From 944ac4259e39801c843a915c3da8194ac9af0440 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 19:26:08 -0400 Subject: ftrace: ftrace dump on oops control Impact: add (default-off) dump-trace-on-oops flag Currently, ftrace is set up to dump its contents to the console if the kernel panics or oops. This can be annoying if you have trace data in the buffers and you experience an oops, but the trace data is old or static. Usually when you want ftrace to dump its contents is when you are debugging your system and you have set up ftrace to trace the events leading to an oops. This patch adds a control variable called "ftrace_dump_on_oops" that will enable the ftrace dump to console on oops. This variable is default off but a developer can enable it either through the kernel command line by adding "ftrace_dump_on_oops" or at run time by setting (or disabling) /proc/sys/kernel/ftrace_dump_on_oops. v2: Replaced /** with /* as Randy explained that kernel-doc does not yet handle variables. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a13bd4dfaeb1..84754f5801e6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -484,6 +484,16 @@ static struct ctl_table kern_table[] = { .proc_handler = &ftrace_enable_sysctl, }, #endif +#ifdef CONFIG_TRACING + { + .ctl_name = CTL_UNNUMBERED, + .procname = "ftrace_dump_on_opps", + .data = &ftrace_dump_on_oops, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef CONFIG_MODULES { .ctl_name = KERN_MODPROBE, -- cgit v1.2.3-71-gd317 From 3299b4dd1180762da831be5eb6adc44553eaec26 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 Nov 2008 11:58:21 +0100 Subject: ftrace: sysctl typo Impact: fix sysctl name typo Steve must have needed more coffee ;-) Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6b6b727258b5..65d4a9ba79e4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -487,7 +487,7 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_TRACING { .ctl_name = CTL_UNNUMBERED, - .procname = "ftrace_dump_on_opps", + .procname = "ftrace_dump_on_oops", .data = &ftrace_dump_on_oops, .maxlen = sizeof(int), .mode = 0644, -- cgit v1.2.3-71-gd317 From 76aac0e9a17742e60d408be1a706e9aaad370891 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:12 +1100 Subject: CRED: Wrap task credential accesses in the core kernel Wrap access to task credentials so that they can be separated more easily from the task_struct during the introduction of COW creds. Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id(). Change some task->e?[ug]id to task_e?[ug]id(). In some places it makes more sense to use RCU directly rather than a convenient wrapper; these will be addressed by later patches. Signed-off-by: David Howells Reviewed-by: James Morris Acked-by: Serge Hallyn Cc: Al Viro Cc: linux-audit@redhat.com Cc: containers@lists.linux-foundation.org Cc: linux-mm@kvack.org Signed-off-by: James Morris --- kernel/acct.c | 7 +++---- kernel/auditsc.c | 6 ++++-- kernel/cgroup.c | 9 +++++---- kernel/futex.c | 8 +++++--- kernel/futex_compat.c | 3 ++- kernel/ptrace.c | 15 +++++++++------ kernel/sched.c | 11 +++++++---- kernel/signal.c | 15 +++++++++------ kernel/sys.c | 16 ++++++++-------- kernel/sysctl.c | 2 +- kernel/timer.c | 8 ++++---- kernel/user_namespace.c | 2 +- mm/mempolicy.c | 7 +++++-- mm/migrate.c | 7 +++++-- mm/shmem.c | 8 ++++---- 15 files changed, 72 insertions(+), 52 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/acct.c b/kernel/acct.c index f6006a60df5d..d57b7cbb98b6 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -530,15 +530,14 @@ static void do_acct_process(struct bsd_acct_struct *acct, do_div(elapsed, AHZ); ac.ac_btime = get_seconds() - elapsed; /* we really need to bite the bullet and change layout */ - ac.ac_uid = current->uid; - ac.ac_gid = current->gid; + current_uid_gid(&ac.ac_uid, &ac.ac_gid); #if ACCT_VERSION==2 ac.ac_ahz = AHZ; #endif #if ACCT_VERSION==1 || ACCT_VERSION==2 /* backward-compatible 16 bit fields */ - ac.ac_uid16 = current->uid; - ac.ac_gid16 = current->gid; + ac.ac_uid16 = ac.ac_uid; + ac.ac_gid16 = ac.ac_gid; #endif #if ACCT_VERSION==3 ac.ac_pid = task_tgid_nr_ns(current, ns); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index cef34235b362..9c7e47ae4576 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2628,7 +2628,8 @@ void audit_core_dumps(long signr) { struct audit_buffer *ab; u32 sid; - uid_t auid = audit_get_loginuid(current); + uid_t auid = audit_get_loginuid(current), uid; + gid_t gid; unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) @@ -2638,8 +2639,9 @@ void audit_core_dumps(long signr) return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + current_uid_gid(&uid, &gid); audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", - auid, current->uid, current->gid, sessionid); + auid, uid, gid, sessionid); security_task_getsecid(current, &sid); if (sid) { char *ctx = NULL; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 35eebd5510c2..78f9b310c4f3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -571,8 +571,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + 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; @@ -1279,6 +1279,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) { struct task_struct *tsk; + uid_t euid; int ret; if (pid) { @@ -1291,8 +1292,8 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) get_task_struct(tsk); rcu_read_unlock(); - if ((current->euid) && (current->euid != tsk->uid) - && (current->euid != tsk->suid)) { + euid = current_euid(); + if (euid && euid != tsk->uid && euid != tsk->suid) { put_task_struct(tsk); return -EACCES; } diff --git a/kernel/futex.c b/kernel/futex.c index 8af10027514b..e06962132aaf 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -439,10 +439,11 @@ static void free_pi_state(struct futex_pi_state *pi_state) static struct task_struct * futex_find_get_task(pid_t pid) { struct task_struct *p; + uid_t euid = current_euid(); rcu_read_lock(); p = find_task_by_vpid(pid); - if (!p || ((current->euid != p->euid) && (current->euid != p->uid))) + if (!p || (euid != p->euid && euid != p->uid)) p = ERR_PTR(-ESRCH); else get_task_struct(p); @@ -1829,6 +1830,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, { struct robust_list_head __user *head; unsigned long ret; + uid_t euid = current_euid(); if (!futex_cmpxchg_enabled) return -ENOSYS; @@ -1844,8 +1846,8 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_PTRACE)) + if (euid != p->euid && euid != p->uid && + !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 04ac3a9e42cf..3254d4e41e88 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -135,6 +135,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, { struct compat_robust_list_head __user *head; unsigned long ret; + uid_t euid = current_euid(); if (!futex_cmpxchg_enabled) return -ENOSYS; @@ -150,7 +151,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && + if (euid != p->euid && euid != p->uid && !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->compat_robust_list; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1e68e4c39e2c..937f6b5b2008 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -123,16 +123,19 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ + uid_t uid; + gid_t gid; int dumpable = 0; /* Don't let security modules deny introspection */ if (task == current) return 0; - if (((current->uid != task->euid) || - (current->uid != task->suid) || - (current->uid != task->uid) || - (current->gid != task->egid) || - (current->gid != task->sgid) || - (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) + current_uid_gid(&uid, &gid); + if ((uid != task->euid || + uid != task->suid || + uid != task->uid || + gid != task->egid || + gid != task->sgid || + gid != task->gid) && !capable(CAP_SYS_PTRACE)) return -EPERM; smp_rmb(); if (task->mm) diff --git a/kernel/sched.c b/kernel/sched.c index e8819bc6f462..c3b8b1fcde0d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5128,6 +5128,7 @@ static int __sched_setscheduler(struct task_struct *p, int policy, unsigned long flags; const struct sched_class *prev_class = p->sched_class; struct rq *rq; + uid_t euid; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -5180,8 +5181,9 @@ recheck: return -EPERM; /* can't change other user's priorities */ - if ((current->euid != p->euid) && - (current->euid != p->uid)) + euid = current_euid(); + if (euid != p->euid && + euid != p->uid) return -EPERM; } @@ -5392,6 +5394,7 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask) cpumask_t cpus_allowed; cpumask_t new_mask = *in_mask; struct task_struct *p; + uid_t euid; int retval; get_online_cpus(); @@ -5412,9 +5415,9 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask) get_task_struct(p); read_unlock(&tasklist_lock); + euid = current_euid(); retval = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_NICE)) + if (euid != p->euid && euid != p->uid && !capable(CAP_SYS_NICE)) goto out_unlock; retval = security_task_setscheduler(p, 0, NULL); diff --git a/kernel/signal.c b/kernel/signal.c index 4530fc654455..167b535fe1a9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -567,6 +567,7 @@ static int check_kill_permission(int sig, struct siginfo *info, struct task_struct *t) { struct pid *sid; + uid_t uid, euid; int error; if (!valid_signal(sig)) @@ -579,8 +580,10 @@ static int check_kill_permission(int sig, struct siginfo *info, if (error) return error; - if ((current->euid ^ t->suid) && (current->euid ^ t->uid) && - (current->uid ^ t->suid) && (current->uid ^ t->uid) && + uid = current_uid(); + euid = current_euid(); + if ((euid ^ t->suid) && (euid ^ t->uid) && + (uid ^ t->suid) && (uid ^ t->uid) && !capable(CAP_KILL)) { switch (sig) { case SIGCONT: @@ -844,7 +847,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, q->info.si_errno = 0; q->info.si_code = SI_USER; q->info.si_pid = task_pid_vnr(current); - q->info.si_uid = current->uid; + q->info.si_uid = current_uid(); break; case (unsigned long) SEND_SIG_PRIV: q->info.si_signo = sig; @@ -1598,7 +1601,7 @@ void ptrace_notify(int exit_code) info.si_signo = SIGTRAP; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); /* Let the debugger run. */ spin_lock_irq(¤t->sighand->siglock); @@ -2211,7 +2214,7 @@ sys_kill(pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_USER; info.si_pid = task_tgid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); return kill_something_info(sig, &info, pid); } @@ -2228,7 +2231,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_TKILL; info.si_pid = task_tgid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); rcu_read_lock(); p = find_task_by_vpid(pid); diff --git a/kernel/sys.c b/kernel/sys.c index 31deba8f7d16..ed5c29c748ac 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -114,10 +114,10 @@ void (*pm_power_off_prepare)(void); static int set_one_prio(struct task_struct *p, int niceval, int error) { + uid_t euid = current_euid(); int no_nice; - if (p->uid != current->euid && - p->euid != current->euid && !capable(CAP_SYS_NICE)) { + if (p->uid != euid && p->euid != euid && !capable(CAP_SYS_NICE)) { error = -EPERM; goto out; } @@ -176,16 +176,16 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) case PRIO_USER: user = current->user; if (!who) - who = current->uid; + who = current_uid(); else - if ((who != current->uid) && !(user = find_user(who))) + if (who != current_uid() && !(user = find_user(who))) goto out_unlock; /* No processes for this user */ do_each_thread(g, p) if (p->uid == who) error = set_one_prio(p, niceval, error); while_each_thread(g, p); - if (who != current->uid) + if (who != current_uid()) free_uid(user); /* For find_user() */ break; } @@ -238,9 +238,9 @@ asmlinkage long sys_getpriority(int which, int who) case PRIO_USER: user = current->user; if (!who) - who = current->uid; + who = current_uid(); else - if ((who != current->uid) && !(user = find_user(who))) + if (who != current_uid() && !