diff options
Diffstat (limited to 'include/linux')
38 files changed, 1938 insertions, 571 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4efe45d1af7e..b2059869cb92 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -19,8 +19,8 @@ struct request_queue; typedef struct request_queue request_queue_t; -struct elevator_s; -typedef struct elevator_s elevator_t; +struct elevator_queue; +typedef struct elevator_queue elevator_t; struct request_pm_state; #define BLKDEV_MIN_RQ 4 @@ -52,6 +52,20 @@ struct as_io_context { sector_t seek_mean; }; +struct cfq_queue; +struct cfq_io_context { + void (*dtor)(struct cfq_io_context *); + void (*exit)(struct cfq_io_context *); + + struct io_context *ioc; + + /* + * circular list of cfq_io_contexts belonging to a process io context + */ + struct list_head list; + struct cfq_queue *cfqq; +}; + /* * This is the per-process I/O subsystem state. It is refcounted and * kmalloc'ed. Currently all fields are modified in process io context @@ -67,7 +81,10 @@ struct io_context { unsigned long last_waited; /* Time last woken after wait for request */ int nr_batch_requests; /* Number of requests left in the batch */ + spinlock_t lock; + struct as_io_context *aic; + struct cfq_io_context *cic; }; void put_io_context(struct io_context *ioc); @@ -80,6 +97,7 @@ struct request_list { int count[2]; mempool_t *rq_pool; wait_queue_head_t wait[2]; + wait_queue_head_t drain; }; #define BLK_MAX_CDB 16 @@ -279,7 +297,7 @@ struct request_queue */ struct list_head queue_head; struct request *last_merge; - elevator_t elevator; + elevator_t *elevator; /* * the queue request freelist, one for reads and one for writes @@ -342,6 +360,7 @@ struct request_queue unsigned long nr_requests; /* Max # of requests */ unsigned int nr_congestion_on; unsigned int nr_congestion_off; + unsigned int nr_batching; unsigned short max_sectors; unsigned short max_hw_sectors; @@ -381,6 +400,7 @@ struct request_queue #define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */ #define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */ #define QUEUE_FLAG_ORDERED 8 /* supports ordered writes */ +#define QUEUE_FLAG_DRAIN 9 /* draining queue for sched switch */ #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) @@ -617,6 +637,8 @@ extern void blk_dump_rq_flags(struct request *, char *); extern void generic_unplug_device(request_queue_t *); extern void __generic_unplug_device(request_queue_t *); extern long nr_blockdev_pages(void); +extern void blk_wait_queue_drained(request_queue_t *); +extern void blk_finish_queue_drain(request_queue_t *); int blk_get_queue(request_queue_t *); request_queue_t *blk_alloc_queue(int); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 367a8a313506..47fb6a02d630 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -155,7 +155,6 @@ void invalidate_bdev(struct block_device *, int); int sync_blockdev(struct block_device *bdev); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); -void wake_up_buffer(struct buffer_head *bh); int fsync_bdev(struct block_device *); struct super_block *freeze_bdev(struct block_device *); void thaw_bdev(struct block_device *, struct super_block *); diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index bcc9410761d9..1c1f5efffd64 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -499,6 +499,7 @@ struct cdrom_generic_command #define GPMODE_VENDOR_PAGE 0x00 #define GPMODE_R_W_ERROR_PAGE 0x01 #define GPMODE_WRITE_PARMS_PAGE 0x05 +#define GPMODE_WCACHING_PAGE 0x08 #define GPMODE_AUDIO_CTL_PAGE 0x0e #define GPMODE_POWER_PAGE 0x1a #define GPMODE_FAULT_FAIL_PAGE 0x1c @@ -947,6 +948,8 @@ struct cdrom_device_info { __u8 reserved : 6; /* not used yet */ int cdda_method; /* see flags */ __u8 last_sense; + __u8 media_written; /* dirty flag, DVD+RW bookkeeping */ + unsigned short mmc3_profile; /* current MMC3 profile */ int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 77f59742c407..71da7d1260cd 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -382,6 +382,8 @@ COMPATIBLE_IOCTL(CDROMREADALL) COMPATIBLE_IOCTL(DVD_READ_STRUCT) COMPATIBLE_IOCTL(DVD_WRITE_STRUCT) COMPATIBLE_IOCTL(DVD_AUTH) +/* pktcdvd */ +COMPATIBLE_IOCTL(PACKET_CTRL_CMD) /* Big L */ ULONG_IOCTL(LOOP_SET_FD) ULONG_IOCTL(LOOP_CHANGE_FD) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index b378e57b2743..f4bc1ac23daa 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -28,7 +28,7 @@ struct vfsmount; * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * - * hash comes first so it snuggles against d_parent and d_bucket in the + * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { @@ -91,7 +91,6 @@ struct dentry { * so they all fit in a 16-byte range, with 16-byte alignment. */ struct dentry *d_parent; /* parent directory */ - struct hlist_head *d_bucket; /* lookup hash bucket */ struct qstr d_name; struct list_head d_lru; /* LRU list */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 27e8183f4776..8cf0e3f290bf 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -22,9 +22,9 @@ typedef int (elevator_set_req_fn) (request_queue_t *, struct request *, int); typedef void (elevator_put_req_fn) (request_queue_t *, struct request *); typedef int (elevator_init_fn) (request_queue_t *, elevator_t *); -typedef void (elevator_exit_fn) (request_queue_t *, elevator_t *); +typedef void (elevator_exit_fn) (elevator_t *); -struct elevator_s +struct elevator_ops { elevator_merge_fn *elevator_merge_fn; elevator_merged_fn *elevator_merged_fn; @@ -48,12 +48,32 @@ struct elevator_s elevator_init_fn *elevator_init_fn; elevator_exit_fn *elevator_exit_fn; +}; - void *elevator_data; +#define ELV_NAME_MAX (16) - struct kobject kobj; +/* + * identifies an elevator type, such as AS or deadline + */ +struct elevator_type +{ + struct list_head list; + struct elevator_ops ops; + struct elevator_type *elevator_type; struct kobj_type *elevator_ktype; - const char *elevator_name; + char elevator_name[ELV_NAME_MAX]; + struct module *elevator_owner; +}; + +/* + * each queue has an elevator_queue assoicated with it + */ +struct elevator_queue +{ + struct elevator_ops *ops; + void *elevator_data; + struct kobject kobj; + struct elevator_type *elevator_type; }; /* @@ -79,28 +99,19 @@ extern int elv_set_request(request_queue_t *, struct request *, int); extern void elv_put_request(request_queue_t *, struct request *); /* - * noop I/O scheduler. always merges, always inserts new request at tail - */ -extern elevator_t elevator_noop; - -/* - * deadline i/o scheduler. uses request time outs to prevent indefinite - * starvation + * io scheduler registration */ -extern elevator_t iosched_deadline; +extern int elv_register(struct elevator_type *); +extern void elv_unregister(struct elevator_type *); /* - * anticipatory I/O scheduler + * io scheduler sysfs switching */ -extern elevator_t iosched_as; +extern ssize_t elv_iosched_show(request_queue_t *, char *); +extern ssize_t elv_iosched_store(request_queue_t *, const char *, size_t); -/* - * completely fair queueing I/O scheduler - */ -extern elevator_t iosched_cfq; - -extern int elevator_init(request_queue_t *, elevator_t *); -extern void elevator_exit(request_queue_t *); +extern int elevator_init(request_queue_t *, char *); +extern void elevator_exit(elevator_t *); extern int elv_rq_merge_ok(struct request *, struct bio *); extern int elv_try_merge(struct request *, struct bio *); extern int elv_try_last_merge(request_queue_t *, struct bio *); @@ -119,4 +130,13 @@ extern int elv_try_last_merge(request_queue_t *, struct bio *); #define ELEVATOR_INSERT_BACK 2 #define ELEVATOR_INSERT_SORT 3 +/* + * return values from elevator_may_queue_fn + */ +enum { + ELV_MQUEUE_MAY, + ELV_MQUEUE_NO, + ELV_MQUEUE_MUST, +}; + #endif diff --git a/include/linux/fb.h b/include/linux/fb.h index c38132231c64..a09f31d7c6ee 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -318,6 +318,7 @@ struct fb_cursor { struct fbcurpos hot; /* cursor hot spot */ struct fb_image image; /* Cursor image */ /* all fields below are for fbcon use only */ + int flash; /* cursor blink */ char *data; /* copy of bitmap */ }; @@ -555,6 +556,82 @@ struct fb_ops { int (*fb_mmap)(struct fb_info *info, struct file *file, struct vm_area_struct *vma); }; +#ifdef CONFIG_FB_TILEBLITTING + +#define FB_TILE_CURSOR_NONE 0 +#define FB_TILE_CURSOR_UNDERLINE 1 +#define FB_TILE_CURSOR_LOWER_THIRD 2 +#define FB_TILE_CURSOR_LOWER_HALF 3 +#define FB_TILE_CURSOR_TWO_THIRDS 4 +#define FB_TILE_CURSOR_BLOCK 5 + +struct fb_tilemap { + __u32 width; /* width of each tile in pixels */ + __u32 height; /* height of each tile in scanlines */ + __u32 depth; /* color depth of each tile */ + __u32 length; /* number of tiles in the map */ + __u8 *data; /* actual tile map: a bitmap array, packed + to the nearest byte */ +}; + +struct fb_tilerect { + __u32 sx; /* origin in the x-axis */ + __u32 sy; /* origin in the y-axis */ + __u32 width; /* number of tiles in the x-axis */ + __u32 height; /* number of tiles in the y-axis */ + __u32 index; /* what tile to use: index to tile map */ + __u32 fg; /* foreground color */ + __u32 bg; /* background color */ + __u32 rop; /* raster operation */ +}; + +struct fb_tilearea { + __u32 sx; /* source origin in the x-axis */ + __u32 sy; /* source origin in the y-axis */ + __u32 dx; /* destination origin in the x-axis */ + __u32 dy; /* destination origin in the y-axis */ + __u32 width; /* number of tiles in the x-axis */ + __u32 height; /* number of tiles in the y-axis */ +}; + +struct fb_tileblit { + __u32 sx; /* origin in the x-axis */ + __u32 sy; /* origin in the y-axis */ + __u32 width; /* number of tiles in the x-axis */ + __u32 height; /* number of tiles in the y-axis */ + __u32 fg; /* foreground color */ + __u32 bg; /* background color */ + __u32 length; /* number of tiles to draw */ + __u32 *indices; /* array of indices to tile map */ +}; + +struct fb_tilecursor { + __u32 sx; /* cursor position in the x-axis */ + __u32 sy; /* cursor position in the y-axis */ + __u32 mode; /* 0 = erase, 1 = draw */ + __u32 shape; /* see FB_TILE_CURSOR_* */ + __u32 fg; /* foreground color */ + __u32 bg; /* background color */ +}; + +struct fb_tile_ops { + /* set tile characteristics */ + void (*fb_settile)(struct fb_info *info, struct fb_tilemap *map); + + /* all dimensions from hereon are in terms of tiles */ + + /* move a rectangular region of tiles from one area to another*/ + void (*fb_tilecopy)(struct fb_info *info, struct fb_tilearea *area); + /* fill a rectangular region with a tile */ + void (*fb_tilefill)(struct fb_info *info, struct fb_tilerect *rect); + /* copy an array of tiles */ + void (*fb_tileblit)(struct fb_info *info, struct fb_tileblit *blit); + /* cursor */ + void (*fb_tilecursor)(struct fb_info *info, + struct fb_tilecursor *cursor); +}; +#endif /* CONFIG_FB_TILEBLITTING */ + /* FBINFO_* = fb_info.flags bit flags */ #define FBINFO_MODULE 0x0001 /* Low-level driver is a module */ #define FBINFO_HWACCEL_DISABLED 0x0002 @@ -586,6 +663,7 @@ struct fb_ops { from userspace */ #define FBINFO_MISC_MODESWITCH 0x20000 /* mode switch */ #define FBINFO_MISC_MODESWITCHLATE 0x40000 /* init hardware later */ +#define FBINFO_MISC_TILEBLITTING 0x80000 /* use tile blitting */ struct fb_info { int node; @@ -601,6 +679,10 @@ struct fb_info { struct fb_cmap cmap; /* Current cmap */ struct list_head modelist; /* mode list */ struct fb_ops *fbops; + struct device *device; +#ifdef CONFIG_FB_TILEBLITTING + struct fb_tile_ops *tileops; /* Tile Blitting */ +#endif char __iomem *screen_base; /* Virtual address */ unsigned long screen_size; /* Amount of ioremapped VRAM or 0 */ int currcon; /* Current VC. */ @@ -608,7 +690,7 @@ struct fb_info { #define FBINFO_STATE_RUNNING 0 #define FBINFO_STATE_SUSPENDED 1 u32 state; /* Hardware state i.e suspend */ - + void *fbcon_par; /* fbcon use-only private area */ /* From here on everything is device dependent */ void *par; }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6fe6b575a8..6768655fd11d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -758,6 +758,7 @@ struct super_block { int s_need_sync_fs; atomic_t s_active; void *s_security; + struct xattr_handler **s_xattr; struct list_head s_dirty; /* dirty inodes */ struct list_head s_io; /* parked for writeback */ @@ -981,7 +982,8 @@ struct super_operations { #define I_DIRTY_SYNC 1 /* Not dirty enough for O_DATASYNC */ #define I_DIRTY_DATASYNC 2 /* Data-related inode changes pending */ #define I_DIRTY_PAGES 4 /* Data-related inode changes pending */ -#define I_LOCK 8 +#define __I_LOCK 3 +#define I_LOCK (1 << __I_LOCK) #define I_FREEING 16 #define I_CLEAR 32 #define I_NEW 64 @@ -1254,7 +1256,6 @@ extern struct block_device *bdget(dev_t); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); -extern int blkdev_open(struct inode *, struct file *); extern struct block_device *open_by_devnum(dev_t, unsigned); extern struct file_operations def_blk_fops; extern struct address_space_operations def_blk_aops; @@ -1339,7 +1340,9 @@ extern sector_t bmap(struct inode *, sector_t); extern int setattr_mask(unsigned int); extern int notify_change(struct dentry *, struct iattr *); extern int permission(struct inode *, int, struct nameidata *); -extern int vfs_permission(struct inode *, int); +extern int generic_permission(struct inode *, int, + int (*check_acl)(struct inode *, int)); + extern int get_write_access(struct inode *); extern int deny_write_access(struct file *); static inline void put_write_access(struct inode * inode) diff --git a/include/linux/i2o.h b/include/linux/i2o.h index a68437640135..3481de9c5837 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -147,10 +147,10 @@ struct i2o_controller { struct pci_dev *pdev; /* PCI device */ - int short_req:1; /* use small block sizes */ - int no_quiesce:1; /* dont quiesce before reset */ - int raptor:1; /* split bar */ - int promise:1; /* Promise controller */ + unsigned int short_req:1; /* use small block sizes */ + unsigned int no_quiesce:1; /* dont quiesce before reset */ + unsigned int raptor:1; /* split bar */ + unsigned int promise:1; /* Promise controller */ #ifdef CONFIG_MTRR int mtrr_reg0; @@ -180,9 +180,9 @@ struct i2o_controller { struct i2o_dma in_queue; /* inbound message queue Host->IOP */ struct i2o_dma out_queue; /* outbound message queue IOP->Host */ - int battery:1; /* Has a battery backup */ - int io_alloc:1; /* An I/O resource was allocated */ - int mem_alloc:1; /* A memory resource was allocated */ + unsigned int battery:1; /* Has a battery backup */ + unsigned int io_alloc:1; /* An I/O resource was allocated */ + unsigned int mem_alloc:1; /* A memory resource was allocated */ struct resource io_resource; /* I/O resource allocated to the IOP */ struct resource mem_resource; /* Mem resource allocated to the IOP */ diff --git a/include/linux/jbd.h b/include/linux/jbd.h index e65b90f1962c..dfdd307872bb 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -299,6 +299,7 @@ enum jbd_state_bits { BH_JBDDirty, /* Is dirty but journaled */ BH_State, /* Pins most journal_head state */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ + BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ }; BUFFER_FNS(JBD, jbd) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 459630f41680..d45eff83b906 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -3,10 +3,72 @@ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/spinlock.h> -#include <linux/seqlock.h> -#include <asm/system.h> +#include <linux/time.h> +#include <linux/timex.h> #include <asm/param.h> /* for HZ */ +#include <asm/div64.h> + +#ifndef div_long_long_rem +#define div_long_long_rem(dividend,divisor,remainder) \ +({ \ + u64 result = dividend; \ + *remainder = do_div(result,divisor); \ + result; \ +}) +#endif + +/* + * The following defines establish the engineering parameters of the PLL + * model. The HZ variable establishes the timer interrupt frequency, 100 Hz + * for the SunOS kernel, 256 Hz for the Ultrix kernel and 1024 Hz for the + * OSF/1 kernel. The SHIFT_HZ define expresses the same value as the + * nearest power of two in order to avoid hardware multiply operations. + */ +#if HZ >= 12 && HZ < 24 +# define SHIFT_HZ 4 +#elif HZ >= 24 && HZ < 48 +# define SHIFT_HZ 5 +#elif HZ >= 48 && HZ < 96 +# define SHIFT_HZ 6 +#elif HZ >= 96 && HZ < 192 +# define SHIFT_HZ 7 +#elif HZ >= 192 && HZ < 384 +# define SHIFT_HZ 8 +#elif HZ >= 384 && HZ < 768 +# define SHIFT_HZ 9 +#elif HZ >= 768 && HZ < 1536 +# define SHIFT_HZ 10 +#else +# error You lose. +#endif + +/* LATCH is used in the interval timer and ftape setup. */ +#define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ + +/* Suppose we want to devide two numbers NOM and DEN: NOM/DEN, the we can + * improve accuracy by shifting LSH bits, hence calculating: + * (NOM << LSH) / DEN + * This however means trouble for large NOM, because (NOM << LSH) may no + * longer fit in 32 bits. The following way of calculating this gives us + * some slack, under the following conditions: + * - (NOM / DEN) fits in (32 - LSH) bits. + * - (NOM % DEN) fits in (32 - LSH) bits. + */ +#define SH_DIV(NOM,DEN,LSH) ( ((NOM / DEN) << LSH) \ + + (((NOM % DEN) << LSH) + DEN / 2) / DEN) + +/* HZ is the requested value. ACTHZ is actual HZ ("<< 8" is for accuracy) */ +#define ACTHZ (SH_DIV (CLOCK_TICK_RATE, LATCH, 8)) + +/* TICK_NSEC is the time between ticks in nsec assuming real ACTHZ */ +#define TICK_NSEC (SH_DIV (1000000UL * 1000, ACTHZ, 8)) + +/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ +#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) + +/* TICK_USEC_TO_NSEC is the time between ticks in nsec assuming real ACTHZ and */ +/* a value TUSEC for TICK_USEC (can be set bij adjtimex) */ +#define TICK_USEC_TO_NSEC(TUSEC) (SH_DIV (TUSEC * USER_HZ * 1000, ACTHZ, 8)) /* * The 64-bit value is not volatile - you MUST NOT read it @@ -50,4 +112,320 @@ static inline u64 get_jiffies_64(void) ((long)(a) - (long)(b) >= 0)) #define time_before_eq(a,b) time_after_eq(b,a) +/* + * Have the 32 bit jiffies value wrap 5 minutes after boot + * so jiffies wrap bugs show up earlier. + */ +#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) + +/* + * Change timeval to jiffies, trying to avoid the + * most obvious overflows.. + * + * And some not so obvious. + * + * Note that we don't want to return MAX_LONG, because + * for various timeout reasons we often end up having + * to wait "jiffies+1" in order to guarantee that we wait + * at _least_ "jiffies" - so "jiffies+1" had better still + * be positive. + */ +#define MAX_JIFFY_OFFSET ((~0UL >> 1)-1) + +/* + * We want to do realistic conversions of time so we need to use the same + * values the update wall clock code uses as the jiffies size. This value + * is: TICK_NSEC (which is defined in timex.h). This + * is a constant and is in nanoseconds. We will used scaled math + * with a set of scales defined here as SEC_JIFFIE_SC, USEC_JIFFIE_SC and + * NSEC_JIFFIE_SC. Note that these defines contain nothing but + * constants and so are computed at compile time. SHIFT_HZ (computed in + * timex.h) adjusts the scaling for different HZ values. + + * Scaled math??? What is that? + * + * Scaled math is a way to do integer math on values that would, + * otherwise, either overflow, underflow, or cause undesired div + * instructions to appear in the execution path. In short, we "scale" + * up the operands so they take more bits (more precision, less + * underflow), do the desired operation and then "scale" the result back + * by the same amount. If we do the scaling by shifting we avoid the + * costly mpy and the dastardly div instructions. + + * Suppose, for example, we want to convert from seconds to jiffies + * where jiffies is defined in nanoseconds as NSEC_PER_JIFFIE. The + * simple math is: jiff = (sec * NSEC_PER_SEC) / NSEC_PER_JIFFIE; We + * observe that (NSEC_PER_SEC / NSEC_PER_JIFFIE) is a constant which we + * might calculate at compile time, however, the result will only have + * about 3-4 bits of precision (less for smaller values of HZ). + * + * So, we scale as follows: + * jiff = (sec) * (NSEC_PER_SEC / NSEC_PER_JIFFIE); + * jiff = ((sec) * ((NSEC_PER_SEC * SCALE)/ NSEC_PER_JIFFIE)) / SCALE; + * Then we make SCALE a power of two so: + * jiff = ((sec) * ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) >> SCALE; + * Now we define: + * #define SEC_CONV = ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) + * jiff = (sec * SEC_CONV) >> SCALE; + * + * Often the math we use will expand beyond 32-bits so we tell C how to + * do this and pass the 64-bit result of the mpy through the ">> SCALE" + * which should take the result back to 32-bits. We want this expansion + * to capture as much precision as possible. At the same time we don't + * want to overflow so we pick the SCALE to avoid this. In this file, + * that means using a different scale for each range of HZ values (as + * defined in timex.h). + * + * For those who want to know, gcc will give a 64-bit result from a "*" + * operator if the result is a long long AND at least one of the + * operands is cast to long long (usually just prior to the "*" so as + * not to confuse it into thinking it really has a 64-bit operand, + * which, buy the way, it can do, but it take more code and at least 2 + * mpys). + + * We also need to be aware that one second in nanoseconds is only a + * couple of bits away from overflowing a 32-bit word, so we MUST use + * 64-bits to get the full range time in nanoseconds. + + */ + +/* + * Here are the scales we will use. One for seconds, nanoseconds and + * microseconds. + * + * Within the limits of cpp we do a rough cut at the SEC_JIFFIE_SC and + * check if the sign bit is set. If not, we bump the shift count by 1. + * (Gets an extra bit of precision where we can use it.) + * We know it is set for HZ = 1024 and HZ = 100 not for 1000. + * Haven't tested others. + + * Limits of cpp (for #if expressions) only long (no long long), but + * then we only need the most signicant bit. + */ + +#define SEC_JIFFIE_SC (31 - SHIFT_HZ) +#if !((((NSEC_PER_SEC << 2) / TICK_NSEC) << (SEC_JIFFIE_SC - 2)) & 0x80000000) +#undef SEC_JIFFIE_SC +#define SEC_JIFFIE_SC (32 - SHIFT_HZ) +#endif +#define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) +#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19) +#define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ + TICK_NSEC -1) / (u64)TICK_NSEC)) + +#define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ + TICK_NSEC -1) / (u64)TICK_NSEC)) +#define USEC_CONVERSION \ + ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\ + TICK_NSEC -1) / (u64)TICK_NSEC)) +/* + * USEC_ROUND is used in the timeval to jiffie conversion. See there + * for more details. It is the scaled resolution rounding value. Note + * that it is a 64-bit value. Since, when it is applied, we are already + * in jiffies (albit scaled), it is nothing but the bits we will shift + * off. + */ +#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1) +/* + * The maximum jiffie value is (MAX_INT >> 1). Here we translate that + * into seconds. The 64-bit case will overflow if we are not careful, + * so use the messy SH_DIV macro to do it. Still all constants. + */ +#if BITS_PER_LONG < 64 +# define MAX_SEC_IN_JIFFIES \ + (long)((u64)((u64)MAX_JIFFY_OFFSET * TICK_NSEC) / NSEC_PER_SEC) +#else /* take care of overflow on 64 bits machines */ +# define MAX_SEC_IN_JIFFIES \ + (SH_DIV((MAX_JIFFY_OFFSET >> SEC_JIFFIE_SC) * TICK_NSEC, NSEC_PER_SEC, 1) - 1) + +#endif + +/* + * Convert jiffies to milliseconds and back. + * + * Avoid unnecessary multiplications/divisions in the + * two most common HZ cases: + */ +static inline unsigned int jiffies_to_msecs(const unsigned long j) +{ +#if HZ <= 1000 && !(1000 % HZ) + return (1000 / HZ) * j; +#elif HZ > 1000 && !(HZ % 1000) + return (j + (HZ / 1000) - 1)/(HZ / 1000); +#else + return (j * 1000) / HZ; +#endif +} + +static inline unsigned int jiffies_to_usecs(const unsigned long j) +{ +#if HZ <= 1000 && !(1000 % HZ) + return (1000000 / HZ) * j; +#elif HZ > 1000 && !(HZ % 1000) + return (j*1000 + (HZ - 1000))/(HZ / 1000); +#else + return (j * 1000000) / HZ; +#endif +} + +static inline unsigned long msecs_to_jiffies(const unsigned int m) +{ + if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; +#if HZ <= 1000 && !(1000 % HZ) + return (m + (1000 / HZ) - 1) / (1000 / HZ); +#elif HZ > 1000 && !(HZ % 1000) + return m * (HZ / 1000); +#else + return (m * HZ + 999) / 1000; +#endif +} + +/* + * The TICK_NSEC - 1 rounds up the value to the next resolution. Note + * that a remainder subtract here would not do the right thing as the + * resolution values don't fall on second boundries. I.e. the line: + * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. + * + * Rather, we just shift the bits off the right. + * + * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec + * value to a scaled second value. + */ +static __inline__ unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + unsigned long sec = value->tv_sec; + long nsec = value->tv_nsec + TICK_NSEC - 1; + + if (sec >= MAX_SEC_IN_JIFFIES){ + sec = MAX_SEC_IN_JIFFIES; + nsec = 0; + } + return (((u64)sec * SEC_CONVERSION) + + (((u64)nsec * NSEC_CONVERSION) >> + (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + +} + +static __inline__ void +jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) +{ + /* + * Convert jiffies to nanoseconds and separate with + * one divide. + */ + u64 nsec = (u64)jiffies * TICK_NSEC; + value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec); +} + +/* Same for "timeval" + * + * Well, almost. The problem here is that the real system resolution is + * in nanoseconds and the value being converted is in micro seconds. + * Also for some machines (those that use HZ = 1024, in-particular), + * there is a LARGE error in the tick size in microseconds. + + * The solution we use is to do the rounding AFTER we convert the + * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. + * Instruction wise, this should cost only an additional add with carry + * instruction above the way it was done above. + */ +static __inline__ unsigned long +timeval_to_jiffies(const struct timeval *value) +{ + unsigned long sec = value->tv_sec; + long usec = value->tv_usec; + + if (sec >= MAX_SEC_IN_JIFFIES){ + sec = MAX_SEC_IN_JIFFIES; + usec = 0; + } + return (((u64)sec * SEC_CONVERSION) + + (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> + (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; +} + +static __inline__ void +jiffies_to_timeval(const unsigned long jiffies, struct timeval *value) +{ + /* + * Convert jiffies to nanoseconds and separate with + * one divide. + */ + u64 nsec = (u64)jiffies * TICK_NSEC; + value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_usec); + value->tv_usec /= NSEC_PER_USEC; +} + +/* + * Convert jiffies/jiffies_64 to clock_t and back. + */ +static inline clock_t jiffies_to_clock_t(long x) +{ +#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 + return x / (HZ / USER_HZ); +#else + u64 tmp = (u64)x * TICK_NSEC; + do_div(tmp, (NSEC_PER_SEC / USER_HZ)); + return (long)tmp; +#endif +} + +static inline unsigned long clock_t_to_jiffies(unsigned long x) +{ +#if (HZ % USER_HZ)==0 + if (x >= ~0UL / (HZ / USER_HZ)) + return ~0UL; + return x * (HZ / USER_HZ); +#else + u64 jif; + + /* Don't worry about loss of precision here .. */ + if (x >= ~0UL / HZ * USER_HZ) + return ~0UL; + + /* .. but do try to contain it here */ + jif = x * (u64) HZ; + do_div(jif, USER_HZ); + return jif; +#endif +} + +static inline u64 jiffies_64_to_clock_t(u64 x) +{ +#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 + do_div(x, HZ / USER_HZ); +#else + /* + * There are better ways that don't overflow early, + * but even this doesn't overflow in hundreds of years + * in 64 bits, so.. + */ + x *= TICK_NSEC; + do_div(x, (NSEC_PER_SEC / USER_HZ)); +#endif + return x; +} + +static inline u64 nsec_to_clock_t(u64 x) +{ +#if (NSEC_PER_SEC % USER_HZ) == 0 + do_div(x, (NSEC_PER_SEC / USER_HZ)); +#elif (USER_HZ % 512) == 0 + x *= USER_HZ/512; + do_div(x, (NSEC_PER_SEC / 512)); +#else + /* + * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, + * overflow after 64.99 years. + * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... + */ + x *= 9; + do_div(x, (unsigned long)((9ull * NSEC_PER_SEC + (USER_HZ/2)) + / USER_HZ)); +#endif + return x; +} + #endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 40307a28bb4b..cf2f984e1b95 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -136,6 +136,7 @@ extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in extern int panic_on_oops; extern int tainted; extern const char *print_tainted(void); +extern void add_taint(unsigned); /* Values used for system_state */ extern enum system_states { @@ -150,6 +151,8 @@ extern enum system_states { #define TAINT_FORCED_MODULE (1<<1) #define TAINT_UNSAFE_SMP (1<<2) #define TAINT_FORCED_RMMOD (1<<3) +#define TAINT_MACHINE_CHECK (1<<4) +#define TAINT_BAD_PAGE (1<<5) extern void dump_stack(void); diff --git a/include/linux/key-ui.h b/include/linux/key-ui.h new file mode 100644 index 000000000000..60cc7b762e78 --- /dev/null +++ b/include/linux/key-ui.h @@ -0,0 +1,97 @@ +/* key-ui.h: key userspace interface stuff for use by keyfs + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _LINUX_KEY_UI_H +#define _LINUX_KEY_UI_H + +#include <linux/key.h> + +/* the key tree */ +extern struct rb_root key_serial_tree; +extern spinlock_t key_serial_lock; + +/* required permissions */ +#define KEY_VIEW 0x01 /* require permission to view attributes */ +#define KEY_READ 0x02 /* require permission to read content */ +#define KEY_WRITE 0x04 /* require permission to update / modify */ +#define KEY_SEARCH 0x08 /* require permission to search (keyring) or find (key) */ +#define KEY_LINK 0x10 /* require permission to link */ +#define KEY_ALL 0x1f /* all the above permissions */ + +/* + * the keyring payload contains a list of the keys to which the keyring is + * subscribed + */ +struct keyring_list { + unsigned maxkeys; /* max keys this list can hold */ + unsigned nkeys; /* number of keys currently held */ + struct key *keys[0]; +}; + + +/* + * check to see whether permission is granted to use a key in the desired way + */ +static inline int key_permission(const struct key *key, key_perm_t perm) +{ + key_perm_t kperm; + + if (key->uid == current->fsuid) + kperm = key->perm >> 16; + else if (key->gid != -1 && + key->perm & KEY_GRP_ALL && + in_group_p(key->gid) + ) + kperm = key->perm >> 8; + else + kperm = key->perm; + + kperm = kperm & perm & KEY_ALL; + + return kperm == perm; +} + +/* + * check to see whether permission is granted to use a key in at least one of + * the desired ways + */ +static inline int key_any_permission(const struct key *key, key_perm_t perm) +{ + key_perm_t kperm; + + if (key->uid == current->fsuid) + kperm = key->perm >> 16; + else if (key->gid != -1 && + key->perm & KEY_GRP_ALL && + in_group_p(key->gid) + ) + kperm = key->perm >> 8; + else + kperm = key->perm; + + kperm = kperm & perm & KEY_ALL; + + return kperm != 0; +} + + +extern struct key *lookup_user_key(key_serial_t id, int create, int part, + key_perm_t perm); + +extern long join_session_keyring(const char *name); + +extern struct key_type *key_type_lookup(const char *type); +extern void key_type_put(struct key_type *ktype); + +#define key_negative_timeout 60 /* default timeout on a negative key's existence */ + + +#endif /* _LINUX_KEY_UI_H */ diff --git a/include/linux/key.h b/include/linux/key.h new file mode 100644 index 000000000000..e914be777c4a --- /dev/null +++ b/include/linux/key.h @@ -0,0 +1,284 @@ +/* key.h: authentication token and access key management + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * + * See Documentation/keys.txt for information on keys/keyrings. + */ + +#ifndef _LINUX_KEY_H +#define _LINUX_KEY_H + +#include <linux/types.h> +#include <linux/list.h> +#include <linux/rbtree.h> +#include <linux/spinlock.h> +#include <asm/atomic.h> + +#ifdef __KERNEL__ + +/* key handle serial number */ +typedef int32_t key_serial_t; + +/* key handle permissions mask */ +typedef uint32_t key_perm_t; + +struct key; + +#ifdef CONFIG_KEYS + +#undef KEY_DEBUGGING + +#define KEY_USR_VIEW 0x00010000 /* user can view a key's attributes */ +#define KEY_USR_READ 0x00020000 /* user can read key payload / view keyring */ +#define KEY_USR_WRITE 0x00040000 /* user can update key payload / add link to keyring */ +#define KEY_USR_SEARCH 0x00080000 /* user can find a key in search / search a keyring */ +#define KEY_USR_LINK 0x00100000 /* user can create a link to a key/keyring */ +#define KEY_USR_ALL 0x001f0000 + +#define KEY_GRP_VIEW 0x00000100 /* group permissions... */ +#define KEY_GRP_READ 0x00000200 +#define KEY_GRP_WRITE 0x00000400 +#define KEY_GRP_SEARCH 0x00000800 +#define KEY_GRP_LINK 0x00001000 +#define KEY_GRP_ALL 0x00001f00 + +#define KEY_OTH_VIEW 0x00000001 /* third party permissions... */ +#define KEY_OTH_READ 0x00000002 +#define KEY_OTH_WRITE 0x00000004 +#define KEY_OTH_SEARCH 0x00000008 +#define KEY_OTH_LINK 0x00000010 +#define KEY_OTH_ALL 0x0000001f + +struct seq_file; +struct user_struct; + +struct key_type; +struct key_owner; +struct keyring_list; +struct keyring_name; + +/*****************************************************************************/ +/* + * authentication token / access credential / keyring + * - types of key include: + * - keyrings + * - disk encryption IDs + * - Kerberos TGTs and tickets + */ +struct key { + atomic_t usage; /* number of references */ + key_serial_t serial; /* key serial number */ + struct rb_node serial_node; + struct key_type *type; /* type of key */ + rwlock_t lock; /* examination vs change lock */ + struct rw_semaphore sem; /* change vs change sem */ + struct key_user *user; /* owner of this key */ + time_t expiry; /* time at which key expires (or 0) */ + uid_t uid; + gid_t gid; + key_perm_t perm; /* access permissions */ + unsigned short quotalen; /* length added to quota */ + unsigned short datalen; /* payload data length */ + unsigned short flags; /* status flags (change with lock writelocked) */ +#define KEY_FLAG_INSTANTIATED 0x00000001 /* set if key has been instantiated */ +#define KEY_FLAG_DEAD 0x00000002 /* set if key type has been deleted */ +#define KEY_FLAG_REVOKED 0x00000004 /* set if key had been revoked */ +#define KEY_FLAG_IN_QUOTA 0x00000008 /* set if key consumes quota */ +#define KEY_FLAG_USER_CONSTRUCT 0x00000010 /* set if key is being constructed in userspace */ +#define KEY_FLAG_NEGATIVE 0x00000020 /* set if key is negative */ + +#ifdef KEY_DEBUGGING + unsigned magic; +#define KEY_DEBUG_MAGIC 0x18273645u +#define KEY_DEBUG_MAGIC_X 0xf8e9dacbu +#endif + + /* the description string + * - this is used to match a key against search criteria + * - this should be a printable string + * - eg: for krb5 AFS, this might be "afs@REDHAT.COM" + */ + char *description; + + /* type specific data + * - this is used by the keyring type to index the name + */ + union { + struct list_head link; + } type_data; + + /* key data + * - this is used to hold the data actually used in cryptography or + * whatever + */ + union { + unsigned long value; + void *data; + struct keyring_list *subscriptions; + } payload; +}; + +/*****************************************************************************/ +/* + * kernel managed key type definition + */ +struct key_type { + /* name of the type */ + const char *name; + + /* default payload length for quota precalculation (optional) + * - this can be used instead of calling key_payload_reserve(), that + * function only needs to be called if the real datalen is different + */ + size_t def_datalen; + + /* instantiate a key of this type + * - this method should call key_payload_reserve() to determine if the + * user's quota will hold the payload + */ + int (*instantiate)(struct key *key, const void *data, size_t datalen); + + /* duplicate a key of this type (optional) + * - the source key will be locked against change + * - the new description will be attached + * - the quota will have been adjusted automatically from + * source->quotalen + */ + int (*duplicate)(struct key *key, const struct key *source); + + /* update a key of this type (optional) + * - this method should call key_payload_reserve() to recalculate the + * quota consumption + * - the key must be locked against read when modifying + */ + int (*update)(struct key *key, const void *data, size_t datalen); + + /* match a key against a description */ + int (*match)(const struct key *key, const void *desc); + + /* clear the data from a key (optional) */ + void (*destroy)(struct key *key); + + /* describe a key */ + void (*describe)(const struct key *key, struct seq_file *p); + + /* read a key's data (optional) + * - permission checks will be done by the caller + * - the key's semaphore will be readlocked by the caller + * - should return the amount of data that could be read, no matter how + * much is copied into the buffer + * - shouldn't do the copy if the buffer is NULL + */ + long (*read)(const struct key *key, char __user *buffer, size_t buflen); + + /* internal fields */ + struct list_head link; /* link in types list */ +}; + +extern struct key_type key_type_keyring; + +extern int register_key_type(struct key_type *ktype); +extern void unregister_key_type(struct key_type *ktype); + +extern struct key *key_alloc(struct key_type *type, + const char *desc, + uid_t uid, gid_t gid, key_perm_t perm, + int not_in_quota); +extern int key_payload_reserve(struct key *key, size_t datalen); +extern int key_instantiate_and_link(struct key *key, + const void *data, + size_t datalen, + struct key *keyring); +extern int key_negate_and_link(struct key *key, + unsigned timeout, + struct key *keyring); +extern void key_revoke(struct key *key); +extern void key_put(struct key *key); + +static inline struct key *key_get(struct key *key) +{ + if (key) + atomic_inc(&key->usage); + return key; +} + +extern struct key *request_key(struct key_type *type, + const char *description, + const char *callout_info); + +extern int key_validate(struct key *key); + +extern struct key *key_create_or_update(struct key *keyring, + const char *type, + const char *description, + const void *payload, + size_t plen, + int not_in_quota); + +extern int key_update(struct key *key, + const void *payload, + size_t plen); + +extern int key_link(struct key *keyring, + struct key *key); + +extern int key_unlink(struct key *keyring, + struct key *key); + +extern struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid, + int not_in_quota, struct key *dest); + +extern int keyring_clear(struct key *keyring); + +extern struct key *keyring_search(struct key *keyring, + struct key_type *type, + const char *description); + +extern struct key *search_process_keyrings(struct key_type *type, + const char *description); + +extern int keyring_add_key(struct key *keyring, + struct key *key); + +extern struct key *key_lookup(key_serial_t id); + +#define key_serial(key) ((key) ? (key)->serial : 0) + +/* + * the userspace interface + */ +extern struct key root_user_keyring, root_session_keyring; +extern int alloc_uid_keyring(struct user_struct *user); +extern void switch_uid_keyring(struct user_struct *new_user); +extern int copy_keys(unsigned long clone_flags, struct task_struct *tsk); +extern void exit_keys(struct task_struct *tsk); +extern int suid_keys(struct task_struct *tsk); +extern int exec_keys(struct task_struct *tsk); +extern void key_fsuid_changed(struct task_struct *tsk); +extern void key_fsgid_changed(struct task_struct *tsk); + +#else /* CONFIG_KEYS */ + +#define key_validate(k) 0 +#define key_serial(k) 0 +#define key_get(k) NULL +#define key_put(k) do { } while(0) +#define alloc_uid_keyring(u) 0 +#define switch_uid_keyring(u) do { } while(0) +#define copy_keys(f,t) 0 +#define exit_keys(t) do { } while(0) +#define suid_keys(t) do { } while(0) +#define exec_keys(t) do { } while(0) +#define key_fsuid_changed(t) do { } while(0) +#define key_fsgid_changed(t) do { } while(0) + +#endif /* CONFIG_KEYS */ +#endif /* __KERNEL__ */ +#endif /* _LINUX_KEY_H */ diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h new file mode 100644 index 000000000000..381dedc370a3 --- /dev/null +++ b/include/linux/keyctl.h @@ -0,0 +1,39 @@ +/* keyctl.h: keyctl command IDs + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _LINUX_KEYCTL_H +#define _LINUX_KEYCTL_H + +/* special process keyring shortcut IDs */ +#define KEY_SPEC_THREAD_KEYRING -1 /* - key ID for thread-specific keyring */ +#define KEY_SPEC_PROCESS_KEYRING -2 /* - key ID for process-specific keyring */ +#define KEY_SPEC_SESSION_KEYRING -3 /* - key ID for session-specific keyring */ +#define KEY_SPEC_USER_KEYRING -4 /* - key ID for UID-specific keyring */ +#define KEY_SPEC_USER_SESSION_KEYRING -5 /* - key ID for UID-session keyring */ +#define KEY_SPEC_GROUP_KEYRING -6 /* - key ID for GID-specific keyring */ + +/* keyctl commands */ +#define KEYCTL_GET_KEYRING_ID 0 /* ask for a keyring's ID */ +#define KEYCTL_JOIN_SESSION_KEYRING 1 /* join or start named session keyring */ +#define KEYCTL_UPDATE 2 /* update a key */ +#define KEYCTL_REVOKE 3 /* revoke a key */ +#define KEYCTL_CHOWN 4 /* set ownership of a key */ +#define KEYCTL_SETPERM 5 /* set perms on a key */ +#define KEYCTL_DESCRIBE 6 /* describe a key */ +#define KEYCTL_CLEAR 7 /* clear contents of a keyring */ +#define KEYCTL_LINK 8 /* link a key into a keyring */ +#define KEYCTL_UNLINK 9 /* unlink a key from a keyring */ +#define KEYCTL_SEARCH 10 /* search for a key in a keyring */ +#define KEYCTL_READ 11 /* read a key or keyring's contents */ +#define KEYCTL_INSTANTIATE 12 /* instantiate a partially constructed key */ +#define KEYCTL_NEGATE 13 /* negate a partially constructed key */ + +#endif /* _LINUX_KEYCTL_H */ diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h new file mode 100644 index 000000000000..0e6e972a9f70 --- /dev/null +++ b/include/linux/kfifo.h @@ -0,0 +1,157 @@ +/* + * A simple kernel FIFO implementation. + * + * Copyright (C) 2004 Stelian Pop <stelian@popies.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ +#ifndef _LINUX_KFIFO_H +#define _LINUX_KFIFO_H + +#ifdef __KERNEL__ + +#include <linux/kernel.h> +#include <linux/spinlock.h> + +struct kfifo { + unsigned char *buffer; /* the buffer holding the data */ + unsigned int size; /* the size of the allocated buffer */ + unsigned int in; /* data is added at offset (in % size) */ + unsigned int out; /* data is extracted from off. (out % size) */ + spinlock_t *lock; /* protects concurrent modifications */ +}; + +extern struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size, + int gfp_mask, spinlock_t *lock); +extern struct kfifo *kfifo_alloc(unsigned int size, int gfp_mask, + spinlock_t *lock); +extern void kfifo_free(struct kfifo *fifo); +extern unsigned int __kfifo_put(struct kfifo *fifo, + unsigned char *buffer, unsigned int len); +extern unsigned int __kfifo_get(struct kfifo *fifo, + unsigned char *buffer, unsigned int len); + +/* + * __kfifo_reset - removes the entire FIFO contents, no locking version + * @fifo: the fifo to be emptied. + */ +static inline void __kfifo_reset(struct kfifo *fifo) +{ + fifo->in = fifo->out = 0; +} + +/* + * kfifo_reset - removes the entire FIFO contents + * @fifo: the fifo to be emptied. + */ +static inline void kfifo_reset(struct kfifo *fifo) +{ + unsigned long flags; + + spin_lock_irqsave(fifo->lock, flags); + + __kfifo_reset(fifo); + + spin_unlock_irqrestore(fifo->lock, flags); +} + +/* + * kfifo_put - puts some data into the FIFO + * @fifo: the fifo to be used. + * @buffer: the data to be added. + * @len: the length of the data to be added. + * + * This function copies at most 'len' bytes from the 'buffer' into + * the FIFO depending on the free space, and returns the number of + * bytes copied. + */ +static inline unsigned int kfifo_put(struct kfifo *fifo, + unsigned char *buffer, unsigned int len) +{ + unsigned long flags; + unsigned int ret; + + spin_lock_irqsave(fifo->lock, flags); + + ret = __kfifo_put(fifo, buffer, len); + + spin_unlock_irqrestore(fifo->lock, flags); + + return ret; +} + +/* + * kfifo_get - gets some data from the FIFO + * @fifo: the fifo to be used. + * @buffer: where the data must be copied. + * @len: the size of the destination buffer. + * + * This function copies at most 'len' bytes from the FIFO into the + * 'buffer' and returns the number of copied bytes. + */ +static inline unsigned int kfifo_get(struct kfifo *fifo, + unsigned char *buffer, unsigned int len) +{ + unsigned long flags; + unsigned int ret; + + spin_lock_irqsave(fifo->lock, flags); + + ret = __kfifo_get(fifo, buffer, len); + + /* + * optimization: if the FIFO is empty, set the indices to 0 + * so we don't wrap the next time + */ + if (fifo->in == fifo->out) + fifo->in = fifo->out = 0; + + spin_unlock_irqrestore(fifo->lock, flags); + + return ret; +} + +/* + * __kfifo_len - returns the number of bytes available in the FIFO, no locking version + * @fifo: the fifo to be used. + */ +static inline unsigned int __kfifo_len(struct kfifo *fifo) +{ + return fifo->in - fifo->out; +} + +/* + * kfifo_len - returns the number of bytes available in the FIFO + * @fifo: the fifo to be used. + */ +static inline unsigned int kfifo_len(struct kfifo *fifo) +{ + unsigned long flags; + unsigned int ret; + + spin_lock_irqsave(fifo->lock, flags); + + ret = __kfifo_len(fifo); + + spin_unlock_irqrestore(fifo->lock, flags); + + return ret; +} + +#else +#warning "don't include kernel headers in userspace" +#endif /* __KERNEL__ */ +#endif diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 7738749e1285..15a806ad61ee 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -56,9 +56,7 @@ int mb_cache_entry_insert(struct mb_cache_entry *, struct block_device *, sector_t, unsigned int[]); void mb_cache_entry_rehash(struct mb_cache_entry *, unsigned int[]); void mb_cache_entry_release(struct mb_cache_entry *); -void mb_cache_entry_takeout(struct mb_cache_entry *); void mb_cache_entry_free(struct mb_cache_entry *); -struct mb_cache_entry *mb_cache_entry_dup(struct mb_cache_entry *); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *, struct block_device *, sector_t); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7c36a10f6720..b812151cdd07 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -410,35 +410,6 @@ extern struct pglist_data contig_page_data; #error ZONES_SHIFT > MAX_ZONES_SHIFT #endif -extern DECLARE_BITMAP(node_online_map, MAX_NUMNODES); - -#if defined(CONFIG_DISCONTIGMEM) || defined(CONFIG_NUMA) - -#define node_online(node) test_bit(node, node_online_map) -#define node_set_online(node) set_bit(node, node_online_map) -#define node_set_offline(node) clear_bit(node, node_online_map) -static inline unsigned int num_online_nodes(void) -{ - int i, num = 0; - - for(i = 0; i < MAX_NUMNODES; i++){ - if (node_online(i)) - num++; - } - return num; -} - -#else /* !CONFIG_DISCONTIGMEM && !CONFIG_NUMA */ - -#define node_online(node) \ - ({ BUG_ON((node) != 0); test_bit(node, node_online_map); }) -#define node_set_online(node) \ - ({ BUG_ON((node) != 0); set_bit(node, node_online_map); }) -#define node_set_offline(node) \ - ({ BUG_ON((node) != 0); clear_bit(node, node_online_map); }) -#define num_online_nodes() 1 - -#endif /* CONFIG_DISCONTIGMEM || CONFIG_NUMA */ #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _LINUX_MMZONE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index fbf2dfc90015..bebd8bc1fd20 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -550,40 +550,20 @@ struct obsolete_modparm { #define MODULE_PARM(var,type) \ struct obsolete_modparm __parm_##var __attribute__((section("__obsparm"))) = \ { __stringify(var), type }; - -static inline void __deprecated MOD_INC_USE_COUNT(struct module *module) -{ - __unsafe(module); - -#if defined(CONFIG_MODULE_UNLOAD) && defined(MODULE) - local_inc(&module->ref[get_cpu()].count); - put_cpu(); -#else - (void)try_module_get(module); -#endif -} - -static inline void __deprecated MOD_DEC_USE_COUNT(struct module *module) -{ - module_put(module); -} - -#define MOD_INC_USE_COUNT MOD_INC_USE_COUNT(THIS_MODULE) -#define MOD_DEC_USE_COUNT MOD_DEC_USE_COUNT(THIS_MODULE) #else #define MODULE_PARM(var,type) -#define MOD_INC_USE_COUNT do { } while (0) -#define MOD_DEC_USE_COUNT do { } while (0) #endif #define __MODULE_STRING(x) __stringify(x) /* Use symbol_get and symbol_put instead. You'll thank me. */ #define HAVE_INTER_MODULE -extern void inter_module_register(const char *, struct module *, const void *); -extern void inter_module_unregister(const char *); -extern const void *inter_module_get(const char *); -extern const void *inter_module_get_request(const char *, const char *); -extern void inter_module_put(const char *); +extern void __deprecated inter_module_register(const char *, + struct module *, const void *); +extern void __deprecated inter_module_unregister(const char *); +extern const void * __deprecated inter_module_get(const char *); +extern const void * __deprecated inter_module_get_request(const char *, + const char *); +extern void __deprecated inter_module_put(const char *); #endif /* _LINUX_MODULE_H */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h new file mode 100644 index 000000000000..4de843d94147 --- /dev/null +++ b/include/linux/nodemask.h @@ -0,0 +1,326 @@ +#ifndef __LINUX_NODEMASK_H +#define __LINUX_NODEMASK_H + +/* + * Nodemasks provide a bitmap suitable for representing the + * set of Node's in a system, one bit position per Node number. + * + * See detailed comments in the file linux/bitmap.h describing the + * data type on which these nodemasks are based. + * + * For details of nodemask_scnprintf() and nodemask_parse(), + * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * + * The available nodemask operations are: + * + * void node_set(node, mask) turn on bit 'node' in mask + * void node_clear(node, mask) turn off bit 'node' in mask + * void nodes_setall(mask) set all bits + * void nodes_clear(mask) clear all bits + * int node_isset(node, mask) true iff bit 'node' set in mask + * int node_test_and_set(node, mask) test and set bit 'node' in mask + * + * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] + * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] + * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 + * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 + * void nodes_complement(dst, src) dst = ~src + * + * int nodes_equal(mask1, mask2) Does mask1 == mask2? + * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? + * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? + * int nodes_empty(mask) Is mask empty (no bits sets)? + * int nodes_full(mask) Is mask full (all bits sets)? + * int nodes_weight(mask) Hamming weight - number of set bits + * + * void nodes_shift_right(dst, src, n) Shift right + * void nodes_shift_left(dst, src, n) Shift left + * + * int first_node(mask) Number lowest set bit, or MAX_NUMNODES + * int next_node(node, mask) Next node past 'node', or MAX_NUMNODES + * + * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set + * NODE_MASK_ALL Initializer - all bits set + * NODE_MASK_NONE Initializer - no bits set + * unsigned long *nodes_addr(mask) Array of unsigned long's in mask + * + * int nodemask_scnprintf(buf, len, mask) Format nodemask for printing + * int nodemask_parse(ubuf, ulen, mask) Parse ascii string as nodemask + * + * for_each_node_mask(node, mask) for-loop node over mask + * + * int num_online_nodes() Number of online Nodes + * int num_possible_nodes() Number of all possible Nodes + * + * int node_online(node) Is some node online? + * int node_possible(node) Is some node possible? + * + * int any_online_node(mask) First online node in mask + * + * node_set_online(node) set bit 'node' in node_online_map + * node_set_offline(node) clear bit 'node' in node_online_map + * + * for_each_node(node) for-loop node over node_possible_map + * for_each_online_node(node) for-loop node over node_online_map + * + * Subtlety: + * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) + * to generate slightly worse code. So use a simple one-line #define + * for node_isset(), instead of wrapping an inline inside a macro, the + * way we do the other calls. + */ + +#include <linux/kernel.h> +#include <linux/threads.h> +#include <linux/bitmap.h> +#include <linux/numa.h> +#include <asm/bug.h> + +typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; +extern nodemask_t _unused_nodemask_arg_; + +#define node_set(node, dst) __node_set((node), &(dst)) +static inline void __node_set(int node, volatile nodemask_t *dstp) +{ + set_bit(node, dstp->bits); +} + +#define node_clear(node, dst) __node_clear((node), &(dst)) +static inline void __node_clear(int node, volatile nodemask_t *dstp) +{ + clear_bit(node, dstp->bits); +} + +#define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) +static inline void __nodes_setall(nodemask_t *dstp, int nbits) +{ + bitmap_fill(dstp->bits, nbits); +} + +#define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) +static inline void __nodes_clear(nodemask_t *dstp, int nbits) +{ + bitmap_zero(dstp->bits, nbits); +} + +/* No static inline type checking - see Subtlety (1) above. */ +#define node_isset(node, nodemask) test_bit((node), (nodemask).bits) + +#define node_test_and_set(node, nodemask) \ + __node_test_and_set((node), &(nodemask)) +static inline int __node_test_and_set(int node, nodemask_t *addr) +{ + return test_and_set_bit(node, addr->bits); +} + +#define nodes_and(dst, src1, src2) \ + __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) +static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define nodes_or(dst, src1, src2) \ + __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) +static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define nodes_xor(dst, src1, src2) \ + __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) +static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define nodes_andnot(dst, src1, src2) \ + __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) +static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define nodes_complement(dst, src) \ + __nodes_complement(&(dst), &(src), MAX_NUMNODES) +static inline void __nodes_complement(nodemask_t *dstp, + const nodemask_t *srcp, int nbits) +{ + bitmap_complement(dstp->bits, srcp->bits, nbits); +} + +#define nodes_equal(src1, src2) \ + __nodes_equal(&(src1), &(src2), MAX_NUMNODES) +static inline int __nodes_equal(const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + return bitmap_equal(src1p->bits, src2p->bits, nbits); +} + +#define nodes_intersects(src1, src2) \ + __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) +static inline int __nodes_intersects(const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + return bitmap_intersects(src1p->bits, src2p->bits, nbits); +} + +#define nodes_subset(src1, src2) \ + __nodes_subset(&(src1), &(src2), MAX_NUMNODES) +static inline int __nodes_subset(const nodemask_t *src1p, + const nodemask_t *src2p, int nbits) +{ + return bitmap_subset(src1p->bits, src2p->bits, nbits); +} + +#define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) +static inline int __nodes_empty(const nodemask_t *srcp, int nbits) +{ + return bitmap_empty(srcp->bits, nbits); +} + +#define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) +static inline int __nodes_full(const nodemask_t *srcp, int nbits) +{ + return bitmap_full(srcp->bits, nbits); +} + +#define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) +static inline int __nodes_weight(const nodemask_t *srcp, int nbits) +{ + return bitmap_weight(srcp->bits, nbits); +} + +#define nodes_shift_right(dst, src, n) \ + __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) +static inline void __nodes_shift_right(nodemask_t *dstp, + const nodemask_t *srcp, int n, int nbits) +{ + bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); +} + +#define nodes_shift_left(dst, src, n) \ + __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) +static inline void __nodes_shift_left(nodemask_t *dstp, + const nodemask_t *srcp, int n, int nbits) +{ + bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); +} + +#define first_node(src) __first_node(&(src), MAX_NUMNODES) +static inline int __first_node(const nodemask_t *srcp, int nbits) +{ + return min_t(int, nbits, find_first_bit(srcp->bits, nbits)); +} + +#define next_node(n, src) __next_node((n), &(src), MAX_NUMNODES) +static inline int __next_node(int n, const nodemask_t *srcp, int nbits) +{ + return min_t(int, nbits, find_next_bit(srcp->bits, nbits, n+1)); +} + +#define nodemask_of_node(node) \ +({ \ + typeof(_unused_nodemask_arg_) m; \ + if (sizeof(m) == sizeof(unsigned long)) { \ + m.bits[0] = 1UL<<(node); \ + } else { \ + nodes_clear(m); \ + node_set((node), m); \ + } \ + m; \ +}) + +#define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) + +#if MAX_NUMNODES <= BITS_PER_LONG + +#define NODE_MASK_ALL \ +((nodemask_t) { { \ + [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ +} }) + +#else + +#define NODE_MASK_ALL \ +((nodemask_t) { { \ + [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ + [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ +} }) + +#endif + +#define NODE_MASK_NONE \ +((nodemask_t) { { \ + [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ +} }) + +#define nodes_addr(src) ((src).bits) + +#define nodemask_scnprintf(buf, len, src) \ + __nodemask_scnprintf((buf), (len), &(src), MAX_NUMNODES) +static inline int __nodemask_scnprintf(char *buf, int len, + const nodemask_t *srcp, int nbits) +{ + return bitmap_scnprintf(buf, len, srcp->bits, nbits); +} + +#define nodemask_parse(ubuf, ulen, src) \ + __nodemask_parse((ubuf), (ulen), &(src), MAX_NUMNODES) +static inline int __nodemask_parse(const char __user *buf, int len, + nodemask_t *dstp, int nbits) +{ + return bitmap_parse(buf, len, dstp->bits, nbits); +} + +#if MAX_NUMNODES > 1 +#define for_each_node_mask(node, mask) \ + for ((node) = first_node(mask); \ + (node) < MAX_NUMNODES; \ + (node) = next_node((node), (mask))) +#else /* MAX_NUMNODES == 1 */ +#define for_each_node_mask(node, mask) \ + if (!nodes_empty(mask)) \ + for ((node) = 0; (node) < 1; (node)++) +#endif /* MAX_NUMNODES */ + +/* + * The following particular system nodemasks and operations + * on them manage all possible and online nodes. + */ + +extern nodemask_t node_online_map; +extern nodemask_t node_possible_map; + +#if MAX_NUMNODES > 1 +#define num_online_nodes() nodes_weight(node_online_map) +#define num_possible_nodes() nodes_weight(node_possible_map) +#define node_online(node) node_isset((node), node_online_map) +#define node_possible(node) node_isset((node), node_possible_map) +#else +#define num_online_nodes() 1 +#define num_possible_nodes() 1 +#define node_online(node) ((node) == 0) +#define node_possible(node) ((node) == 0) +#endif + +#define any_online_node(mask) \ +({ \ + int node; \ + for_each_node_mask(node, (mask)) \ + if (node_online(node)) \ + break; \ + node; \ +}) + +#define node_set_online(node) set_bit((node), node_online_map.bits) +#define node_set_offline(node) clear_bit((node), node_online_map.bits) + +#define for_each_node(node) for_each_node_mask((node), node_possible_map) +#define for_each_online_node(node) for_each_node_mask((node), node_online_map) + +#endif /* __LINUX_NODEMASK_H */ diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index e6e43ce82b55..39cca92a8d63 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -5,14 +5,14 @@ * pages. A pagevec is a multipage container which is used for that. */ -#define PAGEVEC_SIZE 16 +#define PAGEVEC_SIZE 15 struct page; struct address_space; struct pagevec { - unsigned nr; - int cold; + unsigned short nr; + unsigned short cold; struct page *pages[PAGEVEC_SIZE]; }; diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h new file mode 100644 index 000000000000..4e2d2a942ecb --- /dev/null +++ b/include/linux/pktcdvd.h @@ -0,0 +1,275 @@ +/* + * Copyright (C) 2000 Jens Axboe <axboe@suse.de> + * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com> + * + * May be copied or modified under the terms of the GNU General Public + * License. See linux/COPYING for more information. + * + * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and + * DVD-RW devices. + * + */ +#ifndef __PKTCDVD_H +#define __PKTCDVD_H + +#include <linux/types.h> + +/* + * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. + */ +#define PACKET_DEBUG 1 + +#define MAX_WRITERS 8 + +#define PKT_RB_POOL_SIZE 512 + +/* + * How long we should hold a non-full packet before starting data gathering. + */ +#define PACKET_WAIT_TIME (HZ * 5 / 1000) + +/* + * use drive write caching -- we need deferred error handling to be + * able to sucessfully recover with this option (drive will return good + * status as soon as the cdb is validated). + */ +#if defined(CONFIG_CDROM_PKTCDVD_WCACHE) +#define USE_WCACHING 1 +#else +#define USE_WCACHING 0 +#endif + +/* + * No user-servicable parts beyond this point -> + */ + +/* + * device types + */ +#define PACKET_CDR 1 +#define PACKET_CDRW 2 +#define PACKET_DVDR 3 +#define PACKET_DVDRW 4 + +/* + * flags + */ +#define PACKET_WRITABLE 1 /* pd is writable */ +#define PACKET_NWA_VALID 2 /* next writable address valid */ +#define PACKET_LRA_VALID 3 /* last recorded address valid */ +#define PACKET_MERGE_SEGS 4 /* perform segment merging to keep */ + /* underlying cdrom device happy */ + +/* + * Disc status -- from READ_DISC_INFO + */ +#define PACKET_DISC_EMPTY 0 +#define PACKET_DISC_INCOMPLETE 1 +#define PACKET_DISC_COMPLETE 2 +#define PACKET_DISC_OTHER 3 + +/* + * write type, and corresponding data block type + */ +#define PACKET_MODE1 1 +#define PACKET_MODE2 2 +#define PACKET_BLOCK_MODE1 8 +#define PACKET_BLOCK_MODE2 10 + +/* + * Last session/border status + */ +#define PACKET_SESSION_EMPTY 0 +#define PACKET_SESSION_INCOMPLETE 1 +#define PACKET_SESSION_RESERVED 2 +#define PACKET_SESSION_COMPLETE 3 + +#define PACKET_MCN "4a656e734178626f65323030300000" + +#undef PACKET_USE_LS + +#define PKT_CTRL_CMD_SETUP 0 +#define PKT_CTRL_CMD_TEARDOWN 1 +#define PKT_CTRL_CMD_STATUS 2 + +struct pkt_ctrl_command { + __u32 command; /* in: Setup, teardown, status */ + __u32 dev_index; /* in/out: Device index */ + __u32 dev; /* in/out: Device nr for cdrw device */ + __u32 pkt_dev; /* in/out: Device nr for packet device */ + __u32 num_devices; /* out: Largest device index + 1 */ + __u32 padding; /* Not used */ +}; + +/* + * packet ioctls + */ +#define PACKET_IOCTL_MAGIC ('X') +#define PACKET_CTRL_CMD _IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command) + +#ifdef __KERNEL__ +#include <linux/blkdev.h> +#include <linux/completion.h> +#include <linux/cdrom.h> + +struct packet_settings +{ + __u8 size; /* packet size in (512 byte) sectors */ + __u8 fp; /* fixed packets */ + __u8 link_loss; /* the rest is specified + * as per Mt Fuji */ + __u8 write_type; + __u8 track_mode; + __u8 block_mode; +}; + +/* + * Very crude stats for now + */ +struct packet_stats +{ + unsigned long pkt_started; + unsigned long pkt_ended; + unsigned long secs_w; + unsigned long secs_rg; + unsigned long secs_r; +}; + +struct packet_cdrw +{ + struct list_head pkt_free_list; + struct list_head pkt_active_list; + spinlock_t active_list_lock; /* Serialize access to pkt_active_list */ + struct task_struct *thread; + atomic_t pending_bios; +}; + +/* + * Switch to high speed reading after reading this many kilobytes + * with no interspersed writes. + */ +#define HI_SPEED_SWITCH 512 + +struct packet_iosched +{ + atomic_t attention; /* Set to non-zero when queue processing is needed */ + int writing; /* Non-zero when writing, zero when reading */ + spinlock_t lock; /* Protecting read/write queue manipulations */ + struct bio *read_queue; + struct bio *read_queue_tail; + struct bio *write_queue; + struct bio *write_queue_tail; + int high_prio_read; /* An important read request has been queued */ + int successive_reads; +}; + +/* + * 32 buffers of 2048 bytes + */ +#define PACKET_MAX_SIZE 32 +#define PAGES_PER_PACKET (PACKET_MAX_SIZE * CD_FRAMESIZE / PAGE_SIZE) +#define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9) + +enum packet_data_state { + PACKET_IDLE_STATE, /* Not used at the moment */ + PACKET_WAITING_STATE, /* Waiting for more bios to arrive, so */ + /* we don't have to do as much */ + /* data gathering */ + PACKET_READ_WAIT_STATE, /* Waiting for reads to fill in holes */ + PACKET_WRITE_WAIT_STATE, /* Waiting for the write to complete */ + PACKET_RECOVERY_STATE, /* Recover after read/write errors */ + PACKET_FINISHED_STATE, /* After write has finished */ + + PACKET_NUM_STATES /* Number of possible states */ +}; + +/* + * Information needed for writing a single packet + */ +struct pktcdvd_device; + +struct packet_data +{ + struct list_head list; + + spinlock_t lock; /* Lock protecting state transitions and */ + /* orig_bios list */ + + struct bio *orig_bios; /* Original bios passed to pkt_make_request */ + struct bio *orig_bios_tail;/* that will be handled by this packet */ + int write_size; /* Total size of all bios in the orig_bios */ + /* list, measured in number of frames */ + + struct bio *w_bio; /* The bio we will send to the real CD */ + /* device once we have all data for the */ + /* packet we are going to write */ + sector_t sector; /* First sector in this packet */ + int frames; /* Number of frames in this packet */ + + enum packet_data_state state; /* Current state */ + atomic_t run_sm; /* Incremented whenever the state */ + /* machine needs to be run */ + long sleep_time; /* Set this to non-zero to make the state */ + /* machine run after this many jiffies. */ + + atomic_t io_wait; /* Number of pending IO operations */ + atomic_t io_errors; /* Number of read/write errors during IO */ + + struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */ + struct page *pages[PAGES_PER_PACKET]; + + int cache_valid; /* If non-zero, the data for the zone defined */ + /* by the sector variable is completely cached */ + /* in the pages[] vector. */ + + int id; /* ID number for debugging */ + struct pktcdvd_device *pd; +}; + +struct pkt_rb_node { + struct rb_node rb_node; + struct bio *bio; +}; + +struct packet_stacked_data +{ + struct bio *bio; /* Original read request bio */ + struct pktcdvd_device *pd; +}; +#define PSD_POOL_SIZE 64 + +struct pktcdvd_device +{ + struct block_device *bdev; /* dev attached */ + dev_t pkt_dev; /* our dev */ + char name[20]; + struct packet_settings settings; + struct packet_stats stats; + int refcnt; /* Open count */ + int write_speed; /* current write speed, kB/s */ + int read_speed; /* current read speed, kB/s */ + unsigned long offset; /* start offset */ + __u8 mode_offset; /* 0 / 8 */ + __u8 type; + unsigned long flags; + __u16 mmc3_profile; + __u32 nwa; /* next writable address */ + __u32 lra; /* last recorded address */ + struct packet_cdrw cdrw; + wait_queue_head_t wqueue; + + spinlock_t lock; /* Serialize access to bio_queue */ + struct rb_root bio_queue; /* Work queue of bios we need to handle */ + int bio_queue_size; /* Number of nodes in bio_queue */ + sector_t current_sector; /* Keep track of where the elevator is */ + atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ + /* needs to be run. */ + mempool_t *rb_pool; /* mempool for pkt_rb_node allocations */ + + struct packet_iosched iosched; + struct gendisk *disk; +}; + +#endif /* __KERNEL__ */ + +#endif /* __PKTCDVD_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 7bfd2d43963e..6446e4f65e93 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -143,11 +143,6 @@ int pm_send(struct pm_dev *dev, pm_request_t rqst, void *data); */ int pm_send_all(pm_request_t rqst, void *data); -/* - * Find a device - */ -struct pm_dev *pm_find(pm_dev_t type, struct pm_dev *from); - static inline void pm_access(struct pm_dev *dev) {} static inline void pm_dev_idle(struct pm_dev *dev) {} diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index aff9a6adb39e..fc74ef3fef36 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -79,7 +79,6 @@ extern struct posix_acl *posix_acl_from_mode(mode_t, int); extern int posix_acl_equiv_mode(const struct posix_acl *, mode_t *); extern int posix_acl_create_masq(struct posix_acl *, mode_t *); extern int posix_acl_chmod_masq(struct posix_acl *, mode_t); -extern int posix_acl_masq_nfs_mode(struct posix_acl *, mode_t *); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); diff --git a/include/linux/prctl.h b/include/linux/prctl.h index 54333c98e532..edb036b43597 100644 --- a/include/linux/prctl.h +++ b/include/linux/prctl.h @@ -49,7 +49,6 @@ # define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based process timing */ - #define PR_SET_NAME 15 /* Set process name */ #endif /* _LINUX_PRCTL_H */ diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 6eacc2c653f1..df62d2ac38a7 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -438,7 +438,7 @@ static inline void set_offset_v2_k_offset( struct offset_v2 *v2, loff_t offset ) /* Key of an item determines its location in the S+tree, and is composed of 4 components */ -struct key { +struct reiserfs_key { __u32 k_dir_id; /* packing locality: by default parent directory object id */ __u32 k_objectid; /* object identifier */ @@ -450,7 +450,7 @@ struct key { struct cpu_key { - struct key on_disk_key; + struct reiserfs_key on_disk_key; int version; int key_length; /* 3 in all cases but direct2indirect and indirect2direct conversion */ @@ -470,7 +470,7 @@ struct cpu_key { #define KEY_FOUND 1 #define KEY_NOT_FOUND 0 -#define KEY_SIZE (sizeof(struct key)) +#define KEY_SIZE (sizeof(struct reiserfs_key)) #define SHORT_KEY_SIZE (sizeof (__u32) + sizeof (__u32)) /* return values for search_by_key and clones */ @@ -503,7 +503,7 @@ struct item_head { /* Everything in the tree is found by searching for it based on * its key.*/ - struct key ih_key; + struct reiserfs_key ih_key; union { /* The free space in the last unformatted node of an indirect item if this is an indirect item. This @@ -602,7 +602,7 @@ static inline __u32 type2uniqueness (int type) // there is no way to get version of object from key, so, provide // version to these defines // -static inline loff_t le_key_k_offset (int version, const struct key * key) +static inline loff_t le_key_k_offset (int version, const struct reiserfs_key * key) { return (version == KEY_FORMAT_3_5) ? le32_to_cpu( key->u.k_offset_v1.k_offset ) : @@ -614,7 +614,7 @@ static inline loff_t le_ih_k_offset (const struct item_head * ih) return le_key_k_offset (ih_version (ih), &(ih->ih_key)); } -static inline loff_t le_key_k_type (int version, const struct key * key) +static inline loff_t le_key_k_type (int version, const struct reiserfs_key * key) { return (version == KEY_FORMAT_3_5) ? uniqueness2type( le32_to_cpu( key->u.k_offset_v1.k_uniqueness)) : @@ -627,7 +627,7 @@ static inline loff_t le_ih_k_type (const struct item_head * ih) } -static inline void set_le_key_k_offset (int version, struct key * key, loff_t offset) +static inline void set_le_key_k_offset (int version, struct reiserfs_key * key, loff_t offset) { (version == KEY_FORMAT_3_5) ? (void)(key->u.k_offset_v1.k_offset = cpu_to_le32 (offset)) : /* jdm check */ @@ -641,7 +641,7 @@ static inline void set_le_ih_k_offset (struct item_head * ih, loff_t offset) } -static inline void set_le_key_k_type (int version, struct key * key, int type) +static inline void set_le_key_k_type (int version, struct reiserfs_key * key, int type) { (version == KEY_FORMAT_3_5) ? (void)(key->u.k_offset_v1.k_uniqueness = cpu_to_le32(type2uniqueness(type))): @@ -738,7 +738,7 @@ static inline void cpu_key_k_offset_dec (struct cpu_key * key) /* object identifier for root dir */ #define REISERFS_ROOT_OBJECTID 2 #define REISERFS_ROOT_PARENT_OBJECTID 1 -extern struct key root_key; +extern struct reiserfs_key root_key; @@ -760,7 +760,7 @@ struct block_head { __u16 blk_free_space; /* Block free space in bytes. */ __u16 blk_reserved; /* dump this in v4/planA */ - struct key blk_right_delim_key; /* kept only for compatibility */ + struct reiserfs_key blk_right_delim_key; /* kept only for compatibility */ }; #define BLKH_SIZE (sizeof(struct block_head)) @@ -1301,7 +1301,7 @@ struct path var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,} #define UNFM_P_SHIFT 2 // in in-core inode key is stored on le form -#define INODE_PKEY(inode) ((struct key *)(REISERFS_I(inode)->i_key)) +#define INODE_PKEY(inode) ((struct reiserfs_key *)(REISERFS_I(inode)->i_key)) #define MAX_UL_INT 0xffffffff #define MAX_INT 0x7ffffff @@ -1479,7 +1479,7 @@ struct tree_balance int fs_gen; /* saved value of `reiserfs_generation' counter see FILESYSTEM_CHANGED() macro in reiserfs_fs.h */ #ifdef DISPLACE_NEW_PACKING_LOCALITIES - struct key key; /* key pointer, to pass to block allocator or + struct reiserfs_key key; /* key pointer, to pass to block allocator or another low-level subsystem */ #endif } ; @@ -1543,7 +1543,7 @@ struct buffer_info { struct item_operations { int (*bytes_number) (struct item_head * ih, int block_size); void (*decrement_key) (struct cpu_key *); - int (*is_left_mergeable) (struct key * ih, unsigned long bsize); + int (*is_left_mergeable) (struct reiserfs_key * ih, unsigned long bsize); void (*print_item) (struct item_head *, char * item); void (*check_item) (struct item_head *, char * item); @@ -1594,7 +1594,7 @@ extern struct item_operations * item_ops [TYPE_ANY + 1]; #define B_N_PITEM_HEAD(bh,item_num) ( (struct item_head * )((bh)->b_data + BLKH_SIZE) + (item_num) ) /* get key */ -#define B_N_PDELIM_KEY(bh,item_num) ( (struct key * )((bh)->b_data + BLKH_SIZE) + (item_num) ) +#define B_N_PDELIM_KEY(bh,item_num) ( (struct reiserfs_key * )((bh)->b_data + BLKH_SIZE) + (item_num) ) /* get the key */ #define B_N_PKEY(bh,item_num) ( &(B_N_PITEM_HEAD(bh,item_num)->ih_key) ) @@ -1832,11 +1832,11 @@ extern void copy_item_head(struct item_head * p_v_to, const struct item_head * p_v_from); // first key is in cpu form, second - le -extern int comp_keys (const struct key * le_key, +extern int comp_keys (const struct reiserfs_key * le_key, const struct cpu_key * cpu_key); -extern int comp_short_keys (const struct key * le_key, +extern int comp_short_keys (const struct reiserfs_key * le_key, const struct cpu_key * cpu_key); -extern void le_key2cpu_key (struct cpu_key * to, const struct key * from); +extern void le_key2cpu_key (struct cpu_key * to, const struct reiserfs_key * from); // both are cpu keys extern int comp_cpu_keys (const struct cpu_key *, const struct cpu_key *); @@ -1845,13 +1845,13 @@ extern int comp_short_cpu_keys (const struct cpu_key *, extern void cpu_key2cpu_key (struct cpu_key *, const struct cpu_key *); // both are in le form -extern int comp_le_keys (const struct key *, const struct key *); -extern int comp_short_le_keys (const struct key *, const struct key *); +extern int comp_le_keys (const struct reiserfs_key *, const struct reiserfs_key *); +extern int comp_short_le_keys (const struct reiserfs_key *, const struct reiserfs_key *); // // get key version from on disk key - kludge // -static inline int le_key_version (const struct key * key) +static inline int le_key_version (const struct reiserfs_key * key) { int type; @@ -1864,14 +1864,14 @@ static inline int le_key_version (const struct key * key) } -static inline void copy_key (struct key *to, const struct key *from) +static inline void copy_key (struct reiserfs_key *to, const struct reiserfs_key *from) { memcpy (to, from, KEY_SIZE); } int comp_items (const struct item_head * stored_ih, const struct path * p_s_path); -const struct key * get_rkey (const struct path * p_s_chk_path, +const struct reiserfs_key * get_rkey (const struct path * p_s_chk_path, const struct super_block * p_s_sb); inline int bin_search (const void * p_v_key, const void * p_v_base, int p_n_num, int p_n_width, int * p_n_pos); @@ -1913,7 +1913,7 @@ int reiserfs_delete_item (struct reiserfs_transaction_handle *th, struct buffer_head * p_s_un_bh); void reiserfs_delete_solid_item (struct reiserfs_transaction_handle *th, - struct inode *inode, struct key * key); + struct inode *inode, struct reiserfs_key * key); int reiserfs_delete_object (struct reiserfs_transaction_handle *th, struct inode * p_s_inode); int reiserfs_do_truncate (struct reiserfs_transaction_handle *th, struct inode * p_s_inode, struct page *, @@ -2131,7 +2131,7 @@ struct buffer_head * get_FEB (struct tree_balance *); struct __reiserfs_blocknr_hint { struct inode * inode; /* inode passed to allocator, if we allocate unf. nodes */ long block; /* file offset, in blocks */ - struct key key; + struct reiserfs_key key; struct path * path; /* search path, used by allocator to deternine search_start by * various ways */ struct reiserfs_transaction_handle * th; /* transaction handle is needed to log super blocks and diff --git a/include/linux/sched.h b/include/linux/sched.h index dc3f297a726d..c8f981f108d4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -227,7 +227,7 @@ struct mm_struct { unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; unsigned long rss, total_vm, locked_vm, shared_vm; - unsigned long exec_vm, stack_vm, reserved_vm, def_flags; + unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes; unsigned long saved_auxv[42]; /* for /proc/PID/auxv */ @@ -358,6 +358,11 @@ struct user_struct { unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ unsigned long locked_shm; /* How many pages of mlocked shm ? */ +#ifdef CONFIG_KEYS + struct key *uid_keyring; /* UID specific keyring */ + struct key *session_keyring; /* UID's default session keyring */ +#endif + /* Hash table maintenance information */ struct list_head uidhash_list; uid_t uid; @@ -611,6 +616,11 @@ struct task_struct { kernel_cap_t cap_effective, cap_inheritable, cap_permitted; unsigned keep_capabilities:1; struct user_struct *user; +#ifdef CONFIG_KEYS + struct key *session_keyring; /* keyring inherited over fork */ + struct key *process_keyring; /* keyring private to this process (CLONE_THREAD) */ + struct key *thread_keyring; /* keyring private to this thread */ +#endif unsigned short used_math; char comm[16]; /* file system info */ @@ -644,7 +654,7 @@ struct task_struct { /* Thread group tracking */ u32 parent_exec_id; u32 self_exec_id; -/* Protection of (de-)allocation: mm, files, fs, tty */ +/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */ spinlock_t alloc_lock; /* Protection of proc_dentry: nesting proc_lock, dcache_lock, write_lock_irq(&tasklist_lock); */ spinlock_t proc_lock; @@ -828,7 +838,6 @@ extern int force_sigsegv(int, struct task_struct *); extern int force_sig_info(int, struct siginfo *, struct task_struct *); extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp); extern int kill_pg_info(int, struct siginfo *, pid_t); -extern int kill_sl_info(int, struct siginfo *, pid_t); extern int kill_proc_info(int, struct siginfo *, pid_t); extern void do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); @@ -977,8 +986,8 @@ static inline int thread_group_empty(task_t *p) extern void unhash_process(struct task_struct *p); /* - * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm and - * synchronises with wait4(). + * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring + * subscriptions and synchronises with wait4(). Also used in procfs. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), diff --git a/include/linux/security.h b/include/linux/security.h index a1dee9a60587..ab0941c9fca7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -27,13 +27,14 @@ #include <linux/signal.h> #include <linux/resource.h> #include <linux/sem.h> -#include <linux/sysctl.h> #include <linux/shm.h> #include <linux/msg.h> #include <linux/sched.h> #include <linux/skbuff.h> #include <linux/netlink.h> +struct ctl_table; + /* * These functions are in security/capability.c and are used * as the default capabilities functions @@ -395,13 +396,13 @@ struct swap_info_struct; * Return 0 if permission is granted. * @inode_getsecurity: * Copy the extended attribute representation of the security label - * associated with @name for @dentry into @buffer. @buffer may be + * associated with @name for @inode into @buffer. @buffer may be * NULL to request the size of the buffer required. @size indicates * the size of @buffer in bytes. Note that @name is the remainder * of the attribute name after the security. prefix has been removed. * Return number of bytes used/required on success. * @inode_setsecurity: - * Set the security label associated with @name for @dentry from the + * Set the security label associated with @name for @inode from the * extended attribute value @value. @size indicates the size of the * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. * Note that @name is the remainder of the attribute name after the @@ -409,8 +410,9 @@ struct swap_info_struct; * Return 0 on success. * @inode_listsecurity: * Copy the extended attribute names for the security labels - * associated with @dentry into @buffer. @buffer may be NULL to - * request the size of the buffer required. + * associated with @inode into @buffer. The maximum size of @buffer + * is specified by @buffer_size. @buffer may be NULL to request + * the size of the buffer required. * Returns number of bytes used/required on success. * * Security hooks for file operations @@ -1029,7 +1031,7 @@ struct security_operations { kernel_cap_t * inheritable, kernel_cap_t * permitted); int (*acct) (struct file * file); - int (*sysctl) (ctl_table * table, int op); + int (*sysctl) (struct ctl_table * table, int op); int (*capable) (struct task_struct * tsk, int cap); int (*quotactl) (int cmds, int type, int id, struct super_block * sb); int (*quota_on) (struct file * f); @@ -1108,9 +1110,9 @@ struct security_operations { int (*inode_getxattr) (struct dentry *dentry, char *name); int (*inode_listxattr) (struct dentry *dentry); int (*inode_removexattr) (struct dentry *dentry, char *name); - int (*inode_getsecurity)(struct dentry *dentry, const char *name, void *buffer, size_t size); - int (*inode_setsecurity)(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); - int (*inode_listsecurity)(struct dentry *dentry, char *buffer); + int (*inode_getsecurity)(struct inode *inode, const char *name, void *buffer, size_t size); + int (*inode_setsecurity)(struct inode *inode, const char *name, const void *value, size_t size, int flags); + int (*inode_listsecurity)(struct inode *inode, char *buffer, size_t buffer_size); int (*file_permission) (struct file * file, int mask); int (*file_alloc_security) (struct file * file); @@ -1268,7 +1270,7 @@ static inline int security_acct (struct file *file) return security_ops->acct (file); } -static inline int security_sysctl(ctl_table * table, int op) +static inline int security_sysctl(struct ctl_table *table, int op) { return security_ops->sysctl(table, op); } @@ -1575,19 +1577,19 @@ static inline int security_inode_removexattr (struct dentry *dentry, char *name) return security_ops->inode_removexattr (dentry, name); } -static inline int security_inode_getsecurity(struct dentry *dentry, const char *name, void *buffer, size_t size) +static inline int security_inode_getsecurity(struct inode *inode, const char *name, void *buffer, size_t size) { - return security_ops->inode_getsecurity(dentry, name, buffer, size); + return security_ops->inode_getsecurity(inode, name, buffer, size); } -static inline int security_inode_setsecurity(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) +static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { - return security_ops->inode_setsecurity(dentry, name, value, size, flags); + return security_ops->inode_setsecurity(inode, name, value, size, flags); } -static inline int security_inode_listsecurity(struct dentry *dentry, char *buffer) +static inline int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { - return security_ops->inode_listsecurity(dentry, buffer); + return security_ops->inode_listsecurity(inode, buffer, buffer_size); } static inline int security_file_permission (struct file *file, int mask) @@ -1940,7 +1942,7 @@ static inline int security_acct (struct file *file) return 0; } -static inline int security_sysctl(ctl_table * table, int op) +static inline int security_sysctl(struct ctl_table *table, int op) { return 0; } @@ -2214,17 +2216,17 @@ static inline int security_inode_removexattr (struct dentry *dentry, char *name) return cap_inode_removexattr(dentry, name); } -static inline int security_inode_getsecurity(struct dentry *dentry, const char *name, void *buffer, size_t size) +static inline int security_inode_getsecurity(struct inode *inode, const char *name, void *buffer, size_t size) { return -EOPNOTSUPP; } -static inline int security_inode_setsecurity(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) +static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { return -EOPNOTSUPP; } -static inline int security_inode_listsecurity(struct dentry *dentry, char *buffer) +static inline int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { return 0; } diff --git a/include/linux/smb_mount.h b/include/linux/smb_mount.h index 256900c55881..d10f00cb5703 100644 --- a/include/linux/smb_mount.h +++ b/include/linux/smb_mount.h @@ -38,7 +38,10 @@ struct smb_mount_data { #define SMB_MOUNT_DIRATTR 0x0004 /* Use find_first for getattr */ #define SMB_MOUNT_CASE 0x0008 /* Be case sensitive */ #define SMB_MOUNT_UNICODE 0x0010 /* Server talks unicode */ - +#define SMB_MOUNT_UID 0x0020 /* Use user specified uid */ +#define SMB_MOUNT_GID 0x0040 /* Use user specified gid */ +#define SMB_MOUNT_FMODE 0x0080 /* Use user specified file mode */ +#define SMB_MOUNT_DMODE 0x0100 /* Use user specified dir mode */ struct smb_mount_data_kernel { int version; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2a8c7faf2dcc..bc93606badbc 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -61,6 +61,7 @@ struct mq_attr; #include <asm/siginfo.h> #include <asm/signal.h> #include <linux/quota.h> +#include <linux/key.h> asmlinkage long sys_time(int __user *tloc); asmlinkage long sys_stime(time_t __user *tptr); @@ -492,4 +493,18 @@ asmlinkage long sys_uselib(const char __user *library); asmlinkage long sys_setaltroot(const char __user *altroot); asmlinkage long sys_ni_syscall(void); +asmlinkage long sys_add_key(const char __user *_type, + const char __user *_description, + const void __user *_payload, + size_t plen, + key_serial_t destringid); + +asmlinkage long sys_request_key(const char __user *_type, + const char __user *_description, + const char __user *_callout_info, + key_serial_t destringid); + +asmlinkage long sys_keyctl(int cmd, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); + #endif diff --git a/include/linux/threads.h b/include/linux/threads.h index 047e28bd7d8e..4243c55cce87 100644 --- a/include/linux/threads.h +++ b/include/linux/threads.h @@ -30,6 +30,6 @@ /* * A maximum of 4 million PIDs should be enough for a while: */ -#define PID_MAX_LIMIT (4*1024*1024) +#define PID_MAX_LIMIT (sizeof(long) > 4 ? 4*1024*1024 : PID_MAX_DEFAULT) #endif diff --git a/include/linux/time.h b/include/linux/time.h index 2111941c1af7..ae174b8ab036 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -1,9 +1,12 @@ #ifndef _LINUX_TIME_H #define _LINUX_TIME_H -#include <asm/param.h> #include <linux/types.h> +#ifdef __KERNEL__ +#include <linux/seqlock.h> +#endif + #ifndef _STRUCT_TIMESPEC #define _STRUCT_TIMESPEC struct timespec { @@ -24,39 +27,6 @@ struct timezone { #ifdef __KERNEL__ -#include <linux/spinlock.h> -#include <linux/seqlock.h> -#include <linux/timex.h> -#include <asm/div64.h> -#ifndef div_long_long_rem - -#define div_long_long_rem(dividend,divisor,remainder) ({ \ - u64 result = dividend; \ - *remainder = do_div(result,divisor); \ - result; }) - -#endif - -/* - * Have the 32 bit jiffies value wrap 5 minutes after boot - * so jiffies wrap bugs show up earlier. - */ -#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) - -/* - * Change timeval to jiffies, trying to avoid the - * most obvious overflows.. - * - * And some not so obvious. - * - * Note that we don't want to return MAX_LONG, because - * for various timeout reasons we often end up having - * to wait "jiffies+1" in order to guarantee that we wait - * at _least_ "jiffies" - so "jiffies+1" had better still - * be positive. - */ -#define MAX_JIFFY_OFFSET ((~0UL >> 1)-1) - /* Parameters used to convert the timespec values */ #ifndef USEC_PER_SEC #define USEC_PER_SEC (1000000L) @@ -70,232 +40,6 @@ struct timezone { #define NSEC_PER_USEC (1000L) #endif -/* - * We want to do realistic conversions of time so we need to use the same - * values the update wall clock code uses as the jiffies size. This value - * is: TICK_NSEC (which is defined in timex.h). This - * is a constant and is in nanoseconds. We will used scaled math - * with a set of scales defined here as SEC_JIFFIE_SC, USEC_JIFFIE_SC and - * NSEC_JIFFIE_SC. Note that these defines contain nothing but - * constants and so are computed at compile time. SHIFT_HZ (computed in - * timex.h) adjusts the scaling for different HZ values. - - * Scaled math??? What is that? - * - * Scaled math is a way to do integer math on values that would, - * otherwise, either overflow, underflow, or cause undesired div - * instructions to appear in the execution path. In short, we "scale" - * up the operands so they take more bits (more precision, less - * underflow), do the desired operation and then "scale" the result back - * by the same amount. If we do the scaling by shifting we avoid the - * costly mpy and the dastardly div instructions. - - * Suppose, for example, we want to convert from seconds to jiffies - * where jiffies is defined in nanoseconds as NSEC_PER_JIFFIE. The - * simple math is: jiff = (sec * NSEC_PER_SEC) / NSEC_PER_JIFFIE; We - * observe that (NSEC_PER_SEC / NSEC_PER_JIFFIE) is a constant which we - * might calculate at compile time, however, the result will only have - * about 3-4 bits of precision (less for smaller values of HZ). - * - * So, we scale as follows: - * jiff = (sec) * (NSEC_PER_SEC / NSEC_PER_JIFFIE); - * jiff = ((sec) * ((NSEC_PER_SEC * SCALE)/ NSEC_PER_JIFFIE)) / SCALE; - * Then we make SCALE a power of two so: - * jiff = ((sec) * ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) >> SCALE; - * Now we define: - * #define SEC_CONV = ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) - * jiff = (sec * SEC_CONV) >> SCALE; - * - * Often the math we use will expand beyond 32-bits so we tell C how to - * do this and pass the 64-bit result of the mpy through the ">> SCALE" - * which should take the result back to 32-bits. We want this expansion - * to capture as much precision as possible. At the same time we don't - * want to overflow so we pick the SCALE to avoid this. In this file, - * that means using a different scale for each range of HZ values (as - * defined in timex.h). - * - * For those who want to know, gcc will give a 64-bit result from a "*" - * operator if the result is a long long AND at least one of the - * operands is cast to long long (usually just prior to the "*" so as - * not to confuse it into thinking it really has a 64-bit operand, - * which, buy the way, it can do, but it take more code and at least 2 - * mpys). - - * We also need to be aware that one second in nanoseconds is only a - * couple of bits away from overflowing a 32-bit word, so we MUST use - * 64-bits to get the full range time in nanoseconds. - - */ - -/* - * Here are the scales we will use. One for seconds, nanoseconds and - * microseconds. - * - * Within the limits of cpp we do a rough cut at the SEC_JIFFIE_SC and - * check if the sign bit is set. If not, we bump the shift count by 1. - * (Gets an extra bit of precision where we can use it.) - * We know it is set for HZ = 1024 and HZ = 100 not for 1000. - * Haven't tested others. - - * Limits of cpp (for #if expressions) only long (no long long), but - * then we only need the most signicant bit. - */ - -#define SEC_JIFFIE_SC (31 - SHIFT_HZ) -#if !((((NSEC_PER_SEC << 2) / TICK_NSEC) << (SEC_JIFFIE_SC - 2)) & 0x80000000) -#undef SEC_JIFFIE_SC -#define SEC_JIFFIE_SC (32 - SHIFT_HZ) -#endif -#define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) -#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19) -#define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) - -#define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) -#define USEC_CONVERSION \ - ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\ - TICK_NSEC -1) / (u64)TICK_NSEC)) -/* - * USEC_ROUND is used in the timeval to jiffie conversion. See there - * for more details. It is the scaled resolution rounding value. Note - * that it is a 64-bit value. Since, when it is applied, we are already - * in jiffies (albit scaled), it is nothing but the bits we will shift - * off. - */ -#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1) -/* - * The maximum jiffie value is (MAX_INT >> 1). Here we translate that - * into seconds. The 64-bit case will overflow if we are not careful, - * so use the messy SH_DIV macro to do it. Still all constants. - */ -#if BITS_PER_LONG < 64 -# define MAX_SEC_IN_JIFFIES \ - (long)((u64)((u64)MAX_JIFFY_OFFSET * TICK_NSEC) / NSEC_PER_SEC) -#else /* take care of overflow on 64 bits machines */ -# define MAX_SEC_IN_JIFFIES \ - (SH_DIV((MAX_JIFFY_OFFSET >> SEC_JIFFIE_SC) * TICK_NSEC, NSEC_PER_SEC, 1) - 1) - -#endif - -/* - * Convert jiffies to milliseconds and back. - * - * Avoid unnecessary multiplications/divisions in the - * two most common HZ cases: - */ -static inline unsigned int jiffies_to_msecs(const unsigned long j) -{ -#if HZ <= 1000 && !(1000 % HZ) - return (1000 / HZ) * j; -#elif HZ > 1000 && !(HZ % 1000) - return (j + (HZ / 1000) - 1)/(HZ / 1000); -#else - return (j * 1000) / HZ; -#endif -} - -static inline unsigned int jiffies_to_usecs(const unsigned long j) -{ -#if HZ <= 1000 && !(1000 % HZ) - return (1000000 / HZ) * j; -#elif HZ > 1000 && !(HZ % 1000) - return (j*1000 + (HZ - 1000))/(HZ / 1000); -#else - return (j * 1000000) / HZ; -#endif -} - -static inline unsigned long msecs_to_jiffies(const unsigned int m) -{ - if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) - return MAX_JIFFY_OFFSET; -#if HZ <= 1000 && !(1000 % HZ) - return (m + (1000 / HZ) - 1) / (1000 / HZ); -#elif HZ > 1000 && !(HZ % 1000) - return m * (HZ / 1000); -#else - return (m * HZ + 999) / 1000; -#endif -} - -/* - * The TICK_NSEC - 1 rounds up the value to the next resolution. Note - * that a remainder subtract here would not do the right thing as the - * resolution values don't fall on second boundries. I.e. the line: - * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. - * - * Rather, we just shift the bits off the right. - * - * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec - * value to a scaled second value. - */ -static __inline__ unsigned long -timespec_to_jiffies(const struct timespec *value) -{ - unsigned long sec = value->tv_sec; - long nsec = value->tv_nsec + TICK_NSEC - 1; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - nsec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)nsec * NSEC_CONVERSION) >> - (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; - -} - -static __inline__ void -jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u64 nsec = (u64)jiffies * TICK_NSEC; - value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec); -} - -/* Same for "timeval" - * - * Well, almost. The problem here is that the real system resolution is - * in nanoseconds and the value being converted is in micro seconds. - * Also for some machines (those that use HZ = 1024, in-particular), - * there is a LARGE error in the tick size in microseconds. - - * The solution we use is to do the rounding AFTER we convert the - * microsecond part. Thus the USEC_ROUND, the bits to be shifted off. - * Instruction wise, this should cost only an additional add with carry - * instruction above the way it was done above. - */ -static __inline__ unsigned long -timeval_to_jiffies(const struct timeval *value) -{ - unsigned long sec = value->tv_sec; - long usec = value->tv_usec; - - if (sec >= MAX_SEC_IN_JIFFIES){ - sec = MAX_SEC_IN_JIFFIES; - usec = 0; - } - return (((u64)sec * SEC_CONVERSION) + - (((u64)usec * USEC_CONVERSION + USEC_ROUND) >> - (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; -} - -static __inline__ void -jiffies_to_timeval(const unsigned long jiffies, struct timeval *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u64 nsec = (u64)jiffies * TICK_NSEC; - value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_usec); - value->tv_usec /= NSEC_PER_USEC; -} - static __inline__ int timespec_equal(struct timespec *a, struct timespec *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); @@ -347,11 +91,6 @@ struct timespec current_kernel_time(void); #define CURRENT_TIME (current_kernel_time()) -#endif /* __KERNEL__ */ - -#define NFDBITS __NFDBITS - -#ifdef __KERNEL__ extern void do_gettimeofday(struct timeval *tv); extern int do_settimeofday(struct timespec *tv); extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz); @@ -378,7 +117,10 @@ set_normalized_timespec (struct timespec *ts, time_t sec, long nsec) ts->tv_sec = sec; ts->tv_nsec = nsec; } -#endif + +#endif /* __KERNEL__ */ + +#define NFDBITS __NFDBITS #define FD_SETSIZE __FD_SETSIZE #define FD_SET(fd,fdsetp) __FD_SET(fd,fdsetp) diff --git a/include/linux/times.h b/include/linux/times.h index 0c5aa078dad4..e2d3020742a6 100644 --- a/include/linux/times.h +++ b/include/linux/times.h @@ -1,79 +1,7 @@ #ifndef _LINUX_TIMES_H #define _LINUX_TIMES_H -#ifdef __KERNEL__ -#include <linux/timex.h> -#include <asm/div64.h> -#include <asm/types.h> -#include <asm/param.h> - -static inline clock_t jiffies_to_clock_t(long x) -{ -#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 - return x / (HZ / USER_HZ); -#else - u64 tmp = (u64)x * TICK_NSEC; - do_div(tmp, (NSEC_PER_SEC / USER_HZ)); - return (long)tmp; -#endif -} - -static inline unsigned long clock_t_to_jiffies(unsigned long x) -{ -#if (HZ % USER_HZ)==0 - if (x >= ~0UL / (HZ / USER_HZ)) - return ~0UL; - return x * (HZ / USER_HZ); -#else - u64 jif; - - /* Don't worry about loss of precision here .. */ - if (x >= ~0UL / HZ * USER_HZ) - return ~0UL; - - /* .. but do try to contain it here */ - jif = x * (u64) HZ; - do_div(jif, USER_HZ); - return jif; -#endif -} - -static inline u64 jiffies_64_to_clock_t(u64 x) -{ -#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 - do_div(x, HZ / USER_HZ); -#else - /* - * There are better ways that don't overflow early, - * but even this doesn't overflow in hundreds of years - * in 64 bits, so.. - */ - x *= TICK_NSEC; - do_div(x, (NSEC_PER_SEC / USER_HZ)); -#endif - return x; -} -#endif - -static inline u64 nsec_to_clock_t(u64 x) -{ -#if (NSEC_PER_SEC % USER_HZ) == 0 - do_div(x, (NSEC_PER_SEC / USER_HZ)); -#elif (USER_HZ % 512) == 0 - x *= USER_HZ/512; - do_div(x, (NSEC_PER_SEC / 512)); -#else - /* - * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, - * overflow after 64.99 years. - * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... - */ - x *= 9; - do_div(x, (unsigned long)((9ull * NSEC_PER_SEC + (USER_HZ/2)) - / USER_HZ)); -#endif - return x; -} +#include <linux/types.h> struct tms { clock_t tms_utime; diff --git a/include/linux/timex.h b/include/linux/timex.h index 31ef4595b1fd..438645f2fedc 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -55,33 +55,10 @@ #include <linux/config.h> #include <linux/compiler.h> +#include <linux/time.h> #include <asm/param.h> - -/* - * The following defines establish the engineering parameters of the PLL - * model. The HZ variable establishes the timer interrupt frequency, 100 Hz - * for the SunOS kernel, 256 Hz for the Ultrix kernel and 1024 Hz for the - * OSF/1 kernel. The SHIFT_HZ define expresses the same value as the - * nearest power of two in order to avoid hardware multiply operations. - */ -#if HZ >= 12 && HZ < 24 -# define SHIFT_HZ 4 -#elif HZ >= 24 && HZ < 48 -# define SHIFT_HZ 5 -#elif HZ >= 48 && HZ < 96 -# define SHIFT_HZ 6 -#elif HZ >= 96 && HZ < 192 -# define SHIFT_HZ 7 -#elif HZ >= 192 && HZ < 384 -# define SHIFT_HZ 8 -#elif HZ >= 384 && HZ < 768 -# define SHIFT_HZ 9 -#elif HZ >= 768 && HZ < 1536 -# define SHIFT_HZ 10 -#else -# error You lose. -#endif +#include <asm/timex.h> /* * SHIFT_KG and SHIFT_KF establish the damping of the PLL and are chosen @@ -152,41 +129,6 @@ #define MAXGLITCH 30 /* pps signal glitch max (s) */ /* - * Pick up the architecture specific timex specifications - */ -#include <asm/timex.h> - -/* LATCH is used in the interval timer and ftape setup. */ -#define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ - -/* Suppose we want to devide two numbers NOM and DEN: NOM/DEN, the we can - * improve accuracy by shifting LSH bits, hence calculating: - * (NOM << LSH) / DEN - * This however means trouble for large NOM, because (NOM << LSH) may no - * longer fit in 32 bits. The following way of calculating this gives us - * some slack, under the following conditions: - * - (NOM / DEN) fits in (32 - LSH) bits. - * - (NOM % DEN) fits in (32 - LSH) bits. - */ -#define SH_DIV(NOM,DEN,LSH) ( ((NOM / DEN) << LSH) \ - + (((NOM % DEN) << LSH) + DEN / 2) / DEN) - -/* HZ is the requested value. ACTHZ is actual HZ ("<< 8" is for accuracy) */ -#define ACTHZ (SH_DIV (CLOCK_TICK_RATE, LATCH, 8)) - -/* TICK_NSEC is the time between ticks in nsec assuming real ACTHZ */ -#define TICK_NSEC (SH_DIV (1000000UL * 1000, ACTHZ, 8)) - -/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ -#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) - -/* TICK_USEC_TO_NSEC is the time between ticks in nsec assuming real ACTHZ and */ -/* a value TUSEC for TICK_USEC (can be set bij adjtimex) */ -#define TICK_USEC_TO_NSEC(TUSEC) (SH_DIV (TUSEC * USER_HZ * 1000, ACTHZ, 8)) - - -#include <linux/time.h> -/* * syscall interface - used (mainly by NTP daemon) * to discipline kernel clock oscillator */ diff --git a/include/linux/types.h b/include/linux/types.h index 13ccdf3036fd..893c4b367bae 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -140,6 +140,13 @@ typedef unsigned long sector_t; #define pgoff_t unsigned long #endif +#endif /* __KERNEL_STRICT_NAMES */ + +/* + * Below are truly Linux-specific types that should never collide with + * any application/library that wants linux/types.h. + */ + #ifdef __CHECKER__ #define __bitwise __attribute__((bitwise)) #else @@ -153,13 +160,6 @@ typedef __u32 __bitwise __be32; typedef __u64 __bitwise __le64; typedef __u64 __bitwise __be64; -#endif /* __KERNEL_STRICT_NAMES */ - -/* - * Below are truly Linux-specific types that should never collide with - * any application/library that wants linux/types.h. - */ - struct ustat { __kernel_daddr_t f_tfree; __kernel_ino_t f_tinode; diff --git a/include/linux/wait.h b/include/linux/wait.h index 21cd4df67b24..8b3a2b86d92a 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -24,6 +24,7 @@ #include <linux/stddef.h> #include <linux/spinlock.h> #include <asm/system.h> +#include <asm/current.h> typedef struct __wait_queue wait_queue_t; typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int sync, void *key); @@ -37,6 +38,16 @@ struct __wait_queue { struct list_head task_list; }; +struct wait_bit_key { + void *flags; + int bit_nr; +}; + +struct wait_bit_queue { + struct wait_bit_key key; + wait_queue_t wait; +}; + struct __wait_queue_head { spinlock_t lock; struct list_head task_list; @@ -63,6 +74,9 @@ typedef struct __wait_queue_head wait_queue_head_t; #define DECLARE_WAIT_QUEUE_HEAD(name) \ wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name) +#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ + { .flags = word, .bit_nr = bit, } + static inline void init_waitqueue_head(wait_queue_head_t *q) { q->lock = SPIN_LOCK_UNLOCKED; @@ -125,11 +139,17 @@ static inline void __remove_wait_queue(wait_queue_head_t *head, void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key)); extern void FASTCALL(__wake_up_locked(wait_queue_head_t *q, unsigned int mode)); extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr)); +void FASTCALL(__wake_up_bit(wait_queue_head_t *, void *, int)); +int FASTCALL(__wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned)); +int FASTCALL(__wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned)); +void FASTCALL(wake_up_bit(void *, int)); +int FASTCALL(out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned)); +int FASTCALL(out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned)); +wait_queue_head_t *FASTCALL(bit_waitqueue(void *, int)); #define wake_up(x) __wake_up(x, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 0, NULL) -#define wake_up_all_sync(x) __wake_up_sync((x),TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) @@ -300,6 +320,7 @@ void FASTCALL(prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)); void FASTCALL(finish_wait(wait_queue_head_t *q, wait_queue_t *wait)); int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); +int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); #define DEFINE_WAIT(name) \ wait_queue_t name = { \ @@ -310,12 +331,69 @@ int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void * }, \ } +#define DEFINE_WAIT_BIT(name, word, bit) \ + struct wait_bit_queue name = { \ + .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ + .wait = { \ + .task = current, \ + .func = wake_bit_function, \ + .task_list = \ + LIST_HEAD_INIT(name.wait.task_list), \ + }, \ + } + #define init_wait(wait) \ do { \ wait->task = current; \ wait->func = autoremove_wake_function; \ INIT_LIST_HEAD(&wait->task_list); \ } while (0) + +/** + * wait_on_bit - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit. + * For instance, if one were to have waiters on a bitflag, one would + * call wait_on_bit() in threads waiting for the bit to clear. + * One uses wait_on_bit() where one is waiting for the bit to clear, + * but has no intention of setting it. + */ +static inline int wait_on_bit(void *word, int bit, + int (*action)(void *), unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, action, mode); +} + +/** + * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit + * when one intends to set it, for instance, trying to lock bitflags. + * For instance, if one were to have waiters trying to set bitflag + * and waiting for it to clear before setting it, one would call + * wait_on_bit() in threads waiting to be able to set the bit. + * One uses wait_on_bit_lock() where one is waiting for the bit to + * clear with the intention of setting it, and when done, clearing it. + */ +static inline int wait_on_bit_lock(void *word, int bit, + int (*action)(void *), unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, action, mode); +} #endif /* __KERNEL__ */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 7c165c334be5..1c9994fe2acc 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,7 +68,7 @@ struct writeback_control { */ void writeback_inodes(struct writeback_control *wbc); void wake_up_inode(struct inode *inode); -void __wait_on_inode(struct inode * inode); +int inode_wait(void *); void sync_inodes_sb(struct super_block *, int wait); void sync_inodes(int wait); @@ -76,8 +76,8 @@ void sync_inodes(int wait); static inline void wait_on_inode(struct inode *inode) { might_sleep(); - if (inode->i_state & I_LOCK) - __wait_on_inode(inode); + wait_on_bit(&inode->i_state, __I_LOCK, inode_wait, + TASK_UNINTERRUPTIBLE); } /* diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d9c5d5c83d49..23f9c61d9546 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -5,6 +5,7 @@ Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. + Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H @@ -14,4 +15,19 @@ #define XATTR_SECURITY_PREFIX "security." +struct xattr_handler { + char *prefix; + size_t (*list)(struct inode *inode, char *list, size_t list_size, + const char *name, size_t name_len); + int (*get)(struct inode *inode, const char *name, void *buffer, + size_t size); + int (*set)(struct inode *inode, const char *name, const void *buffer, + size_t size, int flags); +}; + +ssize_t generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size); +ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); +int generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); +int generic_removexattr(struct dentry *dentry, const char *name); + #endif /* _LINUX_XATTR_H */ |