diff options
Diffstat (limited to 'ipc/util.c')
| -rw-r--r-- | ipc/util.c | 793 |
1 files changed, 391 insertions, 402 deletions
diff --git a/ipc/util.c b/ipc/util.c index fd1b50da9db..27d74e69fd5 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -15,6 +15,29 @@ * Jun 2006 - namespaces ssupport * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> + * + * General sysv ipc locking scheme: + * rcu_read_lock() + * obtain the ipc object (kern_ipc_perm) by looking up the id in an idr + * tree. + * - perform initial checks (capabilities, auditing and permission, + * etc). + * - perform read-only operations, such as STAT, INFO commands. + * acquire the ipc lock (kern_ipc_perm.lock) through + * ipc_lock_object() + * - perform data updates, such as SET, RMID commands and + * mechanism-specific operations (semop/semtimedop, + * msgsnd/msgrcv, shmat/shmdt). + * drop the ipc lock, through ipc_unlock_object(). + * rcu_read_unlock() + * + * The ids->rwsem must be taken when: + * - creating, removing and iterating the existing entries in ipc + * identifier sets. + * - iterating through files under /proc/sysvipc/ + * + * Note that sems have a special fast path that avoids kern_ipc_perm.lock - + * see sem_lock(). */ #include <linux/mm.h> @@ -23,6 +46,7 @@ #include <linux/msg.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/notifier.h> #include <linux/capability.h> #include <linux/highuid.h> #include <linux/security.h> @@ -33,6 +57,7 @@ #include <linux/audit.h> #include <linux/nsproxy.h> #include <linux/rwsem.h> +#include <linux/memory.h> #include <linux/ipc_namespace.h> #include <asm/unistd.h> @@ -46,61 +71,89 @@ struct ipc_proc_iface { int (*show)(struct seq_file *, void *); }; -struct ipc_namespace init_ipc_ns = { - .kref = { - .refcount = ATOMIC_INIT(2), - }, +static void ipc_memory_notifier(struct work_struct *work) +{ + ipcns_notify(IPCNS_MEMCHANGED); +} + +static int ipc_memory_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier); + + switch (action) { + case MEM_ONLINE: /* memory successfully brought online */ + case MEM_OFFLINE: /* or offline: it's time to recompute msgmni */ + /* + * This is done by invoking the ipcns notifier chain with the + * IPC_MEMCHANGED event. + * In order not to keep the lock on the hotplug memory chain + * for too long, queue a work item that will, when waken up, + * activate the ipcns notification chain. + */ + schedule_work(&ipc_memory_wq); + break; + case MEM_GOING_ONLINE: + case MEM_GOING_OFFLINE: + case MEM_CANCEL_ONLINE: + case MEM_CANCEL_OFFLINE: + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block ipc_memory_nb = { + .notifier_call = ipc_memory_callback, + .priority = IPC_CALLBACK_PRI, }; /** - * ipc_init - initialise IPC subsystem + * ipc_init - initialise ipc subsystem + * + * The various sysv ipc resources (semaphores, messages and shared + * memory) are initialised. * - * The various system5 IPC resources (semaphores, messages and shared - * memory) are initialised + * A callback routine is registered into the memory hotplug notifier + * chain: since msgmni scales to lowmem this callback routine will be + * called upon successful memory add / remove to recompute msmgni. */ - static int __init ipc_init(void) { sem_init(); msg_init(); shm_init(); + register_hotmemory_notifier(&ipc_memory_nb); + register_ipcns_notifier(&init_ipc_ns); return 0; } -__initcall(ipc_init); +device_initcall(ipc_init); /** - * ipc_init_ids - initialise IPC identifiers - * @ids: Identifier set + * ipc_init_ids - initialise ipc identifiers + * @ids: ipc identifier set * - * Set up the sequence range to use for the ipc identifier range (limited - * below IPCMNI) then initialise the ids idr. + * Set up the sequence range to use for the ipc identifier range (limited + * below IPCMNI) then initialise the ids idr. */ - void ipc_init_ids(struct ipc_ids *ids) { - init_rwsem(&ids->rw_mutex); - ids->in_use = 0; ids->seq = 0; - { - int seq_limit = INT_MAX/SEQ_MULTIPLIER; - if(seq_limit > USHRT_MAX) - ids->seq_max = USHRT_MAX; - else - ids->seq_max = seq_limit; - } - + ids->next_id = -1; + init_rwsem(&ids->rwsem); idr_init(&ids->ipcs_idr); } #ifdef CONFIG_PROC_FS static const struct file_operations sysvipc_proc_fops; /** - * ipc_init_proc_interface - Create a proc interface for sysipc types using a seq_file interface. - * @path: Path in procfs - * @header: Banner to be printed at the beginning of the file. - * @ids: ipc id table to iterate. - * @show: show routine. + * ipc_init_proc_interface - create a proc interface for sysipc types using a seq_file interface. + * @path: Path in procfs + * @header: Banner to be printed at the beginning of the file. + * @ids: ipc id table to iterate. + * @show: show routine. */ void __init ipc_init_proc_interface(const char *path, const char *header, int ids, int (*show)(struct seq_file *, void *)) @@ -116,29 +169,26 @@ void __init ipc_init_proc_interface(const char *path, const char *header, iface->ids = ids; iface->show = show; - pde = create_proc_entry(path, - S_IRUGO, /* world readable */ - NULL /* parent dir */); - if (pde) { - pde->data = iface; - pde->proc_fops = &sysvipc_proc_fops; - } else { + pde = proc_create_data(path, + S_IRUGO, /* world readable */ + NULL, /* parent dir */ + &sysvipc_proc_fops, + iface); + if (!pde) kfree(iface); - } } #endif /** - * ipc_findkey - find a key in an ipc identifier set - * @ids: Identifier set - * @key: The key to find - * - * Requires ipc_ids.rw_mutex locked. - * Returns the LOCKED pointer to the ipc structure if found or NULL - * if not. - * If key is found ipc points to the owning ipc structure + * ipc_findkey - find a key in an ipc identifier set + * @ids: ipc identifier set + * @key: key to find + * + * Returns the locked pointer to the ipc structure if found or NULL + * otherwise. If key is found ipc points to the owning ipc structure + * + * Called with ipc_ids.rwsem held. */ - static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key) { struct kern_ipc_perm *ipc; @@ -156,7 +206,8 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key) continue; } - ipc_lock_by_ptr(ipc); + rcu_read_lock(); + ipc_lock_object(ipc); return ipc; } @@ -164,12 +215,11 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key) } /** - * ipc_get_maxid - get the last assigned id - * @ids: IPC identifier set + * ipc_get_maxid - get the last assigned id + * @ids: ipc identifier set * - * Called with ipc_ids.rw_mutex held. + * Called with ipc_ids.rwsem held. */ - int ipc_get_maxid(struct ipc_ids *ids) { struct kern_ipc_perm *ipc; @@ -195,22 +245,24 @@ int ipc_get_maxid(struct ipc_ids *ids) } /** - * ipc_addid - add an IPC identifier - * @ids: IPC identifier set - * @new: new IPC permission set - * @size: limit for the number of used ids + * ipc_addid - add an ipc identifier + * @ids: ipc identifier set + * @new: new ipc permission set + * @size: limit for the number of used ids * - * Add an entry 'new' to the IPC ids idr. The permissions object is - * initialised and the first free entry is set up and the id assigned - * is returned. The 'new' entry is returned in a locked state on success. - * On failure the entry is not locked and a negative err-code is returned. + * Add an entry 'new' to the ipc ids idr. The permissions object is + * initialised and the first free entry is set up and the id assigned + * is returned. The 'new' entry is returned in a locked state on success. + * On failure the entry is not locked and a negative err-code is returned. * - * Called with ipc_ids.rw_mutex held as a writer. + * Called with writer ipc_ids.rwsem held. */ - -int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) +int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size) { - int id, err; + kuid_t euid; + kgid_t egid; + int id; + int next_id = ids->next_id; if (size > IPCMNI) size = IPCMNI; @@ -218,76 +270,86 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) if (ids->in_use >= size) return -ENOSPC; - err = idr_get_new(&ids->ipcs_idr, new, &id); - if (err) - return err; + idr_preload(GFP_KERNEL); + + spin_lock_init(&new->lock); + new->deleted = false; + rcu_read_lock(); + spin_lock(&new->lock); + + id = idr_alloc(&ids->ipcs_idr, new, + (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0, + GFP_NOWAIT); + idr_preload_end(); + if (id < 0) { + spin_unlock(&new->lock); + rcu_read_unlock(); + return id; + } ids->in_use++; - new->cuid = new->uid = current->euid; - new->gid = new->cgid = current->egid; + current_euid_egid(&euid, &egid); + new->cuid = new->uid = euid; + new->gid = new->cgid = egid; - new->seq = ids->seq++; - if(ids->seq > ids->seq_max) - ids->seq = 0; + if (next_id < 0) { + new->seq = ids->seq++; + if (ids->seq > IPCID_SEQ_MAX) + ids->seq = 0; + } else { + new->seq = ipcid_to_seqx(next_id); + ids->next_id = -1; + } - spin_lock_init(&new->lock); - new->deleted = 0; - rcu_read_lock(); - spin_lock(&new->lock); + new->id = ipc_buildid(id, new->seq); return id; } /** - * ipcget_new - create a new ipc object - * @ns: namespace - * @ids: IPC identifer set - * @ops: the actual creation routine to call - * @params: its parameters - * - * This routine is called by sys_msgget, sys_semget() and sys_shmget() - * when the key is IPC_PRIVATE. + * ipcget_new - create a new ipc object + * @ns: ipc namespace + * @ids: ipc identifer set + * @ops: the actual creation routine to call + * @params: its parameters + * + * This routine is called by sys_msgget, sys_semget() and sys_shmget() + * when the key is IPC_PRIVATE. */ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids, - struct ipc_ops *ops, struct ipc_params *params) + const struct ipc_ops *ops, struct ipc_params *params) { int err; -retry: - err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL); - - if (!err) - return -ENOMEM; - down_write(&ids->rw_mutex); + down_write(&ids->rwsem); err = ops->getnew(ns, params); - up_write(&ids->rw_mutex); - - if (err == -EAGAIN) - goto retry; - + up_write(&ids->rwsem); return err; } /** - * ipc_check_perms - check security and permissions for an IPC - * @ipcp: ipc permission set - * @ops: the actual security routine to call - * @params: its parameters + * ipc_check_perms - check security and permissions for an ipc object + * @ns: ipc namespace + * @ipcp: ipc permission set + * @ops: the actual security routine to call + * @params: its parameters * - * This routine is called by sys_msgget(), sys_semget() and sys_shmget() - * when the key is not IPC_PRIVATE and that key already exists in the - * ids IDR. + * This routine is called by sys_msgget(), sys_semget() and sys_shmget() + * when the key is not IPC_PRIVATE and that key already exists in the + * ds IDR. * - * On success, the IPC id is returned. + * On success, the ipc id is returned. * - * It is called with ipc_ids.rw_mutex and ipcp->lock held. + * It is called with ipc_ids.rwsem and ipcp->lock held. */ -static int ipc_check_perms(struct kern_ipc_perm *ipcp, struct ipc_ops *ops, - struct ipc_params *params) +static int ipc_check_perms(struct ipc_namespace *ns, + struct kern_ipc_perm *ipcp, + const struct ipc_ops *ops, + struct ipc_params *params) { int err; - if (ipcperms(ipcp, params->flg)) + if (ipcperms(ns, ipcp, params->flg)) err = -EACCES; else { err = ops->associate(ipcp, params->flg); @@ -299,40 +361,36 @@ static int ipc_check_perms(struct kern_ipc_perm *ipcp, struct ipc_ops *ops, } /** - * ipcget_public - get an ipc object or create a new one - * @ns: namespace - * @ids: IPC identifer set - * @ops: the actual creation routine to call - * @params: its parameters - * - * This routine is called by sys_msgget, sys_semget() and sys_shmget() - * when the key is not IPC_PRIVATE. - * It adds a new entry if the key is not found and does some permission - * / security checkings if the key is found. - * - * On success, the ipc id is returned. + * ipcget_public - get an ipc object or create a new one + * @ns: ipc namespace + * @ids: ipc identifer set + * @ops: the actual creation routine to call + * @params: its parameters + * + * This routine is called by sys_msgget, sys_semget() and sys_shmget() + * when the key is not IPC_PRIVATE. + * It adds a new entry if the key is not found and does some permission + * / security checkings if the key is found. + * + * On success, the ipc id is returned. */ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids, - struct ipc_ops *ops, struct ipc_params *params) + const struct ipc_ops *ops, struct ipc_params *params) { struct kern_ipc_perm *ipcp; int flg = params->flg; int err; -retry: - err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL); /* * Take the lock as a writer since we are potentially going to add * a new entry + read locks are not "upgradable" */ - down_write(&ids->rw_mutex); + down_write(&ids->rwsem); ipcp = ipc_findkey(ids, params->key); if (ipcp == NULL) { /* key not used */ if (!(flg & IPC_CREAT)) err = -ENOENT; - else if (!err) - err = -ENOMEM; else err = ops->getnew(ns, params); } else { @@ -349,53 +407,44 @@ retry: * ipc_check_perms returns the IPC id on * success */ - err = ipc_check_perms(ipcp, ops, params); + err = ipc_check_perms(ns, ipcp, ops, params); } ipc_unlock(ipcp); } - up_write(&ids->rw_mutex); - - if (err == -EAGAIN) - goto retry; + up_write(&ids->rwsem); return err; } /** - * ipc_rmid - remove an IPC identifier - * @ids: IPC identifier set - * @ipcp: ipc perm structure containing the identifier to remove + * ipc_rmid - remove an ipc identifier + * @ids: ipc identifier set + * @ipcp: ipc perm structure containing the identifier to remove * - * ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held - * before this function is called, and remain locked on the exit. + * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held + * before this function is called, and remain locked on the exit. */ - void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) { int lid = ipcid_to_idx(ipcp->id); idr_remove(&ids->ipcs_idr, lid); - ids->in_use--; - - ipcp->deleted = 1; - - return; + ipcp->deleted = true; } /** - * ipc_alloc - allocate ipc space - * @size: size desired + * ipc_alloc - allocate ipc space + * @size: size desired * - * Allocate memory from the appropriate pools and return a pointer to it. - * NULL is returned if the allocation fails + * Allocate memory from the appropriate pools and return a pointer to it. + * NULL is returned if the allocation fails */ - -void* ipc_alloc(int size) +void *ipc_alloc(int size) { - void* out; - if(size > PAGE_SIZE) + void *out; + if (size > PAGE_SIZE) out = vmalloc(size); else out = kmalloc(size, GFP_KERNEL); @@ -403,183 +452,94 @@ void* ipc_alloc(int size) } /** - * ipc_free - free ipc space - * @ptr: pointer returned by ipc_alloc - * @size: size of block + * ipc_free - free ipc space + * @ptr: pointer returned by ipc_alloc + * @size: size of block * - * Free a block created with ipc_alloc(). The caller must know the size - * used in the allocation call. + * Free a block created with ipc_alloc(). The caller must know the size + * used in the allocation call. */ - -void ipc_free(void* ptr, int size) +void ipc_free(void *ptr, int size) { - if(size > PAGE_SIZE) + if (size > PAGE_SIZE) vfree(ptr); else kfree(ptr); } -/* - * rcu allocations: - * There are three headers that are prepended to the actual allocation: - * - during use: ipc_rcu_hdr. - * - during the rcu grace period: ipc_rcu_grace. - * - [only if vmalloc]: ipc_rcu_sched. - * Their lifetime doesn't overlap, thus the headers share the same memory. - * Unlike a normal union, they are right-aligned, thus some container_of - * forward/backward casting is necessary: - */ -struct ipc_rcu_hdr -{ - int refcount; - int is_vmalloc; - void *data[0]; -}; - - -struct ipc_rcu_grace -{ - struct rcu_head rcu; - /* "void *" makes sure alignment of following data is sane. */ - void *data[0]; -}; - -struct ipc_rcu_sched -{ - struct work_struct work; - /* "void *" makes sure alignment