diff options
Diffstat (limited to 'fs/proc')
| -rw-r--r-- | fs/proc/array.c | 125 | ||||
| -rw-r--r-- | fs/proc/base.c | 247 | ||||
| -rw-r--r-- | fs/proc/generic.c | 52 | ||||
| -rw-r--r-- | fs/proc/inode.c | 279 | ||||
| -rw-r--r-- | fs/proc/proc_misc.c | 25 | ||||
| -rw-r--r-- | fs/proc/proc_tty.c | 15 |
6 files changed, 595 insertions, 148 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c index 74f30e0c0381..ee4814dd98f9 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -62,6 +62,8 @@ #include <linux/mman.h> #include <linux/proc_fs.h> #include <linux/ioport.h> +#include <linux/uaccess.h> +#include <linux/io.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> @@ -76,9 +78,7 @@ #include <linux/rcupdate.h> #include <linux/delayacct.h> -#include <asm/uaccess.h> #include <asm/pgtable.h> -#include <asm/io.h> #include <asm/processor.h> #include "internal.h" @@ -87,10 +87,10 @@ do { memcpy(buffer, string, strlen(string)); \ buffer += strlen(string); } while (0) -static inline char * task_name(struct task_struct *p, char * buf) +static inline char *task_name(struct task_struct *p, char *buf) { int i; - char * name; + char *name; char tcomm[sizeof(p->comm)]; get_task_comm(tcomm, p); @@ -138,7 +138,7 @@ static const char *task_state_array[] = { "X (dead)" /* 32 */ }; -static inline const char * get_task_state(struct task_struct *tsk) +static inline const char *get_task_state(struct task_struct *tsk) { unsigned int state = (tsk->state & (TASK_RUNNING | TASK_INTERRUPTIBLE | @@ -156,7 +156,7 @@ static inline const char * get_task_state(struct task_struct *tsk) return *p; } -static inline char * task_state(struct task_struct *p, char *buffer) +static inline char *task_state(struct task_struct *p, char *buffer) { struct group_info *group_info; int g; @@ -165,7 +165,6 @@ static inline char * task_state(struct task_struct *p, char *buffer) rcu_read_lock(); buffer += sprintf(buffer, "State:\t%s\n" - "SleepAVG:\t%lu%%\n" "Tgid:\t%d\n" "Pid:\t%d\n" "PPid:\t%d\n" @@ -173,9 +172,8 @@ static inline char * task_state(struct task_struct *p, char *buffer) "Uid:\t%d\t%d\t%d\t%d\n" "Gid:\t%d\t%d\t%d\t%d\n", get_task_state(p), - (p->sleep_avg/1024)*100/(1020000000/1024), - p->tgid, p->pid, - pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0, + p->tgid, p->pid, + pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0, pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0, p->uid, p->euid, p->suid, p->fsuid, p->gid, p->egid, p->sgid, p->fsgid); @@ -193,15 +191,15 @@ static inline char * task_state(struct task_struct *p, char *buffer) get_group_info(group_info); task_unlock(p); - for (g = 0; g < min(group_info->ngroups,NGROUPS_SMALL); g++) - buffer += sprintf(buffer, "%d ", GROUP_AT(group_info,g)); + for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++) + buffer += sprintf(buffer, "%d ", GROUP_AT(group_info, g)); put_group_info(group_info); buffer += sprintf(buffer, "\n"); return buffer; } -static char * render_sigset_t(const char *header, sigset_t *set, char *buffer) +static char *render_sigset_t(const char *header, sigset_t *set, char *buffer) { int i, len; @@ -241,7 +239,7 @@ static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, } } -static inline char * task_sig(struct task_struct *p, char *buffer) +static inline char *task_sig(struct task_struct *p, char *buffer) { unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; @@ -291,14 +289,23 @@ static inline char *task_cap(struct task_struct *p, char *buffer) cap_t(p->cap_effective)); } -int proc_pid_status(struct task_struct *task, char * buffer) +static inline char *task_context_switch_counts(struct task_struct *p, + char *buffer) { - char * orig = buffer; + return buffer + sprintf(buffer, "voluntary_ctxt_switches:\t%lu\n" + "nonvoluntary_ctxt_switches:\t%lu\n", + p->nvcsw, + p->nivcsw); +} + +int proc_pid_status(struct task_struct *task, char *buffer) +{ + char *orig = buffer; struct mm_struct *mm = get_task_mm(task); buffer = task_name(task, buffer); buffer = task_state(task, buffer); - + if (mm) { buffer = task_mem(mm, buffer); mmput(mm); @@ -309,10 +316,61 @@ int proc_pid_status(struct task_struct *task, char * buffer) #if defined(CONFIG_S390) buffer = task_show_regs(task, buffer); #endif + buffer = task_context_switch_counts(task, buffer); return buffer - orig; } -static int do_task_stat(struct task_struct *task, char * buffer, int whole) +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +static cputime_t task_utime(struct task_struct *p) +{ + return p->utime; +} + +static cputime_t task_stime(struct task_struct *p) +{ + return p->stime; +} +#else +static cputime_t task_utime(struct task_struct *p) +{ + clock_t utime = cputime_to_clock_t(p->utime), + total = utime + cputime_to_clock_t(p->stime); + u64 temp; + + /* + * Use CFS's precise accounting: + */ + temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + + if (total) { + temp *= utime; + do_div(temp, total); + } + utime = (clock_t)temp; + + return clock_t_to_cputime(utime); +} + +static cputime_t task_stime(struct task_struct *p) +{ + clock_t stime; + + /* + * Use CFS's precise accounting. (we subtract utime from + * the total, to make sure the total observed by userspace + * grows monotonically - apps rely on that): + */ + stime = nsec_to_clock_t(p->se.sum_exec_runtime) - + cputime_to_clock_t(task_utime(p)); + + return clock_t_to_cputime(stime); +} +#endif + +static int do_task_stat(struct task_struct *task, char *buffer, int whole) { unsigned long vsize, eip, esp, wchan = ~0UL; long priority, nice; @@ -320,7 +378,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) sigset_t sigign, sigcatch; char state; int res; - pid_t ppid = 0, pgid = -1, sid = -1; + pid_t ppid = 0, pgid = -1, sid = -1; int num_threads = 0; struct mm_struct *mm; unsigned long long start_time; @@ -370,8 +428,8 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); + utime = cputime_add(utime, task_utime(t)); + stime = cputime_add(stime, task_stime(t)); t = next_thread(t); } while (t != task); @@ -389,13 +447,13 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) } rcu_read_unlock(); - if (!whole || num_threads<2) + if (!whole || num_threads < 2) wchan = get_wchan(task); if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; - utime = task->utime; - stime = task->stime; + utime = task_utime(task); + stime = task_stime(task); } /* scale priority and nice values from timeslices to -20..20 */ @@ -405,12 +463,13 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) /* Temporary variable needed for gcc-2.96 */ /* convert timespec -> nsec*/ - start_time = (unsigned long long)task->start_time.tv_sec * NSEC_PER_SEC - + task->start_time.tv_nsec; + start_time = + (unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC + + task->real_start_time.tv_nsec; /* convert nsec -> ticks */ start_time = nsec_to_clock_t(start_time); - res = sprintf(buffer,"%d (%s) %c %d %d %d %d %d %u %lu \ + res = sprintf(buffer, "%d (%s) %c %d %d %d %d %d %u %lu \ %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \ %lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu\n", task->pid, @@ -436,7 +495,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) start_time, vsize, mm ? get_mm_rss(mm) : 0, - rsslim, + rsslim, mm ? mm->start_code : 0, mm ? mm->end_code : 0, mm ? mm->start_stack : 0, @@ -458,17 +517,17 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) task->rt_priority, task->policy, (unsigned long long)delayacct_blkio_ticks(task)); - if(mm) + if (mm) mmput(mm); return res; } -int proc_tid_stat(struct task_struct *task, char * buffer) +int proc_tid_stat(struct task_struct *task, char *buffer) { return do_task_stat(task, buffer, 0); } -int proc_tgid_stat(struct task_struct *task, char * buffer) +int proc_tgid_stat(struct task_struct *task, char *buffer) { return do_task_stat(task, buffer, 1); } @@ -477,12 +536,12 @@ int proc_pid_statm(struct task_struct *task, char *buffer) { int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0; struct mm_struct *mm = get_task_mm(task); - + if (mm) { size = task_statm(mm, &shared, &text, &data, &resident); mmput(mm); } - return sprintf(buffer,"%d %d %d %d %d %d %d\n", + return sprintf(buffer, "%d %d %d %d %d %d %d\n", size, resident, shared, text, lib, data, 0); } diff --git a/fs/proc/base.c b/fs/proc/base.c index a5fa1fdafc4e..19489b0d5554 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -67,12 +67,12 @@ #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> -#include <linux/seccomp.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> #include <linux/nsproxy.h> #include <linux/oom.h> +#include <linux/elf.h> #include "internal.h" /* NOTE: @@ -204,12 +204,17 @@ static int proc_pid_environ(struct task_struct *task, char * buffer) int res = 0; struct mm_struct *mm = get_task_mm(task); if (mm) { - unsigned int len = mm->env_end - mm->env_start; + unsigned int len; + + res = -ESRCH; + if (!ptrace_may_attach(task)) + goto out; + + len = mm->env_end - mm->env_start; if (len > PAGE_SIZE) len = PAGE_SIZE; res = access_process_vm(task, mm->env_start, buffer, len, 0); - if (!ptrace_may_attach(task)) - res = -ESRCH; +out: mmput(mm); } return res; @@ -279,7 +284,7 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer) static int proc_pid_wchan(struct task_struct *task, char *buffer) { unsigned long wchan; - char symname[KSYM_NAME_LEN+1]; + char symname[KSYM_NAME_LEN]; wchan = get_wchan(task); @@ -296,7 +301,7 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer) */ static int proc_pid_schedstat(struct task_struct *task, char *buffer) { - return sprintf(buffer, "%lu %lu %lu\n", + return sprintf(buffer, "%llu %llu %lu\n", task->sched_info.cpu_time, task->sched_info.run_delay, task->sched_info.pcnt); @@ -812,71 +817,6 @@ static const struct file_operations proc_loginuid_operations = { }; #endif -#ifdef CONFIG_SECCOMP -static ssize_t seccomp_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode); - char __buf[20]; - size_t len; - - if (!tsk) - return -ESRCH; - /* no need to print the trailing zero, so use only len */ - len = sprintf(__buf, "%u\n", tsk->seccomp.mode); - put_task_struct(tsk); - - return simple_read_from_buffer(buf, count, ppos, __buf, len); -} - -static ssize_t seccomp_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct task_struct *tsk = get_proc_task(file->f_dentry->d_inode); - char __buf[20], *end; - unsigned int seccomp_mode; - ssize_t result; - - result = -ESRCH; - if (!tsk) - goto out_no_task; - - /* can set it only once to be even more secure */ - result = -EPERM; - if (unlikely(tsk->seccomp.mode)) - goto out; - - result = -EFAULT; - memset(__buf, 0, sizeof(__buf)); - count = min(count, sizeof(__buf) - 1); - if (copy_from_user(__buf, buf, count)) - goto out; - - seccomp_mode = simple_strtoul(__buf, &end, 0); - if (*end == '\n') - end++; - result = -EINVAL; - if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) { - tsk->seccomp.mode = seccomp_mode; - set_tsk_thread_flag(tsk, TIF_SECCOMP); - } else - goto out; - result = -EIO; - if (unlikely(!(end - __buf))) - goto out; - result = end - __buf; -out: - put_task_struct(tsk); -out_no_task: - return result; -} - -static const struct file_operations proc_seccomp_operations = { - .read = seccomp_read, - .write = seccomp_write, -}; -#endif /* CONFIG_SECCOMP */ - #ifdef CONFIG_FAULT_INJECTION static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) @@ -929,6 +869,69 @@ static const struct file_operations proc_fault_inject_operations = { }; #endif +#ifdef CONFIG_SCHED_DEBUG +/* + * Print out various scheduling related per-task fields: + */ +static int sched_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + WARN_ON(!inode); + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct task_struct *p; + + WARN_ON(!inode); + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_set_task(p); + + put_task_struct(p); + + return count; +} + +static int sched_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = single_open(filp, sched_show, NULL); + if (!ret) { + struct seq_file *m = filp->private_data; + + m->private = inode; + } + return ret; +} + +static const struct file_operations proc_pid_sched_operations = { + .open = sched_open, + .read = seq_read, + .write = sched_write, + .llseek = seq_lseek, + .release = single_release, +}; + +#endif + static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; @@ -1012,7 +1015,7 @@ static int task_dumpable(struct task_struct *task) task_lock(task); mm = task->mm; if (mm) - dumpable = mm->dumpable; + dumpable = get_dumpable(mm); task_unlock(task); if(dumpable == 1) return 1; @@ -1783,6 +1786,91 @@ static const struct inode_operations proc_attr_dir_inode_operations = { #endif +#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE) +static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file->f_dentry->d_inode); + struct mm_struct *mm; + char buffer[PROC_NUMBUF]; + size_t len; + int ret; + + if (!task) + return -ESRCH; + + ret = 0; + mm = get_task_mm(task); + if (mm) { + len = snprintf(buffer, sizeof(buffer), "%08lx\n", + ((mm->flags & MMF_DUMP_FILTER_MASK) >> + MMF_DUMP_FILTER_SHIFT)); + mmput(mm); + ret = simple_read_from_buffer(buf, count, ppos, buffer, len); + } + + put_task_struct(task); + + return ret; +} + +static ssize_t proc_coredump_filter_write(struct file *file, + const char __user *buf, + size_t count, + loff_t *ppos) +{ + struct task_struct *task; + struct mm_struct *mm; + char buffer[PROC_NUMBUF], *end; + unsigned int val; + int ret; + int i; + unsigned long mask; + + ret = -EFAULT; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + goto out_no_task; + + ret = -EINVAL; + val = (unsigned int)simple_strtoul(buffer, &end, 0); + if (*end == '\n') + end++; + if (end - buffer == 0) + goto out_no_task; + + ret = -ESRCH; + task = get_proc_task(file->f_dentry->d_inode); + if (!task) + goto out_no_task; + + ret = end - buffer; + mm = get_task_mm(task); + if (!mm) + goto out_no_mm; + + for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { + if (val & mask) + set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); + else + clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); + } + + mmput(mm); + out_no_mm: + put_task_struct(task); + out_no_task: + return ret; +} + +static const struct file_operations proc_coredump_filter_operations = { + .read = proc_coredump_filter_read, + .write = proc_coredump_filter_write, +}; +#endif + /* * /proc/self: */ @@ -1963,6 +2051,9 @@ static const struct pid_entry tgid_base_stuff[] = { INF("environ", S_IRUSR, pid_environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, pid_sched), +#endif INF("cmdline", S_IRUGO, pid_cmdline), INF("stat", S_IRUGO, tgid_stat), INF("statm", S_IRUGO, pid_statm), @@ -1971,9 +2062,6 @@ static const struct pid_entry tgid_base_stuff[] = { REG("numa_maps", S_IRUGO, numa_maps), #endif REG("mem", S_IRUSR|S_IWUSR, mem), -#ifdef CONFIG_SECCOMP - REG("seccomp", S_IRUSR|S_IWUSR, seccomp), -#endif LNK("cwd", cwd), LNK("root", root), LNK("exe", exe), @@ -2003,6 +2091,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject), #endif +#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE) + REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter), +#endif #ifdef CONFIG_TASK_IO_ACCOUNTING INF("io", S_IRUGO, pid_io_accounting), #endif @@ -2247,6 +2338,9 @@ static const struct pid_entry tid_base_stuff[] = { INF("environ", S_IRUSR, pid_environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, pid_sched), +#endif INF("cmdline", S_IRUGO, pid_cmdline), INF("stat", S_IRUGO, tid_stat), INF("statm", S_IRUGO, pid_statm), @@ -2255,9 +2349,6 @@ static const struct pid_entry tid_base_stuff[] = { REG("numa_maps", S_IRUGO, numa_maps), #endif REG("mem", S_IRUSR|S_IWUSR, mem), -#ifdef CONFIG_SECCOMP - REG("seccomp", S_IRUSR|S_IWUSR, seccomp), -#endif LNK("cwd", cwd), LNK("root", root), LNK("exe", exe), diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8a40e15f5ecb..b5e7155d30d8 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -20,6 +20,7 @@ #include <linux/namei.h> #include <linux/bitops.h> #include <linux/spinlock.h> +#include <linux/completion.h> #include <asm/uaccess.h> #include "internal.h" @@ -529,12 +530,6 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp return -EAGAIN; dp->low_ino = i; - spin_lock(&proc_subdir_lock); - dp->next = dir->subdir; - dp->parent = dir; - dir->subdir = dp; - spin_unlock(&proc_subdir_lock); - if (S_ISDIR(dp->mode)) { if (dp->proc_iops == NULL) { dp->proc_fops = &proc_dir_operations; @@ -550,6 +545,13 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp if (dp->proc_iops == NULL) dp->proc_iops = &proc_file_inode_operations; } + + spin_lock(&proc_subdir_lock); + dp->next = dir->subdir; + dp->parent = dir; + dir->subdir = dp; + spin_unlock(&proc_subdir_lock); + return 0; } @@ -613,6 +615,9 @@ static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent, ent->namelen = len; ent->mode = mode; ent->nlink = nlink; + ent->pde_users = 0; + spin_lock_init(&ent->pde_unload_lock); + ent->pde_unload_completion = NULL; out: return ent; } @@ -649,9 +654,6 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode, ent = proc_create(&parent, name, S_IFDIR | mode, 2); if (ent) { - ent->proc_fops = &proc_dir_operations; - ent->proc_iops = &proc_dir_inode_operations; - if (proc_register(parent, ent) < 0) { kfree(ent); ent = NULL; @@ -686,10 +688,6 @@ struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode, ent = proc_create(&parent,name,mode,nlink); if (ent) { - if (S_ISDIR(mode)) { - ent->proc_fops = &proc_dir_operations; - ent->proc_iops = &proc_dir_inode_operations; - } if (proc_register(parent, ent) < 0) { kfree(ent); ent = NULL; @@ -734,9 +732,35 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) de = *p; *p = de->next; de->next = NULL; + + spin_lock(&de->pde_unload_lock); + /* + * Stop accepting new callers into module. If you're + * dynamically allocating ->proc_fops, save a pointer somewhere. + */ + de->proc_fops = NULL; + /* Wait until all existing callers into module are done. */ + if (de->pde_users > 0) { + DECLARE_COMPLETION_ONSTACK(c); + + if (!de->pde_unload_completion) + de->pde_unload_completion = &c; + + spin_unlock(&de->pde_unload_lock); + spin_unlock(&proc_subdir_lock); + + wait_for_completion(de->pde_unload_completion); + + spin_lock(&proc_subdir_lock); + goto continue_removing; + } + spin_unlock(&de->pde_unload_lock); + +continue_removing: if (S_ISDIR(de->mode)) parent->nlink--; - proc_kill_inodes(de); + if (!S_ISREG(de->mode)) + proc_kill_inodes(de); de->nlink = 0; WARN_ON(de->subdir); if (!atomic_read(&de->count)) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index d5ce65c68d7b..0e4d37c93eea 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -10,6 +10,8 @@ #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> +#include <linux/completion.h> +#include <linux/poll.h> #include <linux/file.h> #include <linux/limits.h> #include <linux/init.h> @@ -111,14 +113,14 @@ static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flag inode_init_once(&ei->vfs_inode); } - + int __init proc_init_inodecache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD), - init_once, NULL); + init_once); if (proc_inode_cachep == NULL) return -ENOMEM; return 0; @@ -140,6 +142,264 @@ static const struct super_operations proc_sops = { .remount_fs = proc_remount, }; +static void pde_users_dec(struct proc_dir_entry *pde) +{ + spin_lock(&pde->pde_unload_lock); + pde->pde_users--; + if (pde->pde_unload_completion && pde->pde_users == 0) + complete(pde->pde_unload_completion); + spin_unlock(&pde->pde_unload_lock); +} + +static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + loff_t rv = -EINVAL; + loff_t (*llseek)(struct file *, loff_t, int); + + spin_lock(&pde->pde_unload_lock); + /* + * remove_proc_entry() is going to delete PDE (as part of module + * cleanup sequence). No new callers into module allowed. + */ + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + /* + * Bump refcount so that remove_proc_entry will wail for ->llseek to + * complete. + */ + pde->pde_users++; + /* + * Save function pointer under lock, to protect against ->proc_fops + * NULL'ifying right after ->pde_unload_lock is dropped. + */ + llseek = pde->proc_fops->llseek; + spin_unlock(&pde->pde_unload_lock); + + if (!llseek) + llseek = default_llseek; + rv = llseek(file, offset, whence); + + pde_users_dec(pde); + return rv; +} + +static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + ssize_t rv = -EIO; + ssize_t (*read)(struct file *, char __user *, size_t, loff_t *); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + read = pde->proc_fops->read; + spin_unlock(&pde->pde_unload_lock); + + if (read) + rv = read(file, buf, count, ppos); + + pde_users_dec(pde); + return rv; +} + +static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + ssize_t rv = -EIO; + ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + write = pde->proc_fops->write; + spin_unlock(&pde->pde_unload_lock); + + if (write) + rv = write(file, buf, count, ppos); + + pde_users_dec(pde); + return rv; +} + +static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + unsigned int rv = DEFAULT_POLLMASK; + unsigned int (*poll)(struct file *, struct poll_table_struct *); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + poll = pde->proc_fops->poll; + spin_unlock(&pde->pde_unload_lock); + + if (poll) + rv = poll(file, pts); + + pde_users_dec(pde); + return rv; +} + +static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + long rv = -ENOTTY; + long (*unlocked_ioctl)(struct file *, unsigned int, unsigned long); + int (*ioctl)(struct inode *, struct file *, unsigned int, unsigned long); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + unlocked_ioctl = pde->proc_fops->unlocked_ioctl; + ioctl = pde->proc_fops->ioctl; + spin_unlock(&pde->pde_unload_lock); + + if (unlocked_ioctl) { + rv = unlocked_ioctl(file, cmd, arg); + if (rv == -ENOIOCTLCMD) + rv = -EINVAL; + } else if (ioctl) { + lock_kernel(); + rv = ioctl(file->f_path.dentry->d_inode, file, cmd, arg); + unlock_kernel(); + } + + pde_users_dec(pde); + return rv; +} + +#ifdef CONFIG_COMPAT +static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + long rv = -ENOTTY; + long (*compat_ioctl)(struct file *, unsigned int, unsigned long); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + compat_ioctl = pde->proc_fops->compat_ioctl; + spin_unlock(&pde->pde_unload_lock); + + if (compat_ioctl) + rv = compat_ioctl(file, cmd, arg); + + pde_users_dec(pde); + return rv; +} +#endif + +static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + int rv = -EIO; + int (*mmap)(struct file *, struct vm_area_struct *); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + mmap = pde->proc_fops->mmap; + spin_unlock(&pde->pde_unload_lock); + + if (mmap) + rv = mmap(file, vma); + + pde_users_dec(pde); + return rv; +} + +static int proc_reg_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + int rv = 0; + int (*open)(struct inode *, struct file *); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + open = pde->proc_fops->open; + spin_unlock(&pde->pde_unload_lock); + + if (open) + rv = open(inode, file); + + pde_users_dec(pde); + return rv; +} + +static int proc_reg_release(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + int rv = 0; + int (*release)(struct inode *, struct file *); + + spin_lock(&pde->pde_unload_lock); + if (!pde->proc_fops) { + spin_unlock(&pde->pde_unload_lock); + return rv; + } + pde->pde_users++; + release = pde->proc_fops->release; + spin_unlock(&pde->pde_unload_lock); + + if (release) + rv = release(inode, file); + + pde_users_dec(pde); + return rv; +} + +static const struct file_operations proc_reg_file_ops = { + .llseek = proc_reg_llseek, + .read = proc_reg_read, + .write = proc_reg_write, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = proc_reg_compat_ioctl, +#endif + .mmap = proc_reg_mmap, + .open = proc_reg_open, + .release = proc_reg_release, +}; + +#ifdef CONFIG_COMPAT +static const struct file_operations proc_reg_file_ops_no_compat = { + .llseek = proc_reg_llseek, + .read = proc_reg_read, + .write = proc_reg_write, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, + .mmap = proc_reg_mmap, + .open = proc_reg_open, + .release = proc_reg_release, +}; +#endif + struct inode *proc_get_inode(struct super_block *sb, unsigned int ino, struct proc_dir_entry *de) { @@ -166,8 +426,19 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino, inode->i_nlink = de->nlink; if (de->proc_iops) inode->i_op = de->proc_iops; - if (de->proc_fops) - inode->i_fop = de->proc_fops; + if (de->proc_fops) { + if (S_ISREG(inode->i_mode)) { +#ifdef CONFIG_COMPAT + if (!de->proc_fops->compat_ioctl) + inode->i_fop = + &proc_reg_file_ops_no_compat; + else +#endif + inode->i_fop = &proc_reg_file_ops; + } + else + inode->i_fop = de->proc_fops; + } } return inode; diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 5fd49e47f83a..bee251cb87c8 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -105,6 +105,7 @@ static int uptime_read_proc(char *page, char **start, off_t off, cputime_t idletime = cputime_add(init_task.utime, init_task.stime); do_posix_clock_monotonic_gettime(&uptime); + monotonic_to_bootbased(&uptime); cputime_to_timespec(idletime, &idle); len = sprintf(page,"%lu.%02lu %lu.%02lu\n", (unsigned long) uptime.tv_sec, @@ -443,12 +444,17 @@ static int show_stat(struct seq_file *p, void *v) unsigned long jif; cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; u64 sum = 0; + struct timespec boottime; + unsigned int *per_irq_sum; + + per_irq_sum = kzalloc(sizeof(unsigned int)*NR_IRQS, GFP_KERNEL); + if (!per_irq_sum) + return -ENOMEM; user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; - jif = - wall_to_monotonic.tv_sec; - if (wall_to_monotonic.tv_nsec) - --jif; + getboottime(&boottime); + jif = boottime.tv_sec; for_each_possible_cpu(i) { int j; @@ -461,8 +467,11 @@ static int show_stat(struct seq_file *p, void *v) irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); - for (j = 0 ; j < NR_IRQS ; j++) - sum += kstat_cpu(i).irqs[j]; + for (j = 0; j < NR_IRQS; j++) { + unsigned int temp = kstat_cpu(i).irqs[j]; + sum += temp; + per_irq_sum[j] += temp; + } } seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu\n", @@ -498,9 +507,10 @@ static int show_stat(struct seq_file *p, void *v) } seq_printf(p, "intr %llu", (unsigned long long)sum); -#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) && !defined(CONFIG_IA64) +#ifndef CONFIG_SMP + /* Touches too many cache lines on SMP setups */ for (i = 0; i < NR_IRQS; i++) - seq_printf(p, " %u", kstat_irqs(i)); + seq_printf(p, " %u", per_irq_sum[i]); #endif seq_printf(p, @@ -515,6 +525,7 @@ static int show_stat(struct seq_file *p, void *v) nr_running(), nr_iowait()); + kfree(per_irq_sum); return 0; } diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index b3a473b0a191..22846225acfa 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -69,7 +69,7 @@ static void show_tty_range(struct seq_file *m, struct tty_driver *p, static int show_tty_driver(struct seq_file *m, void *v) { - struct tty_driver *p = v; + struct tty_driver *p = list_entry(v, struct tty_driver, tty_drivers); dev_t from = MKDEV(p->major, p->minor_start); dev_t to = from + p->num; @@ -106,22 +106,13 @@ static int show_tty_driver(struct seq_file *m, void *v) /* iterator */ static void *t_start(struct seq_file *m, loff_t *pos) { - struct list_head *p; - loff_t l = *pos; - mutex_lock(&tty_mutex); - list_for_each(p, &tty_drivers) - if (!l--) - return list_entry(p, struct tty_driver, tty_drivers); - return NULL; + return seq_list_start(&tty_drivers, *pos); } static void *t_next(struct seq_file *m, void *v, loff_t *pos) { - struct list_head *p = ((struct tty_driver *)v)->tty_drivers.next; - (*pos)++; - return p==&tty_drivers ? NULL : - list_entry(p, struct tty_driver, tty_drivers); + return seq_list_next(v, &tty_drivers, pos); } static void t_stop(struct seq_file *m, void *v) |