X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsysctl.c;h=c7314f95264763d10d5b0417aa29cf41ed26fd36;hb=e86908614f2c7fec401827e5cefd7a6ea9407f85;hp=cb46d015684090afa96d5f017b95a179d72c7dac;hpb=ae836810263509ff7a3c2c021754ce6f66b3fab6;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cb46d01..c7314f9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -27,8 +27,8 @@ #include #include #include -#include #include +#include #include #include #include @@ -45,13 +45,11 @@ #include #include #include +#include #include #include -extern int proc_nr_files(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); - #ifdef CONFIG_X86 #include #include @@ -61,6 +59,7 @@ extern int proc_nr_files(ctl_table *table, int write, struct file *filp, /* External variables not in a header file. */ extern int C_A_D; +extern int print_fatal_signals; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern int sysctl_panic_on_oom; @@ -76,6 +75,9 @@ extern int pid_max_min, pid_max_max; extern int sysctl_drop_caches; extern int percpu_pagelist_fraction; extern int compat_log; +extern int maps_protect; +extern int sysctl_stat_interval; +extern int audit_argv_kb; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ static int maxolduid = 65535; @@ -158,26 +160,8 @@ extern ctl_table inotify_table[]; int sysctl_legacy_va_layout; #endif - -/* /proc declarations: */ - -#ifdef CONFIG_PROC_SYSCTL - -static ssize_t proc_readsys(struct file *, char __user *, size_t, loff_t *); -static ssize_t proc_writesys(struct file *, const char __user *, size_t, loff_t *); -static int proc_opensys(struct inode *, struct file *); - -const struct file_operations proc_sys_file_operations = { - .open = proc_opensys, - .read = proc_readsys, - .write = proc_writesys, -}; - -extern struct proc_dir_entry *proc_sys_root; - -static void register_proc_table(ctl_table *, struct proc_dir_entry *, void *); -static void unregister_proc_table(ctl_table *, struct proc_dir_entry *); -#endif +extern int prove_locking; +extern int lock_stat; /* The default sysctl tables: */ @@ -220,11 +204,133 @@ static ctl_table root_table[] = { .mode = 0555, .child = dev_table, }, - +/* + * NOTE: do not add new entries to this table unless you have read + * Documentation/sysctl/ctl_unnumbered.txt + */ { .ctl_name = 0 } }; +#ifdef CONFIG_SCHED_DEBUG +static unsigned long min_sched_granularity_ns = 100000; /* 100 usecs */ +static unsigned long max_sched_granularity_ns = 1000000000; /* 1 second */ +static unsigned long min_wakeup_granularity_ns; /* 0 usecs */ +static unsigned long max_wakeup_granularity_ns = 1000000000; /* 1 second */ +#endif + static ctl_table kern_table[] = { +#ifdef CONFIG_SCHED_DEBUG + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_min_granularity_ns", + .data = &sysctl_sched_min_granularity, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &min_sched_granularity_ns, + .extra2 = &max_sched_granularity_ns, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_latency_ns", + .data = &sysctl_sched_latency, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &min_sched_granularity_ns, + .extra2 = &max_sched_granularity_ns, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_wakeup_granularity_ns", + .data = &sysctl_sched_wakeup_granularity, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &min_wakeup_granularity_ns, + .extra2 = &max_wakeup_granularity_ns, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_batch_wakeup_granularity_ns", + .data = &sysctl_sched_batch_wakeup_granularity, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &min_wakeup_granularity_ns, + .extra2 = &max_wakeup_granularity_ns, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_stat_granularity_ns", + .data = &sysctl_sched_stat_granularity, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &min_wakeup_granularity_ns, + .extra2 = &max_wakeup_granularity_ns, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_runtime_limit_ns", + .data = &sysctl_sched_runtime_limit, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &min_sched_granularity_ns, + .extra2 = &max_sched_granularity_ns, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_features", + .data = &sysctl_sched_features, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif + { + .ctl_name = CTL_UNNUMBERED, + .procname = "sched_compat_yield", + .data = &sysctl_sched_compat_yield, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#ifdef CONFIG_PROVE_LOCKING + { + .ctl_name = CTL_UNNUMBERED, + .procname = "prove_locking", + .data = &prove_locking, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif +#ifdef CONFIG_LOCK_STAT + { + .ctl_name = CTL_UNNUMBERED, + .procname = "lock_stat", + .data = &lock_stat, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif { .ctl_name = KERN_PANIC, .procname = "panic", @@ -241,11 +347,21 @@ static ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, +#ifdef CONFIG_AUDITSYSCALL + { + .ctl_name = CTL_UNNUMBERED, + .procname = "audit_argv_kb", + .data = &audit_argv_kb, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif { .ctl_name = KERN_CORE_PATTERN, .procname = "core_pattern", .data = core_pattern, - .maxlen = 128, + .maxlen = CORENAME_MAX_SIZE, .mode = 0644, .proc_handler = &proc_dostring, .strategy = &sysctl_string, @@ -278,6 +394,14 @@ static ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif + { + .ctl_name = CTL_UNNUMBERED, + .procname = "print-fatal-signals", + .data = &print_fatal_signals, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, #ifdef __sparc__ { .ctl_name = KERN_SPARC_REBOOT, @@ -583,11 +707,11 @@ static ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif -#ifdef CONFIG_ACPI_SLEEP +#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86) { .ctl_name = KERN_ACPI_VIDEO_FLAGS, .procname = "acpi_video_flags", - .data = &acpi_video_flags, + .data = &acpi_realmode_flags, .maxlen = sizeof (unsigned long), .mode = 0644, .proc_handler = &proc_doulongvec_minmax, @@ -623,13 +747,36 @@ static ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif - +#ifdef CONFIG_PROC_FS + { + .ctl_name = CTL_UNNUMBERED, + .procname = "maps_protect", + .data = &maps_protect, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif + { + .ctl_name = CTL_UNNUMBERED, + .procname = "poweroff_cmd", + .data = &poweroff_cmd, + .maxlen = POWEROFF_CMD_PATH_LEN, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, +/* + * NOTE: do not add new entries to this table unless you have read + * Documentation/sysctl/ctl_unnumbered.txt + */ { .ctl_name = 0 } }; /* Constants for minimum and maximum testing in vm_table. We use these as one-element integer vectors. */ static int zero; +static int two = 2; static int one_hundred = 100; @@ -742,6 +889,14 @@ static ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "hugepages_treat_as_movable", + .data = &hugepages_treat_as_movable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &hugetlb_treat_movable_handler, + }, #endif { .ctl_name = VM_LOWMEM_RESERVE_RATIO, @@ -866,7 +1021,40 @@ static ctl_table vm_table[] = { .extra2 = &one_hundred, }, #endif -#ifdef CONFIG_X86_32 +#ifdef CONFIG_SMP + { + .ctl_name = CTL_UNNUMBERED, + .procname = "stat_interval", + .data = &sysctl_stat_interval, + .maxlen = sizeof(sysctl_stat_interval), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, +#endif +#ifdef CONFIG_SECURITY + { + .ctl_name = CTL_UNNUMBERED, + .procname = "mmap_min_addr", + .data = &mmap_min_addr, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + }, +#endif +#ifdef CONFIG_NUMA + { + .ctl_name = CTL_UNNUMBERED, + .procname = "numa_zonelist_order", + .data = &numa_zonelist_order, + .maxlen = NUMA_ZONELIST_ORDER_LEN, + .mode = 0644, + .proc_handler = &numa_zonelist_order_handler, + .strategy = &sysctl_string, + }, +#endif +#if defined(CONFIG_X86_32) || \ + (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL)) { .ctl_name = VM_VDSO_ENABLED, .procname = "vdso_enabled", @@ -878,6 +1066,10 @@ static ctl_table vm_table[] = { .extra1 = &zero, }, #endif +/* + * NOTE: do not add new entries to this table unless you have read + * Documentation/sysctl/ctl_unnumbered.txt + */ { .ctl_name = 0 } }; @@ -975,7 +1167,10 @@ static ctl_table fs_table[] = { .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &two, }, { .ctl_name = FS_AIO_NR, @@ -1018,10 +1213,24 @@ static ctl_table fs_table[] = { .child = binfmt_misc_table, }, #endif +/* + * NOTE: do not add new entries to this table unless you have read + * Documentation/sysctl/ctl_unnumbered.txt + */ { .ctl_name = 0 } }; static ctl_table debug_table[] = { +#if defined(CONFIG_X86) || defined(CONFIG_PPC) + { + .ctl_name = CTL_UNNUMBERED, + .procname = "exception-trace", + .data = &show_unhandled_signals, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif { .ctl_name = 0 } }; @@ -1070,18 +1279,47 @@ static void start_unregistering(struct ctl_table_header *p) list_del_init(&p->ctl_entry); } -void __init sysctl_init(void) +void sysctl_head_finish(struct ctl_table_header *head) { -#ifdef CONFIG_PROC_SYSCTL - register_proc_table(root_table, proc_sys_root, &root_table_header); -#endif + if (!head) + return; + spin_lock(&sysctl_lock); + unuse_table(head); + spin_unlock(&sysctl_lock); +} + +struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev) +{ + struct ctl_table_header *head; + struct list_head *tmp; + spin_lock(&sysctl_lock); + if (prev) { + tmp = &prev->ctl_entry; + unuse_table(prev); + goto next; + } + tmp = &root_table_header.ctl_entry; + for (;;) { + head = list_entry(tmp, struct ctl_table_header, ctl_entry); + + if (!use_table(head)) + goto next; + spin_unlock(&sysctl_lock); + return head; + next: + tmp = tmp->next; + if (tmp == &root_table_header.ctl_entry) + break; + } + spin_unlock(&sysctl_lock); + return NULL; } #ifdef CONFIG_SYSCTL_SYSCALL int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen) { - struct list_head *tmp; + struct ctl_table_header *head; int error = -ENOTDIR; if (nlen <= 0 || nlen >= CTL_MAXNAME) @@ -1091,26 +1329,16 @@ int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *ol if (!oldlenp || get_user(old_len, oldlenp)) return -EFAULT; } - spin_lock(&sysctl_lock); - tmp = &root_table_header.ctl_entry; - do { - struct ctl_table_header *head = - list_entry(tmp, struct ctl_table_header, ctl_entry); - - if (!use_table(head)) - continue; - - spin_unlock(&sysctl_lock); + for (head = sysctl_head_next(NULL); head; + head = sysctl_head_next(head)) { error = parse_table(name, nlen, oldval, oldlenp, newval, newlen, head->ctl_table); - - spin_lock(&sysctl_lock); - unuse_table(head); - if (error != -ENOTDIR) + if (error != -ENOTDIR) { + sysctl_head_finish(head); break; - } while ((tmp = tmp->next) != &root_table_header.ctl_entry); - spin_unlock(&sysctl_lock); + } + } return error; } @@ -1131,7 +1359,7 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args) #endif /* CONFIG_SYSCTL_SYSCALL */ /* - * ctl_perm does NOT grant the superuser all rights automatically, because + * sysctl_perm does NOT grant the superuser all rights automatically, because * some sysctl variables are readonly even to root. */ @@ -1146,7 +1374,7 @@ static int test_perm(int mode, int op) return -EACCES; } -static inline int ctl_perm(ctl_table *table, int op) +int sysctl_perm(ctl_table *table, int op) { int error; error = security_sysctl(table, op); @@ -1173,7 +1401,7 @@ repeat: if (n == table->ctl_name) { int error; if (table->child) { - if (ctl_perm(table, 001)) + if (sysctl_perm(table, 001)) return -EPERM; name++; nlen--; @@ -1202,7 +1430,7 @@ int do_sysctl_strategy (ctl_table *table, op |= 004; if (newval) op |= 002; - if (ctl_perm(table, op)) + if (sysctl_perm(table, op)) return -EPERM; if (table->strategy) { @@ -1241,10 +1469,26 @@ int do_sysctl_strategy (ctl_table *table, } #endif /* CONFIG_SYSCTL_SYSCALL */ +static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table) +{ + for (; table->ctl_name || table->procname; table++) { + table->parent = parent; + if (table->child) + sysctl_set_parent(table, table->child); + } +} + +static __init int sysctl_init(void) +{ + sysctl_set_parent(NULL, root_table); + return 0; +} + +core_initcall(sysctl_init); + /** * register_sysctl_table - register a sysctl hierarchy * @table: the top-level table structure - * @insert_at_head: whether the entry should be inserted in front or at the end * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. An entry with a ctl_name of 0 terminates the table. @@ -1310,8 +1554,7 @@ int do_sysctl_strategy (ctl_table *table, * This routine returns %NULL on a failure to register, and a pointer * to the table header on success. */ -struct ctl_table_header *register_sysctl_table(ctl_table * table, - int insert_at_head) +struct ctl_table_header *register_sysctl_table(ctl_table * table) { struct ctl_table_header *tmp; tmp = kmalloc(sizeof(struct ctl_table_header), GFP_KERNEL); @@ -1321,15 +1564,10 @@ struct ctl_table_header *register_sysctl_table(ctl_table * table, INIT_LIST_HEAD(&tmp->ctl_entry); tmp->used = 0; tmp->unregistering = NULL; + sysctl_set_parent(NULL, table); spin_lock(&sysctl_lock); - if (insert_at_head) - list_add(&tmp->ctl_entry, &root_table_header.ctl_entry); - else - list_add_tail(&tmp->ctl_entry, &root_table_header.ctl_entry); + list_add_tail(&tmp->ctl_entry, &root_table_header.ctl_entry); spin_unlock(&sysctl_lock); -#ifdef CONFIG_PROC_SYSCTL - register_proc_table(table, proc_sys_root, tmp); -#endif return tmp; } @@ -1345,16 +1583,12 @@ void unregister_sysctl_table(struct ctl_table_header * header) might_sleep(); spin_lock(&sysctl_lock); start_unregistering(header); -#ifdef CONFIG_PROC_SYSCTL - unregister_proc_table(header->ctl_table, proc_sys_root); -#endif spin_unlock(&sysctl_lock); kfree(header); } #else /* !CONFIG_SYSCTL */ -struct ctl_table_header * register_sysctl_table(ctl_table * table, - int insert_at_head) +struct ctl_table_header *register_sysctl_table(ctl_table * table) { return NULL; } @@ -1371,155 +1605,6 @@ void unregister_sysctl_table(struct ctl_table_header * table) #ifdef CONFIG_PROC_SYSCTL -/* Scan the sysctl entries in table and add them all into /proc */ -static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, void *set) -{ - struct proc_dir_entry *de; - int len; - mode_t mode; - - for (; table->ctl_name || table->procname; table++) { - /* Can't do anything without a proc name. */ - if (!table->procname) - continue; - /* Maybe we can't do anything with it... */ - if (!table->proc_handler && !table->child) { - printk(KERN_WARNING "SYSCTL: Can't register %s\n", - table->procname); - continue; - } - - len = strlen(table->procname); - mode = table->mode; - - de = NULL; - if (table->proc_handler) - mode |= S_IFREG; - else { - mode |= S_IFDIR; - for (de = root->subdir; de; de = de->next) { - if (proc_match(len, table->procname, de)) - break; - } - /* If the subdir exists already, de is non-NULL */ - } - - if (!de) { - de = create_proc_entry(table->procname, mode, root); - if (!de) - continue; - de->set = set; - de->data = (void *) table; - if (table->proc_handler) - de->proc_fops = &proc_sys_file_operations; - } - table->de = de; - if (de->mode & S_IFDIR) - register_proc_table(table->child, de, set); - } -} - -/* - * Unregister a /proc sysctl table and any subdirectories. - */ -static void unregister_proc_table(ctl_table * table, struct proc_dir_entry *root) -{ - struct proc_dir_entry *de; - for (; table->ctl_name || table->procname; table++) { - if (!(de = table->de)) - continue; - if (de->mode & S_IFDIR) { - if (!table->child) { - printk (KERN_ALERT "Help - malformed sysctl tree on free\n"); - continue; - } - unregister_proc_table(table->child, de); - - /* Don't unregister directories which still have entries.. */ - if (de->subdir) - continue; - } - - /* - * In any case, mark the entry as goner; we'll keep it - * around if it's busy, but we'll know to do nothing with - * its fields. We are under sysctl_lock here. - */ - de->data = NULL; - - /* Don't unregister proc entries that are still being used.. */ - if (atomic_read(&de->count)) - continue; - - table->de = NULL; - remove_proc_entry(table->procname, root); - } -} - -static ssize_t do_rw_proc(int write, struct file * file, char __user * buf, - size_t count, loff_t *ppos) -{ - int op; - struct proc_dir_entry *de = PDE(file->f_path.dentry->d_inode); - struct ctl_table *table; - size_t res; - ssize_t error = -ENOTDIR; - - spin_lock(&sysctl_lock); - if (de && de->data && use_table(de->set)) { - /* - * at that point we know that sysctl was not unregistered - * and won't be until we finish - */ - spin_unlock(&sysctl_lock); - table = (struct ctl_table *) de->data; - if (!table || !table->proc_handler) - goto out; - error = -EPERM; - op = (write ? 002 : 004); - if (ctl_perm(table, op)) - goto out; - - /* careful: calling conventions are nasty here */ - res = count; - error = (*table->proc_handler)(table, write, file, - buf, &res, ppos); - if (!error) - error = res; - out: - spin_lock(&sysctl_lock); - unuse_table(de->set); - } - spin_unlock(&sysctl_lock); - return error; -} - -static int proc_opensys(struct inode *inode, struct file *file) -{ - if (file->f_mode & FMODE_WRITE) { - /* - * sysctl entries that are not writable, - * are _NOT_ writable, capabilities or not. - */ - if (!(inode->i_mode & S_IWUSR)) - return -EPERM; - } - - return 0; -} - -static ssize_t proc_readsys(struct file * file, char __user * buf, - size_t count, loff_t *ppos) -{ - return do_rw_proc(0, file, buf, count, ppos); -} - -static ssize_t proc_writesys(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) -{ - return do_rw_proc(1, file, (char __user *) buf, count, ppos); -} - static int _proc_do_string(void* data, int maxlen, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -1819,7 +1904,7 @@ static int proc_dointvec_taint(ctl_table *table, int write, struct file *filp, { int op; - if (!capable(CAP_SYS_ADMIN)) + if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; op = OP_OR;