From dd17c8f72993f9461e9c19250e3f155d6d99df22 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 29 Oct 2009 22:34:15 +0900 Subject: percpu: remove per_cpu__ prefix. Now that the return from alloc_percpu is compatible with the address of per-cpu vars, it makes sense to hand around the address of per-cpu variables. To make this sane, we remove the per_cpu__ prefix we used created to stop people accidentally using these vars directly. Now we have sparse, we can use that (next patch). tj: * Updated to convert stuff which were missed by or added after the original patch. * Kill per_cpu_var() macro. Signed-off-by: Rusty Russell Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter --- kernel/rcutorture.c | 8 ++++---- kernel/trace/trace.c | 6 +++--- kernel/trace/trace_functions_graph.c | 4 ++-- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 178967b6434e..e339ab349121 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -731,13 +731,13 @@ static void rcu_torture_timer(unsigned long unused) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]); + __this_cpu_inc(rcu_torture_count[pipe_count]); completed = cur_ops->completed() - completed; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]); + __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); } @@ -786,13 +786,13 @@ rcu_torture_reader(void *arg) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]); + __this_cpu_inc(rcu_torture_count[pipe_count]); completed = cur_ops->completed() - completed; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } - __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]); + __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); schedule(); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 85a5ed70b5b2..b808177af816 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -91,12 +91,12 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled); static inline void ftrace_disable_cpu(void) { preempt_disable(); - __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled)); + __this_cpu_inc(ftrace_cpu_disabled); } static inline void ftrace_enable_cpu(void) { - __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled)); + __this_cpu_dec(ftrace_cpu_disabled); preempt_enable(); } @@ -1085,7 +1085,7 @@ trace_function(struct trace_array *tr, struct ftrace_entry *entry; /* If we are reading the ring buffer, don't trace */ - if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled)))) + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return; event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 90a6daa10962..8614e3241ff8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -176,7 +176,7 @@ static int __trace_graph_entry(struct trace_array *tr, struct ring_buffer *buffer = tr->buffer; struct ftrace_graph_ent_entry *entry; - if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled)))) + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return 0; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, @@ -240,7 +240,7 @@ static void __trace_graph_return(struct trace_array *tr, struct ring_buffer *buffer = tr->buffer; struct ftrace_graph_ret_entry *entry; - if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled)))) + if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) return; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, -- cgit v1.2.3 From 86fc80f16e8a2449d5827bf1a9838b7fd9f70097 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 9 Dec 2009 17:13:31 +0100 Subject: capabilities: Use RCU to protect task lookup in sys_capget cap_get_target_pid() protects the task lookup with tasklist_lock. security_capget() is called under tasklist_lock as well but tasklist_lock does not protect anything there. The capabilities are protected by RCU already. So tasklist_lock only protects the lookup and prevents the task going away, which can be done with rcu_read_lock() as well. Signed-off-by: Thomas Gleixner Signed-off-by: James Morris --- kernel/capability.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/capability.c b/kernel/capability.c index 7f876e60521f..9e4697e9b276 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -135,7 +135,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; - read_lock(&tasklist_lock); + rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) @@ -143,7 +143,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, else ret = security_capget(target, pEp, pIp, pPp); - read_unlock(&tasklist_lock); + rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); -- cgit v1.2.3 From e1783a240f491fb233f04edc042e16b18a7a79ba Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 5 Jan 2010 15:34:50 +0900 Subject: module: Use this_cpu_xx to dynamically allocate counters Use cpu ops to deal with the per cpu data instead of a local_t. Reduces memory requirements, cache footprint and decreases cycle counts. The this_cpu_xx operations are also used for !SMP mode. Otherwise we could not drop the use of __module_ref_addr() which would make per cpu data handling complicated. this_cpu_xx operations have their own fallback for !SMP. V8-V9: - Leave include asm/module.h since ringbuffer.c depends on it. Nothing else does though. Another patch will deal with that. - Remove spurious free. Signed-off-by: Christoph Lameter Acked-by: Rusty Russell Signed-off-by: Tejun Heo --- include/linux/module.h | 36 ++++++++++++++---------------------- kernel/module.c | 29 +++++++++++++++-------------- 2 files changed, 29 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/include/linux/module.h b/include/linux/module.h index 6cb1a3cab5d3..2302f09ea2d9 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -18,6 +18,7 @@ #include #include +#include #include #include @@ -363,11 +364,9 @@ struct module /* Destruction function. */ void (*exit)(void); -#ifdef CONFIG_SMP - char *refptr; -#else - local_t ref; -#endif + struct module_ref { + int count; + } *refptr; #endif #ifdef CONFIG_CONSTRUCTORS @@ -454,25 +453,16 @@ void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(MODULE_SYMBOL_PREFIX #x) void symbol_put_addr(void *addr); -static inline local_t *__module_ref_addr(struct module *mod, int cpu) -{ -#ifdef CONFIG_SMP - return (local_t *) (mod->refptr + per_cpu_offset(cpu)); -#else - return &mod->ref; -#endif -} - /* Sometimes we know we already have a refcount, and it's easier not to handle the error case (which only happens with rmmod --wait). */ static inline void __module_get(struct module *module) { if (module) { - unsigned int cpu = get_cpu(); - local_inc(__module_ref_addr(module, cpu)); + preempt_disable(); + __this_cpu_inc(module->refptr->count); trace_module_get(module, _THIS_IP_, - local_read(__module_ref_addr(module, cpu))); - put_cpu(); + __this_cpu_read(module->refptr->count)); + preempt_enable(); } } @@ -481,15 +471,17 @@ static inline int try_module_get(struct module *module) int ret = 1; if (module) { - unsigned int cpu = get_cpu(); + preempt_disable(); + if (likely(module_is_live(module))) { - local_inc(__module_ref_addr(module, cpu)); + __this_cpu_inc(module->refptr->count); trace_module_get(module, _THIS_IP_, - local_read(__module_ref_addr(module, cpu))); + __this_cpu_read(module->refptr->count)); } else ret = 0; - put_cpu(); + + preempt_enable(); } return ret; } diff --git a/kernel/module.c b/kernel/module.c index e96b8ed1cb6a..9bf228052ec5 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -474,9 +474,10 @@ static void module_unload_init(struct module *mod) INIT_LIST_HEAD(&mod->modules_which_use_me); for_each_possible_cpu(cpu) - local_set(__module_ref_addr(mod, cpu), 0); + per_cpu_ptr(mod->refptr, cpu)->count = 0; + /* Hold reference count during initialization. */ - local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1); + __this_cpu_write(mod->refptr->count, 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; } @@ -619,7 +620,7 @@ unsigned int module_refcount(struct module *mod) int cpu; for_each_possible_cpu(cpu) - total += local_read(__module_ref_addr(mod, cpu)); + total += per_cpu_ptr(mod->refptr, cpu)->count; return total; } EXPORT_SYMBOL(module_refcount); @@ -796,14 +797,15 @@ static struct module_attribute refcnt = { void module_put(struct module *module) { if (module) { - unsigned int cpu = get_cpu(); - local_dec(__module_ref_addr(module, cpu)); + preempt_disable(); + __this_cpu_dec(module->refptr->count); + trace_module_put(module, _RET_IP_, - local_read(__module_ref_addr(module, cpu))); + __this_cpu_read(module->refptr->count)); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); - put_cpu(); + preempt_enable(); } } EXPORT_SYMBOL(module_put); @@ -1394,9 +1396,9 @@ static void free_module(struct module *mod) kfree(mod->args); if (mod->percpu) percpu_modfree(mod->percpu); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) +#if defined(CONFIG_MODULE_UNLOAD) if (mod->refptr) - percpu_modfree(mod->refptr); + free_percpu(mod->refptr); #endif /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -2159,9 +2161,8 @@ static noinline struct module *load_module(void __user *umod, mod = (void *)sechdrs[modindex].sh_addr; kmemleak_load_module(mod, hdr, sechdrs, secstrings); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t), - mod->name); +#if defined(CONFIG_MODULE_UNLOAD) + mod->refptr = alloc_percpu(struct module_ref); if (!mod->refptr) { err = -ENOMEM; goto free_init; @@ -2393,8 +2394,8 @@ static noinline struct module *load_module(void __user *umod, kobject_put(&mod->mkobj.kobj); free_unload: module_unload_free(mod); -#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - percpu_modfree(mod->refptr); +#if defined(CONFIG_MODULE_UNLOAD) + free_percpu(mod->refptr); free_init: #endif module_free(mod, mod->module_init); -- cgit v1.2.3 From 79615760f380ec86cd58204744e774c33fab9211 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 5 Jan 2010 15:34:50 +0900 Subject: local_t: Move local.h include to ringbuffer.c and ring_buffer_benchmark.c ringbuffer*.c are the last users of local.h. Remove the include from modules.h and add it to ringbuffer files. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/module.h | 1 - kernel/trace/ring_buffer.c | 1 + kernel/trace/ring_buffer_benchmark.c | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/module.h b/include/linux/module.h index 2302f09ea2d9..7e74ae0051cc 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -17,7 +17,6 @@ #include #include -#include #include #include diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2326b04c95c4..eb6c8988c31a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -20,6 +20,7 @@ #include #include +#include #include "trace.h" /* diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index b2477caf09c2..df74c7982255 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -8,6 +8,7 @@ #include #include #include +#include struct rb_page { u64 ts; -- cgit v1.2.3 From 002345925e6c45861f60db6f4fc6236713fd8847 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 3 Feb 2010 15:36:43 -0800 Subject: syslog: distinguish between /proc/kmsg and syscalls This allows the LSM to distinguish between syslog functions originating from /proc/kmsg access and direct syscalls. By default, the commoncaps will now no longer require CAP_SYS_ADMIN to read an opened /proc/kmsg file descriptor. For example the kernel syslog reader can now drop privileges after opening /proc/kmsg, instead of staying privileged with CAP_SYS_ADMIN. MAC systems that implement security_syslog have unchanged behavior. Signed-off-by: Kees Cook Acked-by: Serge Hallyn Acked-by: John Johansen Signed-off-by: James Morris --- fs/proc/kmsg.c | 14 +++++++------- include/linux/security.h | 11 ++++++----- include/linux/syslog.h | 29 +++++++++++++++++++++++++++++ kernel/printk.c | 7 ++++--- security/commoncap.c | 7 ++++++- security/security.c | 4 ++-- security/selinux/hooks.c | 5 +++-- security/smack/smack_lsm.c | 4 ++-- 8 files changed, 59 insertions(+), 22 deletions(-) create mode 100644 include/linux/syslog.h (limited to 'kernel') diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index 7ca78346d3f0..6a3d843a1088 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -12,37 +12,37 @@ #include #include #include +#include #include #include extern wait_queue_head_t log_wait; -extern int do_syslog(int type, char __user *bug, int count); - static int kmsg_open(struct inode * inode, struct file * file) { - return do_syslog(1,NULL,0); + return do_syslog(1, NULL, 0, SYSLOG_FROM_FILE); } static int kmsg_release(struct inode * inode, struct file * file) { - (void) do_syslog(0,NULL,0); + (void) do_syslog(0, NULL, 0, SYSLOG_FROM_FILE); return 0; } static ssize_t kmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - if ((file->f_flags & O_NONBLOCK) && !do_syslog(9, NULL, 0)) + if ((file->f_flags & O_NONBLOCK) && + !do_syslog(9, NULL, 0, SYSLOG_FROM_FILE)) return -EAGAIN; - return do_syslog(2, buf, count); + return do_syslog(2, buf, count, SYSLOG_FROM_FILE); } static unsigned int kmsg_poll(struct file *file, poll_table *wait) { poll_wait(file, &log_wait, wait); - if (do_syslog(9, NULL, 0)) + if (do_syslog(9, NULL, 0, SYSLOG_FROM_FILE)) return POLLIN | POLLRDNORM; return 0; } diff --git a/include/linux/security.h b/include/linux/security.h index 26eca85b2417..a4dc74d86ac6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -76,7 +76,7 @@ extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp); extern int cap_task_setioprio(struct task_struct *p, int ioprio); extern int cap_task_setnice(struct task_struct *p, int nice); -extern int cap_syslog(int type); +extern int cap_syslog(int type, bool from_file); extern int cap_vm_enough_memory(struct mm_struct *mm, long pages); struct msghdr; @@ -1349,6 +1349,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * logging to the console. * See the syslog(2) manual page for an explanation of the @type values. * @type contains the type of action. + * @from_file indicates the context of action (if it came from /proc). * Return 0 if permission is granted. * @settime: * Check permission to change the system time. @@ -1463,7 +1464,7 @@ struct security_operations { int (*sysctl) (struct ctl_table *table, int op); int (*quotactl) (int cmds, int type, int id, struct super_block *sb); int (*quota_on) (struct dentry *dentry); - int (*syslog) (int type); + int (*syslog) (int type, bool from_file); int (*settime) (struct timespec *ts, struct timezone *tz); int (*vm_enough_memory) (struct mm_struct *mm, long pages); @@ -1762,7 +1763,7 @@ int security_acct(struct file *file); int security_sysctl(struct ctl_table *table, int op); int security_quotactl(int cmds, int type, int id, struct super_block *sb); int security_quota_on(struct dentry *dentry); -int security_syslog(int type); +int security_syslog(int type, bool from_file); int security_settime(struct timespec *ts, struct timezone *tz); int security_vm_enough_memory(long pages); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); @@ -2008,9 +2009,9 @@ static inline int security_quota_on(struct dentry *dentry) return 0; } -static inline int security_syslog(int type) +static inline int security_syslog(int type, bool from_file) { - return cap_syslog(type); + return cap_syslog(type, from_file); } static inline int security_settime(struct timespec *ts, struct timezone *tz) diff --git a/include/linux/syslog.h b/include/linux/syslog.h new file mode 100644 index 000000000000..5f02b1817be1 --- /dev/null +++ b/include/linux/syslog.h @@ -0,0 +1,29 @@ +/* Syslog internals + * + * Copyright 2010 Canonical, Ltd. + * Author: Kees Cook + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _LINUX_SYSLOG_H +#define _LINUX_SYSLOG_H + +#define SYSLOG_FROM_CALL 0 +#define SYSLOG_FROM_FILE 1 + +int do_syslog(int type, char __user *buf, int count, bool from_file); + +#endif /* _LINUX_SYSLOG_H */ diff --git a/kernel/printk.c b/kernel/printk.c index 17463ca2e229..809cf9a258a0 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -35,6 +35,7 @@ #include #include #include +#include #include @@ -273,14 +274,14 @@ static inline void boot_delay_msec(void) * 9 -- Return number of unread characters in the log buffer * 10 -- Return size of the log buffer */ -int do_syslog(int type, char __user *buf, int len) +int do_syslog(int type, char __user *buf, int len, bool from_file) { unsigned i, j, limit, count; int do_clear = 0; char c; int error = 0; - error = security_syslog(type); + error = security_syslog(type, from_file); if (error) return error; @@ -417,7 +418,7 @@ out: SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { - return do_syslog(type, buf, len); + return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } /* diff --git a/security/commoncap.c b/security/commoncap.c index f800fdb3de94..677fad9d5cba 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * If a non-root user executes a setuid-root binary in @@ -888,12 +889,16 @@ error: /** * cap_syslog - Determine whether syslog function is permitted * @type: Function requested + * @from_file: Whether this request came from an open file (i.e. /proc) * * Determine whether the current process is permitted to use a particular * syslog function, returning 0 if permission is granted, -ve if not. */ -int cap_syslog(int type) +int cap_syslog(int type, bool from_file) { + /* /proc/kmsg can open be opened by CAP_SYS_ADMIN */ + if (type != 1 && from_file) + return 0; if ((type != 3 && type != 10) && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; diff --git a/security/security.c b/security/security.c index 440afe5eb54c..971092c06f31 100644 --- a/security/security.c +++ b/security/security.c @@ -203,9 +203,9 @@ int security_quota_on(struct dentry *dentry) return security_ops->quota_on(dentry); } -int security_syslog(int type) +int security_syslog(int type, bool from_file) { - return security_ops->syslog(type); + return security_ops->syslog(type, from_file); } int security_settime(struct timespec *ts, struct timezone *tz) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 9a2ee845e9d4..a4862a0730fa 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -76,6 +76,7 @@ #include #include #include +#include #include "avc.h" #include "objsec.h" @@ -2049,11 +2050,11 @@ static int selinux_quota_on(struct dentry *dentry) return dentry_has_perm(cred, NULL, dentry, FILE__QUOTAON); } -static int selinux_syslog(int type) +static int selinux_syslog(int type, bool from_file) { int rc; - rc = cap_syslog(type); + rc = cap_syslog(type, from_file); if (rc) return rc; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 529c9ca65878..a5721b373f53 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -157,12 +157,12 @@ static int smack_ptrace_traceme(struct task_struct *ptp) * * Returns 0 on success, error code otherwise. */ -static int smack_syslog(int type) +static int smack_syslog(int type, bool from_file) { int rc; char *sp = current_security(); - rc = cap_syslog(type); + rc = cap_syslog(type, from_file); if (rc != 0) return rc; -- cgit v1.2.3 From d78ca3cd733d8a2c3dcd88471beb1a15d973eed8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 3 Feb 2010 15:37:13 -0800 Subject: syslog: use defined constants instead of raw numbers Right now the syslog "type" action are just raw numbers which makes the source difficult to follow. This patch replaces the raw numbers with defined constants for some level of sanity. Signed-off-by: Kees Cook Acked-by: John Johansen Acked-by: Serge Hallyn Signed-off-by: James Morris --- fs/proc/kmsg.c | 10 +++++----- include/linux/syslog.h | 23 +++++++++++++++++++++++ kernel/printk.c | 45 +++++++++++++++++++-------------------------- security/commoncap.c | 5 +++-- security/selinux/hooks.c | 21 +++++++++++---------- 5 files changed, 61 insertions(+), 43 deletions(-) (limited to 'kernel') diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index 6a3d843a1088..cfe90a48a6e8 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -21,12 +21,12 @@ extern wait_queue_head_t log_wait; static int kmsg_open(struct inode * inode, struct file * file) { - return do_syslog(1, NULL, 0, SYSLOG_FROM_FILE); + return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_FILE); } static int kmsg_release(struct inode * inode, struct file * file) { - (void) do_syslog(0, NULL, 0, SYSLOG_FROM_FILE); + (void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_FILE); return 0; } @@ -34,15 +34,15 @@ static ssize_t kmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { if ((file->f_flags & O_NONBLOCK) && - !do_syslog(9, NULL, 0, SYSLOG_FROM_FILE)) + !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE)) return -EAGAIN; - return do_syslog(2, buf, count, SYSLOG_FROM_FILE); + return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_FILE); } static unsigned int kmsg_poll(struct file *file, poll_table *wait) { poll_wait(file, &log_wait, wait); - if (do_syslog(9, NULL, 0, SYSLOG_FROM_FILE)) + if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE)) return POLLIN | POLLRDNORM; return 0; } diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 5f02b1817be1..38911391a139 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -21,6 +21,29 @@ #ifndef _LINUX_SYSLOG_H #define _LINUX_SYSLOG_H +/* Close the log. Currently a NOP. */ +#define SYSLOG_ACTION_CLOSE 0 +/* Open the log. Currently a NOP. */ +#define SYSLOG_ACTION_OPEN 1 +/* Read from the log. */ +#define SYSLOG_ACTION_READ 2 +/* Read all messages remaining in the ring buffer. */ +#define SYSLOG_ACTION_READ_ALL 3 +/* Read and clear all messages remaining in the ring buffer */ +#define SYSLOG_ACTION_READ_CLEAR 4 +/* Clear ring buffer. */ +#define SYSLOG_ACTION_CLEAR 5 +/* Disable printk's to console */ +#define SYSLOG_ACTION_CONSOLE_OFF 6 +/* Enable printk's to console */ +#define SYSLOG_ACTION_CONSOLE_ON 7 +/* Set level of messages printed to console */ +#define SYSLOG_ACTION_CONSOLE_LEVEL 8 +/* Return number of unread characters in the log buffer */ +#define SYSLOG_ACTION_SIZE_UNREAD 9 +/* Return size of the log buffer */ +#define SYSLOG_ACTION_SIZE_BUFFER 10 + #define SYSLOG_FROM_CALL 0 #define SYSLOG_FROM_FILE 1 diff --git a/kernel/printk.c b/kernel/printk.c index 809cf9a258a0..3e162d867098 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -259,21 +259,6 @@ static inline void boot_delay_msec(void) } #endif -/* - * Commands to do_syslog: - * - * 0 -- Close the log. Currently a NOP. - * 1 -- Open the log. Currently a NOP. - * 2 -- Read from the log. - * 3 -- Read all messages remaining in the ring buffer. - * 4 -- Read and clear all messages remaining in the ring buffer - * 5 -- Clear ring buffer. - * 6 -- Disable printk's to console - * 7 -- Enable printk's to console - * 8 -- Set level of messages printed to console - * 9 -- Return number of unread characters in the log buffer - * 10 -- Return size of the log buffer - */ int do_syslog(int type, char __user *buf, int len, bool from_file) { unsigned i, j, limit, count; @@ -286,11 +271,11 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) return error; switch (type) { - case 0: /* Close log */ + case SYSLOG_ACTION_CLOSE: /* Close log */ break; - case 1: /* Open log */ + case SYSLOG_ACTION_OPEN: /* Open log */ break; - case 2: /* Read from log */ + case SYSLOG_ACTION_READ: /* Read from log */ error = -EINVAL; if (!buf || len < 0) goto out; @@ -321,10 +306,12 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) if (!error) error = i; break; - case 4: /* Read/clear last kernel messages */ + /* Read/clear last kernel messages */ + case SYSLOG_ACTION_READ_CLEAR: do_clear = 1; /* FALL THRU */ - case 3: /* Read last kernel messages */ + /* Read last kernel messages */ + case SYSLOG_ACTION_READ_ALL: error = -EINVAL; if (!buf || len < 0) goto out; @@ -377,21 +364,25 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) } } break; - case 5: /* Clear ring buffer */ + /* Clear ring buffer */ + case SYSLOG_ACTION_CLEAR: logged_chars = 0; break; - case 6: /* Disable logging to console */ + /* Disable logging to console */ + case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == -1) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; - case 7: /* Enable logging to console */ + /* Enable logging to console */ + case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != -1) { console_loglevel = saved_console_loglevel; saved_console_loglevel = -1; } break; - case 8: /* Set level of messages printed to console */ + /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_LEVEL: error = -EINVAL; if (len < 1 || len > 8) goto out; @@ -402,10 +393,12 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) saved_console_loglevel = -1; error = 0; break; - case 9: /* Number of chars in the log buffer */ + /* Number of chars in the log buffer */ + case SYSLOG_ACTION_SIZE_UNREAD: error = log_end - log_start; break; - case 10: /* Size of the log buffer */ + /* Size of the log buffer */ + case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: diff --git a/security/commoncap.c b/security/commoncap.c index 677fad9d5cba..cf01b2eebb60 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -897,9 +897,10 @@ error: int cap_syslog(int type, bool from_file) { /* /proc/kmsg can open be opened by CAP_SYS_ADMIN */ - if (type != 1 && from_file) + if (type != SYSLOG_ACTION_OPEN && from_file) return 0; - if ((type != 3 && type != 10) && !capable(CAP_SYS_ADMIN)) + if ((type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER) && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index a4862a0730fa..6b36ce2eef2e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2059,20 +2059,21 @@ static int selinux_syslog(int type, bool from_file) return rc; switch (type) { - case 3: /* Read last kernel messages */ - case 10: /* Return size of the log buffer */ + case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ + case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ rc = task_has_system(current, SYSTEM__SYSLOG_READ); break; - case 6: /* Disable logging to console */ - case 7: /* Enable logging to console */ - case 8: /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ + case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ + /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_LEVEL: rc = task_has_system(current, SYSTEM__SYSLOG_CONSOLE); break; - case 0: /* Close log */ - case 1: /* Open log */ - case 2: /* Read from log */ - case 4: /* Read/clear last kernel messages */ - case 5: /* Clear ring buffer */ + case SYSLOG_ACTION_CLOSE: /* Close log */ + case SYSLOG_ACTION_OPEN: /* Open log */ + case SYSLOG_ACTION_READ: /* Read from log */ + case SYSLOG_ACTION_READ_CLEAR: /* Read/clear last kernel messages */ + case SYSLOG_ACTION_CLEAR: /* Clear ring buffer */ default: rc = task_has_system(current, SYSTEM__SYSLOG_MOD); break; -- cgit v1.2.3 From c41b20e721ea4f6f20f66a66e7f0c3c97a2ca9c2 Mon Sep 17 00:00:00 2001 From: Adam Buchbinder Date: Fri, 11 Dec 2009 16:35:39 -0500 Subject: Fix misspellings of "truly" in comments. Some comments misspell "truly"; this fixes them. No code changes. Signed-off-by: Adam Buchbinder Signed-off-by: Jiri Kosina --- drivers/char/random.c | 2 +- drivers/gpu/drm/radeon/radeon_state.c | 2 +- drivers/net/cs89x0.c | 2 +- fs/dlm/member.c | 2 +- fs/namei.c | 2 +- include/math-emu/op-common.h | 2 +- kernel/trace/ring_buffer.c | 4 ++-- 7 files changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/drivers/char/random.c b/drivers/char/random.c index 2849713d2231..2fd3d39995d5 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1191,7 +1191,7 @@ const struct file_operations urandom_fops = { void generate_random_uuid(unsigned char uuid_out[16]) { get_random_bytes(uuid_out, 16); - /* Set UUID version to 4 --- truely random generation */ + /* Set UUID version to 4 --- truly random generation */ uuid_out[6] = (uuid_out[6] & 0x0F) | 0x40; /* Set the UUID variant to DCE */ uuid_out[8] = (uuid_out[8] & 0x3F) | 0x80; diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c index 067167cb39ca..1982a87386a1 100644 --- a/drivers/gpu/drm/radeon/radeon_state.c +++ b/drivers/gpu/drm/radeon/radeon_state.c @@ -1065,7 +1065,7 @@ static void radeon_cp_dispatch_clear(struct drm_device * dev, /* judging by the first tile offset needed, could possibly directly address/clear 4x4 tiles instead of 8x2 * 4x4 macro tiles, though would still need clear mask for - right/bottom if truely 4x4 granularity is desired ? */ + right/bottom if truly 4x4 granularity is desired ? */ OUT_RING(tileoffset * 16); /* the number of tiles to clear */ OUT_RING(nrtilesx + 1); diff --git a/drivers/net/cs89x0.c b/drivers/net/cs89x0.c index 0e79cef95c0a..9b5bbc6ea2fa 100644 --- a/drivers/net/cs89x0.c +++ b/drivers/net/cs89x0.c @@ -580,7 +580,7 @@ cs89x0_probe1(struct net_device *dev, int ioaddr, int modular) } #ifdef CONFIG_SH_HICOSH4 - /* truely reset the chip */ + /* truly reset the chip */ writeword(ioaddr, ADD_PORT, 0x0114); writeword(ioaddr, DATA_PORT, 0x0040); #endif diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 84f70bfb0baf..b12532e553f8 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -312,7 +312,7 @@ int dlm_ls_stop(struct dlm_ls *ls) /* * This in_recovery lock does two things: * 1) Keeps this function from returning until all threads are out - * of locking routines and locking is truely stopped. + * of locking routines and locking is truly stopped. * 2) Keeps any new requests from being processed until it's unlocked * when recovery is complete. */ diff --git a/fs/namei.c b/fs/namei.c index 94a5e60779f9..e05c243105a0 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2556,7 +2556,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * e) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on - * ->i_mutex on parents, which works but leads to some truely excessive + * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h index f456534dcaf9..fd882261225e 100644 --- a/include/math-emu/op-common.h +++ b/include/math-emu/op-common.h @@ -29,7 +29,7 @@ _FP_FRAC_DECL_##wc(X) /* - * Finish truely unpacking a native fp value by classifying the kind + * Finish truly unpacking a native fp value by classifying the kind * of fp value and normalizing both the exponent and the fraction. */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8c1b2d290718..9ab578f1bb65 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2541,7 +2541,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable); * @buffer: The ring buffer to enable writes * * Note, multiple disables will need the same number of enables - * to truely enable the writing (much like preempt_disable). + * to truly enable the writing (much like preempt_disable). */ void ring_buffer_record_enable(struct ring_buffer *buffer) { @@ -2577,7 +2577,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu); * @cpu: The CPU to enable. * * Note, multiple disables will need the same number of enables - * to truely enable the writing (much like preempt_disable). + * to truly enable the writing (much like preempt_disable). */ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu) { -- cgit v1.2.3 From 2a61aa401638529cd4231f6106980d307fba98fa Mon Sep 17 00:00:00 2001 From: Adam Buchbinder Date: Fri, 11 Dec 2009 16:35:40 -0500 Subject: Fix misspellings of "invocation" in comments. Some comments misspell "invocation"; this fixes them. No code changes. Signed-off-by: Adam Buchbinder Signed-off-by: Jiri Kosina --- fs/buffer.c | 2 +- fs/mpage.c | 2 +- include/linux/mmzone.h | 2 +- kernel/sched_cpupri.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/fs/buffer.c b/fs/buffer.c index 6fa530256bfd..1d920bab5e70 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2893,7 +2893,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, /* * The page straddles i_size. It must be zeroed out on each and every - * writepage invokation because it may be mmapped. "A file is mapped + * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." diff --git a/fs/mpage.c b/fs/mpage.c index 42381bd6543b..598d54e200eb 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -561,7 +561,7 @@ page_is_mapped: if (page->index >= end_index) { /* * The page straddles i_size. It must be zeroed out on each - * and every writepage invokation because it may be mmapped. + * and every writepage invocation because it may be mmapped. * "A file is mapped in multiples of the page size. For a file * that is not a multiple of the page size, the remaining memory * is zeroed when mapped, and writes to that region are not diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 30fe668c2542..e60a340fe890 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -349,7 +349,7 @@ struct zone { * prev_priority holds the scanning priority for this zone. It is * defined as the scanning priority at which we achieved our reclaim * target at the previous try_to_free_pages() or balance_pgdat() - * invokation. + * invocation. * * We use prev_priority as a measure of how much stress page reclaim is * under - it drives the swappiness decision: whether to unmap mapped diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index 597b33099dfa..3db4b1a0e921 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -58,7 +58,7 @@ static int convert_prio(int prio) * @lowest_mask: A mask to fill in with selected CPUs (or NULL) * * Note: This function returns the recommended CPUs as calculated during the - * current invokation. By the time the call returns, the CPUs may have in + * current invocation. By the time the call returns, the CPUs may have in * fact changed priorities any number of times. While not ideal, it is not * an issue of correctness since the normal rebalancer logic will correct * any discrepancies created by racing against the uncertainty of the current -- cgit v1.2.3 From c9404c9c392d557a4687c4cbda022b03cb787ce9 Mon Sep 17 00:00:00 2001 From: Adam Buchbinder Date: Fri, 18 Dec 2009 15:40:42 -0500 Subject: Fix misspelling of "should" and "shouldn't" in comments. Some comments misspell "should" or "shouldn't"; this fixes them. No code changes. Signed-off-by: Adam Buchbinder Signed-off-by: Jiri Kosina --- arch/x86/kernel/ptrace.c | 2 +- drivers/ata/libata-core.c | 2 +- drivers/gpu/drm/radeon/atombios.h | 2 +- drivers/ieee1394/pcilynx.c | 2 +- drivers/input/tablet/aiptek.c | 2 +- drivers/mmc/card/sdio_uart.c | 2 +- drivers/scsi/lpfc/lpfc_scsi.c | 4 ++-- drivers/video/sstfb.c | 2 +- fs/locks.c | 2 +- kernel/audit.c | 2 +- mm/slub.c | 2 +- 11 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 017d937639fe..118428085ea2 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -604,7 +604,7 @@ ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, struct perf_event_attr attr; /* - * We shoud have at least an inactive breakpoint at this + * We should have at least an inactive breakpoint at this * slot. It means the user is writing dr7 without having * written the address register first */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 6728328f3bea..698ef474767e 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2232,7 +2232,7 @@ retry: * Some drives were very specific about that exact sequence. * * Note that ATA4 says lba is mandatory so the second check - * shoud never trigger. + * should never trigger. */ if (ata_id_major_version(id) < 4 || !ata_id_has_lba(id)) { err_mask = ata_dev_init_params(dev, id[3], id[6]); diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h index 91ad0d1c1b17..2a88029f6a1e 100644 --- a/drivers/gpu/drm/radeon/atombios.h +++ b/drivers/gpu/drm/radeon/atombios.h @@ -2275,7 +2275,7 @@ typedef struct _ATOM_LCD_RTS_RECORD { UCHAR ucRTSValue; } ATOM_LCD_RTS_RECORD; -/* !! If the record below exits, it shoud always be the first record for easy use in command table!!! */ +/* !! If the record below exits, it should always be the first record for easy use in command table!!! */ typedef struct _ATOM_LCD_MODE_CONTROL_CAP { UCHAR ucRecordType; USHORT usLCDCap; diff --git a/drivers/ieee1394/pcilynx.c b/drivers/ieee1394/pcilynx.c index 9555fd253865..bf47fee79808 100644 --- a/drivers/ieee1394/pcilynx.c +++ b/drivers/ieee1394/pcilynx.c @@ -1452,7 +1452,7 @@ static int __devinit add_card(struct pci_dev *dev, PRINT(KERN_ERR, lynx->id, "unable to read bus info block from i2c"); } else { PRINT(KERN_INFO, lynx->id, "got bus info block from serial eeprom"); - /* FIXME: probably we shoud rewrite the max_rec, max_ROM(1394a), + /* FIXME: probably we should rewrite the max_rec, max_ROM(1394a), * generation(1394a) and link_spd(1394a) field and recalculate * the CRC */ diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c index 7d005a3616d7..4be039d7dcad 100644 --- a/drivers/input/tablet/aiptek.c +++ b/drivers/input/tablet/aiptek.c @@ -362,7 +362,7 @@ static const int macroKeyEvents[] = { }; /*********************************************************************** - * Map values to strings and back. Every map shoudl have the following + * Map values to strings and back. Every map should have the following * as its last element: { NULL, AIPTEK_INVALID_VALUE }. */ #define AIPTEK_INVALID_VALUE -1 diff --git a/drivers/mmc/card/sdio_uart.c b/drivers/mmc/card/sdio_uart.c index f53755533e7e..a4e37758be41 100644 --- a/drivers/mmc/card/sdio_uart.c +++ b/drivers/mmc/card/sdio_uart.c @@ -581,7 +581,7 @@ static int uart_carrier_raised(struct tty_port *tport) struct sdio_uart_port *port = container_of(tport, struct sdio_uart_port, port); unsigned int ret = sdio_uart_claim_func(port); - if (ret) /* Missing hardware shoudn't block for carrier */ + if (ret) /* Missing hardware shouldn't block for carrier */ return 1; ret = sdio_uart_get_mctrl(port); sdio_uart_release_func(port); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index a246410ce9df..28c6bfd3e82e 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1574,7 +1574,7 @@ lpfc_bg_scsi_prep_dma_buf(struct lpfc_hba *phba, case LPFC_PG_TYPE_NO_DIF: num_bde = lpfc_bg_setup_bpl(phba, scsi_cmnd, bpl, datasegcnt); - /* we shoud have 2 or more entries in buffer list */ + /* we should have 2 or more entries in buffer list */ if (num_bde < 2) goto err; break; @@ -1611,7 +1611,7 @@ lpfc_bg_scsi_prep_dma_buf(struct lpfc_hba *phba, num_bde = lpfc_bg_setup_bpl_prot(phba, scsi_cmnd, bpl, datasegcnt, protsegcnt); - /* we shoud have 3 or more entries in buffer list */ + /* we should have 3 or more entries in buffer list */ if (num_bde < 3) goto err; break; diff --git a/drivers/video/sstfb.c b/drivers/video/sstfb.c index 609d0a521ca2..79840f11fecb 100644 --- a/drivers/video/sstfb.c +++ b/drivers/video/sstfb.c @@ -1102,7 +1102,7 @@ static void sst_set_vidmod_ics(struct fb_info *info, const int bpp) * detect dac type * prerequisite : write to FbiInitx enabled, video and fbi and pci fifo reset, * dram refresh disabled, FbiInit remaped. - * TODO: mmh.. maybe i shoud put the "prerequisite" in the func ... + * TODO: mmh.. maybe i should put the "prerequisite" in the func ... */ diff --git a/fs/locks.c b/fs/locks.c index a8794f233bc9..cde572db112f 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1454,7 +1454,7 @@ EXPORT_SYMBOL(generic_setlease); * leases held by processes on this node. * * There is also no break_lease method; filesystems that - * handle their own leases shoud break leases themselves from the + * handle their own leases should break leases themselves from the * filesystem's open, create, and (on truncate) setattr methods. * * Warning: the only current setlease methods exist only to disable diff --git a/kernel/audit.c b/kernel/audit.c index 5feed232be9d..78f7f86aa238 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -398,7 +398,7 @@ static void kauditd_send_skb(struct sk_buff *skb) skb_get(skb); err = netlink_unicast(audit_sock, skb, audit_nlk_pid, 0); if (err < 0) { - BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */ + BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */ printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid); audit_log_lost("auditd dissapeared\n"); audit_pid = 0; diff --git a/mm/slub.c b/mm/slub.c index 8d71aaf888d7..00e0961b11fe 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3086,7 +3086,7 @@ static void slab_mem_offline_callback(void *arg) /* * if n->nr_slabs > 0, slabs still exist on the node * that is going down. We were unable to free them, - * and offline_pages() function shoudn't call this + * and offline_pages() function shouldn't call this * callback. So, we must fail. */ BUG_ON(slabs_node(s, offline_node)); -- cgit v1.2.3 From af66585270ef99aa6097faf3bd7344855077e75d Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Sun, 17 Jan 2010 19:14:26 -0200 Subject: fix comment typo boo -> boot in ksysfs.c Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Jiri Kosina --- kernel/ksysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 3feaf5a74514..ac08efca54c3 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -33,7 +33,7 @@ static ssize_t uevent_seqnum_show(struct kobject *kobj, } KERNEL_ATTR_RO(uevent_seqnum); -/* uevent helper program, used during early boo */ +/* uevent helper program, used during early boot */ static ssize_t uevent_helper_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { -- cgit v1.2.3 From 350f82586b7554240bee18c41cc5c842f63265ae Mon Sep 17 00:00:00 2001 From: "Edward Z. Yang" Date: Mon, 1 Feb 2010 18:26:59 -0500 Subject: Remove redundant trailing semicolons from macros Signed-off-by: Edward Z. Yang Acked-by: Rusty Russell Signed-off-by: Jiri Kosina --- kernel/params.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/params.c b/kernel/params.c index cf1b69183127..2278ce244cf8 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -402,8 +402,8 @@ int param_get_string(char *buffer, struct kernel_param *kp) } /* sysfs output in /sys/modules/XYZ/parameters/ */ -#define to_module_attr(n) container_of(n, struct module_attribute, attr); -#define to_module_kobject(n) container_of(n, struct module_kobject, kobj); +#define to_module_attr(n) container_of(n, struct module_attribute, attr) +#define to_module_kobject(n) container_of(n, struct module_kobject, kobj) extern struct kernel_param __start___param[], __stop___param[]; @@ -421,7 +421,7 @@ struct module_param_attrs }; #ifdef CONFIG_SYSFS -#define to_param_attr(n) container_of(n, struct param_attribute, mattr); +#define to_param_attr(n) container_of(n, struct param_attribute, mattr) static ssize_t param_attr_show(struct module_attribute *mattr, struct module *mod, char *buf) -- cgit v1.2.3 From 9ce8e498ee58bb8a866a6c3c08fcb385ed66e9d2 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Tue, 2 Feb 2010 08:54:51 +0200 Subject: devres: typo fix s/dev/devm/ Signed-off-by: Baruch Siach Signed-off-by: Jiri Kosina --- kernel/irq/devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index d06df9c41cba..30d56bafc9c2 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -81,7 +81,7 @@ EXPORT_SYMBOL(devm_request_threaded_irq); * Except for the extra @dev argument, this function takes the * same arguments and performs the same function as free_irq(). * This function instead of free_irq() should be used to manually - * free IRQs allocated with dev_request_irq(). + * free IRQs allocated with devm_request_irq(). */ void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id) { -- cgit v1.2.3 From 1537a3638cbf741d3826c1002026cce487a6bee0 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 29 Jan 2010 15:57:49 +0800 Subject: tree-wide: fix 'lenght' typo in comments and code Some misspelled occurences of 'octet' and some comments were also fixed as I was on it. Signed-off-by: Daniel Mack Cc: Jiri Kosina Cc: Joe Perches Cc: Junio C Hamano Signed-off-by: Jiri Kosina --- arch/arm/mach-at91/include/mach/at91_mci.h | 2 +- arch/s390/crypto/sha_common.c | 2 +- drivers/crypto/hifn_795x.c | 2 +- drivers/isdn/mISDN/l1oip_core.c | 2 +- drivers/usb/wusbcore/wusbhc.h | 2 +- drivers/uwb/uwbd.c | 2 +- fs/cifs/asn1.c | 2 +- fs/ext4/mballoc.c | 2 +- fs/udf/inode.c | 2 +- kernel/trace/trace.h | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/arch/arm/mach-at91/include/mach/at91_mci.h b/arch/arm/mach-at91/include/mach/at91_mci.h index 550d503a1bca..57f8ee154943 100644 --- a/arch/arm/mach-at91/include/mach/at91_mci.h +++ b/arch/arm/mach-at91/include/mach/at91_mci.h @@ -77,7 +77,7 @@ #define AT91_MCI_BLKR 0x18 /* Block Register */ #define AT91_MCI_BLKR_BCNT(n) ((0xffff & (n)) << 0) /* Block count */ -#define AT91_MCI_BLKR_BLKLEN(n) ((0xffff & (n)) << 16) /* Block lenght */ +#define AT91_MCI_BLKR_BLKLEN(n) ((0xffff & (n)) << 16) /* Block length */ #define AT91_MCI_RSPR(n) (0x20 + ((n) * 4)) /* Response Registers 0-3 */ #define AT91_MCR_RDR 0x30 /* Receive Data Register */ diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index 7903ec47e6b9..f42dbabc0d30 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -79,7 +79,7 @@ int s390_sha_final(struct shash_desc *desc, u8 *out) memset(ctx->buf + index, 0x00, end - index - 8); /* - * Append message length. Well, SHA-512 wants a 128 bit lenght value, + * Append message length. Well, SHA-512 wants a 128 bit length value, * nevertheless we use u64, should be enough for now... */ bits = ctx->count * 8; diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c index 09ad9154d86c..73e8b1713b54 100644 --- a/drivers/crypto/hifn_795x.c +++ b/drivers/crypto/hifn_795x.c @@ -321,7 +321,7 @@ static atomic_t hifn_dev_number; #define HIFN_PUBOPLEN_MOD_M 0x0000007f /* modulus length mask */ #define HIFN_PUBOPLEN_MOD_S 0 /* modulus length shift */ #define HIFN_PUBOPLEN_EXP_M 0x0003ff80 /* exponent length mask */ -#define HIFN_PUBOPLEN_EXP_S 7 /* exponent lenght shift */ +#define HIFN_PUBOPLEN_EXP_S 7 /* exponent length shift */ #define HIFN_PUBOPLEN_RED_M 0x003c0000 /* reducend length mask */ #define HIFN_PUBOPLEN_RED_S 18 /* reducend length shift */ diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index 0843fcf8b381..325b1ad7d4b8 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -477,7 +477,7 @@ l1oip_socket_parse(struct l1oip *hc, struct sockaddr_in *sin, u8 *buf, int len) printk(KERN_DEBUG "%s: received frame, parsing... (%d)\n", __func__, len); - /* check lenght */ + /* check length */ if (len < 1+1+2) { printk(KERN_WARNING "%s: packet error - length %d below " "4 bytes\n", __func__, len); diff --git a/drivers/usb/wusbcore/wusbhc.h b/drivers/usb/wusbcore/wusbhc.h index fd2fd4e277e1..759cda55f7c3 100644 --- a/drivers/usb/wusbcore/wusbhc.h +++ b/drivers/usb/wusbcore/wusbhc.h @@ -198,7 +198,7 @@ struct wusb_port { * ports) this HC will take. Read-only. * * @port Array of port status for each fake root port. Guaranteed to - * always be the same lenght during device existence + * always be the same length during device existence * [this allows for some unlocked but referenced reading]. * * @mmcies_max Max number of Information Elements this HC can send diff --git a/drivers/uwb/uwbd.c b/drivers/uwb/uwbd.c index 5a777d8624da..6210fe1fd1bb 100644 --- a/drivers/uwb/uwbd.c +++ b/drivers/uwb/uwbd.c @@ -43,7 +43,7 @@ * * EVENTS * - * Events have a type, a subtype, a lenght, some other stuff and the + * Events have a type, a subtype, a length, some other stuff and the * data blob, which depends on the event. The header is 'struct * uwb_event'; for payloads, see 'struct uwbd_evt_*'. * diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 20692fbfdb24..a20bea598933 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -136,7 +136,7 @@ asn1_enum_decode(struct asn1_ctx *ctx, __le32 *val) return 0; } - ch = *(ctx->pointer)++; /* ch has 0xa, ptr points to lenght octet */ + ch = *(ctx->pointer)++; /* ch has 0xa, ptr points to length octet */ if ((ch) == ASN1_ENUM) /* if ch value is ENUM, 0xa */ *val = *(++(ctx->pointer)); /* value has enum value */ else diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d34afad3e137..b794dd8141a0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -69,7 +69,7 @@ * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space - * pa_len -> lenght for this prealloc space + * pa_len -> length for this prealloc space * pa_free -> free space available in this prealloc space * * The inode preallocation space is used looking at the _logical_ start diff --git a/fs/udf/inode.c b/fs/udf/inode.c index f90231eb2916..772a4fa557f2 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -102,7 +102,7 @@ void udf_clear_inode(struct inode *inode) if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && inode->i_size != iinfo->i_lenExtents) { printk(KERN_WARNING "UDF-fs (%s): Inode %lu (mode %o) has " - "inode size %llu different from extent lenght %llu. " + "inode size %llu different from extent length %llu. " "Filesystem need not be standards compliant.\n", inode->i_sb->s_id, inode->i_ino, inode->i_mode, (unsigned long long)inode->i_size, diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4df6a77eb196..e4b32c8aa85f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -549,7 +549,7 @@ static inline int ftrace_trace_task(struct task_struct *task) * struct trace_parser - servers for reading the user input separated by spaces * @cont: set if the input is not complete - no final space char was found * @buffer: holds the parsed user input - * @idx: user input lenght + * @idx: user input length * @size: buffer size */ struct trace_parser { -- cgit v1.2.3 From cccc6bba3f771ef29b33e4f79e70ebc3dba245b0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 25 Dec 2009 05:07:33 -0500 Subject: Lose the first argument of audit_inode_child() it's always equal to ->d_name.name of the second argument Signed-off-by: Al Viro --- fs/namei.c | 2 +- include/linux/audit.h | 11 +++++------ include/linux/fsnotify.h | 8 ++++---- kernel/auditsc.c | 7 ++----- 4 files changed, 12 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/fs/namei.c b/fs/namei.c index f69df876fac3..865282f8e012 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1337,7 +1337,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir) return -ENOENT; BUG_ON(victim->d_parent->d_inode != dir); - audit_inode_child(victim->d_name.name, victim, dir); + audit_inode_child(victim, dir); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) diff --git a/include/linux/audit.h b/include/linux/audit.h index 3c7a358241a7..f391d45c8aea 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -424,7 +424,7 @@ extern void audit_syscall_exit(int failed, long return_code); extern void __audit_getname(const char *name); extern void audit_putname(const char *name); extern void __audit_inode(const char *name, const struct dentry *dentry); -extern void __audit_inode_child(const char *dname, const struct dentry *dentry, +extern void __audit_inode_child(const struct dentry *dentry, const struct inode *parent); extern void __audit_ptrace(struct task_struct *t); @@ -442,11 +442,10 @@ static inline void audit_inode(const char *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry); } -static inline void audit_inode_child(const char *dname, - const struct dentry *dentry, +static inline void audit_inode_child(const struct dentry *dentry, const struct inode *parent) { if (unlikely(!audit_dummy_context())) - __audit_inode_child(dname, dentry, parent); + __audit_inode_child(dentry, parent); } void audit_core_dumps(long signr); @@ -544,9 +543,9 @@ extern int audit_signals; #define audit_getname(n) do { ; } while (0) #define audit_putname(n) do { ; } while (0) #define __audit_inode(n,d) do { ; } while (0) -#define __audit_inode_child(d,i,p) do { ; } while (0) +#define __audit_inode_child(i,p) do { ; } while (0) #define audit_inode(n,d) do { ; } while (0) -#define audit_inode_child(d,i,p) do { ; } while (0) +#define audit_inode_child(i,p) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define auditsc_get_stamp(c,t,s) (0) #define audit_get_loginuid(t) (-1) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 2d755c49c324..df8fd9a3b214 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -104,7 +104,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL); fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0); } - audit_inode_child(new_name, moved, new_dir); + audit_inode_child(moved, new_dir); } /* @@ -147,7 +147,7 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) { inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name, dentry->d_inode); - audit_inode_child(dentry->d_name.name, dentry, inode); + audit_inode_child(dentry, inode); fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); } @@ -162,7 +162,7 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct inotify_inode_queue_event(dir, IN_CREATE, 0, new_dentry->d_name.name, inode); fsnotify_link_count(inode); - audit_inode_child(new_dentry->d_name.name, new_dentry, dir); + audit_inode_child(new_dentry, dir); fsnotify(dir, FS_CREATE, inode, FSNOTIFY_EVENT_INODE, new_dentry->d_name.name, 0); } @@ -176,7 +176,7 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) struct inode *d_inode = dentry->d_inode; inotify_inode_queue_event(inode, mask, 0, dentry->d_name.name, d_inode); - audit_inode_child(dentry->d_name.name, dentry, inode); + audit_inode_child(dentry, inode); fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index fc0f928167e7..f3a461c0970a 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1988,7 +1988,6 @@ void __audit_inode(const char *name, const struct dentry *dentry) /** * audit_inode_child - collect inode info for created/removed objects - * @dname: inode's dentry name * @dentry: dentry being audited * @parent: inode of dentry parent * @@ -2000,13 +1999,14 @@ void __audit_inode(const char *name, const struct dentry *dentry) * must be hooked prior, in order to capture the target inode during * unsuccessful attempts. */ -void __audit_inode_child(const char *dname, const struct dentry *dentry, +void __audit_inode_child(const struct dentry *dentry, const struct inode *parent) { int idx; struct audit_context *context = current->audit_context; const char *found_parent = NULL, *found_child = NULL; const struct inode *inode = dentry->d_inode; + const char *dname = dentry->d_name.name; int dirlen = 0; if (!context->in_syscall) @@ -2014,9 +2014,6 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry, if (inode) handle_one(inode); - /* determine matching parent */ - if (!dname) - goto add_names; /* parent is more likely, look for it first */ for (idx = 0; idx < context->name_count; idx++) { -- cgit v1.2.3 From b80109e256bc17ed66c9d559175f087b03ca2a8e Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 9 Feb 2010 15:07:40 +1100 Subject: Remove reference to kthread_create_on_cpu kthread_create_on_cpu doesn't exist so update a comment in kthread.c to reflect this. Signed-off-by: Anton Blanchard Acked-by: Rusty Russell Signed-off-by: Jiri Kosina --- kernel/kthread.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kthread.c b/kernel/kthread.c index fbb6222fe7e0..82ed0ea15194 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -101,7 +101,7 @@ static void create_kthread(struct kthread_create_info *create) * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start - * it. See also kthread_run(), kthread_create_on_cpu(). + * it. See also kthread_run(). * * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a -- cgit v1.2.3 From ced5b697a76d325e7a7ac7d382dbbb632c765093 Mon Sep 17 00:00:00 2001 From: Brandon Phiilps Date: Wed, 10 Feb 2010 01:20:06 -0800 Subject: x86: Avoid race condition in pci_enable_msix() Keep chip_data in create_irq_nr and destroy_irq. When two drivers are setting up MSI-X at the same time via pci_enable_msix() there is a race. See this dmesg excerpt: [ 85.170610] ixgbe 0000:02:00.1: irq 97 for MSI/MSI-X [ 85.170611] alloc irq_desc for 99 on node -1 [ 85.170613] igb 0000:08:00.1: irq 98 for MSI/MSI-X [ 85.170614] alloc kstat_irqs on node -1 [ 85.170616] alloc irq_2_iommu on node -1 [ 85.170617] alloc irq_desc for 100 on node -1 [ 85.170619] alloc kstat_irqs on node -1 [ 85.170621] alloc irq_2_iommu on node -1 [ 85.170625] ixgbe 0000:02:00.1: irq 99 for MSI/MSI-X [ 85.170626] alloc irq_desc for 101 on node -1 [ 85.170628] igb 0000:08:00.1: irq 100 for MSI/MSI-X [ 85.170630] alloc kstat_irqs on node -1 [ 85.170631] alloc irq_2_iommu on node -1 [ 85.170635] alloc irq_desc for 102 on node -1 [ 85.170636] alloc kstat_irqs on node -1 [ 85.170639] alloc irq_2_iommu on node -1 [ 85.170646] BUG: unable to handle kernel NULL pointer dereference at 0000000000000088 As you can see igb and ixgbe are both alternating on create_irq_nr() via pci_enable_msix() in their probe function. ixgbe: While looping through irq_desc_ptrs[] via create_irq_nr() ixgbe choses irq_desc_ptrs[102] and exits the loop, drops vector_lock and calls dynamic_irq_init. Then it sets irq_desc_ptrs[102]->chip_data = NULL via dynamic_irq_init(). igb: Grabs the vector_lock now and starts looping over irq_desc_ptrs[] via create_irq_nr(). It gets to irq_desc_ptrs[102] and does this: cfg_new = irq_desc_ptrs[102]->chip_data; if (cfg_new->vector != 0) continue; This hits the NULL deref. Another possible race exists via pci_disable_msix() in a driver or in the number of error paths that call free_msi_irqs(): destroy_irq() dynamic_irq_cleanup() which sets desc->chip_data = NULL ...race window... desc->chip_data = cfg; Remove the save and restore code for cfg in create_irq_nr() and destroy_irq() and take the desc->lock when checking the irq_cfg. Reported-and-analyzed-by: Brandon Philips Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-3-git-send-email-yinghai@kernel.org> Signed-off-by: Brandon Phililps Cc: stable@kernel.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/io_apic.c | 18 ++++----------- include/linux/irq.h | 2 ++ kernel/irq/chip.c | 52 ++++++++++++++++++++++++++++++++++-------- 3 files changed, 50 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 53243ca7816d..c86591b906fa 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3228,12 +3228,9 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) } spin_unlock_irqrestore(&vector_lock, flags); - if (irq > 0) { - dynamic_irq_init(irq); - /* restore it, in case dynamic_irq_init clear it */ - if (desc_new) - desc_new->chip_data = cfg_new; - } + if (irq > 0) + dynamic_irq_init_keep_chip_data(irq); + return irq; } @@ -3256,17 +3253,12 @@ void destroy_irq(unsigned int irq) { unsigned long flags; struct irq_cfg *cfg; - struct irq_desc *desc; - /* store it, in case dynamic_irq_cleanup clear it */ - desc = irq_to_desc(irq); - cfg = desc->chip_data; - dynamic_irq_cleanup(irq); - /* connect back irq_cfg */ - desc->chip_data = cfg; + dynamic_irq_cleanup_keep_chip_data(irq); free_irte(irq); spin_lock_irqsave(&vector_lock, flags); + cfg = irq_to_desc(irq)->chip_data; __clear_irq_vector(irq, cfg); spin_unlock_irqrestore(&vector_lock, flags); } diff --git a/include/linux/irq.h b/include/linux/irq.h index 451481c082b5..4d9b26e044bc 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -400,7 +400,9 @@ static inline int irq_has_action(unsigned int irq) /* Dynamic irq helper functions */ extern void dynamic_irq_init(unsigned int irq); +void dynamic_irq_init_keep_chip_data(unsigned int irq); extern void dynamic_irq_cleanup(unsigned int irq); +void dynamic_irq_cleanup_keep_chip_data(unsigned int irq); /* Set/get chip/data for an IRQ: */ extern int set_irq_chip(unsigned int irq, struct irq_chip *chip); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index ecc3fa28f666..d70394f12ee9 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -18,11 +18,7 @@ #include "internals.h" -/** - * dynamic_irq_init - initialize a dynamically allocated irq - * @irq: irq number to initialize - */ -void dynamic_irq_init(unsigned int irq) +static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data) { struct irq_desc *desc; unsigned long flags; @@ -41,7 +37,8 @@ void dynamic_irq_init(unsigned int irq) desc->depth = 1; desc->msi_desc = NULL; desc->handler_data = NULL; - desc->chip_data = NULL; + if (!keep_chip_data) + desc->chip_data = NULL; desc->action = NULL; desc->irq_count = 0; desc->irqs_unhandled = 0; @@ -55,10 +52,26 @@ void dynamic_irq_init(unsigned int irq) } /** - * dynamic_irq_cleanup - cleanup a dynamically allocated irq + * dynamic_irq_init - initialize a dynamically allocated irq * @irq: irq number to initialize */ -void dynamic_irq_cleanup(unsigned int irq) +void dynamic_irq_init(unsigned int irq) +{ + dynamic_irq_init_x(irq, false); +} + +/** + * dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq + * @irq: irq number to initialize + * + * does not set irq_to_desc(irq)->chip_data to NULL + */ +void dynamic_irq_init_keep_chip_data(unsigned int irq) +{ + dynamic_irq_init_x(irq, true); +} + +static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; @@ -77,7 +90,8 @@ void dynamic_irq_cleanup(unsigned int irq) } desc->msi_desc = NULL; desc->handler_data = NULL; - desc->chip_data = NULL; + if (!keep_chip_data) + desc->chip_data = NULL; desc->handle_irq = handle_bad_irq; desc->chip = &no_irq_chip; desc->name = NULL; @@ -85,6 +99,26 @@ void dynamic_irq_cleanup(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); } +/** + * dynamic_irq_cleanup - cleanup a dynamically allocated irq + * @irq: irq number to initialize + */ +void dynamic_irq_cleanup(unsigned int irq) +{ + dynamic_irq_cleanup_x(irq, false); +} + +/** + * dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq + * @irq: irq number to initialize + * + * does not set irq_to_desc(irq)->chip_data to NULL + */ +void dynamic_irq_cleanup_keep_chip_data(unsigned int irq) +{ + dynamic_irq_cleanup_x(irq, true); +} + /** * set_irq_chip - set the irq chip for an irq -- cgit v1.2.3 From 27811d8cabe56e0c3622251b049086f49face4ff Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:07 -0800 Subject: x86: Move range related operation to one file We have almost the same code for mtrr cleanup and amd_bus checkup, and this code will also be used in replacing bootmem with early_res, so try to move them together and reuse it from different parts. Also rename update_range to subtract_range as that is what the function is actually doing. -v2: update comments as Christoph requested Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-4-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mtrr/cleanup.c | 180 ++++--------------------------------- arch/x86/kernel/mmconf-fam10h_64.c | 7 +- arch/x86/pci/amd_bus.c | 70 +++------------ include/linux/range.h | 22 +++++ kernel/Makefile | 2 +- kernel/range.c | 163 +++++++++++++++++++++++++++++++++ 6 files changed, 214 insertions(+), 230 deletions(-) create mode 100644 include/linux/range.h create mode 100644 kernel/range.c (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 09b1698e0466..669da09ab9a8 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -22,10 +22,10 @@ #include #include #include -#include #include #include #include +#include #include #include @@ -34,11 +34,6 @@ #include "mtrr.h" -struct res_range { - unsigned long start; - unsigned long end; -}; - struct var_mtrr_range_state { unsigned long base_pfn; unsigned long size_pfn; @@ -56,7 +51,7 @@ struct var_mtrr_state { /* Should be related to MTRR_VAR_RANGES nums */ #define RANGE_NUM 256 -static struct res_range __initdata range[RANGE_NUM]; +static struct range __initdata range[RANGE_NUM]; static int __initdata nr_range; static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; @@ -64,152 +59,11 @@ static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; static int __initdata debug_print; #define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0) - -static int __init -add_range(struct res_range *range, int nr_range, - unsigned long start, unsigned long end) -{ - /* Out of slots: */ - if (nr_range >= RANGE_NUM) - return nr_range; - - range[nr_range].start = start; - range[nr_range].end = end; - - nr_range++; - - return nr_range; -} - -static int __init -add_range_with_merge(struct res_range *range, int nr_range, - unsigned long start, unsigned long end) -{ - int i; - - /* Try to merge it with old one: */ - for (i = 0; i < nr_range; i++) { - unsigned long final_start, final_end; - unsigned long common_start, common_end; - - if (!range[i].end) - continue; - - common_start = max(range[i].start, start); - common_end = min(range[i].end, end); - if (common_start > common_end + 1) - continue; - - final_start = min(range[i].start, start); - final_end = max(range[i].end, end); - - range[i].start = final_start; - range[i].end = final_end; - return nr_range; - } - - /* Need to add it: */ - return add_range(range, nr_range, start, end); -} - -static void __init -subtract_range(struct res_range *range, unsigned long start, unsigned long end) -{ - int i, j; - - for (j = 0; j < RANGE_NUM; j++) { - if (!range[j].end) - continue; - - if (start <= range[j].start && end >= range[j].end) { - range[j].start = 0; - range[j].end = 0; - continue; - } - - if (start <= range[j].start && end < range[j].end && - range[j].start < end + 1) { - range[j].start = end + 1; - continue; - } - - - if (start > range[j].start && end >= range[j].end && - range[j].end > start - 1) { - range[j].end = start - 1; - continue; - } - - if (start > range[j].start && end < range[j].end) { - /* Find the new spare: */ - for (i = 0; i < RANGE_NUM; i++) { - if (range[i].end == 0) - break; - } - if (i < RANGE_NUM) { - range[i].end = range[j].end; - range[i].start = end + 1; - } else { - printk(KERN_ERR "run of slot in ranges\n"); - } - range[j].end = start - 1; - continue; - } - } -} - -static int __init cmp_range(const void *x1, const void *x2) -{ - const struct res_range *r1 = x1; - const struct res_range *r2 = x2; - long start1, start2; - - start1 = r1->start; - start2 = r2->start; - - return start1 - start2; -} - -static int __init clean_sort_range(struct res_range *range, int az) -{ - int i, j, k = az - 1, nr_range = 0; - - for (i = 0; i < k; i++) { - if (range[i].end) - continue; - for (j = k; j > i; j--) { - if (range[j].end) { - k = j; - break; - } - } - if (j == i) - break; - range[i].start = range[k].start; - range[i].end = range[k].end; - range[k].start = 0; - range[k].end = 0; - k--; - } - /* count it */ - for (i = 0; i < az; i++) { - if (!range[i].end) { - nr_range = i; - break; - } - } - - /* sort them */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); - - return nr_range; -} - #define BIOS_BUG_MSG KERN_WARNING \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" static int __init -x86_get_mtrr_mem_range(struct res_range *range, int nr_range, +x86_get_mtrr_mem_range(struct range *range, int nr_range, unsigned long extra_remove_base, unsigned long extra_remove_size) { @@ -223,13 +77,13 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, continue; base = range_state[i].base_pfn; size = range_state[i].size_pfn; - nr_range = add_range_with_merge(range, nr_range, base, - base + size - 1); + nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, + base, base + size - 1); } if (debug_print) { printk(KERN_DEBUG "After WB checking\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end + 1); } @@ -252,10 +106,10 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, size -= (1<<(20-PAGE_SHIFT)) - base; base = 1<<(20-PAGE_SHIFT); } - subtract_range(range, base, base + size - 1); + subtract_range(range, RANGE_NUM, base, base + size - 1); } if (extra_remove_size) - subtract_range(range, extra_remove_base, + subtract_range(range, RANGE_NUM, extra_remove_base, extra_remove_base + extra_remove_size - 1); if (debug_print) { @@ -263,7 +117,7 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, for (i = 0; i < RANGE_NUM; i++) { if (!range[i].end) continue; - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end + 1); } } @@ -273,20 +127,16 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, if (debug_print) { printk(KERN_DEBUG "After sorting\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end + 1); } - /* clear those is not used */ - for (i = nr_range; i < RANGE_NUM; i++) - memset(&range[i], 0, sizeof(range[i])); - return nr_range; } #ifdef CONFIG_MTRR_SANITIZER -static unsigned long __init sum_ranges(struct res_range *range, int nr_range) +static unsigned long __init sum_ranges(struct range *range, int nr_range) { unsigned long sum = 0; int i; @@ -621,7 +471,7 @@ static int __init parse_mtrr_spare_reg(char *arg) early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg); static int __init -x86_setup_var_mtrrs(struct res_range *range, int nr_range, +x86_setup_var_mtrrs(struct range *range, int nr_range, u64 chunk_size, u64 gran_size) { struct var_mtrr_state var_state; @@ -742,7 +592,7 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size, unsigned long x_remove_base, unsigned long x_remove_size, int i) { - static struct res_range range_new[RANGE_NUM]; + static struct range range_new[RANGE_NUM]; unsigned long range_sums_new; static int nr_range_new; int num_reg; @@ -869,10 +719,10 @@ int __init mtrr_cleanup(unsigned address_bits) * [0, 1M) should always be covered by var mtrr with WB * and fixed mtrrs should take effect before var mtrr for it: */ - nr_range = add_range_with_merge(range, nr_range, 0, + nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0, (1ULL<<(20 - PAGE_SHIFT)) - 1); /* Sort the ranges: */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + sort_range(range, nr_range); range_sums = sum_ranges(range, nr_range); printk(KERN_INFO "total RAM covered: %ldM\n", diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index 712d15fdc416..71825806cd44 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -7,6 +7,8 @@ #include #include #include +#include + #include #include #include @@ -30,11 +32,6 @@ static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = { { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, }; -struct range { - u64 start; - u64 end; -}; - static int __cpuinit cmp_range(const void *x1, const void *x2) { const struct range *r1 = x1; diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 95ecbd495955..2356ea18697d 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -2,6 +2,8 @@ #include #include #include +#include + #include #ifdef CONFIG_X86_64 @@ -17,58 +19,6 @@ #ifdef CONFIG_X86_64 -#define RANGE_NUM 16 - -struct res_range { - size_t start; - size_t end; -}; - -static void __init update_range(struct res_range *range, size_t start, - size_t end) -{ - int i; - int j; - - for (j = 0; j < RANGE_NUM; j++) { - if (!range[j].end) - continue; - - if (start <= range[j].start && end >= range[j].end) { - range[j].start = 0; - range[j].end = 0; - continue; - } - - if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) { - range[j].start = end + 1; - continue; - } - - - if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) { - range[j].end = start - 1; - continue; - } - - if (start > range[j].start && end < range[j].end) { - /* find the new spare */ - for (i = 0; i < RANGE_NUM; i++) { - if (range[i].end == 0) - break; - } - if (i < RANGE_NUM) { - range[i].end = range[j].end; - range[i].start = end + 1; - } else { - printk(KERN_ERR "run of slot in ranges\n"); - } - range[j].end = start - 1; - continue; - } - } -} - struct pci_hostbridge_probe { u32 bus; u32 slot; @@ -111,6 +61,8 @@ static void __init get_pci_mmcfg_amd_fam10h_range(void) fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1; } +#define RANGE_NUM 16 + /** * early_fill_mp_bus_to_node() * called before pcibios_scan_root and pci_scan_bus @@ -132,7 +84,7 @@ static int __init early_fill_mp_bus_info(void) struct resource *res; size_t start; size_t end; - struct res_range range[RANGE_NUM]; + struct range range[RANGE_NUM]; u64 val; u32 address; @@ -226,7 +178,7 @@ static int __init early_fill_mp_bus_info(void) if (end > 0xffff) end = 0xffff; update_res(info, start, end, IORESOURCE_IO, 1); - update_range(range, start, end); + subtract_range(range, RANGE_NUM, start, end); } /* add left over io port range to def node/link, [0, 0xffff] */ /* find the position */ @@ -256,14 +208,14 @@ static int __init early_fill_mp_bus_info(void) end = (val & 0xffffff800000ULL); printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20); if (end < (1ULL<<32)) - update_range(range, 0, end - 1); + subtract_range(range, RANGE_NUM, 0, end - 1); /* get mmconfig */ get_pci_mmcfg_amd_fam10h_range(); /* need to take out mmconf range */ if (fam10h_mmconf_end) { printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end); - update_range(range, fam10h_mmconf_start, fam10h_mmconf_end); + subtract_range(range, RANGE_NUM, fam10h_mmconf_start, fam10h_mmconf_end); } /* mmio resource */ @@ -318,7 +270,7 @@ static int __init early_fill_mp_bus_info(void) /* we got a hole */ endx = fam10h_mmconf_start - 1; update_res(info, start, endx, IORESOURCE_MEM, 0); - update_range(range, start, endx); + subtract_range(range, RANGE_NUM, start, endx); printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx); start = fam10h_mmconf_end + 1; changed = 1; @@ -334,7 +286,7 @@ static int __init early_fill_mp_bus_info(void) } update_res(info, start, end, IORESOURCE_MEM, 1); - update_range(range, start, end); + subtract_range(range, RANGE_NUM, start, end); printk(KERN_CONT "\n"); } @@ -349,7 +301,7 @@ static int __init early_fill_mp_bus_info(void) rdmsrl(address, val); end = (val & 0xffffff800000ULL); printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20); - update_range(range, 1ULL<<32, end - 1); + subtract_range(range, RANGE_NUM, 1ULL<<32, end - 1); } /* diff --git a/include/linux/range.h b/include/linux/range.h new file mode 100644 index 000000000000..0789f1412e1f --- /dev/null +++ b/include/linux/range.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_RANGE_H +#define _LINUX_RANGE_H + +struct range { + u64 start; + u64 end; +}; + +int add_range(struct range *range, int az, int nr_range, + u64 start, u64 end); + + +int add_range_with_merge(struct range *range, int az, int nr_range, + u64 start, u64 end); + +void subtract_range(struct range *range, int az, u64 start, u64 end); + +int clean_sort_range(struct range *range, int az); + +void sort_range(struct range *range, int nr_range); + +#endif diff --git a/kernel/Makefile b/kernel/Makefile index 864ff75d65f2..ad47330ccf32 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -10,7 +10,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ - async.o + async.o range.o obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER diff --git a/kernel/range.c b/kernel/range.c new file mode 100644 index 000000000000..71e0021281fe --- /dev/null +++ b/kernel/range.c @@ -0,0 +1,163 @@ +/* + * Range add and subtract + */ +#include +#include +#include + +#include + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +int add_range(struct range *range, int az, int nr_range, u64 start, u64 end) +{ + if (start > end) + return nr_range; + + /* Out of slots: */ + if (nr_range >= az) + return nr_range; + + range[nr_range].start = start; + range[nr_range].end = end; + + nr_range++; + + return nr_range; +} + +int add_range_with_merge(struct range *range, int az, int nr_range, + u64 start, u64 end) +{ + int i; + + if (start > end) + return nr_range; + + /* Try to merge it with old one: */ + for (i = 0; i < nr_range; i++) { + u64 final_start, final_end; + u64 common_start, common_end; + + if (!range[i].end) + continue; + + common_start = max(range[i].start, start); + common_end = min(range[i].end, end); + if (common_start > common_end + 1) + continue; + + final_start = min(range[i].start, start); + final_end = max(range[i].end, end); + + range[i].start = final_start; + range[i].end = final_end; + return nr_range; + } + + /* Need to add it: */ + return add_range(range, az, nr_range, start, end); +} + +void subtract_range(struct range *range, int az, u64 start, u64 end) +{ + int i, j; + + if (start > end) + return; + + for (j = 0; j < az; j++) { + if (!range[j].end) + continue; + + if (start <= range[j].start && end >= range[j].end) { + range[j].start = 0; + range[j].end = 0; + continue; + } + + if (start <= range[j].start && end < range[j].end && + range[j].start < end + 1) { + range[j].start = end + 1; + continue; + } + + + if (start > range[j].start && end >= range[j].end && + range[j].end > start - 1) { + range[j].end = start - 1; + continue; + } + + if (start > range[j].start && end < range[j].end) { + /* Find the new spare: */ + for (i = 0; i < az; i++) { + if (range[i].end == 0) + break; + } + if (i < az) { + range[i].end = range[j].end; + range[i].start = end + 1; + } else { + printk(KERN_ERR "run of slot in ranges\n"); + } + range[j].end = start - 1; + continue; + } + } +} + +static int cmp_range(const void *x1, const void *x2) +{ + const struct range *r1 = x1; + const struct range *r2 = x2; + s64 start1, start2; + + start1 = r1->start; + start2 = r2->start; + + return start1 - start2; +} + +int clean_sort_range(struct range *range, int az) +{ + int i, j, k = az - 1, nr_range = 0; + + for (i = 0; i < k; i++) { + if (range[i].end) + continue; + for (j = k; j > i; j--) { + if (range[j].end) { + k = j; + break; + } + } + if (j == i) + break; + range[i].start = range[k].start; + range[i].end = range[k].end; + range[k].start = 0; + range[k].end = 0; + k--; + } + /* count it */ + for (i = 0; i < az; i++) { + if (!range[i].end) { + nr_range = i; + break; + } + } + + /* sort them */ + sort(range, nr_range, sizeof(struct range), cmp_range, NULL); + + return nr_range; +} + +void sort_range(struct range *range, int nr_range) +{ + /* sort them */ + sort(range, nr_range, sizeof(struct range), cmp_range, NULL); +} -- cgit v1.2.3 From e9a0064ad03b899938059bb576615ad9ed0f27f9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:13 -0800 Subject: x86: Change range end to start+size So make interface more consistent with early_res. Later we can share some code with early_res. Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-10-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mtrr/cleanup.c | 32 ++++++++++++++++---------------- arch/x86/pci/amd_bus.c | 24 ++++++++++++++---------- kernel/range.c | 20 ++++++++++---------- 3 files changed, 40 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 669da09ab9a8..06130b52f012 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -78,13 +78,13 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, base = range_state[i].base_pfn; size = range_state[i].size_pfn; nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, - base, base + size - 1); + base, base + size); } if (debug_print) { printk(KERN_DEBUG "After WB checking\n"); for (i = 0; i < nr_range; i++) printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end + 1); + range[i].start, range[i].end); } /* Take out UC ranges: */ @@ -106,11 +106,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, size -= (1<<(20-PAGE_SHIFT)) - base; base = 1<<(20-PAGE_SHIFT); } - subtract_range(range, RANGE_NUM, base, base + size - 1); + subtract_range(range, RANGE_NUM, base, base + size); } if (extra_remove_size) subtract_range(range, RANGE_NUM, extra_remove_base, - extra_remove_base + extra_remove_size - 1); + extra_remove_base + extra_remove_size); if (debug_print) { printk(KERN_DEBUG "After UC checking\n"); @@ -118,7 +118,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, if (!range[i].end) continue; printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end + 1); + range[i].start, range[i].end); } } @@ -128,7 +128,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, printk(KERN_DEBUG "After sorting\n"); for (i = 0; i < nr_range; i++) printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end + 1); + range[i].start, range[i].end); } return nr_range; @@ -142,7 +142,7 @@ static unsigned long __init sum_ranges(struct range *range, int nr_range) int i; for (i = 0; i < nr_range; i++) - sum += range[i].end + 1 - range[i].start; + sum += range[i].end - range[i].start; return sum; } @@ -489,7 +489,7 @@ x86_setup_var_mtrrs(struct range *range, int nr_range, /* Write the range: */ for (i = 0; i < nr_range; i++) { set_var_mtrr_range(&var_state, range[i].start, - range[i].end - range[i].start + 1); + range[i].end - range[i].start); } /* Write the last range: */ @@ -720,7 +720,7 @@ int __init mtrr_cleanup(unsigned address_bits) * and fixed mtrrs should take effect before var mtrr for it: */ nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0, - (1ULL<<(20 - PAGE_SHIFT)) - 1); + 1ULL<<(20 - PAGE_SHIFT)); /* Sort the ranges: */ sort_range(range, nr_range); @@ -939,9 +939,9 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) nr_range = 0; if (mtrr_tom2) { range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT)); - range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1; - if (highest_pfn < range[nr_range].end + 1) - highest_pfn = range[nr_range].end + 1; + range[nr_range].end = mtrr_tom2 >> PAGE_SHIFT; + if (highest_pfn < range[nr_range].end) + highest_pfn = range[nr_range].end; nr_range++; } nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0); @@ -953,15 +953,15 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* Check the holes: */ for (i = 0; i < nr_range - 1; i++) { - if (range[i].end + 1 < range[i+1].start) - total_trim_size += real_trim_memory(range[i].end + 1, + if (range[i].end < range[i+1].start) + total_trim_size += real_trim_memory(range[i].end, range[i+1].start); } /* Check the top: */ i = nr_range - 1; - if (range[i].end + 1 < end_pfn) - total_trim_size += real_trim_memory(range[i].end + 1, + if (range[i].end < end_pfn) + total_trim_size += real_trim_memory(range[i].end, end_pfn); if (total_trim_size) { diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index ea6072fcf3d4..fc1e8fe07e5c 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -145,7 +145,7 @@ static int __init early_fill_mp_bus_info(void) def_link = (reg >> 8) & 0x03; memset(range, 0, sizeof(range)); - range[0].end = 0xffff; + add_range(range, RANGE_NUM, 0, 0, 0xffff + 1); /* io port resource */ for (i = 0; i < 4; i++) { reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3)); @@ -175,7 +175,7 @@ static int __init early_fill_mp_bus_info(void) if (end > 0xffff) end = 0xffff; update_res(info, start, end, IORESOURCE_IO, 1); - subtract_range(range, RANGE_NUM, start, end); + subtract_range(range, RANGE_NUM, start, end + 1); } /* add left over io port range to def node/link, [0, 0xffff] */ /* find the position */ @@ -190,14 +190,16 @@ static int __init early_fill_mp_bus_info(void) if (!range[i].end) continue; - update_res(info, range[i].start, range[i].end, + update_res(info, range[i].start, range[i].end - 1, IORESOURCE_IO, 1); } } memset(range, 0, sizeof(range)); /* 0xfd00000000-0xffffffffff for HT */ - range[0].end = cap_resource((0xfdULL<<32) - 1); + end = cap_resource((0xfdULL<<32) - 1); + end++; + add_range(range, RANGE_NUM, 0, 0, end); /* need to take out [0, TOM) for RAM*/ address = MSR_K8_TOP_MEM1; @@ -205,14 +207,15 @@ static int __init early_fill_mp_bus_info(void) end = (val & 0xffffff800000ULL); printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20); if (end < (1ULL<<32)) - subtract_range(range, RANGE_NUM, 0, end - 1); + subtract_range(range, RANGE_NUM, 0, end); /* get mmconfig */ get_pci_mmcfg_amd_fam10h_range(); /* need to take out mmconf range */ if (fam10h_mmconf_end) { printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end); - subtract_range(range, RANGE_NUM, fam10h_mmconf_start, fam10h_mmconf_end); + subtract_range(range, RANGE_NUM, fam10h_mmconf_start, + fam10h_mmconf_end + 1); } /* mmio resource */ @@ -267,7 +270,8 @@ static int __init early_fill_mp_bus_info(void) /* we got a hole */ endx = fam10h_mmconf_start - 1; update_res(info, start, endx, IORESOURCE_MEM, 0); - subtract_range(range, RANGE_NUM, start, endx); + subtract_range(range, RANGE_NUM, start, + endx + 1); printk(KERN_CONT " ==> [%llx, %llx]", start, endx); start = fam10h_mmconf_end + 1; changed = 1; @@ -284,7 +288,7 @@ static int __init early_fill_mp_bus_info(void) update_res(info, cap_resource(start), cap_resource(end), IORESOURCE_MEM, 1); - subtract_range(range, RANGE_NUM, start, end); + subtract_range(range, RANGE_NUM, start, end + 1); printk(KERN_CONT "\n"); } @@ -299,7 +303,7 @@ static int __init early_fill_mp_bus_info(void) rdmsrl(address, val); end = (val & 0xffffff800000ULL); printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20); - subtract_range(range, RANGE_NUM, 1ULL<<32, end - 1); + subtract_range(range, RANGE_NUM, 1ULL<<32, end); } /* @@ -319,7 +323,7 @@ static int __init early_fill_mp_bus_info(void) continue; update_res(info, cap_resource(range[i].start), - cap_resource(range[i].end), + cap_resource(range[i].end - 1), IORESOURCE_MEM, 1); } } diff --git a/kernel/range.c b/kernel/range.c index 71e0021281fe..74e2e6114927 100644 --- a/kernel/range.c +++ b/kernel/range.c @@ -13,7 +13,7 @@ int add_range(struct range *range, int az, int nr_range, u64 start, u64 end) { - if (start > end) + if (start >= end) return nr_range; /* Out of slots: */ @@ -33,7 +33,7 @@ int add_range_with_merge(struct range *range, int az, int nr_range, { int i; - if (start > end) + if (start >= end) return nr_range; /* Try to merge it with old one: */ @@ -46,7 +46,7 @@ int add_range_with_merge(struct range *range, int az, int nr_range, common_start = max(range[i].start, start); common_end = min(range[i].end, end); - if (common_start > common_end + 1) + if (common_start > common_end) continue; final_start = min(range[i].start, start); @@ -65,7 +65,7 @@ void subtract_range(struct range *range, int az, u64 start, u64 end) { int i, j; - if (start > end) + if (start >= end) return; for (j = 0; j < az; j++) { @@ -79,15 +79,15 @@ void subtract_range(struct range *range, int az, u64 start, u64 end) } if (start <= range[j].start && end < range[j].end && - range[j].start < end + 1) { - range[j].start = end + 1; + range[j].start < end) { + range[j].start = end; continue; } if (start > range[j].start && end >= range[j].end && - range[j].end > start - 1) { - range[j].end = start - 1; + range[j].end > start) { + range[j].end = start; continue; } @@ -99,11 +99,11 @@ void subtract_range(struct range *range, int az, u64 start, u64 end) } if (i < az) { range[i].end = range[j].end; - range[i].start = end + 1; + range[i].start = end; } else { printk(KERN_ERR "run of slot in ranges\n"); } - range[j].end = start - 1; + range[j].end = start; continue; } } -- cgit v1.2.3 From 5c42dc7070c94622ca914b5a2e227f3744e857e7 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 11 Feb 2010 15:04:36 +0100 Subject: devres/irq: Fix devm_irq_match comment Fix the reference (in comment). Signed-off-by: Jean Delvare Signed-off-by: Jiri Kosina --- kernel/irq/devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 30d56bafc9c2..1ef4ffcdfa55 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -42,7 +42,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data) * automatically freed on driver detach. * * If an IRQ allocated with this function needs to be freed - * separately, dev_free_irq() must be used. + * separately, devm_free_irq() must be used. */ int devm_request_threaded_irq(struct device *dev, unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, -- cgit v1.2.3 From dfff0615d28bdb3e8d213e5537dd069265912667 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 12 Feb 2010 21:58:11 +0100 Subject: tree-wide: fix typos "ass?o[sc]iac?te" -> "associate" in comments MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Uwe Kleine-König Signed-off-by: Jiri Kosina --- drivers/usb/musb/davinci.c | 2 +- drivers/zorro/zorro.ids | 2 +- include/net/irda/irttp.h | 2 +- kernel/irq/chip.