(user = find_user(who))) goto out_unlock; /* No processes for this user */ do_each_thread(g, p) @@ -250,7 +250,7 @@ asmlinkage long sys_getpriority(int which, int who) retval = niceval; } while_each_thread(g, p); - if (who != current->uid) + if (who != current_uid()) free_uid(user); /* for find_user() */ break; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 9d048fa2d902..511031381c33 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1641,7 +1641,7 @@ out: static int test_perm(int mode, int op) { - if (!current->euid) + if (!current_euid()) mode >>= 6; else if (in_egroup_p(0)) mode >>= 3; diff --git a/kernel/timer.c b/kernel/timer.c index 56becf373c58..b54e4646cee7 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1123,25 +1123,25 @@ asmlinkage long sys_getppid(void) asmlinkage long sys_getuid(void) { /* Only we change this so SMP safe */ - return current->uid; + return current_uid(); } asmlinkage long sys_geteuid(void) { /* Only we change this so SMP safe */ - return current->euid; + return current_euid(); } asmlinkage long sys_getgid(void) { /* Only we change this so SMP safe */ - return current->gid; + return current_gid(); } asmlinkage long sys_getegid(void) { /* Only we change this so SMP safe */ - return current->egid; + return current_egid(); } #endif diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 532858fa5b88..f82730adea00 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -38,7 +38,7 @@ static struct user_namespace *clone_user_ns(struct user_namespace *old_ns) } /* Reset current->user with a new one */ - new_user = alloc_uid(ns, current->uid); + new_user = alloc_uid(ns, current_uid()); if (!new_user) { free_uid(ns->root_user); kfree(ns); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 36f42573a335..07a96474077d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1115,6 +1115,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, nodemask_t old; nodemask_t new; nodemask_t task_nodes; + uid_t uid, euid; int err; err = get_nodes(&old, old_nodes, maxnode); @@ -1144,8 +1145,10 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + uid = current_uid(); + euid = current_euid(); + if (euid != task->suid && euid != task->uid && + uid != task->suid && uid != task->uid && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out; diff --git a/mm/migrate.c b/mm/migrate.c index 6602941bfab0..6263c24c4afe 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1048,6 +1048,7 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, struct task_struct *task; struct mm_struct *mm; int err; + uid_t uid, euid; /* Check flags */ if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) @@ -1075,8 +1076,10 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + uid = current_uid(); + euid = current_euid(); + if (euid != task->suid && euid != task->uid && + uid != task->suid && uid != task->uid && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out; diff --git a/mm/shmem.c b/mm/shmem.c index 0ed075215e5f..f1b0d4871f3a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1513,8 +1513,8 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) inode = new_inode(sb); if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -2278,8 +2278,8 @@ static int shmem_fill_super(struct super_block *sb, sbinfo->max_blocks = 0; sbinfo->max_inodes = 0; sbinfo->mode = S_IRWXUGO | S_ISVTX; - sbinfo->uid = current->fsuid; - sbinfo->gid = current->fsgid; + sbinfo->uid = current_fsuid(); + sbinfo->gid = current_fsgid(); sbinfo->mpol = NULL; sb->s_fs_info = sbinfo; -- cgit v1.2.3-71-gd317 From 0871420fad5844cb63cfcf85508c17bd9b15c08f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 16 Nov 2008 23:49:24 -0800 Subject: sparc64: Add tsb-ratio sysctl. Add a sysctl to tweak the RSS limit used to decide when to grow the TSB for an address space. In order to avoid expensive divides and multiplies only simply positive and negative powers of two are supported. The function computed takes the number of TSB translations that will fit at one time in the TSB of a given size, and either adds or subtracts a percentage of entries. This final value is the RSS limit. See tsb_size_to_rss_limit(). Signed-off-by: David S. Miller --- arch/sparc/mm/tsb.c | 21 ++++++++++++++------- kernel/sysctl.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+), 7 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index f0282fad632a..36a0813f9517 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -265,6 +265,18 @@ void __init pgtable_cache_init(void) } } +int sysctl_tsb_ratio = -2; + +static unsigned long tsb_size_to_rss_limit(unsigned long new_size) +{ + unsigned long num_ents = (new_size / sizeof(struct tsb)); + + if (sysctl_tsb_ratio < 0) + return num_ents - (num_ents >> -sysctl_tsb_ratio); + else + return num_ents + (num_ents >> sysctl_tsb_ratio); +} + /* When the RSS of an address space exceeds tsb_rss_limit for a TSB, * do_sparc64_fault() invokes this routine to try and grow it. * @@ -295,19 +307,14 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss) new_cache_index = 0; for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) { - unsigned long n_entries = new_size / sizeof(struct tsb); - - n_entries = (n_entries * 3) / 4; - if (n_entries > rss) + new_rss_limit = tsb_size_to_rss_limit(new_size); + if (new_rss_limit > rss) break; - new_cache_index++; } if (new_size == max_tsb_size) new_rss_limit = ~0UL; - else - new_rss_limit = ((new_size / sizeof(struct tsb)) * 3) / 4; retry_tsb_alloc: gfp_flags = GFP_KERNEL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3d56fe7570da..4e2ac0aec9b0 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -121,6 +121,10 @@ extern int sg_big_buff; #include #endif +#ifdef CONFIG_SPARC64 +extern int sysctl_tsb_ratio; +#endif + #ifdef __hppa__ extern int pwrsw_enabled; extern int unaligned_enabled; @@ -451,6 +455,16 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif +#ifdef CONFIG_SPARC64 + { + .ctl_name = CTL_UNNUMBERED, + .procname = "tsb-ratio", + .data = &sysctl_tsb_ratio, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef __hppa__ { .ctl_name = KERN_HPPA_PWRSW, -- cgit v1.2.3-71-gd317 From f38f1d2aa5a3520cf05da7cd6bd12fe2b0c509b7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 16 Dec 2008 23:06:40 -0500 Subject: trace: add a way to enable or disable the stack tracer Impact: enhancement to stack tracer The stack tracer currently is either on when configured in or off when it is not. It can not be disabled when it is configured on. (besides disabling the function tracer that it uses) This patch adds a way to enable or disable the stack tracer at run time. It defaults off on bootup, but a kernel parameter 'stacktrace' has been added to enable it on bootup. A new sysctl has been added "kernel.stack_tracer_enabled" to let the user enable or disable the stack tracer at run time. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- Documentation/kernel-parameters.txt | 4 +++ include/linux/ftrace.h | 8 ++++++ kernel/sysctl.c | 10 +++++++ kernel/trace/Kconfig | 13 +++++++--- kernel/trace/trace_stack.c | 52 ++++++++++++++++++++++++++++++++++--- 5 files changed, 79 insertions(+), 8 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 2919a2e91938..edab81c13182 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -89,6 +89,7 @@ parameter is applicable: SPARC Sparc architecture is enabled. SWSUSP Software suspend (hibernation) is enabled. SUSPEND System suspend states are enabled. + FTRACE Function tracing enabled. TS Appropriate touchscreen support is enabled. USB USB support is enabled. USBHID USB Human Interface Device support is enabled. @@ -2173,6 +2174,9 @@ and is between 256 and 4096 characters. It is defined in the file st= [HW,SCSI] SCSI tape parameters (buffers, etc.) See Documentation/scsi/st.txt. + stacktrace [FTRACE] + Enabled the stack tracer on boot up. + sti= [PARISC,HW] Format: Set the STI (builtin display/keyboard on the HP-PARISC diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 44020f31bd81..6b0db53caa7d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -86,6 +86,14 @@ static inline void ftrace_stop(void) { } static inline void ftrace_start(void) { } #endif /* CONFIG_FUNCTION_TRACER */ +#ifdef CONFIG_STACK_TRACER +extern int stack_tracer_enabled; +int +stack_trace_sysctl(struct ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + #ifdef CONFIG_DYNAMIC_FTRACE /* asm/ftrace.h must be defined for archs supporting dynamic ftrace */ #include diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c83f566e940a..6ac501a2dcc6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -487,6 +487,16 @@ static struct ctl_table kern_table[] = { .proc_handler = &ftrace_enable_sysctl, }, #endif +#ifdef CONFIG_STACK_TRACER + { + .ctl_name = CTL_UNNUMBERED, + .procname = "stack_tracer_enabled", + .data = &stack_tracer_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &stack_trace_sysctl, + }, +#endif #ifdef CONFIG_TRACING { .ctl_name = CTL_UNNUMBERED, diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d8bae6f4219e..e2a4ff6fc3a6 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -244,10 +244,15 @@ config STACK_TRACER This tracer works by hooking into every function call that the kernel executes, and keeping a maximum stack depth value and - stack-trace saved. Because this logic has to execute in every - kernel function, all the time, this option can slow down the - kernel measurably and is generally intended for kernel - developers only. + stack-trace saved. If this is configured with DYNAMIC_FTRACE + then it will not have any overhead while the stack tracer + is disabled. + + To enable the stack tracer on bootup, pass in 'stacktrace' + on the kernel command line. + + The stack tracer can also be enabled or disabled via the + sysctl kernel.stack_tracer_enabled Say N if unsure. diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0b863f2cbc8e..4842c969c785 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include "trace.h" @@ -31,6 +32,10 @@ static raw_spinlock_t max_stack_lock = static int stack_trace_disabled __read_mostly; static DEFINE_PER_CPU(int, trace_active); +static DEFINE_MUTEX(stack_sysctl_mutex); + +int stack_tracer_enabled; +static int last_stack_tracer_enabled; static inline void check_stack(void) { @@ -174,7 +179,7 @@ stack_max_size_write(struct file *filp, const char __user *ubuf, return count; } -static struct file_operations stack_max_size_fops = { +static const struct file_operations stack_max_size_fops = { .open = tracing_open_generic, .read = stack_max_size_read, .write = stack_max_size_write, @@ -272,7 +277,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations stack_trace_seq_ops = { +static const struct seq_operations stack_trace_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, @@ -288,12 +293,48 @@ static int stack_trace_open(struct inode *inode, struct file *file) return ret; } -static struct file_operations stack_trace_fops = { +static const struct file_operations stack_trace_fops = { .open = stack_trace_open, .read = seq_read, .llseek = seq_lseek, }; +int +stack_trace_sysctl(struct ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + mutex_lock(&stack_sysctl_mutex); + + ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + + if (ret || !write || + (last_stack_tracer_enabled == stack_tracer_enabled)) + goto out; + + last_stack_tracer_enabled = stack_tracer_enabled; + + if (stack_tracer_enabled) + register_ftrace_function(&trace_ops); + else + unregister_ftrace_function(&trace_ops); + + out: + mutex_unlock(&stack_sysctl_mutex); + return ret; +} + +static int start_stack_trace __initdata; + +static __init int enable_stacktrace(char *str) +{ + start_stack_trace = 1; + return 1; +} +__setup("stacktrace", enable_stacktrace); + static __init int stack_trace_init(void) { struct dentry *d_tracer; @@ -311,7 +352,10 @@ static __init int stack_trace_init(void) if (!entry) pr_warning("Could not create debugfs 'stack_trace' entry\n"); - register_ftrace_function(&trace_ops); + if (start_stack_trace) { + register_ftrace_function(&trace_ops); + stack_tracer_enabled = 1; + } return 0; } -- cgit v1.2.3-71-gd317 From 2da02997e08d3efe8174c7a47696e6f7cbe69ba9 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 6 Jan 2009 14:39:31 -0800 Subject: mm: add dirty_background_bytes and dirty_bytes