of following data is sane. */ - void *data[0]; -}; - -#define HDRLEN_KMALLOC (sizeof(struct ipc_rcu_grace) > sizeof(struct ipc_rcu_hdr) ? \ - sizeof(struct ipc_rcu_grace) : sizeof(struct ipc_rcu_hdr)) -#define HDRLEN_VMALLOC (sizeof(struct ipc_rcu_sched) > HDRLEN_KMALLOC ? \ - sizeof(struct ipc_rcu_sched) : HDRLEN_KMALLOC) - -static inline int rcu_use_vmalloc(int size) -{ - /* Too big for a single page? */ - if (HDRLEN_KMALLOC + size > PAGE_SIZE) - return 1; - return 0; -} - /** - * ipc_rcu_alloc - allocate ipc and rcu space - * @size: size desired + * ipc_rcu_alloc - allocate ipc and rcu space + * @size: size desired * - * Allocate memory for the rcu header structure + the object. - * Returns the pointer to the object. - * NULL is returned if the allocation fails. + * Allocate memory for the rcu header structure + the object. + * Returns the pointer to the object or NULL upon failure. */ - -void* ipc_rcu_alloc(int size) +void *ipc_rcu_alloc(int size) { - void* out; - /* - * We prepend the allocation with the rcu struct, and - * workqueue if necessary (for vmalloc). + /* + * We prepend the allocation with the rcu struct */ - if (rcu_use_vmalloc(size)) { - out = vmalloc(HDRLEN_VMALLOC + size); - if (out) { - out += HDRLEN_VMALLOC; - container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 1; - container_of(out, struct ipc_rcu_hdr, data)->refcount = 1; - } - } else { - out = kmalloc(HDRLEN_KMALLOC + size, GFP_KERNEL); - if (out) { - out += HDRLEN_KMALLOC; - container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 0; - container_of(out, struct ipc_rcu_hdr, data)->refcount = 1; - } - } - - return out; + struct ipc_rcu *out = ipc_alloc(sizeof(struct ipc_rcu) + size); + if (unlikely(!out)) + return NULL; + atomic_set(&out->refcount, 1); + return out + 1; } -void ipc_rcu_getref(void *ptr) +int ipc_rcu_getref(void *ptr) { - container_of(ptr, struct ipc_rcu_hdr, data)->refcount++; -} + struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; -static void ipc_do_vfree(struct work_struct *work) -{ - vfree(container_of(work, struct ipc_rcu_sched, work)); + return atomic_inc_not_zero(&p->refcount); } -/** - * ipc_schedule_free - free ipc + rcu space - * @head: RCU callback structure for queued work - * - * Since RCU callback function is called in bh, - * we need to defer the vfree to schedule_work(). - */ -static void ipc_schedule_free(struct rcu_head *head) +void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)) { - struct ipc_rcu_grace *grace; - struct ipc_rcu_sched *sched; + struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; - grace = container_of(head, struct ipc_rcu_grace, rcu); - sched = container_of(&(grace->data[0]), struct ipc_rcu_sched, - data[0]); + if (!atomic_dec_and_test(&p->refcount)) + return; - INIT_WORK(&sched->work, ipc_do_vfree); - schedule_work(&sched->work); + call_rcu(&p->rcu, func); } -/** - * ipc_immediate_free - free ipc + rcu space - * @head: RCU callback structure that contains pointer to be freed - * - * Free from the RCU callback context. - */ -static void ipc_immediate_free(struct rcu_head *head) +void ipc_rcu_free(struct rcu_head *head) { - struct ipc_rcu_grace *free = - container_of(head, struct ipc_rcu_grace, rcu); - kfree(free); -} + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); -void ipc_rcu_putref(void *ptr) -{ - if (--container_of(ptr, struct ipc_rcu_hdr, data)->refcount > 0) - return; - - if (container_of(ptr, struct ipc_rcu_hdr, data)->is_vmalloc) { - call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu, - ipc_schedule_free); - } else { - call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu, - ipc_immediate_free); - } + if (is_vmalloc_addr(p)) + vfree(p); + else + kfree(p); } /** - * ipcperms - check IPC permissions - * @ipcp: IPC permission set - * @flag: desired permission set. + * ipcperms - check ipc permissions + * @ns: ipc namespace + * @ipcp: ipc permission set + * @flag: desired permission set + * + * Check user, group, other permissions for access + * to ipc resources. return 0 if allowed * - * Check user, group, other permissions for access - * to ipc resources. return 0 if allowed + * @flag will most probably be 0 or S_...UGO from <linux/stat.h> */ - -int ipcperms (struct kern_ipc_perm *ipcp, short flag) -{ /* flag will most probably be 0 or S_...UGO from <linux/stat.h> */ - int requested_mode, granted_mode, err; +int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag) +{ + kuid_t euid = current_euid(); + 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 (current->euid == ipcp->cuid || current->euid == ipcp->uid) + if (uid_eq(euid, ipcp->cuid) || + uid_eq(euid, ipcp->uid)) granted_mode >>= 6; else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid)) granted_mode >>= 3; /* is there some bit set in requested_mode but not in granted_mode? */ - if ((requested_mode & ~granted_mode & 0007) && - !capable(CAP_IPC_OWNER)) + if ((requested_mode & ~granted_mode & 0007) && + !ns_capable(ns->user_ns, CAP_IPC_OWNER)) return -1; return security_ipc_permission(ipcp, flag); @@ -591,36 +551,33 @@ int ipcperms (struct kern_ipc_perm *ipcp, short flag) */ /** - * kernel_to_ipc64_perm - convert kernel ipc permissions to user - * @in: kernel permissions - * @out: new style IPC permissions + * kernel_to_ipc64_perm - convert kernel ipc permissions to user + * @in: kernel permissions + * @out: new style ipc permissions * - * Turn the kernel object @in into a set of permissions descriptions - * for returning to userspace (@out). + * Turn the kernel object @in into a set of permissions descriptions + * for returning to userspace (@out). */ - - -void kernel_to_ipc64_perm (struct kern_ipc_perm *in, struct ipc64_perm *out) +void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out) { out->key = in->key; - out->uid = in->uid; - out->gid = in->gid; - out->cuid = in->cuid; - out->cgid = in->cgid; + out->uid = from_kuid_munged(current_user_ns(), in->uid); + out->gid = from_kgid_munged(current_user_ns(), in->gid); + out->cuid = from_kuid_munged(current_user_ns(), in->cuid); + out->cgid = from_kgid_munged(current_user_ns(), in->cgid); out->mode = in->mode; out->seq = in->seq; } /** - * ipc64_perm_to_ipc_perm - convert new ipc permissions to old - * @in: new style IPC permissions - * @out: old style IPC permissions + * ipc64_perm_to_ipc_perm - convert new ipc permissions to old + * @in: new style ipc permissions + * @out: old style ipc permissions * - * Turn the new style permissions object @in into a compatibility - * object and store it into the @out pointer. + * Turn the new style permissions object @in into a compatibility + * object and store it into the @out pointer. */ - -void ipc64_perm_to_ipc_perm (struct ipc64_perm *in, struct ipc_perm *out) +void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out) { out->key = in->key; SET_UID(out->uid, in->uid); @@ -632,128 +589,96 @@ void ipc64_perm_to_ipc_perm (struct ipc64_perm *in, struct ipc_perm *out) } /** - * ipc_lock - Lock an ipc structure without rw_mutex held - * @ids: IPC identifier set + * ipc_obtain_object + * @ids: ipc identifier set * @id: ipc id to look for * - * Look for an id in the ipc ids idr and lock the associated ipc object. - * - * The ipc object is locked on exit. + * Look for an id in the ipc ids idr and return associated ipc object. * - * This is the routine that should be called when the rw_mutex is not already - * held, i.e. idr tree not protected: it protects the idr tree in read mode - * during the idr_find(). + * Call inside the RCU critical section. + * The ipc object is *not* locked on exit. */ - -struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id) +struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id) { struct kern_ipc_perm *out; int lid = ipcid_to_idx(id); - down_read(&ids->rw_mutex); - - rcu_read_lock(); out = idr_find(&ids->ipcs_idr, lid); - if (out == NULL) { - rcu_read_unlock(); - up_read(&ids->rw_mutex); + if (!out) return ERR_PTR(-EINVAL); - } - - up_read(&ids->rw_mutex); - - spin_lock(&out->lock); - - /* ipc_rmid() may have already freed the ID while ipc_lock - * was spinning: here verify that the structure is still valid - */ - if (out->deleted) { - spin_unlock(&out->lock); - rcu_read_unlock(); - return ERR_PTR(-EINVAL); - } return out; } /** - * ipc_lock_down - Lock an ipc structure with rw_sem held - * @ids: IPC identifier set + * ipc_lock - lock an ipc structure without rwsem held + * @ids: ipc identifier set * @id: ipc id to look for * * Look for an id in the ipc ids idr and lock the associated ipc object. * - * The ipc object is locked on exit. - * - * This is the routine that should be called when the rw_mutex is already - * held, i.e. idr tree protected. + * The ipc object is locked on successful exit. */ - -struct kern_ipc_perm *ipc_lock_down(struct ipc_ids *ids, int id) +struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id) { struct kern_ipc_perm *out; - int lid = ipcid_to_idx(id); rcu_read_lock(); - out = idr_find(&ids->ipcs_idr, lid); - if (out == NULL) { - rcu_read_unlock(); - return ERR_PTR(-EINVAL); - } + out = ipc_obtain_object(ids, id); + if (IS_ERR(out)) + goto err1; spin_lock(&out->lock); - /* - * No need to verify that the structure is still valid since the - * rw_mutex is held. + /* ipc_rmid() may have already freed the ID while ipc_lock + * was spinning: here verify that the structure is still valid */ - return out; -} - -struct kern_ipc_perm *ipc_lock_check_down(struct ipc_ids *ids, int id) -{ - struct kern_ipc_perm *out; - - out = ipc_lock_down(ids, id); - if (IS_ERR(out)) + if (ipc_valid_object(out)) return out; - if (ipc_checkid(out, id)) { - ipc_unlock(out); - return ERR_PTR(-EIDRM); - } - + spin_unlock(&out->lock); + out = ERR_PTR(-EINVAL); +err1: + rcu_read_unlock(); return out; } -struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id) +/** + * ipc_obtain_object_check + * @ids: ipc identifier set + * @id: ipc id to look for + * + * Similar to ipc_obtain_object() but also checks + * the ipc object reference counter. + * + * Call inside the RCU critical section. + * The ipc object is *not* locked on exit. + */ +struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id) { - struct kern_ipc_perm *out; + struct kern_ipc_perm *out = ipc_obtain_object(ids, id); - out = ipc_lock(ids, id); if (IS_ERR(out)) - return out; + goto out; - if (ipc_checkid(out, id)) { - ipc_unlock(out); + if (ipc_checkid(out, id)) return ERR_PTR(-EIDRM); - } - +out: return out; } /** * ipcget - Common sys_*get() code - * @ns : namsepace - * @ids : IPC identifier set - * @ops : operations to be called on ipc object creation, permission checks - * and further checks - * @params : the parameters needed by the previous operations. + * @ns: namsepace + * @ids: ipc identifier set + * @ops: operations to be called on ipc object creation, permission checks + * and further checks + * @params: the parameters needed by the previous operations. * * Common routine called by sys_msgget(), sys_semget() and sys_shmget(). */ int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, - struct ipc_ops *ops, struct ipc_params *params) + const struct ipc_ops *ops, struct ipc_params *params) { if (params->key == IPC_PRIVATE) return ipcget_new(ns, ids, ops, params); @@ -761,19 +686,83 @@ int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, return ipcget_public(ns, ids, ops, params); } -#ifdef __ARCH_WANT_IPC_PARSE_VERSION +/** + * ipc_update_perm - update the permissions of an ipc object + * @in: the permission given as input. + * @out: the permission of the ipc to set. + */ +int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out) +{ + kuid_t uid = make_kuid(current_user_ns(), in->uid); + kgid_t gid = make_kgid(current_user_ns(), in->gid); + if (!uid_valid(uid) || !gid_valid(gid)) + return -EINVAL; + + out->uid = uid; + out->gid = gid; + out->mode = (out->mode & ~S_IRWXUGO) + | (in->mode & S_IRWXUGO); + + return 0; +} + +/** + * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd + * @ns: ipc namespace + * @ids: the table of ids where to look for the ipc + * @id: the id of the ipc to retrieve + * @cmd: the cmd to check + * @perm: the permission to set + * @extra_perm: one extra permission parameter used by msq + * + * This function does some common audit and permissions check for some IPC_XXX + * cmd and is called from semctl_down, shmctl_down and msgctl_down. + * It must be called without any lock held and + * - retrieves the ipc with the given id in the given table. + * - performs some audit and permission check, depending on the given cmd + * - returns a pointer to the ipc object or otherwise, the corresponding error. + * + * Call holding the both the rwsem and the rcu read lock. + */ +struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns, + struct ipc_ids *ids, int id, int cmd, + struct ipc64_perm *perm, int extra_perm) +{ + kuid_t euid; + int err = -EPERM; + struct kern_ipc_perm *ipcp; + + ipcp = ipc_obtain_object_check(ids, id); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto err; + } + + audit_ipc_obj(ipcp); + if (cmd == IPC_SET) + audit_ipc_set_perm(extra_perm, perm->uid, + perm->gid, perm->mode); + + euid = current_euid(); + if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) || + ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return ipcp; /* successful lookup */ +err: + return ERR_PTR(err); +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION /** - * ipc_parse_version - IPC call version - * @cmd: pointer to command + * ipc_parse_version - ipc call version + * @cmd: pointer to command * - * Return IPC_64 for new style IPC and IPC_OLD for old style IPC. - * The @cmd value is turned from an encoding command and version into - * just the command code. + * Return IPC_64 for new style IPC and IPC_OLD for old style IPC. + * The @cmd value is turned from an encoding command and version into + * just the command code. */ - -int ipc_parse_version (int *cmd) +int ipc_parse_version(int *cmd) { if (*cmd & IPC_64) { *cmd ^= IPC_64; @@ -783,7 +772,7 @@ int ipc_parse_version (int *cmd) } } -#endif /* __ARCH_WANT_IPC_PARSE_VERSION */ +#endif /* CONFIG_ARCH_WANT_IPC_PARSE_VERSION */ #ifdef CONFIG_PROC_FS struct ipc_proc_iter { @@ -810,11 +799,12 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, if (total >= ids->in_use) return NULL; - for ( ; pos < IPCMNI; pos++) { + for (; pos < IPCMNI; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { *new_pos = pos + 1; - ipc_lock_by_ptr(ipc); + rcu_read_lock(); + ipc_lock_object(ipc); return ipc; } } @@ -852,7 +842,7 @@ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos) * Take the lock - this will be released by the corresponding * call to stop(). */ - down_read(&ids->rw_mutex); + down_read(&ids->rwsem); /* pos < 0 is invalid */ if (*pos < 0) @@ -879,7 +869,7 @@ static void sysvipc_proc_stop(struct seq_file *s, void *it) ids = &iter->ns->ids[iface->ids]; /* Release the lock we took in start() */ - up_read(&ids->rw_mutex); + up_read(&ids->rwsem); } static int sysvipc_proc_show(struct seq_file *s, void *it) @@ -893,7 +883,7 @@ static int sysvipc_proc_show(struct seq_file *s, void *it) return iface->show(s, it); } -static struct seq_operations sysvipc_proc_seqops = { +static const struct seq_operations sysvipc_proc_seqops = { .start = sysvipc_proc_start, .stop = sysvipc_proc_stop, .next = sysvipc_proc_next, @@ -912,19 +902,18 @@ static int sysvipc_proc_open(struct inode *inode, struct file *file) goto out; ret = seq_open(file, &sysvipc_proc_seqops); - if (ret) - goto out_kfree; + if (ret) { + kfree(iter); + goto out; + } seq = file->private_data; seq->private = iter; - iter->iface = PDE(inode)->data; + iter->iface = PDE_DATA(inode); iter->ns = get_ipc_ns(current->nsproxy->ipc_ns); out: return ret; -out_kfree: - kfree(iter); - goto out; } static int sysvipc_proc_release(struct inode *inode, struct file *file) |