cregit-Linux how code gets into the kernel

Release 4.10 fs/fcntl.c

Directory: fs
/*
 *  linux/fs/fcntl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/pipe_fs_i.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/shmem_fs.h>

#include <asm/poll.h>
#include <asm/siginfo.h>
#include <linux/uaccess.h>


#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)


static int setfl(int fd, struct file * filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) { if (!filp->f_mapping || !filp->f_mapping->a_ops || !filp->f_mapping->a_ops->direct_IO) return -EINVAL; } if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); spin_unlock(&filp->f_lock); out: return error; }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git11240.14%318.75%
matthew wilcoxmatthew wilcox8028.67%212.50%
jonathan corbetjonathan corbet3010.75%318.75%
cesar eduardo barroscesar eduardo barros2810.04%16.25%
stanislav kinsburskiystanislav kinsburskiy103.58%16.25%
dean gaudetdean gaudet72.51%16.25%
andrew mortonandrew morton62.15%16.25%
al viroal viro41.43%212.50%
serge hallynserge hallyn10.36%16.25%
satyam sharmasatyam sharma10.36%16.25%
Total279100.00%16100.00%


static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); }

Contributors

PersonTokensPropCommitsCommitProp
james morrisjames morris7159.66%125.00%
eric w. biedermaneric w. biederman2722.69%125.00%
oleg nesterovoleg nesterov1915.97%125.00%
linus torvaldslinus torvalds21.68%125.00%
Total119100.00%4100.00%


void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { security_file_set_fowner(filp); f_modown(filp, pid, type, force); }

Contributors

PersonTokensPropCommitsCommitProp
james morrisjames morris2360.53%120.00%
eric w. biedermaneric w. biederman1231.58%120.00%
greg kroah-hartmangreg kroah-hartman25.26%240.00%
jeff laytonjeff layton12.63%120.00%
Total38100.00%5100.00%

EXPORT_SYMBOL(__f_setown);
void f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; struct pid *pid; int who = arg; type = PIDTYPE_PID; if (who < 0) { type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); pid = find_vpid(who); __f_setown(filp, pid, type, force); rcu_read_unlock(); }

Contributors

PersonTokensPropCommitsCommitProp
eric w. biedermaneric w. biederman7497.37%133.33%
jeff laytonjeff layton11.32%133.33%
pavel emelianovpavel emelianov11.32%133.33%
Total76100.00%3100.00%

EXPORT_SYMBOL(f_setown);
void f_delown(struct file *filp) { f_modown(filp, NULL, PIDTYPE_PID, 1); }

Contributors

PersonTokensPropCommitsCommitProp
james morrisjames morris1885.71%150.00%
eric w. biedermaneric w. biederman314.29%150.00%
Total21100.00%2100.00%


pid_t f_getown(struct file *filp) { pid_t pid; read_lock(&filp->f_owner.lock); pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; read_unlock(&filp->f_owner.lock); return pid; }

Contributors

PersonTokensPropCommitsCommitProp
eric w. biedermaneric w. biederman6198.39%266.67%
pavel emelianovpavel emelianov11.61%133.33%
Total62100.00%3100.00%


static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_MAX; break; case F_OWNER_PID: type = PIDTYPE_PID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
peter zijlstrapeter zijlstra14397.28%250.00%
al viroal viro21.36%125.00%
dan carpenterdan carpenter21.36%125.00%
Total147100.00%4100.00%


static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; int ret = 0; read_lock(&filp->f_owner.lock); owner.pid = pid_vnr(filp->f_owner.pid); switch (filp->f_owner.pid_type) { case PIDTYPE_MAX: owner.type = F_OWNER_TID; break; case PIDTYPE_PID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
peter zijlstrapeter zijlstra14391.67%250.00%
dan carpenterdan carpenter117.05%125.00%
al viroal viro21.28%125.00%
Total156100.00%4100.00%

#ifdef CONFIG_CHECKPOINT_RESTORE
static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; }

Contributors

PersonTokensPropCommitsCommitProp
cyrill gorcunovcyrill gorcunov12998.47%150.00%
al viroal viro21.53%150.00%
Total131100.00%2100.00%

#else
static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
cyrill gorcunovcyrill gorcunov19100.00%1100.00%
Total19100.00%1100.00%

#endif
static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(arg, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(arg, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, arg & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: err = fcntl_getlk(filp, cmd, (struct flock __user *) arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: #endif /* Fallthrough */ case F_SETLK: case F_SETLKW: err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: f_setown(filp, arg, 1); err = 0; break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(arg)) { break; } err = 0; filp->f_owner.signum = arg; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, arg); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, arg); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, arg); break; case F_ADD_SEALS: case F_GET_SEALS: err = shmem_fcntl(filp, cmd, arg); break; default: break; } return err; }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git23059.43%1337.14%
jeff laytonjeff layton328.27%411.43%
peter zijlstrapeter zijlstra266.72%12.86%
al viroal viro194.91%38.57%
jens axboejens axboe184.65%12.86%
david herrmanndavid herrmann184.65%12.86%
cyrill gorcunovcyrill gorcunov133.36%12.86%
james morrisjames morris61.55%12.86%
david howellsdavid howells51.29%12.86%
andrew mortonandrew morton41.03%25.71%
jesper juhljesper juhl41.03%12.86%
eric w. biedermaneric w. biederman30.78%12.86%
linus torvaldslinus torvalds20.52%12.86%
stephen rothwellstephen rothwell20.52%12.86%
matthew wilcoxmatthew wilcox20.52%12.86%
peter staubachpeter staubach20.52%12.86%
ulrich drepperulrich drepper10.26%12.86%
Total387100.00%35100.00%


static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
al viroal viro36100.00%1100.00%
Total36100.00%1100.00%

SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = fcntl_setlk64(fd, f.file, cmd, (struct flock64 __user *) arg); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const long band_table[NSIGPOLL] = { POLLIN | POLLRDNORM, /* POLL_IN */ POLLOUT | POLLWRNORM | POLLWRBAND, /* POLL_OUT */ POLLIN | POLLRDNORM | POLLMSG, /* POLL_MSG */ POLLERR, /* POLL_ERR */ POLLPRI | POLLRDBAND, /* POLL_PRI */ POLLHUP | POLLERR /* POLL_HUP */ };
static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git3833.33%444.44%
david howellsdavid howells3127.19%222.22%
eric w. biedermaneric w. biederman2118.42%111.11%
chris wrightchris wright1513.16%111.11%
james morrisjames morris97.89%111.11%
Total114100.00%9100.00%


static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, int group) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = ACCESS_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { siginfo_t si; default: /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason & __SI_MASK) != __SI_POLL); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = band_table[reason - POLL_IN]; si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, group)) break; /* fall-through: fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, group); } }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git9561.69%850.00%
james morrisjames morris2918.83%16.25%
oleg nesterovoleg nesterov159.74%212.50%
peter zijlstrapeter zijlstra53.25%16.25%
stephen d. smalleystephen d. smalley42.60%16.25%
eric sesterhenneric sesterhenn31.95%16.25%
roland mcgrathroland mcgrath21.30%16.25%
chris wrightchris wright10.65%16.25%
Total154100.00%16100.00%


void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; struct pid *pid; int group = 1; read_lock(&fown->lock); type = fown->pid_type; if (type == PIDTYPE_MAX) { group = 0; type = PIDTYPE_PID; } pid = fown->pid; if (!pid) goto out_unlock_fown; read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, group); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); out_unlock_fown: read_unlock(&fown->lock); }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git4433.08%333.33%
james morrisjames morris3727.82%111.11%
peter zijlstrapeter zijlstra2317.29%111.11%
eric w. biedermaneric w. biederman1813.53%111.11%
kirill korotaevkirill korotaev75.26%111.11%
matthew wilcoxmatthew wilcox21.50%111.11%
ingo molnaringo molnar21.50%111.11%
Total133100.00%9100.00%


static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, int group) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, group); }

Contributors

PersonTokensPropCommitsCommitProp
james morrisjames morris3175.61%125.00%
peter zijlstrapeter zijlstra614.63%125.00%
chris wrightchris wright24.88%125.00%
roland mcgrathroland mcgrath24.88%125.00%
Total41100.00%4100.00%


int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; int group = 1; int ret = 0; read_lock(&fown->lock); type = fown->pid_type; if (type == PIDTYPE_MAX) { group = 0; type = PIDTYPE_PID; } pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, group); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); out_unlock_fown: read_unlock(&fown->lock); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
james morrisjames morris7757.04%116.67%
peter zijlstrapeter zijlstra2317.04%116.67%
eric w. biedermaneric w. biederman2014.81%116.67%
pre-gitpre-git75.19%116.67%
kirill korotaevkirill korotaev75.19%116.67%
matthew wilcoxmatthew wilcox10.74%116.67%
Total135100.00%6100.00%

static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __read_mostly;
static void fasync_free_rcu(struct rcu_head *head) { kmem_cache_free(fasync_cache, container_of(head, struct fasync_struct, fa_rcu)); }

Contributors

PersonTokensPropCommitsCommitProp
eric dumazeteric dumazet26100.00%1100.00%
Total26100.00%1100.00%

/* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */
int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; spin_lock_irq(&fa->fa_lock); fa->fa_file = NULL; spin_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; call_rcu(&fa->fa_rcu, fasync_free_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds9263.45%133.33%
eric dumazeteric dumazet3020.69%133.33%
pre-gitpre-git2315.86%133.33%
Total145100.00%3100.00%


struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds17100.00%1100.00%
Total17100.00%1100.00%

/* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */
void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds17100.00%1100.00%
Total17100.00%1100.00%

/* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */
struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; spin_lock_irq(&fa->fa_lock); fa->fa_fd = fd; spin_unlock_irq(&fa->fa_lock); goto out; } spin_lock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git8448.55%116.67%
linus torvaldslinus torvalds3620.81%233.33%
eric dumazeteric dumazet3017.34%116.67%
jonathan corbetjonathan corbet2313.29%233.33%
Total173100.00%6100.00%

/* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */
static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; }

Contributors

PersonTokensPropCommitsCommitProp
linus torvaldslinus torvalds6496.97%150.00%
pre-gitpre-git23.03%150.00%
Total66100.00%2100.00%

/* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */
int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) {