From a33e6751003c5ade603737d828b1519d980ce392 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2008 03:40:06 -0500 Subject: sanitize audit_ipc_obj() * get rid of allocations * make it return void * simplify callers Signed-off-by: Al Viro --- ipc/shm.c | 4 +--- ipc/util.c | 9 +++------ 2 files changed, 4 insertions(+), 9 deletions(-) (limited to 'ipc') diff --git a/ipc/shm.c b/ipc/shm.c index 38a055758a9b..57dd50046cef 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -747,9 +747,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) goto out; } - err = audit_ipc_obj(&(shp->shm_perm)); - if (err) - goto out_unlock; + audit_ipc_obj(&(shp->shm_perm)); if (!capable(CAP_IPC_LOCK)) { uid_t euid = current_euid(); diff --git a/ipc/util.c b/ipc/util.c index 5a1808c774a2..579552abd50a 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -624,10 +624,9 @@ void ipc_rcu_putref(void *ptr) int ipcperms (struct kern_ipc_perm *ipcp, short flag) { /* flag will most probably be 0 or S_...UGO from */ uid_t euid = current_euid(); - int requested_mode, granted_mode, err; + int requested_mode, granted_mode; - if (unlikely((err = audit_ipc_obj(ipcp)))) - return err; + audit_ipc_obj(ipcp); requested_mode = (flag >> 6) | (flag >> 3) | flag; granted_mode = ipcp->mode; if (euid == ipcp->cuid || @@ -803,9 +802,7 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, goto out_up; } - err = audit_ipc_obj(ipcp); - if (err) - goto out_unlock; + audit_ipc_obj(ipcp); if (cmd == IPC_SET) { err = audit_ipc_set_perm(extra_perm, perm->uid, -- cgit v1.2.3 From e816f370cbadd2afea9f1a42f232d0636137d563 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2008 03:47:15 -0500 Subject: sanitize audit_ipc_set_perm() * get rid of allocations * make it return void * simplify callers Signed-off-by: Al Viro --- include/linux/audit.h | 9 ++++---- ipc/util.c | 9 ++------ kernel/auditsc.c | 59 +++++++++++++++++++++++---------------------------- 3 files changed, 32 insertions(+), 45 deletions(-) (limited to 'ipc') diff --git a/include/linux/audit.h b/include/linux/audit.h index f8578b9088e1..b7abfe0d6737 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -444,7 +444,7 @@ extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); #define audit_get_sessionid(t) ((t)->sessionid) extern void audit_log_task_context(struct audit_buffer *ab); extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); -extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); +extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); extern int audit_bprm(struct linux_binprm *bprm); extern void audit_socketcall(int nargs, unsigned long *args); extern int audit_sockaddr(int len, void *addr); @@ -471,11 +471,10 @@ static inline int audit_fd_pair(int fd1, int fd2) return __audit_fd_pair(fd1, fd2); return 0; } -static inline int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) +static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) { if (unlikely(!audit_dummy_context())) - return __audit_ipc_set_perm(qbytes, uid, gid, mode); - return 0; + __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr) { @@ -546,7 +545,7 @@ extern int audit_signals; #define audit_get_sessionid(t) (-1) #define audit_log_task_context(b) do { ; } while (0) #define audit_ipc_obj(i) ((void)0) -#define audit_ipc_set_perm(q,u,g,m) ({ 0; }) +#define audit_ipc_set_perm(q,u,g,m) ((void)0) #define audit_bprm(p) ({ 0; }) #define audit_socketcall(n,a) ((void)0) #define audit_fd_pair(n,a) ({ 0; }) diff --git a/ipc/util.c b/ipc/util.c index 579552abd50a..7585a72e259b 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -803,13 +803,9 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, } audit_ipc_obj(ipcp); - - if (cmd == IPC_SET) { - err = audit_ipc_set_perm(extra_perm, perm->uid, + if (cmd == IPC_SET) + audit_ipc_set_perm(extra_perm, perm->uid, perm->gid, perm->mode); - if (err) - goto out_unlock; - } euid = current_euid(); if (euid == ipcp->cuid || @@ -817,7 +813,6 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, return ipcp; err = -EPERM; -out_unlock: ipc_unlock(ipcp); out_up: up_write(&ids->rw_mutex); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 73504313264f..fbed62e05bce 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -151,16 +151,6 @@ struct audit_aux_data_mq_getsetattr { struct mq_attr mqstat; }; -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; - u32 osid; -}; - struct audit_aux_data_execve { struct audit_aux_data d; int argc; @@ -252,6 +242,11 @@ struct audit_context { gid_t gid; mode_t mode; u32 osid; + int has_perm; + uid_t perm_uid; + gid_t perm_gid; + mode_t perm_mode; + unsigned long qbytes; } ipc; }; @@ -1260,6 +1255,19 @@ static void show_special(struct audit_context *context, int *call_panic) security_release_secctx(ctx, len); } } + if (context->ipc.has_perm) { + audit_log_end(ab); + ab = audit_log_start(context, GFP_KERNEL, + AUDIT_IPC_SET_PERM); + audit_log_format(ab, + "qbytes=%lx ouid=%u ogid=%u mode=%#o", + context->ipc.qbytes, + context->ipc.perm_uid, + context->ipc.perm_gid, + context->ipc.perm_mode); + if (!ab) + return; + } break; } } audit_log_end(ab); @@ -1379,13 +1387,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs); break; } - case AUDIT_IPC_SET_PERM: { - struct audit_aux_data_ipcctl *axi = (void *)aux; - audit_log_format(ab, - "qbytes=%lx ouid=%u ogid=%u mode=%#o", - axi->qbytes, axi->uid, axi->gid, axi->mode); - break; } - case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; audit_log_execve_info(context, &ab, axi); @@ -2352,6 +2353,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) context->ipc.uid = ipcp->uid; context->ipc.gid = ipcp->gid; context->ipc.mode = ipcp->mode; + context->ipc.has_perm = 0; security_ipc_getsecid(ipcp, &context->ipc.osid); context->type = AUDIT_IPC; } @@ -2363,26 +2365,17 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) * @gid: msgq group id * @mode: msgq mode (permissions) * - * Returns 0 for success or NULL context or < 0 on error. + * Called only after audit_ipc_obj(). */ -int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) +void __audit_ipc_set_perm(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; - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - ax->qbytes = qbytes; - ax->uid = uid; - ax->gid = gid; - ax->mode = mode; - - ax->d.type = AUDIT_IPC_SET_PERM; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->ipc.qbytes = qbytes; + context->ipc.perm_uid = uid; + context->ipc.perm_gid = gid; + context->ipc.perm_mode = mode; + context->ipc.has_perm = 1; } int audit_bprm(struct linux_binprm *bprm) -- cgit v1.2.3 From 7392906ea915b9a2c14dea32b3604b4e178f82f7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2008 06:58:59 -0500 Subject: sanitize audit_mq_getsetattr() * get rid of allocations * make it return void * don't duplicate parts of audit_dummy_context() Signed-off-by: Al Viro --- include/linux/audit.h | 9 ++++----- ipc/mqueue.c | 6 +----- kernel/auditsc.c | 54 ++++++++++++++++----------------------------------- 3 files changed, 22 insertions(+), 47 deletions(-) (limited to 'ipc') diff --git a/include/linux/audit.h b/include/linux/audit.h index b7abfe0d6737..b7707e577b80 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -454,7 +454,7 @@ extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout); extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout); extern int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification); -extern int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); +extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); @@ -500,11 +500,10 @@ static inline int audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_n return __audit_mq_notify(mqdes, u_notification); return 0; } -static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) +static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) - return __audit_mq_getsetattr(mqdes, mqstat); - return 0; + __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, @@ -555,7 +554,7 @@ extern int audit_signals; #define audit_mq_timedsend(d,l,p,t) ({ 0; }) #define audit_mq_timedreceive(d,l,p,t) ({ 0; }) #define audit_mq_notify(d,n) ({ 0; }) -#define audit_mq_getsetattr(d,s) ({ 0; }) +#define audit_mq_getsetattr(d,s) ((void)0) #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; }) #define audit_log_capset(pid, ncr, ocr) ({ 0; }) #define audit_ptrace(t) ((void)0) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d9393f8e4c3e..7563611c6615 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1150,11 +1150,7 @@ asmlinkage long sys_mq_getsetattr(mqd_t mqdes, omqstat = info->attr; omqstat.mq_flags = filp->f_flags & O_NONBLOCK; if (u_mqstat) { - ret = audit_mq_getsetattr(mqdes, &mqstat); - if (ret != 0) { - spin_unlock(&info->lock); - goto out_fput; - } + audit_mq_getsetattr(mqdes, &mqstat); if (mqstat.mq_flags & O_NONBLOCK) filp->f_flags |= O_NONBLOCK; else diff --git a/kernel/auditsc.c b/kernel/auditsc.c index fbed62e05bce..c50178c7e245 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -145,12 +145,6 @@ struct audit_aux_data_mq_notify { struct sigevent notification; }; -struct audit_aux_data_mq_getsetattr { - struct audit_aux_data d; - mqd_t mqdes; - struct mq_attr mqstat; -}; - struct audit_aux_data_execve { struct audit_aux_data d; int argc; @@ -248,6 +242,10 @@ struct audit_context { mode_t perm_mode; unsigned long qbytes; } ipc; + struct { + mqd_t mqdes; + struct mq_attr mqstat; + } mq_getsetattr; }; #if AUDIT_DEBUG @@ -1269,6 +1267,15 @@ static void show_special(struct audit_context *context, int *call_panic) return; } break; } + case AUDIT_MQ_GETSETATTR: { + struct mq_attr *attr = &context->mq_getsetattr.mqstat; + audit_log_format(ab, + "mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld " + "mq_curmsgs=%ld ", + context->mq_getsetattr.mqdes, + attr->mq_flags, attr->mq_maxmsg, + attr->mq_msgsize, attr->mq_curmsgs); + break; } } audit_log_end(ab); } @@ -1377,16 +1384,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts axi->notification.sigev_signo); break; } - case AUDIT_MQ_GETSETATTR: { - struct audit_aux_data_mq_getsetattr *axi = (void *)aux; - audit_log_format(ab, - "mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld " - "mq_curmsgs=%ld ", - axi->mqdes, - axi->mqstat.mq_flags, axi->mqstat.mq_maxmsg, - axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs); - break; } - case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; audit_log_execve_info(context, &ab, axi); @@ -2316,30 +2313,13 @@ int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification) * @mqdes: MQ descriptor * @mqstat: MQ flags * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) +void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { - struct audit_aux_data_mq_getsetattr *ax; struct audit_context *context = current->audit_context; - - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - ax->mqdes = mqdes; - ax->mqstat = *mqstat; - - ax->d.type = AUDIT_MQ_GETSETATTR; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->mq_getsetattr.mqdes = mqdes; + context->mq_getsetattr.mqstat = *mqstat; + context->type = AUDIT_MQ_GETSETATTR; } /** -- cgit v1.2.3 From 20114f71b27cafeb7c7e41d2b0f0b68c3fbb022b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2008 07:16:12 -0500 Subject: sanitize audit_mq_notify() * don't copy_from_user() twice * don't bother with allocations * don't duplicate parts of audit_dummy_context() * make it return void Signed-off-by: Al Viro --- include/linux/audit.h | 9 ++++----- ipc/mqueue.c | 14 ++++++------- kernel/auditsc.c | 56 +++++++++++++++------------------------------------ 3 files changed, 27 insertions(+), 52 deletions(-) (limited to 'ipc') diff --git a/include/linux/audit.h b/include/linux/audit.h index b7707e577b80..8101d2c4a995 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -453,7 +453,7 @@ extern int audit_set_macxattr(const char *name); extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr); extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout); extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout); -extern int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification); +extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, @@ -494,11 +494,10 @@ static inline int audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned in return __audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout); return 0; } -static inline int audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification) +static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) - return __audit_mq_notify(mqdes, u_notification); - return 0; + __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { @@ -553,7 +552,7 @@ extern int audit_signals; #define audit_mq_open(o,m,a) ({ 0; }) #define audit_mq_timedsend(d,l,p,t) ({ 0; }) #define audit_mq_timedreceive(d,l,p,t) ({ 0; }) -#define audit_mq_notify(d,n) ({ 0; }) +#define audit_mq_notify(d,n) ((void)0) #define audit_mq_getsetattr(d,s) ((void)0) #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; }) #define audit_log_capset(pid, ncr, ocr) ({ 0; }) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 7563611c6615..e7b2f68f8d77 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1003,17 +1003,17 @@ asmlinkage long sys_mq_notify(mqd_t mqdes, struct mqueue_inode_info *info; struct sk_buff *nc; - ret = audit_mq_notify(mqdes, u_notification); - if (ret != 0) - return ret; - - nc = NULL; - sock = NULL; - if (u_notification != NULL) { + if (u_notification) { if (copy_from_user(¬ification, u_notification, sizeof(struct sigevent))) return -EFAULT; + } + + audit_mq_notify(mqdes, u_notification ? ¬ification : NULL); + nc = NULL; + sock = NULL; + if (u_notification != NULL) { if (unlikely(notification.sigev_notify != SIGEV_NONE && notification.sigev_notify != SIGEV_SIGNAL && notification.sigev_notify != SIGEV_THREAD)) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index c50178c7e245..3ece960de894 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -139,12 +139,6 @@ struct audit_aux_data_mq_sendrecv { struct timespec abs_timeout; }; -struct audit_aux_data_mq_notify { - struct audit_aux_data d; - mqd_t mqdes; - struct sigevent notification; -}; - struct audit_aux_data_execve { struct audit_aux_data d; int argc; @@ -246,6 +240,10 @@ struct audit_context { mqd_t mqdes; struct mq_attr mqstat; } mq_getsetattr; + struct { + mqd_t mqdes; + int sigev_signo; + } mq_notify; }; #if AUDIT_DEBUG @@ -1267,6 +1265,11 @@ static void show_special(struct audit_context *context, int *call_panic) return; } break; } + case AUDIT_MQ_NOTIFY: { + audit_log_format(ab, "mqdes=%d sigev_signo=%d", + context->mq_notify.mqdes, + context->mq_notify.sigev_signo); + break; } case AUDIT_MQ_GETSETATTR: { struct mq_attr *attr = &context->mq_getsetattr.mqstat; audit_log_format(ab, @@ -1376,14 +1379,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec); break; } - case AUDIT_MQ_NOTIFY: { - struct audit_aux_data_mq_notify *axi = (void *)aux; - audit_log_format(ab, - "mqdes=%d sigev_signo=%d", - axi->mqdes, - axi->notification.sigev_signo); - break; } - case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; audit_log_execve_info(context, &ab, axi); @@ -2274,38 +2269,19 @@ int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, * @mqdes: MQ descriptor * @u_notification: Notification event * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification) +void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { - struct audit_aux_data_mq_notify *ax; struct audit_context *context = current->audit_context; - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_notification != NULL) { - if (copy_from_user(&ax->notification, u_notification, sizeof(ax->notification))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->notification, 0, sizeof(ax->notification)); - - ax->mqdes = mqdes; + if (notification) + context->mq_notify.sigev_signo = notification->sigev_signo; + else + context->mq_notify.sigev_signo = 0; - ax->d.type = AUDIT_MQ_NOTIFY; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->mq_notify.mqdes = mqdes; + context->type = AUDIT_MQ_NOTIFY; } /** -- cgit v1.2.3 From c32c8af43b9adde8d6f938d8e6328c13b8de79ac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 14 Dec 2008 03:46:48 -0500 Subject: sanitize AUDIT_MQ_SENDRECV * logging the original value of *msg_prio in mq_timedreceive(2) is insane - the argument is write-only (i.e. syscall always ignores the original value and only overwrites it). * merge __audit_mq_timed{send,receive} * don't do copy_from_user() twice * don't mess with allocations in auditsc part * ... and don't bother checking !audit_enabled and !context in there - we'd already checked for audit_dummy_context(). Signed-off-by: Al Viro --- include/linux/audit.h | 17 ++----- ipc/mqueue.c | 54 +++++++++++---------- kernel/auditsc.c | 127 ++++++++++++-------------------------------------- 3 files changed, 63 insertions(+), 135 deletions(-) (limited to 'ipc') diff --git a/include/linux/audit.h b/include/linux/audit.h index 8101d2c4a995..67f0cdd991ba 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -451,8 +451,7 @@ extern int audit_sockaddr(int len, void *addr); extern int __audit_fd_pair(int fd1, int fd2); extern int audit_set_macxattr(const char *name); extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr); -extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout); -extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout); +extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, @@ -482,17 +481,10 @@ static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u return __audit_mq_open(oflag, mode, u_attr); return 0; } -static inline int audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout) +static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout) { if (unlikely(!audit_dummy_context())) - return __audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout); - return 0; -} -static inline int audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout) -{ - if (unlikely(!audit_dummy_context())) - return __audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout); - return 0; + __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { @@ -550,8 +542,7 @@ extern int audit_signals; #define audit_sockaddr(len, addr) ({ 0; }) #define audit_set_macxattr(n) do { ; } while (0) #define audit_mq_open(o,m,a) ({ 0; }) -#define audit_mq_timedsend(d,l,p,t) ({ 0; }) -#define audit_mq_timedreceive(d,l,p,t) ({ 0; }) +#define audit_mq_sendrecv(d,l,p,t) ((void)0) #define audit_mq_notify(d,n) ((void)0) #define audit_mq_getsetattr(d,s) ((void)0) #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; }) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index e7b2f68f8d77..192da806c283 