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/stackcollapse.py

diff options

Diffstat (limited to 'tools/perf/scripts/python/stackcollapse.py')

0 files changed, 0 insertions, 0 deletions

.de> 2006-03-30 08:16:46 -0500 committer Linus Torvalds <torvalds@g5.osdl.org> 2006-03-30 15:28:18 -0500 [PATCH] splice: add support for SPLICE_F_MOVE flag' href='/cgit/cgit.cgi/litmus-rt-imx6.git/commit/fs/splice.c?id=5abc97aa25b2c41413b3a520faee83f2282d9f18'>5abc97aa25b2

12
13

16
17

26
27

46
47

55
56
57

60
61

62
63
64

95
96

98
99
100

102
103

106
107

109
110

134
135

137
138

140
141

144
145
146

150
151

152
153
154

155
156
157

160
161

164
165
166

167
168

170
171

176
177

180
181
182

185
186

196
197

204
205
206

208
209
210

211
212

236
237
238

239
240
241

242
243
244

245
246

247
248

249
250

252
253
254

255
256

257
258

264
265
266

267
268

273
274

285
286

292
293

296
297

315
316

318
319
320

335
336

337
338

339
340

346
347

414
415

416
417

435
436
437

444
445

449
450

451
452

464
465

475
476
477

510
511

524
525

527
528
529

563
564

568
569

616
617
618

637
638

652
653
654

660
661
662

676
677

702
703

709
710

738
739
740

741
742
743

745
746

749
750
751

752
753

800
801
802

825
826

836
837

843
844

846
847

868
869
870

871
872
873

874
875

876
877

893
894

897
898
899

903
904

906
907

909
910

912
913
914

916
917

918
919
920

921
922
923

926
927

929
930

932
933

940
941

944
945

947
948

949
950

951
952
953

989
990
991

1077
1078

1079
1080
1081

1088
1089
1090

1091
1092
1093

1096
1097
1098

1109
1110
1111

1112
1113
1114

1117
1118
1119

1284
1285

1286
1287
1288

1311
1312
1313

1324
1325

1327
1328

1329
1330
1331

1341
1342

1453
1454

1455
1456

1457
1458

1466
1467

1471
1472

1504
1505

1507
1508

1509
1510

/*
 * "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/pipe_fs_i.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>

struct partial_page {
	unsigned int offset;
	unsigned int len;
};

/*
 * Passed to splice_to_pipe
 */
struct splice_pipe_desc {
	struct page **pages;		/* page map */
	struct partial_page *partial;	/* pages[] may not be contig */
	int nr_pages;			/* number of pages in map */
	unsigned int flags;		/* splice flags */
	const struct pipe_buf_operations *ops;/* ops associated with output pipe */
};

/*
 * 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 (PagePrivate(page))
			try_to_release_page(page, GFP_KERNEL);

		/*
		 * 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.
	 */
	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;
}

static int page_cache_pipe_buf_pin(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,
	.pin = page_cache_pipe_buf_pin,
	.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,
	.pin = generic_pipe_buf_pin,
	.release = page_cache_pipe_buf_release,
	.steal = user_page_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

/*
 * Pipe output worker. This sets up our pipe format with the page cache
 * pipe buffer operations. Otherwise very similar to the regular pipe_writev().
 */
static ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
			      struct splice_pipe_desc *spd)
{
	int ret, do_wakeup, page_nr;

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

	if (pipe->inode)
		mutex_lock(&pipe->inode->i_mutex);

	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->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--;
	}

	if (pipe->inode)
		mutex_unlock(&pipe->inode->i_mutex);

	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->nr_pages)
		page_cache_release(spd->pages[page_nr++]);

	return ret;
}

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;
	struct page *pages[PIPE_BUFFERS];
	struct partial_page partial[PIPE_BUFFERS];
	struct page *page;
	pgoff_t index, end_index;
	loff_t isize;
	size_t total_len;
	int error, page_nr;
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &page_cache_pipe_buf_ops,
	};

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

	if (nr_pages > PIPE_BUFFERS)
		nr_pages = PIPE_BUFFERS;

	/*
	 * Don't try to 2nd guess the read-ahead logic, call into
	 * page_cache_readahead() like the page cache reads would do.
	 */
	page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);

	/*
	 * Now fill in the holes:
	 */
	error = 0;
	total_len = 0;

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

	/*
	 * If find_get_pages_contig() returned fewer pages than we needed,
	 * allocate the rest.
	 */
	index += spd.nr_pages;
	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) {
			/*
			 * Make sure the read-ahead engine is notified
			 * about this failure.
			 */
			handle_ra_miss(mapping, &in->f_ra, index);

			/*
			 * 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);
		}

		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 = pages[page_nr];

		/*
		 * If the page isn't uptodate, we may need to start io on it
		 */
		if (!PageUptodate(page)) {
			/*
			 * If in nonblock mode then dont block on waiting
			 * for an in-flight io page
			 */
			if (flags & SPLICE_F_NONBLOCK) {
				if (TestSetPageLocked(page))
					break;
			} else
				lock_page(page);

			/*
			 * page was truncated, stop here. if this isn't the
			 * first page, we'll just complete what we already
			 * added
			 */
			if (!page->mapping) {
				unlock_page(page);
				break;
			}
			/*
			 * 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;
			}

			/*
			 * i_size must be checked after ->readpage().
			 */
			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) {
				loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK);
				if (total_len + loff > isize)
					break;
				/*
				 * force quit after adding this page
				 */
				len = this_len;
				this_len = min(this_len, loff);
				loff = 0;
			}
		}
fill_it:
		partial[page_nr].offset = loff;
		partial[page_nr].len = this_len;
		len -= this_len;
		total_len += this_len;
		loff = 0;
		spd.nr_pages++;
		index++;
	}

	/*
	 * Release any pages at the end, if we quit early. 'i' is how far
	 * we got, 'nr_pages' is how many pages are in the map.
	 */
	while (page_nr < nr_pages)
		page_cache_release(pages[page_nr++]);

	if (spd.nr_pages)
		return splice_to_pipe(pipe, &spd);

	return error;
}

/**
 * generic_file_splice_read - splice data from file to a pipe
 * @in:		file to splice from
 * @pipe:	pipe to splice to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Will read pages from given file and fill them into a pipe.
 */
ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
				 struct pipe_inode_info *pipe, size_t len,
				 unsigned int flags)
{
	ssize_t spliced;
	int ret;

	ret = 0;
	spliced = 0;

	while (len) {
		ret = __generic_file_splice_read(in, ppos, pipe, len, flags);

		if (ret < 0)
			break;
		else if (!ret) {
			if (spliced)
				break;
			if (flags & SPLICE_F_NONBLOCK) {
				ret = -EAGAIN;
				break;
			}
		}

		*ppos += ret;
		len -= ret;
		spliced += ret;
	}

	if (spliced)
		return spliced;

	return ret;
}

EXPORT_SYMBOL(generic_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->file;
	loff_t pos = sd->pos;
	int ret, more;

	ret = buf->ops->pin(pipe, buf);
	if (!ret) {
		more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;

		ret = file->f_op->sendpage(file, buf->page, buf->offset,
					   sd->len, &pos, more);
	}

	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.
 */
static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
			struct splice_desc *sd)
{
	struct file *file = sd->file;
	struct address_space *mapping = file->f_mapping;
	unsigned int offset, this_len;
	struct page *page;
	pgoff_t index;
	int ret;

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

	index = sd->pos >> PAGE_CACHE_SHIFT;
	offset = sd->pos & ~PAGE_CACHE_MASK;

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

find_page:
	page = find_lock_page(mapping, index);
	if (!page) {
		ret = -ENOMEM;
		page = page_cache_alloc_cold(mapping);
		if (unlikely(!page))
			goto out_ret;

		/*
		 * This will also lock the page
		 */
		ret = add_to_page_cache_lru(page, mapping, index,
					    GFP_KERNEL);
		if (unlikely(ret))
			goto out;
	}

	ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
	if (unlikely(ret)) {
		loff_t isize = i_size_read(mapping->host);

		if (ret != AOP_TRUNCATED_PAGE)
			unlock_page(page);
		page_cache_release(page);
		if (ret == AOP_TRUNCATED_PAGE)
			goto find_page;

		/*
		 * prepare_write() may have instantiated a few blocks
		 * outside i_size.  Trim these off again.
		 */
		if (sd->pos + this_len > isize)
			vmtruncate(mapping->host, isize);

		goto out_ret;
	}

	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 = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
	if (ret) {
		if (ret == AOP_TRUNCATED_PAGE) {
			page_cache_release(page);
			goto find_page;
		}
		if (ret < 0)
			goto out;
		/*
		 * Partial write has happened, so 'ret' already initialized by
		 * number of bytes written, Where is nothing we have to do here.
		 */
	} else
		ret = this_len;
	/*
	 * Return the number of bytes written and mark page as
	 * accessed, we are now done!
	 */
	mark_page_accessed(page);
	balance_dirty_pages_ratelimited(mapping);
out:
	page_cache_release(page);
	unlock_page(page);
out_ret:
	return ret;
}

/*
 * Pipe input worker. Most of this logic works like a regular pipe, the
 * key here is the 'actor' worker passed in that actually moves the data
 * to the wanted destination. See pipe_to_file/pipe_to_sendpage above.
 */
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)
{
	int ret, do_wakeup, err;
	struct splice_desc sd;

	ret = 0;
	do_wakeup = 0;

	sd.total_len = len;
	sd.flags = flags;
	sd.file = out;
	sd.pos = *ppos;

	for (;;) {
		if (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;

			err = actor(pipe, buf, &sd);
			if (err <= 0) {
				if (!ret && err != -ENODATA)
					ret = err;

				break;
			}

			ret += err;
			buf->offset += err;
			buf->len -= err;

			sd.len -= err;
			sd.pos += err;
			sd.total_len -= err;
			if (sd.len)
				continue;

			if (!buf->len) {
				buf->ops = NULL;
				ops->release(pipe, buf);
				pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
				pipe->nrbufs--;
				if (pipe->inode)
					do_wakeup = 1;
			}

			if (!sd.total_len)
				break;
		}

		if (pipe->nrbufs)
			continue;
		if (!pipe->writers)
			break;
		if (!pipe->waiting_writers) {
			if (ret)
				break;
		}

		if (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_writers, SIGIO, POLL_OUT);
			do_wakeup = 0;
		}

		pipe_wait(pipe);
	}

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

	return ret;
}
EXPORT_SYMBOL(__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 inode *inode = out->f_mapping->host;

	/*
	 * The actor worker might be calling ->prepare_write and
	 * ->commit_write. Most of the time, these expect i_mutex to
	 * be held. Since this may result in an ABBA deadlock with
	 * pipe->inode, we have to order lock acquiry here.
	 */
	inode_double_lock(inode, pipe->inode);
	ret = __splice_from_pipe(pipe, out, ppos, len, flags, actor);
	inode_double_unlock(inode, pipe->inode);

	return ret;
}

/**
 * generic_file_splice_write_nolock - generic_file_splice_write without mutexes
 * @pipe:	pipe info
 * @out:	file to write to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Will either move or copy pages (determined by @flags options) from
 * the given pipe inode to the given file. The caller is responsible
 * for acquiring i_mutex on both inodes.
 *
 */
ssize_t
generic_file_splice_write_nolock(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;
	ssize_t ret;
	int err;

	err = remove_suid(out->f_path.dentry);


context:
space:
mode: