litmus-rt-ext-res.git - LITMUS^RT with extended reservations for Forbidden Zones paper @ RTAS'20

about summary refs log tree commit diff stats

path: root/tools/perf/scripts/python/failed-syscalls-by-pid.py

diff options

author	Rafael J. Wysocki <rafael.j.wysocki@intel.com>	2019-04-12 03:59:56 -0400
committer	Rafael J. Wysocki <rafael.j.wysocki@intel.com>	2019-04-12 03:59:56 -0400
commit	f456277ee15ff5d150191cb4a2f0181a8804c851 (patch)
tree	f8df5107185f42225fe7545702a9a5542e853449 /tools/perf/scripts/python/failed-syscalls-by-pid.py
parent	c5781ffbbd4f742a58263458145fe7f0ac01d9e0 (diff)
parent	6c6a828f86d67c157c7a2b26d46ebca0ed0d9c47 (diff)

Merge back ACPICA changes for v5.2.

Diffstat (limited to 'tools/perf/scripts/python/failed-syscalls-by-pid.py')

0 files changed, 0 insertions, 0 deletions

d4eb4c65d40b8ee7d6ea3c81dd61'>a0f06780257

75723957673

912d35f8678

75723957673

bc40d73c950

912d35f8678

75723957673

912d35f8678

75723957673

12
13

16
17

27
28

42
43
44

47
48

49
50
51

63
64

82
83

84
85

87
88
89

91
92

97
98

99
100

102
103

127
128

130
131

133
134

137
138

143
144

145
146
147

148
149
150

153
154

157
158

160
161

163
164

172
173
174

176
177

181
182
183

196
197

200
201
202

205
206
207

209
210
211

212
213

237
238
239

240
241
242

243
244
245

246
247

255
256

299
300
301

302
303

305
306

308
309

319
320
321

326
327

328
329

333
334

338
339

344
345

347
348

358
359

360
361

362
363

369
370

403
404

409
410
411

419
420

442
443

444
445

462
463

466
467

469
470

473
474

477
478

481
482

483
484

487
488
489

498
499

500
501
502

514
515
516

532
533

534
535
536

537
538

565
566

587
588
589

613
614
615

617
618

634
635

646
647

649
650

665
666
667

671
672

673
674
675

681
682

688
689

720
721

729
730

734
735

737
738

749
750
751

760
761

763
764

795
796

800
801
802

804
805
806

831
832
833

835
836
837

855
856

858
859

861
862

864
865
866

867
868

869
870

872
873
874

876
877

950
951
952

977
978
979

980
981
982

983
984

985
986

997
998

1009
1010

1034
1035
1036

1037
1038

1039
1040

1041
1042

1064
1065
1066

1069
1070

1071
1072

1076
1077
1078

1079
1080
1081

1082
1083

1088
1089

1092
1093
1094

1098
1099

1100
1101

1103
1104

1105
1106
1107

1109
1110
1111

1112
1113
1114

1115
1116
1117

1118
1119

1120
1121
1122

1123
1124
1125

1127
1128

1129
1130

1132
1133

1135
1136
1137

1138
1139
1140

1141
1142
1143

1144
1145

1156
1157

1158
1159
1160

1165
1166

1199
1200
1201

1209
1210

1216
1217
1218

1227
1228

1231
1232
1233

1236
1237

1240
1241

1261
1262

1273
1274

1275
1276

1303
1304

1309
1310

1311
1312
1313

1328
1329

1330
1331
1332

1334
1335

1360
1361

1367
1368
1369

1380
1381

1387
1388
1389

1411
1412

1413
1414
1415

1416
1417

1425
1426

1427
1428
1429

1430
1431
1432

1434
1435
1436

1455
1456

1458
1459

1539
1540
1541

1630
1631

1634
1635

1656
1657
1658

1660
1661

1662
1663

1680
1681

1696
1697
1698

1706
1707
1708

1719
1720

1722
1723

1724
1725
1726

1736
1737

1738
1739
1740

1788
1789
1790

1943
1944
1945

1947
1948

1966
1967

1968
1969

1970
1971

1979
1980

1984
1985

2000
2001

2025
2026

2028
2029

2030
2031

2043
2044

2047
2048

/*
 * "splice": joining two ropes together by interweaving their strands.
 *
 * This is the "extended pipe" functionality, where a pipe is used as
 * an arbitrary in-memory buffer. Think of a pipe as a small kernel
 * buffer that you can use to transfer data from one end to the other.
 *