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c index 66913811af5e..a883f9dd3f8a 100644 --- a/drivers/usb/musb/davinci.c +++ b/drivers/usb/musb/davinci.c @@ -274,7 +274,7 @@ static irqreturn_t davinci_interrupt(int irq, void *__hci) /* NOTE: DaVinci shadows the Mentor IRQs. Don't manage them through * the Mentor registers (except for setup), use the TI ones and EOI. * - * Docs describe irq "vector" registers asociated with the CPPI and + * Docs describe irq "vector" registers associated with the CPPI and * USB EOI registers. These hold a bitmask corresponding to the * current IRQ, not an irq handler address. Would using those bits * resolve some of the races observed in this dispatch code?? diff --git a/drivers/zorro/zorro.ids b/drivers/zorro/zorro.ids index 0c0f99e2dd62..de24e3decedd 100644 --- a/drivers/zorro/zorro.ids +++ b/drivers/zorro/zorro.ids @@ -108,7 +108,7 @@ 0c00 500XP/SupraDrive WordSync [SCSI Host Adapter] 0d00 SupraDrive WordSync II [SCSI Host Adapter] 1000 2400zi+ [Modem] -0422 Computer Systems Assosiates +0422 Computer Systems Associates 1100 Magnum 40 [Accelerator and SCSI Host Adapter] 1500 12 Gauge [SCSI Host Adapter] 0439 Marc Michael Groth diff --git a/include/net/irda/irttp.h b/include/net/irda/irttp.h index 0788c23d2828..11aee7a2972a 100644 --- a/include/net/irda/irttp.h +++ b/include/net/irda/irttp.h @@ -97,7 +97,7 @@ #define TTP_MAX_SDU_SIZE 0x01 /* - * This structure contains all data assosiated with one instance of a TTP + * This structure contains all data associated with one instance of a TTP * connection. */ struct tsap_cb { diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index ecc3fa28f666..ec8a96382461 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -520,7 +520,7 @@ out: * signal. The occurence is latched into the irq controller hardware * and must be acked in order to be reenabled. After the ack another * interrupt can happen on the same source even before the first one - * is handled by the assosiacted event handler. If this happens it + * is handled by the associated event handler. If this happens it * might be necessary to disable (mask) the interrupt depending on the * controller hardware. This requires to reenable the interrupt inside * of the loop which handles the interrupts which have arrived while -- cgit v1.2.3 From 43cf38eb5cea91245502df3fcee4dbfc1c74dd1c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 2 Feb 2010 14:38:57 +0900 Subject: percpu: add __percpu sparse annotations to core kernel subsystems Add __percpu sparse annotations to core subsystems. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter Acked-by: Paul E. McKenney Cc: Jens Axboe Cc: linux-mm@kvack.org Cc: Rusty Russell Cc: Dipankar Sarma Cc: Peter Zijlstra Cc: Andrew Morton Cc: Eric Biederman --- include/linux/blktrace_api.h | 4 ++-- include/linux/genhd.h | 2 +- include/linux/kexec.h | 2 +- include/linux/mmzone.h | 2 +- include/linux/module.h | 2 +- include/linux/percpu_counter.h | 2 +- include/linux/srcu.h | 2 +- kernel/kexec.c | 2 +- kernel/sched.c | 4 ++-- kernel/stop_machine.c | 2 +- mm/percpu.c | 18 ++++++++++-------- 11 files changed, 22 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 3b73b9992b26..416bf62d6d46 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -150,8 +150,8 @@ struct blk_user_trace_setup { struct blk_trace { int trace_state; struct rchan *rchan; - unsigned long *sequence; - unsigned char *msg_data; + unsigned long __percpu *sequence; + unsigned char __percpu *msg_data; u16 act_mask; u64 start_lba; u64 end_lba; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9717081c75ad..56b50514ab25 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -101,7 +101,7 @@ struct hd_struct { unsigned long stamp; int in_flight[2]; #ifdef CONFIG_SMP - struct disk_stats *dkstats; + struct disk_stats __percpu *dkstats; #else struct disk_stats dkstats; #endif diff --git a/include/linux/kexec.h b/include/linux/kexec.h index c356b6914ffd..03e8e8dbc577 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -199,7 +199,7 @@ extern struct kimage *kexec_crash_image; */ extern struct resource crashk_res; typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4]; -extern note_buf_t *crash_notes; +extern note_buf_t __percpu *crash_notes; extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7874201a3556..41acd4bf7664 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -301,7 +301,7 @@ struct zone { unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif - struct per_cpu_pageset *pageset; + struct per_cpu_pageset __percpu *pageset; /* * free areas of different sizes */ diff --git a/include/linux/module.h b/include/linux/module.h index 7e74ae0051cc..dd618eb026aa 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -365,7 +365,7 @@ struct module struct module_ref { int count; - } *refptr; + } __percpu *refptr; #endif #ifdef CONFIG_CONSTRUCTORS diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index a7684a513994..9bd103c844ee 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -21,7 +21,7 @@ struct percpu_counter { #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif - s32 *counters; + s32 __percpu *counters; }; extern int percpu_counter_batch; diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4765d97dcafb..41eedccc962c 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -33,7 +33,7 @@ struct srcu_struct_array { struct srcu_struct { int completed; - struct srcu_struct_array *per_cpu_ref; + struct srcu_struct_array __percpu *per_cpu_ref; struct mutex mutex; }; diff --git a/kernel/kexec.c b/kernel/kexec.c index ef077fb73155..87ebe8adc474 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -41,7 +41,7 @@ #include /* Per cpu memory for storing cpu states in case of system crash. */ -note_buf_t* crash_notes; +note_buf_t __percpu *crash_notes; /* vmcoreinfo stuff */ static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; diff --git a/kernel/sched.c b/kernel/sched.c index 3a8fb30a91b1..978edfd35a96 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1566,7 +1566,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static __read_mostly unsigned long *update_shares_data; +static __read_mostly unsigned long __percpu *update_shares_data; static void __set_se_shares(struct sched_entity *se, unsigned long shares); @@ -10683,7 +10683,7 @@ struct cgroup_subsys cpu_cgroup_subsys = { struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 *cpuusage; + u64 __percpu *cpuusage; struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; struct cpuacct *parent; }; diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 912823e2a11b..9bb9fb1bd79c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -45,7 +45,7 @@ static int refcount; static struct workqueue_struct *stop_machine_wq; static struct stop_machine_data active, idle; static const struct cpumask *active_cpus; -static void *stop_machine_work; +static void __percpu *stop_machine_work; static void set_state(enum stopmachine_state newstate) { diff --git a/mm/percpu.c b/mm/percpu.c index b336638d20e7..768419d44ad7 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -80,13 +80,15 @@ /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ - (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ - + (unsigned long)__per_cpu_start) + (void __percpu *)((unsigned long)(addr) - \ + (unsigned long)pcpu_base_addr + \ + (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ - (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ - - (unsigned long)__per_cpu_start) + (void __force *)((unsigned long)(ptr) + \ + (unsigned long)pcpu_base_addr - \ + (unsigned long)__per_cpu_start) #endif struct pcpu_chunk { @@ -1065,7 +1067,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void) * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -static void *pcpu_alloc(size_t size, size_t align, bool reserved) +static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved) { static int warn_limit = 10; struct pcpu_chunk *chunk; @@ -1194,7 +1196,7 @@ fail_unlock_mutex: * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -void *__alloc_percpu(size_t size, size_t align) +void __percpu *__alloc_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, false); } @@ -1215,7 +1217,7 @@ EXPORT_SYMBOL_GPL(__alloc_percpu); * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -void *__alloc_reserved_percpu(size_t size, size_t align) +void __percpu *__alloc_reserved_percpu(size_t size, size_t align) { return pcpu_alloc(size, align, true); } @@ -1267,7 +1269,7 @@ static void pcpu_reclaim(struct work_struct *work) * CONTEXT: * Can be called from atomic context. */ -void free_percpu(void *ptr) +void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; -- cgit v1.2.3 From 580e0ad21d6d6f932461d24b47041e3dd499c23f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 16 Feb 2010 18:40:35 -0800 Subject: core: Move early_res from arch/x86 to kernel/ This makes the range reservation feature available to other architectures. -v2: add get_max_mapped, max_pfn_mapped only defined in x86... to fix PPC compiling -v3: according to hpa, add CONFIG_HAVE_EARLY_RES -v4: fix typo about EARLY_RES in config Signed-off-by: Yinghai Lu LKML-Reference: <4B7B5723.4070009@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 3 + arch/x86/include/asm/e820.h | 2 +- arch/x86/include/asm/early_res.h | 21 -- arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/e820.c | 10 +- arch/x86/kernel/early_res.c | 521 --------------------------------------- include/linux/early_res.h | 22 ++ kernel/Makefile | 1 + kernel/early_res.c | 513 ++++++++++++++++++++++++++++++++++++++ 9 files changed, 550 insertions(+), 545 deletions(-) delete mode 100644 arch/x86/include/asm/early_res.h delete mode 100644 arch/x86/kernel/early_res.c create mode 100644 include/linux/early_res.h create mode 100644 kernel/early_res.c (limited to 'kernel') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 29f9efb74fc7..0e9f8b10de52 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -183,6 +183,9 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y +config HAVE_EARLY_RES + def_bool y + config HAVE_INTEL_TXT def_bool y depends on EXPERIMENTAL && DMAR && ACPI diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index a8299e134437..0e22296790d3 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -112,7 +112,7 @@ extern unsigned long end_user_pfn; extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align); extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align); extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); -#include +#include extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); diff --git a/arch/x86/include/asm/early_res.h b/arch/x86/include/asm/early_res.h deleted file mode 100644 index 9758f3df9dad..000000000000 --- a/arch/x86/include/asm/early_res.h +++ /dev/null @@ -1,21 +0,0 @@ -#ifndef _ASM_X86_EARLY_RES_H -#define _ASM_X86_EARLY_RES_H -#ifdef __KERNEL__ - -extern void reserve_early(u64 start, u64 end, char *name); -extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); -extern void free_early(u64 start, u64 end); -extern void early_res_to_bootmem(u64 start, u64 end); - -void reserve_early_without_check(u64 start, u64 end, char *name); -u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, - u64 size, u64 align); -u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start, - u64 *sizep, u64 align); -u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align); -#include -int get_free_all_memory_range(struct range **rangep, int nodeid); - -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_EARLY_RES_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f5fb9f0b6277..d87f09bc5a52 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -38,7 +38,7 @@ obj-$(CONFIG_X86_32) += probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o -obj-y += bootflag.o e820.o early_res.o +obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 36918d8463ab..740b440fbd73 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -17,7 +17,6 @@ #include #include -#include #include #include @@ -752,6 +751,15 @@ u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align) { return find_e820_area(start, end, size, align); } + +u64 __init get_max_mapped(void) +{ + u64 end = max_pfn_mapped; + + end <<= PAGE_SHIFT; + + return end; +} /* * Find next free range after *start */ diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c deleted file mode 100644 index 1458dc022343..000000000000 --- a/arch/x86/kernel/early_res.c +++ /dev/null @@ -1,521 +0,0 @@ -/* - * early_res, could be used to replace bootmem - */ -#include -#include -#include -#include -#include - -#include - -/* - * Early reserved memory areas. - */ -/* - * need to make sure this one is bigger enough before - * find_fw_memmap_area could be used - */ -#define MAX_EARLY_RES_X 32 - -struct early_res { - u64 start, end; - char name[15]; - char overlap_ok; -}; -static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata; - -static int max_early_res __initdata = MAX_EARLY_RES_X; -static struct early_res *early_res __initdata = &early_res_x[0]; -static int early_res_count __initdata; - -static int __init find_overlapped_early(u64 start, u64 end) -{ - int i; - struct early_res *r; - - for (i = 0; i < max_early_res && early_res[i].end; i++) { - r = &early_res[i]; - if (end > r->start && start < r->end) - break; - } - - return i; -} - -/* - * Drop the i-th range from the early reservation map, - * by copying any higher ranges down one over it, and - * clearing what had been the last slot. - */ -static void __init drop_range(int i) -{ - int j; - - for (j = i + 1; j < max_early_res && early_res[j].end; j++) - ; - - memmove(&early_res[i], &early_res[i + 1], - (j - 1 - i) * sizeof(struct early_res)); - - early_res[j - 1].end = 0; - early_res_count--; -} - -/* - * Split any existing ranges that: - * 1) are marked 'overlap_ok', and - * 2) overlap with the stated range [start, end) - * into whatever portion (if any) of the existing range is entirely - * below or entirely above the stated range. Drop the portion - * of the existing range that overlaps with the stated range, - * which will allow the caller of this routine to then add that - * stated range without conflicting with any existing range. - */ -static void __init drop_overlaps_that_are_ok(u64 start, u64 end) -{ - int i; - struct early_res *r; - u64 lower_start, lower_end; - u64 upper_start, upper_end; - char name[15]; - - for (i = 0; i < max_early_res && early_res[i].end; i++) { - r = &early_res[i]; - - /* Continue past non-overlapping ranges */ - if (end <= r->start || start >= r->end) - continue; - - /* - * Leave non-ok overlaps as is; let caller - * panic "Overlapping early reservations" - * when it hits this overlap. - */ - if (!r->overlap_ok) - return; - - /* - * We have an ok overlap. We will drop it from the early - * reservation map, and add back in any non-overlapping - * portions (lower or upper) as separate, overlap_ok, - * non-overlapping ranges. - */ - - /* 1. Note any non-overlapping (lower or upper) ranges. */ - strncpy(name, r->name, sizeof(name) - 1); - - lower_start = lower_end = 0; - upper_start = upper_end = 0; - if (r->start < start) { - lower_start = r->start; - lower_end = start; - } - if (r->end > end) { - upper_start = end; - upper_end = r->end; - } - - /* 2. Drop the original ok overlapping range */ - drop_range(i); - - i--; /* resume for-loop on copied down entry */ - - /* 3. Add back in any non-overlapping ranges. */ - if (lower_end) - reserve_early_overlap_ok(lower_start, lower_end, name); - if (upper_end) - reserve_early_overlap_ok(upper_start, upper_end, name); - } -} - -static void __init __reserve_early(u64 start, u64 end, char *name, - int overlap_ok) -{ - int i; - struct early_res *r; - - i = find_overlapped_early(start, end); - if (i >= max_early_res) - panic("Too many early reservations"); - r = &early_res[i]; - if (r->end) - panic("Overlapping early reservations " - "%llx-%llx %s to %llx-%llx %s\n", - start, end - 1, name ? name : "", r->start, - r->end - 1, r->name); - r->start = start; - r->end = end; - r->overlap_ok = overlap_ok; - if (name) - strncpy(r->name, name, sizeof(r->name) - 1); - early_res_count++; -} - -/* - * A few early reservtations come here. - * - * The 'overlap_ok' in the name of this routine does -not- mean it - * is ok for these reservations to overlap an earlier reservation. - * Rather it means that it is ok for subsequent reservations to - * overlap this one. - * - * Use this entry point to reserve early ranges when you are doing - * so out of "Paranoia", reserving perhaps more memory than you need, - * just in case, and don't mind a subsequent overlapping reservation - * that is known to be needed. - * - * The drop_overlaps_that_are_ok() call here isn't really needed. - * It would be needed if we had two colliding 'overlap_ok' - * reservations, so that the second such would not panic on the - * overlap with the first. We don't have any such as of this - * writing, but might as well tolerate such if it happens in - * the future. - */ -void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) -{ - drop_overlaps_that_are_ok(start, end); - __reserve_early(start, end, name, 1); -} - -u64 __init __weak find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align) -{ - panic("should have find_fw_memmap_area defined with arch"); - - return -1ULL; -} - -static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end) -{ - u64 start, end, size, mem; - struct early_res *new; - - /* do we have enough slots left ? */ - if ((max_early_res - early_res_count) > max(max_early_res/8, 2)) - return; - - /* double it */ - mem = -1ULL; - size = sizeof(struct early_res) * max_early_res * 2; - if (early_res == early_res_x) - start = 0; - else - start = early_res[0].end; - end = ex_start; - if (start + size < end) - mem = find_fw_memmap_area(start, end, size, - sizeof(struct early_res)); - if (mem == -1ULL) { - start = ex_end; - end = max_pfn_mapped << PAGE_SHIFT; - if (start + size < end) - mem = find_fw_memmap_area(start, end, size, - sizeof(struct early_res)); - } - if (mem == -1ULL) - panic("can not find more space for early_res array"); - - new = __va(mem); - /* save the first one for own */ - new[0].start = mem; - new[0].end = mem + size; - new[0].overlap_ok = 0; - /* copy old to new */ - if (early_res == early_res_x) { - memcpy(&new[1], &early_res[0], - sizeof(struct early_res) * max_early_res); - memset(&new[max_early_res+1], 0, - sizeof(struct early_res) * (max_early_res - 1)); - early_res_count++; - } else { - memcpy(&new[1], &early_res[1], - sizeof(struct early_res) * (max_early_res - 1)); - memset(&new[max_early_res], 0, - sizeof(struct early_res) * max_early_res); - } - memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); - early_res = new; - max_early_res *= 2; - printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n", - max_early_res, mem, mem + size - 1); -} - -/* - * Most early reservations come here. - * - * We first have drop_overlaps_that_are_ok() drop any pre-existing - * 'overlap_ok' ranges, so that we can then reserve this memory - * range without risk of panic'ing on an overlapping overlap_ok - * early reservation. - */ -void __init reserve_early(u64 start, u64 end, char *name) -{ - if (start >= end) - return; - - __check_and_double_early_res(start, end); - - drop_overlaps_that_are_ok(start, end); - __reserve_early(start, end, name, 0); -} - -void __init reserve_early_without_check(u64 start, u64 end, char *name) -{ - struct early_res *r; - - if (start >= end) - return; - - __check_and_double_early_res(start, end); - - r = &early_res[early_res_count]; - - r->start = start; - r->end = end; - r->overlap_ok = 0; - if (name) - strncpy(r->name, name, sizeof(r->name) - 1); - early_res_count++; -} - -void __init free_early(u64 start, u64 end) -{ - struct early_res *r; - int i; - - i = find_overlapped_early(start, end); - r = &early_res[i]; - if (i >= max_early_res || r->end != end || r->start != start) - panic("free_early on not reserved area: %llx-%llx!", - start, end - 1); - - drop_range(i); -} - -#ifdef CONFIG_NO_BOOTMEM -static void __init subtract_early_res(struct range *range, int az) -{ - int i, count; - u64 final_start, final_end; - int idx = 0; - - count = 0; - for (i = 0; i < max_early_res && early_res[i].end; i++) - count++; - - /* need to skip first one ?*/ - if (early_res != early_res_x) - idx = 1; - -#define DEBUG_PRINT_EARLY_RES 1 - -#if DEBUG_PRINT_EARLY_RES - printk(KERN_INFO "Subtract (%d early reservations)\n", count); -#endif - for (i = idx; i < count; i++) { - struct early_res *r = &early_res[i]; -#if DEBUG_PRINT_EARLY_RES - printk(KERN_INFO " #%d [%010llx - %010llx] %15s\n", i, - r->start, r->end, r->name); -#endif - final_start = PFN_DOWN(r->start); - final_end = PFN_UP(r->end); - if (final_start >= final_end) - continue; - subtract_range(range, az, final_start, final_end); - } - -} - -int __init get_free_all_memory_range(struct range **rangep, int nodeid) -{ - int i, count; - u64 start = 0, end; - u64 size; - u64 mem; - struct range *range; - int nr_range; - - count = 0; - for (i = 0; i < max_early_res && early_res[i].end; i++) - count++; - - count *= 2; - - size = sizeof(struct range) * count; -#ifdef MAX_DMA32_PFN - if (max_pfn_mapped > MAX_DMA32_PFN) - start = MAX_DMA32_PFN << PAGE_SHIFT; -#endif - end = max_pfn_mapped << PAGE_SHIFT; - mem = find_fw_memmap_area(start, end, size, sizeof(struct range)); - if (mem == -1ULL) - panic("can not find more space for range free"); - - range = __va(mem); - /* use early_node_map[] and early_res to get range array at first */ - memset(range, 0, size); - nr_range = 0; - - /* need to go over early_node_map to find out good range for node */ - nr_range = add_from_early_node_map(range, count, nr_range, nodeid); -#ifdef CONFIG_X86_32 - subtract_range(range, count, max_low_pfn, -1ULL); -#endif - subtract_early_res(range, count); - nr_range = clean_sort_range(range, count); - - /* need to clear it ? */ - if (nodeid == MAX_NUMNODES) { - memset(&early_res[0], 0, - sizeof(struct early_res) * max_early_res); - early_res = NULL; - max_early_res = 0; - } - - *rangep = range; - return nr_range; -} -#else -void __init early_res_to_bootmem(u64 start, u64 end) -{ - int i, count; - u64 final_start, final_end; - int idx = 0; - - count = 0; - for (i = 0; i < max_early_res && early_res[i].end; i++) - count++; - - /* need to skip first one ?*/ - if (early_res != early_res_x) - idx = 1; - - printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n", - count - idx, max_early_res, start, end); - for (i = idx; i < count; i++) { - struct early_res *r = &early_res[i]; - printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, - r->start, r->end, r->name); - final_start = max(start, r->start); - final_end = min(end, r->end); - if (final_start >= final_end) { - printk(KERN_CONT "\n"); - continue; - } - printk(KERN_CONT " ==> [%010llx - %010llx]\n", - final_start, final_end); - reserve_bootmem_generic(final_start, final_end - final_start, - BOOTMEM_DEFAULT); - } - /* clear them */ - memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); - early_res = NULL; - max_early_res = 0; - early_res_count = 0; -} -#endif - -/* Check for already reserved areas */ -static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) -{ - int i; - u64 addr = *addrp; - int changed = 0; - struct early_res *r; -again: - i = find_overlapped_early(addr, addr + size); - r = &early_res[i]; - if (i < max_early_res && r->end) { - *addrp = addr = round_up(r->end, align); - changed = 1; - goto again; - } - return changed; -} - -/* Check for already reserved areas */ -static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) -{ - int i; - u64 addr = *addrp, last; - u64 size = *sizep; - int changed = 0; -again: - last = addr + size; - for (i = 0; i < max_early_res && early_res[i].end; i++) { - struct early_res *r = &early_res[i]; - if (last > r->start && addr < r->start) { - size = r->start - addr; - changed = 1; - goto again; - } - if (last > r->end && addr < r->end) { - addr = round_up(r->end, align); - size = last - addr; - changed = 1; - goto again; - } - if (last <= r->end && addr >= r->start) { - (*sizep)++; - return 0; - } - } - if (changed) { - *addrp = addr; - *sizep = size; - } - return changed; -} - -/* - * Find a free area with specified alignment in a specific range. - * only with the area.between start to end is active range from early_node_map - * so they are good as RAM - */ -u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, - u64 size, u64 align) -{ - u64 addr, last; - - addr = round_up(ei_start, align); - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - goto out; - while (bad_addr(&addr, size, align) && addr+size <= ei_last) - ; - last = addr + size; - if (last > ei_last) - goto out; - if (last > end) - goto out; - - return addr; - -out: - return -1ULL; -} - -u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start, - u64 *sizep, u64 align) -{ - u64 addr, last; - - addr = round_up(ei_start, align); - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - goto out; - *sizep = ei_last - addr; - while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last) - ; - last = addr + *sizep; - if (last > ei_last) - goto out; - - return addr; - -out: - return -1ULL; -} diff --git a/include/linux/early_res.h b/include/linux/early_res.h new file mode 100644 index 000000000000..50f7663bb8b1 --- /dev/null +++ b/include/linux/early_res.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_EARLY_RES_H +#define _LINUX_EARLY_RES_H +#ifdef __KERNEL__ + +extern void reserve_early(u64 start, u64 end, char *name); +extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); +extern void free_early(u64 start, u64 end); +extern void early_res_to_bootmem(u64 start, u64 end); + +void reserve_early_without_check(u64 start, u64 end, char *name); +u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, + u64 size, u64 align); +u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start, + u64 *sizep, u64 align); +u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align); +u64 get_max_mapped(void); +#include +int get_free_all_memory_range(struct range **rangep, int nodeid); + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_EARLY_RES_H */ diff --git a/kernel/Makefile b/kernel/Makefile index ad47330ccf32..1292b863d667 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,6 +11,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ async.o range.o +obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER diff --git a/kernel/early_res.c b/kernel/early_res.c new file mode 100644 index 000000000000..aa5494ac4462 --- /dev/null +++ b/kernel/early_res.c @@ -0,0 +1,513 @@ +/* + * early_res, could be used to replace bootmem + */ +#include +#include +#include +#include +#include +#include + +/* + * Early reserved memory areas. + */ +/* + * need to make sure this one is bigger enough before + * find_fw_memmap_area could be used + */ +#define MAX_EARLY_RES_X 32 + +struct early_res { + u64 start, end; + char name[15]; + char overlap_ok; +}; +static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata; + +static int max_early_res __initdata = MAX_EARLY_RES_X; +static struct early_res *early_res __initdata = &early_res_x[0]; +static int early_res_count __initdata; + +static int __init find_overlapped_early(u64 start, u64 end) +{ + int i; + struct early_res *r; + + for (i = 0; i < max_early_res && early_res[i].end; i++) { + r = &early_res[i]; + if (end > r->start && start < r->end) + break; + } + + return i; +} + +/* + * Drop the i-th range from the early reservation map, + * by copying any higher ranges down one over it, and + * clearing what had been the last slot. + */ +static void __init drop_range(int i) +{ + int j; + + for (j = i + 1; j < max_early_res && early_res[j].end; j++) + ; + + memmove(&early_res[i], &early_res[i + 1], + (j - 1 - i) * sizeof(struct early_res)); + + early_res[j - 1].end = 0; + early_res_count--; +} + +/* + * Split any existing ranges that: + * 1) are marked 'overlap_ok', and + * 2) overlap with the stated range [start, end) + * into whatever portion (if any) of the existing range is entirely + * below or entirely above the stated range. Drop the portion + * of the existing range that overlaps with the stated range, + * which will allow the caller of this routine to then add that + * stated range without conflicting with any existing range. + */ +static void __init drop_overlaps_that_are_ok(u64 start, u64 end) +{ + int i; + struct early_res *r; + u64 lower_start, lower_end; + u64 upper_start, upper_end; + char name[15]; + + for (i = 0; i < max_early_res && early_res[i].end; i++) { + r = &early_res[i]; + + /* Continue past non-overlapping ranges */ + if (end <= r->start || start >= r->end) + continue; + + /* + * Leave non-ok overlaps as is; let caller + * panic "Overlapping early reservations" + * when it hits this overlap. + */ + if (!r->overlap_ok) + return; + + /* + * We have an ok overlap. We will drop it from the early + * reservation map, and add back in any non-overlapping + * portions (lower or upper) as separate, overlap_ok, + * non-overlapping ranges. + */ + + /* 1. Note any non-overlapping (lower or upper) ranges. */ + strncpy(name, r->name, sizeof(name) - 1); + + lower_start = lower_end = 0; + upper_start = upper_end = 0; + if (r->start < start) { + lower_start = r->start; + lower_end = start; + } + if (r->end > end) { + upper_start = end; + upper_end = r->end; + } + + /* 2. Drop the original ok overlapping range */ + drop_range(i); + + i--; /* resume for-loop on copied down entry */ + + /* 3. Add back in any non-overlapping ranges. */ + if (lower_end) + reserve_early_overlap_ok(lower_start, lower_end, name); + if (upper_end) + reserve_early_overlap_ok(upper_start, upper_end, name); + } +} + +static void __init __reserve_early(u64 start, u64 end, char *name, + int overlap_ok) +{ + int i; + struct early_res *r; + + i = find_overlapped_early(start, end); + if (i >= max_early_res) + panic("Too many early reservations"); + r = &early_res[i]; + if (r->end) + panic("Overlapping early reservations " + "%llx-%llx %s to %llx-%llx %s\n", + start, end - 1, name ? name : "", r->start, + r->end - 1, r->name); + r->start = start; + r->end = end; + r->overlap_ok = overlap_ok; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); + early_res_count++; +} + +/* + * A few early reservtations come here. + * + * The 'overlap_ok' in the name of this routine does -not- mean it + * is ok for these reservations to overlap an earlier reservation. + * Rather it means that it is ok for subsequent reservations to + * overlap this one. + * + * Use this entry point to reserve early ranges when you are doing + * so out of "Paranoia", reserving perhaps more memory than you need, + * just in case, and don't mind a subsequent overlapping reservation + * that is known to be needed. + * + * The drop_overlaps_that_are_ok() call here isn't really needed. + * It would be needed if we had two colliding 'overlap_ok' + * reservations, so that the second such would not panic on the + * overlap with the first. We don't have any such as of this + * writing, but might as well tolerate such if it happens in + * the future. + */ +void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 1); +} + +static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end) +{ + u64 start, end, size, mem; + struct early_res *new; + + /* do we have enough slots left ? */ + if ((max_early_res - early_res_count) > max(max_early_res/8, 2)) + return; + + /* double it */ + mem = -1ULL; + size = sizeof(struct early_res) * max_early_res * 2; + if (early_res == early_res_x) + start = 0; + else + start = early_res[0].end; + end = ex_start; + if (start + size < end) + mem = find_fw_memmap_area(start, end, size, + sizeof(struct early_res)); + if (mem == -1ULL) { + start = ex_end; + end = get_max_mapped(); + if (start + size < end) + mem = find_fw_memmap_area(start, end, size, + sizeof(struct early_res)); + } + if (mem == -1ULL) + panic("can not find more space for early_res array"); + + new = __va(mem); + /* save the first one for own */ + new[0].start = mem; + new[0].end = mem + size; + new[0].overlap_ok = 0; + /* copy old to new */ + if (early_res == early_res_x) { + memcpy(&new[1], &early_res[0], + sizeof(struct early_res) * max_early_res); + memset(&new[max_early_res+1], 0, + sizeof(struct early_res) * (max_early_res - 1)); + early_res_count++; + } else { + memcpy(&new[1], &early_res[1], + sizeof(struct early_res) * (max_early_res - 1)); + memset(&new[max_early_res], 0, + sizeof(struct early_res) * max_early_res); + } + memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); + early_res = new; + max_early_res *= 2; + printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n", + max_early_res, mem, mem + size - 1); +} + +/* + * Most early reservations come here. + * + * We first have drop_overlaps_that_are_ok() drop any pre-existing + * 'overlap_ok' ranges, so that we can then reserve this memory + * range without risk of panic'ing on an overlapping overlap_ok + * early reservation. + */ +void __init reserve_early(u64 start, u64 end, char *name) +{ + if (start >= end) + return; + + __check_and_double_early_res(start, end); + + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 0); +} + +void __init reserve_early_without_check(u64 start, u64 end, char *name) +{ + struct early_res *r; + + if (start >= end) + return; + + __check_and_double_early_res(start, end); + + r = &early_res[early_res_count]; + + r->start = start; + r->end = end; + r->overlap_ok = 0; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); + early_res_count++; +} + +void __init free_early(u64 start, u64 end) +{ + struct early_res *r; + int i; + + i = find_overlapped_early(start, end); + r = &early_res[i]; + if (i >= max_early_res || r->end != end || r->start != start) + panic("free_early on not reserved area: %llx-%llx!", + start, end - 1); + + drop_range(i); +} + +#ifdef CONFIG_NO_BOOTMEM +static void __init subtract_early_res(struct range *range, int az) +{ + int i, count; + u64 final_start, final_end; + int idx = 0; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + /* need to skip first one ?*/ + if (early_res != early_res_x) + idx = 1; + +#define DEBUG_PRINT_EARLY_RES 1 + +#if DEBUG_PRINT_EARLY_RES + printk(KERN_INFO "Subtract (%d early reservations)\n", count); +#endif + for (i = idx; i < count; i++) { + struct early_res *r = &early_res[i]; +#if DEBUG_PRINT_EARLY_RES + printk(KERN_INFO " #%d [%010llx - %010llx] %15s\n", i, + r->start, r->end, r->name); +#endif + final_start = PFN_DOWN(r->start); + final_end = PFN_UP(r->end); + if (final_start >= final_end) + continue; + subtract_range(range, az, final_start, final_end); + } + +} + +int __init get_free_all_memory_range(struct range **rangep, int nodeid) +{ + int i, count; + u64 start = 0, end; + u64 size; + u64 mem; + struct range *range; + int nr_range; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + count *= 2; + + size = sizeof(struct range) * count; + end = get_max_mapped(); +#ifdef MAX_DMA32_PFN + if (end > (MAX_DMA32_PFN << PAGE_SHIFT)) + start = MAX_DMA32_PFN << PAGE_SHIFT; +#endif + mem = find_fw_memmap_area(start, end, size, sizeof(struct range)); + if (mem == -1ULL) + panic("can not find more space for range free"); + + range = __va(mem); + /* use early_node_map[] and early_res to get range array at first */ + memset(range, 0, size); + nr_range = 0; + + /* need to go over early_node_map to find out good range for node */ + nr_range = add_from_early_node_map(range, count, nr_range, nodeid); +#ifdef CONFIG_X86_32 + subtract_range(range, count, max_low_pfn, -1ULL); +#endif + subtract_early_res(range, count); + nr_range = clean_sort_range(range, count); + + /* need to clear it ? */ + if (nodeid == MAX_NUMNODES) { + memset(&early_res[0], 0, + sizeof(struct early_res) * max_early_res); + early_res = NULL; + max_early_res = 0; + } + + *rangep = range; + return nr_range; +} +#else +void __init early_res_to_bootmem(u64 start, u64 end) +{ + int i, count; + u64 final_start, final_end; + int idx = 0; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + /* need to skip first one ?*/ + if (early_res != early_res_x) + idx = 1; + + printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n", + count - idx, max_early_res, start, end); + for (i = idx; i < count; i++) { + struct early_res *r = &early_res[i]; + printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, + r->start, r->end, r->name); + final_start = max(start, r->start); + final_end = min(end, r->end); + if (final_start >= final_end) { + printk(KERN_CONT "\n"); + continue; + } + printk(KERN_CONT " ==> [%010llx - %010llx]\n", + final_start, final_end); + reserve_bootmem_generic(final_start, final_end - final_start, + BOOTMEM_DEFAULT); + } + /* clear them */ + memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); + early_res = NULL; + max_early_res = 0; + early_res_count = 0; +} +#endif + +/* Check for already reserved areas */ +static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) +{ + int i; + u64 addr = *addrp; + int changed = 0; + struct early_res *r; +again: + i = find_overlapped_early(addr, addr + size); + r = &early_res[i]; + if (i < max_early_res && r->end) { + *addrp = addr = round_up(r->end, align); + changed = 1; + goto again; + } + return changed; +} + +/* Check for already reserved areas */ +static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) +{ + int i; + u64 addr = *addrp, last; + u64 size = *sizep; + int changed = 0; +again: + last = addr + size; + for (i = 0; i < max_early_res && early_res[i].end; i++) { + struct early_res *r = &early_res[i]; + if (last > r->start && addr < r->start) { + size = r->start - addr; + changed = 1; + goto again; + } + if (last > r->end && addr < r->end) { + addr = round_up(r->end, align); + size = last - addr; + changed = 1; + goto again; + } + if (last <= r->end && addr >= r->start) { + (*sizep)++; + return 0; + } + } + if (changed) { + *addrp = addr; + *sizep = size; + } + return changed; +} + +/* + * Find a free area with specified alignment in a specific range. + * only with the area.between start to end is active range from early_node_map + * so they are good as RAM + */ +u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, + u64 size, u64 align) +{ + u64 addr, last; + + addr = round_up(ei_start, align); + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + goto out; + while (bad_addr(&addr, size, align) && addr+size <= ei_last) + ; + last = addr + size; + if (last > ei_last) + goto out; + if (last > end) + goto out; + + return addr; + +out: + return -1ULL; +} + +u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start, + u64 *sizep, u64 align) +{ + u64 addr, last; + + addr = round_up(ei_start, align); + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + goto out; + *sizep = ei_last - addr; + while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last) + ; + last = addr + *sizep; + if (last > ei_last) + goto out; + + return addr; + +out: + return -1ULL; +} -- cgit v1.2.3 From febcb0c59ac19fef2081a30e371e7af3619b5e91 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:32 -0800 Subject: irq: Remove unnecessary bootmem code mem_init is moved early already. Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-29-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- kernel/irq/handle.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 814940e7f485..0e823c0d1c9c 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include "internals.h" @@ -87,12 +86,8 @@ void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr) { void *ptr; - if (slab_is_available()) - ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), - GFP_ATOMIC, node); - else - ptr = alloc_bootmem_node(NODE_DATA(node), - nr * sizeof(*desc->kstat_irqs)); + ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), + GFP_ATOMIC, node); /* * don't overwite if can not get new one @@ -219,10 +214,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) if (desc) goto out_unlock; - if (slab_is_available()) - desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); - else - desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc)); + desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); printk(KERN_DEBUG " alloc irq_desc for %d on node %d\n", irq, node); if (!desc) { -- cgit v1.2.3 From 99558f0bbe68cb09799ec38adbaa3f3b2dc7ba63 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:34 -0800 Subject: sparseirq: Change irq_desc_ptrs to static Add replace_irq_desc() instead of poking at the array directly. -v2: remove unneeded boundary check in replace_irq_desc Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-31-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- kernel/irq/handle.c | 7 ++++++- kernel/irq/internals.h | 6 +----- kernel/irq/numa_migrate.c | 4 ++-- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 0e823c0d1c9c..266f7986aa08 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -127,7 +127,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node) */ DEFINE_RAW_SPINLOCK(sparse_irq_lock); -struct irq_desc **irq_desc_ptrs __read_mostly; +static struct irq_desc **irq_desc_ptrs __read_mostly; static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { [0 ... NR_IRQS_LEGACY-1] = { @@ -192,6 +192,11 @@ struct irq_desc *irq_to_desc(unsigned int irq) return NULL; } +void replace_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + irq_desc_ptrs[irq] = desc; +} + struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) { struct irq_desc *desc; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index b2821f070a3d..c63f3bc88f0b 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -21,11 +21,7 @@ extern void clear_kstat_irqs(struct irq_desc *desc); extern raw_spinlock_t sparse_irq_lock; #ifdef CONFIG_SPARSE_IRQ -/* irq_desc_ptrs allocated at boot time */ -extern struct irq_desc **irq_desc_ptrs; -#else -/* irq_desc_ptrs is a fixed size array */ -extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; +void replace_irq_desc(unsigned int irq, struct irq_desc *desc); #endif #ifdef CONFIG_PROC_FS diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index 26bac9d8f860..963559dbd858 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -70,7 +70,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, raw_spin_lock_irqsave(&sparse_irq_lock, flags); /* We have to check it to avoid races with another CPU */ - desc = irq_desc_ptrs[irq]; + desc = irq_to_desc(irq); if (desc && old_desc != desc) goto out_unlock; @@ -90,7 +90,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, goto out_unlock; } - irq_desc_ptrs[irq] = desc; + replace_irq_desc(irq, desc); raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); /* free the old one */ -- cgit v1.2.3 From b5eb78f76ddfa7caf4340cf6893b032f45d8114a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:35 -0800 Subject: sparseirq: Use radix_tree instead of ptrs array Use radix_tree irq_desc_tree instead of irq_desc_ptrs. -v2: according to Eric and cyrill to use radix_tree_lookup_slot and radix_tree_replace_slot Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-32-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- kernel/irq/handle.c | 49 +++++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 24 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 266f7986aa08..76d5a671bfe1 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "internals.h" @@ -127,7 +128,26 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node) */ DEFINE_RAW_SPINLOCK(sparse_irq_lock); -static struct irq_desc **irq_desc_ptrs __read_mostly; +static RADIX_TREE(irq_desc_tree, GFP_ATOMIC); + +static void set_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + radix_tree_insert(&irq_desc_tree, irq, desc); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return radix_tree_lookup(&irq_desc_tree, irq); +} + +void replace_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + void **ptr; + + ptr = radix_tree_lookup_slot(&irq_desc_tree, irq); + if (ptr) + radix_tree_replace_slot(ptr, desc); +} static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { [0 ... NR_IRQS_LEGACY-1] = { @@ -159,9 +179,6 @@ int __init early_irq_init(void) legacy_count = ARRAY_SIZE(irq_desc_legacy); node = first_online_node; - /* allocate irq_desc_ptrs array based on nr_irqs */ - irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT); - /* allocate based on nr_cpu_ids */ kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids * sizeof(int), GFP_NOWAIT, node); @@ -175,28 +192,12 @@ int __init early_irq_init(void) lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); alloc_desc_masks(&desc[i], node, true); init_desc_masks(&desc[i]); - irq_desc_ptrs[i] = desc + i; + set_irq_desc(i, &desc[i]); } - for (i = legacy_count; i < nr_irqs; i++) - irq_desc_ptrs[i] = NULL; - return arch_early_irq_init(); } -struct irq_desc *irq_to_desc(unsigned int irq) -{ - if (irq_desc_ptrs && irq < nr_irqs) - return irq_desc_ptrs[irq]; - - return NULL; -} - -void replace_irq_desc(unsigned int irq, struct irq_desc *desc) -{ - irq_desc_ptrs[irq] = desc; -} - struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) { struct irq_desc *desc; @@ -208,14 +209,14 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) return NULL; } - desc = irq_desc_ptrs[irq]; + desc = irq_to_desc(irq); if (desc) return desc; raw_spin_lock_irqsave(&sparse_irq_lock, flags); /* We have to check it to avoid races with another CPU */ - desc = irq_desc_ptrs[irq]; + desc = irq_to_desc(irq); if (desc) goto out_unlock; @@ -228,7 +229,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) } init_one_irq_desc(irq, desc, node); - irq_desc_ptrs[irq] = desc; + set_irq_desc(irq, desc); out_unlock: raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); -- cgit v1.2.3 From b54452b07a7b1b8cc1385edba3ef2ef6d4679d5a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Feb 2010 08:14:31 +0000 Subject: const: struct nla_policy Make remaining netlink policies as const. Fixup coding style where needed. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/netlink.h | 2 +- kernel/taskstats.c | 6 ++---- net/dcb/dcbnl.c | 16 ++++++++-------- net/irda/irnetlink.c | 2 +- net/wimax/op-msg.c | 3 +-- net/wimax/op-reset.c | 3 +-- net/wimax/op-rfkill.c | 3 +-- net/wimax/op-state-get.c | 3 +-- net/wimax/stack.c | 3 +-- net/wireless/nl80211.c | 14 +++++--------- 10 files changed, 22 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/include/net/netlink.h b/include/net/netlink.h index a63b2192ac1c..f82e463c875a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -196,7 +196,7 @@ enum { * All other Exact length of attribute payload * * Example: - * static struct nla_policy my_policy[ATTR_MAX+1] __read_mostly = { + * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = { .len = sizeof(struct mystruct) }, diff --git a/kernel/taskstats.c b/kernel/taskstats.c index ea8384d3caa7..899ca51be5e8 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -46,15 +46,13 @@ static struct genl_family family = { .maxattr = TASKSTATS_CMD_ATTR_MAX, }; -static struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] -__read_mostly = { +static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = { [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; -static struct nla_policy -cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] __read_mostly = { +static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = { [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, }; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index db9f5b39388f..813e399220a7 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -54,7 +54,7 @@ MODULE_LICENSE("GPL"); /**************** DCB attribute policies *************************************/ /* DCB netlink attributes policy */ -static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_IFNAME] = {.type = NLA_NUL_STRING, .len = IFNAMSIZ - 1}, [DCB_ATTR_STATE] = {.type = NLA_U8}, [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED}, @@ -68,7 +68,7 @@ static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { }; /* DCB priority flow control to User Priority nested attributes */ -static struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = { [DCB_PFC_UP_ATTR_0] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_1] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_2] = {.type = NLA_U8}, @@ -81,7 +81,7 @@ static struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = { }; /* DCB priority grouping nested attributes */ -static struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = { [DCB_PG_ATTR_TC_0] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_1] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_2] = {.type = NLA_NESTED}, @@ -103,7 +103,7 @@ static struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = { }; /* DCB traffic class nested attributes. */ -static struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = { +static const struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = { [DCB_TC_ATTR_PARAM_PGID] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_UP_MAPPING] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_STRICT_PRIO] = {.type = NLA_U8}, @@ -112,7 +112,7 @@ static struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = { }; /* DCB capabilities nested attributes. */ -static struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { [DCB_CAP_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_CAP_ATTR_PG] = {.type = NLA_U8}, [DCB_CAP_ATTR_PFC] = {.type = NLA_U8}, @@ -124,14 +124,14 @@ static struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { }; /* DCB capabilities nested attributes. */ -static struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = { [DCB_NUMTCS_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_NUMTCS_ATTR_PG] = {.type = NLA_U8}, [DCB_NUMTCS_ATTR_PFC] = {.type = NLA_U8}, }; /* DCB BCN nested attributes. */ -static struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { [DCB_BCN_ATTR_RP_0] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_1] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_2] = {.type = NLA_U8}, @@ -160,7 +160,7 @@ static struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { }; /* DCB APP nested attributes. */ -static struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { +static const struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { [DCB_APP_ATTR_IDTYPE] = {.type = NLA_U8}, [DCB_APP_ATTR_ID] = {.type = NLA_U16}, [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8}, diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c index 476b307bd801..69b5b75f5431 100644 --- a/net/irda/irnetlink.c +++ b/net/irda/irnetlink.c @@ -124,7 +124,7 @@ static int irda_nl_get_mode(struct sk_buff *skb, struct genl_info *info) return ret; } -static struct nla_policy irda_nl_policy[IRDA_NL_ATTR_MAX + 1] = { +static const struct nla_policy irda_nl_policy[IRDA_NL_ATTR_MAX + 1] = { [IRDA_NL_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, [IRDA_NL_ATTR_MODE] = { .type = NLA_U32 }, diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c index d3bfb6ef13ae..7718657e93dc 100644 --- a/net/wimax/op-msg.c +++ b/net/wimax/op-msg.c @@ -320,8 +320,7 @@ int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name, EXPORT_SYMBOL_GPL(wimax_msg); -static const -struct nla_policy wimax_gnl_msg_policy[WIMAX_GNL_ATTR_MAX + 1] = { +static const struct nla_policy wimax_gnl_msg_policy[WIMAX_GNL_ATTR_MAX + 1] = { [WIMAX_GNL_MSG_IFIDX] = { .type = NLA_U32, }, diff --git a/net/wimax/op-reset.c b/net/wimax/op-reset.c index 35f370091f4f..4dc82a54ba30 100644 --- a/net/wimax/op-reset.c +++ b/net/wimax/op-reset.c @@ -91,8 +91,7 @@ int wimax_reset(struct wimax_dev *wimax_dev) EXPORT_SYMBOL(wimax_reset); -static const -struct nla_policy wimax_gnl_reset_policy[WIMAX_GNL_ATTR_MAX + 1] = { +static const struct nla_policy wimax_gnl_reset_policy[WIMAX_GNL_ATTR_MAX + 1] = { [WIMAX_GNL_RESET_IFIDX] = { .type = NLA_U32, }, diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c index ae752a64d920..e978c7136c97 100644 --- a/net/wimax/op-rfkill.c +++ b/net/wimax/op-rfkill.c @@ -410,8 +410,7 @@ void wimax_rfkill_rm(struct wimax_dev *wimax_dev) * just query). */ -static const -struct nla_policy wimax_gnl_rfkill_policy[WIMAX_GNL_ATTR_MAX + 1] = { +static const struct nla_policy wimax_gnl_rfkill_policy[WIMAX_GNL_ATTR_MAX + 1] = { [WIMAX_GNL_RFKILL_IFIDX] = { .type = NLA_U32, }, diff --git a/net/wimax/op-state-get.c b/net/wimax/op-state-get.c index a76b8fcb056d..11ad3356eb56 100644 --- a/net/wimax/op-state-get.c +++ b/net/wimax/op-state-get.c @@ -33,8 +33,7 @@ #include "debug-levels.h" -static const -struct nla_policy wimax_gnl_state_get_policy[WIMAX_GNL_ATTR_MAX + 1] = { +static const struct nla_policy wimax_gnl_state_get_policy[WIMAX_GNL_ATTR_MAX + 1] = { [WIMAX_GNL_STGET_IFIDX] = { .type = NLA_U32, }, diff --git a/net/wimax/stack.c b/net/wimax/stack.c index c8866412f830..813e1eaea29b 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -75,8 +75,7 @@ MODULE_PARM_DESC(debug, * close to where the data is generated. */ /* -static const -struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = { +static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = { [WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 }, [WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 }, }; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5b79ecf17bea..a001ea32cb7d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -58,7 +58,7 @@ static int get_rdev_dev_by_info_ifindex(struct genl_info *info, } /* policy for the attributes */ -static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { +static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING, .len = 20-1 }, @@ -148,8 +148,7 @@ static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { }; /* policy for the attributes */ -static struct nla_policy -nl80211_key_policy[NL80211_KEY_MAX + 1] __read_mostly = { +static const struct nla_policy nl80211_key_policy[NL80211_KEY_MAX + 1] = { [NL80211_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, [NL80211_KEY_IDX] = { .type = NLA_U8 }, [NL80211_KEY_CIPHER] = { .type = NLA_U32 }, @@ -2501,8 +2500,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) return err; } -static const struct nla_policy - reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] = { +static const struct nla_policy reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] = { [NL80211_ATTR_REG_RULE_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_FREQ_RANGE_START] = { .type = NLA_U32 }, [NL80211_ATTR_FREQ_RANGE_END] = { .type = NLA_U32 }, @@ -2671,8 +2669,7 @@ do {\ } \ } while (0);\ -static struct nla_policy -nl80211_meshconf_params_policy[NL80211_MESHCONF_ATTR_MAX+1] __read_mostly = { +static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_ATTR_MAX+1] = { [NL80211_MESHCONF_RETRY_TIMEOUT] = { .type = NLA_U16 }, [NL80211_MESHCONF_CONFIRM_TIMEOUT] = { .type = NLA_U16 }, [NL80211_MESHCONF_HOLDING_TIMEOUT] = { .type = NLA_U16 }, @@ -4470,8 +4467,7 @@ static u32 rateset_to_mask(struct ieee80211_supported_band *sband, return mask; } -static struct nla_policy -nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] __read_mostly = { +static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { [NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY, .len = NL80211_MAX_SUPP_RATES }, }; -- cgit v1.2.3 From 4610ee1d3638fa05ba8e87ccfa971db8e4033ae7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:33:59 -0500 Subject: kprobes: Introduce generic insn_slot framework Make insn_slot framework support various size slots. Current insn_slot just supports one-size instruction buffer slot. However, kprobes jump optimization needs larger size buffers. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133358.6725.82430.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers --- kernel/kprobes.c | 104 ++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 65 insertions(+), 39 deletions(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ccec774c716d..78105623d739 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -105,57 +105,74 @@ static struct kprobe_blackpoint kprobe_blacklist[] = { * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster */ -#define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) - struct kprobe_insn_page { struct list_head list; kprobe_opcode_t *insns; /* Page of instruction slots */ - char slot_used[INSNS_PER_PAGE]; int nused; int ngarbage; + char slot_used[]; +}; + +#define KPROBE_INSN_PAGE_SIZE(slots) \ + (offsetof(struct kprobe_insn_page, slot_used) + \ + (sizeof(char) * (slots))) + +struct kprobe_insn_cache { + struct list_head pages; /* list of kprobe_insn_page */ + size_t insn_size; /* size of instruction slot */ + int nr_garbage; }; +static int slots_per_page(struct kprobe_insn_cache *c) +{ + return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t)); +} + enum kprobe_slot_state { SLOT_CLEAN = 0, SLOT_DIRTY = 1, SLOT_USED = 2, }; -static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_pages */ -static LIST_HEAD(kprobe_insn_pages); -static int kprobe_garbage_slots; -static int collect_garbage_slots(void); +static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_slots */ +static struct kprobe_insn_cache kprobe_insn_slots = { + .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), + .insn_size = MAX_INSN_SIZE, + .nr_garbage = 0, +}; +static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c); /** * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ -static kprobe_opcode_t __kprobes *__get_insn_slot(void) +static kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; retry: - list_for_each_entry(kip, &kprobe_insn_pages, list) { - if (kip->nused < INSNS_PER_PAGE) { + list_for_each_entry(kip, &c->pages, list) { + if (kip->nused < slots_per_page(c)) { int i; - for (i = 0; i < INSNS_PER_PAGE; i++) { + for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; kip->nused++; - return kip->insns + (i * MAX_INSN_SIZE); + return kip->insns + (i * c->insn_size); } } - /* Surprise! No unused slots. Fix kip->nused. */ - kip->nused = INSNS_PER_PAGE; + /* kip->nused is broken. Fix it. */ + kip->nused = slots_per_page(c); + WARN_ON(1); } } /* If there are any garbage slots, collect it and try again. */ - if (kprobe_garbage_slots && collect_garbage_slots() == 0) { + if (c->nr_garbage && collect_garbage_slots(c) == 0) goto retry; - } - /* All out of space. Need to allocate a new page. Use slot 0. */ - kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL); + + /* All out of space. Need to allocate a new page. */ + kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL); if (!kip) return NULL; @@ -170,20 +187,23 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void) return NULL; } INIT_LIST_HEAD(&kip->list); - list_add(&kip->list, &kprobe_insn_pages); - memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE); + memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); kip->slot_used[0] = SLOT_USED; kip->nused = 1; kip->ngarbage = 0; + list_add(&kip->list, &c->pages); return kip->insns; } + kprobe_opcode_t __kprobes *get_insn_slot(void) { - kprobe_opcode_t *ret; + kprobe_opcode_t *ret = NULL; + mutex_lock(&kprobe_insn_mutex); - ret = __get_insn_slot(); + ret = __get_insn_slot(&kprobe_insn_slots); mutex_unlock(&kprobe_insn_mutex); + return ret; } @@ -199,7 +219,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) * so as not to have to set it up again the * next time somebody inserts a probe. */ - if (!list_is_singular(&kprobe_insn_pages)) { + if (!list_is_singular(&kip->list)) { list_del(&kip->list); module_free(NULL, kip->insns); kfree(kip); @@ -209,49 +229,55 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) return 0; } -static int __kprobes collect_garbage_slots(void) +static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip, *next; /* Ensure no-one is interrupted on the garbages */ synchronize_sched(); - list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) { + list_for_each_entry_safe(kip, next, &c->pages, list) { int i; if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ - for (i = 0; i < INSNS_PER_PAGE; i++) { + for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i)) break; } } - kprobe_garbage_slots = 0; + c->nr_garbage = 0; return 0; } -void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) +static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c, + kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; - mutex_lock(&kprobe_insn_mutex); - list_for_each_entry(kip, &kprobe_insn_pages, list) { - if (kip->insns <= slot && - slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) { - int i = (slot - kip->insns) / MAX_INSN_SIZE; + list_for_each_entry(kip, &c->pages, list) { + long idx = ((long)slot - (long)kip->insns) / c->insn_size; + if (idx >= 0 && idx < slots_per_page(c)) { + WARN_ON(kip->slot_used[idx] != SLOT_USED); if (dirty) { - kip->slot_used[i] = SLOT_DIRTY; + kip->slot_used[idx] = SLOT_DIRTY; kip->ngarbage++; + if (++c->nr_garbage > slots_per_page(c)) + collect_garbage_slots(c); } else - collect_one_slot(kip, i); - break; + collect_one_slot(kip, idx); + return; } } + /* Could not free this slot. */ + WARN_ON(1); +} - if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE) - collect_garbage_slots(); - +void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) +{ + mutex_lock(&kprobe_insn_mutex); + __free_insn_slot(&kprobe_insn_slots, slot, dirty); mutex_unlock(&kprobe_insn_mutex); } #endif -- cgit v1.2.3 From afd66255b9a48f5851326ddae50e2203fbf71dc9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:07 -0500 Subject: kprobes: Introduce kprobes jump optimization Introduce kprobes jump optimization arch-independent parts. Kprobes uses breakpoint instruction for interrupting execution flow, on some architectures, it can be replaced by a jump instruction and interruption emulation code. This gains kprobs' performance drastically. To enable this feature, set CONFIG_OPTPROBES=y (default y if the arch supports OPTPROBE). Changes in v9: - Fix a bug to optimize probe when enabling. - Check nearby probes can be optimize/unoptimize when disarming/arming kprobes, instead of registering/unregistering. This will help kprobe-tracer because most of probes on it are usually disabled. Changes in v6: - Cleanup coding style for readability. - Add comments around get/put_online_cpus(). Changes in v5: - Use get_online_cpus()/put_online_cpus() for avoiding text_mutex deadlock. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133407.6725.81992.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- arch/Kconfig | 13 ++ include/linux/kprobes.h | 36 ++++ kernel/kprobes.c | 461 ++++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 459 insertions(+), 51 deletions(-) (limited to 'kernel') diff --git a/arch/Kconfig b/arch/Kconfig index 9d055b4f0585..e0ad3caf16d9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -57,6 +57,17 @@ config KPROBES for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". +config OPTPROBES + bool "Kprobes jump optimization support (EXPERIMENTAL)" + default y + depends on KPROBES + depends on !PREEMPT + depends on HAVE_OPTPROBES + select KALLSYMS_ALL + help + This option will allow kprobes to optimize breakpoint to + a jump for reducing its overhead. + config HAVE_EFFICIENT_UNALIGNED_ACCESS bool help @@ -99,6 +110,8 @@ config HAVE_KPROBES config HAVE_KRETPROBES bool +config HAVE_OPTPROBES + bool # # An arch should select this if it provides all these things: # diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1b672f74a32f..aed1f95c582f 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -122,6 +122,11 @@ struct kprobe { /* Kprobe status flags */ #define KPROBE_FLAG_GONE 1 /* breakpoint has already gone */ #define KPROBE_FLAG_DISABLED 2 /* probe is temporarily disabled */ +#define KPROBE_FLAG_OPTIMIZED 4 /* + * probe is really optimized. + * NOTE: + * this flag is only for optimized_kprobe. + */ /* Has this kprobe gone ? */ static inline int kprobe_gone(struct kprobe *p) @@ -134,6 +139,12 @@ static inline int kprobe_disabled(struct kprobe *p) { return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE); } + +/* Is this kprobe really running optimized path ? */ +static inline int kprobe_optimized(struct kprobe *p) +{ + return p->flags & KPROBE_FLAG_OPTIMIZED; +} /* * Special probe type that uses setjmp-longjmp type tricks to resume * execution at a specified entry with a matching prototype corresponding @@ -249,6 +260,31 @@ extern kprobe_opcode_t *get_insn_slot(void); extern void free_insn_slot(kprobe_opcode_t *slot, int dirty); extern void kprobes_inc_nmissed_count(struct kprobe *p); +#ifdef CONFIG_OPTPROBES +/* + * Internal structure for direct jump optimized probe + */ +struct optimized_kprobe { + struct kprobe kp; + struct list_head list; /* list for optimizing queue */ + struct arch_optimized_insn optinsn; +}; + +/* Architecture dependent functions for direct jump optimization */ +extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); +extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); +extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); +extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); +extern int arch_optimize_kprobe(struct optimized_kprobe *op); +extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); +extern kprobe_opcode_t *get_optinsn_slot(void); +extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); +extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr); + +extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); +#endif /* CONFIG_OPTPROBES */ + /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); void kretprobe_hash_lock(struct task_struct *tsk, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 78105623d739..612af2d61614 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -280,6 +281,33 @@ void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) __free_insn_slot(&kprobe_insn_slots, slot, dirty); mutex_unlock(&kprobe_insn_mutex); } +#ifdef CONFIG_OPTPROBES +/* For optimized_kprobe buffer */ +static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */ +static struct kprobe_insn_cache kprobe_optinsn_slots = { + .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), + /* .insn_size is initialized later */ + .nr_garbage = 0, +}; +/* Get a slot for optimized_kprobe buffer */ +kprobe_opcode_t __kprobes *get_optinsn_slot(void) +{ + kprobe_opcode_t *ret = NULL; + + mutex_lock(&kprobe_optinsn_mutex); + ret = __get_insn_slot(&kprobe_optinsn_slots); + mutex_unlock(&kprobe_optinsn_mutex); + + return ret; +} + +void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty) +{ + mutex_lock(&kprobe_optinsn_mutex); + __free_insn_slot(&kprobe_optinsn_slots, slot, dirty); + mutex_unlock(&kprobe_optinsn_mutex); +} +#endif #endif /* We have preemption disabled.. so it is safe to use __ versions */ @@ -310,23 +338,324 @@ struct kprobe __kprobes *get_kprobe(void *addr) if (p->addr == addr) return p; } + return NULL; } +static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); + +/* Return true if the kprobe is an aggregator */ +static inline int kprobe_aggrprobe(struct kprobe *p) +{ + return p->pre_handler == aggr_pre_handler; +} + +/* + * Keep all fields in the kprobe consistent + */ +static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) +{ + memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t)); + memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn)); +} + +#ifdef CONFIG_OPTPROBES +/* + * Call all pre_handler on the list, but ignores its return value. + * This must be called from arch-dep optimized caller. + */ +void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe *kp; + + list_for_each_entry_rcu(kp, &p->list, list) { + if (kp->pre_handler && likely(!kprobe_disabled(kp))) { + set_kprobe_instance(kp); + kp->pre_handler(kp, regs); + } + reset_kprobe_instance(); + } +} + +/* Return true(!0) if the kprobe is ready for optimization. */ +static inline int kprobe_optready(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if (kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + return arch_prepared_optinsn(&op->optinsn); + } + + return 0; +} + +/* + * Return an optimized kprobe whose optimizing code replaces + * instructions including addr (exclude breakpoint). + */ +struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr) +{ + int i; + struct kprobe *p = NULL; + struct optimized_kprobe *op; + + /* Don't check i == 0, since that is a breakpoint case. */ + for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) + p = get_kprobe((void *)(addr - i)); + + if (p && kprobe_optready(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (arch_within_optimized_kprobe(op, addr)) + return p; + } + + return NULL; +} + +/* Optimization staging list, protected by kprobe_mutex */ +static LIST_HEAD(optimizing_list); + +static void kprobe_optimizer(struct work_struct *work); +static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); +#define OPTIMIZE_DELAY 5 + +/* Kprobe jump optimizer */ +static __kprobes void kprobe_optimizer(struct work_struct *work) +{ + struct optimized_kprobe *op, *tmp; + + /* Lock modules while optimizing kprobes */ + mutex_lock(&module_mutex); + mutex_lock(&kprobe_mutex); + if (kprobes_all_disarmed) + goto end; + + /* + * Wait for quiesence period to ensure all running interrupts + * are done. Because optprobe may modify multiple instructions + * there is a chance that Nth instruction is interrupted. In that + * case, running interrupt can return to 2nd-Nth byte of jump + * instruction. This wait is for avoiding it. + */ + synchronize_sched(); + + /* + * The optimization/unoptimization refers online_cpus via + * stop_machine() and cpu-hotplug modifies online_cpus. + * And same time, text_mutex will be held in cpu-hotplug and here. + * This combination can cause a deadlock (cpu-hotplug try to lock + * text_mutex but stop_machine can not be done because online_cpus + * has been changed) + * To avoid this deadlock, we need to call get_online_cpus() + * for preventing cpu-hotplug outside of text_mutex locking. + */ + get_online_cpus(); + mutex_lock(&text_mutex); + list_for_each_entry_safe(op, tmp, &optimizing_list, list) { + WARN_ON(kprobe_disabled(&op->kp)); + if (arch_optimize_kprobe(op) < 0) + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + list_del_init(&op->list); + } + mutex_unlock(&text_mutex); + put_online_cpus(); +end: + mutex_unlock(&kprobe_mutex); + mutex_unlock(&module_mutex); +} + +/* Optimize kprobe if p is ready to be optimized */ +static __kprobes void optimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + /* Check if the kprobe is disabled or not ready for optimization. */ + if (!kprobe_optready(p) || + (kprobe_disabled(p) || kprobes_all_disarmed)) + return; + + /* Both of break_handler and post_handler are not supported. */ + if (p->break_handler || p->post_handler) + return; + + op = container_of(p, struct optimized_kprobe, kp); + + /* Check there is no other kprobes at the optimized instructions */ + if (arch_check_optimized_kprobe(op) < 0) + return; + + /* Check if it is already optimized. */ + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + return; + + op->kp.flags |= KPROBE_FLAG_OPTIMIZED; + list_add(&op->list, &optimizing_list); + if (!delayed_work_pending(&optimizing_work)) + schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); +} + +/* Unoptimize a kprobe if p is optimized */ +static __kprobes void unoptimize_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) { + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + else + /* Replace jump with break */ + arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } +} + +/* Remove optimized instructions */ +static void __kprobes kill_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + if (!list_empty(&op->list)) { + /* Dequeue from the optimization queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } + /* Don't unoptimize, because the target code will be freed. */ + arch_remove_optimized_kprobe(op); +} + +/* Try to prepare optimized instructions */ +static __kprobes void prepare_optimized_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_prepare_optimized_kprobe(op); +} + +/* Free optimized instructions and optimized_kprobe */ +static __kprobes void free_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = container_of(p, struct optimized_kprobe, kp); + arch_remove_optimized_kprobe(op); + kfree(op); +} + +/* Allocate new optimized_kprobe and try to prepare optimized instructions */ +static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + struct optimized_kprobe *op; + + op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); + if (!op) + return NULL; + + INIT_LIST_HEAD(&op->list); + op->kp.addr = p->addr; + arch_prepare_optimized_kprobe(op); + + return &op->kp; +} + +static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); + +/* + * Prepare an optimized_kprobe and optimize it + * NOTE: p must be a normal registered kprobe + */ +static __kprobes void try_to_optimize_kprobe(struct kprobe *p) +{ + struct kprobe *ap; + struct optimized_kprobe *op; + + ap = alloc_aggr_kprobe(p); + if (!ap) + return; + + op = container_of(ap, struct optimized_kprobe, kp); + if (!arch_prepared_optinsn(&op->optinsn)) { + /* If failed to setup optimizing, fallback to kprobe */ + free_aggr_kprobe(ap); + return; + } + + init_aggr_kprobe(ap, p); + optimize_kprobe(ap); +} + +static void __kprobes __arm_kprobe(struct kprobe *p) +{ + struct kprobe *old_p; + + /* Check collision with other optimized kprobes */ + old_p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(old_p)) + unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */ + + arch_arm_kprobe(p); + optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ +} + +static void __kprobes __disarm_kprobe(struct kprobe *p) +{ + struct kprobe *old_p; + + unoptimize_kprobe(p); /* Try to unoptimize */ + arch_disarm_kprobe(p); + + /* If another kprobe was blocked, optimize it. */ + old_p = get_optimized_kprobe((unsigned long)p->addr); + if (unlikely(old_p)) + optimize_kprobe(old_p); +} + +#else /* !CONFIG_OPTPROBES */ + +#define optimize_kprobe(p) do {} while (0) +#define unoptimize_kprobe(p) do {} while (0) +#define kill_optimized_kprobe(p) do {} while (0) +#define prepare_optimized_kprobe(p) do {} while (0) +#define try_to_optimize_kprobe(p) do {} while (0) +#define __arm_kprobe(p) arch_arm_kprobe(p) +#define __disarm_kprobe(p) arch_disarm_kprobe(p) + +static __kprobes void free_aggr_kprobe(struct kprobe *p) +{ + kfree(p); +} + +static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) +{ + return kzalloc(sizeof(struct kprobe), GFP_KERNEL); +} +#endif /* CONFIG_OPTPROBES */ + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { + /* + * Here, since __arm_kprobe() doesn't use stop_machine(), + * this doesn't cause deadlock on text_mutex. So, we don't + * need get_online_cpus(). + */ mutex_lock(&text_mutex); - arch_arm_kprobe(kp); + __arm_kprobe(kp); mutex_unlock(&text_mutex); } /* Disarm a kprobe with text_mutex */ static void __kprobes disarm_kprobe(struct kprobe *kp) { + get_online_cpus(); /* For avoiding text_mutex deadlock */ mutex_lock(&text_mutex); - arch_disarm_kprobe(kp); + __disarm_kprobe(kp); mutex_unlock(&text_mutex); + put_online_cpus(); } /* @@ -395,7 +724,7 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs) void __kprobes kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; - if (p->pre_handler != aggr_pre_handler) { + if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) @@ -518,15 +847,6 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp) free_rp_inst(rp); } -/* - * Keep all fields in the kprobe consistent - */ -static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) -{ - memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t)); - memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn)); -} - /* * Add the new probe to ap->list. Fail if this is the * second jprobe at the address - two jprobes can't coexist @@ -534,6 +854,10 @@ static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); + + if (p->break_handler || p->post_handler) + unoptimize_kprobe(ap); /* Fall back to normal kprobe */ + if (p->break_handler) { if (ap->break_handler) return -EEXIST; @@ -548,7 +872,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) /* Arm the breakpoint again. */ - arm_kprobe(ap); + __arm_kprobe(ap); } return 0; } @@ -557,12 +881,13 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ -static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) +static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { + /* Copy p's insn slot to ap */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; - ap->flags = p->flags; + ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ @@ -572,8 +897,9 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); - list_add_rcu(&p->list, &ap->list); + INIT_HLIST_NODE(&ap->hlist); + list_add_rcu(&p->list, &ap->list); hlist_replace_rcu(&p->hlist, &ap->hlist); } @@ -587,12 +913,12 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, int ret = 0; struct kprobe *ap = old_p; - if (old_p->pre_handler != aggr_pre_handler) { - /* If old_p is not an aggr_probe, create new aggr_kprobe. */ - ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL); + if (!kprobe_aggrprobe(old_p)) { + /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */ + ap = alloc_aggr_kprobe(old_p); if (!ap) return -ENOMEM; - add_aggr_kprobe(ap, old_p); + init_aggr_kprobe(ap, old_p); } if (kprobe_gone(ap)) { @@ -611,6 +937,9 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, */ return ret; + /* Prepare optimized instructions if possible. */ + prepare_optimized_kprobe(ap); + /* * Clear gone flag to prevent allocating new slot again, and * set disabled flag because it is not armed yet. @@ -619,6 +948,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, | KPROBE_FLAG_DISABLED; } + /* Copy ap's insn slot to p */ copy_kprobe(ap, p); return add_new_kprobe(ap, p); } @@ -769,27 +1099,34 @@ int __kprobes register_kprobe(struct kprobe *p) p->nmissed = 0; INIT_LIST_HEAD(&p->list); mutex_lock(&kprobe_mutex); + + get_online_cpus(); /* For avoiding text_mutex deadlock. */ + mutex_lock(&text_mutex); + old_p = get_kprobe(p->addr); if (old_p) { + /* Since this may unoptimize old_p, locking text_mutex. */ ret = register_aggr_kprobe(old_p, p); goto out; } - mutex_lock(&text_mutex); ret = arch_prepare_kprobe(p); if (ret) - goto out_unlock_text; + goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arch_arm_kprobe(p); + __arm_kprobe(p); + + /* Try to optimize kprobe */ + try_to_optimize_kprobe(p); -out_unlock_text: - mutex_unlock(&text_mutex); out: + mutex_unlock(&text_mutex); + put_online_cpus(); mutex_unlock(&kprobe_mutex); if (probed_mod) @@ -811,7 +1148,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) return -EINVAL; if (old_p == p || - (old_p->pre_handler == aggr_pre_handler && + (kprobe_aggrprobe(old_p) && list_is_singular(&old_p->list))) { /* * Only probe on the hash list. Disarm only if kprobes are @@ -819,7 +1156,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p) * already have been removed. We save on flushing icache. */ if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) - disarm_kprobe(p); + disarm_kprobe(old_p); hlist_del_rcu(&old_p->hlist); } else { if (p->break_handler && !kprobe_gone(p)) @@ -835,8 +1172,13 @@ noclean: list_del_rcu(&p->list); if (!kprobe_disabled(old_p)) { try_to_disable_aggr_kprobe(old_p); - if (!kprobes_all_disarmed && kprobe_disabled(old_p)) - disarm_kprobe(old_p); + if (!kprobes_all_disarmed) { + if (kprobe_disabled(old_p)) + disarm_kprobe(old_p); + else + /* Try to optimize this probe again */ + optimize_kprobe(old_p); + } } } return 0; @@ -853,7 +1195,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) old_p = list_entry(p->list.next, struct kprobe, list); list_del(&p->list); arch_remove_kprobe(old_p); - kfree(old_p); + free_aggr_kprobe(old_p); } } @@ -1149,7 +1491,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) struct kprobe *kp; p->flags |= KPROBE_FLAG_GONE; - if (p->pre_handler == aggr_pre_handler) { + if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. @@ -1158,6 +1500,7 @@ static void __kprobes kill_kprobe(struct kprobe *p) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; p->break_handler = NULL; + kill_optimized_kprobe(p); } /* * Here, we can remove insn_slot safely, because no thread calls @@ -1267,6 +1610,11 @@ static int __init init_kprobes(void) } } +#if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) + /* Init kprobe_optinsn_slots */ + kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; +#endif + /* By default, kprobes are armed */ kprobes_all_disarmed = false; @@ -1285,7 +1633,7 @@ static int __init init_kprobes(void) #ifdef CONFIG_DEBUG_FS static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, - const char *sym, int offset,char *modname) + const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; @@ -1295,19 +1643,21 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, kprobe_type = "j"; else kprobe_type = "k"; + if (sym) - seq_printf(pi, "%p %s %s+0x%x %s %s%s\n", + seq_printf(pi, "%p %s %s+0x%x %s ", p->addr, kprobe_type, sym, offset, - (modname ? modname : " "), - (kprobe_gone(p) ? "[GONE]" : ""), - ((kprobe_disabled(p) && !kprobe_gone(p)) ? - "[DISABLED]" : "")); + (modname ? modname : " ")); else - seq_printf(pi, "%p %s %p %s%s\n", - p->addr, kprobe_type, p->addr, - (kprobe_gone(p) ? "[GONE]" : ""), - ((kprobe_disabled(p) && !kprobe_gone(p)) ? - "[DISABLED]" : "")); + seq_printf(pi, "%p %s %p ", + p->addr, kprobe_type, p->addr); + + if (!pp) + pp = p; + seq_printf(pi, "%s%s%s\n", + (kprobe_gone(p) ? "[GONE]" : ""), + ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), + (kprobe_optimized(pp) ? "[OPTIMIZED]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -1343,11 +1693,11 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) hlist_for_each_entry_rcu(p, node, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); - if (p->pre_handler == aggr_pre_handler) { + if (kprobe_aggrprobe(p)) { list_for_each_entry_rcu(kp, &p->list, list) - report_probe(pi, kp, sym, offset, modname); + report_probe(pi, kp, sym, offset, modname, p); } else - report_probe(pi, p, sym, offset, modname); + report_probe(pi, p, sym, offset, modname, NULL); } preempt_enable(); return 0; @@ -1425,12 +1775,13 @@ int __kprobes enable_kprobe(struct kprobe *kp) goto out; } - if (!kprobes_all_disarmed && kprobe_disabled(p)) - arm_kprobe(p); - - p->flags &= ~KPROBE_FLAG_DISABLED; if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; + + if (!kprobes_all_disarmed && kprobe_disabled(p)) { + p->flags &= ~KPROBE_FLAG_DISABLED; + arm_kprobe(p); + } out: mutex_unlock(&kprobe_mutex); return ret; @@ -1450,12 +1801,13 @@ static void __kprobes arm_all_kprobes(void) if (!kprobes_all_disarmed) goto already_enabled; + /* Arming kprobes doesn't optimize kprobe itself */ mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_disabled(p)) - arch_arm_kprobe(p); + __arm_kprobe(p); } mutex_unlock(&text_mutex); @@ -1482,16 +1834,23 @@ static void __kprobes disarm_all_kprobes(void) kprobes_all_disarmed = true; printk(KERN_INFO "Kprobes globally disabled\n"); + + /* + * Here we call get_online_cpus() for avoiding text_mutex deadlock, + * because disarming may also unoptimize kprobes. + */ + get_online_cpus(); mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - arch_disarm_kprobe(p); + __disarm_kprobe(p); } } mutex_unlock(&text_mutex); + put_online_cpus(); mutex_unlock(&kprobe_mutex); /* Allow all currently running kprobes to complete */ synchronize_sched(); -- cgit v1.2.3 From b2be84df99ebc93599c69e931a3c4a5105abfabc Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 25 Feb 2010 08:34:15 -0500 Subject: kprobes: Jump optimization sysctl interface Add /proc/sys/debug/kprobes-optimization sysctl which enables and disables kprobes jump optimization on the fly for debugging. Changes in v7: - Remove ctl_name = CTL_UNNUMBERED for upstream compatibility. Changes in v6: - Update comments and coding style. Signed-off-by: Masami Hiramatsu Cc: systemtap Cc: DLE Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Srikar Dronamraju Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Anders Kaseorg Cc: Tim Abbott Cc: Andi Kleen Cc: Jason Baron Cc: Mathieu Desnoyers Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli LKML-Reference: <20100225133415.6725.8274.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 8 +++++ kernel/kprobes.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++-- kernel/sysctl.c | 12 +++++++ 3 files changed, 105 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index aed1f95c582f..e7d1b2e0070d 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -283,6 +283,14 @@ extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr); extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); + +#ifdef CONFIG_SYSCTL +extern int sysctl_kprobes_optimization; +extern int proc_kprobes_optimization_handler(struct ctl_table *table, + int write, void __user *buffer, + size_t *length, loff_t *ppos); +#endif + #endif /* CONFIG_OPTPROBES */ /* Get the kprobe at this addr (if any) - called with preemption disabled */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 612af2d61614..fa034d29cf73 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -360,6 +361,9 @@ static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p) } #ifdef CONFIG_OPTPROBES +/* NOTE: change this value only with kprobe_mutex held */ +static bool kprobes_allow_optimization; + /* * Call all pre_handler on the list, but ignores its return value. * This must be called from arch-dep optimized caller. @@ -428,7 +432,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); mutex_lock(&kprobe_mutex); - if (kprobes_all_disarmed) + if (kprobes_all_disarmed || !kprobes_allow_optimization) goto end; /* @@ -471,7 +475,7 @@ static __kprobes void optimize_kprobe(struct kprobe *p) struct optimized_kprobe *op; /* Check if the kprobe is disabled or not ready for optimization. */ - if (!kprobe_optready(p) || + if (!kprobe_optready(p) || !kprobes_allow_optimization || (kprobe_disabled(p) || kprobes_all_disarmed)) return; @@ -588,6 +592,80 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p) optimize_kprobe(ap); } +#ifdef CONFIG_SYSCTL +static void __kprobes optimize_all_kprobes(void) +{ + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + /* If optimization is already allowed, just return */ + if (kprobes_allow_optimization) + return; + + kprobes_allow_optimization = true; + mutex_lock(&text_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) + if (!kprobe_disabled(p)) + optimize_kprobe(p); + } + mutex_unlock(&text_mutex); + printk(KERN_INFO "Kprobes globally optimized\n"); +} + +static void __kprobes unoptimize_all_kprobes(void) +{ + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + /* If optimization is already prohibited, just return */ + if (!kprobes_allow_optimization) + return; + + kprobes_allow_optimization = false; + printk(KERN_INFO "Kprobes globally unoptimized\n"); + get_online_cpus(); /* For avoiding text_mutex deadlock */ + mutex_lock(&text_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) { + if (!kprobe_disabled(p)) + unoptimize_kprobe(p); + } + } + + mutex_unlock(&text_mutex); + put_online_cpus(); + /* Allow all currently running kprobes to complete */ + synchronize_sched(); +} + +int sysctl_kprobes_optimization; +int proc_kprobes_optimization_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, + loff_t *ppos) +{ + int ret; + + mutex_lock(&kprobe_mutex); + sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + + if (sysctl_kprobes_optimization) + optimize_all_kprobes(); + else + unoptimize_all_kprobes(); + mutex_unlock(&kprobe_mutex); + + return ret; +} +#endif /* CONFIG_SYSCTL */ + static void __kprobes __arm_kprobe(struct kprobe *p) { struct kprobe *old_p; @@ -1610,10 +1688,14 @@ static int __init init_kprobes(void) } } -#if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) +#if defined(CONFIG_OPTPROBES) +#if defined(__ARCH_WANT_KPROBES_INSN_SLOT) /* Init kprobe_optinsn_slots */ kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; #endif + /* By default, kprobes can be optimized */ + kprobes_allow_optimization = true; +#endif /* By default, kprobes are armed */ kprobes_all_disarmed = false; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8a68b2448468..40d791d616b5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -1449,6 +1450,17 @@ static struct ctl_table debug_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#endif +#if defined(CONFIG_OPTPROBES) + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = &zero, + .extra2 = &one, + }, #endif { } }; -- cgit v1.2.3 From fb90ef93df654f2678933efbbf864adac0ae490e Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 24 Feb 2010 18:36:53 -0800 Subject: early_res: Add free_early_partial() To free partial areas in pcpu_setup... Reported-by: Peter Zijlstra Signed-off-by: Yinghai Lu Cc: Tejun Heo Cc: Christoph Lameter Cc: Stephen Rothwell Cc: Linus Torvalds Cc: Jesse Barnes Cc: Pekka Enberg LKML-Reference: <4B85E245.5030001@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/setup_percpu.c | 6 +++++ include/linux/early_res.h | 1 + kernel/early_res.c | 55 ++++++++++++++++++++++++++++++++++++++++++ mm/percpu.c | 3 --- 4 files changed, 62 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 35abcb8b00e9..ef6370b00e70 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -137,7 +137,13 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { +#ifdef CONFIG_NO_BOOTMEM + u64 start = __pa(ptr); + u64 end = start + size; + free_early_partial(start, end); +#else free_bootmem(__pa(ptr), size); +#endif } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/include/linux/early_res.h b/include/linux/early_res.h index 50f7663bb8b1..29c09f57a13c 100644 --- a/include/linux/early_res.h +++ b/include/linux/early_res.h @@ -5,6 +5,7 @@ extern void reserve_early(u64 start, u64 end, char *name); extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); extern void free_early(u64 start, u64 end); +void free_early_partial(u64 start, u64 end); extern void early_res_to_bootmem(u64 start, u64 end); void reserve_early_without_check(u64 start, u64 end, char *name); diff --git a/kernel/early_res.c b/kernel/early_res.c index aa5494ac4462..9ab11cd84853 100644 --- a/kernel/early_res.c +++ b/kernel/early_res.c @@ -61,6 +61,40 @@ static void __init drop_range(int i) early_res_count--; } +static void __init drop_range_partial(int i, u64 start, u64 end) +{ + u64 common_start, common_end; + u64 old_start, old_end; + + old_start = early_res[i].start; + old_end = early_res[i].end; + common_start = max(old_start, start); + common_end = min(old_end, end); + + /* no overlap ? */ + if (common_start >= common_end) + return; + + if (old_start < common_start) { + /* make head segment */ + early_res[i].end = common_start; + if (old_end > common_end) { + /* add another for left over on tail */ + reserve_early_without_check(common_end, old_end, + early_res[i].name); + } + return; + } else { + if (old_end > common_end) { + /* reuse the entry for tail left */ + early_res[i].start = common_end; + return; + } + /* all covered */ + drop_range(i); + } +} + /* * Split any existing ranges that: * 1) are marked 'overlap_ok', and @@ -284,6 +318,27 @@ void __init free_early(u64 start, u64 end) drop_range(i); } +void __init free_early_partial(u64 start, u64 end) +{ + struct early_res *r; + int i; + +try_next: + i = find_overlapped_early(start, end); + if (i >= max_early_res) + return; + + r = &early_res[i]; + /* hole ? */ + if (r->end >= end && r->start <= start) { + drop_range_partial(i, start, end); + return; + } + + drop_range_partial(i, start, end); + goto try_next; +} + #ifdef CONFIG_NO_BOOTMEM static void __init subtract_early_res(struct range *range, int az) { diff --git a/mm/percpu.c b/mm/percpu.c index 841defeeef86..083e7c91e5f6 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1929,10 +1929,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size, } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); -#ifndef CONFIG_NO_BOOTMEM - /* fix partial free ! */ free_fn(ptr + size_sum, ai->unit_size - size_sum); -#endif } } -- cgit v1.2.3 From 44ee63587dce85593c22497140db16f4e5027860 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 17 Feb 2010 10:50:50 +0900 Subject: percpu: Add __percpu sparse annotations to hw_breakpoint Add __percpu sparse annotations to hw_breakpoint. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. In kernel/hw_breakpoint.c, per_cpu(nr_task_bp_pinned, cpu)'s will trigger spurious noderef related warnings from sparse. Changing it to &per_cpu(nr_task_bp_pinned[0], cpu) will work around the problem but deemed to ugly by the maintainer. Leave it alone until better solution can be found. Signed-off-by: Tejun Heo Cc: Stephen Rothwell Cc: K.Prasad LKML-Reference: <4B7B4B7A.9050902@kernel.org> Signed-off-by: Frederic Weisbecker --- include/linux/hw_breakpoint.h | 8 ++++---- kernel/hw_breakpoint.c | 10 +++++----- samples/hw_breakpoint/data_breakpoint.c | 6 +++--- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 5977b724f7c6..c70d27af03f9 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -66,14 +66,14 @@ register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, int cpu); -extern struct perf_event ** +extern struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered); extern int register_perf_hw_breakpoint(struct perf_event *bp); extern int __register_perf_hw_breakpoint(struct perf_event *bp); extern void unregister_hw_breakpoint(struct perf_event *bp); -extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events); +extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events); extern int dbg_reserve_bp_slot(struct perf_event *bp); extern int dbg_release_bp_slot(struct perf_event *bp); @@ -100,7 +100,7 @@ static inline struct perf_event * register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, int cpu) { return NULL; } -static inline struct perf_event ** +static inline struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered) { return NULL; } static inline int @@ -109,7 +109,7 @@ static inline int __register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } static inline void unregister_hw_breakpoint(struct perf_event *bp) { } static inline void -unregister_wide_hw_breakpoint(struct perf_event **cpu_events) { } +unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { } static inline int reserve_bp_slot(struct perf_event *bp) {return -ENOSYS; } static inline void release_bp_slot(struct perf_event *bp) { } diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index 967e66143e11..6542eacb3fa5 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -413,17 +413,17 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); * * @return a set of per_cpu pointers to perf events */ -struct perf_event ** +struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered) { - struct perf_event **cpu_events, **pevent, *bp; + struct perf_event * __percpu *cpu_events, **pevent, *bp; long err; int cpu; cpu_events = alloc_percpu(typeof(*cpu_events)); if (!cpu_events) - return ERR_PTR(-ENOMEM); + return (void __percpu __force *)ERR_PTR(-ENOMEM); get_online_cpus(); for_each_online_cpu(cpu) { @@ -451,7 +451,7 @@ fail: put_online_cpus(); free_percpu(cpu_events); - return ERR_PTR(err); + return (void __percpu __force *)ERR_PTR(err); } EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); @@ -459,7 +459,7 @@ EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel * @cpu_events: the per cpu set of events to unregister */ -void unregister_wide_hw_breakpoint(struct perf_event **cpu_events) +void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { int cpu; struct perf_event **pevent; diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c index c69cbe9b2426..bd0f337afcab 100644 --- a/samples/hw_breakpoint/data_breakpoint.c +++ b/samples/hw_breakpoint/data_breakpoint.c @@ -34,7 +34,7 @@ #include #include -struct perf_event **sample_hbp; +struct perf_event * __percpu *sample_hbp; static char ksym_name[KSYM_NAME_LEN] = "pid_max"; module_param_string(ksym, ksym_name, KSYM_NAME_LEN, S_IRUGO); @@ -61,8 +61,8 @@ static int __init hw_break_module_init(void) attr.bp_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; sample_hbp = register_wide_hw_breakpoint(&attr, sample_hbp_handler); - if (IS_ERR(sample_hbp)) { - ret = PTR_ERR(sample_hbp); + if (IS_ERR((void __force *)sample_hbp)) { + ret = PTR_ERR((void __force *)sample_hbp); goto fail; } -- cgit v1.2.3 From 622ea685f1fafdf84d612440535c84341f0860b8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 27 Feb 2010 14:53:07 -0800 Subject: rcu: Fix holdoff for accelerated GPs for last non-dynticked CPU Make the holdoff only happen when the full number of attempts have been made. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1267311188-16603-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 464ad2cdee00..79b53bda8943 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1010,6 +1010,10 @@ int rcu_needs_cpu(int cpu) int c = 0; int thatcpu; + /* Check for being in the holdoff period. */ + if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) + return rcu_needs_cpu_quick_check(cpu); + /* Don't bother unless we are the last non-dyntick-idle CPU. */ for_each_cpu_not(thatcpu, nohz_cpu_mask) if (thatcpu != cpu) { @@ -1041,10 +1045,8 @@ int rcu_needs_cpu(int cpu) } /* If RCU callbacks are still pending, RCU still needs this CPU. */ - if (c) { + if (c) raise_softirq(RCU_SOFTIRQ); - per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; - } return c; } -- cgit v1.2.3 From ae1f30384baef4056438d81b305a6a5199b0d16c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 28 Feb 2010 19:42:38 +0100 Subject: tracing: Include irqflags headers from trace clock trace_clock.c includes spinlock.h, which ends up including asm/system.h, which in turn includes linux/irqflags.h in x86. So the definition of raw_local_irq_save is luckily covered there, but this is not the case in parisc: tip/kernel/trace/trace_clock.c:86: error: implicit declaration of function 'raw_local_irq_save' tip/kernel/trace/trace_clock.c:112: error: implicit declaration of function 'raw_local_irq_restore' We need to include linux/irqflags.h directly from trace_clock.c to avoid such build error. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Robert Richter Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/trace/trace_clock.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 84a3a7ba072a..6fbfb8f417b9 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -13,6 +13,7 @@ * Tracer plugins will chose a default from these clocks. */ #include +#include #include #include #include -- cgit v1.2.3 From 1e259e0a9982078896f3404240096cbea01daca4 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 28 Feb 2010 20:51:15 +0100 Subject: hw-breakpoints: Remove stub unthrottle callback We support event unthrottling in breakpoint events. It means that if we have more than sysctl_perf_event_sample_rate/HZ, perf will throttle, ignoring subsequent events until the next tick. So if ptrace exceeds this max rate, it will omit events, which breaks the ptrace determinism that is supposed to report every triggered breakpoints. This is likely to happen if we set sysctl_perf_event_sample_rate to 1. This patch removes support for unthrottling in breakpoint events to break throttling and restore ptrace determinism. Signed-off-by: Frederic Weisbecker Cc: 2.6.33.x Cc: Peter Zijlstra Cc: K.Prasad Cc: Paul Mackerras --- arch/x86/kernel/hw_breakpoint.c | 5 ----- kernel/hw_breakpoint.c | 1 - 2 files changed, 6 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index bb6006e3e295..1e8ceadc0d6a 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -531,8 +531,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp) { /* TODO */ } - -void hw_breakpoint_pmu_unthrottle(struct perf_event *bp) -{ - /* TODO */ -} diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index 967e66143e11..4d99512ee149 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -489,5 +489,4 @@ struct pmu perf_ops_bp = { .enable = arch_install_hw_breakpoint, .disable = arch_uninstall_hw_breakpoint, .read = hw_breakpoint_pmu_read, - .unthrottle = hw_breakpoint_pmu_unthrottle }; -- cgit v1.2.3 From 4b17764737bb4ee3364b8bfa2059f51ebc19ccd6 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 1 Mar 2010 00:02:23 -0800 Subject: sparc: Support show_unhandled_signals. Just faults right now, will add other traps later. Signed-off-by: David S. Miller --- arch/sparc/mm/fault_32.c | 106 +++++++++++++++++++++++++++-------------------- arch/sparc/mm/fault_64.c | 34 +++++++++++++-- kernel/sysctl.c | 2 +- 3 files changed, 92 insertions(+), 50 deletions(-) (limited to 'kernel') diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index a3413acb8f12..ec8f22c681ef 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -35,6 +35,8 @@ extern int prom_node_root; +int show_unhandled_signals = 1; + /* At boot time we determine these two values necessary for setting * up the segment maps and page table entries (pte's). */ @@ -149,6 +151,45 @@ asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc, return 0; } +static inline void +show_signal_msg(struct pt_regs *regs, int sig, int code, + unsigned long address, struct task_struct *tsk) +{ + if (!unhandled_signal(tsk, sig)) + return; + + if (!printk_ratelimit()) + return; + + printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, + tsk->comm, task_pid_nr(tsk), address, + (void *)regs->pc, (void *)regs->u_regs[UREG_I7], + (void *)regs->u_regs[UREG_FP], code); + + print_vma_addr(KERN_CONT " in ", regs->pc); + + printk(KERN_CONT "\n"); +} + +static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs, + unsigned long addr) +{ + siginfo_t info; + + info.si_signo = sig; + info.si_code = code; + info.si_errno = 0; + info.si_addr = (void __user *) addr; + info.si_trapno = 0; + + if (unlikely(show_unhandled_signals)) + show_signal_msg(regs, sig, info.si_code, + addr, current); + + force_sig_info (sig, &info, current); +} + extern unsigned long safe_compute_effective_address(struct pt_regs *, unsigned int); @@ -168,6 +209,14 @@ static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault) return safe_compute_effective_address(regs, insn); } +static noinline void do_fault_siginfo(int code, int sig, struct pt_regs *regs, + int text_fault) +{ + unsigned long addr = compute_si_addr(regs, text_fault); + + __do_fault_siginfo(code, sig, regs, addr); +} + asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, unsigned long address) { @@ -176,9 +225,8 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, struct mm_struct *mm = tsk->mm; unsigned int fixup; unsigned long g2; - siginfo_t info; int from_user = !(regs->psr & PSR_PS); - int fault; + int fault, code; if(text_fault) address = regs->pc; @@ -195,7 +243,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (!ARCH_SUN4C && address >= TASK_SIZE) goto vmalloc_fault; - info.si_code = SEGV_MAPERR; + code = SEGV_MAPERR; /* * If we're in an interrupt or have no user @@ -229,7 +277,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, * we can handle it.. */ good_area: - info.si_code = SEGV_ACCERR; + code = SEGV_ACCERR; if(write) { if(!(vma->vm_flags & VM_WRITE)) goto bad_area; @@ -273,18 +321,8 @@ bad_area: bad_area_nosemaphore: /* User mode accesses just cause a SIGSEGV */ - if(from_user) { -#if 0 - printk("Fault whee %s [%d]: segfaults at %08lx pc=%08lx\n", - tsk->comm, tsk->pid, address, regs->pc); -#endif - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* info.si_code set above to make clear whether - this was a SEGV_MAPERR or SEGV_ACCERR fault. */ - info.si_addr = (void __user *)compute_si_addr(regs, text_fault); - info.si_trapno = 0; - force_sig_info (SIGSEGV, &info, tsk); + if (from_user) { + do_fault_siginfo(code, SIGSEGV, regs, text_fault); return; } @@ -335,12 +373,7 @@ out_of_memory: do_sigbus: up_read(&mm->mmap_sem); - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void __user *) compute_si_addr(regs, text_fault); - info.si_trapno = 0; - force_sig_info (SIGBUS, &info, tsk); + do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, text_fault); if (!from_user) goto no_context; @@ -466,14 +499,10 @@ static void force_user_fault(unsigned long address, int write) struct vm_area_struct *vma; struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; - siginfo_t info; + int code; - info.si_code = SEGV_MAPERR; + code = SEGV_MAPERR; -#if 0 - printk("wf\n", - tsk->pid, write, address); -#endif down_read(&mm->mmap_sem); vma = find_vma(mm, address); if(!vma) @@ -485,7 +514,7 @@ static void force_user_fault(unsigned long address, int write) if(expand_stack(vma, address)) goto bad_area; good_area: - info.si_code = SEGV_ACCERR; + code = SEGV_ACCERR; if(write) { if(!(vma->vm_flags & VM_WRITE)) goto bad_area; @@ -502,27 +531,12 @@ good_area: return; bad_area: up_read(&mm->mmap_sem); -#if 0 - printk("Window whee %s [%d]: segfaults at %08lx\n", - tsk->comm, tsk->pid, address); -#endif - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* info.si_code set above to make clear whether - this was a SEGV_MAPERR or SEGV_ACCERR fault. */ - info.si_addr = (void __user *) address; - info.si_trapno = 0; - force_sig_info (SIGSEGV, &info, tsk); + __do_fault_siginfo(code, SIGSEGV, tsk->thread.kregs, address); return; do_sigbus: up_read(&mm->mmap_sem); - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void __user *) address; - info.si_trapno = 0; - force_sig_info (SIGBUS, &info, tsk); + __do_fault_siginfo(BUS_ADRERR, SIGBUS, tsk->thread.kregs, address); } void window_overflow_fault(void) diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index b9d4ff02b8fc..f92ce56a8b22 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -32,6 +32,8 @@ #include #include +int show_unhandled_signals = 1; + static inline __kprobes int notify_page_fault(struct pt_regs *regs) { int ret = 0; @@ -128,22 +130,48 @@ outret: return insn; } +static inline void +show_signal_msg(struct pt_regs *regs, int sig, int code, + unsigned long address, struct task_struct *tsk) +{ + if (!unhandled_signal(tsk, sig)) + return; + + if (!printk_ratelimit()) + return; + + printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, + tsk->comm, task_pid_nr(tsk), address, + (void *)regs->tpc, (void *)regs->u_regs[UREG_I7], + (void *)regs->u_regs[UREG_FP], code); + + print_vma_addr(KERN_CONT " in ", regs->tpc); + + printk(KERN_CONT "\n"); +} + extern unsigned long compute_effective_address(struct pt_regs *, unsigned int, unsigned int); static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, unsigned int insn, int fault_code) { + unsigned long addr; siginfo_t info; info.si_code = code; info.si_signo = sig; info.si_errno = 0; if (fault_code & FAULT_CODE_ITLB) - info.si_addr = (void __user *) regs->tpc; + addr = regs->tpc; else - info.si_addr = (void __user *) - compute_effective_address(regs, insn, 0); + addr = compute_effective_address(regs, insn, 0); + info.si_addr = (void __user *) addr; info.si_trapno = 0; + + if (unlikely(show_unhandled_signals)) + show_signal_msg(regs, sig, code, addr, current); + force_sig_info(sig, &info, current); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8a68b2448468..33e7a38b6eb9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1441,7 +1441,7 @@ static struct ctl_table fs_table[] = { }; static struct ctl_table debug_table[] = { -#if defined(CONFIG_X86) || defined(CONFIG_PPC) +#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) { .procname = "exception-trace", .data = &show_unhandled_signals, -- cgit v1.2.3 From 90a6501f94aedd7fb40f5556334843194fb598be Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 28 Feb 2010 08:32:18 -0800 Subject: sched, rcu: Fix rcu_dereference() for RCU-lockdep Make rcu_dereference() of runqueue data structures be rcu_dereference_sched(). Located-by: Ingo Molnar Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <20100228163218.GD6846@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 3e1fd96c6cf9..5a5ea2cd924f 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -3476,7 +3476,7 @@ static void run_rebalance_domains(struct softirq_action *h) static inline int on_null_domain(int cpu) { - return !rcu_dereference(cpu_rq(cpu)->sd); + return !rcu_dereference_sched(cpu_rq(cpu)->sd); } /* -- cgit v1.2.3 From 37b99dd5372cff42f83210c280f314f10f99138e Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Mon, 1 Mar 2010 21:55:51 +0800 Subject: resource: Fix generic page_is_ram() for partial RAM pages The System RAM walk shall skip partial RAM pages and avoid calling func() on them. So that page_is_ram() return 0 for a partial RAM page. In particular, it shall not call func() with len=0. This fixes a boot time bug reported by Sachin and root caused by Thomas: > >>> WARNING: at arch/x86/mm/ioremap.c:111 __ioremap_caller+0x169/0x2f1() > >>> Hardware name: BladeCenter LS21 -[79716AA]- > >>> Modules linked in: > >>> Pid: 0, comm: swapper Not tainted 2.6.33-git6-autotest #1 > >>> Call Trace: > >>> [] ? __ioremap_caller+0x169/0x2f1 > >>> [] warn_slowpath_common+0x77/0xa4 > >>> [] warn_slowpath_null+0xf/0x11 > >>> [] __ioremap_caller+0x169/0x2f1 > >>> [] ? acpi_os_map_memory+0x12/0x1b > >>> [] ioremap_nocache+0x12/0x14 > >>> [] acpi_os_map_memory+0x12/0x1b > >>> [] acpi_tb_verify_table+0x29/0x5b > >>> [] acpi_load_tables+0x39/0x15a > >>> [] acpi_early_init+0x60/0xf5 > >>> [] start_kernel+0x397/0x3a7 > >>> [] x86_64_start_reservations+0xa5/0xa9 > >>> [] x86_64_start_kernel+0xe1/0xe8 > >>> ---[ end trace 4eaa2a86a8e2da22 ]--- > >>> ioremap reserve_memtype failed -22 The return code is -EINVAL, so it failed in the is_ram check, which is not too surprising > BIOS-provided physical RAM map: > BIOS-e820: 0000000000000000 - 000000000009c000 (usable) > BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved) > BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) > BIOS-e820: 0000000000100000 - 00000000cffa3900 (usable) > BIOS-e820: 00000000cffa3900 - 00000000cffa7400 (ACPI data) The ACPI data is not starting on a page boundary and neither does the usable RAM area end on a page boundary. Very useful ! > ACPI: DSDT 00000000cffa3900 036CE (v01 IBM SERLEWIS 00001000 INTL 20060912) ACPI is trying to map DSDT at cffa3900, which results in a check vs. cffa3000 which is the relevant page boundary. The generic is_ram check correctly identifies that as RAM because it's in the usable resource area. The old e820 based is_ram check does not take overlapping resource areas into account. That's why it works. CC: Sachin Sant CC: Thomas Gleixner CC: KAMEZAWA Hiroyuki Signed-off-by: Wu Fengguang LKML-Reference: <20100301135551.GA9998@localhost> Signed-off-by: H. Peter Anvin --- kernel/resource.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 03c897f7935e..8f0e3d0f4bff 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -274,7 +274,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) { struct resource res; - unsigned long pfn, len; + unsigned long pfn, end_pfn; u64 orig_end; int ret = -1; @@ -284,9 +284,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, orig_end = res.end; while ((res.start < res.end) && (find_next_system_ram(&res, "System RAM") >= 0)) { - pfn = (unsigned long)(res.start >> PAGE_SHIFT); - len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT); - ret = (*func)(pfn, len, arg); + pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; + end_pfn = (res.end + 1) >> PAGE_SHIFT; + if (end_pfn > pfn) + ret = (*func)(pfn, end_pfn - pfn, arg); if (ret) break; res.start = res.end + 1; -- cgit v1.2.3 From dce46a04d55d6358d2d4ab44a4946a19f9425fe2 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 1 Mar 2010 18:48:52 -0800 Subject: early_res: Need to save the allocation name in drop_range_partial() During free_early_partial(), reserve_early_without_check() could end extending the early_res area from __check_and_double_early_res(); as a result, the location of the name for the current reservation could change. Therefore, we need to save a local copy of the name. [ hpa: rewrote comment and checkin description ] Signed-off-by: Yinghai Lu LKML-Reference: <4B8C7C94.7070000@kernel.org> Signed-off-by: H. Peter Anvin --- kernel/early_res.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/early_res.c b/kernel/early_res.c index 9ab11cd84853..3cb2c661bb78 100644 --- a/kernel/early_res.c +++ b/kernel/early_res.c @@ -79,9 +79,19 @@ static void __init drop_range_partial(int i, u64 start, u64 end) /* make head segment */ early_res[i].end = common_start; if (old_end > common_end) { + char name[15]; + + /* + * Save a local copy of the name, since the + * early_res array could get resized inside + * reserve_early_without_check() -> + * __check_and_double_early_res(), which would + * make the current name pointer invalid. + */ + strncpy(name, early_res[i].name, + sizeof(early_res[i].name) - 1); /* add another for left over on tail */ - reserve_early_without_check(common_end, old_end, - early_res[i].name); + reserve_early_without_check(common_end, old_end, name); } return; } else { -- cgit v1.2.3 From ad6759fbf35d104dbf573cd6f4c6784ad6823f7e Mon Sep 17 00:00:00 2001 From: john stultz Date: Mon, 1 Mar 2010 12:34:43 -0800 Subject: timekeeping: Prevent oops when GENERIC_TIME=n Aaro Koskinen reported an issue in kernel.org bugzilla #15366, where on non-GENERIC_TIME systems, accessing /sys/devices/system/clocksource/clocksource0/current_clocksource results in an oops. It seems the timekeeper/clocksource rework missed initializing the curr_clocksource value in the !GENERIC_TIME case. Thanks to Aaro for reporting and diagnosing the issue as well as testing the fix! Reported-by: Aaro Koskinen Signed-off-by: John Stultz Cc: Martin Schwidefsky Cc: stable@kernel.org LKML-Reference: <1267475683.4216.61.camel@localhost.localdomain> Signed-off-by: Thomas Gleixner --- kernel/time/clocksource.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1f663d23e85e..1f5dde637457 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -592,6 +592,10 @@ static inline void clocksource_select(void) { } */ static int __init clocksource_done_booting(void) { + mutex_lock(&clocksource_mutex); + curr_clocksource = clocksource_default_clock(); + mutex_unlock(&clocksource_mutex); + finished_booting = 1; /* -- cgit v1.2.3 From 320ebf09cbb6d01954c9a060266aa8e0d27f4638 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 2 Mar 2010 12:35:37 +0100 Subject: perf, x86: Restrict the ANY flag The ANY flag can show SMT data of another task (like 'top'), so we want to disable it when system-wide profiling is disabled. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 3 +++ include/linux/perf_event.h | 15 +++++++++++++++ kernel/perf_event.c | 15 --------------- 3 files changed, 18 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 6531b4bdb22d..aab2e1ce9dee 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -503,6 +503,9 @@ static int __hw_perf_event_init(struct perf_event *event) */ if (attr->type == PERF_TYPE_RAW) { hwc->config |= x86_pmu.raw_event(attr->config); + if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) && + perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return -EACCES; return 0; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 04f06b4be297..90e0521b1690 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -857,6 +857,21 @@ extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; +static inline bool perf_paranoid_tracepoint_raw(void) +{ + return sysctl_perf_event_paranoid > -1; +} + +static inline bool perf_paranoid_cpu(void) +{ + return sysctl_perf_event_paranoid > 0; +} + +static inline bool perf_paranoid_kernel(void) +{ + return sysctl_perf_event_paranoid > 1; +} + extern void perf_event_init(void); extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size); extern void perf_bp_event(struct perf_event *event, void *data); diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a661e7991865..482d5e1d3764 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -56,21 +56,6 @@ static atomic_t nr_task_events __read_mostly; */ int sysctl_perf_event_paranoid __read_mostly = 1; -static inline bool perf_paranoid_tracepoint_raw(void) -{ - return sysctl_perf_event_paranoid > -1; -} - -static inline bool perf_paranoid_cpu(void) -{ - return sysctl_perf_event_paranoid > 0; -} - -static inline bool perf_paranoid_kernel(void) -{ - return sysctl_perf_event_paranoid > 1; -} - int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */ /* -- cgit v1.2.3 From f41496607e03ab99f263b8e26689ad0fc853007f Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 2 Mar 2010 11:21:09 -0800 Subject: resource: Fix broken indentation Fix broken indentation in patch 37b99dd5372cff42f83210c280f314f10f99138e. Reported-by: Linus Torvalds Cc: Wu Fengguang LKML-Reference: <20100301135551.GA9998@localhost> Signed-off-by: H. Peter Anvin --- kernel/resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 8f0e3d0f4bff..91f430fd467e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -287,7 +287,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; end_pfn = (res.end + 1) >> PAGE_SHIFT; if (end_pfn > pfn) - ret = (*func)(pfn, end_pfn - pfn, arg); + ret = (*func)(pfn, end_pfn - pfn, arg); if (ret) break; res.start = res.end + 1; -- cgit v1.2.3 From ac91d85456372a90af5b85eb6620fd2efb1e431b Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 2 Mar 2010 17:54:50 +0800 Subject: tracing: Fix warning in s_next of trace file ops This warning in s_next() can be triggered by lseek(): [] ? s_next+0x77/0x80 [] warn_slowpath_common+0x81/0xa0 [] ? s_next+0x77/0x80 [] warn_slowpath_null+0x1a/0x20 [] s_next+0x77/0x80 [] traverse+0x117/0x200 [] seq_lseek+0xa3/0x120 [] ? seq_lseek+0x0/0x120 [] vfs_llseek+0x41/0x50 [] sys_llseek+0x66/0xa0 [] sysenter_do_call+0x12/0x26 The iterator "leftover" variable is zeroed in the opening of the trace file. But lseek can call s_start() which will call s_next() without reseting the "leftover" variable back to zero, which might trigger the WARN_ON_ONCE(iter->leftover) that is in s_next(). Cc: stable@kernel.org Signed-off-by: Lai Jiangshan LKML-Reference: <4B8CE06A.9090207@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 032c57ca6502..5edf410bc540 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1703,6 +1703,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) ftrace_enable_cpu(); + iter->leftover = 0; for (p = iter; p && l < *pos; p = s_next(m, p, &l)) ; -- cgit v1.2.3 From 8737c9305bd5602b11f7eb4655d5695d4a42a0c6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Dec 2009 06:47:55 -0500 Subject: Switch may_open() and break_lease() to passing O_... ... instead of mixing FMODE_ and O_ Signed-off-by: Al Viro --- arch/um/drivers/mconsole_kern.c | 2 +- fs/cifs/file.c | 4 ++-- fs/locks.c | 5 +++-- fs/namei.c | 10 +++++----- fs/nfsctl.c | 5 ++--- fs/nfsd/vfs.c | 4 ++-- fs/open.c | 2 +- kernel/sysctl_binary.c | 7 ++----- 8 files changed, 18 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 3b3c36601a7b..de317d0c3294 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -140,7 +140,7 @@ void mconsole_proc(struct mc_request *req) goto out; } - err = may_open(&nd.path, MAY_READ, FMODE_READ); + err = may_open(&nd.path, MAY_READ, O_RDONLY); if (result) { mconsole_reply(req, "Failed to open file", 1, 0); path_put(&nd.path); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 057e1dae12ab..3d8f8a96f5a3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2289,9 +2289,9 @@ cifs_oplock_break(struct slow_work *work) if (inode && S_ISREG(inode->i_mode)) { #ifdef CONFIG_CIFS_EXPERIMENTAL if (cinode->clientCanCacheAll == 0) - break_lease(inode, FMODE_READ); + break_lease(inode, O_RDONLY); else if (cinode->clientCanCacheRead == 0) - break_lease(inode, FMODE_WRITE); + break_lease(inode, O_WRONLY); #endif rc = filemap_fdatawrite(inode->i_mapping); if (cinode->clientCanCacheRead == 0) { diff --git a/fs/locks.c b/fs/locks.c index a8794f233bc9..ae9ded026b7c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1182,8 +1182,9 @@ int __break_lease(struct inode *inode, unsigned int mode) struct file_lock *fl; unsigned long break_time; int i_have_this_lease = 0; + int want_write = (mode & O_ACCMODE) != O_RDONLY; - new_fl = lease_alloc(NULL, mode & FMODE_WRITE ? F_WRLCK : F_RDLCK); + new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); lock_kernel(); @@ -1197,7 +1198,7 @@ int __break_lease(struct inode *inode, unsigned int mode) if (fl->fl_owner == current->files) i_have_this_lease = 1; - if (mode & FMODE_WRITE) { + if (want_write) { /* If we want write access, we have to revoke any lease. */ future = F_UNLCK | F_INPROGRESS; } else if (flock->fl_type & F_INPROGRESS) { diff --git a/fs/namei.c b/fs/namei.c index a4855af776a8..b20f83d1e065 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1503,7 +1503,7 @@ int may_open(struct path *path, int acc_mode, int flag) * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { - if ((flag & FMODE_WRITE) && !(flag & O_APPEND)) + if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; @@ -1547,7 +1547,7 @@ static int handle_truncate(struct path *path) * what get passed to sys_open(). */ static int __open_namei_create(struct nameidata *nd, struct path *path, - int flag, int mode) + int open_flag, int mode) { int error; struct dentry *dir = nd->path.dentry; @@ -1565,7 +1565,7 @@ out_unlock: if (error) return error; /* Don't check for write permission, don't truncate */ - return may_open(&nd->path, 0, flag & ~O_TRUNC); + return may_open(&nd->path, 0, open_flag & ~O_TRUNC); } /* @@ -1736,7 +1736,7 @@ do_last: error = mnt_want_write(nd.path.mnt); if (error) goto exit_mutex_unlock; - error = __open_namei_create(&nd, &path, flag, mode); + error = __open_namei_create(&nd, &path, open_flag, mode); if (error) { mnt_drop_write(nd.path.mnt); goto exit; @@ -1798,7 +1798,7 @@ ok: if (error) goto exit; } - error = may_open(&nd.path, acc_mode, flag); + error = may_open(&nd.path, acc_mode, open_flag); if (error) { if (will_truncate) mnt_drop_write(nd.path.mnt); diff --git a/fs/nfsctl.c b/fs/nfsctl.c index d3854d94b7cf..bf9cbd242ddd 100644 --- a/fs/nfsctl.c +++ b/fs/nfsctl.c @@ -36,10 +36,9 @@ static struct file *do_open(char *name, int flags) return ERR_PTR(error); if (flags == O_RDWR) - error = may_open(&nd.path, MAY_READ|MAY_WRITE, - FMODE_READ|FMODE_WRITE); + error = may_open(&nd.path, MAY_READ|MAY_WRITE, flags); else - error = may_open(&nd.path, MAY_WRITE, FMODE_WRITE); + error = may_open(&nd.path, MAY_WRITE, flags); if (!error) return dentry_open(nd.path.dentry, nd.path.mnt, flags, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 8715d194561a..15dc2deaac5f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -361,7 +361,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, * If we are changing the size of the file, then * we need to break all leases. */ - host_err = break_lease(inode, FMODE_WRITE | O_NONBLOCK); + host_err = break_lease(inode, O_WRONLY | O_NONBLOCK); if (host_err == -EWOULDBLOCK) host_err = -ETIMEDOUT; if (host_err) /* ENOMEM or EWOULDBLOCK */ @@ -734,7 +734,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, * Check to see if there are any leases on this file. * This may block while leases are broken. */ - host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? FMODE_WRITE : 0)); + host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0)); if (host_err == -EWOULDBLOCK) host_err = -ETIMEDOUT; if (host_err) /* NOMEM or WOULDBLOCK */ diff --git a/fs/open.c b/fs/open.c index 040cef72bc00..e0b2d88b0380 100644 --- a/fs/open.c +++ b/fs/open.c @@ -271,7 +271,7 @@ static long do_sys_truncate(const char __user *pathname, loff_t length) * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ - error = break_lease(inode, FMODE_WRITE); + error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 8f5d16e0707a..8cd50d8f9bde 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1331,7 +1331,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, ssize_t result; char *pathname; int flags; - int acc_mode, fmode; + int acc_mode; pathname = sysctl_getname(name, nlen, &table); result = PTR_ERR(pathname); @@ -1342,15 +1342,12 @@ static ssize_t binary_sysctl(const int *name, int nlen, if (oldval && oldlen && newval && newlen) { flags = O_RDWR; acc_mode = MAY_READ | MAY_WRITE; - fmode = FMODE_READ | FMODE_WRITE; } else if (newval && newlen) { flags = O_WRONLY; acc_mode = MAY_WRITE; - fmode = FMODE_WRITE; } else if (oldval && oldlen) { flags = O_RDONLY; acc_mode = MAY_READ; - fmode = FMODE_READ; } else { result = 0; goto out_putname; @@ -1361,7 +1358,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, if (result) goto out_putname; - result = may_open(&nd.path, acc_mode, fmode); + result = may_open(&nd.path, acc_mode, flags); if (result) goto out_putpath; -- cgit v1.2.3 From 2096f759abcb42200a81d776f597362fd9265024 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 30 Jan 2010 13:16:21 -0500 Subject: New helper: path_is_under(path1, path2) Analog of is_subdir for vfsmount,dentry pairs, moved from audit_tree.c Signed-off-by: Al Viro --- fs/dcache.c | 24 ++++++++++++++++++++++++ include/linux/fs.h | 1 + kernel/audit_tree.c | 51 ++++++++++++--------------------------------------- 3 files changed, 37 insertions(+), 39 deletions(-) (limited to 'kernel') diff --git a/fs/dcache.c b/fs/dcache.c index 4365998b8df4..74da947b160b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2191,6 +2191,30 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) return result; } +int path_is_under(struct path *path1, struct path *path2) +{ + struct vfsmount *mnt = path1->mnt; + struct dentry *dentry = path1->dentry; + int res; + spin_lock(&vfsmount_lock); + if (mnt != path2->mnt) { + for (;;) { + if (mnt->mnt_parent == mnt) { + spin_unlock(&vfsmount_lock); + return 0; + } + if (mnt->mnt_parent == path2->mnt) + break; + mnt = mnt->mnt_parent; + } + dentry = mnt->mnt_mountpoint; + } + res = is_subdir(dentry, path2->dentry); + spin_unlock(&vfsmount_lock); + return res; +} +EXPORT_SYMBOL(path_is_under); + void d_genocide(struct dentry *root) { struct dentry *this_parent = root; diff --git a/include/linux/fs.h b/include/linux/fs.h index d443c9dd3caa..8d53bc17f93f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2126,6 +2126,7 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern int is_subdir(struct dentry *, struct dentry *); +extern int path_is_under(struct path *, struct path *); extern ino_t find_inode_number(struct dentry *, struct qstr *); #include diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 4b05bd9479db..f09b42d9c32d 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -603,22 +603,6 @@ skip_it: mutex_unlock(&audit_filter_mutex); } -static int is_under(struct vfsmount *mnt, struct dentry *dentry, - struct path *path) -{ - if (mnt != path->mnt) { - for (;;) { - if (mnt->mnt_parent == mnt) - return 0; - if (mnt->mnt_parent == path->mnt) - break; - mnt = mnt->mnt_parent; - } - dentry = mnt->mnt_mountpoint; - } - return is_subdir(dentry, path->dentry); -} - int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) { @@ -714,29 +698,24 @@ int audit_tag_tree(char *old, char *new) { struct list_head cursor, barrier; int failed = 0; - struct path path; + struct path path1, path2; struct vfsmount *tagged; struct list_head list; - struct vfsmount *mnt; - struct dentry *dentry; int err; - err = kern_path(new, 0, &path); + err = kern_path(new, 0, &path2); if (err) return err; - tagged = collect_mounts(&path); - path_put(&path); + tagged = collect_mounts(&path2); + path_put(&path2); if (!tagged) return -ENOMEM; - err = kern_path(old, 0, &path); + err = kern_path(old, 0, &path1); if (err) { drop_collected_mounts(tagged); return err; } - mnt = mntget(path.mnt); - dentry = dget(path.dentry); - path_put(&path); list_add_tail(&list, &tagged->mnt_list); @@ -747,6 +726,7 @@ int audit_tag_tree(char *old, char *new) while (cursor.next != &tree_list) { struct audit_tree *tree; struct vfsmount *p; + int good_one = 0; tree = container_of(cursor.next, struct audit_tree, list); get_tree(tree); @@ -754,23 +734,17 @@ int audit_tag_tree(char *old, char *new) list_add(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); - err = kern_path(tree->pathname, 0, &path); - if (err) { - put_tree(tree); - mutex_lock(&audit_filter_mutex); - continue; + err = kern_path(tree->pathname, 0, &path2); + if (!err) { + good_one = path_is_under(&path1, &path2); + path_put(&path2); } - spin_lock(&vfsmount_lock); - if (!is_under(mnt, dentry, &path)) { - spin_unlock(&vfsmount_lock); - path_put(&path); + if (!good_one) { put_tree(tree); mutex_lock(&audit_filter_mutex); continue; } - spin_unlock(&vfsmount_lock); - path_put(&path); list_for_each_entry(p, &list, mnt_list) { failed = tag_chunk(p->mnt_root->d_inode, tree); @@ -820,8 +794,7 @@ int audit_tag_tree(char *old, char *new) list_del(&cursor); list_del(&list); mutex_unlock(&audit_filter_mutex); - dput(dentry); - mntput(mnt); + path_put(&path1); drop_collected_mounts(tagged); return failed; } -- cgit v1.2.3 From 1f707137b55764740981d022d29c622832a61880 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 30 Jan 2010 22:51:25 -0500 Subject: new helper: iterate_mounts() apply function to vfsmounts in set returned by collect_mounts(), stop if it returns non-zero. Signed-off-by: Al Viro --- fs/namespace.c | 15 +++++++++++++++ include/linux/fs.h | 3 ++- kernel/audit_tree.c | 49 ++++++++++++++++--------------------------------- 3 files changed, 33 insertions(+), 34 deletions(-) (limited to 'kernel') diff --git a/fs/namespace.c b/fs/namespace.c index d25d4602ab50..d5906c19e08e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1246,6 +1246,21 @@ void drop_collected_mounts(struct vfsmount *mnt) release_mounts(&umount_list); } +int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, + struct vfsmount *root) +{ + struct vfsmount *mnt; + int res = f(root, arg); + if (res) + return res; + list_for_each_entry(mnt, &root->mnt_list, mnt_list) { + res = f(mnt, arg); + if (res) + return res; + } + return 0; +} + static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end) { struct vfsmount *p; diff --git a/include/linux/fs.h b/include/linux/fs.h index 8d53bc17f93f..e764f247d0ab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1794,7 +1794,8 @@ extern int may_umount(struct vfsmount *); extern long do_mount(char *, char *, char *, unsigned long, void *); extern struct vfsmount *collect_mounts(struct path *); extern void drop_collected_mounts(struct vfsmount *); - +extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, + struct vfsmount *); extern int vfs_statfs(struct dentry *, struct kstatfs *); extern int current_umask(void); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index f09b42d9c32d..028e85663f27 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -548,6 +548,11 @@ int audit_remove_tree_rule(struct audit_krule *rule) return 0; } +static int compare_root(struct vfsmount *mnt, void *arg) +{ + return mnt->mnt_root->d_inode == arg; +} + void audit_trim_trees(void) { struct list_head cursor; @@ -559,7 +564,6 @@ void audit_trim_trees(void) struct path path; struct vfsmount *root_mnt; struct node *node; - struct list_head list; int err; tree = container_of(cursor.next, struct audit_tree, list); @@ -577,24 +581,16 @@ void audit_trim_trees(void) if (!root_mnt) goto skip_it; - list_add_tail(&list, &root_mnt->mnt_list); spin_lock(&hash_lock); list_for_each_entry(node, &tree->chunks, list) { - struct audit_chunk *chunk = find_chunk(node); - struct inode *inode = chunk->watch.inode; - struct vfsmount *mnt; + struct inode *inode = find_chunk(node)->watch.inode; node->index |= 1U<<31; - list_for_each_entry(mnt, &list, mnt_list) { - if (mnt->mnt_root->d_inode == inode) { - node->index &= ~(1U<<31); - break; - } - } + if (iterate_mounts(compare_root, inode, root_mnt)) + node->index &= ~(1U<<31); } spin_unlock(&hash_lock); trim_marked(tree); put_tree(tree); - list_del_init(&list); drop_collected_mounts(root_mnt); skip_it: mutex_lock(&audit_filter_mutex); @@ -622,13 +618,17 @@ void audit_put_tree(struct audit_tree *tree) put_tree(tree); } +static int tag_mount(struct vfsmount *mnt, void *arg) +{ + return tag_chunk(mnt->mnt_root->d_inode, arg); +} + /* called with audit_filter_mutex */ int audit_add_tree_rule(struct audit_krule *rule) { struct audit_tree *seed = rule->tree, *tree; struct path path; - struct vfsmount *mnt, *p; - struct list_head list; + struct vfsmount *mnt; int err; list_for_each_entry(tree, &tree_list, list) { @@ -654,16 +654,9 @@ int audit_add_tree_rule(struct audit_krule *rule) err = -ENOMEM; goto Err; } - list_add_tail(&list, &mnt->mnt_list); get_tree(tree); - list_for_each_entry(p, &list, mnt_list) { - err = tag_chunk(p->mnt_root->d_inode, tree); - if (err) - break; - } - - list_del(&list); + err = iterate_mounts(tag_mount, tree, mnt); drop_collected_mounts(mnt); if (!err) { @@ -700,7 +693,6 @@ int audit_tag_tree(char *old, char *new) int failed = 0; struct path path1, path2; struct vfsmount *tagged; - struct list_head list; int err; err = kern_path(new, 0, &path2); @@ -717,15 +709,12 @@ int audit_tag_tree(char *old, char *new) return err; } - list_add_tail(&list, &tagged->mnt_list); - mutex_lock(&audit_filter_mutex); list_add(&barrier, &tree_list); list_add(&cursor, &barrier); while (cursor.next != &tree_list) { struct audit_tree *tree; - struct vfsmount *p; int good_one = 0; tree = container_of(cursor.next, struct audit_tree, list); @@ -746,12 +735,7 @@ int audit_tag_tree(char *old, char *new) continue; } - list_for_each_entry(p, &list, mnt_list) { - failed = tag_chunk(p->mnt_root->d_inode, tree); - if (failed) - break; - } - + failed = iterate_mounts(tag_mount, tree, tagged); if (failed) { put_tree(tree); mutex_lock(&audit_filter_mutex); @@ -792,7 +776,6 @@ int audit_tag_tree(char *old, char *new) } list_del(&barrier); list_del(&cursor); - list_del(&list); mutex_unlock(&audit_filter_mutex); path_put(&path1); drop_collected_mounts(tagged); -- cgit v1.2.3 From a27341cd5fcb7cf2d2d4726e9f324009f7162c00 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 2 Mar 2010 08:36:46 -0800 Subject: Prioritize synchronous signals over 'normal' signals This makes sure that we pick the synchronous signals caused by a processor fault over any pending regular asynchronous signals sent to use by [t]kill(). This is not strictly required semantics, but it makes it _much_ easier for programs like Wine that expect to find the fault information in the signal stack. Without this, if a non-synchronous signal gets picked first, the delayed asynchronous signal will have its signal context pointing to the new signal invocation, rather than the instruction that caused the SIGSEGV or SIGBUS in the first place. This is not all that pretty, and we're discussing making the synchronous signals more explicit rather than have these kinds of implicit preferences of SIGSEGV and friends. See for example http://bugzilla.kernel.org/show_bug.cgi?id=15395 for some of the discussion. But in the meantime this is a simple and fairly straightforward work-around, and the whole if (x & Y) x &= Y; thing can be compiled into (and gcc does do it) just three instructions: movq %rdx, %rax andl $Y, %eax cmovne %rax, %rdx so it is at least a simple solution to a subtle issue. Reported-and-tested-by: Pavel Vilim Acked-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- kernel/signal.c | 43 ++++++++++++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 934ae5e687b9..5bb9baffa4f1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -159,6 +159,10 @@ void recalc_sigpending(void) /* Given the mask, find the first available signal that should be serviced. */ +#define SYNCHRONOUS_MASK \ + (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ + sigmask(SIGTRAP) | sigmask(SIGFPE)) + int next_signal(struct sigpending *pending, sigset_t *mask) { unsigned long i, *s, *m, x; @@ -166,26 +170,39 @@ int next_signal(struct sigpending *pending, sigset_t *mask) s = pending->signal.sig; m = mask->sig; + + /* + * Handle the first word specially: it contains the + * synchronous signals that need to be dequeued first. + */ + x = *s &~ *m; + if (x) { + if (x & SYNCHRONOUS_MASK) + x &= SYNCHRONOUS_MASK; + sig = ffz(~x) + 1; + return sig; + } + switch (_NSIG_WORDS) { default: - for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m) - if ((x = *s &~ *m) != 0) { - sig = ffz(~x) + i*_NSIG_BPW + 1; - break; - } + for (i = 1; i < _NSIG_WORDS; ++i) { + x = *++s &~ *++m; + if (!x) + continue; + sig = ffz(~x) + i*_NSIG_BPW + 1; + break; + } break; - case 2: if ((x = s[0] &~ m[0]) != 0) - sig = 1; - else if ((x = s[1] &~ m[1]) != 0) - sig = _NSIG_BPW + 1; - else + case 2: + x = s[1] &~ m[1]; + if (!x) break; - sig += ffz(~x); + sig = ffz(~x) + _NSIG_BPW + 1; break; - case 1: if ((x = *s &~ *m) != 0) - sig = ffz(~x) + 1; + case 1: + /* Nothing to do */ break; } -- cgit v1.2.3 From 74781387822cd7a549123ae2b35862bf802689be Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Thu, 4 Mar 2010 13:30:22 +0800 Subject: padata: Allocate the cpumask for the padata instance The cpumask of the padata instance was used without allocated. This caused boot crashes if CONFIG_CPUMASK_OFFSTACK is enabled. This patch fixes this by doing proper allocation for this cpumask. Signed-off-by: Steffen Klassert Signed-off-by: Herbert Xu --- kernel/padata.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/padata.c b/kernel/padata.c index 6f9bcb8313d6..93caf65ff57c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -642,6 +642,9 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask, if (!pd) goto err_free_inst; + if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL)) + goto err_free_pd; + rcu_assign_pointer(pinst->pd, pd); pinst->wq = wq; @@ -654,12 +657,14 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask, pinst->cpu_notifier.priority = 0; err = register_hotcpu_notifier(&pinst->cpu_notifier); if (err) - goto err_free_pd; + goto err_free_cpumask; mutex_init(&pinst->lock); return pinst; +err_free_cpumask: + free_cpumask_var(pinst->cpumask); err_free_pd: padata_free_pd(pd); err_free_inst: @@ -685,6 +690,7 @@ void padata_free(struct padata_instance *pinst) unregister_hotcpu_notifier(&pinst->cpu_notifier); padata_free_pd(pinst->pd); + free_cpumask_var(pinst->cpumask); kfree(pinst); } EXPORT_SYMBOL(padata_free); -- cgit v1.2.3 From db1466b3e1bd1727375cdbfcbea4bcce2f860f61 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 Mar 2010 07:46:56 -0800 Subject: rcu: Use wrapper function instead of exporting tasklist_lock Lockdep-RCU commit d11c563d exported tasklist_lock, which is not a good thing. This patch instead exports a function that uses lockdep to check whether tasklist_lock is held. Suggested-by: Christoph Hellwig Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: Christoph Hellwig LKML-Reference: <1267631219-8713-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/cred.h | 2 +- include/linux/sched.h | 4 ++++ kernel/exit.c | 2 +- kernel/fork.c | 9 ++++++++- kernel/pid.c | 4 +++- 5 files changed, 17 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/cred.h b/include/linux/cred.h index 4db09f89b637..52507c3e1387 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -280,7 +280,7 @@ static inline void put_cred(const struct cred *_cred) * task or by holding tasklist_lock to prevent it from being unlinked. */ #define __task_cred(task) \ - ((const struct cred *)(rcu_dereference_check((task)->real_cred, rcu_read_lock_held() || lockdep_is_held(&tasklist_lock)))) + ((const struct cred *)(rcu_dereference_check((task)->real_cred, rcu_read_lock_held() || lockdep_tasklist_lock_is_held()))) /** * get_task_cred - Get another task's objective credentials diff --git a/include/linux/sched.h b/include/linux/sched.h index 0eef87b58ea5..a47af2064dcc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -258,6 +258,10 @@ extern spinlock_t mmlist_lock; struct task_struct; +#ifdef CONFIG_PROVE_RCU +extern int lockdep_tasklist_lock_is_held(void); +#endif /* #ifdef CONFIG_PROVE_RCU */ + extern void sched_init(void); extern void sched_init_smp(void); extern asmlinkage void schedule_tail(struct task_struct *prev); diff --git a/kernel/exit.c b/kernel/exit.c index 45ed043b8bf5..fed3a4db6f04 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -87,7 +87,7 @@ static void __exit_signal(struct task_struct *tsk) sighand = rcu_dereference_check(tsk->sighand, rcu_read_lock_held() || - lockdep_is_held(&tasklist_lock)); + lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); posix_cpu_timers_exit(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index 17bbf093356d..8691c540a470 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -86,7 +86,14 @@ int max_threads; /* tunable limit on nr_threads */ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ -EXPORT_SYMBOL_GPL(tasklist_lock); + +#ifdef CONFIG_PROVE_RCU +int lockdep_tasklist_lock_is_held(void) +{ + return lockdep_is_held(&tasklist_lock); +} +EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); +#endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { diff --git a/kernel/pid.c b/kernel/pid.c index b08e697cd83f..b6064405f367 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -367,7 +367,9 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type) struct task_struct *result = NULL; if (pid) { struct hlist_node *first; - first = rcu_dereference_check(pid->tasks[type].first, rcu_read_lock_held() || lockdep_is_held(&tasklist_lock)); + first = rcu_dereference_check(pid->tasks[type].first, + rcu_read_lock_held() || + lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pids[(type)].node); } -- cgit v1.2.3 From cc5b83a9f884fe8722a275069a5a6fde39988455 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 Mar 2010 07:46:59 -0800 Subject: rcu: Add control variables to lockdep_rcu_dereference() diagnostics Add the values of rcu_scheduler_active() and debug_locks() to the lockdep_rcu_dereference() output to help diagnose RCU lockdep splats that occur shortly after the scheduler starts. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1267631219-8713-4-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/lockdep.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 0c30d0455de1..681bc2e1e187 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3822,6 +3822,7 @@ void lockdep_rcu_dereference(const char *file, const int line) printk("%s:%d invoked rcu_dereference_check() without protection!\n", file, line); printk("\nother info that might help us debug this:\n\n"); + printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks); lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); dump_stack(); -- cgit v1.2.3 From 8d53dd546f36073e0d29b0cfc24c665db301e3e7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 Mar 2010 17:50:18 -0800 Subject: rcu, ftrace: Fix RCU lockdep splat in ftrace_perf_buf_prepare() Change the pair of rcu_dereference() calls in ftrace_perf_buf_prepare() to rcu_dereference_sched(). Signed-off-by: Paul E. McKenney Acked-by: Frederic Weisbecker Cc: Steven Rostedt Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: Frederic Weisbecker LKML-Reference: <1267667418-32233-3-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/trace/ftrace.h | 4 ++-- kernel/trace/trace_event_profile.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 0804cd594803..601ad7744247 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -699,9 +699,9 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ * __cpu = smp_processor_id(); * * if (in_nmi()) - * trace_buf = rcu_dereference(perf_trace_buf_nmi); + * trace_buf = rcu_dereference_sched(perf_trace_buf_nmi); * else - * trace_buf = rcu_dereference(perf_trace_buf); + * trace_buf = rcu_dereference_sched(perf_trace_buf); * * if (!trace_buf) * goto end; diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index f0d693005075..c1cc3ab633de 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -138,9 +138,9 @@ __kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type, cpu = smp_processor_id(); if (in_nmi()) - trace_buf = rcu_dereference(perf_trace_buf_nmi); + trace_buf = rcu_dereference_sched(perf_trace_buf_nmi); else - trace_buf = rcu_dereference(perf_trace_buf); + trace_buf = rcu_dereference_sched(perf_trace_buf); if (!trace_buf) goto err; -- cgit v1.2.3 From 801c29fd1fdeb84f60241beb445ff5db154450ae Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 5 Mar 2010 20:02:19 -0500 Subject: function-graph: Fix unused reference to ftrace_set_func() The declaration of ftrace_set_func() is at the start of the ftrace.c file and wrapped with a #ifdef CONFIG_FUNCTION_GRAPH condition. If function graph tracing is enabled but CONFIG_DYNAMIC_FTRACE is not, a warning about that function being declared static and unused is given. This really should have been placed within the CONFIG_FUNCTION_GRAPH condition that uses ftrace_set_func(). Moving the declaration down fixes the warning and makes the code cleaner. Reported-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d996353473fd..d0407c9f368c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -85,10 +85,6 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int ftrace_set_func(unsigned long *array, int *idx, char *buffer); -#endif - static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) { struct ftrace_ops *op = ftrace_list; @@ -2300,6 +2296,8 @@ __setup("ftrace_filter=", set_ftrace_filter); #ifdef CONFIG_FUNCTION_GRAPH_TRACER static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; +static int ftrace_set_func(unsigned long *array, int *idx, char *buffer); + static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); -- cgit v1.2.3 From a094fe04c751698a18c3a0d376a3bdb117f1e0d8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 5 Mar 2010 20:08:58 -0500 Subject: function-graph: Use comment notation for func names of dangling '}' When a '}' does not have a matching function start, the name is printed within parenthesis. But this makes it confusing between ending '}' and function starts. This patch makes the function name appear in C comment notation. Old view: 3) 1.281 us | } (might_fault) 3) 3.620 us | } (filldir) 3) 5.251 us | } (call_filldir) 3) | call_filldir() { 3) | filldir() { New view: 3) 1.281 us | } /* might_fault */ 3) 3.620 us | } /* filldir */ 3) 5.251 us | } /* call_filldir */ 3) | call_filldir() { 3) | filldir() { Requested-by: Ingo Molnar Signed-off-by: Steven Rostedt --- kernel/trace/trace_functions_graph.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index e998a824e9db..7b1f24618d97 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -920,7 +920,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, if (!ret) return TRACE_TYPE_PARTIAL_LINE; } else { - ret = trace_seq_printf(s, "} (%ps)\n", (void *)trace->func); + ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } -- cgit v1.2.3 From 1acaa1b2d9b5904c9cce06122990a2d71046ce16 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 5 Mar 2010 18:23:50 -0300 Subject: tracing: Update the comm field in the right variable in update_max_tr The latency output showed: # | task: -3 (uid:0 nice:0 policy:1 rt_prio:99) The comm is missing in the "task:" and it looks like a minus 3 is the output. The correct display should be: # | task: migration/0-3 (uid:0 nice:0 policy:1 rt_prio:99) The problem is that the comm is being stored in the wrong data structure. The max_tr.data[cpu] is what stores the comm, not the tr->data[cpu]. Before this patch the max_tr.data[cpu]->comm was zeroed and the /debug/trace ended up showing just the '-' sign followed by the pid. Also remove a needless initialization of max_data. Signed-off-by: Arnaldo Carvalho de Melo LKML-Reference: <1267824230-23861-1-git-send-email-acme@infradead.org> Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 032c57ca6502..6efd5cb3c252 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -592,7 +592,7 @@ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct trace_array_cpu *data = tr->data[cpu]; - struct trace_array_cpu *max_data = tr->data[cpu]; + struct trace_array_cpu *max_data; max_tr.cpu = cpu; max_tr.time_start = data->preempt_timestamp; @@ -602,7 +602,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; - memcpy(data->comm, tsk->comm, TASK_COMM_LEN); + memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN); max_data->pid = tsk->pid; max_data->uid = task_uid(tsk); max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; -- cgit v1.2.3 From 0e95017355dcf43031da6d0e360a748717e56df1 Mon Sep 17 00:00:00 2001 From: Tim Bird Date: Thu, 25 Feb 2010 15:36:43 -0800 Subject: function-graph: Add tracing_thresh support to function_graph tracer Add support for tracing_thresh to the function_graph tracer. This version of this feature isolates the checks into new entry and return functions, to avoid adding more conditional code into the main function_graph paths. When the tracing_thresh is set and the function graph tracer is enabled, only the functions that took longer than the time in microseconds that was set in tracing_thresh are recorded. To do this efficiently, only the function exits are recorded: [tracing]# echo 100 > tracing_thresh [tracing]# echo function_graph > current_tracer [tracing]# cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) ! 119.214 us | } /* smp_apic_timer_interrupt */ 1) <========== | 0) ! 101.527 us | } /* __rcu_process_callbacks */ 0) ! 126.461 us | } /* rcu_process_callbacks */ 0) ! 145.111 us | } /* __do_softirq */ 0) ! 149.667 us | } /* do_softirq */ 0) ! 168.817 us | } /* irq_exit */ 0) ! 248.254 us | } /* smp_apic_timer_interrupt */ Also, add support for specifying tracing_thresh on the kernel command line. When used like so: "tracing_thresh=200 ftrace=function_graph" this can be used to analyse system startup. It is important to disable tracing soon after boot, in order to avoid losing the trace data. Acked-by: Frederic Weisbecker Signed-off-by: Tim Bird LKML-Reference: <4B87098B.4040308@am.sony.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 20 ++++++++++++++++++-- kernel/trace/trace.h | 3 ++- kernel/trace/trace_functions_graph.c | 25 +++++++++++++++++++++++-- 3 files changed, 43 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6efd5cb3c252..ababedb4e87f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -374,6 +374,21 @@ static int __init set_buf_size(char *str) } __setup("trace_buf_size=", set_buf_size); +static int __init set_tracing_thresh(char *str) +{ + unsigned long threshhold; + int ret; + + if (!str) + return 0; + ret = strict_strtoul(str, 0, &threshhold); + if (ret < 0) + return 0; + tracing_thresh = threshhold * 1000; + return 1; +} +__setup("tracing_thresh=", set_tracing_thresh); + unsigned long nsecs_to_usecs(unsigned long nsecs) { return nsecs / 1000; @@ -579,9 +594,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) static arch_spinlock_t ftrace_max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; +unsigned long __read_mostly tracing_thresh; + #ifdef CONFIG_TRACER_MAX_TRACE unsigned long __read_mostly tracing_max_latency; -unsigned long __read_mostly tracing_thresh; /* * Copy the new maximum trace into the separate maximum-trace @@ -4248,10 +4264,10 @@ static __init int tracer_init_debugfs(void) #ifdef CONFIG_TRACER_MAX_TRACE trace_create_file("tracing_max_latency", 0644, d_tracer, &tracing_max_latency, &tracing_max_lat_fops); +#endif trace_create_file("tracing_thresh", 0644, d_tracer, &tracing_thresh, &tracing_max_lat_fops); -#endif trace_create_file("README", 0444, d_tracer, NULL, &tracing_readme_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index fd05bcaf91b0..1bc8cd1431d7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -396,9 +396,10 @@ extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr); extern unsigned long nsecs_to_usecs(unsigned long nsecs); +extern unsigned long tracing_thresh; + #ifdef CONFIG_TRACER_MAX_TRACE extern unsigned long tracing_max_latency; -extern unsigned long tracing_thresh; void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); void update_max_tr_single(struct trace_array *tr, diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 7b1f24618d97..e9df04b60267 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -237,6 +237,14 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return ret; } +int trace_graph_thresh_entry(struct ftrace_graph_ent *trace) +{ + if (tracing_thresh) + return 1; + else + return trace_graph_entry(trace); +} + static void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, unsigned long flags, @@ -290,13 +298,26 @@ void set_graph_array(struct trace_array *tr) smp_mb(); } +void trace_graph_thresh_return(struct ftrace_graph_ret *trace) +{ + if (tracing_thresh && + (trace->rettime - trace->calltime < tracing_thresh)) + return; + else + trace_graph_return(trace); +} + static int graph_trace_init(struct trace_array *tr) { int ret; set_graph_array(tr); - ret = register_ftrace_graph(&trace_graph_return, - &trace_graph_entry); + if (tracing_thresh) + ret = register_ftrace_graph(&trace_graph_thresh_return, + &trace_graph_thresh_entry); + else + ret = register_ftrace_graph(&trace_graph_return, + &trace_graph_entry); if (ret) return ret; tracing_start_cmdline_record(); -- cgit v1.2.3 From 984b3f5746ed2cde3d184651dabf26980f2b66e5 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 5 Mar 2010 13:41:37 -0800 Subject: bitops: rename for_each_bit() to for_each_set_bit() Rename for_each_bit to for_each_set_bit in the kernel source tree. To permit for_each_clear_bit(), should that ever be added. The patch includes a macro to map the old for_each_bit() onto the new for_each_set_bit(). This is a (very) temporary thing to ease the migration. [akpm@linux-foundation.org: add temporary for_each_bit()] Suggested-by: Alexey Dobriyan Suggested-by: Andrew Morton Signed-off-by: Akinobu Mita Cc: "David S. Miller" Cc: Russell King Cc: David Woodhouse Cc: Artem Bityutskiy Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/cpu/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event_intel.c | 2 +- drivers/dma/ioat/dma.c | 2 +- drivers/gpio/pl061.c | 2 +- drivers/gpio/timbgpio.c | 2 +- drivers/i2c/busses/i2c-designware.c | 4 ++-- drivers/mfd/htc-egpio.c | 2 +- drivers/misc/sgi-xp/xpnet.c | 2 +- drivers/net/gianfar.c | 12 ++++++------ drivers/net/ixgbe/ixgbe_main.c | 2 +- drivers/net/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/wireless/ath/ar9170/main.c | 2 +- drivers/net/wireless/iwmc3200wifi/debugfs.c | 2 +- drivers/net/wireless/iwmc3200wifi/rx.c | 2 +- fs/ocfs2/quota_local.c | 2 +- include/linux/bitops.h | 4 +++- kernel/sched_cpupri.c | 2 +- sound/soc/codecs/uda1380.c | 2 +- 18 files changed, 26 insertions(+), 24 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 641ccb9dddbc..b1fbdeecf6c9 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -676,7 +676,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (c->weight != w) continue; - for_each_bit(j, c->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit(j, c->idxmsk, X86_PMC_IDX_MAX) { if (!test_bit(j, used_mask)) break; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index cf6590cf4a5f..977e7544738c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -757,7 +757,7 @@ again: inc_irq_stat(apic_perf_irqs); ack = status; - for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; clear_bit(bit, (unsigned long *) &status); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 5d0e42b263df..af14c9a5b8d4 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -71,7 +71,7 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data) } attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET); - for_each_bit(bit, &attnstatus, BITS_PER_LONG) { + for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) { chan = ioat_chan_by_index(instance, bit); tasklet_schedule(&chan->cleanup_task); } diff --git a/drivers/gpio/pl061.c b/drivers/gpio/pl061.c index 4ee4c8367a3f..3ad1eeb49609 100644 --- a/drivers/gpio/pl061.c +++ b/drivers/gpio/pl061.c @@ -219,7 +219,7 @@ static void pl061_irq_handler(unsigned irq, struct irq_desc *desc) if (pending == 0) continue; - for_each_bit(offset, &pending, PL061_GPIO_NR) + for_each_set_bit(offset, &pending, PL061_GPIO_NR) generic_handle_irq(pl061_to_irq(&chip->gc, offset)); } desc->chip->unmask(irq); diff --git a/drivers/gpio/timbgpio.c b/drivers/gpio/timbgpio.c index d941f45fe557..4ecba6e5a32d 100644 --- a/drivers/gpio/timbgpio.c +++ b/drivers/gpio/timbgpio.c @@ -175,7 +175,7 @@ static void timbgpio_irq(unsigned int irq, struct irq_desc *desc) ipr = ioread32(tgpio->membase + TGPIO_IPR); iowrite32(ipr, tgpio->membase + TGPIO_ICR); - for_each_bit(offset, &ipr, tgpio->gpio.ngpio) + for_each_set_bit(offset, &ipr, tgpio->gpio.ngpio) generic_handle_irq(timbgpio_to_irq(&tgpio->gpio, offset)); } diff --git a/drivers/i2c/busses/i2c-designware.c b/drivers/i2c/busses/i2c-designware.c index 9e18ef97f156..3e72b69aa7f8 100644 --- a/drivers/i2c/busses/i2c-designware.c +++ b/drivers/i2c/busses/i2c-designware.c @@ -497,13 +497,13 @@ static int i2c_dw_handle_tx_abort(struct dw_i2c_dev *dev) int i; if (abort_source & DW_IC_TX_ABRT_NOACK) { - for_each_bit(i, &abort_source, ARRAY_SIZE(abort_sources)) + for_each_set_bit(i, &abort_source, ARRAY_SIZE(abort_sources)) dev_dbg(dev->dev, "%s: %s\n", __func__, abort_sources[i]); return -EREMOTEIO; } - for_each_bit(i, &abort_source, ARRAY_SIZE(abort_sources)) + for_each_set_bit(i, &abort_source, ARRAY_SIZE(abort_sources)) dev_err(dev->dev, "%s: %s\n", __func__, abort_sources[i]); if (abort_source & DW_IC_TX_ARB_LOST) diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c index aa266e1f69b2..addb846c1e34 100644 --- a/drivers/mfd/htc-egpio.c +++ b/drivers/mfd/htc-egpio.c @@ -108,7 +108,7 @@ static void egpio_handler(unsigned int irq, struct irq_desc *desc) ack_irqs(ei); /* Process all set pins. */ readval &= ei->irqs_enabled; - for_each_bit(irqpin, &readval, ei->nirqs) { + for_each_set_bit(irqpin, &readval, ei->nirqs) { /* Run irq handler */ pr_debug("got IRQ %d\n", irqpin); irq = ei->irq_start + irqpin; diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c index 16f0abda1423..57b152f8d1b9 100644 --- a/drivers/misc/sgi-xp/xpnet.c +++ b/drivers/misc/sgi-xp/xpnet.c @@ -475,7 +475,7 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->data[0] == 0xff) { /* we are being asked to broadcast to all partitions */ - for_each_bit(dest_partid, xpnet_broadcast_partitions, + for_each_set_bit(dest_partid, xpnet_broadcast_partitions, xp_max_npartitions) { xpnet_send(skb, queued_msg, start_addr, end_addr, diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index 6aa526ee9096..61a7b4351e78 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -998,7 +998,7 @@ static int gfar_probe(struct of_device *ofdev, } /* Need to reverse the bit maps as bit_map's MSB is q0 - * but, for_each_bit parses from right to left, which + * but, for_each_set_bit parses from right to left, which * basically reverses the queue numbers */ for (i = 0; i< priv->num_grps; i++) { priv->gfargrp[i].tx_bit_map = reverse_bitmap( @@ -1011,7 +1011,7 @@ static int gfar_probe(struct of_device *ofdev, * also assign queues to groups */ for (grp_idx = 0; grp_idx < priv->num_grps; grp_idx++) { priv->gfargrp[grp_idx].num_rx_queues = 0x0; - for_each_bit(i, &priv->gfargrp[grp_idx].rx_bit_map, + for_each_set_bit(i, &priv->gfargrp[grp_idx].rx_bit_map, priv->num_rx_queues) { priv->gfargrp[grp_idx].num_rx_queues++; priv->rx_queue[i]->grp = &priv->gfargrp[grp_idx]; @@ -1019,7 +1019,7 @@ static int gfar_probe(struct of_device *ofdev, rqueue = rqueue | ((RQUEUE_EN0 | RQUEUE_EX0) >> i); } priv->gfargrp[grp_idx].num_tx_queues = 0x0; - for_each_bit (i, &priv->gfargrp[grp_idx].tx_bit_map, + for_each_set_bit(i, &priv->gfargrp[grp_idx].tx_bit_map, priv->num_tx_queues) { priv->gfargrp[grp_idx].num_tx_queues++; priv->tx_queue[i]->grp = &priv->gfargrp[grp_idx]; @@ -1709,7 +1709,7 @@ void gfar_configure_coalescing(struct gfar_private *priv, if (priv->mode == MQ_MG_MODE) { baddr = ®s->txic0; - for_each_bit (i, &tx_mask, priv->num_tx_queues) { + for_each_set_bit(i, &tx_mask, priv->num_tx_queues) { if (likely(priv->tx_queue[i]->txcoalescing)) { gfar_write(baddr + i, 0); gfar_write(baddr + i, priv->tx_queue[i]->txic); @@ -1717,7 +1717,7 @@ void gfar_configure_coalescing(struct gfar_private *priv, } baddr = ®s->rxic0; - for_each_bit (i, &rx_mask, priv->num_rx_queues) { + for_each_set_bit(i, &rx_mask, priv->num_rx_queues) { if (likely(priv->rx_queue[i]->rxcoalescing)) { gfar_write(baddr + i, 0); gfar_write(baddr + i, priv->rx_queue[i]->rxic); @@ -2607,7 +2607,7 @@ static int gfar_poll(struct napi_struct *napi, int budget) budget_per_queue = left_over_budget/num_queues; left_over_budget = 0; - for_each_bit(i, &gfargrp->rx_bit_map, priv->num_rx_queues) { + for_each_set_bit(i, &gfargrp->rx_bit_map, priv->num_rx_queues) { if (test_bit(i, &serviced_queues)) continue; rx_queue = priv->rx_queue[i]; diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 45e3532b166f..684af371462d 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -1050,7 +1050,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { q_vector = adapter->q_vector[v_idx]; - /* XXX for_each_bit(...) */ + /* XXX for_each_set_bit(...) */ r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); diff --git a/drivers/net/ixgbevf/ixgbevf_main.c b/drivers/net/ixgbevf/ixgbevf_main.c index 235b5fd4b8d4..ca653c49b765 100644 --- a/drivers/net/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ixgbevf/ixgbevf_main.c @@ -751,7 +751,7 @@ static void ixgbevf_configure_msix(struct ixgbevf_adapter *adapter) */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { q_vector = adapter->q_vector[v_idx]; - /* XXX for_each_bit(...) */ + /* XXX for_each_set_bit(...) */ r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c index 8a964f130367..a6452af9c6c5 100644 --- a/drivers/net/wireless/ath/ar9170/main.c +++ b/drivers/net/wireless/ath/ar9170/main.c @@ -394,7 +394,7 @@ static void ar9170_tx_fake_ampdu_status(struct ar9170 *ar) ieee80211_tx_status_irqsafe(ar->hw, skb); } - for_each_bit(i, &queue_bitmap, BITS_PER_BYTE) { + for_each_set_bit(i, &queue_bitmap, BITS_PER_BYTE) { #ifdef AR9170_QUEUE_STOP_DEBUG printk(KERN_DEBUG "%s: wake queue %d\n", wiphy_name(ar->hw->wiphy), i); diff --git a/drivers/net/wireless/iwmc3200wifi/debugfs.c b/drivers/net/wireless/iwmc3200wifi/debugfs.c index be992ca41cf1..c29c994de0e2 100644 --- a/drivers/net/wireless/iwmc3200wifi/debugfs.c +++ b/drivers/net/wireless/iwmc3200wifi/debugfs.c @@ -89,7 +89,7 @@ static int iwm_debugfs_dbg_modules_write(void *data, u64 val) for (i = 0; i < __IWM_DM_NR; i++) iwm->dbg.dbg_module[i] = 0; - for_each_bit(bit, &iwm->dbg.dbg_modules, __IWM_DM_NR) + for_each_set_bit(bit, &iwm->dbg.dbg_modules, __IWM_DM_NR) iwm->dbg.dbg_module[bit] = iwm->dbg.dbg_level; return 0; diff --git a/drivers/net/wireless/iwmc3200wifi/rx.c b/drivers/net/wireless/iwmc3200wifi/rx.c index ad8f7eabb5aa..8456b4dbd146 100644 --- a/drivers/net/wireless/iwmc3200wifi/rx.c +++ b/drivers/net/wireless/iwmc3200wifi/rx.c @@ -1116,7 +1116,7 @@ static int iwm_ntf_stop_resume_tx(struct iwm_priv *iwm, u8 *buf, return -EINVAL; } - for_each_bit(bit, (unsigned long *)&tid_msk, IWM_UMAC_TID_NR) { + for_each_set_bit(bit, (unsigned long *)&tid_msk, IWM_UMAC_TID_NR) { tid_info = &sta_info->tid_info[bit]; mutex_lock(&tid_info->mutex); diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 21f9e71223ca..a6467f3d262e 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -457,7 +457,7 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode, break; } dchunk = (struct ocfs2_local_disk_chunk *)hbh->b_data; - for_each_bit(bit, rchunk->rc_bitmap, ol_chunk_entries(sb)) { + for_each_set_bit(bit, rchunk->rc_bitmap, ol_chunk_entries(sb)) { qbh = NULL; status = ocfs2_read_quota_block(lqinode, ol_dqblk_block(sb, chunk, bit), diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 25b8b2f33ae9..b79389879238 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -16,11 +16,13 @@ */ #include -#define for_each_bit(bit, addr, size) \ +#define for_each_set_bit(bit, addr, size) \ for ((bit) = find_first_bit((addr), (size)); \ (bit) < (size); \ (bit) = find_next_bit((addr), (size), (bit) + 1)) +/* Temporary */ +#define for_each_bit(bit, addr, size) for_each_set_bit(bit, addr, size) static __inline__ int get_bitmask_order(unsigned int count) { diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index eeb3506c4834..82095bf2099f 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -47,7 +47,7 @@ static int convert_prio(int prio) } #define for_each_cpupri_active(array, idx) \ - for_each_bit(idx, array, CPUPRI_NR_PRIORITIES) + for_each_set_bit(idx, array, CPUPRI_NR_PRIORITIES) /** * cpupri_find - find the best (lowest-pri) CPU in the system diff --git a/sound/soc/codecs/uda1380.c b/sound/soc/codecs/uda1380.c index a2763c2e7348..9cd0a66b7663 100644 --- a/sound/soc/codecs/uda1380.c +++ b/sound/soc/codecs/uda1380.c @@ -137,7 +137,7 @@ static void uda1380_flush_work(struct work_struct *work) { int bit, reg; - for_each_bit(bit, &uda1380_cache_dirty, UDA1380_CACHEREGNUM - 0x10) { + for_each_set_bit(bit, &uda1380_cache_dirty, UDA1380_CACHEREGNUM - 0x10) { reg = 0x10 + bit; pr_debug("uda1380: flush reg %x val %x:\n", reg, uda1380_read_reg_cache(uda1380_codec, reg)); -- cgit v1.2.3 From d559db086ff5be9bcc259e5aa50bf3d881eaf1d1 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 5 Mar 2010 13:41:39 -0800 Subject: mm: clean up mm_counter Presently, per-mm statistics counter is defined by macro in sched.h This patch modifies it to - defined in mm.h as inlinf functions - use array instead of macro's name creation. This patch is for reducing patch size in future patch to modify implementation of per-mm counter. Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Minchan Kim Cc: Christoph Lameter Cc: Lee Schermerhorn Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 4 +- include/linux/mm.h | 104 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 33 ++++++++++----- include/linux/sched.h | 54 ------------------------ kernel/fork.c | 3 +- kernel/tsacct.c | 1 + mm/filemap_xip.c | 2 +- mm/fremap.c | 2 +- mm/memory.c | 56 +++++++++++++++---------- mm/oom_kill.c | 4 +- mm/rmap.c | 10 ++--- mm/swapfile.c | 2 +- 12 files changed, 174 insertions(+), 101 deletions(-) (limited to 'kernel') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f277c4a111cb..375581276011 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -65,11 +65,11 @@ unsigned long task_vsize(struct mm_struct *mm) int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { - *shared = get_mm_counter(mm, file_rss); + *shared = get_mm_counter(mm, MM_FILEPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->total_vm - mm->shared_vm; - *resident = *shared + get_mm_counter(mm, anon_rss); + *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); return mm->total_vm; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 90957f14195c..2124cdb2d1d0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -870,6 +870,110 @@ extern int mprotect_fixup(struct vm_area_struct *vma, */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +/* + * per-process(per-mm_struct) statistics. + */ +#if USE_SPLIT_PTLOCKS +/* + * The mm counters are not protected by its page_table_lock, + * so must be incremented atomically. + */ +static inline void set_mm_counter(struct mm_struct *mm, int member, long value) +{ + atomic_long_set(&mm->rss_stat.count[member], value); +} + +static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) +{ + return (unsigned long)atomic_long_read(&mm->rss_stat.count[member]); +} + +static inline void add_mm_counter(struct mm_struct *mm, int member, long value) +{ + atomic_long_add(value, &mm->rss_stat.count[member]); +} + +static inline void inc_mm_counter(struct mm_struct *mm, int member) +{ + atomic_long_inc(&mm->rss_stat.count[member]); +} + +static inline void dec_mm_counter(struct mm_struct *mm, int member) +{ + atomic_long_dec(&mm->rss_stat.count[member]); +} + +#else /* !USE_SPLIT_PTLOCKS */ +/* + * The mm counters are protected by its page_table_lock, + * so can be incremented directly. + */ +static inline void set_mm_counter(struct mm_struct *mm, int member, long value) +{ + mm->rss_stat.count[member] = value; +} + +static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) +{ + return mm->rss_stat.count[member]; +} + +static inline void add_mm_counter(struct mm_struct *mm, int member, long value) +{ + mm->rss_stat.count[member] += value; +} + +static inline void inc_mm_counter(struct mm_struct *mm, int member) +{ + mm->rss_stat.count[member]++; +} + +static inline void dec_mm_counter(struct mm_struct *mm, int member) +{ + mm->rss_stat.count[member]--; +} + +#endif /* !USE_SPLIT_PTLOCKS */ + +static inline unsigned long get_mm_rss(struct mm_struct *mm) +{ + return get_mm_counter(mm, MM_FILEPAGES) + + get_mm_counter(mm, MM_ANONPAGES); +} + +static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) +{ + return max(mm->hiwater_rss, get_mm_rss(mm)); +} + +static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) +{ + return max(mm->hiwater_vm, mm->total_vm); +} + +static inline void update_hiwater_rss(struct mm_struct *mm) +{ + unsigned long _rss = get_mm_rss(mm); + + if ((mm)->hiwater_rss < _rss) + (mm)->hiwater_rss = _rss; +} + +static inline void update_hiwater_vm(struct mm_struct *mm) +{ + if (mm->hiwater_vm < mm->total_vm) + mm->hiwater_vm = mm->total_vm; +} + +static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, + struct mm_struct *mm) +{ + unsigned long hiwater_rss = get_mm_hiwater_rss(mm); + + if (*maxrss < hiwater_rss) + *maxrss = hiwater_rss; +} + /* * A callback you can register to apply pressure to ageable caches. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 36f96271306c..e1ca64be6678 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -24,12 +24,6 @@ struct address_space; #define USE_SPLIT_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#if USE_SPLIT_PTLOCKS -typedef atomic_long_t mm_counter_t; -#else /* !USE_SPLIT_PTLOCKS */ -typedef unsigned long mm_counter_t; -#endif /* !USE_SPLIT_PTLOCKS */ - /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -201,6 +195,22 @@ struct core_state { struct completion startup; }; +enum { + MM_FILEPAGES, + MM_ANONPAGES, + NR_MM_COUNTERS +}; + +#if USE_SPLIT_PTLOCKS +struct mm_rss_stat { + atomic_long_t count[NR_MM_COUNTERS]; +}; +#else /* !USE_SPLIT_PTLOCKS */ +struct mm_rss_stat { + unsigned long count[NR_MM_COUNTERS]; +}; +#endif /* !USE_SPLIT_PTLOCKS */ + struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; @@ -227,11 +237,6 @@ struct mm_struct { * by mmlist_lock */ - /* Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - mm_counter_t _file_rss; - mm_counter_t _anon_rss; unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ @@ -244,6 +249,12 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + /* + * Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + struct mm_rss_stat rss_stat; + struct linux_binfmt *binfmt; cpumask_t cpu_vm_mask; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4b1753f7e48e..cbeafa49a53b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -396,60 +396,6 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} #endif -#if USE_SPLIT_PTLOCKS -/* - * The mm counters are not protected by its page_table_lock, - * so must be incremented atomically. - */ -#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value) -#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member)) -#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member) -#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member) -#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member) - -#else /* !USE_SPLIT_PTLOCKS */ -/* - * The mm counters are protected by its page_table_lock, - * so can be incremented directly. - */ -#define set_mm_counter(mm, member, value) (mm)->_##member = (value) -#define get_mm_counter(mm, member) ((mm)->_##member) -#define add_mm_counter(mm, member, value) (mm)->_##member += (value) -#define inc_mm_counter(mm, member) (mm)->_##member++ -#define dec_mm_counter(mm, member) (mm)->_##member-- - -#endif /* !USE_SPLIT_PTLOCKS */ - -#define get_mm_rss(mm) \ - (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss)) -#define update_hiwater_rss(mm) do { \ - unsigned long _rss = get_mm_rss(mm); \ - if ((mm)->hiwater_rss < _rss) \ - (mm)->hiwater_rss = _rss; \ -} while (0) -#define update_hiwater_vm(mm) do { \ - if ((mm)->hiwater_vm < (mm)->total_vm) \ - (mm)->hiwater_vm = (mm)->total_vm; \ -} while (0) - -static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) -{ - return max(mm->hiwater_rss, get_mm_rss(mm)); -} - -static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, - struct mm_struct *mm) -{ - unsigned long hiwater_rss = get_mm_hiwater_rss(mm); - - if (*maxrss < hiwater_rss) - *maxrss = hiwater_rss; -} - -static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) -{ - return max(mm->hiwater_vm, mm->total_vm); -} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); diff --git a/kernel/fork.c b/kernel/fork.c index 17bbf093356d..7616bcf107b9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -455,8 +455,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; mm->core_state = NULL; mm->nr_ptes = 0; - set_mm_counter(mm, file_rss, 0); - set_mm_counter(mm, anon_rss, 0); + memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); mm->free_area_cache = TASK_UNMAPPED_BASE; mm->cached_hole_size = ~0UL; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 00d59d048edf..0a67e041edf8 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -21,6 +21,7 @@ #include #include #include +#include /* * fill in basic accounting fields diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 1888b2d71bb8..78b94f0b6d5d 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -194,7 +194,7 @@ retry: flush_cache_page(vma, address, pte_pfn(*pte)); pteval = ptep_clear_flush_notify(vma, address, pte); page_remove_rmap(page); - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); BUG_ON(pte_dirty(pteval)); pte_unmap_unlock(pte, ptl); page_cache_release(page); diff --git a/mm/fremap.c b/mm/fremap.c index b6ec85abbb39..46f5dacf90a2 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -40,7 +40,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, page_remove_rmap(page); page_cache_release(page); update_hiwater_rss(mm); - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); } } else { if (!pte_file(pte)) diff --git a/mm/memory.c b/mm/memory.c index 72fb5f39bccc..c57678478801 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -121,6 +121,7 @@ static int __init init_zero_pfn(void) } core_initcall(init_zero_pfn); + /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but @@ -376,12 +377,18 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) return 0; } -static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +static inline void init_rss_vec(int *rss) { - if (file_rss) - add_mm_counter(mm, file_rss, file_rss); - if (anon_rss) - add_mm_counter(mm, anon_rss, anon_rss); + memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); +} + +static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) + if (rss[i]) + add_mm_counter(mm, i, rss[i]); } /* @@ -632,7 +639,10 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (page) { get_page(page); page_dup_rmap(page); - rss[PageAnon(page)]++; + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; } out_set_pte: @@ -648,11 +658,12 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress = 0; - int rss[2]; + int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; again: - rss[1] = rss[0] = 0; + init_rss_vec(rss); + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) return -ENOMEM; @@ -688,7 +699,7 @@ again: arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap_nested(orig_src_pte); - add_mm_rss(dst_mm, rss[0], rss[1]); + add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); @@ -816,8 +827,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, struct mm_struct *mm = tlb->mm; pte_t *pte; spinlock_t *ptl; - int file_rss = 0; - int anon_rss = 0; + int rss[NR_MM_COUNTERS]; + + init_rss_vec(rss); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); @@ -863,14 +875,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, set_pte_at(mm, addr, pte, pgoff_to_pte(page->index)); if (PageAnon(page)) - anon_rss--; + rss[MM_ANONPAGES]--; else { if (pte_dirty(ptent)) set_page_dirty(page); if (pte_young(ptent) && likely(!VM_SequentialReadHint(vma))) mark_page_accessed(page); - file_rss--; + rss[MM_FILEPAGES]--; } page_remove_rmap(page); if (unlikely(page_mapcount(page) < 0)) @@ -893,7 +905,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); - add_mm_rss(mm, file_rss, anon_rss); + add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); @@ -1527,7 +1539,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter(mm, file_rss); + inc_mm_counter(mm, MM_FILEPAGES); page_add_file_rmap(page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); @@ -2163,11 +2175,11 @@ gotten: if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { - dec_mm_counter(mm, file_rss); - inc_mm_counter(mm, anon_rss); + dec_mm_counter(mm, MM_FILEPAGES); + inc_mm_counter(mm, MM_ANONPAGES); } } else - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2604,7 +2616,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * discarded at swap_free(). */ - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); pte = mk_pte(page, vma->vm_page_prot); if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); @@ -2688,7 +2700,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_none(*page_table)) goto release; - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); setpte: set_pte_at(mm, address, page_table, entry); @@ -2842,10 +2854,10 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (flags & FAULT_FLAG_WRITE) entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (anon) { - inc_mm_counter(mm, anon_rss); + inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); } else { - inc_mm_counter(mm, file_rss); + inc_mm_counter(mm, MM_FILEPAGES); page_add_file_rmap(page); if (flags & FAULT_FLAG_WRITE) { dirty_page = page; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 237050478f28..35755a4156d6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -401,8 +401,8 @@ static void __oom_kill_task(struct task_struct *p, int verbose) "vsz:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(p), p->comm, K(p->mm->total_vm), - K(get_mm_counter(p->mm, anon_rss)), - K(get_mm_counter(p->mm, file_rss))); + K(get_mm_counter(p->mm, MM_ANONPAGES)), + K(get_mm_counter(p->mm, MM_FILEPAGES))); task_unlock(p); /* diff --git a/mm/rmap.c b/mm/rmap.c index 278cd277bdec..73d0472884c2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -815,9 +815,9 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { if (PageAnon(page)) - dec_mm_counter(mm, anon_rss); + dec_mm_counter(mm, MM_ANONPAGES); else - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); } else if (PageAnon(page)) { @@ -839,7 +839,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } - dec_mm_counter(mm, anon_rss); + dec_mm_counter(mm, MM_ANONPAGES); } else if (PAGE_MIGRATION) { /* * Store the pfn of the page in a special migration @@ -857,7 +857,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, entry = make_migration_entry(page, pte_write(pteval)); set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); } else - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); page_remove_rmap(page); page_cache_release(page); @@ -996,7 +996,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, page_remove_rmap(page); page_cache_release(page); - dec_mm_counter(mm, file_rss); + dec_mm_counter(mm, MM_FILEPAGES); (*mapcount)--; } pte_unmap_unlock(pte - 1, ptl); diff --git a/mm/swapfile.c b/mm/swapfile.c index 6c0585b16418..893984946a2c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -840,7 +840,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, goto out; } - inc_mm_counter(vma->vm_mm, anon_rss); + inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); -- cgit v1.2.3 From 34e55232e59f7b19050267a05ff1226e5cd122a5 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 5 Mar 2010 13:41:40 -0800 Subject: mm: avoid false sharing of mm_counter Considering the nature of per mm stats, it's the shared object among threads and can be a cache-miss point in the page fault path. This patch adds per-thread cache for mm_counter. RSS value will be counted into a struct in task_struct and synchronized with mm's one at events. Now, in this patch, the event is the number of calls to handle_mm_fault. Per-thread value is added to mm at each 64 calls. rough estimation with small benchmark on parallel thread (2threads) shows [before] 4.5 cache-miss/faults [after] 4.0 cache-miss/faults Anyway, the most contended object is mmap_sem if the number of threads grows. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KAMEZAWA Hiroyuki Cc: Minchan Kim Cc: Christoph Lameter Cc: Lee Schermerhorn Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 6 +++ fs/exec.c | 1 + include/linux/mm.h | 8 ++-- include/linux/mm_types.h | 6 +++ include/linux/sched.h | 4 +- kernel/exit.c | 3 +- mm/memory.c | 94 ++++++++++++++++++++++++++++++++++---- 7 files changed, 107 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 0d07513a67a6..e418f3d8f427 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -188,6 +188,12 @@ memory usage. Its seven fields are explained in Table 1-3. The stat file contains details information about the process itself. Its fields are explained in Table 1-4. +(for SMP CONFIG users) +For making accounting scalable, RSS related information are handled in +asynchronous manner and the vaule may not be very precise. To see a precise +snapshot of a moment, you can see /proc//smaps file and scan page table. +It's slow but very precise. + Table 1-2: Contents of the statm files (as of 2.6.30-rc7) .............................................................................. Field Content diff --git a/fs/exec.c b/fs/exec.c index cce6bbdbdbb1..ea7861727efd 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -718,6 +718,7 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; + sync_mm_rss(tsk, old_mm); mm_release(tsk, old_mm); if (old_mm) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 2124cdb2d1d0..8e580c07d171 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -873,7 +873,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, /* * per-process(per-mm_struct) statistics. */ -#if USE_SPLIT_PTLOCKS +#if defined(SPLIT_RSS_COUNTING) /* * The mm counters are not protected by its page_table_lock, * so must be incremented atomically. @@ -883,10 +883,7 @@ static inline void set_mm_counter(struct mm_struct *mm, int member, long value) atomic_long_set(&mm->rss_stat.count[member], value); } -static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) -{ - return (unsigned long)atomic_long_read(&mm->rss_stat.count[member]); -} +unsigned long get_mm_counter(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { @@ -974,6 +971,7 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, *maxrss = hiwater_rss; } +void sync_mm_rss(struct task_struct *task, struct mm_struct *mm); /* * A callback you can register to apply pressure to ageable caches. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e1ca64be6678..21861239ab0c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -202,9 +202,15 @@ enum { }; #if USE_SPLIT_PTLOCKS +#define SPLIT_RSS_COUNTING struct mm_rss_stat { atomic_long_t count[NR_MM_COUNTERS]; }; +/* per-thread cached information, */ +struct task_rss_stat { + int events; /* for synchronization threshold */ + int count[NR_MM_COUNTERS]; +}; #else /* !USE_SPLIT_PTLOCKS */ struct mm_rss_stat { unsigned long count[NR_MM_COUNTERS]; diff --git a/include/linux/sched.h b/include/linux/sched.h index cbeafa49a53b..46c6f8d5dc06 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1220,7 +1220,9 @@ struct task_struct { struct plist_node pushable_tasks; struct mm_struct *mm, *active_mm; - +#if defined(SPLIT_RSS_COUNTING) + struct task_rss_stat rss_stat; +#endif /* task state */ int exit_state; int exit_code, exit_signal; diff --git a/kernel/exit.c b/kernel/exit.c index 45ed043b8bf5..10d3c5d5ae44 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -952,7 +952,8 @@ NORET_TYPE void do_exit(long code) preempt_count()); acct_update_integrals(tsk); - + /* sync mm's RSS info before statistics gathering */ + sync_mm_rss(tsk, tsk->mm); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { hrtimer_cancel(&tsk->signal->real_timer); diff --git a/mm/memory.c b/mm/memory.c index c57678478801..a4597614f18d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -122,6 +122,79 @@ static int __init init_zero_pfn(void) core_initcall(init_zero_pfn); +#if defined(SPLIT_RSS_COUNTING) + +void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) { + if (task->rss_stat.count[i]) { + add_mm_counter(mm, i, task->rss_stat.count[i]); + task->rss_stat.count[i] = 0; + } + } + task->rss_stat.events = 0; +} + +static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) +{ + struct task_struct *task = current; + + if (likely(task->mm == mm)) + task->rss_stat.count[member] += val; + else + add_mm_counter(mm, member, val); +} +#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) +#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) + +/* sync counter once per 64 page faults */ +#define TASK_RSS_EVENTS_THRESH (64) +static void check_sync_rss_stat(struct task_struct *task) +{ + if (unlikely(task != current)) + return; + if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) + __sync_task_rss_stat(task, task->mm); +} + +unsigned long get_mm_counter(struct mm_struct *mm, int member) +{ + long val = 0; + + /* + * Don't use task->mm here...for avoiding to use task_get_mm().. + * The caller must guarantee task->mm is not invalid. + */ + val = atomic_long_read(&mm->rss_stat.count[member]); + /* + * counter is updated in asynchronous manner and may go to minus. + * But it's never be expected number for users. + */ + if (val < 0) + return 0; + return (unsigned long)val; +} + +void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) +{ + __sync_task_rss_stat(task, mm); +} +#else + +#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) +#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) + +static void check_sync_rss_stat(struct task_struct *task) +{ +} + +void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) +{ +} +#endif + /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but @@ -386,6 +459,8 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; + if (current->mm == mm) + sync_mm_rss(current, mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); @@ -1539,7 +1614,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, MM_FILEPAGES); page_add_file_rmap(page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); @@ -2175,11 +2250,11 @@ gotten: if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { - dec_mm_counter(mm, MM_FILEPAGES); - inc_mm_counter(mm, MM_ANONPAGES); + dec_mm_counter_fast(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); } } else - inc_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2616,7 +2691,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * discarded at swap_free(). */ - inc_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); pte = mk_pte(page, vma->vm_page_prot); if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); @@ -2700,7 +2775,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_none(*page_table)) goto release; - inc_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); setpte: set_pte_at(mm, address, page_table, entry); @@ -2854,10 +2929,10 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (flags & FAULT_FLAG_WRITE) entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (anon) { - inc_mm_counter(mm, MM_ANONPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); } else { - inc_mm_counter(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, MM_FILEPAGES); page_add_file_rmap(page); if (flags & FAULT_FLAG_WRITE) { dirty_page = page; @@ -3035,6 +3110,9 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(PGFAULT); + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); -- cgit v1.2.3 From 5beb49305251e5669852ed541e8e2f2f7696c53e Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 5 Mar 2010 13:42:07 -0800 Subject: mm: change anon_vma linking to fix multi-process server scalability issue The old anon_vma code can lead to scalability issues with heavily forking workloads. Specifically, each anon_vma will be shared between the parent process and all its child processes. In a workload with 1000 child processes and a VMA with 1000 anonymous pages per process that get COWed, this leads to a system with a million anonymous pages in the same anon_vma, each of which is mapped in just one of the 1000 processes. However, the current rmap code needs to walk them all, leading to O(N) scanning complexity for each page. This can result in systems where one CPU is walking the page tables of 1000 processes in page_referenced_one, while all other CPUs are stuck on the anon_vma lock. This leads to catastrophic failure for a benchmark like AIM7, where the total number of processes can reach in the tens of thousands. Real workloads are still a factor 10 less process intensive than AIM7, but they are catching up. This patch changes the way anon_vmas and VMAs are linked, which allows us to associate multiple anon_vmas with a VMA. At fork time, each child process gets its own anon_vmas, in which its COWed pages will be instantiated. The parents' anon_vma is also linked to the VMA, because non-COWed pages could be present in any of the children. This reduces rmap scanning complexity to O(1) for the pages of the 1000 child processes, with O(N) complexity for at most 1/N pages in the system. This reduces the average scanning cost in heavily forking workloads from O(N) to 2. The only real complexity in this patch stems from the fact that linking a VMA to anon_vmas now involves memory allocations. This means vma_adjust can fail, if it needs to attach a VMA to anon_vma structures. This in turn means error handling needs to be added to the calling functions. A second source of complexity is that, because there can be multiple anon_vmas, the anon_vma linking in vma_adjust can no longer be done under "the" anon_vma lock. To prevent the rmap code from walking up an incomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit flag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h to make sure it is impossible to compile a kernel that needs both symbolic values for the same bitflag. Some test results: Without the anon_vma changes, when AIM7 hits around 9.7k users (on a test box with 16GB RAM and not quite enough IO), the system ends up running >99% in system time, with every CPU on the same anon_vma lock in the pageout code. With these changes, AIM7 hits the cross-over point around 29.7k users. This happens with ~99% IO wait time, there never seems to be any spike in system time. The anon_vma lock contention appears to be resolved. [akpm@linux-foundation.org: cleanups] Signed-off-by: Rik van Riel Cc: KOSAKI Motohiro Cc: Larry Woodman Cc: Lee Schermerhorn Cc: Minchan Kim Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/perfmon.c | 1 + arch/ia64/mm/init.c | 2 + fs/exec.c | 6 +- include/linux/mm.h | 6 +- include/linux/mm_types.h | 3 +- include/linux/rmap.h | 35 ++++++++-- kernel/fork.c | 6 +- mm/ksm.c | 12 +++- mm/memory-failure.c | 5 +- mm/memory.c | 4 +- mm/mmap.c | 138 +++++++++++++++++++++++++++------------ mm/mremap.c | 7 +- mm/nommu.c | 2 +- mm/rmap.c | 156 +++++++++++++++++++++++++++++++++++++-------- 14 files changed, 298 insertions(+), 85 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index b81e46b1629b..703062c44fb9 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2315,6 +2315,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("Cannot allocate vma\n")); goto error_kmem; } + INIT_LIST_HEAD(&vma->anon_vma_chain); /* * partially initialize the vma for the sampling buffer diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index ca3335ea56cc..ed41759efcac 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -117,6 +117,7 @@ ia64_init_addr_space (void) */ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (vma) { + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = current->mm; vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; @@ -135,6 +136,7 @@ ia64_init_addr_space (void) if (!(current->personality & MMAP_PAGE_ZERO)) { vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (vma) { + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = current->mm; vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); diff --git a/fs/exec.c b/fs/exec.c index ea7861727efd..591030735591 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -246,6 +246,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) goto err; @@ -516,7 +517,8 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) /* * cover the whole range: [new_start, old_end) */ - vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL); + if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL)) + return -ENOMEM; /* * move the page tables downwards, on failure we rely on @@ -547,7 +549,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) tlb_finish_mmu(tlb, new_end, old_end); /* - * shrink the vma to just the new range. + * Shrink the vma to just the new range. Always succeeds. */ vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e580c07d171..8e2841a2f441 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,7 +97,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ +#ifdef CONFIG_MMU +#define VM_LOCK_RMAP 0x01000000 /* Do not follow this rmap (mmu mmap) */ +#else #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ +#endif #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ @@ -1216,7 +1220,7 @@ static inline void vma_nonlinear_insert(struct vm_area_struct *vma, /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern void vma_adjust(struct vm_area_struct *vma, unsigned long start, +extern int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert); extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 19549d7275ab..048b46270aa5 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -163,7 +163,8 @@ struct vm_area_struct { * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ - struct list_head anon_vma_node; /* Serialized by anon_vma->lock */ + struct list_head anon_vma_chain; /* Serialized by mmap_sem & + * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b019ae64e2ab..62da2001d55c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -37,7 +37,27 @@ struct anon_vma { * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ - struct list_head head; /* List of private "related" vmas */ + struct list_head head; /* Chain of private "related" vmas */ +}; + +/* + * The copy-on-write semantics of fork mean that an anon_vma + * can become associated with multiple processes. Furthermore, + * each child process will have its own anon_vma, where new + * pages for that process are instantiated. + * + * This structure allows us to find the anon_vmas associated + * with a VMA, or the VMAs associated with an anon_vma. + * The "same_vma" list contains the anon_vma_chains linking + * all the anon_vmas associated with this VMA. + * The "same_anon_vma" list contains the anon_vma_chains + * which link all the VMAs associated with this anon_vma. + */ +struct anon_vma_chain { + struct vm_area_struct *vma; + struct anon_vma *anon_vma; + struct list_head same_vma; /* locked by mmap_sem & page_table_lock */ + struct list_head same_anon_vma; /* locked by anon_vma->lock */ }; #ifdef CONFIG_MMU @@ -89,12 +109,19 @@ static inline void anon_vma_unlock(struct vm_area_struct *vma) */ void anon_vma_init(void); /* create anon_vma_cachep */ int anon_vma_prepare(struct vm_area_struct *); -void __anon_vma_merge(struct vm_area_struct *, struct vm_area_struct *); -void anon_vma_unlink(struct vm_area_struct *); -void anon_vma_link(struct vm_area_struct *); +void unlink_anon_vmas(struct vm_area_struct *); +int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); +int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); void __anon_vma_link(struct vm_area_struct *); void anon_vma_free(struct anon_vma *); +static inline void anon_vma_merge(struct vm_area_struct *vma, + struct vm_area_struct *next) +{ + VM_BUG_ON(vma->anon_vma != next->anon_vma); + unlink_anon_vmas(next); +} + /* * rmap interfaces called when adding or removing pte of page */ diff --git a/kernel/fork.c b/kernel/fork.c index 7616bcf107b9..bab7b254ad39 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -329,15 +329,17 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (!tmp) goto fail_nomem; *tmp = *mpnt; + INIT_LIST_HEAD(&tmp->anon_vma_chain); pol = mpol_dup(vma_policy(mpnt)); retval = PTR_ERR(pol); if (IS_ERR(pol)) goto fail_nomem_policy; vma_set_policy(tmp, pol); + if (anon_vma_fork(tmp, mpnt)) + goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; tmp->vm_mm = mm; tmp->vm_next = NULL; - anon_vma_link(tmp); file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; @@ -392,6 +394,8 @@ out: flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); return retval; +fail_nomem_anon_vma_fork: + mpol_put(pol); fail_nomem_policy: kmem_cache_free(vm_area_cachep, tmp); fail_nomem: diff --git a/mm/ksm.c b/mm/ksm.c index 56a0da1f9979..a93f1b7f508c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1563,10 +1563,12 @@ int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, again: hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; struct vm_area_struct *vma; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) { + vma = vmac->vma; if (rmap_item->address < vma->vm_start || rmap_item->address >= vma->vm_end) continue; @@ -1614,10 +1616,12 @@ int try_to_unmap_ksm(struct page *page, enum ttu_flags flags) again: hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; struct vm_area_struct *vma; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) { + vma = vmac->vma; if (rmap_item->address < vma->vm_start || rmap_item->address >= vma->vm_end) continue; @@ -1664,10 +1668,12 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *, again: hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; + struct anon_vma_chain *vmac; struct vm_area_struct *vma; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) { + vma = vmac->vma; if (rmap_item->address < vma->vm_start || rmap_item->address >= vma->vm_end) continue; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 17299fd4577c..d1f335162976 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -383,9 +383,12 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (av == NULL) /* Not actually mapped anymore */ goto out; for_each_process (tsk) { + struct anon_vma_chain *vmac; + if (!task_early_kill(tsk)) continue; - list_for_each_entry (vma, &av->head, anon_vma_node) { + list_for_each_entry(vmac, &av->head, same_anon_vma) { + vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; if (vma->vm_mm == tsk->mm) diff --git a/mm/memory.c b/mm/memory.c index 77d9f840936b..dc785b438d70 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -374,7 +374,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { @@ -388,7 +388,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, diff --git a/mm/mmap.c b/mm/mmap.c index 31656147128e..6a0c15db7f60 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -437,7 +437,6 @@ __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { __vma_link_list(mm, vma, prev, rb_parent); __vma_link_rb(mm, vma, rb_link, rb_parent); - __anon_vma_link(vma); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, @@ -499,7 +498,7 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ -void vma_adjust(struct vm_area_struct *vma, unsigned long start, +int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { struct mm_struct *mm = vma->vm_mm; @@ -542,6 +541,28 @@ again: remove_next = 1 + (end > next->vm_end); } } + /* + * When changing only vma->vm_end, we don't really need anon_vma lock. + */ + if (vma->anon_vma && (insert || importer || start != vma->vm_start)) + anon_vma = vma->anon_vma; + if (anon_vma) { + /* + * Easily overlooked: when mprotect shifts the boundary, + * make sure the expanding vma has anon_vma set if the + * shrinking vma had, to cover any anon pages imported. + */ + if (importer && !importer->anon_vma) { + /* Block reverse map lookups until things are set up. */ + importer->vm_flags |= VM_LOCK_RMAP; + if (anon_vma_clone(importer, vma)) { + importer->vm_flags &= ~VM_LOCK_RMAP; + return -ENOMEM; + } + importer->anon_vma = anon_vma; + } + } + if (file) { mapping = file->f_mapping; if (!(vma->vm_flags & VM_NONLINEAR)) @@ -567,25 +588,6 @@ again: remove_next = 1 + (end > next->vm_end); } } - /* - * When changing only vma->vm_end, we don't really need - * anon_vma lock. - */ - if (vma->anon_vma && (insert || importer || start != vma->vm_start)) - anon_vma = vma->anon_vma; - if (anon_vma) { - spin_lock(&anon_vma->lock); - /* - * Easily overlooked: when mprotect shifts the boundary, - * make sure the expanding vma has anon_vma set if the - * shrinking vma had, to cover any anon pages imported. - */ - if (importer && !importer->anon_vma) { - importer->anon_vma = anon_vma; - __anon_vma_link(importer); - } - } - if (root) { flush_dcache_mmap_lock(mapping); vma_prio_tree_remove(vma, root); @@ -616,8 +618,11 @@ again: remove_next = 1 + (end > next->vm_end); __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); - if (next->anon_vma) - __anon_vma_merge(vma, next); + /* + * This VMA is now dead, no need for rmap to follow it. + * Call anon_vma_merge below, outside of i_mmap_lock. + */ + next->vm_flags |= VM_LOCK_RMAP; } else if (insert) { /* * split_vma has split insert from vma, and needs @@ -627,17 +632,25 @@ again: remove_next = 1 + (end > next->vm_end); __insert_vm_struct(mm, insert); } - if (anon_vma) - spin_unlock(&anon_vma->lock); if (mapping) spin_unlock(&mapping->i_mmap_lock); + /* + * The current VMA has been set up. It is now safe for the + * rmap code to get from the pages to the ptes. + */ + if (anon_vma && importer) + importer->vm_flags &= ~VM_LOCK_RMAP; + if (remove_next) { if (file) { fput(file); if (next->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); } + /* Protected by mmap_sem and VM_LOCK_RMAP. */ + if (next->anon_vma) + anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); kmem_cache_free(vm_area_cachep, next); @@ -653,6 +666,8 @@ again: remove_next = 1 + (end > next->vm_end); } validate_mm(mm); + + return 0; } /* @@ -759,6 +774,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; + int err; /* * We later require that vma->vm_flags == vm_flags, @@ -792,11 +808,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, is_mergeable_anon_vma(prev->anon_vma, next->anon_vma)) { /* cases 1, 6 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL); } else /* cases 2, 5, 7 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL); + if (err) + return NULL; return prev; } @@ -808,11 +826,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen)) { if (prev && addr < prev->vm_end) /* case 4 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL); else /* cases 3, 8 */ - vma_adjust(area, addr, next->vm_end, + err = vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL); + if (err) + return NULL; return area; } @@ -1205,6 +1225,7 @@ munmap_back: vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; + INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { error = -EINVAL; @@ -1865,6 +1886,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, { struct mempolicy *pol; struct vm_area_struct *new; + int err = -ENOMEM; if (is_vm_hugetlb_page(vma) && (addr & ~(huge_page_mask(hstate_vma(vma))))) @@ -1872,11 +1894,13 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) - return -ENOMEM; + goto out_err; /* most fields are the same, copy all, and then fixup */ *new = *vma; + INIT_LIST_HEAD(&new->anon_vma_chain); + if (new_below) new->vm_end = addr; else { @@ -1886,11 +1910,14 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, pol = mpol_dup(vma_policy(vma)); if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new); - return PTR_ERR(pol); + err = PTR_ERR(pol); + goto out_free_vma; } vma_set_policy(new, pol); + if (anon_vma_clone(new, vma)) + goto out_free_mpol; + if (new->vm_file) { get_file(new->vm_file); if (vma->vm_flags & VM_EXECUTABLE) @@ -1901,12 +1928,28 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_ops->open(new); if (new_below) - vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + + err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else - vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); + err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); - return 0; + /* Success. */ + if (!err) + return 0; + + /* Clean everything up if vma_adjust failed. */ + new->vm_ops->close(new); + if (new->vm_file) { + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(mm); + fput(new->vm_file); + } + out_free_mpol: + mpol_put(pol); + out_free_vma: + kmem_cache_free(vm_area_cachep, new); + out_err: + return err; } /* @@ -2116,6 +2159,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) return -ENOMEM; } + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2252,10 +2296,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma) { *new_vma = *vma; pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new_vma); - return NULL; - } + if (IS_ERR(pol)) + goto out_free_vma; + INIT_LIST_HEAD(&new_vma->anon_vma_chain); + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; vma_set_policy(new_vma, pol); new_vma->vm_start = addr; new_vma->vm_end = addr + len; @@ -2271,6 +2316,12 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } } return new_vma; + + out_free_mempol: + mpol_put(pol); + out_free_vma: + kmem_cache_free(vm_area_cachep, new_vma); + return NULL; } /* @@ -2348,6 +2399,7 @@ int install_special_mapping(struct mm_struct *mm, if (unlikely(vma == NULL)) return -ENOMEM; + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2448,6 +2500,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = -EINTR; BUG_ON(down_read_trylock(&mm->mmap_sem)); @@ -2465,7 +2518,8 @@ int mm_take_all_locks(struct mm_struct *mm) if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) - vm_lock_anon_vma(mm, vma->anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_lock_anon_vma(mm, avc->anon_vma); } ret = 0; @@ -2520,13 +2574,15 @@ static void vm_unlock_mapping(struct address_space *mapping) void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; + struct anon_vma_chain *avc; BUG_ON(down_read_trylock(&mm->mmap_sem)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) - vm_unlock_anon_vma(vma->anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } diff --git a/mm/mremap.c b/mm/mremap.c index 4c4c803453f3..e9c75efce609 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -460,8 +460,11 @@ unsigned long do_mremap(unsigned long addr, if (vma_expandable(vma, new_len - old_len)) { int pages = (new_len - old_len) >> PAGE_SHIFT; - vma_adjust(vma, vma->vm_start, - addr + new_len, vma->vm_pgoff, NULL); + if (vma_adjust(vma, vma->vm_start, addr + new_len, + vma->vm_pgoff, NULL)) { + ret = -ENOMEM; + goto out; + } mm->total_vm += pages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); diff --git a/mm/nommu.c b/mm/nommu.c index 48a2ecfaf059..55727a74af98 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1209,7 +1209,7 @@ unsigned long do_mmap_pgoff(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_node); + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_flags = vm_flags; vma->vm_pgoff = pgoff; diff --git a/mm/rmap.c b/mm/rmap.c index 5cb47111f79e..be34094e4595 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -62,6 +62,7 @@ #include "internal.h" static struct kmem_cache *anon_vma_cachep; +static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { @@ -73,6 +74,16 @@ void anon_vma_free(struct anon_vma *anon_vma) kmem_cache_free(anon_vma_cachep, anon_vma); } +static inline struct anon_vma_chain *anon_vma_chain_alloc(void) +{ + return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL); +} + +void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) +{ + kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); +} + /** * anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question @@ -103,18 +114,23 @@ void anon_vma_free(struct anon_vma *anon_vma) int anon_vma_prepare(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; might_sleep(); if (unlikely(!anon_vma)) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *allocated; + avc = anon_vma_chain_alloc(); + if (!avc) + goto out_enomem; + anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) - return -ENOMEM; + goto out_enomem_free_avc; allocated = anon_vma; } spin_lock(&anon_vma->lock); @@ -123,53 +139,113 @@ int anon_vma_prepare(struct vm_area_struct *vma) spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; - list_add_tail(&vma->anon_vma_node, &anon_vma->head); + avc->anon_vma = anon_vma; + avc->vma = vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + list_add(&avc->same_anon_vma, &anon_vma->head); allocated = NULL; } spin_unlock(&mm->page_table_lock); spin_unlock(&anon_vma->lock); - if (unlikely(allocated)) + if (unlikely(allocated)) { anon_vma_free(allocated); + anon_vma_chain_free(avc); + } } return 0; + + out_enomem_free_avc: + anon_vma_chain_free(avc); + out_enomem: + return -ENOMEM; } -void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) +static void anon_vma_chain_link(struct vm_area_struct *vma, + struct anon_vma_chain *avc, + struct anon_vma *anon_vma) { - BUG_ON(vma->anon_vma != next->anon_vma); - list_del(&next->anon_vma_node); + avc->vma = vma; + avc->anon_vma = anon_vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + + spin_lock(&anon_vma->lock); + list_add_tail(&avc->same_anon_vma, &anon_vma->head); + spin_unlock(&anon_vma->lock); } -void __anon_vma_link(struct vm_area_struct *vma) +/* + * Attach the anon_vmas from src to dst. + * Returns 0 on success, -ENOMEM on failure. + */ +int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc, *pavc; + + list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { + avc = anon_vma_chain_alloc(); + if (!avc) + goto enomem_failure; + anon_vma_chain_link(dst, avc, pavc->anon_vma); + } + return 0; - if (anon_vma) - list_add_tail(&vma->anon_vma_node, &anon_vma->head); + enomem_failure: + unlink_anon_vmas(dst); + return -ENOMEM; } -void anon_vma_link(struct vm_area_struct *vma) +/* + * Attach vma to its own anon_vma, as well as to the anon_vmas that + * the corresponding VMA in the parent process is attached to. + * Returns 0 on success, non-zero on failure. + */ +int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; + struct anon_vma *anon_vma; - if (anon_vma) { - spin_lock(&anon_vma->lock); - list_add_tail(&vma->anon_vma_node, &anon_vma->head); - spin_unlock(&anon_vma->lock); - } + /* Don't bother if the parent process has no anon_vma here. */ + if (!pvma->anon_vma) + return 0; + + /* + * First, attach the new VMA to the parent VMA's anon_vmas, + * so rmap can find non-COWed pages in child processes. + */ + if (anon_vma_clone(vma, pvma)) + return -ENOMEM; + + /* Then add our own anon_vma. */ + anon_vma = anon_vma_alloc(); + if (!anon_vma) + goto out_error; + avc = anon_vma_chain_alloc(); + if (!avc) + goto out_error_free_anon_vma; + anon_vma_chain_link(vma, avc, anon_vma); + /* Mark this anon_vma as the one where our new (COWed) pages go. */ + vma->anon_vma = anon_vma; + + return 0; + + out_error_free_anon_vma: + anon_vma_free(anon_vma); + out_error: + return -ENOMEM; } -void anon_vma_unlink(struct vm_area_struct *vma) +static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma *anon_vma = anon_vma_chain->anon_vma; int empty; + /* If anon_vma_fork fails, we can get an empty anon_vma_chain. */ if (!anon_vma) return; spin_lock(&anon_vma->lock); - list_del(&vma->anon_vma_node); + list_del(&anon_vma_chain->same_anon_vma); /* We must garbage collect the anon_vma if it's empty */ empty = list_empty(&anon_vma->head) && !ksm_refcount(anon_vma); @@ -179,6 +255,18 @@ void anon_vma_unlink(struct vm_area_struct *vma) anon_vma_free(anon_vma); } +void unlink_anon_vmas(struct vm_area_struct *vma) +{ + struct anon_vma_chain *avc, *next; + + /* Unlink each anon_vma chained to the VMA. */ + list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { + anon_vma_unlink(avc); + list_del(&avc->same_vma); + anon_vma_chain_free(avc); + } +} + static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; @@ -192,6 +280,7 @@ void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor); + anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC); } /* @@ -240,6 +329,18 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* page should be within @vma mapping range */ return -EFAULT; } + if (unlikely(vma->vm_flags & VM_LOCK_RMAP)) { + /* + * This VMA is being unlinked or is not yet linked into the + * VMA tree. Do not try to follow this rmap. This race + * condition can result in page_referenced() ignoring a + * reference or in try_to_unmap() failing to unmap a page. + * The VMA cannot be freed under us because we hold the + * anon_vma->lock, which the munmap code takes while + * unlinking the anon_vmas from the VMA. + */ + return -EFAULT; + } return address; } @@ -396,7 +497,7 @@ static int page_referenced_anon(struct page *page, { unsigned int mapcount; struct anon_vma *anon_vma; - struct vm_area_struct *vma; + struct anon_vma_chain *avc; int referenced = 0; anon_vma = page_lock_anon_vma(page); @@ -404,7 +505,8 @@ static int page_referenced_anon(struct page *page, return referenced; mapcount = page_mapcount(page); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; @@ -1025,14 +1127,15 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) { struct anon_vma *anon_vma; - struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = SWAP_AGAIN; anon_vma = page_lock_anon_vma(page); if (!anon_vma) return ret; - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; @@ -1223,7 +1326,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, struct vm_area_struct *, unsigned long, void *), void *arg) { struct anon_vma *anon_vma; - struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = SWAP_AGAIN; /* @@ -1238,7 +1341,8 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *, if (!anon_vma) return ret; spin_lock(&anon_vma->lock); - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + list_for_each_entry(avc, &anon_vma->head, same_anon_vma) { + struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); if (address == -EFAULT) continue; -- cgit v1.2.3 From 452aa6999e6703ffbddd7f6ea124d3968915f3e3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 5 Mar 2010 13:42:13 -0800 Subject: mm/pm: force GFP_NOIO during suspend/hibernation and resume There are quite a few GFP_KERNEL memory allocations made during suspend/hibernation and resume that may cause the system to hang, because the I/O operations they depend on cannot be completed due to the underlying devices being suspended. Avoid this problem by clearing the __GFP_IO and __GFP_FS bits in gfp_allowed_mask before suspend/hibernation and restoring the original values of these bits in gfp_allowed_mask durig the subsequent resume. [akpm@linux-foundation.org: fix CONFIG_PM=n linkage] Signed-off-by: Rafael J. Wysocki Reported-by: Maxim Levitsky Cc: Sebastian Ott Cc: Benjamin Herrenschmidt Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 7 +++---- init/main.c | 2 +- kernel/power/hibernate.c | 9 +++++++++ kernel/power/suspend.c | 3 +++ mm/page_alloc.c | 25 +++++++++++++++++++++++++ 5 files changed, 41 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index e5567e6762f3..2e1b32c0484d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -83,6 +83,7 @@ struct vm_area_struct; #define GFP_HIGHUSER_MOVABLE (__GFP_WAIT | __GFP_IO | __GFP_FS | \ __GFP_HARDWALL | __GFP_HIGHMEM | \ __GFP_MOVABLE) +#define GFP_IOFS (__GFP_IO | __GFP_FS) #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) @@ -337,9 +338,7 @@ void drain_local_pages(void *dummy); extern gfp_t gfp_allowed_mask; -static inline void set_gfp_allowed_mask(gfp_t mask) -{ - gfp_allowed_mask = mask; -} +extern void set_gfp_allowed_mask(gfp_t mask); +extern gfp_t clear_gfp_allowed_mask(gfp_t mask); #endif /* __LINUX_GFP_H */ diff --git a/init/main.c b/init/main.c index 40aaa020cd68..41d0f10dbbc7 100644 --- a/init/main.c +++ b/init/main.c @@ -618,7 +618,7 @@ asmlinkage void __init start_kernel(void) local_irq_enable(); /* Interrupts are enabled now so all GFP allocations are safe. */ - set_gfp_allowed_mask(__GFP_BITS_MASK); + gfp_allowed_mask = __GFP_BITS_MASK; kmem_cache_init_late(); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index bbfe472d7524..da5288ec2392 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -323,6 +323,7 @@ static int create_image(int platform_mode) int hibernation_snapshot(int platform_mode) { int error; + gfp_t saved_mask; error = platform_begin(platform_mode); if (error) @@ -334,6 +335,7 @@ int hibernation_snapshot(int platform_mode) goto Close; suspend_console(); + saved_mask = clear_gfp_allowed_mask(GFP_IOFS); error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Recover_platform; @@ -351,6 +353,7 @@ int hibernation_snapshot(int platform_mode) dpm_resume_end(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); + set_gfp_allowed_mask(saved_mask); resume_console(); Close: platform_end(platform_mode); @@ -445,14 +448,17 @@ static int resume_target_kernel(bool platform_mode) int hibernation_restore(int platform_mode) { int error; + gfp_t saved_mask; pm_prepare_console(); suspend_console(); + saved_mask = clear_gfp_allowed_mask(GFP_IOFS); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); dpm_resume_end(PMSG_RECOVER); } + set_gfp_allowed_mask(saved_mask); resume_console(); pm_restore_console(); return error; @@ -466,6 +472,7 @@ int hibernation_restore(int platform_mode) int hibernation_platform_enter(void) { int error; + gfp_t saved_mask; if (!hibernation_ops) return -ENOSYS; @@ -481,6 +488,7 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); + saved_mask = clear_gfp_allowed_mask(GFP_IOFS); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -518,6 +526,7 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); + set_gfp_allowed_mask(saved_mask); resume_console(); Close: diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 6f10dfc2d3e9..44cce10b582d 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -189,6 +189,7 @@ static int suspend_enter(suspend_state_t state) int suspend_devices_and_enter(suspend_state_t state) { int error; + gfp_t saved_mask; if (!suspend_ops) return -ENOSYS; @@ -199,6 +200,7 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); + saved_mask = clear_gfp_allowed_mask(GFP_IOFS); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -215,6 +217,7 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); + set_gfp_allowed_mask(saved_mask); resume_console(); Close: if (suspend_ops->end) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0734bedabd9c..298f307c63a1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -76,6 +76,31 @@ unsigned long totalreserve_pages __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; +#ifdef CONFIG_PM_SLEEP +/* + * The following functions are used by the suspend/hibernate code to temporarily + * change gfp_allowed_mask in order to avoid using I/O during memory allocations + * while devices are suspended. To avoid races with the suspend/hibernate code, + * they should always be called with pm_mutex held (gfp_allowed_mask also should + * only be modified with pm_mutex held, unless the suspend/hibernate code is + * guaranteed not to run in parallel with that modification). + */ +void set_gfp_allowed_mask(gfp_t mask) +{ + WARN_ON(!mutex_is_locked(&pm_mutex)); + gfp_allowed_mask = mask; +} + +gfp_t clear_gfp_allowed_mask(gfp_t mask) +{ + gfp_t ret = gfp_allowed_mask; + + WARN_ON(!mutex_is_locked(&pm_mutex)); + gfp_allowed_mask &= ~mask; + return ret; +} +#endif /* CONFIG_PM_SLEEP */ + #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE int pageblock_order __read_mostly; #endif -- cgit v1.2.3 From 87d5e0236d9d688fb575e9e12232764ac617617c Mon Sep 17 00:00:00 2001 From: Chen Gong Date: Fri, 5 Mar 2010 13:42:38 -0800 Subject: kernel/cpu.c: delete deprecated definition in cpu_up() Additional_cpus is only supported for IA64 now. X86_64 should not be included. Signed-off-by: Chen Gong Cc: Ingo Molnar Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index 677f25376a38..f8cced2692b3 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -338,7 +338,7 @@ int __cpuinit cpu_up(unsigned int cpu) if (!cpu_possible(cpu)) { printk(KERN_ERR "can't online cpu %d because it is not " "configured as may-hotadd at boot time\n", cpu); -#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) +#if defined(CONFIG_IA64) printk(KERN_ERR "please check additional_cpus= boot " "parameter\n"); #endif -- cgit v1.2.3 From 5f1664f92b2247111b7d37e454a050b76ac61b7f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 Mar 2010 13:42:51 -0800 Subject: splice: comparing unsigned int < 0 "ret" needs to be signed or the error handling for splice_to_pipe() won't work correctly. Signed-off-by: Dan Carpenter Cc: Tom Zanussi Cc: Jens Axboe Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/relay.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/relay.c b/kernel/relay.c index c705a41b4ba3..3d97f2821611 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1215,14 +1215,14 @@ static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i) /* * subbuf_splice_actor - splice up to one subbuf's worth of data */ -static int subbuf_splice_actor(struct file *in, +static ssize_t subbuf_splice_actor(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags, int *nonpad_ret) { - unsigned int pidx, poff, total_len, subbuf_pages, nr_pages, ret; + unsigned int pidx, poff, total_len, subbuf_pages, nr_pages; struct rchan_buf *rbuf = in->private_data; unsigned int subbuf_size = rbuf->chan->subbuf_size; uint64_t pos = (uint64_t) *ppos; @@ -1241,6 +1241,7 @@ static int subbuf_splice_actor(struct file *in, .ops = &relay_pipe_buf_ops, .spd_release = relay_page_release, }; + ssize_t ret; if (rbuf->subbufs_produced == rbuf->subbufs_consumed) return 0; -- cgit v1.2.3 From 9c03c383563f147907f1a90cf16f1e190e2f4aae Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 5 Mar 2010 13:42:52 -0800 Subject: includecheck fix for kernel/params.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following 'make includecheck' warning: kernel/params.c: linux/string.h is included more than once. Signed-off-by: Jaswinder Singh Rajput Cc: André Goddard Rosa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/params.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/params.c b/kernel/params.c index cf1b69183127..8d95f5451b22 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -24,7 +24,6 @@ #include #include #include -#include #if 0 #define DEBUGP printk -- cgit v1.2.3 From f3abd4f9531becb71626bd206955d47d5ea54f06 Mon Sep 17 00:00:00 2001 From: Thiago Farina Date: Fri, 5 Mar 2010 13:42:52 -0800 Subject: kernel/exit.c: fix shadows sparse warning kernel/exit.c:1183:26: warning: symbol 'status' shadows an earlier one kernel/exit.c:1173:21: originally declared here Signed-off-by: Thiago Farina Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index 10d3c5d5ae44..ce1e48c2d93d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1189,7 +1189,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) if (unlikely(wo->wo_flags & WNOWAIT)) { int exit_code = p->exit_code; - int why, status; + int why; get_task_struct(p); read_unlock(&tasklist_lock); -- cgit v1.2.3 From d4bb527438b4181cd3c564ae04dd344c381283a1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 5 Mar 2010 13:42:53 -0800 Subject: posix-cpu-timers: cleanup rlimits usage Fetch rlimit (both hard and soft) values only once and work on them. It removes many accesses through sig structure and makes the code cleaner. Mostly a preparation for writable resource limits support. Signed-off-by: Jiri Slaby Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/posix-cpu-timers.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 438ff4523513..dbb16bf15c45 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -982,6 +982,7 @@ static void check_thread_timers(struct task_struct *tsk, int maxfire; struct list_head *timers = tsk->cpu_timers; struct signal_struct *const sig = tsk->signal; + unsigned long soft; maxfire = 20; tsk->cputime_expires.prof_exp = cputime_zero; @@ -1030,9 +1031,9 @@ static void check_thread_timers(struct task_struct *tsk, /* * Check for the special case thread timers. */ - if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) { + soft = sig->rlim[RLIMIT_RTTIME].rlim_cur; + if (soft != RLIM_INFINITY) { unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max; - unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur; if (hard != RLIM_INFINITY && tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { @@ -1043,14 +1044,13 @@ static void check_thread_timers(struct task_struct *tsk, __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); return; } - if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) { + if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { /* * At the soft limit, send a SIGXCPU every second. */ - if (sig->rlim[RLIMIT_RTTIME].rlim_cur - < sig->rlim[RLIMIT_RTTIME].rlim_max) { - sig->rlim[RLIMIT_RTTIME].rlim_cur += - USEC_PER_SEC; + if (soft < hard) { + soft += USEC_PER_SEC; + sig->rlim[RLIMIT_RTTIME].rlim_cur = soft; } printk(KERN_INFO "RT Watchdog Timeout: %s[%d]\n", @@ -1121,6 +1121,7 @@ static void check_process_timers(struct task_struct *tsk, unsigned long long sum_sched_runtime, sched_expires; struct list_head *timers = sig->cpu_timers; struct task_cputime cputime; + unsigned long soft; /* * Don't sample the current process CPU clocks if there are no timers. @@ -1193,11 +1194,12 @@ static void check_process_timers(struct task_struct *tsk, SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, SIGVTALRM); - - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { + soft = sig->rlim[RLIMIT_CPU].rlim_cur; + if (soft != RLIM_INFINITY) { unsigned long psecs = cputime_to_secs(ptime); + unsigned long hard = sig->rlim[RLIMIT_CPU].rlim_max; cputime_t x; - if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) { + if (psecs >= hard) { /* * At the hard limit, we just die. * No need to calculate anything else now. @@ -1205,17 +1207,17 @@ static void check_process_timers(struct task_struct *tsk, __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); return; } - if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) { + if (psecs >= soft) { /* * At the soft limit, send a SIGXCPU every second. */ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); - if (sig->rlim[RLIMIT_CPU].rlim_cur - < sig->rlim[RLIMIT_CPU].rlim_max) { - sig->rlim[RLIMIT_CPU].rlim_cur++; + if (soft < hard) { + soft++; + sig->rlim[RLIMIT_CPU].rlim_cur = soft; } } - x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); + x = secs_to_cputime(soft); if (cputime_eq(prof_expires, cputime_zero) || cputime_lt(x, prof_expires)) { prof_expires = x; -- cgit v1.2.3 From 78d7d407b62a021e6d2e8dc24c0b90e390ab58a1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 5 Mar 2010 13:42:54 -0800 Subject: kernel core: use helpers for rlimits Make sure compiler won't do weird things with limits. E.g. fetching them twice may return 2 different values after writable limits are implemented. I.e. either use rlimit helpers added in commit 3e10e716abf3 ("resource: add helpers for fetching rlimits") or ACCESS_ONCE if not applicable. Signed-off-by: Jiri Slaby Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 10 ++++++---- kernel/perf_event.c | 2 +- kernel/posix-cpu-timers.c | 10 ++++++---- kernel/sched.c | 4 ++-- kernel/sched_rt.c | 5 +++-- kernel/signal.c | 2 +- kernel/sys.c | 3 +-- 7 files changed, 20 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index bab7b254ad39..b0ec34abc0bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -828,6 +828,8 @@ void __cleanup_sighand(struct sighand_struct *sighand) */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { + unsigned long cpu_limit; + /* Thread group counters. */ thread_group_cputime_init(sig); @@ -842,9 +844,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) sig->cputime_expires.virt_exp = cputime_zero; sig->cputime_expires.sched_exp = 0; - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - sig->cputime_expires.prof_exp = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); + cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + if (cpu_limit != RLIM_INFINITY) { + sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); sig->cputimer.running = 1; } @@ -1037,7 +1039,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif retval = -EAGAIN; if (atomic_read(&p->real_cred->user->processes) >= - p->signal->rlim[RLIMIT_NPROC].rlim_cur) { + task_rlimit(p, RLIMIT_NPROC)) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && p->real_cred->user != INIT_USER) goto bad_fork_free; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a661e7991865..8e352c756ba7 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2610,7 +2610,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (user_locked > user_lock_limit) extra = user_locked - user_lock_limit; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = vma->vm_mm->locked_vm + extra; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index dbb16bf15c45..1a22dfd42df9 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1031,9 +1031,10 @@ static void check_thread_timers(struct task_struct *tsk, /* * Check for the special case thread timers. */ - soft = sig->rlim[RLIMIT_RTTIME].rlim_cur; + soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur); if (soft != RLIM_INFINITY) { - unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max; + unsigned long hard = + ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); if (hard != RLIM_INFINITY && tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { @@ -1194,10 +1195,11 @@ static void check_process_timers(struct task_struct *tsk, SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, SIGVTALRM); - soft = sig->rlim[RLIMIT_CPU].rlim_cur; + soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (soft != RLIM_INFINITY) { unsigned long psecs = cputime_to_secs(ptime); - unsigned long hard = sig->rlim[RLIMIT_CPU].rlim_max; + unsigned long hard = + ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); cputime_t x; if (psecs >= hard) { /* diff --git a/kernel/sched.c b/kernel/sched.c index abb36b16b93b..b47ceeec1a91 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4353,7 +4353,7 @@ int can_nice(const struct task_struct *p, const int nice) /* convert nice value [19,-20] to rlimit style value [1,40] */ int nice_rlim = 20 - nice; - return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); } @@ -4530,7 +4530,7 @@ recheck: if (!lock_task_sighand(p, &flags)) return -ESRCH; - rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; + rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); unlock_task_sighand(p, &flags); /* can't set/change the rt policy */ diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index bf3e38fdbe6d..5a6ed1f0990a 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1662,8 +1662,9 @@ static void watchdog(struct rq *rq, struct task_struct *p) if (!p->signal) return; - soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur; - hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max; + /* max may change after cur was read, this will be fixed next tick */ + soft = task_rlimit(p, RLIMIT_RTTIME); + hard = task_rlimit_max(p, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { unsigned long next; diff --git a/kernel/signal.c b/kernel/signal.c index 5bb9baffa4f1..dbd7fe073c55 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -245,7 +245,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi if (override_rlimit || atomic_read(&user->sigpending) <= - t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) { + task_rlimit(t, RLIMIT_SIGPENDING)) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); diff --git a/kernel/sys.c b/kernel/sys.c index 877fe4f8e05e..9814e43fb23b 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -571,8 +571,7 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; - if (atomic_read(&new_user->processes) >= - current->signal->rlim[RLIMIT_NPROC].rlim_cur && + if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && new_user != INIT_USER) { free_uid(new_user); return -EAGAIN; -- cgit v1.2.3 From 8aeee85a29e27e043db582bf2ae8e5f42767934f Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 5 Mar 2010 13:42:55 -0800 Subject: panic: fix panic_timeout accuracy when running on a hypervisor I've had some complaints about panic_timeout being wildly innacurate on shared processor PowerPC partitions (a 3 minute panic_timeout taking 30 minutes). The problem is we loop on mdelay(1) and with a 1ms in 10ms hypervisor timeslice each of these will take 10ms (ie 10x) longer. I expect other platforms with shared processor hypervisors will see the same issue. This patch keeps the old behaviour if we have a panic_blink (only keyboard LEDs right now) and does 1 second mdelays if we don't. Signed-off-by: Anton Blanchard Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 46 ++++++++++++++++++++++++++++++---------------- 1 file changed, 30 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index c787333282b8..13d966b4c14a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -36,15 +36,36 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); -static long no_blink(long time) -{ - return 0; -} - /* Returns how long it waited in ms */ long (*panic_blink)(long time); EXPORT_SYMBOL(panic_blink); +static void panic_blink_one_second(void) +{ + static long i = 0, end; + + if (panic_blink) { + end = i + MSEC_PER_SEC; + + while (i < end) { + i += panic_blink(i); + mdelay(1); + i++; + } + } else { + /* + * When running under a hypervisor a small mdelay may get + * rounded up to the hypervisor timeslice. For example, with + * a 1ms in 10ms hypervisor timeslice we might inflate a + * mdelay(1) loop by 10x. + * + * If we have nothing to blink, spin on 1 second calls to + * mdelay to avoid this. + */ + mdelay(MSEC_PER_SEC); + } +} + /** * panic - halt the system * @fmt: The text string to print @@ -95,9 +116,6 @@ NORET_TYPE void panic(const char * fmt, ...) bust_spinlocks(0); - if (!panic_blink) - panic_blink = no_blink; - if (panic_timeout > 0) { /* * Delay timeout seconds before rebooting the machine. @@ -105,11 +123,9 @@ NORET_TYPE void panic(const char * fmt, ...) */ printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout); - for (i = 0; i < panic_timeout*1000; ) { + for (i = 0; i < panic_timeout; i++) { touch_nmi_watchdog(); - i += panic_blink(i); - mdelay(1); - i++; + panic_blink_one_second(); } /* * This will not be a clean reboot, with everything @@ -135,11 +151,9 @@ NORET_TYPE void panic(const char * fmt, ...) } #endif local_irq_enable(); - for (i = 0; ; ) { + while (1) { touch_softlockup_watchdog(); - i += panic_blink(i); - mdelay(1); - i++; + panic_blink_one_second(); } } -- cgit v1.2.3 From 9728e5d6e6c432ee8487c63ce6e479e2474d9945 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 5 Mar 2010 13:42:56 -0800 Subject: kernel/pid.c: update comment on find_task_by_pid_ns tasklist_lock does protect the task and its pid, it can't go away. The problem is that find_pid_ns() itself is unsafe without rcu lock, it can race with copy_process()->free_pid(any_pid). Protecting copy_process()->free_pid(any_pid) with tasklist_lock would make it possible to call find_task_by_pid_ns() under tasklist safely, but we don't do so because we are trying to get rid of the read_lock sites of tasklist_lock. Signed-off-by: Tetsuo Handa Cc: Oleg Nesterov Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/pid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/pid.c b/kernel/pid.c index b08e697cd83f..86b296943e5f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -376,7 +376,7 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type) EXPORT_SYMBOL(pid_task); /* - * Must be called under rcu_read_lock() or with tasklist_lock read-held. + * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { -- cgit v1.2.3 From cea83886dde49fd7524e9f4a246dd5dff4ad236a Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Fri, 5 Mar 2010 13:42:58 -0800 Subject: printk: avoid warning when CONFIG_PRINTK is disabled kernel/printk.c:72: warning: `saved_console_loglevel' defined but not used Signed-off-by: Gustavo F. Padovan Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/printk.c b/kernel/printk.c index 40674122ecf2..75077ad0b537 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -70,8 +70,6 @@ int console_printk[4] = { DEFAULT_CONSOLE_LOGLEVEL, /* default_console_loglevel */ }; -static int saved_console_loglevel = -1; - /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. @@ -146,6 +144,7 @@ static char __log_buf[__LOG_BUF_LEN]; static char *log_buf = __log_buf; static int log_buf_len = __LOG_BUF_LEN; static unsigned logged_chars; /* Number of chars produced since last read+clear operation */ +static int saved_console_loglevel = -1; #ifdef CONFIG_KEXEC /* -- cgit v1.2.3 From 1fcccbac89f5bbc5e41aa72086960059fce372da Mon Sep 17 00:00:00 2001 From: Daisuke HATAYAMA Date: Fri, 5 Mar 2010 13:44:07 -0800 Subject: elf coredump: replace ELF_CORE_EXTRA_* macros by functions elf_core_dump() and elf_fdpic_core_dump() use #ifdef and the corresponding macro for hiding _multiline_ logics in functions. This patch removes #ifdef and replaces ELF_CORE_EXTRA_* by corresponding functions. For architectures not implemeonting ELF_CORE_EXTRA_*, we use weak functions in order to reduce a range of modification. This cleanup is for my next patches, but I think this cleanup itself is worth doing regardless of my firnal purpose. Signed-off-by: Daisuke HATAYAMA Cc: "Luck, Tony" Cc: Jeff Dike Cc: David Howells Cc: Greg Ungerer Cc: Roland McGrath Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Alexander Viro Cc: Andi Kleen Cc: Alan Cox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/elf.h | 48 -------------------------------- arch/ia64/kernel/Makefile | 2 ++ arch/ia64/kernel/elfcore.c | 64 +++++++++++++++++++++++++++++++++++++++++++ arch/um/sys-i386/Makefile | 2 ++ arch/um/sys-i386/asm/elf.h | 43 ----------------------------- arch/um/sys-i386/elfcore.c | 67 +++++++++++++++++++++++++++++++++++++++++++++ fs/binfmt_elf.c | 14 ++++------ fs/binfmt_elf_fdpic.c | 14 ++++------ fs/compat_binfmt_elf.c | 2 ++ include/linux/elf.h | 2 ++ include/linux/elfcore.h | 16 +++++++++++ kernel/Makefile | 3 ++ kernel/elfcore.c | 23 ++++++++++++++++ 13 files changed, 191 insertions(+), 109 deletions(-) create mode 100644 arch/ia64/kernel/elfcore.c create mode 100644 arch/um/sys-i386/elfcore.c create mode 100644 kernel/elfcore.c (limited to 'kernel') diff --git a/arch/ia64/include/asm/elf.h b/arch/ia64/include/asm/elf.h index 4c41656ede87..b5298eb09adb 100644 --- a/arch/ia64/include/asm/elf.h +++ b/arch/ia64/include/asm/elf.h @@ -219,54 +219,6 @@ do { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, (unsigned long) GATE_EHDR); \ } while (0) - -/* - * These macros parameterize elf_core_dump in fs/binfmt_elf.c to write out - * extra segments containing the gate DSO contents. Dumping its - * contents makes post-mortem fully interpretable later without matching up - * the same kernel and hardware config to see what PC values meant. - * Dumping its extra ELF program headers includes all the other information - * a debugger needs to easily find how the gate DSO was being used. - */ -#define ELF_CORE_EXTRA_PHDRS (GATE_EHDR->e_phnum) -#define ELF_CORE_WRITE_EXTRA_PHDRS \ -do { \ - const struct elf_phdr *const gate_phdrs = \ - (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); \ - int i; \ - Elf64_Off ofs = 0; \ - for (i = 0; i < GATE_EHDR->e_phnum; ++i) { \ - struct elf_phdr phdr = gate_phdrs[i]; \ - if (phdr.p_type == PT_LOAD) { \ - phdr.p_memsz = PAGE_ALIGN(phdr.p_memsz); \ - phdr.p_filesz = phdr.p_memsz; \ - if (ofs == 0) { \ - ofs = phdr.p_offset = offset; \ - offset += phdr.p_filesz; \ - } \ - else \ - phdr.p_offset = ofs; \ - } \ - else \ - phdr.p_offset += ofs; \ - phdr.p_paddr = 0; /* match other core phdrs */ \ - DUMP_WRITE(&phdr, sizeof(phdr)); \ - } \ -} while (0) -#define ELF_CORE_WRITE_EXTRA_DATA \ -do { \ - const struct elf_phdr *const gate_phdrs = \ - (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); \ - int i; \ - for (i = 0; i < GATE_EHDR->e_phnum; ++i) { \ - if (gate_phdrs[i].p_type == PT_LOAD) { \ - DUMP_WRITE((void *) gate_phdrs[i].p_vaddr, \ - PAGE_ALIGN(gate_phdrs[i].p_memsz)); \ - break; \ - } \ - } \ -} while (0) - /* * format for entries in the Global Offset Table */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 4138282aefa8..db10b1e378b0 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -45,6 +45,8 @@ endif obj-$(CONFIG_DMAR) += pci-dma.