k_clock *clock, struct timespec *tp, + int abs, u64 *exp, struct timespec *wall_to) +{ + struct timespec now; + struct timespec oc = *tp; + u64 jiffies_64_f; + int rtn =0; + + if (abs) { + /* + * The mask pick up the 4 basic clocks + */ + if (!((clock - &posix_clocks[0]) & ~CLOCKS_MASK)) { + jiffies_64_f = do_posix_clock_monotonic_gettime_parts( + &now, wall_to); + /* + * If we are doing a MONOTONIC clock + */ + if((clock - &posix_clocks[0]) & CLOCKS_MONO){ + now.tv_sec += wall_to->tv_sec; + now.tv_nsec += wall_to->tv_nsec; + } + } else { + /* + * Not one of the basic clocks + */ + clock->clock_get(clock - posix_clocks, &now); + jiffies_64_f = get_jiffies_64(); + } + /* + * Take away now to get delta + */ + oc.tv_sec -= now.tv_sec; + oc.tv_nsec -= now.tv_nsec; + /* + * Normalize... + */ + while ((oc.tv_nsec - NSEC_PER_SEC) >= 0) { + oc.tv_nsec -= NSEC_PER_SEC; + oc.tv_sec++; + } + while ((oc.tv_nsec) < 0) { + oc.tv_nsec += NSEC_PER_SEC; + oc.tv_sec--; + } + }else{ + jiffies_64_f = get_jiffies_64(); + } + /* + * Check if the requested time is prior to now (if so set now) + */ + if (oc.tv_sec < 0) + oc.tv_sec = oc.tv_nsec = 0; + + if (oc.tv_sec | oc.tv_nsec) + set_normalized_timespec(&oc, oc.tv_sec, + oc.tv_nsec + clock->res); + tstojiffie(&oc, clock->res, exp); + + /* + * Check if the requested time is more than the timer code + * can handle (if so we error out but return the value too). + */ + if (*exp > ((u64)MAX_JIFFY_OFFSET)) + /* + * This is a considered response, not exactly in + * line with the standard (in fact it is silent on + * possible overflows). We assume such a large + * value is ALMOST always a programming error and + * try not to compound it by setting a really dumb + * value. + */ + rtn = -EINVAL; + /* + * return the actual jiffies expire time, full 64 bits + */ + *exp += jiffies_64_f; + return rtn; +} + +/* Set a POSIX.1b interval timer. */ +/* timr->it_lock is taken. */ +static inline int +common_timer_set(struct k_itimer *timr, int flags, + struct itimerspec *new_setting, struct itimerspec *old_setting) +{ + struct k_clock *clock = &posix_clocks[timr->it_clock]; + u64 expire_64; + + if (old_setting) + common_timer_get(timr, old_setting); + + /* disable the timer */ + timr->it.real.incr = 0; + /* + * careful here. If smp we could be in the "fire" routine which will + * be spinning as we hold the lock. But this is ONLY an SMP issue. + */ +#ifdef CONFIG_SMP + if (timer_active(timr) && !del_timer(&timr->it.real.timer)) + /* + * It can only be active if on an other cpu. Since + * we have cleared the interval stuff above, it should + * clear once we release the spin lock. Of course once + * we do that anything could happen, including the + * complete melt down of the timer. So return with + * a "retry" exit status. + */ + return TIMER_RETRY; + + set_timer_inactive(timr); +#else + del_timer(&timr->it.real.timer); +#endif + remove_from_abslist(timr); + + timr->it_requeue_pending = (timr->it_requeue_pending + 2) & + ~REQUEUE_PENDING; + timr->it_overrun_last = 0; + timr->it_overrun = -1; + /* + *switch off the timer when it_value is zero + */ + if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) { + timr->it.real.timer.expires = 0; + return 0; + } + + if (adjust_abs_time(clock, + &new_setting->it_value, flags & TIMER_ABSTIME, + &expire_64, &(timr->it.real.wall_to_prev))) { + return -EINVAL; + } + timr->it.real.timer.expires = (unsigned long)expire_64; + tstojiffie(&new_setting->it_interval, clock->res, &expire_64); + timr->it.real.incr = (unsigned long)expire_64; + + /* + * We do not even queue SIGEV_NONE timers! But we do put them + * in the abs list so we can do that right. + */ + if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)) + add_timer(&timr->it.real.timer); + + if (flags & TIMER_ABSTIME && clock->abs_struct) { + spin_lock(&clock->abs_struct->lock); + list_add_tail(&(timr->it.real.abs_timer_entry), + &(clock->abs_struct->list)); + spin_unlock(&clock->abs_struct->lock); + } + return 0; +} + +/* Set a POSIX.1b interval timer */ +asmlinkage