From 4508a7a734b111b8b7e39986237d84acb1168dd0 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 20 Mar 2006 17:53:53 +1100 Subject: [PATCH] sysfs: Allow sysfs attribute files to be pollable It works like this: Open the file Read all the contents. Call poll requesting POLLERR or POLLPRI (so select/exceptfds works) When poll returns, close the file and go to top of loop. or lseek to start of file and go back to the 'read'. Events are signaled by an object manager calling sysfs_notify(kobj, dir, attr); If the dir is non-NULL, it is used to find a subdirectory which contains the attribute (presumably created by sysfs_create_group). This has a cost of one int per attribute, one wait_queuehead per kobject, one int per open file. The name "sysfs_notify" may be confused with the inotify functionality. Maybe it would be nice to support inotify for sysfs attributes as well? This patch also uses sysfs_notify to allow /sys/block/md*/md/sync_action to be pollable Signed-off-by: Neil Brown Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 1 + fs/sysfs/dir.c | 1 + fs/sysfs/file.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++ fs/sysfs/sysfs.h | 1 + include/linux/kobject.h | 2 ++ include/linux/sysfs.h | 6 ++++ lib/kobject.c | 1 + 7 files changed, 88 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 1ed5152db450..434ca39d19c1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -163,6 +163,7 @@ void md_new_event(mddev_t *mddev) { atomic_inc(&md_event_count); wake_up(&md_event_waiters); + sysfs_notify(&mddev->kobj, NULL, "sync_action"); } EXPORT_SYMBOL_GPL(md_new_event); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 6cfdc9a87772..610b5bdbe75b 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -43,6 +43,7 @@ static struct sysfs_dirent * sysfs_new_dirent(struct sysfs_dirent * parent_sd, memset(sd, 0, sizeof(*sd)); atomic_set(&sd->s_count, 1); + atomic_set(&sd->s_event, 0); INIT_LIST_HEAD(&sd->s_children); list_add(&sd->s_sibling, &parent_sd->s_children); sd->s_element = element; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index f1cb1ddde511..cf3786625bfa 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -57,6 +58,7 @@ struct sysfs_buffer { struct sysfs_ops * ops; struct semaphore sem; int needs_read_fill; + int event; }; @@ -72,6 +74,7 @@ struct sysfs_buffer { */ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer) { + struct sysfs_dirent * sd = dentry->d_fsdata; struct attribute * attr = to_attr(dentry); struct kobject * kobj = to_kobj(dentry->d_parent); struct sysfs_ops * ops = buffer->ops; @@ -83,6 +86,7 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer if (!buffer->page) return -ENOMEM; + buffer->event = atomic_read(&sd->s_event); count = ops->show(kobj,attr,buffer->page); buffer->needs_read_fill = 0; BUG_ON(count > (ssize_t)PAGE_SIZE); @@ -348,12 +352,84 @@ static int sysfs_release(struct inode * inode, struct file * filp) return 0; } +/* Sysfs attribute files are pollable. The idea is that you read + * the content and then you use 'poll' or 'select' to wait for + * the content to change. When the content changes (assuming the + * manager for the kobject supports notification), poll will + * return POLLERR|POLLPRI, and select will return the fd whether + * it is waiting for read, write, or exceptions. + * Once poll/select indicates that the value has changed, you + * need to close and re-open the file, as simply seeking and reading + * again will not get new data, or reset the state of 'poll'. + * Reminder: this only works for attributes which actively support + * it, and it is not possible to test an attribute from userspace + * to see if it supports poll (Nether 'poll' or 'select' return + * an appropriate error code). When in doubt, set a suitable timeout value. + */ +static unsigned int sysfs_poll(struct file *filp, poll_table *wait) +{ + struct sysfs_buffer * buffer = filp->private_data; + struct kobject * kobj = to_kobj(filp->f_dentry->d_parent); + struct sysfs_dirent * sd = filp->f_dentry->d_fsdata; + int res = 0; + + poll_wait(filp, &kobj->poll, wait); + + if (buffer->event != atomic_read(&sd->s_event)) { + res = POLLERR|POLLPRI; + buffer->needs_read_fill = 1; + } + + return res; +} + + +static struct dentry *step_down(struct dentry *dir, const char * name) +{ + struct dentry * de; + + if (dir == NULL || dir->d_inode == NULL) + return NULL; + + mutex_lock(&dir->d_inode->i_mutex); + de = lookup_one_len(name, dir, strlen(name)); + mutex_unlock(&dir->d_inode->i_mutex); + dput(dir); + if (IS_ERR(de)) + return NULL; + if (de->d_inode == NULL) { + dput(de); + return NULL; + } + return de; +} + +void sysfs_notify(struct kobject * k, char *dir, char *attr) +{ + struct dentry *de = k->dentry; + if (de) + dget(de); + if (de && dir) + de = step_down(de, dir); + if (de && attr) + de = step_down(de, attr); + if (de) { + struct sysfs_dirent * sd = de->d_fsdata; + if (sd) + atomic_inc(&sd->s_event); + wake_up_interruptible(&k->poll); + dput(de); + } +} +EXPORT_SYMBOL_GPL(sysfs_notify); + const struct file_operations sysfs_file_operations = { .read = sysfs_read_file, .write = sysfs_write_file, .llseek = generic_file_llseek, .open = sysfs_open_file, .release = sysfs_release, + .poll = sysfs_poll, }; diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 32958a7c50e9..3651ffb5ec09 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -11,6 +11,7 @@ extern int sysfs_make_dirent(struct sysfs_dirent *, struct dentry *, void *, extern int sysfs_add_file(struct dentry *, const struct attribute *, int); extern void sysfs_hash_and_remove(struct dentry * dir, const char * name); +extern struct sysfs_dirent *sysfs_find(struct sysfs_dirent *dir, const char * name); extern int sysfs_create_subdir(struct kobject *, const char *, struct dentry **); extern void sysfs_remove_subdir(struct dentry *); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 4cb1214ec290..dcd0623be892 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -24,6 +24,7 @@ #include #include #include +#include #include #define KOBJ_NAME_LEN 20 @@ -56,6 +57,7 @@ struct kobject { struct kset * kset; struct kobj_type * ktype; struct dentry * dentry; + wait_queue_head_t poll; }; extern int kobject_set_name(struct kobject *, const char *, ...) diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 392da5a6dacb..1ea5d3cda6ae 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -74,6 +74,7 @@ struct sysfs_dirent { umode_t s_mode; struct dentry * s_dentry; struct iattr * s_iattr; + atomic_t s_event; }; #define SYSFS_ROOT 0x0001 @@ -117,6 +118,7 @@ int sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr); int sysfs_create_group(struct kobject *, const struct attribute_group *); void sysfs_remove_group(struct kobject *, const struct attribute_group *); +void sysfs_notify(struct kobject * k, char *dir, char *attr); #else /* CONFIG_SYSFS */ @@ -185,6 +187,10 @@ static inline void sysfs_remove_group(struct kobject * k, const struct attribute ; } +static inline void sysfs_notify(struct kobject * k, char *dir, char *attr) +{ +} + #endif /* CONFIG_SYSFS */ #endif /* _SYSFS_H_ */ diff --git a/lib/kobject.c b/lib/kobject.c index 25204a41a9b0..01d957513940 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -128,6 +128,7 @@ void kobject_init(struct kobject * kobj) { kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); + init_waitqueue_head(&kobj->poll); kobj->kset = kset_get(kobj->kset); } -- cgit v1.2.1 From 0f836ca4c122f4ef096110d652a6326fe34e6961 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 31 Mar 2006 11:52:25 -0500 Subject: [PATCH] driver core: safely unbind drivers for devices not on a bus This patch (as667) changes the __device_release_driver() routine to prevent it from crashing when it runs across a device not on any bus. This seems logical, inasmuch as the corresponding bus_add_device() routine has an explicit check allowing it to accept such devices. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 730a9ce0a14a..889c71111239 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -209,7 +209,7 @@ static void __device_release_driver(struct device * dev) sysfs_remove_link(&dev->kobj, "driver"); klist_remove(&dev->knode_driver); - if (dev->bus->remove) + if (dev->bus && dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); -- cgit v1.2.1 From d4d7e5dffc4844ef51fe11f497bd774c04413a00 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 24 Mar 2006 20:45:35 +0100 Subject: [PATCH] BLOCK: delay all uevents until partition table is scanned [BLOCK] delay all uevents until partition table is scanned Here we delay the annoucement of all block device events until the disk's partition table is scanned and all partition devices are already created and sysfs is populated. We have a bunch of old bugs for removable storage handling where we probe successfully for a filesystem on the raw disk, but at the same time the kernel recognizes a partition table and creates partition devices. Currently there is no sane way to tell if partitions will show up or not at the time the disk device is announced to userspace. With the delayed events we can simply skip any probe for a filesystem on the raw disk when we find already present partitions. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- fs/partitions/check.c | 38 ++++++++++++++++++++++++++++++-------- include/linux/genhd.h | 1 + 2 files changed, 31 insertions(+), 8 deletions(-) diff --git a/fs/partitions/check.c b/fs/partitions/check.c index af0cb4b9e784..f3b6af071722 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -331,7 +331,9 @@ void delete_partition(struct gendisk *disk, int part) devfs_remove("%s/part%d", disk->devfs_name, part); if (p->holder_dir) kobject_unregister(p->holder_dir); - kobject_unregister(&p->kobj); + kobject_uevent(&p->kobj, KOBJ_REMOVE); + kobject_del(&p->kobj); + kobject_put(&p->kobj); } void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len) @@ -357,7 +359,10 @@ void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len) snprintf(p->kobj.name,KOBJ_NAME_LEN,"%s%d",disk->kobj.name,part); p->kobj.parent = &disk->kobj; p->kobj.ktype = &ktype_part; - kobject_register(&p->kobj); + kobject_init(&p->kobj); + kobject_add(&p->kobj); + if (!disk->part_uevent_suppress) + kobject_uevent(&p->kobj, KOBJ_ADD); partition_sysfs_add_subdir(p); disk->part[part-1] = p; } @@ -395,6 +400,8 @@ void register_disk(struct gendisk *disk) { struct block_device *bdev; char *s; + int i; + struct hd_struct *p; int err; strlcpy(disk->kobj.name,disk->disk_name,KOBJ_NAME_LEN); @@ -406,13 +413,12 @@ void register_disk(struct gendisk *disk) return; disk_sysfs_symlinks(disk); disk_sysfs_add_subdirs(disk); - kobject_uevent(&disk->kobj, KOBJ_ADD); /* No minors to use for partitions */ if (disk->minors == 1) { if (disk->devfs_name[0] != '\0') devfs_add_disk(disk); - return; + goto exit; } /* always add handle for the whole disk */ @@ -420,16 +426,32 @@ void register_disk(struct gendisk *disk) /* No such device (e.g., media were just removed) */ if (!get_capacity(disk)) - return; + goto exit; bdev = bdget_disk(disk, 0); if (!bdev) - return; + goto exit; + /* scan partition table, but suppress uevents */ bdev->bd_invalidated = 1; - if (blkdev_get(bdev, FMODE_READ, 0) < 0) - return; + disk->part_uevent_suppress = 1; + err = blkdev_get(bdev, FMODE_READ, 0); + disk->part_uevent_suppress = 0; + if (err < 0) + goto exit; blkdev_put(bdev); + +exit: + /* announce disk after possible partitions are already created */ + kobject_uevent(&disk->kobj, KOBJ_ADD); + + /* announce possible partitions */ + for (i = 1; i < disk->minors; i++) { + p = disk->part[i-1]; + if (!p || !p->nr_sects) + continue; + kobject_uevent(&p->kobj, KOBJ_ADD); + } } int rescan_partitions(struct gendisk *disk, struct block_device *bdev) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 10a27f29d692..2ef845b35175 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -105,6 +105,7 @@ struct gendisk { * disks that can't be partitioned. */ char disk_name[32]; /* name of major driver */ struct hd_struct **part; /* [indexed by minor] */ + int part_uevent_suppress; struct block_device_operations *fops; struct request_queue *queue; void *private_data; -- cgit v1.2.1 From a14388904ca67197c9a531dba2358d8131697865 Mon Sep 17 00:00:00 2001 From: Jayachandran C Date: Mon, 3 Apr 2006 12:31:53 -0700 Subject: [PATCH] driver core: fix unnecessary NULL check in drivers/base/class.c This patch tries to fix an issue in drivers/base/class.c, please review and apply if correct. Patch Description: "parent_class" is checked for NULL already, so removed the unnecessary check. Signed-off-by: Jayachandran C. Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index df7fdabd0730..0e71dff327cd 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -562,14 +562,13 @@ int class_device_add(struct class_device *class_dev) kobject_uevent(&class_dev->kobj, KOBJ_ADD); /* notify any interfaces this device is now here */ - if (parent_class) { - down(&parent_class->sem); - list_add_tail(&class_dev->node, &parent_class->children); - list_for_each_entry(class_intf, &parent_class->interfaces, node) - if (class_intf->add) - class_intf->add(class_dev, class_intf); - up(&parent_class->sem); + down(&parent_class->sem); + list_add_tail(&class_dev->node, &parent_class->children); + list_for_each_entry(class_intf, &parent_class->interfaces, node) { + if (class_intf->add) + class_intf->add(class_dev, class_intf); } + up(&parent_class->sem); register_done: if (error) { -- cgit v1.2.1 From 372254018eb1b65ee69210d11686bfc65c8d84db Mon Sep 17 00:00:00 2001 From: Ryan Wilson Date: Wed, 22 Mar 2006 16:26:25 -0500 Subject: [PATCH] driver core: driver_bind attribute returns incorrect value The manual driver <-> device binding attribute in sysfs doesn't return the correct value on failure or success of driver_probe_device. driver_probe_device returns 1 on success (the driver accepted the device) or 0 on probe failure (when the driver didn't accept the device but no real error occured). However, the attribute can't just return 0 or 1, it must return the number of bytes consumed from buf or an error value. Returning 0 indicates to userspace that nothing was written (even though the kernel has tried to do the bind/probe and failed). Returning 1 indicates that only one character was accepted in which case userspace will re-try the write with a partial string. A more correct version of driver_bind would return count (to indicate the entire string was consumed) when driver_probe_device returns 1 and -ENODEV when driver_probe_device returns 0. This patch makes that change. Signed-off-by: Ryan Wilson Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 48718b7f4fa0..76656acd00d4 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -188,6 +188,11 @@ static ssize_t driver_bind(struct device_driver *drv, up(&dev->sem); if (dev->parent) up(&dev->parent->sem); + + if (err > 0) /* success */ + err = count; + else if (err == 0) /* driver didn't accept device */ + err = -ENODEV; } put_device(dev); put_bus(bus); -- cgit v1.2.1 From 026694920579590c73b5c56705d543568ed5ad41 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 23 Mar 2006 01:38:34 -0800 Subject: [PATCH] pm: print name of failed suspend function Print more diagnostic info to help identify the source of power management suspend failures. Example: usb_hcd_pci_suspend(): pci_set_power_state+0x0/0x1af() returns -22 pci_device_suspend(): usb_hcd_pci_suspend+0x0/0x11b() returns -22 suspend_device(): pci_device_suspend+0x0/0x34() returns -22 Work-in-progress. It needs lots more suspend_report_result() calls sprinkled everywhere. Cc: Patrick Mochel Cc: Pavel Machek Cc: Nigel Cunningham Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/base/power/suspend.c | 12 ++++++++++++ drivers/pci/pci-driver.c | 6 ++++-- drivers/pci/pci.c | 6 ++++-- drivers/usb/core/hcd-pci.c | 7 +++---- include/linux/pm.h | 8 ++++++++ 5 files changed, 31 insertions(+), 8 deletions(-) diff --git a/drivers/base/power/suspend.c b/drivers/base/power/suspend.c index bdb60663f2ef..662209d3f42d 100644 --- a/drivers/base/power/suspend.c +++ b/drivers/base/power/suspend.c @@ -10,6 +10,8 @@ #include #include +#include +#include #include "../base.h" #include "power.h" @@ -58,6 +60,7 @@ int suspend_device(struct device * dev, pm_message_t state) if (dev->bus && dev->bus->suspend && !dev->power.power_state.event) { dev_dbg(dev, "suspending\n"); error = dev->bus->suspend(dev, state); + suspend_report_result(dev->bus->suspend, error); } up(&dev->sem); return error; @@ -169,3 +172,12 @@ int device_power_down(pm_message_t state) EXPORT_SYMBOL_GPL(device_power_down); +void __suspend_report_result(const char *function, void *fn, int ret) +{ + if (ret) { + printk(KERN_ERR "%s(): ", function); + print_fn_descriptor_symbol("%s() returns ", (unsigned long)fn); + printk("%d\n", ret); + } +} +EXPORT_SYMBOL_GPL(__suspend_report_result); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index f22f69ac6445..1456759936c5 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -271,10 +271,12 @@ static int pci_device_suspend(struct device * dev, pm_message_t state) struct pci_driver * drv = pci_dev->driver; int i = 0; - if (drv && drv->suspend) + if (drv && drv->suspend) { i = drv->suspend(pci_dev, state); - else + suspend_report_result(drv->suspend, i); + } else { pci_save_state(pci_dev); + } return i; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index bea1ad1ad5ba..042fa5265cf6 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -307,9 +307,11 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state) * Can enter D0 from any state, but if we can only go deeper * to sleep if we're already in a low power state */ - if (state != PCI_D0 && dev->current_state > state) + if (state != PCI_D0 && dev->current_state > state) { + printk(KERN_ERR "%s(): %s: state=%d, current state=%d\n", + __FUNCTION__, pci_name(dev), state, dev->current_state); return -EINVAL; - else if (dev->current_state == state) + } else if (dev->current_state == state) return 0; /* we're already there */ /* find PCI PM capability in list */ diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 0d2193b69235..66b78404ab34 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -213,11 +213,9 @@ int usb_hcd_pci_suspend (struct pci_dev *dev, pm_message_t message) if (hcd->driver->suspend) { retval = hcd->driver->suspend(hcd, message); - if (retval) { - dev_dbg (&dev->dev, "PCI pre-suspend fail, %d\n", - retval); + suspend_report_result(hcd->driver->suspend, retval); + if (retval) goto done; - } } synchronize_irq(dev->irq); @@ -263,6 +261,7 @@ int usb_hcd_pci_suspend (struct pci_dev *dev, pm_message_t message) * some device state (e.g. as part of clock reinit). */ retval = pci_set_power_state (dev, PCI_D3hot); + suspend_report_result(pci_set_power_state, retval); if (retval == 0) { int wake = device_can_wakeup(&hcd->self.root_hub->dev); diff --git a/include/linux/pm.h b/include/linux/pm.h index 6df2585c0169..66be58902b17 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -199,6 +199,12 @@ extern int device_suspend(pm_message_t state); extern int dpm_runtime_suspend(struct device *, pm_message_t); extern void dpm_runtime_resume(struct device *); +extern void __suspend_report_result(const char *function, void *fn, int ret); + +#define suspend_report_result(fn, ret) \ + do { \ + __suspend_report_result(__FUNCTION__, fn, ret); \ + } while (0) #else /* !CONFIG_PM */ @@ -219,6 +225,8 @@ static inline void dpm_runtime_resume(struct device * dev) { } +#define suspend_report_result(fn, ret) do { } while (0) + #endif /* changes to device_may_wakeup take effect on the next pm state change. -- cgit v1.2.1 From 4f705ae3e94ffaafe8d35f71ff4d5c499bb06814 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 3 Apr 2006 17:09:22 -0700 Subject: [PATCH] DMI: move dmi_scan.c from arch/i386 to drivers/firmware/ dmi_scan.c is arch-independent and is used by i386, x86_64, and ia64. Currently all three arches compile it from arch/i386, which means that ia64 and x86_64 depend on things in arch/i386 that they wouldn't otherwise care about. This is simply "mv arch/i386/kernel/dmi_scan.c drivers/firmware/" (removing trailing whitespace) and the associated Makefile changes. All three architectures already set CONFIG_DMI in their top-level Kconfig files. Signed-off-by: Bjorn Helgaas Cc: Andi Kleen Cc: "Luck, Tony" Cc: Andrey Panin Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- arch/i386/kernel/Makefile | 2 +- arch/i386/kernel/dmi_scan.c | 358 -------------------------------------------- arch/ia64/kernel/Makefile | 3 +- arch/x86_64/kernel/Makefile | 4 +- drivers/firmware/Makefile | 3 +- drivers/firmware/dmi_scan.c | 358 ++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 363 insertions(+), 365 deletions(-) delete mode 100644 arch/i386/kernel/dmi_scan.c create mode 100644 drivers/firmware/dmi_scan.c diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile index 5b9ed21216cf..96fb8a020af2 100644 --- a/arch/i386/kernel/Makefile +++ b/arch/i386/kernel/Makefile @@ -6,7 +6,7 @@ extra-y := head.o init_task.o vmlinux.lds obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \ ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \ - pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \ + pci-dma.o i386_ksyms.o i387.o bootflag.o \ quirks.o i8237.o topology.o alternative.o obj-y += cpu/ diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c deleted file mode 100644 index 5efceebc48dc..000000000000 --- a/arch/i386/kernel/dmi_scan.c +++ /dev/null @@ -1,358 +0,0 @@ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static char * __init dmi_string(struct dmi_header *dm, u8 s) -{ - u8 *bp = ((u8 *) dm) + dm->length; - char *str = ""; - - if (s) { - s--; - while (s > 0 && *bp) { - bp += strlen(bp) + 1; - s--; - } - - if (*bp != 0) { - str = dmi_alloc(strlen(bp) + 1); - if (str != NULL) - strcpy(str, bp); - else - printk(KERN_ERR "dmi_string: out of memory.\n"); - } - } - - return str; -} - -/* - * We have to be cautious here. We have seen BIOSes with DMI pointers - * pointing to completely the wrong place for example - */ -static int __init dmi_table(u32 base, int len, int num, - void (*decode)(struct dmi_header *)) -{ - u8 *buf, *data; - int i = 0; - - buf = dmi_ioremap(base, len); - if (buf == NULL) - return -1; - - data = buf; - - /* - * Stop when we see all the items the table claimed to have - * OR we run off the end of the table (also happens) - */ - while ((i < num) && (data - buf + sizeof(struct dmi_header)) <= len) { - struct dmi_header *dm = (struct dmi_header *)data; - /* - * We want to know the total length (formated area and strings) - * before decoding to make sure we won't run off the table in - * dmi_decode or dmi_string - */ - data += dm->length; - while ((data - buf < len - 1) && (data[0] || data[1])) - data++; - if (data - buf < len - 1) - decode(dm); - data += 2; - i++; - } - dmi_iounmap(buf, len); - return 0; -} - -static int __init dmi_checksum(u8 *buf) -{ - u8 sum = 0; - int a; - - for (a = 0; a < 15; a++) - sum += buf[a]; - - return sum == 0; -} - -static char *dmi_ident[DMI_STRING_MAX]; -static LIST_HEAD(dmi_devices); - -/* - * Save a DMI string - */ -static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) -{ - char *p, *d = (char*) dm; - - if (dmi_ident[slot]) - return; - - p = dmi_string(dm, d[string]); - if (p == NULL) - return; - - dmi_ident[slot] = p; -} - -static void __init dmi_save_devices(struct dmi_header *dm) -{ - int i, count = (dm->length - sizeof(struct dmi_header)) / 2; - struct dmi_device *dev; - - for (i = 0; i < count; i++) { - char *d = (char *)(dm + 1) + (i * 2); - - /* Skip disabled device */ - if ((*d & 0x80) == 0) - continue; - - dev = dmi_alloc(sizeof(*dev)); - if (!dev) { - printk(KERN_ERR "dmi_save_devices: out of memory.\n"); - break; - } - - dev->type = *d++ & 0x7f; - dev->name = dmi_string(dm, *d); - dev->device_data = NULL; - - list_add(&dev->list, &dmi_devices); - } -} - -static void __init dmi_save_ipmi_device(struct dmi_header *dm) -{ - struct dmi_device *dev; - void * data; - - data = dmi_alloc(dm->length); - if (data == NULL) { - printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n"); - return; - } - - memcpy(data, dm, dm->length); - - dev = dmi_alloc(sizeof(*dev)); - if (!dev) { - printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n"); - return; - } - - dev->type = DMI_DEV_TYPE_IPMI; - dev->name = "IPMI controller"; - dev->device_data = data; - - list_add(&dev->list, &dmi_devices); -} - -/* - * Process a DMI table entry. Right now all we care about are the BIOS - * and machine entries. For 2.5 we should pull the smbus controller info - * out of here. - */ -static void __init dmi_decode(struct dmi_header *dm) -{ - switch(dm->type) { - case 0: /* BIOS Information */ - dmi_save_ident(dm, DMI_BIOS_VENDOR, 4); - dmi_save_ident(dm, DMI_BIOS_VERSION, 5); - dmi_save_ident(dm, DMI_BIOS_DATE, 8); - break; - case 1: /* System Information */ - dmi_save_ident(dm, DMI_SYS_VENDOR, 4); - dmi_save_ident(dm, DMI_PRODUCT_NAME, 5); - dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); - dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); - break; - case 2: /* Base Board Information */ - dmi_save_ident(dm, DMI_BOARD_VENDOR, 4); - dmi_save_ident(dm, DMI_BOARD_NAME, 5); - dmi_save_ident(dm, DMI_BOARD_VERSION, 6); - break; - case 10: /* Onboard Devices Information */ - dmi_save_devices(dm); - break; - case 38: /* IPMI Device Information */ - dmi_save_ipmi_device(dm); - } -} - -static int __init dmi_present(char __iomem *p) -{ - u8 buf[15]; - memcpy_fromio(buf, p, 15); - if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) { - u16 num = (buf[13] << 8) | buf[12]; - u16 len = (buf[7] << 8) | buf[6]; - u32 base = (buf[11] << 24) | (buf[10] << 16) | - (buf[9] << 8) | buf[8]; - - /* - * DMI version 0.0 means that the real version is taken from - * the SMBIOS version, which we don't know at this point. - */ - if (buf[14] != 0) - printk(KERN_INFO "DMI %d.%d present.\n", - buf[14] >> 4, buf[14] & 0xF); - else - printk(KERN_INFO "DMI present.\n"); - if (dmi_table(base,len, num, dmi_decode) == 0) - return 0; - } - return 1; -} - -void __init dmi_scan_machine(void) -{ - char __iomem *p, *q; - int rc; - - if (efi_enabled) { - if (efi.smbios == EFI_INVALID_TABLE_ADDR) - goto out; - - /* This is called as a core_initcall() because it isn't - * needed during early boot. This also means we can - * iounmap the space when we're done with it. - */ - p = dmi_ioremap(efi.smbios, 32); - if (p == NULL) - goto out; - - rc = dmi_present(p + 0x10); /* offset of _DMI_ string */ - dmi_iounmap(p, 32); - if (!rc) - return; - } - else { - /* - * no iounmap() for that ioremap(); it would be a no-op, but - * it's so early in setup that sucker gets confused into doing - * what it shouldn't if we actually call it. - */ - p = dmi_ioremap(0xF0000, 0x10000); - if (p == NULL) - goto out; - - for (q = p; q < p + 0x10000; q += 16) { - rc = dmi_present(q); - if (!rc) - return; - } - } - out: printk(KERN_INFO "DMI not present or invalid.\n"); -} - -/** - * dmi_check_system - check system DMI data - * @list: array of dmi_system_id structures to match against - * - * Walk the blacklist table running matching functions until someone - * returns non zero or we hit the end. Callback function is called for - * each successfull match. Returns the number of matches. - */ -int dmi_check_system(struct dmi_system_id *list) -{ - int i, count = 0; - struct dmi_system_id *d = list; - - while (d->ident) { - for (i = 0; i < ARRAY_SIZE(d->matches); i++) { - int s = d->matches[i].slot; - if (s == DMI_NONE) - continue; - if (dmi_ident[s] && strstr(dmi_ident[s], d->matches[i].substr)) - continue; - /* No match */ - goto fail; - } - count++; - if (d->callback && d->callback(d)) - break; -fail: d++; - } - - return count; -} -EXPORT_SYMBOL(dmi_check_system); - -/** - * dmi_get_system_info - return DMI data value - * @field: data index (see enum dmi_filed) - * - * Returns one DMI data value, can be used to perform - * complex DMI data checks. - */ -char *dmi_get_system_info(int field) -{ - return dmi_ident[field]; -} -EXPORT_SYMBOL(dmi_get_system_info); - -/** - * dmi_find_device - find onboard device by type/name - * @type: device type or %DMI_DEV_TYPE_ANY to match all device types - * @desc: device name string or %NULL to match all - * @from: previous device found in search, or %NULL for new search. - * - * Iterates through the list of known onboard devices. If a device is - * found with a matching @vendor and @device, a pointer to its device - * structure is returned. Otherwise, %NULL is returned. - * A new search is initiated by passing %NULL to the @from argument. - * If @from is not %NULL, searches continue from next device. - */ -struct dmi_device * dmi_find_device(int type, const char *name, - struct dmi_device *from) -{ - struct list_head *d, *head = from ? &from->list : &dmi_devices; - - for(d = head->next; d != &dmi_devices; d = d->next) { - struct dmi_device *dev = list_entry(d, struct dmi_device, list); - - if (((type == DMI_DEV_TYPE_ANY) || (dev->type == type)) && - ((name == NULL) || (strcmp(dev->name, name) == 0))) - return dev; - } - - return NULL; -} -EXPORT_SYMBOL(dmi_find_device); - -/** - * dmi_get_year - Return year of a DMI date - * @field: data index (like dmi_get_system_info) - * - * Returns -1 when the field doesn't exist. 0 when it is broken. - */ -int dmi_get_year(int field) -{ - int year; - char *s = dmi_get_system_info(field); - - if (!s) - return -1; - if (*s == '\0') - return 0; - s = strrchr(s, '/'); - if (!s) - return 0; - - s += 1; - year = simple_strtoul(s, NULL, 0); - if (year && year < 100) { /* 2-digit year */ - year += 1900; - if (year < 1996) /* no dates < spec 1.0 */ - year += 100; - } - - return year; -} diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 59e871dae742..09a0dbc17fb6 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -7,7 +7,7 @@ extra-y := head.o init_task.o vmlinux.lds obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \ irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \ salinfo.o semaphore.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \ - unwind.o mca.o mca_asm.o topology.o dmi_scan.o + unwind.o mca.o mca_asm.o topology.o obj-$(CONFIG_IA64_BRL_EMU) += brl_emu.o obj-$(CONFIG_IA64_GENERIC) += acpi-ext.o @@ -30,7 +30,6 @@ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o mca_recovery-y += mca_drv.o mca_drv_asm.o -dmi_scan-y += ../../i386/kernel/dmi_scan.o # The gate DSO image is built using a special linker script. targets += gate.so gate-syms.o diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile index a098a11e7755..059c88313f4e 100644 --- a/arch/x86_64/kernel/Makefile +++ b/arch/x86_64/kernel/Makefile @@ -8,7 +8,7 @@ obj-y := process.o signal.o entry.o traps.o irq.o \ ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_x86_64.o \ x8664_ksyms.o i387.o syscall.o vsyscall.o \ setup64.o bootflag.o e820.o reboot.o quirks.o i8237.o \ - dmi_scan.o pci-dma.o pci-nommu.o + pci-dma.o pci-nommu.o obj-$(CONFIG_X86_MCE) += mce.o obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o @@ -49,5 +49,3 @@ intel_cacheinfo-y += ../../i386/kernel/cpu/intel_cacheinfo.o quirks-y += ../../i386/kernel/quirks.o i8237-y += ../../i386/kernel/i8237.o msr-$(subst m,y,$(CONFIG_X86_MSR)) += ../../i386/kernel/msr.o -dmi_scan-y += ../../i386/kernel/dmi_scan.o - diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index 85429979d0db..98e395f4bb29 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -1,7 +1,8 @@ # # Makefile for the linux kernel. # -obj-$(CONFIG_EDD) += edd.o +obj-$(CONFIG_DMI) += dmi_scan.o +obj-$(CONFIG_EDD) += edd.o obj-$(CONFIG_EFI_VARS) += efivars.o obj-$(CONFIG_EFI_PCDP) += pcdp.o obj-$(CONFIG_DELL_RBU) += dell_rbu.o diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c new file mode 100644 index 000000000000..948bd7e1445a --- /dev/null +++ b/drivers/firmware/dmi_scan.c @@ -0,0 +1,358 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static char * __init dmi_string(struct dmi_header *dm, u8 s) +{ + u8 *bp = ((u8 *) dm) + dm->length; + char *str = ""; + + if (s) { + s--; + while (s > 0 && *bp) { + bp += strlen(bp) + 1; + s--; + } + + if (*bp != 0) { + str = dmi_alloc(strlen(bp) + 1); + if (str != NULL) + strcpy(str, bp); + else + printk(KERN_ERR "dmi_string: out of memory.\n"); + } + } + + return str; +} + +/* + * We have to be cautious here. We have seen BIOSes with DMI pointers + * pointing to completely the wrong place for example + */ +static int __init dmi_table(u32 base, int len, int num, + void (*decode)(struct dmi_header *)) +{ + u8 *buf, *data; + int i = 0; + + buf = dmi_ioremap(base, len); + if (buf == NULL) + return -1; + + data = buf; + + /* + * Stop when we see all the items the table claimed to have + * OR we run off the end of the table (also happens) + */ + while ((i < num) && (data - buf + sizeof(struct dmi_header)) <= len) { + struct dmi_header *dm = (struct dmi_header *)data; + /* + * We want to know the total length (formated area and strings) + * before decoding to make sure we won't run off the table in + * dmi_decode or dmi_string + */ + data += dm->length; + while ((data - buf < len - 1) && (data[0] || data[1])) + data++; + if (data - buf < len - 1) + decode(dm); + data += 2; + i++; + } + dmi_iounmap(buf, len); + return 0; +} + +static int __init dmi_checksum(u8 *buf) +{ + u8 sum = 0; + int a; + + for (a = 0; a < 15; a++) + sum += buf[a]; + + return sum == 0; +} + +static char *dmi_ident[DMI_STRING_MAX]; +static LIST_HEAD(dmi_devices); + +/* + * Save a DMI string + */ +static void __init dmi_save_ident(struct dmi_header *dm, int slot, int string) +{ + char *p, *d = (char*) dm; + + if (dmi_ident[slot]) + return; + + p = dmi_string(dm, d[string]); + if (p == NULL) + return; + + dmi_ident[slot] = p; +} + +static void __init dmi_save_devices(struct dmi_header *dm) +{ + int i, count = (dm->length - sizeof(struct dmi_header)) / 2; + struct dmi_device *dev; + + for (i = 0; i < count; i++) { + char *d = (char *)(dm + 1) + (i * 2); + + /* Skip disabled device */ + if ((*d & 0x80) == 0) + continue; + + dev = dmi_alloc(sizeof(*dev)); + if (!dev) { + printk(KERN_ERR "dmi_save_devices: out of memory.\n"); + break; + } + + dev->type = *d++ & 0x7f; + dev->name = dmi_string(dm, *d); + dev->device_data = NULL; + + list_add(&dev->list, &dmi_devices); + } +} + +static void __init dmi_save_ipmi_device(struct dmi_header *dm) +{ + struct dmi_device *dev; + void * data; + + data = dmi_alloc(dm->length); + if (data == NULL) { + printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n"); + return; + } + + memcpy(data, dm, dm->length); + + dev = dmi_alloc(sizeof(*dev)); + if (!dev) { + printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n"); + return; + } + + dev->type = DMI_DEV_TYPE_IPMI; + dev->name = "IPMI controller"; + dev->device_data = data; + + list_add(&dev->list, &dmi_devices); +} + +/* + * Process a DMI table entry. Right now all we care about are the BIOS + * and machine entries. For 2.5 we should pull the smbus controller info + * out of here. + */ +static void __init dmi_decode(struct dmi_header *dm) +{ + switch(dm->type) { + case 0: /* BIOS Information */ + dmi_save_ident(dm, DMI_BIOS_VENDOR, 4); + dmi_save_ident(dm, DMI_BIOS_VERSION, 5); + dmi_save_ident(dm, DMI_BIOS_DATE, 8); + break; + case 1: /* System Information */ + dmi_save_ident(dm, DMI_SYS_VENDOR, 4); + dmi_save_ident(dm, DMI_PRODUCT_NAME, 5); + dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6); + dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7); + break; + case 2: /* Base Board Information */ + dmi_save_ident(dm, DMI_BOARD_VENDOR, 4); + dmi_save_ident(dm, DMI_BOARD_NAME, 5); + dmi_save_ident(dm, DMI_BOARD_VERSION, 6); + break; + case 10: /* Onboard Devices Information */ + dmi_save_devices(dm); + break; + case 38: /* IPMI Device Information */ + dmi_save_ipmi_device(dm); + } +} + +static int __init dmi_present(char __iomem *p) +{ + u8 buf[15]; + memcpy_fromio(buf, p, 15); + if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) { + u16 num = (buf[13] << 8) | buf[12]; + u16 len = (buf[7] << 8) | buf[6]; + u32 base = (buf[11] << 24) | (buf[10] << 16) | + (buf[9] << 8) | buf[8]; + + /* + * DMI version 0.0 means that the real version is taken from + * the SMBIOS version, which we don't know at this point. + */ + if (buf[14] != 0) + printk(KERN_INFO "DMI %d.%d present.\n", + buf[14] >> 4, buf[14] & 0xF); + else + printk(KERN_INFO "DMI present.\n"); + if (dmi_table(base,len, num, dmi_decode) == 0) + return 0; + } + return 1; +} + +void __init dmi_scan_machine(void) +{ + char __iomem *p, *q; + int rc; + + if (efi_enabled) { + if (efi.smbios == EFI_INVALID_TABLE_ADDR) + goto out; + + /* This is called as a core_initcall() because it isn't + * needed during early boot. This also means we can + * iounmap the space when we're done with it. + */ + p = dmi_ioremap(efi.smbios, 32); + if (p == NULL) + goto out; + + rc = dmi_present(p + 0x10); /* offset of _DMI_ string */ + dmi_iounmap(p, 32); + if (!rc) + return; + } + else { + /* + * no iounmap() for that ioremap(); it would be a no-op, but + * it's so early in setup that sucker gets confused into doing + * what it shouldn't if we actually call it. + */ + p = dmi_ioremap(0xF0000, 0x10000); + if (p == NULL) + goto out; + + for (q = p; q < p + 0x10000; q += 16) { + rc = dmi_present(q); + if (!rc) + return; + } + } + out: printk(KERN_INFO "DMI not present or invalid.\n"); +} + +/** + * dmi_check_system - check system DMI data + * @list: array of dmi_system_id structures to match against + * + * Walk the blacklist table running matching functions until someone + * returns non zero or we hit the end. Callback function is called for + * each successfull match. Returns the number of matches. + */ +int dmi_check_system(struct dmi_system_id *list) +{ + int i, count = 0; + struct dmi_system_id *d = list; + + while (d->ident) { + for (i = 0; i < ARRAY_SIZE(d->matches); i++) { + int s = d->matches[i].slot; + if (s == DMI_NONE) + continue; + if (dmi_ident[s] && strstr(dmi_ident[s], d->matches[i].substr)) + continue; + /* No match */ + goto fail; + } + count++; + if (d->callback && d->callback(d)) + break; +fail: d++; + } + + return count; +} +EXPORT_SYMBOL(dmi_check_system); + +/** + * dmi_get_system_info - return DMI data value + * @field: data index (see enum dmi_filed) + * + * Returns one DMI data value, can be used to perform + * complex DMI data checks. + */ +char *dmi_get_system_info(int field) +{ + return dmi_ident[field]; +} +EXPORT_SYMBOL(dmi_get_system_info); + +/** + * dmi_find_device - find onboard device by type/name + * @type: device type or %DMI_DEV_TYPE_ANY to match all device types + * @desc: device name string or %NULL to match all + * @from: previous device found in search, or %NULL for new search. + * + * Iterates through the list of known onboard devices. If a device is + * found with a matching @vendor and @device, a pointer to its device + * structure is returned. Otherwise, %NULL is returned. + * A new search is initiated by passing %NULL to the @from argument. + * If @from is not %NULL, searches continue from next device. + */ +struct dmi_device * dmi_find_device(int type, const char *name, + struct dmi_device *from) +{ + struct list_head *d, *head = from ? &from->list : &dmi_devices; + + for(d = head->next; d != &dmi_devices; d = d->next) { + struct dmi_device *dev = list_entry(d, struct dmi_device, list); + + if (((type == DMI_DEV_TYPE_ANY) || (dev->type == type)) && + ((name == NULL) || (strcmp(dev->name, name) == 0))) + return dev; + } + + return NULL; +} +EXPORT_SYMBOL(dmi_find_device); + +/** + * dmi_get_year - Return year of a DMI date + * @field: data index (like dmi_get_system_info) + * + * Returns -1 when the field doesn't exist. 0 when it is broken. + */ +int dmi_get_year(int field) +{ + int year; + char *s = dmi_get_system_info(field); + + if (!s) + return -1; + if (*s == '\0') + return 0; + s = strrchr(s, '/'); + if (!s) + return 0; + + s += 1; + year = simple_strtoul(s, NULL, 0); + if (year && year < 100) { /* 2-digit year */ + year += 1900; + if (year < 1996) /* no dates < spec 1.0 */ + year += 100; + } + + return year; +} -- cgit v1.2.1