sysctls This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra Cc: Dave Chinner Cc: Christoph Lameter Signed-off-by: David Rientjes Cc: Andrea Righi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 26 +++++++++- Documentation/sysctl/vm.txt | 3 +- include/linux/writeback.h | 11 ++++ kernel/sysctl.c | 27 ++++++++-- mm/page-writeback.c | 102 +++++++++++++++++++++++++++++++------ 5 files changed, 146 insertions(+), 23 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 71df353e367c..32e94635484f 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1385,6 +1385,15 @@ swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100 causes the kernel to prefer to reclaim dentries and inodes. +dirty_background_bytes +---------------------- + +Contains the amount of dirty memory at which the pdflush background writeback +daemon will start writeback. + +If dirty_background_bytes is written, dirty_background_ratio becomes a function +of its value (dirty_background_bytes / the amount of dirtyable system memory). + dirty_background_ratio ---------------------- @@ -1393,14 +1402,29 @@ pages + file cache, not including locked pages and HugePages), the number of pages at which the pdflush background writeback daemon will start writing out dirty data. +If dirty_background_ratio is written, dirty_background_bytes becomes a function +of its value (dirty_background_ratio * the amount of dirtyable system memory). + +dirty_bytes +----------- + +Contains the amount of dirty memory at which a process generating disk writes +will itself start writeback. + +If dirty_bytes is written, dirty_ratio becomes a function of its value +(dirty_bytes / the amount of dirtyable system memory). + dirty_ratio ------------------ +----------- Contains, as a percentage of the dirtyable system memory (free pages + mapped pages + file cache, not including locked pages and HugePages), the number of pages at which a process which is generating disk writes will itself start writing out dirty data. +If dirty_ratio is written, dirty_bytes becomes a function of its value +(dirty_ratio * the amount of dirtyable system memory). + dirty_writeback_centisecs ------------------------- diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index d79eeda7a699..cd05994a49e6 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -41,7 +41,8 @@ Currently, these files are in /proc/sys/vm: ============================================================== -dirty_ratio, dirty_background_ratio, dirty_expire_centisecs, +dirty_bytes, dirty_ratio, dirty_background_bytes, +dirty_background_ratio, dirty_expire_centisecs, dirty_writeback_centisecs, highmem_is_dirtyable, vfs_cache_pressure, laptop_mode, block_dump, swap_token_timeout, drop-caches, hugepages_treat_as_movable: diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 259e9ea58cab..bb28c975c1d7 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -107,7 +107,9 @@ void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ extern int dirty_background_ratio; +extern unsigned long dirty_background_bytes; extern int vm_dirty_ratio; +extern unsigned long vm_dirty_bytes; extern int dirty_writeback_interval; extern int dirty_expire_interval; extern int vm_highmem_is_dirtyable; @@ -116,9 +118,18 @@ extern int laptop_mode; extern unsigned long determine_dirtyable_memory(void); +extern int dirty_background_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); +extern int dirty_background_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); extern int dirty_ratio_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); +extern int dirty_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); struct ctl_table; struct file; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ff6d45c7626f..92f6e5bc3c24 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -87,10 +87,6 @@ extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ /* Constants used for minimum and maximum */ -#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP) -static int one = 1; -#endif - #ifdef CONFIG_DETECT_SOFTLOCKUP static int sixty = 60; static int neg_one = -1; @@ -101,6 +97,7 @@ static int two = 2; #endif static int zero; +static int one = 1; static int one_hundred = 100; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -952,11 +949,21 @@ static struct ctl_table vm_table[] = { .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = &dirty_background_ratio_handler, .strategy = &sysctl_intvec, .extra1 = &zero, .extra2 = &one_hundred, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "dirty_background_bytes", + .data = &dirty_background_bytes, + .maxlen = sizeof(dirty_background_bytes), + .mode = 0644, + .proc_handler = &dirty_background_bytes_handler, + .strategy = &sysctl_intvec, + .extra1 = &one, + }, { .ctl_name = VM_DIRTY_RATIO, .procname = "dirty_ratio", @@ -968,6 +975,16 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, .extra2 = &one_hundred, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "dirty_bytes", + .data = &vm_dirty_bytes, + .maxlen = sizeof(vm_dirty_bytes), + .mode = 0644, + .proc_handler = &dirty_bytes_handler, + .strategy = &sysctl_intvec, + .extra1 = &one, + }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4d4074cff300..b493db7841dc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -68,6 +68,12 @@ static inline long sync_writeback_pages(void) */ int dirty_background_ratio = 5; +/* + * dirty_background_bytes starts at 0 (disabled) so that it is a function of + * dirty_background_ratio * the amount of dirtyable memory + */ +unsigned long dirty_background_bytes; + /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true @@ -79,6 +85,12 @@ int vm_highmem_is_dirtyable; */ int vm_dirty_ratio = 10; +/* + * vm_dirty_bytes starts at 0 (disabled) so that it is a function of + * vm_dirty_ratio * the amount of dirtyable memory + */ +unsigned long vm_dirty_bytes; + /* * The interval between `kupdate'-style writebacks, in jiffies */ @@ -135,23 +147,75 @@ static int calc_period_shift(void) { unsigned long dirty_total; - dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100; + if (vm_dirty_bytes) + dirty_total = vm_dirty_bytes / PAGE_SIZE; + else + dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / + 100; return 2 + ilog2(dirty_total - 1); } /* - * update the period when the dirty ratio changes. + * update the period when the dirty threshold changes. */ +static void update_completion_period(void) +{ + int shift = calc_period_shift(); + prop_change_shift(&vm_completions, shift); + prop_change_shift(&vm_dirties, shift); +} + +int dirty_background_ratio_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_bytes = 0; + return ret; +} + +int dirty_background_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write) + dirty_background_ratio = 0; + return ret; +} + int dirty_ratio_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret; + + ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { - int shift = calc_period_shift(); - prop_change_shift(&vm_completions, shift); - prop_change_shift(&vm_dirties, shift); + update_completion_period(); + vm_dirty_bytes = 0; + } + return ret; +} + + +int dirty_bytes_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_bytes = vm_dirty_bytes; + int ret; + + ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + if (ret == 0 && write && vm_dirty_bytes != old_bytes) { + update_completion_period(); + vm_dirty_ratio = 0; } return ret; } @@ -365,23 +429,29 @@ void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, unsigned long *pbdi_dirty, struct backing_dev_info *bdi) { - int background_ratio; /* Percentages */ - int dirty_ratio; unsigned long background; unsigned long dirty; unsigned long available_memory = determine_dirtyable_memory(); struct task_struct *tsk; - dirty_ratio = vm_dirty_ratio; - if (dirty_ratio < 5) - dirty_ratio = 5; + if (vm_dirty_bytes) + dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); + else { + int dirty_ratio; - background_ratio = dirty_background_ratio; - if (background_ratio >= dirty_ratio) - background_ratio = dirty_ratio / 2; + dirty_ratio = vm_dirty_ratio; + if (dirty_ratio < 5) + dirty_ratio = 5; + dirty = (dirty_ratio * available_memory) / 100; + } + + if (dirty_background_bytes) + background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE); + else + background = (dirty_background_ratio * available_memory) / 100; - background = (background_ratio * available_memory) / 100; - dirty = (dirty_ratio * available_memory) / 100; + if (background >= dirty) + background = dirty / 2; tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { background += background / 4; -- cgit v1.2.3-71-gd317 From dd8632a12e500a684478fea0951f380478d56fed Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 8 Jan 2009 12:04:47 +0000 Subject: NOMMU: Make mmap allocation page trimming behaviour configurable. NOMMU mmap allocates a piece of memory for an mmap that's rounded up in size to the nearest power-of-2 number of pages. Currently it then discards the excess pages back to the page allocator, making that memory available for use by other things. This can, however, cause greater amount of fragmentation. To counter this, a sysctl is added in order to fine-tune the trimming behaviour. The default behaviour remains to trim pages aggressively, while this can either be disabled completely or set to a higher page-granular watermark in order to have finer-grained control. vm region vm_top bits taken from an earlier patch by David Howells. Signed-off-by: Paul Mundt Signed-off-by: David Howells Tested-by: Mike Frysinger --- Documentation/nommu-mmap.txt | 15 ++++++++++ Documentation/sysctl/vm.txt | 18 ++++++++++++ include/linux/mm_types.h | 1 + kernel/sysctl.c | 14 ++++++++++ mm/nommu.c | 65 ++++++++++++++++++++++++++++---------------- 5 files changed, 90 insertions(+), 23 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 02b89dcf38ac..b565e8279d13 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -248,3 +248,18 @@ PROVIDING SHAREABLE BLOCK DEVICE SUPPORT Provision of shared mappings on block device files is exactly the same as for character devices. If there isn't a real device underneath, then the driver should allocate sufficient contiguous memory to honour any supported mapping. + + +================================= +ADJUSTING PAGE TRIMMING BEHAVIOUR +================================= + +NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages +when performing an allocation. This can have adverse effects on memory +fragmentation, and as such, is left configurable. The default behaviour is to +aggressively trim allocations and discard any excess pages back in to the page +allocator. In order to retain finer-grained control over fragmentation, this +behaviour can either be disabled completely, or bumped up to a higher page +watermark where trimming begins. + +Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'. diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index cd05994a49e6..a3415070bcac 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -38,6 +38,7 @@ Currently, these files are in /proc/sys/vm: - numa_zonelist_order - nr_hugepages - nr_overcommit_hugepages +- nr_trim_pages (only if CONFIG_MMU=n) ============================================================== @@ -348,3 +349,20 @@ Change the maximum size of the hugepage pool. The maximum is nr_hugepages + nr_overcommit_hugepages. See Documentation/vm/hugetlbpage.txt + +============================================================== + +nr_trim_pages + +This is available only on NOMMU kernels. + +This value adjusts the excess page trimming behaviour of power-of-2 aligned +NOMMU mmap allocations. + +A value of 0 disables trimming of allocations entirely, while a value of 1 +trims excess pages aggressively. Any value >= 1 acts as the watermark where +trimming of allocations is initiated. + +The default value is 1. + +See Documentation/nommu-mmap.txt for more information. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1c1e0d3a1714..92915e81443f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -106,6 +106,7 @@ struct vm_region { 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_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 92f6e5bc3c24..89d74436318c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -82,6 +82,9 @@ extern int percpu_pagelist_fraction; extern int compat_log; extern int latencytop_enabled; extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifndef CONFIG_MMU +extern int sysctl_nr_trim_pages; +#endif #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ @@ -1102,6 +1105,17 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_dointvec }, +#else + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nr_trim_pages", + .data = &sysctl_nr_trim_pages, + .maxlen = sizeof(sysctl_nr_trim_pages), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, #endif { .ctl_name = VM_LAPTOP_MODE, diff --git a/mm/nommu.c b/mm/nommu.c index 0d363dfcf10e..a6e8ccfbd400 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -10,7 +10,7 @@ * Copyright (c) 2000-2003 David McCullough * Copyright (c) 2000-2001 D Jeff Dionne * Copyright (c) 2002 Greg Ungerer - * Copyright (c) 2007 Paul Mundt + * Copyright (c) 2007-2008 Paul Mundt */ #include @@ -66,6 +66,7 @@ atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0); int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; +int sysctl_nr_trim_pages = 1; /* page trimming behaviour */ int heap_stack_gap = 0; atomic_t mmap_pages_allocated; @@ -455,6 +456,8 @@ static noinline void validate_nommu_regions(void) last = rb_entry(lastp, struct vm_region, vm_rb); if (unlikely(last->vm_end <= last->vm_start)) BUG(); + if (unlikely(last->vm_top < last->vm_end)) + BUG(); while ((p = rb_next(lastp))) { region = rb_entry(p, struct vm_region, vm_rb); @@ -462,7 +465,9 @@ static noinline void validate_nommu_regions(void) if (unlikely(region->vm_end <= region->vm_start)) BUG(); - if (unlikely(region->vm_start < last->vm_end)) + if (unlikely(region->vm_top < region->vm_end)) + BUG(); + if (unlikely(region->vm_start < last->vm_top)) BUG(); lastp = p; @@ -536,7 +541,7 @@ static void free_page_series(unsigned long from, unsigned long to) /* * 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 + * - the region may not have been added to the tree yet, in which case vm_top * will equal vm_start */ static void __put_nommu_region(struct vm_region *region) @@ -547,7 +552,7 @@ static void __put_nommu_region(struct vm_region *region) BUG_ON(!nommu_region_tree.rb_node); if (atomic_dec_and_test(®ion->vm_usage)) { - if (region->vm_end > region->vm_start) + if (region->vm_top > region->vm_start) delete_nommu_region(region); up_write(&nommu_region_sem); @@ -558,7 +563,7 @@ static void __put_nommu_region(struct vm_region *region) * 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); + free_page_series(region->vm_start, region->vm_top); } kmem_cache_free(vm_region_jar, region); } else { @@ -999,6 +1004,10 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) int ret; ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + if (ret == 0) { + vma->vm_region->vm_top = vma->vm_region->vm_end; + return ret; + } if (ret != -ENOSYS) return ret; @@ -1027,11 +1036,14 @@ static int do_mmap_private(struct vm_area_struct *vma, */ if (vma->vm_file) { ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); - if (ret != -ENOSYS) { + if (ret == 0) { /* shouldn't return success if we're not sharing */ - BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE)); - return ret; /* success or a real error */ + BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); + vma->vm_region->vm_top = vma->vm_region->vm_end; + return ret; } + if (ret != -ENOSYS) + return ret; /* getting an ENOSYS error indicates that direct mmap isn't * possible (as opposed to tried but failed) so we'll try to @@ -1051,23 +1063,25 @@ static int do_mmap_private(struct vm_area_struct *vma, if (!pages) goto enomem; - /* 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); + + /* we allocated a power-of-2 sized page set, so we may want to trim off + * the excess */ + if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) { + 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]); @@ -1075,6 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma, region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; region->vm_start = (unsigned long) base; region->vm_end = region->vm_start + rlen; + region->vm_top = region->vm_start + (total << PAGE_SHIFT); vma->vm_start = region->vm_start; vma->vm_end = region->vm_start + len; @@ -1110,6 +1125,7 @@ error_free: free_page_series(region->vm_start, region->vm_end); region->vm_start = vma->vm_start = 0; region->vm_end = vma->vm_end = 0; + region->vm_top = 0; return ret; enomem: @@ -1401,7 +1417,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, npages = (addr - vma->vm_start) >> PAGE_SHIFT; if (new_below) { - region->vm_end = new->vm_end = addr; + region->vm_top = region->vm_end = new->vm_end = addr; } else { region->vm_start = new->vm_start = addr; region->vm_pgoff = new->vm_pgoff += npages; @@ -1418,6 +1434,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; } else { vma->vm_region->vm_end = vma->vm_end = addr; + vma->vm_region->vm_top = addr; } add_nommu_region(vma->vm_region); add_nommu_region(new->vm_region); @@ -1454,10 +1471,12 @@ static int shrink_vma(struct mm_struct *mm, down_write(&nommu_region_sem); delete_nommu_region(region); - if (from > region->vm_start) - region->vm_end = from; - else + if (from > region->vm_start) { + to = region->vm_top; + region->vm_top = region->vm_end = from; + } else { region->vm_start = to; + } add_nommu_region(region); up_write(&nommu_region_sem); -- cgit v1.2.3-71-gd317 From 1e7bfb2134dfec37ce04fb3a4ca89299e892d10c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 14 Jan 2009 14:14:29 +0100 Subject: [CVE-2009-0029] System call wrappers part 27 Signed-off-by: Heiko Carstens --- fs/exec.c | 2 +- fs/filesystems.c | 2 +- fs/nfsctl.c | 4 ++-- kernel/printk.c | 2 +- kernel/ptrace.c | 2 +- kernel/sysctl.c | 4 ++-- kernel/timer.c | 2 +- security/keys/keyctl.c | 18 +++++++++--------- 8 files changed, 18 insertions(+), 18 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/fs/exec.c b/fs/exec.c index 71a6efe5d8bd..0dd60a01f1b4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -99,7 +99,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt) * * Also note that we take the address to load from from the file itself. */ -asmlinkage long sys_uselib(const char __user * library) +SYSCALL_DEFINE1(uselib, const char __user *, library) { struct file *file; struct nameidata nd; diff --git a/fs/filesystems.c b/fs/filesystems.c index d488dcd7f2bb..1aa70260e6d1 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -179,7 +179,7 @@ static int fs_maxindex(void) /* * Whee.. Weird sysv syscall. */ -asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2) +SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) { int retval = -EINVAL; diff --git a/fs/nfsctl.c b/fs/nfsctl.c index b27451909dff..8f9a20556f79 100644 --- a/fs/nfsctl.c +++ b/fs/nfsctl.c @@ -86,8 +86,8 @@ static struct { }, }; -long -asmlinkage sys_nfsservctl(int cmd, struct nfsctl_arg __user *arg, void __user *res) +SYSCALL_DEFINE3(nfsservctl, int, cmd, struct nfsctl_arg __user *, arg, + void __user *, res) { struct file *file; void __user *p = &arg->u; diff --git a/kernel/printk.c b/kernel/printk.c index e48cf33783fc..69188f226a93 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -382,7 +382,7 @@ out: return error; } -asmlinkage long sys_syslog(int type, char __user *buf, int len) +SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len); } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 29dc700e198c..c9cf48b21f05 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -574,7 +574,7 @@ struct task_struct *ptrace_get_task_struct(pid_t pid) #define arch_ptrace_attach(child) do { } while (0) #endif -asmlinkage long sys_ptrace(long request, long pid, long addr, long data) +SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data) { struct task_struct *child; long ret; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 89d74436318c..3e38b74b6124 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1688,7 +1688,7 @@ int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *ol return error; } -asmlinkage long sys_sysctl(struct __sysctl_args __user *args) +SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) { struct __sysctl_args tmp; int error; @@ -2989,7 +2989,7 @@ int sysctl_ms_jiffies(struct ctl_table *table, #else /* CONFIG_SYSCTL_SYSCALL */ -asmlinkage long sys_sysctl(struct __sysctl_args __user *args) +SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) { struct __sysctl_args tmp; int error; diff --git a/kernel/timer.c b/kernel/timer.c index 14a51530a4cd..13dd64fe143d 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1400,7 +1400,7 @@ out: return 0; } -asmlinkage long sys_sysinfo(struct sysinfo __user *info) +SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) { struct sysinfo val; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 09796797d122..070a53eab80f 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -54,11 +54,11 @@ static int key_get_type_from_user(char *type, * - returns the new key's serial number * - implements add_key() */ -asmlinkage long sys_add_key(const char __user *_type, - const char __user *_description, - const void __user *_payload, - size_t plen, - key_serial_t ringid) +SYSCALL_DEFINE5(add_key, const char __user *, _type, + const char __user *, _description, + const void __user *, _payload, + size_t, plen, + key_serial_t, ringid) { key_ref_t keyring_ref, key_ref; char type[32], *description; @@ -146,10 +146,10 @@ asmlinkage long sys_add_key(const char __user *_type, * - if the _callout_info string is empty, it will be rendered as "-" * - implements request_key() */ -asmlinkage long sys_request_key(const char __user *_type, - const char __user *_description, - const char __user *_callout_info, - key_serial_t destringid) +SYSCALL_DEFINE4(request_key, const char __user *, _type, + const char __user *, _description, + const char __user *, _callout_info, + key_serial_t, destringid) { struct key_type *ktype; struct key *key; -- cgit v1.2.3-71-gd317 From 88fc241f54459ac3d86c5e13b449730199f66061 Mon Sep 17 00:00:00 2001 From: Doug Chapman Date: Thu, 15 Jan 2009 10:38:56 -0800 Subject: [IA64] dump stack on kernel unaligned warnings Often the cause of kernel unaligned access warnings is not obvious from just the ip displayed in the warning. This adds the option via proc to dump the stack in addition to the warning. The default is off (just display the 1 line warning). To enable the stack to be shown: echo 1 > /proc/sys/kernel/unaligned-dump-stack Signed-off-by: Doug Chapman Signed-off-by: Tony Luck --- arch/ia64/kernel/unaligned.c | 6 +++++- kernel/sysctl.c | 9 +++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c index ff0e7c10faa7..6db08599ebbc 100644 --- a/arch/ia64/kernel/unaligned.c +++ b/arch/ia64/kernel/unaligned.c @@ -59,6 +59,7 @@ dump (const char *str, void *vp, size_t len) * (i.e. don't allow attacker to fill up logs with unaligned accesses). */ int no_unaligned_warning; +int unaligned_dump_stack; static int noprint_warning; /* @@ -1371,9 +1372,12 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) } } } else { - if (within_logging_rate_limit()) + if (within_logging_rate_limit()) { printk(KERN_WARNING "kernel unaligned access to 0x%016lx, ip=0x%016lx\n", ifa, regs->cr_iip + ipsr->ri); + if (unaligned_dump_stack) + dump_stack(); + } set_fs(KERNEL_DS); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3e38b74b6124..368d1638ee78 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -144,6 +144,7 @@ extern int acct_parm[]; #ifdef CONFIG_IA64 extern int no_unaligned_warning; +extern int unaligned_dump_stack; #endif #ifdef CONFIG_RT_MUTEXES @@ -781,6 +782,14 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "unaligned-dump-stack", + .data = &unaligned_dump_stack, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, #endif #ifdef CONFIG_DETECT_SOFTLOCKUP { -- cgit v1.2.3-71-gd317