diff options
Diffstat (limited to 'fs/proc/base.c')
-rw-r--r-- | fs/proc/base.c | 294 |
1 files changed, 226 insertions, 68 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c index ace151fa4878..a170450aadb1 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -11,6 +11,40 @@ * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. + * + * + * Changelog: + * 17-Jan-2005 + * Allan Bezerra + * Bruna Moreira <bruna.moreira@indt.org.br> + * Edjard Mota <edjard.mota@indt.org.br> + * Ilias Biris <ilias.biris@indt.org.br> + * Mauricio Lin <mauricio.lin@indt.org.br> + * + * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT + * + * A new process specific entry (smaps) included in /proc. It shows the + * size of rss for each memory area. The maps entry lacks information + * about physical memory size (rss) for each mapped file, i.e., + * rss information for executables and library files. + * This additional information is useful for any tools that need to know + * about physical memory consumption for a process specific library. + * + * Changelog: + * 21-Feb-2005 + * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT + * Pud inclusion in the page table walking. + * + * ChangeLog: + * 10-Mar-2005 + * 10LE Instituto Nokia de Tecnologia - INdT: + * A better way to walks through the page table as suggested by Hugh Dickins. + * + * Simo Piiroinen <simo.piiroinen@nokia.com>: + * Smaps information related to shared, private, clean and dirty pages. + * + * Paul Mundt <paul.mundt@nokia.com>: + * Overall revision about smaps. */ #include <asm/uaccess.h> @@ -28,6 +62,7 @@ #include <linux/namespace.h> #include <linux/mm.h> #include <linux/smp_lock.h> +#include <linux/rcupdate.h> #include <linux/kallsyms.h> #include <linux/mount.h> #include <linux/security.h> @@ -65,8 +100,12 @@ enum pid_directory_inos { PROC_TGID_STAT, PROC_TGID_STATM, PROC_TGID_MAPS, + PROC_TGID_NUMA_MAPS, PROC_TGID_MOUNTS, PROC_TGID_WCHAN, +#ifdef CONFIG_MMU + PROC_TGID_SMAPS, +#endif #ifdef CONFIG_SCHEDSTATS PROC_TGID_SCHEDSTAT, #endif @@ -83,7 +122,6 @@ enum pid_directory_inos { #ifdef CONFIG_AUDITSYSCALL PROC_TGID_LOGINUID, #endif - PROC_TGID_FD_DIR, PROC_TGID_OOM_SCORE, PROC_TGID_OOM_ADJUST, PROC_TID_INO, @@ -102,8 +140,12 @@ enum pid_directory_inos { PROC_TID_STAT, PROC_TID_STATM, PROC_TID_MAPS, + PROC_TID_NUMA_MAPS, PROC_TID_MOUNTS, PROC_TID_WCHAN, +#ifdef CONFIG_MMU + PROC_TID_SMAPS, +#endif #ifdef CONFIG_SCHEDSTATS PROC_TID_SCHEDSTAT, #endif @@ -120,9 +162,11 @@ enum pid_directory_inos { #ifdef CONFIG_AUDITSYSCALL PROC_TID_LOGINUID, #endif - PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ PROC_TID_OOM_SCORE, PROC_TID_OOM_ADJUST, + + /* Add new entries before this */ + PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ }; struct pid_entry { @@ -144,6 +188,9 @@ static struct pid_entry tgid_base_stuff[] = { E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO), E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO), E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO), +#ifdef CONFIG_NUMA + E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), +#endif E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), #ifdef CONFIG_SECCOMP E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), @@ -152,6 +199,9 @@ static struct pid_entry tgid_base_stuff[] = { E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), +#ifdef CONFIG_MMU + E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), +#endif #ifdef CONFIG_SECURITY E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), #endif @@ -180,6 +230,9 @@ static struct pid_entry tid_base_stuff[] = { E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO), E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO), E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO), +#ifdef CONFIG_NUMA + E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), +#endif E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), #ifdef CONFIG_SECCOMP E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), @@ -188,6 +241,9 @@ static struct pid_entry tid_base_stuff[] = { E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), +#ifdef CONFIG_MMU + E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), +#endif #ifdef CONFIG_SECURITY E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), #endif @@ -236,30 +292,36 @@ static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsm files = get_files_struct(task); if (files) { - spin_lock(&files->file_lock); + rcu_read_lock(); file = fcheck_files(files, fd); if (file) { *mnt = mntget(file->f_vfsmnt); *dentry = dget(file->f_dentry); - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); return 0; } - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); } return -ENOENT; } -static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +static struct fs_struct *get_fs_struct(struct task_struct *task) { struct fs_struct *fs; - int result = -ENOENT; - task_lock(proc_task(inode)); - fs = proc_task(inode)->fs; + task_lock(task); + fs = task->fs; if(fs) atomic_inc(&fs->count); - task_unlock(proc_task(inode)); + task_unlock(task); + return fs; +} + +static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +{ + struct fs_struct *fs = get_fs_struct(proc_task(inode)); + int result = -ENOENT; if (fs) { read_lock(&fs->lock); *mnt = mntget(fs->pwdmnt); @@ -273,13 +335,55 @@ static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfs static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) { + struct fs_struct *fs = get_fs_struct(proc_task(inode)); + int result = -ENOENT; + if (fs) { + read_lock(&fs->lock); + *mnt = mntget(fs->rootmnt); + *dentry = dget(fs->root); + read_unlock(&fs->lock); + result = 0; + put_fs_struct(fs); + } + return result; +} + + +/* Same as proc_root_link, but this addionally tries to get fs from other + * threads in the group */ +static int proc_task_root_link(struct inode *inode, struct dentry **dentry, + struct vfsmount **mnt) +{ struct fs_struct *fs; int result = -ENOENT; - task_lock(proc_task(inode)); - fs = proc_task(inode)->fs; - if(fs) + struct task_struct *leader = proc_task(inode); + + task_lock(leader); + fs = leader->fs; + if (fs) { atomic_inc(&fs->count); - task_unlock(proc_task(inode)); + task_unlock(leader); + } else { + /* Try to get fs from other threads */ + task_unlock(leader); + read_lock(&tasklist_lock); + if (pid_alive(leader)) { + struct task_struct *task = leader; + + while ((task = next_thread(task)) != leader) { + task_lock(task); + fs = task->fs; + if (fs) { + atomic_inc(&fs->count); + task_unlock(task); + break; + } + task_unlock(task); + } + } + read_unlock(&tasklist_lock); + } + if (fs) { read_lock(&fs->lock); *mnt = mntget(fs->rootmnt); @@ -291,6 +395,7 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf return result; } + #define MAY_PTRACE(task) \ (task == current || \ (task->parent == current && \ @@ -298,33 +403,6 @@ 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 may_ptrace_attach(struct task_struct *task) -{ - int retval = 0; - - task_lock(task); - - if (!task->mm) - goto out; - if (((current->uid != task->euid) || - (current->uid != task->suid) || - (current->uid != task->uid) || - (current->gid != task->egid) || - (current->gid != task->sgid) || - (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) - goto out; - rmb(); - if (task->mm->dumpable != 1 && !capable(CAP_SYS_PTRACE)) - goto out; - if (security_ptrace(current, task)) - goto out; - - retval = 1; -out: - task_unlock(task); - return retval; -} - static int proc_pid_environ(struct task_struct *task, char * buffer) { int res = 0; @@ -334,7 +412,7 @@ static int proc_pid_environ(struct task_struct *task, char * buffer) if (len > PAGE_SIZE) len = PAGE_SIZE; res = access_process_vm(task, mm->env_start, buffer, len, 0); - if (!may_ptrace_attach(task)) + if (!ptrace_may_attach(task)) res = -ESRCH; mmput(mm); } @@ -449,14 +527,14 @@ static int proc_oom_score(struct task_struct *task, char *buffer) /* permission checks */ -static int proc_check_root(struct inode *inode) +/* If the process being read is separated by chroot from the reading process, + * don't let the reader access the threads. + */ +static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt) { - struct dentry *de, *base, *root; - struct vfsmount *our_vfsmnt, *vfsmnt, *mnt; + struct dentry *de, *base; + struct vfsmount *our_vfsmnt, *mnt; int res = 0; - - if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */ - return -ENOENT; read_lock(¤t->fs->lock); our_vfsmnt = mntget(current->fs->rootmnt); base = dget(current->fs->root); @@ -489,6 +567,16 @@ out: goto exit; } +static int proc_check_root(struct inode *inode) +{ + struct dentry *root; + struct vfsmount *vfsmnt; + + if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */ + return -ENOENT; + return proc_check_chroot(root, vfsmnt); +} + static int proc_permission(struct inode *inode, int mask, struct nameidata *nd) { if (generic_permission(inode, mask, NULL) != 0) @@ -496,6 +584,20 @@ static int proc_permission(struct inode *inode, int mask, struct nameidata *nd) return proc_check_root(inode); } +static int proc_task_permission(struct inode *inode, int mask, struct nameidata *nd) +{ + struct dentry *root; + struct vfsmount *vfsmnt; + + if (generic_permission(inode, mask, NULL) != 0) + return -EACCES; + + if (proc_task_root_link(inode, &root, &vfsmnt)) + return -ENOENT; + + return proc_check_chroot(root, vfsmnt); +} + extern struct seq_operations proc_pid_maps_op; static int maps_open(struct inode *inode, struct file *file) { @@ -515,6 +617,48 @@ static struct file_operations proc_maps_operations = { .release = seq_release, }; +#ifdef CONFIG_NUMA +extern struct seq_operations proc_pid_numa_maps_op; +static int numa_maps_open(struct inode *inode, struct file *file) +{ + struct task_struct *task = proc_task(inode); + int ret = seq_open(file, &proc_pid_numa_maps_op); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = task; + } + return ret; +} + +static struct file_operations proc_numa_maps_operations = { + .open = numa_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; +#endif + +#ifdef CONFIG_MMU +extern struct seq_operations proc_pid_smaps_op; +static int smaps_open(struct inode *inode, struct file *file) +{ + struct task_struct *task = proc_task(inode); + int ret = seq_open(file, &proc_pid_smaps_op); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = task; + } + return ret; +} + +static struct file_operations proc_smaps_operations = { + .open = smaps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; +#endif + extern struct seq_operations mounts_op; static int mounts_open(struct inode *inode, struct file *file) { @@ -597,7 +741,7 @@ static ssize_t mem_read(struct file * file, char __user * buf, int ret = -ESRCH; struct mm_struct *mm; - if (!MAY_PTRACE(task) || !may_ptrace_attach(task)) + if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) goto out; ret = -ENOMEM; @@ -623,7 +767,7 @@ static ssize_t mem_read(struct file * file, char __user * buf, this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; retval = access_process_vm(task, src, page, this_len, 0); - if (!retval || !MAY_PTRACE(task) || !may_ptrace_attach(task)) { + if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) { if (!ret) ret = -EIO; break; @@ -661,7 +805,7 @@ static ssize_t mem_write(struct file * file, const char * buf, struct task_struct *task = proc_task(file->f_dentry->d_inode); unsigned long dst = *ppos; - if (!MAY_PTRACE(task) || !may_ptrace_attach(task)) + if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) return -ESRCH; page = (char *)__get_free_page(GFP_USER); @@ -890,7 +1034,7 @@ static struct file_operations proc_seccomp_operations = { }; #endif /* CONFIG_SECCOMP */ -static int proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) +static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; int error = -EACCES; @@ -907,7 +1051,7 @@ static int proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt); nd->last_type = LAST_BIND; out: - return error; + return ERR_PTR(error); } static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt, @@ -978,6 +1122,7 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) int retval; char buf[NUMBUF]; struct files_struct * files; + struct fdtable *fdt; retval = -ENOENT; if (!pid_alive(p)) @@ -1000,15 +1145,16 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) files = get_files_struct(p); if (!files) goto out; - spin_lock(&files->file_lock); + rcu_read_lock(); + fdt = files_fdtable(files); for (fd = filp->f_pos-2; - fd < files->max_fds; + fd < fdt->max_fds; fd++, filp->f_pos++) { unsigned int i,j; if (!fcheck_files(files, fd)) continue; - spin_unlock(&files->file_lock); + rcu_read_unlock(); j = NUMBUF; i = fd; @@ -1020,12 +1166,12 @@ static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) ino = fake_ino(tid, PROC_TID_FD_DIR + fd); if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) { - spin_lock(&files->file_lock); + rcu_read_lock(); break; } - spin_lock(&files->file_lock); + rcu_read_lock(); } - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); } out: @@ -1200,9 +1346,9 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) files = get_files_struct(task); if (files) { - spin_lock(&files->file_lock); + rcu_read_lock(); if (fcheck_files(files, fd)) { - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); if (task_dumpable(task)) { inode->i_uid = task->euid; @@ -1214,7 +1360,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) security_task_to_inode(task, inode); return 1; } - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); } d_drop(dentry); @@ -1306,7 +1452,7 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, if (!files) goto out_unlock; inode->i_mode = S_IFLNK; - spin_lock(&files->file_lock); + rcu_read_lock(); file = fcheck_files(files, fd); if (!file) goto out_unlock2; @@ -1314,7 +1460,7 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, inode->i_mode |= S_IRUSR | S_IXUSR; if (file->f_mode & 2) inode->i_mode |= S_IWUSR | S_IXUSR; - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; @@ -1324,7 +1470,7 @@ static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, return NULL; out_unlock2: - spin_unlock(&files->file_lock); + rcu_read_unlock(); put_files_struct(files); out_unlock: iput(inode); @@ -1355,7 +1501,7 @@ static struct inode_operations proc_fd_inode_operations = { static struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, - .permission = proc_permission, + .permission = proc_task_permission, }; #ifdef CONFIG_SECURITY @@ -1524,6 +1670,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir, case PROC_TGID_MAPS: inode->i_fop = &proc_maps_operations; break; +#ifdef CONFIG_NUMA + case PROC_TID_NUMA_MAPS: + case PROC_TGID_NUMA_MAPS: + inode->i_fop = &proc_numa_maps_operations; + break; +#endif case PROC_TID_MEM: case PROC_TGID_MEM: inode->i_op = &proc_mem_inode_operations; @@ -1539,6 +1691,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir, case PROC_TGID_MOUNTS: inode->i_fop = &proc_mounts_operations; break; +#ifdef CONFIG_MMU + case PROC_TID_SMAPS: + case PROC_TGID_SMAPS: + inode->i_fop = &proc_smaps_operations; + break; +#endif #ifdef CONFIG_SECURITY case PROC_TID_ATTR: inode->i_nlink = 2; @@ -1692,11 +1850,11 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, return vfs_readlink(dentry,buffer,buflen,tmp); } -static int proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) +static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) { char tmp[30]; sprintf(tmp, "%d", current->tgid); - return vfs_follow_link(nd,tmp); + return ERR_PTR(vfs_follow_link(nd,tmp)); } static struct inode_operations proc_self_inode_operations = { |