X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=fs%2Fproc%2Fbase.c;h=21510c9aa89cb51688581c982547c967539c0e90;hb=6f4e643353aea52d80f33960bd88954a7c074f0f;hp=46ea5d56e1bb9bd7a3cf60e163d2e9951832d50d;hpb=e030dbf91a87da7e8be3be3ca781558695bea683;p=linux-2.6 diff --git a/fs/proc/base.c b/fs/proc/base.c index 46ea5d56e1..21510c9aa8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -67,12 +67,14 @@ #include #include #include -#include +#include #include #include #include #include #include +#include +#include #include "internal.h" /* NOTE: @@ -199,22 +201,6 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ security_ptrace(current,task) == 0)) -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; - 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; - mmput(mm); - } - return res; -} - static int proc_pid_cmdline(struct task_struct *task, char * buffer) { int res = 0; @@ -279,7 +265,7 @@ 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); @@ -299,7 +285,7 @@ static int proc_pid_schedstat(struct task_struct *task, char *buffer) return sprintf(buffer, "%llu %llu %lu\n", task->sched_info.cpu_time, task->sched_info.run_delay, - task->sched_info.pcnt); + task->sched_info.pcount); } #endif @@ -365,18 +351,21 @@ struct proc_mounts { static int mounts_open(struct inode *inode, struct file *file) { struct task_struct *task = get_proc_task(inode); + struct nsproxy *nsp; struct mnt_namespace *ns = NULL; struct proc_mounts *p; int ret = -EINVAL; if (task) { - task_lock(task); - if (task->nsproxy) { - ns = task->nsproxy->mnt_ns; + rcu_read_lock(); + nsp = task_nsproxy(task); + if (nsp) { + ns = nsp->mnt_ns; if (ns) get_mnt_ns(ns); } - task_unlock(task); + rcu_read_unlock(); + put_task_struct(task); } @@ -439,16 +428,20 @@ static int mountstats_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *m = file->private_data; + struct nsproxy *nsp; struct mnt_namespace *mnt_ns = NULL; struct task_struct *task = get_proc_task(inode); if (task) { - task_lock(task); - if (task->nsproxy) - mnt_ns = task->nsproxy->mnt_ns; - if (mnt_ns) - get_mnt_ns(mnt_ns); - task_unlock(task); + rcu_read_lock(); + nsp = task_nsproxy(task); + if (nsp) { + mnt_ns = nsp->mnt_ns; + if (mnt_ns) + get_mnt_ns(mnt_ns); + } + rcu_read_unlock(); + put_task_struct(task); } @@ -487,7 +480,7 @@ static ssize_t proc_info_read(struct file * file, char __user * buf, count = PROC_BLOCK_SIZE; length = -ENOMEM; - if (!(page = __get_free_page(GFP_KERNEL))) + if (!(page = __get_free_page(GFP_TEMPORARY))) goto out; length = PROC_I(inode)->op.proc_read(task, (char*)page); @@ -527,7 +520,7 @@ static ssize_t mem_read(struct file * file, char __user * buf, goto out; ret = -ENOMEM; - page = (char *)__get_free_page(GFP_USER); + page = (char *)__get_free_page(GFP_TEMPORARY); if (!page) goto out; @@ -597,7 +590,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf, goto out; copied = -ENOMEM; - page = (char *)__get_free_page(GFP_USER); + page = (char *)__get_free_page(GFP_TEMPORARY); if (!page) goto out; @@ -653,6 +646,76 @@ static const struct file_operations proc_mem_operations = { .open = mem_open, }; +static ssize_t environ_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); + char *page; + unsigned long src = *ppos; + int ret = -ESRCH; + struct mm_struct *mm; + + if (!task) + goto out_no_task; + + if (!ptrace_may_attach(task)) + goto out; + + ret = -ENOMEM; + page = (char *)__get_free_page(GFP_TEMPORARY); + if (!page) + goto out; + + ret = 0; + + mm = get_task_mm(task); + if (!mm) + goto out_free; + + while (count > 0) { + int this_len, retval, max_len; + + this_len = mm->env_end - (mm->env_start + src); + + if (this_len <= 0) + break; + + max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; + this_len = (this_len > max_len) ? max_len : this_len; + + retval = access_process_vm(task, (mm->env_start + src), + page, this_len, 0); + + if (retval <= 0) { + ret = retval; + break; + } + + if (copy_to_user(buf, page, retval)) { + ret = -EFAULT; + break; + } + + ret += retval; + src += retval; + buf += retval; + count -= retval; + } + *ppos = src; + + mmput(mm); +out_free: + free_page((unsigned long) page); +out: + put_task_struct(task); +out_no_task: + return ret; +} + +static const struct file_operations proc_environ_operations = { + .read = environ_read, +}; + static ssize_t oom_adjust_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -783,7 +846,7 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, /* No partial writes. */ return -EINVAL; } - page = (char*)__get_free_page(GFP_USER); + page = (char*)__get_free_page(GFP_TEMPORARY); if (!page) return -ENOMEM; length = -EFAULT; @@ -812,71 +875,6 @@ 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) @@ -987,7 +985,7 @@ static const struct file_operations proc_pid_sched_operations = { .read = seq_read, .write = sched_write, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; #endif @@ -1014,7 +1012,8 @@ static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt, char __user *buffer, int buflen) { struct inode * inode; - char *tmp = (char*)__get_free_page(GFP_KERNEL), *path; + char *tmp = (char*)__get_free_page(GFP_TEMPORARY); + char *path; int len; if (!tmp) @@ -1075,7 +1074,7 @@ 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; @@ -1786,7 +1785,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, goto out; length = -ENOMEM; - page = (char*)__get_free_page(GFP_USER); + page = (char*)__get_free_page(GFP_TEMPORARY); if (!page) goto out; @@ -1846,6 +1845,91 @@ 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: */ @@ -2023,7 +2107,7 @@ static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, task), DIR("fd", S_IRUSR|S_IXUSR, fd), DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo), - INF("environ", S_IRUSR, pid_environ), + REG("environ", S_IRUSR, environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), #ifdef CONFIG_SCHED_DEBUG @@ -2037,9 +2121,6 @@ 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), @@ -2058,8 +2139,11 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_SCHEDSTATS INF("schedstat", S_IRUGO, pid_schedstat), #endif -#ifdef CONFIG_CPUSETS +#ifdef CONFIG_PROC_PID_CPUSET REG("cpuset", S_IRUGO, cpuset), +#endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, cgroup), #endif INF("oom_score", S_IRUGO, oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), @@ -2069,6 +2153,9 @@ 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 @@ -2118,27 +2205,27 @@ static const struct inode_operations proc_tgid_base_inode_operations = { * that no dcache entries will exist at process exit time it * just makes it very unlikely that any will persist. */ -void proc_flush_task(struct task_struct *task) +static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) { struct dentry *dentry, *leader, *dir; char buf[PROC_NUMBUF]; struct qstr name; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", task->pid); - dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name); + name.len = snprintf(buf, sizeof(buf), "%d", pid); + dentry = d_hash_and_lookup(mnt->mnt_root, &name); if (dentry) { shrink_dcache_parent(dentry); d_drop(dentry); dput(dentry); } - if (thread_group_leader(task)) + if (tgid == 0) goto out; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", task->tgid); - leader = d_hash_and_lookup(proc_mnt->mnt_root, &name); + name.len = snprintf(buf, sizeof(buf), "%d", tgid); + leader = d_hash_and_lookup(mnt->mnt_root, &name); if (!leader) goto out; @@ -2149,7 +2236,7 @@ void proc_flush_task(struct task_struct *task) goto out_put_leader; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", task->pid); + name.len = snprintf(buf, sizeof(buf), "%d", pid); dentry = d_hash_and_lookup(dir, &name); if (dentry) { shrink_dcache_parent(dentry); @@ -2164,6 +2251,36 @@ out: return; } +/* + * when flushing dentries from proc one need to flush them from global + * proc (proc_mnt) and from all the namespaces' procs this task was seen + * in. this call is supposed to make all this job. + */ + +void proc_flush_task(struct task_struct *task) +{ + int i, leader; + struct pid *pid, *tgid; + struct upid *upid; + + leader = thread_group_leader(task); + proc_flush_task_mnt(proc_mnt, task->pid, leader ? task->tgid : 0); + pid = task_pid(task); + if (pid->level == 0) + return; + + tgid = task_tgid(task); + for (i = 1; i <= pid->level; i++) { + upid = &pid->numbers[i]; + proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr, + leader ? 0 : tgid->numbers[i].nr); + } + + upid = &pid->numbers[pid->level]; + if (upid->nr == 1) + pid_ns_release_proc(upid->ns); +} + static struct dentry *proc_pid_instantiate(struct inode *dir, struct dentry * dentry, struct task_struct *task, const void *ptr) @@ -2234,7 +2351,7 @@ static struct task_struct *next_tgid(unsigned int tgid) rcu_read_lock(); retry: task = NULL; - pid = find_ge_pid(tgid); + pid = find_ge_pid(tgid, &init_pid_ns); if (pid) { tgid = pid->nr + 1; task = pid_task(pid, PIDTYPE_PID); @@ -2310,7 +2427,7 @@ out_no_task: static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, fd), DIR("fdinfo", S_IRUSR|S_IXUSR, fdinfo), - INF("environ", S_IRUSR, pid_environ), + REG("environ", S_IRUSR, environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), #ifdef CONFIG_SCHED_DEBUG @@ -2324,9 +2441,6 @@ 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), @@ -2344,8 +2458,11 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_SCHEDSTATS INF("schedstat", S_IRUGO, pid_schedstat), #endif -#ifdef CONFIG_CPUSETS +#ifdef CONFIG_PROC_PID_CPUSET REG("cpuset", S_IRUGO, cpuset), +#endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, cgroup), #endif INF("oom_score", S_IRUGO, oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), @@ -2563,7 +2680,7 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - tid = filp->f_version; + tid = (int)filp->f_version; filp->f_version = 0; for (task = first_tid(leader, tid, pos - 2); task; @@ -2572,7 +2689,7 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) { /* returning this tgid failed, save it as the first * pid for the next readir call */ - filp->f_version = tid; + filp->f_version = (u64)tid; put_task_struct(task); break; }