[PATCH] relayfs

Here's the latest version of relayfs, against linux-2.6.11-mm2.  I'm hoping
you'll consider putting this version back into your tree - the previous
rounds of comment seem to have shaken out all the API issues and the number
of comments on the code itself have also steadily dwindled.

This patch is essentially the same as the relayfs redux part 5 patch, with
some minor changes based on reviewer comments.  Thanks again to Pekka
Enberg for those.  The patch size without documentation is now a little
smaller at just over 40k.  Here's a detailed list of the changes:

- removed the attribute_flags in relay open and changed it to a
  boolean specifying either overwrite or no-overwrite mode, and removed
  everything referencing the attribute flags.
- added a check for NULL names in relayfs_create_entry()
- got rid of the unnecessary multiple labels in relay_create_buf()
- some minor simplification of relay_alloc_buf() which got rid of a
  couple params
- updated the Documentation

In addition, this version (through code contained in the relay-apps tarball
linked to below, not as part of the relayfs patch) tries to make it as easy
as possible to create the cooperating kernel/user pieces of a typical and
common type of logging application, one where kernel logging is kicked off
when a user space data collection app starts and stops when the collection
app exits, with the data being automatically logged to disk in between.  To
create this type of application, you basically just include a header file
(relay-app.h, included in the relay-apps tarball) in your kernel module,
define a couple of callbacks and call an initialization function, and on
the user side call a single function that sets up and continuously monitors
the buffers, and writes data to files as it becomes available.  Channels
are created when the collection app is started and destroyed when it exits,
not when the kernel module is inserted, so different channel buffer sizes
can be specified for each separate run via command-line options.  See the
README in the relay-apps tarball for details.

Also included in the relay-apps tarball are a couple examples
demonstrating how you can use this to create quick and dirty kernel
logging/debugging applications.  They are:

- tprintk, short for 'tee printk', which temporarily puts a kprobe on
  printk() and writes a duplicate stream of printk output to a relayfs
  channel.  This could be used anywhere there's printk() debugging code
  in the kernel which you'd like to exercise, but would rather not have
  your system logs cluttered with debugging junk.  You'd probably want
  to kill klogd while you do this, otherwise there wouldn't be much
  point (since putting a kprobe on printk() doesn't change the output
  of printk()).  I've used this method to temporarily divert the packet
  logging output of the iptables LOG target from the system logs to
  relayfs files instead, for instance.

- klog, which just provides a printk-like formatted logging function
  on top of relayfs.  Again, you can use this to keep stuff out of your
  system logs if used in place of printk.

The example applications can be found here:

http://prdownloads.sourceforge.net/dprobes/relay-apps.tar.gz?download

From: Christoph Hellwig <hch@lst.de>

  avoid lookup_hash usage in relayfs

Signed-off-by: Tom Zanussi <zanussi@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 189 insertions, 0 deletions

diff --git a/fs/relayfs/buffers.c b/fs/relayfs/buffers.c
new file mode 100644
index 000000000000..2aa8e2719999
--- /dev/null
+++ b/fs/relayfs/buffers.c
@@ -0,0 +1,189 @@
+/*
+ * RelayFS buffer management code.
+ *
+ * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp
+ * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com)
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/relayfs_fs.h>
+#include "relay.h"
+#include "buffers.h"
+
+/*
+ * close() vm_op implementation for relayfs file mapping.
+ */
+static void relay_file_mmap_close(struct vm_area_struct *vma)
+{
+	struct rchan_buf *buf = vma->vm_private_data;
+	buf->chan->cb->buf_unmapped(buf, vma->vm_file);
+}
+
+/*
+ * nopage() vm_op implementation for relayfs file mapping.
+ */
+static struct page *relay_buf_nopage(struct vm_area_struct *vma,
+				     unsigned long address,
+				     int *type)
+{
+	struct page *page;
+	struct rchan_buf *buf = vma->vm_private_data;
+	unsigned long offset = address - vma->vm_start;
+
+	if (address > vma->vm_end)
+		return NOPAGE_SIGBUS; /* Disallow mremap */
+	if (!buf)
+		return NOPAGE_OOM;
+
+	page = vmalloc_to_page(buf->start + offset);
+	if (!page)
+		return NOPAGE_OOM;
+	get_page(page);
+
+	if (type)
+		*type = VM_FAULT_MINOR;
+
+	return page;
+}
+
+/*
+ * vm_ops for relay file mappings.
+ */
+static struct vm_operations_struct relay_file_mmap_ops = {
+	.nopage = relay_buf_nopage,
+	.close = relay_file_mmap_close,
+};
+
+/**
+ *	relay_mmap_buf: - mmap channel buffer to process address space
+ *	@buf: relay channel buffer
+ *	@vma: vm_area_struct describing memory to be mapped
+ *
+ *	Returns 0 if ok, negative on error
+ *
+ *	Caller should already have grabbed mmap_sem.
+ */
+int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
+{
+	unsigned long length = vma->vm_end - vma->vm_start;
+	struct file *filp = vma->vm_file;
+
+	if (!buf)
+		return -EBADF;
+
+	if (length != (unsigned long)buf->chan->alloc_size)
+		return -EINVAL;
+
+	vma->vm_ops = &relay_file_mmap_ops;
+	vma->vm_private_data = buf;
+	buf->chan->cb->buf_mapped(buf, filp);
+
+	return 0;
+}
+
+/**
+ *	relay_alloc_buf - allocate a channel buffer
+ *	@buf: the buffer struct
+ *	@size: total size of the buffer
+ *
+ *	Returns a pointer to the resulting buffer, NULL if unsuccessful
+ */
+static void *relay_alloc_buf(struct rchan_buf *buf, unsigned long size)
+{
+	void *mem;
+	unsigned int i, j, n_pages;
+
+	size = PAGE_ALIGN(size);
+	n_pages = size >> PAGE_SHIFT;
+
+	buf->page_array = kcalloc(n_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!buf->page_array)
+		return NULL;
+
+	for (i = 0; i < n_pages; i++) {
+		buf->page_array[i] = alloc_page(GFP_KERNEL);
+		if (unlikely(!buf->page_array[i]))
+			goto depopulate;
+	}
+	mem = vmap(buf->page_array, n_pages, GFP_KERNEL, PAGE_KERNEL);
+	if (!mem)
+		goto depopulate;
+
+	memset(mem, 0, size);
+	buf->page_count = n_pages;
+	return mem;
+
+depopulate:
+	for (j = 0; j < i; j++)
+		__free_page(buf->page_array[j]);
+	kfree(buf->page_array);
+	return NULL;
+}
+
+/**
+ *	relay_create_buf - allocate and initialize a channel buffer
+ *	@alloc_size: size of the buffer to allocate
+ *	@n_subbufs: number of sub-buffers in the channel
+ *
+ *	Returns channel buffer if successful, NULL otherwise
+ */
+struct rchan_buf *relay_create_buf(struct rchan *chan)
+{
+	struct rchan_buf *buf = kcalloc(1, sizeof(struct rchan_buf), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL);
+	if (!buf->padding)
+		goto free_buf;
+
+	buf->start = relay_alloc_buf(buf, chan->alloc_size);
+	if (!buf->start)
+		goto free_buf;
+
+	buf->chan = chan;
+	kref_get(&buf->chan->kref);
+	return buf;
+
+free_buf:
+	kfree(buf->padding);
+	kfree(buf);
+	return NULL;
+}
+
+/**
+ *	relay_destroy_buf - destroy an rchan_buf struct and associated buffer
+ *	@buf: the buffer struct
+ */
+void relay_destroy_buf(struct rchan_buf *buf)
+{
+	struct rchan *chan = buf->chan;
+	unsigned int i;
+
+	if (likely(buf->start)) {
+		vunmap(buf->start);
+		for (i = 0; i < buf->page_count; i++)
+			__free_page(buf->page_array[i]);
+		kfree(buf->page_array);
+	}
+	kfree(buf->padding);
+	kfree(buf);
+	kref_put(&chan->kref, relay_destroy_channel);
+}
+
+/**
+ *	relay_remove_buf - remove a channel buffer
+ *
+ *	Removes the file from the relayfs fileystem, which also frees the
+ *	rchan_buf_struct and the channel buffer.  Should only be called from
+ *	kref_put().
+ */
+void relay_remove_buf(struct kref *kref)
+{
+	struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref);
+	relayfs_remove(buf->dentry);
+}