lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
Open Source and information security mailing list archives
| ||
|
Message-Id: <1193474399.27652.15.camel@twins> Date: Sat, 27 Oct 2007 10:39:59 +0200 From: Peter Zijlstra <peterz@...radead.org> To: Greg KH <greg@...ah.com> Cc: Kay Sievers <kay.sievers@...y.org>, Nick Piggin <nickpiggin@...oo.com.au>, Andrew Morton <akpm@...ux-foundation.org>, linux-kernel@...r.kernel.org, Jens Axboe <jens.axboe@...cle.com>, Fengguang Wu <fengguang.wu@...il.com>, Trond Myklebust <trond.myklebust@....uio.no>, Miklos Szeredi <miklos@...redi.hu> Subject: Re: per BDI dirty limit (was Re: -mm merge plans for 2.6.24) On Fri, 2007-10-26 at 19:40 -0700, Greg KH wrote: > On Sat, Oct 27, 2007 at 03:18:08AM +0200, Peter Zijlstra wrote: > > > > On Fri, 2007-10-26 at 22:04 +0200, Peter Zijlstra wrote: > > > This crashes and burns on bootup, but I'm too tired to figure out what I > > > did wrong... will give it another try tomorrow.. > > > > Ok, can't sleep.. took a look. I have several problems here. > > > > The thing that makes it go *boom* is the __ATTR_NULL. Removing that > > makes it boot. Albeit it then warns me of multiple duplicate sysfs > > objects, all named "bdi". > > > > For some obscure reason this device interface insists on using the > > bus_id as name (?!), and further reduces usability by limiting that to > > 20 odd characters. > > > > This makes it quite useless. I tried fudging around that limit by using > > device_rename and kobject_rename, but to no avail. > > > > Really, it should not be this hard to use, trying to expose a handfull > > of simple integers to userspace should not take 8h+ and still not work. > > > > Peter, who thinks sysfs is contorted mess beyond his skill. I'll stick > > to VM and scheduler code, that actually makes sense. > > Heh, that's funny :) > > I'll look at this and see what I can come up with. Would you just like > a whole new patch, or one against this one? Sorry for the grumpy note, I get that way at 3.30 am. Maybe I ought not have mailed :-/ This is the code I had at that time. Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl> --- block/genhd.c | 2 fs/fuse/inode.c | 2 fs/nfs/client.c | 2 include/linux/backing-dev.h | 21 ++++++ include/linux/string.h | 4 + include/linux/writeback.h | 3 mm/backing-dev.c | 144 ++++++++++++++++++++++++++++++++++++++++++++ mm/page-writeback.c | 2 mm/util.c | 42 ++++++++++++ 9 files changed, 219 insertions(+), 3 deletions(-) Index: linux-2.6-2/fs/fuse/inode.c =================================================================== --- linux-2.6-2.orig/fs/fuse/inode.c +++ linux-2.6-2/fs/fuse/inode.c @@ -467,7 +467,7 @@ static struct fuse_conn *new_conn(void) atomic_set(&fc->num_waiting, 0); fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; fc->bdi.unplug_io_fn = default_unplug_io_fn; - err = bdi_init(&fc->bdi); + err = bdi_init_fmt(&fc->bdi, "bdi-fuse-%llu", (unsigned long long)fc->id); if (err) { kfree(fc); fc = NULL; Index: linux-2.6-2/fs/nfs/client.c =================================================================== --- linux-2.6-2.orig/fs/nfs/client.c +++ linux-2.6-2/fs/nfs/client.c @@ -678,7 +678,7 @@ static int nfs_probe_fsinfo(struct nfs_s goto out_error; nfs_server_set_fsinfo(server, &fsinfo); - error = bdi_init(&server->backing_dev_info); + error = bdi_init_fmt(&server->backing_dev_info, "bdi-nfs-%s-%p", clp->cl_hostname, server); if (error) goto out_error; Index: linux-2.6-2/include/linux/backing-dev.h =================================================================== --- linux-2.6-2.orig/include/linux/backing-dev.h +++ linux-2.6-2/include/linux/backing-dev.h @@ -11,6 +11,8 @@ #include <linux/percpu_counter.h> #include <linux/log2.h> #include <linux/proportions.h> +#include <linux/kernel.h> +#include <linux/device.h> #include <asm/atomic.h> struct page; @@ -48,11 +50,30 @@ struct backing_dev_info { struct prop_local_percpu completions; int dirty_exceeded; + +#ifdef CONFIG_SYSFS + struct device kdev; +#endif }; int bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); +void bdi_unregister(struct backing_dev_info *bdi); + +#define bdi_init_fmt(bdi, fmt...) \ + ({ \ + int ret; \ + ret = bdi_init(bdi); \ + if (!ret) { \ + ret = bdi_register(bdi, ##fmt); \ + if (ret) \ + bdi_destroy(bdi); \ + } \ + ret; \ + }) + static inline void __add_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item, s64 amount) { Index: linux-2.6-2/include/linux/writeback.h =================================================================== --- linux-2.6-2.orig/include/linux/writeback.h +++ linux-2.6-2/include/linux/writeback.h @@ -113,6 +113,9 @@ struct file; int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +void get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty, + struct backing_dev_info *bdi); + void page_writeback_init(void); void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied); Index: linux-2.6-2/mm/backing-dev.c =================================================================== --- linux-2.6-2.orig/mm/backing-dev.c +++ linux-2.6-2/mm/backing-dev.c @@ -4,12 +4,153 @@ #include <linux/fs.h> #include <linux/sched.h> #include <linux/module.h> +#include <linux/writeback.h> +#include <linux/device.h> + +#ifdef CONFIG_SYSFS + +static void bdi_release(struct device *dev) +{ +} + +static int bdi_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + return 0; +} + +static struct class bdi_class = { + .name = "bdi", + .dev_release = bdi_release, + .dev_uevent = bdi_uevent, +}; + +static ssize_t readahead_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct backing_dev_info *bdi = + container_of(dev, struct backing_dev_info, kdev); + char *end; + + bdi->ra_pages = simple_strtoul(buf, &end, 10); + + return end - buf; +} + +#define BDI_SHOW(name, expr) \ +static ssize_t name##_show(struct device *dev, \ + struct device_attribute *attr, char *page) \ +{ \ + struct backing_dev_info *bdi = \ + container_of(dev, struct backing_dev_info, kdev); \ + \ + return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \ +} + +BDI_SHOW(readahead, bdi->ra_pages) + +BDI_SHOW(reclaimable, bdi_stat(bdi, BDI_RECLAIMABLE)) +BDI_SHOW(writeback, bdi_stat(bdi, BDI_WRITEBACK)) + +static inline unsigned long get_dirty(struct backing_dev_info *bdi, int i) +{ + unsigned long thresh[3]; + + get_dirty_limits(&thresh[0], &thresh[1], &thresh[2], bdi); + + return thresh[i]; +} + +BDI_SHOW(dirty, get_dirty(bdi, 1)) +BDI_SHOW(bdi_dirty, get_dirty(bdi, 2)) + +static struct device_attribute bdi_dev_attrs[] = { + __ATTR(readahead, 0644, readahead_show, readahead_store), + __ATTR_RO(reclaimable), + __ATTR_RO(writeback), + __ATTR_RO(dirty), + __ATTR_RO(bdi_dirty), +}; + +static struct attribute *bdi_attributes[ARRAY_SIZE(bdi_dev_attrs) + 1]; + +static struct attribute_group bdi_attribute_group = { + .attrs = bdi_attributes, +}; + +static struct attribute_group *bdi_attribute_groups[] = { + &bdi_attribute_group, + NULL, +}; + +static __init int bdi_class_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(bdi_dev_attrs); i++) + bdi_attributes[i] = &bdi_dev_attrs[i].attr; + + return class_register(&bdi_class); +} + +__initcall(bdi_class_init); + +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) +{ + int ret; + + bdi->kdev.class = &bdi_class; + bdi->kdev.groups = bdi_attribute_groups; + strcpy(bdi->kdev.bus_id, "bdi"); + ret = device_register(&bdi->kdev); + if (!ret) { + char *name; + va_list args; + + va_start(args, fmt); + name = kvprintf(fmt, args); + va_end(args); + + if (!name) { + device_unregister(&bdi->kdev); + return -ENOMEM; + } + + ret = device_rename(&bdi->kdev, name); + kfree(name); + + if (!ret) + device_unregister(&bdi->kdev); + } + + return ret; +} + +void bdi_unregister(struct backing_dev_info *bdi) +{ + device_unregister(&bdi->kdev); +} +#else +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) +{ + return 0; +} + +void bdi_unregister(struct backing_dev_info *bdi) +{ +} +#endif + +EXPORT_SYMBOL(bdi_register); +EXPORT_SYMBOL(bdi_unregister); int bdi_init(struct backing_dev_info *bdi) { int i, j; int err; + memset(bdi, 0, sizeof(*bdi)); + for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0); if (err) @@ -33,6 +174,8 @@ void bdi_destroy(struct backing_dev_info { int i; + bdi_unregister(bdi); + for (i = 0; i < NR_BDI_STAT_ITEMS; i++) percpu_counter_destroy(&bdi->bdi_stat[i]); @@ -90,3 +233,4 @@ long congestion_wait(int rw, long timeou } EXPORT_SYMBOL(congestion_wait); + Index: linux-2.6-2/mm/page-writeback.c =================================================================== --- linux-2.6-2.orig/mm/page-writeback.c +++ linux-2.6-2/mm/page-writeback.c @@ -291,7 +291,7 @@ static unsigned long determine_dirtyable return x + 1; /* Ensure that we never return 0 */ } -static void +void get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty, struct backing_dev_info *bdi) { Index: linux-2.6-2/block/genhd.c =================================================================== --- linux-2.6-2.orig/block/genhd.c +++ linux-2.6-2/block/genhd.c @@ -182,6 +182,7 @@ void add_disk(struct gendisk *disk) disk->minors, NULL, exact_match, exact_lock, disk); register_disk(disk); blk_register_queue(disk); + bdi_register(&disk->queue->backing_dev_info, "bdi-%s", disk->disk_name); } EXPORT_SYMBOL(add_disk); @@ -190,6 +191,7 @@ EXPORT_SYMBOL(del_gendisk); /* in partit void unlink_gendisk(struct gendisk *disk) { blk_unregister_queue(disk); + bdi_unregister(&disk->queue->backing_dev_info); blk_unregister_region(MKDEV(disk->major, disk->first_minor), disk->minors); } Index: linux-2.6-2/include/linux/string.h =================================================================== --- linux-2.6-2.orig/include/linux/string.h +++ linux-2.6-2/include/linux/string.h @@ -8,6 +8,7 @@ #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ +#include <stdarg.h> #ifdef __cplusplus extern "C" { @@ -111,6 +112,9 @@ extern void *kmemdup(const void *src, si extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); +char *kvprintf(const char *fmt, va_list args); +char *kprintf(const char *fmt, ...); + #ifdef __cplusplus } #endif Index: linux-2.6-2/mm/util.c =================================================================== --- linux-2.6-2.orig/mm/util.c +++ linux-2.6-2/mm/util.c @@ -136,3 +136,45 @@ char *strndup_user(const char __user *s, return p; } EXPORT_SYMBOL(strndup_user); + +char *kvprintf(const char *fmt, va_list args) +{ + char c; + char *buf; + int need; + int limit; + va_list args1; + + va_copy(args1, args); + need = vsnprintf(&c, 1, fmt, args1); + va_end(args1); + + /* Allocate the new space and copy the string in */ + limit = need + 1; + buf = kmalloc(limit, GFP_KERNEL); + if (!buf) + return NULL; + need = vsnprintf(buf, limit, fmt, args); + + /* something wrong with the string we copied? */ + if (need >= limit) { + kfree(buf); + return NULL; + } + + return buf; +} +EXPORT_SYMBOL(kvprintf); + +char *kprintf(const char *fmt, ...) +{ + char *buf; + va_list args; + + va_start(args, fmt); + buf = kvprintf(fmt, args); + va_end(args); + + return buf; +} +EXPORT_SYMBOL(kprintf); - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@...r.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists