[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20080617143502.GE10316@Krystal>
Date: Tue, 17 Jun 2008 10:35:02 -0400
From: Mathieu Desnoyers <compudj@...stal.dyndns.org>
To: Eduard - Gabriel Munteanu <eduard.munteanu@...ux360.ro>
Cc: tzanussi@...il.com, linux-kernel@...r.kernel.org,
penberg@...helsinki.fi, akpm@...ux-foundation.org,
torvalds@...ux-foundation.org
Subject: Re: [PATCH 3/3] relay: Add buffer-only channels; useful for early
logging.
* Eduard - Gabriel Munteanu (eduard.munteanu@...ux360.ro) wrote:
> 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.
>
> This is needed by kmemtrace to do tracing in early kernel code.
>
> Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@...ux360.ro>
> ---
> Documentation/filesystems/relay.txt | 11 +++
> include/linux/relay.h | 5 +
> kernel/relay.c | 141 +++++++++++++++++++++++++++--------
> 3 files changed, 126 insertions(+), 31 deletions(-)
>
> diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt
> index 094f2d2..b417f83 100644
> --- a/Documentation/filesystems/relay.txt
> +++ b/Documentation/filesystems/relay.txt
> @@ -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'
> ---------------
>
> diff --git a/include/linux/relay.h b/include/linux/relay.h
> index a3a03e7..1d3dcf8 100644
> --- a/include/linux/relay.h
> +++ b/include/linux/relay.h
> @@ -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,
> diff --git a/kernel/relay.c b/kernel/relay.c
> index 250a27a..80a6a40 100644
> --- a/kernel/relay.c
> +++ b/kernel/relay.c
> @@ -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);
spin_lock_* on a variable named rw_lock, insn't it a bit confusing ?
See rwlock_* and friends to figure out why this naming is not so
appropriate.
> + buf->dentry = dentry;
> + buf->dentry->d_inode->i_size = buf->early_bytes;
> + spin_unlock_irqrestore(&buf->rw_lock, flags);
As long as this rw_lock is not taken on the read/write, etc path, it
won't protect against races. I think it should be left to the
relay_setup_buf_file() caller to provide proper synchronization, and
therefore begs for a comment on top of relay_late_setup_files().
Note that since relay_late_setup_files() takes a mutex, locking will
become a bit problematic, since you cannot nest a spinlock in a mutex.
> +
> + return 0;
> +
> +failed:
> + return 1;
> +}
> +
> /*
> * relay_open_buf - create a new relay channel buffer
> *
> @@ -415,48 +448,33 @@ 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 +557,8 @@ 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 +580,6 @@ 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;
> @@ -578,7 +594,10 @@ 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);
>
> @@ -607,6 +626,62 @@ 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 err;
> + struct rchan_buf *buf;
> +
> + if (!chan || !base_filename)
> + return 1;
> +
> + strlcpy(chan->base_filename, base_filename, NAME_MAX);
> +
> + mutex_lock(&relay_channels_mutex);
> + if (unlikely(chan->has_base_filename))
> + goto out;
> + chan->has_base_filename = 1;
> + chan->parent = parent;
> + /*
> + * The CPU hotplug notifier ran before us and created buffers with
> + * no files associated. So it's safe to call relay_setup_buf_file()
> + * on all currently online CPUs.
The following scenario will hide data :
cpu0 online
cpu1 online
tracing some stuff
cpu1 offline
relay_late_setup_files() is called.
You should iterate on all possible cpus and detect which ones have
buffers allocated.
> + */
> + for_each_online_cpu(i) {
> + buf = chan->buf[i];
> +
> + if (unlikely(!buf)) {
> + printk(KERN_ERR "relay_late_setup_files: "
> + "all CPUs should have buffers!\n");
> + goto out;
> + }
> +
> + err = relay_setup_buf_file(chan, buf, i);
> + if (unlikely(err))
> + goto out;
> + }
> + mutex_unlock(&relay_channels_mutex);
> +
> + return 0;
> +
> +out:
> + mutex_unlock(&relay_channels_mutex);
> + return 1;
> +}
> +
> +/**
> * relay_switch_subbuf - switch to a new sub-buffer
> * @buf: channel buffer
> * @length: size of current event
> @@ -629,8 +704,13 @@ 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))
> /*
> @@ -1241,9 +1321,8 @@ EXPORT_SYMBOL_GPL(relay_file_operations);
>
> static __init int relay_init(void)
> {
> -
Whitespace removal does not belong in this patch.
> hotcpu_notifier(relay_hotcpu_callback, 0);
> return 0;
> }
>
> -module_init(relay_init);
> +early_initcall(relay_init);
See discussion about "how early" in the previous patch of this patchset.
> --
> 1.5.5.4
>
--
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists