diff options
Diffstat (limited to 'drivers/base/power')
| -rw-r--r-- | drivers/base/power/Makefile | 1 | ||||
| -rw-r--r-- | drivers/base/power/main.c | 1 | ||||
| -rw-r--r-- | drivers/base/power/resume.c | 45 | ||||
| -rw-r--r-- | drivers/base/power/shutdown.c | 1 | ||||
| -rw-r--r-- | drivers/base/power/suspend.c | 99 | ||||
| -rw-r--r-- | drivers/base/power/sysfs.c | 35 | ||||
| -rw-r--r-- | drivers/base/power/trace.c | 228 |
7 files changed, 352 insertions, 58 deletions
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile index ceeeba2c56c7..91f230939c1e 100644 --- a/drivers/base/power/Makefile +++ b/drivers/base/power/Makefile @@ -1,5 +1,6 @@ obj-y := shutdown.o obj-$(CONFIG_PM) += main.o suspend.o resume.o runtime.o sysfs.o +obj-$(CONFIG_PM_TRACE) += trace.o ifeq ($(CONFIG_DEBUG_DRIVER),y) EXTRA_CFLAGS += -DDEBUG diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 0d2e101e4f15..fdfa3d0cf6af 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -19,7 +19,6 @@ * ancestral dependencies that the subsystem list maintains. */ -#include <linux/config.h> #include <linux/device.h> #include "power.h" diff --git a/drivers/base/power/resume.c b/drivers/base/power/resume.c index 317edbf0feca..020be36705a6 100644 --- a/drivers/base/power/resume.c +++ b/drivers/base/power/resume.c @@ -9,6 +9,7 @@ */ #include <linux/device.h> +#include <linux/resume-trace.h> #include "../base.h" #include "power.h" @@ -23,6 +24,8 @@ int resume_device(struct device * dev) { int error = 0; + TRACE_DEVICE(dev); + TRACE_RESUME(0); down(&dev->sem); if (dev->power.pm_parent && dev->power.pm_parent->power.power_state.event) { @@ -35,12 +38,35 @@ int resume_device(struct device * dev) dev_dbg(dev,"resuming\n"); error = dev->bus->resume(dev); } + if (dev->class && dev->class->resume) { + dev_dbg(dev,"class resume\n"); + error = dev->class->resume(dev); + } up(&dev->sem); + TRACE_RESUME(error); return error; } +static int resume_device_early(struct device * dev) +{ + int error = 0; + TRACE_DEVICE(dev); + TRACE_RESUME(0); + if (dev->bus && dev->bus->resume_early) { + dev_dbg(dev,"EARLY resume\n"); + error = dev->bus->resume_early(dev); + } + TRACE_RESUME(error); + return error; +} + +/* + * Resume the devices that have either not gone through + * the late suspend, or that did go through it but also + * went through the early resume + */ void dpm_resume(void) { down(&dpm_list_sem); @@ -49,8 +75,7 @@ void dpm_resume(void) struct device * dev = to_device(entry); get_device(dev); - list_del_init(entry); - list_add_tail(entry, &dpm_active); + list_move_tail(entry, &dpm_active); up(&dpm_list_sem); if (!dev->power.prev_state.event) @@ -71,6 +96,7 @@ void dpm_resume(void) void device_resume(void) { + might_sleep(); down(&dpm_sem); dpm_resume(); up(&dpm_sem); @@ -80,12 +106,12 @@ EXPORT_SYMBOL_GPL(device_resume); /** - * device_power_up_irq - Power on some devices. + * dpm_power_up - Power on some devices. * * Walk the dpm_off_irq list and power each device up. This * is used for devices that required they be powered down with - * interrupts disabled. As devices are powered on, they are moved to - * the dpm_suspended list. + * interrupts disabled. As devices are powered on, they are moved + * to the dpm_active list. * * Interrupts must be disabled when calling this. */ @@ -96,17 +122,14 @@ void dpm_power_up(void) struct list_head * entry = dpm_off_irq.next; struct device * dev = to_device(entry); - get_device(dev); - list_del_init(entry); - list_add_tail(entry, &dpm_active); - resume_device(dev); - put_device(dev); + list_move_tail(entry, &dpm_off); + resume_device_early(dev); } } /** - * device_pm_power_up - Turn on all devices that need special attention. + * device_power_up - Turn on all devices that need special attention. * * Power on system devices then devices that required we shut them down * with interrupts disabled. diff --git a/drivers/base/power/shutdown.c b/drivers/base/power/shutdown.c index 8826a5b6673e..3483ae4d57f5 100644 --- a/drivers/base/power/shutdown.c +++ b/drivers/base/power/shutdown.c @@ -8,7 +8,6 @@ * */ -#include <linux/config.h> #include <linux/device.h> #include <asm/semaphore.h> diff --git a/drivers/base/power/suspend.c b/drivers/base/power/suspend.c index 1a1fe43a3057..ece136bf97e3 100644 --- a/drivers/base/power/suspend.c +++ b/drivers/base/power/suspend.c @@ -34,6 +34,7 @@ static inline char *suspend_verb(u32 event) switch (event) { case PM_EVENT_SUSPEND: return "suspend"; case PM_EVENT_FREEZE: return "freeze"; + case PM_EVENT_PRETHAW: return "prethaw"; default: return "(unknown suspend event)"; } } @@ -65,7 +66,19 @@ int suspend_device(struct device * dev, pm_message_t state) dev->power.prev_state = dev->power.power_state; - if (dev->bus && dev->bus->suspend && !dev->power.power_state.event) { + if (dev->class && dev->class->suspend && !dev->power.power_state.event) { + dev_dbg(dev, "class %s%s\n", + suspend_verb(state.event), + ((state.event == PM_EVENT_SUSPEND) + && device_may_wakeup(dev)) + ? ", may wakeup" + : "" + ); + error = dev->class->suspend(dev, state); + suspend_report_result(dev->class->suspend, error); + } + + if (!error && dev->bus && dev->bus->suspend && !dev->power.power_state.event) { dev_dbg(dev, "%s%s\n", suspend_verb(state.event), ((state.event == PM_EVENT_SUSPEND) @@ -81,15 +94,42 @@ int suspend_device(struct device * dev, pm_message_t state) } +/* + * This is called with interrupts off, only a single CPU + * running. We can't do down() on a semaphore (and we don't + * need the protection) + */ +static int suspend_device_late(struct device *dev, pm_message_t state) +{ + int error = 0; + + if (dev->bus && dev->bus->suspend_late && !dev->power.power_state.event) { + dev_dbg(dev, "LATE %s%s\n", + suspend_verb(state.event), + ((state.event == PM_EVENT_SUSPEND) + && device_may_wakeup(dev)) + ? ", may wakeup" + : "" + ); + error = dev->bus->suspend_late(dev, state); + suspend_report_result(dev->bus->suspend_late, error); + } + return error; +} + /** * device_suspend - Save state and stop all devices in system. * @state: Power state to put each device in. * * Walk the dpm_active list, call ->suspend() for each device, and move - * it to dpm_off. - * Check the return value for each. If it returns 0, then we move the - * the device to the dpm_off list. If it returns -EAGAIN, we move it to - * the dpm_off_irq list. If we get a different error, try and back out. + * it to the dpm_off list. + * + * (For historical reasons, if it returns -EAGAIN, that used to mean + * that the device would be called again with interrupts disabled. + * These days, we use the "suspend_late()" callback for that, so we + * print a warning and consider it an error). + * + * If we get a different error, try and back out. * * If we hit a failure with any of the devices, call device_resume() * above to bring the suspended devices back to life. @@ -100,6 +140,7 @@ int device_suspend(pm_message_t state) { int error = 0; + might_sleep(); down(&dpm_sem); down(&dpm_list_sem); while (!list_empty(&dpm_active) && error == 0) { @@ -115,42 +156,27 @@ int device_suspend(pm_message_t state) /* Check if the device got removed */ if (!list_empty(&dev->power.entry)) { - /* Move it to the dpm_off or dpm_off_irq list */ - if (!error) { - list_del(&dev->power.entry); - list_add(&dev->power.entry, &dpm_off); - } else if (error == -EAGAIN) { - list_del(&dev->power.entry); - list_add(&dev->power.entry, &dpm_off_irq); - error = 0; - } + /* Move it to the dpm_off list */ + if (!error) + list_move(&dev->power.entry, &dpm_off); } if (error) printk(KERN_ERR "Could not suspend device %s: " - "error %d\n", kobject_name(&dev->kobj), error); + "error %d%s\n", + kobject_name(&dev->kobj), error, + error == -EAGAIN ? " (please convert to suspend_late)" : ""); put_device(dev); } up(&dpm_list_sem); - if (error) { - /* we failed... before resuming, bring back devices from - * dpm_off_irq list back to main dpm_off list, we do want - * to call resume() on them, in case they partially suspended - * despite returning -EAGAIN - */ - while (!list_empty(&dpm_off_irq)) { - struct list_head * entry = dpm_off_irq.next; - list_del(entry); - list_add(entry, &dpm_off); - } + if (error) dpm_resume(); - } + up(&dpm_sem); return error; } EXPORT_SYMBOL_GPL(device_suspend); - /** * device_power_down - Shut down special devices. * @state: Power state to enter. @@ -165,14 +191,17 @@ int device_power_down(pm_message_t state) int error = 0; struct device * dev; - list_for_each_entry_reverse(dev, &dpm_off_irq, power.entry) { - if ((error = suspend_device(dev, state))) - break; + while (!list_empty(&dpm_off)) { + struct list_head * entry = dpm_off.prev; + + dev = to_device(entry); + error = suspend_device_late(dev, state); + if (error) + goto Error; + list_move(&dev->power.entry, &dpm_off_irq); } - if (error) - goto Error; - if ((error = sysdev_suspend(state))) - goto Error; + + error = sysdev_suspend(state); Done: return error; Error: diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 40d7242a07c1..2d47517dbe32 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -7,22 +7,29 @@ #include "power.h" +#ifdef CONFIG_PM_SYSFS_DEPRECATED + /** * state - Control current power state of device * * show() returns the current power state of the device. '0' indicates - * the device is on. Other values (1-3) indicate the device is in a low + * the device is on. Other values (2) indicate the device is in some low * power state. * - * store() sets the current power state, which is an integer value - * between 0-3. If the device is on ('0'), and the value written is - * greater than 0, then the device is placed directly into the low-power - * state (via its driver's ->suspend() method). - * If the device is currently in a low-power state, and the value is 0, - * the device is powered back on (via the ->resume() method). - * If the device is in a low-power state, and a different low-power state - * is requested, the device is first resumed, then suspended into the new - * low-power state. + * store() sets the current power state, which is an integer valued + * 0, 2, or 3. Devices with bus.suspend_late(), or bus.resume_early() + * methods fail this operation; those methods couldn't be called. + * Otherwise, + * + * - If the recorded dev->power.power_state.event matches the + * target value, nothing is done. + * - If the recorded event code is nonzero, the device is reactivated + * by calling bus.resume() and/or class.resume(). + * - If the target value is nonzero, the device is suspended by + * calling class.suspend() and/or bus.suspend() with event code + * PM_EVENT_SUSPEND. + * + * This mechanism is DEPRECATED and should only be used for testing. */ static ssize_t state_show(struct device * dev, struct device_attribute *attr, char * buf) @@ -38,6 +45,10 @@ static ssize_t state_store(struct device * dev, struct device_attribute *attr, c pm_message_t state; int error = -EINVAL; + /* disallow incomplete suspend sequences */ + if (dev->bus && (dev->bus->suspend_late || dev->bus->resume_early)) + return error; + state.event = PM_EVENT_SUSPEND; /* Older apps expected to write "3" here - confused with PCI D3 */ if ((n == 1) && !strcmp(buf, "3")) @@ -57,6 +68,8 @@ static ssize_t state_store(struct device * dev, struct device_attribute *attr, c static DEVICE_ATTR(state, 0644, state_show, state_store); +#endif /* CONFIG_PM_SYSFS_DEPRECATED */ + /* * wakeup - Report/change current wakeup option for device * @@ -130,7 +143,9 @@ static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store); static struct attribute * power_attrs[] = { +#ifdef CONFIG_PM_SYSFS_DEPRECATED &dev_attr_state.attr, +#endif &dev_attr_wakeup.attr, NULL, }; diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c new file mode 100644 index 000000000000..a9ab30fefffc --- /dev/null +++ b/drivers/base/power/trace.c @@ -0,0 +1,228 @@ +/* + * drivers/base/power/trace.c + * + * Copyright (C) 2006 Linus Torvalds + * + * Trace facility for suspend/resume problems, when none of the + * devices may be working. + */ + +#include <linux/resume-trace.h> +#include <linux/rtc.h> + +#include <asm/rtc.h> + +#include "power.h" + +/* + * Horrid, horrid, horrid. + * + * It turns out that the _only_ piece of hardware that actually + * keeps its value across a hard boot (and, more importantly, the + * POST init sequence) is literally the realtime clock. + * + * Never mind that an RTC chip has 114 bytes (and often a whole + * other bank of an additional 128 bytes) of nice SRAM that is + * _designed_ to keep data - the POST will clear it. So we literally + * can just use the few bytes of actual time data, which means that + * we're really limited. + * + * It means, for example, that we can't use the seconds at all + * (since the time between the hang and the boot might be more + * than a minute), and we'd better not depend on the low bits of + * the minutes either. + * + * There are the wday fields etc, but I wouldn't guarantee those + * are dependable either. And if the date isn't valid, either the + * hw or POST will do strange things. + * + * So we're left with: + * - year: 0-99 + * - month: 0-11 + * - day-of-month: 1-28 + * - hour: 0-23 + * - min: (0-30)*2 + * + * Giving us a total range of 0-16128000 (0xf61800), ie less + * than 24 bits of actual data we can save across reboots. + * + * And if your box can't boot in less than three minutes, + * you're screwed. + * + * Now, almost 24 bits of data is pitifully small, so we need + * to be pretty dense if we want to use it for anything nice. + * What we do is that instead of saving off nice readable info, + * we save off _hashes_ of information that we can hopefully + * regenerate after the reboot. + * + * In particular, this means that we might be unlucky, and hit + * a case where we have a hash collision, and we end up not + * being able to tell for certain exactly which case happened. + * But that's hopefully unlikely. + * + * What we do is to take the bits we can fit, and split them + * into three parts (16*997*1009 = 16095568), and use the values + * for: + * - 0-15: user-settable + * - 0-996: file + line number + * - 0-1008: device + */ +#define USERHASH (16) +#define FILEHASH (997) +#define DEVHASH (1009) + +#define DEVSEED (7919) + +static unsigned int dev_hash_value; + +static int set_magic_time(unsigned int user, unsigned int file, unsigned int device) +{ + unsigned int n = user + USERHASH*(file + FILEHASH*device); + + // June 7th, 2006 + static struct rtc_time time = { + .tm_sec = 0, + .tm_min = 0, + .tm_hour = 0, + .tm_mday = 7, + .tm_mon = 5, // June - counting from zero + .tm_year = 106, + .tm_wday = 3, + .tm_yday = 160, + .tm_isdst = 1 + }; + + time.tm_year = (n % 100); + n /= 100; + time.tm_mon = (n % 12); + n /= 12; + time.tm_mday = (n % 28) + 1; + n /= 28; + time.tm_hour = (n % 24); + n /= 24; + time.tm_min = (n % 20) * 3; + n /= 20; + set_rtc_time(&time); + return n ? -1 : 0; +} + +static unsigned int read_magic_time(void) +{ + struct rtc_time time; + unsigned int val; + + get_rtc_time(&time); + printk("Time: %2d:%02d:%02d Date: %02d/%02d/%02d\n", + time.tm_hour, time.tm_min, time.tm_sec, + time.tm_mon, time.tm_mday, time.tm_year); + val = time.tm_year; /* 100 years */ + if (val > 100) + val -= 100; + val += time.tm_mon * 100; /* 12 months */ + val += (time.tm_mday-1) * 100 * 12; /* 28 month-days */ + val += time.tm_hour * 100 * 12 * 28; /* 24 hours */ + val += (time.tm_min / 3) * 100 * 12 * 28 * 24; /* 20 3-minute intervals */ + return val; +} + +/* + * This is just the sdbm hash function with a user-supplied + * seed and final size parameter. + */ +static unsigned int hash_string(unsigned int seed, const char *data, unsigned int mod) +{ + unsigned char c; + while ((c = *data++) != 0) { + seed = (seed << 16) + (seed << 6) - seed + c; + } + return seed % mod; +} + +void set_trace_device(struct device *dev) +{ + dev_hash_value = hash_string(DEVSEED, dev->bus_id, DEVHASH); +} + +/* + * We could just take the "tracedata" index into the .tracedata + * section instead. Generating a hash of the data gives us a + * chance to work across kernel versions, and perhaps more + * importantly it also gives us valid/invalid check (ie we will + * likely not give totally bogus reports - if the hash matches, + * it's not any guarantee, but it's a high _likelihood_ that + * the match is valid). + */ +void generate_resume_trace(void *tracedata, unsigned int user) +{ + unsigned short lineno = *(unsigned short *)tracedata; + const char *file = *(const char **)(tracedata + 2); + unsigned int user_hash_value, file_hash_value; + + user_hash_value = user % USERHASH; + file_hash_value = hash_string(lineno, file, FILEHASH); + set_magic_time(user_hash_value, file_hash_value, dev_hash_value); +} + +extern char __tracedata_start, __tracedata_end; +static int show_file_hash(unsigned int value) +{ + int match; + char *tracedata; + + match = 0; + for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ; tracedata += 6) { + unsigned short lineno = *(unsigned short *)tracedata; + const char *file = *(const char **)(tracedata + 2); + unsigned int hash = hash_string(lineno, file, FILEHASH); + if (hash != value) + continue; + printk(" hash matches %s:%u\n", file, lineno); + match++; + } + return match; +} + +static int show_dev_hash(unsigned int value) +{ + int match = 0; + struct list_head * entry = dpm_active.prev; + + while (entry != &dpm_active) { + struct device * dev = to_device(entry); + unsigned int hash = hash_string(DEVSEED, dev->bus_id, DEVHASH); + if (hash == value) { + printk(" hash matches device %s\n", dev->bus_id); + match++; + } + entry = entry->prev; + } + return match; +} + +static unsigned int hash_value_early_read; + +static int early_resume_init(void) +{ + hash_value_early_read = read_magic_time(); + return 0; +} + +static int late_resume_init(void) +{ + unsigned int val = hash_value_early_read; + unsigned int user, file, dev; + + user = val % USERHASH; + val = val / USERHASH; + file = val % FILEHASH; + val = val / FILEHASH; + dev = val /* % DEVHASH */; + + printk(" Magic number: %d:%d:%d\n", user, file, dev); + show_file_hash(file); + show_dev_hash(dev); + return 0; +} + +core_initcall(early_resume_init); +late_initcall(late_resume_init); |
