// SPDX-License-Identifier: GPL-2.0 /* * Functions to sequence PREFLUSH and FUA writes. * * Copyright (C) 2011 Max Planck Institute for Gravitational Physics * Copyright (C) 2011 Tejun Heo * * REQ_{PREFLUSH|FUA} requests are decomposed to sequences consisted of three * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request * properties and hardware capability. * * If a request doesn't have data, only REQ_PREFLUSH makes sense, which * indicates a simple flush request. If there is data, REQ_PREFLUSH indicates * that the device cache should be flushed before the data is executed, and * REQ_FUA means that the data must be on non-volatile media on request * completion. * * If the device doesn't have writeback cache, PREFLUSH and FUA don't make any * difference. The requests are either completed immediately if there's no data * or executed as normal requests otherwise. * * If the device has writeback cache and supports FUA, REQ_PREFLUSH is * translated to PREFLUSH but REQ_FUA is passed down directly with DATA. * * If the device has writeback cache and doesn't support FUA, REQ_PREFLUSH * is translated to PREFLUSH and REQ_FUA to POSTFLUSH. * * The actual execution of flush is double buffered. Whenever a request * needs to execute PRE or POSTFLUSH, it queues at * fq->flush_queue[fq->flush_pending_idx]. Once certain criteria are met, a * REQ_OP_FLUSH is issued and the pending_idx is toggled. When the flush * completes, all the requests which were pending are proceeded to the next * step. This allows arbitrary merging of different types of PREFLUSH/FUA * requests. * * Currently, the following conditions are used to determine when to issue * flush. * * C1. At any given time, only one flush shall be in progress. This makes * double buffering sufficient. * * C2. Flush is deferred if any request is executing DATA of its sequence. * This avoids issuing separate POSTFLUSHes for requests which shared * PREFLUSH. * * C3. The second condition is ignored if there is a request which has * waited longer than FLUSH_PENDING_TIMEOUT. This is to avoid * starvation in the unlikely case where there are continuous stream of * FUA (without PREFLUSH) requests. * * For devices which support FUA, it isn't clear whether C2 (and thus C3) * is beneficial. * * Note that a sequenced PREFLUSH/FUA request with DATA is completed twice. * Once while executing DATA and again after the whole sequence is * complete. The first completion updates the contained bio but doesn't * finish it so that the bio submitter is notified only after the whole * sequence is complete. This is implemented by testing RQF_FLUSH_SEQ in * req_bio_endio(). * * The above peculiarity requires that each PREFLUSH/FUA request has only one * bio attached to it, which is guaranteed as they aren't allowed to be * merged in the usual way. */ #include #include #include #include #include #include #include #include "blk.h" #include "blk-mq.h" #include "blk-mq-tag.h" #include "blk-mq-sched.h" /* PREFLUSH/FUA sequences */ enum { REQ_FSEQ_PREFLUSH = (1 << 0), /* pre-flushing in progress */ REQ_FSEQ_DATA = (1 << 1), /* data write in progress */ REQ_FSEQ_POSTFLUSH = (1 << 2), /* post-flushing in progress */ REQ_FSEQ_DONE = (1 << 3), REQ_FSEQ_ACTIONS = REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA | REQ_FSEQ_POSTFLUSH, /* * If flush has been pending longer than the following timeout, * it's issued even if flush_data requests are still in flight. */ FLUSH_PENDING_TIMEOUT = 5 * HZ, }; static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, unsigned int flags); static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq) { unsigned int policy = 0; if (blk_rq_sectors(rq)) policy |= REQ_FSEQ_DATA; if (fflags & (1UL << QUEUE_FLAG_WC)) { if (rq->cmd_flags & REQ_PREFLUSH) policy |= REQ_FSEQ_PREFLUSH; if (!(fflags & (1UL << QUEUE_FLAG_FUA)) && (rq->cmd_flags & REQ_FUA)) policy |= REQ_FSEQ_POSTFLUSH; } return policy; } static unsigned int blk_flush_cur_seq(struct request *rq) { return 1 << ffz(rq->flush.seq); } static void blk_flush_restore_request(struct request *rq) { /* * After flush data completion, @rq->bio is %NULL but we need to * complete the bio again. @rq->biotail is guaranteed to equal the * original @rq->bio. Restore it. */ rq->bio = rq->biotail; /* make @rq a normal request */ rq->rq_flags &= ~RQF_FLUSH_SEQ; rq->end_io = rq->flush.saved_end_io; } static void blk_flush_queue_rq(struct request *rq, bool add_front) { blk_mq_add_to_requeue_list(rq, add_front, true); } static void blk_account_io_flush(struct request *rq) { struct hd_struct *part = &rq->rq_disk->part0; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); part_stat_add(part, nsecs[STAT_FLUSH], ktime_get_ns() - rq->start_time_ns); part_stat_unlock(); } /** * blk_flush_complete_seq - complete flush sequence * @rq: PREFLUSH/FUA request being sequenced * @fq: flush queue * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero) * @error: whether an error occurred * * @rq just completed @seq part of its flush sequence, record the * completion and trigger the next step. * * CONTEXT: * spin_lock_irq(fq->mq_flush_lock) */ static void blk_flush_complete_seq(struct request *rq, struct blk_flush_queue *fq, unsigned int seq, blk_status_t error) { struct request_queue *q = rq->q; struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; unsigned int cmd_flags; BUG_ON(rq->flush.seq & seq); rq->flush.seq |= seq; cmd_flags = rq->cmd_flags; if (likely(!error)) seq = blk_flush_cur_seq(rq); else seq = REQ_FSEQ_DONE; switch (seq) { case REQ_FSEQ_PREFLUSH: case REQ_FSEQ_POSTFLUSH: /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; list_move_tail(&rq->flush.list, pending); break; case REQ_FSEQ_DATA: list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); blk_flush_queue_rq(rq, true); break; case REQ_FSEQ_DONE: /* * @rq was previously adjusted by blk_insert_flush() for * flush sequencing and may already have gone through the * flush data request completion path. Restore @rq for * normal completion and end it. */ BUG_ON(!list_empty(&rq->queuelist)); list_del_init(&rq->flush.list); blk_flush_restore_request(rq); blk_mq_end_request(rq, error); break; default: BUG(); } blk_kick_flush(q, fq, cmd_flags); } static void flush_end_io(struct request *flush_rq, blk_status_t error) { struct request_queue *q = flush_rq->q; struct list_head *running; struct request *rq, *n; unsigned long flags = 0; struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); struct blk_mq_hw_ctx *hctx; blk_account_io_flush(flush_rq); /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); if (!refcount_dec_and_test(&flush_rq->ref)) { fq->rq_status = error; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return; } if (fq->rq_status != BLK_STS_OK) error = fq->rq_status; hctx = flush_rq->mq_hctx; if (!q->elevator) { blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq); flush_rq->tag = -1; } else { blk_mq_put_driver_tag(flush_rq); flush_rq->internal_tag = -1; } running = &fq->flush_queue[fq->flush_running_idx]; BUG_ON(fq->flush_pending_idx == fq->flush_running_idx); /* account completion of the flush request */ fq->flush_running_idx ^= 1; /* and push the waiting requests to the next stage */ list_for_each_entry_safe(rq, n, running, flush.list) { unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); blk_flush_complete_seq(rq, fq, seq, error); } spin_unlock_irqrestore(&fq->mq_flush_lock, flags); } /** * blk_kick_flush - consider issuing flush request * @q: request_queue being kicked * @fq: flush queue * @flags: cmd_flags of the original request * * Flush related states of @q have changed, consider issuing flush request. * Please read the comment at the top of this file for more info. * * CONTEXT: * spin_lock_irq(fq->mq_flush_lock) * */ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, unsigned int flags) { struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; struct request *first_rq = list_first_entry(pending, struct request, flush.list); struct request *flush_rq = fq->flush_rq; /* C1 described at the top of this file */ if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending)) return; /* C2 and C3 * * For blk-mq + scheduling, we can risk having all driver tags * assigned to empty flushes, and we deadlock if we are expecting * other requests to make progress. Don't defer for that case. */ if (!list_empty(&fq->flush_data_in_flight) && q->elevator && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return; /* * Issue flush and toggle pending_idx. This makes pending_idx * different from running_idx, which means flush is in flight. */ fq->flush_pending_idx ^= 1; blk_rq_init(q, flush_rq); /* * In case of none scheduler, borrow tag from the first request * since they can't be in flight at the same time. And acquire * the tag's ownership for flush req. * * In case of IO scheduler, flush rq need to borrow scheduler tag * just for cheating put/get driver tag. */ flush_rq->mq_ctx = first_rq->mq_ctx; flush_rq->mq_hctx = first_rq->mq_hctx; if (!q->elevator) { fq->orig_rq = first_rq; flush_rq->tag = first_rq->tag; blk_mq_tag_set_rq(flush_rq->mq_hctx, first_rq->tag, flush_rq); } else { flush_rq->internal_tag = first_rq->internal_tag; } flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH; flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK); flush_rq->rq_flags |= RQF_FLUSH_SEQ; flush_rq->rq_disk = first_rq->rq_disk; flush_rq->end_io = flush_end_io; blk_flush_queue_rq(flush_rq, false); } static void mq_flush_data_end_io(struct request *rq, blk_status_t error) { struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_mq_ctx *ctx = rq->mq_ctx; unsigned long flags; struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx); if (q->elevator) { WARN_ON(rq->tag < 0); blk_mq_put_driver_tag(rq); } /* * After populating an empty queue, kick it to avoid stall. Read * the comment in flush_end_io(). */ spin_lock_irqsave(&fq->mq_flush_lock, flags); blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); blk_mq_sched_restart(hctx); } /** * blk_insert_flush - insert a new PREFLUSH/FUA request * @rq: request to insert * * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions. * or __blk_mq_run_hw_queue() to dispatch request. * @rq is being submitted. Analyze what needs to be done and put it on the * right queue. */ void blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; unsigned long fflags = q->queue_flags; /* may change, cache */ unsigned int policy = blk_flush_policy(fflags, rq); struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); /* * @policy now records what operations need to be done. Adjust * REQ_PREFLUSH and FUA for the driver. */ rq->cmd_flags &= ~REQ_PREFLUSH; if (!(fflags & (1UL << QUEUE_FLAG_FUA))) rq->cmd_flags &= ~REQ_FUA; /* * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any * of those flags, we have to set REQ_SYNC to avoid skewing * the request accounting. */ rq->cmd_flags |= REQ_SYNC; /* * An empty flush handed down from a stacking driver may * translate into nothing if the underlying device does not * advertise a write-back cache. In this case, simply * complete the request. */ if (!policy) { blk_mq_end_request(rq, 0); return; } BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */ /* * If there's data but flush is not necessary, the request can be * processed directly without going through flush machinery. Queue * for normal execution. */ if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { blk_mq_request_bypass_insert(rq, false, false); return; } /* * @rq should go through flush machinery. Mark it part of flush * sequence and submit for further processing. */ memset(&rq->flush, 0, sizeof(rq->flush)); INIT_LIST_HEAD(&rq->flush.list); rq->rq_flags |= RQF_FLUSH_SEQ; rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ rq->end_io = mq_flush_data_end_io; spin_lock_irq(&fq->mq_flush_lock); blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0); spin_unlock_irq(&fq->mq_flush_lock); } /** * blkdev_issue_flush - queue a flush * @bdev: blockdev to issue flush for * @gfp_mask: memory allocation flags (for bio_alloc) * * Description: * Issue a flush for the block device in question. */ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) { struct bio *bio; int ret = 0; bio = bio_alloc(gfp_mask, 0); bio_set_dev(bio, bdev); bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; ret = submit_bio_wait(bio); bio_put(bio); return ret; } EXPORT_SYMBOL(blkdev_issue_flush); struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, gfp_t flags) { struct blk_flush_queue *fq; int rq_sz = sizeof(struct request); fq = kzalloc_node(sizeof(*fq), flags, node); if (!fq) goto fail; spin_lock_init(&fq->mq_flush_lock); rq_sz = round_up(rq_sz + cmd_size, cache_line_size()); fq->flush_rq = kzalloc_node(rq_sz, flags, node); if (!fq->flush_rq) goto fail_rq; INIT_LIST_HEAD(&fq->flush_queue[0]); INIT_LIST_HEAD(&fq->flush_queue[1]); INIT_LIST_HEAD(&fq->flush_data_in_flight); lockdep_register_key(&fq->key); lockdep_set_class(&fq->mq_flush_lock, &fq->key); return fq; fail_rq: kfree(fq); fail: return NULL; } void blk_free_flush_queue(struct blk_flush_queue *fq) { /* bio based request queue hasn't flush queue */ if (!fq) return; lockdep_unregister_key(&fq->key); kfree(fq->flush_rq); kfree(fq); } href='#n320'>320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 
/*
 *  linux/fs/proc/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/pid_namespace.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/completion.h>
#include <linux/poll.h>
#include <linux/printk.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/magic.h>

#include <asm/uaccess.h>

#include "internal.h"

static void proc_evict_inode(struct inode *inode)
{
	struct proc_dir_entry *de;
	struct ctl_table_header *head;
	const struct proc_ns_operations *ns_ops;
	void *ns;

	truncate_inode_pages_final(&inode->i_data);
	clear_inode(inode);

	/* Stop tracking associated processes */
	put_pid(PROC_I(inode)->pid);

	/* Let go of any associated proc directory entry */
	de = PROC_I(inode)->pde;
	if (de)
		pde_put(de);
	head = PROC_I(inode)->sysctl;
	if (head) {
		rcu_assign_pointer(PROC_I(inode)->sysctl, NULL);
		sysctl_head_put(head);
	}
	/* Release any associated namespace */
	ns_ops = PROC_I(inode)->ns.ns_ops;
	ns = PROC_I(inode)->ns.ns;
	if (ns_ops && ns)
		ns_ops->put(ns);
}

static struct kmem_cache * proc_inode_cachep;

static struct inode *proc_alloc_inode(struct super_block *sb)
{
	struct proc_inode *ei;
	struct inode *inode;

	ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	ei->pid = NULL;
	ei->fd = 0;
	ei->op.proc_get_link = NULL;
	ei->pde = NULL;
	ei->sysctl = NULL;
	ei->sysctl_entry = NULL;
	ei->ns.ns = NULL;
	ei->ns.ns_ops = NULL;
	inode = &ei->vfs_inode;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	return inode;
}

static void proc_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
}

static void proc_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, proc_i_callback);
}

static void init_once(void *foo)
{
	struct proc_inode *ei = (struct proc_inode *) foo;

	inode_init_once(&ei->vfs_inode);
}

void __init proc_init_inodecache(void)
{
	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
					     sizeof(struct proc_inode),
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD|SLAB_PANIC),
					     init_once);
}

static int proc_show_options(struct seq_file *seq, struct dentry *root)
{
	struct super_block *sb = root->d_sb;
	struct pid_namespace *pid = sb->s_fs_info;

	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
	if (pid->hide_pid != 0)
		seq_printf(seq, ",hidepid=%u", pid->hide_pid);

	return 0;
}

static const struct super_operations proc_sops = {
	.alloc_inode	= proc_alloc_inode,
	.destroy_inode	= proc_destroy_inode,
	.drop_inode	= generic_delete_inode,
	.evict_inode	= proc_evict_inode,
	.statfs		= simple_statfs,
	.remount_fs	= proc_remount,
	.show_options	= proc_show_options,
};

enum {BIAS = -1U<<31};

static inline int use_pde(struct proc_dir_entry *pde)
{
	return atomic_inc_unless_negative(&pde->in_use);
}

static void unuse_pde(struct proc_dir_entry *pde)
{
	if (atomic_dec_return(&pde->in_use) == BIAS)
		complete(pde->pde_unload_completion);
}

/* pde is locked */
static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
{
	if (pdeo->closing) {
		/* somebody else is doing that, just wait */
		DECLARE_COMPLETION_ONSTACK(c);
		pdeo->c = &c;
		spin_unlock(&pde->pde_unload_lock);
		wait_for_completion(&c);
		spin_lock(&pde->pde_unload_lock);
	} else {
		struct file *file;
		pdeo->closing = 1;
		spin_unlock(&pde->pde_unload_lock);
		file = pdeo->file;
		pde->proc_fops->release(file_inode(file), file);
		spin_lock(&pde->pde_unload_lock);
		list_del_init(&pdeo->lh);
		if (pdeo->c)
			complete(pdeo->c);
		kfree(pdeo);
	}
}

void proc_entry_rundown(struct proc_dir_entry *de)
{
	DECLARE_COMPLETION_ONSTACK(c);
	/* Wait until all existing callers into module are done. */
	de->pde_unload_completion = &c;
	if (atomic_add_return(BIAS, &de->in_use) != BIAS)
		wait_for_completion(&c);

	spin_lock(&de->pde_unload_lock);
	while (!list_empty(&de->pde_openers)) {
		struct pde_opener *pdeo;
		pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
		close_pdeo(de, pdeo);
	}
	spin_unlock(&de->pde_unload_lock);
}

static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
{
	struct proc_dir_entry *pde = PDE(file_inode(file));
	loff_t rv = -EINVAL;
	if (use_pde(pde)) {
		loff_t (*llseek)(struct file *, loff_t, int);
		llseek = pde->proc_fops->llseek;
		if (!llseek)
			llseek = default_llseek;
		rv = llseek(file, offset, whence);
		unuse_pde(pde);
	}
	return rv;
}

static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
	struct proc_dir_entry *pde = PDE(file_inode(file));
	ssize_t rv = -EIO;
	if (use_pde(pde)) {
		read = pde->proc_fops->read;
		if (read)
			rv = read(file, buf, count, ppos);
		unuse_pde(pde);
	}
	return rv;
}

static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
	struct proc_dir_entry *pde = PDE(file_inode(file));
	ssize_t rv = -EIO;
	if (use_pde(pde)) {
		write = pde->proc_fops->write;
		if (write)
			rv = write(file, buf, count, ppos);
		unuse_pde(pde);
	}
	return rv;
}

static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
{
	struct proc_dir_entry *pde = PDE(file_inode(file));
	unsigned int rv = DEFAULT_POLLMASK;
	unsigned int (*poll)(struct file *, struct poll_table_struct *);
	if (use_pde(pde)) {
		poll = pde->proc_fops->poll;
		if (poll)
			rv = poll(file, pts);
		unuse_pde(pde);
	}
	return rv;
}

static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct proc_dir_entry *pde = PDE(file_inode(file));
	long rv = -ENOTTY;
	long (*ioctl)(struct file *, unsigned int, unsigned long);
	if (use_pde(pde)) {
		ioctl = pde->proc_fops->unlocked_ioctl;
		if (ioctl)
			rv = ioctl(file, cmd, arg);
		unuse_pde(pde);
	}
	return rv;
}

#ifdef CONFIG_COMPAT
static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct proc_dir_entry *pde = PDE(file_inode(file));
	long rv = -ENOTTY;
	long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
	if (use_pde(pde)) {
		compat_ioctl = pde->proc_fops->compat_ioctl;
		if (compat_ioctl)
			rv = compat_ioctl(file, cmd, arg);
		unuse_pde(pde);
	}
	return rv;
}
#endif

static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct proc_dir_entry *pde = PDE(file_inode(file));
	int rv = -EIO;
	int (*mmap)(struct file *, struct vm_area_struct *);
	if (use_pde(pde)) {
		mmap = pde->proc_fops->mmap;
		if (mmap)
			rv = mmap(file, vma);
		unuse_pde(pde);
	}
	return rv;
}

static unsigned long
proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
			   unsigned long len, unsigned long pgoff,
			   unsigned long flags)
{
	struct proc_dir_entry *pde = PDE(file_inode(file));
	unsigned long rv = -EIO;

	if (use_pde(pde)) {
		typeof(proc_reg_get_unmapped_area) *get_area;

		get_area = pde->proc_fops->get_unmapped_area;
#ifdef CONFIG_MMU
		if (!get_area)
			get_area = current->mm->get_unmapped_area;
#endif

		if (get_area)
			rv = get_area(file, orig_addr, len, pgoff, flags);
		else
			rv = orig_addr;
		unuse_pde(pde);
	}
	return rv;
}

static int proc_reg_open(struct inode *inode, struct file *file)
{
	struct proc_dir_entry *pde = PDE(inode);
	int rv = 0;
	int (*open)(struct inode *, struct file *);
	int (*release)(struct inode *, struct file *);
	struct pde_opener *pdeo;

	/*
	 * What for, you ask? Well, we can have open, rmmod, remove_proc_entry
	 * sequence. ->release won't be called because ->proc_fops will be
	 * cleared. Depending on complexity of ->release, consequences vary.
	 *
	 * We can't wait for mercy when close will be done for real, it's
	 * deadlockable: rmmod foo </proc/foo . So, we're going to do ->release
	 * by hand in remove_proc_entry(). For this, save opener's credentials
	 * for later.
	 */
	pdeo = kzalloc(sizeof(struct pde_opener), GFP_KERNEL);
	if (!pdeo)
		return -ENOMEM;

	if (!use_pde(pde)) {
		kfree(pdeo);
		return -ENOENT;
	}
	open = pde->proc_fops->open;
	release = pde->proc_fops->release;

	if (open)
		rv = open(inode, file);

	if (rv == 0 && release) {
		/* To know what to release. */
		pdeo->file = file;
		/* Strictly for "too late" ->release in proc_reg_release(). */
		spin_lock(&pde->pde_unload_lock);
		list_add(&pdeo->lh, &pde->pde_openers);
		spin_unlock(&pde->pde_unload_lock);
	} else
		kfree(pdeo);

	unuse_pde(pde);
	return rv;
}

static int proc_reg_release(struct inode *inode, struct file *file)
{
	struct proc_dir_entry *pde = PDE(inode);
	struct pde_opener *pdeo;
	spin_lock(&pde->pde_unload_lock);
	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
		if (pdeo->file == file) {
			close_pdeo(pde, pdeo);
			break;
		}
	}
	spin_unlock(&pde->pde_unload_lock);
	return 0;
}

static const struct file_operations proc_reg_file_ops = {
	.llseek		= proc_reg_llseek,
	.read		= proc_reg_read,
	.write		= proc_reg_write,
	.poll		= proc_reg_poll,
	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= proc_reg_compat_ioctl,
#endif
	.mmap		= proc_reg_mmap,
	.get_unmapped_area = proc_reg_get_unmapped_area,
	.open		= proc_reg_open,
	.release	= proc_reg_release,
};

#ifdef CONFIG_COMPAT
static const struct file_operations proc_reg_file_ops_no_compat = {
	.llseek		= proc_reg_llseek,
	.read		= proc_reg_read,
	.write		= proc_reg_write,
	.poll		= proc_reg_poll,
	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
	.mmap		= proc_reg_mmap,
	.get_unmapped_area = proc_reg_get_unmapped_area,
	.open		= proc_reg_open,
	.release	= proc_reg_release,
};
#endif

struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
{
	struct inode *inode = new_inode_pseudo(sb);

	if (inode) {
		inode->i_ino = de->low_ino;
		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
		PROC_I(inode)->pde = de;

		if (de->mode) {
			inode->i_mode = de->mode;
			inode->i_uid = de->uid;
			inode->i_gid = de->gid;
		}
		if (de->size)
			inode->i_size = de->size;
		if (de->nlink)
			set_nlink(inode, de->nlink);
		WARN_ON(!de->proc_iops);
		inode->i_op = de->proc_iops;
		if (de->proc_fops) {
			if (S_ISREG(inode->i_mode)) {
#ifdef CONFIG_COMPAT
				if (!de->proc_fops->compat_ioctl)
					inode->i_fop =
						&proc_reg_file_ops_no_compat;
				else
#endif
					inode->i_fop = &proc_reg_file_ops;
			} else {
				inode->i_fop = de->proc_fops;
			}
		}
	} else
	       pde_put(de);
	return inode;
}

int proc_fill_super(struct super_block *s)
{
	struct inode *root_inode;

	s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
	s->s_blocksize = 1024;
	s->s_blocksize_bits = 10;
	s->s_magic = PROC_SUPER_MAGIC;