relay: Add buffer-only channels; useful for early logging.

kernel/relay.c +5 -2

@@ -578,12 +592,15 @@ struct rchan *relay_open(const char *base_filename,
 	chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs);
 	chan->parent = parent;
 	chan->private_data = private_data;
-	strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	if (base_filename) {
+		chan->has_base_filename = 1;
+		strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	}
 	setup_callbacks(chan, cb);
 	kref_init(&chan->kref);
 
 	mutex_lock(&relay_channels_mutex);
-	for_each_online_cpu(i) {
+	for_each_present_cpu(i) {
 		chan->buf[i] = relay_open_buf(chan, i);
 		if (!chan->buf[i])
 			goto free_bufs;

Why do we need to change for_each_online_cpu to for_each_present_cpu? I guess it's because we don't have all the CPUs online at early boot?

Wouldn't it then be better to implement CPU hotplug support instead?

Quoted 3 lines · On Fri, 13 Jun 2008 10:04:57 +0300 Pekka Enberg <[email protected]> wrote:

Why do we need to change for_each_online_cpu to for_each_present_cpu? I guess it's because we don't have all the CPUs online at early boot?

Yes, that's true. Only one CPU is online at that early point.

Quoted 2 lines

Wouldn't it then be better to implement CPU hotplug support instead?

It's difficult for me to write such code, as I'm unable to test CPU hotplug; my machines are a Turion X2 laptop and a Athlon Barton desktop computer. So I can't turn off, or unplug in a software sense, one CPU core. Correct me if I'm wrong, but I don't see any way to do that in /sys/devices/system/cpu/

But I suppose I could write a patch very carefully, and then submit to someone that can test this. Anyway, I'll look into this and try to understand the code without being able to test.

Eduard

If you need to "emulate" having many CPUs, Xen is always an option.

Hrm, sounds like a bad idea... please try getting a test setup working, it will save you a gazillion iterations and let you stress-test your code.

Quoted 1 line · On Mon, 16 Jun 2008 08:30:03 -0400 Mathieu Desnoyers…

If you need to "emulate" having many CPUs, Xen is always an option.

I'd rather set up a QEMU environment than rebase this on Xen.

Quoted 3 lines

Hrm, sounds like a bad idea... please try getting a test setup working, it will save you a gazillion iterations and let you stress-test your code.

Check your mailbox, I resubmitted the buffer-only channels along with hotplug fixes. I couldn't test on my machine all hotplug has to offer, but hotplug does create the buffers correctly when the kernel goes SMP.

Eduard

Allows one to create and use a channel with no associated files. Files can be initialized later. This is useful in scenarios such as logging in early code, before VFS is up. Therefore, such channels can be created and used as soon as kmem_cache_init() completed.

Signed-off-by Eduard - Gabriel Munteanu <[email protected]>

---
 Documentation/filesystems/relay.txt |   11 +++
 include/linux/relay.h               |    5 ++
 kernel/relay.c                      |  123 ++++++++++++++++++++++++++---------
 3 files changed, 107 insertions(+), 32 deletions(-)

Documentation/filesystems/relay.txt +11 -0

index 094f2d2..b417f83 100644
@@ -161,6 +161,7 @@ TBD(curr. line MT:/API/)
     relay_close(chan)
     relay_flush(chan)
     relay_reset(chan)
+    relay_late_setup_files(chan, base_filename, parent)
 
   channel management typically called on instigation of userspace:
 

@@ -294,6 +295,16 @@ user-defined data with a channel, and is immediately available
 (including in create_buf_file()) via chan->private_data or
 buf->chan->private_data.
 
+Buffer-only channels
+--------------------
+
+These channels have no files associated and can be created with
+relay_open(NULL, NULL, ...). Such channels are useful in scenarios such
+as when doing early tracing in the kernel, before the VFS is up. In these
+cases, one may open a buffer-only channel and then call 
+relay_late_setup_files() when the kernel is ready to handle files,
+to expose the buffered data to the userspace.
+
 Channel 'modes'
 ---------------
 

include/linux/relay.h +5 -0

index a3a03e7..1d3dcf8 100644
@@ -49,6 +49,7 @@ struct rchan_buf
 	size_t *padding;		/* padding counts per sub-buffer */
 	size_t prev_padding;		/* temporary variable */
 	size_t bytes_consumed;		/* bytes consumed in cur read subbuf */
+	size_t early_bytes;		/* bytes consumed before VFS inited */
 	unsigned int cpu;		/* this buf's cpu */
 } ____cacheline_aligned;
 

@@ -69,6 +70,7 @@ struct rchan
 	int is_global;			/* One global buffer ? */
 	struct list_head list;		/* for channel list */
 	struct dentry *parent;		/* parent dentry passed to open */
+	int has_base_filename;		/* has a filename associated? */
 	char base_filename[NAME_MAX];	/* saved base filename */
 };
 

@@ -170,6 +172,9 @@ struct rchan *relay_open(const char *base_filename,
 			 size_t n_subbufs,
 			 struct rchan_callbacks *cb,
 			 void *private_data);
+extern int relay_late_setup_files(struct rchan *chan,
+				  const char *base_filename,
+				  struct dentry *parent);
 extern void relay_close(struct rchan *chan);
 extern void relay_flush(struct rchan *chan);
 extern void relay_subbufs_consumed(struct rchan *chan,

kernel/relay.c +91 -32

index 250a27a..a544172 100644
@@ -407,6 +407,39 @@ void relay_reset(struct rchan *chan)
 }
 EXPORT_SYMBOL_GPL(relay_reset);
 
+static int relay_setup_buf_file(struct rchan *chan,
+				struct rchan_buf *buf,
+				unsigned int cpu)
+{
+	struct dentry *dentry;
+	unsigned long flags;
+	char *tmpname;
+
+	tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
+	if (!tmpname)
+		goto failed;
+	snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
+
+	/* Create file in fs */
+	dentry = chan->cb->create_buf_file(tmpname, chan->parent,
+					   S_IRUSR, buf,
+					   &chan->is_global);
+
+	kfree(tmpname);
+
+	if (!dentry)
+		goto failed;
+	spin_lock_irqsave(&buf->rw_lock, flags);
+	buf->dentry = dentry;
+	buf->dentry->d_inode->i_size = buf->early_bytes;
+	spin_unlock_irqrestore(&buf->rw_lock, flags);
+
+	return 0;
+
+failed:
+	return 1;
+}
+
 /*
  *	relay_open_buf - create a new relay channel buffer
  *

@@ -415,48 +448,31 @@ EXPORT_SYMBOL_GPL(relay_reset);
 static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 {
  	struct rchan_buf *buf = NULL;
-	struct dentry *dentry;
- 	char *tmpname;
 
  	if (chan->is_global)
 		return chan->buf[0];
 
-	tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
- 	if (!tmpname)
- 		goto end;
- 	snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
-
 	buf = relay_create_buf(chan);
 	if (!buf)
- 		goto free_name;
+		return NULL;
 
-	spin_lock_init(&buf->rw_lock);
+	if (chan->has_base_filename)
+		if (relay_setup_buf_file(chan, buf, cpu))
+			goto free_buf;
 
  	buf->cpu = cpu;
  	__relay_reset(buf, 1);
 
-	/* Create file in fs */
- 	dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR,
- 					   buf, &chan->is_global);
- 	if (!dentry)
- 		goto free_buf;
-
-	buf->dentry = dentry;
-
  	if(chan->is_global) {
  		chan->buf[0] = buf;
  		buf->cpu = 0;
   	}
 
- 	goto free_name;
+	return buf;
 
 free_buf:
  	relay_destroy_buf(buf);
- 	buf = NULL;
-free_name:
- 	kfree(tmpname);
-end:
-	return buf;
+	return NULL;
 }
 
 /**

@@ -539,8 +555,8 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
 
 /**
  *	relay_open - create a new relay channel
- *	@base_filename: base name of files to create
- *	@parent: dentry of parent directory, %NULL for root directory
+ *	@base_filename: base name of files to create, %NULL for buffering only
+ *	@parent: dentry of parent directory, %NULL for root directory or buffer
  *	@subbuf_size: size of sub-buffers
  *	@n_subbufs: number of sub-buffers
  *	@cb: client callback functions

@@ -562,8 +578,6 @@ struct rchan *relay_open(const char *base_filename,
 {
 	unsigned int i;
 	struct rchan *chan;
-	if (!base_filename)
-		return NULL;
 
 	if (!(subbuf_size && n_subbufs))
 		return NULL;

@@ -578,12 +592,15 @@ struct rchan *relay_open(const char *base_filename,
 	chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs);
 	chan->parent = parent;
 	chan->private_data = private_data;
-	strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	if (base_filename) {
+		chan->has_base_filename = 1;
+		strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	}
 	setup_callbacks(chan, cb);
 	kref_init(&chan->kref);
 
 	mutex_lock(&relay_channels_mutex);
-	for_each_online_cpu(i) {
+	for_each_present_cpu(i) {
 		chan->buf[i] = relay_open_buf(chan, i);
 		if (!chan->buf[i])
 			goto free_bufs;

@@ -594,7 +611,7 @@ struct rchan *relay_open(const char *base_filename,
 	return chan;
 
 free_bufs:
-	for_each_online_cpu(i) {
+	for_each_present_cpu(i) {
 		if (!chan->buf[i])
 			break;
 		relay_close_buf(chan->buf[i]);

@@ -607,6 +624,43 @@ free_bufs:
 EXPORT_SYMBOL_GPL(relay_open);
 
 /**
+ *	relay_late_setup_files - triggers file creation
+ *	@chan: channel to operate on
+ *	@base_filename: base name of files to create
+ *	@parent: dentry of parent directory, %NULL for root directory
+ *
+ *	Returns 0 if successful, non-zero otherwise.
+ *
+ *	Use to setup files for a previously buffer-only channel.
+ *	Useful to do early tracing in kernel, before VFS is up, for example.
+ */
+int relay_late_setup_files(struct rchan *chan,
+			   const char *base_filename,
+			   struct dentry *parent)
+{
+	unsigned int i;
+	int ret;
+	struct rchan_buf *buf;
+
+	if (!chan || !base_filename)
+		return 1;
+
+	strlcpy(chan->base_filename, base_filename, NAME_MAX);
+	chan->has_base_filename = 1;
+	chan->parent = parent;
+
+	for_each_present_cpu(i) {
+		buf = chan->buf[i];
+
+		ret = relay_setup_buf_file(chan, buf, i);
+		if (unlikely(ret))
+			return 1;
+	}
+
+	return 0;
+}
+
+/**
  *	relay_switch_subbuf - switch to a new sub-buffer
  *	@buf: channel buffer
  *	@length: size of current event

@@ -629,8 +683,13 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 		old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
 		buf->padding[old_subbuf] = buf->prev_padding;
 		buf->subbufs_produced++;
-		buf->dentry->d_inode->i_size += buf->chan->subbuf_size -
-			buf->padding[old_subbuf];
+		if (buf->dentry)
+			buf->dentry->d_inode->i_size +=
+				buf->chan->subbuf_size -
+				buf->padding[old_subbuf];
+		else
+			buf->early_bytes += buf->chan->subbuf_size -
+					    buf->padding[old_subbuf];
 		smp_mb();
 		if (waitqueue_active(&buf->read_wait))
 			/*

Signature · 1 line

1.5.5.4

I think it would be good to add a patch to this patch series which allows to allocate such early boot buffers either statically in a kernel menuconfig option or in a kernel command line argument, so we do not depend on vmap. That would make it usable "very early".

Mathieu