diff options
Diffstat (limited to 'old/xenolinux-2.4.16-sparse/drivers')
| -rw-r--r-- | old/xenolinux-2.4.16-sparse/drivers/block/Config.in | 51 | ||||
| -rw-r--r-- | old/xenolinux-2.4.16-sparse/drivers/block/ll_rw_blk.c | 1251 | ||||
| -rw-r--r-- | old/xenolinux-2.4.16-sparse/drivers/block/rd.c | 1009 | ||||
| -rw-r--r-- | old/xenolinux-2.4.16-sparse/drivers/char/tty_io.c | 2388 |
4 files changed, 4699 insertions, 0 deletions
diff --git a/old/xenolinux-2.4.16-sparse/drivers/block/Config.in b/old/xenolinux-2.4.16-sparse/drivers/block/Config.in new file mode 100644 index 0000000000..716774fe74 --- /dev/null +++ b/old/xenolinux-2.4.16-sparse/drivers/block/Config.in @@ -0,0 +1,51 @@ +# +# Block device driver configuration +# +mainmenu_option next_comment +comment 'Block devices' + +tristate 'Normal PC floppy disk support' CONFIG_BLK_DEV_FD +if [ "$CONFIG_AMIGA" = "y" ]; then + tristate 'Amiga floppy support' CONFIG_AMIGA_FLOPPY +fi +if [ "$CONFIG_ATARI" = "y" ]; then + tristate 'Atari floppy support' CONFIG_ATARI_FLOPPY +fi +if [ "$CONFIG_MAC" = "y" ]; then + dep_bool 'Macintosh IIfx/Quadra 900/Quadra 950 floppy support (EXPERIMENTAL)' CONFIG_BLK_DEV_SWIM_IOP $CONFIG_EXPERIMENTAL +fi +if [ "$CONFIG_MCA" = "y" ]; then + tristate 'PS/2 ESDI hard disk support' CONFIG_BLK_DEV_PS2 +fi +if [ "$CONFIG_ZORRO" = "y" ]; then + tristate 'Amiga Zorro II ramdisk support' CONFIG_AMIGA_Z2RAM +fi +if [ "$CONFIG_ATARI" = "y" ]; then + tristate 'Atari ACSI support' CONFIG_ATARI_ACSI + if [ "$CONFIG_ATARI_ACSI" != "n" ]; then + comment 'Some devices (e.g. CD jukebox) support multiple LUNs' + bool ' Probe all LUNs on each ACSI device' CONFIG_ACSI_MULTI_LUN + tristate ' Atari SLM laser printer support' CONFIG_ATARI_SLM + fi +fi +dep_tristate 'XT hard disk support' CONFIG_BLK_DEV_XD $CONFIG_ISA +dep_tristate 'Parallel port IDE device support' CONFIG_PARIDE $CONFIG_PARPORT +if [ "$CONFIG_PARIDE" = "y" -o "$CONFIG_PARIDE" = "m" ]; then + source drivers/block/paride/Config.in +fi +dep_tristate 'Compaq SMART2 support' CONFIG_BLK_CPQ_DA $CONFIG_PCI +dep_tristate 'Compaq Smart Array 5xxx support' CONFIG_BLK_CPQ_CISS_DA $CONFIG_PCI +dep_tristate 'Mylex DAC960/DAC1100 PCI RAID Controller support' CONFIG_BLK_DEV_DAC960 $CONFIG_PCI + +tristate 'Loopback device support' CONFIG_BLK_DEV_LOOP +dep_tristate 'Network block device support' CONFIG_BLK_DEV_NBD $CONFIG_NET + +tristate 'RAM disk support' CONFIG_BLK_DEV_RAM +if [ "$CONFIG_BLK_DEV_RAM" = "y" -o "$CONFIG_BLK_DEV_RAM" = "m" ]; then + int ' Default RAM disk size' CONFIG_BLK_DEV_RAM_SIZE 4096 +fi +dep_bool ' Initial RAM disk (initrd) support' CONFIG_BLK_DEV_INITRD $CONFIG_BLK_DEV_RAM + +bool 'XenoLinux virtual block device support' CONFIG_XENOLINUX_BLOCK + +endmenu diff --git a/old/xenolinux-2.4.16-sparse/drivers/block/ll_rw_blk.c b/old/xenolinux-2.4.16-sparse/drivers/block/ll_rw_blk.c new file mode 100644 index 0000000000..cd1cb7ca9c --- /dev/null +++ b/old/xenolinux-2.4.16-sparse/drivers/block/ll_rw_blk.c @@ -0,0 +1,1251 @@ +/* + * linux/drivers/block/ll_rw_blk.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 1994, Karl Keyte: Added support for disk statistics + * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE + * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> + * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> - July2000 + */ + +/* + * This handles all read/write requests to block devices + */ +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/config.h> +#include <linux/locks.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/init.h> +#include <linux/smp_lock.h> +#include <linux/completion.h> + +#include <asm/system.h> +#include <asm/io.h> +#include <linux/blk.h> +#include <linux/highmem.h> +#include <linux/slab.h> +#include <linux/module.h> + +/* + * MAC Floppy IWM hooks + */ + +#ifdef CONFIG_MAC_FLOPPY_IWM +extern int mac_floppy_init(void); +#endif + +/* + * For the allocated request tables + */ +static kmem_cache_t *request_cachep; + +/* + * The "disk" task queue is used to start the actual requests + * after a plug + */ +DECLARE_TASK_QUEUE(tq_disk); + +/* + * Protect the request list against multiple users.. + * + * With this spinlock the Linux block IO subsystem is 100% SMP threaded + * from the IRQ event side, and almost 100% SMP threaded from the syscall + * side (we still have protect against block device array operations, and + * the do_request() side is casually still unsafe. The kernel lock protects + * this part currently.). + * + * there is a fair chance that things will work just OK if these functions + * are called with no global kernel lock held ... + */ +spinlock_t io_request_lock = SPIN_LOCK_UNLOCKED; + +/* This specifies how many sectors to read ahead on the disk. */ + +int read_ahead[MAX_BLKDEV]; + +/* blk_dev_struct is: + * *request_fn + * *current_request + */ +struct blk_dev_struct blk_dev[MAX_BLKDEV]; /* initialized by blk_dev_init() */ + +/* + * blk_size contains the size of all block-devices in units of 1024 byte + * sectors: + * + * blk_size[MAJOR][MINOR] + * + * if (!blk_size[MAJOR]) then no minor size checking is done. + */ +int * blk_size[MAX_BLKDEV]; + +/* + * blksize_size contains the size of all block-devices: + * + * blksize_size[MAJOR][MINOR] + * + * if (!blksize_size[MAJOR]) then 1024 bytes is assumed. + */ +int * blksize_size[MAX_BLKDEV]; + +/* + * hardsect_size contains the size of the hardware sector of a device. + * + * hardsect_size[MAJOR][MINOR] + * + * if (!hardsect_size[MAJOR]) + * then 512 bytes is assumed. + * else + * sector_size is hardsect_size[MAJOR][MINOR] + * This is currently set by some scsi devices and read by the msdos fs driver. + * Other uses may appear later. + */ +int * hardsect_size[MAX_BLKDEV]; + +/* + * The following tunes the read-ahead algorithm in mm/filemap.c + */ +int * max_readahead[MAX_BLKDEV]; + +/* + * Max number of sectors per request + */ +int * max_sectors[MAX_BLKDEV]; + +/* + * How many reqeusts do we allocate per queue, + * and how many do we "batch" on freeing them? + */ +static int queue_nr_requests, batch_requests; + +static inline int get_max_sectors(kdev_t dev) +{ + if (!max_sectors[MAJOR(dev)]) + return MAX_SECTORS; + return max_sectors[MAJOR(dev)][MINOR(dev)]; +} + +inline request_queue_t *blk_get_queue(kdev_t dev) +{ + struct blk_dev_struct *bdev = blk_dev + MAJOR(dev); + + if (bdev->queue) + return bdev->queue(dev); + else + return &blk_dev[MAJOR(dev)].request_queue; +} + +static int __blk_cleanup_queue(struct request_list *list) +{ + struct list_head *head = &list->free; + struct request *rq; + int i = 0; + + while (!list_empty(head)) { + rq = list_entry(head->next, struct request, queue); + list_del(&rq->queue); + kmem_cache_free(request_cachep, rq); + i++; + }; + + if (i != list->count) + printk("request list leak!\n"); + + list->count = 0; + return i; +} + +/** + * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed + * @q: the request queue to be released + * + * Description: + * blk_cleanup_queue is the pair to blk_init_queue(). It should + * be called when a request queue is being released; typically + * when a block device is being de-registered. Currently, its + * primary task it to free all the &struct request structures that + * were allocated to the queue. + * Caveat: + * Hopefully the low level driver will have finished any + * outstanding requests first... + **/ +void blk_cleanup_queue(request_queue_t * q) +{ + int count = queue_nr_requests; + + count -= __blk_cleanup_queue(&q->rq[READ]); + count -= __blk_cleanup_queue(&q->rq[WRITE]); + + if (count) + printk("blk_cleanup_queue: leaked requests (%d)\n", count); + + memset(q, 0, sizeof(*q)); +} + +/** + * blk_queue_headactive - indicate whether head of request queue may be active + * @q: The queue which this applies to. + * @active: A flag indication where the head of the queue is active. + * + * Description: + * The driver for a block device may choose to leave the currently active + * request on the request queue, removing it only when it has completed. + * The queue handling routines assume this by default for safety reasons + * and will not involve the head of the request queue in any merging or + * reordering of requests when the queue is unplugged (and thus may be + * working on this particular request). + * + * If a driver removes requests from the queue before processing them, then + * it may indicate that it does so, there by allowing the head of the queue + * to be involved in merging and reordering. This is done be calling + * blk_queue_headactive() with an @active flag of %0. + * + * If a driver processes several requests at once, it must remove them (or + * at least all but one of them) from the request queue. + * + * When a queue is plugged the head will be assumed to be inactive. + **/ + +void blk_queue_headactive(request_queue_t * q, int active) +{ + q->head_active = active; +} + +/** + * blk_queue_make_request - define an alternate make_request function for a device + * @q: the request queue for the device to be affected + * @mfn: the alternate make_request function + * + * Description: + * The normal way for &struct buffer_heads to be passed to a device + * driver is for them to be collected into requests on a request + * queue, and then to allow the device driver to select requests + * off that queue when it is ready. This works well for many block + * devices. However some block devices (typically virtual devices + * such as md or lvm) do not benefit from the processing on the + * request queue, and are served best by having the requests passed + * directly to them. This can be achieved by providing a function + * to blk_queue_make_request(). + * + * Caveat: + * The driver that does this *must* be able to deal appropriately + * with buffers in "highmemory", either by calling bh_kmap() to get + * a kernel mapping, to by calling create_bounce() to create a + * buffer in normal memory. + **/ + +void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn) +{ + q->make_request_fn = mfn; +} + +static inline int ll_new_segment(request_queue_t *q, struct request *req, int max_segments) +{ + if (req->nr_segments < max_segments) { + req->nr_segments++; + return 1; + } + return 0; +} + +static int ll_back_merge_fn(request_queue_t *q, struct request *req, + struct buffer_head *bh, int max_segments) +{ + if (req->bhtail->b_data + req->bhtail->b_size == bh->b_data) + return 1; + return ll_new_segment(q, req, max_segments); +} + +static int ll_front_merge_fn(request_queue_t *q, struct request *req, + struct buffer_head *bh, int max_segments) +{ + if (bh->b_data + bh->b_size == req->bh->b_data) + return 1; + return ll_new_segment(q, req, max_segments); +} + +static int ll_merge_requests_fn(request_queue_t *q, struct request *req, + struct request *next, int max_segments) +{ + int total_segments = req->nr_segments + next->nr_segments; + + if (req->bhtail->b_data + req->bhtail->b_size == next->bh->b_data) + total_segments--; + + if (total_segments > max_segments) + return 0; + + req->nr_segments = total_segments; + return 1; +} + +/* + * "plug" the device if there are no outstanding requests: this will + * force the transfer to start only after we have put all the requests + * on the list. + * + * This is called with interrupts off and no requests on the queue. + * (and with the request spinlock acquired) + */ +static void generic_plug_device(request_queue_t *q, kdev_t dev) +{ + /* + * no need to replug device + */ + if (!list_empty(&q->queue_head) || q->plugged) + return; + + q->plugged = 1; + queue_task(&q->plug_tq, &tq_disk); +} + +/* + * remove the plug and let it rip.. + */ +static inline void __generic_unplug_device(request_queue_t *q) +{ + if (q->plugged) { + q->plugged = 0; + if (!list_empty(&q->queue_head)) + q->request_fn(q); + } +} + +void generic_unplug_device(void *data) +{ + request_queue_t *q = (request_queue_t *) data; + unsigned long flags; + + spin_lock_irqsave(&io_request_lock, flags); + __generic_unplug_device(q); + spin_unlock_irqrestore(&io_request_lock, flags); +} + +static void blk_init_free_list(request_queue_t *q) +{ + struct request *rq; + int i; + + INIT_LIST_HEAD(&q->rq[READ].free); + INIT_LIST_HEAD(&q->rq[WRITE].free); + q->rq[READ].count = 0; + q->rq[WRITE].count = 0; + + /* + * Divide requests in half between read and write + */ + for (i = 0; i < queue_nr_requests; i++) { + rq = kmem_cache_alloc(request_cachep, SLAB_KERNEL); + if (rq == NULL) { + /* We'll get a `leaked requests' message from blk_cleanup_queue */ + printk(KERN_EMERG "blk_init_free_list: error allocating requests\n"); + break; + } + memset(rq, 0, sizeof(struct request)); + rq->rq_status = RQ_INACTIVE; + list_add(&rq->queue, &q->rq[i&1].free); + q->rq[i&1].count++; + } + + init_waitqueue_head(&q->wait_for_request); + spin_lock_init(&q->queue_lock); +} + +static int __make_request(request_queue_t * q, int rw, struct buffer_head * bh); + +/** + * blk_init_queue - prepare a request queue for use with a block device + * @q: The &request_queue_t to be initialised + * @rfn: The function to be called to process requests that have been + * placed on the queue. + * + * Description: + * If a block device wishes to use the standard request handling procedures, + * which sorts requests and coalesces adjacent requests, then it must + * call blk_init_queue(). The function @rfn will be called when there + * are requests on the queue that need to be processed. If the device + * supports plugging, then @rfn may not be called immediately when requests + * are available on the queue, but may be called at some time later instead. + * Plugged queues are generally unplugged when a buffer belonging to one + * of the requests on the queue is needed, or due to memory pressure. + * + * @rfn is not required, or even expected, to remove all requests off the + * queue, but only as many as it can handle at a time. If it does leave + * requests on the queue, it is responsible for arranging that the requests + * get dealt with eventually. + * + * A global spin lock $io_request_lock must be held while manipulating the + * requests on the request queue. + * + * The request on the head of the queue is by default assumed to be + * potentially active, and it is not considered for re-ordering or merging + * whenever the given queue is unplugged. This behaviour can be changed with + * blk_queue_headactive(). + * + * Note: + * blk_init_queue() must be paired with a blk_cleanup_queue() call + * when the block device is deactivated (such as at module unload). + **/ +void blk_init_queue(request_queue_t * q, request_fn_proc * rfn) +{ + INIT_LIST_HEAD(&q->queue_head); + elevator_init(&q->elevator, ELEVATOR_LINUS); + blk_init_free_list(q); + q->request_fn = rfn; + q->back_merge_fn = ll_back_merge_fn; + q->front_merge_fn = ll_front_merge_fn; + q->merge_requests_fn = ll_merge_requests_fn; + q->make_request_fn = __make_request; + q->plug_tq.sync = 0; + q->plug_tq.routine = &generic_unplug_device; + q->plug_tq.data = q; + q->plugged = 0; + /* + * These booleans describe the queue properties. We set the + * default (and most common) values here. Other drivers can + * use the appropriate functions to alter the queue properties. + * as appropriate. + */ + q->plug_device_fn = generic_plug_device; + q->head_active = 1; +} + +#define blkdev_free_rq(list) list_entry((list)->next, struct request, queue); +/* + * Get a free request. io_request_lock must be held and interrupts + * disabled on the way in. + */ +static inline struct request *get_request(request_queue_t *q, int rw) +{ + struct request *rq = NULL; + struct request_list *rl = q->rq + rw; + + if (!list_empty(&rl->free)) { + rq = blkdev_free_rq(&rl->free); + list_del(&rq->queue); + rl->count--; + rq->rq_status = RQ_ACTIVE; + rq->special = NULL; + rq->q = q; + } + + return rq; +} + +/* + * No available requests for this queue, unplug the device. + */ +static struct request *__get_request_wait(request_queue_t *q, int rw) +{ + register struct request *rq; + DECLARE_WAITQUEUE(wait, current); + + generic_unplug_device(q); + add_wait_queue(&q->wait_for_request, &wait); + do { + set_current_state(TASK_UNINTERRUPTIBLE); + if (q->rq[rw].count < batch_requests) + schedule(); + spin_lock_irq(&io_request_lock); + rq = get_request(q,rw); + spin_unlock_irq(&io_request_lock); + } while (rq == NULL); + remove_wait_queue(&q->wait_for_request, &wait); + current->state = TASK_RUNNING; + return rq; +} + +static inline struct request *get_request_wait(request_queue_t *q, int rw) +{ + register struct request *rq; + + spin_lock_irq(&io_request_lock); + rq = get_request(q, rw); + spin_unlock_irq(&io_request_lock); + if (rq) + return rq; + return __get_request_wait(q, rw); +} + +/* RO fail safe mechanism */ + +static long ro_bits[MAX_BLKDEV][8]; + +int is_read_only(kdev_t dev) +{ + int minor,major; + + major = MAJOR(dev); + minor = MINOR(dev); + if (major < 0 || major >= MAX_BLKDEV) return 0; + return ro_bits[major][minor >> 5] & (1 << (minor & 31)); +} + +void set_device_ro(kdev_t dev,int flag) +{ + int minor,major; + + major = MAJOR(dev); + minor = MINOR(dev); + if (major < 0 || major >= MAX_BLKDEV) return; + if (flag) ro_bits[major][minor >> 5] |= 1 << (minor & 31); + else ro_bits[major][minor >> 5] &= ~(1 << (minor & 31)); +} + +inline void drive_stat_acct (kdev_t dev, int rw, + unsigned long nr_sectors, int new_io) +{ + unsigned int major = MAJOR(dev); + unsigned int index; + + index = disk_index(dev); + if ((index >= DK_MAX_DISK) || (major >= DK_MAX_MAJOR)) + return; + + kstat.dk_drive[major][index] += new_io; + if (rw == READ) { + kstat.dk_drive_rio[major][index] += new_io; + kstat.dk_drive_rblk[major][index] += nr_sectors; + } else if (rw == WRITE) { + kstat.dk_drive_wio[major][index] += new_io; + kstat.dk_drive_wblk[major][index] += nr_sectors; + } else + printk(KERN_ERR "drive_stat_acct: cmd not R/W?\n"); +} + +/* + * add-request adds a request to the linked list. + * io_request_lock is held and interrupts disabled, as we muck with the + * request queue list. + * + * By this point, req->cmd is always either READ/WRITE, never READA, + * which is important for drive_stat_acct() above. + */ +static inline void add_request(request_queue_t * q, struct request * req, + struct list_head *insert_here) +{ + drive_stat_acct(req->rq_dev, req->cmd, req->nr_sectors, 1); + + if (!q->plugged && q->head_active && insert_here == &q->queue_head) { + spin_unlock_irq(&io_request_lock); + printk("list_empty(&q->queue_head) is %d\n", + list_empty(&q->queue_head)); + BUG(); + } + + /* + * elevator indicated where it wants this request to be + * inserted at elevator_merge time + */ + list_add(&req->queue, insert_here); +} + +/* + * Must be called with io_request_lock held and interrupts disabled + */ +inline void blkdev_release_request(struct request *req) +{ + request_queue_t *q = req->q; + int rw = req->cmd; + + req->rq_status = RQ_INACTIVE; + req->q = NULL; + + /* + * Request may not have originated from ll_rw_blk. if not, + * assume it has free buffers and check waiters + */ + if (q) { + list_add(&req->queue, &q->rq[rw].free); + if (++q->rq[rw].count >= batch_requests && waitqueue_active(&q->wait_for_request)) + wake_up(&q->wait_for_request); + } +} + +/* + * Has to be called with the request spinlock acquired + */ +static void attempt_merge(request_queue_t * q, + struct request *req, + int max_sectors, + int max_segments) +{ + struct request *next; + + next = blkdev_next_request(req); + if (req->sector + req->nr_sectors != next->sector) + return; + if (req->cmd != next->cmd + || req->rq_dev != next->rq_dev + || req->nr_sectors + next->nr_sectors > max_sectors + || next->waiting) + return; + /* + * If we are not allowed to merge these requests, then + * return. If we are allowed to merge, then the count + * will have been updated to the appropriate number, + * and we shouldn't do it here too. + */ + if (!q->merge_requests_fn(q, req, next, max_segments)) + return; + + q->elevator.elevator_merge_req_fn(req, next); + req->bhtail->b_reqnext = next->bh; + req->bhtail = next->bhtail; + req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors; + list_del(&next->queue); + blkdev_release_request(next); +} + +static inline void attempt_back_merge(request_queue_t * q, + struct request *req, + int max_sectors, + int max_segments) +{ + if (&req->queue == q->queue_head.prev) + return; + attempt_merge(q, req, max_sectors, max_segments); +} + +static inline void attempt_front_merge(request_queue_t * q, + struct list_head * head, + struct request *req, + int max_sectors, + int max_segments) +{ + struct list_head * prev; + + prev = req->queue.prev; + if (head == prev) + return; + attempt_merge(q, blkdev_entry_to_request(prev), max_sectors, max_segments); +} + +static int __make_request(request_queue_t * q, int rw, + struct buffer_head * bh) +{ + unsigned int sector, count; + int max_segments = MAX_SEGMENTS; + struct request * req, *freereq = NULL; + int rw_ahead, max_sectors, el_ret; + struct list_head *head, *insert_here; + int latency; + elevator_t *elevator = &q->elevator; + + count = bh->b_size >> 9; + sector = bh->b_rsector; + + rw_ahead = 0; /* normal case; gets changed below for READA */ + switch (rw) { + case READA: + rw_ahead = 1; + rw = READ; /* drop into READ */ + case READ: + case WRITE: + latency = elevator_request_latency(elevator, rw); + break; + default: + BUG(); + goto end_io; + } + + /* We'd better have a real physical mapping! + Check this bit only if the buffer was dirty and just locked + down by us so at this point flushpage will block and + won't clear the mapped bit under us. */ + if (!buffer_mapped(bh)) + BUG(); + + /* + * Temporary solution - in 2.5 this will be done by the lowlevel + * driver. Create a bounce buffer if the buffer data points into + * high memory - keep the original buffer otherwise. + */ +#if CONFIG_HIGHMEM + bh = create_bounce(rw, bh); +#endif + +/* look for a free request. */ + /* + * Try to coalesce the new request with old requests + */ + max_sectors = get_max_sectors(bh->b_rdev); + +again: + req = NULL; + head = &q->queue_head; + /* + * Now we acquire the request spinlock, we have to be mega careful + * not to schedule or do something nonatomic + */ + spin_lock_irq(&io_request_lock); + + insert_here = head->prev; + if (list_empty(head)) { + q->plug_device_fn(q, bh->b_rdev); /* is atomic */ + goto get_rq; + } else if (q->head_active && !q->plugged) + head = head->next; + + el_ret = elevator->elevator_merge_fn(q, &req, head, bh, rw,max_sectors); + switch (el_ret) { + + case ELEVATOR_BACK_MERGE: + if (!q->back_merge_fn(q, req, bh, max_segments)) + break; + elevator->elevator_merge_cleanup_fn(q, req, count); + req->bhtail->b_reqnext = bh; + req->bhtail = bh; + req->nr_sectors = req->hard_nr_sectors += count; + blk_started_io(count); + drive_stat_acct(req->rq_dev, req->cmd, count, 0); + attempt_back_merge(q, req, max_sectors, max_segments); + goto out; + + case ELEVATOR_FRONT_MERGE: + if (!q->front_merge_fn(q, req, bh, max_segments)) + break; + elevator->elevator_merge_cleanup_fn(q, req, count); + bh->b_reqnext = req->bh; + req->bh = bh; + req->buffer = bh->b_data; + req->current_nr_sectors = count; + req->sector = req->hard_sector = sector; + req->nr_sectors = req->hard_nr_sectors += count; + blk_started_io(count); + drive_stat_acct(req->rq_dev, req->cmd, count, 0); + attempt_front_merge(q, head, req, max_sectors, max_segments); + goto out; + + /* + * elevator says don't/can't merge. get new request + */ + case ELEVATOR_NO_MERGE: + /* + * use elevator hints as to where to insert the + * request. if no hints, just add it to the back + * of the queue + */ + if (req) + insert_here = &req->queue; + break; + + default: + printk("elevator returned crap (%d)\n", el_ret); + BUG(); + } + + /* + * Grab a free request from the freelist - if that is empty, check + * if we are doing read ahead and abort instead of blocking for + * a free slot. + */ +get_rq: + if (freereq) { + req = freereq; + freereq = NULL; + } else if ((req = get_request(q, rw)) == NULL) { + spin_unlock_irq(&io_request_lock); + if (rw_ahead) + goto end_io; + + freereq = __get_request_wait(q, rw); + goto again; + } + +/* fill up the request-info, and add it to the queue */ + req->elevator_sequence = latency; + req->cmd = rw; + req->errors = 0; + req->hard_sector = req->sector = sector; + req->hard_nr_sectors = req->nr_sectors = count; + req->current_nr_sectors = count; + req->nr_segments = 1; /* Always 1 for a new request. */ + req->nr_hw_segments = 1; /* Always 1 for a new request. */ + req->buffer = bh->b_data; + req->waiting = NULL; + req->bh = bh; + req->bhtail = bh; + req->rq_dev = bh->b_rdev; + blk_started_io(count); + + add_request(q, req, insert_here); +out: + if (freereq) + blkdev_release_request(freereq); + spin_unlock_irq(&io_request_lock); + return 0; +end_io: + bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state)); + return 0; +} + +/** + * generic_make_request: hand a buffer head to it's device driver for I/O + * @rw: READ, WRITE, or READA - what sort of I/O is desired. + * @bh: The buffer head describing the location in memory and on the device. + * + * generic_make_request() is used to make I/O requests of block + * devices. It is passed a &struct buffer_head and a &rw value. The + * %READ and %WRITE options are (hopefully) obvious in meaning. The + * %READA value means that a read is required, but that the driver is + * free to fail the request if, for example, it cannot get needed + * resources immediately. + * + * generic_make_request() does not return any status. The + * success/failure status of the request, along with notification of + * completion, is delivered asynchronously through the bh->b_end_io + * function described (one day) else where. + * + * The caller of generic_make_request must make sure that b_page, + * b_addr, b_size are set to describe the memory buffer, that b_rdev + * and b_rsector are set to describe the device address, and the + * b_end_io and optionally b_private are set to describe how + * completion notification should be signaled. BH_Mapped should also + * be set (to confirm that b_dev and b_blocknr are valid). + * + * generic_make_request and the drivers it calls may use b_reqnext, + * and may change b_rdev and b_rsector. So the values of these fields + * should NOT be depended on after the call to generic_make_request. + * Because of this, the caller should record the device address + * information in b_dev and b_blocknr. + * + * Apart from those fields mentioned above, no other fields, and in + * particular, no other flags, are changed by generic_make_request or + * any lower level drivers. + * */ +void generic_make_request (int rw, struct buffer_head * bh) +{ + int major = MAJOR(bh->b_rdev); + int minorsize = 0; + request_queue_t *q; + + if (!bh->b_end_io) + BUG(); + + /* Test device size, when known. */ + if (blk_size[major]) + minorsize = blk_size[major][MINOR(bh->b_rdev)]; + if (minorsize) { + unsigned long maxsector = (minorsize << 1) + 1; + unsigned long sector = bh->b_rsector; + unsigned int count = bh->b_size >> 9; + + if (maxsector < count || maxsector - count < sector) { + /* Yecch */ + bh->b_state &= (1 << BH_Lock) | (1 << BH_Mapped); + + /* This may well happen - the kernel calls bread() + without checking the size of the device, e.g., + when mounting a device. */ + printk(KERN_INFO + "attempt to access beyond end of device\n"); + printk(KERN_INFO "%s: rw=%d, want=%ld, limit=%d\n", + kdevname(bh->b_rdev), rw, + (sector + count)>>1, minorsize); + + /* Yecch again */ + bh->b_end_io(bh, 0); + return; + } + } + + /* + * Resolve the mapping until finished. (drivers are + * still free to implement/resolve their own stacking + * by explicitly returning 0) + */ + /* NOTE: we don't repeat the blk_size check for each new device. + * Stacking drivers are expected to know what they are doing. + */ + do { + q = blk_get_queue(bh->b_rdev); + if (!q) { + printk(KERN_ERR + "generic_make_request: Trying to access " + "nonexistent block-device %s (%ld)\n", + kdevname(bh->b_rdev), bh->b_rsector); + buffer_IO_error(bh); + break; + } + } while (q->make_request_fn(q, rw, bh)); +} + + +/** + * submit_bh: submit a buffer_head to the block device later for I/O + * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead) + * @bh: The &struct buffer_head which describes the I/O + * + * submit_bh() is very similar in purpose to generic_make_request(), and + * uses that function to do most of the work. + * + * The extra functionality provided by submit_bh is to determine + * b_rsector from b_blocknr and b_size, and to set b_rdev from b_dev. + * This is is appropriate for IO requests that come from the buffer + * cache and page cache which (currently) always use aligned blocks. + */ +void submit_bh(int rw, struct buffer_head * bh) +{ + int count = bh->b_size >> 9; + + if (!test_bit(BH_Lock, &bh->b_state)) + BUG(); + + set_bit(BH_Req, &bh->b_state); + + /* + * First step, 'identity mapping' - RAID or LVM might + * further remap this. + */ + bh->b_rdev = bh->b_dev; + bh->b_rsector = bh->b_blocknr * count; + + generic_make_request(rw, bh); + + switch (rw) { + case WRITE: + kstat.pgpgout += count; + break; + default: + kstat.pgpgin += count; + break; + } +} + +/** + * ll_rw_block: low-level access to block devices + * @rw: whether to %READ or %WRITE or maybe %READA (readahead) + * @nr: number of &struct buffer_heads in the array + * @bhs: array of pointers to &struct buffer_head + * + * ll_rw_block() takes an array of pointers to &struct buffer_heads, + * and requests an I/O operation on them, either a %READ or a %WRITE. + * The third %READA option is described in the documentation for + * generic_make_request() which ll_rw_block() calls. + * + * This function provides extra functionality that is not in + * generic_make_request() that is relevant to buffers in the buffer + * cache or page cache. In particular it drops any buffer that it + * cannot get a lock on (with the BH_Lock state bit), any buffer that + * appears to be clean when doing a write request, and any buffer that + * appears to be up-to-date when doing read request. Further it marks + * as clean buffers that are processed for writing (the buffer cache + * wont assume that they are actually clean until the buffer gets + * unlocked). + * + * ll_rw_block sets b_end_io to simple completion handler that marks + * the buffer up-to-date (if approriate), unlocks the buffer and wakes + * any waiters. As client that needs a more interesting completion + * routine should call submit_bh() (or generic_make_request()) + * directly. + * + * Caveat: + * All of the buffers must be for the same device, and must also be + * of the current approved size for the device. */ + +void ll_rw_block(int rw, int nr, struct buffer_head * bhs[]) +{ + unsigned int major; + int correct_size; + int i; + + if (!nr) + return; + + major = MAJOR(bhs[0]->b_dev); + + /* Determine correct block size for this device. */ + correct_size = get_hardsect_size(bhs[0]->b_dev); + + /* Verify requested block sizes. */ + for (i = 0; i < nr; i++) { + struct buffer_head *bh = bhs[i]; + if (bh->b_size % correct_size) { + printk(KERN_NOTICE "ll_rw_block: device %s: " + "only %d-char blocks implemented (%u)\n", + kdevname(bhs[0]->b_dev), + correct_size, bh->b_size); + goto sorry; + } + } + + if ((rw & WRITE) && is_read_only(bhs[0]->b_dev)) { + printk(KERN_NOTICE "Can't write to read-only device %s\n", + kdevname(bhs[0]->b_dev)); + goto sorry; + } + + for (i = 0; i < nr; i++) { + struct buffer_head *bh = bhs[i]; + + /* Only one thread can actually submit the I/O. */ + if (test_and_set_bit(BH_Lock, &bh->b_state)) + continue; + + /* We have the buffer lock */ + atomic_inc(&bh->b_count); + bh->b_end_io = end_buffer_io_sync; + + switch(rw) { + case WRITE: + if (!atomic_set_buffer_clean(bh)) + /* Hmmph! Nothing to write */ + goto end_io; + __mark_buffer_clean(bh); + break; + + case READA: + case READ: + if (buffer_uptodate(bh)) + /* Hmmph! Already have it */ + goto end_io; + break; + default: + BUG(); + end_io: + bh->b_end_io(bh, test_bit(BH_Uptodate, &bh->b_state)); + continue; + } + + submit_bh(rw, bh); + } + return; + +sorry: + /* Make sure we don't get infinite dirty retries.. */ + for (i = 0; i < nr; i++) + mark_buffer_clean(bhs[i]); +} + +#ifdef CONFIG_STRAM_SWAP +extern int stram_device_init (void); +#endif + + +/** + * end_that_request_first - end I/O on one buffer. + * @req: the request being processed + * @uptodate: 0 for I/O error + * @name: the name printed for an I/O error + * + * Description: + * Ends I/O on the first buffer attached to @req, and sets it up + * for the next buffer_head (if any) in the cluster. + * + * Return: + * 0 - we are done with this request, call end_that_request_last() + * 1 - still buffers pending for this request + * + * Caveat: + * Drivers implementing their own end_request handling must call + * blk_finished_io() appropriately. + **/ + +int end_that_request_first (struct request *req, int uptodate, char *name) +{ + struct buffer_head * bh; + int nsect; + + req->errors = 0; + if (!uptodate) + printk("end_request: I/O error, dev %s (%s), sector %lu\n", + kdevname(req->rq_dev), name, req->sector); + + if ((bh = req->bh) != NULL) { + nsect = bh->b_size >> 9; + blk_finished_io(nsect); + req->bh = bh->b_reqnext; + bh->b_reqnext = NULL; + bh->b_end_io(bh, uptodate); + if ((bh = req->bh) != NULL) { + req->hard_sector += nsect; + req->hard_nr_sectors -= nsect; + req->sector = req->hard_sector; + req->nr_sectors = req->hard_nr_sectors; + + req->current_nr_sectors = bh->b_size >> 9; + if (req->nr_sectors < req->current_nr_sectors) { + req->nr_sectors = req->current_nr_sectors; + printk("end_request: buffer-list destroyed\n"); + } + req->buffer = bh->b_data; + return 1; + } + } + return 0; +} + +void end_that_request_last(struct request *req) +{ + if (req->waiting != NULL) + complete(req->waiting); + + blkdev_release_request(req); +} + +#define MB(kb) ((kb) << 10) + +int __init blk_dev_init(void) +{ + struct blk_dev_struct *dev; + int total_ram; + + request_cachep = kmem_cache_create("blkdev_requests", + sizeof(struct request), + 0, SLAB_HWCACHE_ALIGN, NULL, NULL); + + if (!request_cachep) + panic("Can't create request pool slab cache\n"); + + for (dev = blk_dev + MAX_BLKDEV; dev-- != blk_dev;) + dev->queue = NULL; + + memset(ro_bits,0,sizeof(ro_bits)); + memset(max_readahead, 0, sizeof(max_readahead)); + memset(max_sectors, 0, sizeof(max_sectors)); + + total_ram = nr_free_pages() << (PAGE_SHIFT - 10); + + /* + * Free request slots per queue. + * (Half for reads, half for writes) + */ + queue_nr_requests = 64; + if (total_ram > MB(32)) + queue_nr_requests = 128; + + /* + * Batch frees according to queue length + */ + batch_requests = queue_nr_requests/4; + printk("block: %d slots per queue, batch=%d\n", queue_nr_requests, batch_requests); + +#ifdef CONFIG_AMIGA_Z2RAM + z2_init(); +#endif +#ifdef CONFIG_STRAM_SWAP + stram_device_init(); +#endif +#ifdef CONFIG_BLK_DEV_RAM + rd_init(); +#endif +#ifdef CONFIG_ISP16_CDI + isp16_init(); +#endif +#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_IDE) + ide_init(); /* this MUST precede hd_init */ +#endif +#if defined(CONFIG_IDE) && defined(CONFIG_BLK_DEV_HD) + hd_init(); +#endif +#ifdef CONFIG_BLK_DEV_PS2 + ps2esdi_init(); +#endif +#ifdef CONFIG_BLK_DEV_XD + xd_init(); +#endif +#ifdef CONFIG_BLK_DEV_MFM + mfm_init(); +#endif +#ifdef CONFIG_PARIDE + { extern void paride_init(void); paride_init(); }; +#endif +#ifdef CONFIG_MAC_FLOPPY + swim3_init(); +#endif +#ifdef CONFIG_BLK_DEV_SWIM_IOP + swimiop_init(); +#endif +#ifdef CONFIG_AMIGA_FLOPPY + amiga_floppy_init(); +#endif +#ifdef CONFIG_ATARI_FLOPPY + atari_floppy_init(); +#endif +#ifdef CONFIG_BLK_DEV_FD + floppy_init(); +#else +#if defined(__i386__) && !defined(CONFIG_XENO) /* Do we even need this? */ + outb_p(0xc, 0x3f2); +#endif +#endif +#ifdef CONFIG_CDU31A + cdu31a_init(); +#endif +#ifdef CONFIG_ATARI_ACSI + acsi_init(); +#endif +#ifdef CONFIG_MCD + mcd_init(); +#endif +#ifdef CONFIG_MCDX + mcdx_init(); +#endif +#ifdef CONFIG_SBPCD + sbpcd_init(); +#endif +#ifdef CONFIG_AZTCD + aztcd_init(); +#endif +#ifdef CONFIG_CDU535 + sony535_init(); +#endif +#ifdef CONFIG_GSCD + gscd_init(); +#endif +#ifdef CONFIG_CM206 + cm206_init(); +#endif +#ifdef CONFIG_OPTCD + optcd_init(); +#endif +#ifdef CONFIG_SJCD + sjcd_init(); +#endif +#ifdef CONFIG_APBLOCK + ap_init(); +#endif +#ifdef CONFIG_DDV + ddv_init(); +#endif +#ifdef CONFIG_MDISK + mdisk_init(); +#endif +#ifdef CONFIG_DASD + dasd_init(); +#endif +#if defined(CONFIG_S390_TAPE) && defined(CONFIG_S390_TAPE_BLOCK) + tapeblock_init(); +#endif +#ifdef CONFIG_BLK_DEV_XPRAM + xpram_init(); +#endif + +#ifdef CONFIG_SUN_JSFLASH + jsfd_init(); +#endif + +#ifdef CONFIG_XENOLINUX_BLOCK + xlblk_init(); +#endif + + return 0; +}; + +EXPORT_SYMBOL(io_request_lock); +EXPORT_SYMBOL(end_that_request_first); +EXPORT_SYMBOL(end_that_request_last); +EXPORT_SYMBOL(blk_init_queue); +EXPORT_SYMBOL(blk_get_queue); +EXPORT_SYMBOL(blk_cleanup_queue); +EXPORT_SYMBOL(blk_queue_headactive); +EXPORT_SYMBOL(blk_queue_make_request); +EXPORT_SYMBOL(generic_make_request); +EXPORT_SYMBOL(blkdev_release_request); +EXPORT_SYMBOL(generic_unplug_device); diff --git a/old/xenolinux-2.4.16-sparse/drivers/block/rd.c b/old/xenolinux-2.4.16-sparse/drivers/block/rd.c new file mode 100644 index 0000000000..ffcc9d3825 --- /dev/null +++ b/old/xenolinux-2.4.16-sparse/drivers/block/rd.c @@ -0,0 +1,1009 @@ +/* + * ramdisk.c - Multiple RAM disk driver - gzip-loading version - v. 0.8 beta. + * + * (C) Chad Page, Theodore Ts'o, et. al, 1995. + * + * This RAM disk is designed to have filesystems created on it and mounted + * just like a regular floppy disk. + * + * It also does something suggested by Linus: use the buffer cache as the + * RAM disk data. This makes it possible to dynamically allocate the RAM disk + * buffer - with some consequences I have to deal with as I write this. + * + * This code is based on the original ramdisk.c, written mostly by + * Theodore Ts'o (TYT) in 1991. The code was largely rewritten by + * Chad Page to use the buffer cache to store the RAM disk data in + * 1995; Theodore then took over the driver again, and cleaned it up + * for inclusion in the mainline kernel. + * + * The original CRAMDISK code was written by Richard Lyons, and + * adapted by Chad Page to use the new RAM disk interface. Theodore + * Ts'o rewrote it so that both the compressed RAM disk loader and the + * kernel decompressor uses the same inflate.c codebase. The RAM disk + * loader now also loads into a dynamic (buffer cache based) RAM disk, + * not the old static RAM disk. Support for the old static RAM disk has + * been completely removed. + * + * Loadable module support added by Tom Dyas. + * + * Further cleanups by Chad Page (page0588@sundance.sjsu.edu): + * Cosmetic changes in #ifdef MODULE, code movement, etc. + * When the RAM disk module is removed, free the protected buffers + * Default RAM disk size changed to 2.88 MB + * + * Added initrd: Werner Almesberger & Hans Lermen, Feb '96 + * + * 4/25/96 : Made RAM disk size a parameter (default is now 4 MB) + * - Chad Page + * + * Add support for fs images split across >1 disk, Paul Gortmaker, Mar '98 + * + * Make block size and block size shift for RAM disks a global macro + * and set blk_size for -ENOSPC, Werner Fink <werner@suse.de>, Apr '99 + */ + +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/minix_fs.h> +#include <linux/ext2_fs.h> +#include <linux/romfs_fs.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/hdreg.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/slab.h> +#include <linux/ioctl.h> +#include <linux/fd.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/devfs_fs_kernel.h> +#include <linux/smp_lock.h> + +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/byteorder.h> + +extern void wait_for_keypress(void); + +/* + * 35 has been officially registered as the RAMDISK major number, but + * so is the original MAJOR number of 1. We're using 1 in + * include/linux/major.h for now + */ +#define MAJOR_NR RAMDISK_MAJOR +#include <linux/blk.h> +#include <linux/blkpg.h> + +/* The RAM disk size is now a parameter */ +#define NUM_RAMDISKS 16 /* This cannot be overridden (yet) */ + +#ifndef MODULE +/* We don't have to load RAM disks or gunzip them in a module. */ +#define RD_LOADER +#define BUILD_CRAMDISK + +void rd_load(void); +static int crd_load(struct file *fp, struct file *outfp); + +#ifdef CONFIG_BLK_DEV_INITRD +static int initrd_users; +#endif +#endif + +/* Various static variables go here. Most are used only in the RAM disk code. + */ + +static unsigned long rd_length[NUM_RAMDISKS]; /* Size of RAM disks in bytes */ +static int rd_hardsec[NUM_RAMDISKS]; /* Size of real blocks in bytes */ +static int rd_blocksizes[NUM_RAMDISKS]; /* Size of 1024 byte blocks :) */ +static int rd_kbsize[NUM_RAMDISKS]; /* Size in blocks of 1024 bytes */ +static devfs_handle_t devfs_handle; +static struct block_device *rd_bdev[NUM_RAMDISKS];/* Protected device data */ + +/* + * Parameters for the boot-loading of the RAM disk. These are set by + * init/main.c (from arguments to the kernel command line) or from the + * architecture-specific setup routine (from the stored boot sector + * information). + */ +int rd_size = CONFIG_BLK_DEV_RAM_SIZE; /* Size of the RAM disks */ +/* + * It would be very desiderable to have a soft-blocksize (that in the case + * of the ramdisk driver is also the hardblocksize ;) of PAGE_SIZE because + * doing that we'll achieve a far better MM footprint. Using a rd_blocksize of + * BLOCK_SIZE in the worst case we'll make PAGE_SIZE/BLOCK_SIZE buffer-pages + * unfreeable. With a rd_blocksize of PAGE_SIZE instead we are sure that only + * 1 page will be protected. Depending on the size of the ramdisk you + * may want to change the ramdisk blocksize to achieve a better or worse MM + * behaviour. The default is still BLOCK_SIZE (needed by rd_load_image that + * supposes the filesystem in the image uses a BLOCK_SIZE blocksize). + */ +int rd_blocksize = BLOCK_SIZE; /* blocksize of the RAM disks */ + +#ifndef MODULE + +int rd_doload; /* 1 = load RAM disk, 0 = don't load */ +int rd_prompt = 1; /* 1 = prompt for RAM disk, 0 = don't prompt */ +int rd_image_start; /* starting block # of image */ +#ifdef CONFIG_BLK_DEV_INITRD +unsigned long initrd_start, initrd_end; +int mount_initrd = 1; /* zero if initrd should not be mounted */ +int initrd_below_start_ok; + +static int __init no_initrd(char *str) +{ + mount_initrd = 0; + return 1; +} + +__setup("noinitrd", no_initrd); + +#endif + +static int __init ramdisk_start_setup(char *str) +{ + rd_image_start = simple_strtol(str,NULL,0); + return 1; +} + +static int __init load_ramdisk(char *str) +{ + rd_doload = simple_strtol(str,NULL,0) & 3; + return 1; +} + +static int __init prompt_ramdisk(char *str) +{ + rd_prompt = simple_strtol(str,NULL,0) & 1; + return 1; +} + +static int __init ramdisk_size(char *str) +{ + rd_size = simple_strtol(str,NULL,0); + return 1; +} + +static int __init ramdisk_size2(char *str) +{ + return ramdisk_size(str); +} + +static int __init ramdisk_blocksize(char *str) +{ + rd_blocksize = simple_strtol(str,NULL,0); + return 1; +} + +__setup("ramdisk_start=", ramdisk_start_setup); +__setup("load_ramdisk=", load_ramdisk); +__setup("prompt_ramdisk=", prompt_ramdisk); +__setup("ramdisk=", ramdisk_size); +__setup("ramdisk_size=", ramdisk_size2); +__setup("ramdisk_blocksize=", ramdisk_blocksize); + +#endif + +/* + * Copyright (C) 2000 Linus Torvalds. + * 2000 Transmeta Corp. + * aops copied from ramfs. + */ +static int ramdisk_readpage(struct file *file, struct page * page) +{ + if (!Page_Uptodate(page)) { + memset(kmap(page), 0, PAGE_CACHE_SIZE); + kunmap(page); + flush_dcache_page(page); + SetPageUptodate(page); + } + UnlockPage(page); + return 0; +} + +static int ramdisk_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to) +{ + if (!Page_Uptodate(page)) { + void *addr = page_address(page); + memset(addr, 0, PAGE_CACHE_SIZE); + flush_dcache_page(page); + SetPageUptodate(page); + } + SetPageDirty(page); + return 0; +} + +static int ramdisk_commit_write(struct file *file, struct page *page, unsigned offset, unsigned to) +{ + return 0; +} + +static struct address_space_operations ramdisk_aops = { + readpage: ramdisk_readpage, + writepage: fail_writepage, + prepare_write: ramdisk_prepare_write, + commit_write: ramdisk_commit_write, +}; + +static int rd_blkdev_pagecache_IO(int rw, struct buffer_head * sbh, int minor) +{ + struct address_space * mapping; + unsigned long index; + int offset, size, err; + + err = -EIO; + err = 0; + mapping = rd_bdev[minor]->bd_inode->i_mapping; + + index = sbh->b_rsector >> (PAGE_CACHE_SHIFT - 9); + offset = (sbh->b_rsector << 9) & ~PAGE_CACHE_MASK; + size = sbh->b_size; + + do { + int count; + struct page ** hash; + struct page * page; + char * src, * dst; + int unlock = 0; + + count = PAGE_CACHE_SIZE - offset; + if (count > size) + count = size; + size -= count; + + hash = page_hash(mapping, index); + page = __find_get_page(mapping, index, hash); + if (!page) { + page = grab_cache_page(mapping, index); + err = -ENOMEM; + if (!page) + goto out; + err = 0; + + if (!Page_Uptodate(page)) { + memset(kmap(page), 0, PAGE_CACHE_SIZE); + kunmap(page); + SetPageUptodate(page); + } + + unlock = 1; + } + + index++; + + if (rw == READ) { + src = kmap(page); + src += offset; + dst = bh_kmap(sbh); + } else { + dst = kmap(page); + dst += offset; + src = bh_kmap(sbh); + } + offset = 0; + + memcpy(dst, src, count); + + kunmap(page); + bh_kunmap(sbh); + + if (rw == READ) { + flush_dcache_page(page); + } else { + SetPageDirty(page); + } + if (unlock) + UnlockPage(page); + __free_page(page); + } while (size); + + out: + return err; +} + +/* + * Basically, my strategy here is to set up a buffer-head which can't be + * deleted, and make that my Ramdisk. If the request is outside of the + * allocated size, we must get rid of it... + * + * 19-JAN-1998 Richard Gooch <rgooch@atnf.csiro.au> Added devfs support + * + */ +static int rd_make_request(request_queue_t * q, int rw, struct buffer_head *sbh) +{ + unsigned int minor; + unsigned long offset, len; + + minor = MINOR(sbh->b_rdev); + + if (minor >= NUM_RAMDISKS) + goto fail; + + + offset = sbh->b_rsector << 9; + len = sbh->b_size; + + if ((offset + len) > rd_length[minor]) + goto fail; + + if (rw==READA) + rw=READ; + if ((rw != READ) && (rw != WRITE)) { + printk(KERN_INFO "RAMDISK: bad command: %d\n", rw); + goto fail; + } + + if (rd_blkdev_pagecache_IO(rw, sbh, minor)) + goto fail; + + sbh->b_end_io(sbh,1); + return 0; + fail: + sbh->b_end_io(sbh,0); + return 0; +} + +static int rd_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg) +{ + int error = -EINVAL; + unsigned int minor; + + if (!inode || !inode->i_rdev) + goto out; + + minor = MINOR(inode->i_rdev); + + switch (cmd) { + case BLKFLSBUF: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + /* special: we want to release the ramdisk memory, + it's not like with the other blockdevices where + this ioctl only flushes away the buffer cache. */ + error = -EBUSY; + down(&inode->i_bdev->bd_sem); + if (inode->i_bdev->bd_openers <= 2) { + truncate_inode_pages(inode->i_mapping, 0); + error = 0; + } + up(&inode->i_bdev->bd_sem); + break; + case BLKGETSIZE: /* Return device size */ + if (!arg) + break; + error = put_user(rd_kbsize[minor] << 1, (unsigned long *) arg); + break; + case BLKGETSIZE64: + error = put_user((u64)rd_kbsize[minor]<<10, (u64*)arg); + break; + case BLKROSET: + case BLKROGET: + case BLKSSZGET: + error = blk_ioctl(inode->i_rdev, cmd, arg); + }; +out: + return error; +} + + +#ifdef CONFIG_BLK_DEV_INITRD + +static ssize_t initrd_read(struct file *file, char *buf, + size_t count, loff_t *ppos) +{ + int left; + + left = initrd_end - initrd_start - *ppos; + if (count > left) count = left; + if (count == 0) return 0; + copy_to_user(buf, (char *)initrd_start + *ppos, count); + *ppos += count; + return count; +} + + +static int initrd_release(struct inode *inode,struct file *file) +{ + extern void free_initrd_mem(unsigned long, unsigned long); + + lock_kernel(); + if (!--initrd_users) { + free_initrd_mem(initrd_start, initrd_end); + initrd_start = 0; + } + unlock_kernel(); + blkdev_put(inode->i_bdev, BDEV_FILE); + return 0; +} + + +static struct file_operations initrd_fops = { + read: initrd_read, + release: initrd_release, +}; + +#endif + + +static int rd_open(struct inode * inode, struct file * filp) +{ + int unit = DEVICE_NR(inode->i_rdev); + +#ifdef CONFIG_BLK_DEV_INITRD + if (unit == INITRD_MINOR) { + if (!initrd_start) return -ENODEV; + initrd_users++; + filp->f_op = &initrd_fops; + return 0; + } +#endif + + if (unit >= NUM_RAMDISKS) + return -ENXIO; + + /* + * Immunize device against invalidate_buffers() and prune_icache(). + */ + if (rd_bdev[unit] == NULL) { + rd_bdev[unit] = bdget(kdev_t_to_nr(inode->i_rdev)); + rd_bdev[unit]->bd_openers++; + rd_bdev[unit]->bd_inode->i_mapping->a_ops = &ramdisk_aops; + } + + return 0; +} + +static struct block_device_operations rd_bd_op = { + owner: THIS_MODULE, + open: rd_open, + ioctl: rd_ioctl, +}; + +#ifdef MODULE +/* Before freeing the module, invalidate all of the protected buffers! */ +static void __exit rd_cleanup (void) +{ + int i; + + for (i = 0 ; i < NUM_RAMDISKS; i++) { + struct block_device *bdev = rd_bdev[i]; + rd_bdev[i] = NULL; + if (bdev) + blkdev_put(bdev, BDEV_FILE); + destroy_buffers(MKDEV(MAJOR_NR, i)); + } + + devfs_unregister (devfs_handle); + unregister_blkdev( MAJOR_NR, "ramdisk" ); + hardsect_size[MAJOR_NR] = NULL; + blksize_size[MAJOR_NR] = NULL; + blk_size[MAJOR_NR] = NULL; +} +#endif + +/* This is the registration and initialization section of the RAM disk driver */ +int __init rd_init (void) +{ + int i; + + if (rd_blocksize > PAGE_SIZE || rd_blocksize < 512 || + (rd_blocksize & (rd_blocksize-1))) + { + printk("RAMDISK: wrong blocksize %d, reverting to defaults\n", + rd_blocksize); + rd_blocksize = BLOCK_SIZE; + } + + if (register_blkdev(MAJOR_NR, "ramdisk", &rd_bd_op)) { + printk("RAMDISK: Could not get major %d", MAJOR_NR); + return -EIO; + } + + blk_queue_make_request(BLK_DEFAULT_QUEUE(MAJOR_NR), &rd_make_request); + + for (i = 0; i < NUM_RAMDISKS; i++) { + /* rd_size is given in kB */ + rd_length[i] = rd_size << 10; + rd_hardsec[i] = rd_blocksize; + rd_blocksizes[i] = rd_blocksize; + rd_kbsize[i] = rd_size; + } + devfs_handle = devfs_mk_dir (NULL, "rd", NULL); + devfs_register_series (devfs_handle, "%u", NUM_RAMDISKS, + DEVFS_FL_DEFAULT, MAJOR_NR, 0, + S_IFBLK | S_IRUSR | S_IWUSR, + &rd_bd_op, NULL); + + for (i = 0; i < NUM_RAMDISKS; i++) + register_disk(NULL, MKDEV(MAJOR_NR,i), 1, &rd_bd_op, rd_size<<1); + +#ifdef CONFIG_BLK_DEV_INITRD + /* We ought to separate initrd operations here */ + register_disk(NULL, MKDEV(MAJOR_NR,INITRD_MINOR), 1, &rd_bd_op, rd_size<<1); +#endif + + hardsect_size[MAJOR_NR] = rd_hardsec; /* Size of the RAM disk blocks */ + blksize_size[MAJOR_NR] = rd_blocksizes; /* Avoid set_blocksize() check */ + blk_size[MAJOR_NR] = rd_kbsize; /* Size of the RAM disk in kB */ + + /* rd_size is given in kB */ + printk("RAMDISK driver initialized: " + "%d RAM disks of %dK size %d blocksize\n", + NUM_RAMDISKS, rd_size, rd_blocksize); + + return 0; +} + +#ifdef MODULE +module_init(rd_init); +module_exit(rd_cleanup); +#endif + +/* loadable module support */ +MODULE_PARM (rd_size, "1i"); +MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes."); +MODULE_PARM (rd_blocksize, "i"); +MODULE_PARM_DESC(rd_blocksize, "Blocksize of each RAM disk in bytes."); + +MODULE_LICENSE("GPL"); + +/* End of non-loading portions of the RAM disk driver */ + +#ifdef RD_LOADER +/* + * This routine tries to find a RAM disk image to load, and returns the + * number of blocks to read for a non-compressed image, 0 if the image + * is a compressed image, and -1 if an image with the right magic + * numbers could not be found. + * + * We currently check for the following magic numbers: + * minix + * ext2 + * romfs + * gzip + */ +static int __init +identify_ramdisk_image(kdev_t device, struct file *fp, int start_block) +{ + const int size = 512; + struct minix_super_block *minixsb; + struct ext2_super_block *ext2sb; + struct romfs_super_block *romfsb; + int nblocks = -1; + unsigned char *buf; + + buf = kmalloc(size, GFP_KERNEL); + if (buf == 0) + return -1; + + minixsb = (struct minix_super_block *) buf; + ext2sb = (struct ext2_super_block *) buf; + romfsb = (struct romfs_super_block *) buf; + memset(buf, 0xe5, size); + + /* + * Read block 0 to test for gzipped kernel + */ + if (fp->f_op->llseek) + fp->f_op->llseek(fp, start_block * BLOCK_SIZE, 0); + fp->f_pos = start_block * BLOCK_SIZE; + + fp->f_op->read(fp, buf, size, &fp->f_pos); + + /* + * If it matches the gzip magic numbers, return -1 + */ + if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) { + printk(KERN_NOTICE + "RAMDISK: Compressed image found at block %d\n", + start_block); + nblocks = 0; + goto done; + } + + /* romfs is at block zero too */ + if (romfsb->word0 == ROMSB_WORD0 && + romfsb->word1 == ROMSB_WORD1) { + printk(KERN_NOTICE + "RAMDISK: romfs filesystem found at block %d\n", + start_block); + nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS; + goto done; + } + + /* + * Read block 1 to test for minix and ext2 superblock + */ + if (fp->f_op->llseek) + fp->f_op->llseek(fp, (start_block+1) * BLOCK_SIZE, 0); + fp->f_pos = (start_block+1) * BLOCK_SIZE; + + fp->f_op->read(fp, buf, size, &fp->f_pos); + + /* Try minix */ + if (minixsb->s_magic == MINIX_SUPER_MAGIC || + minixsb->s_magic == MINIX_SUPER_MAGIC2) { + printk(KERN_NOTICE + "RAMDISK: Minix filesystem found at block %d\n", + start_block); + nblocks = minixsb->s_nzones << minixsb->s_log_zone_size; + goto done; + } + + /* Try ext2 */ + if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) { + printk(KERN_NOTICE + "RAMDISK: ext2 filesystem found at block %d\n", + start_block); + nblocks = le32_to_cpu(ext2sb->s_blocks_count); + goto done; + } + + printk(KERN_NOTICE + "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n", + start_block); + +done: + if (fp->f_op->llseek) + fp->f_op->llseek(fp, start_block * BLOCK_SIZE, 0); + fp->f_pos = start_block * BLOCK_SIZE; + + kfree(buf); + return nblocks; +} + +/* + * This routine loads in the RAM disk image. + */ +static void __init rd_load_image(kdev_t device, int offset, int unit) +{ + struct inode *inode, *out_inode; + struct file infile, outfile; + struct dentry in_dentry, out_dentry; + mm_segment_t fs; + kdev_t ram_device; + int nblocks, i; + char *buf; + unsigned short rotate = 0; + unsigned short devblocks = 0; +#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES) && !defined(CONFIG_XENO) + char rotator[4] = { '|' , '/' , '-' , '\\' }; +#endif + ram_device = MKDEV(MAJOR_NR, unit); + + if ((inode = get_empty_inode()) == NULL) + return; + memset(&infile, 0, sizeof(infile)); + memset(&in_dentry, 0, sizeof(in_dentry)); + infile.f_mode = 1; /* read only */ + infile.f_dentry = &in_dentry; + in_dentry.d_inode = inode; + infile.f_op = &def_blk_fops; + init_special_inode(inode, S_IFBLK | S_IRUSR, kdev_t_to_nr(device)); + + if ((out_inode = get_empty_inode()) == NULL) + goto free_inode; + memset(&outfile, 0, sizeof(outfile)); + memset(&out_dentry, 0, sizeof(out_dentry)); + outfile.f_mode = 3; /* read/write */ + outfile.f_dentry = &out_dentry; + out_dentry.d_inode = out_inode; + outfile.f_op = &def_blk_fops; + init_special_inode(out_inode, S_IFBLK | S_IRUSR | S_IWUSR, kdev_t_to_nr(ram_device)); + + if (blkdev_open(inode, &infile) != 0) { + iput(out_inode); + goto free_inode; + } + if (blkdev_open(out_inode, &outfile) != 0) + goto free_inodes; + + fs = get_fs(); + set_fs(KERNEL_DS); + + nblocks = identify_ramdisk_image(device, &infile, offset); + if (nblocks < 0) + goto done; + + if (nblocks == 0) { +#ifdef BUILD_CRAMDISK + if (crd_load(&infile, &outfile) == 0) + goto successful_load; +#else + printk(KERN_NOTICE + "RAMDISK: Kernel does not support compressed " + "RAM disk images\n"); +#endif + goto done; + } + + /* + * NOTE NOTE: nblocks suppose that the blocksize is BLOCK_SIZE, so + * rd_load_image will work only with filesystem BLOCK_SIZE wide! + * So make sure to use 1k blocksize while generating ext2fs + * ramdisk-images. + */ + if (nblocks > (rd_length[unit] >> BLOCK_SIZE_BITS)) { + printk("RAMDISK: image too big! (%d/%ld blocks)\n", + nblocks, rd_length[unit] >> BLOCK_SIZE_BITS); + goto done; + } + + /* + * OK, time to copy in the data + */ + buf = kmalloc(BLOCK_SIZE, GFP_KERNEL); + if (buf == 0) { + printk(KERN_ERR "RAMDISK: could not allocate buffer\n"); + goto done; + } + + if (blk_size[MAJOR(device)]) + devblocks = blk_size[MAJOR(device)][MINOR(device)]; + +#ifdef CONFIG_BLK_DEV_INITRD + if (MAJOR(device) == MAJOR_NR && MINOR(device) == INITRD_MINOR) + devblocks = nblocks; +#endif + + if (devblocks == 0) { + printk(KERN_ERR "RAMDISK: could not determine device size\n"); + goto done; + } + + printk(KERN_NOTICE "RAMDISK: Loading %d blocks [%d disk%s] into ram disk... ", + nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : ""); + for (i=0; i < nblocks; i++) { + if (i && (i % devblocks == 0)) { + printk("done disk #%d.\n", i/devblocks); + rotate = 0; + if (infile.f_op->release(inode, &infile) != 0) { + printk("Error closing the disk.\n"); + goto noclose_input; + } + printk("Please insert disk #%d and press ENTER\n", i/devblocks+1); + wait_for_keypress(); + if (blkdev_open(inode, &infile) != 0) { + printk("Error opening disk.\n"); + goto noclose_input; + } + infile.f_pos = 0; + printk("Loading disk #%d... ", i/devblocks+1); + } + infile.f_op->read(&infile, buf, BLOCK_SIZE, &infile.f_pos); + outfile.f_op->write(&outfile, buf, BLOCK_SIZE, &outfile.f_pos); +#if !defined(CONFIG_ARCH_S390) && !defined(CONFIG_PPC_ISERIES) && !defined(CONFIG_XENO) + if (!(i % 16)) { + printk("%c\b", rotator[rotate & 0x3]); + rotate++; + } +#endif + } + printk("done.\n"); + kfree(buf); + +successful_load: + ROOT_DEV = MKDEV(MAJOR_NR, unit); + if (ROOT_DEVICE_NAME != NULL) strcpy (ROOT_DEVICE_NAME, "rd/0"); + +done: + infile.f_op->release(inode, &infile); +noclose_input: + blkdev_close(out_inode, &outfile); + iput(inode); + iput(out_inode); + set_fs(fs); + return; +free_inodes: /* free inodes on error */ + iput(out_inode); + infile.f_op->release(inode, &infile); +free_inode: + iput(inode); +} + +#ifdef CONFIG_MAC_FLOPPY +int swim3_fd_eject(int devnum); +#endif + +static void __init rd_load_disk(int n) +{ + + if (rd_doload == 0) + return; + + if (MAJOR(ROOT_DEV) != FLOPPY_MAJOR +#ifdef CONFIG_BLK_DEV_INITRD + && MAJOR(real_root_dev) != FLOPPY_MAJOR +#endif + ) + return; + + if (rd_prompt) { +#ifdef CONFIG_BLK_DEV_FD + floppy_eject(); +#endif +#ifdef CONFIG_MAC_FLOPPY + if(MAJOR(ROOT_DEV) == FLOPPY_MAJOR) + swim3_fd_eject(MINOR(ROOT_DEV)); + else if(MAJOR(real_root_dev) == FLOPPY_MAJOR) + swim3_fd_eject(MINOR(real_root_dev)); +#endif + printk(KERN_NOTICE + "VFS: Insert root floppy disk to be loaded into RAM disk and press ENTER\n"); + wait_for_keypress(); + } + + rd_load_image(ROOT_DEV,rd_image_start, n); + +} + +void __init rd_load(void) +{ + rd_load_disk(0); +} + +void __init rd_load_secondary(void) +{ + rd_load_disk(1); +} + +#ifdef CONFIG_BLK_DEV_INITRD +void __init initrd_load(void) +{ + rd_load_image(MKDEV(MAJOR_NR, INITRD_MINOR),rd_image_start,0); +} +#endif + +#endif /* RD_LOADER */ + +#ifdef BUILD_CRAMDISK + +/* + * gzip declarations + */ + +#define OF(args) args + +#ifndef memzero +#define memzero(s, n) memset ((s), 0, (n)) +#endif + +typedef unsigned char uch; +typedef unsigned short ush; +typedef unsigned long ulg; + +#define INBUFSIZ 4096 +#define WSIZE 0x8000 /* window size--must be a power of two, and */ + /* at least 32K for zip's deflate method */ + +static uch *inbuf; +static uch *window; + +static unsigned insize; /* valid bytes in inbuf */ +static unsigned inptr; /* index of next byte to be processed in inbuf */ +static unsigned outcnt; /* bytes in output buffer */ +static int exit_code; +static long bytes_out; +static struct file *crd_infp, *crd_outfp; + +#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) + +/* Diagnostic functions (stubbed out) */ +#define Assert(cond,msg) +#define Trace(x) +#define Tracev(x) +#define Tracevv(x) +#define Tracec(c,x) +#define Tracecv(c,x) + +#define STATIC static + +static int fill_inbuf(void); +static void flush_window(void); +static void *malloc(int size); +static void free(void *where); +static void error(char *m); +static void gzip_mark(void **); +static void gzip_release(void **); + +#include "../../lib/inflate.c" + +static void __init *malloc(int size) +{ + return kmalloc(size, GFP_KERNEL); +} + +static void __init free(void *where) +{ + kfree(where); +} + +static void __init gzip_mark(void **ptr) +{ +} + +static void __init gzip_release(void **ptr) +{ +} + + +/* =========================================================================== + * Fill the input buffer. This is called only when the buffer is empty + * and at least one byte is really needed. + */ +static int __init fill_inbuf(void) +{ + if (exit_code) return -1; + + insize = crd_infp->f_op->read(crd_infp, inbuf, INBUFSIZ, + &crd_infp->f_pos); + if (insize == 0) return -1; + + inptr = 1; + + return inbuf[0]; +} + +/* =========================================================================== + * Write the output window window[0..outcnt-1] and update crc and bytes_out. + * (Used for the decompressed data only.) + */ +static void __init flush_window(void) +{ + ulg c = crc; /* temporary variable */ + unsigned n; + uch *in, ch; + + crd_outfp->f_op->write(crd_outfp, window, outcnt, &crd_outfp->f_pos); + in = window; + for (n = 0; n < outcnt; n++) { + ch = *in++; + c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8); + } + crc = c; + bytes_out += (ulg)outcnt; + outcnt = 0; +} + +static void __init error(char *x) +{ + printk(KERN_ERR "%s", x); + exit_code = 1; +} + +static int __init +crd_load(struct file * fp, struct file *outfp) +{ + int result; + + insize = 0; /* valid bytes in inbuf */ + inptr = 0; /* index of next byte to be processed in inbuf */ + outcnt = 0; /* bytes in output buffer */ + exit_code = 0; + bytes_out = 0; + crc = (ulg)0xffffffffL; /* shift register contents */ + + crd_infp = fp; + crd_outfp = outfp; + inbuf = kmalloc(INBUFSIZ, GFP_KERNEL); + if (inbuf == 0) { + printk(KERN_ERR "RAMDISK: Couldn't allocate gzip buffer\n"); + return -1; + } + window = kmalloc(WSIZE, GFP_KERNEL); + if (window == 0) { + printk(KERN_ERR "RAMDISK: Couldn't allocate gzip window\n"); + kfree(inbuf); + return -1; + } + makecrc(); + result = gunzip(); + kfree(inbuf); + kfree(window); + return result; +} + +#endif /* BUILD_CRAMDISK */ + diff --git a/old/xenolinux-2.4.16-sparse/drivers/char/tty_io.c b/old/xenolinux-2.4.16-sparse/drivers/char/tty_io.c new file mode 100644 index 0000000000..1466b03add --- /dev/null +++ b/old/xenolinux-2.4.16-sparse/drivers/char/tty_io.c @@ -0,0 +1,2388 @@ +/* + * linux/drivers/char/tty_io.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles + * or rs-channels. It also implements echoing, cooked mode etc. + * + * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0. + * + * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the + * tty_struct and tty_queue structures. Previously there was an array + * of 256 tty_struct's which was statically allocated, and the + * tty_queue structures were allocated at boot time. Both are now + * dynamically allocated only when the tty is open. + * + * Also restructured routines so that there is more of a separation + * between the high-level tty routines (tty_io.c and tty_ioctl.c) and + * the low-level tty routines (serial.c, pty.c, console.c). This + * makes for cleaner and more compact code. -TYT, 9/17/92 + * + * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines + * which can be dynamically activated and de-activated by the line + * discipline handling modules (like SLIP). + * + * NOTE: pay no attention to the line discipline code (yet); its + * interface is still subject to change in this version... + * -- TYT, 1/31/92 + * + * Added functionality to the OPOST tty handling. No delays, but all + * other bits should be there. + * -- Nick Holloway <alfie@dcs.warwick.ac.uk>, 27th May 1993. + * + * Rewrote canonical mode and added more termios flags. + * -- julian@uhunix.uhcc.hawaii.edu (J. Cowley), 13Jan94 + * + * Reorganized FASYNC support so mouse code can share it. + * -- ctm@ardi.com, 9Sep95 + * + * New TIOCLINUX variants added. + * -- mj@k332.feld.cvut.cz, 19-Nov-95 + * + * Restrict vt switching via ioctl() + * -- grif@cs.ucr.edu, 5-Dec-95 + * + * Move console and virtual terminal code to more appropriate files, + * implement CONFIG_VT and generalize console device interface. + * -- Marko Kohtala <Marko.Kohtala@hut.fi>, March 97 + * + * Rewrote init_dev and release_dev to eliminate races. + * -- Bill Hawes <whawes@star.net>, June 97 + * + * Added devfs support. + * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 13-Jan-1998 + * + * Added support for a Unix98-style ptmx device. + * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998 + * + * Reduced memory usage for older ARM systems + * -- Russell King <rmk@arm.linux.org.uk> + * + * Move do_SAK() into process context. Less stack use in devfs functions. + * alloc_tty_struct() always uses kmalloc() -- Andrew Morton <andrewm@uow.edu.eu> 17Mar01 + */ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/major.h> +#include <linux/errno.h> +#include <linux/signal.h> +#include <linux/fcntl.h> +#include <linux/sched.h> +#include <linux/interrupt.h> +#include <linux/tty.h> +#include <linux/tty_driver.h> +#include <linux/tty_flip.h> +#include <linux/devpts_fs.h> +#include <linux/file.h> +#include <linux/console.h> +#include <linux/timer.h> +#include <linux/ctype.h> +#include <linux/kd.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/poll.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/smp_lock.h> + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/bitops.h> + +#include <linux/kbd_kern.h> +#include <linux/vt_kern.h> +#include <linux/selection.h> +#include <linux/devfs_fs_kernel.h> + +#include <linux/kmod.h> + +#ifdef CONFIG_XENO +extern void xeno_console_init(void); +#endif + +#ifdef CONFIG_VT +extern void con_init_devfs (void); +#endif + +#define CONSOLE_DEV MKDEV(TTY_MAJOR,0) +#define TTY_DEV MKDEV(TTYAUX_MAJOR,0) +#define SYSCONS_DEV MKDEV(TTYAUX_MAJOR,1) +#define PTMX_DEV MKDEV(TTYAUX_MAJOR,2) + +#undef TTY_DEBUG_HANGUP + +#define TTY_PARANOIA_CHECK 1 +#define CHECK_TTY_COUNT 1 + +struct termios tty_std_termios; /* for the benefit of tty drivers */ +struct tty_driver *tty_drivers; /* linked list of tty drivers */ +struct tty_ldisc ldiscs[NR_LDISCS]; /* line disc dispatch table */ + +#ifdef CONFIG_UNIX98_PTYS +extern struct tty_driver ptm_driver[]; /* Unix98 pty masters; for /dev/ptmx */ +extern struct tty_driver pts_driver[]; /* Unix98 pty slaves; for /dev/ptmx */ +#endif + +/* + * redirect is the pseudo-tty that console output + * is redirected to if asked by TIOCCONS. + */ +struct tty_struct * redirect; + +static void initialize_tty_struct(struct tty_struct *tty); + +static ssize_t tty_read(struct file *, char *, size_t, loff_t *); +static ssize_t tty_write(struct file *, const char *, size_t, loff_t *); +static unsigned int tty_poll(struct file *, poll_table *); +static int tty_open(struct inode *, struct file *); +static int tty_release(struct inode *, struct file *); +int tty_ioctl(struct inode * inode, struct file * file, + unsigned int cmd, unsigned long arg); +static int tty_fasync(int fd, struct file * filp, int on); +extern int vme_scc_init (void); +extern long vme_scc_console_init(void); +extern int serial167_init(void); +extern long serial167_console_init(void); +extern void console_8xx_init(void); +extern int rs_8xx_init(void); +extern void mac_scc_console_init(void); +extern void hwc_console_init(void); +extern void hwc_tty_init(void); +extern void con3215_init(void); +extern void tty3215_init(void); +extern void tub3270_con_init(void); +extern void tub3270_init(void); +extern void rs285_console_init(void); +extern void sa1100_rs_console_init(void); +extern void sgi_serial_console_init(void); +extern void sci_console_init(void); +extern void tx3912_console_init(void); +extern void tx3912_rs_init(void); + +#ifndef MIN +#define MIN(a,b) ((a) < (b) ? (a) : (b)) +#endif +#ifndef MAX +#define MAX(a,b) ((a) < (b) ? (b) : (a)) +#endif + +static struct tty_struct *alloc_tty_struct(void) +{ + struct tty_struct *tty; + + tty = kmalloc(sizeof(struct tty_struct), GFP_KERNEL); + if (tty) + memset(tty, 0, sizeof(struct tty_struct)); + return tty; +} + +static inline void free_tty_struct(struct tty_struct *tty) +{ + kfree(tty); +} + +/* + * This routine returns the name of tty. + */ +static char * +_tty_make_name(struct tty_struct *tty, const char *name, char *buf) +{ + int idx = (tty)?MINOR(tty->device) - tty->driver.minor_start:0; + + if (!tty) /* Hmm. NULL pointer. That's fun. */ + strcpy(buf, "NULL tty"); + else + sprintf(buf, name, + idx + tty->driver.name_base); + + return buf; +} + +#define TTY_NUMBER(tty) (MINOR((tty)->device) - (tty)->driver.minor_start + \ + (tty)->driver.name_base) + +char *tty_name(struct tty_struct *tty, char *buf) +{ + return _tty_make_name(tty, (tty)?tty->driver.name:NULL, buf); +} + +inline int tty_paranoia_check(struct tty_struct *tty, kdev_t device, + const char *routine) +{ +#ifdef TTY_PARANOIA_CHECK + static const char badmagic[] = KERN_WARNING + "Warning: bad magic number for tty struct (%s) in %s\n"; + static const char badtty[] = KERN_WARNING + "Warning: null TTY for (%s) in %s\n"; + + if (!tty) { + printk(badtty, kdevname(device), routine); + return 1; + } + if (tty->magic != TTY_MAGIC) { + printk(badmagic, kdevname(device), routine); + return 1; + } +#endif + return 0; +} + +static int check_tty_count(struct tty_struct *tty, const char *routine) +{ +#ifdef CHECK_TTY_COUNT + struct list_head *p; + int count = 0; + + file_list_lock(); + for(p = tty->tty_files.next; p != &tty->tty_files; p = p->next) { + if(list_entry(p, struct file, f_list)->private_data == tty) + count++; + } + file_list_unlock(); + if (tty->driver.type == TTY_DRIVER_TYPE_PTY && + tty->driver.subtype == PTY_TYPE_SLAVE && + tty->link && tty->link->count) + count++; + if (tty->count != count) { + printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) " + "!= #fd's(%d) in %s\n", + kdevname(tty->device), tty->count, count, routine); + return count; + } +#endif + return 0; +} + +int tty_register_ldisc(int disc, struct tty_ldisc *new_ldisc) +{ + if (disc < N_TTY || disc >= NR_LDISCS) + return -EINVAL; + + if (new_ldisc) { + ldiscs[disc] = *new_ldisc; + ldiscs[disc].flags |= LDISC_FLAG_DEFINED; + ldiscs[disc].num = disc; + } else + memset(&ldiscs[disc], 0, sizeof(struct tty_ldisc)); + + return 0; +} + +EXPORT_SYMBOL(tty_register_ldisc); + +/* Set the discipline of a tty line. */ +static int tty_set_ldisc(struct tty_struct *tty, int ldisc) +{ + int retval = 0; + struct tty_ldisc o_ldisc; + char buf[64]; + + if ((ldisc < N_TTY) || (ldisc >= NR_LDISCS)) + return -EINVAL; + /* Eduardo Blanco <ejbs@cs.cs.com.uy> */ + /* Cyrus Durgin <cider@speakeasy.org> */ + if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED)) { + char modname [20]; + sprintf(modname, "tty-ldisc-%d", ldisc); + request_module (modname); + } + if (!(ldiscs[ldisc].flags & LDISC_FLAG_DEFINED)) + return -EINVAL; + + if (tty->ldisc.num == ldisc) + return 0; /* We are already in the desired discipline */ + o_ldisc = tty->ldisc; + + tty_wait_until_sent(tty, 0); + + /* Shutdown the current discipline. */ + if (tty->ldisc.close) + (tty->ldisc.close)(tty); + + /* Now set up the new line discipline. */ + tty->ldisc = ldiscs[ldisc]; + tty->termios->c_line = ldisc; + if (tty->ldisc.open) + retval = (tty->ldisc.open)(tty); + if (retval < 0) { + tty->ldisc = o_ldisc; + tty->termios->c_line = tty->ldisc.num; + if (tty->ldisc.open && (tty->ldisc.open(tty) < 0)) { + tty->ldisc = ldiscs[N_TTY]; + tty->termios->c_line = N_TTY; + if (tty->ldisc.open) { + int r = tty->ldisc.open(tty); + + if (r < 0) + panic("Couldn't open N_TTY ldisc for " + "%s --- error %d.", + tty_name(tty, buf), r); + } + } + } + if (tty->ldisc.num != o_ldisc.num && tty->driver.set_ldisc) + tty->driver.set_ldisc(tty); + return retval; +} + +/* + * This routine returns a tty driver structure, given a device number + */ +struct tty_driver *get_tty_driver(kdev_t device) +{ + int major, minor; + struct tty_driver *p; + + minor = MINOR(device); + major = MAJOR(device); + + for (p = tty_drivers; p; p = p->next) { + if (p->major != major) + continue; + if (minor < p->minor_start) + continue; + if (minor >= p->minor_start + p->num) + continue; + return p; + } + return NULL; +} + +/* + * If we try to write to, or set the state of, a terminal and we're + * not in the foreground, send a SIGTTOU. If the signal is blocked or + * ignored, go ahead and perform the operation. (POSIX 7.2) + */ +int tty_check_change(struct tty_struct * tty) +{ + if (current->tty != tty) + return 0; + if (tty->pgrp <= 0) { + printk(KERN_WARNING "tty_check_change: tty->pgrp <= 0!\n"); + return 0; + } + if (current->pgrp == tty->pgrp) + return 0; + if (is_ignored(SIGTTOU)) + return 0; + if (is_orphaned_pgrp(current->pgrp)) + return -EIO; + (void) kill_pg(current->pgrp,SIGTTOU,1); + return -ERESTARTSYS; +} + +static ssize_t hung_up_tty_read(struct file * file, char * buf, + size_t count, loff_t *ppos) +{ + /* Can't seek (pread) on ttys. */ + if (ppos != &file->f_pos) + return -ESPIPE; + return 0; +} + +static ssize_t hung_up_tty_write(struct file * file, const char * buf, + size_t count, loff_t *ppos) +{ + /* Can't seek (pwrite) on ttys. */ + if (ppos != &file->f_pos) + return -ESPIPE; + return -EIO; +} + +/* No kernel lock held - none needed ;) */ +static unsigned int hung_up_tty_poll(struct file * filp, poll_table * wait) +{ + return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM; +} + +static int hung_up_tty_ioctl(struct inode * inode, struct file * file, + unsigned int cmd, unsigned long arg) +{ + return cmd == TIOCSPGRP ? -ENOTTY : -EIO; +} + +static struct file_operations tty_fops = { + llseek: no_llseek, + read: tty_read, + write: tty_write, + poll: tty_poll, + ioctl: tty_ioctl, + open: tty_open, + release: tty_release, + fasync: tty_fasync, +}; + +static struct file_operations hung_up_tty_fops = { + llseek: no_llseek, + read: hung_up_tty_read, + write: hung_up_tty_write, + poll: hung_up_tty_poll, + ioctl: hung_up_tty_ioctl, + release: tty_release, +}; + +/* + * This can be called by the "eventd" kernel thread. That is process synchronous, + * but doesn't hold any locks, so we need to make sure we have the appropriate + * locks for what we're doing.. + */ +void do_tty_hangup(void *data) +{ + struct tty_struct *tty = (struct tty_struct *) data; + struct file * cons_filp = NULL; + struct task_struct *p; + struct list_head *l; + int closecount = 0, n; + + if (!tty) + return; + + /* inuse_filps is protected by the single kernel lock */ + lock_kernel(); + + check_tty_count(tty, "do_tty_hangup"); + file_list_lock(); + for (l = tty->tty_files.next; l != &tty->tty_files; l = l->next) { + struct file * filp = list_entry(l, struct file, f_list); + if (filp->f_dentry->d_inode->i_rdev == CONSOLE_DEV || + filp->f_dentry->d_inode->i_rdev == SYSCONS_DEV) { + cons_filp = filp; + continue; + } + if (filp->f_op != &tty_fops) + continue; + closecount++; + tty_fasync(-1, filp, 0); /* can't block */ + filp->f_op = &hung_up_tty_fops; + } + file_list_unlock(); + + /* FIXME! What are the locking issues here? This may me overdoing things.. */ + { + unsigned long flags; + + save_flags(flags); cli(); + if (tty->ldisc.flush_buffer) + tty->ldisc.flush_buffer(tty); + if (tty->driver.flush_buffer) + tty->driver.flush_buffer(tty); + if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) && + tty->ldisc.write_wakeup) + (tty->ldisc.write_wakeup)(tty); + restore_flags(flags); + } + + wake_up_interruptible(&tty->write_wait); + wake_up_interruptible(&tty->read_wait); + + /* + * Shutdown the current line discipline, and reset it to + * N_TTY. + */ + if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) + *tty->termios = tty->driver.init_termios; + if (tty->ldisc.num != ldiscs[N_TTY].num) { + if (tty->ldisc.close) + (tty->ldisc.close)(tty); + tty->ldisc = ldiscs[N_TTY]; + tty->termios->c_line = N_TTY; + if (tty->ldisc.open) { + int i = (tty->ldisc.open)(tty); + if (i < 0) + printk(KERN_ERR "do_tty_hangup: N_TTY open: " + "error %d\n", -i); + } + } + + read_lock(&tasklist_lock); + for_each_task(p) { + if ((tty->session > 0) && (p->session == tty->session) && + p->leader) { + send_sig(SIGHUP,p,1); + send_sig(SIGCONT,p,1); + if (tty->pgrp > 0) + p->tty_old_pgrp = tty->pgrp; + } + if (p->tty == tty) + p->tty = NULL; + } + read_unlock(&tasklist_lock); + + tty->flags = 0; + tty->session = 0; + tty->pgrp = -1; + tty->ctrl_status = 0; + /* + * If one of the devices matches a console pointer, we + * cannot just call hangup() because that will cause + * tty->count and state->count to go out of sync. + * So we just call close() the right number of times. + */ + if (cons_filp) { + if (tty->driver.close) + for (n = 0; n < closecount; n++) + tty->driver.close(tty, cons_filp); + } else if (tty->driver.hangup) + (tty->driver.hangup)(tty); + unlock_kernel(); +} + +void tty_hangup(struct tty_struct * tty) +{ +#ifdef TTY_DEBUG_HANGUP + char buf[64]; + + printk(KERN_DEBUG "%s hangup...\n", tty_name(tty, buf)); +#endif + schedule_task(&tty->tq_hangup); +} + +void tty_vhangup(struct tty_struct * tty) +{ +#ifdef TTY_DEBUG_HANGUP + char buf[64]; + + printk(KERN_DEBUG "%s vhangup...\n", tty_name(tty, buf)); +#endif + do_tty_hangup((void *) tty); +} + +int tty_hung_up_p(struct file * filp) +{ + return (filp->f_op == &hung_up_tty_fops); +} + +/* + * This function is typically called only by the session leader, when + * it wants to disassociate itself from its controlling tty. + * + * It performs the following functions: + * (1) Sends a SIGHUP and SIGCONT to the foreground process group + * (2) Clears the tty from being controlling the session + * (3) Clears the controlling tty for all processes in the + * session group. + * + * The argument on_exit is set to 1 if called when a process is + * exiting; it is 0 if called by the ioctl TIOCNOTTY. + */ +void disassociate_ctty(int on_exit) +{ + struct tty_struct *tty = current->tty; + struct task_struct *p; + int tty_pgrp = -1; + + if (tty) { + tty_pgrp = tty->pgrp; + if (on_exit && tty->driver.type != TTY_DRIVER_TYPE_PTY) + tty_vhangup(tty); + } else { + if (current->tty_old_pgrp) { + kill_pg(current->tty_old_pgrp, SIGHUP, on_exit); + kill_pg(current->tty_old_pgrp, SIGCONT, on_exit); + } + return; + } + if (tty_pgrp > 0) { + kill_pg(tty_pgrp, SIGHUP, on_exit); + if (!on_exit) + kill_pg(tty_pgrp, SIGCONT, on_exit); + } + + current->tty_old_pgrp = 0; + tty->session = 0; + tty->pgrp = -1; + + read_lock(&tasklist_lock); + for_each_task(p) + if (p->session == current->session) + p->tty = NULL; + read_unlock(&tasklist_lock); +} + +void wait_for_keypress(void) +{ + struct console *c = console_drivers; + if (c) c->wait_key(c); +} + +void stop_tty(struct tty_struct *tty) +{ + if (tty->stopped) + return; + tty->stopped = 1; + if (tty->link && tty->link->packet) { + tty->ctrl_status &= ~TIOCPKT_START; + tty->ctrl_status |= TIOCPKT_STOP; + wake_up_interruptible(&tty->link->read_wait); + } + if (tty->driver.stop) + (tty->driver.stop)(tty); +} + +void start_tty(struct tty_struct *tty) +{ + if (!tty->stopped || tty->flow_stopped) + return; + tty->stopped = 0; + if (tty->link && tty->link->packet) { + tty->ctrl_status &= ~TIOCPKT_STOP; + tty->ctrl_status |= TIOCPKT_START; + wake_up_interruptible(&tty->link->read_wait); + } + if (tty->driver.start) + (tty->driver.start)(tty); + if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) && + tty->ldisc.write_wakeup) + (tty->ldisc.write_wakeup)(tty); + wake_up_interruptible(&tty->write_wait); +} + +static ssize_t tty_read(struct file * file, char * buf, size_t count, + loff_t *ppos) +{ + int i; + struct tty_struct * tty; + struct inode *inode; + + /* Can't seek (pread) on ttys. */ + if (ppos != &file->f_pos) + return -ESPIPE; + + tty = (struct tty_struct *)file->private_data; + inode = file->f_dentry->d_inode; + if (tty_paranoia_check(tty, inode->i_rdev, "tty_read")) + return -EIO; + if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags))) + return -EIO; + + /* This check not only needs to be done before reading, but also + whenever read_chan() gets woken up after sleeping, so I've + moved it to there. This should only be done for the N_TTY + line discipline, anyway. Same goes for write_chan(). -- jlc. */ +#if 0 + if ((inode->i_rdev != CONSOLE_DEV) && /* don't stop on /dev/console */ + (tty->pgrp > 0) && + (current->tty == tty) && + (tty->pgrp != current->pgrp)) + if (is_ignored(SIGTTIN) || is_orphaned_pgrp(current->pgrp)) + return -EIO; + else { + (void) kill_pg(current->pgrp, SIGTTIN, 1); + return -ERESTARTSYS; + } +#endif + lock_kernel(); + if (tty->ldisc.read) + i = (tty->ldisc.read)(tty,file,buf,count); + else + i = -EIO; + unlock_kernel(); + if (i > 0) + inode->i_atime = CURRENT_TIME; + return i; +} + +/* + * Split writes up in sane blocksizes to avoid + * denial-of-service type attacks + */ +static inline ssize_t do_tty_write( + ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t), + struct tty_struct *tty, + struct file *file, + const unsigned char *buf, + size_t count) +{ + ssize_t ret = 0, written = 0; + + if (down_interruptible(&tty->atomic_write)) { + return -ERESTARTSYS; + } + if ( test_bit(TTY_NO_WRITE_SPLIT, &tty->flags) ) { + lock_kernel(); + written = write(tty, file, buf, count); + unlock_kernel(); + } else { + for (;;) { + unsigned long size = MAX(PAGE_SIZE*2,16384); + if (size > count) + size = count; + lock_kernel(); + ret = write(tty, file, buf, size); + unlock_kernel(); + if (ret <= 0) + break; + written += ret; + buf += ret; + count -= ret; + if (!count) + break; + ret = -ERESTARTSYS; + if (signal_pending(current)) + break; + if (current->need_resched) + schedule(); + } + } + if (written) { + file->f_dentry->d_inode->i_mtime = CURRENT_TIME; + ret = written; + } + up(&tty->atomic_write); + return ret; +} + + +static ssize_t tty_write(struct file * file, const char * buf, size_t count, + loff_t *ppos) +{ + int is_console; + struct tty_struct * tty; + struct inode *inode; + + /* Can't seek (pwrite) on ttys. */ + if (ppos != &file->f_pos) + return -ESPIPE; + + /* + * For now, we redirect writes from /dev/console as + * well as /dev/tty0. + */ + inode = file->f_dentry->d_inode; + is_console = (inode->i_rdev == SYSCONS_DEV || + inode->i_rdev == CONSOLE_DEV); + + if (is_console && redirect) + tty = redirect; + else + tty = (struct tty_struct *)file->private_data; + if (tty_paranoia_check(tty, inode->i_rdev, "tty_write")) + return -EIO; + if (!tty || !tty->driver.write || (test_bit(TTY_IO_ERROR, &tty->flags))) + return -EIO; +#if 0 + if (!is_console && L_TOSTOP(tty) && (tty->pgrp > 0) && + (current->tty == tty) && (tty->pgrp != current->pgrp)) { + if (is_orphaned_pgrp(current->pgrp)) + return -EIO; + if (!is_ignored(SIGTTOU)) { + (void) kill_pg(current->pgrp, SIGTTOU, 1); + return -ERESTARTSYS; + } + } +#endif + if (!tty->ldisc.write) + return -EIO; + return do_tty_write(tty->ldisc.write, tty, file, + (const unsigned char *)buf, count); +} + +/* Semaphore to protect creating and releasing a tty */ +static DECLARE_MUTEX(tty_sem); + +static void down_tty_sem(int index) +{ + down(&tty_sem); +} + +static void up_tty_sem(int index) +{ + up(&tty_sem); +} + +static void release_mem(struct tty_struct *tty, int idx); + +/* + * WSH 06/09/97: Rewritten to remove races and properly clean up after a + * failed open. The new code protects the open with a semaphore, so it's + * really quite straightforward. The semaphore locking can probably be + * relaxed for the (most common) case of reopening a tty. + */ +static int init_dev(kdev_t device, struct tty_struct **ret_tty) +{ + struct tty_struct *tty, *o_tty; + struct termios *tp, **tp_loc, *o_tp, **o_tp_loc; + struct termios *ltp, **ltp_loc, *o_ltp, **o_ltp_loc; + struct tty_driver *driver; + int retval=0; + int idx; + + driver = get_tty_driver(device); + if (!driver) + return -ENODEV; + + idx = MINOR(device) - driver->minor_start; + + /* + * Check whether we need to acquire the tty semaphore to avoid + * race conditions. For now, play it safe. + */ + down_tty_sem(idx); + + /* check whether we're reopening an existing tty */ + tty = driver->table[idx]; + if (tty) goto fast_track; + + /* + * First time open is complex, especially for PTY devices. + * This code guarantees that either everything succeeds and the + * TTY is ready for operation, or else the table slots are vacated + * and the allocated memory released. (Except that the termios + * and locked termios may be retained.) + */ + + o_tty = NULL; + tp = o_tp = NULL; + ltp = o_ltp = NULL; + + tty = alloc_tty_struct(); + if(!tty) + goto fail_no_mem; + initialize_tty_struct(tty); + tty->device = device; + tty->driver = *driver; + + tp_loc = &driver->termios[idx]; + if (!*tp_loc) { + tp = (struct termios *) kmalloc(sizeof(struct termios), + GFP_KERNEL); + if (!tp) + goto free_mem_out; + *tp = driver->init_termios; + } + + ltp_loc = &driver->termios_locked[idx]; + if (!*ltp_loc) { + ltp = (struct termios *) kmalloc(sizeof(struct termios), + GFP_KERNEL); + if (!ltp) + goto free_mem_out; + memset(ltp, 0, sizeof(struct termios)); + } + + if (driver->type == TTY_DRIVER_TYPE_PTY) { + o_tty = alloc_tty_struct(); + if (!o_tty) + goto free_mem_out; + initialize_tty_struct(o_tty); + o_tty->device = (kdev_t) MKDEV(driver->other->major, + driver->other->minor_start + idx); + o_tty->driver = *driver->other; + + o_tp_loc = &driver->other->termios[idx]; + if (!*o_tp_loc) { + o_tp = (struct termios *) + kmalloc(sizeof(struct termios), GFP_KERNEL); + if (!o_tp) + goto free_mem_out; + *o_tp = driver->other->init_termios; + } + + o_ltp_loc = &driver->other->termios_locked[idx]; + if (!*o_ltp_loc) { + o_ltp = (struct termios *) + kmalloc(sizeof(struct termios), GFP_KERNEL); + if (!o_ltp) + goto free_mem_out; + memset(o_ltp, 0, sizeof(struct termios)); + } + + /* + * Everything allocated ... set up the o_tty structure. + */ + driver->other->table[idx] = o_tty; + if (!*o_tp_loc) + *o_tp_loc = o_tp; + if (!*o_ltp_loc) + *o_ltp_loc = o_ltp; + o_tty->termios = *o_tp_loc; + o_tty->termios_locked = *o_ltp_loc; + (*driver->other->refcount)++; + if (driver->subtype == PTY_TYPE_MASTER) + o_tty->count++; + + /* Establish the links in both directions */ + tty->link = o_tty; + o_tty->link = tty; + } + + /* + * All structures have been allocated, so now we install them. + * Failures after this point use release_mem to clean up, so + * there's no need to null out the local pointers. + */ + driver->table[idx] = tty; + + if (!*tp_loc) + *tp_loc = tp; + if (!*ltp_loc) + *ltp_loc = ltp; + tty->termios = *tp_loc; + tty->termios_locked = *ltp_loc; + (*driver->refcount)++; + tty->count++; + + /* + * Structures all installed ... call the ldisc open routines. + * If we fail here just call release_mem to clean up. No need + * to decrement the use counts, as release_mem doesn't care. + */ + if (tty->ldisc.open) { + retval = (tty->ldisc.open)(tty); + if (retval) + goto release_mem_out; + } + if (o_tty && o_tty->ldisc.open) { + retval = (o_tty->ldisc.open)(o_tty); + if (retval) { + if (tty->ldisc.close) + (tty->ldisc.close)(tty); + goto release_mem_out; + } + } + goto success; + + /* + * This fast open can be used if the tty is already open. + * No memory is allocated, and the only failures are from + * attempting to open a closing tty or attempting multiple + * opens on a pty master. + */ +fast_track: + if (test_bit(TTY_CLOSING, &tty->flags)) { + retval = -EIO; + goto end_init; + } + if (driver->type == TTY_DRIVER_TYPE_PTY && + driver->subtype == PTY_TYPE_MASTER) { + /* + * special case for PTY masters: only one open permitted, + * and the slave side open count is incremented as well. + */ + if (tty->count) { + retval = -EIO; + goto end_init; + } + tty->link->count++; + } + tty->count++; + tty->driver = *driver; /* N.B. why do this every time?? */ + +success: + *ret_tty = tty; + + /* All paths come through here to release the semaphore */ +end_init: + up_tty_sem(idx); + return retval; + + /* Release locally allocated memory ... nothing placed in slots */ +free_mem_out: + if (o_tp) + kfree(o_tp); + if (o_tty) + free_tty_struct(o_tty); + if (ltp) + kfree(ltp); + if (tp) + kfree(tp); + free_tty_struct(tty); + +fail_no_mem: + retval = -ENOMEM; + goto end_init; + + /* call the tty release_mem routine to clean out this slot */ +release_mem_out: + printk(KERN_INFO "init_dev: ldisc open failed, " + "clearing slot %d\n", idx); + release_mem(tty, idx); + goto end_init; +} + +/* + * Releases memory associated with a tty structure, and clears out the + * driver table slots. + */ +static void release_mem(struct tty_struct *tty, int idx) +{ + struct tty_struct *o_tty; + struct termios *tp; + + if ((o_tty = tty->link) != NULL) { + o_tty->driver.table[idx] = NULL; + if (o_tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) { + tp = o_tty->driver.termios[idx]; + o_tty->driver.termios[idx] = NULL; + kfree(tp); + } + o_tty->magic = 0; + (*o_tty->driver.refcount)--; + list_del(&o_tty->tty_files); + free_tty_struct(o_tty); + } + + tty->driver.table[idx] = NULL; + if (tty->driver.flags & TTY_DRIVER_RESET_TERMIOS) { + tp = tty->driver.termios[idx]; + tty->driver.termios[idx] = NULL; + kfree(tp); + } + tty->magic = 0; + (*tty->driver.refcount)--; + list_del(&tty->tty_files); + free_tty_struct(tty); +} + +/* + * Even releasing the tty structures is a tricky business.. We have + * to be very careful that the structures are all released at the + * same time, as interrupts might otherwise get the wrong pointers. + * + * WSH 09/09/97: rewritten to avoid some nasty race conditions that could + * lead to double frees or releasing memory still in use. + */ +static void release_dev(struct file * filp) +{ + struct tty_struct *tty, *o_tty; + int pty_master, tty_closing, o_tty_closing, do_sleep; + int idx; + char buf[64]; + + tty = (struct tty_struct *)filp->private_data; + if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "release_dev")) + return; + + check_tty_count(tty, "release_dev"); + + tty_fasync(-1, filp, 0); + + idx = MINOR(tty->device) - tty->driver.minor_start; + pty_master = (tty->driver.type == TTY_DRIVER_TYPE_PTY && + tty->driver.subtype == PTY_TYPE_MASTER); + o_tty = tty->link; + +#ifdef TTY_PARANOIA_CHECK + if (idx < 0 || idx >= tty->driver.num) { + printk(KERN_DEBUG "release_dev: bad idx when trying to " + "free (%s)\n", kdevname(tty->device)); + return; + } + if (tty != tty->driver.table[idx]) { + printk(KERN_DEBUG "release_dev: driver.table[%d] not tty " + "for (%s)\n", idx, kdevname(tty->device)); + return; + } + if (tty->termios != tty->driver.termios[idx]) { + printk(KERN_DEBUG "release_dev: driver.termios[%d] not termios " + "for (%s)\n", + idx, kdevname(tty->device)); + return; + } + if (tty->termios_locked != tty->driver.termios_locked[idx]) { + printk(KERN_DEBUG "release_dev: driver.termios_locked[%d] not " + "termios_locked for (%s)\n", + idx, kdevname(tty->device)); + return; + } +#endif + +#ifdef TTY_DEBUG_HANGUP + printk(KERN_DEBUG "release_dev of %s (tty count=%d)...", + tty_name(tty, buf), tty->count); +#endif + +#ifdef TTY_PARANOIA_CHECK + if (tty->driver.other) { + if (o_tty != tty->driver.other->table[idx]) { + printk(KERN_DEBUG "release_dev: other->table[%d] " + "not o_tty for (%s)\n", + idx, kdevname(tty->device)); + return; + } + if (o_tty->termios != tty->driver.other->termios[idx]) { + printk(KERN_DEBUG "release_dev: other->termios[%d] " + "not o_termios for (%s)\n", + idx, kdevname(tty->device)); + return; + } + if (o_tty->termios_locked != + tty->driver.other->termios_locked[idx]) { + printk(KERN_DEBUG "release_dev: other->termios_locked[" + "%d] not o_termios_locked for (%s)\n", + idx, kdevname(tty->device)); + return; + } + if (o_tty->link != tty) { + printk(KERN_DEBUG "release_dev: bad pty pointers\n"); + return; + } + } +#endif + + if (tty->driver.close) + tty->driver.close(tty, filp); + + /* + * Sanity check: if tty->count is going to zero, there shouldn't be + * any waiters on tty->read_wait or tty->write_wait. We test the + * wait queues and kick everyone out _before_ actually starting to + * close. This ensures that we won't block while releasing the tty + * structure. + * + * The test for the o_tty closing is necessary, since the master and + * slave sides may close in any order. If the slave side closes out + * first, its count will be one, since the master side holds an open. + * Thus this test wouldn't be triggered at the time the slave closes, + * so we do it now. + * + * Note that it's possible for the tty to be opened again while we're + * flushing out waiters. By recalculating the closing flags before + * each iteration we avoid any problems. + */ + while (1) { + tty_closing = tty->count <= 1; + o_tty_closing = o_tty && + (o_tty->count <= (pty_master ? 1 : 0)); + do_sleep = 0; + + if (tty_closing) { + if (waitqueue_active(&tty->read_wait)) { + wake_up(&tty->read_wait); + do_sleep++; + } + if (waitqueue_active(&tty->write_wait)) { + wake_up(&tty->write_wait); + do_sleep++; + } + } + if (o_tty_closing) { + if (waitqueue_active(&o_tty->read_wait)) { + wake_up(&o_tty->read_wait); + do_sleep++; + } + if (waitqueue_active(&o_tty->write_wait)) { + wake_up(&o_tty->write_wait); + do_sleep++; + } + } + if (!do_sleep) + break; + + printk(KERN_WARNING "release_dev: %s: read/write wait queue " + "active!\n", tty_name(tty, buf)); + schedule(); + } + + /* + * The closing flags are now consistent with the open counts on + * both sides, and we've completed the last operation that could + * block, so it's safe to proceed with closing. + */ + if (pty_master) { + if (--o_tty->count < 0) { + printk(KERN_WARNING "release_dev: bad pty slave count " + "(%d) for %s\n", + o_tty->count, tty_name(o_tty, buf)); + o_tty->count = 0; + } + } + if (--tty->count < 0) { + printk(KERN_WARNING "release_dev: bad tty->count (%d) for %s\n", + tty->count, tty_name(tty, buf)); + tty->count = 0; + } + + /* + * We've decremented tty->count, so we should zero out + * filp->private_data, to break the link between the tty and + * the file descriptor. Otherwise if filp_close() blocks before + * the file descriptor is removed from the inuse_filp + * list, check_tty_count() could observe a discrepancy and + * printk a warning message to the user. + */ + filp->private_data = 0; + + /* + * Perform some housekeeping before deciding whether to return. + * + * Set the TTY_CLOSING flag if this was the last open. In the + * case of a pty we may have to wait around for the other side + * to close, and TTY_CLOSING makes sure we can't be reopened. + */ + if(tty_closing) + set_bit(TTY_CLOSING, &tty->flags); + if(o_tty_closing) + set_bit(TTY_CLOSING, &o_tty->flags); + + /* + * If _either_ side is closing, make sure there aren't any + * processes that still think tty or o_tty is their controlling + * tty. Also, clear redirect if it points to either tty. + */ + if (tty_closing || o_tty_closing) { + struct task_struct *p; + + read_lock(&tasklist_lock); + for_each_task(p) { + if (p->tty == tty || (o_tty && p->tty == o_tty)) + p->tty = NULL; + } + read_unlock(&tasklist_lock); + + if (redirect == tty || (o_tty && redirect == o_tty)) + redirect = NULL; + } + + /* check whether both sides are closing ... */ + if (!tty_closing || (o_tty && !o_tty_closing)) + return; + +#ifdef TTY_DEBUG_HANGUP + printk(KERN_DEBUG "freeing tty structure..."); +#endif + + /* + * Shutdown the current line discipline, and reset it to N_TTY. + * N.B. why reset ldisc when we're releasing the memory?? + */ + if (tty->ldisc.close) + (tty->ldisc.close)(tty); + tty->ldisc = ldiscs[N_TTY]; + tty->termios->c_line = N_TTY; + if (o_tty) { + if (o_tty->ldisc.close) + (o_tty->ldisc.close)(o_tty); + o_tty->ldisc = ldiscs[N_TTY]; + } + + /* + * Make sure that the tty's task queue isn't activated. + */ + run_task_queue(&tq_timer); + flush_scheduled_tasks(); + + /* + * The release_mem function takes care of the details of clearing + * the slots and preserving the termios structure. + */ + release_mem(tty, idx); +} + +/* + * tty_open and tty_release keep up the tty count that contains the + * number of opens done on a tty. We cannot use the inode-count, as + * different inodes might point to the same tty. + * + * Open-counting is needed for pty masters, as well as for keeping + * track of serial lines: DTR is dropped when the last close happens. + * (This is not done solely through tty->count, now. - Ted 1/27/92) + * + * The termios state of a pty is reset on first open so that + * settings don't persist across reuse. + */ +static int tty_open(struct inode * inode, struct file * filp) +{ + struct tty_struct *tty; + int noctty, retval; + kdev_t device; + unsigned short saved_flags; + char buf[64]; + + saved_flags = filp->f_flags; +retry_open: + noctty = filp->f_flags & O_NOCTTY; + device = inode->i_rdev; + if (device == TTY_DEV) { + if (!current->tty) + return -ENXIO; + device = current->tty->device; + filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */ + /* noctty = 1; */ + } +#ifdef CONFIG_VT + if (device == CONSOLE_DEV) { + extern int fg_console; + device = MKDEV(TTY_MAJOR, fg_console + 1); + noctty = 1; + } +#endif + if (device == SYSCONS_DEV) { + struct console *c = console_drivers; + while(c && !c->device) + c = c->next; + if (!c) + return -ENODEV; + device = c->device(c); + filp->f_flags |= O_NONBLOCK; /* Don't let /dev/console block */ + noctty = 1; + } + + if (device == PTMX_DEV) { +#ifdef CONFIG_UNIX98_PTYS + + /* find a free pty. */ + int major, minor; + struct tty_driver *driver; + + /* find a device that is not in use. */ + retval = -1; + for ( major = 0 ; major < UNIX98_NR_MAJORS ; major++ ) { + driver = &ptm_driver[major]; + for (minor = driver->minor_start ; + minor < driver->minor_start + driver->num ; + minor++) { + device = MKDEV(driver->major, minor); + if (!init_dev(device, &tty)) goto ptmx_found; /* ok! */ + } + } + return -EIO; /* no free ptys */ + ptmx_found: + set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ + minor -= driver->minor_start; + devpts_pty_new(driver->other->name_base + minor, MKDEV(driver->other->major, minor + driver->other->minor_start)); + tty_register_devfs(&pts_driver[major], DEVFS_FL_NO_PERSISTENCE, + pts_driver[major].minor_start + minor); + noctty = 1; + goto init_dev_done; + +#else /* CONFIG_UNIX_98_PTYS */ + + return -ENODEV; + +#endif /* CONFIG_UNIX_98_PTYS */ + } + + retval = init_dev(device, &tty); + if (retval) + return retval; + +#ifdef CONFIG_UNIX98_PTYS +init_dev_done: +#endif + filp->private_data = tty; + file_move(filp, &tty->tty_files); + check_tty_count(tty, "tty_open"); + if (tty->driver.type == TTY_DRIVER_TYPE_PTY && + tty->driver.subtype == PTY_TYPE_MASTER) + noctty = 1; +#ifdef TTY_DEBUG_HANGUP + printk(KERN_DEBUG "opening %s...", tty_name(tty, buf)); +#endif + if (tty->driver.open) + retval = tty->driver.open(tty, filp); + else + retval = -ENODEV; + filp->f_flags = saved_flags; + + if (!retval && test_bit(TTY_EXCLUSIVE, &tty->flags) && !suser()) + retval = -EBUSY; + + if (retval) { +#ifdef TTY_DEBUG_HANGUP + printk(KERN_DEBUG "error %d in opening %s...", retval, + tty_name(tty, buf)); +#endif + + release_dev(filp); + if (retval != -ERESTARTSYS) + return retval; + if (signal_pending(current)) + return retval; + schedule(); + /* + * Need to reset f_op in case a hangup happened. + */ + filp->f_op = &tty_fops; + goto retry_open; + } + if (!noctty && + current->leader && + !current->tty && + tty->session == 0) { + task_lock(current); + current->tty = tty; + task_unlock(current); + current->tty_old_pgrp = 0; + tty->session = current->session; + tty->pgrp = current->pgrp; + } + if ((tty->driver.type == TTY_DRIVER_TYPE_SERIAL) && + (tty->driver.subtype == SERIAL_TYPE_CALLOUT) && + (tty->count == 1)) { + static int nr_warns; + if (nr_warns < 5) { + printk(KERN_WARNING "tty_io.c: " + "process %d (%s) used obsolete /dev/%s - " + "update software to use /dev/ttyS%d\n", + current->pid, current->comm, + tty_name(tty, buf), TTY_NUMBER(tty)); + nr_warns++; + } + } + return 0; +} + +static int tty_release(struct inode * inode, struct file * filp) +{ + lock_kernel(); + release_dev(filp); + unlock_kernel(); + return 0; +} + +/* No kernel lock held - fine */ +static unsigned int tty_poll(struct file * filp, poll_table * wait) +{ + struct tty_struct * tty; + + tty = (struct tty_struct *)filp->private_data; + if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_poll")) + return 0; + + if (tty->ldisc.poll) + return (tty->ldisc.poll)(tty, filp, wait); + return 0; +} + +static int tty_fasync(int fd, struct file * filp, int on) +{ + struct tty_struct * tty; + int retval; + + tty = (struct tty_struct *)filp->private_data; + if (tty_paranoia_check(tty, filp->f_dentry->d_inode->i_rdev, "tty_fasync")) + return 0; + + retval = fasync_helper(fd, filp, on, &tty->fasync); + if (retval <= 0) + return retval; + + if (on) { + if (!waitqueue_active(&tty->read_wait)) + tty->minimum_to_wake = 1; + if (filp->f_owner.pid == 0) { + filp->f_owner.pid = (-tty->pgrp) ? : current->pid; + filp->f_owner.uid = current->uid; + filp->f_owner.euid = current->euid; + } + } else { + if (!tty->fasync && !waitqueue_active(&tty->read_wait)) + tty->minimum_to_wake = N_TTY_BUF_SIZE; + } + return 0; +} + +static int tiocsti(struct tty_struct *tty, char * arg) +{ + char ch, mbz = 0; + + if ((current->tty != tty) && !suser()) + return -EPERM; + if (get_user(ch, arg)) + return -EFAULT; + tty->ldisc.receive_buf(tty, &ch, &mbz, 1); + return 0; +} + +static int tiocgwinsz(struct tty_struct *tty, struct winsize * arg) +{ + if (copy_to_user(arg, &tty->winsize, sizeof(*arg))) + return -EFAULT; + return 0; +} + +static int tiocswinsz(struct tty_struct *tty, struct tty_struct *real_tty, + struct winsize * arg) +{ + struct winsize tmp_ws; + + if (copy_from_user(&tmp_ws, arg, sizeof(*arg))) + return -EFAULT; + if (!memcmp(&tmp_ws, &tty->winsize, sizeof(*arg))) + return 0; + if (tty->pgrp > 0) + kill_pg(tty->pgrp, SIGWINCH, 1); + if ((real_tty->pgrp != tty->pgrp) && (real_tty->pgrp > 0)) + kill_pg(real_tty->pgrp, SIGWINCH, 1); + tty->winsize = tmp_ws; + real_tty->winsize = tmp_ws; + return 0; +} + +static int tioccons(struct inode *inode, + struct tty_struct *tty, struct tty_struct *real_tty) +{ + if (inode->i_rdev == SYSCONS_DEV || + inode->i_rdev == CONSOLE_DEV) { + if (!suser()) + return -EPERM; + redirect = NULL; + return 0; + } + if (redirect) + return -EBUSY; + redirect = real_tty; + return 0; +} + + +static int fionbio(struct file *file, int *arg) +{ + int nonblock; + + if (get_user(nonblock, arg)) + return -EFAULT; + + if (nonblock) + file->f_flags |= O_NONBLOCK; + else + file->f_flags &= ~O_NONBLOCK; + return 0; +} + +static int tiocsctty(struct tty_struct *tty, int arg) +{ + if (current->leader && + (current->session == tty->session)) + return 0; + /* + * The process must be a session leader and + * not have a controlling tty already. + */ + if (!current->leader || current->tty) + return -EPERM; + if (tty->session > 0) { + /* + * This tty is already the controlling + * tty for another session group! + */ + if ((arg == 1) && suser()) { + /* + * Steal it away + */ + struct task_struct *p; + + read_lock(&tasklist_lock); + for_each_task(p) + if (p->tty == tty) + p->tty = NULL; + read_unlock(&tasklist_lock); + } else + return -EPERM; + } + task_lock(current); + current->tty = tty; + task_unlock(current); + current->tty_old_pgrp = 0; + tty->session = current->session; + tty->pgrp = current->pgrp; + return 0; +} + +static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg) +{ + /* + * (tty == real_tty) is a cheap way of + * testing if the tty is NOT a master pty. + */ + if (tty == real_tty && current->tty != real_tty) + return -ENOTTY; + return put_user(real_tty->pgrp, arg); +} + +static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg) +{ + pid_t pgrp; + int retval = tty_check_change(real_tty); + + if (retval == -EIO) + return -ENOTTY; + if (retval) + return retval; + if (!current->tty || + (current->tty != real_tty) || + (real_tty->session != current->session)) + return -ENOTTY; + if (get_user(pgrp, (pid_t *) arg)) + return -EFAULT; + if (pgrp < 0) + return -EINVAL; + if (session_of_pgrp(pgrp) != current->session) + return -EPERM; + real_tty->pgrp = pgrp; + return 0; +} + +static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t *arg) +{ + /* + * (tty == real_tty) is a cheap way of + * testing if the tty is NOT a master pty. + */ + if (tty == real_tty && current->tty != real_tty) + return -ENOTTY; + if (real_tty->session <= 0) + return -ENOTTY; + return put_user(real_tty->session, arg); +} + +static int tiocttygstruct(struct tty_struct *tty, struct tty_struct *arg) +{ + if (copy_to_user(arg, tty, sizeof(*arg))) + return -EFAULT; + return 0; +} + +static int tiocsetd(struct tty_struct *tty, int *arg) +{ + int ldisc; + + if (get_user(ldisc, arg)) + return -EFAULT; + return tty_set_ldisc(tty, ldisc); +} + +static int send_break(struct tty_struct *tty, int duration) +{ + set_current_state(TASK_INTERRUPTIBLE); + + tty->driver.break_ctl(tty, -1); + if (!signal_pending(current)) + schedule_timeout(duration); + tty->driver.break_ctl(tty, 0); + if (signal_pending(current)) + return -EINTR; + return 0; +} + +/* + * Split this up, as gcc can choke on it otherwise.. + */ +int tty_ioctl(struct inode * inode, struct file * file, + unsigned int cmd, unsigned long arg) +{ + struct tty_struct *tty, *real_tty; + int retval; + + tty = (struct tty_struct *)file->private_data; + if (tty_paranoia_check(tty, inode->i_rdev, "tty_ioctl")) + return -EINVAL; + + real_tty = tty; + if (tty->driver.type == TTY_DRIVER_TYPE_PTY && + tty->driver.subtype == PTY_TYPE_MASTER) + real_tty = tty->link; + + /* + * Break handling by driver + */ + if (!tty->driver.break_ctl) { + switch(cmd) { + case TIOCSBRK: + case TIOCCBRK: + if (tty->driver.ioctl) + return tty->driver.ioctl(tty, file, cmd, arg); + return -EINVAL; + + /* These two ioctl's always return success; even if */ + /* the driver doesn't support them. */ + case TCSBRK: + case TCSBRKP: + if (!tty->driver.ioctl) + return 0; + retval = tty->driver.ioctl(tty, file, cmd, arg); + if (retval == -ENOIOCTLCMD) + retval = 0; + return retval; + } + } + + /* + * Factor out some common prep work + */ + switch (cmd) { + case TIOCSETD: + case TIOCSBRK: + case TIOCCBRK: + case TCSBRK: + case TCSBRKP: + retval = tty_check_change(tty); + if (retval) + return retval; + if (cmd != TIOCCBRK) { + tty_wait_until_sent(tty, 0); + if (signal_pending(current)) + return -EINTR; + } + break; + } + + switch (cmd) { + case TIOCSTI: + return tiocsti(tty, (char *)arg); + case TIOCGWINSZ: + return tiocgwinsz(tty, (struct winsize *) arg); + case TIOCSWINSZ: + return tiocswinsz(tty, real_tty, (struct winsize *) arg); + case TIOCCONS: + return tioccons(inode, tty, real_tty); + case FIONBIO: + return fionbio(file, (int *) arg); + case TIOCEXCL: + set_bit(TTY_EXCLUSIVE, &tty->flags); + return 0; + case TIOCNXCL: + clear_bit(TTY_EXCLUSIVE, &tty->flags); + return 0; + case TIOCNOTTY: + if (current->tty != tty) + return -ENOTTY; + if (current->leader) + disassociate_ctty(0); + task_lock(current); + current->tty = NULL; + task_unlock(current); + return 0; + case TIOCSCTTY: + return tiocsctty(tty, arg); + case TIOCGPGRP: + return tiocgpgrp(tty, real_tty, (pid_t *) arg); + case TIOCSPGRP: + return tiocspgrp(tty, real_tty, (pid_t *) arg); + case TIOCGSID: + return tiocgsid(tty, real_tty, (pid_t *) arg); + case TIOCGETD: + return put_user(tty->ldisc.num, (int *) arg); + case TIOCSETD: + return tiocsetd(tty, (int *) arg); +#ifdef CONFIG_VT + case TIOCLINUX: + return tioclinux(tty, arg); +#endif + case TIOCTTYGSTRUCT: + return tiocttygstruct(tty, (struct tty_struct *) arg); + + /* + * Break handling + */ + case TIOCSBRK: /* Turn break on, unconditionally */ + tty->driver.break_ctl(tty, -1); + return 0; + + case TIOCCBRK: /* Turn break off, unconditionally */ + tty->driver.break_ctl(tty, 0); + return 0; + case TCSBRK: /* SVID version: non-zero arg --> no break */ + /* + * XXX is the above comment correct, or the + * code below correct? Is this ioctl used at + * all by anyone? + */ + if (!arg) + return send_break(tty, HZ/4); + return 0; + case TCSBRKP: /* support for POSIX tcsendbreak() */ + return send_break(tty, arg ? arg*(HZ/10) : HZ/4); + } + if (tty->driver.ioctl) { + int retval = (tty->driver.ioctl)(tty, file, cmd, arg); + if (retval != -ENOIOCTLCMD) + return retval; + } + if (tty->ldisc.ioctl) { + int retval = (tty->ldisc.ioctl)(tty, file, cmd, arg); + if (retval != -ENOIOCTLCMD) + return retval; + } + return -EINVAL; +} + + +/* + * This implements the "Secure Attention Key" --- the idea is to + * prevent trojan horses by killing all processes associated with this + * tty when the user hits the "Secure Attention Key". Required for + * super-paranoid applications --- see the Orange Book for more details. + * + * This code could be nicer; ideally it should send a HUP, wait a few + * seconds, then send a INT, and then a KILL signal. But you then + * have to coordinate with the init process, since all processes associated + * with the current tty must be dead before the new getty is allowed + * to spawn. + * + * Now, if it would be correct ;-/ The current code has a nasty hole - + * it doesn't catch files in flight. We may send the descriptor to ourselves + * via AF_UNIX socket, close it and later fetch from socket. FIXME. + * + * Nasty bug: do_SAK is being called in interrupt context. This can + * deadlock. We punt it up to process context. AKPM - 16Mar2001 + */ +static void __do_SAK(void *arg) +{ +#ifdef TTY_SOFT_SAK + tty_hangup(tty); +#else + struct tty_struct *tty = arg; + struct task_struct *p; + int session; + int i; + struct file *filp; + + if (!tty) + return; + session = tty->session; + if (tty->ldisc.flush_buffer) + tty->ldisc.flush_buffer(tty); + if (tty->driver.flush_buffer) + tty->driver.flush_buffer(tty); + read_lock(&tasklist_lock); + for_each_task(p) { + if ((p->tty == tty) || + ((session > 0) && (p->session == session))) { + send_sig(SIGKILL, p, 1); + continue; + } + task_lock(p); + if (p->files) { + read_lock(&p->files->file_lock); + for (i=0; i < p->files->max_fds; i++) { + filp = fcheck_files(p->files, i); + if (filp && (filp->f_op == &tty_fops) && + (filp->private_data == tty)) { + send_sig(SIGKILL, p, 1); + break; + } + } + read_unlock(&p->files->file_lock); + } + task_unlock(p); + } + read_unlock(&tasklist_lock); +#endif +} + +/* + * The tq handling here is a little racy - tty->SAK_tq may already be queued. + * But there's no mechanism to fix that without futzing with tqueue_lock. + * Fortunately we don't need to worry, because if ->SAK_tq is already queued, + * the values which we write to it will be identical to the values which it + * already has. --akpm + */ +void do_SAK(struct tty_struct *tty) +{ + if (!tty) + return; + PREPARE_TQUEUE(&tty->SAK_tq, __do_SAK, tty); + schedule_task(&tty->SAK_tq); +} + +/* + * This routine is called out of the software interrupt to flush data + * from the flip buffer to the line discipline. + */ +static void flush_to_ldisc(void *private_) +{ + struct tty_struct *tty = (struct tty_struct *) private_; + unsigned char *cp; + char *fp; + int count; + unsigned long flags; + + if (test_bit(TTY_DONT_FLIP, &tty->flags)) { + queue_task(&tty->flip.tqueue, &tq_timer); + return; + } + if (tty->flip.buf_num) { + cp = tty->flip.char_buf + TTY_FLIPBUF_SIZE; + fp = tty->flip.flag_buf + TTY_FLIPBUF_SIZE; + tty->flip.buf_num = 0; + + save_flags(flags); cli(); + tty->flip.char_buf_ptr = tty->flip.char_buf; + tty->flip.flag_buf_ptr = tty->flip.flag_buf; + } else { + cp = tty->flip.char_buf; + fp = tty->flip.flag_buf; + tty->flip.buf_num = 1; + + save_flags(flags); cli(); + tty->flip.char_buf_ptr = tty->flip.char_buf + TTY_FLIPBUF_SIZE; + tty->flip.flag_buf_ptr = tty->flip.flag_buf + TTY_FLIPBUF_SIZE; + } + count = tty->flip.count; + tty->flip.count = 0; + restore_flags(flags); + + tty->ldisc.receive_buf(tty, cp, fp, count); +} + +/* + * Routine which returns the baud rate of the tty + * + * Note that the baud_table needs to be kept in sync with the + * include/asm/termbits.h file. + */ +static int baud_table[] = { + 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800, + 9600, 19200, 38400, 57600, 115200, 230400, 460800, +#ifdef __sparc__ + 76800, 153600, 307200, 614400, 921600 +#else + 500000, 576000, 921600, 1000000, 1152000, 1500000, 2000000, + 2500000, 3000000, 3500000, 4000000 +#endif +}; + +static int n_baud_table = sizeof(baud_table)/sizeof(int); + +int tty_get_baud_rate(struct tty_struct *tty) +{ + unsigned int cflag, i; + + cflag = tty->termios->c_cflag; + + i = cflag & CBAUD; + if (i & CBAUDEX) { + i &= ~CBAUDEX; + if (i < 1 || i+15 >= n_baud_table) + tty->termios->c_cflag &= ~CBAUDEX; + else + i += 15; + } + if (i==15 && tty->alt_speed) { + if (!tty->warned) { + printk(KERN_WARNING "Use of setserial/setrocket to " + "set SPD_* flags is deprecated\n"); + tty->warned = 1; + } + return(tty->alt_speed); + } + + return baud_table[i]; +} + +void tty_flip_buffer_push(struct tty_struct *tty) +{ + if (tty->low_latency) + flush_to_ldisc((void *) tty); + else + queue_task(&tty->flip.tqueue, &tq_timer); +} + +/* + * This subroutine initializes a tty structure. + */ +static void initialize_tty_struct(struct tty_struct *tty) +{ + memset(tty, 0, sizeof(struct tty_struct)); + tty->magic = TTY_MAGIC; + tty->ldisc = ldiscs[N_TTY]; + tty->pgrp = -1; + tty->flip.char_buf_ptr = tty->flip.char_buf; + tty->flip.flag_buf_ptr = tty->flip.flag_buf; + tty->flip.tqueue.routine = flush_to_ldisc; + tty->flip.tqueue.data = tty; + init_MUTEX(&tty->flip.pty_sem); + init_waitqueue_head(&tty->write_wait); + init_waitqueue_head(&tty->read_wait); + tty->tq_hangup.routine = do_tty_hangup; + tty->tq_hangup.data = tty; + sema_init(&tty->atomic_read, 1); + sema_init(&tty->atomic_write, 1); + spin_lock_init(&tty->read_lock); + INIT_LIST_HEAD(&tty->tty_files); + INIT_TQUEUE(&tty->SAK_tq, 0, 0); +} + +/* + * The default put_char routine if the driver did not define one. + */ +void tty_default_put_char(struct tty_struct *tty, unsigned char ch) +{ + tty->driver.write(tty, 0, &ch, 1); +} + +/* + * Register a tty device described by <driver>, with minor number <minor>. + */ +void tty_register_devfs (struct tty_driver *driver, unsigned int flags, unsigned minor) +{ +#ifdef CONFIG_DEVFS_FS + umode_t mode = S_IFCHR | S_IRUSR | S_IWUSR; + kdev_t device = MKDEV (driver->major, minor); + int idx = minor - driver->minor_start; + char buf[32]; + + switch (device) { + case TTY_DEV: + case PTMX_DEV: + mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; + break; + default: + if (driver->major == PTY_MASTER_MAJOR) + mode |= S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; + break; + } + if ( (minor < driver->minor_start) || + (minor >= driver->minor_start + driver->num) ) { + printk(KERN_ERR "Attempt to register invalid minor number " + "with devfs (%d:%d).\n", (int)driver->major,(int)minor); + return; + } +# ifdef CONFIG_UNIX98_PTYS + if ( (driver->major >= UNIX98_PTY_SLAVE_MAJOR) && + (driver->major < UNIX98_PTY_SLAVE_MAJOR + UNIX98_NR_MAJORS) ) + flags |= DEVFS_FL_CURRENT_OWNER; +# endif + sprintf(buf, driver->name, idx + driver->name_base); + devfs_register (NULL, buf, flags | DEVFS_FL_DEFAULT, + driver->major, minor, mode, &tty_fops, NULL); +#endif /* CONFIG_DEVFS_FS */ +} + +void tty_unregister_devfs (struct tty_driver *driver, unsigned minor) +{ +#ifdef CONFIG_DEVFS_FS + void * handle; + int idx = minor - driver->minor_start; + char buf[32]; + + sprintf(buf, driver->name, idx + driver->name_base); + handle = devfs_find_handle (NULL, buf, driver->major, minor, + DEVFS_SPECIAL_CHR, 0); + devfs_unregister (handle); +#endif /* CONFIG_DEVFS_FS */ +} + +EXPORT_SYMBOL(tty_register_devfs); +EXPORT_SYMBOL(tty_unregister_devfs); + +/* + * Called by a tty driver to register itself. + */ +int tty_register_driver(struct tty_driver *driver) +{ + int error; + int i; + + if (driver->flags & TTY_DRIVER_INSTALLED) + return 0; + + error = devfs_register_chrdev(driver->major, driver->name, &tty_fops); + if (error < 0) + return error; + else if(driver->major == 0) + driver->major = error; + + if (!driver->put_char) + driver->put_char = tty_default_put_char; + + driver->prev = 0; + driver->next = tty_drivers; + if (tty_drivers) tty_drivers->prev = driver; + tty_drivers = driver; + + if ( !(driver->flags & TTY_DRIVER_NO_DEVFS) ) { + for(i = 0; i < driver->num; i++) + tty_register_devfs(driver, 0, driver->minor_start + i); + } + proc_tty_register_driver(driver); + return error; +} + +/* + * Called by a tty driver to unregister itself. + */ +int tty_unregister_driver(struct tty_driver *driver) +{ + int retval; + struct tty_driver *p; + int i, found = 0; + struct termios *tp; + const char *othername = NULL; + + if (*driver->refcount) + return -EBUSY; + + for (p = tty_drivers; p; p = p->next) { + if (p == driver) + found++; + else if (p->major == driver->major) + othername = p->name; + } + + if (!found) + return -ENOENT; + + if (othername == NULL) { + retval = devfs_unregister_chrdev(driver->major, driver->name); + if (retval) + return retval; + } else + devfs_register_chrdev(driver->major, othername, &tty_fops); + + if (driver->prev) + driver->prev->next = driver->next; + else + tty_drivers = driver->next; + + if (driver->next) + driver->next->prev = driver->prev; + + /* + * Free the termios and termios_locked structures because + * we don't want to get memory leaks when modular tty + * drivers are removed from the kernel. + */ + for (i = 0; i < driver->num; i++) { + tp = driver->termios[i]; + if (tp) { + driver->termios[i] = NULL; + kfree(tp); + } + tp = driver->termios_locked[i]; + if (tp) { + driver->termios_locked[i] = NULL; + kfree(tp); + } + tty_unregister_devfs(driver, driver->minor_start + i); + } + proc_tty_unregister_driver(driver); + return 0; +} + + +/* + * Initialize the console device. This is called *early*, so + * we can't necessarily depend on lots of kernel help here. + * Just do some early initializations, and do the complex setup + * later. + */ +void __init console_init(void) +{ + /* Setup the default TTY line discipline. */ + memset(ldiscs, 0, sizeof(ldiscs)); + (void) tty_register_ldisc(N_TTY, &tty_ldisc_N_TTY); + + /* + * Set up the standard termios. Individual tty drivers may + * deviate from this; this is used as a template. + */ + memset(&tty_std_termios, 0, sizeof(struct termios)); + memcpy(tty_std_termios.c_cc, INIT_C_CC, NCCS); + tty_std_termios.c_iflag = ICRNL | IXON; + tty_std_termios.c_oflag = OPOST | ONLCR; + tty_std_termios.c_cflag = B38400 | CS8 | CREAD | HUPCL; + tty_std_termios.c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK | + ECHOCTL | ECHOKE | IEXTEN; + + /* + * set up the console device so that later boot sequences can + * inform about problems etc.. + */ +#ifdef CONFIG_XENO + xeno_console_init(); +#endif +#ifdef CONFIG_VT + con_init(); +#endif +#ifdef CONFIG_AU1000_SERIAL_CONSOLE + au1000_serial_console_init(); +#endif +#ifdef CONFIG_SERIAL_CONSOLE +#if (defined(CONFIG_8xx) || defined(CONFIG_8260)) + console_8xx_init(); +#elif defined(CONFIG_MAC_SERIAL) + mac_scc_console_init(); +#elif defined(CONFIG_PARISC) + pdc_console_init(); +#elif defined(CONFIG_SERIAL) + serial_console_init(); +#endif /* CONFIG_8xx */ +#ifdef CONFIG_SGI_SERIAL + sgi_serial_console_init(); +#endif +#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC) + vme_scc_console_init(); +#endif +#if defined(CONFIG_SERIAL167) + serial167_console_init(); +#endif +#if defined(CONFIG_SH_SCI) + sci_console_init(); +#endif +#endif +#ifdef CONFIG_TN3270_CONSOLE + tub3270_con_init(); +#endif +#ifdef CONFIG_TN3215 + con3215_init(); +#endif +#ifdef CONFIG_HWC + hwc_console_init(); +#endif +#ifdef CONFIG_STDIO_CONSOLE + stdio_console_init(); +#endif +#ifdef CONFIG_SERIAL_21285_CONSOLE + rs285_console_init(); +#endif +#ifdef CONFIG_SERIAL_SA1100_CONSOLE + sa1100_rs_console_init(); +#endif +#ifdef CONFIG_ARC_CONSOLE + arc_console_init(); +#endif +#ifdef CONFIG_SERIAL_AMBA_CONSOLE + ambauart_console_init(); +#endif +#ifdef CONFIG_SERIAL_TX3912_CONSOLE + tx3912_console_init(); +#endif +} + +static struct tty_driver dev_tty_driver, dev_syscons_driver; +#ifdef CONFIG_UNIX98_PTYS +static struct tty_driver dev_ptmx_driver; +#endif +#ifdef CONFIG_VT +static struct tty_driver dev_console_driver; +#endif + +/* + * Ok, now we can initialize the rest of the tty devices and can count + * on memory allocations, interrupts etc.. + */ +void __init tty_init(void) +{ + /* + * dev_tty_driver and dev_console_driver are actually magic + * devices which get redirected at open time. Nevertheless, + * we register them so that register_chrdev is called + * appropriately. + */ + memset(&dev_tty_driver, 0, sizeof(struct tty_driver)); + dev_tty_driver.magic = TTY_DRIVER_MAGIC; + dev_tty_driver.driver_name = "/dev/tty"; + dev_tty_driver.name = dev_tty_driver.driver_name + 5; + dev_tty_driver.name_base = 0; + dev_tty_driver.major = TTYAUX_MAJOR; + dev_tty_driver.minor_start = 0; + dev_tty_driver.num = 1; + dev_tty_driver.type = TTY_DRIVER_TYPE_SYSTEM; + dev_tty_driver.subtype = SYSTEM_TYPE_TTY; + + if (tty_register_driver(&dev_tty_driver)) + panic("Couldn't register /dev/tty driver\n"); + + dev_syscons_driver = dev_tty_driver; + dev_syscons_driver.driver_name = "/dev/console"; + dev_syscons_driver.name = dev_syscons_driver.driver_name + 5; + dev_syscons_driver.major = TTYAUX_MAJOR; + dev_syscons_driver.minor_start = 1; + dev_syscons_driver.type = TTY_DRIVER_TYPE_SYSTEM; + dev_syscons_driver.subtype = SYSTEM_TYPE_SYSCONS; + + if (tty_register_driver(&dev_syscons_driver)) + panic("Couldn't register /dev/console driver\n"); + + /* console calls tty_register_driver() before kmalloc() works. + * Thus, we can't devfs_register() then. Do so now, instead. + */ +#ifdef CONFIG_VT + con_init_devfs(); +#endif + +#ifdef CONFIG_UNIX98_PTYS + dev_ptmx_driver = dev_tty_driver; + dev_ptmx_driver.driver_name = "/dev/ptmx"; + dev_ptmx_driver.name = dev_ptmx_driver.driver_name + 5; + dev_ptmx_driver.major= MAJOR(PTMX_DEV); + dev_ptmx_driver.minor_start = MINOR(PTMX_DEV); + dev_ptmx_driver.type = TTY_DRIVER_TYPE_SYSTEM; + dev_ptmx_driver.subtype = SYSTEM_TYPE_SYSPTMX; + + if (tty_register_driver(&dev_ptmx_driver)) + panic("Couldn't register /dev/ptmx driver\n"); +#endif + +#ifdef CONFIG_VT + dev_console_driver = dev_tty_driver; + dev_console_driver.driver_name = "/dev/vc/0"; + dev_console_driver.name = dev_console_driver.driver_name + 5; + dev_console_driver.major = TTY_MAJOR; + dev_console_driver.type = TTY_DRIVER_TYPE_SYSTEM; + dev_console_driver.subtype = SYSTEM_TYPE_CONSOLE; + + if (tty_register_driver(&dev_console_driver)) + panic("Couldn't register /dev/tty0 driver\n"); + + kbd_init(); +#endif + +#ifdef CONFIG_ESPSERIAL /* init ESP before rs, so rs doesn't see the port */ + espserial_init(); +#endif +#if defined(CONFIG_MVME162_SCC) || defined(CONFIG_BVME6000_SCC) || defined(CONFIG_MVME147_SCC) + vme_scc_init(); +#endif +#ifdef CONFIG_SERIAL_TX3912 + tx3912_rs_init(); +#endif +#ifdef CONFIG_ROCKETPORT + rp_init(); +#endif +#ifdef CONFIG_SERIAL167 + serial167_init(); +#endif +#ifdef CONFIG_CYCLADES + cy_init(); +#endif +#ifdef CONFIG_STALLION + stl_init(); +#endif +#ifdef CONFIG_ISTALLION + stli_init(); +#endif +#ifdef CONFIG_DIGI + pcxe_init(); +#endif +#ifdef CONFIG_DIGIEPCA + pc_init(); +#endif +#ifdef CONFIG_SPECIALIX + specialix_init(); +#endif +#if (defined(CONFIG_8xx) || defined(CONFIG_8260)) + rs_8xx_init(); +#endif /* CONFIG_8xx */ + pty_init(); +#ifdef CONFIG_MOXA_SMARTIO + mxser_init(); +#endif +#ifdef CONFIG_MOXA_INTELLIO + moxa_init(); +#endif +#ifdef CONFIG_VT + vcs_init(); +#endif +#ifdef CONFIG_TN3270 + tub3270_init(); +#endif +#ifdef CONFIG_TN3215 + tty3215_init(); +#endif +#ifdef CONFIG_HWC + hwc_tty_init(); +#endif +#ifdef CONFIG_A2232 + a2232board_init(); +#endif +} |