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -524,31 +524,27 @@ static void __do_notify(struct mqueue_inode_info *info) wake_up(&info->wait_q); } -static long prepare_timeout(const struct timespec __user *u_arg) +static long prepare_timeout(struct timespec *p) { - struct timespec ts, nowts; + struct timespec nowts; long timeout; - if (u_arg) { - if (unlikely(copy_from_user(&ts, u_arg, - sizeof(struct timespec)))) - return -EFAULT; - - if (unlikely(ts.tv_nsec < 0 || ts.tv_sec < 0 - || ts.tv_nsec >= NSEC_PER_SEC)) + if (p) { + if (unlikely(p->tv_nsec < 0 || p->tv_sec < 0 + || p->tv_nsec >= NSEC_PER_SEC)) return -EINVAL; nowts = CURRENT_TIME; /* first subtract as jiffies can't be too big */ - ts.tv_sec -= nowts.tv_sec; - if (ts.tv_nsec < nowts.tv_nsec) { - ts.tv_nsec += NSEC_PER_SEC; - ts.tv_sec--; + p->tv_sec -= nowts.tv_sec; + if (p->tv_nsec < nowts.tv_nsec) { + p->tv_nsec += NSEC_PER_SEC; + p->tv_sec--; } - ts.tv_nsec -= nowts.tv_nsec; - if (ts.tv_sec < 0) + p->tv_nsec -= nowts.tv_nsec; + if (p->tv_sec < 0) return 0; - timeout = timespec_to_jiffies(&ts) + 1; + timeout = timespec_to_jiffies(p) + 1; } else return MAX_SCHEDULE_TIMEOUT; @@ -829,17 +825,22 @@ asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, struct ext_wait_queue *receiver; struct msg_msg *msg_ptr; struct mqueue_inode_info *info; + struct timespec ts, *p = NULL; long timeout; int ret; - ret = audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout); - if (ret != 0) - return ret; + if (u_abs_timeout) { + if (copy_from_user(&ts, u_abs_timeout, + sizeof(struct timespec))) + return -EFAULT; + p = &ts; + } if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX)) return -EINVAL; - timeout = prepare_timeout(u_abs_timeout); + audit_mq_sendrecv(mqdes, msg_len, msg_prio, p); + timeout = prepare_timeout(p); ret = -EBADF; filp = fget(mqdes); @@ -918,12 +919,17 @@ asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, struct inode *inode; struct mqueue_inode_info *info; struct ext_wait_queue wait; + struct timespec ts, *p = NULL; - ret = audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout); - if (ret != 0) - return ret; + if (u_abs_timeout) { + if (copy_from_user(&ts, u_abs_timeout, + sizeof(struct timespec))) + return -EFAULT; + p = &ts; + } - timeout = prepare_timeout(u_abs_timeout); + audit_mq_sendrecv(mqdes, msg_len, 0, p); + timeout = prepare_timeout(p); ret = -EBADF; filp = fget(mqdes); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 3ece960de894..140c47453470 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -131,14 +131,6 @@ struct audit_aux_data_mq_open { struct mq_attr attr; }; -struct audit_aux_data_mq_sendrecv { - struct audit_aux_data d; - mqd_t mqdes; - size_t msg_len; - unsigned int msg_prio; - struct timespec abs_timeout; -}; - struct audit_aux_data_execve { struct audit_aux_data d; int argc; @@ -244,6 +236,12 @@ struct audit_context { mqd_t mqdes; int sigev_signo; } mq_notify; + struct { + mqd_t mqdes; + size_t msg_len; + unsigned int msg_prio; + struct timespec abs_timeout; + } mq_sendrecv; }; #if AUDIT_DEBUG @@ -1265,6 +1263,16 @@ static void show_special(struct audit_context *context, int *call_panic) return; } break; } + case AUDIT_MQ_SENDRECV: { + audit_log_format(ab, + "mqdes=%d msg_len=%zd msg_prio=%u " + "abs_timeout_sec=%ld abs_timeout_nsec=%ld", + context->mq_sendrecv.mqdes, + context->mq_sendrecv.msg_len, + context->mq_sendrecv.msg_prio, + context->mq_sendrecv.abs_timeout.tv_sec, + context->mq_sendrecv.abs_timeout.tv_nsec); + break; } case AUDIT_MQ_NOTIFY: { audit_log_format(ab, "mqdes=%d sigev_signo=%d", context->mq_notify.mqdes, @@ -1370,15 +1378,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts axi->attr.mq_curmsgs); break; } - case AUDIT_MQ_SENDRECV: { - struct audit_aux_data_mq_sendrecv *axi = (void *)aux; - audit_log_format(ab, - "mqdes=%d msg_len=%zd msg_prio=%u " - "abs_timeout_sec=%ld abs_timeout_nsec=%ld", - axi->mqdes, axi->msg_len, axi->msg_prio, - axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec); - break; } - case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; audit_log_execve_info(context, &ab, axi); @@ -2171,97 +2170,29 @@ int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr) } /** - * __audit_mq_timedsend - record audit data for a POSIX MQ timed send + * __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive * @mqdes: MQ descriptor * @msg_len: Message length * @msg_prio: Message priority - * @u_abs_timeout: Message timeout in absolute time - * - * Returns 0 for success or NULL context or < 0 on error. - */ -int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, - const struct timespec __user *u_abs_timeout) -{ - struct audit_aux_data_mq_sendrecv *ax; - struct audit_context *context = current->audit_context; - - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_abs_timeout != NULL) { - if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout)); - - ax->mqdes = mqdes; - ax->msg_len = msg_len; - ax->msg_prio = msg_prio; - - ax->d.type = AUDIT_MQ_SENDRECV; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; -} - -/** - * __audit_mq_timedreceive - record audit data for a POSIX MQ timed receive - * @mqdes: MQ descriptor - * @msg_len: Message length - * @u_msg_prio: Message priority - * @u_abs_timeout: Message timeout in absolute time + * @abs_timeout: Message timeout in absolute time * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, - unsigned int __user *u_msg_prio, - const struct timespec __user *u_abs_timeout) +void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, + const struct timespec *abs_timeout) { - struct audit_aux_data_mq_sendrecv *ax; struct audit_context *context = current->audit_context; + struct timespec *p = &context->mq_sendrecv.abs_timeout; - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_msg_prio != NULL) { - if (get_user(ax->msg_prio, u_msg_prio)) { - kfree(ax); - return -EFAULT; - } - } else - ax->msg_prio = 0; - - if (u_abs_timeout != NULL) { - if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout)); + if (abs_timeout) + memcpy(p, abs_timeout, sizeof(struct timespec)); + else + memset(p, 0, sizeof(struct timespec)); - ax->mqdes = mqdes; - ax->msg_len = msg_len; + context->mq_sendrecv.mqdes = mqdes; + context->mq_sendrecv.msg_len = msg_len; + context->mq_sendrecv.msg_prio = msg_prio; - ax->d.type = AUDIT_MQ_SENDRECV; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->type = AUDIT_MQ_SENDRECV; } /** -- cgit v1.2.3 From 564f6993ffef656aebaf46cf2f1f6cb4f5c97207 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 14 Dec 2008 04:02:26 -0500 Subject: sanitize audit_mq_open() * don't bother with allocations * don't do double copy_from_user() * don't duplicate parts of check for audit_dummy_context() Signed-off-by: Al Viro --- include/linux/audit.h | 9 ++++--- ipc/mqueue.c | 23 +++++++++--------- kernel/auditsc.c | 65 ++++++++++++++++++--------------------------------- 3 files changed, 38 insertions(+), 59 deletions(-) (limited to 'ipc') diff --git a/include/linux/audit.h b/include/linux/audit.h index 67f0cdd991ba..54978bdd2bd4 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -450,7 +450,7 @@ extern void audit_socketcall(int nargs, unsigned long *args); extern int audit_sockaddr(int len, void *addr); extern int __audit_fd_pair(int fd1, int fd2); extern int audit_set_macxattr(const char *name); -extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr); +extern void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); @@ -475,11 +475,10 @@ static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } -static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr) +static inline void audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) - return __audit_mq_open(oflag, mode, u_attr); - return 0; + __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout) { @@ -541,7 +540,7 @@ extern int audit_signals; #define audit_fd_pair(n,a) ({ 0; }) #define audit_sockaddr(len, addr) ({ 0; }) #define audit_set_macxattr(n) do { ; } while (0) -#define audit_mq_open(o,m,a) ({ 0; }) +#define audit_mq_open(o,m,a) ((void)0) #define audit_mq_sendrecv(d,l,p,t) ((void)0) #define audit_mq_notify(d,n) ((void)0) #define audit_mq_getsetattr(d,s) ((void)0) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 192da806c283..d448b69672b5 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -588,22 +588,18 @@ static int mq_attr_ok(struct mq_attr *attr) * Invoked when creating a new queue via sys_mq_open */ static struct file *do_create(struct dentry *dir, struct dentry *dentry, - int oflag, mode_t mode, struct mq_attr __user *u_attr) + int oflag, mode_t mode, struct mq_attr *attr) { const struct cred *cred = current_cred(); - struct mq_attr attr; struct file *result; int ret; - if (u_attr) { - ret = -EFAULT; - if (copy_from_user(&attr, u_attr, sizeof(attr))) - goto out; + if (attr) { ret = -EINVAL; - if (!mq_attr_ok(&attr)) + if (!mq_attr_ok(attr)) goto out; /* store for use during create */ - dentry->d_fsdata = &attr; + dentry->d_fsdata = attr; } mode &= ~current->fs->umask; @@ -660,11 +656,13 @@ asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode, struct dentry *dentry; struct file *filp; char *name; + struct mq_attr attr; int fd, error; - error = audit_mq_open(oflag, mode, u_attr); - if (error != 0) - return error; + if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr))) + return -EFAULT; + + audit_mq_open(oflag, mode, u_attr ? &attr : NULL); if (IS_ERR(name = getname(u_name))) return PTR_ERR(name); @@ -690,7 +688,8 @@ asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode, filp = do_open(dentry, oflag); } else { filp = do_create(mqueue_mnt->mnt_root, dentry, - oflag, mode, u_attr); + oflag, mode, + u_attr ? &attr : NULL); } } else { error = -ENOENT; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 140c47453470..83e946f1cdde 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -124,13 +124,6 @@ struct audit_aux_data { /* Number of target pids per aux struct. */ #define AUDIT_AUX_PIDS 16 -struct audit_aux_data_mq_open { - struct audit_aux_data d; - int oflag; - mode_t mode; - struct mq_attr attr; -}; - struct audit_aux_data_execve { struct audit_aux_data d; int argc; @@ -242,6 +235,11 @@ struct audit_context { unsigned int msg_prio; struct timespec abs_timeout; } mq_sendrecv; + struct { + int oflag; + mode_t mode; + struct mq_attr attr; + } mq_open; }; #if AUDIT_DEBUG @@ -1263,6 +1261,16 @@ static void show_special(struct audit_context *context, int *call_panic) return; } break; } + case AUDIT_MQ_OPEN: { + audit_log_format(ab, + "oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld " + "mq_msgsize=%ld mq_curmsgs=%ld", + context->mq_open.oflag, context->mq_open.mode, + context->mq_open.attr.mq_flags, + context->mq_open.attr.mq_maxmsg, + context->mq_open.attr.mq_msgsize, + context->mq_open.attr.mq_curmsgs); + break; } case AUDIT_MQ_SENDRECV: { audit_log_format(ab, "mqdes=%d msg_len=%zd msg_prio=%u " @@ -1368,15 +1376,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts continue; /* audit_panic has been called */ switch (aux->type) { - case AUDIT_MQ_OPEN: { - struct audit_aux_data_mq_open *axi = (void *)aux; - audit_log_format(ab, - "oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld " - "mq_msgsize=%ld mq_curmsgs=%ld", - axi->oflag, axi->mode, axi->attr.mq_flags, - axi->attr.mq_maxmsg, axi->attr.mq_msgsize, - axi->attr.mq_curmsgs); - break; } case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; @@ -2135,38 +2134,20 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid) * @mode: mode bits * @u_attr: queue attributes * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr) +void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr) { - struct audit_aux_data_mq_open *ax; struct audit_context *context = current->audit_context; - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_attr != NULL) { - if (copy_from_user(&ax->attr, u_attr, sizeof(ax->attr))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->attr, 0, sizeof(ax->attr)); + if (attr) + memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr)); + else + memset(&context->mq_open.attr, 0, sizeof(struct mq_attr)); - ax->oflag = oflag; - ax->mode = mode; + context->mq_open.oflag = oflag; + context->mq_open.mode = mode; - ax->d.type = AUDIT_MQ_OPEN; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->type = AUDIT_MQ_OPEN; } /** -- cgit v1.2.3 From 56ff5efad96182f4d3cb3dc6b07396762c658f16 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 9 Dec 2008 09:34:39 -0500 Subject: zero i_uid/i_gid on inode allocation ... and don't bother in callers. Don't bother with zeroing i_blocks, while we are at it - it's already been zeroed. i_mode is not worth the effort; it has no common default value. Signed-off-by: Al Viro --- arch/powerpc/platforms/cell/spufs/inode.c | 1 - arch/s390/hypfs/inode.c | 1 - drivers/infiniband/hw/ipath/ipath_fs.c | 3 --- drivers/isdn/capi/capifs.c | 2 -- drivers/misc/ibmasm/ibmasmfs.c | 2 -- drivers/oprofile/oprofilefs.c | 3 --- drivers/usb/core/inode.c | 1 - drivers/usb/gadget/inode.c | 1 - fs/autofs/inode.c | 2 -- fs/autofs4/inode.c | 4 ---- fs/binfmt_misc.c | 3 --- fs/configfs/inode.c | 3 --- fs/cramfs/inode.c | 2 -- fs/debugfs/inode.c | 3 --- fs/devpts/inode.c | 4 ---- fs/hugetlbfs/inode.c | 1 - fs/inode.c | 2 ++ fs/libfs.c | 5 ----- fs/ocfs2/dlm/dlmfs.c | 2 -- fs/omfs/inode.c | 1 - fs/openpromfs/inode.c | 3 --- fs/proc/base.c | 4 ---- fs/proc/proc_sysctl.c | 1 - fs/ramfs/inode.c | 1 - fs/romfs/inode.c | 1 - fs/sysfs/inode.c | 3 --- ipc/mqueue.c | 1 - kernel/cgroup.c | 1 - net/sunrpc/rpc_pipe.c | 2 -- security/inode.c | 3 --- security/selinux/selinuxfs.c | 2 -- 31 files changed, 2 insertions(+), 66 deletions(-) (limited to 'ipc') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 6296bfd9cb0b..e309ef70a531 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -97,7 +97,6 @@ spufs_new_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; out: return inode; diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 9d4f8e6c0800..5a805df216bb 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -106,7 +106,6 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode) ret->i_mode = mode; ret->i_uid = hypfs_info->uid; ret->i_gid = hypfs_info->gid; - ret->i_blocks = 0; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; if (mode & S_IFDIR) ret->i_nlink = 2; diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index 53912c327bfe..8dc2bb781605 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -57,9 +57,6 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, } inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_private = data; if ((mode & S_IFMT) == S_IFDIR) { diff --git a/drivers/isdn/capi/capifs.c b/drivers/isdn/capi/capifs.c index 0aa66ec4cbdd..b129409925af 100644 --- a/drivers/isdn/capi/capifs.c +++ b/drivers/isdn/capi/capifs.c @@ -111,8 +111,6 @@ capifs_fill_super(struct super_block *s, void *data, int silent) goto fail; inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_blocks = 0; - inode->i_uid = inode->i_gid = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index 22a7e8ba211d..de966a6fb7e6 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -146,8 +146,6 @@ static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode) if (ret) { ret->i_mode = mode; - ret->i_uid = ret->i_gid = 0; - ret->i_blocks = 0; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } return ret; diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index ddc4c59f02dc..b7e4cee24269 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -29,9 +29,6 @@ static struct inode *oprofilefs_get_inode(struct super_block *sb, int mode) if (inode) { inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } return inode; diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 185be760833e..2a129cb7bb56 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -279,7 +279,6 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { default: diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index eeb26c0f88e5..317b48fdbf01 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -2001,7 +2001,6 @@ gadgetfs_make_inode (struct super_block *sb, inode->i_mode = mode; inode->i_uid = default_uid; inode->i_gid = default_gid; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_private = data; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index c773680d5c60..e1734f2d6e26 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -251,13 +251,11 @@ struct inode *autofs_iget(struct super_block *sb, unsigned long ino) inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_nlink = 2; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_blocks = 0; if (ino == AUTOFS_ROOT_INO) { inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &autofs_root_inode_operations; inode->i_fop = &autofs_root_operations; - inode->i_uid = inode->i_gid = 0; /* Changed in read_super */ goto done; } diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 7b19802cfef4..cfc23e53b6f4 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -455,11 +455,7 @@ struct inode *autofs4_get_inode(struct super_block *sb, if (sb->s_root) { inode->i_uid = sb->s_root->d_inode->i_uid; inode->i_gid = sb->s_root->d_inode->i_gid; - } else { - inode->i_uid = 0; - inode->i_gid = 0; } - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; if (S_ISDIR(inf->mode)) { diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index f2744ab4e5b3..e1158cb4fbd6 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -496,9 +496,6 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) if (inode) { inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb); } diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 4803ccc94480..5d349d38e056 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -117,8 +117,6 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr) static inline void set_default_inode_attr(struct inode * inode, mode_t mode) { inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } @@ -136,7 +134,6 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { - inode->i_blocks = 0; inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; inode->i_op = &configfs_inode_operations; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index f40423eb1a14..a07338d2d140 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -83,8 +83,6 @@ static struct inode *get_cramfs_inode(struct super_block *sb, inode->i_op = &page_symlink_inode_operations; inode->i_data.a_ops = &cramfs_aops; } else { - inode->i_size = 0; - inode->i_blocks = 0; init_special_inode(inode, inode->i_mode, old_decode_dev(cramfs_inode->size)); } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 3dbe2169cf36..81ae9ea3c6e1 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -37,9 +37,6 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d if (inode) { inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { default: diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index fff96e152c0c..5f3231b9633f 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -189,8 +189,6 @@ static int mknod_ptmx(struct super_block *sb) } inode->i_ino = 2; - inode->i_uid = inode->i_gid = 0; - inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; mode = S_IFCHR|opts->ptmxmode; @@ -300,8 +298,6 @@ devpts_fill_super(struct super_block *s, void *data, int silent) goto free_fsi; inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_blocks = 0; - inode->i_uid = inode->i_gid = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 7d479ce3aceb..0ab0c6f5f438 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -506,7 +506,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode->i_mode = mode; inode->i_uid = uid; inode->i_gid = gid; - inode->i_blocks = 0; inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/inode.c b/fs/inode.c index 7de1cda92489..bd48e5e6d3e8 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -131,6 +131,8 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->i_op = &empty_iops; inode->i_fop = &empty_fops; inode->i_nlink = 1; + inode->i_uid = 0; + inode->i_gid = 0; atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_blocks = 0; diff --git a/fs/libfs.c b/fs/libfs.c index e960a8321902..7de05f7ce746 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -231,7 +231,6 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name, */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; - root->i_uid = root->i_gid = 0; root->i_atime = root->i_mtime = root->i_ctime = CURRENT_TIME; dentry = d_alloc(NULL, &d_name); if (!dentry) { @@ -436,8 +435,6 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; - inode->i_uid = inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; @@ -464,8 +461,6 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files if (!inode) goto out; inode->i_mode = S_IFREG | files->mode; - inode->i_uid = inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_fop = files->ops; inode->i_ino = i; diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 6f7a77d54020..1c9efb406a96 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -341,7 +341,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inc_nlink(inode); @@ -367,7 +366,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent, inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 6afe57c84f84..633e9dc972bb 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -39,7 +39,6 @@ struct inode *omfs_new_inode(struct inode *dir, int mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_mapping->a_ops = &omfs_aops; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index d41bdc784de4..ffcd04f0012c 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -256,9 +256,6 @@ found: break; } - inode->i_gid = 0; - inode->i_uid = 0; - d_add(dentry, inode); return NULL; } diff --git a/fs/proc/base.c b/fs/proc/base.c index cad92c1ac2b3..10fd5223d600 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1426,8 +1426,6 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st if (!ei->pid) goto out_unlock; - inode->i_uid = 0; - inode->i_gid = 0; if (task_dumpable(task)) { rcu_read_lock(); cred = __task_cred(task); @@ -2349,8 +2347,6 @@ static struct dentry *proc_base_instantiate(struct inode *dir, if (!ei->pid) goto out_iput; - inode->i_uid = 0; - inode->i_gid = 0; inode->i_mode = p->mode; if (S_ISDIR(inode->i_mode)) inode->i_nlink = 2; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 06ed10b7da9e..94fcfff6863a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -31,7 +31,6 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */ inode->i_mode = table->mode; - inode->i_uid = inode->i_gid = 0; if (!table->child) { inode->i_mode |= S_IFREG; inode->i_op = &proc_sys_inode_operations; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index a83a3518ae33..b7e6ac706b87 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -57,7 +57,6 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); diff --git a/fs/romfs/inode.c b/fs/romfs/inode.c index 60d2f822e87b..c97d4c931715 100644 --- a/fs/romfs/inode.c +++ b/fs/romfs/inode.c @@ -524,7 +524,6 @@ romfs_iget(struct super_block *sb, unsigned long ino) i->i_size = be32_to_cpu(ri.size); i->i_mtime.tv_sec = i->i_atime.tv_sec = i->i_ctime.tv_sec = 0; i->i_mtime.tv_nsec = i->i_atime.tv_nsec = i->i_ctime.tv_nsec = 0; - i->i_uid = i->i_gid = 0; /* Precalculate the data offset */ ino = romfs_strnlen(i, ino+ROMFH_SIZE, ROMFS_MAXFN); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index eb53c632f856..dfa3d94cfc74 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -107,8 +107,6 @@ int sysfs_setattr(struct dentry * dentry, struct iattr * iattr) static inline void set_default_inode_attr(struct inode * inode, mode_t mode) { inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } @@ -149,7 +147,6 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode) { struct bin_attribute *bin_attr; - inode->i_blocks = 0; inode->i_mapping->a_ops = &sysfs_aops; inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; inode->i_op = &sysfs_inode_operations; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d9393f8e4c3e..41b72f02fa70 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -120,7 +120,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode, inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_mtime = inode->i_ctime = inode->i_atime = CURRENT_TIME; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 48348dde6d81..f7c5099a0572 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -573,7 +573,6 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info; } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 192453248870..577385a4a5dc 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -522,8 +522,6 @@ rpc_get_inode(struct super_block *sb, int mode) if (!inode) return NULL; inode->i_mode = mode; - inode->i_uid = inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch(mode & S_IFMT) { case S_IFDIR: diff --git a/security/inode.c b/security/inode.c index efea5a605466..007ef252dde7 100644 --- a/security/inode.c +++ b/security/inode.c @@ -61,9 +61,6 @@ static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) if (inode) { inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { default: diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index e5520996a75b..8f612c8becb5 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -847,8 +847,6 @@ static struct inode *sel_make_inode(struct super_block *sb, int mode) if (ret) { ret->i_mode = mode; - ret->i_uid = ret->i_gid = 0; - ret->i_blocks = 0; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } return ret; -- cgit v1.2.3 From 046c68842bce6b77509cf56e94a561029124b0ce Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Mon, 5 Jan 2009 14:06:29 +0000 Subject: mm: update my address Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- ipc/sem.c | 2 +- mm/mmap.c | 2 +- mm/mprotect.c | 2 +- mm/mremap.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'ipc') diff --git a/ipc/sem.c b/ipc/sem.c index 082122469b17..fea0ad3aed7b 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -58,7 +58,7 @@ * SMP-threaded, sysctl's added * (c) 1999 Manfred Spraul * Enforced range limit on SEM_UNDO - * (c) 2001 Red Hat Inc + * (c) 2001 Red Hat Inc * Lockless wakeup * (c) 2003 Manfred Spraul * diff --git a/mm/mmap.c b/mm/mmap.c index d4855a682ab6..2c778fcfd9bd 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3,7 +3,7 @@ * * Written by obz. * - * Address space accounting code + * Address space accounting code */ #include diff --git a/mm/mprotect.c b/mm/mprotect.c index fded06f923f4..cfb4c4852062 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -4,7 +4,7 @@ * (C) Copyright 1994 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig * - * Address space accounting code + * Address space accounting code * (C) Copyright 2002 Red Hat Inc, All Rights Reserved */ diff --git a/mm/mremap.c b/mm/mremap.c index 58a2908f42f5..646de959aa58 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -3,7 +3,7 @@ * * (C) Copyright 1996 Linus Torvalds * - * Address space accounting code + * Address space accounting code * (C) Copyright 2002 Red Hat Inc, All Rights Reserved */ -- cgit v1.2.3 From e8148f7588064e45080bf1120883380a2efe5c9b Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 6 Jan 2009 14:42:49 -0800 Subject: ipc: clean up ipc/shm.c Use the macro shm_ids(). Remove useless check for a userspace pointer, because copy_to_user() will check it. Some style cleanups. Signed-off-by: WANG Cong Cc: Nadia Derbey Cc: Pierre Peiffer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'ipc') diff --git a/ipc/shm.c b/ipc/shm.c index 57dd50046cef..b125b560240e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -75,7 +75,7 @@ void shm_init_ns(struct ipc_namespace *ns) ns->shm_ctlall = SHMALL; ns->shm_ctlmni = SHMMNI; ns->shm_tot = 0; - ipc_init_ids(&ns->ids[IPC_SHM_IDS]); + ipc_init_ids(&shm_ids(ns)); } /* @@ -644,7 +644,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) if (err) return err; - memset(&shminfo,0,sizeof(shminfo)); + memset(&shminfo, 0, sizeof(shminfo)); shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni; shminfo.shmmax = ns->shm_ctlmax; shminfo.shmall = ns->shm_ctlall; @@ -669,7 +669,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) if (err) return err; - memset(&shm_info,0,sizeof(shm_info)); + memset(&shm_info, 0, sizeof(shm_info)); down_read(&shm_ids(ns).rw_mutex); shm_info.used_ids = shm_ids(ns).in_use; shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp); @@ -678,7 +678,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) shm_info.swap_successes = 0; err = ipc_get_maxid(&shm_ids(ns)); up_read(&shm_ids(ns).rw_mutex); - if(copy_to_user (buf, &shm_info, sizeof(shm_info))) { + if (copy_to_user(buf, &shm_info, sizeof(shm_info))) { err = -EFAULT; goto out; } @@ -692,11 +692,6 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) struct shmid64_ds tbuf; int result; - if (!buf) { - err = -EFAULT; - goto out; - } - if (cmd == SHM_STAT) { shp = shm_lock(ns, shmid); if (IS_ERR(shp)) { @@ -712,7 +707,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) } result = 0; } - err=-EACCES; + err = -EACCES; if (ipcperms (&shp->shm_perm, S_IRUGO)) goto out_unlock; err = security_shm_shmctl(shp, cmd); -- cgit v1.2.3 From e953ac2195659940d0d042f7ac962700a6a0f0e3 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Tue, 6 Jan 2009 14:42:50 -0800 Subject: ipc: do not goto to the next line Signed-off-by: Denis V. Lunev Reviewed-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 1 - 1 file changed, 1 deletion(-) (limited to 'ipc') diff --git a/ipc/sem.c b/ipc/sem.c index fea0ad3aed7b..c68cd3f8f0c9 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1216,7 +1216,6 @@ asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops, if (timeout && jiffies_left == 0) error = -EAGAIN; list_del(&queue.list); - goto out_unlock_free; out_unlock_free: sem_unlock(sma); -- cgit v1.2.3 From 4c2c3b4aaf3c10a636490438e9648a314ce414f9 Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Tue, 6 Jan 2009 14:42:51 -0800 Subject: ipc/ipc_sysctl.c: move the definition of ipc_auto_callback() proc_ipcauto_dointvec_minmax() is the only user of ipc_auto_callback(), since the former function is protected by CONFIG_PROC_FS, so should be the latter one. Just move its definition down. Signed-off-by: WANG Cong Cc: Eric Biederman Cc: Nadia Derbey Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/ipc_sysctl.c | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'ipc') diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 0dfebc509426..4a7a12c95abe 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -26,29 +26,6 @@ static void *get_ipc(ctl_table *table) return which; } -/* - * Routine that is called when the file "auto_msgmni" has successfully been - * written. - * Two values are allowed: - * 0: unregister msgmni's callback routine from the ipc namespace notifier - * chain. This means that msgmni won't be recomputed anymore upon memory - * add/remove or ipc namespace creation/removal. - * 1: register back the callback routine. - */ -static void ipc_auto_callback(int val) -{ - if (!val) - unregister_ipcns_notifier(current->nsproxy->ipc_ns); - else { - /* - * Re-enable automatic recomputing only if not already - * enabled. - */ - recompute_msgmni(current->nsproxy->ipc_ns); - cond_register_ipcns_notifier(current->nsproxy->ipc_ns); - } -} - #ifdef CONFIG_PROC_FS static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -94,6 +71,29 @@ static int proc_ipc_doulongvec_minmax(ctl_table *table, int write, lenp, ppos); } +/* + * Routine that is called when the file "auto_msgmni" has successfully been + * written. + * Two values are allowed: + * 0: unregister msgmni's callback routine from the ipc namespace notifier + * chain. This means that msgmni won't be recomputed anymore upon memory + * add/remove or ipc namespace creation/removal. + * 1: register back the callback routine. + */ +static void ipc_auto_callback(int val) +{ + if (!val) + unregister_ipcns_notifier(current->nsproxy->ipc_ns); + else { + /* + * Re-enable automatic recomputing only if not already + * enabled. + */ + recompute_msgmni(current->nsproxy->ipc_ns); + cond_register_ipcns_notifier(current->nsproxy->ipc_ns); + } +} + static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { -- cgit v1.2.3 From 8feae13110d60cc6287afabc2887366b0eb226c2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 8 Jan 2009 12:04:47 +0000 Subject: NOMMU: Make VMAs per MM as for MMU-mode linux Make VMAs per mm_struct as for MMU-mode linux. This solves two problems: (1) In SYSV SHM where nattch for a segment does not reflect the number of shmat's (and forks) done. (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an exec'ing process when VM_EXECUTABLE is specified, regardless of the fact that a VMA might be shared and already have its vm_mm assigned to another process or a dead process. A new struct (vm_region) is introduced to track a mapped region and to remember the circumstances under which it may be shared and the vm_list_struct structure is discarded as it's no longer required. This patch makes the following additional changes: (1) Regions are now allocated with alloc_pages() rather than kmalloc() and with no recourse to __GFP_COMP, so the pages are not composite. Instead, each page has a reference on it held by the region. Anything else that is interested in such a page will have to get a reference on it to retain it. When the pages are released due to unmapping, each page is passed to put_page() and will be freed when the page usage count reaches zero. (2) Excess pages are trimmed after an allocation as the allocation must be made as a power-of-2 quantity of pages. (3) VMAs are added to the parent MM's R/B tree and mmap lists. As an MM may end up with overlapping VMAs within the tree, the VMA struct address is appended to the sort key. (4) Non-anonymous VMAs are now added to the backing inode's prio list. (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of the backing region. The VMA and region structs will be split if necessary. (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory segment instead of all the attachments at that addresss. Multiple shmat()'s return the same address under NOMMU-mode instead of different virtual addresses as under MMU-mode. (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode. (8) /proc/maps is now the global list of mapped regions, and may list bits that aren't actually mapped anywhere. (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount of RAM currently allocated by mmap to hold mappable regions that can't be mapped directly. These are copies of the backing device or file if not anonymous. These changes make NOMMU mode more similar to MMU mode. The downside is that NOMMU mode requires some extra memory to track things over NOMMU without this patch (VMAs are no longer shared, and there are now region structs). Signed-off-by: David Howells Tested-by: Mike Frysinger Acked-by: Paul Mundt --- Documentation/nommu-mmap.txt | 18 +- arch/arm/include/asm/mmu.h | 1 - arch/blackfin/include/asm/mmu.h | 1 - arch/blackfin/kernel/ptrace.c | 6 +- arch/blackfin/kernel/traps.c | 11 +- arch/frv/kernel/ptrace.c | 11 +- arch/h8300/include/asm/mmu.h | 1 - arch/m68knommu/include/asm/mmu.h | 1 - arch/sh/include/asm/mmu.h | 1 - fs/binfmt_elf_fdpic.c | 27 +- fs/proc/internal.h | 2 - fs/proc/meminfo.c | 6 + fs/proc/nommu.c | 71 ++- fs/proc/task_nommu.c | 108 +++-- include/asm-frv/mmu.h | 1 - include/asm-m32r/mmu.h | 1 - include/linux/mm.h | 18 +- include/linux/mm_types.h | 18 +- ipc/shm.c | 12 + kernel/fork.c | 4 +- lib/Kconfig.debug | 7 + mm/mmap.c | 10 + mm/nommu.c | 960 +++++++++++++++++++++++++++------------ 23 files changed, 860 insertions(+), 436 deletions(-) (limited to 'ipc') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 7714f57caad5..02b89dcf38ac 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -109,12 +109,18 @@ and it's also much more restricted in the latter case: FURTHER NOTES ON NO-MMU MMAP ============================ - (*) A request for a private mapping of less than a page in size may not return - a page-aligned buffer. This is because the kernel calls kmalloc() to - allocate the buffer, not get_free_page(). - - (*) A list of all the mappings on the system is visible through /proc/maps in - no-MMU mode. + (*) A request for a private mapping of a file may return a buffer that is not + page-aligned. This is because XIP may take place, and the data may not be + paged aligned in the backing store. + + (*) A request for an anonymous mapping will always be page aligned. If + possible the size of the request should be a power of two otherwise some + of the space may be wasted as the kernel must allocate a power-of-2 + granule but will only discard the excess if appropriately configured as + this has an effect on fragmentation. + + (*) A list of all the private copy and anonymous mappings on the system is + visible through /proc/maps in no-MMU mode. (*) A list of all the mappings in use by a process is visible through /proc//maps in no-MMU mode. diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index 53099d4ee421..b561584d04a1 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -24,7 +24,6 @@ typedef struct { * modified for 2.6 by Hyok S. Choi */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/blackfin/include/asm/mmu.h b/arch/blackfin/include/asm/mmu.h index 757e43906ed4..dbfd686360e6 100644 --- a/arch/blackfin/include/asm/mmu.h +++ b/arch/blackfin/include/asm/mmu.h @@ -10,7 +10,6 @@ struct sram_list_struct { }; typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; unsigned long stack_start; diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index d2d388536630..594e325b40e4 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -160,15 +160,15 @@ put_reg(struct task_struct *task, int regno, unsigned long data) static inline int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) { - struct vm_list_struct *vml; + struct vm_area_struct *vma; struct sram_list_struct *sraml; /* overflow */ if (start + len < start) return -EIO; - for (vml = child->mm->context.vmlist; vml; vml = vml->next) - if (start >= vml->vma->vm_start && start + len < vml->vma->vm_end) + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) return 0; for (sraml = child->mm->context.sram_list; sraml; sraml = sraml->next) diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c index 17d8e4172896..5b0667da8d05 100644 --- a/arch/blackfin/kernel/traps.c +++ b/arch/blackfin/kernel/traps.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -83,6 +84,7 @@ static void decode_address(char *buf, unsigned long address) struct mm_struct *mm; unsigned long flags, offset; unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic(); + struct rb_node *n; #ifdef CONFIG_KALLSYMS unsigned long symsize; @@ -128,9 +130,10 @@ static void decode_address(char *buf, unsigned long address) if (!mm) continue; - vml = mm->context.vmlist; - while (vml) { - struct vm_area_struct *vma = vml->vma; + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + struct vm_area_struct *vma; + + vma = rb_entry(n, struct vm_area_struct, vm_rb); if (address >= vma->vm_start && address < vma->vm_end) { char _tmpbuf[256]; @@ -176,8 +179,6 @@ static void decode_address(char *buf, unsigned long address) goto done; } - - vml = vml->next; } if (!in_atomic) mmput(mm); diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c index 709e9bdc6126..5e7d401d21e7 100644 --- a/arch/frv/kernel/ptrace.c +++ b/arch/frv/kernel/ptrace.c @@ -69,7 +69,8 @@ static inline int put_reg(struct task_struct *task, int regno, } /* - * check that an address falls within the bounds of the target process's memory mappings + * check that an address falls within the bounds of the target process's memory + * mappings */ static inline int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) @@ -79,11 +80,11 @@ static inline int is_user_addr_valid(struct task_struct *child, return -EIO; return 0; #else - struct vm_list_struct *vml; + struct vm_area_struct *vma; - for (vml = child->mm->context.vmlist; vml; vml = vml->next) - if (start >= vml->vma->vm_start && start + len <= vml->vma->vm_end) - return 0; + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) + return 0; return -EIO; #endif diff --git a/arch/h8300/include/asm/mmu.h b/arch/h8300/include/asm/mmu.h index 2ce06ea46104..31309969df70 100644 --- a/arch/h8300/include/asm/mmu.h +++ b/arch/h8300/include/asm/mmu.h @@ -4,7 +4,6 @@ /* Copyright (C) 2002, David McCullough */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/m68knommu/include/asm/mmu.h b/arch/m68knommu/include/asm/mmu.h index 5fa6b68353ba..e2da1e6f09fe 100644 --- a/arch/m68knommu/include/asm/mmu.h +++ b/arch/m68knommu/include/asm/mmu.h @@ -4,7 +4,6 @@ /* Copyright (C) 2002, David McCullough */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/sh/include/asm/mmu.h b/arch/sh/include/asm/mmu.h index fdcb93bc6d11..6c43625bb1a5 100644 --- a/arch/sh/include/asm/mmu.h +++ b/arch/sh/include/asm/mmu.h @@ -9,7 +9,6 @@ typedef struct { mm_context_id_t id; void *vdso; #else - struct vm_list_struct *vmlist; unsigned long end_brk; #endif #ifdef CONFIG_BINFMT_ELF_FDPIC diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index aa5b43205e37..22baf1b13493 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1567,11 +1567,9 @@ end_coredump: static int elf_fdpic_dump_segments(struct file *file, size_t *size, unsigned long *limit, unsigned long mm_flags) { - struct vm_list_struct *vml; - - for (vml = current->mm->context.vmlist; vml; vml = vml->next) { - struct vm_area_struct *vma = vml->vma; + struct vm_area_struct *vma; + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { if (!maydump(vma, mm_flags)) continue; @@ -1617,9 +1615,6 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, elf_fpxregset_t *xfpu = NULL; #endif int thread_status_size = 0; -#ifndef CONFIG_MMU - struct vm_list_struct *vml; -#endif elf_addr_t *auxv; unsigned long mm_flags; @@ -1685,13 +1680,7 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, fill_prstatus(prstatus, current, signr); elf_core_copy_regs(&prstatus->pr_reg, regs); -#ifdef CONFIG_MMU segs = current->mm->map_count; -#else - segs = 0; - for (vml = current->mm->context.vmlist; vml; vml = vml->next) - segs++; -#endif #ifdef ELF_CORE_EXTRA_PHDRS segs += ELF_CORE_EXTRA_PHDRS; #endif @@ -1766,20 +1755,10 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, mm_flags = current->mm->flags; /* write program headers for segments dump */ - for ( -#ifdef CONFIG_MMU - vma = current->mm->mmap; vma; vma = vma->vm_next -#else - vml = current->mm->context.vmlist; vml; vml = vml->next -#endif - ) { + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { struct elf_phdr phdr; size_t sz; -#ifndef CONFIG_MMU - vma = vml->vma; -#endif - sz = vma->vm_end - vma->vm_start; phdr.p_type = PT_LOAD; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 3e8aeb8b61ce..cd53ff838498 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -41,8 +41,6 @@ do { \ (vmi)->used = 0; \ (vmi)->largest_chunk = 0; \ } while(0) - -extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *); #endif extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns, diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index b1675c4e66da..43d23948384a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -73,6 +73,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "HighFree: %8lu kB\n" "LowTotal: %8lu kB\n" "LowFree: %8lu kB\n" +#endif +#ifndef CONFIG_MMU + "MmapCopy: %8lu kB\n" #endif "SwapTotal: %8lu kB\n" "SwapFree: %8lu kB\n" @@ -115,6 +118,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freehigh), K(i.totalram-i.totalhigh), K(i.freeram-i.freehigh), +#endif +#ifndef CONFIG_MMU + K((unsigned long) atomic_read(&mmap_pages_allocated)), #endif K(i.totalswap), K(i.freeswap), diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 3f87d2632947..b446d7ad0b0d 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -33,33 +33,33 @@ #include "internal.h" /* - * display a single VMA to a sequenced file + * display a single region to a sequenced file */ -int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) +static int nommu_region_show(struct seq_file *m, struct vm_region *region) { unsigned long ino = 0; struct file *file; dev_t dev = 0; int flags, len; - flags = vma->vm_flags; - file = vma->vm_file; + flags = region->vm_flags; + file = region->vm_file; if (file) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = region->vm_file->f_path.dentry->d_inode; dev = inode->i_sb->s_dev; ino = inode->i_ino; } seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", - vma->vm_start, - vma->vm_end, + region->vm_start, + region->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', - ((loff_t)vma->vm_pgoff) << PAGE_SHIFT, + ((loff_t)region->vm_pgoff) << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); if (file) { @@ -75,61 +75,54 @@ int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) } /* - * display a list of all the VMAs the kernel knows about + * display a list of all the REGIONs the kernel knows about * - nommu kernals have a single flat list */ -static int nommu_vma_list_show(struct seq_file *m, void *v) +static int nommu_region_list_show(struct seq_file *m, void *_p) { - struct vm_area_struct *vma; + struct rb_node *p = _p; - vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb); - return nommu_vma_show(m, vma); + return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb)); } -static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos) +static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos) { - struct rb_node *_rb; + struct rb_node *p; loff_t pos = *_pos; - void *next = NULL; - down_read(&nommu_vma_sem); + down_read(&nommu_region_sem); - for (_rb = rb_first(&nommu_vma_tree); _rb; _rb = rb_next(_rb)) { - if (pos == 0) { - next = _rb; - break; - } - pos--; - } - - return next; + for (p = rb_first(&nommu_region_tree); p; p = rb_next(p)) + if (pos-- == 0) + return p; + return NULL; } -static void nommu_vma_list_stop(struct seq_file *m, void *v) +static void nommu_region_list_stop(struct seq_file *m, void *v) { - up_read(&nommu_vma_sem); + up_read(&nommu_region_sem); } -static void *nommu_vma_list_next(struct seq_file *m, void *v, loff_t *pos) +static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos) { (*pos)++; return rb_next((struct rb_node *) v); } -static const struct seq_operations proc_nommu_vma_list_seqop = { - .start = nommu_vma_list_start, - .next = nommu_vma_list_next, - .stop = nommu_vma_list_stop, - .show = nommu_vma_list_show +static struct seq_operations proc_nommu_region_list_seqop = { + .start = nommu_region_list_start, + .next = nommu_region_list_next, + .stop = nommu_region_list_stop, + .show = nommu_region_list_show }; -static int proc_nommu_vma_list_open(struct inode *inode, struct file *file) +static int proc_nommu_region_list_open(struct inode *inode, struct file *file) { - return seq_open(file, &proc_nommu_vma_list_seqop); + return seq_open(file, &proc_nommu_region_list_seqop); } -static const struct file_operations proc_nommu_vma_list_operations = { - .open = proc_nommu_vma_list_open, +static const struct file_operations proc_nommu_region_list_operations = { + .open = proc_nommu_region_list_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, @@ -137,7 +130,7 @@ static const struct file_operations proc_nommu_vma_list_operations = { static int __init proc_nommu_init(void) { - proc_create("maps", S_IRUGO, NULL, &proc_nommu_vma_list_operations); + proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations); return 0; } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index d4a8be32b902..ca4a48d0d311 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -15,25 +15,25 @@ */ void task_mem(struct seq_file *m, struct mm_struct *mm) { - struct vm_list_struct *vml; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long bytes = 0, sbytes = 0, slack = 0; down_read(&mm->mmap_sem); - for (vml = mm->context.vmlist; vml; vml = vml->next) { - if (!vml->vma) - continue; + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); - bytes += kobjsize(vml); + bytes += kobjsize(vma); if (atomic_read(&mm->mm_count) > 1 || - atomic_read(&vml->vma->vm_usage) > 1 - ) { - sbytes += kobjsize((void *) vml->vma->vm_start); - sbytes += kobjsize(vml->vma); + vma->vm_region || + vma->vm_flags & VM_MAYSHARE) { + sbytes += kobjsize((void *) vma->vm_start); + if (vma->vm_region) + sbytes += kobjsize(vma->vm_region); } else { - bytes += kobjsize((void *) vml->vma->vm_start); - bytes += kobjsize(vml->vma); - slack += kobjsize((void *) vml->vma->vm_start) - - (vml->vma->vm_end - vml->vma->vm_start); + bytes += kobjsize((void *) vma->vm_start); + slack += kobjsize((void *) vma->vm_start) - + (vma->vm_end - vma->vm_start); } } @@ -70,13 +70,14 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long task_vsize(struct mm_struct *mm) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long vsize = 0; down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - if (tbp->vma) - vsize += kobjsize((void *) tbp->vma->vm_start); + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + vsize += vma->vm_region->vm_end - vma->vm_region->vm_start; } up_read(&mm->mmap_sem); return vsize; @@ -85,16 +86,15 @@ unsigned long task_vsize(struct mm_struct *mm) int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; int size = kobjsize(mm); down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - size += kobjsize(tbp); - if (tbp->vma) { - size += kobjsize(tbp->vma); - size += kobjsize((void *) tbp->vma->vm_start); - } + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + size += kobjsize(vma); + size += kobjsize((void *) vma->vm_start); } size += (*text = mm->end_code - mm->start_code); @@ -104,21 +104,63 @@ int task_statm(struct mm_struct *mm, int *shared, int *text, return size; } +/* + * display a single VMA to a sequenced file + */ +static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) +{ + unsigned long ino = 0; + struct file *file; + dev_t dev = 0; + int flags, len; + + flags = vma->vm_flags; + file = vma->vm_file; + + if (file) { + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + } + + seq_printf(m, + "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", + vma->vm_start, + vma->vm_end, + flags & VM_READ ? 'r' : '-', + flags & VM_WRITE ? 'w' : '-', + flags & VM_EXEC ? 'x' : '-', + flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', + vma->vm_pgoff << PAGE_SHIFT, + MAJOR(dev), MINOR(dev), ino, &len); + + if (file) { + len = 25 + sizeof(void *) * 6 - len; + if (len < 1) + len = 1; + seq_printf(m, "%*c", len, ' '); + seq_path(m, &file->f_path, ""); + } + + seq_putc(m, '\n'); + return 0; +} + /* * display mapping lines for a particular process's /proc/pid/maps */ -static int show_map(struct seq_file *m, void *_vml) +static int show_map(struct seq_file *m, void *_p) { - struct vm_list_struct *vml = _vml; + struct rb_node *p = _p; - return nommu_vma_show(m, vml->vma); + return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb)); } static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_maps_private *priv = m->private; - struct vm_list_struct *vml; struct mm_struct *mm; + struct rb_node *p; loff_t n = *pos; /* pin the task and mm whilst we play with them */ @@ -134,9 +176,9 @@ static void *m_start(struct seq_file *m, loff_t *pos) } /* start from the Nth VMA */ - for (vml = mm->context.vmlist; vml; vml = vml->next) + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) if (n-- == 0) - return vml; + return p; return NULL; } @@ -152,12 +194,12 @@ static void m_stop(struct seq_file *m, void *_vml) } } -static void *m_next(struct seq_file *m, void *_vml, loff_t *pos) +static void *m_next(struct seq_file *m, void *_p, loff_t *pos) { - struct vm_list_struct *vml = _vml; + struct rb_node *p = _p; (*pos)++; - return vml ? vml->next : NULL; + return p ? rb_next(p) : NULL; } static const struct seq_operations proc_pid_maps_ops = { diff --git a/include/asm-frv/mmu.h b/include/asm-frv/mmu.h index 22c03714fb14..86ca0e86e7d2 100644 --- a/include/asm-frv/mmu.h +++ b/include/asm-frv/mmu.h @@ -22,7 +22,6 @@ typedef struct { unsigned long dtlb_ptd_mapping; /* [DAMR5] PTD mapping for dtlb cached PGE */ #else - struct vm_list_struct *vmlist; unsigned long end_brk; #endif diff --git a/include/asm-m32r/mmu.h b/include/asm-m32r/mmu.h index d9bd724479cf..150cb92bb666 100644 --- a/include/asm-m32r/mmu.h +++ b/include/asm-m32r/mmu.h @@ -4,7 +4,6 @@ #if !defined(CONFIG_MMU) typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/include/linux/mm.h b/include/linux/mm.h index 4a3d28c86443..b91a73fd1bcc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -56,19 +56,9 @@ extern unsigned long mmap_min_addr; extern struct kmem_cache *vm_area_cachep; -/* - * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is - * disabled, then there's a single shared list of VMAs maintained by the - * system, and mm's subscribe to these individually - */ -struct vm_list_struct { - struct vm_list_struct *next; - struct vm_area_struct *vma; -}; - #ifndef CONFIG_MMU -extern struct rb_root nommu_vma_tree; -extern struct rw_semaphore nommu_vma_sem; +extern struct rb_root nommu_region_tree; +extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif @@ -1061,6 +1051,7 @@ extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); extern void setup_per_zone_pages_min(void); extern void mem_init(void); +extern void __init mmap_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -1072,6 +1063,9 @@ extern void setup_per_cpu_pageset(void); static inline void setup_per_cpu_pageset(void) {} #endif +/* nommu.c */ +extern atomic_t mmap_pages_allocated; + /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9cfc9b627fdd..1c1e0d3a1714 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,22 @@ struct page { #endif /* WANT_PAGE_VIRTUAL */ }; +/* + * A region containing a mapping of a non-memory backed file under NOMMU + * conditions. These are held in a global tree and are pinned by the VMAs that + * map parts of them. + */ +struct vm_region { + struct rb_node vm_rb; /* link in global region tree */ + unsigned long vm_flags; /* VMA vm_flags */ + unsigned long vm_start; /* start address of region */ + unsigned long vm_end; /* region initialised to here */ + unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ + struct file *vm_file; /* the backing file or NULL */ + + atomic_t vm_usage; /* region usage count */ +}; + /* * This struct defines a memory VMM memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -152,7 +168,7 @@ struct vm_area_struct { unsigned long vm_truncate_count;/* truncate_count or restart_addr */ #ifndef CONFIG_MMU - atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */ + struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ diff --git a/ipc/shm.c b/ipc/shm.c index b125b560240e..d0ab5527bf45 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -990,6 +990,7 @@ asmlinkage long sys_shmdt(char __user *shmaddr) */ vma = find_vma(mm, addr); +#ifdef CONFIG_MMU while (vma) { next = vma->vm_next; @@ -1034,6 +1035,17 @@ asmlinkage long sys_shmdt(char __user *shmaddr) vma = next; } +#else /* CONFIG_MMU */ + /* under NOMMU conditions, the exact address to be destroyed must be + * given */ + retval = -EINVAL; + if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start); + retval = 0; + } + +#endif + up_write(&mm->mmap_sem); return retval; } diff --git a/kernel/fork.c b/kernel/fork.c index 7b8f2a78be3d..0bce4a43bb37 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1481,12 +1481,10 @@ void __init proc_caches_init(void) fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + mmap_init(); } /* diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2e75478e9c69..d0a32aab03ff 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -512,6 +512,13 @@ config DEBUG_VIRTUAL If unsure, say N. +config DEBUG_NOMMU_REGIONS + bool "Debug the global anon/private NOMMU mapping region tree" + depends on DEBUG_KERNEL && !MMU + help + This option causes the global tree of anonymous and private mapping + regions to be regularly checked for invalid topology. + config DEBUG_WRITECOUNT bool "Debug filesystem writers count" depends on DEBUG_KERNEL diff --git a/mm/mmap.c b/mm/mmap.c index a910c045cfd4..749623196cb9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2472,3 +2472,13 @@ void mm_drop_all_locks(struct mm_struct *mm) mutex_unlock(&mm_all_locks_mutex); } + +/* + * initialise the VMA slab + */ +void __init mmap_init(void) +{ + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL); +} diff --git a/mm/nommu.c b/mm/nommu.c index 23f355bbe262..0d363dfcf10e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -6,7 +6,7 @@ * * See Documentation/nommu-mmap.txt * - * Copyright (c) 2004-2005 David Howells + * Copyright (c) 2004-2008 David Howells * Copyright (c) 2000-2003 David McCullough * Copyright (c) 2000-2001 D Jeff Dionne * Copyright (c) 2002 Greg Ungerer @@ -33,6 +33,28 @@ #include #include #include +#include "internal.h" + +static inline __attribute__((format(printf, 1, 2))) +void no_printk(const char *fmt, ...) +{ +} + +#if 0 +#define kenter(FMT, ...) \ + printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) \ + printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) \ + printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__) +#else +#define kenter(FMT, ...) \ + no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) \ + no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) \ + no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__) +#endif #include "internal.h" @@ -46,12 +68,15 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int heap_stack_gap = 0; +atomic_t mmap_pages_allocated; + EXPORT_SYMBOL(mem_map); EXPORT_SYMBOL(num_physpages); -/* list of shareable VMAs */ -struct rb_root nommu_vma_tree = RB_ROOT; -DECLARE_RWSEM(nommu_vma_sem); +/* list of mapped, potentially shareable regions */ +static struct kmem_cache *vm_region_jar; +struct rb_root nommu_region_tree = RB_ROOT; +DECLARE_RWSEM(nommu_region_sem); struct vm_operations_struct generic_file_vm_ops = { }; @@ -400,129 +425,174 @@ asmlinkage unsigned long sys_brk(unsigned long brk) return mm->brk = brk; } -#ifdef DEBUG -static void show_process_blocks(void) +/* + * initialise the VMA and region record slabs + */ +void __init mmap_init(void) { - struct vm_list_struct *vml; - - printk("Process blocks %d:", current->pid); - - for (vml = ¤t->mm->context.vmlist; vml; vml = vml->next) { - printk(" %p: %p", vml, vml->vma); - if (vml->vma) - printk(" (%d @%lx #%d)", - kobjsize((void *) vml->vma->vm_start), - vml->vma->vm_start, - atomic_read(&vml->vma->vm_usage)); - printk(vml->next ? " ->" : ".\n"); - } + vm_region_jar = kmem_cache_create("vm_region_jar", + sizeof(struct vm_region), 0, + SLAB_PANIC, NULL); + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL); } -#endif /* DEBUG */ /* - * add a VMA into a process's mm_struct in the appropriate place in the list - * - should be called with mm->mmap_sem held writelocked + * validate the region tree + * - the caller must hold the region lock */ -static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml) +#ifdef CONFIG_DEBUG_NOMMU_REGIONS +static noinline void validate_nommu_regions(void) { - struct vm_list_struct **ppv; + struct vm_region *region, *last; + struct rb_node *p, *lastp; - for (ppv = ¤t->mm->context.vmlist; *ppv; ppv = &(*ppv)->next) - if ((*ppv)->vma->vm_start > vml->vma->vm_start) - break; + lastp = rb_first(&nommu_region_tree); + if (!lastp) + return; + + last = rb_entry(lastp, struct vm_region, vm_rb); + if (unlikely(last->vm_end <= last->vm_start)) + BUG(); + + while ((p = rb_next(lastp))) { + region = rb_entry(p, struct vm_region, vm_rb); + last = rb_entry(lastp, struct vm_region, vm_rb); + + if (unlikely(region->vm_end <= region->vm_start)) + BUG(); + if (unlikely(region->vm_start < last->vm_end)) + BUG(); - vml->next = *ppv; - *ppv = vml; + lastp = p; + } } +#else +#define validate_nommu_regions() do {} while(0) +#endif /* - * look up the first VMA in which addr resides, NULL if none - * - should be called with mm->mmap_sem at least held readlocked + * add a region into the global tree */ -struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +static void add_nommu_region(struct vm_region *region) { - struct vm_list_struct *loop, *vml; + struct vm_region *pregion; + struct rb_node **p, *parent; - /* search the vm_start ordered list */ - vml = NULL; - for (loop = mm->context.vmlist; loop; loop = loop->next) { - if (loop->vma->vm_start > addr) - break; - vml = loop; + validate_nommu_regions(); + + BUG_ON(region->vm_start & ~PAGE_MASK); + + parent = NULL; + p = &nommu_region_tree.rb_node; + while (*p) { + parent = *p; + pregion = rb_entry(parent, struct vm_region, vm_rb); + if (region->vm_start < pregion->vm_start) + p = &(*p)->rb_left; + else if (region->vm_start > pregion->vm_start) + p = &(*p)->rb_right; + else if (pregion == region) + return; + else + BUG(); } - if (vml && vml->vma->vm_end > addr) - return vml->vma; + rb_link_node(®ion->vm_rb, parent, p); + rb_insert_color(®ion->vm_rb, &nommu_region_tree); - return NULL; + validate_nommu_regions(); } -EXPORT_SYMBOL(find_vma); /* - * find a VMA - * - we don't extend stack VMAs under NOMMU conditions + * delete a region from the global tree */ -struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +static void delete_nommu_region(struct vm_region *region) { - return find_vma(mm, addr); -} + BUG_ON(!nommu_region_tree.rb_node); -int expand_stack(struct vm_area_struct *vma, unsigned long address) -{ - return -ENOMEM; + validate_nommu_regions(); + rb_erase(®ion->vm_rb, &nommu_region_tree); + validate_nommu_regions(); } /* - * look up the first VMA exactly that exactly matches addr - * - should be called with mm->mmap_sem at least held readlocked + * free a contiguous series of pages */ -static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm, - unsigned long addr) +static void free_page_series(unsigned long from, unsigned long to) { - struct vm_list_struct *vml; - - /* search the vm_start ordered list */ - for (vml = mm->context.vmlist; vml; vml = vml->next) { - if (vml->vma->vm_start == addr) - return vml->vma; - if (vml->vma->vm_start > addr) - break; + for (; from < to; from += PAGE_SIZE) { + struct page *page = virt_to_page(from); + + kdebug("- free %lx", from); + atomic_dec(&mmap_pages_allocated); + if (page_count(page) != 1) + kdebug("free page %p [%d]", page, page_count(page)); + put_page(page); } - - return NULL; } /* - * find a VMA in the global tree + * release a reference to a region + * - the caller must hold the region semaphore, which this releases + * - the region may not have been added to the tree yet, in which case vm_end + * will equal vm_start */ -static inline struct vm_area_struct *find_nommu_vma(unsigned long start) +static void __put_nommu_region(struct vm_region *region) + __releases(nommu_region_sem) { - struct vm_area_struct *vma; - struct rb_node *n = nommu_vma_tree.rb_node; + kenter("%p{%d}", region, atomic_read(®ion->vm_usage)); - while (n) { - vma = rb_entry(n, struct vm_area_struct, vm_rb); + BUG_ON(!nommu_region_tree.rb_node); - if (start < vma->vm_start) - n = n->rb_left; - else if (start > vma->vm_start) - n = n->rb_right; - else - return vma; + if (atomic_dec_and_test(®ion->vm_usage)) { + if (region->vm_end > region->vm_start) + delete_nommu_region(region); + up_write(&nommu_region_sem); + + if (region->vm_file) + fput(region->vm_file); + + /* IO memory and memory shared directly out of the pagecache + * from ramfs/tmpfs mustn't be released here */ + if (region->vm_flags & VM_MAPPED_COPY) { + kdebug("free series"); + free_page_series(region->vm_start, region->vm_end); + } + kmem_cache_free(vm_region_jar, region); + } else { + up_write(&nommu_region_sem); } +} - return NULL; +/* + * release a reference to a region + */ +static void put_nommu_region(struct vm_region *region) +{ + down_write(&nommu_region_sem); + __put_nommu_region(region); } /* - * add a VMA in the global tree + * add a VMA into a process's mm_struct in the appropriate place in the list + * and tree and add to the address space's page tree also if not an anonymous + * page + * - should be called with mm->mmap_sem held writelocked */ -static void add_nommu_vma(struct vm_area_struct *vma) +static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) { - struct vm_area_struct *pvma; + struct vm_area_struct *pvma, **pp; struct address_space *mapping; - struct rb_node **p = &nommu_vma_tree.rb_node; - struct rb_node *parent = NULL; + struct rb_node **p, *parent; + + kenter(",%p", vma); + + BUG_ON(!vma->vm_region); + + mm->map_count++; + vma->vm_mm = mm; /* add the VMA to the mapping */ if (vma->vm_file) { @@ -533,42 +603,62 @@ static void add_nommu_vma(struct vm_area_struct *vma) flush_dcache_mmap_unlock(mapping); } - /* add the VMA to the master list */ + /* add the VMA to the tree */ + parent = NULL; + p = &mm->mm_rb.rb_node; while (*p) { parent = *p; pvma = rb_entry(parent, struct vm_area_struct, vm_rb); - if (vma->vm_start < pvma->vm_start) { + /* sort by: start addr, end addr, VMA struct addr in that order + * (the latter is necessary as we may get identical VMAs) */ + if (vma->vm_start < pvma->vm_start) p = &(*p)->rb_left; - } - else if (vma->vm_start > pvma->vm_start) { + else if (vma->vm_start > pvma->vm_start) p = &(*p)->rb_right; - } - else { - /* mappings are at the same address - this can only - * happen for shared-mem chardevs and shared file - * mappings backed by ramfs/tmpfs */ - BUG_ON(!(pvma->vm_flags & VM_SHARED)); - - if (vma < pvma) - p = &(*p)->rb_left; - else if (vma > pvma) - p = &(*p)->rb_right; - else - BUG(); - } + else if (vma->vm_end < pvma->vm_end) + p = &(*p)->rb_left; + else if (vma->vm_end > pvma->vm_end) + p = &(*p)->rb_right; + else if (vma < pvma) + p = &(*p)->rb_left; + else if (vma > pvma) + p = &(*p)->rb_right; + else + BUG(); } rb_link_node(&vma->vm_rb, parent, p); - rb_insert_color(&vma->vm_rb, &nommu_vma_tree); + rb_insert_color(&vma->vm_rb, &mm->mm_rb); + + /* add VMA to the VMA list also */ + for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) { + if (pvma->vm_start > vma->vm_start) + break; + if (pvma->vm_start < vma->vm_start) + continue; + if (pvma->vm_end < vma->vm_end) + break; + } + + vma->vm_next = *pp; + *pp = vma; } /* - * delete a VMA from the global list + * delete a VMA from its owning mm_struct and address space */ -static void delete_nommu_vma(struct vm_area_struct *vma) +static void delete_vma_from_mm(struct vm_area_struct *vma) { + struct vm_area_struct **pp; struct address_space *mapping; + struct mm_struct *mm = vma->vm_mm; + + kenter("%p", vma); + + mm->map_count--; + if (mm->mmap_cache == vma) + mm->mmap_cache = NULL; /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -579,8 +669,115 @@ static void delete_nommu_vma(struct vm_area_struct *vma) flush_dcache_mmap_unlock(mapping); } - /* remove from the master list */ - rb_erase(&vma->vm_rb, &nommu_vma_tree); + /* remove from the MM's tree and list */ + rb_erase(&vma->vm_rb, &mm->mm_rb); + for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) { + if (*pp == vma) { + *pp = vma->vm_next; + break; + } + } + + vma->vm_mm = NULL; +} + +/* + * destroy a VMA record + */ +static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) +{ + kenter("%p", vma); + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) { + fput(vma->vm_file); + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(mm); + } + put_nommu_region(vma->vm_region); + kmem_cache_free(vm_area_cachep, vma); +} + +/* + * look up the first VMA in which addr resides, NULL if none + * - should be called with mm->mmap_sem at least held readlocked + */ +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + struct rb_node *n = mm->mm_rb.rb_node; + + /* check the cache first */ + vma = mm->mmap_cache; + if (vma && vma->vm_start <= addr && vma->vm_end > addr) + return vma; + + /* trawl the tree (there may be multiple mappings in which addr + * resides) */ + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + vma = rb_entry(n, struct vm_area_struct, vm_rb); + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end > addr) { + mm->mmap_cache = vma; + return vma; + } + } + + return NULL; +} +EXPORT_SYMBOL(find_vma); + +/* + * find a VMA + * - we don't extend stack VMAs under NOMMU conditions + */ +struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +/* + * expand a stack to a given address + * - not supported under NOMMU conditions + */ +int expand_stack(struct vm_area_struct *vma, unsigned long address) +{ + return -ENOMEM; +} + +/* + * look up the first VMA exactly that exactly matches addr + * - should be called with mm->mmap_sem at least held readlocked + */ +static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + struct vm_area_struct *vma; + struct rb_node *n = mm->mm_rb.rb_node; + unsigned long end = addr + len; + + /* check the cache first */ + vma = mm->mmap_cache; + if (vma && vma->vm_start == addr && vma->vm_end == end) + return vma; + + /* trawl the tree (there may be multiple mappings in which addr + * resides) */ + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + vma = rb_entry(n, struct vm_area_struct, vm_rb); + if (vma->vm_start < addr) + continue; + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end == end) { + mm->mmap_cache = vma; + return vma; + } + } + + return NULL; } /* @@ -595,7 +792,7 @@ static int validate_mmap_request(struct file *file, unsigned long pgoff, unsigned long *_capabilities) { - unsigned long capabilities; + unsigned long capabilities, rlen; unsigned long reqprot = prot; int ret; @@ -615,12 +812,12 @@ static int validate_mmap_request(struct file *file, return -EINVAL; /* Careful about overflows.. */ - len = PAGE_ALIGN(len); - if (!len || len > TASK_SIZE) + rlen = PAGE_ALIGN(len); + if (!rlen || rlen > TASK_SIZE) return -ENOMEM; /* offset overflow? */ - if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) + if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; if (file) { @@ -794,9 +991,10 @@ static unsigned long determine_vm_flags(struct file *file, } /* - * set up a shared mapping on a file + * set up a shared mapping on a file (the driver or filesystem provides and + * pins the storage) */ -static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len) +static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; @@ -814,10 +1012,14 @@ static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len) /* * set up a private mapping or an anonymous shared mapping */ -static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) +static int do_mmap_private(struct vm_area_struct *vma, + struct vm_region *region, + unsigned long len) { + struct page *pages; + unsigned long total, point, n, rlen; void *base; - int ret; + int ret, order; /* invoke the file's mapping function so that it can keep track of * shared mappings on devices or memory @@ -836,23 +1038,46 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) * make a private copy of the data and map that instead */ } + rlen = PAGE_ALIGN(len); + /* allocate some memory to hold the mapping * - note that this may not return a page-aligned address if the object * we're allocating is smaller than a page */ - base = kmalloc(len, GFP_KERNEL|__GFP_COMP); - if (!base) + order = get_order(rlen); + kdebug("alloc order %d for %lx", order, len); + + pages = alloc_pages(GFP_KERNEL, order); + if (!pages) goto enomem; - vma->vm_start = (unsigned long) base; - vma->vm_end = vma->vm_start + len; - vma->vm_flags |= VM_MAPPED_COPY; + /* we allocated a power-of-2 sized page set, so we need to trim off the + * excess */ + total = 1 << order; + atomic_add(total, &mmap_pages_allocated); + + point = rlen >> PAGE_SHIFT; + while (total > point) { + order = ilog2(total - point); + n = 1 << order; + kdebug("shave %lu/%lu @%lu", n, total - point, total); + atomic_sub(n, &mmap_pages_allocated); + total -= n; + set_page_refcounted(pages + total); + __free_pages(pages + total, order); + } + + total = rlen >> PAGE_SHIFT; + for (point = 1; point < total; point++) + set_page_refcounted(&pages[point]); -#ifdef WARN_ON_SLACK - if (len + WARN_ON_SLACK <= kobjsize(result)) - printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n", - len, current->pid, kobjsize(result) - len); -#endif + base = page_address(pages); + region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; + region->vm_start = (unsigned long) base; + region->vm_end = region->vm_start + rlen; + + vma->vm_start = region->vm_start; + vma->vm_end = region->vm_start + len; if (vma->vm_file) { /* read the contents of a file into the copy */ @@ -864,26 +1089,27 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) old_fs = get_fs(); set_fs(KERNEL_DS); - ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos); + ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos); set_fs(old_fs); if (ret < 0) goto error_free; /* clear the last little bit */ - if (ret < len) - memset(base + ret, 0, len - ret); + if (ret < rlen) + memset(base + ret, 0, rlen - ret); } else { /* if it's an anonymous mapping, then just clear it */ - memset(base, 0, len); + memset(base, 0, rlen); } return 0; error_free: - kfree(base); - vma->vm_start = 0; + free_page_series(region->vm_start, region->vm_end); + region->vm_start = vma->vm_start = 0; + region->vm_end = vma->vm_end = 0; return ret; enomem: @@ -903,13 +1129,14 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long flags, unsigned long pgoff) { - struct vm_list_struct *vml = NULL; - struct vm_area_struct *vma = NULL; + struct vm_area_struct *vma; + struct vm_region *region; struct rb_node *rb; - unsigned long capabilities, vm_flags; - void *result; + unsigned long capabilities, vm_flags, result; int ret; + kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff); + if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); @@ -917,73 +1144,120 @@ unsigned long do_mmap_pgoff(struct file *file, * mapping */ ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, &capabilities); - if (ret < 0) + if (ret < 0) { + kleave(" = %d [val]", ret); return ret; + } /* we've determined that we can make the mapping, now translate what we * now know into VMA flags */ vm_flags = determine_vm_flags(file, prot, flags, capabilities); - /* we're going to need to record the mapping if it works */ - vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL); - if (!vml) - goto error_getting_vml; + /* we're going to need to record the mapping */ + region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL); + if (!region) + goto error_getting_region; + + vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + if (!vma) + goto error_getting_vma; + + atomic_set(®ion->vm_usage, 1); + region->vm_flags = vm_flags; + region->vm_pgoff = pgoff; - down_write(&nommu_vma_sem); + INIT_LIST_HEAD(&vma->anon_vma_node); + vma->vm_flags = vm_flags; + vma->vm_pgoff = pgoff; - /* if we want to share, we need to check for VMAs created by other + if (file) { + region->vm_file = file; + get_file(file); + vma->vm_file = file; + get_file(file); + if (vm_flags & VM_EXECUTABLE) { + added_exe_file_vma(current->mm); + vma->vm_mm = current->mm; + } + } + + down_write(&nommu_region_sem); + + /* if we want to share, we need to check for regions created by other * mmap() calls that overlap with our proposed mapping - * - we can only share with an exact match on most regular files + * - we can only share with a superset match on most regular files * - shared mappings on character devices and memory backed files are * permitted to overlap inexactly as far as we are concerned for in * these cases, sharing is handled in the driver or filesystem rather * than here */ if (vm_flags & VM_MAYSHARE) { - unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long vmpglen; + struct vm_region *pregion; + unsigned long pglen, rpglen, pgend, rpgend, start; - /* suppress VMA sharing for shared regions */ - if (vm_flags & VM_SHARED && - capabilities & BDI_CAP_MAP_DIRECT) - goto dont_share_VMAs; + pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgend = pgoff + pglen; - for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) { - vma = rb_entry(rb, struct vm_area_struct, vm_rb); + for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) { + pregion = rb_entry(rb, struct vm_region, vm_rb); - if (!(vma->vm_flags & VM_MAYSHARE)) + if (!(pregion->vm_flags & VM_MAYSHARE)) continue; /* search for overlapping mappings on the same file */ - if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode) + if (pregion->vm_file->f_path.dentry->d_inode != + file->f_path.dentry->d_inode) continue; - if (vma->vm_pgoff >= pgoff + pglen) + if (pregion->vm_pgoff >= pgend) continue; - vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1; - vmpglen >>= PAGE_SHIFT; - if (pgoff >= vma->vm_pgoff + vmpglen) + rpglen = pregion->vm_end - pregion->vm_start; + rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT; + rpgend = pregion->vm_pgoff + rpglen; + if (pgoff >= rpgend) continue; - /* handle inexactly overlapping matches between mappings */ - if (vma->vm_pgoff != pgoff || vmpglen != pglen) { + /* handle inexactly overlapping matches between + * mappings */ + if ((pregion->vm_pgoff != pgoff || rpglen != pglen) && + !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) { + /* new mapping is not a subset of the region */ if (!(capabilities & BDI_CAP_MAP_DIRECT)) goto sharing_violation; continue; } - /* we've found a VMA we can share */ - atomic_inc(&vma->vm_usage); - - vml->vma = vma; - result = (void *) vma->vm_start; - goto shared; + /* we've found a region we can share */ + atomic_inc(&pregion->vm_usage); + vma->vm_region = pregion; + start = pregion->vm_start; + start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT; + vma->vm_start = start; + vma->vm_end = start + len; + + if (pregion->vm_flags & VM_MAPPED_COPY) { + kdebug("share copy"); + vma->vm_flags |= VM_MAPPED_COPY; + } else { + kdebug("share mmap"); + ret = do_mmap_shared_file(vma); + if (ret < 0) { + vma->vm_region = NULL; + vma->vm_start = 0; + vma->vm_end = 0; + atomic_dec(&pregion->vm_usage); + pregion = NULL; + goto error_just_free; + } + } + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + region = pregion; + result = start; + goto share; } - dont_share_VMAs: - vma = NULL; - /* obtain the address at which to make a shared mapping * - this is the hook for quasi-memory character devices to * tell us the location of a shared mapping @@ -994,102 +1268,93 @@ unsigned long do_mmap_pgoff(struct file *file, if (IS_ERR((void *) addr)) { ret = addr; if (ret != (unsigned long) -ENOSYS) - goto error; + goto error_just_free; /* the driver refused to tell us where to site * the mapping so we'll have to attempt to copy * it */ ret = (unsigned long) -ENODEV; if (!(capabilities & BDI_CAP_MAP_COPY)) - goto error; + goto error_just_free; capabilities &= ~BDI_CAP_MAP_DIRECT; + } else { + vma->vm_start = region->vm_start = addr; + vma->vm_end = region->vm_end = addr + len; } } } - /* we're going to need a VMA struct as well */ - vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL); - if (!vma) - goto error_getting_vma; - - INIT_LIST_HEAD(&vma->anon_vma_node); - atomic_set(&vma->vm_usage, 1); - if (file) { - get_file(file); - if (vm_flags & VM_EXECUTABLE) { - added_exe_file_vma(current->mm); - vma->vm_mm = current->mm; - } - } - vma->vm_file = file; - vma->vm_flags = vm_flags; - vma->vm_start = addr; - vma->vm_end = addr + len; - vma->vm_pgoff = pgoff; - - vml->vma = vma; + vma->vm_region = region; /* set up the mapping */ if (file && vma->vm_flags & VM_SHARED) - ret = do_mmap_shared_file(vma, len); + ret = do_mmap_shared_file(vma); else - ret = do_mmap_private(vma, len); + ret = do_mmap_private(vma, region, len); if (ret < 0) - goto error; + goto error_put_region; + + add_nommu_region(region); /* okay... we have a mapping; now we have to register it */ - result = (void *) vma->vm_start; + result = vma->vm_start; current->mm->total_vm += len >> PAGE_SHIFT; - add_nommu_vma(vma); +share: + add_vma_to_mm(current->mm, vma); - shared: - add_vma_to_mm(current->mm, vml); - - up_write(&nommu_vma_sem); + up_write(&nommu_region_sem); if (prot & PROT_EXEC) - flush_icache_range((unsigned long) result, - (unsigned long) result + len); + flush_icache_range(result, result + len); -#ifdef DEBUG - printk("do_mmap:\n"); - show_process_blocks(); -#endif + kleave(" = %lx", result); + return result; - return (unsigned long) result; - - error: - up_write(&nommu_vma_sem); - kfree(vml); +error_put_region: + __put_nommu_region(region); if (vma) { if (vma->vm_file) { fput(vma->vm_file); if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(vma->vm_mm); } - kfree(vma); + kmem_cache_free(vm_area_cachep, vma); } + kleave(" = %d [pr]", ret); return ret; - sharing_violation: - up_write(&nommu_vma_sem); - printk("Attempt to share mismatched mappings\n"); - kfree(vml); - return -EINVAL; +error_just_free: + up_write(&nommu_region_sem); +error: + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + fput(vma->vm_file); + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(vma->vm_mm); + kmem_cache_free(vm_area_cachep, vma); + kleave(" = %d", ret); + return ret; + +sharing_violation: + up_write(&nommu_region_sem); + printk(KERN_WARNING "Attempt to share mismatched mappings\n"); + ret = -EINVAL; + goto error; - error_getting_vma: - up_write(&nommu_vma_sem); - kfree(vml); - printk("Allocation of vma for %lu byte allocation from process %d failed\n", +error_getting_vma: + kmem_cache_free(vm_region_jar, region); + printk(KERN_WARNING "Allocation of vma for %lu byte allocation" + " from process %d failed\n", len, current->pid); show_free_areas(); return -ENOMEM; - error_getting_vml: - printk("Allocation of vml for %lu byte allocation from process %d failed\n", +error_getting_region: + printk(KERN_WARNING "Allocation of vm region for %lu byte allocation" + " from process %d failed\n", len, current->pid); show_free_areas(); return -ENOMEM; @@ -1097,77 +1362,180 @@ unsigned long do_mmap_pgoff(struct file *file, EXPORT_SYMBOL(do_mmap_pgoff); /* - * handle mapping disposal for uClinux + * split a vma into two pieces at address 'addr', a new vma is allocated either + * for the first part or the tail. */ -static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma) +int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, int new_below) { - if (vma) { - down_write(&nommu_vma_sem); + struct vm_area_struct *new; + struct vm_region *region; + unsigned long npages; - if (atomic_dec_and_test(&vma->vm_usage)) { - delete_nommu_vma(vma); + kenter(""); - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + /* we're only permitted to split anonymous regions that have a single + * owner */ + if (vma->vm_file || + atomic_read(&vma->vm_region->vm_usage) != 1) + return -ENOMEM; - /* IO memory and memory shared directly out of the pagecache from - * ramfs/tmpfs mustn't be released here */ - if (vma->vm_flags & VM_MAPPED_COPY) - kfree((void *) vma->vm_start); + if (mm->map_count >= sysctl_max_map_count) + return -ENOMEM; - if (vma->vm_file) { - fput(vma->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); - } - kfree(vma); - } + region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL); + if (!region) + return -ENOMEM; + + new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + if (!new) { + kmem_cache_free(vm_region_jar, region); + return -ENOMEM; + } + + /* most fields are the same, copy all, and then fixup */ + *new = *vma; + *region = *vma->vm_region; + new->vm_region = region; + + npages = (addr - vma->vm_start) >> PAGE_SHIFT; + + if (new_below) { + region->vm_end = new->vm_end = addr; + } else { + region->vm_start = new->vm_start = addr; + region->vm_pgoff = new->vm_pgoff += npages; + } - up_write(&nommu_vma_sem); + if (new->vm_ops && new->vm_ops->open) + new->vm_ops->open(new); + + delete_vma_from_mm(vma); + down_write(&nommu_region_sem); + delete_nommu_region(vma->vm_region); + if (new_below) { + vma->vm_region->vm_start = vma->vm_start = addr; + vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; + } else { + vma->vm_region->vm_end = vma->vm_end = addr; } + add_nommu_region(vma->vm_region); + add_nommu_region(new->vm_region); + up_write(&nommu_region_sem); + add_vma_to_mm(mm, vma); + add_vma_to_mm(mm, new); + return 0; } /* - * release a mapping - * - under NOMMU conditions the parameters must match exactly to the mapping to - * be removed + * shrink a VMA by removing the specified chunk from either the beginning or + * the end */ -int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) +static int shrink_vma(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long from, unsigned long to) { - struct vm_list_struct *vml, **parent; - unsigned long end = addr + len; + struct vm_region *region; -#ifdef DEBUG - printk("do_munmap:\n"); -#endif + kenter(""); - for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) { - if ((*parent)->vma->vm_start > addr) - break; - if ((*parent)->vma->vm_start == addr && - ((len == 0) || ((*parent)->vma->vm_end == end))) - goto found; - } + /* adjust the VMA's pointers, which may reposition it in the MM's tree + * and list */ + delete_vma_from_mm(vma); + if (from > vma->vm_start) + vma->vm_end = from; + else + vma->vm_start = to; + add_vma_to_mm(mm, vma); - printk("munmap of non-mmaped memory by process %d (%s): %p\n", - current->pid, current->comm, (void *) addr); - return -EINVAL; + /* cut the backing region down to size */ + region = vma->vm_region; + BUG_ON(atomic_read(®ion->vm_usage) != 1); - found: - vml = *parent; + down_write(&nommu_region_sem); + delete_nommu_region(region); + if (from > region->vm_start) + region->vm_end = from; + else + region->vm_start = to; + add_nommu_region(region); + up_write(&nommu_region_sem); - put_vma(mm, vml->vma); + free_page_series(from, to); + return 0; +} - *parent = vml->next; - kfree(vml); +/* + * release a mapping + * - under NOMMU conditions the chunk to be unmapped must be backed by a single + * VMA, though it need not cover the whole VMA + */ +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) +{ + struct vm_area_struct *vma; + struct rb_node *rb; + unsigned long end = start + len; + int ret; - update_hiwater_vm(mm); - mm->total_vm -= len >> PAGE_SHIFT; + kenter(",%lx,%zx", start, len); -#ifdef DEBUG - show_process_blocks(); -#endif + if (len == 0) + return -EINVAL; + + /* find the first potentially overlapping VMA */ + vma = find_vma(mm, start); + if (!vma) { + printk(KERN_WARNING + "munmap of memory not mmapped by process %d (%s):" + " 0x%lx-0x%lx\n", + current->pid, current->comm, start, start + len - 1); + return -EINVAL; + } + /* we're allowed to split an anonymous VMA but not a file-backed one */ + if (vma->vm_file) { + do { + if (start > vma->vm_start) { + kleave(" = -EINVAL [miss]"); + return -EINVAL; + } + if (end == vma->vm_end) + goto erase_whole_vma; + rb = rb_next(&vma->vm_rb); + vma = rb_entry(rb, struct vm_area_struct, vm_rb); + } while (rb); + kleave(" = -EINVAL [split file]"); + return -EINVAL; + } else { + /* the chunk must be a subset of the VMA found */ + if (start == vma->vm_start && end == vma->vm_end) + goto erase_whole_vma; + if (start < vma->vm_start || end > vma->vm_end) { + kleave(" = -EINVAL [superset]"); + return -EINVAL; + } + if (start & ~PAGE_MASK) { + kleave(" = -EINVAL [unaligned start]"); + return -EINVAL; + } + if (end != vma->vm_end && end & ~PAGE_MASK) { + kleave(" = -EINVAL [unaligned split]"); + return -EINVAL; + } + if (start != vma->vm_start && end != vma->vm_end) { + ret = split_vma(mm, vma, start, 1); + if (ret < 0) { + kleave(" = %d [split]", ret); + return ret; + } + } + return shrink_vma(mm, vma, start, end); + } + +erase_whole_vma: + delete_vma_from_mm(vma); + delete_vma(mm, vma); + kleave(" = 0"); return 0; } EXPORT_SYMBOL(do_munmap); @@ -1184,29 +1552,26 @@ asmlinkage long sys_munmap(unsigned long addr, size_t len) } /* - * Release all mappings + * release all the mappings made in a process's VM space */ -void exit_mmap(struct mm_struct * mm) +void exit_mmap(struct mm_struct *mm) { - struct vm_list_struct *tmp; + struct vm_area_struct *vma; - if (mm) { -#ifdef DEBUG - printk("Exit_mmap:\n"); -#endif + if (!mm) + return; - mm->total_vm = 0; + kenter(""); - while ((tmp = mm->context.vmlist)) { - mm->context.vmlist = tmp->next; - put_vma(mm, tmp->vma); - kfree(tmp); - } + mm->total_vm = 0; -#ifdef DEBUG - show_process_blocks(); -#endif + while ((vma = mm->mmap)) { + mm->mmap = vma->vm_next; + delete_vma_from_mm(vma); + delete_vma(mm, vma); } + + kleave(""); } unsigned long do_brk(unsigned long addr, unsigned long len) @@ -1219,8 +1584,8 @@ unsigned long do_brk(unsigned long addr, unsigned long len) * time (controlled by the MREMAP_MAYMOVE flag and available VM space) * * under NOMMU conditions, we only permit changing a mapping's size, and only - * as long as it stays within the hole allocated by the kmalloc() call in - * do_mmap_pgoff() and the block is not shareable + * as long as it stays within the region allocated by do_mmap_private() and the + * block is not shareable * * MREMAP_FIXED is not supported under NOMMU conditions */ @@ -1231,13 +1596,16 @@ unsigned long do_mremap(unsigned long addr, struct vm_area_struct *vma; /* insanity checks first */ - if (new_len == 0) + if (old_len == 0 || new_len == 0) return (unsigned long) -EINVAL; + if (addr & ~PAGE_MASK) + return -EINVAL; + if (flags & MREMAP_FIXED && new_addr != addr) return (unsigned long) -EINVAL; - vma = find_vma_exact(current->mm, addr); + vma = find_vma_exact(current->mm, addr, old_len); if (!vma) return (unsigned long) -EINVAL; @@ -1247,19 +1615,19 @@ unsigned long do_mremap(unsigned long addr, if (vma->vm_flags & VM_MAYSHARE) return (unsigned long) -EPERM; - if (new_len > kobjsize((void *) addr)) + if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start) return (unsigned long) -ENOMEM; /* all checks complete - do it */ vma->vm_end = vma->vm_start + new_len; - return vma->vm_start; } EXPORT_SYMBOL(do_mremap); -asmlinkage unsigned long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr) +asmlinkage +unsigned long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr) { unsigned long ret; -- cgit v1.2.3 From a6684999f7c6bddd75cf9755ad7ff44435f72fff Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 7 Jan 2009 18:08:50 -0800 Subject: mqueue: fix si_pid value in mqueue do_notify() If a process registers for asynchronous notification on a POSIX message queue, it gets a signal and a siginfo_t structure when a message arrives on the message queue. The si_pid in the siginfo_t structure is set to the PID of the process that sent the message to the message queue. The principle is the following: . when mq_notify(SIGEV_SIGNAL) is called, the caller registers for notification when a msg arrives. The associated pid structure is stroed into inode_info->notify_owner. Let's call this process P1. . when mq_send() is called by say P2, P2 sends a signal to P1 to notify him about msg arrival. The way .si_pid is set today is not correct, since it doesn't take into account the fact that the process that is sending the message might not be in the same namespace as the notified one. This patch proposes to set si_pid to the sender's pid into the notify_owner namespace. Signed-off-by: Nadia Derbey Signed-off-by: Sukadev Bhattiprolu Acked-by: Oleg Nesterov Cc: Roland McGrath Cc: Bastian Blank Cc: Pavel Emelyanov Cc: Eric W. Biederman Acked-by: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/mqueue.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'ipc') diff --git a/ipc/mqueue.c b/ipc/mqueue.c index eddb6247a553..23fdb8492b8e 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -505,7 +505,8 @@ static void __do_notify(struct mqueue_inode_info *info) sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; - sig_i.si_pid = task_tgid_vnr(current); + sig_i.si_pid = task_tgid_nr_ns(current, + ns_of_pid(info->notify_owner)); sig_i.si_uid = current_uid(); kill_pid_info(info->notify.sigev_signo, -- cgit v1.2.3 From 2ed7c03ec17779afb4fcfa3b8c61df61bd4879ba Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 14 Jan 2009 14:13:54 +0100 Subject: [CVE-2009-0029] Convert all system calls to return a long Convert all system calls to return a long. This should be a NOP since all converted types should have the same size anyway. With the exception of sys_exit_group which returned void. But that doesn't matter since the system call doesn't return. Signed-off-by: Heiko Carstens --- fs/read_write.c | 18 +++++------ fs/xattr.c | 12 ++++---- include/linux/syscalls.h | 79 ++++++++++++++++++++++++------------------------ ipc/mqueue.c | 2 +- kernel/exit.c | 4 ++- kernel/signal.c | 2 +- kernel/timer.c | 2 +- mm/filemap.c | 2 +- mm/mmap.c | 2 +- mm/mremap.c | 2 +- mm/nommu.c | 2 +- 11 files changed, 64 insertions(+), 63 deletions(-) (limited to 'ipc') diff --git a/fs/read_write.c b/fs/read_write.c index 5cc6924eb158..940367f51f2a 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -147,7 +147,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int origin) } EXPORT_SYMBOL(vfs_llseek); -asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, unsigned int origin) +asmlinkage long sys_lseek(unsigned int fd, off_t offset, unsigned int origin) { off_t retval; struct file * file; @@ -369,7 +369,7 @@ static inline void file_pos_write(struct file *file, loff_t pos) file->f_pos = pos; } -asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count) +asmlinkage long sys_read(unsigned int fd, char __user * buf, size_t count) { struct file *file; ssize_t ret = -EBADF; @@ -386,7 +386,7 @@ asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count) return ret; } -asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t count) +asmlinkage long sys_write(unsigned int fd, const char __user * buf, size_t count) { struct file *file; ssize_t ret = -EBADF; @@ -403,7 +403,7 @@ asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t co return ret; } -asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf, +asmlinkage long sys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { struct file *file; @@ -424,7 +424,7 @@ asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf, return ret; } -asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf, +asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { struct file *file; @@ -672,7 +672,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, EXPORT_SYMBOL(vfs_writev); -asmlinkage ssize_t +asmlinkage long sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) { struct file *file; @@ -693,7 +693,7 @@ sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) return ret; } -asmlinkage ssize_t +asmlinkage long sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) { struct file *file; @@ -812,7 +812,7 @@ out: return retval; } -asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, size_t count) +asmlinkage long sys_sendfile(int out_fd, int in_fd, off_t __user *offset, size_t count) { loff_t pos; off_t off; @@ -831,7 +831,7 @@ asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, siz return do_sendfile(out_fd, in_fd, NULL, count, 0); } -asmlinkage ssize_t sys_sendfile64(int out_fd, int in_fd, loff_t __user *offset, size_t count) +asmlinkage long sys_sendfile64(int out_fd, int in_fd, loff_t __user *offset, size_t count) { loff_t pos; ssize_t ret; diff --git a/fs/xattr.c b/fs/xattr.c index 237804cd6b56..d049ae27aae7 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -349,7 +349,7 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, return error; } -asmlinkage ssize_t +asmlinkage long sys_getxattr(const char __user *pathname, const char __user *name, void __user *value, size_t size) { @@ -364,7 +364,7 @@ sys_getxattr(const char __user *pathname, const char __user *name, return error; } -asmlinkage ssize_t +asmlinkage long sys_lgetxattr(const char __user *pathname, const char __user *name, void __user *value, size_t size) { @@ -379,7 +379,7 @@ sys_lgetxattr(const char __user *pathname, const char __user *name, void __user return error; } -asmlinkage ssize_t +asmlinkage long sys_fgetxattr(int fd, const char __user *name, void __user *value, size_t size) { struct file *f; @@ -424,7 +424,7 @@ listxattr(struct dentry *d, char __user *list, size_t size) return error; } -asmlinkage ssize_t +asmlinkage long sys_listxattr(const char __user *pathname, char __user *list, size_t size) { struct path path; @@ -438,7 +438,7 @@ sys_listxattr(const char __user *pathname, char __user *list, size_t size) return error; } -asmlinkage ssize_t +asmlinkage long sys_llistxattr(const char __user *pathname, char __user *list, size_t size) { struct path path; @@ -452,7 +452,7 @@ sys_llistxattr(const char __user *pathname, char __user *list, size_t size) return error; } -asmlinkage ssize_t +asmlinkage long sys_flistxattr(int fd, char __user *list, size_t size) { struct file *f; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a7593f670ca6..22290eeaf553 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -77,7 +77,7 @@ asmlinkage long sys_times(struct tms __user *tbuf); asmlinkage long sys_gettid(void); asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp); -asmlinkage unsigned long sys_alarm(unsigned int seconds); +asmlinkage long sys_alarm(unsigned int seconds); asmlinkage long sys_getpid(void); asmlinkage long sys_getppid(void); asmlinkage long sys_getuid(void); @@ -166,7 +166,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, unsigned long flags); asmlinkage long sys_exit(int error_code); -asmlinkage void sys_exit_group(int error_code); +asmlinkage long sys_exit_group(int error_code); asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, int options, struct rusage __user *ru); asmlinkage long sys_waitid(int which, pid_t pid, @@ -196,7 +196,7 @@ asmlinkage long sys_tkill(int pid, int sig); asmlinkage long sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo); asmlinkage long sys_sgetmask(void); asmlinkage long sys_ssetmask(int newmask); -asmlinkage unsigned long sys_signal(int sig, __sighandler_t handler); +asmlinkage long sys_signal(int sig, __sighandler_t handler); asmlinkage long sys_pause(void); asmlinkage long sys_sync(void); @@ -246,29 +246,29 @@ asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_fsetxattr(int fd, const char __user *name, const void __user *value, size_t size, int flags); -asmlinkage ssize_t sys_getxattr(const char __user *path, const char __user *name, - void __user *value, size_t size); -asmlinkage ssize_t sys_lgetxattr(const char __user *path, const char __user *name, - void __user *value, size_t size); -asmlinkage ssize_t sys_fgetxattr(int fd, const char __user *name, - void __user *value, size_t size); -asmlinkage ssize_t sys_listxattr(const char __user *path, char __user *list, - size_t size); -asmlinkage ssize_t sys_llistxattr(const char __user *path, char __user *list, - size_t size); -asmlinkage ssize_t sys_flistxattr(int fd, char __user *list, size_t size); +asmlinkage long sys_getxattr(const char __user *path, const char __user *name, + void __user *value, size_t size); +asmlinkage long sys_lgetxattr(const char __user *path, const char __user *name, + void __user *value, size_t size); +asmlinkage long sys_fgetxattr(int fd, const char __user *name, + void __user *value, size_t size); +asmlinkage long sys_listxattr(const char __user *path, char __user *list, + size_t size); +asmlinkage long sys_llistxattr(const char __user *path, char __user *list, + size_t size); +asmlinkage long sys_flistxattr(int fd, char __user *list, size_t size); asmlinkage long sys_removexattr(const char __user *path, const char __user *name); asmlinkage long sys_lremovexattr(const char __user *path, const char __user *name); asmlinkage long sys_fremovexattr(int fd, const char __user *name); -asmlinkage unsigned long sys_brk(unsigned long brk); +asmlinkage long sys_brk(unsigned long brk); asmlinkage long sys_mprotect(unsigned long start, size_t len, unsigned long prot); -asmlinkage unsigned long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr); +asmlinkage long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); @@ -321,10 +321,10 @@ asmlinkage long sys_io_submit(aio_context_t, long, struct iocb __user * __user *); asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, struct io_event __user *result); -asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, - off_t __user *offset, size_t count); -asmlinkage ssize_t sys_sendfile64(int out_fd, int in_fd, - loff_t __user *offset, size_t count); +asmlinkage long sys_sendfile(int out_fd, int in_fd, + off_t __user *offset, size_t count); +asmlinkage long sys_sendfile64(int out_fd, int in_fd, + loff_t __user *offset, size_t count); asmlinkage long sys_readlink(const char __user *path, char __user *buf, int bufsiz); asmlinkage long sys_creat(const char __user *pathname, int mode); @@ -368,26 +368,25 @@ asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times); asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes); -asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, - unsigned int origin); +asmlinkage long sys_lseek(unsigned int fd, off_t offset, + unsigned int origin); asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high, unsigned long offset_low, loff_t __user *result, unsigned int origin); -asmlinkage ssize_t sys_read(unsigned int fd, char __user *buf, - size_t count); -asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count); -asmlinkage ssize_t sys_readv(unsigned long fd, - const struct iovec __user *vec, - unsigned long vlen); -asmlinkage ssize_t sys_write(unsigned int fd, const char __user *buf, - size_t count); -asmlinkage ssize_t sys_writev(unsigned long fd, - const struct iovec __user *vec, - unsigned long vlen); -asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf, - size_t count, loff_t pos); -asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf, - size_t count, loff_t pos); +asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count); +asmlinkage long sys_readahead(int fd, loff_t offset, size_t count); +asmlinkage long sys_readv(unsigned long fd, + const struct iovec __user *vec, + unsigned long vlen); +asmlinkage long sys_write(unsigned int fd, const char __user *buf, + size_t count); +asmlinkage long sys_writev(unsigned long fd, + const struct iovec __user *vec, + unsigned long vlen); +asmlinkage long sys_pread64(unsigned int fd, char __user *buf, + size_t count, loff_t pos); +asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, + size_t count, loff_t pos); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); @@ -476,7 +475,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); asmlinkage long sys_mq_open(const char __user *name, int oflag, mode_t mode, struct mq_attr __user *attr); asmlinkage long sys_mq_unlink(const char __user *name); asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout); -asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); +asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 23fdb8492b8e..6df028b70543 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -907,7 +907,7 @@ out: return ret; } -asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, +asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout) { diff --git a/kernel/exit.c b/kernel/exit.c index c7740fa3252c..fac9b040af2c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1182,9 +1182,11 @@ do_group_exit(int exit_code) * 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) +asmlinkage long sys_exit_group(int error_code) { do_group_exit((error_code & 0xff) << 8); + /* NOTREACHED */ + return 0; } static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) diff --git a/kernel/signal.c b/kernel/signal.c index 3152ac3b62e2..856a5479d49d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2559,7 +2559,7 @@ sys_ssetmask(int newmask) /* * For backwards compatibility. Functionality superseded by sigaction. */ -asmlinkage unsigned long +asmlinkage long sys_signal(int sig, __sighandler_t handler) { struct k_sigaction new_sa, old_sa; diff --git a/kernel/timer.c b/kernel/timer.c index dee3f641a7a7..7b8697d7f04d 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1129,7 +1129,7 @@ void do_timer(unsigned long ticks) * For backwards compatibility? This can be done in libc so Alpha * and all newer ports shouldn't need it. */ -asmlinkage unsigned long sys_alarm(unsigned int seconds) +asmlinkage long sys_alarm(unsigned int seconds) { return alarm_setitimer(seconds); } diff --git a/mm/filemap.c b/mm/filemap.c index ceba0bd03662..538b75ed6236 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1374,7 +1374,7 @@ do_readahead(struct address_space *mapping, struct file *filp, return 0; } -asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count) +asmlinkage long sys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; struct file *file; diff --git a/mm/mmap.c b/mm/mmap.c index 749623196cb9..a970d890cb21 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -245,7 +245,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) return next; } -asmlinkage unsigned long sys_brk(unsigned long brk) +asmlinkage long sys_brk(unsigned long brk) { unsigned long rlim, retval; unsigned long newbrk, oldbrk; diff --git a/mm/mremap.c b/mm/mremap.c index 646de959aa58..5572e0825d80 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -420,7 +420,7 @@ out_nc: return ret; } -asmlinkage unsigned long sys_mremap(unsigned long addr, +asmlinkage long sys_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr) { diff --git a/mm/nommu.c b/mm/nommu.c index 60ed8375c986..ee3e78927739 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -416,7 +416,7 @@ EXPORT_SYMBOL(vm_insert_page); * to a regular file. in this case, the unmapping will need * to invoke file system routines that need the global lock. */ -asmlinkage unsigned long sys_brk(unsigned long brk) +asmlinkage long sys_brk(unsigned long brk) { struct mm_struct *mm = current->mm; -- cgit v1.2.3 From 6673e0c3fbeaed2cd08e2fd4a4aa97382d6fedb0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 14 Jan 2009 14:14:02 +0100 Subject: [CVE-2009-0029] System call wrapper special cases System calls with an unsigned long long argument can't be converted with the standard wrappers since that would include a cast to long, which in turn means that we would lose the upper 32 bit on 32 bit architectures. Also semctl can't use the standard wrapper since it has a 'union' parameter. So we handle them as special case and add some extra wrappers instead. Signed-off-by: Heiko Carstens --- fs/dcookies.c | 10 ++++++++-- fs/open.c | 27 ++++++++++++++++++++++++--- fs/read_write.c | 24 ++++++++++++++++++++---- fs/sync.c | 26 ++++++++++++++++++++++---- ipc/sem.c | 9 ++++++++- mm/fadvise.c | 18 ++++++++++++++++-- mm/filemap.c | 9 ++++++++- 7 files changed, 106 insertions(+), 17 deletions(-) (limited to 'ipc') diff --git a/fs/dcookies.c b/fs/dcookies.c index 180e9fec4ad8..a21cabdbd87b 100644 --- a/fs/dcookies.c +++ b/fs/dcookies.c @@ -145,7 +145,7 @@ out: /* And here is where the userspace process can look up the cookie value * to retrieve the path. */ -asmlinkage long sys_lookup_dcookie(u64 cookie64, char __user * buf, size_t len) +SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len) { unsigned long cookie = (unsigned long)cookie64; int err = -EINVAL; @@ -198,7 +198,13 @@ out: mutex_unlock(&dcookie_mutex); return err; } - +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_lookup_dcookie(u64 cookie64, long buf, long len) +{ + return SYSC_lookup_dcookie(cookie64, (char __user *) buf, (size_t) len); +} +SYSCALL_ALIAS(sys_lookup_dcookie, SyS_lookup_dcookie); +#endif static int dcookie_init(void) { diff --git a/fs/open.c b/fs/open.c index d882fd2351d6..e349013fc790 100644 --- a/fs/open.c +++ b/fs/open.c @@ -351,21 +351,35 @@ asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length) /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 -asmlinkage long sys_truncate64(const char __user * path, loff_t length) +SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length) { return do_sys_truncate(path, length); } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_truncate64(long path, loff_t length) +{ + return SYSC_truncate64((const char __user *) path, length); +} +SYSCALL_ALIAS(sys_truncate64, SyS_truncate64); +#endif -asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length) +SYSCALL_DEFINE(ftruncate64)(unsigned int fd, loff_t length) { long ret = do_sys_ftruncate(fd, length, 0); /* avoid REGPARM breakage on x86: */ asmlinkage_protect(2, ret, fd, length); return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_ftruncate64(long fd, loff_t length) +{ + return SYSC_ftruncate64((unsigned int) fd, length); +} +SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64); #endif +#endif /* BITS_PER_LONG == 32 */ -asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len) +SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) { struct file *file; struct inode *inode; @@ -422,6 +436,13 @@ out_fput: out: return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len) +{ + return SYSC_fallocate((int)fd, (int)mode, offset, len); +} +SYSCALL_ALIAS(sys_fallocate, SyS_fallocate); +#endif /* * access() needs to use the real uid/gid, not the effective uid/gid. diff --git a/fs/read_write.c b/fs/read_write.c index 940367f51f2a..7a8326bc5903 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -403,8 +403,8 @@ asmlinkage long sys_write(unsigned int fd, const char __user * buf, size_t count return ret; } -asmlinkage long sys_pread64(unsigned int fd, char __user *buf, - size_t count, loff_t pos) +SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf, + size_t count, loff_t pos) { struct file *file; ssize_t ret = -EBADF; @@ -423,9 +423,17 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos) +{ + return SYSC_pread64((unsigned int) fd, (char __user *) buf, + (size_t) count, pos); +} +SYSCALL_ALIAS(sys_pread64, SyS_pread64); +#endif -asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, - size_t count, loff_t pos) +SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf, + size_t count, loff_t pos) { struct file *file; ssize_t ret = -EBADF; @@ -444,6 +452,14 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos) +{ + return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf, + (size_t) count, pos); +} +SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64); +#endif /* * Reduce an iovec's length in-place. Return the resulting number of segments diff --git a/fs/sync.c b/fs/sync.c index ac02b56548bc..23ebbd72ecc9 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -201,8 +201,8 @@ asmlinkage long sys_fdatasync(unsigned int fd) * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ -asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, - unsigned int flags) +SYSCALL_DEFINE(sync_file_range)(int fd, loff_t offset, loff_t nbytes, + unsigned int flags) { int ret; struct file *file; @@ -262,14 +262,32 @@ out_put: out: return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_sync_file_range(long fd, loff_t offset, loff_t nbytes, + long flags) +{ + return SYSC_sync_file_range((int) fd, offset, nbytes, + (unsigned int) flags); +} +SYSCALL_ALIAS(sys_sync_file_range, SyS_sync_file_range); +#endif /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ -asmlinkage long sys_sync_file_range2(int fd, unsigned int flags, - loff_t offset, loff_t nbytes) +SYSCALL_DEFINE(sync_file_range2)(int fd, unsigned int flags, + loff_t offset, loff_t nbytes) { return sys_sync_file_range(fd, offset, nbytes, flags); } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_sync_file_range2(long fd, long flags, + loff_t offset, loff_t nbytes) +{ + return SYSC_sync_file_range2((int) fd, (unsigned int) flags, + offset, nbytes); +} +SYSCALL_ALIAS(sys_sync_file_range2, SyS_sync_file_range2); +#endif /* * `endbyte' is inclusive diff --git a/ipc/sem.c b/ipc/sem.c index c68cd3f8f0c9..c385c40c061c 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -887,7 +887,7 @@ out_up: return err; } -asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) +SYSCALL_DEFINE(semctl)(int semid, int semnum, int cmd, union semun arg) { int err = -EINVAL; int version; @@ -923,6 +923,13 @@ asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg) return -EINVAL; } } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_semctl(int semid, int semnum, int cmd, union semun arg) +{ + return SYSC_semctl((int) semid, (int) semnum, (int) cmd, arg); +} +SYSCALL_ALIAS(sys_semctl, SyS_semctl); +#endif /* If the task doesn't already have a undo_list, then allocate one * here. We guarantee there is only one thread using this undo list, diff --git a/mm/fadvise.c b/mm/fadvise.c index a1da969bd980..54a0f8040afa 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -24,7 +24,7 @@ * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could * deactivate the pages and clear PG_Referenced. */ -asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) { struct file *file = fget(fd); struct address_space *mapping; @@ -126,12 +126,26 @@ out: fput(file); return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_fadvise64_64(long fd, loff_t offset, loff_t len, long advice) +{ + return SYSC_fadvise64_64((int) fd, offset, len, (int) advice); +} +SYSCALL_ALIAS(sys_fadvise64_64, SyS_fadvise64_64); +#endif #ifdef __ARCH_WANT_SYS_FADVISE64 -asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice) +SYSCALL_DEFINE(fadvise64)(int fd, loff_t offset, size_t len, int advice) { return sys_fadvise64_64(fd, offset, len, advice); } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_fadvise64(long fd, loff_t offset, long len, long advice) +{ + return SYSC_fadvise64((int) fd, offset, (size_t)len, (int)advice); +} +SYSCALL_ALIAS(sys_fadvise64, SyS_fadvise64); +#endif #endif diff --git a/mm/filemap.c b/mm/filemap.c index 538b75ed6236..23acefe51808 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1374,7 +1374,7 @@ do_readahead(struct address_space *mapping, struct file *filp, return 0; } -asmlinkage long sys_readahead(int fd, loff_t offset, size_t count) +SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count) { ssize_t ret; struct file *file; @@ -1393,6 +1393,13 @@ asmlinkage long sys_readahead(int fd, loff_t offset, size_t count) } return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_readahead(long fd, loff_t offset, long count) +{ + return SYSC_readahead((int) fd, offset, (size_t) count); +} +SYSCALL_ALIAS(sys_readahead, SyS_readahead); +#endif #ifdef CONFIG_MMU /** -- cgit v1.2.3 From e48fbb699f82ef1e80bd7126046394d2dc9ca7e6 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 14 Jan 2009 14:14:26 +0100 Subject: [CVE-2009-0029] System call wrappers part 24 Signed-off-by: Heiko Carstens --- ipc/msg.c | 12 ++++++------ kernel/sys.c | 13 +++++++------ 2 files changed, 13 insertions(+), 12 deletions(-) (limited to 'ipc') diff --git a/ipc/msg.c b/ipc/msg.c index b4eee1c6101d..2ceab7f12fcb 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -309,7 +309,7 @@ static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg) return security_msg_queue_associate(msq, msgflg); } -asmlinkage long sys_msgget(key_t key, int msgflg) +SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) { struct ipc_namespace *ns; struct ipc_ops msg_ops; @@ -466,7 +466,7 @@ out_up: return err; } -asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) +SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { struct msg_queue *msq; int err, version; @@ -723,8 +723,8 @@ out_free: return err; } -asmlinkage long -sys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) +SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, + int, msgflg) { long mtype; @@ -904,8 +904,8 @@ out_unlock: return msgsz; } -asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, - long msgtyp, int msgflg) +SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, + long, msgtyp, int, msgflg) { long err, mtype; diff --git a/kernel/sys.c b/kernel/sys.c index 5292f2119da4..70ffa8408cd4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1395,7 +1395,7 @@ EXPORT_SYMBOL(in_egroup_p); DECLARE_RWSEM(uts_sem); -asmlinkage long sys_newuname(struct new_utsname __user * name) +SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { int errno = 0; @@ -1478,7 +1478,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) return errno; } -asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim) +SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { if (resource >= RLIM_NLIMITS) return -EINVAL; @@ -1497,7 +1497,8 @@ asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim) * Back compatibility for getrlimit. Needed for some apps. */ -asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim) +SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, + struct rlimit __user *, rlim) { struct rlimit x; if (resource >= RLIM_NLIMITS) @@ -1515,7 +1516,7 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r #endif -asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) +SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim, *old_rlim; int retval; @@ -1688,7 +1689,7 @@ int getrusage(struct task_struct *p, int who, struct rusage __user *ru) return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } -asmlinkage long sys_getrusage(int who, struct rusage __user *ru) +SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) @@ -1696,7 +1697,7 @@ asmlinkage long sys_getrusage(int who, struct rusage __user *ru) return getrusage(current, who, ru); } -asmlinkage long sys_umask(int mask) +SYSCALL_DEFINE1(umask, int, mask) { mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; -- cgit v1.2.3 From d5460c9974a321a194aded4a8c4daaac68ea8171 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 14 Jan 2009 14:14:27 +0100 Subject: [CVE-2009-0029] System call wrappers part 25 Signed-off-by: Heiko Carstens --- ipc/mqueue.c | 6 +++--- ipc/sem.c | 9 +++++---- ipc/shm.c | 8 ++++---- 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'ipc') diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 6df028b70543..faac04c85e74 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -650,8 +650,8 @@ static struct file *do_open(struct dentry *dentry, int oflag) return dentry_open(dentry, mqueue_mnt, oflag, cred); } -asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode, - struct mq_attr __user *u_attr) +SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, mode_t, mode, + struct mq_attr __user *, u_attr) { struct dentry *dentry; struct file *filp; @@ -721,7 +721,7 @@ out_putname: return fd; } -asmlinkage long sys_mq_unlink(const char __user *u_name) +SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) { int err; char *name; diff --git a/ipc/sem.c b/ipc/sem.c index c385c40c061c..16a2189e96f9 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -308,7 +308,7 @@ static inline int sem_more_checks(struct kern_ipc_perm *ipcp, return 0; } -asmlinkage long sys_semget(key_t key, int nsems, int semflg) +SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) { struct ipc_namespace *ns; struct ipc_ops sem_ops; @@ -1055,8 +1055,8 @@ out: return un; } -asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops, - unsigned nsops, const struct timespec __user *timeout) +SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops, const struct timespec __user *, timeout) { int error = -EINVAL; struct sem_array *sma; @@ -1232,7 +1232,8 @@ out_free: return error; } -asmlinkage long sys_semop (int semid, struct sembuf __user *tsops, unsigned nsops) +SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops) { return sys_semtimedop(semid, tsops, nsops, NULL); } diff --git a/ipc/shm.c b/ipc/shm.c index d0ab5527bf45..a9e09ad2263e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -440,7 +440,7 @@ static inline int shm_more_checks(struct kern_ipc_perm *ipcp, return 0; } -asmlinkage long sys_shmget (key_t key, size_t size, int shmflg) +SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) { struct ipc_namespace *ns; struct ipc_ops shm_ops; @@ -621,7 +621,7 @@ out_up: return err; } -asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) +SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { struct shmid_kernel *shp; int err, version; @@ -939,7 +939,7 @@ out_put_dentry: goto out_nattch; } -asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg) +SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) { unsigned long ret; long err; @@ -955,7 +955,7 @@ asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg) * detach and kill segment if marked destroyed. * The work is done in shm_close. */ -asmlinkage long sys_shmdt(char __user *shmaddr) +SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *next; -- cgit v1.2.3 From c4ea37c26a691ad0b7e86aa5884aab27830e95c9 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 14 Jan 2009 14:14:28 +0100 Subject: [CVE-2009-0029] System call wrappers part 26 Signed-off-by: Heiko Carstens --- drivers/pci/syscall.c | 12 ++++-------- ipc/mqueue.c | 22 +++++++++++----------- kernel/sys.c | 4 ++-- mm/swapfile.c | 4 ++-- 4 files changed, 19 insertions(+), 23 deletions(-) (limited to 'ipc') diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c index 645d7a60e412..ec22284eed30 100644 --- a/drivers/pci/syscall.c +++ b/drivers/pci/syscall.c @@ -14,10 +14,8 @@ #include #include "pci.h" -asmlinkage long -sys_pciconfig_read(unsigned long bus, unsigned long dfn, - unsigned long off, unsigned long len, - void __user *buf) +SYSCALL_DEFINE5(pciconfig_read, unsigned long, bus, unsigned long, dfn, + unsigned long, off, unsigned long, len, void __user *, buf) { struct pci_dev *dev; u8 byte; @@ -86,10 +84,8 @@ error: return err; } -asmlinkage long -sys_pciconfig_write(unsigned long bus, unsigned long dfn, - unsigned long off, unsigned long len, - void __user *buf) +SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn, + unsigned long, off, unsigned long, len, void __user *, buf) { struct pci_dev *dev; u8 byte; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index faac04c85e74..54b4077fed79 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -814,9 +814,9 @@ static inline void pipelined_receive(struct mqueue_inode_info *info) sender->state = STATE_READY; } -asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, - size_t msg_len, unsigned int msg_prio, - const struct timespec __user *u_abs_timeout) +SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, + size_t, msg_len, unsigned int, msg_prio, + const struct timespec __user *, u_abs_timeout) { struct file *filp; struct inode *inode; @@ -907,9 +907,9 @@ out: return ret; } -asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, - size_t msg_len, unsigned int __user *u_msg_prio, - const struct timespec __user *u_abs_timeout) +SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, + size_t, msg_len, unsigned int __user *, u_msg_prio, + const struct timespec __user *, u_abs_timeout) { long timeout; ssize_t ret; @@ -997,8 +997,8 @@ out: * and he isn't currently owner of notification, will be silently discarded. * It isn't explicitly defined in the POSIX. */ -asmlinkage long sys_mq_notify(mqd_t mqdes, - const struct sigevent __user *u_notification) +SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes, + const struct sigevent __user *, u_notification) { int ret; struct file *filp; @@ -1123,9 +1123,9 @@ out: return ret; } -asmlinkage long sys_mq_getsetattr(mqd_t mqdes, - const struct mq_attr __user *u_mqstat, - struct mq_attr __user *u_omqstat) +SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes, + const struct mq_attr __user *, u_mqstat, + struct mq_attr __user *, u_omqstat) { int ret; struct mq_attr mqstat, omqstat; diff --git a/kernel/sys.c b/kernel/sys.c index 70ffa8408cd4..59aadcdad6ce 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1703,8 +1703,8 @@ SYSCALL_DEFINE1(umask, int, mask) return mask; } -asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5) +SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, + unsigned long, arg4, unsigned long, arg5) { struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; diff --git a/mm/swapfile.c b/mm/swapfile.c index da422c47e2ee..f48b831e5e5c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1377,7 +1377,7 @@ out: return ret; } -asmlinkage long sys_swapoff(const char __user * specialfile) +SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct * p = NULL; unsigned short *swap_map; @@ -1633,7 +1633,7 @@ late_initcall(max_swapfiles_check); * * The swapon system call */ -asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) +SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct * p; char *name = NULL; -- cgit v1.2.3 From fc8744adc870a8d4366908221508bb113d8b72ee Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 31 Jan 2009 15:08:56 -0800 Subject: Stop playing silly games with the VM_ACCOUNT flag The mmap_region() code would temporarily set the VM_ACCOUNT flag for anonymous shared mappings just to inform shmem_zero_setup() that it should enable accounting for the resulting shm object. It would then clear the flag after calling ->mmap (for the /dev/zero case) or doing shmem_zero_setup() (for the MAP_ANON case). This just resulted in vma merge issues, but also made for just unnecessary confusion. Use the already-existing VM_NORESERVE flag for this instead, and let shmem_{zero|file}_setup() just figure it out from that. This also happens to make it obvious that the new DRI2 GEM layer uses a non-reserving backing store for its object allocation - which is quite possibly not intentional. But since I didn't want to change semantics in this patch, I left it alone, and just updated the caller to use the new flag semantics. Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_gem.c | 2 +- ipc/shm.c | 4 ++-- mm/mmap.c | 48 ++++++++++++++++++++++++----------------------- mm/shmem.c | 2 +- 4 files changed, 29 insertions(+), 27 deletions(-) (limited to 'ipc') diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 9da581452874..6915fb82d0b0 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -136,7 +136,7 @@ drm_gem_object_alloc(struct drm_device *dev, size_t size) obj = kcalloc(1, sizeof(*obj), GFP_KERNEL); obj->dev = dev; - obj->filp = shmem_file_setup("drm mm object", size, 0); + obj->filp = shmem_file_setup("drm mm object", size, VM_NORESERVE); if (IS_ERR(obj->filp)) { kfree(obj); return NULL; diff --git a/ipc/shm.c b/ipc/shm.c index a9e09ad2263e..c0a021f7f41a 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -368,14 +368,14 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) file = hugetlb_file_setup(name, size); shp->mlock_user = current_user(); } else { - int acctflag = VM_ACCOUNT; + int acctflag = 0; /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. */ if ((shmflg & SHM_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) - acctflag = 0; + acctflag = VM_NORESERVE; file = shmem_file_setup(name, size, acctflag); } error = PTR_ERR(file); diff --git a/mm/mmap.c b/mm/mmap.c index c581df14d0de..214b6a258eeb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1090,6 +1090,15 @@ int vma_wants_writenotify(struct vm_area_struct *vma) mapping_cap_account_dirty(vma->vm_file->f_mapping); } +/* + * We account for memory if it's a private writeable mapping, + * and VM_NORESERVE wasn't set. + */ +static inline int accountable_mapping(unsigned int vm_flags) +{ + return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; +} + unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, unsigned int vm_flags, unsigned long pgoff, @@ -1117,23 +1126,24 @@ munmap_back: if (!may_expand_vm(mm, len >> PAGE_SHIFT)) return -ENOMEM; - if (flags & MAP_NORESERVE) + /* + * Set 'VM_NORESERVE' if we should not account for the + * memory use of this mapping. We only honor MAP_NORESERVE + * if we're allowed to overcommit memory. + */ + if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + if (!accountable) vm_flags |= VM_NORESERVE; - if (accountable && (!(flags & MAP_NORESERVE) || - sysctl_overcommit_memory == OVERCOMMIT_NEVER)) { - if (vm_flags & VM_SHARED) { - /* Check memory availability in shmem_file_setup? */ - vm_flags |= VM_ACCOUNT; - } else if (vm_flags & VM_WRITE) { - /* - * Private writable mapping: check memory availability - */ - charged = len >> PAGE_SHIFT; - if (security_vm_enough_memory(charged)) - return -ENOMEM; - vm_flags |= VM_ACCOUNT; - } + /* + * Private writable mapping: check memory availability + */ + if (accountable_mapping(vm_flags)) { + charged = len >> PAGE_SHIFT; + if (security_vm_enough_memory(charged)) + return -ENOMEM; + vm_flags |= VM_ACCOUNT; } /* @@ -1184,14 +1194,6 @@ munmap_back: goto free_vma; } - /* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform - * shmem_zero_setup (perhaps called through /dev/zero's ->mmap) - * that memory reservation must be checked; but that reservation - * belongs to shared memory object, not to vma: so now clear it. - */ - if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT)) - vma->vm_flags &= ~VM_ACCOUNT; - /* Can addr have changed?? * * Answer: Yes, several device drivers can do it in their diff --git a/mm/shmem.c b/mm/shmem.c index 5d0de96c9789..19d566ccdeea 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2628,7 +2628,7 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) goto close_file; #ifdef CONFIG_SHMEM - SHMEM_I(inode)->flags = flags & VM_ACCOUNT; + SHMEM_I(inode)->flags = (flags & VM_NORESERVE) ? 0 : VM_ACCOUNT; #endif d_instantiate(dentry, inode); inode->i_size = size; -- cgit v1.2.3 From a68e61e8ff2d46327a37b69056998b47745db6fa Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Wed, 4 Feb 2009 15:12:04 -0800 Subject: shm: fix shmctl(SHM_INFO) lockup with !CONFIG_SHMEM shm_get_stat() assumes that the inode is a "struct shmem_inode_info", which is incorrect for !CONFIG_SHMEM (see fs/ramfs/inode.c: ramfs_get_inode() vs. mm/shmem.c: shmem_get_inode()). This bad assumption can cause shmctl(SHM_INFO) to lockup when shm_get_stat() tries to spin_lock(&info->lock). Users of !CONFIG_SHMEM may encounter this lockup simply by invoking the 'ipcs' command. Reported by Jiri Olsa back in February 2008: http://lkml.org/lkml/2008/2/29/74 Signed-off-by: Tony Battersby Cc: Jiri Kosina Reported-by: Jiri Olsa Cc: Hugh Dickins Cc: [2.6.everything] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'ipc') diff --git a/ipc/shm.c b/ipc/shm.c index c0a021f7f41a..f8f69fad3a27 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -565,11 +565,15 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, struct hstate *h = hstate_file(shp->shm_file); *rss += pages_per_huge_page(h) * mapping->nrpages; } else { +#ifdef CONFIG_SHMEM struct shmem_inode_info *info = SHMEM_I(inode); spin_lock(&info->lock); *rss += inode->i_mapping->nrpages; *swp += info->swapped; spin_unlock(&info->lock); +#else + *rss += inode->i_mapping->nrpages; +#endif } total++; -- cgit v1.2.3