From: Jeffle Xu <jefflexu@linux.alibaba.com>
To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org,
chao@kernel.org, linux-erofs@lists.ozlabs.org
Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org,
willy@infradead.org, linux-fsdevel@vger.kernel.org,
joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com,
tao.peng@linux.alibaba.com, gerry@linux.alibaba.com,
eguan@linux.alibaba.com, linux-kernel@vger.kernel.org
Subject: [PATCH v4 03/21] cachefiles: introduce on-demand read mode
Date: Mon, 7 Mar 2022 20:32:47 +0800 [thread overview]
Message-ID: <20220307123305.79520-4-jefflexu@linux.alibaba.com> (raw)
In-Reply-To: <20220307123305.79520-1-jefflexu@linux.alibaba.com>
Fscache/cachefiles used to serve as a local cache for remote fs. This
patch, along with the following patches, introduces a new on-demand read
mode for cachefiles, which can boost the scenario where on-demand read
semantics is needed, e.g. container image distribution.
The essential difference between the original mode and on-demand read
mode is that, in the original mode, when cache miss, netfs itself will
fetch data from remote, and then write the fetched data into cache file.
While in on-demand read mode, a user daemon is responsible for fetching
data and then writing to the cache file.
This patch only adds the command to enable on-demand read mode. An
optional parameter to "bind" command is added. On-demand mode will be
turned on when this optional argument matches "ondemand" exactly, i.e.
"bind ondemand". Otherwise cachefiles will keep working in the original
mode.
The following patches will implement the data plane of on-demand read
mode.
Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
---
fs/cachefiles/Kconfig | 11 ++++
fs/cachefiles/daemon.c | 132 +++++++++++++++++++++++++++++++--------
fs/cachefiles/internal.h | 6 ++
3 files changed, 124 insertions(+), 25 deletions(-)
diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig
index 719faeeda168..58aad1fb4c5c 100644
--- a/fs/cachefiles/Kconfig
+++ b/fs/cachefiles/Kconfig
@@ -26,3 +26,14 @@ config CACHEFILES_ERROR_INJECTION
help
This permits error injection to be enabled in cachefiles whilst a
cache is in service.
+
+config CACHEFILES_ONDEMAND
+ bool "Support for on-demand read"
+ depends on CACHEFILES
+ default n
+ help
+ This permits on-demand read mode of cachefiles. In this mode, when
+ cache miss, the cachefiles backend instead of netfs, is responsible
+ for fetching data, e.g. through user daemon.
+
+ If unsure, say N.
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 7ac04ee2c0a0..c0c3a3cbee28 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -78,6 +78,65 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = {
{ "", NULL }
};
+#ifdef CONFIG_CACHEFILES_ONDEMAND
+static inline void cachefiles_ondemand_open(struct cachefiles_cache *cache)
+{
+ xa_init_flags(&cache->reqs, XA_FLAGS_ALLOC);
+ rwlock_init(&cache->reqs_lock);
+}
+
+static inline void cachefiles_ondemand_release(struct cachefiles_cache *cache)
+{
+ xa_destroy(&cache->reqs);
+}
+
+static inline __poll_t cachefiles_ondemand_mask(struct cachefiles_cache *cache)
+{
+ __poll_t mask = 0;
+
+ if (!xa_empty(&cache->reqs))
+ mask |= EPOLLIN;
+
+ if (test_bit(CACHEFILES_CULLING, &cache->flags))
+ mask |= EPOLLOUT;
+
+ return mask;
+}
+
+static inline
+bool cachefiles_ondemand_daemon_bind(struct cachefiles_cache *cache, char *args)
+{
+ if (!strcmp(args, "ondemand")) {
+ set_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags);
+ return true;
+ }
+
+ return false;
+}
+
+#else
+static inline void cachefiles_ondemand_open(struct cachefiles_cache *cache) {}
+static inline void cachefiles_ondemand_release(struct cachefiles_cache *cache) {}
+
+static inline
+__poll_t cachefiles_ondemand_mask(struct cachefiles_cache *cache)
+{
+ return 0;
+}
+
+static inline
+bool cachefiles_ondemand_daemon_bind(struct cachefiles_cache *cache, char *args)
+{
+ return false;
+}
+#endif
+
+static inline
+ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
+ char __user *_buffer, size_t buflen)
+{
+ return -EOPNOTSUPP;
+}
/*
* Prepare a cache for caching.
@@ -108,6 +167,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file)
INIT_LIST_HEAD(&cache->volumes);
INIT_LIST_HEAD(&cache->object_list);
spin_lock_init(&cache->object_list_lock);
+ cachefiles_ondemand_open(cache);
/* set default caching limits
* - limit at 1% free space and/or free files
@@ -139,6 +199,7 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file)
set_bit(CACHEFILES_DEAD, &cache->flags);
+ cachefiles_ondemand_release(cache);
cachefiles_daemon_unbind(cache);
/* clean up the control file interface */
@@ -152,23 +213,15 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file)
return 0;
}
-/*
- * Read the cache state.
- */
-static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
- size_t buflen, loff_t *pos)
+static ssize_t cachefiles_do_daemon_read(struct cachefiles_cache *cache,
+ char __user *_buffer,
+ size_t buflen)
{
- struct cachefiles_cache *cache = file->private_data;
unsigned long long b_released;
unsigned f_released;
char buffer[256];
int n;
- //_enter(",,%zu,", buflen);
-
- if (!test_bit(CACHEFILES_READY, &cache->flags))
- return 0;
-
/* check how much space the cache has */
cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check);
@@ -206,6 +259,25 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
return n;
}
+/*
+ * Read the cache state.
+ */
+static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
+ size_t buflen, loff_t *pos)
+{
+ struct cachefiles_cache *cache = file->private_data;
+
+ //_enter(",,%zu,", buflen);
+
+ if (!test_bit(CACHEFILES_READY, &cache->flags))
+ return 0;
+
+ if (likely(!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)))
+ return cachefiles_do_daemon_read(cache, _buffer, buflen);
+ else
+ return cachefiles_ondemand_daemon_read(cache, _buffer, buflen);
+}
+
/*
* Take a command from cachefilesd, parse it and act on it.
*/
@@ -284,6 +356,21 @@ static ssize_t cachefiles_daemon_write(struct file *file,
goto error;
}
+
+static inline
+__poll_t cachefiles_daemon_mask(struct cachefiles_cache *cache)
+{
+ __poll_t mask = 0;
+
+ if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
+ mask |= EPOLLIN;
+
+ if (test_bit(CACHEFILES_CULLING, &cache->flags))
+ mask |= EPOLLOUT;
+
+ return mask;
+}
+
/*
* Poll for culling state
* - use EPOLLOUT to indicate culling state
@@ -292,18 +379,13 @@ static __poll_t cachefiles_daemon_poll(struct file *file,
struct poll_table_struct *poll)
{
struct cachefiles_cache *cache = file->private_data;
- __poll_t mask;
poll_wait(file, &cache->daemon_pollwq, poll);
- mask = 0;
-
- if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
- mask |= EPOLLIN;
-
- if (test_bit(CACHEFILES_CULLING, &cache->flags))
- mask |= EPOLLOUT;
- return mask;
+ if (likely(!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)))
+ return cachefiles_daemon_mask(cache);
+ else
+ return cachefiles_ondemand_mask(cache);
}
/*
@@ -687,11 +769,6 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
cache->brun_percent >= 100)
return -ERANGE;
- if (*args) {
- pr_err("'bind' command doesn't take an argument\n");
- return -EINVAL;
- }
-
if (!cache->rootdirname) {
pr_err("No cache directory specified\n");
return -EINVAL;
@@ -703,6 +780,11 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
return -EBUSY;
}
+ if (!cachefiles_ondemand_daemon_bind(cache, args) && *args) {
+ pr_err("'bind' command doesn't take an argument\n");
+ return -EINVAL;
+ }
+
/* Make sure we have copies of the tag string */
if (!cache->tag) {
/*
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index e80673d0ab97..3f791882fa3f 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -15,6 +15,7 @@
#include <linux/fscache-cache.h>
#include <linux/cred.h>
#include <linux/security.h>
+#include <linux/xarray.h>
#define CACHEFILES_DIO_BLOCK_SIZE 4096
@@ -98,9 +99,14 @@ struct cachefiles_cache {
#define CACHEFILES_DEAD 1 /* T if cache dead */
#define CACHEFILES_CULLING 2 /* T if cull engaged */
#define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */
+#define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */
char *rootdirname; /* name of cache root directory */
char *secctx; /* LSM security context */
char *tag; /* cache binding tag */
+#ifdef CONFIG_CACHEFILES_ONDEMAND
+ struct xarray reqs; /* xarray of pending on-demand requests */
+ rwlock_t reqs_lock; /* Lock for reqs xarray */
+#endif
};
#include <trace/events/cachefiles.h>
--
2.27.0
next prev parent reply other threads:[~2022-03-07 12:33 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-07 12:32 [PATCH v4 00/21] fscache,erofs: fscache-based on-demand read semantics Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 01/21] fscache: export fscache_end_operation() Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 02/21] cachefiles: export write routine Jeffle Xu
2022-03-07 12:32 ` Jeffle Xu [this message]
2022-03-07 12:32 ` [PATCH v4 04/21] cachefiles: notify user daemon with anon_fd when opening cache file Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 05/21] cachefiles: implement on-demand read Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 06/21] cachefiles: document on-demand read mode Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 07/21] erofs: use meta buffers for erofs_read_superblock() Jeffle Xu
2022-03-11 7:36 ` Chao Yu
2022-03-07 12:32 ` [PATCH v4 08/21] erofs: export erofs_map_blocks() Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 09/21] erofs: add mode checking helper Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 10/21] erofs: register global fscache volume Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 11/21] erofs: add cookie context helper functions Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 12/21] erofs: add anonymous inode managing page cache of blob file Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 13/21] erofs: add erofs_fscache_read_pages() helper Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 14/21] erofs: register cookie context for bootstrap blob Jeffle Xu
2022-03-07 12:32 ` [PATCH v4 15/21] erofs: implement fscache-based metadata read Jeffle Xu
2022-03-07 12:33 ` [PATCH v4 16/21] erofs: implement fscache-based data read for non-inline layout Jeffle Xu
2022-03-07 12:33 ` [PATCH v4 17/21] erofs: implement fscache-based data read for inline layout Jeffle Xu
2022-03-07 12:33 ` [PATCH v4 18/21] erofs: register cookie context for data blobs Jeffle Xu
2022-03-07 12:33 ` [PATCH v4 19/21] erofs: implement fscache-based data read " Jeffle Xu
2022-03-07 12:33 ` [PATCH v4 20/21] erofs: implement fscache-based data readahead Jeffle Xu
2022-03-07 12:33 ` [PATCH v4 21/21] erofs: add 'uuid' mount option Jeffle Xu
2022-03-14 9:24 ` [PATCH v4 00/21] fscache,erofs: fscache-based on-demand read semantics luodaowen.backend
2022-03-18 9:42 ` Fan,Naihao
2022-03-18 11:48 ` JeffleXu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220307123305.79520-4-jefflexu@linux.alibaba.com \
--to=jefflexu@linux.alibaba.com \
--cc=bo.liu@linux.alibaba.com \
--cc=chao@kernel.org \
--cc=dhowells@redhat.com \
--cc=eguan@linux.alibaba.com \
--cc=gerry@linux.alibaba.com \
--cc=gregkh@linuxfoundation.org \
--cc=joseph.qi@linux.alibaba.com \
--cc=linux-cachefs@redhat.com \
--cc=linux-erofs@lists.ozlabs.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tao.peng@linux.alibaba.com \
--cc=torvalds@linux-foundation.org \
--cc=willy@infradead.org \
--cc=xiang@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox