diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit.c | 8 | ||||
-rw-r--r-- | kernel/auditfilter.c | 10 | ||||
-rw-r--r-- | kernel/fork.c | 1 | ||||
-rw-r--r-- | kernel/gcov/Kconfig | 2 | ||||
-rw-r--r-- | kernel/perf_event.c | 17 | ||||
-rw-r--r-- | kernel/pid.c | 2 | ||||
-rw-r--r-- | kernel/pm_qos_params.c | 24 | ||||
-rw-r--r-- | kernel/power/Kconfig | 237 | ||||
-rw-r--r-- | kernel/power/hibernate.c | 9 | ||||
-rw-r--r-- | kernel/power/main.c | 3 | ||||
-rw-r--r-- | kernel/power/snapshot.c | 8 | ||||
-rw-r--r-- | kernel/power/suspend.c | 4 | ||||
-rw-r--r-- | kernel/printk.c | 138 | ||||
-rw-r--r-- | kernel/sched.c | 12 | ||||
-rw-r--r-- | kernel/smp.c | 71 | ||||
-rw-r--r-- | kernel/sys.c | 4 | ||||
-rw-r--r-- | kernel/sysctl.c | 5 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 4 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_events_filter.c | 2 | ||||
-rw-r--r-- | kernel/workqueue.c | 6 |
21 files changed, 341 insertions, 228 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index e495624..9395003 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -74,6 +74,8 @@ static int audit_initialized; int audit_enabled; int audit_ever_enabled; +EXPORT_SYMBOL_GPL(audit_enabled); + /* Default state when kernel boots without any parameters. */ static int audit_default; @@ -671,9 +673,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) pid = NETLINK_CREDS(skb)->pid; uid = NETLINK_CREDS(skb)->uid; - loginuid = NETLINK_CB(skb).loginuid; - sessionid = NETLINK_CB(skb).sessionid; - sid = NETLINK_CB(skb).sid; + loginuid = audit_get_loginuid(current); + sessionid = audit_get_sessionid(current); + security_task_getsecid(current, &sid); seq = nlh->nlmsg_seq; data = NLMSG_DATA(nlh); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index add2819..f8277c8 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1238,6 +1238,7 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb, for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; int result = 0; + u32 sid; switch (f->type) { case AUDIT_PID: @@ -1250,19 +1251,22 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb, result = audit_comparator(cb->creds.gid, f->op, f->val); break; case AUDIT_LOGINUID: - result = audit_comparator(cb->loginuid, f->op, f->val); + result = audit_comparator(audit_get_loginuid(current), + f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: - if (f->lsm_rule) - result = security_audit_rule_match(cb->sid, + if (f->lsm_rule) { + security_task_getsecid(current, &sid); + result = security_audit_rule_match(sid, f->type, f->op, f->lsm_rule, NULL); + } break; } diff --git a/kernel/fork.c b/kernel/fork.c index 25e4291..05b92c4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -193,6 +193,7 @@ void __put_task_struct(struct task_struct *tsk) if (!profile_handoff_task(tsk)) free_task(tsk); } +EXPORT_SYMBOL_GPL(__put_task_struct); /* * macro override instead of weak attribute alias, to workaround diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 70a298d..b8cadf7 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -34,7 +34,7 @@ config GCOV_KERNEL config GCOV_PROFILE_ALL bool "Profile entire Kernel" depends on GCOV_KERNEL - depends on S390 || X86 || (PPC && EXPERIMENTAL) || MICROBLAZE + depends on SUPERH || S390 || X86 || (PPC && EXPERIMENTAL) || MICROBLAZE default n ---help--- This options activates profiling for the entire kernel. diff --git a/kernel/perf_event.c b/kernel/perf_event.c index ed253aa..3472bb1 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -5122,7 +5122,7 @@ static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) { if (event->hw.state & PERF_HES_STOPPED) - return 0; + return 1; if (regs) { if (event->attr.exclude_user && user_mode(regs)) @@ -5478,6 +5478,8 @@ static int perf_tp_event_match(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { + if (event->hw.state & PERF_HES_STOPPED) + return 0; /* * All tracepoints are from kernel-space. */ @@ -6720,17 +6722,20 @@ __perf_event_exit_task(struct perf_event *child_event, struct perf_event_context *child_ctx, struct task_struct *child) { - struct perf_event *parent_event; + if (child_event->parent) { + raw_spin_lock_irq(&child_ctx->lock); + perf_group_detach(child_event); + raw_spin_unlock_irq(&child_ctx->lock); + } perf_remove_from_context(child_event); - parent_event = child_event->parent; /* - * It can happen that parent exits first, and has events + * It can happen that the parent exits first, and has events * that are still around due to the child reference. These - * events need to be zapped - but otherwise linger. + * events need to be zapped. */ - if (parent_event) { + if (child_event->parent) { sync_child_event(child_event, child); free_event(child_event); } diff --git a/kernel/pid.c b/kernel/pid.c index 39b65b6..02f2212 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -435,6 +435,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type) rcu_read_unlock(); return pid; } +EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { @@ -446,6 +447,7 @@ struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) rcu_read_unlock(); return result; } +EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index aeaa7f8..0da058b 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -103,11 +103,14 @@ static struct pm_qos_object *pm_qos_array[] = { static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos); +static ssize_t pm_qos_power_read(struct file *filp, char __user *buf, + size_t count, loff_t *f_pos); static int pm_qos_power_open(struct inode *inode, struct file *filp); static int pm_qos_power_release(struct inode *inode, struct file *filp); static const struct file_operations pm_qos_power_fops = { .write = pm_qos_power_write, + .read = pm_qos_power_read, .open = pm_qos_power_open, .release = pm_qos_power_release, .llseek = noop_llseek, @@ -376,6 +379,27 @@ static int pm_qos_power_release(struct inode *inode, struct file *filp) } +static ssize_t pm_qos_power_read(struct file *filp, char __user *buf, + size_t count, loff_t *f_pos) +{ + s32 value; + unsigned long flags; + struct pm_qos_object *o; + struct pm_qos_request_list *pm_qos_req = filp->private_data;; + + if (!pm_qos_req) + return -EINVAL; + if (!pm_qos_request_active(pm_qos_req)) + return -EINVAL; + + o = pm_qos_array[pm_qos_req->pm_qos_class]; + spin_lock_irqsave(&pm_qos_lock, flags); + value = pm_qos_get_value(o); + spin_unlock_irqrestore(&pm_qos_lock, flags); + + return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32)); +} + static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) { diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 2657299..4603f08 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -1,125 +1,12 @@ -config PM - bool "Power Management support" - depends on !IA64_HP_SIM - ---help--- - "Power Management" means that parts of your computer are shut - off or put into a power conserving "sleep" mode if they are not - being used. There are two competing standards for doing this: APM - and ACPI. If you want to use either one, say Y here and then also - to the requisite support below. - - Power Management is most important for battery powered laptop - computers; if you have a laptop, check out the Linux Laptop home - page on the WWW at <http://www.linux-on-laptops.com/> or - Tuxmobil - Linux on Mobile Computers at <http://www.tuxmobil.org/> - and the Battery Powered Linux mini-HOWTO, available from - <http://www.tldp.org/docs.html#howto>. - - Note that, even if you say N here, Linux on the x86 architecture - will issue the hlt instruction if nothing is to be done, thereby - sending the processor to sleep and saving power. - -config PM_DEBUG - bool "Power Management Debug Support" - depends on PM - ---help--- - This option enables various debugging support in the Power Management - code. This is helpful when debugging and reporting PM bugs, like - suspend support. - -config PM_ADVANCED_DEBUG - bool "Extra PM attributes in sysfs for low-level debugging/testing" - depends on PM_DEBUG - default n - ---help--- - Add extra sysfs attributes allowing one to access some Power Management - fields of device objects from user space. If you are not a kernel - developer interested in debugging/testing Power Management, say "no". - -config PM_VERBOSE - bool "Verbose Power Management debugging" - depends on PM_DEBUG - default n - ---help--- - This option enables verbose messages