From 03f595668017f1a1fb971c02fc37140bc6e7bb1c Mon Sep 17 00:00:00 2001 From: Stanislav Kinsbursky Date: Fri, 4 Jan 2013 15:34:50 -0800 Subject: [PATCH] ipc: add sysctl to specify desired next object id Add 3 new variables and sysctls to tune them (by one "next_id" variable for messages, semaphores and shared memory respectively). This variable can be used to set desired id for next allocated IPC object. By default it's equal to -1 and old behaviour is preserved. If this variable is non-negative, then desired idr will be extracted from it and used as a start value to search for free IDR slot. Notes: 1) this patch doesn't guarantee that the new object will have desired id. So it's up to user space how to handle new object with wrong id. 2) After a sucessful id allocation attempt, "next_id" will be set back to -1 (if it was non-negative). [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Stanislav Kinsbursky Cc: Serge Hallyn Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Al Viro Cc: KOSAKI Motohiro Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 19 +++++++++++++++++++ include/linux/ipc_namespace.h | 1 + ipc/ipc_sysctl.c | 32 ++++++++++++++++++++++++++++++++ ipc/util.c | 16 ++++++++++++---- ipc/util.h | 1 + 5 files changed, 65 insertions(+), 4 deletions(-) diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 2907ba6c3607..51b953a1b149 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -38,6 +38,7 @@ show up in /proc/sys/kernel: - l2cr [ PPC only ] - modprobe ==> Documentation/debugging-modules.txt - modules_disabled +- msg_next_id [ sysv ipc ] - msgmax - msgmnb - msgmni @@ -62,7 +63,9 @@ show up in /proc/sys/kernel: - rtsig-max - rtsig-nr - sem +- sem_next_id [ sysv ipc ] - sg-big-buff [ generic SCSI device (sg) ] +- shm_next_id [ sysv ipc ] - shm_rmid_forced - shmall - shmmax [ sysv ipc ] @@ -320,6 +323,22 @@ to false. ============================================================== +msg_next_id, sem_next_id, and shm_next_id: + +These three toggles allows to specify desired id for next allocated IPC +object: message, semaphore or shared memory respectively. + +By default they are equal to -1, which means generic allocation logic. +Possible values to set are in range {0..INT_MAX}. + +Notes: +1) kernel doesn't guarantee, that new object will have desired id. So, +it's up to userspace, how to handle an object with "wrong" id. +2) Toggle with non-default value will be set back to -1 by kernel after +successful IPC object allocation. + +============================================================== + nmi_watchdog: Enables/Disables the NMI watchdog on x86 systems. When the value is diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index fe771978e877..ae221a7b5092 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -24,6 +24,7 @@ struct ipc_ids { unsigned short seq_max; struct rw_semaphore rw_mutex; struct idr ipcs_idr; + int next_id; }; struct ipc_namespace { diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 00fba2bab87d..130dfece27ac 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -158,6 +158,9 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, static int zero; static int one = 1; +#ifdef CONFIG_CHECKPOINT_RESTORE +static int int_max = INT_MAX; +#endif static struct ctl_table ipc_kern_table[] = { { @@ -227,6 +230,35 @@ static struct ctl_table ipc_kern_table[] = { .extra1 = &zero, .extra2 = &one, }, +#ifdef CONFIG_CHECKPOINT_RESTORE + { + .procname = "sem_next_id", + .data = &init_ipc_ns.ids[IPC_SEM_IDS].next_id, + .maxlen = sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id), + .mode = 0644, + .proc_handler = proc_ipc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max, + }, + { + .procname = "msg_next_id", + .data = &init_ipc_ns.ids[IPC_MSG_IDS].next_id, + .maxlen = sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id), + .mode = 0644, + .proc_handler = proc_ipc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max, + }, + { + .procname = "shm_next_id", + .data = &init_ipc_ns.ids[IPC_SHM_IDS].next_id, + .maxlen = sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id), + .mode = 0644, + .proc_handler = proc_ipc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max, + }, +#endif {} }; diff --git a/ipc/util.c b/ipc/util.c index 72fd0785ac94..74e1d9c7a98a 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -122,6 +122,7 @@ void ipc_init_ids(struct ipc_ids *ids) ids->in_use = 0; ids->seq = 0; + ids->next_id = -1; { int seq_limit = INT_MAX/SEQ_MULTIPLIER; if (seq_limit > USHRT_MAX) @@ -252,6 +253,7 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) kuid_t euid; kgid_t egid; int id, err; + int next_id = ids->next_id; if (size > IPCMNI) size = IPCMNI; @@ -264,7 +266,8 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) rcu_read_lock(); spin_lock(&new->lock); - err = idr_get_new(&ids->ipcs_idr, new, &id); + err = idr_get_new_above(&ids->ipcs_idr, new, + (next_id < 0) ? 0 : ipcid_to_idx(next_id), &id); if (err) { spin_unlock(&new->lock); rcu_read_unlock(); @@ -277,9 +280,14 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) 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 > ids->seq_max) + ids->seq = 0; + } else { + new->seq = ipcid_to_seqx(next_id); + ids->next_id = -1; + } new->id = ipc_buildid(id, new->seq); return id; diff --git a/ipc/util.h b/ipc/util.h index c8fe2f7631e9..a61e0ca2bffd 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -92,6 +92,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header, #define IPC_SHM_IDS 2 #define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER) +#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER) /* must be called with ids->rw_mutex acquired for writing */ int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);