long +sys_timer_settime(timer_t timer_id, int flags, + const struct itimerspec __user *new_setting, + struct itimerspec __user *old_setting) +{ + struct k_itimer *timr; + struct itimerspec new_spec, old_spec; + int error = 0; + long flag; + struct itimerspec *rtn = old_setting ? &old_spec : NULL; + + if (!new_setting) + return -EINVAL; + + if (copy_from_user(&new_spec, new_setting, sizeof (new_spec))) + return -EFAULT; + + if ((!good_timespec(&new_spec.it_interval)) || + (!good_timespec(&new_spec.it_value))) + return -EINVAL; +retry: + timr = lock_timer(timer_id, &flag); + if (!timr) + return -EINVAL; + + error = CLOCK_DISPATCH(timr->it_clock, timer_set, + (timr, flags, &new_spec, rtn)); + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { + rtn = NULL; // We already got the old time... + goto retry; + } + + if (old_setting && !error && copy_to_user(old_setting, + &old_spec, sizeof (old_spec))) + error = -EFAULT; + + return error; +} + +static inline int common_timer_del(struct k_itimer *timer) +{ + timer->it.real.incr = 0; +#ifdef CONFIG_SMP + if (timer_active(timer) && !del_timer(&timer->it.real.timer)) + /* + * It can only be active if on an other cpu. Since + * we have cleared the interval stuff above, it should + * clear once we release the spin lock. Of course once + * we do that anything could happen, including the + * complete melt down of the timer. So return with + * a "retry" exit status. + */ + return TIMER_RETRY; +#else + del_timer(&timer->it.real.timer); +#endif + remove_from_abslist(timer); + + return 0; +} + +static inline int timer_delete_hook(struct k_itimer *timer) +{ + return CLOCK_DISPATCH(timer->it_clock, timer_del, (timer)); +} + +/* Delete a POSIX.1b interval timer. */ +asmlinkage long +sys_timer_delete(timer_t timer_id) +{ + struct k_itimer *timer; + long flags; + +#ifdef CONFIG_SMP + int error; +retry_delete: +#endif + timer = lock_timer(timer_id, &flags); + if (!timer) + return -EINVAL; + +#ifdef CONFIG_SMP + error = timer_delete_hook(timer); + + if (error == TIMER_RETRY) { + unlock_timer(timer, flags); + goto retry_delete; + } +#else + timer_delete_hook(timer); +#endif + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); + spin_unlock(¤t->sighand->siglock); + /* + * This keeps any tasks waiting on the spin lock from thinking + * they got something (see the lock code above). + */ + if (timer->it_process) { + if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) + put_task_struct(timer->it_process); + timer->it_process = NULL; + } + unlock_timer(timer, flags); + release_posix_timer(timer, IT_ID_SET); + return 0; +} +/* + * return timer owned by the process, used by exit_itimers + */ +static inline void itimer_delete(struct k_itimer *timer) +{ + unsigned long flags; + +#ifdef CONFIG_SMP + int error; +retry_delete: +#endif + spin_lock_irqsave(&timer->it_lock, flags); + +#ifdef CONFIG_SMP + error = timer_delete_hook(timer); + + if (error == TIMER_RETRY) { + unlock_timer(timer, flags); + goto retry_delete; + } +#else + timer_delete_hook(timer); +#endif + list_del(&timer->list); + /* + * This keeps any tasks waiting on the spin lock from thinking + * they got something (see the lock code above). + */ + if (timer->it_process) { + if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) + put_task_struct(timer->it_process); + timer->it_process = NULL; + } + unlock_timer(timer, flags); + release_posix_timer(timer, IT_ID_SET); +} + +/* + * This is called by __exit_signal, only when there are no more + * references to the shared signal_struct. + */ +void exit_itimers(struct signal_struct *sig) +{ + struct k_itimer *tmr; + + while (!list_empty(&sig->posix_timers)) { + tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + itimer_delete(tmr); + } +} + +/* + * And now for the "clock" calls + * + * These functions are called both from timer functions (with the timer + * spin_lock_irq() held and from clock calls with no locking. They must + * use the save flags versions of locks. + */ + +/* + * We do ticks here to avoid the irq lock ( they take sooo long). + * The seqlock is great here. Since we a reader, we don't really care + * if we are interrupted since we don't take lock that will stall us or + * any other cpu. Voila, no irq lock is needed. + * + */ + +static u64 do_posix_clock_monotonic_gettime_parts( + struct timespec *tp, struct timespec *mo) +{ + u64 jiff; + unsigned int seq; + + do { + seq = read_seqbegin(&xtime_lock); + getnstimeofday(tp); + *mo = wall_to_monotonic; + jiff = jiffies_64; + + } while(read_seqretry(&xtime_lock, seq)); + + return jiff; +} + +static int do_posix_clock_monotonic_get(clockid_t clock, struct timespec *tp) +{ + struct timespec wall_to_mono; + + do_posix_clock_monotonic_gettime_parts(tp, &wall_to_mono); + + tp->tv_sec += wall_to_mono.tv_sec; + tp->tv_nsec += wall_to_mono.tv_nsec; + + if ((tp->tv_nsec - NSEC_PER_SEC) > 0) { + tp->tv_nsec -= NSEC_PER_SEC; + tp->tv_sec++; + } + return 0; +} + +int do_posix_clock_monotonic_gettime(struct timespec *tp) +{ + return do_posix_clock_monotonic_get(CLOCK_MONOTONIC, tp); +} + +int do_posix_clock_nosettime(clockid_t clockid, struct timespec *tp) +{ + return -EINVAL; +} +EXPORT_SYMBOL_GPL(do_posix_clock_nosettime); + +int do_posix_clock_notimer_create(struct k_itimer *timer) +{ + return -EINVAL; +} +EXPORT_SYMBOL_GPL(do_posix_clock_notimer_create); + +int do_posix_clock_nonanosleep(clockid_t clock, int flags, struct timespec *t) +{ +#ifndef ENOTSUP + return -EOPNOTSUPP; /* aka ENOTSUP in userland for POSIX */ +#else /* parisc does define it separately. */ + return -ENOTSUP; +#endif +} +EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep); + +asmlinkage long +sys_clock_settime(clockid_t which_clock, const struct timespec __user *tp) +{ + struct timespec new_tp; + + if (invalid_clockid(which_clock)) + return -EINVAL; + if (copy_from_user(&new_tp, tp, sizeof (*tp))) + return -EFAULT; + + return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp)); +} + +asmlinkage long +sys_clock_gettime(clockid_t which_clock, struct timespec __user *tp) +{ + struct timespec kernel_tp; + int error; + + if (invalid_clockid(which_clock)) + return -EINVAL; + error = CLOCK_DISPATCH(which_clock, clock_get, + (which_clock, &kernel_tp)); + if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp))) + error = -EFAULT; + + return error; + +} + +asmlinkage long +sys_clock_getres(clockid_t which_clock, struct timespec __user *tp) +{ + struct timespec rtn_tp; + int error; + + if (invalid_clockid(which_clock)) + return -EINVAL; + + error = CLOCK_DISPATCH(which_clock, clock_getres, + (which_clock, &rtn_tp)); + + if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp))) { + error = -EFAULT; + } + + return error; +} + +static void nanosleep_wake_up(unsigned long __data) +{ + struct task_struct *p = (struct task_struct *) __data; + + wake_up_process(p); +} + +/* + * The standard says that an absolute nanosleep call MUST wake up at + * the requested time in spite of clock settings. Here is what we do: + * For each nanosleep call that needs it (only absolute and not on + * CLOCK_MONOTONIC* (as it can not be set)) we thread a little structure + * into the "nanosleep_abs_list". All we need is the task_struct pointer. + * When ever the clock is set we just wake up all those tasks. The rest + * is done by the while loop in clock_nanosleep(). + * + * On locking, clock_was_set() is called from update_wall_clock which + * holds (or has held for it) a write_lock_irq( xtime_lock) and is + * called from the timer bh code. Thus we need the irq save locks. + * + * Also, on the call from update_wall_clock, that is done as part of a + * softirq thing. We don't want to delay the system that much (possibly + * long list of timers to fix), so we defer that work to keventd. + */ + +static DECLARE_WAIT_QUEUE_HEAD(nanosleep_abs_wqueue); +static DECLARE_WORK(clock_was_set_work, (void(*)(void*))clock_was_set, NULL); + +static DECLARE_MUTEX(clock_was_set_lock); + +void clock_was_set(void) +{ + struct k_itimer *timr; + struct timespec new_wall_to; + LIST_HEAD(cws_list); + unsigned long seq; + + + if (unlikely(in_interrupt())) { + schedule_work(&clock_was_set_work); + return; + } + wake_up_all(&nanosleep_abs_wqueue); + + /* + * Check if there exist TIMER_ABSTIME timers to correct. + * + * Notes on locking: This code is run in task context with irq + * on. We CAN be interrupted! All other usage of the abs list + * lock is under the timer lock which holds the irq lock as + * well. We REALLY don't want to scan the whole list with the + * interrupt system off, AND we would like a sequence lock on + * this code as well. Since we assume that the clock will not + * be set often, it seems ok to take and release the irq lock + * for each timer. In fact add_timer will do this, so this is + * not an issue. So we know when we are done, we will move the + * whole list to a new location. Then as we process each entry, + * we will move it to the actual list again. This way, when our + * copy is empty, we are done. We are not all that concerned + * about preemption so we will use a semaphore lock to protect + * aginst reentry. This way we will not stall another + * processor. It is possible that this may delay some timers + * that should have expired, given the new clock, but even this + * will be minimal as we will always update to the current time, + * even if it was set by a task that is waiting for entry to + * this code. Timers that expire too early will be caught by + * the expire code and restarted. + + * Absolute timers that repeat are left in the abs list while + * waiting for the task to pick up the signal. This means we + * may find timers that are not in the "add_timer" list, but are + * in the abs list. We do the same thing for these, save + * putting them back in the "add_timer" list. (Note, these are + * left in the abs list mainly to indicate that they are + * ABSOLUTE timers, a fact that is used by the re-arm code, and + * for which we have no other flag.) + + */ + + down(&clock_was_set_lock); + spin_lock_irq(&abs_list.lock); + list_splice_init(&abs_list.list, &cws_list); + spin_unlock_irq(&abs_list.lock); + do { + do { + seq = read_seqbegin(&xtime_lock); + new_wall_to = wall_to_monotonic; + } while (read_seqretry(&xtime_lock, seq)); + + spin_lock_irq(&abs_list.lock); + if (list_empty(&cws_list)) { + spin_unlock_irq(&abs_list.lock); + break; + } + timr = list_entry(cws_list.next, struct k_itimer, + it.real.abs_timer_entry); + + list_del_init(&timr->it.real.abs_timer_entry); + if (add_clockset_delta(timr, &new_wall_to) && + del_timer(&timr->it.real.timer)) /* timer run yet? */ + add_timer(&timr->it.real.timer); + list_add(&timr->it.real.abs_timer_entry, &abs_list.list); + spin_unlock_irq(&abs_list.lock); + } while (1); + + up(&clock_was_set_lock); +} + +long clock_nanosleep_restart(struct restart_block *restart_block); + +asmlinkage long +sys_clock_nanosleep(clockid_t which_clock, int flags, + const struct timespec __user *rqtp, + struct timespec __user *rmtp) +{ + struct timespec t; + struct restart_block *restart_block = + &(current_thread_info()->restart_block); + int ret; + + if (invalid_clockid(which_clock)) + return -EINVAL; + + if (copy_from_user(&t, rqtp, sizeof (struct timespec))) + return -EFAULT; + + if ((unsigned) t.tv_nsec >= NSEC_PER_SEC || t.tv_sec < 0) + return -EINVAL; + + /* + * Do this here as nsleep function does not have the real address. + */ + restart_block->arg1 = (unsigned long)rmtp; + + ret = CLOCK_DISPATCH(which_clock, nsleep, (which_clock, flags, &t)); + + if ((ret == -ERESTART_RESTARTBLOCK) && rmtp && + copy_to_user(rmtp, &t, sizeof (t))) + return -EFAULT; + return ret; +} + + +static int common_nsleep(clockid_t which_clock, + int flags, struct timespec *tsave) +{ + struct timespec t, dum; + struct timer_list new_timer; + DECLARE_WAITQUEUE(abs_wqueue, current); + u64 rq_time = (u64)0; + s64 left; + int abs; + struct restart_block *restart_block = + ¤t_thread_info()->restart_block; + + abs_wqueue.flags = 0; + init_timer(&new_timer); + new_timer.expires = 0; + new_timer.data = (unsigned long) current; + new_timer.function = nanosleep_wake_up; + abs = flags & TIMER_ABSTIME; + + if (restart_block->fn == clock_nanosleep_restart) { + /* + * Interrupted by a non-delivered signal, pick up remaining + * time and continue. Remaining time is in arg2 & 3. + */ + restart_block->fn = do_no_restart_syscall; + + rq_time = restart_block->arg3; + rq_time = (rq_time << 32) + restart_block->arg2; + if (!rq_time) + return -EINTR; + left = rq_time - get_jiffies_64(); + if (left <= (s64)0) + return 0; /* Already passed */ + } + + if (abs && (posix_clocks[which_clock].clock_get != + posix_clocks[CLOCK_MONOTONIC].clock_get)) + add_wait_queue(&nanosleep_abs_wqueue, &abs_wqueue); + + do { + t = *tsave; + if (abs || !rq_time) { + adjust_abs_time(&posix_clocks[which_clock], &t, abs, + &rq_time, &dum); + } + + left = rq_time - get_jiffies_64(); + if (left >= (s64)MAX_JIFFY_OFFSET) + left = (s64)MAX_JIFFY_OFFSET; + if (left < (s64)0) + break; + + new_timer.expires = jiffies + left; + __set_current_state(TASK_INTERRUPTIBLE); + add_timer(&new_timer); + + schedule(); + + del_timer_sync(&new_timer); + left = rq_time - get_jiffies_64(); + } while (left > (s64)0 && !test_thread_flag(TIF_SIGPENDING)); + + if (abs_wqueue.task_list.next) + finish_wait(&nanosleep_abs_wqueue, &abs_wqueue); + + if (left > (s64)0) { + + /* + * Always restart abs calls from scratch to pick up any + * clock shifting that happened while we are away. + */ + if (abs) + return -ERESTARTNOHAND; + + left *= TICK_NSEC; + tsave->tv_sec = div_long_long_rem(left, + NSEC_PER_SEC, + &tsave->tv_nsec); + /* + * Restart works by saving the time remaing in + * arg2 & 3 (it is 64-bits of jiffies). The other + * info we need is the clock_id (saved in arg0). + * The sys_call interface needs the users + * timespec return address which _it_ saves in arg1. + * Since we have cast the nanosleep call to a clock_nanosleep + * both can be restarted with the same code. + */ + restart_block->fn = clock_nanosleep_restart; + restart_block->arg0 = which_clock; + /* + * Caller sets arg1 + */ + restart_block->arg2 = rq_time & 0xffffffffLL; + restart_block->arg3 = rq_time >> 32; + + return -ERESTART_RESTARTBLOCK; + } + + return 0; +} +/* + * This will restart clock_nanosleep. + */ +long +clock_nanosleep_restart(struct restart_block *restart_block) +{ + struct timespec t; + int ret = common_nsleep(restart_block->arg0, 0, &t); + + if ((ret == -ERESTART_RESTARTBLOCK) && restart_block->arg1 && + copy_to_user((struct timespec __user *)(restart_block->arg1), &t, + sizeof (t))) + return -EFAULT; + return ret; +} diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig new file mode 100644 index 000000000000..696387ffe49c --- /dev/null +++ b/kernel/power/Kconfig @@ -0,0 +1,74 @@ +config PM + bool "Power Management support" + ---help--- + "Power Management" means that parts of your computer are shut + off or put into a power conserving "sleep" mode if they are not + being used. There are two competing standards for doing this: APM + and ACPI. If you want to use either one, say Y here and then also + to the requisite support below. + + Power Management is most important for battery powered laptop + computers; if you have a laptop, check out the Linux Laptop home + page on the WWW at or + Tuxmobil - Linux on Mobile Computers at + and the Battery Powered Linux mini-HOWTO, available from + . + + Note that, even if you say N here, Linux on the x86 architecture + will issue the hlt instruction if nothing is to be done, thereby + sending the processor to sleep and saving power. + +config PM_DEBUG + bool "Power Management Debug Support" + depends on PM + ---help--- + This option enables verbose debugging support in the Power Management + code. This is helpful when debugging and reporting various PM bugs, + like suspend support. + +config SOFTWARE_SUSPEND + bool "Software Suspend (EXPERIMENTAL)" + depends on EXPERIMENTAL && PM && SWAP + ---help--- + Enable the possibility of suspending the machine. + It doesn't need APM. + You may suspend your machine by 'swsusp' or 'shutdown -z