from the Power Management code. - -config CAN_PM_TRACE - def_bool y - depends on PM_DEBUG && PM_SLEEP && EXPERIMENTAL - -config PM_TRACE - bool - help - This enables code to save the last PM event point across - reboot. The architecture needs to support this, x86 for - example does by saving things in the RTC, see below. - - The architecture specific code must provide the extern - functions from <linux/resume-trace.h> as well as the - <asm/resume-trace.h> header with a TRACE_RESUME() macro. - - The way the information is presented is architecture- - dependent, x86 will print the information during a - late_initcall. - -config PM_TRACE_RTC - bool "Suspend/resume event tracing" - depends on CAN_PM_TRACE - depends on X86 - select PM_TRACE - default n - ---help--- - This enables some cheesy code to save the last PM event point in the - RTC across reboots, so that you can debug a machine that just hangs - during suspend (or more commonly, during resume). - - To use this debugging feature you should attempt to suspend the - machine, reboot it and then run - - dmesg -s 1000000 | grep 'hash matches' - - CAUTION: this option will cause your machine's real-time clock to be - set to an invalid time after a resume. - -config PM_SLEEP_SMP - bool - depends on SMP - depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE - depends on PM_SLEEP - select HOTPLUG - select HOTPLUG_CPU - default y - -config PM_SLEEP - bool - depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE - default y - -config PM_SLEEP_ADVANCED_DEBUG - bool - depends on PM_ADVANCED_DEBUG - default n - config SUSPEND bool "Suspend to RAM and standby" - depends on PM && ARCH_SUSPEND_POSSIBLE + depends on ARCH_SUSPEND_POSSIBLE default y ---help--- Allow the system to enter sleep states in which main memory is powered and thus its contents are preserved, such as the suspend-to-RAM state (e.g. the ACPI S3 state). -config PM_TEST_SUSPEND - bool "Test suspend/resume and wakealarm during bootup" - depends on SUSPEND && PM_DEBUG && RTC_CLASS=y - ---help--- - This option will let you suspend your machine during bootup, and - make it wake up a few seconds later using an RTC wakeup alarm. - Enable this with a kernel parameter like "test_suspend=mem". - - You probably want to have your system's RTC driver statically - linked, ensuring that it's available when this test runs. - config SUSPEND_FREEZER bool "Enable freezer for suspend to RAM/standby" \ if ARCH_WANTS_FREEZER_CONTROL || BROKEN @@ -133,7 +20,7 @@ config SUSPEND_FREEZER config HIBERNATION bool "Hibernation (aka 'suspend to disk')" - depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE + depends on SWAP && ARCH_HIBERNATION_POSSIBLE select LZO_COMPRESS select LZO_DECOMPRESS ---help--- @@ -196,6 +83,106 @@ config PM_STD_PARTITION suspended image to. It will simply pick the first available swap device. +config PM_SLEEP + def_bool y + depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE + +config PM_SLEEP_SMP + def_bool y + depends on SMP + depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE + depends on PM_SLEEP + select HOTPLUG + select HOTPLUG_CPU + +config PM_RUNTIME + bool "Run-time PM core functionality" + depends on !IA64_HP_SIM + ---help--- + Enable functionality allowing I/O devices to be put into energy-saving + (low power) states at run time (or autosuspended) after a specified + period of inactivity and woken up in response to a hardware-generated + wake-up event or a driver's request. + + Hardware support is generally required for this functionality to work + and the bus type drivers of the buses the devices are on are + responsible for the actual handling of the autosuspend requests and + wake-up events. + +config PM + def_bool y + depends on PM_SLEEP || PM_RUNTIME + +config PM_DEBUG + bool "Power Management Debug Support" + depends on PM + ---help--- + This option enables various debugging support in the Power Management + code. This is helpful when debugging and reporting PM bugs, like + suspend support. + +config PM_VERBOSE + bool "Verbose Power Management debugging" + depends on PM_DEBUG + ---help--- + This option enables verbose messages from the Power Management code. + +config PM_ADVANCED_DEBUG + bool "Extra PM attributes in sysfs for low-level debugging/testing" + depends on PM_DEBUG + ---help--- + Add extra sysfs attributes allowing one to access some Power Management + fields of device objects from user space. If you are not a kernel + developer interested in debugging/testing Power Management, say "no". + +config PM_TEST_SUSPEND + bool "Test suspend/resume and wakealarm during bootup" + depends on SUSPEND && PM_DEBUG && RTC_CLASS=y + ---help--- + This option will let you suspend your machine during bootup, and + make it wake up a few seconds later using an RTC wakeup alarm. + Enable this with a kernel parameter like "test_suspend=mem". + + You probably want to have your system's RTC driver statically + linked, ensuring that it's available when this test runs. + +config CAN_PM_TRACE + def_bool y + depends on PM_DEBUG && PM_SLEEP + +config PM_TRACE + bool + help + This enables code to save the last PM event point across + reboot. The architecture needs to support this, x86 for + example does by saving things in the RTC, see below. + + The architecture specific code must provide the extern + functions from <linux/resume-trace.h> as well as the + <asm/resume-trace.h> header with a TRACE_RESUME() macro. + + The way the information is presented is architecture- + dependent, x86 will print the information during a + late_initcall. + +config PM_TRACE_RTC + bool "Suspend/resume event tracing" + depends on CAN_PM_TRACE + depends on X86 + select PM_TRACE + ---help--- + This enables some cheesy code to save the last PM event point in the + RTC across reboots, so that you can debug a machine that just hangs + during suspend (or more commonly, during resume). + + To use this debugging feature you should attempt to suspend the + machine, reboot it and then run + + dmesg -s 1000000 | grep 'hash matches' + + CAUTION: this option will cause your machine's real-time clock to be + set to an invalid time after a resume. + config APM_EMULATION tristate "Advanced Power Management Emulation" depends on PM && SYS_SUPPORTS_APM_EMULATION @@ -222,31 +209,11 @@ config APM_EMULATION anything, try disabling/enabling this option (or disabling/enabling APM in your BIOS). -config PM_RUNTIME - bool "Run-time PM core functionality" - depends on PM - ---help--- - Enable functionality allowing I/O devices to be put into energy-saving - (low power) states at run time (or autosuspended) after a specified - period of inactivity and woken up in response to a hardware-generated - wake-up event or a driver's request. - - Hardware support is generally required for this functionality to work - and the bus type drivers of the buses the devices are on are - responsible for the actual handling of the autosuspend requests and - wake-up events. - -config PM_OPS - bool - depends on PM_SLEEP || PM_RUNTIME - default y - config ARCH_HAS_OPP bool config PM_OPP bool "Operating Performance Point (OPP) Layer library" - depends on PM depends on ARCH_HAS_OPP ---help--- SOCs have a standard set of tuples consisting of frequency and diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 1832bd2..aeabd26 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -23,6 +23,7 @@ #include <linux/cpu.h> #include <linux/freezer.h> #include <linux/gfp.h> +#include <linux/syscore_ops.h> #include <scsi/scsi_scan.h> #include <asm/suspend.h> @@ -272,6 +273,8 @@ static int create_image(int platform_mode) local_irq_disable(); error = sysdev_suspend(PMSG_FREEZE); + if (!error) + error = syscore_suspend(); if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " "aborting hibernation\n"); @@ -295,6 +298,7 @@ static int create_image(int platform_mode) } Power_up: + syscore_resume(); sysdev_resume(); /* NOTE: dpm_resume_noirq() is just a resume() for devices * that suspended with irqs off ... no overall powerup. @@ -403,6 +407,8 @@ static int resume_target_kernel(bool platform_mode) local_irq_disable(); error = sysdev_suspend(PMSG_QUIESCE); + if (!error) + error = syscore_suspend(); if (error) goto Enable_irqs; @@ -429,6 +435,7 @@ static int resume_target_kernel(bool platform_mode) restore_processor_state(); touch_softlockup_watchdog(); + syscore_resume(); sysdev_resume(); Enable_irqs: @@ -516,6 +523,7 @@ int hibernation_platform_enter(void) local_irq_disable(); sysdev_suspend(PMSG_HIBERNATE); + syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; goto Power_up; @@ -526,6 +534,7 @@ int hibernation_platform_enter(void) while (1); Power_up: + syscore_resume(); sysdev_resume(); local_irq_enable(); enable_nonboot_cpus(); diff --git a/kernel/power/main.c b/kernel/power/main.c index 7018530..8eaba5f 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -17,9 +17,6 @@ DEFINE_MUTEX(pm_mutex); -unsigned int pm_flags; -EXPORT_SYMBOL(pm_flags); - #ifdef CONFIG_PM_SLEEP /* Routines for PM-transition notifications */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 64db648..ca0aacc 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -42,15 +42,15 @@ static void swsusp_unset_page_forbidden(struct page *); /* * Preferred image size in bytes (tunable via /sys/power/image_size). - * When it is set to N, swsusp will do its best to ensure the image - * size will not exceed N bytes, but if that is impossible, it will - * try to create the smallest image possible. + * When it is set to N, the image creating code will do its best to + * ensure the image size will not exceed N bytes, but if that is + * impossible, it will try to create the smallest image possible. */ unsigned long image_size; void __init hibernate_image_size_init(void) { - image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE; + image_size = (totalram_pages / 3) * PAGE_SIZE; } /* List of PBEs needed for restoring the pages that were allocated before diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index de6f86b..2814c32 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -22,6 +22,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/suspend.h> +#include <linux/syscore_ops.h> #include <trace/events/power.h> #include "power.h" @@ -163,11 +164,14 @@ static int suspend_enter(suspend_state_t state) BUG_ON(!irqs_disabled()); error = sysdev_suspend(PMSG_SUSPEND); + if (!error) + error = syscore_suspend(); if (!error) { if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) { error = suspend_ops->enter(state); events_check_enabled = false; } + syscore_resume(); sysdev_resume(); } diff --git a/kernel/printk.c b/kernel/printk.c index 3623152..33284ad 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -515,6 +515,71 @@ static void _call_console_drivers(unsigned start, } /* + * Parse the syslog header <[0-9]*>. The decimal value represents 32bit, the + * lower 3 bit are the log level, the rest are the log facility. In case + * userspace passes usual userspace syslog messages to /dev/kmsg or + * /dev/ttyprintk, the log prefix might contain the facility. Printk needs + * to extract the correct log level for in-kernel processing, and not mangle + * the original value. + * + * If a prefix is found, the length of the prefix is returned. If 'level' is + * passed, it will be filled in with the log level without a possible facility + * value. If 'special' is passed, the special printk prefix chars are accepted + * and returned. If no valid header is found, 0 is returned and the passed + * variables are not touched. + */ +static size_t log_prefix(const char *p, unsigned int *level, char *special) +{ + unsigned int lev = 0; + char sp = '\0'; + size_t len; + + if (p[0] != '<' || !p[1]) + return 0; + if (p[2] == '>') { + /* usual single digit level number or special char */ + switch (p[1]) { + case '0' ... '7': + lev = p[1] - '0'; + break; + case 'c': /* KERN_CONT */ + case 'd': /* KERN_DEFAULT */ + sp = p[1]; + break; + default: + return 0; + } + len = 3; + } else { + /* multi digit including the level and facility number */ + char *endp = NULL; + + if (p[1] < '0' && p[1] > '9') + return 0; + + lev = (simple_strtoul(&p[1], &endp, 10) & 7); + if (endp == NULL || endp[0] != '>') + return 0; + len = (endp + 1) - p; + } + + /* do not accept special char if not asked for */ + if (sp && !special) + return 0; + + if (special) { + *special = sp; + /* return special char, do not touch level */ + if (sp) + return len; + } + + if (level) + *level = lev; + return len; +} + +/* * Call the console drivers, asking them to write out * log_buf[start] to log_buf[end - 1]. * The console_lock must be held. @@ -529,13 +594,9 @@ static void call_console_drivers(unsigned start, unsigned end) cur_index = start; start_print = start; while (cur_index != end) { - if (msg_level < 0 && ((end - cur_index) > 2) && - LOG_BUF(cur_index + 0) == '<' && - LOG_BUF(cur_index + 1) >= '0' && - LOG_BUF(cur_index + 1) <= '7' && - LOG_BUF(cur_index + 2) == '>') { - msg_level = LOG_BUF(cur_index + 1) - '0'; - cur_index += 3; + if (msg_level < 0 && ((end - cur_index) > 2)) { + /* strip log prefix */ + cur_index += log_prefix(&LOG_BUF(cur_index), &msg_level, NULL); start_print = cur_index; } while (cur_index != end) { @@ -733,6 +794,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) unsigned long flags; int this_cpu; char *p; + size_t plen; + char special; boot_delay_msec(); printk_delay(); @@ -773,45 +836,52 @@ asmlinkage int vprintk(const char *fmt, va_list args) printed_len += vscnprintf(printk_buf + printed_len, sizeof(printk_buf) - printed_len, fmt, args); - p = printk_buf; - /* Do we have a loglevel in the string? */ - if (p[0] == '<') { - unsigned char c = p[1]; - if (c && p[2] == '>') { - switch (c) { - case '0' ... '7': /* loglevel */ - current_log_level = c - '0'; - /* Fallthrough - make sure we're on a new line */ - case 'd': /* KERN_DEFAULT */ - if (!new_text_line) { - emit_log_char('\n'); - new_text_line = 1; - } - /* Fallthrough - skip the loglevel */ - case 'c': /* KERN_CONT */ - p += 3; - break; + /* Read log level and handle special printk prefix */ + plen = log_prefix(p, ¤t_log_level, &special); + if (plen) { + p += plen; + + switch (special) { + case 'c': /* Strip <c> KERN_CONT, continue line */ + plen = 0; + break; + case 'd': /* Strip <d> KERN_DEFAULT, start new line */ + plen = 0; + default: + if (!new_text_line) { + emit_log_char('\n'); + new_text_line = 1; } } } /* - * Copy the output into log_buf. If the caller didn't provide - * appropriate log level tags, we insert them here + * Copy the output into log_buf. If the caller didn't provide + * the appropriate log prefix, we insert them here */ - for ( ; *p; p++) { + for (; *p; p++) { if (new_text_line) { - /* Always output the token */ - emit_log_char('<'); - emit_log_char(current_log_level + '0'); - emit_log_char('>'); - printed_len += 3; new_text_line = 0; + if (plen) { + /* Copy original log prefix */ + int i; + + for (i = 0; i < plen; i++) + emit_log_char(printk_buf[i]); + printed_len += plen; + } else { + /* Add log prefix */ + emit_log_char('<'); + emit_log_char(current_log_level + '0'); + emit_log_char('>'); + printed_len += 3; + } + if (printk_time) { - /* Follow the token with the time */ + /* Add the current time stamp */ char tbuf[50], *tp; unsigned tlen; unsigned long long t; diff --git a/kernel/sched.c b/kernel/sched.c index c8e40b7..a172494 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -32,7 +32,6 @@ #include <linux/init.h> #include <linux/uaccess.h> #include <linux/highmem.h> -#include <linux/smp_lock.h> #include <asm/mmu_context.h> #include <linux/interrupt.h> #include <linux/capability.h> @@ -661,10 +660,9 @@ static void update_rq_clock(struct rq *rq) #endif /** - * runqueue_is_locked + * runqueue_is_locked - Returns true if the current cpu runqueue is locked * @cpu: the processor in question. * - * Returns true if the current cpu runqueue is locked. * This interface allows printk to be called with the runqueue lock * held and know whether or not it is OK to wake up the klogd. */ @@ -4087,9 +4085,6 @@ need_resched: rcu_note_context_switch(cpu); prev = rq->curr; - release_kernel_lock(prev); -need_resched_nonpreemptible: - schedule_debug(prev); if (sched_feat(HRTICK)) @@ -4149,9 +4144,6 @@ need_resched_nonpreemptible: post_schedule(rq); - if (unlikely(reacquire_kernel_lock(prev))) - goto need_resched_nonpreemptible; - preempt_enable_no_resched(); if (need_resched()) goto need_resched; @@ -8278,7 +8270,7 @@ static inline int preempt_count_equals(int preempt_offset) { int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); - return (nested == PREEMPT_INATOMIC_BASE + preempt_offset); + return (nested == preempt_offset); } void __might_sleep(const char *file, int line, int preempt_offset) diff --git a/kernel/smp.c b/kernel/smp.c index 9910744..7cbd0f2 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -194,7 +194,7 @@ void generic_smp_call_function_interrupt(void) */ list_for_each_entry_rcu(data, &call_function.queue, csd.list) { int refs; - void (*func) (void *info); + smp_call_func_t func; /* * Since we walk the list without any locks, we might @@ -214,17 +214,17 @@ void generic_smp_call_function_interrupt(void) if (atomic_read(&data->refs) == 0) continue; - func = data->csd.func; /* for later warn */ - data->csd.func(data->csd.info); + func = data->csd.func; /* save for later warn */ + func(data->csd.info); /* - * If the cpu mask is not still set then it enabled interrupts, - * we took another smp interrupt, and executed the function - * twice on this cpu. In theory that copy decremented refs. + * If the cpu mask is not still set then func enabled + * interrupts (BUG), and this cpu took another smp call + * function interrupt and executed func(info) twice + * on this cpu. That nested execution decremented refs. */ if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) { - WARN(1, "%pS enabled interrupts and double executed\n", - func); + WARN(1, "%pf enabled interrupts and double executed\n", func); continue; } @@ -450,7 +450,7 @@ void smp_call_function_many(const struct cpumask *mask, { struct call_function_data *data; unsigned long flags; - int cpu, next_cpu, this_cpu = smp_processor_id(); + int refs, cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. @@ -461,7 +461,7 @@ void smp_call_function_many(const struct cpumask *mask, WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress && !early_boot_irqs_disabled); - /* So, what's a CPU they want? Ignoring this one. */ + /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); @@ -483,22 +483,49 @@ void smp_call_function_many(const struct cpumask *mask, data = &__get_cpu_var(cfd_data); csd_lock(&data->csd); + + /* This BUG_ON verifies our reuse assertions and can be removed */ BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask)); + /* + * The global call function queue list add and delete are protected + * by a lock, but the list is traversed without any lock, relying + * on the rcu list add and delete to allow safe concurrent traversal. + * We reuse the call function data without waiting for any grace + * period after some other cpu removes it from the global queue. + * This means a cpu might find our data block as it is being + * filled out. + * + * We hold off the interrupt handler on the other cpu by + * ordering our writes to the cpu mask vs our setting of the + * refs counter. We assert only the cpu owning the data block + * will set a bit in cpumask, and each bit will only be cleared + * by the subject cpu. Each cpu must first find its bit is + * set and then check that refs is set indicating the element is + * ready to be processed, otherwise it must skip the entry. + * + * On the previous iteration refs was set to 0 by another cpu. + * To avoid the use of transitivity, set the counter to 0 here + * so the wmb will pair with the rmb in the interrupt handler. + */ + atomic_set(&data->refs, 0); /* convert 3rd to 1st party write */ + data->csd.func = func; data->csd.info = info; - cpumask_and(data->cpumask, mask, cpu_online_mask); - cpumask_clear_cpu(this_cpu, data->cpumask); - /* - * To ensure the interrupt handler gets an complete view - * we order the cpumask and refs writes and order the read - * of them in the interrupt handler. In addition we may - * only clear our own cpu bit from the mask. - */ + /* Ensure 0 refs is visible before mask. Also orders func and info */ smp_wmb(); - atomic_set(&data->refs, cpumask_weight(data->cpumask)); + /* We rely on the "and" being processed before the store */ + cpumask_and(data->cpumask, mask, cpu_online_mask); + cpumask_clear_cpu(this_cpu, data->cpumask); + refs = cpumask_weight(data->cpumask); + + /* Some callers race with other cpus changing the passed mask */ + if (unlikely(!refs)) { + csd_unlock(&data->csd); + return; + } raw_spin_lock_irqsave(&call_function.lock, flags); /* @@ -507,6 +534,12 @@ void smp_call_function_many(const struct cpumask *mask, * will not miss any other list entries: */ list_add_rcu(&data->csd.list, &call_function.queue); + /* + * We rely on the wmb() in list_add_rcu to complete our writes + * to the cpumask before this write to refs, which indicates + * data is on the list and is ready to be processed. + */ + atomic_set(&data->refs, refs); raw_spin_unlock_irqrestore(&call_function.lock, flags); /* diff --git a/kernel/sys.c b/kernel/sys.c index 18da702..1ad48b3 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -37,6 +37,7 @@ #include <linux/ptrace.h> #include <linux/fs_struct.h> #include <linux/gfp.h> +#include <linux/syscore_ops.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -298,6 +299,7 @@ void kernel_restart_prepare(char *cmd) system_state = SYSTEM_RESTART; device_shutdown(); sysdev_shutdown(); + syscore_shutdown(); } /** @@ -336,6 +338,7 @@ void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); sysdev_shutdown(); + syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); machine_halt(); @@ -355,6 +358,7 @@ void kernel_power_off(void) pm_power_off_prepare(); disable_nonboot_cpus(); sysdev_shutdown(); + syscore_shutdown(); printk(KERN_EMERG "Power down.\n"); kmsg_dump(KMSG_DUMP_POWEROFF); machine_power_off(); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 51054fe..40245d6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1683,13 +1683,8 @@ static int test_perm(int mode, int op) int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op) { - int error; int mode; - error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC)); - if (error) - return error; - if (root->permissions) mode = root->permissions(root, current->nsproxy, table); else diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 14674dc..61d7d59f 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -275,7 +275,7 @@ config PROFILE_ANNOTATED_BRANCHES This tracer profiles all the the likely and unlikely macros in the kernel. It will display the results in: - /sys/kernel/debug/tracing/profile_annotated_branch + /sys/kernel/debug/tracing/trace_stat/branch_annotated Note: this will add a significant overhead; only turn this on if you need to profile the system's use of these macros. @@ -288,7 +288,7 @@ config PROFILE_ALL_BRANCHES taken in the kernel is recorded whether it hit or miss. The results will be displayed in: - /sys/kernel/debug/tracing/profile_branch + /sys/kernel/debug/tracing/trace_stat/branch_all This option also enables the likely/unlikely profiler. diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index db7b439..d9c8bca 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -668,7 +668,7 @@ static struct list_head *rb_list_head(struct list_head *list) * the reader page). But if the next page is a header page, * its flags will be non zero. */ -static int inline +static inline int rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *page, struct list_head *list) { diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 3249b4f..8008ddc 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -391,8 +391,8 @@ static int process_ops(struct filter_pred *preds, struct filter_pred *op, void *rec) { struct filter_pred *pred; + int match = 0; int type; - int match; int i; /* diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b5fe4c0..5ca7ce9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -251,10 +251,12 @@ struct workqueue_struct *system_wq __read_mostly; struct workqueue_struct *system_long_wq __read_mostly; struct workqueue_struct *system_nrt_wq __read_mostly; struct workqueue_struct *system_unbound_wq __read_mostly; +struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_wq); EXPORT_SYMBOL_GPL(system_long_wq); EXPORT_SYMBOL_GPL(system_nrt_wq); EXPORT_SYMBOL_GPL(system_unbound_wq); +EXPORT_SYMBOL_GPL(system_freezable_wq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> @@ -3781,8 +3783,10 @@ static int __init init_workqueues(void) system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); + system_freezable_wq = alloc_workqueue("events_freezable", + WQ_FREEZABLE, 0); BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq || - !system_unbound_wq); + !system_unbound_wq || !system_freezable_wq); return 0; } early_initcall(init_workqueues); |