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o +obj-$(CONFIG_BINFMT_ELF) += elfcore.o + # fp_emulate() expects f2-f5,f16-f31 to contain the user-level state. CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31 diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c new file mode 100644 index 000000000000..57a2298a8581 --- /dev/null +++ b/arch/ia64/kernel/elfcore.c @@ -0,0 +1,64 @@ +#include +#include +#include +#include + +#include + + +Elf64_Half elf_core_extra_phdrs(void) +{ + return GATE_EHDR->e_phnum; +} + +int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, + unsigned long limit) +{ + const struct elf_phdr *const gate_phdrs = + (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); + int i; + Elf64_Off ofs = 0; + + for (i = 0; i < GATE_EHDR->e_phnum; ++i) { + struct elf_phdr phdr = gate_phdrs[i]; + + if (phdr.p_type == PT_LOAD) { + phdr.p_memsz = PAGE_ALIGN(phdr.p_memsz); + phdr.p_filesz = phdr.p_memsz; + if (ofs == 0) { + ofs = phdr.p_offset = offset; + offset += phdr.p_filesz; + } else { + phdr.p_offset = ofs; + } + } else { + phdr.p_offset += ofs; + } + phdr.p_paddr = 0; /* match other core phdrs */ + *size += sizeof(phdr); + if (*size > limit || !dump_write(file, &phdr, sizeof(phdr))) + return 0; + } + return 1; +} + +int elf_core_write_extra_data(struct file *file, size_t *size, + unsigned long limit) +{ + const struct elf_phdr *const gate_phdrs = + (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); + int i; + + for (i = 0; i < GATE_EHDR->e_phnum; ++i) { + if (gate_phdrs[i].p_type == PT_LOAD) { + void *addr = (void *)gate_phdrs[i].p_vaddr; + size_t memsz = PAGE_ALIGN(gate_phdrs[i].p_memsz); + + *size += memsz; + if (*size > limit || !dump_write(file, addr, memsz)) + return 0; + break; + } + } + return 1; +} diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile index 1b549bca4645..804b28dd0328 100644 --- a/arch/um/sys-i386/Makefile +++ b/arch/um/sys-i386/Makefile @@ -6,6 +6,8 @@ obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \ ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \ sys_call_table.o tls.o +obj-$(CONFIG_BINFMT_ELF) += elfcore.o + subarch-obj-y = lib/semaphore_32.o lib/string_32.o subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem_32.o subarch-obj-$(CONFIG_MODULES) += kernel/module.o diff --git a/arch/um/sys-i386/asm/elf.h b/arch/um/sys-i386/asm/elf.h index 770885472ed4..e64cd41d7bab 100644 --- a/arch/um/sys-i386/asm/elf.h +++ b/arch/um/sys-i386/asm/elf.h @@ -116,47 +116,4 @@ do { \ } \ } while (0) -/* - * These macros parameterize elf_core_dump in fs/binfmt_elf.c to write out - * extra segments containing the vsyscall DSO contents. Dumping its - * contents makes post-mortem fully interpretable later without matching up - * the same kernel and hardware config to see what PC values meant. - * Dumping its extra ELF program headers includes all the other information - * a debugger needs to easily find how the vsyscall DSO was being used. - */ -#define ELF_CORE_EXTRA_PHDRS \ - (vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0 ) - -#define ELF_CORE_WRITE_EXTRA_PHDRS \ -if ( vsyscall_ehdr ) { \ - const struct elfhdr *const ehdrp = (struct elfhdr *)vsyscall_ehdr; \ - const struct elf_phdr *const phdrp = \ - (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); \ - int i; \ - Elf32_Off ofs = 0; \ - for (i = 0; i < ehdrp->e_phnum; ++i) { \ - struct elf_phdr phdr = phdrp[i]; \ - if (phdr.p_type == PT_LOAD) { \ - ofs = phdr.p_offset = offset; \ - offset += phdr.p_filesz; \ - } \ - else \ - phdr.p_offset += ofs; \ - phdr.p_paddr = 0; /* match other core phdrs */ \ - DUMP_WRITE(&phdr, sizeof(phdr)); \ - } \ -} -#define ELF_CORE_WRITE_EXTRA_DATA \ -if ( vsyscall_ehdr ) { \ - const struct elfhdr *const ehdrp = (struct elfhdr *)vsyscall_ehdr; \ - const struct elf_phdr *const phdrp = \ - (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); \ - int i; \ - for (i = 0; i < ehdrp->e_phnum; ++i) { \ - if (phdrp[i].p_type == PT_LOAD) \ - DUMP_WRITE((void *) phdrp[i].p_vaddr, \ - phdrp[i].p_filesz); \ - } \ -} - #endif diff --git a/arch/um/sys-i386/elfcore.c b/arch/um/sys-i386/elfcore.c new file mode 100644 index 000000000000..30cac52a04b4 --- /dev/null +++ b/arch/um/sys-i386/elfcore.c @@ -0,0 +1,67 @@ +#include +#include +#include +#include + +#include + + +Elf32_Half elf_core_extra_phdrs(void) +{ + return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; +} + +int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, + unsigned long limit) +{ + if ( vsyscall_ehdr ) { + const struct elfhdr *const ehdrp = + (struct elfhdr *) vsyscall_ehdr; + const struct elf_phdr *const phdrp = + (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); + int i; + Elf32_Off ofs = 0; + + for (i = 0; i < ehdrp->e_phnum; ++i) { + struct elf_phdr phdr = phdrp[i]; + + if (phdr.p_type == PT_LOAD) { + ofs = phdr.p_offset = offset; + offset += phdr.p_filesz; + } else { + phdr.p_offset += ofs; + } + phdr.p_paddr = 0; /* match other core phdrs */ + *size += sizeof(phdr); + if (*size > limit + || !dump_write(file, &phdr, sizeof(phdr))) + return 0; + } + } + return 1; +} + +int elf_core_write_extra_data(struct file *file, size_t *size, + unsigned long limit) +{ + if ( vsyscall_ehdr ) { + const struct elfhdr *const ehdrp = + (struct elfhdr *) vsyscall_ehdr; + const struct elf_phdr *const phdrp = + (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); + int i; + + for (i = 0; i < ehdrp->e_phnum; ++i) { + if (phdrp[i].p_type == PT_LOAD) { + void *addr = (void *) phdrp[i].p_vaddr; + size_t filesz = phdrp[i].p_filesz; + + *size += filesz; + if (*size > limit + || !dump_write(file, addr, filesz)) + return 0; + } + } + } + return 1; +} diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0bcfbb05c32d..c1a499599b7d 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1878,9 +1878,7 @@ static int elf_core_dump(struct coredump_params *cprm) * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here. */ segs = current->mm->map_count; -#ifdef ELF_CORE_EXTRA_PHDRS - segs += ELF_CORE_EXTRA_PHDRS; -#endif + segs += elf_core_extra_phdrs(); gate_vma = get_gate_vma(current); if (gate_vma != NULL) @@ -1958,9 +1956,8 @@ static int elf_core_dump(struct coredump_params *cprm) goto end_coredump; } -#ifdef ELF_CORE_WRITE_EXTRA_PHDRS - ELF_CORE_WRITE_EXTRA_PHDRS; -#endif + if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit)) + goto end_coredump; /* write out the notes section */ if (!write_note_info(&info, cprm->file, &foffset)) @@ -1999,9 +1996,8 @@ static int elf_core_dump(struct coredump_params *cprm) } } -#ifdef ELF_CORE_WRITE_EXTRA_DATA - ELF_CORE_WRITE_EXTRA_DATA; -#endif + if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit)) + goto end_coredump; end_coredump: set_fs(fs); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 63edf40b569b..952699a86ec3 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1664,9 +1664,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) elf_core_copy_regs(&prstatus->pr_reg, cprm->regs); segs = current->mm->map_count; -#ifdef ELF_CORE_EXTRA_PHDRS - segs += ELF_CORE_EXTRA_PHDRS; -#endif + segs += elf_core_extra_phdrs(); /* Set up header */ fill_elf_fdpic_header(elf, segs + 1); /* including notes section */ @@ -1773,9 +1771,8 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) goto end_coredump; } -#ifdef ELF_CORE_WRITE_EXTRA_PHDRS - ELF_CORE_WRITE_EXTRA_PHDRS; -#endif + if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit)) + goto end_coredump; /* write out the notes section */ for (i = 0; i < numnote; i++) @@ -1799,9 +1796,8 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) mm_flags) < 0) goto end_coredump; -#ifdef ELF_CORE_WRITE_EXTRA_DATA - ELF_CORE_WRITE_EXTRA_DATA; -#endif + if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit)) + goto end_coredump; if (cprm->file->f_pos != offset) { /* Sanity check */ diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 0adced2f296f..112e45a17e99 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -28,10 +28,12 @@ #undef elfhdr #undef elf_phdr +#undef elf_shdr #undef elf_note #undef elf_addr_t #define elfhdr elf32_hdr #define elf_phdr elf32_phdr +#define elf_shdr elf32_shdr #define elf_note elf32_note #define elf_addr_t Elf32_Addr diff --git a/include/linux/elf.h b/include/linux/elf.h index ad990c5f63f6..ccde3fd45f36 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -396,6 +396,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_phdr elf32_phdr #define elf_note elf32_note #define elf_addr_t Elf32_Off +#define Elf_Half Elf32_Half #else @@ -404,6 +405,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_phdr elf64_phdr #define elf_note elf64_note #define elf_addr_t Elf64_Off +#define Elf_Half Elf64_Half #endif diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 00d6a68d0421..cfda74f521b5 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -8,6 +8,8 @@ #include #endif #include +#include +#include struct elf_siginfo { @@ -150,5 +152,19 @@ static inline int elf_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregse #endif /* __KERNEL__ */ +/* + * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out + * extra segments containing the gate DSO contents. Dumping its + * contents makes post-mortem fully interpretable later without matching up + * the same kernel and hardware config to see what PC values meant. + * Dumping its extra ELF program headers includes all the other information + * a debugger needs to easily find how the gate DSO was being used. + */ +extern Elf_Half elf_core_extra_phdrs(void); +extern int +elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, + unsigned long limit); +extern int +elf_core_write_extra_data(struct file *file, size_t *size, unsigned long limit); #endif /* _LINUX_ELFCORE_H */ diff --git a/kernel/Makefile b/kernel/Makefile index 7b974699f8c2..a987aa1676b5 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -91,6 +91,9 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_X86_DS) += trace/ diff --git a/kernel/elfcore.c b/kernel/elfcore.c new file mode 100644 index 000000000000..5445741f4b4c --- /dev/null +++ b/kernel/elfcore.c @@ -0,0 +1,23 @@ +#include +#include +#include + +#include + + +Elf_Half __weak elf_core_extra_phdrs(void) +{ + return 0; +} + +int __weak elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, + unsigned long limit) +{ + return 1; +} + +int __weak elf_core_write_extra_data(struct file *file, size_t *size, + unsigned long limit) +{ + return 1; +} -- cgit v1.2.3 From 8d9032bbe4671dc481261ccd4e161cd96e54b118 Mon Sep 17 00:00:00 2001 From: Daisuke HATAYAMA Date: Fri, 5 Mar 2010 13:44:10 -0800 Subject: elf coredump: add extended numbering support The current ELF dumper implementation can produce broken corefiles if program headers exceed 65535. This number is determined by the number of vmas which the process have. In particular, some extreme programs may use more than 65535 vmas. (If you google max_map_count, you can find some users facing this problem.) This kind of program never be able to generate correct coredumps. This patch implements ``extended numbering'' that uses sh_info field of the first section header instead of e_phnum field in order to represent upto 4294967295 vmas. This is supported by AMD64-ABI(http://www.x86-64.org/documentation.html) and Solaris(http://docs.sun.com/app/docs/doc/817-1984/). Of course, we are preparing patches for gdb and binutils. Signed-off-by: Daisuke HATAYAMA Cc: "Luck, Tony" Cc: Jeff Dike Cc: David Howells Cc: Greg Ungerer Cc: Roland McGrath Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Alexander Viro Cc: Andi Kleen Cc: Alan Cox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/elfcore.c | 16 +++++++++++ arch/um/sys-i386/elfcore.c | 16 +++++++++++ fs/binfmt_elf.c | 66 +++++++++++++++++++++++++++++++++++++++++++--- fs/binfmt_elf_fdpic.c | 63 +++++++++++++++++++++++++++++++++++++++++-- include/linux/elf.h | 26 +++++++++++++++++- include/linux/elfcore.h | 1 + kernel/elfcore.c | 5 ++++ 7 files changed, 187 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c index 57a2298a8581..bac1639bc320 100644 --- a/arch/ia64/kernel/elfcore.c +++ b/arch/ia64/kernel/elfcore.c @@ -62,3 +62,19 @@ int elf_core_write_extra_data(struct file *file, size_t *size, } return 1; } + +size_t elf_core_extra_data_size(void) +{ + const struct elf_phdr *const gate_phdrs = + (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); + int i; + size_t size = 0; + + for (i = 0; i < GATE_EHDR->e_phnum; ++i) { + if (gate_phdrs[i].p_type == PT_LOAD) { + size += PAGE_ALIGN(gate_phdrs[i].p_memsz); + break; + } + } + return size; +} diff --git a/arch/um/sys-i386/elfcore.c b/arch/um/sys-i386/elfcore.c index 30cac52a04b4..6bb49b687c97 100644 --- a/arch/um/sys-i386/elfcore.c +++ b/arch/um/sys-i386/elfcore.c @@ -65,3 +65,19 @@ int elf_core_write_extra_data(struct file *file, size_t *size, } return 1; } + +size_t elf_core_extra_data_size(void) +{ + if ( vsyscall_ehdr ) { + const struct elfhdr *const ehdrp = + (struct elfhdr *)vsyscall_ehdr; + const struct elf_phdr *const phdrp = + (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); + int i; + + for (i = 0; i < ehdrp->e_phnum; ++i) + if (phdrp[i].p_type == PT_LOAD) + return (size_t) phdrp[i].p_filesz; + } + return 0; +} diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6fc49b6ed936..78de530cfb02 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1838,6 +1838,34 @@ static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma, return gate_vma; } +static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum, + elf_addr_t e_shoff, int segs) +{ + elf->e_shoff = e_shoff; + elf->e_shentsize = sizeof(*shdr4extnum); + elf->e_shnum = 1; + elf->e_shstrndx = SHN_UNDEF; + + memset(shdr4extnum, 0, sizeof(*shdr4extnum)); + + shdr4extnum->sh_type = SHT_NULL; + shdr4extnum->sh_size = elf->e_shnum; + shdr4extnum->sh_link = elf->e_shstrndx; + shdr4extnum->sh_info = segs; +} + +static size_t elf_core_vma_data_size(struct vm_area_struct *gate_vma, + unsigned long mm_flags) +{ + struct vm_area_struct *vma; + size_t size = 0; + + for (vma = first_vma(current, gate_vma); vma != NULL; + vma = next_vma(vma, gate_vma)) + size += vma_dump_size(vma, mm_flags); + return size; +} + /* * Actual dumper * @@ -1857,6 +1885,9 @@ static int elf_core_dump(struct coredump_params *cprm) unsigned long mm_flags; struct elf_note_info info; struct elf_phdr *phdr4note = NULL; + struct elf_shdr *shdr4extnum = NULL; + Elf_Half e_phnum; + elf_addr_t e_shoff; /* * We no longer stop all VM operations. @@ -1885,12 +1916,19 @@ static int elf_core_dump(struct coredump_params *cprm) if (gate_vma != NULL) segs++; + /* for notes section */ + segs++; + + /* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid + * this, kernel supports extended numbering. Have a look at + * include/linux/elf.h for further information. */ + e_phnum = segs > PN_XNUM ? PN_XNUM : segs; + /* * Collect all the non-memory information about the process for the * notes. This also sets up the file header. */ - if (!fill_note_info(elf, segs + 1, /* including notes section */ - &info, cprm->signr, cprm->regs)) + if (!fill_note_info(elf, e_phnum, &info, cprm->signr, cprm->regs)) goto cleanup; has_dumped = 1; @@ -1900,7 +1938,7 @@ static int elf_core_dump(struct coredump_params *cprm) set_fs(KERNEL_DS); offset += sizeof(*elf); /* Elf header */ - offset += (segs + 1) * sizeof(struct elf_phdr); /* Program headers */ + offset += segs * sizeof(struct elf_phdr); /* Program headers */ foffset = offset; /* Write notes phdr entry */ @@ -1926,6 +1964,19 @@ static int elf_core_dump(struct coredump_params *cprm) */ mm_flags = current->mm->flags; + offset += elf_core_vma_data_size(gate_vma, mm_flags); + offset += elf_core_extra_data_size(); + e_shoff = offset; + + if (e_phnum == PN_XNUM) { + shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL); + if (!shdr4extnum) + goto end_coredump; + fill_extnum_info(elf, shdr4extnum, e_shoff, segs); + } + + offset = dataoff; + size += sizeof(*elf); if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf))) goto end_coredump; @@ -2003,11 +2054,20 @@ static int elf_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit)) goto end_coredump; + if (e_phnum == PN_XNUM) { + size += sizeof(*shdr4extnum); + if (size > cprm->limit + || !dump_write(cprm->file, shdr4extnum, + sizeof(*shdr4extnum))) + goto end_coredump; + } + end_coredump: set_fs(fs); cleanup: free_note_info(&info); + kfree(shdr4extnum); kfree(phdr4note); kfree(elf); out: diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 112da491d75d..e49d9c06a4b6 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1505,6 +1505,22 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) return sz; } +static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum, + elf_addr_t e_shoff, int segs) +{ + elf->e_shoff = e_shoff; + elf->e_shentsize = sizeof(*shdr4extnum); + elf->e_shnum = 1; + elf->e_shstrndx = SHN_UNDEF; + + memset(shdr4extnum, 0, sizeof(*shdr4extnum)); + + shdr4extnum->sh_type = SHT_NULL; + shdr4extnum->sh_size = elf->e_shnum; + shdr4extnum->sh_link = elf->e_shstrndx; + shdr4extnum->sh_info = segs; +} + /* * dump the segments for an MMU process */ @@ -1569,6 +1585,17 @@ static int elf_fdpic_dump_segments(struct file *file, size_t *size, } #endif +static size_t elf_core_vma_data_size(unsigned long mm_flags) +{ + struct vm_area_struct *vma; + size_t size = 0; + + for (vma = current->mm->mmap; vma; vma->vm_next) + if (maydump(vma, mm_flags)) + size += vma->vm_end - vma->vm_start; + return size; +} + /* * Actual dumper * @@ -1601,6 +1628,9 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) elf_addr_t *auxv; unsigned long mm_flags; struct elf_phdr *phdr4note = NULL; + struct elf_shdr *shdr4extnum = NULL; + Elf_Half e_phnum; + elf_addr_t e_shoff; /* * We no longer stop all VM operations. @@ -1667,8 +1697,16 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) segs = current->mm->map_count; segs += elf_core_extra_phdrs(); + /* for notes section */ + segs++; + + /* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid + * this, kernel supports extended numbering. Have a look at + * include/linux/elf.h for further information. */ + e_phnum = segs > PN_XNUM ? PN_XNUM : segs; + /* Set up header */ - fill_elf_fdpic_header(elf, segs + 1); /* including notes section */ + fill_elf_fdpic_header(elf, e_phnum); has_dumped = 1; current->flags |= PF_DUMPCORE; @@ -1708,7 +1746,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) set_fs(KERNEL_DS); offset += sizeof(*elf); /* Elf header */ - offset += (segs+1) * sizeof(struct elf_phdr); /* Program headers */ + offset += segs * sizeof(struct elf_phdr); /* Program headers */ foffset = offset; /* Write notes phdr entry */ @@ -1738,6 +1776,19 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) */ mm_flags = current->mm->flags; + offset += elf_core_vma_data_size(mm_flags); + offset += elf_core_extra_data_size(); + e_shoff = offset; + + if (e_phnum == PN_XNUM) { + shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL); + if (!shdr4extnum) + goto end_coredump; + fill_extnum_info(elf, shdr4extnum, e_shoff, segs); + } + + offset = dataoff; + size += sizeof(*elf); if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf))) goto end_coredump; @@ -1802,6 +1853,14 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit)) goto end_coredump; + if (e_phnum == PN_XNUM) { + size += sizeof(*shdr4extnum); + if (size > cprm->limit + || !dump_write(cprm->file, shdr4extnum, + sizeof(*shdr4extnum))) + goto end_coredump; + } + if (cprm->file->f_pos != offset) { /* Sanity check */ printk(KERN_WARNING diff --git a/include/linux/elf.h b/include/linux/elf.h index ccde3fd45f36..597858418051 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -50,6 +50,28 @@ typedef __s64 Elf64_Sxword; #define PT_GNU_STACK (PT_LOOS + 0x474e551) +/* + * Extended Numbering + * + * If the real number of program header table entries is larger than + * or equal to PN_XNUM(0xffff), it is set to sh_info field of the + * section header at index 0, and PN_XNUM is set to e_phnum + * field. Otherwise, the section header at index 0 is zero + * initialized, if it exists. + * + * Specifications are available in: + * + * - Sun microsystems: Linker and Libraries. + * Part No: 817-1984-17, September 2008. + * URL: http://docs.sun.com/app/docs/doc/817-1984 + * + * - System V ABI AMD64 Architecture Processor Supplement + * Draft Version 0.99., + * May 11, 2009. + * URL: http://www.x86-64.org/ + */ +#define PN_XNUM 0xffff + /* These constants define the different elf file types */ #define ET_NONE 0 #define ET_REL 1 @@ -286,7 +308,7 @@ typedef struct elf64_phdr { #define SHN_COMMON 0xfff2 #define SHN_HIRESERVE 0xffff -typedef struct { +typedef struct elf32_shdr { Elf32_Word sh_name; Elf32_Word sh_type; Elf32_Word sh_flags; @@ -394,6 +416,7 @@ typedef struct elf64_note { extern Elf32_Dyn _DYNAMIC []; #define elfhdr elf32_hdr #define elf_phdr elf32_phdr +#define elf_shdr elf32_shdr #define elf_note elf32_note #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half @@ -403,6 +426,7 @@ extern Elf32_Dyn _DYNAMIC []; extern Elf64_Dyn _DYNAMIC []; #define elfhdr elf64_hdr #define elf_phdr elf64_phdr +#define elf_shdr elf64_shdr #define elf_note elf64_note #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index cfda74f521b5..e687bc3ba4da 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -166,5 +166,6 @@ elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, unsigned long limit); extern int elf_core_write_extra_data(struct file *file, size_t *size, unsigned long limit); +extern size_t elf_core_extra_data_size(void); #endif /* _LINUX_ELFCORE_H */ diff --git a/kernel/elfcore.c b/kernel/elfcore.c index 5445741f4b4c..ff915efef66d 100644 --- a/kernel/elfcore.c +++ b/kernel/elfcore.c @@ -21,3 +21,8 @@ int __weak elf_core_write_extra_data(struct file *file, size_t *size, { return 1; } + +size_t __weak elf_core_extra_data_size(void) +{ + return 0; +} -- cgit v1.2.3 From c9be0a36f9bf392a7984473124a67a12964df11f Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 5 Jan 2010 12:47:58 +0100 Subject: sysdev: Pass attribute in sysdev_class attributes show/store Passing the attribute to the low level IO functions allows all kinds of cleanups, by sharing low level IO code without requiring an own function for every piece of data. Also drivers can extend the attributes with own data fields and use that in the low level function. Similar to sysdev_attributes and normal attributes. This is a tree-wide sweep, converting everything in one go. No functional changes in this patch other than passing the new argument everywhere. Tested on x86, the non x86 parts are uncompiled. Signed-off-by: Andi Kleen Signed-off-by: Greg Kroah-Hartman --- arch/mips/txx9/generic/7segled.c | 5 +++- arch/s390/kernel/smp.c | 8 +++++-- arch/s390/kernel/time.c | 49 ++++++++++++++++++++++++++++++---------- drivers/base/cpu.c | 9 +++++--- drivers/base/node.c | 17 ++++++++++---- drivers/base/sys.c | 4 ++-- drivers/cpuidle/sysfs.c | 4 ++++ include/linux/sysdev.h | 6 +++-- kernel/perf_event.c | 13 ++++++++--- kernel/sched.c | 4 ++++ 10 files changed, 89 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/arch/mips/txx9/generic/7segled.c b/arch/mips/txx9/generic/7segled.c index 727ab21b6618..7f8416f86222 100644 --- a/arch/mips/txx9/generic/7segled.c +++ b/arch/mips/txx9/generic/7segled.c @@ -58,13 +58,16 @@ static ssize_t raw_store(struct sys_device *dev, static SYSDEV_ATTR(ascii, 0200, NULL, ascii_store); static SYSDEV_ATTR(raw, 0200, NULL, raw_store); -static ssize_t map_seg7_show(struct sysdev_class *class, char *buf) +static ssize_t map_seg7_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { memcpy(buf, &txx9_seg7map, sizeof(txx9_seg7map)); return sizeof(txx9_seg7map); } static ssize_t map_seg7_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t size) { if (size != sizeof(txx9_seg7map)) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 8b10127c00ad..e2121099f03b 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1020,7 +1020,9 @@ out: return rc; } -static ssize_t __ref rescan_store(struct sysdev_class *class, const char *buf, +static ssize_t __ref rescan_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + const char *buf, size_t count) { int rc; @@ -1041,7 +1043,9 @@ static ssize_t dispatching_show(struct sysdev_class *class, char *buf) return count; } -static ssize_t dispatching_store(struct sysdev_class *dev, const char *buf, +static ssize_t dispatching_store(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, + const char *buf, size_t count) { int val, rc; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index a8f93f1705ad..75894c281710 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -1116,14 +1116,18 @@ static struct sys_device etr_port1_dev = { /* * ETR class attributes */ -static ssize_t etr_stepping_port_show(struct sysdev_class *class, char *buf) +static ssize_t etr_stepping_port_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { return sprintf(buf, "%i\n", etr_port0.esw.p); } static SYSDEV_CLASS_ATTR(stepping_port, 0400, etr_stepping_port_show, NULL); -static ssize_t etr_stepping_mode_show(struct sysdev_class *class, char *buf) +static ssize_t etr_stepping_mode_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { char *mode_str; @@ -1584,7 +1588,9 @@ static struct sysdev_class stp_sysclass = { .name = "stp", }; -static ssize_t stp_ctn_id_show(struct sysdev_class *class, char *buf) +static ssize_t stp_ctn_id_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online) return -ENODATA; @@ -1594,7 +1600,9 @@ static ssize_t stp_ctn_id_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL); -static ssize_t stp_ctn_type_show(struct sysdev_class *class, char *buf) +static ssize_t stp_ctn_type_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online) return -ENODATA; @@ -1603,7 +1611,9 @@ static ssize_t stp_ctn_type_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL); -static ssize_t stp_dst_offset_show(struct sysdev_class *class, char *buf) +static ssize_t stp_dst_offset_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online || !(stp_info.vbits & 0x2000)) return -ENODATA; @@ -1612,7 +1622,9 @@ static ssize_t stp_dst_offset_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL); -static ssize_t stp_leap_seconds_show(struct sysdev_class *class, char *buf) +static ssize_t stp_leap_seconds_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online || !(stp_info.vbits & 0x8000)) return -ENODATA; @@ -1621,7 +1633,9 @@ static ssize_t stp_leap_seconds_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL); -static ssize_t stp_stratum_show(struct sysdev_class *class, char *buf) +static ssize_t stp_stratum_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online) return -ENODATA; @@ -1630,7 +1644,9 @@ static ssize_t stp_stratum_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(stratum, 0400, stp_stratum_show, NULL); -static ssize_t stp_time_offset_show(struct sysdev_class *class, char *buf) +static ssize_t stp_time_offset_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online || !(stp_info.vbits & 0x0800)) return -ENODATA; @@ -1639,7 +1655,9 @@ static ssize_t stp_time_offset_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(time_offset, 0400, stp_time_offset_show, NULL); -static ssize_t stp_time_zone_offset_show(struct sysdev_class *class, char *buf) +static ssize_t stp_time_zone_offset_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online || !(stp_info.vbits & 0x4000)) return -ENODATA; @@ -1649,7 +1667,9 @@ static ssize_t stp_time_zone_offset_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(time_zone_offset, 0400, stp_time_zone_offset_show, NULL); -static ssize_t stp_timing_mode_show(struct sysdev_class *class, char *buf) +static ssize_t stp_timing_mode_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online) return -ENODATA; @@ -1658,7 +1678,9 @@ static ssize_t stp_timing_mode_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL); -static ssize_t stp_timing_state_show(struct sysdev_class *class, char *buf) +static ssize_t stp_timing_state_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { if (!stp_online) return -ENODATA; @@ -1667,12 +1689,15 @@ static ssize_t stp_timing_state_show(struct sysdev_class *class, char *buf) static SYSDEV_CLASS_ATTR(timing_state, 0400, stp_timing_state_show, NULL); -static ssize_t stp_online_show(struct sysdev_class *class, char *buf) +static ssize_t stp_online_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { return sprintf(buf, "%i\n", stp_online); } static ssize_t stp_online_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { unsigned int value; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 958bd1540c30..fd1b2f9b7b8f 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -151,7 +151,8 @@ static ssize_t print_cpus_map(char *buf, const struct cpumask *map) } #define print_cpus_func(type) \ -static ssize_t print_cpus_##type(struct sysdev_class *class, char *buf) \ +static ssize_t print_cpus_##type(struct sysdev_class *class, \ + struct sysdev_class_attribute *attr, char *buf) \ { \ return print_cpus_map(buf, cpu_##type##_mask); \ } \ @@ -165,7 +166,8 @@ print_cpus_func(present); /* * Print values for NR_CPUS and offlined cpus */ -static ssize_t print_cpus_kernel_max(struct sysdev_class *class, char *buf) +static ssize_t print_cpus_kernel_max(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1); return n; @@ -175,7 +177,8 @@ static SYSDEV_CLASS_ATTR(kernel_max, 0444, print_cpus_kernel_max, NULL); /* arch-optional setting to enable display of offline cpus >= nr_cpu_ids */ unsigned int total_cpus; -static ssize_t print_cpus_offline(struct sysdev_class *class, char *buf) +static ssize_t print_cpus_offline(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { int n = 0, len = PAGE_SIZE-2; cpumask_var_t offline; diff --git a/drivers/base/node.c b/drivers/base/node.c index 70122791683d..85c9d30d7004 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -544,23 +544,29 @@ static ssize_t print_nodes_state(enum node_states state, char *buf) return n; } -static ssize_t print_nodes_possible(struct sysdev_class *class, char *buf) +static ssize_t print_nodes_possible(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { return print_nodes_state(N_POSSIBLE, buf); } -static ssize_t print_nodes_online(struct sysdev_class *class, char *buf) +static ssize_t print_nodes_online(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { return print_nodes_state(N_ONLINE, buf); } static ssize_t print_nodes_has_normal_memory(struct sysdev_class *class, - char *buf) + struct sysdev_class_attribute *attr, + char *buf) { return print_nodes_state(N_NORMAL_MEMORY, buf); } -static ssize_t print_nodes_has_cpu(struct sysdev_class *class, char *buf) +static ssize_t print_nodes_has_cpu(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { return print_nodes_state(N_CPU, buf); } @@ -573,7 +579,8 @@ static SYSDEV_CLASS_ATTR(has_cpu, 0444, print_nodes_has_cpu, NULL); #ifdef CONFIG_HIGHMEM static ssize_t print_nodes_has_high_memory(struct sysdev_class *class, - char *buf) + struct sysdev_class_attribute *attr, + char *buf) { return print_nodes_state(N_HIGH_MEMORY, buf); } diff --git a/drivers/base/sys.c b/drivers/base/sys.c index 0d903909af7e..a38445c0f8c5 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -89,7 +89,7 @@ static ssize_t sysdev_class_show(struct kobject *kobj, struct attribute *attr, struct sysdev_class_attribute *class_attr = to_sysdev_class_attr(attr); if (class_attr->show) - return class_attr->show(class, buffer); + return class_attr->show(class, class_attr, buffer); return -EIO; } @@ -100,7 +100,7 @@ static ssize_t sysdev_class_store(struct kobject *kobj, struct attribute *attr, struct sysdev_class_attribute *class_attr = to_sysdev_class_attr(attr); if (class_attr->store) - return class_attr->store(class, buffer, count); + return class_attr->store(class, class_attr, buffer, count); return -EIO; } diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 97b003839fb6..c9cefacabf37 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -22,6 +22,7 @@ static int __init cpuidle_sysfs_setup(char *unused) __setup("cpuidle_sysfs_switch", cpuidle_sysfs_setup); static ssize_t show_available_governors(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { ssize_t i = 0; @@ -41,6 +42,7 @@ out: } static ssize_t show_current_driver(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { ssize_t ret; @@ -56,6 +58,7 @@ static ssize_t show_current_driver(struct sysdev_class *class, } static ssize_t show_current_governor(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { ssize_t ret; @@ -71,6 +74,7 @@ static ssize_t show_current_governor(struct sysdev_class *class, } static ssize_t store_current_governor(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { char gov_name[CPUIDLE_NAME_LEN]; diff --git a/include/linux/sysdev.h b/include/linux/sysdev.h index f395bb3fa2f2..c2458fa8376c 100644 --- a/include/linux/sysdev.h +++ b/include/linux/sysdev.h @@ -41,8 +41,10 @@ struct sysdev_class { struct sysdev_class_attribute { struct attribute attr; - ssize_t (*show)(struct sysdev_class *, char *); - ssize_t (*store)(struct sysdev_class *, const char *, size_t); + ssize_t (*show)(struct sysdev_class *, struct sysdev_class_attribute *, + char *); + ssize_t (*store)(struct sysdev_class *, struct sysdev_class_attribute *, + const char *, size_t); }; #define _SYSDEV_CLASS_ATTR(_name,_mode,_show,_store) \ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 8e352c756ba7..f40560b86544 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -5481,13 +5481,16 @@ void __init perf_event_init(void) register_cpu_notifier(&perf_cpu_nb); } -static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, char *buf) +static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { return sprintf(buf, "%d\n", perf_reserved_percpu); } static ssize_t perf_set_reserve_percpu(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { @@ -5516,13 +5519,17 @@ perf_set_reserve_percpu(struct sysdev_class *class, return count; } -static ssize_t perf_show_overcommit(struct sysdev_class *class, char *buf) +static ssize_t perf_show_overcommit(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + char *buf) { return sprintf(buf, "%d\n", perf_overcommit); } static ssize_t -perf_set_overcommit(struct sysdev_class *class, const char *buf, size_t count) +perf_set_overcommit(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + const char *buf, size_t count) { unsigned long val; int err; diff --git a/kernel/sched.c b/kernel/sched.c index b47ceeec1a91..150b6988de49 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7406,11 +7406,13 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) #ifdef CONFIG_SCHED_MC static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) { return sprintf(page, "%u\n", sched_mc_power_savings); } static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 0); @@ -7422,11 +7424,13 @@ static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, #ifdef CONFIG_SCHED_SMT static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, char *page) { return sprintf(page, "%u\n", sched_smt_power_savings); } static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 1); -- cgit v1.2.3 From 9cd43611ccfb46632bfa7d19f688924ea93f1613 Mon Sep 17 00:00:00 2001 From: Emese Revfy Date: Thu, 31 Dec 2009 14:52:51 +0100 Subject: kobject: Constify struct kset_uevent_ops Constify struct kset_uevent_ops. This is part of the ops structure constification effort started by Arjan van de Ven et al. Benefits of this constification: * prevents modification of data that is shared (referenced) by many other structure instances at runtime * detects/prevents accidental (but not intentional) modification attempts on archs that enforce read-only kernel data at runtime * potentially better optimized code as the compiler can assume that the const data cannot be changed * the compiler/linker move const data into .rodata and therefore exclude them from false sharing Signed-off-by: Emese Revfy Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 2 +- drivers/base/core.c | 2 +- drivers/base/memory.c | 2 +- fs/gfs2/sys.c | 2 +- include/linux/kobject.h | 10 +++++----- kernel/params.c | 2 +- lib/kobject.c | 4 ++-- lib/kobject_uevent.c | 2 +- mm/slub.c | 2 +- 9 files changed, 14 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index c0c5a43d9fb3..2afe599eb35d 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -154,7 +154,7 @@ static int bus_uevent_filter(struct kset *kset, struct kobject *kobj) return 0; } -static struct kset_uevent_ops bus_uevent_ops = { +static const struct kset_uevent_ops bus_uevent_ops = { .filter = bus_uevent_filter, }; diff --git a/drivers/base/core.c b/drivers/base/core.c index f6c73a9e3d95..58ec1069f4b0 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -252,7 +252,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, return retval; } -static struct kset_uevent_ops device_uevent_ops = { +static const struct kset_uevent_ops device_uevent_ops = { .filter = dev_uevent_filter, .name = dev_uevent_name, .uevent = dev_uevent, diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 495f15e92d4c..2f8691511190 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -44,7 +44,7 @@ static int memory_uevent(struct kset *kset, struct kobject *obj, struct kobj_uev return retval; } -static struct kset_uevent_ops memory_uevent_ops = { +static const struct kset_uevent_ops memory_uevent_ops = { .name = memory_uevent_name, .uevent = memory_uevent, }; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index b5f1a46133c8..543503010ed0 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -574,7 +574,7 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj, return 0; } -static struct kset_uevent_ops gfs2_uevent_ops = { +static const struct kset_uevent_ops gfs2_uevent_ops = { .uevent = gfs2_uevent, }; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 58ae8e00fcdd..57a1eaae9096 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -118,9 +118,9 @@ struct kobj_uevent_env { }; struct kset_uevent_ops { - int (*filter)(struct kset *kset, struct kobject *kobj); - const char *(*name)(struct kset *kset, struct kobject *kobj); - int (*uevent)(struct kset *kset, struct kobject *kobj, + int (* const filter)(struct kset *kset, struct kobject *kobj); + const char *(* const name)(struct kset *kset, struct kobject *kobj); + int (* const uevent)(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env); }; @@ -155,14 +155,14 @@ struct kset { struct list_head list; spinlock_t list_lock; struct kobject kobj; - struct kset_uevent_ops *uevent_ops; + const struct kset_uevent_ops *uevent_ops; }; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); extern void kset_unregister(struct kset *kset); extern struct kset * __must_check kset_create_and_add(const char *name, - struct kset_uevent_ops *u, + const struct kset_uevent_ops *u, struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) diff --git a/kernel/params.c b/kernel/params.c index 8d95f5451b22..48370be3c0a1 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -736,7 +736,7 @@ static int uevent_filter(struct kset *kset, struct kobject *kobj) return 0; } -static struct kset_uevent_ops module_uevent_ops = { +static const struct kset_uevent_ops module_uevent_ops = { .filter = uevent_filter, }; diff --git a/lib/kobject.c b/lib/kobject.c index b512b746d2af..cecf5a0ef6e1 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -789,7 +789,7 @@ static struct kobj_type kset_ktype = { * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, - struct kset_uevent_ops *uevent_ops, + const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; @@ -832,7 +832,7 @@ static struct kset *kset_create(const char *name, * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, - struct kset_uevent_ops *uevent_ops, + const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 920a3ca6e259..c9d3a3e8405d 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -95,7 +95,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, const char *subsystem; struct kobject *top_kobj; struct kset *kset; - struct kset_uevent_ops *uevent_ops; + const struct kset_uevent_ops *uevent_ops; u64 seq; int i = 0; int retval = 0; diff --git a/mm/slub.c b/mm/slub.c index 0bfd3863d521..a26753c12dcd 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4409,7 +4409,7 @@ static int uevent_filter(struct kset *kset, struct kobject *kobj) return 0; } -static struct kset_uevent_ops slab_uevent_ops = { +static const struct kset_uevent_ops slab_uevent_ops = { .filter = uevent_filter, }; -- cgit v1.2.3 From 52cf25d0ab7f78eeecc59ac652ed5090f69b619e Mon Sep 17 00:00:00 2001 From: Emese Revfy Date: Tue, 19 Jan 2010 02:58:23 +0100 Subject: Driver core: Constify struct sysfs_ops in struct kobj_type Constify struct sysfs_ops. This is part of the ops structure constification effort started by Arjan van de Ven et al. Benefits of this constification: * prevents modification of data that is shared (referenced) by many other structure instances at runtime * detects/prevents accidental (but not intentional) modification attempts on archs that enforce read-only kernel data at runtime * potentially better optimized code as the compiler can assume that the const data cannot be changed * the compiler/linker move const data into .rodata and therefore exclude them from false sharing Signed-off-by: Emese Revfy Acked-by: David Teigland Acked-by: Matt Domsch Acked-by: Maciej Sosnowski Acked-by: Hans J. Koch Acked-by: Pekka Enberg Acked-by: Jens Axboe Acked-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- Documentation/kobject.txt | 2 +- arch/ia64/kernel/topology.c | 2 +- arch/powerpc/kernel/cacheinfo.c | 2 +- arch/sh/kernel/cpu/sh4/sq.c | 2 +- arch/x86/kernel/cpu/intel_cacheinfo.c | 2 +- arch/x86/kernel/cpu/mcheck/mce_amd.c | 2 +- block/blk-integrity.c | 2 +- block/blk-sysfs.c | 2 +- block/elevator.c | 2 +- drivers/base/bus.c | 4 ++-- drivers/base/class.c | 2 +- drivers/base/core.c | 2 +- drivers/base/sys.c | 4 ++-- drivers/block/pktcdvd.c | 2 +- drivers/cpufreq/cpufreq.c | 2 +- drivers/cpuidle/sysfs.c | 4 ++-- drivers/dma/ioat/dma.c | 2 +- drivers/dma/ioat/dma.h | 2 +- drivers/edac/edac_device_sysfs.c | 6 +++--- drivers/edac/edac_mc_sysfs.c | 4 ++-- drivers/edac/edac_pci_sysfs.c | 4 ++-- drivers/firmware/edd.c | 2 +- drivers/firmware/efivars.c | 2 +- drivers/firmware/iscsi_ibft.c | 2 +- drivers/firmware/memmap.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 2 +- drivers/gpu/drm/ttm/ttm_memory.c | 2 +- drivers/infiniband/core/cm.c | 2 +- drivers/infiniband/core/sysfs.c | 2 +- drivers/md/dm-sysfs.c | 2 +- drivers/md/md.c | 4 ++-- drivers/net/ibmveth.c | 2 +- drivers/net/iseries_veth.c | 4 ++-- drivers/parisc/pdc_stable.c | 2 +- drivers/pci/hotplug/fakephp.c | 2 +- drivers/pci/slot.c | 2 +- drivers/uio/uio.c | 4 ++-- drivers/uwb/wlp/sysfs.c | 3 +-- drivers/video/omap2/dss/manager.c | 2 +- drivers/video/omap2/dss/overlay.c | 2 +- drivers/xen/sys-hypervisor.c | 2 +- fs/btrfs/sysfs.c | 4 ++-- fs/dlm/lockspace.c | 2 +- fs/ext4/super.c | 2 +- fs/gfs2/sys.c | 2 +- fs/ocfs2/cluster/masklog.c | 2 +- fs/sysfs/file.c | 8 ++++---- include/linux/kobject.h | 4 ++-- kernel/params.c | 2 +- lib/kobject.c | 2 +- mm/slub.c | 2 +- net/bridge/br_private.h | 2 +- net/bridge/br_sysfs_if.c | 2 +- samples/kobject/kset-example.c | 2 +- 54 files changed, 69 insertions(+), 70 deletions(-) (limited to 'kernel') diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt index c79ab996dada..bdb13817e1e9 100644 --- a/Documentation/kobject.txt +++ b/Documentation/kobject.txt @@ -266,7 +266,7 @@ kobj_type: struct kobj_type { void (*release)(struct kobject *); - struct sysfs_ops *sysfs_ops; + const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; }; diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 8f060352e129..b3a5818088d9 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -282,7 +282,7 @@ static ssize_t cache_show(struct kobject * kobj, struct attribute * attr, char * return ret; } -static struct sysfs_ops cache_sysfs_ops = { +static const struct sysfs_ops cache_sysfs_ops = { .show = cache_show }; diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index bb37b1d19a58..01fe9ce28379 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -642,7 +642,7 @@ static struct kobj_attribute *cache_index_opt_attrs[] = { &cache_assoc_attr, }; -static struct sysfs_ops cache_index_ops = { +static const struct sysfs_ops cache_index_ops = { .show = cache_index_show, }; diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index fc065f9da6e5..14726eef1ce0 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -326,7 +326,7 @@ static struct attribute *sq_sysfs_attrs[] = { NULL, }; -static struct sysfs_ops sq_sysfs_ops = { +static const struct sysfs_ops sq_sysfs_ops = { .show = sq_sysfs_show, .store = sq_sysfs_store, }; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index eddb1bdd1b8f..b3eeb66c0a51 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -903,7 +903,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = show, .store = store, }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 83a3d1f4efca..cda932ca3ade 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -388,7 +388,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops threshold_ops = { +static const struct sysfs_ops threshold_ops = { .show = show, .store = store, }; diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 15c630813b1c..96e83c2bdb94 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -278,7 +278,7 @@ static struct attribute *integrity_attrs[] = { NULL, }; -static struct sysfs_ops integrity_ops = { +static const struct sysfs_ops integrity_ops = { .show = &integrity_attr_show, .store = &integrity_attr_store, }; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e85442415db3..2ae2cb3f362f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -450,7 +450,7 @@ static void blk_release_queue(struct kobject *kobj) kmem_cache_free(blk_requestq_cachep, q); } -static struct sysfs_ops queue_sysfs_ops = { +static const struct sysfs_ops queue_sysfs_ops = { .show = queue_attr_show, .store = queue_attr_store, }; diff --git a/block/elevator.c b/block/elevator.c index ee3a883840f2..df75676f6671 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -892,7 +892,7 @@ elv_attr_store(struct kobject *kobj, struct attribute *attr, return error; } -static struct sysfs_ops elv_sysfs_ops = { +static const struct sysfs_ops elv_sysfs_ops = { .show = elv_attr_show, .store = elv_attr_store, }; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 2afe599eb35d..cca1aa10054c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -70,7 +70,7 @@ static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops driver_sysfs_ops = { +static const struct sysfs_ops driver_sysfs_ops = { .show = drv_attr_show, .store = drv_attr_store, }; @@ -115,7 +115,7 @@ static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops bus_sysfs_ops = { +static const struct sysfs_ops bus_sysfs_ops = { .show = bus_attr_show, .store = bus_attr_store, }; diff --git a/drivers/base/class.c b/drivers/base/class.c index 2e297cc4cd3d..0147f476b8a9 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -63,7 +63,7 @@ static void class_release(struct kobject *kobj) kfree(cp); } -static struct sysfs_ops class_sysfs_ops = { +static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; diff --git a/drivers/base/core.c b/drivers/base/core.c index 58ec1069f4b0..b0d6646a2814 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -100,7 +100,7 @@ static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops dev_sysfs_ops = { +static const struct sysfs_ops dev_sysfs_ops = { .show = dev_attr_show, .store = dev_attr_store, }; diff --git a/drivers/base/sys.c b/drivers/base/sys.c index 747c99e0568b..8980feec5d14 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -54,7 +54,7 @@ sysdev_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = sysdev_show, .store = sysdev_store, }; @@ -104,7 +104,7 @@ static ssize_t sysdev_class_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops sysfs_class_ops = { +static const struct sysfs_ops sysfs_class_ops = { .show = sysdev_class_show, .store = sysdev_class_store, }; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 73d815d3f1b2..39c8514442eb 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -284,7 +284,7 @@ static ssize_t kobj_pkt_store(struct kobject *kobj, return len; } -static struct sysfs_ops kobj_pkt_ops = { +static const struct sysfs_ops kobj_pkt_ops = { .show = kobj_pkt_show, .store = kobj_pkt_store }; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 67bc2ece7b4b..2d5d575e889d 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -766,7 +766,7 @@ static void cpufreq_sysfs_release(struct kobject *kobj) complete(&policy->kobj_unregister); } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = show, .store = store, }; diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index c9cefacabf37..8719b36e1a4d 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -195,7 +195,7 @@ static ssize_t cpuidle_store(struct kobject * kobj, struct attribute * attr, return ret; } -static struct sysfs_ops cpuidle_sysfs_ops = { +static const struct sysfs_ops cpuidle_sysfs_ops = { .show = cpuidle_show, .store = cpuidle_store, }; @@ -281,7 +281,7 @@ static ssize_t cpuidle_state_show(struct kobject * kobj, return ret; } -static struct sysfs_ops cpuidle_state_sysfs_ops = { +static const struct sysfs_ops cpuidle_state_sysfs_ops = { .show = cpuidle_state_show, }; diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index af14c9a5b8d4..0099340b9616 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -1138,7 +1138,7 @@ ioat_attr_show(struct kobject *kobj, struct attribute *attr, char *page) return entry->show(&chan->common, page); } -struct sysfs_ops ioat_sysfs_ops = { +const struct sysfs_ops ioat_sysfs_ops = { .show = ioat_attr_show, }; diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index 4f747a254074..86b97ac8774e 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -346,7 +346,7 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan, unsigned long *phys_complete); void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type); void ioat_kobject_del(struct ioatdma_device *device); -extern struct sysfs_ops ioat_sysfs_ops; +extern const struct sysfs_ops ioat_sysfs_ops; extern struct ioat_sysfs_entry ioat_version_attr; extern struct ioat_sysfs_entry ioat_cap_attr; #endif /* IOATDMA_H */ diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 53764577035f..5fdedbc0f545 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -137,7 +137,7 @@ static ssize_t edac_dev_ctl_info_store(struct kobject *kobj, } /* edac_dev file operations for an 'ctl_info' */ -static struct sysfs_ops device_ctl_info_ops = { +static const struct sysfs_ops device_ctl_info_ops = { .show = edac_dev_ctl_info_show, .store = edac_dev_ctl_info_store }; @@ -373,7 +373,7 @@ static ssize_t edac_dev_instance_store(struct kobject *kobj, } /* edac_dev file operations for an 'instance' */ -static struct sysfs_ops device_instance_ops = { +static const struct sysfs_ops device_instance_ops = { .show = edac_dev_instance_show, .store = edac_dev_instance_store }; @@ -476,7 +476,7 @@ static ssize_t edac_dev_block_store(struct kobject *kobj, } /* edac_dev file operations for a 'block' */ -static struct sysfs_ops device_block_ops = { +static const struct sysfs_ops device_block_ops = { .show = edac_dev_block_show, .store = edac_dev_block_store }; diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index e1d4ce083481..88840e9fa3e0 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -245,7 +245,7 @@ static ssize_t csrowdev_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops csrowfs_ops = { +static const struct sysfs_ops csrowfs_ops = { .show = csrowdev_show, .store = csrowdev_store }; @@ -575,7 +575,7 @@ static ssize_t mcidev_store(struct kobject *kobj, struct attribute *attr, } /* Intermediate show/store table */ -static struct sysfs_ops mci_ops = { +static const struct sysfs_ops mci_ops = { .show = mcidev_show, .store = mcidev_store }; diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index fb60a877d768..bef94e3d9944 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -121,7 +121,7 @@ static ssize_t edac_pci_instance_store(struct kobject *kobj, } /* fs_ops table */ -static struct sysfs_ops pci_instance_ops = { +static const struct sysfs_ops pci_instance_ops = { .show = edac_pci_instance_show, .store = edac_pci_instance_store }; @@ -261,7 +261,7 @@ static ssize_t edac_pci_dev_store(struct kobject *kobj, return -EIO; } -static struct sysfs_ops edac_pci_sysfs_ops = { +static const struct sysfs_ops edac_pci_sysfs_ops = { .show = edac_pci_dev_show, .store = edac_pci_dev_store }; diff --git a/drivers/firmware/edd.c b/drivers/firmware/edd.c index 9e4f59dc7f1e..110e24e50883 100644 --- a/drivers/firmware/edd.c +++ b/drivers/firmware/edd.c @@ -122,7 +122,7 @@ edd_attr_show(struct kobject * kobj, struct attribute *attr, char *buf) return ret; } -static struct sysfs_ops edd_attr_ops = { +static const struct sysfs_ops edd_attr_ops = { .show = edd_attr_show, }; diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index f4f709d1370b..082f06ecd327 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -362,7 +362,7 @@ static ssize_t efivar_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops efivar_attr_ops = { +static const struct sysfs_ops efivar_attr_ops = { .show = efivar_attr_show, .store = efivar_attr_store, }; diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index a3600e3ed0fa..ed2801c378de 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -519,7 +519,7 @@ static ssize_t ibft_show_attribute(struct kobject *kobj, return ret; } -static struct sysfs_ops ibft_attr_ops = { +static const struct sysfs_ops ibft_attr_ops = { .show = ibft_show_attribute, }; diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 20f645743ead..d59f7cad2269 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -74,7 +74,7 @@ static struct attribute *def_attrs[] = { NULL }; -static struct sysfs_ops memmap_attr_ops = { +static const struct sysfs_ops memmap_attr_ops = { .show = memmap_attr_show, }; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index c7320ce4567d..89c38c49066f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -128,7 +128,7 @@ static struct attribute *ttm_bo_global_attrs[] = { NULL }; -static struct sysfs_ops ttm_bo_global_ops = { +static const struct sysfs_ops ttm_bo_global_ops = { .show = &ttm_bo_global_show }; diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c index f5245c02b8fd..eb143e04d402 100644 --- a/drivers/gpu/drm/ttm/ttm_memory.c +++ b/drivers/gpu/drm/ttm/ttm_memory.c @@ -152,7 +152,7 @@ static struct attribute *ttm_mem_zone_attrs[] = { NULL }; -static struct sysfs_ops ttm_mem_zone_ops = { +static const struct sysfs_ops ttm_mem_zone_ops = { .show = &ttm_mem_zone_show, .store = &ttm_mem_zone_store }; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 5130fc55b8e2..764787ebe8d8 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3597,7 +3597,7 @@ static ssize_t cm_show_counter(struct kobject *obj, struct attribute *attr, atomic_long_read(&group->counter[cm_attr->index])); } -static struct sysfs_ops cm_counter_ops = { +static const struct sysfs_ops cm_counter_ops = { .show = cm_show_counter }; diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 158a214da2f7..1558bb7fc74d 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -79,7 +79,7 @@ static ssize_t port_attr_show(struct kobject *kobj, return port_attr->show(p, port_attr, buf); } -static struct sysfs_ops port_sysfs_ops = { +static const struct sysfs_ops port_sysfs_ops = { .show = port_attr_show }; diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index f91b40942e07..84d2b91e4efb 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -75,7 +75,7 @@ static struct attribute *dm_attrs[] = { NULL, }; -static struct sysfs_ops dm_sysfs_ops = { +static const struct sysfs_ops dm_sysfs_ops = { .show = dm_attr_show, }; diff --git a/drivers/md/md.c b/drivers/md/md.c index a20a71e5efd3..fdc1890b6ac5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2642,7 +2642,7 @@ static void rdev_free(struct kobject *ko) mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj); kfree(rdev); } -static struct sysfs_ops rdev_sysfs_ops = { +static const struct sysfs_ops rdev_sysfs_ops = { .show = rdev_attr_show, .store = rdev_attr_store, }; @@ -4059,7 +4059,7 @@ static void md_free(struct kobject *ko) kfree(mddev); } -static struct sysfs_ops md_sysfs_ops = { +static const struct sysfs_ops md_sysfs_ops = { .show = md_attr_show, .store = md_attr_store, }; diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index f2b937966950..0bc777bac9b4 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -1577,7 +1577,7 @@ static struct attribute * veth_pool_attrs[] = { NULL, }; -static struct sysfs_ops veth_pool_ops = { +static const struct sysfs_ops veth_pool_ops = { .show = veth_pool_show, .store = veth_pool_store, }; diff --git a/drivers/net/iseries_veth.c b/drivers/net/iseries_veth.c index 966de5d69521..e6e972d9b7ca 100644 --- a/drivers/net/iseries_veth.c +++ b/drivers/net/iseries_veth.c @@ -384,7 +384,7 @@ static struct attribute *veth_cnx_default_attrs[] = { NULL }; -static struct sysfs_ops veth_cnx_sysfs_ops = { +static const struct sysfs_ops veth_cnx_sysfs_ops = { .show = veth_cnx_attribute_show }; @@ -441,7 +441,7 @@ static struct attribute *veth_port_default_attrs[] = { NULL }; -static struct sysfs_ops veth_port_sysfs_ops = { +static const struct sysfs_ops veth_port_sysfs_ops = { .show = veth_port_attribute_show }; diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index 0bc5d474b168..1062b8ffe244 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -481,7 +481,7 @@ pdcspath_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops pdcspath_attr_ops = { +static const struct sysfs_ops pdcspath_attr_ops = { .show = pdcspath_attr_show, .store = pdcspath_attr_store, }; diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c index 6151389fd903..0a894efd4b9b 100644 --- a/drivers/pci/hotplug/fakephp.c +++ b/drivers/pci/hotplug/fakephp.c @@ -73,7 +73,7 @@ static void legacy_release(struct kobject *kobj) } static struct kobj_type legacy_ktype = { - .sysfs_ops = &(struct sysfs_ops){ + .sysfs_ops = &(const struct sysfs_ops){ .store = legacy_store, .show = legacy_show }, .release = &legacy_release, diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index 49c9e6c9779a..f75a44d37fbe 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -29,7 +29,7 @@ static ssize_t pci_slot_attr_store(struct kobject *kobj, return attribute->store ? attribute->store(slot, buf, len) : -EIO; } -static struct sysfs_ops pci_slot_sysfs_ops = { +static const struct sysfs_ops pci_slot_sysfs_ops = { .show = pci_slot_attr_show, .store = pci_slot_attr_store, }; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index e941367dd28f..4de382acd8f2 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -129,7 +129,7 @@ static ssize_t map_type_show(struct kobject *kobj, struct attribute *attr, return entry->show(mem, buf); } -static struct sysfs_ops map_sysfs_ops = { +static const struct sysfs_ops map_sysfs_ops = { .show = map_type_show, }; @@ -217,7 +217,7 @@ static ssize_t portio_type_show(struct kobject *kobj, struct attribute *attr, return entry->show(port, buf); } -static struct sysfs_ops portio_sysfs_ops = { +static const struct sysfs_ops portio_sysfs_ops = { .show = portio_type_show, }; diff --git a/drivers/uwb/wlp/sysfs.c b/drivers/uwb/wlp/sysfs.c index 0370399ff4bb..6627c94cc854 100644 --- a/drivers/uwb/wlp/sysfs.c +++ b/drivers/uwb/wlp/sysfs.c @@ -615,8 +615,7 @@ ssize_t wlp_wss_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static -struct sysfs_ops wss_sysfs_ops = { +static const struct sysfs_ops wss_sysfs_ops = { .show = wlp_wss_attr_show, .store = wlp_wss_attr_store, }; diff --git a/drivers/video/omap2/dss/manager.c b/drivers/video/omap2/dss/manager.c index 913142d4cab1..9acef00c47ea 100644 --- a/drivers/video/omap2/dss/manager.c +++ b/drivers/video/omap2/dss/manager.c @@ -341,7 +341,7 @@ static ssize_t manager_attr_store(struct kobject *kobj, struct attribute *attr, return manager_attr->store(manager, buf, size); } -static struct sysfs_ops manager_sysfs_ops = { +static const struct sysfs_ops manager_sysfs_ops = { .show = manager_attr_show, .store = manager_attr_store, }; diff --git a/drivers/video/omap2/dss/overlay.c b/drivers/video/omap2/dss/overlay.c index 0c5bea263ac6..aed3f3194347 100644 --- a/drivers/video/omap2/dss/overlay.c +++ b/drivers/video/omap2/dss/overlay.c @@ -320,7 +320,7 @@ static ssize_t overlay_attr_store(struct kobject *kobj, struct attribute *attr, return overlay_attr->store(overlay, buf, size); } -static struct sysfs_ops overlay_sysfs_ops = { +static const struct sysfs_ops overlay_sysfs_ops = { .show = overlay_attr_show, .store = overlay_attr_store, }; diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c index ae5cb05a1a1c..bb71ab2336c8 100644 --- a/drivers/xen/sys-hypervisor.c +++ b/drivers/xen/sys-hypervisor.c @@ -426,7 +426,7 @@ static ssize_t hyp_sysfs_store(struct kobject *kobj, return 0; } -static struct sysfs_ops hyp_sysfs_ops = { +static const struct sysfs_ops hyp_sysfs_ops = { .show = hyp_sysfs_show, .store = hyp_sysfs_store, }; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index a240b6fa81df..4ce16ef702a3 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -164,12 +164,12 @@ static void btrfs_root_release(struct kobject *kobj) complete(&root->kobj_unregister); } -static struct sysfs_ops btrfs_super_attr_ops = { +static const struct sysfs_ops btrfs_super_attr_ops = { .show = btrfs_super_attr_show, .store = btrfs_super_attr_store, }; -static struct sysfs_ops btrfs_root_attr_ops = { +static const struct sysfs_ops btrfs_root_attr_ops = { .show = btrfs_root_attr_show, .store = btrfs_root_attr_store, }; diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 26a8bd40400a..f994a7dfda85 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -148,7 +148,7 @@ static void lockspace_kobj_release(struct kobject *k) kfree(ls); } -static struct sysfs_ops dlm_attr_ops = { +static const struct sysfs_ops dlm_attr_ops = { .show = dlm_attr_show, .store = dlm_attr_store, }; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2b83b96cb2eb..ce84a6ed4a48 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2358,7 +2358,7 @@ static void ext4_sb_release(struct kobject *kobj) } -static struct sysfs_ops ext4_attr_ops = { +static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, }; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 543503010ed0..419042f7f0b6 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -49,7 +49,7 @@ static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr, return a->store ? a->store(sdp, buf, len) : len; } -static struct sysfs_ops gfs2_attr_ops = { +static const struct sysfs_ops gfs2_attr_ops = { .show = gfs2_attr_show, .store = gfs2_attr_store, }; diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index b39da877b12f..3bb928a2bf7d 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -136,7 +136,7 @@ static ssize_t mlog_store(struct kobject *obj, struct attribute *attr, return mlog_mask_store(mlog_attr->mask, buf, count); } -static struct sysfs_ops mlog_attr_ops = { +static const struct sysfs_ops mlog_attr_ops = { .show = mlog_show, .store = mlog_store, }; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 50b725bcc3f3..ced2299f1c9a 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -53,7 +53,7 @@ struct sysfs_buffer { size_t count; loff_t pos; char * page; - struct sysfs_ops * ops; + const struct sysfs_ops * ops; struct mutex mutex; int needs_read_fill; int event; @@ -75,7 +75,7 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer { struct sysfs_dirent *attr_sd = dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_ops * ops = buffer->ops; + const struct sysfs_ops * ops = buffer->ops; int ret = 0; ssize_t count; @@ -199,7 +199,7 @@ flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t { struct sysfs_dirent *attr_sd = dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_ops * ops = buffer->ops; + const struct sysfs_ops * ops = buffer->ops; int rc; /* need attr_sd for attr and ops, its parent for kobj */ @@ -335,7 +335,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; struct sysfs_buffer *buffer; - struct sysfs_ops *ops; + const struct sysfs_ops *ops; int error = -EACCES; char *p; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 57a1eaae9096..3950d3c2850d 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -106,7 +106,7 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); - struct sysfs_ops *sysfs_ops; + const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; }; @@ -132,7 +132,7 @@ struct kobj_attribute { const char *buf, size_t count); }; -extern struct sysfs_ops kobj_sysfs_ops; +extern const struct sysfs_ops kobj_sysfs_ops; /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. diff --git a/kernel/params.c b/kernel/params.c index 48370be3c0a1..68396d73c838 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -722,7 +722,7 @@ static ssize_t module_attr_store(struct kobject *kobj, return ret; } -static struct sysfs_ops module_sysfs_ops = { +static const struct sysfs_ops module_sysfs_ops = { .show = module_attr_show, .store = module_attr_store, }; diff --git a/lib/kobject.c b/lib/kobject.c index cecf5a0ef6e1..8115eb1bbf4d 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -700,7 +700,7 @@ static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -struct sysfs_ops kobj_sysfs_ops = { +const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; diff --git a/mm/slub.c b/mm/slub.c index a26753c12dcd..a2b8969ba6d0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4390,7 +4390,7 @@ static void kmem_cache_release(struct kobject *kobj) kfree(s); } -static struct sysfs_ops slab_sysfs_ops = { +static const struct sysfs_ops slab_sysfs_ops = { .show = slab_attr_show, .store = slab_attr_store, }; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1cf2cef78584..fef0384e3c0b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -423,7 +423,7 @@ extern void br_ifinfo_notify(int event, struct net_bridge_port *port); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ -extern struct sysfs_ops brport_sysfs_ops; +extern const struct sysfs_ops brport_sysfs_ops; extern int br_sysfs_addif(struct net_bridge_port *p); /* br_sysfs_br.c */ diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 696596cd3384..0b9916489d6b 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -238,7 +238,7 @@ static ssize_t brport_store(struct kobject * kobj, return ret; } -struct sysfs_ops brport_sysfs_ops = { +const struct sysfs_ops brport_sysfs_ops = { .show = brport_show, .store = brport_store, }; diff --git a/samples/kobject/kset-example.c b/samples/kobject/kset-example.c index 7c6088140528..3b126d1f8599 100644 --- a/samples/kobject/kset-example.c +++ b/samples/kobject/kset-example.c @@ -87,7 +87,7 @@ static ssize_t foo_attr_store(struct kobject *kobj, } /* Our custom sysfs_ops that we will associate with our ktype later on */ -static struct sysfs_ops foo_sysfs_ops = { +static const struct sysfs_ops foo_sysfs_ops = { .show = foo_attr_show, .store = foo_attr_store, }; -- cgit v1.2.3 From a07e4156a2ee6359d31a44946d7ee7f85dbf6bca Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 11 Feb 2010 15:23:05 -0800 Subject: sysfs: Use sysfs_attr_init and sysfs_bin_attr_init on dynamic attributes These are the non-static sysfs attributes that exist on my test machine. Fix them to use sysfs_attr_init or sysfs_bin_attr_init as appropriate. It simply requires making a sysfs attribute present to see this. So this is a little bit tedious but otherwise not too bad. Signed-off-by: Eric W. Biederman Acked-by: WANG Cong Cc: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mcheck/mce.c | 1 + drivers/acpi/system.c | 2 ++ drivers/pci/pci-sysfs.c | 5 +++++ kernel/params.c | 1 + 4 files changed, 9 insertions(+) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a8aacd4b513c..28cba46bf32c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2044,6 +2044,7 @@ static __init void mce_init_banks(void) struct mce_bank *b = &mce_banks[i]; struct sysdev_attribute *a = &b->attr; + sysfs_attr_init(&a->attr); a->attr.name = b->attrname; snprintf(b->attrname, ATTR_LEN, "bank%d", i); diff --git a/drivers/acpi/system.c b/drivers/acpi/system.c index a206a12da78a..743f2445e2a1 100644 --- a/drivers/acpi/system.c +++ b/drivers/acpi/system.c @@ -101,6 +101,7 @@ static void acpi_table_attr_init(struct acpi_table_attr *table_attr, struct acpi_table_header *header = NULL; struct acpi_table_attr *attr = NULL; + sysfs_attr_init(&table_attr->attr.attr); if (table_header->signature[0] != '\0') memcpy(table_attr->name, table_header->signature, ACPI_NAME_SIZE); @@ -475,6 +476,7 @@ void acpi_irq_stats_init(void) goto fail; strncpy(name, buffer, strlen(buffer) + 1); + sysfs_attr_init(&counter_attrs[i].attr); counter_attrs[i].attr.name = name; counter_attrs[i].attr.mode = 0644; counter_attrs[i].show = counter_show; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 807224ec8351..9fa183cfb0e9 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -642,6 +642,7 @@ void pci_create_legacy_files(struct pci_bus *b) if (!b->legacy_io) goto kzalloc_err; + sysfs_bin_attr_init(&b->legacy_io); b->legacy_io->attr.name = "legacy_io"; b->legacy_io->size = 0xffff; b->legacy_io->attr.mode = S_IRUSR | S_IWUSR; @@ -654,6 +655,7 @@ void pci_create_legacy_files(struct pci_bus *b) goto legacy_io_err; /* Allocated above after the legacy_io struct */ + sysfs_bin_attr_init(&b->legacy_mem); b->legacy_mem = b->legacy_io + 1; b->legacy_mem->attr.name = "legacy_mem"; b->legacy_mem->size = 1024*1024; @@ -800,6 +802,7 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) if (res_attr) { char *res_attr_name = (char *)(res_attr + 1); + sysfs_bin_attr_init(res_attr); if (write_combine) { pdev->res_attr_wc[num] = res_attr; sprintf(res_attr_name, "resource%d_wc", num); @@ -972,6 +975,7 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev) if (!attr) return -ENOMEM; + sysfs_bin_attr_init(attr); attr->size = dev->vpd->len; attr->attr.name = "vpd"; attr->attr.mode = S_IRUSR | S_IWUSR; @@ -1038,6 +1042,7 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev) retval = -ENOMEM; goto err_resource_files; } + sysfs_bin_attr_init(attr); attr->size = rom_size; attr->attr.name = "rom"; attr->attr.mode = S_IRUSR; diff --git a/kernel/params.c b/kernel/params.c index 68396d73c838..d55a53ec9234 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -516,6 +516,7 @@ static __modinit int add_sysfs_param(struct module_kobject *mk, new->grp.attrs = attrs; /* Tack new one on the end. */ + sysfs_attr_init(&new->attrs[num].mattr.attr); new->attrs[num].param = kp; new->attrs[num].mattr.show = param_attr_show; new->attrs[num].mattr.store = param_attr_store; -- cgit v1.2.3 From 361795b1eb7c08e9e65a2ebb4a4e536294d378a2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 12 Feb 2010 13:41:56 -0800 Subject: sysfs: Use sysfs_attr_init and sysfs_bin_attr_init on module dynamic attributes A little more whack-a-mole annotating the dynamic sysfs attributes. I had everything built into my earlier test kernel, and so I missed these. Signed-off-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index e5538d5f00ad..c968d3606dca 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1085,6 +1085,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, if (sattr->name == NULL) goto out; sect_attrs->nsections++; + sysfs_attr_init(&sattr->mattr.attr); sattr->mattr.show = module_sect_show; sattr->mattr.store = NULL; sattr->mattr.attr.name = sattr->name; @@ -1180,6 +1181,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, if (sect_empty(&sechdrs[i])) continue; if (sechdrs[i].sh_type == SHT_NOTE) { + sysfs_bin_attr_init(nattr); nattr->attr.name = mod->sect_attrs->attrs[loaded].name; nattr->attr.mode = S_IRUGO; nattr->size = sechdrs[i].sh_size; @@ -1252,6 +1254,7 @@ int module_add_modinfo_attrs(struct module *mod) if (!attr->test || (attr->test && attr->test(mod))) { memcpy(temp_attr, attr, sizeof(*temp_attr)); + sysfs_attr_init(&temp_attr->attr); error = sysfs_create_file(&mod->mkobj.kobj,&temp_attr->attr); ++temp_attr; } -- cgit v1.2.3 From dc1d628a67a8f042e711ea5accc0beedc3ef0092 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Mar 2010 15:55:04 +0100 Subject: perf: Provide generic perf_sample_data initialization This makes it easier to extend perf_sample_data and fixes a bug on arm and sparc, which failed to set ->raw to NULL, which can cause crashes when combined with PERF_SAMPLE_RAW. It also optimizes PowerPC and tracepoint, because the struct initialization is forced to zero out the whole structure. Signed-off-by: Peter Zijlstra Acked-by: Jean Pihet Reviewed-by: Frederic Weisbecker Acked-by: David S. Miller Cc: Jamie Iles Cc: Paul Mackerras Cc: Stephane Eranian Cc: stable@kernel.org LKML-Reference: <20100304140100.315416040@chello.nl> Signed-off-by: Ingo Molnar --- arch/arm/kernel/perf_event.c | 4 ++-- arch/powerpc/kernel/perf_event.c | 8 ++++---- arch/sparc/kernel/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.c | 3 +-- arch/x86/kernel/cpu/perf_event_intel.c | 6 ++---- include/linux/perf_event.h | 7 +++++++ kernel/perf_event.c | 21 ++++++++------------- 7 files changed, 25 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index c54ceb3d1f97..3875d99cc40f 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -965,7 +965,7 @@ armv6pmu_handle_irq(int irq_num, */ armv6_pmcr_write(pmcr); - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx <= armpmu->num_events; ++idx) { @@ -1945,7 +1945,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx <= armpmu->num_events; ++idx) { diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index b6cf8f1f4d35..5120bd44f69a 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1164,10 +1164,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * Finally record data if requested. */ if (record) { - struct perf_sample_data data = { - .addr = ~0ULL, - .period = event->hw.last_period, - }; + struct perf_sample_data data; + + perf_sample_data_init(&data, ~0ULL); + data.period = event->hw.last_period; if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 9f2b2bac8b2b..6504208f375f 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1189,7 +1189,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, regs = args->regs; - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 97cddbf32936..42aafd11e170 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1097,8 +1097,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 73102df8bfc1..44b60c852107 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -590,10 +590,9 @@ static void intel_pmu_drain_bts_buffer(void) ds->bts_index = ds->bts_buffer_base; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - data.addr = 0; - data.raw = NULL; regs.ip = 0; /* @@ -742,8 +741,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 ack, status; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 90e0521b1690..6f8cd7da1a01 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -801,6 +801,13 @@ struct perf_sample_data { struct perf_raw_record *raw; }; +static inline +void perf_sample_data_init(struct perf_sample_data *data, u64 addr) +{ + data->addr = addr; + data->raw = NULL; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, diff --git a/kernel/perf_event.c b/kernel/perf_event.c index e68745053013..4393b9e73740 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4108,8 +4108,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi, if (rctx < 0) return; - data.addr = addr; - data.raw = NULL; + perf_sample_data_init(&data, addr); do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); @@ -4154,11 +4153,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) struct perf_event *event; u64 period; - event = container_of(hrtimer, struct perf_event, hw.hrtimer); + event = container_of(hrtimer, struct perf_event, hw.hrtimer); event->pmu->read(event); - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; regs = get_irq_regs(); /* @@ -4322,17 +4320,15 @@ static const struct pmu perf_ops_task_clock = { void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size) { + struct pt_regs *regs = get_irq_regs(); + struct perf_sample_data data; struct perf_raw_record raw = { .size = entry_size, .data = record, }; - struct perf_sample_data data = { - .addr = addr, - .raw = &raw, - }; - - struct pt_regs *regs = get_irq_regs(); + perf_sample_data_init(&data, addr); + data.raw = &raw; if (!regs) regs = task_pt_regs(current); @@ -4448,8 +4444,7 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; - sample.raw = NULL; - sample.addr = bp->attr.bp_addr; + perf_sample_data_init(&sample, bp->attr.bp_addr); if (!perf_exclude_event(bp, regs)) perf_swevent_add(bp, 1, 1, &sample, regs); -- cgit v1.2.3 From 3f6da3905398826d85731247e7fbcf53400c18bd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Mar 2010 13:01:18 +0100 Subject: perf: Rework and fix the arch CPU-hotplug hooks Remove the hw_perf_event_*() hotplug hooks in favour of per PMU hotplug notifiers. This has the advantage of reducing the static weak interface as well as exposing all hotplug actions to the PMU. Use this to fix x86 hotplug usage where we did things in ONLINE which should have been done in UP_PREPARE or STARTING. Signed-off-by: Peter Zijlstra Cc: Paul Mundt Cc: paulus@samba.org Cc: eranian@google.com Cc: robert.richter@amd.com Cc: fweisbec@gmail.com Cc: Arnaldo Carvalho de Melo LKML-Reference: <20100305154128.736225361@chello.nl> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/perf_event.c | 21 +++++++++- arch/sh/kernel/perf_event.c | 20 +++++++++- arch/x86/kernel/cpu/perf_event.c | 70 ++++++++++++++++++++-------------- arch/x86/kernel/cpu/perf_event_amd.c | 60 ++++++++++++----------------- arch/x86/kernel/cpu/perf_event_intel.c | 5 ++- include/linux/perf_event.h | 16 ++++++++ kernel/perf_event.c | 15 -------- 7 files changed, 126 insertions(+), 81 deletions(-) (limited to 'kernel') diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 5120bd44f69a..fbe101d7505d 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1287,7 +1287,7 @@ static void perf_event_interrupt(struct pt_regs *regs) irq_exit(); } -void hw_perf_event_setup(int cpu) +static void power_pmu_setup(int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); @@ -1297,6 +1297,23 @@ void hw_perf_event_setup(int cpu) cpuhw->mmcr[0] = MMCR0_FC; } +static int __cpuinit +power_pmu_notify(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + power_pmu_setup(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + int register_power_pmu(struct power_pmu *pmu) { if (ppmu) @@ -1314,5 +1331,7 @@ int register_power_pmu(struct power_pmu *pmu) freeze_events_kernel = MMCR0_FCHV; #endif /* CONFIG_PPC64 */ + perf_cpu_notifier(power_pmu_notifier); + return 0; } diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7ff0943e7a08..9f253e9cce01 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -275,13 +275,30 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) return &pmu; } -void hw_perf_event_setup(int cpu) +static void sh_pmu_setup(int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); memset(cpuhw, 0, sizeof(struct cpu_hw_events)); } +static int __cpuinit +sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + sh_pmu_setup(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + void hw_perf_enable(void) { if (!sh_pmu_initialized()) @@ -308,5 +325,6 @@ int register_sh_pmu(struct sh_pmu *pmu) WARN_ON(pmu->num_events > MAX_HWEVENTS); + perf_cpu_notifier(sh_pmu_notifier); return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 42aafd11e170..585d5608ae6b 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -157,6 +157,11 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + + void (*cpu_prepare)(int cpu); + void (*cpu_starting)(int cpu); + void (*cpu_dying)(int cpu); + void (*cpu_dead)(int cpu); }; static struct x86_pmu x86_pmu __read_mostly; @@ -293,7 +298,7 @@ static inline bool bts_available(void) return x86_pmu.enable_bts != NULL; } -static inline void init_debug_store_on_cpu(int cpu) +static void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -305,7 +310,7 @@ static inline void init_debug_store_on_cpu(int cpu) (u32)((u64)(unsigned long)ds >> 32)); } -static inline void fini_debug_store_on_cpu(int cpu) +static void fini_debug_store_on_cpu(int cpu) { if (!per_cpu(cpu_hw_events, cpu).ds) return; @@ -1337,6 +1342,39 @@ undo: #include "perf_event_p6.c" #include "perf_event_intel.c" +static int __cpuinit +x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + if (x86_pmu.cpu_prepare) + x86_pmu.cpu_prepare(cpu); + break; + + case CPU_STARTING: + if (x86_pmu.cpu_starting) + x86_pmu.cpu_starting(cpu); + break; + + case CPU_DYING: + if (x86_pmu.cpu_dying) + x86_pmu.cpu_dying(cpu); + break; + + case CPU_DEAD: + if (x86_pmu.cpu_dead) + x86_pmu.cpu_dead(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + static void __init pmu_check_apic(void) { if (cpu_has_apic) @@ -1415,6 +1453,8 @@ void __init init_hw_perf_events(void) pr_info("... max period: %016Lx\n", x86_pmu.max_period); pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); pr_info("... event mask: %016Lx\n", perf_event_mask); + + perf_cpu_notifier(x86_pmu_notifier); } static inline void x86_pmu_read(struct perf_event *event) @@ -1674,29 +1714,3 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } - -void hw_perf_event_setup_online(int cpu) -{ - init_debug_store_on_cpu(cpu); - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - amd_pmu_cpu_online(cpu); - break; - default: - return; - } -} - -void hw_perf_event_setup_offline(int cpu) -{ - init_debug_store_on_cpu(cpu); - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - amd_pmu_cpu_offline(cpu); - break; - default: - return; - } -} diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 8f3dbfda3c4f..014528ba7d57 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -271,28 +271,6 @@ done: return &emptyconstraint; } -static __initconst struct x86_pmu amd_pmu = { - .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, - .eventsel = MSR_K7_EVNTSEL0, - .perfctr = MSR_K7_PERFCTR0, - .event_map = amd_pmu_event_map, - .raw_event = amd_pmu_raw_event, - .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_events = 4, - .event_bits = 48, - .event_mask = (1ULL << 48) - 1, - .apic = 1, - /* use highest bit to detect overflow */ - .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints, - .put_event_constraints = amd_put_event_constraints -}; - static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) { struct amd_nb *nb; @@ -378,6 +356,31 @@ static void amd_pmu_cpu_offline(int cpu) raw_spin_unlock(&amd_nb_lock); } +static __initconst struct x86_pmu amd_pmu = { + .name = "AMD", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .eventsel = MSR_K7_EVNTSEL0, + .perfctr = MSR_K7_PERFCTR0, + .event_map = amd_pmu_event_map, + .raw_event = amd_pmu_raw_event, + .max_events = ARRAY_SIZE(amd_perfmon_event_map), + .num_events = 4, + .event_bits = 48, + .event_mask = (1ULL << 48) - 1, + .apic = 1, + /* use highest bit to detect overflow */ + .max_period = (1ULL << 47) - 1, + .get_event_constraints = amd_get_event_constraints, + .put_event_constraints = amd_put_event_constraints, + + .cpu_prepare = amd_pmu_cpu_online, + .cpu_dead = amd_pmu_cpu_offline, +}; + static __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -390,11 +393,6 @@ static __init int amd_pmu_init(void) memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - /* - * explicitly initialize the boot cpu, other cpus will get - * the cpu hotplug callbacks from smp_init() - */ - amd_pmu_cpu_online(smp_processor_id()); return 0; } @@ -405,12 +403,4 @@ static int amd_pmu_init(void) return 0; } -static void amd_pmu_cpu_online(int cpu) -{ -} - -static void amd_pmu_cpu_offline(int cpu) -{ -} - #endif diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 44b60c852107..12e811a7d747 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -870,7 +870,10 @@ static __initconst struct x86_pmu intel_pmu = { .max_period = (1ULL << 31) - 1, .enable_bts = intel_pmu_enable_bts, .disable_bts = intel_pmu_disable_bts, - .get_event_constraints = intel_get_event_constraints + .get_event_constraints = intel_get_event_constraints, + + .cpu_starting = init_debug_store_on_cpu, + .cpu_dying = fini_debug_store_on_cpu, }; static __init int intel_pmu_init(void) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6f8cd7da1a01..80acbf3d5de1 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -936,5 +936,21 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_output_put(handle, x) \ perf_output_copy((handle), &(x), sizeof(x)) +/* + * This has to have a higher priority than migration_notifier in sched.c. + */ +#define perf_cpu_notifier(fn) \ +do { \ + static struct notifier_block fn##_nb __cpuinitdata = \ + { .notifier_call = fn, .priority = 20 }; \ + fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_STARTING, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ + (void *)(unsigned long)smp_processor_id()); \ + register_cpu_notifier(&fn##_nb); \ +} while (0) + #endif /* __KERNEL__ */ #endif /* _LINUX_PERF_EVENT_H */ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 4393b9e73740..73329dedb5ad 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -81,10 +81,6 @@ extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event) void __weak hw_perf_disable(void) { barrier(); } void __weak hw_perf_enable(void) { barrier(); } -void __weak hw_perf_event_setup(int cpu) { barrier(); } -void __weak hw_perf_event_setup_online(int cpu) { barrier(); } -void __weak hw_perf_event_setup_offline(int cpu) { barrier(); } - int __weak hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, @@ -5382,8 +5378,6 @@ static void __cpuinit perf_event_init_cpu(int cpu) spin_lock(&perf_resource_lock); cpuctx->max_pertask = perf_max_events - perf_reserved_percpu; spin_unlock(&perf_resource_lock); - - hw_perf_event_setup(cpu); } #ifdef CONFIG_HOTPLUG_CPU @@ -5423,20 +5417,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) perf_event_init_cpu(cpu); break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - hw_perf_event_setup_online(cpu); - break; - case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: perf_event_exit_cpu(cpu); break; - case CPU_DEAD: - hw_perf_event_setup_offline(cpu); - break; - default: break; } -- cgit v1.2.3 From 32975a4f114be52286f9a5bf6c230dbb8c0e1903 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 6 Mar 2010 19:49:19 +0100 Subject: perf: Optimize perf_disable Currently we always call hw_perf_disable(), even if its already disabled, this seems superflous, esp. since it cannot be made NMI safe (see further patches). Signed-off-by: Peter Zijlstra Cc: paulus@samba.org Cc: eranian@google.com Cc: robert.richter@amd.com Cc: fweisbec@gmail.com Cc: Arnaldo Carvalho de Melo LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 73329dedb5ad..d8108465397d 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -93,25 +93,15 @@ void __weak perf_event_print_debug(void) { } static DEFINE_PER_CPU(int, perf_disable_count); -void __perf_disable(void) -{ - __get_cpu_var(perf_disable_count)++; -} - -bool __perf_enable(void) -{ - return !--__get_cpu_var(perf_disable_count); -} - void perf_disable(void) { - __perf_disable(); - hw_perf_disable(); + if (!__get_cpu_var(perf_disable_count)++) + hw_perf_disable(); } void perf_enable(void) { - if (__perf_enable()) + if (!--__get_cpu_var(perf_disable_count)) hw_perf_enable(); } -- cgit v1.2.3 From d4944a06666054707d23e11888e480af239e5abf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 8 Mar 2010 13:51:20 +0100 Subject: perf: Provide better condition for event rotation Try to avoid useless rotation and PMU disables. [ Could be improved by keeping a nr_runnable count to better account for the < PERF_STAT_INACTIVE counters ] Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: paulus@samba.org Cc: eranian@google.com Cc: robert.richter@amd.com Cc: fweisbec@gmail.com LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index d8108465397d..52c69a34d697 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1524,12 +1524,15 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx) */ if (interrupts == MAX_INTERRUPTS) { perf_log_throttle(event, 1); + perf_disable(); event->pmu->unthrottle(event); + perf_enable(); } if (!event->attr.freq || !event->attr.sample_freq) continue; + perf_disable(); event->pmu->read(event); now = atomic64_read(&event->count); delta = now - hwc->freq_count_stamp; @@ -1537,6 +1540,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx) if (delta > 0) perf_adjust_period(event, TICK_NSEC, delta); + perf_enable(); } raw_spin_unlock(&ctx->lock); } @@ -1546,9 +1550,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx) */ static void rotate_ctx(struct perf_event_context *ctx) { - if (!ctx->nr_events) - return; - raw_spin_lock(&ctx->lock); /* Rotate the first entry last of non-pinned groups */ @@ -1561,19 +1562,28 @@ void perf_event_task_tick(struct task_struct *curr) { struct perf_cpu_context *cpuctx; struct perf_event_context *ctx; + int rotate = 0; if (!atomic_read(&nr_events)) return; cpuctx = &__get_cpu_var(perf_cpu_context); - ctx = curr->perf_event_ctxp; + if (cpuctx->ctx.nr_events && + cpuctx->ctx.nr_events != cpuctx->ctx.nr_active) + rotate = 1; - perf_disable(); + ctx = curr->perf_event_ctxp; + if (ctx && ctx->nr_events && ctx->nr_events != ctx->nr_active) + rotate = 1; perf_ctx_adjust_freq(&cpuctx->ctx); if (ctx) perf_ctx_adjust_freq(ctx); + if (!rotate) + return; + + perf_disable(); cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); if (ctx) task_ctx_sched_out(ctx, EVENT_FLEXIBLE); @@ -1585,7 +1595,6 @@ void perf_event_task_tick(struct task_struct *curr) cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) task_ctx_sched_in(curr, EVENT_FLEXIBLE); - perf_enable(); } -- cgit v1.2.3 From db2c4c7791cd04512093d05afc693c3511a65fd7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 2 Feb 2010 23:34:40 +0100 Subject: lockdep: Move lock events under lockdep recursion protection There are rcu locked read side areas in the path where we submit a trace event. And these rcu_read_(un)lock() trigger lock events, which create recursive events. One pair in do_perf_sw_event: __lock_acquire | |--96.11%-- lock_acquire | | | |--27.21%-- do_perf_sw_event | | perf_tp_event | | | | | |--49.62%-- ftrace_profile_lock_release | | | lock_release | | | | | | | |--33.85%-- _raw_spin_unlock Another pair in perf_output_begin/end: __lock_acquire |--23.40%-- perf_output_begin | | __perf_event_overflow | | perf_swevent_overflow | | perf_swevent_add | | perf_swevent_ctx_event | | do_perf_sw_event | | perf_tp_event | | | | | |--55.37%-- ftrace_profile_lock_acquire | | | lock_acquire | | | | | | | |--37.31%-- _raw_spin_lock The problem is not that much the trace recursion itself, as we have a recursion protection already (though it's always wasteful to recurse). But the trace events are outside the lockdep recursion protection, then each lockdep event triggers a lock trace, which will trigger two other lockdep events. Here the recursive lock trace event won't be taken because of the trace recursion, so the recursion stops there but lockdep will still analyse these new events: To sum up, for each lockdep events we have: lock_*() | trace lock_acquire | ----- rcu_read_lock() | | | lock_acquire() | | | trace_lock_acquire() (stopped) | | | lockdep analyze | ----- rcu_read_unlock() | lock_release | trace_lock_release() (stopped) | lockdep analyze And you can repeat the above two times as we have two rcu read side sections when we submit an event. This is fixed in this patch by moving the lock trace event under the lockdep recursion protection. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Steven Rostedt Cc: Paul Mackerras Cc: Hitoshi Mitake Cc: Li Zefan Cc: Lai Jiangshan Cc: Masami Hiramatsu Cc: Jens Axboe --- kernel/lockdep.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 0c30d0455de1..65b5f5b7c298 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3211,8 +3211,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, { unsigned long flags; - trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); - if (unlikely(current->lockdep_recursion)) return; @@ -3220,6 +3218,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, check_flags(flags); current->lockdep_recursion = 1; + trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, irqs_disabled_flags(flags), nest_lock, ip, 0); current->lockdep_recursion = 0; @@ -3232,14 +3231,13 @@ void lock_release(struct lockdep_map *lock, int nested, { unsigned long flags; - trace_lock_release(lock, nested, ip); - if (unlikely(current->lockdep_recursion)) return; raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; + trace_lock_release(lock, nested, ip); __lock_release(lock, nested, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); @@ -3413,8 +3411,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_contended(lock, ip); - if (unlikely(!lock_stat)) return; @@ -3424,6 +3420,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; + trace_lock_contended(lock, ip); __lock_contended(lock, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); -- cgit v1.2.3 From 5331d7b84613b8325362dde53dc2bff2fb87d351 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 4 Mar 2010 21:15:56 +0100 Subject: perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot Events that trigger overflows by interrupting a context can use get_irq_regs() or task_pt_regs() to retrieve the state when the event triggered. But this is not the case for some other class of events like trace events as tracepoints are executed in the same context than the code that triggered the event. It means we need a different api to capture the regs there, namely we need a hot snapshot to get the most important informations for perf: the instruction pointer to get the event origin, the frame pointer for the callchain, the code segment for user_mode() tests (we always use __KERNEL_CS as trace events always occur from the kernel) and the eflags for further purposes. v2: rename perf_save_regs to perf_fetch_caller_regs as per Masami's suggestion. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Masami Hiramatsu Cc: Jason Baron Cc: Archs --- arch/x86/kernel/cpu/perf_event.c | 12 ++++++++++++ arch/x86/kernel/dumpstack.h | 15 ++++++++++++++ include/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++++++++++- kernel/perf_event.c | 5 +++++ 4 files changed, 73 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1d665a0b202c..c6bde7d7afdc 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1707,3 +1707,15 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } + +void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) +{ + regs->ip = ip; + /* + * perf_arch_fetch_caller_regs adds another call, we need to increment + * the skip level + */ + regs->bp = rewind_frame_pointer(skip + 1); + regs->cs = __KERNEL_CS; + local_save_flags(regs->flags); +} diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index 4fd1420faffa..29e5f7c845b2 100644 --- a/arch/x86/kernel/dumpstack.h +++ b/arch/x86/kernel/dumpstack.h @@ -29,4 +29,19 @@ struct stack_frame { struct stack_frame *next_frame; unsigned long return_address; }; + +static inline unsigned long rewind_frame_pointer(int n) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + while (n--) + frame = frame->next_frame; #endif + + return (unsigned long)frame; +} + +#endif /* DUMPSTACK_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 80acbf3d5de1..70cffd052c04 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -452,6 +452,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 @@ -847,6 +848,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) __perf_sw_event(event_id, nr, nmi, regs, addr); } +extern void +perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); + +/* + * Take a snapshot of the regs. Skip ip and frame pointer to + * the nth caller. We only need a few of the regs: + * - ip for PERF_SAMPLE_IP + * - cs for user_mode() tests + * - bp for callchains + * - eflags, for future purposes, just in case + */ +static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) +{ + unsigned long ip; + + memset(regs, 0, sizeof(*regs)); + + switch (skip) { + case 1 : + ip = CALLER_ADDR0; + break; + case 2 : + ip = CALLER_ADDR1; + break; + case 3 : + ip = CALLER_ADDR2; + break; + case 4: + ip = CALLER_ADDR3; + break; + /* No need to support further for now */ + default: + ip = 0; + } + + return perf_arch_fetch_caller_regs(regs, ip, skip); +} + extern void __perf_event_mmap(struct vm_area_struct *vma); static inline void perf_event_mmap(struct vm_area_struct *vma) @@ -880,7 +919,8 @@ static inline bool perf_paranoid_kernel(void) } extern void perf_event_init(void); -extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size); +extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, + int entry_size, struct pt_regs *regs); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 52c69a34d697..359d7f690c2b 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2786,6 +2786,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return NULL; } +__weak +void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) +{ +} + /* * Output */ -- cgit v1.2.3 From c530665c31c0140b74ca7689e7f836177796e5bd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 3 Mar 2010 07:16:16 +0100 Subject: perf: Take a hot regs snapshot for trace events We are taking a wrong regs snapshot when a trace event triggers. Either we use get_irq_regs(), which gives us the interrupted registers if we are in an interrupt, or we use task_pt_regs() which gives us the state before we entered the kernel, assuming we are lucky enough to be no kernel thread, in which case task_pt_regs() returns the initial set of regs when the kernel thread was started. What we want is different. We need a hot snapshot of the regs, so that we can get the instruction pointer to record in the sample, the frame pointer for the callchain, and some other things. Let's use the new perf_fetch_caller_regs() for that. Comparison with perf record -e lock: -R -a -f -g Before: perf [kernel] [k] __do_softirq | --- __do_softirq | |--55.16%-- __open | --44.84%-- __write_nocancel After: perf [kernel] [k] perf_tp_event | --- perf_tp_event | |--41.07%-- lock_acquire | | | |--39.36%-- _raw_spin_lock | | | | | |--7.81%-- hrtimer_interrupt | | | smp_apic_timer_interrupt | | | apic_timer_interrupt The old case was producing unreliable callchains. Now having right frame and instruction pointers, we have the trace we want. Also syscalls and kprobe events already have the right regs, let's use them instead of wasting a retrieval. v2: Follow the rename perf_save_regs() -> perf_fetch_caller_regs() Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Masami Hiramatsu Cc: Jason Baron Cc: Archs --- include/linux/ftrace_event.h | 7 +++++-- include/trace/ftrace.h | 6 +++++- kernel/perf_event.c | 8 ++------ kernel/trace/trace_event_profile.c | 3 ++- kernel/trace/trace_kprobe.c | 5 +++-- kernel/trace/trace_syscalls.c | 4 ++-- 6 files changed, 19 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 6b7c444ab8f6..ac424f18ce63 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -187,6 +187,9 @@ do { \ #ifdef CONFIG_PERF_EVENTS struct perf_event; + +DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); + extern int ftrace_profile_enable(int event_id); extern void ftrace_profile_disable(int event_id); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, @@ -198,11 +201,11 @@ ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp, static inline void ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr, - u64 count, unsigned long irq_flags) + u64 count, unsigned long irq_flags, struct pt_regs *regs) { struct trace_entry *entry = raw_data; - perf_tp_event(entry->type, addr, count, raw_data, size); + perf_tp_event(entry->type, addr, count, raw_data, size, regs); perf_swevent_put_recursion_context(rctx); local_irq_restore(irq_flags); } diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 0804cd594803..f31bb8b9777c 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -764,6 +764,7 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ struct ftrace_raw_##call *entry; \ u64 __addr = 0, __count = 1; \ unsigned long irq_flags; \ + struct pt_regs *__regs; \ int __entry_size; \ int __data_size; \ int rctx; \ @@ -784,8 +785,11 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ \ { assign; } \ \ + __regs = &__get_cpu_var(perf_trace_regs); \ + perf_fetch_caller_regs(__regs, 2); \ + \ ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr, \ - __count, irq_flags); \ + __count, irq_flags, __regs); \ } #undef DEFINE_EVENT diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 359d7f690c2b..45b4b6e55891 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4318,9 +4318,8 @@ static const struct pmu perf_ops_task_clock = { #ifdef CONFIG_EVENT_TRACING void perf_tp_event(int event_id, u64 addr, u64 count, void *record, - int entry_size) + int entry_size, struct pt_regs *regs) { - struct pt_regs *regs = get_irq_regs(); struct perf_sample_data data; struct perf_raw_record raw = { .size = entry_size, @@ -4330,12 +4329,9 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record, perf_sample_data_init(&data, addr); data.raw = &raw; - if (!regs) - regs = task_pt_regs(current); - /* Trace events already protected against recursion */ do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, - &data, regs); + &data, regs); } EXPORT_SYMBOL_GPL(perf_tp_event); diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index f0d693005075..e66d21e15a0f 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -2,13 +2,14 @@ * trace event based perf counter profiling * * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra - * + * Copyright (C) 2009-2010 Frederic Weisbecker */ #include #include #include "trace.h" +DEFINE_PER_CPU(struct pt_regs, perf_trace_regs); static char *perf_trace_buf; static char *perf_trace_buf_nmi; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 505c92273b1a..f7a20a8bfb31 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1240,7 +1240,7 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp, for (i = 0; i < tp->nr_args; i++) entry->args[i] = call_fetch(&tp->args[i].fetch, regs); - ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags); + ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs); } /* Kretprobe profile handler */ @@ -1271,7 +1271,8 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri, for (i = 0; i < tp->nr_args; i++) entry->args[i] = call_fetch(&tp->args[i].fetch, regs); - ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags); + ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, + irq_flags, regs); } static int probe_profile_enable(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index cba47d7935cc..7e6e84fb7b6c 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -467,7 +467,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags); + ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags, regs); } int prof_sysenter_enable(struct ftrace_event_call *call) @@ -542,7 +542,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags); + ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags, regs); } int prof_sysexit_enable(struct ftrace_event_call *call) -- cgit v1.2.3 From 97d5a22005f38057b4bc0d95f81cd26510268794 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 5 Mar 2010 05:35:37 +0100 Subject: perf: Drop the obsolete profile naming for trace events Drop the obsolete "profile" naming used by perf for trace events. Perf can now do more than simple events counting, so generalize the API naming. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Masami Hiramatsu Cc: Jason Baron --- include/linux/ftrace_event.h | 16 ++-- include/linux/syscalls.h | 24 +++--- include/trace/ftrace.h | 38 ++++----- include/trace/syscall.h | 8 +- kernel/perf_event.c | 4 +- kernel/trace/Makefile | 2 +- kernel/trace/trace_event_perf.c | 165 +++++++++++++++++++++++++++++++++++++ kernel/trace/trace_event_profile.c | 165 ------------------------------------- kernel/trace/trace_events.c | 2 +- kernel/trace/trace_kprobe.c | 28 +++---- kernel/trace/trace_syscalls.c | 72 ++++++++-------- 11 files changed, 262 insertions(+), 262 deletions(-) create mode 100644 kernel/trace/trace_event_perf.c delete mode 100644 kernel/trace/trace_event_profile.c (limited to 'kernel') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index ac424f18ce63..c0f4b364c711 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -131,12 +131,12 @@ struct ftrace_event_call { void *mod; void *data; - int profile_count; - int (*profile_enable)(struct ftrace_event_call *); - void (*profile_disable)(struct ftrace_event_call *); + int perf_refcount; + int (*perf_event_enable)(struct ftrace_event_call *); + void (*perf_event_disable)(struct ftrace_event_call *); }; -#define FTRACE_MAX_PROFILE_SIZE 2048 +#define PERF_MAX_TRACE_SIZE 2048 #define MAX_FILTER_PRED 32 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ @@ -190,17 +190,17 @@ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -extern int ftrace_profile_enable(int event_id); -extern void ftrace_profile_disable(int event_id); +extern int perf_trace_enable(int event_id); +extern void perf_trace_disable(int event_id); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); extern void * -ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp, +perf_trace_buf_prepare(int size, unsigned short type, int *rctxp, unsigned long *irq_flags); static inline void -ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr, +perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, u64 count, unsigned long irq_flags, struct pt_regs *regs) { struct trace_entry *entry = raw_data; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8126f239edf0..51435bcc3460 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -101,18 +101,18 @@ struct perf_event_attr; #ifdef CONFIG_PERF_EVENTS -#define TRACE_SYS_ENTER_PROFILE_INIT(sname) \ - .profile_enable = prof_sysenter_enable, \ - .profile_disable = prof_sysenter_disable, +#define TRACE_SYS_ENTER_PERF_INIT(sname) \ + .perf_event_enable = perf_sysenter_enable, \ + .perf_event_disable = perf_sysenter_disable, -#define TRACE_SYS_EXIT_PROFILE_INIT(sname) \ - .profile_enable = prof_sysexit_enable, \ - .profile_disable = prof_sysexit_disable, +#define TRACE_SYS_EXIT_PERF_INIT(sname) \ + .perf_event_enable = perf_sysexit_enable, \ + .perf_event_disable = perf_sysexit_disable, #else -#define TRACE_SYS_ENTER_PROFILE(sname) -#define TRACE_SYS_ENTER_PROFILE_INIT(sname) -#define TRACE_SYS_EXIT_PROFILE(sname) -#define TRACE_SYS_EXIT_PROFILE_INIT(sname) +#define TRACE_SYS_ENTER_PERF(sname) +#define TRACE_SYS_ENTER_PERF_INIT(sname) +#define TRACE_SYS_EXIT_PERF(sname) +#define TRACE_SYS_EXIT_PERF_INIT(sname) #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_FTRACE_SYSCALLS @@ -149,7 +149,7 @@ struct perf_event_attr; .regfunc = reg_event_syscall_enter, \ .unregfunc = unreg_event_syscall_enter, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_ENTER_PROFILE_INIT(sname) \ + TRACE_SYS_ENTER_PERF_INIT(sname) \ } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ @@ -171,7 +171,7 @@ struct perf_event_attr; .regfunc = reg_event_syscall_exit, \ .unregfunc = unreg_event_syscall_exit, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_EXIT_PROFILE_INIT(sname) \ + TRACE_SYS_EXIT_PERF_INIT(sname) \ } #define SYSCALL_METADATA(sname, nb) \ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index f31bb8b9777c..25ab56f75d65 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -401,18 +401,18 @@ static inline notrace int ftrace_get_offsets_##call( \ #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) \ \ -static void ftrace_profile_##name(proto); \ +static void perf_trace_##name(proto); \ \ static notrace int \ -ftrace_profile_enable_##name(struct ftrace_event_call *unused) \ +perf_trace_enable_##name(struct ftrace_event_call *unused) \ { \ - return register_trace_##name(ftrace_profile_##name); \ + return register_trace_##name(perf_trace_##name); \ } \ \ static notrace void \ -ftrace_profile_disable_##name(struct ftrace_event_call *unused) \ +perf_trace_disable_##name(struct ftrace_event_call *unused) \ { \ - unregister_trace_##name(ftrace_profile_##name); \ + unregister_trace_##name(perf_trace_##name); \ } #undef DEFINE_EVENT_PRINT @@ -507,12 +507,12 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused) \ #ifdef CONFIG_PERF_EVENTS -#define _TRACE_PROFILE_INIT(call) \ - .profile_enable = ftrace_profile_enable_##call, \ - .profile_disable = ftrace_profile_disable_##call, +#define _TRACE_PERF_INIT(call) \ + .perf_event_enable = perf_trace_enable_##call, \ + .perf_event_disable = perf_trace_disable_##call, #else -#define _TRACE_PROFILE_INIT(call) +#define _TRACE_PERF_INIT(call) #endif /* CONFIG_PERF_EVENTS */ #undef __entry @@ -638,7 +638,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .unregfunc = ftrace_raw_unreg_event_##call, \ .print_fmt = print_fmt_##template, \ .define_fields = ftrace_define_fields_##template, \ - _TRACE_PROFILE_INIT(call) \ + _TRACE_PERF_INIT(call) \ } #undef DEFINE_EVENT_PRINT @@ -657,18 +657,18 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .unregfunc = ftrace_raw_unreg_event_##call, \ .print_fmt = print_fmt_##call, \ .define_fields = ftrace_define_fields_##template, \ - _TRACE_PROFILE_INIT(call) \ + _TRACE_PERF_INIT(call) \ } #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* - * Define the insertion callback to profile events + * Define the insertion callback to perf events * * The job is very similar to ftrace_raw_event_ except that we don't * insert in the ring buffer but in a perf counter. * - * static void ftrace_profile_(proto) + * static void ftrace_perf_(proto) * { * struct ftrace_data_offsets_ __maybe_unused __data_offsets; * struct ftrace_event_call *event_call = &event_; @@ -757,7 +757,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ -ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ +perf_trace_templ_##call(struct ftrace_event_call *event_call, \ proto) \ { \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ @@ -774,10 +774,10 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ sizeof(u64)); \ __entry_size -= sizeof(u32); \ \ - if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE, \ + if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE, \ "profile buffer not large enough")) \ return; \ - entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare( \ + entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare( \ __entry_size, event_call->id, &rctx, &irq_flags); \ if (!entry) \ return; \ @@ -788,17 +788,17 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ __regs = &__get_cpu_var(perf_trace_regs); \ perf_fetch_caller_regs(__regs, 2); \ \ - ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr, \ + perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ __count, irq_flags, __regs); \ } #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ -static notrace void ftrace_profile_##call(proto) \ +static notrace void perf_trace_##call(proto) \ { \ struct ftrace_event_call *event_call = &event_##call; \ \ - ftrace_profile_templ_##template(event_call, args); \ + perf_trace_templ_##template(event_call, args); \ } #undef DEFINE_EVENT_PRINT diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 0387100752f0..e5e5f48dbfb3 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -47,10 +47,10 @@ enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags); #endif #ifdef CONFIG_PERF_EVENTS -int prof_sysenter_enable(struct ftrace_event_call *call); -void prof_sysenter_disable(struct ftrace_event_call *call); -int prof_sysexit_enable(struct ftrace_event_call *call); -void prof_sysexit_disable(struct ftrace_event_call *call); +int perf_sysenter_enable(struct ftrace_event_call *call); +void perf_sysenter_disable(struct ftrace_event_call *call); +int perf_sysexit_enable(struct ftrace_event_call *call); +void perf_sysexit_disable(struct ftrace_event_call *call); #endif #endif /* _TRACE_SYSCALL_H */ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 45b4b6e55891..c502b18594cc 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4347,7 +4347,7 @@ static int perf_tp_event_match(struct perf_event *event, static void tp_perf_event_destroy(struct perf_event *event) { - ftrace_profile_disable(event->attr.config); + perf_trace_disable(event->attr.config); } static const struct pmu *tp_perf_event_init(struct perf_event *event) @@ -4361,7 +4361,7 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event) !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (ftrace_profile_enable(event->attr.config)) + if (perf_trace_enable(event->attr.config)) return NULL; event->destroy = tp_perf_event_destroy; diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index d00c6fe23f54..78edc6490038 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events.o obj-$(CONFIG_EVENT_TRACING) += trace_export.o obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o ifeq ($(CONFIG_PERF_EVENTS),y) -obj-$(CONFIG_EVENT_TRACING) += trace_event_profile.o +obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c new file mode 100644 index 000000000000..f315b12a41d8 --- /dev/null +++ b/kernel/trace/trace_event_perf.c @@ -0,0 +1,165 @@ +/* + * trace event based perf event profiling/tracing + * + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra + * Copyright (C) 2009-2010 Frederic Weisbecker + */ + +#include +#include +#include "trace.h" + +DEFINE_PER_CPU(struct pt_regs, perf_trace_regs); + +static char *perf_trace_buf; +static char *perf_trace_buf_nmi; + +typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ; + +/* Count the events in use (per event id, not per instance) */ +static int total_ref_count; + +static int perf_trace_event_enable(struct ftrace_event_call *event) +{ + char *buf; + int ret = -ENOMEM; + + if (event->perf_refcount++ > 0) + return 0; + + if (!total_ref_count) { + buf = (char *)alloc_percpu(perf_trace_t); + if (!buf) + goto fail_buf; + + rcu_assign_pointer(perf_trace_buf, buf); + + buf = (char *)alloc_percpu(perf_trace_t); + if (!buf) + goto fail_buf_nmi; + + rcu_assign_pointer(perf_trace_buf_nmi, buf); + } + + ret = event->perf_event_enable(event); + if (!ret) { + total_ref_count++; + return 0; + } + +fail_buf_nmi: + if (!total_ref_count) { + free_percpu(perf_trace_buf_nmi); + free_percpu(perf_trace_buf); + perf_trace_buf_nmi = NULL; + perf_trace_buf = NULL; + } +fail_buf: + event->perf_refcount--; + + return ret; +} + +int perf_trace_enable(int event_id) +{ + struct ftrace_event_call *event; + int ret = -EINVAL; + + mutex_lock(&event_mutex); + list_for_each_entry(event, &ftrace_events, list) { + if (event->id == event_id && event->perf_event_enable && + try_module_get(event->mod)) { + ret = perf_trace_event_enable(event); + break; + } + } + mutex_unlock(&event_mutex); + + return ret; +} + +static void perf_trace_event_disable(struct ftrace_event_call *event) +{ + char *buf, *nmi_buf; + + if (--event->perf_refcount > 0) + return; + + event->perf_event_disable(event); + + if (!--total_ref_count) { + buf = perf_trace_buf; + rcu_assign_pointer(perf_trace_buf, NULL); + + nmi_buf = perf_trace_buf_nmi; + rcu_assign_pointer(perf_trace_buf_nmi, NULL); + + /* + * Ensure every events in profiling have finished before + * releasing the buffers + */ + synchronize_sched(); + + free_percpu(buf); + free_percpu(nmi_buf); + } +} + +void perf_trace_disable(int event_id) +{ + struct ftrace_event_call *event; + + mutex_lock(&event_mutex); + list_for_each_entry(event, &ftrace_events, list) { + if (event->id == event_id) { + perf_trace_event_disable(event); + module_put(event->mod); + break; + } + } + mutex_unlock(&event_mutex); +} + +__kprobes void *perf_trace_buf_prepare(int size, unsigned short type, + int *rctxp, unsigned long *irq_flags) +{ + struct trace_entry *entry; + char *trace_buf, *raw_data; + int pc, cpu; + + pc = preempt_count(); + + /* Protect the per cpu buffer, begin the rcu read side */ + local_irq_save(*irq_flags); + + *rctxp = perf_swevent_get_recursion_context(); + if (*rctxp < 0) + goto err_recursion; + + cpu = smp_processor_id(); + + if (in_nmi()) + trace_buf = rcu_dereference(perf_trace_buf_nmi); + else + trace_buf = rcu_dereference(perf_trace_buf); + + if (!trace_buf) + goto err; + + raw_data = per_cpu_ptr(trace_buf, cpu); + + /* zero the dead bytes from align to not leak stack to user */ + *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + + entry = (struct trace_entry *)raw_data; + tracing_generic_entry_update(entry, *irq_flags, pc); + entry->type = type; + + return raw_data; +err: + perf_swevent_put_recursion_context(*rctxp); +err_recursion: + local_irq_restore(*irq_flags); + return NULL; +} +EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c deleted file mode 100644 index e66d21e15a0f..000000000000 --- a/kernel/trace/trace_event_profile.c +++ /dev/null @@ -1,165 +0,0 @@ -/* - * trace event based perf counter profiling - * - * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra - * Copyright (C) 2009-2010 Frederic Weisbecker - */ - -#include -#include -#include "trace.h" - -DEFINE_PER_CPU(struct pt_regs, perf_trace_regs); - -static char *perf_trace_buf; -static char *perf_trace_buf_nmi; - -typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ; - -/* Count the events in use (per event id, not per instance) */ -static int total_profile_count; - -static int ftrace_profile_enable_event(struct ftrace_event_call *event) -{ - char *buf; - int ret = -ENOMEM; - - if (event->profile_count++ > 0) - return 0; - - if (!total_profile_count) { - buf = (char *)alloc_percpu(perf_trace_t); - if (!buf) - goto fail_buf; - - rcu_assign_pointer(perf_trace_buf, buf); - - buf = (char *)alloc_percpu(perf_trace_t); - if (!buf) - goto fail_buf_nmi; - - rcu_assign_pointer(perf_trace_buf_nmi, buf); - } - - ret = event->profile_enable(event); - if (!ret) { - total_profile_count++; - return 0; - } - -fail_buf_nmi: - if (!total_profile_count) { - free_percpu(perf_trace_buf_nmi); - free_percpu(perf_trace_buf); - perf_trace_buf_nmi = NULL; - perf_trace_buf = NULL; - } -fail_buf: - event->profile_count--; - - return ret; -} - -int ftrace_profile_enable(int event_id) -{ - struct ftrace_event_call *event; - int ret = -EINVAL; - - mutex_lock(&event_mutex); - list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id && event->profile_enable && - try_module_get(event->mod)) { - ret = ftrace_profile_enable_event(event); - break; - } - } - mutex_unlock(&event_mutex); - - return ret; -} - -static void ftrace_profile_disable_event(struct ftrace_event_call *event) -{ - char *buf, *nmi_buf; - - if (--event->profile_count > 0) - return; - - event->profile_disable(event); - - if (!--total_profile_count) { - buf = perf_trace_buf; - rcu_assign_pointer(perf_trace_buf, NULL); - - nmi_buf = perf_trace_buf_nmi; - rcu_assign_pointer(perf_trace_buf_nmi, NULL); - - /* - * Ensure every events in profiling have finished before - * releasing the buffers - */ - synchronize_sched(); - - free_percpu(buf); - free_percpu(nmi_buf); - } -} - -void ftrace_profile_disable(int event_id) -{ - struct ftrace_event_call *event; - - mutex_lock(&event_mutex); - list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id) { - ftrace_profile_disable_event(event); - module_put(event->mod); - break; - } - } - mutex_unlock(&event_mutex); -} - -__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type, - int *rctxp, unsigned long *irq_flags) -{ - struct trace_entry *entry; - char *trace_buf, *raw_data; - int pc, cpu; - - pc = preempt_count(); - - /* Protect the per cpu buffer, begin the rcu read side */ - local_irq_save(*irq_flags); - - *rctxp = perf_swevent_get_recursion_context(); - if (*rctxp < 0) - goto err_recursion; - - cpu = smp_processor_id(); - - if (in_nmi()) - trace_buf = rcu_dereference(perf_trace_buf_nmi); - else - trace_buf = rcu_dereference(perf_trace_buf); - - if (!trace_buf) - goto err; - - raw_data = per_cpu_ptr(trace_buf, cpu); - - /* zero the dead bytes from align to not leak stack to user */ - *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; - - entry = (struct trace_entry *)raw_data; - tracing_generic_entry_update(entry, *irq_flags, pc); - entry->type = type; - - return raw_data; -err: - perf_swevent_put_recursion_context(*rctxp); -err_recursion: - local_irq_restore(*irq_flags); - return NULL; -} -EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 3f972ad98d04..beab8bf2f310 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -938,7 +938,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, trace_create_file("enable", 0644, call->dir, call, enable); - if (call->id && call->profile_enable) + if (call->id && call->perf_event_enable) trace_create_file("id", 0444, call->dir, call, id); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f7a20a8bfb31..1251e367bae9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1214,7 +1214,7 @@ static int set_print_fmt(struct trace_probe *tp) #ifdef CONFIG_PERF_EVENTS /* Kprobe profile handler */ -static __kprobes void kprobe_profile_func(struct kprobe *kp, +static __kprobes void kprobe_perf_func(struct kprobe *kp, struct pt_regs *regs) { struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); @@ -1227,11 +1227,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp, __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args); size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; - entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags); + entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags); if (!entry) return; @@ -1240,11 +1240,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp, for (i = 0; i < tp->nr_args; i++) entry->args[i] = call_fetch(&tp->args[i].fetch, regs); - ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs); + perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs); } /* Kretprobe profile handler */ -static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri, +static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); @@ -1257,11 +1257,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri, __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args); size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; - entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags); + entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags); if (!entry) return; @@ -1271,11 +1271,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri, for (i = 0; i < tp->nr_args; i++) entry->args[i] = call_fetch(&tp->args[i].fetch, regs); - ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, + perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags, regs); } -static int probe_profile_enable(struct ftrace_event_call *call) +static int probe_perf_enable(struct ftrace_event_call *call) { struct trace_probe *tp = (struct trace_probe *)call->data; @@ -1287,7 +1287,7 @@ static int probe_profile_enable(struct ftrace_event_call *call) return enable_kprobe(&tp->rp.kp); } -static void probe_profile_disable(struct ftrace_event_call *call) +static void probe_perf_disable(struct ftrace_event_call *call) { struct trace_probe *tp = (struct trace_probe *)call->data; @@ -1312,7 +1312,7 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) kprobe_trace_func(kp, regs); #ifdef CONFIG_PERF_EVENTS if (tp->flags & TP_FLAG_PROFILE) - kprobe_profile_func(kp, regs); + kprobe_perf_func(kp, regs); #endif return 0; /* We don't tweek kernel, so just return 0 */ } @@ -1326,7 +1326,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) kretprobe_trace_func(ri, regs); #ifdef CONFIG_PERF_EVENTS if (tp->flags & TP_FLAG_PROFILE) - kretprobe_profile_func(ri, regs); + kretprobe_perf_func(ri, regs); #endif return 0; /* We don't tweek kernel, so just return 0 */ } @@ -1359,8 +1359,8 @@ static int register_probe_event(struct trace_probe *tp) call->unregfunc = probe_event_disable; #ifdef CONFIG_PERF_EVENTS - call->profile_enable = probe_profile_enable; - call->profile_disable = probe_profile_disable; + call->perf_event_enable = probe_perf_enable; + call->perf_event_disable = probe_perf_disable; #endif call->data = tp; ret = trace_add_event_call(call); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 7e6e84fb7b6c..33c2a5b769dc 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -428,12 +428,12 @@ core_initcall(init_ftrace_syscalls); #ifdef CONFIG_PERF_EVENTS -static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls); -static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls); -static int sys_prof_refcount_enter; -static int sys_prof_refcount_exit; +static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls); +static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls); +static int sys_perf_refcount_enter; +static int sys_perf_refcount_exit; -static void prof_syscall_enter(struct pt_regs *regs, long id) +static void perf_syscall_enter(struct pt_regs *regs, long id) { struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; @@ -443,7 +443,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) int size; syscall_nr = syscall_get_nr(current, regs); - if (!test_bit(syscall_nr, enabled_prof_enter_syscalls)) + if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) return; sys_data = syscall_nr_to_meta(syscall_nr); @@ -455,11 +455,11 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) size = ALIGN(size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, - "profile buffer not large enough")) + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, + "perf buffer not large enough")) return; - rec = (struct syscall_trace_enter *)ftrace_perf_buf_prepare(size, + rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, sys_data->enter_event->id, &rctx, &flags); if (!rec) return; @@ -467,10 +467,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags, regs); + perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs); } -int prof_sysenter_enable(struct ftrace_event_call *call) +int perf_sysenter_enable(struct ftrace_event_call *call) { int ret = 0; int num; @@ -478,34 +478,34 @@ int prof_sysenter_enable(struct ftrace_event_call *call) num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); - if (!sys_prof_refcount_enter) - ret = register_trace_sys_enter(prof_syscall_enter); + if (!sys_perf_refcount_enter) + ret = register_trace_sys_enter(perf_syscall_enter); if (ret) { pr_info("event trace: Could not activate" "syscall entry trace point"); } else { - set_bit(num, enabled_prof_enter_syscalls); - sys_prof_refcount_enter++; + set_bit(num, enabled_perf_enter_syscalls); + sys_perf_refcount_enter++; } mutex_unlock(&syscall_trace_lock); return ret; } -void prof_sysenter_disable(struct ftrace_event_call *call) +void perf_sysenter_disable(struct ftrace_event_call *call) { int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); - sys_prof_refcount_enter--; - clear_bit(num, enabled_prof_enter_syscalls); - if (!sys_prof_refcount_enter) - unregister_trace_sys_enter(prof_syscall_enter); + sys_perf_refcount_enter--; + clear_bit(num, enabled_perf_enter_syscalls); + if (!sys_perf_refcount_enter) + unregister_trace_sys_enter(perf_syscall_enter); mutex_unlock(&syscall_trace_lock); } -static void prof_syscall_exit(struct pt_regs *regs, long ret) +static void perf_syscall_exit(struct pt_regs *regs, long ret) { struct syscall_metadata *sys_data; struct syscall_trace_exit *rec; @@ -515,7 +515,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) int size; syscall_nr = syscall_get_nr(current, regs); - if (!test_bit(syscall_nr, enabled_prof_exit_syscalls)) + if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) return; sys_data = syscall_nr_to_meta(syscall_nr); @@ -530,11 +530,11 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) * Impossible, but be paranoid with the future * How to put this check outside runtime? */ - if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, - "exit event has grown above profile buffer size")) + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, + "exit event has grown above perf buffer size")) return; - rec = (struct syscall_trace_exit *)ftrace_perf_buf_prepare(size, + rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, sys_data->exit_event->id, &rctx, &flags); if (!rec) return; @@ -542,10 +542,10 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags, regs); + perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs); } -int prof_sysexit_enable(struct ftrace_event_call *call) +int perf_sysexit_enable(struct ftrace_event_call *call) { int ret = 0; int num; @@ -553,30 +553,30 @@ int prof_sysexit_enable(struct ftrace_event_call *call) num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); - if (!sys_prof_refcount_exit) - ret = register_trace_sys_exit(prof_syscall_exit); + if (!sys_perf_refcount_exit) + ret = register_trace_sys_exit(perf_syscall_exit); if (ret) { pr_info("event trace: Could not activate" "syscall exit trace point"); } else { - set_bit(num, enabled_prof_exit_syscalls); - sys_prof_refcount_exit++; + set_bit(num, enabled_perf_exit_syscalls); + sys_perf_refcount_exit++; } mutex_unlock(&syscall_trace_lock); return ret; } -void prof_sysexit_disable(struct ftrace_event_call *call) +void perf_sysexit_disable(struct ftrace_event_call *call) { int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; mutex_lock(&syscall_trace_lock); - sys_prof_refcount_exit--; - clear_bit(num, enabled_prof_exit_syscalls); - if (!sys_prof_refcount_exit) - unregister_trace_sys_exit(prof_syscall_exit); + sys_perf_refcount_exit--; + clear_bit(num, enabled_perf_exit_syscalls); + if (!sys_perf_refcount_exit) + unregister_trace_sys_exit(perf_syscall_exit); mutex_unlock(&syscall_trace_lock); } -- cgit v1.2.3 From 0b1adaa031a55e44f5dd942f234bf09d28e8a0d6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 9 Mar 2010 19:45:54 +0100 Subject: genirq: Prevent oneshot irq thread race Lars-Peter pointed out that the oneshot threaded interrupt handler code has the following race: CPU0 CPU1 hande_level_irq(irq X) mask_ack_irq(irq X) handle_IRQ_event(irq X) wake_up(thread_handler) thread handler(irq X) runs finalize_oneshot(irq X) does not unmask due to !(desc->status & IRQ_MASKED) return from irq does not unmask due to (desc->status & IRQ_ONESHOT) This leaves the interrupt line masked forever. The reason for this is the inconsistent handling of the IRQ_MASKED flag. Instead of setting it in the mask function the oneshot support sets the flag after waking up the irq thread. The solution for this is to set/clear the IRQ_MASKED status whenever we mask/unmask an interrupt line. That's the easy part, but that cleanup opens another race: CPU0 CPU1 hande_level_irq(irq) mask_ack_irq(irq) handle_IRQ_event(irq) wake_up(thread_handler) thread handler(irq) runs finalize_oneshot_irq(irq) unmask(irq) irq triggers again handle_level_irq(irq) mask_ack_irq(irq) return from irq due to IRQ_INPROGRESS return from irq does not unmask due to (desc->status & IRQ_ONESHOT) This requires that we synchronize finalize_oneshot_irq() with the primary handler. If IRQ_INPROGESS is set we wait until the primary handler on the other CPU has returned before unmasking the interrupt line again. We probably have never seen that problem because it does not happen on UP and on SMP the irqbalancer protects us by pinning the primary handler and the thread to the same CPU. Reported-by: Lars-Peter Clausen Signed-off-by: Thomas Gleixner Cc: stable@kernel.org --- kernel/irq/chip.c | 31 ++++++++++++++++++++++--------- kernel/irq/manage.c | 18 ++++++++++++++++++ 2 files changed, 40 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index d70394f12ee9..71eba24a39a2 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -359,6 +359,23 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq) if (desc->chip->ack) desc->chip->ack(irq); } + desc->status |= IRQ_MASKED; +} + +static inline void mask_irq(struct irq_desc *desc, int irq) +{ + if (desc->chip->mask) { + desc->chip->mask(irq); + desc->status |= IRQ_MASKED; + } +} + +static inline void unmask_irq(struct irq_desc *desc, int irq) +{ + if (desc->chip->unmask) { + desc->chip->unmask(irq); + desc->status &= ~IRQ_MASKED; + } } /* @@ -484,10 +501,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc) raw_spin_lock(&desc->lock); desc->status &= ~IRQ_INPROGRESS; - if (unlikely(desc->status & IRQ_ONESHOT)) - desc->status |= IRQ_MASKED; - else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask) - desc->chip->unmask(irq); + if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT))) + unmask_irq(desc, irq); out_unlock: raw_spin_unlock(&desc->lock); } @@ -524,8 +539,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) action = desc->action; if (unlikely(!action || (desc->status & IRQ_DISABLED))) { desc->status |= IRQ_PENDING; - if (desc->chip->mask) - desc->chip->mask(irq); + mask_irq(desc, irq); goto out; } @@ -593,7 +607,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) irqreturn_t action_ret; if (unlikely(!action)) { - desc->chip->mask(irq); + mask_irq(desc, irq); goto out_unlock; } @@ -605,8 +619,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) if (unlikely((desc->status & (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) == (IRQ_PENDING | IRQ_MASKED))) { - desc->chip->unmask(irq); - desc->status &= ~IRQ_MASKED; + unmask_irq(desc, irq); } desc->status &= ~IRQ_PENDING; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index eb6078ca60c7..69a3d7b9414c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -483,8 +483,26 @@ static int irq_wait_for_interrupt(struct irqaction *action) */ static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc) { +again: chip_bus_lock(irq, desc); raw_spin_lock_irq(&desc->lock); + + /* + * Implausible though it may be we need to protect us against + * the following scenario: + * + * The thread is faster done than the hard interrupt handler + * on the other CPU. If we unmask the irq line then the + * interrupt can come in again and masks the line, leaves due + * to IRQ_INPROGRESS and the irq line is masked forever. + */ + if (unlikely(desc->status & IRQ_INPROGRESS)) { + raw_spin_unlock_irq(&desc->lock); + chip_bus_sync_unlock(irq, desc); + cpu_relax(); + goto again; + } + if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) { desc->status &= ~IRQ_MASKED; desc->chip->unmask(irq); -- cgit v1.2.3 From 220b140b52ab6cc133f674a7ffec8fa792054f25 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 10 Mar 2010 20:45:52 +1100 Subject: perf_event: Fix oops triggered by cpu offline/online Anton Blanchard found that he could reliably make the kernel hit a BUG_ON in the slab allocator by taking a cpu offline and then online while a system-wide perf record session was running. The reason is that when the cpu comes up, we completely reinitialize the ctx field of the struct perf_cpu_context for the cpu. If there is a system-wide perf record session running, then there will be a struct perf_event that has a reference to the context, so its refcount will be 2. (The perf_event has been removed from the context's group_entry and event_entry lists by perf_event_exit_cpu(), but that doesn't remove the perf_event's reference to the context and doesn't decrement the context's refcount.) When the cpu comes up, perf_event_init_cpu() gets called, and it calls __perf_event_init_context() on the cpu's context. That resets the refcount to 1. Then when the perf record session finishes and the perf_event is closed, the refcount gets decremented to 0 and the context gets kfreed after an RCU grace period. Since the context wasn't kmalloced -- it's part of a per-cpu variable -- bad things happen. In fact we don't need to completely reinitialize the context when the cpu comes up. It's sufficient to initialize the context once at boot, but we need to do it for all possible cpus. This moves the context initialization to happen at boot time. With this, we don't trash the refcount and the context never gets kfreed, and we don't hit the BUG_ON. Reported-by: Anton Blanchard Signed-off-by: Paul Mackerras Tested-by: Anton Blanchard Acked-by: Peter Zijlstra Cc: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index c502b18594cc..fb3031cf9f17 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -5368,12 +5368,22 @@ int perf_event_init_task(struct task_struct *child) return ret; } +static void __init perf_event_init_all_cpus(void) +{ + int cpu; + struct perf_cpu_context *cpuctx; + + for_each_possible_cpu(cpu) { + cpuctx = &per_cpu(perf_cpu_context, cpu); + __perf_event_init_context(&cpuctx->ctx, NULL); + } +} + static void __cpuinit perf_event_init_cpu(int cpu) { struct perf_cpu_context *cpuctx; cpuctx = &per_cpu(perf_cpu_context, cpu); - __perf_event_init_context(&cpuctx->ctx, NULL); spin_lock(&perf_resource_lock); cpuctx->max_pertask = perf_max_events - perf_reserved_percpu; @@ -5439,6 +5449,7 @@ static struct notifier_block __cpuinitdata perf_cpu_nb = { void __init perf_event_init(void) { + perf_event_init_all_cpus(); perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE, -- cgit v1.2.3 From 3f379b03fbfddd20536389a85c6456f8233d1f8d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 5 Mar 2010 15:03:25 -0800 Subject: ftrace: Replace read_barrier_depends() with rcu_dereference_raw() Replace the calls to read_barrier_depends() in ftrace_list_func() with rcu_dereference_raw() to improve readability. The reason that we use rcu_dereference_raw() here is that removed entries are never freed, instead they are simply leaked. This is one of a very few cases where use of rcu_dereference_raw() is the long-term right answer. And I don't yet know of any others. ;-) Signed-off-by: Paul E. McKenney Acked-by: Steven Rostedt Cc: Frederic Weisbecker Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1267830207-9474-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 83783579378f..8c5adc0e5db3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -88,18 +89,22 @@ ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static int ftrace_set_func(unsigned long *array, int *idx, char *buffer); #endif +/* + * Traverse the ftrace_list, invoking all entries. The reason that we + * can use rcu_dereference_raw() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw() calls are needed to handle + * concurrent insertions into the ftrace_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) { - struct ftrace_ops *op = ftrace_list; - - /* in case someone actually ports this to alpha! */ - read_barrier_depends(); + struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/ while (op != &ftrace_list_end) { - /* silly alpha */ - read_barrier_depends(); op->func(ip, parent_ip); - op = op->next; + op = rcu_dereference_raw(op->next); /*see above*/ }; } @@ -154,8 +159,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) * the ops->next pointer is valid before another CPU sees * the ops pointer included into the ftrace_list. */ - smp_wmb(); - ftrace_list = ops; + rcu_assign_pointer(ftrace_list, ops); if (ftrace_enabled) { ftrace_func_t func; -- cgit v1.2.3 From 007b09243b099811124f69d492adeebe9e439f96 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 5 Mar 2010 15:03:26 -0800 Subject: rcu: Increase RCU CPU stall timeouts if PROVE_RCU CONFIG_PROVE_RCU imposes additional overhead on the kernel, so increase the RCU CPU stall timeouts in an attempt to allow for this effect. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1267830207-9474-2-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/rcutree.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 1439eb504c22..4a525a30e08e 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -246,12 +246,21 @@ struct rcu_data { #define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ #ifdef CONFIG_RCU_CPU_STALL_DETECTOR -#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rsp->jiffies_stall */ -#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rsp->jiffies_stall */ -#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */ - /* to take at least one */ - /* scheduling clock irq */ - /* before ratting on them. */ + +#ifdef CONFIG_PROVE_RCU +#define RCU_STALL_DELAY_DELTA (5 * HZ) +#else +#define RCU_STALL_DELAY_DELTA 0 +#endif + +#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ + RCU_STALL_DELAY_DELTA) + /* for rsp->jiffies_stall */ +#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA) + /* for rsp->jiffies_stall */ +#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */ + /* to take at least one */ + /* scheduling clock irq */ + /* before ratting on them. */ #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ -- cgit v1.2.3 From 83ff56f46a8532488ee364bb93a9cb2a59490d33 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 9 Mar 2010 10:22:19 -0500 Subject: kprobes: Calculate the index correctly when freeing the out-of-line execution slot From : Ananth N Mavinakayanahalli When freeing the instruction slot, the arithmetic to calculate the index of the slot in the page needs to account for the total size of the instruction on the various architectures. Calculate the index correctly when freeing the out-of-line execution slot. Reported-by: Sachin Sant Reported-by: Heiko Carstens Signed-off-by: Ananth N Mavinakayanahalli Signed-off-by: Masami Hiramatsu LKML-Reference: <4B9667AB.9050507@redhat.com> Signed-off-by: Ingo Molnar --- kernel/kprobes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index fa034d29cf73..0ed46f3e51e9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -259,7 +259,8 @@ static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c, struct kprobe_insn_page *kip; list_for_each_entry(kip, &c->pages, list) { - long idx = ((long)slot - (long)kip->insns) / c->insn_size; + long idx = ((long)slot - (long)kip->insns) / + (c->insn_size * sizeof(kprobe_opcode_t)); if (idx >= 0 && idx < slots_per_page(c)) { WARN_ON(kip->slot_used[idx] != SLOT_USED); if (dirty) { -- cgit v1.2.3 From 639fe4b12f92b54c9c3b38c82cdafaa38cfd3e63 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 11 Mar 2010 15:30:35 +0800 Subject: perf: export perf_trace_regs and perf_arch_fetch_caller_regs Export perf_trace_regs and perf_arch_fetch_caller_regs since module will use these. Signed-off-by: Xiao Guangrong [ use EXPORT_PER_CPU_SYMBOL_GPL() ] Signed-off-by: Peter Zijlstra LKML-Reference: <4B989C1B.2090407@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 1 + kernel/trace/trace_event_perf.c | 1 + 2 files changed, 2 insertions(+) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5fb490c6ee5c..7645faea8e85 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1713,3 +1713,4 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski regs->cs = __KERNEL_CS; local_save_flags(regs->flags); } +EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index f315b12a41d8..0709e4f75114 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -10,6 +10,7 @@ #include "trace.h" DEFINE_PER_CPU(struct pt_regs, perf_trace_regs); +EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs); static char *perf_trace_buf; static char *perf_trace_buf_nmi; -- cgit v1.2.3 From 80a05b9ffa7dc13f6693902dd8999a2b61a3a0d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 Mar 2010 17:34:14 +0100 Subject: clockevents: Sanitize min_delta_ns adjustment and prevent overflows The current logic which handles clock events programming failures can increase min_delta_ns unlimited and even can cause overflows. Sanitize it by: - prevent zero increase when min_delta_ns == 1 - limiting min_delta_ns to a jiffie - bail out if the jiffie limit is hit - add retries stats for /proc/timer_list so we can gather data Reported-by: Uwe Kleine-Koenig Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 2 ++ kernel/time/tick-oneshot.c | 52 +++++++++++++++++++++++++++++++++++----------- kernel/time/timer_list.c | 3 ++- 3 files changed, 44 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 0cf725bdd2a1..fc53492b6ad7 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -73,6 +73,7 @@ enum clock_event_nofitiers { * @list: list head for the management code * @mode: operating mode assigned by the management code * @next_event: local storage for the next event in oneshot mode + * @retries: number of forced programming retries */ struct clock_event_device { const char *name; @@ -93,6 +94,7 @@ struct clock_event_device { struct list_head list; enum clock_event_mode mode; ktime_t next_event; + unsigned long retries; }; /* diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 0a8a213016f0..aada0e52680a 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -22,6 +22,29 @@ #include "tick-internal.h" +/* Limit min_delta to a jiffie */ +#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) + +static int tick_increase_min_delta(struct clock_event_device *dev) +{ + /* Nothing to do if we already reached the limit */ + if (dev->min_delta_ns >= MIN_DELTA_LIMIT) + return -ETIME; + + if (dev->min_delta_ns < 5000) + dev->min_delta_ns = 5000; + else + dev->min_delta_ns += dev->min_delta_ns >> 1; + + if (dev->min_delta_ns > MIN_DELTA_LIMIT) + dev->min_delta_ns = MIN_DELTA_LIMIT; + + printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); + return 0; +} + /** * tick_program_event internal worker function */ @@ -37,23 +60,28 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires, if (!ret || !force) return ret; + dev->retries++; /* - * We tried 2 times to program the device with the given - * min_delta_ns. If that's not working then we double it + * We tried 3 times to program the device with the given + * min_delta_ns. If that's not working then we increase it * and emit a warning. */ if (++i > 2) { /* Increase the min. delta and try again */ - if (!dev->min_delta_ns) - dev->min_delta_ns = 5000; - else - dev->min_delta_ns += dev->min_delta_ns >> 1; - - printk(KERN_WARNING - "CE: %s increasing min_delta_ns to %llu nsec\n", - dev->name ? dev->name : "?", - (unsigned long long) dev->min_delta_ns << 1); - + if (tick_increase_min_delta(dev)) { + /* + * Get out of the loop if min_delta_ns + * hit the limit already. That's + * better than staying here forever. + * + * We clear next_event so we have a + * chance that the box survives. + */ + printk(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); + dev->next_event.tv64 = KTIME_MAX; + return -ETIME; + } i = 0; } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index bdfb8dd1050c..1a4a7dd78777 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -228,6 +228,7 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) SEQ_printf(m, " event_handler: "); print_name_offset(m, dev->event_handler); SEQ_printf(m, "\n"); + SEQ_printf(m, " retries: %lu\n", dev->retries); } static void timer_list_show_tickdevices(struct seq_file *m) @@ -257,7 +258,7 @@ static int timer_list_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Timer List Version: v0.5\n"); + SEQ_printf(m, "Timer List Version: v0.6\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); -- cgit v1.2.3 From 829b6c1ef488856c6a46a2f705f5068062d5f34c Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 11 Mar 2010 14:04:30 -0800 Subject: timer stats: Fix del_timer_sync() and try_to_del_timer_sync() These functions forgot to run timer_stats_timer_clear_start_info(). It's unobvious what effect this has and whether it matters much - we won't be printing it out anyway if the timer's detached. Untested, just an Ingo trollpatch. [ Nevertheless correct - tglx ] Signed-off-by: Andrew Morton Cc: Ingo Molnar Cc: johnstul@us.ibm.com Signed-off-by: Thomas Gleixner --- kernel/timer.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/timer.c b/kernel/timer.c index c61a7949387f..fc965eae0e87 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -880,6 +880,7 @@ int try_to_del_timer_sync(struct timer_list *timer) if (base->running_timer == timer) goto out; + timer_stats_timer_clear_start_info(timer); ret = 0; if (timer_pending(timer)) { detach_timer(timer, 1); -- cgit v1.2.3 From 15365c108ea27598e265f8c13e7051d99ca5b0b9 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 11 Mar 2010 14:04:31 -0800 Subject: posix-cpu-timers: Reset expire cache when no timer is running When a process deletes cpu timer or a timer expires we do not clear the expiration cache sig->cputimer_expires. As a result the fastpath_timer_check() which prevents us to loop over all threads in case no timer is active is not working and we run the slow path needlessly on every tick. Zero sig->cputimer_expires in stop_process_timers(). Signed-off-by: Stanislaw Gruszka Cc: Ingo Molnar Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Hidetoshi Seto Cc: Spencer Candland Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- kernel/posix-cpu-timers.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 438ff4523513..edec25a68e9e 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1060,9 +1060,9 @@ static void check_thread_timers(struct task_struct *tsk, } } -static void stop_process_timers(struct task_struct *tsk) +static void stop_process_timers(struct signal_struct *sig) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = &sig->cputimer; unsigned long flags; if (!cputimer->running) @@ -1071,6 +1071,10 @@ static void stop_process_timers(struct task_struct *tsk) spin_lock_irqsave(&cputimer->lock, flags); cputimer->running = 0; spin_unlock_irqrestore(&cputimer->lock, flags); + + sig->cputime_expires.prof_exp = cputime_zero; + sig->cputime_expires.virt_exp = cputime_zero; + sig->cputime_expires.sched_exp = 0; } static u32 onecputick; @@ -1131,7 +1135,7 @@ static void check_process_timers(struct task_struct *tsk, list_empty(&timers[CPUCLOCK_VIRT]) && cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) && list_empty(&timers[CPUCLOCK_SCHED])) { - stop_process_timers(tsk); + stop_process_timers(sig); return; } -- cgit v1.2.3 From baed7fc9b580bd3fb8252ff1d9b36eaf1f86b670 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:18 -0800 Subject: Add generic sys_ipc wrapper Add a generic implementation of the ipc demultiplexer syscall. Except for s390 and sparc64 all implementations of the sys_ipc are nearly identical. There are slight differences in the types of the parameters, where mips and powerpc as the only 64-bit architectures with sys_ipc use unsigned long for the "third" argument as it gets casted to a pointer later, while it traditionally is an "int" like most other paramters. frv goes even further and uses unsigned long for all parameters execept for "ptr" which is a pointer type everywhere. The change from int to unsigned long for "third" and back to "int" for the others on frv should be fine due to the in-register calling conventions for syscalls (we already had a similar issue with the generic sys_ptrace), but I'd prefer to have the arch maintainers looks over this in details. Except for that h8300, m68k and m68knommu lack an impplementation of the semtimedop sub call which this patch adds, and various architectures have gets used - at least on i386 it seems superflous as the compat code on x86-64 and ia64 doesn't even bother to implement it. [akpm@linux-foundation.org: add sys_ipc to sys_ni.c] Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Reviewed-by: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Acked-by: Jesper Nilsson Acked-by: Russell King Acked-by: David Howells Acked-by: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/unistd.h | 1 + arch/arm/kernel/sys_arm.c | 82 -------------------------- arch/arm/kernel/sys_oabi-compat.c | 3 - arch/cris/include/asm/unistd.h | 1 + arch/cris/kernel/sys_cris.c | 78 ------------------------- arch/frv/include/asm/unistd.h | 1 + arch/frv/kernel/sys_frv.c | 89 ---------------------------- arch/h8300/include/asm/unistd.h | 1 + arch/h8300/kernel/sys_h8300.c | 88 ---------------------------- arch/m32r/include/asm/unistd.h | 1 + arch/m32r/kernel/sys_m32r.c | 81 -------------------------- arch/m68k/include/asm/unistd.h | 1 + arch/m68k/kernel/sys_m68k.c | 81 -------------------------- arch/m68knommu/kernel/sys_m68k.c | 86 --------------------------- arch/mips/include/asm/unistd.h | 1 + arch/mips/kernel/syscall.c | 88 ---------------------------- arch/mn10300/include/asm/unistd.h | 1 + arch/mn10300/kernel/sys_mn10300.c | 88 ---------------------------- arch/powerpc/include/asm/syscalls.h | 2 - arch/powerpc/include/asm/unistd.h | 1 + arch/powerpc/kernel/syscalls.c | 94 ------------------------------ arch/s390/kernel/entry.h | 2 +- arch/s390/kernel/sys_s390.c | 2 +- arch/s390/kernel/syscalls.S | 2 +- arch/sh/include/asm/syscalls.h | 2 - arch/sh/include/asm/unistd_32.h | 1 + arch/sh/include/asm/unistd_64.h | 1 + arch/sh/kernel/sys_sh.c | 104 --------------------------------- arch/sparc/include/asm/unistd.h | 4 +- arch/sparc/kernel/sys_sparc_32.c | 113 ------------------------------------ arch/sparc/kernel/sys_sparc_64.c | 2 +- arch/sparc/kernel/systbls.h | 2 +- arch/sparc/kernel/systbls_64.S | 2 +- arch/um/sys-i386/syscalls.c | 86 --------------------------- arch/x86/include/asm/syscalls.h | 1 - arch/x86/include/asm/unistd_32.h | 1 + arch/x86/kernel/sys_i386_32.c | 85 --------------------------- include/linux/syscalls.h | 2 + ipc/Makefile | 2 +- ipc/syscall.c | 99 +++++++++++++++++++++++++++++++ kernel/sys_ni.c | 1 + 41 files changed, 124 insertions(+), 1259 deletions(-) create mode 100644 ipc/syscall.c (limited to 'kernel') diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index e6eeb2d29953..dd2bf53000fe 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -448,6 +448,7 @@ #if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT) #define __ARCH_WANT_SYS_TIME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_UTIME diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index a2e0e6f2ea7f..4350f75e578c 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -28,88 +28,6 @@ #include #include -#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT) -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, int third, - void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user(&tmp,(struct ipc_kludge __user *)ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, (struct msqid_ds __user *)ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *)ptr, second, &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong __user *)third); - } - case 1: /* Of course, we don't support iBCS2! */ - return -EINVAL; - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} -#endif - /* Fork a new task - this creates a new program thread. * This is called indirectly via a small wrapper */ diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index d59a0cd537f0..33ff678e32f2 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -346,9 +346,6 @@ asmlinkage long sys_oabi_semop(int semid, struct oabi_sembuf __user *tsops, return sys_oabi_semtimedop(semid, tsops, nsops, NULL); } -extern asmlinkage int sys_ipc(uint call, int first, int second, int third, - void __user *ptr, long fifth); - asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, void __user *ptr, long fifth) { diff --git a/arch/cris/include/asm/unistd.h b/arch/cris/include/asm/unistd.h index 8cffd22623fd..f6fad83b3a8c 100644 --- a/arch/cris/include/asm/unistd.h +++ b/arch/cris/include/asm/unistd.h @@ -352,6 +352,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/cris/kernel/sys_cris.c b/arch/cris/kernel/sys_cris.c index 22f9d6cd947f..7aa036ec78ff 100644 --- a/arch/cris/kernel/sys_cris.c +++ b/arch/cris/kernel/sys_cris.c @@ -33,81 +33,3 @@ sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, /* bug(?): 8Kb pages here */ return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. (same as arch/i386) - */ - -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: { - ulong raddr; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h index be6ef0f5cd42..b28da499e22a 100644 --- a/arch/frv/include/asm/unistd.h +++ b/arch/frv/include/asm/unistd.h @@ -354,6 +354,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM /* #define __ARCH_WANT_SYS_GETHOSTNAME */ +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE /* #define __ARCH_WANT_SYS_SGETMASK */ /* #define __ARCH_WANT_SYS_SIGNAL */ diff --git a/arch/frv/kernel/sys_frv.c b/arch/frv/kernel/sys_frv.c index 1d3d4c9e2521..9c4980825bbb 100644 --- a/arch/frv/kernel/sys_frv.c +++ b/arch/frv/kernel/sys_frv.c @@ -42,92 +42,3 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff >> (PAGE_SHIFT - 12)); } - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage long sys_ipc(unsigned long call, - unsigned long first, - unsigned long second, - unsigned long third, - void __user *ptr, - unsigned long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - /* The "(ulong *) third" is valid _only_ because of the kernel segment thing */ - return do_shmat (first, (char __user *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} diff --git a/arch/h8300/include/asm/unistd.h b/arch/h8300/include/asm/unistd.h index 54dab4726954..50f2c5a36591 100644 --- a/arch/h8300/include/asm/unistd.h +++ b/arch/h8300/include/asm/unistd.h @@ -336,6 +336,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c index 1f13fd6e5309..f9b3f44da69f 100644 --- a/arch/h8300/kernel/sys_h8300.c +++ b/arch/h8300/kernel/sys_h8300.c @@ -26,94 +26,6 @@ #include #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - return sys_semop (first, (struct sembuf *)ptr, second); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void **) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -EINVAL; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, (struct msgbuf *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user (&tmp, - (struct ipc_kludge *)ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds *) ptr); - default: - return -EINVAL; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char *) ptr, - second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong *) third); - } - } - case SHMDT: - return sys_shmdt ((char *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds *) ptr); - default: - return -EINVAL; - } - - return -EINVAL; -} - /* sys_cacheflush -- no support. */ asmlinkage int sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len) diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h index cf701c933249..76125777483c 100644 --- a/arch/m32r/include/asm/unistd.h +++ b/arch/m32r/include/asm/unistd.h @@ -339,6 +339,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_UTIME diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index d3c865c5a6ba..cf2e7279ce9b 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -76,87 +76,6 @@ asmlinkage int sys_tas(int __user *addr) return oldval; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds __user *) ptr); - case SHMAT: { - ulong raddr; - - if (!access_ok(VERIFY_WRITE, (ulong __user *) third, - sizeof(ulong))) - return -EFAULT; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - asmlinkage int sys_uname(struct old_utsname __user * name) { int err; diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index d801154310ea..60b15d0aa072 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -351,6 +351,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 7b309e7b6cef..77896692eb0a 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -46,87 +46,6 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - return sys_semop (first, ptr, second); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user *__user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -ENOSYS; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, ptr, second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user (&tmp, ptr, sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, ptr); - default: - return -ENOSYS; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - } - case SHMDT: - return sys_shmdt (ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, ptr); - default: - return -ENOSYS; - } - - return -EINVAL; -} - /* Convert virtual (user) address VADDR to physical address PADDR */ #define virt_to_phys_040(vaddr) \ ({ \ diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c index 3e371cc9fd91..d65e9c4c930c 100644 --- a/arch/m68knommu/kernel/sys_m68k.c +++ b/arch/m68knommu/kernel/sys_m68k.c @@ -27,92 +27,6 @@ #include #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc (uint call, int first, int second, - int third, void *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - return sys_semop (first, (struct sembuf *)ptr, second); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void **) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -EINVAL; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, (struct msgbuf *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - if (copy_from_user (&tmp, - (struct ipc_kludge *)ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds *) ptr); - default: - return -EINVAL; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - } - case SHMDT: - return sys_shmdt (ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, ptr); - default: - return -ENOSYS; - } - - return -EINVAL; -} - /* sys_cacheflush -- flush (part of) the processor cache. */ asmlinkage int sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len) diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 65c679ecbe6b..97fe472095f2 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -1004,6 +1004,7 @@ #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_UTIME diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3f7f466190b4..257bf0141775 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -406,94 +406,6 @@ _sys_sysmips(nabi_no_regargs struct pt_regs regs) return -EINVAL; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, int, second, - unsigned long, third, void __user *, ptr, long, fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, - (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user *__user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, - (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - unsigned long raddr; - ret = do_shmat(first, (char __user *) ptr, second, - &raddr); - if (ret) - return ret; - return put_user(raddr, (unsigned long __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat(first, (char __user *) ptr, second, - (unsigned long *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - /* * No implemented yet ... */ diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h index d13a56e99bad..9d056f515929 100644 --- a/arch/mn10300/include/asm/unistd.h +++ b/arch/mn10300/include/asm/unistd.h @@ -363,6 +363,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/mn10300/kernel/sys_mn10300.c b/arch/mn10300/kernel/sys_mn10300.c index bef69d6daf15..815f1355fad4 100644 --- a/arch/mn10300/kernel/sys_mn10300.c +++ b/arch/mn10300/kernel/sys_mn10300.c @@ -31,91 +31,3 @@ asmlinkage long old_mmap(unsigned long addr, unsigned long len, return -EINVAL; return sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT); } - -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage long sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, - second, - (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, - (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *) ptr, second, - &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat(first, (char __user *) ptr, second, - (ulong *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -EINVAL; - } -} diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index eb8eb400c664..23bb74e7f946 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -35,8 +35,6 @@ asmlinkage long sys_pipe2(int __user *fildes, int flags); asmlinkage long sys_rt_sigaction(int sig, const struct sigaction __user *act, struct sigaction __user *oact, size_t sigsetsize); -asmlinkage int sys_ipc(uint call, int first, unsigned long second, - long third, void __user *ptr, long fifth); asmlinkage long ppc64_personality(unsigned long personality); asmlinkage int ppc_rtas(struct rtas_args __user *uargs); asmlinkage time_t sys64_time(time_t __user * tloc); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index f6ca76176766..c13821fe8741 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -364,6 +364,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 3370e62e43d4..5251221e7a5a 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -42,100 +42,6 @@ #include #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -int sys_ipc(uint call, int first, unsigned long second, long third, - void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - ret = -ENOSYS; - switch (call) { - case SEMOP: - ret = sys_semtimedop(first, (struct sembuf __user *)ptr, - (unsigned)second, NULL); - break; - case SEMTIMEDOP: - ret = sys_semtimedop(first, (struct sembuf __user *)ptr, - (unsigned)second, - (const struct timespec __user *) fifth); - break; - case SEMGET: - ret = sys_semget (first, (int)second, third); - break; - case SEMCTL: { - union semun fourth; - - ret = -EINVAL; - if (!ptr) - break; - if ((ret = get_user(fourth.__pad, (void __user * __user *)ptr))) - break; - ret = sys_semctl(first, (int)second, third, fourth); - break; - } - case MSGSND: - ret = sys_msgsnd(first, (struct msgbuf __user *)ptr, - (size_t)second, third); - break; - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - - ret = -EINVAL; - if (!ptr) - break; - if ((ret = copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp)) ? -EFAULT : 0)) - break; - ret = sys_msgrcv(first, tmp.msgp, (size_t) second, - tmp.msgtyp, third); - break; - } - default: - ret = sys_msgrcv (first, (struct msgbuf __user *) ptr, - (size_t)second, fifth, third); - break; - } - break; - case MSGGET: - ret = sys_msgget((key_t)first, (int)second); - break; - case MSGCTL: - ret = sys_msgctl(first, (int)second, - (struct msqid_ds __user *)ptr); - break; - case SHMAT: { - ulong raddr; - ret = do_shmat(first, (char __user *)ptr, (int)second, &raddr); - if (ret) - break; - ret = put_user(raddr, (ulong __user *) third); - break; - } - case SHMDT: - ret = sys_shmdt((char __user *)ptr); - break; - case SHMGET: - ret = sys_shmget(first, (size_t)second, third); - break; - case SHMCTL: - ret = sys_shmctl(first, (int)second, - (struct shmid_ds __user *)ptr); - break; - } - - return ret; -} - static inline unsigned long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long off, int shift) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 5de54d2af0b2..15fd68b196c0 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -30,7 +30,7 @@ struct fadvise64_64_args; struct old_sigaction; long sys_mmap2(struct s390_mmap_arg_struct __user *arg); -long sys_ipc(uint call, int first, unsigned long second, +long sys_s390_ipc(uint call, int first, unsigned long second, unsigned long third, void __user *ptr); long sys_s390_newuname(struct new_utsname __user *name); long sys_s390_personality(unsigned long personality); diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index b2563509b5a9..b8b78092ab7c 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -64,7 +64,7 @@ out: * * This is really horribly ugly. */ -SYSCALL_DEFINE5(ipc, uint, call, int, first, unsigned long, second, +SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second, unsigned long, third, void __user *, ptr) { struct ipc_kludge tmp; diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 2a24766567af..990ac8b321c8 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -125,7 +125,7 @@ NI_SYSCALL /* vm86old for i386 */ SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4_wrapper) SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper) /* 115 */ SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper) -SYSCALL(sys_ipc,sys_ipc,sys32_ipc_wrapper) +SYSCALL(sys_s390_ipc,sys_s390_ipc,sys32_ipc_wrapper) SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ diff --git a/arch/sh/include/asm/syscalls.h b/arch/sh/include/asm/syscalls.h index c1e2b8deb837..c1ce2862f7be 100644 --- a/arch/sh/include/asm/syscalls.h +++ b/arch/sh/include/asm/syscalls.h @@ -11,8 +11,6 @@ asmlinkage int old_mmap(unsigned long addr, unsigned long len, asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth); asmlinkage int sys_uname(struct old_utsname __user *name); #ifdef CONFIG_SUPERH32 diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h index 365744b05269..a48f65e2e429 100644 --- a/arch/sh/include/asm/unistd_32.h +++ b/arch/sh/include/asm/unistd_32.h @@ -358,6 +358,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h index 25de158aac3a..7709b2b8f752 100644 --- a/arch/sh/include/asm/unistd_64.h +++ b/arch/sh/include/asm/unistd_64.h @@ -398,6 +398,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index 71399cde03b5..c18cfaa67fdd 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -53,110 +53,6 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMTIMEDOP) - switch (call) { - case SEMOP: - return sys_semtimedop(first, - (struct sembuf __user *)ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, - (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - default: - return -EINVAL; - } - - if (call <= MSGCTL) - switch (call) { - case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: - { - struct ipc_kludge tmp; - - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) - return -EFAULT; - - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, - (struct msqid_ds __user *) ptr); - default: - return -EINVAL; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char __user *) ptr, - second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat (first, (char __user *) ptr, - second, (ulong *) third); - } - case SHMDT: - return sys_shmdt ((char __user *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds __user *) ptr); - default: - return -EINVAL; - } - - return -EINVAL; -} - /* sys_cacheflush -- flush (part of) the processor cache. */ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, int op) { diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index cb4b9bfd0d87..d0b3b01ac9d4 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -432,7 +432,9 @@ #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_RT_SIGSUSPEND -#ifndef __32bit_syscall_numbers__ +#ifdef __32bit_syscall_numbers__ +#define __ARCH_WANT_SYS_IPC +#else #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND #endif diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 3a82e65d8db2..ee995b7dae7e 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -98,119 +98,6 @@ out: return error; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ - -asmlinkage int sys_ipc (uint call, int first, int second, int third, void __user *ptr, long fifth) -{ - int version, err; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - if (call <= SEMCTL) - switch (call) { - case SEMOP: - err = sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); - goto out; - case SEMTIMEDOP: - err = sys_semtimedop (first, (struct sembuf __user *)ptr, second, (const struct timespec __user *) fifth); - goto out; - case SEMGET: - err = sys_semget (first, second, third); - goto out; - case SEMCTL: { - union semun fourth; - err = -EINVAL; - if (!ptr) - goto out; - err = -EFAULT; - if (get_user(fourth.__pad, - (void __user * __user *)ptr)) - goto out; - err = sys_semctl (first, second, third, fourth); - goto out; - } - default: - err = -ENOSYS; - goto out; - } - if (call <= MSGCTL) - switch (call) { - case MSGSND: - err = sys_msgsnd (first, (struct msgbuf __user *) ptr, - second, third); - goto out; - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - err = -EINVAL; - if (!ptr) - goto out; - err = -EFAULT; - if (copy_from_user(&tmp, (struct ipc_kludge __user *) ptr, sizeof (tmp))) - goto out; - err = sys_msgrcv (first, tmp.msgp, second, tmp.msgtyp, third); - goto out; - } - case 1: default: - err = sys_msgrcv (first, - (struct msgbuf __user *) ptr, - second, fifth, third); - goto out; - } - case MSGGET: - err = sys_msgget ((key_t) first, second); - goto out; - case MSGCTL: - err = sys_msgctl (first, second, (struct msqid_ds __user *) ptr); - goto out; - default: - err = -ENOSYS; - goto out; - } - if (call <= SHMCTL) - switch (call) { - case SHMAT: - switch (version) { - case 0: default: { - ulong raddr; - err = do_shmat (first, (char __user *) ptr, second, &raddr); - if (err) - goto out; - err = -EFAULT; - if (put_user (raddr, (ulong __user *) third)) - goto out; - err = 0; - goto out; - } - case 1: /* iBCS2 emulator entry point */ - err = -EINVAL; - goto out; - } - case SHMDT: - err = sys_shmdt ((char __user *)ptr); - goto out; - case SHMGET: - err = sys_shmget (first, second, third); - goto out; - case SHMCTL: - err = sys_shmctl (first, second, (struct shmid_ds __user *) ptr); - goto out; - default: - err = -ENOSYS; - goto out; - } - else - err = -ENOSYS; -out: - return err; -} - int sparc_mmap_check(unsigned long addr, unsigned long len) { if (ARCH_SUN4C && diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index cb1bef6f14b7..45410e939628 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -426,7 +426,7 @@ out: * This is really horribly ugly. */ -SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, +SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second, unsigned long, third, void __user *, ptr, long, fifth) { long err; diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h index 68312fe8da74..2c331c37e748 100644 --- a/arch/sparc/kernel/systbls.h +++ b/arch/sparc/kernel/systbls.h @@ -10,7 +10,7 @@ struct new_utsname; extern asmlinkage unsigned long sys_getpagesize(void); extern asmlinkage long sparc_pipe(struct pt_regs *regs); -extern asmlinkage long sys_ipc(unsigned int call, int first, +extern asmlinkage long sys_sparc_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user *ptr, long fifth); diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 17614251fb6d..30ca2b1d3a17 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -136,7 +136,7 @@ sys_call_table: /*200*/ .word sys_ssetmask, sys_nis_syscall, sys_newlstat, sys_uselib, sys_nis_syscall .word sys_readahead, sys_socketcall, sys_syslog, sys_lookup_dcookie, sys_fadvise64 /*210*/ .word sys_fadvise64_64, sys_tgkill, sys_waitpid, sys_swapoff, sys_sysinfo - .word sys_ipc, sys_nis_syscall, sys_clone, sys_ioprio_get, sys_adjtimex + .word sys_sparc_ipc, sys_nis_syscall, sys_clone, sys_ioprio_get, sys_adjtimex /*220*/ .word sys_nis_syscall, sys_ni_syscall, sys_delete_module, sys_ni_syscall, sys_getpgid .word sys_bdflush, sys_sysfs, sys_nis_syscall, sys_setfsuid, sys_setfsgid /*230*/ .word sys_select, sys_nis_syscall, sys_splice, sys_stime, sys_statfs64 diff --git a/arch/um/sys-i386/syscalls.c b/arch/um/sys-i386/syscalls.c index d0aa8f125ee6..70ca357393b8 100644 --- a/arch/um/sys-i386/syscalls.c +++ b/arch/um/sys-i386/syscalls.c @@ -34,92 +34,6 @@ long sys_clone(unsigned long clone_flags, unsigned long newsp, return ret; } -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -long sys_ipc (uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *) ptr, - second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *) ptr, - second, - (const struct timespec __user *) fifth); - case SEMGET: - return sys_semget (first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl (first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd (first, (struct msgbuf *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge *) ptr, - sizeof (tmp))) - return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - panic("msgrcv with version != 0"); - return sys_msgrcv (first, - (struct msgbuf *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget ((key_t) first, second); - case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat (first, (char *) ptr, second, &raddr); - if (ret) - return ret; - return put_user (raddr, (ulong *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - return do_shmat (first, (char *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt ((char *)ptr); - case SHMGET: - return sys_shmget (first, second, third); - case SHMCTL: - return sys_shmctl (first, second, - (struct shmid_ds *) ptr); - default: - return -ENOSYS; - } -} - long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 86ab6a0623fd..50f6a569f0d1 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -54,7 +54,6 @@ unsigned long sys_sigreturn(struct pt_regs *); struct oldold_utsname; struct old_utsname; -asmlinkage int sys_ipc(uint, int, int, int, void __user *, long); asmlinkage int sys_uname(struct old_utsname __user *); asmlinkage int sys_olduname(struct oldold_utsname __user *); diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index daa65d9aae95..45e64a17b86e 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -354,6 +354,7 @@ #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM #define __ARCH_WANT_SYS_GETHOSTNAME +#define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_SGETMASK #define __ARCH_WANT_SYS_SIGNAL diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index 7955e90c8341..8b5c348fdcf2 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -24,91 +24,6 @@ #include -/* - * sys_ipc() is the de-multiplexer for the SysV IPC calls.. - * - * This is really horribly ugly. - */ -asmlinkage int sys_ipc(uint call, int first, int second, - int third, void __user *ptr, long fifth) -{ - int version, ret; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL); - case SEMTIMEDOP: - return sys_semtimedop(first, (struct sembuf __user *)ptr, second, - (const struct timespec __user *)fifth); - - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: { - union semun fourth; - if (!ptr) - return -EINVAL; - if (get_user(fourth.__pad, (void __user * __user *) ptr)) - return -EFAULT; - return sys_semctl(first, second, third, fourth); - } - - case MSGSND: - return sys_msgsnd(first, (struct msgbuf __user *) ptr, - second, third); - case MSGRCV: - switch (version) { - case 0: { - struct ipc_kludge tmp; - if (!ptr) - return -EINVAL; - - if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof(tmp))) - return -EFAULT; - return sys_msgrcv(first, tmp.msgp, second, - tmp.msgtyp, third); - } - default: - return sys_msgrcv(first, - (struct msgbuf __user *) ptr, - second, fifth, third); - } - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return sys_msgctl(first, second, (struct msqid_ds __user *) ptr); - - case SHMAT: - switch (version) { - default: { - ulong raddr; - ret = do_shmat(first, (char __user *) ptr, second, &raddr); - if (ret) - return ret; - return put_user(raddr, (ulong __user *) third); - } - case 1: /* iBCS2 emulator entry point */ - if (!segment_eq(get_fs(), get_ds())) - return -EINVAL; - /* The "(ulong *) third" is valid _only_ because of the kernel segment thing */ - return do_shmat(first, (char __user *) ptr, second, (ulong *) third); - } - case SHMDT: - return sys_shmdt((char __user *)ptr); - case SHMGET: - return sys_shmget(first, second, third); - case SHMCTL: - return sys_shmctl(first, second, - (struct shmid_ds __user *) ptr); - default: - return -ENOSYS; - } -} - /* * Old cruft */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b60907e3b0d5..fbb61ae70e06 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -684,6 +684,8 @@ asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); asmlinkage long sys_shmget(key_t key, size_t size, int flag); asmlinkage long sys_shmdt(char __user *shmaddr); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); +asmlinkage long sys_ipc(unsigned int call, int first, int second, + unsigned long third, void __user *ptr, long fifth); asmlinkage long sys_mq_open(const char __user *name, int oflag, mode_t mode, struct mq_attr __user *attr); asmlinkage long sys_mq_unlink(const char __user *name); diff --git a/ipc/Makefile b/ipc/Makefile index 4e1955ea815d..9075e172e52c 100644 --- a/ipc/Makefile +++ b/ipc/Makefile @@ -3,7 +3,7 @@ # obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o -obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o +obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o syscall.o obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o obj_mq-$(CONFIG_COMPAT) += compat_mq.o obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y) diff --git a/ipc/syscall.c b/ipc/syscall.c new file mode 100644 index 000000000000..355a3da9ec73 --- /dev/null +++ b/ipc/syscall.c @@ -0,0 +1,99 @@ +/* + * sys_ipc() is the old de-multiplexer for the SysV IPC calls. + * + * This is really horribly ugly, and new architectures should just wire up + * the individual syscalls instead. + */ +#include + +#ifdef __ARCH_WANT_SYS_IPC +#include +#include +#include +#include +#include + +SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, int, second, + unsigned long, third, void __user *, ptr, long, fifth) +{ + int version, ret; + + version = call >> 16; /* hack for backward compatibility */ + call &= 0xffff; + + switch (call) { + case SEMOP: + return sys_semtimedop(first, (struct sembuf __user *)ptr, + second, NULL); + case SEMTIMEDOP: + return sys_semtimedop(first, (struct sembuf __user *)ptr, + second, + (const struct timespec __user *)fifth); + + case SEMGET: + return sys_semget(first, second, third); + case SEMCTL: { + union semun fourth; + if (!ptr) + return -EINVAL; + if (get_user(fourth.__pad, (void __user * __user *) ptr)) + return -EFAULT; + return sys_semctl(first, second, third, fourth); + } + + case MSGSND: + return sys_msgsnd(first, (struct msgbuf __user *) ptr, + second, third); + case MSGRCV: + switch (version) { + case 0: { + struct ipc_kludge tmp; + if (!ptr) + return -EINVAL; + + if (copy_from_user(&tmp, + (struct ipc_kludge __user *) ptr, + sizeof(tmp))) + return -EFAULT; + return sys_msgrcv(first, tmp.msgp, second, + tmp.msgtyp, third); + } + default: + return sys_msgrcv(first, + (struct msgbuf __user *) ptr, + second, fifth, third); + } + case MSGGET: + return sys_msgget((key_t) first, second); + case MSGCTL: + return sys_msgctl(first, second, (struct msqid_ds __user *)ptr); + + case SHMAT: + switch (version) { + default: { + unsigned long raddr; + ret = do_shmat(first, (char __user *)ptr, + second, &raddr); + if (ret) + return ret; + return put_user(raddr, (unsigned long __user *) third); + } + case 1: + /* + * This was the entry point for kernel-originating calls + * from iBCS2 in 2.2 days. + */ + return -EINVAL; + } + case SHMDT: + return sys_shmdt((char __user *)ptr); + case SHMGET: + return sys_shmget(first, second, third); + case SHMCTL: + return sys_shmctl(first, second, + (struct shmid_ds __user *) ptr); + default: + return -ENOSYS; + } +} +#endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 695384f12a7d..70f2ea758ffe 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -126,6 +126,7 @@ cond_syscall(sys_setreuid16); cond_syscall(sys_setuid16); cond_syscall(sys_vm86old); cond_syscall(sys_vm86); +cond_syscall(sys_ipc); cond_syscall(compat_sys_ipc); cond_syscall(compat_sys_sysctl); cond_syscall(sys_flock); -- cgit v1.2.3 From e28cbf22933d0c0ccaf3c4c27a1a263b41f73859 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:19 -0800 Subject: improve sys_newuname() for compat architectures On an architecture that supports 32-bit compat we need to override the reported machine in uname with the 32-bit value. Instead of doing this separately in every architecture introduce a COMPAT_UTS_MACHINE define in and apply it directly in sys_newuname(). Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/compat.h | 3 ++- arch/mips/include/asm/compat.h | 3 ++- arch/mips/kernel/linux32.c | 16 ---------------- arch/mips/kernel/scall64-n32.S | 2 +- arch/mips/kernel/scall64-o32.S | 2 +- arch/parisc/include/asm/compat.h | 3 ++- arch/parisc/kernel/sys_parisc.c | 15 --------------- arch/parisc/kernel/syscall_table.S | 2 +- arch/powerpc/include/asm/compat.h | 3 ++- arch/powerpc/include/asm/syscalls.h | 2 -- arch/powerpc/include/asm/systbl.h | 2 +- arch/powerpc/kernel/syscalls.c | 13 ------------- arch/s390/include/asm/compat.h | 3 ++- arch/s390/kernel/compat_wrapper.S | 2 +- arch/s390/kernel/entry.h | 2 -- arch/s390/kernel/sys_s390.c | 11 ----------- arch/s390/kernel/syscalls.S | 2 +- arch/sparc/include/asm/compat.h | 3 ++- arch/sparc/kernel/sys_sparc_64.c | 11 ----------- arch/sparc/kernel/systbls.h | 3 --- arch/sparc/kernel/systbls_64.S | 4 ++-- arch/um/sys-x86_64/syscall_table.c | 5 ----- arch/um/sys-x86_64/syscalls.c | 14 -------------- arch/x86/include/asm/compat.h | 3 ++- arch/x86/include/asm/syscalls.h | 3 --- arch/x86/include/asm/unistd_64.h | 2 +- arch/x86/kernel/sys_x86_64.c | 12 ------------ kernel/sys.c | 13 +++++++++++++ 28 files changed, 36 insertions(+), 123 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h index dfcf75b8426d..f90edc85b509 100644 --- a/arch/ia64/include/asm/compat.h +++ b/arch/ia64/include/asm/compat.h @@ -5,7 +5,8 @@ */ #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "i686\0\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index f58aed354bfd..613f6912dfc1 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -8,7 +8,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "mips\0\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index bde79ef602e6..a39d0597a375 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -249,22 +249,6 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz, } #endif -SYSCALL_DEFINE1(32_newuname, struct new_utsname __user *, name) -{ - int ret = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof *name)) - ret = -EFAULT; - up_read(&uts_sem); - - if (current->personality == PER_LINUX32 && !ret) - if (copy_to_user(name->machine, "mips\0\0\0", 8)) - ret = -EFAULT; - - return ret; -} - SYSCALL_DEFINE1(32_personality, unsigned long, personality) { int ret; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 66b5a48676dd..44337ba03717 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -181,7 +181,7 @@ EXPORT(sysn32_call_table) PTR sys_exit PTR compat_sys_wait4 PTR sys_kill /* 6060 */ - PTR sys_32_newuname + PTR sys_newuname PTR sys_semget PTR sys_semop PTR sys_n32_semctl diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 515f9eab2b28..813689ef2384 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -325,7 +325,7 @@ sys_call_table: PTR sys32_sigreturn PTR sys32_clone /* 4120 */ PTR sys_setdomainname - PTR sys_32_newuname + PTR sys_newuname PTR sys_ni_syscall /* sys_modify_ldt */ PTR compat_sys_adjtimex PTR sys_mprotect /* 4125 */ diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 7f32611a7a5e..02b77baa5da6 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -7,7 +7,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "parisc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 9147391afb03..c9b932260f47 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -234,18 +234,3 @@ long parisc_personality(unsigned long personality) return err; } - -long parisc_newuname(struct new_utsname __user *name) -{ - int err = sys_newuname(name); - -#ifdef CONFIG_COMPAT - if (!err && personality(current->personality) == PER_LINUX32) { - if (__put_user(0, name->machine + 6) || - __put_user(0, name->machine + 7)) - err = -EFAULT; - } -#endif - - return err; -} diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index de5f6dab48b7..3d52c978738f 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -127,7 +127,7 @@ ENTRY_SAME(socketpair) ENTRY_SAME(setpgid) ENTRY_SAME(send) - ENTRY_OURS(newuname) + ENTRY_SAME(newuname) ENTRY_SAME(umask) /* 60 */ ENTRY_SAME(chroot) ENTRY_COMP(ustat) diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 4774c2f92232..396d21a80058 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -7,7 +7,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "ppc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 23bb74e7f946..4084e567d28e 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -7,7 +7,6 @@ #include #include -struct new_utsname; struct pt_regs; struct rtas_args; struct sigaction; @@ -38,7 +37,6 @@ asmlinkage long sys_rt_sigaction(int sig, asmlinkage long ppc64_personality(unsigned long personality); asmlinkage int ppc_rtas(struct rtas_args __user *uargs); asmlinkage time_t sys64_time(time_t __user * tloc); -asmlinkage long ppc_newuname(struct new_utsname __user * name); asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 07d2d19ab5e9..a5ee345b6a5c 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -125,7 +125,7 @@ SYSCALL_SPU(fsync) SYS32ONLY(sigreturn) PPC_SYS(clone) COMPAT_SYS_SPU(setdomainname) -PPC_SYS_SPU(newuname) +SYSCALL_SPU(newuname) SYSCALL(ni_syscall) COMPAT_SYS_SPU(adjtimex) SYSCALL_SPU(mprotect) diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 5251221e7a5a..69d3c5d50a54 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -132,19 +132,6 @@ static inline int override_machine(char __user *mach) return 0; } -long ppc_newuname(struct new_utsname __user * name) -{ - int err = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof(*name))) - err = -EFAULT; - up_read(&uts_sem); - if (!err) - err = override_machine(name->machine); - return err; -} - int sys_uname(struct old_utsname __user *name) { int err = 0; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 01a08020bc0e..104f2007f097 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -35,7 +35,8 @@ extern long psw32_user_bits; -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "s390\0\0\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 30de2d0e52bb..672ce52341b4 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -547,7 +547,7 @@ sys32_setdomainname_wrapper: .globl sys32_newuname_wrapper sys32_newuname_wrapper: llgtr %r2,%r2 # struct new_utsname * - jg sys_s390_newuname # branch to system call + jg sys_newuname # branch to system call .globl compat_sys_adjtimex_wrapper compat_sys_adjtimex_wrapper: diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 15fd68b196c0..eb15c12ec158 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -24,7 +24,6 @@ int __cpuinit start_secondary(void *cpuvoid); void __init startup_init(void); void die(const char * str, struct pt_regs * regs, long err); -struct new_utsname; struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; @@ -32,7 +31,6 @@ struct old_sigaction; long sys_mmap2(struct s390_mmap_arg_struct __user *arg); long sys_s390_ipc(uint call, int first, unsigned long second, unsigned long third, void __user *ptr); -long sys_s390_newuname(struct new_utsname __user *name); long sys_s390_personality(unsigned long personality); long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low, size_t len, int advice); diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index b8b78092ab7c..7b6b0f81a283 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -131,17 +131,6 @@ SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second, } #ifdef CONFIG_64BIT -SYSCALL_DEFINE1(s390_newuname, struct new_utsname __user *, name) -{ - int ret = sys_newuname(name); - - if (personality(current->personality) == PER_LINUX32 && !ret) { - ret = copy_to_user(name->machine, "s390\0\0\0\0", 8); - if (ret) ret = -EFAULT; - } - return ret; -} - SYSCALL_DEFINE1(s390_personality, unsigned long, personality) { int ret; diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 990ac8b321c8..201ce6bed34e 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -130,7 +130,7 @@ SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper) SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn) SYSCALL(sys_clone,sys_clone,sys_clone_wrapper) /* 120 */ SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper) -SYSCALL(sys_newuname,sys_s390_newuname,sys32_newuname_wrapper) +SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper) NI_SYSCALL /* modify_ldt for i386 */ SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper) SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper) /* 125 */ diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 0e706257918f..5016f76ea98a 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -5,7 +5,8 @@ */ #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "sparc\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 45410e939628..3d435c42e6db 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -510,17 +510,6 @@ out: return err; } -SYSCALL_DEFINE1(sparc64_newuname, struct new_utsname __user *, name) -{ - int ret = sys_newuname(name); - - if (current->personality == PER_LINUX32 && !ret) { - ret = (copy_to_user(name->machine, "sparc\0\0", 8) - ? -EFAULT : 0); - } - return ret; -} - SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality) { int ret; diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h index 2c331c37e748..118759cd7342 100644 --- a/arch/sparc/kernel/systbls.h +++ b/arch/sparc/kernel/systbls.h @@ -6,15 +6,12 @@ #include #include -struct new_utsname; - extern asmlinkage unsigned long sys_getpagesize(void); extern asmlinkage long sparc_pipe(struct pt_regs *regs); extern asmlinkage long sys_sparc_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user *ptr, long fifth); -extern asmlinkage long sparc64_newuname(struct new_utsname __user *name); extern asmlinkage long sparc64_personality(unsigned long personality); extern asmlinkage long sys64_munmap(unsigned long addr, size_t len); extern asmlinkage unsigned long sys64_mremap(unsigned long addr, diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 30ca2b1d3a17..9db058dd039e 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -55,7 +55,7 @@ sys_call_table32: /*170*/ .word sys32_lsetxattr, sys32_fsetxattr, sys_getxattr, sys_lgetxattr, compat_sys_getdents .word sys_setsid, sys_fchdir, sys32_fgetxattr, sys_listxattr, sys_llistxattr /*180*/ .word sys32_flistxattr, sys_removexattr, sys_lremovexattr, compat_sys_sigpending, sys_ni_syscall - .word sys32_setpgid, sys32_fremovexattr, sys32_tkill, sys32_exit_group, sys_sparc64_newuname + .word sys32_setpgid, sys32_fremovexattr, sys32_tkill, sys32_exit_group, sys_newuname /*190*/ .word sys32_init_module, sys_sparc64_personality, sys_remap_file_pages, sys32_epoll_create, sys32_epoll_ctl .word sys32_epoll_wait, sys32_ioprio_set, sys_getppid, sys32_sigaction, sys_sgetmask /*200*/ .word sys32_ssetmask, sys_sigsuspend, compat_sys_newlstat, sys_uselib, compat_sys_old_readdir @@ -130,7 +130,7 @@ sys_call_table: /*170*/ .word sys_lsetxattr, sys_fsetxattr, sys_getxattr, sys_lgetxattr, sys_getdents .word sys_setsid, sys_fchdir, sys_fgetxattr, sys_listxattr, sys_llistxattr /*180*/ .word sys_flistxattr, sys_removexattr, sys_lremovexattr, sys_nis_syscall, sys_ni_syscall - .word sys_setpgid, sys_fremovexattr, sys_tkill, sys_exit_group, sys_sparc64_newuname + .word sys_setpgid, sys_fremovexattr, sys_tkill, sys_exit_group, sys_newuname /*190*/ .word sys_init_module, sys_sparc64_personality, sys_remap_file_pages, sys_epoll_create, sys_epoll_ctl .word sys_epoll_wait, sys_ioprio_set, sys_getppid, sys_nis_syscall, sys_sgetmask /*200*/ .word sys_ssetmask, sys_nis_syscall, sys_newlstat, sys_uselib, sys_nis_syscall diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/um/sys-x86_64/syscall_table.c index dd21d69715e6..47d469e7e7ce 100644 --- a/arch/um/sys-x86_64/syscall_table.c +++ b/arch/um/sys-x86_64/syscall_table.c @@ -26,11 +26,6 @@ /* On UML we call it this way ("old" means it's not mmap2) */ #define sys_mmap old_mmap -/* - * On x86-64 sys_uname is actually sys_newuname plus a compatibility trick. - * See arch/x86_64/kernel/sys_x86_64.c - */ -#define sys_uname sys_uname64 #define stub_clone sys_clone #define stub_fork sys_fork diff --git a/arch/um/sys-x86_64/syscalls.c b/arch/um/sys-x86_64/syscalls.c index f1199fd34d38..f3d82bb6e15a 100644 --- a/arch/um/sys-x86_64/syscalls.c +++ b/arch/um/sys-x86_64/syscalls.c @@ -12,20 +12,6 @@ #include "asm/uaccess.h" #include "os.h" -asmlinkage long sys_uname64(struct new_utsname __user * name) -{ - int err; - - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); - up_read(&uts_sem); - - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - - return err ? -EFAULT : 0; -} - long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) { unsigned long *ptr = addr, tmp; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 9a9c7bdc923d..306160e58b48 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -8,7 +8,8 @@ #include #include -#define COMPAT_USER_HZ 100 +#define COMPAT_USER_HZ 100 +#define COMPAT_UTS_MACHINE "i686\0\0" typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 50f6a569f0d1..47cd606c3537 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -68,11 +68,8 @@ int sys_vm86(unsigned long, unsigned long, struct pt_regs *); long sys_arch_prctl(int, unsigned long); /* kernel/sys_x86_64.c */ -struct new_utsname; - asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -asmlinkage long sys_uname(struct new_utsname __user *); #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALLS_H */ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 4843f7ba754a..83e2d6dc5038 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -146,7 +146,7 @@ __SYSCALL(__NR_wait4, sys_wait4) #define __NR_kill 62 __SYSCALL(__NR_kill, sys_kill) #define __NR_uname 63 -__SYSCALL(__NR_uname, sys_uname) +__SYSCALL(__NR_uname, sys_newuname) #define __NR_semget 64 __SYSCALL(__NR_semget, sys_semget) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 8aa2057efd12..ff14a5044ce6 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -209,15 +209,3 @@ bottomup: return addr; } - - -SYSCALL_DEFINE1(uname, struct new_utsname __user *, name) -{ - int err; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - return err ? -EFAULT : 0; -} diff --git a/kernel/sys.c b/kernel/sys.c index 9814e43fb23b..e483eb5530e4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -1114,6 +1115,15 @@ out: DECLARE_RWSEM(uts_sem); +#ifdef COMPAT_UTS_MACHINE +#define override_architecture(name) \ + (current->personality == PER_LINUX32 && \ + copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ + sizeof(COMPAT_UTS_MACHINE))) +#else +#define override_architecture(name) 0 +#endif + SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { int errno = 0; @@ -1122,6 +1132,9 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) if (copy_to_user(name, utsname(), sizeof *name)) errno = -EFAULT; up_read(&uts_sem); + + if (!errno && override_architecture(name)) + errno = -EFAULT; return errno; } -- cgit v1.2.3 From 5cacdb4add1b1e50fe75edc50ebbb7bddd9cf5e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:21 -0800 Subject: Add generic sys_olduname() Add generic implementations of the old and really old uname system calls. Note that sh only implements sys_olduname but not sys_oldolduname, but I'm not going to bother with another ifdef for that special case. m32r implemented an old uname but never wired it up, so kill it, too. Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m32r/kernel/sys_m32r.c | 11 -------- arch/mips/include/asm/unistd.h | 1 + arch/mips/kernel/syscall.c | 42 ----------------------------- arch/powerpc/include/asm/unistd.h | 1 + arch/powerpc/kernel/syscalls.c | 57 --------------------------------------- arch/sh/include/asm/syscalls.h | 3 --- arch/sh/include/asm/unistd_32.h | 1 + arch/sh/include/asm/unistd_64.h | 1 + arch/sh/kernel/sys_sh.c | 11 -------- arch/um/kernel/syscall.c | 45 ------------------------------- arch/x86/ia32/ia32entry.S | 4 +-- arch/x86/ia32/sys_ia32.c | 52 ----------------------------------- arch/x86/include/asm/sys_ia32.h | 5 ---- arch/x86/include/asm/syscalls.h | 7 ----- arch/x86/include/asm/unistd_32.h | 1 + arch/x86/include/asm/unistd_64.h | 1 + arch/x86/kernel/sys_i386_32.c | 49 --------------------------------- include/linux/syscalls.h | 4 +++ kernel/sys.c | 54 +++++++++++++++++++++++++++++++++++++ 19 files changed, 66 insertions(+), 284 deletions(-) (limited to 'kernel') diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index cf2e7279ce9b..0a00f467edfa 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -76,17 +76,6 @@ asmlinkage int sys_tas(int __user *addr) return oldval; } -asmlinkage int sys_uname(struct old_utsname __user * name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); - up_read(&uts_sem); - return err?-EFAULT:0; -} - asmlinkage int sys_cacheflush(void *addr, int bytes, int cache) { /* This should flush more selectively ... */ diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 97fe472095f2..1b5a6648eb86 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -1014,6 +1014,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 257bf0141775..e96b1c30c7aa 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -215,48 +215,6 @@ out: return error; } -/* - * Compacrapability ... - */ -SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) -{ - if (name && !copy_to_user(name, utsname(), sizeof (*name))) - return 0; - return -EFAULT; -} - -/* - * Compacrapability ... - */ -SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) -{ - int error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error -= __put_user(0, name->sysname + __OLD_UTS_LEN); - error -= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error -= __put_user(0, name->nodename + __OLD_UTS_LEN); - error -= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error -= __put_user(0, name->release + __OLD_UTS_LEN); - error -= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error -= __put_user(0, name->version + __OLD_UTS_LEN); - error -= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error = __put_user(0, name->machine + __OLD_UTS_LEN); - error = error ? -EFAULT : 0; - - return error; -} - SYSCALL_DEFINE1(set_thread_area, unsigned long, addr) { struct thread_info *ti = task_thread_info(current); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index c13821fe8741..f0a10266e7f7 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -377,6 +377,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 69d3c5d50a54..f2496f2faecc 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -116,63 +116,6 @@ long ppc64_personality(unsigned long personality) } #endif -#ifdef CONFIG_PPC64 -#define OVERRIDE_MACHINE (personality(current->personality) == PER_LINUX32) -#else -#define OVERRIDE_MACHINE 0 -#endif - -static inline int override_machine(char __user *mach) -{ - if (OVERRIDE_MACHINE) { - /* change ppc64 to ppc */ - if (__put_user(0, mach+3) || __put_user(0, mach+4)) - return -EFAULT; - } - return 0; -} - -int sys_uname(struct old_utsname __user *name) -{ - int err = 0; - - down_read(&uts_sem); - if (copy_to_user(name, utsname(), sizeof(*name))) - err = -EFAULT; - up_read(&uts_sem); - if (!err) - err = override_machine(name->machine); - return err; -} - -int sys_olduname(struct oldold_utsname __user *name) -{ - int error; - - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= override_machine(name->machine); - up_read(&uts_sem); - - return error? -EFAULT: 0; -} - long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, u32 len_high, u32 len_low) { diff --git a/arch/sh/include/asm/syscalls.h b/arch/sh/include/asm/syscalls.h index c1ce2862f7be..507725af2e54 100644 --- a/arch/sh/include/asm/syscalls.h +++ b/arch/sh/include/asm/syscalls.h @@ -3,15 +3,12 @@ #ifdef __KERNEL__ -struct old_utsname; - asmlinkage int old_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, int fd, unsigned long off); asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); -asmlinkage int sys_uname(struct old_utsname __user *name); #ifdef CONFIG_SUPERH32 # include "syscalls_32.h" diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h index a48f65e2e429..0e7f0fc8f086 100644 --- a/arch/sh/include/asm/unistd_32.h +++ b/arch/sh/include/asm/unistd_32.h @@ -371,6 +371,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h index 7709b2b8f752..0580c33a1e04 100644 --- a/arch/sh/include/asm/unistd_64.h +++ b/arch/sh/include/asm/unistd_64.h @@ -411,6 +411,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index c18cfaa67fdd..81f58371613d 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -93,14 +93,3 @@ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, int op) up_read(¤t->mm->mmap_sem); return 0; } - -asmlinkage int sys_uname(struct old_utsname __user *name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - return err?-EFAULT:0; -} diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index cccab850c27e..4393173923f5 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -51,51 +51,6 @@ long old_mmap(unsigned long addr, unsigned long len, return err; } -long sys_uname(struct old_utsname __user * name) -{ - long err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); - up_read(&uts_sem); - return err?-EFAULT:0; -} - -long sys_olduname(struct oldold_utsname __user * name) -{ - long error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= __put_user(0, name->machine + __OLD_UTS_LEN); - - up_read(&uts_sem); - - error = error ? -EFAULT : 0; - - return error; -} - int kernel_execve(const char *filename, char *const argv[], char *const envp[]) { mm_segment_t fs; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 34f821802c23..59b4556a5b92 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -563,7 +563,7 @@ ia32_sys_call_table: .quad quiet_ni_syscall /* old mpx syscall holder */ .quad sys_setpgid .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys32_olduname + .quad sys_olduname .quad sys_umask /* 60 */ .quad sys_chroot .quad compat_sys_ustat @@ -613,7 +613,7 @@ ia32_sys_call_table: .quad compat_sys_newstat .quad compat_sys_newlstat .quad compat_sys_newfstat - .quad sys32_uname + .quad sys_uname .quad stub32_iopl /* 110 */ .quad sys_vhangup .quad quiet_ni_syscall /* old "idle" system call */ diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 56c99f46e289..74c35431b7d8 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -448,58 +448,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd, return ret; } -asmlinkage long sys32_olduname(struct oldold_utsname __user *name) -{ - char *arch = "x86_64"; - int err; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - err = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - err |= __put_user(0, name->sysname+__OLD_UTS_LEN); - err |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - err |= __put_user(0, name->nodename+__OLD_UTS_LEN); - err |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - err |= __put_user(0, name->release+__OLD_UTS_LEN); - err |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - err |= __put_user(0, name->version+__OLD_UTS_LEN); - - if (personality(current->personality) == PER_LINUX32) - arch = "i686"; - - err |= __copy_to_user(&name->machine, arch, strlen(arch) + 1); - - up_read(&uts_sem); - - err = err ? -EFAULT : 0; - - return err; -} - -long sys32_uname(struct old_utsname __user *name) -{ - int err; - - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - - return err ? -EFAULT : 0; -} - asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 7d348d803669..3ad421784ae7 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -54,11 +54,6 @@ asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); asmlinkage long sys32_personality(unsigned long); asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32); -struct oldold_utsname; -struct old_utsname; -asmlinkage long sys32_olduname(struct oldold_utsname __user *); -long sys32_uname(struct old_utsname __user *); - asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 47cd606c3537..5c044b43e9a7 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -50,13 +50,6 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); unsigned long sys_sigreturn(struct pt_regs *); -/* kernel/sys_i386_32.c */ -struct oldold_utsname; -struct old_utsname; - -asmlinkage int sys_uname(struct old_utsname __user *); -asmlinkage int sys_olduname(struct oldold_utsname __user *); - /* kernel/vm86_32.c */ int sys_vm86old(struct vm86_struct __user *, struct pt_regs *); int sys_vm86(unsigned long, unsigned long, struct pt_regs *); diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 45e64a17b86e..beb9b5f8f8a4 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -367,6 +367,7 @@ #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLD_MMAP #define __ARCH_WANT_SYS_OLD_SELECT #define __ARCH_WANT_SYS_OLDUMOUNT diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 83e2d6dc5038..ff4307b0e81e 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -680,6 +680,7 @@ __SYSCALL(__NR_recvmmsg, sys_recvmmsg) #define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT +#define __ARCH_WANT_SYS_OLD_UNAME #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index 8b5c348fdcf2..196552bb412c 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -24,55 +24,6 @@ #include -/* - * Old cruft - */ -asmlinkage int sys_uname(struct old_utsname __user *name) -{ - int err; - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - return err? -EFAULT:0; -} - -asmlinkage int sys_olduname(struct oldold_utsname __user *name) -{ - int error; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - error = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - error |= __put_user(0, name->sysname + __OLD_UTS_LEN); - error |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - error |= __put_user(0, name->nodename + __OLD_UTS_LEN); - error |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - error |= __put_user(0, name->release + __OLD_UTS_LEN); - error |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - error |= __put_user(0, name->version + __OLD_UTS_LEN); - error |= __copy_to_user(&name->machine, &utsname()->machine, - __OLD_UTS_LEN); - error |= __put_user(0, name->machine + __OLD_UTS_LEN); - - up_read(&uts_sem); - - error = error ? -EFAULT : 0; - - return error; -} - - /* * Do a system call from kernel instead of calling sys_execve so we * end up with proper pt_regs. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fbb61ae70e06..44f2ad0e8825 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -31,6 +31,8 @@ struct msqid_ds; struct new_utsname; struct nfsctl_arg; struct __old_kernel_stat; +struct oldold_utsname; +struct old_utsname; struct pollfd; struct rlimit; struct rusage; @@ -655,6 +657,8 @@ asmlinkage long sys_gethostname(char __user *name, int len); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); asmlinkage long sys_newuname(struct new_utsname __user *name); +asmlinkage long sys_uname(struct old_utsname __user *); +asmlinkage long sys_olduname(struct oldold_utsname __user *); asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); diff --git a/kernel/sys.c b/kernel/sys.c index e483eb5530e4..8298878f4f71 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1138,6 +1138,60 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) return errno; } +#ifdef __ARCH_WANT_SYS_OLD_UNAME +/* + * Old cruft + */ +SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) +{ + int error = 0; + + if (!name) + return -EFAULT; + + down_read(&uts_sem); + if (copy_to_user(name, utsname(), sizeof(*name))) + error = -EFAULT; + up_read(&uts_sem); + + if (!error && override_architecture(name)) + error = -EFAULT; + return error; +} + +SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) +{ + int error; + + if (!name) + return -EFAULT; + if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) + return -EFAULT; + + down_read(&uts_sem); + error = __copy_to_user(&name->sysname, &utsname()->sysname, + __OLD_UTS_LEN); + error |= __put_user(0, name->sysname + __OLD_UTS_LEN); + error |= __copy_to_user(&name->nodename, &utsname()->nodename, + __OLD_UTS_LEN); + error |= __put_user(0, name->nodename + __OLD_UTS_LEN); + error |= __copy_to_user(&name->release, &utsname()->release, + __OLD_UTS_LEN); + error |= __put_user(0, name->release + __OLD_UTS_LEN); + error |= __copy_to_user(&name->version, &utsname()->version, + __OLD_UTS_LEN); + error |= __put_user(0, name->version + __OLD_UTS_LEN); + error |= __copy_to_user(&name->machine, &utsname()->machine, + __OLD_UTS_LEN); + error |= __put_user(0, name->machine + __OLD_UTS_LEN); + up_read(&uts_sem); + + if (!error && override_architecture(name)) + error = -EFAULT; + return error ? -EFAULT : 0; +} +#endif + SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; -- cgit v1.2.3 From 2468c7234b366eeb799ee0648cb58f9cba394a54 Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Wed, 10 Mar 2010 15:22:03 -0800 Subject: cgroup: introduce cancel_attach() Add cancel_attach() operation to struct cgroup_subsys. cancel_attach() can be used when can_attach() operation prepares something for the subsys, but we should rollback what can_attach() operation has prepared if attach task fails after we've succeeded in can_attach(). Signed-off-by: Daisuke Nishimura Acked-by: Li Zefan Reviewed-by: Paul Menage Cc: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 13 ++++++++++++- include/linux/cgroup.h | 2 ++ kernel/cgroup.c | 40 ++++++++++++++++++++++++++++++++------- 3 files changed, 47 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 0b33bfe7dde9..d45082653e3d 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -536,10 +536,21 @@ returns an error, this will abort the attach operation. If a NULL task is passed, then a successful result indicates that *any* unspecified task can be moved into the cgroup. Note that this isn't called on a fork. If this method returns 0 (success) then this should -remain valid while the caller holds cgroup_mutex. If threadgroup is +remain valid while the caller holds cgroup_mutex and it is ensured that either +attach() or cancel_attach() will be called in future. If threadgroup is true, then a successful result indicates that all threads in the given thread's threadgroup can be moved together. +void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *task, bool threadgroup) +(cgroup_mutex held by caller) + +Called when a task attach operation has failed after can_attach() has succeeded. +A subsystem whose can_attach() has some side-effects should provide this +function, so that the subsytem can implement a rollback. If not, not necessary. +This will be called only about subsystems whose can_attach() operation have +succeeded. + void attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task, bool threadgroup) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c9bbcb2a75ae..d08cfe7e12e5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -428,6 +428,8 @@ struct cgroup_subsys { void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *tsk, bool threadgroup); + void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup); void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *tsk, bool threadgroup); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4fd90e129772..be45d2f6008a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1554,7 +1554,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { int retval = 0; - struct cgroup_subsys *ss; + struct cgroup_subsys *ss, *failed_ss = NULL; struct cgroup *oldcgrp; struct css_set *cg; struct css_set *newcg; @@ -1568,8 +1568,16 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->can_attach) { retval = ss->can_attach(ss, cgrp, tsk, false); - if (retval) - return retval; + if (retval) { + /* + * Remember on which subsystem the can_attach() + * failed, so that we only call cancel_attach() + * against the subsystems whose can_attach() + * succeeded. (See below) + */ + failed_ss = ss; + goto out; + } } } @@ -1583,14 +1591,17 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) */ newcg = find_css_set(cg, cgrp); put_css_set(cg); - if (!newcg) - return -ENOMEM; + if (!newcg) { + retval = -ENOMEM; + goto out; + } task_lock(tsk); if (tsk->flags & PF_EXITING) { task_unlock(tsk); put_css_set(newcg); - return -ESRCH; + retval = -ESRCH; + goto out; } rcu_assign_pointer(tsk->cgroups, newcg); task_unlock(tsk); @@ -1616,7 +1627,22 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) * is no longer empty. */ cgroup_wakeup_rmdir_waiter(cgrp); - return 0; +out: + if (retval) { + for_each_subsys(root, ss) { + if (ss == failed_ss) + /* + * This subsystem was the one that failed the + * can_attach() check earlier, so we don't need + * to call cancel_attach() against it or any + * remaining subsystems. + */ + break; + if (ss->cancel_attach) + ss->cancel_attach(ss, cgrp, tsk, false); + } + } + return retval; } /* -- cgit v1.2.3 From d7b9fff711d5e8db8c844161c684017e556c38a0 Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Wed, 10 Mar 2010 15:22:05 -0800 Subject: cgroup: introduce coalesce css_get() and css_put() Current css_get() and css_put() increment/decrement css->refcnt one by one. This patch add a new function __css_get(), which takes "count" as a arg and increment the css->refcnt by "count". And this patch also add a new arg("count") to __css_put() and change the function to decrement the css->refcnt by "count". These coalesce version of __css_get()/__css_put() will be used to improve performance of memcg's moving charge feature later, where instead of calling css_get()/css_put() repeatedly, these new functions will be used. No change is needed for current users of css_get()/css_put(). Signed-off-by: Daisuke Nishimura Acked-by: Paul Menage Cc: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 12 +++++++++--- kernel/cgroup.c | 5 +++-- 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d08cfe7e12e5..14160b5b693f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -76,6 +76,12 @@ enum { CSS_REMOVED, /* This CSS is dead */ }; +/* Caller must verify that the css is not for root cgroup */ +static inline void __css_get(struct cgroup_subsys_state *css, int count) +{ + atomic_add(count, &css->refcnt); +} + /* * Call css_get() to hold a reference on the css; it can be used * for a reference obtained via: @@ -87,7 +93,7 @@ static inline void css_get(struct cgroup_subsys_state *css) { /* We don't need to reference count the root state */ if (!test_bit(CSS_ROOT, &css->flags)) - atomic_inc(&css->refcnt); + __css_get(css, 1); } static inline bool css_is_removed(struct cgroup_subsys_state *css) @@ -118,11 +124,11 @@ static inline bool css_tryget(struct cgroup_subsys_state *css) * css_get() or css_tryget() */ -extern void __css_put(struct cgroup_subsys_state *css); +extern void __css_put(struct cgroup_subsys_state *css, int count); static inline void css_put(struct cgroup_subsys_state *css) { if (!test_bit(CSS_ROOT, &css->flags)) - __css_put(css); + __css_put(css, 1); } /* bits in struct cgroup flags field */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index be45d2f6008a..cace83ddbcdc 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3746,12 +3746,13 @@ static void check_for_release(struct cgroup *cgrp) } } -void __css_put(struct cgroup_subsys_state *css) +/* Caller must verify that the css is not for root cgroup */ +void __css_put(struct cgroup_subsys_state *css, int count) { struct cgroup *cgrp = css->cgroup; int val; rcu_read_lock(); - val = atomic_dec_return(&css->refcnt); + val = atomic_sub_return(count, &css->refcnt); if (val == 1) { if (notify_on_release(cgrp)) { set_bit(CGRP_RELEASABLE, &cgrp->flags); -- cgit v1.2.3 From aae8aab40367036931608fdaf9e2dc568b516f19 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 10 Mar 2010 15:22:07 -0800 Subject: cgroups: revamp subsys array This patch series provides the ability for cgroup subsystems to be compiled as modules both within and outside the kernel tree. This is mainly useful for classifiers and subsystems that hook into components that are already modules. cls_cgroup and blkio-cgroup serve as the example use cases for this feature. It provides an interface cgroup_load_subsys() and cgroup_unload_subsys() which modular subsystems can use to register and depart during runtime. The net_cls classifier subsystem serves as the example for a subsystem which can be converted into a module using these changes. Patch #1 sets up the subsys[] array so its contents can be dynamic as modules appear and (eventually) disappear. Iterations over the array are modified to handle when subsystems are absent, and the dynamic section of the array is protected by cgroup_mutex. Patch #2 implements an interface for modules to load subsystems, called cgroup_load_subsys, similar to cgroup_init_subsys, and adds a module pointer in struct cgroup_subsys. Patch #3 adds a mechanism for unloading modular subsystems, which includes a more advanced rework of the rudimentary reference counting introduced in patch 2. Patch #4 modifies the net_cls subsystem, which already had some module declarations, to be configurable as a module, which also serves as a simple proof-of-concept. Part of implementing patches 2 and 4 involved updating css pointers in each css_set when the module appears or leaves. In doing this, it was discovered that css_sets always remain linked to the dummy cgroup, regardless of whether or not any subsystems are actually bound to it (i.e., not mounted on an actual hierarchy). The subsystem loading and unloading code therefore should keep in mind the special cases where the added subsystem is the only one in the dummy cgroup (and therefore all css_sets need to be linked back into it) and where the removed subsys was the only one in the dummy cgroup (and therefore all css_sets should be unlinked from it) - however, as all css_sets always stay attached to the dummy cgroup anyway, these cases are ignored. Any fix that addresses this issue should also make sure these cases are addressed in the subsystem loading and unloading code. This patch: Make subsys[] able to be dynamically populated to support modular subsystems This patch reworks the way the subsys[] array is used so that subsystems can register themselves after boot time, and enables the internals of cgroups to be able to handle when subsystems are not present or may appear/disappear. Signed-off-by: Ben Blum Acked-by: Li Zefan Cc: Paul Menage Cc: "David S. Miller" Cc: KAMEZAWA Hiroyuki Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 10 ++++-- kernel/cgroup.c | 96 +++++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 88 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 14160b5b693f..28319a9fe569 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -40,13 +40,19 @@ extern int cgroupstats_build(struct cgroupstats *stats, extern const struct file_operations proc_cgroup_operations; -/* Define the enumeration of all cgroup subsystems */ +/* Define the enumeration of all builtin cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, enum cgroup_subsys_id { #include - CGROUP_SUBSYS_COUNT + CGROUP_BUILTIN_SUBSYS_COUNT }; #undef SUBSYS +/* + * This define indicates the maximum number of subsystems that can be loaded + * at once. We limit to this many since cgroupfs_root has subsys_bits to keep + * track of all of them. + */ +#define CGROUP_SUBSYS_COUNT (BITS_PER_BYTE*sizeof(unsigned long)) /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index cace83ddbcdc..c92fb9549358 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -57,10 +57,14 @@ static DEFINE_MUTEX(cgroup_mutex); -/* Generate an array of cgroup subsystem pointers */ +/* + * Generate an array of cgroup subsystem pointers. At boot time, this is + * populated up to CGROUP_BUILTIN_SUBSYS_COUNT, and modular subsystems are + * registered after that. The mutable section of this array is protected by + * cgroup_mutex. + */ #define SUBSYS(_x) &_x ## _subsys, - -static struct cgroup_subsys *subsys[] = { +static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = { #include }; @@ -448,8 +452,11 @@ static struct css_set *find_existing_css_set( struct hlist_node *node; struct css_set *cg; - /* Built the set of subsystem state objects that we want to - * see in the new css_set */ + /* + * Build the set of subsystem state objects that we want to see in the + * new css_set. while subsystems can change globally, the entries here + * won't change, so no need for locking. + */ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { if (root->subsys_bits & (1UL << i)) { /* Subsystem is in this hierarchy. So we want @@ -884,7 +891,9 @@ void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css) css_put(css); } - +/* + * Call with cgroup_mutex held. + */ static int rebind_subsystems(struct cgroupfs_root *root, unsigned long final_bits) { @@ -892,6 +901,8 @@ static int rebind_subsystems(struct cgroupfs_root *root, struct cgroup *cgrp = &root->top_cgroup; int i; + BUG_ON(!mutex_is_locked(&cgroup_mutex)); + removed_bits = root->actual_subsys_bits & ~final_bits; added_bits = final_bits & ~root->actual_subsys_bits; /* Check that any added subsystems are currently free */ @@ -900,6 +911,12 @@ static int rebind_subsystems(struct cgroupfs_root *root, struct cgroup_subsys *ss = subsys[i]; if (!(bit & added_bits)) continue; + /* + * Nobody should tell us to do a subsys that doesn't exist: + * parse_cgroupfs_options should catch that case and refcounts + * ensure that subsystems won't disappear once selected. + */ + BUG_ON(ss == NULL); if (ss->root != &rootnode) { /* Subsystem isn't free */ return -EBUSY; @@ -919,6 +936,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, unsigned long bit = 1UL << i; if (bit & added_bits) { /* We're binding this subsystem to this hierarchy */ + BUG_ON(ss == NULL); BUG_ON(cgrp->subsys[i]); BUG_ON(!dummytop->subsys[i]); BUG_ON(dummytop->subsys[i]->cgroup != dummytop); @@ -932,6 +950,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, mutex_unlock(&ss->hierarchy_mutex); } else if (bit & removed_bits) { /* We're removing this subsystem */ + BUG_ON(ss == NULL); BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]); BUG_ON(cgrp->subsys[i]->cgroup != cgrp); mutex_lock(&ss->hierarchy_mutex); @@ -944,6 +963,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, mutex_unlock(&ss->hierarchy_mutex); } else if (bit & final_bits) { /* Subsystem state should already exist */ + BUG_ON(ss == NULL); BUG_ON(!cgrp->subsys[i]); } else { /* Subsystem state shouldn't exist */ @@ -986,14 +1006,18 @@ struct cgroup_sb_opts { }; -/* Convert a hierarchy specifier into a bitmask of subsystems and - * flags. */ +/* + * Convert a hierarchy specifier into a bitmask of subsystems and flags. Call + * with cgroup_mutex held to protect the subsys[] array. + */ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data ?: "all"; unsigned long mask = (unsigned long)-1; + BUG_ON(!mutex_is_locked(&cgroup_mutex)); + #ifdef CONFIG_CPUSETS mask = ~(1UL << cpuset_subsys_id); #endif @@ -1009,6 +1033,8 @@ static int parse_cgroupfs_options(char *data, opts->subsys_bits = 0; for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; if (!ss->disabled) opts->subsys_bits |= 1ul << i; } @@ -1053,6 +1079,8 @@ static int parse_cgroupfs_options(char *data, int i; for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { ss = subsys[i]; + if (ss == NULL) + continue; if (!strcmp(token, ss->name)) { if (!ss->disabled) set_bit(i, &opts->subsys_bits); @@ -1306,7 +1334,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type, struct cgroupfs_root *new_root; /* First find the desired set of subsystems */ + mutex_lock(&cgroup_mutex); ret = parse_cgroupfs_options(data, &opts); + mutex_unlock(&cgroup_mutex); if (ret) goto out_err; @@ -2918,8 +2948,14 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root) /* We need to take each hierarchy_mutex in a consistent order */ int i; + /* + * No worry about a race with rebind_subsystems that might mess up the + * locking order, since both parties are under cgroup_mutex. + */ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; if (ss->root == root) mutex_lock(&ss->hierarchy_mutex); } @@ -2931,6 +2967,8 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; if (ss->root == root) mutex_unlock(&ss->hierarchy_mutex); } @@ -3054,11 +3092,16 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) * synchronization other than RCU, and the subsystem linked * list isn't RCU-safe */ int i; + /* + * We won't need to lock the subsys array, because the subsystems + * we're concerned about aren't going anywhere since our cgroup root + * has a reference on them. + */ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; struct cgroup_subsys_state *css; - /* Skip subsystems not in this hierarchy */ - if (ss->root != cgrp->root) + /* Skip subsystems not present or not in this hierarchy */ + if (ss == NULL || ss->root != cgrp->root) continue; css = cgrp->subsys[ss->subsys_id]; /* When called from check_for_release() it's possible @@ -3279,7 +3322,8 @@ int __init cgroup_init_early(void) for (i = 0; i < CSS_SET_TABLE_SIZE; i++) INIT_HLIST_HEAD(&css_set_table[i]); - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + /* at bootup time, we don't worry about modular subsystems */ + for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; BUG_ON(!ss->name); @@ -3314,7 +3358,8 @@ int __init cgroup_init(void) if (err) return err; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + /* at bootup time, we don't worry about modular subsystems */ + for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (!ss->early_init) cgroup_init_subsys(ss); @@ -3423,9 +3468,16 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v) int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); + /* + * ideally we don't want subsystems moving around while we do this. + * cgroup_mutex is also necessary to guarantee an atomic snapshot of + * subsys/hierarchy state. + */ mutex_lock(&cgroup_mutex); for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; seq_printf(m, "%s\t%d\t%d\t%d\n", ss->name, ss->root->hierarchy_id, ss->root->number_of_cgroups, !ss->disabled); @@ -3483,7 +3535,12 @@ void cgroup_fork_callbacks(struct task_struct *child) { if (need_forkexit_callback) { int i; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + /* + * forkexit callbacks are only supported for builtin + * subsystems, and the builtin section of the subsys array is + * immutable, so we don't need to lock the subsys array here. + */ + for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->fork) ss->fork(ss, child); @@ -3552,7 +3609,11 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) struct css_set *cg; if (run_callbacks && need_forkexit_callback) { - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + /* + * modular subsystems can't use callbacks, so no need to lock + * the subsys array + */ + for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->exit) ss->exit(ss, tsk); @@ -3844,8 +3905,11 @@ static int __init cgroup_disable(char *str) while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; - - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + /* + * cgroup_disable, being at boot time, can't know about module + * subsystems, so we don't worry about them. + */ + for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (!strcmp(token, ss->name)) { -- cgit v1.2.3 From e6a1105ba08b265023dd71a4174fb4a29ebc7083 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 10 Mar 2010 15:22:09 -0800 Subject: cgroups: subsystem module loading interface Add interface between cgroups subsystem management and module loading This patch implements rudimentary module-loading support for cgroups - namely, a cgroup_load_subsys (similar to cgroup_init_subsys) for use as a module initcall, and a struct module pointer in struct cgroup_subsys. Several functions that might be wanted by modules have had EXPORT_SYMBOL added to them, but it's unclear exactly which functions want it and which won't. Signed-off-by: Ben Blum Acked-by: Li Zefan Cc: Paul Menage Cc: "David S. Miller" Cc: KAMEZAWA Hiroyuki Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 4 + include/linux/cgroup.h | 4 + kernel/cgroup.c | 150 ++++++++++++++++++++++++++++++++++++-- 3 files changed, 153 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index d45082653e3d..ae8a037a761e 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -488,6 +488,10 @@ Each subsystem should: - add an entry in linux/cgroup_subsys.h - define a cgroup_subsys object called _subsys +If a subsystem can be compiled as a module, it should also have in its +module initcall a call to cgroup_load_subsys(&its_subsys_struct). It +should also set its_subsys.module = THIS_MODULE in its .c file. + Each subsystem may export the following methods. The only mandatory methods are create/destroy. Any others that are null are presumed to be successful no-ops. diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 28319a9fe569..402ce477c47e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -37,6 +37,7 @@ extern void cgroup_post_fork(struct task_struct *p); extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); +extern int cgroup_load_subsys(struct cgroup_subsys *ss); extern const struct file_operations proc_cgroup_operations; @@ -486,6 +487,9 @@ struct cgroup_subsys { /* used when use_id == true */ struct idr idr; spinlock_t id_lock; + + /* should be defined only by modular subsystems */ + struct module *module; }; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c92fb9549358..2cae38e64c59 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include @@ -254,7 +255,8 @@ struct cg_cgroup_link { static struct css_set init_css_set; static struct cg_cgroup_link init_css_set_link; -static int cgroup_subsys_init_idr(struct cgroup_subsys *ss); +static int cgroup_init_idr(struct cgroup_subsys *ss, + struct cgroup_subsys_state *css); /* css_set_lock protects the list of css_set objects, and the * chain of tasks off each css_set. Nests outside task->alloc_lock @@ -2125,6 +2127,7 @@ int cgroup_add_file(struct cgroup *cgrp, error = PTR_ERR(dentry); return error; } +EXPORT_SYMBOL_GPL(cgroup_add_file); int cgroup_add_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, @@ -2139,6 +2142,7 @@ int cgroup_add_files(struct cgroup *cgrp, } return 0; } +EXPORT_SYMBOL_GPL(cgroup_add_files); /** * cgroup_task_count - count the number of tasks in a cgroup. @@ -3292,7 +3296,144 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) mutex_init(&ss->hierarchy_mutex); lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; + + /* this function shouldn't be used with modular subsystems, since they + * need to register a subsys_id, among other things */ + BUG_ON(ss->module); +} + +/** + * cgroup_load_subsys: load and register a modular subsystem at runtime + * @ss: the subsystem to load + * + * This function should be called in a modular subsystem's initcall. If the + * subsytem is built as a module, it will be assigned a new subsys_id and set + * up for use. If the subsystem is built-in anyway, work is delegated to the + * simpler cgroup_init_subsys. + */ +int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) +{ + int i; + struct cgroup_subsys_state *css; + + /* check name and function validity */ + if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN || + ss->create == NULL || ss->destroy == NULL) + return -EINVAL; + + /* + * we don't support callbacks in modular subsystems. this check is + * before the ss->module check for consistency; a subsystem that could + * be a module should still have no callbacks even if the user isn't + * compiling it as one. + */ + if (ss->fork || ss->exit) + return -EINVAL; + + /* + * an optionally modular subsystem is built-in: we want to do nothing, + * since cgroup_init_subsys will have already taken care of it. + */ + if (ss->module == NULL) { + /* a few sanity checks */ + BUG_ON(ss->subsys_id >= CGROUP_BUILTIN_SUBSYS_COUNT); + BUG_ON(subsys[ss->subsys_id] != ss); + return 0; + } + + /* + * need to register a subsys id before anything else - for example, + * init_cgroup_css needs it. + */ + mutex_lock(&cgroup_mutex); + /* find the first empty slot in the array */ + for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) { + if (subsys[i] == NULL) + break; + } + if (i == CGROUP_SUBSYS_COUNT) { + /* maximum number of subsystems already registered! */ + mutex_unlock(&cgroup_mutex); + return -EBUSY; + } + /* assign ourselves the subsys_id */ + ss->subsys_id = i; + subsys[i] = ss; + + /* + * no ss->create seems to need anything important in the ss struct, so + * this can happen first (i.e. before the rootnode attachment). + */ + css = ss->create(ss, dummytop); + if (IS_ERR(css)) { + /* failure case - need to deassign the subsys[] slot. */ + subsys[i] = NULL; + mutex_unlock(&cgroup_mutex); + return PTR_ERR(css); + } + + list_add(&ss->sibling, &rootnode.subsys_list); + ss->root = &rootnode; + + /* our new subsystem will be attached to the dummy hierarchy. */ + init_cgroup_css(css, ss, dummytop); + /* init_idr must be after init_cgroup_css because it sets css->id. */ + if (ss->use_id) { + int ret = cgroup_init_idr(ss, css); + if (ret) { + dummytop->subsys[ss->subsys_id] = NULL; + ss->destroy(ss, dummytop); + subsys[i] = NULL; + mutex_unlock(&cgroup_mutex); + return ret; + } + } + + /* + * Now we need to entangle the css into the existing css_sets. unlike + * in cgroup_init_subsys, there are now multiple css_sets, so each one + * will need a new pointer to it; done by iterating the css_set_table. + * furthermore, modifying the existing css_sets will corrupt the hash + * table state, so each changed css_set will need its hash recomputed. + * this is all done under the css_set_lock. + */ + write_lock(&css_set_lock); + for (i = 0; i < CSS_SET_TABLE_SIZE; i++) { + struct css_set *cg; + struct hlist_node *node, *tmp; + struct hlist_head *bucket = &css_set_table[i], *new_bucket; + + hlist_for_each_entry_safe(cg, node, tmp, bucket, hlist) { + /* skip entries that we already rehashed */ + if (cg->subsys[ss->subsys_id]) + continue; + /* remove existing entry */ + hlist_del(&cg->hlist); + /* set new value */ + cg->subsys[ss->subsys_id] = css; + /* recompute hash and restore entry */ + new_bucket = css_set_hash(cg->subsys); + hlist_add_head(&cg->hlist, new_bucket); + } + } + write_unlock(&css_set_lock); + + mutex_init(&ss->hierarchy_mutex); + lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); + ss->active = 1; + + /* + * pin the subsystem's module so it doesn't go away. this shouldn't + * fail, since the module's initcall calls us. + * TODO: with module unloading, move this elsewhere + */ + BUG_ON(!try_module_get(ss->module)); + + /* success! */ + mutex_unlock(&cgroup_mutex); + return 0; } +EXPORT_SYMBOL_GPL(cgroup_load_subsys); /** * cgroup_init_early - cgroup initialization at system boot @@ -3364,7 +3505,7 @@ int __init cgroup_init(void) if (!ss->early_init) cgroup_init_subsys(ss); if (ss->use_id) - cgroup_subsys_init_idr(ss); + cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]); } /* Add init_css_set to the hash table */ @@ -4033,15 +4174,14 @@ err_out: } -static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss) +static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss, + struct cgroup_subsys_state *rootcss) { struct css_id *newid; - struct cgroup_subsys_state *rootcss; spin_lock_init(&ss->id_lock); idr_init(&ss->idr); - rootcss = init_css_set.subsys[ss->subsys_id]; newid = get_new_cssid(ss, 0); if (IS_ERR(newid)) return PTR_ERR(newid); -- cgit v1.2.3 From cf5d5941fda647fe3d2f2d00cf9e0245236a5f08 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 10 Mar 2010 15:22:09 -0800 Subject: cgroups: subsystem module unloading Provides support for unloading modular subsystems. This patch adds a new function cgroup_unload_subsys which is to be used for removing a loaded subsystem during module deletion. Reference counting of the subsystems' modules is moved from once (at load time) to once per attached hierarchy (in parse_cgroupfs_options and rebind_subsystems) (i.e., 0 or 1). Signed-off-by: Ben Blum Acked-by: Li Zefan Cc: Paul Menage Cc: "David S. Miller" Cc: KAMEZAWA Hiroyuki Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 5 +- include/linux/cgroup.h | 4 +- kernel/cgroup.c | 167 ++++++++++++++++++++++++++++++++------ 3 files changed, 148 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index ae8a037a761e..764007b63921 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -489,8 +489,9 @@ Each subsystem should: - define a cgroup_subsys object called _subsys If a subsystem can be compiled as a module, it should also have in its -module initcall a call to cgroup_load_subsys(&its_subsys_struct). It -should also set its_subsys.module = THIS_MODULE in its .c file. +module initcall a call to cgroup_load_subsys(), and in its exitcall a +call to cgroup_unload_subsys(). It should also set its_subsys.module = +THIS_MODULE in its .c file. Each subsystem may export the following methods. The only mandatory methods are create/destroy. Any others that are null are presumed to diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 402ce477c47e..2a59d3101e5d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -38,6 +38,7 @@ extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); extern int cgroup_load_subsys(struct cgroup_subsys *ss); +extern void cgroup_unload_subsys(struct cgroup_subsys *ss); extern const struct file_operations proc_cgroup_operations; @@ -271,7 +272,8 @@ struct css_set { /* * Set of subsystem states, one for each subsystem. This array * is immutable after creation apart from the init_css_set - * during subsystem registration (at boot time). + * during subsystem registration (at boot time) and modular subsystem + * loading/unloading. */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2cae38e64c59..aa889c96cc74 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -894,7 +894,9 @@ void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css) } /* - * Call with cgroup_mutex held. + * Call with cgroup_mutex held. Drops reference counts on modules, including + * any duplicate ones that parse_cgroupfs_options took. If this function + * returns an error, no reference counts are touched. */ static int rebind_subsystems(struct cgroupfs_root *root, unsigned long final_bits) @@ -950,6 +952,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, if (ss->bind) ss->bind(ss, cgrp); mutex_unlock(&ss->hierarchy_mutex); + /* refcount was already taken, and we're keeping it */ } else if (bit & removed_bits) { /* We're removing this subsystem */ BUG_ON(ss == NULL); @@ -963,10 +966,20 @@ static int rebind_subsystems(struct cgroupfs_root *root, subsys[i]->root = &rootnode; list_move(&ss->sibling, &rootnode.subsys_list); mutex_unlock(&ss->hierarchy_mutex); + /* subsystem is now free - drop reference on module */ + module_put(ss->module); } else if (bit & final_bits) { /* Subsystem state should already exist */ BUG_ON(ss == NULL); BUG_ON(!cgrp->subsys[i]); + /* + * a refcount was taken, but we already had one, so + * drop the extra reference. + */ + module_put(ss->module); +#ifdef CONFIG_MODULE_UNLOAD + BUG_ON(ss->module && !module_refcount(ss->module)); +#endif } else { /* Subsystem state shouldn't exist */ BUG_ON(cgrp->subsys[i]); @@ -1010,13 +1023,16 @@ struct cgroup_sb_opts { /* * Convert a hierarchy specifier into a bitmask of subsystems and flags. Call - * with cgroup_mutex held to protect the subsys[] array. + * with cgroup_mutex held to protect the subsys[] array. This function takes + * refcounts on subsystems to be used, unless it returns error, in which case + * no refcounts are taken. */ -static int parse_cgroupfs_options(char *data, - struct cgroup_sb_opts *opts) +static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data ?: "all"; unsigned long mask = (unsigned long)-1; + int i; + bool module_pin_failed = false; BUG_ON(!mutex_is_locked(&cgroup_mutex)); @@ -1031,7 +1047,6 @@ static int parse_cgroupfs_options(char *data, return -EINVAL; if (!strcmp(token, "all")) { /* Add all non-disabled subsystems */ - int i; opts->subsys_bits = 0; for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; @@ -1054,7 +1069,6 @@ static int parse_cgroupfs_options(char *data, if (!opts->release_agent) return -ENOMEM; } else if (!strncmp(token, "name=", 5)) { - int i; const char *name = token + 5; /* Can't specify an empty name */ if (!strlen(name)) @@ -1078,7 +1092,6 @@ static int parse_cgroupfs_options(char *data, return -ENOMEM; } else { struct cgroup_subsys *ss; - int i; for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { ss = subsys[i]; if (ss == NULL) @@ -1117,9 +1130,54 @@ static int parse_cgroupfs_options(char *data, if (!opts->subsys_bits && !opts->name) return -EINVAL; + /* + * Grab references on all the modules we'll need, so the subsystems + * don't dance around before rebind_subsystems attaches them. This may + * take duplicate reference counts on a subsystem that's already used, + * but rebind_subsystems handles this case. + */ + for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) { + unsigned long bit = 1UL << i; + + if (!(bit & opts->subsys_bits)) + continue; + if (!try_module_get(subsys[i]->module)) { + module_pin_failed = true; + break; + } + } + if (module_pin_failed) { + /* + * oops, one of the modules was going away. this means that we + * raced with a module_delete call, and to the user this is + * essentially a "subsystem doesn't exist" case. + */ + for (i--; i >= CGROUP_BUILTIN_SUBSYS_COUNT; i--) { + /* drop refcounts only on the ones we took */ + unsigned long bit = 1UL << i; + + if (!(bit & opts->subsys_bits)) + continue; + module_put(subsys[i]->module); + } + return -ENOENT; + } + return 0; } +static void drop_parsed_module_refcounts(unsigned long subsys_bits) +{ + int i; + for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) { + unsigned long bit = 1UL << i; + + if (!(bit & subsys_bits)) + continue; + module_put(subsys[i]->module); + } +} + static int cgroup_remount(struct super_block *sb, int *flags, char *data) { int ret = 0; @@ -1136,21 +1194,19 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) if (ret) goto out_unlock; - /* Don't allow flags to change at remount */ - if (opts.flags != root->flags) { - ret = -EINVAL; - goto out_unlock; - } - - /* Don't allow name to change at remount */ - if (opts.name && strcmp(opts.name, root->name)) { + /* Don't allow flags or name to change at remount */ + if (opts.flags != root->flags || + (opts.name && strcmp(opts.name, root->name))) { ret = -EINVAL; + drop_parsed_module_refcounts(opts.subsys_bits); goto out_unlock; } ret = rebind_subsystems(root, opts.subsys_bits); - if (ret) + if (ret) { + drop_parsed_module_refcounts(opts.subsys_bits); goto out_unlock; + } /* (re)populate subsystem files */ cgroup_populate_dir(cgrp); @@ -1349,7 +1405,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, new_root = cgroup_root_from_opts(&opts); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); - goto out_err; + goto drop_modules; } opts.new_root = new_root; @@ -1358,7 +1414,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, if (IS_ERR(sb)) { ret = PTR_ERR(sb); cgroup_drop_root(opts.new_root); - goto out_err; + goto drop_modules; } root = sb->s_fs_info; @@ -1414,6 +1470,11 @@ static int cgroup_get_sb(struct file_system_type *fs_type, free_cg_links(&tmp_cg_links); goto drop_new_super; } + /* + * There must be no failure case after here, since rebinding + * takes care of subsystems' refcounts, which are explicitly + * dropped in the failure exit path. + */ /* EBUSY should be the only error here */ BUG_ON(ret); @@ -1452,6 +1513,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type, * any) is not needed */ cgroup_drop_root(opts.new_root); + /* no subsys rebinding, so refcounts don't change */ + drop_parsed_module_refcounts(opts.subsys_bits); } simple_set_mnt(mnt, sb); @@ -1461,6 +1524,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type, drop_new_super: deactivate_locked_super(sb); + drop_modules: + drop_parsed_module_refcounts(opts.subsys_bits); out_err: kfree(opts.release_agent); kfree(opts.name); @@ -3422,19 +3487,71 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; - /* - * pin the subsystem's module so it doesn't go away. this shouldn't - * fail, since the module's initcall calls us. - * TODO: with module unloading, move this elsewhere - */ - BUG_ON(!try_module_get(ss->module)); - /* success! */ mutex_unlock(&cgroup_mutex); return 0; } EXPORT_SYMBOL_GPL(cgroup_load_subsys); +/** + * cgroup_unload_subsys: unload a modular subsystem + * @ss: the subsystem to unload + * + * This function should be called in a modular subsystem's exitcall. When this + * function is invoked, the refcount on the subsystem's module will be 0, so + * the subsystem will not be attached to any hierarchy. + */ +void cgroup_unload_subsys(struct cgroup_subsys *ss) +{ + struct cg_cgroup_link *link; + struct hlist_head *hhead; + + BUG_ON(ss->module == NULL); + + /* + * we shouldn't be called if the subsystem is in use, and the use of + * try_module_get in parse_cgroupfs_options should ensure that it + * doesn't start being used while we're killing it off. + */ + BUG_ON(ss->root != &rootnode); + + mutex_lock(&cgroup_mutex); + /* deassign the subsys_id */ + BUG_ON(ss->subsys_id < CGROUP_BUILTIN_SUBSYS_COUNT); + subsys[ss->subsys_id] = NULL; + + /* remove subsystem from rootnode's list of subsystems */ + list_del(&ss->sibling); + + /* + * disentangle the css from all css_sets attached to the dummytop. as + * in loading, we need to pay our respects to the hashtable gods. + */ + write_lock(&css_set_lock); + list_for_each_entry(link, &dummytop->css_sets, cgrp_link_list) { + struct css_set *cg = link->cg; + + hlist_del(&cg->hlist); + BUG_ON(!cg->subsys[ss->subsys_id]); + cg->subsys[ss->subsys_id] = NULL; + hhead = css_set_hash(cg->subsys); + hlist_add_head(&cg->hlist, hhead); + } + write_unlock(&css_set_lock); + + /* + * remove subsystem's css from the dummytop and free it - need to free + * before marking as null because ss->destroy needs the cgrp->subsys + * pointer to find their state. note that this also takes care of + * freeing the css_id. + */ + ss->destroy(ss, dummytop); + dummytop->subsys[ss->subsys_id] = NULL; + + mutex_unlock(&cgroup_mutex); +} +EXPORT_SYMBOL_GPL(cgroup_unload_subsys); + /** * cgroup_init_early - cgroup initialization at system boot * -- cgit v1.2.3 From 67523c48aa74d5637848edeccf285af1c60bf14a Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 10 Mar 2010 15:22:11 -0800 Subject: cgroups: blkio subsystem as module Modify the Block I/O cgroup subsystem to be able to be built as a module. As the CFQ disk scheduler optionally depends on blk-cgroup, config options in block/Kconfig, block/Kconfig.iosched, and block/blk-cgroup.h are enhanced to support the new module dependency. Signed-off-by: Ben Blum Cc: Li Zefan Cc: Paul Menage Cc: "David S. Miller" Cc: KAMEZAWA Hiroyuki Cc: Lai Jiangshan Cc: Vivek Goyal Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- block/Kconfig | 2 +- block/Kconfig.iosched | 2 +- block/blk-cgroup.c | 53 ++++++++++++++++++++++++++++++++++++----------- block/blk-cgroup.h | 10 +++++++-- include/linux/iocontext.h | 2 +- kernel/cgroup.c | 9 ++++++++ 6 files changed, 61 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/block/Kconfig b/block/Kconfig index e20fbde0875c..62a5921321cd 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -78,7 +78,7 @@ config BLK_DEV_INTEGRITY Protection. If in doubt, say N. config BLK_CGROUP - bool + tristate depends on CGROUPS default n ---help--- diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index b71abfb0d726..fc71cf071fb2 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -23,6 +23,7 @@ config IOSCHED_DEADLINE config IOSCHED_CFQ tristate "CFQ I/O scheduler" + select BLK_CGROUP if CFQ_GROUP_IOSCHED default y ---help--- The CFQ I/O scheduler tries to distribute bandwidth equally @@ -35,7 +36,6 @@ config IOSCHED_CFQ config CFQ_GROUP_IOSCHED bool "CFQ Group Scheduling support" depends on IOSCHED_CFQ && CGROUPS - select BLK_CGROUP default n ---help--- Enable group IO scheduling in CFQ. diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c85d74cae200..4b686ad08eaa 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -23,6 +23,31 @@ static LIST_HEAD(blkio_list); struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT }; EXPORT_SYMBOL_GPL(blkio_root_cgroup); +static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *, + struct cgroup *); +static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *, + struct task_struct *, bool); +static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *, + struct cgroup *, struct task_struct *, bool); +static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *); +static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *); + +struct cgroup_subsys blkio_subsys = { + .name = "blkio", + .create = blkiocg_create, + .can_attach = blkiocg_can_attach, + .attach = blkiocg_attach, + .destroy = blkiocg_destroy, + .populate = blkiocg_populate, +#ifdef CONFIG_BLK_CGROUP + /* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */ + .subsys_id = blkio_subsys_id, +#endif + .use_id = 1, + .module = THIS_MODULE, +}; +EXPORT_SYMBOL_GPL(blkio_subsys); + struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id), @@ -253,7 +278,8 @@ remove_entry: done: free_css_id(&blkio_subsys, &blkcg->css); rcu_read_unlock(); - kfree(blkcg); + if (blkcg != &blkio_root_cgroup) + kfree(blkcg); } static struct cgroup_subsys_state * @@ -319,17 +345,6 @@ static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup, task_unlock(tsk); } -struct cgroup_subsys blkio_subsys = { - .name = "blkio", - .create = blkiocg_create, - .can_attach = blkiocg_can_attach, - .attach = blkiocg_attach, - .destroy = blkiocg_destroy, - .populate = blkiocg_populate, - .subsys_id = blkio_subsys_id, - .use_id = 1, -}; - void blkio_policy_register(struct blkio_policy_type *blkiop) { spin_lock(&blkio_list_lock); @@ -345,3 +360,17 @@ void blkio_policy_unregister(struct blkio_policy_type *blkiop) spin_unlock(&blkio_list_lock); } EXPORT_SYMBOL_GPL(blkio_policy_unregister); + +static int __init init_cgroup_blkio(void) +{ + return cgroup_load_subsys(&blkio_subsys); +} + +static void __exit exit_cgroup_blkio(void) +{ + cgroup_unload_subsys(&blkio_subsys); +} + +module_init(init_cgroup_blkio); +module_exit(exit_cgroup_blkio); +MODULE_LICENSE("GPL"); diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 84bf745fa775..8ccc20464dae 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -15,7 +15,13 @@ #include -#ifdef CONFIG_BLK_CGROUP +#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) + +#ifndef CONFIG_BLK_CGROUP +/* When blk-cgroup is a module, its subsys_id isn't a compile-time constant */ +extern struct cgroup_subsys blkio_subsys; +#define blkio_subsys_id blkio_subsys.subsys_id +#endif struct blkio_cgroup { struct cgroup_subsys_state css; @@ -91,7 +97,7 @@ static inline void blkiocg_update_blkio_group_dequeue_stats( struct blkio_group *blkg, unsigned long dequeue) {} #endif -#ifdef CONFIG_BLK_CGROUP +#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) extern struct blkio_cgroup blkio_root_cgroup; extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup); extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 1195a806fe0c..a0bb301afac0 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -42,7 +42,7 @@ struct io_context { unsigned short ioprio; unsigned short ioprio_changed; -#ifdef CONFIG_BLK_CGROUP +#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) unsigned short cgroup_changed; #endif diff --git a/kernel/cgroup.c b/kernel/cgroup.c index aa889c96cc74..521591dbab2f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -705,6 +705,7 @@ void cgroup_lock(void) { mutex_lock(&cgroup_mutex); } +EXPORT_SYMBOL_GPL(cgroup_lock); /** * cgroup_unlock - release lock on cgroup changes @@ -715,6 +716,7 @@ void cgroup_unlock(void) { mutex_unlock(&cgroup_mutex); } +EXPORT_SYMBOL_GPL(cgroup_unlock); /* * A couple of forward declarations required, due to cyclic reference loop: @@ -1639,6 +1641,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) memmove(buf, start, buf + buflen - start); return 0; } +EXPORT_SYMBOL_GPL(cgroup_path); /** * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp' @@ -1805,6 +1808,7 @@ bool cgroup_lock_live_group(struct cgroup *cgrp) } return true; } +EXPORT_SYMBOL_GPL(cgroup_lock_live_group); static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft, const char *buffer) @@ -4082,6 +4086,7 @@ void __css_put(struct cgroup_subsys_state *css, int count) rcu_read_unlock(); WARN_ON_ONCE(val < 1); } +EXPORT_SYMBOL_GPL(__css_put); /* * Notify userspace when a cgroup is released, by running the @@ -4197,6 +4202,7 @@ unsigned short css_id(struct cgroup_subsys_state *css) return cssid->id; return 0; } +EXPORT_SYMBOL_GPL(css_id); unsigned short css_depth(struct cgroup_subsys_state *css) { @@ -4206,6 +4212,7 @@ unsigned short css_depth(struct cgroup_subsys_state *css) return cssid->depth; return 0; } +EXPORT_SYMBOL_GPL(css_depth); bool css_is_ancestor(struct cgroup_subsys_state *child, const struct cgroup_subsys_state *root) @@ -4242,6 +4249,7 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) spin_unlock(&ss->id_lock); call_rcu(&id->rcu_head, __free_css_id_cb); } +EXPORT_SYMBOL_GPL(free_css_id); /* * This is called by init or create(). Then, calls to this function are @@ -4358,6 +4366,7 @@ struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id) return rcu_dereference(cssid->css); } +EXPORT_SYMBOL_GPL(css_lookup); /** * css_get_next - lookup next cgroup under specified hierarchy. -- cgit v1.2.3 From b70cc5fdb445a6929a01e9c406593265b136c99d Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 10 Mar 2010 15:22:12 -0800 Subject: cgroups: clean up cgroup_pidlist_find() a bit Don't call get_pid_ns() before we locate/alloc the ns. Signed-off-by: Li Zefan Cc: Serge Hallyn Acked-by: Paul Menage Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 521591dbab2f..1bf4d6db54ab 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2597,7 +2597,8 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ - struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns); + struct pid_namespace *ns = current->nsproxy->pid_ns; + /* * We can't drop the pidlist_mutex before taking the l->mutex in case * the last ref-holder is trying to remove l from the list at the same @@ -2607,8 +2608,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) { if (l->key.type == type && l->key.ns == ns) { - /* found a matching list - drop the extra refcount */ - put_pid_ns(ns); /* make sure l doesn't vanish out from under us */ down_write(&l->mutex); mutex_unlock(&cgrp->pidlist_mutex); @@ -2619,13 +2618,12 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); if (!l) { mutex_unlock(&cgrp->pidlist_mutex); - put_pid_ns(ns); return l; } init_rwsem(&l->mutex); down_write(&l->mutex); l->key.type = type; - l->key.ns = ns; + l->key.ns = get_pid_ns(ns); l->use_count = 0; /* don't increment here */ l->list = NULL; l->owner = cgrp; -- cgit v1.2.3 From 0dea116876eefc9c7ca9c5d74fe665481e499fa3 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 10 Mar 2010 15:22:20 -0800 Subject: cgroup: implement eventfd-based generic API for notifications This patchset introduces eventfd-based API for notifications in cgroups and implements memory notifications on top of it. It uses statistics in memory controler to track memory usage. Output of time(1) on building kernel on tmpfs: Root cgroup before changes: make -j2 506.37 user 60.93s system 193% cpu 4:52.77 total Non-root cgroup before changes: make -j2 507.14 user 62.66s system 193% cpu 4:54.74 total Root cgroup after changes (0 thresholds): make -j2 507.13 user 62.20s system 193% cpu 4:53.55 total Non-root cgroup after changes (0 thresholds): make -j2 507.70 user 64.20s system 193% cpu 4:55.70 total Root cgroup after changes (1 thresholds, never crossed): make -j2 506.97 user 62.20s system 193% cpu 4:53.90 total Non-root cgroup after changes (1 thresholds, never crossed): make -j2 507.55 user 64.08s system 193% cpu 4:55.63 total This patch: Introduce the write-only file "cgroup.event_control" in every cgroup. To register new notification handler you need: - create an eventfd; - open a control file to be monitored. Callbacks register_event() and unregister_event() must be defined for the control file; - write " " to cgroup.event_control. Interpretation of args is defined by control file implementation; eventfd will be woken up by control file implementation or when the cgroup is removed. To unregister notification handler just close eventfd. If you need notification functionality for a control file you have to implement callbacks register_event() and unregister_event() in the struct cftype. [kamezawa.hiroyu@jp.fujitsu.com: Kconfig fix] Signed-off-by: Kirill A. Shutemov Reviewed-by: KAMEZAWA Hiroyuki Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Cc: Dan Malek Cc: Vladislav Buzov Cc: Daisuke Nishimura Cc: Alexander Shishkin Cc: Davide Libenzi Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 20 ++++ include/linux/cgroup.h | 24 ++++ init/Kconfig | 1 + kernel/cgroup.c | 228 +++++++++++++++++++++++++++++++++++++- 4 files changed, 272 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index c0358c30c64f..fd588ff0e296 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -23,6 +23,7 @@ CONTENTS: 2.1 Basic Usage 2.2 Attaching processes 2.3 Mounting hierarchies by name + 2.4 Notification API 3. Kernel API 3.1 Overview 3.2 Synchronization @@ -435,6 +436,25 @@ you give a subsystem a name. The name of the subsystem appears as part of the hierarchy description in /proc/mounts and /proc//cgroups. +2.4 Notification API +-------------------- + +There is mechanism which allows to get notifications about changing +status of a cgroup. + +To register new notification handler you need: + - create a file descriptor for event notification using eventfd(2); + - open a control file to be monitored (e.g. memory.usage_in_bytes); + - write " " to cgroup.event_control. + Interpretation of args is defined by control file implementation; + +eventfd will be woken up by control file implementation or when the +cgroup is removed. + +To unregister notification handler just close eventfd. + +NOTE: Support of notifications should be implemented for the control +file. See documentation for the subsystem. 3. Kernel API ============= diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 2a59d3101e5d..b4f2201321cd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -235,6 +235,10 @@ struct cgroup { /* For RCU-protected deletion */ struct rcu_head rcu_head; + + /* List of events which userspace want to recieve */ + struct list_head event_list; + spinlock_t event_list_lock; }; /* @@ -378,6 +382,26 @@ struct cftype { int (*trigger)(struct cgroup *cgrp, unsigned int event); int (*release)(struct inode *inode, struct file *file); + + /* + * register_event() callback will be used to add new userspace + * waiter for changes related to the cftype. Implement it if + * you want to provide this functionality. Use eventfd_signal() + * on eventfd to send notification to userspace. + */ + int (*register_event)(struct cgroup *cgrp, struct cftype *cft, + struct eventfd_ctx *eventfd, const char *args); + /* + * unregister_event() callback will be called when userspace + * closes the eventfd or on cgroup removing. + * This callback must be implemented, if you want provide + * notification functionality. + * + * Be careful. It can be called after destroy(), so you have + * to keep all nesessary data, until all events are removed. + */ + int (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, + struct eventfd_ctx *eventfd); }; struct cgroup_scanner { diff --git a/init/Kconfig b/init/Kconfig index 089a230e5652..eb77e8ccde1c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -463,6 +463,7 @@ config HAVE_UNSTABLE_SCHED_CLOCK menuconfig CGROUPS boolean "Control Group support" + depends on EVENTFD help This option adds support for grouping sets of processes together, for use with process control subsystems such as Cpusets, CFS, memory diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1bf4d6db54ab..ea94984a3895 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4,6 +4,10 @@ * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * + * Notifications support + * Copyright (C) 2009 Nokia Corporation + * Author: Kirill A. Shutemov + * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. @@ -53,6 +57,8 @@ #include #include #include /* TODO: replace with more sophisticated array */ +#include +#include #include @@ -152,6 +158,35 @@ struct css_id { unsigned short stack[0]; /* Array of Length (depth+1) */ }; +/* + * cgroup_event represents events which userspace want to recieve. + */ +struct cgroup_event { + /* + * Cgroup which the event belongs to. + */ + struct cgroup *cgrp; + /* + * Control file which the event associated. + */ + struct cftype *cft; + /* + * eventfd to signal userspace about the event. + */ + struct eventfd_ctx *eventfd; + /* + * Each of these stored in a list by the cgroup. + */ + struct list_head list; + /* + * All fields below needed to unregister event when + * userspace closes eventfd. + */ + poll_table pt; + wait_queue_head_t *wqh; + wait_queue_t wait; + struct work_struct remove; +}; /* The list of hierarchy roots */ @@ -760,14 +795,28 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) static int cgroup_call_pre_destroy(struct cgroup *cgrp) { struct cgroup_subsys *ss; + struct cgroup_event *event, *tmp; int ret = 0; for_each_subsys(cgrp->root, ss) if (ss->pre_destroy) { ret = ss->pre_destroy(ss, cgrp); if (ret) - break; + goto out; } + + /* + * Unregister events and notify userspace. + */ + spin_lock(&cgrp->event_list_lock); + list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) { + list_del(&event->list); + eventfd_signal(event->eventfd, 1); + schedule_work(&event->remove); + } + spin_unlock(&cgrp->event_list_lock); + +out: return ret; } @@ -1239,6 +1288,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); + INIT_LIST_HEAD(&cgrp->event_list); + spin_lock_init(&cgrp->event_list_lock); } static void init_cgroup_root(struct cgroupfs_root *root) @@ -2077,6 +2128,16 @@ static const struct inode_operations cgroup_dir_inode_operations = { .rename = cgroup_rename, }; +/* + * Check if a file is a control file + */ +static inline struct cftype *__file_cft(struct file *file) +{ + if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations) + return ERR_PTR(-EINVAL); + return __d_cft(file->f_dentry); +} + static int cgroup_create_file(struct dentry *dentry, mode_t mode, struct super_block *sb) { @@ -2930,6 +2991,166 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp, return 0; } +/* + * Unregister event and free resources. + * + * Gets called from workqueue. + */ +static void cgroup_event_remove(struct work_struct *work) +{ + struct cgroup_event *event = container_of(work, struct cgroup_event, + remove); + struct cgroup *cgrp = event->cgrp; + + /* TODO: check return code */ + event->cft->unregister_event(cgrp, event->cft, event->eventfd); + + eventfd_ctx_put(event->eventfd); + remove_wait_queue(event->wqh, &event->wait); + kfree(event); +} + +/* + * Gets called on POLLHUP on eventfd when user closes it. + * + * Called with wqh->lock held and interrupts disabled. + */ +static int cgroup_event_wake(wait_queue_t *wait, unsigned mode, + int sync, void *key) +{ + struct cgroup_event *event = container_of(wait, + struct cgroup_event, wait); + struct cgroup *cgrp = event->cgrp; + unsigned long flags = (unsigned long)key; + + if (flags & POLLHUP) { + spin_lock(&cgrp->event_list_lock); + list_del(&event->list); + spin_unlock(&cgrp->event_list_lock); + /* + * We are in atomic context, but cgroup_event_remove() may + * sleep, so we have to call it in workqueue. + */ + schedule_work(&event->remove); + } + + return 0; +} + +static void cgroup_event_ptable_queue_proc(struct file *file, + wait_queue_head_t *wqh, poll_table *pt) +{ + struct cgroup_event *event = container_of(pt, + struct cgroup_event, pt); + + event->wqh = wqh; + add_wait_queue(wqh, &event->wait); +} + +/* + * Parse input and register new cgroup event handler. + * + * Input must be in format ' '. + * Interpretation of args is defined by control file implementation. + */ +static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + struct cgroup_event *event = NULL; + unsigned int efd, cfd; + struct file *efile = NULL; + struct file *cfile = NULL; + char *endp; + int ret; + + efd = simple_strtoul(buffer, &endp, 10); + if (*endp != ' ') + return -EINVAL; + buffer = endp + 1; + + cfd = simple_strtoul(buffer, &endp, 10); + if ((*endp != ' ') && (*endp != '\0')) + return -EINVAL; + buffer = endp + 1; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + event->cgrp = cgrp; + INIT_LIST_HEAD(&event->list); + init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc); + init_waitqueue_func_entry(&event->wait, cgroup_event_wake); + INIT_WORK(&event->remove, cgroup_event_remove); + + efile = eventfd_fget(efd); + if (IS_ERR(efile)) { + ret = PTR_ERR(efile); + goto fail; + } + + event->eventfd = eventfd_ctx_fileget(efile); + if (IS_ERR(event->eventfd)) { + ret = PTR_ERR(event->eventfd); + goto fail; + } + + cfile = fget(cfd); + if (!cfile) { + ret = -EBADF; + goto fail; + } + + /* the process need read permission on control file */ + ret = file_permission(cfile, MAY_READ); + if (ret < 0) + goto fail; + + event->cft = __file_cft(cfile); + if (IS_ERR(event->cft)) { + ret = PTR_ERR(event->cft); + goto fail; + } + + if (!event->cft->register_event || !event->cft->unregister_event) { + ret = -EINVAL; + goto fail; + } + + ret = event->cft->register_event(cgrp, event->cft, + event->eventfd, buffer); + if (ret) + goto fail; + + if (efile->f_op->poll(efile, &event->pt) & POLLHUP) { + event->cft->unregister_event(cgrp, event->cft, event->eventfd); + ret = 0; + goto fail; + } + + spin_lock(&cgrp->event_list_lock); + list_add(&event->list, &cgrp->event_list); + spin_unlock(&cgrp->event_list_lock); + + fput(cfile); + fput(efile); + + return 0; + +fail: + if (cfile) + fput(cfile); + + if (event && event->eventfd && !IS_ERR(event->eventfd)) + eventfd_ctx_put(event->eventfd); + + if (!IS_ERR_OR_NULL(efile)) + fput(efile); + + kfree(event); + + return ret; +} + /* * for the common functions, 'private' gives the type of file */ @@ -2955,6 +3176,11 @@ static struct cftype files[] = { .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, + { + .name = CGROUP_FILE_GENERIC_PREFIX "event_control", + .write_string = cgroup_write_event_control, + .mode = S_IWUGO, + }, }; static struct cftype cft_release_agent = { -- cgit v1.2.3 From 4ab78683c17d739c2a2077141dcf81a02b7fb57e Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 10 Mar 2010 15:22:34 -0800 Subject: cgroups: fix race between userspace and kernelspace Notify userspace about cgroup removing only after rmdir of cgroup directory to avoid race between userspace and kernelspace. eventfd are used to notify about two types of event: - control file-specific, like crossing memory threshold; - cgroup removing. To understand what really happen, userspace can check if the cgroup still exists. To avoid race beetween userspace and kernelspace we have to notify userspace about cgroup removing only after rmdir of cgroup directory. Signed-off-by: Kirill A. Shutemov Reviewed-by: KAMEZAWA Hiroyuki Cc: Paul Menage Acked-by: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Cc: Dan Malek Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ea94984a3895..87441fc75663 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -795,28 +795,15 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) static int cgroup_call_pre_destroy(struct cgroup *cgrp) { struct cgroup_subsys *ss; - struct cgroup_event *event, *tmp; int ret = 0; for_each_subsys(cgrp->root, ss) if (ss->pre_destroy) { ret = ss->pre_destroy(ss, cgrp); if (ret) - goto out; + break; } - /* - * Unregister events and notify userspace. - */ - spin_lock(&cgrp->event_list_lock); - list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) { - list_del(&event->list); - eventfd_signal(event->eventfd, 1); - schedule_work(&event->remove); - } - spin_unlock(&cgrp->event_list_lock); - -out: return ret; } @@ -3006,7 +2993,6 @@ static void cgroup_event_remove(struct work_struct *work) event->cft->unregister_event(cgrp, event->cft, event->eventfd); eventfd_ctx_put(event->eventfd); - remove_wait_queue(event->wqh, &event->wait); kfree(event); } @@ -3024,6 +3010,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode, unsigned long flags = (unsigned long)key; if (flags & POLLHUP) { + remove_wait_queue_locked(event->wqh, &event->wait); spin_lock(&cgrp->event_list_lock); list_del(&event->list); spin_unlock(&cgrp->event_list_lock); @@ -3472,6 +3459,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct dentry *d; struct cgroup *parent; DEFINE_WAIT(wait); + struct cgroup_event *event, *tmp; int ret; /* the vfs holds both inode->i_mutex already */ @@ -3555,6 +3543,20 @@ again: set_bit(CGRP_RELEASABLE, &parent->flags); check_for_release(parent); + /* + * Unregister events and notify userspace. + * Notify userspace about cgroup removing only after rmdir of cgroup + * directory to avoid race between userspace and kernelspace + */ + spin_lock(&cgrp->event_list_lock); + list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) { + list_del(&event->list); + remove_wait_queue(event->wqh, &event->wait); + eventfd_signal(event->eventfd, 1); + schedule_work(&event->remove); + } + spin_unlock(&cgrp->event_list_lock); + mutex_unlock(&cgroup_mutex); return 0; } -- cgit v1.2.3 From a0a4db548edcce067c1201ef25cf2bc29f32dca4 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 10 Mar 2010 15:22:34 -0800 Subject: cgroups: remove events before destroying subsystem state objects Events should be removed after rmdir of cgroup directory, but before destroying subsystem state objects. Let's take reference to cgroup directory dentry to do that. Signed-off-by: Kirill A. Shutemov Acked-by: KAMEZAWA Hiroyuki Cc: Paul Menage Acked-by: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Cc: Dan Malek Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 3 --- kernel/cgroup.c | 8 ++++++++ mm/memcontrol.c | 9 --------- 3 files changed, 8 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b4f2201321cd..b8ad1ea99586 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -396,9 +396,6 @@ struct cftype { * closes the eventfd or on cgroup removing. * This callback must be implemented, if you want provide * notification functionality. - * - * Be careful. It can be called after destroy(), so you have - * to keep all nesessary data, until all events are removed. */ int (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 87441fc75663..ef909a329750 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2994,6 +2994,7 @@ static void cgroup_event_remove(struct work_struct *work) eventfd_ctx_put(event->eventfd); kfree(event); + dput(cgrp->dentry); } /* @@ -3114,6 +3115,13 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, goto fail; } + /* + * Events should be removed after rmdir of cgroup directory, but before + * destroying subsystem state objects. Let's take reference to cgroup + * directory dentry to do that. + */ + dget(cgrp->dentry); + spin_lock(&cgrp->event_list_lock); list_add(&event->list, &cgrp->event_list); spin_unlock(&cgrp->event_list_lock); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f9ae4b4c36eb..f7b910fc14fb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3361,12 +3361,6 @@ static int mem_cgroup_register_event(struct cgroup *cgrp, struct cftype *cft, } } - /* - * We need to increment refcnt to be sure that all thresholds - * will be unregistered before calling __mem_cgroup_free() - */ - mem_cgroup_get(memcg); - if (type == _MEM) rcu_assign_pointer(memcg->thresholds, thresholds_new); else @@ -3460,9 +3454,6 @@ assign: /* To be sure that nobody uses thresholds before freeing it */ synchronize_rcu(); - for (i = 0; i < thresholds->size - size; i++) - mem_cgroup_put(memcg); - kfree(thresholds); unlock: mutex_unlock(&memcg->thresholds_lock); -- cgit v1.2.3 From a56704ef6b0c5796c9ff38cc78aa232dfb9644d7 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 10 Mar 2010 15:23:01 -0800 Subject: copy_signal() cleanup: use zalloc and remove initializations Use kmem_cache_zalloc() on signal creation and remove unneeded initialization lines in copy_signal(). Signed-off-by: Veaceslav Falico Acked-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index b0ec34abc0bb..ce2666f84d85 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -863,7 +863,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) if (clone_flags & CLONE_THREAD) return 0; - sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); + sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; @@ -871,46 +871,21 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) atomic_set(&sig->count, 1); atomic_set(&sig->live, 1); init_waitqueue_head(&sig->wait_chldexit); - sig->flags = 0; if (clone_flags & CLONE_NEWPID) sig->flags |= SIGNAL_UNKILLABLE; - sig->group_exit_code = 0; - sig->group_exit_task = NULL; - sig->group_stop_count = 0; sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->leader = 0; /* session leadership doesn't inherit */ - sig->tty_old_pgrp = NULL; - sig->tty = NULL; - - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; - sig->gtime = cputime_zero; - sig->cgtime = cputime_zero; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - sig->prev_utime = sig->prev_stime = cputime_zero; -#endif - sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; - sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; - sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; - sig->maxrss = sig->cmaxrss = 0; - task_io_accounting_init(&sig->ioac); - sig->sum_sched_runtime = 0; - taskstats_tgid_init(sig); - task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); - acct_init_pacct(&sig->pacct); - tty_audit_fork(sig); sig->oom_adj = current->signal->oom_adj; -- cgit v1.2.3 From 4dd66e69d472f0ba5355a2529364d0db9a18a02b Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 10 Mar 2010 15:23:02 -0800 Subject: copy_signal() cleanup: kill taskstats_tgid_init() and acct_init_pacct() Kill unused functions taskstats_tgid_init() and acct_init_pacct() because we don't use them anywhere after using kmem_cache_zalloc() in copy_signal(). Signed-off-by: Veaceslav Falico Cc: Roland McGrath Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acct.h | 2 -- include/linux/taskstats_kern.h | 7 ------- kernel/acct.c | 10 ---------- 3 files changed, 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/acct.h b/include/linux/acct.h index 882dc7248766..93f46096ad4c 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -123,14 +123,12 @@ struct pacct_struct; struct pid_namespace; extern void acct_auto_close_mnt(struct vfsmount *m); extern void acct_auto_close(struct super_block *sb); -extern void acct_init_pacct(struct pacct_struct *pacct); extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); extern void acct_exit_ns(struct pid_namespace *); #else #define acct_auto_close_mnt(x) do { } while (0) #define acct_auto_close(x) do { } while (0) -#define acct_init_pacct(x) do { } while (0) #define acct_collect(x,y) do { } while (0) #define acct_process() do { } while (0) #define acct_exit_ns(ns) do { } while (0) diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index 3398f4553269..b6523c1427ce 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -14,11 +14,6 @@ extern struct kmem_cache *taskstats_cache; extern struct mutex taskstats_exit_mutex; -static inline void taskstats_tgid_init(struct signal_struct *sig) -{ - sig->stats = NULL; -} - static inline void taskstats_tgid_free(struct signal_struct *sig) { if (sig->stats) @@ -30,8 +25,6 @@ extern void taskstats_init_early(void); #else static inline void taskstats_exit(struct task_struct *tsk, int group_dead) {} -static inline void taskstats_tgid_init(struct signal_struct *sig) -{} static inline void taskstats_tgid_free(struct signal_struct *sig) {} static inline void taskstats_init_early(void) diff --git a/kernel/acct.c b/kernel/acct.c index a6605ca921b6..24f8c81fc48d 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -587,16 +587,6 @@ out: revert_creds(orig_cred); } -/** - * acct_init_pacct - initialize a new pacct_struct - * @pacct: per-process accounting info struct to initialize - */ -void acct_init_pacct(struct pacct_struct *pacct) -{ - memset(pacct, 0, sizeof(struct pacct_struct)); - pacct->ac_utime = pacct->ac_stime = cputime_zero; -} - /** * acct_collect - collect accounting information into pacct_struct * @exitcode: task exit code -- cgit v1.2.3 From 93c59907c6f247d09239135caecf294a106a2ae0 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 10 Mar 2010 15:23:03 -0800 Subject: copy_signal() cleanup: clean thread_group_cputime_init() Remove unneeded initializations in thread_group_cputime_init() and in posix_cpu_timers_init_group(). They are useless after kmem_cache_zalloc() was used in copy_signal(). Signed-off-by: Veaceslav Falico Acked-by: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 -- kernel/fork.c | 11 ----------- 2 files changed, 13 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 46c6f8d5dc06..ca635c128482 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2391,9 +2391,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); static inline void thread_group_cputime_init(struct signal_struct *sig) { - sig->cputimer.cputime = INIT_CPUTIME; spin_lock_init(&sig->cputimer.lock); - sig->cputimer.running = 0; } static inline void thread_group_cputime_free(struct signal_struct *sig) diff --git a/kernel/fork.c b/kernel/fork.c index ce2666f84d85..1beb6c303c41 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -833,17 +833,6 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) /* Thread group counters. */ thread_group_cputime_init(sig); - /* Expiration times and increments. */ - sig->it[CPUCLOCK_PROF].expires = cputime_zero; - sig->it[CPUCLOCK_PROF].incr = cputime_zero; - sig->it[CPUCLOCK_VIRT].expires = cputime_zero; - sig->it[CPUCLOCK_VIRT].incr = cputime_zero; - - /* Cached expiration times. */ - sig->cputime_expires.prof_exp = cputime_zero; - sig->cputime_expires.virt_exp = cputime_zero; - sig->cputime_expires.sched_exp = 0; - cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (cpu_limit != RLIM_INFINITY) { sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); -- cgit v1.2.3 From 13aa9a6b0f2371d2ce0de57c2ede62ab7a787157 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 10 Mar 2010 15:23:09 -0800 Subject: pid_ns: zap_pid_ns_processes: use SEND_SIG_NOINFO instead of force_sig() zap_pid_ns_processes() uses force_sig(SIGKILL) to ensure SIGKILL will be delivered to sub-namespace inits as well. This is correct, but we are going to change force_sig_info() semantics. See http://bugzilla.kernel.org/show_bug.cgi?id=15395#c31 We can use send_sig_info(SEND_SIG_NOINFO) instead, since 614c517d7c00af1b26ded20646b329397d6f51a1 ("signals: SEND_SIG_NOINFO should be considered as SI_FROMUSER()") SEND_SIG_NOINFO means "from user" and therefore send_signal() will get the correct from_ancestor_ns = T flag. Signed-off-by: Oleg Nesterov Acked-by: Serge Hallyn Acked-by: Linus Torvalds Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/pid_namespace.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 86b3796b0436..79aac93acf99 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -161,13 +161,12 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) rcu_read_lock(); /* - * Use force_sig() since it clears SIGNAL_UNKILLABLE ensuring - * any nested-container's init processes don't ignore the - * signal + * Any nested-container's init processes won't ignore the + * SEND_SIG_NOINFO signal, see send_signal()->si_fromuser(). */ task = pid_task(find_vpid(nr), PIDTYPE_PID); if (task) - force_sig(SIGKILL, task); + send_sig_info(SIGKILL, SEND_SIG_NOINFO, task); rcu_read_unlock(); -- cgit v1.2.3 From 8467005da3ef6104b89a4cc5e9c9d9445b75565f Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 10 Mar 2010 15:23:10 -0800 Subject: nsproxy: remove INIT_NSPROXY() Remove INIT_NSPROXY(), use C99 initializer. Remove INIT_IPC_NS(), INIT_NET_NS() while I'm at it. Note: headers trim will be done later, now it's quite pointless because results will be invalidated by merge window. Signed-off-by: Alexey Dobriyan Acked-by: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 8 -------- include/linux/ipc_namespace.h | 5 ----- include/net/net_namespace.h | 5 ----- kernel/nsproxy.c | 13 ++++++++++++- 4 files changed, 12 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index abec69b63d7e..b1ed1cd8e2a8 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -32,14 +32,6 @@ extern struct fs_struct init_fs; } extern struct nsproxy init_nsproxy; -#define INIT_NSPROXY(nsproxy) { \ - .pid_ns = &init_pid_ns, \ - .count = ATOMIC_INIT(1), \ - .uts_ns = &init_uts_ns, \ - .mnt_ns = NULL, \ - INIT_NET_NS(net_ns) \ - INIT_IPC_NS(ipc_ns) \ -} #define INIT_SIGHAND(sighand) { \ .count = ATOMIC_INIT(1), \ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 07baa38bce37..51952989ad42 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -62,11 +62,6 @@ extern struct ipc_namespace init_ipc_ns; extern atomic_t nr_ipc_ns; extern spinlock_t mq_lock; -#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) -#define INIT_IPC_NS(ns) .ns = &init_ipc_ns, -#else -#define INIT_IPC_NS(ns) -#endif #ifdef CONFIG_SYSVIPC extern int register_ipcns_notifier(struct ipc_namespace *); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 82b7be4db89a..bd10a7908993 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -100,14 +100,9 @@ struct net { extern struct net init_net; #ifdef CONFIG_NET -#define INIT_NET_NS(net_ns) .net_ns = &init_net, - extern struct net *copy_net_ns(unsigned long flags, struct net *net_ns); #else /* CONFIG_NET */ - -#define INIT_NET_NS(net_ns) - static inline struct net *copy_net_ns(unsigned long flags, struct net *net_ns) { /* There is nothing to copy so this is a noop */ diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 09b4ff9711b2..2ab67233ee8f 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -24,7 +24,18 @@ static struct kmem_cache *nsproxy_cachep; -struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy); +struct nsproxy init_nsproxy = { + .count = ATOMIC_INIT(1), + .uts_ns = &init_uts_ns, +#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) + .ipc_ns = &init_ipc_ns, +#endif + .mnt_ns = NULL, + .pid_ns = &init_pid_ns, +#ifdef CONFIG_NET + .net_ns = &init_net, +#endif +}; static inline struct nsproxy *create_nsproxy(void) { -- cgit v1.2.3 From eb5572fed55f4c2b7dbc42582bc82dcb47632380 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:23:59 -0800 Subject: sysctl extern cleanup: C_A_D Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move C_A_D extern variable declaration to linux/reboot.h Signed-off-by: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reboot.h | 1 + kernel/sysctl.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 988e55fe649b..3005d5a7fce5 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -64,6 +64,7 @@ extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); +extern int C_A_D; /* for sysctl */ void ctrl_alt_del(void); #define POWEROFF_CMD_PATH_LEN 256 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0ef19c614f6d..72c3b1e80d7b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -65,7 +65,6 @@ #if defined(CONFIG_SYSCTL) /* 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; -- cgit v1.2.3 From d33ed52d57e794eba55cea3f5eab3c8f80b6cb5a Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:23:59 -0800 Subject: sysctl extern cleanup: signal Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move print_fatal_signals extern declaration to linux/signal.h Signed-off-by: Dave Young Cc: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 2 ++ kernel/sysctl.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/signal.h b/include/linux/signal.h index ab9272cc270c..fcd2b14b1932 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -7,6 +7,8 @@ #ifdef __KERNEL__ #include +/* for sysctl */ +extern int print_fatal_signals; /* * Real Time signals may be queued. */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 72c3b1e80d7b..a8fd10a9a501 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -65,7 +66,6 @@ #if defined(CONFIG_SYSCTL) /* External variables not in a header file. */ -extern int print_fatal_signals; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern int sysctl_panic_on_oom; -- cgit v1.2.3 From e5ab67726f33b50f40db0ccf271ceb3c658554d5 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:24:05 -0800 Subject: sysctl extern cleanup: rcu Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move rcutorture_runnable extern declaration to linux/rcupdate.h Signed-off-by: Dave Young Acked-by: Josh Triplett Reviewed-by: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rcupdate.h | 4 ++++ kernel/sysctl.c | 3 --- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c84373626336..a005cac5e302 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -41,6 +41,10 @@ #include #include +#ifdef CONFIG_RCU_TORTURE_TEST +extern int rcutorture_runnable; /* for sysctl */ +#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ + /** * struct rcu_head - callback structure for use with RCU * @next: next update requests in a list diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a8fd10a9a501..f18aaa7b0d65 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -87,9 +87,6 @@ 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 */ #ifdef CONFIG_BLOCK extern int blk_iopoll_enabled; #endif -- cgit v1.2.3 From 5ed109103d73b0bafc92e860cead56725231384d Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:24:06 -0800 Subject: sysctl extern cleanup: module Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move modprobe_path extern declaration to linux/kmod.h Move modules_disabled extern declaration to linux/module.h Signed-off-by: Dave Young Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 1 + include/linux/module.h | 1 + kernel/sysctl.c | 4 ---- 3 files changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 384ca8bbf1ac..facb27fe7de0 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -27,6 +27,7 @@ #define KMOD_PATH_LEN 256 #ifdef CONFIG_MODULES +extern char modprobe_path[]; /* for sysctl */ /* modprobe exit status on success, -ve on error. Return value * usually useless though. */ extern int __request_module(bool wait, const char *name, ...) \ diff --git a/include/linux/module.h b/include/linux/module.h index dd618eb026aa..5e869ffd34aa 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -175,6 +175,7 @@ struct notifier_block; #ifdef CONFIG_MODULES +extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f18aaa7b0d65..44e9492368fd 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -116,10 +116,6 @@ static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; -#ifdef CONFIG_MODULES -extern char modprobe_path[]; -extern int modules_disabled; -#endif #ifdef CONFIG_CHR_DEV_SG extern int sg_big_buff; #endif -- cgit v1.2.3 From 15485a4682d1d3bfee2aa78b4b1a5d36f5746b64 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:24:07 -0800 Subject: sysctl extern cleanup: sg Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move sg_big_buff extern declaration to scsi/sg.h Signed-off-by: Dave Young Acked-by: Doug Gilbert Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/scsi/sg.h | 3 +++ kernel/sysctl.c | 7 +++---- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/scsi/sg.h b/include/scsi/sg.h index 934ae389671d..a9f3c6fc3f57 100644 --- a/include/scsi/sg.h +++ b/include/scsi/sg.h @@ -70,6 +70,9 @@ Major new features in SG 3.x driver (cf SG 2.x drivers) (for the lk 2.2 series). */ +#ifdef __KERNEL__ +extern int sg_big_buff; /* for sysctl */ +#endif /* New interface introduced in the 3.x SG drivers follows */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 44e9492368fd..5290c437f151 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -61,6 +61,9 @@ #include #include #endif +#ifdef CONFIG_CHR_DEV_SG +#include +#endif #if defined(CONFIG_SYSCTL) @@ -116,10 +119,6 @@ static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; -#ifdef CONFIG_CHR_DEV_SG -extern int sg_big_buff; -#endif - #ifdef CONFIG_SPARC #include #endif -- cgit v1.2.3 From c55b7c3e82d0ad58f35a0785faaaf2f70b9b6cd3 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:24:08 -0800 Subject: sysctl extern cleanup: acct Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move acct_parm extern declaration to linux/acct.h Signed-off-by: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acct.h | 1 + kernel/sysctl.c | 7 +++---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/acct.h b/include/linux/acct.h index 93f46096ad4c..3e4737fa6cce 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -121,6 +121,7 @@ struct vfsmount; struct super_block; struct pacct_struct; struct pid_namespace; +extern int acct_parm[]; /* for sysctl */ extern void acct_auto_close_mnt(struct vfsmount *m); extern void acct_auto_close(struct super_block *sb); extern void acct_collect(long exitcode, int group_dead); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5290c437f151..7635bb15f5af 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -61,6 +61,9 @@ #include #include #endif +#ifdef CONFIG_BSD_PROCESS_ACCT +#include +#endif #ifdef CONFIG_CHR_DEV_SG #include #endif @@ -140,10 +143,6 @@ extern int sysctl_userprocess_debug; extern int spin_retry; #endif -#ifdef CONFIG_BSD_PROCESS_ACCT -extern int acct_parm[]; -#endif - #ifdef CONFIG_IA64 extern int no_unaligned_warning; extern int unaligned_dump_stack; -- cgit v1.2.3 From 4f0e056fdebc15d3f4724ebc7bbf323158add1d7 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:24:09 -0800 Subject: sysctl extern cleanup: rtmutex Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move max_lock_depth extern declaration to linux/rtmutex.h Signed-off-by: Dave Young Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtmutex.h | 2 ++ kernel/sysctl.c | 7 +++---- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 281d8fd775e8..8d522ffeda33 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -16,6 +16,8 @@ #include #include +extern int max_lock_depth; /* for sysctl */ + /** * The rt_mutex structure * diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7635bb15f5af..622029ba5103 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -64,6 +64,9 @@ #ifdef CONFIG_BSD_PROCESS_ACCT #include #endif +#ifdef CONFIG_RT_MUTEXES +#include +#endif #ifdef CONFIG_CHR_DEV_SG #include #endif @@ -150,10 +153,6 @@ extern int unaligned_dump_stack; extern struct ratelimit_state printk_ratelimit_state; -#ifdef CONFIG_RT_MUTEXES -extern int max_lock_depth; -#endif - #ifdef CONFIG_PROC_SYSCTL static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From 2edf5e49800846a2b2b6461d99cdae18067c440f Mon Sep 17 00:00:00 2001 From: Dave Young Date: Wed, 10 Mar 2010 15:24:10 -0800 Subject: sysctl extern cleanup: lockdep Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move lockdep extern declarations to linux/lockdep.h Signed-off-by: Dave Young Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 4 ++++ kernel/sysctl.c | 6 +++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 10206a87da19..a03977a96d7e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -12,6 +12,10 @@ struct task_struct; struct lockdep_map; +/* for sysctl */ +extern int prove_locking; +extern int lock_stat; + #ifdef CONFIG_LOCKDEP #include diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 622029ba5103..8686b0f5fc12 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -67,6 +67,9 @@ #ifdef CONFIG_RT_MUTEXES #include #endif +#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT) +#include +#endif #ifdef CONFIG_CHR_DEV_SG #include #endif @@ -191,9 +194,6 @@ extern struct ctl_table epoll_table[]; int sysctl_legacy_va_layout; #endif -extern int prove_locking; -extern int lock_stat; - /* The default sysctl tables: */ static struct ctl_table root_table[] = { -- cgit v1.2.3 From 52fbe9cde7fdb5c6fac196d7ebd2d92d05ef3cd4 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Mon, 8 Mar 2010 14:50:43 +0800 Subject: ring-buffer: Move disabled check into preempt disable section The ring buffer resizing and resetting relies on a schedule RCU action. The buffers are disabled, a synchronize_sched() is called and then the resize or reset takes place. But this only works if the disabling of the buffers are within the preempt disabled section, otherwise a window exists that the buffers can be written to while a reset or resize takes place. Cc: stable@kernel.org Reported-by: Li Zefan Signed-off-by: Lai Jiangshan LKML-Reference: <4B949E43.2010906@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8c1b2d290718..54191d6ed195 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2232,12 +2232,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) if (ring_buffer_flags != RB_BUFFERS_ON) return NULL; - if (atomic_read(&buffer->record_disabled)) - return NULL; - /* If we are tracing schedule, we don't want to recurse */ resched = ftrace_preempt_disable(); + if (atomic_read(&buffer->record_disabled)) + goto out_nocheck; + if (trace_recursive_lock()) goto out_nocheck; @@ -2469,11 +2469,11 @@ int ring_buffer_write(struct ring_buffer *buffer, if (ring_buffer_flags != RB_BUFFERS_ON) return -EBUSY; - if (atomic_read(&buffer->record_disabled)) - return -EBUSY; - resched = ftrace_preempt_disable(); + if (atomic_read(&buffer->record_disabled)) + goto out; + cpu = raw_smp_processor_id(); if (!cpumask_test_cpu(cpu, buffer->cpumask)) -- cgit v1.2.3 From ea14eb714041d40fcc5180b5a586034503650149 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 12 Mar 2010 19:41:23 -0500 Subject: function-graph: Init curr_ret_stack with ret_stack If the graph tracer is active, and a task is forked but the allocating of the processes graph stack fails, it can cause crash later on. This is due to the temporary stack being NULL, but the curr_ret_stack variable is copied from the parent. If it is not -1, then in ftrace_graph_probe_sched_switch() the following: for (index = next->curr_ret_stack; index >= 0; index--) next->ret_stack[index].calltime += timestamp; Will cause a kernel OOPS. Found with Li Zefan's ftrace_stress_test. Cc: stable@kernel.org Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d4d1238b096b..bb53edbb5c8c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3349,6 +3349,7 @@ void ftrace_graph_init_task(struct task_struct *t) { /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; + t->curr_ret_stack = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; @@ -3358,7 +3359,6 @@ void ftrace_graph_init_task(struct task_struct *t) GFP_KERNEL); if (!ret_stack) return; - t->curr_ret_stack = -1; atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->ftrace_timestamp = 0; -- cgit v1.2.3 From 283740c619d211e34572cc93c8cdba92ccbdb9cc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 12 Mar 2010 19:48:41 -0500 Subject: tracing: Use same local variable when resetting the ring buffer In the ftrace code that resets the ring buffer it references the buffer with a local variable, but then uses the tr->buffer as the parameter to reset. If the wakeup tracer is running, which can switch the tr->buffer with the max saved buffer, this can break the requirement of disabling the buffer before the reset. buffer = tr->buffer; ring_buffer_record_disable(buffer); synchronize_sched(); __tracing_reset(tr->buffer, cpu); If the tr->buffer is swapped, then the reset is not happening to the buffer that was disabled. This will cause the ring buffer to fail. Found with Li Zefan's ftrace_stress_test. Cc: stable@kernel.org Reported-by: Lai Jiangshan Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6af8d7bc953b..60de37bd0f75 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -840,10 +840,10 @@ out: mutex_unlock(&trace_types_lock); } -static void __tracing_reset(struct trace_array *tr, int cpu) +static void __tracing_reset(struct ring_buffer *buffer, int cpu) { ftrace_disable_cpu(); - ring_buffer_reset_cpu(tr->buffer, cpu); + ring_buffer_reset_cpu(buffer, cpu); ftrace_enable_cpu(); } @@ -855,7 +855,7 @@ void tracing_reset(struct trace_array *tr, int cpu) /* Make sure all commits have finished */ synchronize_sched(); - __tracing_reset(tr, cpu); + __tracing_reset(buffer, cpu); ring_buffer_record_enable(buffer); } @@ -873,7 +873,7 @@ void tracing_reset_online_cpus(struct trace_array *tr) tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) - __tracing_reset(tr, cpu); + __tracing_reset(buffer, cpu); ring_buffer_record_enable(buffer); } -- cgit v1.2.3 From a2f8071428ed9a0f06865f417c962421c9a6b488 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 12 Mar 2010 19:56:00 -0500 Subject: tracing: Disable buffer switching when starting or stopping trace When the trace iterator is read, tracing_start() and tracing_stop() is called to stop tracing while the iterator is processing the trace output. These functions disable both the standard buffer and the max latency buffer. But if the wakeup tracer is running, it can switch these buffers between the two disables: buffer = global_trace.buffer; if (buffer) ring_buffer_record_disable(buffer); <<<--------- swap happens here buffer = max_tr.buffer; if (buffer) ring_buffer_record_disable(buffer); What happens is that we disabled the same buffer twice. On tracing_start() we can enable the same buffer twice. All ring_buffer_record_disable() must be matched with a ring_buffer_record_enable() or the buffer can be disable permanently, or enable prematurely, and cause a bug where a reset happens while a trace is commiting. This patch protects these two by taking the ftrace_max_lock to prevent a switch from occurring. Found with Li Zefan's ftrace_stress_test. Cc: stable@kernel.org Reported-by: Lai Jiangshan Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 60de37bd0f75..484337d33959 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -950,6 +950,8 @@ void tracing_start(void) goto out; } + /* Prevent the buffers from switching */ + arch_spin_lock(&ftrace_max_lock); buffer = global_trace.buffer; if (buffer) @@ -959,6 +961,8 @@ void tracing_start(void) if (buffer) ring_buffer_record_enable(buffer); + arch_spin_unlock(&ftrace_max_lock); + ftrace_start(); out: spin_unlock_irqrestore(&tracing_start_lock, flags); @@ -980,6 +984,9 @@ void tracing_stop(void) if (trace_stop_count++) goto out; + /* Prevent the buffers from switching */ + arch_spin_lock(&ftrace_max_lock); + buffer = global_trace.buffer; if (buffer) ring_buffer_record_disable(buffer); @@ -988,6 +995,8 @@ void tracing_stop(void) if (buffer) ring_buffer_record_disable(buffer); + arch_spin_unlock(&ftrace_max_lock); + out: spin_unlock_irqrestore(&tracing_start_lock, flags); } -- cgit v1.2.3 From b6345879ccbd9b92864fbd7eb8ac48acdb4d6b15 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 12 Mar 2010 20:03:30 -0500 Subject: tracing: Do not record user stack trace from NMI context A bug was found with Li Zefan's ftrace_stress_test that caused applications to segfault during the test. Placing a tracing_off() in the segfault code, and examining several traces, I found that the following was always the case. The lock tracer was enabled (lockdep being required) and userstack was enabled. Testing this out, I just enabled the two, but that was not good enough. I needed to run something else that could trigger it. Running a load like hackbench did not work, but executing a new program would. The following would trigger the segfault within seconds: # echo 1 > /debug/tracing/options/userstacktrace # echo 1 > /debug/tracing/events/lock/enable # while :; do ls > /dev/null ; done Enabling the function graph tracer and looking at what was happening I finally noticed that all cashes happened just after an NMI. 1) | copy_user_handle_tail() { 1) | bad_area_nosemaphore() { 1) | __bad_area_nosemaphore() { 1) | no_context() { 1) | fixup_exception() { 1) 0.319 us | search_exception_tables(); 1) 0.873 us | } [...] 1) 0.314 us | __rcu_read_unlock(); 1) 0.325 us | native_apic_mem_write(); 1) 0.943 us | } 1) 0.304 us | rcu_nmi_exit(); [...] 1) 0.479 us | find_vma(); 1) | bad_area() { 1) | __bad_area() { After capturing several traces of failures, all of them happened after an NMI. Curious about this, I added a trace_printk() to the NMI handler to read the regs->ip to see where the NMI happened. In which I found out it was here: ffffffff8135b660 : ffffffff8135b660: 48 83 ec 78 sub $0x78,%rsp ffffffff8135b664: e8 97 01 00 00 callq ffffffff8135b800 What was happening is that the NMI would happen at the place that a page fault occurred. It would call rcu_read_lock() which was traced by the lock events, and the user_stack_trace would run. This would trigger a page fault inside the NMI. I do not see where the CR2 register is saved or restored in NMI handling. This means that it would corrupt the page fault handling that the NMI interrupted. The reason the while loop of ls helped trigger the bug, was that each execution of ls would cause lots of pages to be faulted in, and increase the chances of the race happening. The simple solution is to not allow user stack traces in NMI context. After this patch, I ran the above "ls" test for a couple of hours without any issues. Without this patch, the bug would trigger in less than a minute. Cc: stable@kernel.org Reported-by: Li Zefan Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 484337d33959..e52683f7c3b2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1284,6 +1284,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) return; + /* + * NMIs can not handle page faults, even with fix ups. + * The save user stack can (and often does) fault. + */ + if (unlikely(in_nmi())) + return; + event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, sizeof(*entry), flags, pc); if (!event) -- cgit v1.2.3 From cd3d8031eb4311e516329aee03c79a08333141f1 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 12 Mar 2010 16:15:36 +0900 Subject: sched: sched_getaffinity(): Allow less than NR_CPUS length [ Note, this commit changes the syscall ABI for > 1024 CPUs systems. ] Recently, some distro decided to use NR_CPUS=4096 for mysterious reasons. Unfortunately, glibc sched interface has the following definition: # define __CPU_SETSIZE 1024 # define __NCPUBITS (8 * sizeof (__cpu_mask)) typedef unsigned long int __cpu_mask; typedef struct { __cpu_mask __bits[__CPU_SETSIZE / __NCPUBITS]; } cpu_set_t; It mean, if NR_CPUS is bigger than 1024, cpu_set_t makes an ABI issue ... More recently, Sharyathi Nagesh reported following test program makes misterious syscall failure: ----------------------------------------------------------------------- #define _GNU_SOURCE #include #include #include int main() { cpu_set_t set; if (sched_getaffinity(0, sizeof(cpu_set_t), &set) < 0) printf("\n Call is failing with:%d", errno); } ----------------------------------------------------------------------- Because the kernel assumes len argument of sched_getaffinity() is bigger than NR_CPUS. But now it is not correct. Now we are faced with the following annoying dilemma, due to the limitations of the glibc interface built in years ago: (1) if we change glibc's __CPU_SETSIZE definition, we lost binary compatibility of _all_ application. (2) if we don't change it, we also lost binary compatibility of Sharyathi's use case. Then, I would propse to change the rule of the len argument of sched_getaffinity(). Old: len should be bigger than NR_CPUS New: len should be bigger than maximum possible cpu id This creates the following behavior: (A) In the real 4096 cpus machine, the above test program still return -EINVAL. (B) NR_CPUS=4096 but the machine have less than 1024 cpus (almost all machines in the world), the above can run successfully. Fortunatelly, BIG SGI machine is mainly used for HPC use case. It means they can rebuild their programs. IOW we hope they are not annoyed by this issue ... Reported-by: Sharyathi Nagesh Signed-off-by: KOSAKI Motohiro Acked-by: Ulrich Drepper Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Jack Steiner Cc: Russ Anderson Cc: Mike Travis LKML-Reference: <20100312161316.9520.A69D9226@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 9ab3cd7858d3..6eaef3df2d19 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4902,7 +4902,9 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, int ret; cpumask_var_t mask; - if (len < cpumask_size()) + if (len < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) return -EINVAL; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) @@ -4910,10 +4912,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - if (copy_to_user(user_mask_ptr, mask, cpumask_size())) + int retlen = min(len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) ret = -EFAULT; else - ret = cpumask_size(); + ret = retlen; } free_cpumask_var(mask); -- cgit v1.2.3 From e3818b8dce2a934cd1521dbc4827e5238d8f45d8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 15 Mar 2010 17:03:43 -0700 Subject: rcu: Make rcu_read_lock_bh_held() allow for disabled BH Disabling BH can stand in for rcu_read_lock_bh(), and this patch updates rcu_read_lock_bh_held() to allow for this. In order to avoid include-file hell, this function is moved out of line to kernel/rcupdate.c. This fixes a false positive RCU warning. Reported-by: Arnd Bergmann Reported-by: Eric Dumazet Signed-off-by: Paul E. McKenney Acked-by: Lai Jiangshan Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <20100316000343.GA25857@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 19 ++++--------------- kernel/rcupdate.c | 23 +++++++++++++++++++++++ 2 files changed, 27 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 3024050c82a1..e1bdc4bfd275 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -123,22 +123,11 @@ static inline int rcu_read_lock_held(void) return lock_is_held(&rcu_lock_map); } -/** - * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? - * - * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in - * an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING, - * this assumes we are in an RCU-bh read-side critical section unless it can - * prove otherwise. - * - * Check rcu_scheduler_active to prevent false positives during boot. +/* + * rcu_read_lock_bh_held() is defined out of line to avoid #include-file + * hell. */ -static inline int rcu_read_lock_bh_held(void) -{ - if (!debug_lockdep_rcu_enabled()) - return 1; - return lock_is_held(&rcu_bh_lock_map); -} +extern int rcu_read_lock_bh_held(void); /** * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index f1125c1a6321..63fe25433980 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -45,6 +45,7 @@ #include #include #include +#include #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; @@ -66,6 +67,28 @@ EXPORT_SYMBOL_GPL(rcu_sched_lock_map); int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/** + * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? + * + * Check for bottom half being disabled, which covers both the + * CONFIG_PROVE_RCU and not cases. Note that if someone uses + * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled) + * will show the situation. + * + * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. + */ +int rcu_read_lock_bh_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + return in_softirq(); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); + +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /* * This function is invoked towards the end of the scheduler's initialization * process. Before this is called, the idle task might contain -- cgit v1.2.3 From c890692bf37671b5b78a1870d55d6d87e1c8a509 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 11 Mar 2010 14:08:43 -0800 Subject: kernel/sched.c: Suppress unused var warning On UP: kernel/sched.c: In function 'wake_up_new_task': kernel/sched.c:2631: warning: unused variable 'cpu' Signed-off-by: Andrew Morton Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 6eaef3df2d19..82975b5b42f7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2650,7 +2650,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { unsigned long flags; struct rq *rq; - int cpu = get_cpu(); + int cpu __maybe_unused = get_cpu(); #ifdef CONFIG_SMP /* -- cgit v1.2.3 From 8bc037fb89bb3104b9ae290d18c877624cd7d9cc Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 17 Mar 2010 09:36:58 +0900 Subject: sched: Use proper type in sched_getaffinity() Using the proper type fixes the following compiler warning: kernel/sched.c:4850: warning: comparison of distinct pointer types lacks a cast Signed-off-by: KOSAKI Motohiro Cc: torvalds@linux-foundation.org Cc: travis@sgi.com Cc: peterz@infradead.org Cc: drepper@redhat.com Cc: rja@sgi.com Cc: sharyath@in.ibm.com Cc: steiner@sgi.com LKML-Reference: <20100317090046.4C79.A69D9226@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 82975b5b42f7..49d2fa7b687a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4912,7 +4912,7 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - int retlen = min(len, cpumask_size()); + size_t retlen = min_t(size_t, len, cpumask_size()); if (copy_to_user(user_mask_ptr, mask, retlen)) ret = -EFAULT; -- cgit v1.2.3 From dcd5c1662db59a6b82942f47fb6ac9dd63f6d3dd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 16 Mar 2010 01:05:02 +0100 Subject: perf: Fix unexported generic perf_arch_fetch_caller_regs perf_arch_fetch_caller_regs() is exported for the overriden x86 version, but not for the generic weak version. As a general rule, weak functions should not have their symbol exported in the same file they are defined. So let's export it on trace_event_perf.c as it is used by trace events only. This fixes: ERROR: ".perf_arch_fetch_caller_regs" [fs/xfs/xfs.ko] undefined! ERROR: ".perf_arch_fetch_caller_regs" [arch/powerpc/platforms/cell/spufs/spufs.ko] undefined! -v2: And also only build it if trace events are enabled. -v3: Fix changelog mistake Reported-by: Stephen Rothwell Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Xiao Guangrong Cc: Paul Mackerras LKML-Reference: <1268697902-9518-1-git-send-regression-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 3 ++- kernel/perf_event.c | 2 ++ kernel/trace/trace_event_perf.c | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 7645faea8e85..60398a0d947c 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1702,6 +1702,7 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } +#ifdef CONFIG_EVENT_TRACING void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) { regs->ip = ip; @@ -1713,4 +1714,4 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski regs->cs = __KERNEL_CS; local_save_flags(regs->flags); } -EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); +#endif diff --git a/kernel/perf_event.c b/kernel/perf_event.c index fb3031cf9f17..574ee58a3046 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2786,10 +2786,12 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return NULL; } +#ifdef CONFIG_EVENT_TRACING __weak void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) { } +#endif /* * Output diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0709e4f75114..7d79a10c3cde 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -12,6 +12,8 @@ DEFINE_PER_CPU(struct pt_regs, perf_trace_regs); EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs); +EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); + static char *perf_trace_buf; static char *perf_trace_buf_nmi; -- cgit v1.2.3 From 2271048d1b3b0aabf83d25b29c20646dcabedc05 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 18 Mar 2010 17:54:19 -0400 Subject: ring-buffer: Do 8 byte alignment for 64 bit that can not handle 4 byte align The ring buffer uses 4 byte alignment while recording events into the buffer, even on 64bit machines. This saves space when there are lots of events being recorded at 4 byte boundaries. The ring buffer has a zero copy method to write into the buffer, with the reserving of space and then committing it. This may cause problems when writing an 8 byte word into a 4 byte alignment (not 8). For x86 and PPC this is not an issue, but on some architectures this would cause an out-of-alignment exception. This patch uses CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS to determine if it is OK to use 4 byte alignments on 64 bit machines. If it is not, it forces the ring buffer event header to be 8 bytes and not 4, and will align the length of the data to be 8 byte aligned. This keeps the data payload at 8 byte alignments and will allow these machines to run without issue. The trick to this is that the header can be either 4 bytes or 8 bytes depending on the length of the data payload. The 4 byte header has a length field that supports up to 112 bytes. If the length of the data is more than 112, the length field is set to zero, and the actual length is stored in the next 4 bytes after the header. When CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is not set, the code forces zero in the 4 byte header forcing the length to be stored in the 4 byte array, even with a small data load. It also forces the length of the data load to be 8 byte aligned. The combination of these two guarantee that the data is always at 8 byte alignment. Tested-by: Frederic Weisbecker (on sparc64) Reported-by: Frederic Weisbecker Acked-by: David S. Miller Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 05a9f83b8819..d1187ef20caf 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -207,6 +207,14 @@ EXPORT_SYMBOL_GPL(tracing_is_on); #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) #define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ +#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +# define RB_FORCE_8BYTE_ALIGNMENT 0 +# define RB_ARCH_ALIGNMENT RB_ALIGNMENT +#else +# define RB_FORCE_8BYTE_ALIGNMENT 1 +# define RB_ARCH_ALIGNMENT 8U +#endif + /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX @@ -1547,7 +1555,7 @@ rb_update_event(struct ring_buffer_event *event, case 0: length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA) + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) event->array[0] = length; else event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT); @@ -1722,11 +1730,11 @@ static unsigned rb_calculate_event_length(unsigned length) if (!length) length = 1; - if (length > RB_MAX_SMALL_DATA) + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) length += sizeof(event.array[0]); length += RB_EVNT_HDR_SIZE; - length = ALIGN(length, RB_ALIGNMENT); + length = ALIGN(length, RB_ARCH_ALIGNMENT); return length; } -- cgit v1.2.3 From 8c2eb4805d422bdbf60ba00ff233c794d23c3c00 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 19 Mar 2010 10:28:02 +0000 Subject: softlockup: Stop spurious softlockup messages due to overflow Ensure additions on touch_ts do not overflow. This can occur when the top 32 bits of the TSC reach 0xffffffff causing additions to touch_ts to overflow and this in turn generates spurious softlockup warnings. Signed-off-by: Colin Ian King Cc: Peter Zijlstra Cc: Eric Dumazet Cc: LKML-Reference: <1268994482.1798.6.camel@lenovo> Signed-off-by: Ingo Molnar --- kernel/softlockup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 0d4c7898ab80..4b493f67dcb5 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -155,11 +155,11 @@ void softlockup_tick(void) * Wake up the high-prio watchdog task twice per * threshold timespan. */ - if (now > touch_ts + softlockup_thresh/2) + if (time_after(now - softlockup_thresh/2, touch_ts)) wake_up_process(per_cpu(softlockup_watchdog, this_cpu)); /* Warn about unreasonable delays: */ - if (now <= (touch_ts + softlockup_thresh)) + if (time_before_eq(now - softlockup_thresh, touch_ts)) return; per_cpu(softlockup_print_ts, this_cpu) = touch_ts; -- cgit v1.2.3 From 830ec0458c390f29c6c99e1ff7feab9e36368d12 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 18 Mar 2010 14:47:30 -0700 Subject: time: Fix accumulation bug triggered by long delay. The logarithmic accumulation done in the timekeeping has some overflow protection that limits the max shift value. That means it will take more then shift loops to accumulate all of the cycles. This causes the shift decrement to underflow, which causes the loop to never exit. The simplest fix would be simply to do a: if (shift) shift--; However that is not optimal, as we know the cycle offset is larger then the interval << shift, the above would make shift drop to zero, then we would be spinning for quite awhile accumulating at interval chunks at a time. Instead, this patch only decreases shift if the offset is smaller then cycle_interval << shift. This makes sure we accumulate using the largest chunks possible without overflowing tick_length, and limits the number of iterations through the loop. This issue was found and reported by Sonic Zhang, who also tested the fix. Many thanks your explanation and testing! Reported-by: Sonic Zhang Signed-off-by: John Stultz Tested-by: Sonic Zhang LKML-Reference: <1268948850-5225-1-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 16736379a9ca..39f6177fafac 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -818,7 +818,8 @@ void update_wall_time(void) shift = min(shift, maxshift); while (offset >= timekeeper.cycle_interval) { offset = logarithmic_accumulation(offset, shift); - shift--; + if(offset < timekeeper.cycle_interval< Date: Thu, 11 Mar 2010 17:01:09 -0700 Subject: resources: add interfaces that return conflict information request_resource() and insert_resource() only return success or failure, which no information about what existing resource conflicted with the proposed new reservation. This patch adds request_resource_conflict() and insert_resource_conflict(), which return the conflicting resource. Callers may use this for better error messages or to adjust the new resource and retry the request. Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 2 ++ kernel/resource.c | 44 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 39 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 71ab79da7e7f..26fad187d661 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,12 +112,14 @@ struct resource_list { extern struct resource ioport_resource; extern struct resource iomem_resource; +extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); extern int release_resource(struct resource *new); void release_child_resources(struct resource *new); extern void reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name); +extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); extern int allocate_resource(struct resource *root, struct resource *new, diff --git a/kernel/resource.c b/kernel/resource.c index 2d5be5d9bf5f..9c358e263534 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -219,19 +219,34 @@ void release_child_resources(struct resource *r) } /** - * request_resource - request and reserve an I/O or memory resource + * request_resource_conflict - request and reserve an I/O or memory resource * @root: root resource descriptor * @new: resource descriptor desired by caller * - * Returns 0 for success, negative error code on error. + * Returns 0 for success, conflict resource on error. */ -int request_resource(struct resource *root, struct resource *new) +struct resource *request_resource_conflict(struct resource *root, struct resource *new) { struct resource *conflict; write_lock(&resource_lock); conflict = __request_resource(root, new); write_unlock(&resource_lock); + return conflict; +} + +/** + * request_resource - request and reserve an I/O or memory resource + * @root: root resource descriptor + * @new: resource descriptor desired by caller + * + * Returns 0 for success, negative error code on error. + */ +int request_resource(struct resource *root, struct resource *new) +{ + struct resource *conflict; + + conflict = request_resource_conflict(root, new); return conflict ? -EBUSY : 0; } @@ -474,25 +489,40 @@ static struct resource * __insert_resource(struct resource *parent, struct resou } /** - * insert_resource - Inserts a resource in the resource tree + * insert_resource_conflict - Inserts resource in the resource tree * @parent: parent of the new resource * @new: new resource to insert * - * Returns 0 on success, -EBUSY if the resource can't be inserted. + * Returns 0 on success, conflict resource if the resource can't be inserted. * - * This function is equivalent to request_resource when no conflict + * This function is equivalent to request_resource_conflict when no conflict * happens. If a conflict happens, and the conflicting resources * entirely fit within the range of the new resource, then the new * resource is inserted and the conflicting resources become children of * the new resource. */ -int insert_resource(struct resource *parent, struct resource *new) +struct resource *insert_resource_conflict(struct resource *parent, struct resource *new) { struct resource *conflict; write_lock(&resource_lock); conflict = __insert_resource(parent, new); write_unlock(&resource_lock); + return conflict; +} + +/** + * insert_resource - Inserts a resource in the resource tree + * @parent: parent of the new resource + * @new: new resource to insert + * + * Returns 0 on success, -EBUSY if the resource can't be inserted. + */ +int insert_resource(struct resource *parent, struct resource *new) +{ + struct resource *conflict; + + conflict = insert_resource_conflict(parent, new); return conflict ? -EBUSY : 0; } -- cgit v1.2.3 From cc8c3b78433222e5dbc1fdfcfdde29e1743f181a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 23 Mar 2010 22:40:53 +0100 Subject: genirq: Protect access to irq_desc->action in can_request_irq() can_request_irq() accesses and dereferences irq_desc->action w/o holding irq_desc->lock. So action can be freed on another CPU before it's dereferenced. Unlikely, but ... Protect it with desc->lock. Signed-off-by: Thomas Gleixner --- kernel/irq/manage.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 69a3d7b9414c..398fda155f6e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -382,6 +382,7 @@ int can_request_irq(unsigned int irq, unsigned long irqflags) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; + unsigned long flags; if (!desc) return 0; @@ -389,11 +390,14 @@ int can_request_irq(unsigned int irq, unsigned long irqflags) if (desc->status & IRQ_NOREQUEST) return 0; + raw_spin_lock_irqsave(&desc->lock, flags); action = desc->action; if (action) if (irqflags & action->flags & IRQF_SHARED) action = NULL; + raw_spin_unlock_irqrestore(&desc->lock, flags); + return !action; } -- cgit v1.2.3 From 860652bfb890bd861c999ec39fcffabe5b712f85 Mon Sep 17 00:00:00 2001 From: Henrik Kretzschmar Date: Wed, 24 Mar 2010 12:59:20 +0100 Subject: genirq: Move two IRQ functions from .init.text to .text Both functions should not be marked as __init, since they be called from modules after the init section is freed. Signed-off-by: Henrik Kretzschmar Cc: Yinghai Lu Cc: Peter Zijlstra Cc: Jiri Kosina LKML-Reference: <1269431961-5731-1-git-send-email-henne@nachtwindheim.de> Signed-off-by: Thomas Gleixner --- kernel/irq/chip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 71eba24a39a2..3c2d6e7737f0 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -729,7 +729,7 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, __set_irq_handler(irq, handle, 0, name); } -void __init set_irq_noprobe(unsigned int irq) +void set_irq_noprobe(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; @@ -744,7 +744,7 @@ void __init set_irq_noprobe(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); } -void __init set_irq_probe(unsigned int irq) +void set_irq_probe(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; -- cgit v1.2.3 From 9d34706f42f9b8c15185423d9af98d37ba21d011 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 23 Mar 2010 13:35:12 -0700 Subject: cgroups: remove duplicate include commit e6a1105b ("cgroups: subsystem module loading interface") and commit c50cc752 ("sched, cgroups: Fix module export") result in duplicate including of module.h Signed-off-by: Li Zefan Acked-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ef909a329750..e2769e13980c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -27,7 +27,6 @@ */ #include -#include #include #include #include -- cgit v1.2.3 From 5ab116c9349ef52d6fbd2e2917a53f13194b048e Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Tue, 23 Mar 2010 13:35:34 -0700 Subject: cpuset: fix the problem that cpuset_mem_spread_node() returns an offline node cpuset_mem_spread_node() returns an offline node, and causes an oops. This patch fixes it by initializing task->mems_allowed to node_states[N_HIGH_MEMORY], and updating task->mems_allowed when doing memory hotplug. Signed-off-by: Miao Xie Acked-by: David Rientjes Reported-by: Nick Piggin Tested-by: Nick Piggin Cc: Paul Menage Cc: Li Zefan Cc: Ingo Molnar Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 +- kernel/cpuset.c | 20 ++++++++++++-------- kernel/kthread.c | 2 +- 3 files changed, 14 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/init/main.c b/init/main.c index a1ab78ceb4b6..cbead27caefc 100644 --- a/init/main.c +++ b/init/main.c @@ -858,7 +858,7 @@ static int __init kernel_init(void * unused) /* * init can allocate pages on any node */ - set_mems_allowed(node_possible_map); + set_mems_allowed(node_states[N_HIGH_MEMORY]); /* * init can run on any cpu. */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index ba401fab459f..5d38bd74483c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -920,9 +920,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * call to guarantee_online_mems(), as we know no one is changing * our task's cpuset. * - * Hold callback_mutex around the two modifications of our tasks - * mems_allowed to synchronize with cpuset_mems_allowed(). - * * While the mm_struct we are migrating is typically from some * other task, the task_struct mems_allowed that we are hacking * is for our current task, which must allocate new pages for that @@ -1391,11 +1388,10 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, if (cs == &top_cpuset) { cpumask_copy(cpus_attach, cpu_possible_mask); - to = node_possible_map; } else { guarantee_online_cpus(cs, cpus_attach); - guarantee_online_mems(cs, &to); } + guarantee_online_mems(cs, &to); /* do per-task migration stuff possibly for each in the threadgroup */ cpuset_attach_task(tsk, &to, cs); @@ -2090,15 +2086,23 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { + nodemask_t oldmems; + cgroup_lock(); switch (action) { case MEM_ONLINE: - case MEM_OFFLINE: + oldmems = top_cpuset.mems_allowed; mutex_lock(&callback_mutex); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; mutex_unlock(&callback_mutex); - if (action == MEM_OFFLINE) - scan_for_empty_cpusets(&top_cpuset); + update_tasks_nodemask(&top_cpuset, &oldmems, NULL); + break; + case MEM_OFFLINE: + /* + * needn't update top_cpuset.mems_allowed explicitly because + * scan_for_empty_cpusets() will update it. + */ + scan_for_empty_cpusets(&top_cpuset); break; default: break; diff --git a/kernel/kthread.c b/kernel/kthread.c index 82ed0ea15194..83911c780175 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -219,7 +219,7 @@ int kthreadd(void *unused) set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); set_cpus_allowed_ptr(tsk, cpu_all_mask); - set_mems_allowed(node_possible_map); + set_mems_allowed(node_states[N_HIGH_MEMORY]); current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; -- cgit v1.2.3 From 53feb29767c29c877f9d47dcfe14211b5b0f7ebd Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Tue, 23 Mar 2010 13:35:35 -0700 Subject: cpuset: alloc nodemask_t on the heap rather than the stack Signed-off-by: Miao Xie Acked-by: David Rientjes Cc: Nick Piggin Cc: Paul Menage Cc: Li Zefan Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 94 ++++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 66 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 5d38bd74483c..d10946748ec2 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -970,15 +970,20 @@ static void cpuset_change_nodemask(struct task_struct *p, struct cpuset *cs; int migrate; const nodemask_t *oldmem = scan->data; - nodemask_t newmems; + NODEMASK_ALLOC(nodemask_t, newmems, GFP_KERNEL); + + if (!newmems) + return; cs = cgroup_cs(scan->cg); - guarantee_online_mems(cs, &newmems); + guarantee_online_mems(cs, newmems); task_lock(p); - cpuset_change_task_nodemask(p, &newmems); + cpuset_change_task_nodemask(p, newmems); task_unlock(p); + NODEMASK_FREE(newmems); + mm = get_task_mm(p); if (!mm) return; @@ -1048,16 +1053,21 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { - nodemask_t oldmem; + NODEMASK_ALLOC(nodemask_t, oldmem, GFP_KERNEL); int retval; struct ptr_heap heap; + if (!oldmem) + return -ENOMEM; + /* * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY]; * it's read-only */ - if (cs == &top_cpuset) - return -EACCES; + if (cs == &top_cpuset) { + retval = -EACCES; + goto done; + } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. @@ -1073,11 +1083,13 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, goto done; if (!nodes_subset(trialcs->mems_allowed, - node_states[N_HIGH_MEMORY])) - return -EINVAL; + node_states[N_HIGH_MEMORY])) { + retval = -EINVAL; + goto done; + } } - oldmem = cs->mems_allowed; - if (nodes_equal(oldmem, trialcs->mems_allowed)) { + *oldmem = cs->mems_allowed; + if (nodes_equal(*oldmem, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } @@ -1093,10 +1105,11 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, cs->mems_allowed = trialcs->mems_allowed; mutex_unlock(&callback_mutex); - update_tasks_nodemask(cs, &oldmem, &heap); + update_tasks_nodemask(cs, oldmem, &heap); heap_free(&heap); done: + NODEMASK_FREE(oldmem); return retval; } @@ -1381,39 +1394,47 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *oldcont, struct task_struct *tsk, bool threadgroup) { - nodemask_t from, to; struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); + NODEMASK_ALLOC(nodemask_t, from, GFP_KERNEL); + NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL); + + if (from == NULL || to == NULL) + goto alloc_fail; if (cs == &top_cpuset) { cpumask_copy(cpus_attach, cpu_possible_mask); } else { guarantee_online_cpus(cs, cpus_attach); } - guarantee_online_mems(cs, &to); + guarantee_online_mems(cs, to); /* do per-task migration stuff possibly for each in the threadgroup */ - cpuset_attach_task(tsk, &to, cs); + cpuset_attach_task(tsk, to, cs); if (threadgroup) { struct task_struct *c; rcu_read_lock(); list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - cpuset_attach_task(c, &to, cs); + cpuset_attach_task(c, to, cs); } rcu_read_unlock(); } /* change mm; only needs to be done once even if threadgroup */ - from = oldcs->mems_allowed; - to = cs->mems_allowed; + *from = oldcs->mems_allowed; + *to = cs->mems_allowed; mm = get_task_mm(tsk); if (mm) { - mpol_rebind_mm(mm, &to); + mpol_rebind_mm(mm, to); if (is_memory_migrate(cs)) - cpuset_migrate_mm(mm, &from, &to); + cpuset_migrate_mm(mm, from, to); mmput(mm); } + +alloc_fail: + NODEMASK_FREE(from); + NODEMASK_FREE(to); } /* The various types of files and directories in a cpuset file system */ @@ -1558,13 +1579,21 @@ static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs) static int cpuset_sprintf_memlist(char *page, struct cpuset *cs) { - nodemask_t mask; + NODEMASK_ALLOC(nodemask_t, mask, GFP_KERNEL); + int retval; + + if (mask == NULL) + return -ENOMEM; mutex_lock(&callback_mutex); - mask = cs->mems_allowed; + *mask = cs->mems_allowed; mutex_unlock(&callback_mutex); - return nodelist_scnprintf(page, PAGE_SIZE, mask); + retval = nodelist_scnprintf(page, PAGE_SIZE, *mask); + + NODEMASK_FREE(mask); + + return retval; } static ssize_t cpuset_common_file_read(struct cgroup *cont, @@ -1993,7 +2022,10 @@ static void scan_for_empty_cpusets(struct cpuset *root) struct cpuset *cp; /* scans cpusets being updated */ struct cpuset *child; /* scans child cpusets of cp */ struct cgroup *cont; - nodemask_t oldmems; + NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL); + + if (oldmems == NULL) + return; list_add_tail((struct list_head *)&root->stack_list, &queue); @@ -2010,7 +2042,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) continue; - oldmems = cp->mems_allowed; + *oldmems = cp->mems_allowed; /* Remove offline cpus and mems from this cpuset. */ mutex_lock(&callback_mutex); @@ -2026,9 +2058,10 @@ static void scan_for_empty_cpusets(struct cpuset *root) remove_tasks_in_empty_cpuset(cp); else { update_tasks_cpumask(cp, NULL); - update_tasks_nodemask(cp, &oldmems, NULL); + update_tasks_nodemask(cp, oldmems, NULL); } } + NODEMASK_FREE(oldmems); } /* @@ -2086,16 +2119,19 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { - nodemask_t oldmems; + NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL); + + if (oldmems == NULL) + return NOTIFY_DONE; cgroup_lock(); switch (action) { case MEM_ONLINE: - oldmems = top_cpuset.mems_allowed; + *oldmems = top_cpuset.mems_allowed; mutex_lock(&callback_mutex); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; mutex_unlock(&callback_mutex); - update_tasks_nodemask(&top_cpuset, &oldmems, NULL); + update_tasks_nodemask(&top_cpuset, oldmems, NULL); break; case MEM_OFFLINE: /* @@ -2108,6 +2144,8 @@ static int cpuset_track_online_nodes(struct notifier_block *self, break; } cgroup_unlock(); + + NODEMASK_FREE(oldmems); return NOTIFY_OK; } #endif -- cgit v1.2.3 From 88be12c440cfa2fa3f5be83507360aac9ea1c54e Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 29 Mar 2010 12:01:50 +0100 Subject: slow-work: use get_ref wrapper instead of directly calling get_ref Otherwise we can get an oops if the user has no get_ref/put_ref requirement. Signed-off-by: Dave Airlie Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/slow-work.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 7494bbf5a270..7d3f4fa9ef4f 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -637,7 +637,7 @@ int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, goto cancelled; /* the timer holds a reference whilst it is pending */ - ret = work->ops->get_ref(work); + ret = slow_work_get_ref(work); if (ret < 0) goto cant_get_ref; -- cgit v1.2.3 From a53f4f9efaeb1d87cfae066346979d4d70e1abe9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 29 Mar 2010 13:08:52 +0100 Subject: SLOW_WORK: CONFIG_SLOW_WORK_PROC should be CONFIG_SLOW_WORK_DEBUG CONFIG_SLOW_WORK_PROC was changed to CONFIG_SLOW_WORK_DEBUG, but not in all instances. Change the remaining instances. This makes the debugfs file display the time mark and the owner's description again. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/fscache/object.c | 6 +++--- fs/fscache/operation.c | 4 ++-- include/linux/fscache-cache.h | 2 +- kernel/slow-work.h | 8 ++++---- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/fs/fscache/object.c b/fs/fscache/object.c index e513ac599c8e..0b589a9b4ffc 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -53,7 +53,7 @@ const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = { static void fscache_object_slow_work_put_ref(struct slow_work *); static int fscache_object_slow_work_get_ref(struct slow_work *); static void fscache_object_slow_work_execute(struct slow_work *); -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG static void fscache_object_slow_work_desc(struct slow_work *, struct seq_file *); #endif static void fscache_initialise_object(struct fscache_object *); @@ -69,7 +69,7 @@ const struct slow_work_ops fscache_object_slow_work_ops = { .get_ref = fscache_object_slow_work_get_ref, .put_ref = fscache_object_slow_work_put_ref, .execute = fscache_object_slow_work_execute, -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG .desc = fscache_object_slow_work_desc, #endif }; @@ -364,7 +364,7 @@ static void fscache_object_slow_work_execute(struct slow_work *work) /* * describe an object for slow-work debugging */ -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG static void fscache_object_slow_work_desc(struct slow_work *work, struct seq_file *m) { diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index 313e79a14266..9f6c928d4586 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -500,7 +500,7 @@ static void fscache_op_execute(struct slow_work *work) /* * describe an operation for slow-work debugging */ -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG static void fscache_op_desc(struct slow_work *work, struct seq_file *m) { struct fscache_operation *op = @@ -517,7 +517,7 @@ const struct slow_work_ops fscache_op_slow_work_ops = { .get_ref = fscache_op_get_ref, .put_ref = fscache_op_put_ref, .execute = fscache_op_execute, -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG .desc = fscache_op_desc, #endif }; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 7be0c6fbe880..c57db27ac861 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -105,7 +105,7 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG const char *name; /* operation name */ const char *state; /* operation state */ #define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) diff --git a/kernel/slow-work.h b/kernel/slow-work.h index 321f3c59d732..a29ebd1ef41d 100644 --- a/kernel/slow-work.h +++ b/kernel/slow-work.h @@ -43,28 +43,28 @@ extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *); */ static inline void slow_work_set_thread_pid(int id, pid_t pid) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG slow_work_pids[id] = pid; #endif } static inline void slow_work_mark_time(struct slow_work *work) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG work->mark = CURRENT_TIME; #endif } static inline void slow_work_begin_exec(int id, struct slow_work *work) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG slow_work_execs[id] = work; #endif } static inline void slow_work_end_exec(int id, struct slow_work *work) { -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG write_lock(&slow_work_execs_lock); slow_work_execs[id] = NULL; write_unlock(&slow_work_execs_lock); -- cgit v1.2.3 From eed63519e3e74d515d2007ecd895338d0ba2a85c Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Sun, 28 Mar 2010 19:42:56 -0700 Subject: x86: Do not free zero sized per cpu areas This avoids an infinite loop in free_early_partial(). Add a warning to free_early_partial() to catch future problems. -v5: put back start > end back into WARN_ONCE() -v6: use one line for warning, suggested by Linus -v7: more tests -v8: remove the function name as suggested by Johannes WARN_ONCE() will print out that function name. Signed-off-by: Ian Campbell Signed-off-by: Yinghai Lu Tested-by: Konrad Rzeszutek Wilk Tested-by: Joel Becker Tested-by: Stanislaw Gruszka Acked-by: Johannes Weiner Cc: Peter Zijlstra Cc: David Miller Cc: Benjamin Herrenschmidt Cc: Linus Torvalds LKML-Reference: <1269830604-26214-4-git-send-email-yinghai@kernel.org> Signed-off-by: Ingo Molnar --- kernel/early_res.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/early_res.c b/kernel/early_res.c index 3cb2c661bb78..31aa9332ef3f 100644 --- a/kernel/early_res.c +++ b/kernel/early_res.c @@ -333,6 +333,12 @@ void __init free_early_partial(u64 start, u64 end) struct early_res *r; int i; + if (start == end) + return; + + if (WARN_ONCE(start > end, " wrong range [%#llx, %#llx]\n", start, end)) + return; + try_next: i = find_overlapped_early(start, end); if (i >= max_early_res) -- cgit v1.2.3 From 570b8fb505896e007fd3bb07573ba6640e51851d Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 30 Mar 2010 00:04:00 +0100 Subject: CRED: Fix memory leak in error handling Fix a memory leak on an OOM condition in prepare_usermodehelper_creds(). Signed-off-by: Mathieu Desnoyers Signed-off-by: David Howells Signed-off-by: James Morris --- kernel/cred.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index 1ed8ca18790c..1b1129d0cce8 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -364,7 +364,7 @@ struct cred *prepare_usermodehelper_creds(void) new = kmem_cache_alloc(cred_jar, GFP_ATOMIC); if (!new) - return NULL; + goto free_tgcred; kdebug("prepare_usermodehelper_creds() alloc %p", new); @@ -397,6 +397,10 @@ struct cred *prepare_usermodehelper_creds(void) error: put_cred(new); +free_tgcred: +#ifdef CONFIG_KEYS + kfree(tgcred); +#endif return NULL; } -- cgit v1.2.3