[PATCH] relay: migrate from relayfs to a generic relay API

Original patch from Paul Mundt, sysfs parts removed by me since they
were broken.
Signed-off-by: Jens Axboe <axboe@suse.de>

fs/Kconfig

@@ -859,18 +859,6 @@ config RAMFS
 	  To compile this as a module, choose M here: the module will be called
 	  ramfs.
 
-config RELAYFS_FS
-	tristate "Relayfs file system support"
-	---help---
-	  Relayfs is a high-speed data relay filesystem designed to provide
-	  an efficient mechanism for tools and facilities to relay large
-	  amounts of data from kernel space to user space.
-
-	  To compile this code as a module, choose M here: the module will be
-	  called relayfs.
-
-	  If unsure, say N.
-
 config CONFIGFS_FS
 	tristate "Userspace-driven configuration filesystem (EXPERIMENTAL)"
 	depends on EXPERIMENTAL

fs/Makefile

@@ -91,7 +91,6 @@ obj-$(CONFIG_AUTOFS4_FS)	+= autofs4/
 obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)		+= fuse/
 obj-$(CONFIG_UDF_FS)		+= udf/
-obj-$(CONFIG_RELAYFS_FS)	+= relayfs/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_JFS_FS)		+= jfs/
 obj-$(CONFIG_XFS_FS)		+= xfs/

fs/relayfs/Makefile

-obj-$(CONFIG_RELAYFS_FS) += relayfs.o
-
-relayfs-y := relay.o inode.o buffers.o
-

fs/relayfs/buffers.c

-/*
- * 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, VM_MAP, 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);
-	buf->chan->cb->remove_buf_file(buf->dentry);
-	relay_destroy_buf(buf);
-}

fs/relayfs/buffers.h

-#ifndef _BUFFERS_H
-#define _BUFFERS_H
-
-/* This inspired by rtai/shmem */
-#define FIX_SIZE(x) (((x) - 1) & PAGE_MASK) + PAGE_SIZE
-
-extern int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma);
-extern struct rchan_buf *relay_create_buf(struct rchan *chan);
-extern void relay_destroy_buf(struct rchan_buf *buf);
-extern void relay_remove_buf(struct kref *kref);
-
-#endif/* _BUFFERS_H */

fs/relayfs/relay.h

-#ifndef _RELAY_H
-#define _RELAY_H
-
-extern int relayfs_remove(struct dentry *dentry);
-extern int relay_buf_empty(struct rchan_buf *buf);
-extern void relay_destroy_channel(struct kref *kref);
-
-#endif /* _RELAY_H */

include/linux/relay.h

+/*
+ * linux/include/linux/relay.h
+ *
+ * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp
+ * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com)
+ *
+ * CONFIG_RELAY definitions and declarations
+ */
+
+#ifndef _LINUX_RELAY_H
+#define _LINUX_RELAY_H
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/kref.h>
+
+/* Needs a _much_ better name... */
+#define FIX_SIZE(x) ((((x) - 1) & PAGE_MASK) + PAGE_SIZE)
+
+/*
+ * Tracks changes to rchan/rchan_buf structs
+ */
+#define RELAYFS_CHANNEL_VERSION		6
+
+/*
+ * Per-cpu relay channel buffer
+ */
+struct rchan_buf
+{
+	void *start;			/* start of channel buffer */
+	void *data;			/* start of current sub-buffer */
+	size_t offset;			/* current offset into sub-buffer */
+	size_t subbufs_produced;	/* count of sub-buffers produced */
+	size_t subbufs_consumed;	/* count of sub-buffers consumed */
+	struct rchan *chan;		/* associated channel */
+	wait_queue_head_t read_wait;	/* reader wait queue */
+	struct work_struct wake_readers; /* reader wake-up work struct */
+	struct dentry *dentry;		/* channel file dentry */
+	struct kref kref;		/* channel buffer refcount */
+	struct page **page_array;	/* array of current buffer pages */
+	unsigned int page_count;	/* number of current buffer pages */
+	unsigned int finalized;		/* buffer has been finalized */
+	size_t *padding;		/* padding counts per sub-buffer */
+	size_t prev_padding;		/* temporary variable */
+	size_t bytes_consumed;		/* bytes consumed in cur read subbuf */
+	unsigned int cpu;		/* this buf's cpu */
+} ____cacheline_aligned;
+
+/*
+ * Relay channel data structure
+ */
+struct rchan
+{
+	u32 version;			/* the version of this struct */
+	size_t subbuf_size;		/* sub-buffer size */
+	size_t n_subbufs;		/* number of sub-buffers per buffer */
+	size_t alloc_size;		/* total buffer size allocated */
+	struct rchan_callbacks *cb;	/* client callbacks */
+	struct kref kref;		/* channel refcount */
+	void *private_data;		/* for user-defined data */
+	size_t last_toobig;		/* tried to log event > subbuf size */
+	struct rchan_buf *buf[NR_CPUS]; /* per-cpu channel buffers */
+};
+
+/*
+ * Relay channel client callbacks
+ */
+struct rchan_callbacks
+{
+	/*
+	 * subbuf_start - called on buffer-switch to a new sub-buffer
+	 * @buf: the channel buffer containing the new sub-buffer
+	 * @subbuf: the start of the new sub-buffer
+	 * @prev_subbuf: the start of the previous sub-buffer
+	 * @prev_padding: unused space at the end of previous sub-buffer
+	 *
+	 * The client should return 1 to continue logging, 0 to stop
+	 * logging.
+	 *
+	 * NOTE: subbuf_start will also be invoked when the buffer is
+	 *       created, so that the first sub-buffer can be initialized
+	 *       if necessary.  In this case, prev_subbuf will be NULL.
+	 *
+	 * NOTE: the client can reserve bytes at the beginning of the new
+	 *       sub-buffer by calling subbuf_start_reserve() in this callback.
+	 */
+	int (*subbuf_start) (struct rchan_buf *buf,
+			     void *subbuf,
+			     void *prev_subbuf,
+			     size_t prev_padding);
+
+	/*
+	 * buf_mapped - relay buffer mmap notification
+	 * @buf: the channel buffer
+	 * @filp: relay file pointer
+	 *
+	 * Called when a relay file is successfully mmapped
+	 */
+        void (*buf_mapped)(struct rchan_buf *buf,
+			   struct file *filp);
+
+	/*
+	 * buf_unmapped - relay buffer unmap notification
+	 * @buf: the channel buffer
+	 * @filp: relay file pointer
+	 *
+	 * Called when a relay file is successfully unmapped
+	 */
+        void (*buf_unmapped)(struct rchan_buf *buf,
+			     struct file *filp);
+	/*
+	 * create_buf_file - create file to represent a relay channel buffer
+	 * @filename: the name of the file to create
+	 * @parent: the parent of the file to create
+	 * @mode: the mode of the file to create
+	 * @buf: the channel buffer
+	 * @is_global: outparam - set non-zero if the buffer should be global
+	 *
+	 * Called during relay_open(), once for each per-cpu buffer,
+	 * to allow the client to create a file to be used to
+	 * represent the corresponding channel buffer.  If the file is
+	 * created outside of relay, the parent must also exist in
+	 * that filesystem.
+	 *
+	 * The callback should return the dentry of the file created
+	 * to represent the relay buffer.
+	 *
+	 * Setting the is_global outparam to a non-zero value will
+	 * cause relay_open() to create a single global buffer rather
+	 * than the default set of per-cpu buffers.
+	 *
+	 * See Documentation/filesystems/relayfs.txt for more info.
+	 */
+	struct dentry *(*create_buf_file)(const char *filename,
+					  struct dentry *parent,
+					  int mode,
+					  struct rchan_buf *buf,
+					  int *is_global);
+
+	/*
+	 * remove_buf_file - remove file representing a relay channel buffer
+	 * @dentry: the dentry of the file to remove
+	 *
+	 * Called during relay_close(), once for each per-cpu buffer,
+	 * to allow the client to remove a file used to represent a
+	 * channel buffer.
+	 *
+	 * The callback should return 0 if successful, negative if not.
+	 */
+	int (*remove_buf_file)(struct dentry *dentry);
+};
+
+/*
+ * CONFIG_RELAY kernel API, kernel/relay.c
+ */
+
+struct rchan *relay_open(const char *base_filename,
+			 struct dentry *parent,
+			 size_t subbuf_size,
+			 size_t n_subbufs,
+			 struct rchan_callbacks *cb);
+extern void relay_close(struct rchan *chan);
+extern void relay_flush(struct rchan *chan);
+extern void relay_subbufs_consumed(struct rchan *chan,
+				   unsigned int cpu,
+				   size_t consumed);
+extern void relay_reset(struct rchan *chan);
+extern int relay_buf_full(struct rchan_buf *buf);
+
+extern size_t relay_switch_subbuf(struct rchan_buf *buf,
+				  size_t length);
+
+/**
+ *	relay_write - write data into the channel
+ *	@chan: relay channel
+ *	@data: data to be written
+ *	@length: number of bytes to write
+ *
+ *	Writes data into the current cpu's channel buffer.
+ *
+ *	Protects the buffer by disabling interrupts.  Use this
+ *	if you might be logging from interrupt context.  Try
+ *	__relay_write() if you know you	won't be logging from
+ *	interrupt context.
+ */
+static inline void relay_write(struct rchan *chan,
+			       const void *data,
+			       size_t length)
+{
+	unsigned long flags;
+	struct rchan_buf *buf;
+
+	local_irq_save(flags);
+	buf = chan->buf[smp_processor_id()];
+	if (unlikely(buf->offset + length > chan->subbuf_size))
+		length = relay_switch_subbuf(buf, length);
+	memcpy(buf->data + buf->offset, data, length);
+	buf->offset += length;
+	local_irq_restore(flags);
+}
+
+/**
+ *	__relay_write - write data into the channel
+ *	@chan: relay channel
+ *	@data: data to be written
+ *	@length: number of bytes to write
+ *
+ *	Writes data into the current cpu's channel buffer.
+ *
+ *	Protects the buffer by disabling preemption.  Use
+ *	relay_write() if you might be logging from interrupt
+ *	context.
+ */
+static inline void __relay_write(struct rchan *chan,
+				 const void *data,
+				 size_t length)
+{
+	struct rchan_buf *buf;
+
+	buf = chan->buf[get_cpu()];
+	if (unlikely(buf->offset + length > buf->chan->subbuf_size))
+		length = relay_switch_subbuf(buf, length);
+	memcpy(buf->data + buf->offset, data, length);
+	buf->offset += length;
+	put_cpu();
+}
+
+/**
+ *	relay_reserve - reserve slot in channel buffer
+ *	@chan: relay channel
+ *	@length: number of bytes to reserve
+ *
+ *	Returns pointer to reserved slot, NULL if full.
+ *
+ *	Reserves a slot in the current cpu's channel buffer.
+ *	Does not protect the buffer at all - caller must provide
+ *	appropriate synchronization.
+ */
+static inline void *relay_reserve(struct rchan *chan, size_t length)
+{
+	void *reserved;
+	struct rchan_buf *buf = chan->buf[smp_processor_id()];
+
+	if (unlikely(buf->offset + length > buf->chan->subbuf_size)) {
+		length = relay_switch_subbuf(buf, length);
+		if (!length)
+			return NULL;
+	}
+	reserved = buf->data + buf->offset;
+	buf->offset += length;
+
+	return reserved;
+}
+
+/**
+ *	subbuf_start_reserve - reserve bytes at the start of a sub-buffer
+ *	@buf: relay channel buffer
+ *	@length: number of bytes to reserve
+ *
+ *	Helper function used to reserve bytes at the beginning of
+ *	a sub-buffer in the subbuf_start() callback.
+ */
+static inline void subbuf_start_reserve(struct rchan_buf *buf,
+					size_t length)
+{
+	BUG_ON(length >= buf->chan->subbuf_size - 1);
+	buf->offset = length;
+}
+
+/*
+ * exported relay file operations, kernel/relay.c
+ */
+extern struct file_operations relay_file_operations;
+
+#endif /* _LINUX_RELAY_H */
+

init/Kconfig

@@ -214,6 +214,17 @@ config CPUSETS
 
 	  Say N if unsure.
 
+config RELAY
+	bool "Kernel->user space relay support (formerly relayfs)"
+	help
+	  This option enables support for relay interface support in
+	  certain file systems (such as debugfs).
+	  It is designed to provide an efficient mechanism for tools and
+	  facilities to relay large amounts of data from kernel space to
+	  user space.
+
+	  If unsure, say N.
+
 source "usr/Kconfig"
 
 config UID16

kernel/Makefile

@@ -34,6 +34,7 @@ obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
+obj-$(CONFIG_RELAY) += relay.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is