 * The traditional unix read/write is extended with a "splice()" operation
 * that transfers data buffers to or from a pipe buffer.
 *
 * Named by Larry McVoy, original implementation from Linus, extended by
 * Jens to support splicing to files, network, direct splicing, etc and
 * fixing lots of bugs.
 *
 * Copyright (C) 2005-2006 Jens Axboe <axboe@kernel.dk>
 * Copyright (C) 2005-2006 Linus Torvalds <torvalds@osdl.org>
 * Copyright (C) 2006 Ingo Molnar <mingo@elte.hu>
 *
 */
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/uio.h>
#include <linux/security.h>
#include <linux/gfp.h>

/*
 * Attempt to steal a page from a pipe buffer. This should perhaps go into
 * a vm helper function, it's already simplified quite a bit by the
 * addition of remove_mapping(). If success is returned, the caller may
 * attempt to reuse this page for another destination.
 */
static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
				     struct pipe_buffer *buf)
{
	struct page *page = buf->page;
	struct address_space *mapping;

	lock_page(page);

	mapping = page_mapping(page);
	if (mapping) {
		WARN_ON(!PageUptodate(page));

		/*
		 * At least for ext2 with nobh option, we need to wait on
		 * writeback completing on this page, since we'll remove it
		 * from the pagecache.  Otherwise truncate wont wait on the
		 * page, allowing the disk blocks to be reused by someone else
		 * before we actually wrote our data to them. fs corruption
		 * ensues.
		 */
		wait_on_page_writeback(page);

		if (page_has_private(page) &&
		    !try_to_release_page(page, GFP_KERNEL))
			goto out_unlock;

		/*
		 * If we succeeded in removing the mapping, set LRU flag
		 * and return good.
		 */
		if (remove_mapping(mapping, page)) {
			buf->flags |= PIPE_BUF_FLAG_LRU;
			return 0;
		}
	}

	/*
	 * Raced with truncate or failed to remove page from current
	 * address space, unlock and return failure.
	 */
out_unlock:
	unlock_page(page);
	return 1;
}

static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe,
					struct pipe_buffer *buf)
{
	page_cache_release(buf->page);
	buf->flags &= ~PIPE_BUF_FLAG_LRU;
}

/*
 * Check whether the contents of buf is OK to access. Since the content
 * is a page cache page, IO may be in flight.
 */
static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe,
				       struct pipe_buffer *buf)
{
	struct page *page = buf->page;
	int err;

	if (!PageUptodate(page)) {
		lock_page(page);

		/*
		 * Page got truncated/unhashed. This will cause a 0-byte
		 * splice, if this is the first page.
		 */
		if (!page->mapping) {
			err = -ENODATA;
			goto error;
		}

		/*
		 * Uh oh, read-error from disk.
		 */
		if (!PageUptodate(page)) {
			err = -EIO;
			goto error;
		}

		/*
		 * Page is ok afterall, we are done.
		 */
		unlock_page(page);
	}

	return 0;
error:
	unlock_page(page);
	return err;
}

static const struct pipe_buf_operations page_cache_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = page_cache_pipe_buf_confirm,
	.release = page_cache_pipe_buf_release,
	.steal = page_cache_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
				    struct pipe_buffer *buf)
{
	if (!(buf->flags & PIPE_BUF_FLAG_GIFT))
		return 1;

	buf->flags |= PIPE_BUF_FLAG_LRU;
	return generic_pipe_buf_steal(pipe, buf);
}

static const struct pipe_buf_operations user_page_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = generic_pipe_buf_confirm,
	.release = page_cache_pipe_buf_release,
	.steal = user_page_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

/**
 * splice_to_pipe - fill passed data into a pipe
 * @pipe:	pipe to fill
 * @spd:	data to fill
 *
 * Description:
 *    @spd contains a map of pages and len/offset tuples, along with
 *    the struct pipe_buf_operations associated with these pages. This
 *    function will link that data to the pipe.
 *
 */
ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
		       struct splice_pipe_desc *spd)
{
	unsigned int spd_pages = spd->nr_pages;
	int ret, do_wakeup, page_nr;

	ret = 0;
	do_wakeup = 0;
	page_nr = 0;

	pipe_lock(pipe);

	for (;;) {
		if (!pipe->readers) {
			send_sig(SIGPIPE, current, 0);
			if (!ret)
				ret = -EPIPE;
			break;
		}

		if (pipe->nrbufs < pipe->buffers) {
			int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
			struct pipe_buffer *buf = pipe->bufs + newbuf;

			buf->page = spd->pages[page_nr];
			buf->offset = spd->partial[page_nr].offset;
			buf->len = spd->partial[page_nr].len;
			buf->private = spd->partial[page_nr].private;
			buf->ops = spd->ops;
			if (spd->flags & SPLICE_F_GIFT)
				buf->flags |= PIPE_BUF_FLAG_GIFT;

			pipe->nrbufs++;
			page_nr++;
			ret += buf->len;

			if (pipe->inode)
				do_wakeup = 1;

			if (!--spd->nr_pages)
				break;
			if (pipe->nrbufs < pipe->buffers)
				continue;

			break;
		}

		if (spd->flags & SPLICE_F_NONBLOCK) {
			if (!ret)
				ret = -EAGAIN;
			break;
		}

		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}

		if (do_wakeup) {
			smp_mb();
			if (waitqueue_active(&pipe->wait))
				wake_up_interruptible_sync(&pipe->wait);
			kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
			do_wakeup = 0;
		}

		pipe->waiting_writers++;
		pipe_wait(pipe);
		pipe->waiting_writers--;
	}

	pipe_unlock(pipe);

	if (do_wakeup) {
		smp_mb();
		if (waitqueue_active(&pipe->wait))
			wake_up_interruptible(&pipe->wait);
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
	}

	while (page_nr < spd_pages)
		spd->spd_release(spd, page_nr++);

	return ret;
}

static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
{
	page_cache_release(spd->pages[i]);
}

/*
 * Check if we need to grow the arrays holding pages and partial page
 * descriptions.
 */
int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
{
	if (pipe->buffers <= PIPE_DEF_BUFFERS)
		return 0;

	spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
	spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL);

	if (spd->pages && spd->partial)
		return 0;

	kfree(spd->pages);
	kfree(spd->partial);
	return -ENOMEM;
}

void splice_shrink_spd(struct pipe_inode_info *pipe,
		       struct splice_pipe_desc *spd)
{
	if (pipe->buffers <= PIPE_DEF_BUFFERS)
		return;

	kfree(spd->pages);
	kfree(spd->partial);
}

static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
			   struct pipe_inode_info *pipe, size_t len,
			   unsigned int flags)
{
	struct address_space *mapping = in->f_mapping;
	unsigned int loff, nr_pages, req_pages;
	struct page *pages[PIPE_DEF_BUFFERS];
	struct partial_page partial[PIPE_DEF_BUFFERS];
	struct page *page;
	pgoff_t index, end_index;
	loff_t isize;
	int error, page_nr;
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &page_cache_pipe_buf_ops,
		.spd_release = spd_release_page,
	};

	if (splice_grow_spd(pipe, &spd))
		return -ENOMEM;

	index = *ppos >> PAGE_CACHE_SHIFT;
	loff = *ppos & ~PAGE_CACHE_MASK;
	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	nr_pages = min(req_pages, pipe->buffers);

	/*
	 * Lookup the (hopefully) full range of pages we need.
	 */
	spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages);
	index += spd.nr_pages;

	/*
	 * If find_get_pages_contig() returned fewer pages than we needed,
	 * readahead/allocate the rest and fill in the holes.
	 */
	if (spd.nr_pages < nr_pages)
		page_cache_sync_readahead(mapping, &in->f_ra, in,
				index, req_pages - spd.nr_pages);

	error = 0;
	while (spd.nr_pages < nr_pages) {
		/*
		 * Page could be there, find_get_pages_contig() breaks on
		 * the first hole.
		 */
		page = find_get_page(mapping, index);
		if (!page) {
			/*
			 * page didn't exist, allocate one.
			 */
			page = page_cache_alloc_cold(mapping);
			if (!page)
				break;

			error = add_to_page_cache_lru(page, mapping, index,
						GFP_KERNEL);
			if (unlikely(error)) {
				page_cache_release(page);
				if (error == -EEXIST)
					continue;
				break;
			}
			/*
			 * add_to_page_cache() locks the page, unlock it
			 * to avoid convoluting the logic below even more.
			 */
			unlock_page(page);
		}

		spd.pages[spd.nr_pages++] = page;
		index++;
	}

	/*
	 * Now loop over the map and see if we need to start IO on any
	 * pages, fill in the partial map, etc.
	 */
	index = *ppos >> PAGE_CACHE_SHIFT;
	nr_pages = spd.nr_pages;
	spd.nr_pages = 0;
	for (page_nr = 0; page_nr < nr_pages; page_nr++) {
		unsigned int this_len;

		if (!len)
			break;

		/*
		 * this_len is the max we'll use from this page
		 */
		this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
		page = spd.pages[page_nr];

		if (PageReadahead(page))
			page_cache_async_readahead(mapping, &in->f_ra, in,
					page, index, req_pages - page_nr);

		/*
		 * If the page isn't uptodate, we may need to start io on it
		 */
		if (!PageUptodate(page)) {
			lock_page(page);

			/*
			 * Page was truncated, or invalidated by the
			 * filesystem.  Redo the find/create, but this time the
			 * page is kept locked, so there's no chance of another
			 * race with truncate/invalidate.
			 */
			if (!page->mapping) {
				unlock_page(page);
				page = find_or_create_page(mapping, index,
						mapping_gfp_mask(mapping));

				if (!page) {
					error = -ENOMEM;
					break;
				}
				page_cache_release(spd.pages[page_nr]);
				spd.pages[page_nr] = page;
			}
			/*
			 * page was already under io and is now done, great
			 */
			if (PageUptodate(page)) {
				unlock_page(page);
				goto fill_it;
			}

			/*
			 * need to read in the page
			 */
			error = mapping->a_ops->readpage(in, page);
			if (unlikely(error)) {
				/*
				 * We really should re-lookup the page here,
				 * but it complicates things a lot. Instead
				 * lets just do what we already stored, and
				 * we'll get it the next time we are called.
				 */
				if (error == AOP_TRUNCATED_PAGE)
					error = 0;

				break;
			}
		}
fill_it:
		/*
		 * i_size must be checked after PageUptodate.
		 */
		isize = i_size_read(mapping->host);
		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
		if (unlikely(!isize || index > end_index))
			break;

		/*
		 * if this is the last page, see if we need to shrink
		 * the length and stop
		 */
		if (end_index == index) {
			unsigned int plen;

			/*
			 * max good bytes in this page
			 */
			plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
			if (plen <= loff)
				break;

			/*
			 * force quit after adding this page
			 */
			this_len = min(this_len, plen - loff);
			len = this_len;
		}

		spd.partial[page_nr].offset = loff;
		spd.partial[page_nr].len = this_len;
		len -= this_len;
		loff = 0;
		spd.nr_pages++;
		index++;
	}

	/*
	 * Release any pages at the end, if we quit early. 'page_nr' is how far
	 * we got, 'nr_pages' is how many pages are in the map.
	 */
	while (page_nr < nr_pages)
		page_cache_release(spd.pages[page_nr++]);
	in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;

	if (spd.nr_pages)
		error = splice_to_pipe(pipe, &spd);

	splice_shrink_spd(pipe, &spd);
	return error;
}

/**
 * generic_file_splice_read - splice data from file to a pipe
 * @in:		file to splice from
 * @ppos:	position in @in
 * @pipe:	pipe to splice to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will read pages from given file and fill them into a pipe. Can be
 *    used as long as the address_space operations for the source implements
 *    a readpage() hook.
 *
 */
ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
				 struct pipe_inode_info *pipe, size_t len,
				 unsigned int flags)
{
	loff_t isize, left;
	int ret;

	isize = i_size_read(in->f_mapping->host);
	if (unlikely(*ppos >= isize))
		return 0;

	left = isize - *ppos;
	if (unlikely(left < len))
		len = left;

	ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
	if (ret > 0) {
		*ppos += ret;
		file_accessed(in);
	}

	return ret;
}
EXPORT_SYMBOL(generic_file_splice_read);

static const struct pipe_buf_operations default_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = generic_pipe_buf_confirm,
	.release = generic_pipe_buf_release,
	.steal = generic_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
			    unsigned long vlen, loff_t offset)
{
	mm_segment_t old_fs;
	loff_t pos = offset;
	ssize_t res;

	old_fs = get_fs();
	set_fs(get_ds());
	/* The cast to a user pointer is valid due to the set_fs() */
	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
	set_fs(old_fs);

	return res;
}

static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
			    loff_t pos)
{
	mm_segment_t old_fs;
	ssize_t res;

	old_fs = get_fs();
	set_fs(get_ds());
	/* The cast to a user pointer is valid due to the set_fs() */
	res = vfs_write(file, (const char __user *)buf, count, &pos);
	set_fs(old_fs);

	return res;
}

ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
				 struct pipe_inode_info *pipe, size_t len,
				 unsigned int flags)
{
	unsigned int nr_pages;
	unsigned int nr_freed;
	size_t offset;
	struct page *pages[PIPE_DEF_BUFFERS];
	struct partial_page partial[PIPE_DEF_BUFFERS];
	struct iovec *vec, __vec[PIPE_DEF_BUFFERS];
	ssize_t res;
	size_t this_len;
	int error;
	int i;
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &default_pipe_buf_ops,
		.spd_release = spd_release_page,
	};

	if (splice_grow_spd(pipe, &spd))
		return -ENOMEM;

	res = -ENOMEM;
	vec = __vec;
	if (pipe->buffers > PIPE_DEF_BUFFERS) {
		vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
		if (!vec)
			goto shrink_ret;
	}

	offset = *ppos & ~PAGE_CACHE_MASK;
	nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

	for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
		struct page *page;

		page = alloc_page(GFP_USER);
		error = -ENOMEM;
		if (!page)
			goto err;

		this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
		vec[i].iov_base = (void __user *) page_address(page);
		vec[i].iov_len = this_len;
		spd.pages[i] = page;
		spd.nr_pages++;
		len -= this_len;
		offset = 0;
	}

	res = kernel_readv(in, vec, spd.nr_pages, *ppos);
	if (res < 0) {
		error = res;
		goto err;
	}

	error = 0;
	if (!res)
		goto err;

	nr_freed = 0;
	for (i = 0; i < spd.nr_pages; i++) {
		this_len = min_t(size_t, vec[i].iov_len, res);
		spd.partial[i].offset = 0;
		spd.partial[i].len = this_len;
		if (!this_len) {
			__free_page(spd.pages[i]);
			spd.pages[i] = NULL;
			nr_freed++;
		}
		res -= this_len;
	}
	spd.nr_pages -= nr_freed;

	res = splice_to_pipe(pipe, &spd);
	if (res > 0)
		*ppos += res;

shrink_ret:
	if (vec != __vec)
		kfree(vec);
	splice_shrink_spd(pipe, &spd);
	return res;

err:
	for (i = 0; i < spd.nr_pages; i++)
		__free_page(spd.pages[i]);

	res = error;
	goto shrink_ret;
}
EXPORT_SYMBOL(default_file_splice_read);

/*
 * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
 * using sendpage(). Return the number of bytes sent.
 */
static int pipe_to_sendpage(struct pipe_inode_info *pipe,
			    struct pipe_buffer *buf, struct splice_desc *sd)
{
	struct file *file = sd->u.file;
	loff_t pos = sd->pos;
	int ret, more;

	ret = buf->ops->confirm(pipe, buf);
	if (!ret) {
		more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
		if (file->f_op && file->f_op->sendpage)
			ret = file->f_op->sendpage(file, buf->page, buf->offset,
						   sd->len, &pos, more);
		else
			ret = -EINVAL;
	}

	return ret;
}

/*
 * This is a little more tricky than the file -> pipe splicing. There are
 * basically three cases:
 *
 *	- Destination page already exists in the address space and there
 *	  are users of it. For that case we have no other option that
 *	  copying the data. Tough luck.
 *	- Destination page already exists in the address space, but there
 *	  are no users of it. Make sure it's uptodate, then drop it. Fall
 *	  through to last case.
 *	- Destination page does not exist, we can add the pipe page to
 *	  the page cache and avoid the copy.
 *
 * If asked to move pages to the output file (SPLICE_F_MOVE is set in
 * sd->flags), we attempt to migrate pages from the pipe to the output
 * file address space page cache. This is possible if no one else has
 * the pipe page referenced outside of the pipe and page cache. If
 * SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
 * a new page in the output file page cache and fill/dirty that.
 */
int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
		 struct splice_desc *sd)
{
	struct file *file = sd->u.file;
	struct address_space *mapping = file->f_mapping;
	unsigned int offset, this_len;
	struct page *page;
	void *fsdata;
	int ret;

	/*
	 * make sure the data in this buffer is uptodate
	 */
	ret = buf->ops->confirm(pipe, buf);
	if (unlikely(ret))
		return ret;

	offset = sd->pos & ~PAGE_CACHE_MASK;

	this_len = sd->len;
	if (this_len + offset > PAGE_CACHE_SIZE)
		this_len = PAGE_CACHE_SIZE - offset;

	ret = pagecache_write_begin(file, mapping, sd->pos, this_len,
				AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
	if (unlikely(ret))
		goto out;

	if (buf->page != page) {
		/*
		 * Careful, ->map() uses KM_USER0!
		 */
		char *src = buf->ops->map(pipe, buf, 1);
		char *dst = kmap_atomic(page, KM_USER1);

		memcpy(dst + offset, src + buf->offset, this_len);
		flush_dcache_page(page);
		kunmap_atomic(dst, KM_USER1);
		buf->ops->unmap(pipe, buf, src);
	}
	ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
				page, fsdata);
out:
	return ret;
}
EXPORT_SYMBOL(pipe_to_file);

static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
{
	smp_mb();
	if (waitqueue_active(&pipe->wait))
		wake_up_interruptible(&pipe->wait);
	kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}

/**
 * splice_from_pipe_feed - feed available data from a pipe to a file
 * @pipe:	pipe to splice from
 * @sd:		information to @actor
 * @actor:	handler that splices the data
 *
 * Description:
 *    This function loops over the pipe and calls @actor to do the
 *    actual moving of a single struct pipe_buffer to the desired
 *    destination.  It returns when there's no more buffers left in
 *    the pipe or if the requested number of bytes (@sd->total_len)
 *    have been copied.  It returns a positive number (one) if the
 *    pipe needs to be filled with more data, zero if the required
 *    number of bytes have been copied and -errno on error.
 *
 *    This, together with splice_from_pipe_{begin,end,next}, may be
 *    used to implement the functionality of __splice_from_pipe() when
 *    locking is required around copying the pipe buffers to the
 *    destination.
 */
int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
			  splice_actor *actor)
{
	int ret;

	while (pipe->nrbufs) {
		struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
		const struct pipe_buf_operations *ops = buf->ops;

		sd->len = buf->len;
		if (sd->len > sd->total_len)
			sd->len = sd->total_len;

		ret = actor(pipe, buf, sd);
		if (ret <= 0) {
			if (ret == -ENODATA)
				ret = 0;
			return ret;
		}
		buf->offset += ret;
		buf->len -= ret;

		sd->num_spliced += ret;
		sd->len -= ret;
		sd->pos += ret;
		sd->total_len -= ret;

		if (!buf->len) {
			buf->ops = NULL;
			ops->release(pipe, buf);
			pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
			pipe->nrbufs--;
			if (pipe->inode)
				sd->need_wakeup = true;
		}

		if (!sd->total_len)
			return 0;
	}

	return 1;
}
EXPORT_SYMBOL(splice_from_pipe_feed);

/**
 * splice_from_pipe_next - wait for some data to splice from
 * @pipe:	pipe to splice from
 * @sd:		information about the splice operation
 *
 * Description:
 *    This function will wait for some data and return a positive
 *    value (one) if pipe buffers are available.  It will return zero
 *    or -errno if no more data needs to be spliced.
 */
int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
	while (!pipe->nrbufs) {
		if (!pipe->writers)
			return 0;

		if (!pipe->waiting_writers && sd->num_spliced)
			return 0;

		if (sd->flags & SPLICE_F_NONBLOCK)
			return -EAGAIN;

		if (signal_pending(current))
			return -ERESTARTSYS;

		if (sd->need_wakeup) {
			wakeup_pipe_writers(pipe);
			sd->need_wakeup = false;
		}

		pipe_wait(pipe);
	}

	return 1;
}
EXPORT_SYMBOL(splice_from_pipe_next);

/**
 * splice_from_pipe_begin - start splicing from pipe
 * @sd:		information about the splice operation
 *
 * Description:
 *    This function should be called before a loop containing
 *    splice_from_pipe_next() and splice_from_pipe_feed() to
 *    initialize the necessary fields of @sd.
 */
void splice_from_pipe_begin(struct splice_desc *sd)
{
	sd->num_spliced = 0;
	sd->need_wakeup = false;
}
EXPORT_SYMBOL(splice_from_pipe_begin);

/**
 * splice_from_pipe_end - finish splicing from pipe
 * @pipe:	pipe to splice from
 * @sd:		information about the splice operation
 *
 * Description:
 *    This function will wake up pipe writers if necessary.  It should
 *    be called after a loop containing splice_from_pipe_next() and
 *    splice_from_pipe_feed().
 */
void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
	if (sd->need_wakeup)
		wakeup_pipe_writers(pipe);
}
EXPORT_SYMBOL(splice_from_pipe_end);

/**
 * __splice_from_pipe - splice data from a pipe to given actor
 * @pipe:	pipe to splice from
 * @sd:		information to @actor
 * @actor:	handler that splices the data
 *
 * Description:
 *    This function does little more than loop over the pipe and call
 *    @actor to do the actual moving of a single struct pipe_buffer to
 *    the desired destination. See pipe_to_file, pipe_to_sendpage, or
 *    pipe_to_user.
 *
 */
ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
			   splice_actor *actor)
{
	int ret;

	splice_from_pipe_begin(sd);
	do {
		ret = splice_from_pipe_next(pipe, sd);
		if (ret > 0)
			ret = splice_from_pipe_feed(pipe, sd, actor);
	} while (ret > 0);
	splice_from_pipe_end(pipe, sd);

	return sd->num_spliced ? sd->num_spliced : ret;
}
EXPORT_SYMBOL(__splice_from_pipe);

/**
 * splice_from_pipe - splice data from a pipe to a file
 * @pipe:	pipe to splice from
 * @out:	file to splice to
 * @ppos:	position in @out
 * @len:	how many bytes to splice
 * @flags:	splice modifier flags
 * @actor:	handler that splices the data
 *
 * Description:
 *    See __splice_from_pipe. This function locks the pipe inode,
 *    otherwise it's identical to __splice_from_pipe().
 *
 */
ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
			 loff_t *ppos, size_t len, unsigned int flags,
			 splice_actor *actor)
{
	ssize_t ret;
	struct splice_desc sd = {
		.total_len = len,
		.flags = flags,
		.pos = *ppos,
		.u.file = out,
	};

	pipe_lock(pipe);
	ret = __splice_from_pipe(pipe, &sd, actor);
	pipe_unlock(pipe);

	return ret;
}

/**
 * generic_file_splice_write - splice data from a pipe to a file
 * @pipe:	pipe info
 * @out:	file to write to
 * @ppos:	position in @out
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will either move or copy pages (determined by @flags options) from
 *    the given pipe inode to the given file.
 *
 */
ssize_t
generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
			  loff_t *ppos, size_t len, unsigned int flags)
{
	struct address_space *mapping = out->f_mapping;
	struct inode *inode = mapping->host;
	struct splice_desc sd = {
		.total_len = len,
		.flags = flags,
		.pos = *ppos,
		.u.file = out,
	};
	ssize_t ret;

	pipe_lock(pipe);

	splice_from_pipe_begin(&sd);
	do {
		ret = splice_from_pipe_next(pipe, &sd);
		if (ret <= 0)
			break;

		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
		ret = file_remove_suid(out);
		if (!ret) {
			file_update_time(out);
			ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file);
		}
		mutex_unlock(&inode->i_mutex);
	} while (ret > 0);
	splice_from_pipe_end(pipe, &sd);

	pipe_unlock(pipe);

	if (sd.num_spliced)
		ret = sd.num_spliced;

	if (ret > 0) {
		unsigned long nr_pages;
		int err;

		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

		err = generic_write_sync(out, *ppos, ret);
		if (err)
			ret = err;
		else
			*ppos += ret;
		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
	}

	return ret;
}

EXPORT_SYMBOL(generic_file_splice_write);

static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
			  struct splice_desc *sd)
{
	int ret;
	void *data;

	ret = buf->ops->confirm(pipe, buf);
	if (ret)
		return ret;

	data = buf->ops->map(pipe, buf, 0);
	ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
	buf->ops->unmap(pipe, buf, data);

	return ret;
}

static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
					 struct file *out, loff_t *ppos,
					 size_t len, unsigned int flags)
{
	ssize_t ret;

	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
	if (ret > 0)
		*ppos += ret;

	return ret;
}

/**
 * generic_splice_sendpage - splice data from a pipe to a socket
 * @pipe:	pipe to splice from
 * @out:	socket to write to
 * @ppos:	position in @out
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will send @len bytes from the pipe to a network socket. No data copying
 *    is involved.
 *
 */
ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
				loff_t *ppos, size_t len, unsigned int flags)
{
	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage);
}

EXPORT_SYMBOL(generic_splice_sendpage);

/*
 * Attempt to initiate a splice from pipe to file.
 */


context:
space:
mode: