Skip to contentSkip to conversation

cgroup: implement cftype->write()

PATCH Applied Tejun Heo 4 participants 12 messages May 6, 2014 – May 13, 2014

Subsystems (9)
Networking Memory management Block layer Security (LSM) +5 more subsystems
lore
Share & tools
lore

Tejun Heo

author maintainer
#0 lore raw

PATCH 1/1 cgroup: implement cftype->write()

Hello,

This patchset implements a new cftype operation ->write() and replace ->write_string() and ->trigger() with it. ->write() is similar to ->write_string() but maps directly to the kernfs write operation and has access to all available context information including the associated kernfs_open_file, which will make things like implementing kernfs active protection manipulation easier.

->write_string() becomes redundant and ->trigger() has always been spurious. This patch replaces all users of the two methods to ->write() and remove them.

This patchset contains the following five patches.

0001-cgroup-implement-cftype-write.patch 0002-cgroup-replace-cftype-write_string-with-cftype-write.patch 0003-cgroup-replace-cftype-trigger-with-cftype-write.patch 0004-cgroup-convert-tasks-and-cgroup.procs-handle-to-use-.patch 0005-cgroup-remove-cgroup-control_kn.patch

0001 implements cftype->write().

0002-0003 replace cftype->write_string() and ->trigger() with it.

0004 convert "tasks" and "cgroup.procs" handler too.

0005 removes cgroup->control_kn as the kernfs_node is now directly accessible from kernfs_open_file.

This patchset is on top of

cgroup/for-3.16 12d3089c192c ("kernel/cpuset.c: convert printk to pr_foo()")
+ [1] [PATCHSET cgroup/for-3.16] cgroup: post unified hierarchy fixes and updates

and available on the following git branch.

git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-post-unified-updates

diffstat follows.

 block/blk-throttle.c      |   32 ++++++++---------
 block/cfq-iosched.c       |   28 +++++++--------
 include/linux/cgroup.h    |   40 +++++++++++----------
 kernel/cgroup.c           |   85 +++++++++++++++++++++++-----------------------
 kernel/cgroup_freezer.c   |   20 ++++------
 kernel/cpuset.c           |   16 ++++----
 mm/hugetlb_cgroup.c       |   33 +++++++++--------
 mm/memcontrol.c           |   80 +++++++++++++++++++++++--------------------
 net/ipv4/tcp_memcontrol.c |   31 +++++++++-------
 security/device_cgroup.c  |   14 +++----
 10 files changed, 197 insertions(+), 182 deletions(-)

Thanks.

--
tejun

[1] http://lkml.kernel.org/g/[email protected]

author maintainer
#1 lore raw

PATCH 1/5 cgroup: implement cftype->write()

During the recent conversion to kernfs, cftype's seq_file operations are updated so that they are directly mapped to kernfs operations and thus can fully access the associated kernfs and cgroup contexts; however, write path hasn't seen similar updates and none of the existing write operations has access to, for example, the associated kernfs_open_file.

Let's introduce a new operation cftype->write() which maps directly to the kernfs write operation and has access to all the arguments and contexts. This will replace ->write_string() and ->trigger() and ease manipulation of kernfs active protection from cgroup file operations.

Two accessors - of_cft() and of_css() - are introduced to enable accessing the associated cgroup context from cftype->write() which only takes kernfs_open_file for the context information. The accessors for seq_file operations - seq_cft() and seq_css() - are rewritten to wrap the of_ accessors.

Signed-off-by Tejun Heo <[email protected]>
---
 include/linux/cgroup.h | 27 +++++++++++++++++++++++----
 kernel/cgroup.c        | 14 ++++++++------
 2 files changed, 31 insertions(+), 10 deletions(-)
include/linux/cgroup.h +23 -4
index 2dfabb3..da7a0ca 100644
@@ -517,6 +517,15 @@ struct cftype {
 	 */
 	int (*trigger)(struct cgroup_subsys_state *css, unsigned int event);
 
+	/*
+	 * write() is the generic write callback which maps directly to
+	 * kernfs write operation and overrides all other operations.
+	 * Maximum write size is determined by ->max_write_len.  Use
+	 * of_css/cft() to access the associated css and cft.
+	 */
+	ssize_t (*write)(struct kernfs_open_file *of,
+			 char *buf, size_t nbytes, loff_t off);
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lock_class_key	lockdep_key;
 #endif

@@ -553,14 +562,24 @@ static inline ino_t cgroup_ino(struct cgroup *cgrp)
 		return 0;
 }
 
-static inline struct cftype *seq_cft(struct seq_file *seq)
+/* cft/css accessors for cftype->write() operation */
+static inline struct cftype *of_cft(struct kernfs_open_file *of)
 {
-	struct kernfs_open_file *of = seq->private;
-
 	return of->kn->priv;
 }
 
-struct cgroup_subsys_state *seq_css(struct seq_file *seq);
+struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
+
+/* cft/css accessors for cftype->seq_*() operations */
+static inline struct cftype *seq_cft(struct seq_file *seq)
+{
+	return of_cft(seq->private);
+}
+
+static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+	return of_css(seq->private);
+}
 
 /*
  * Name / path handling functions.  All are thin wrappers around the kernfs
kernel/cgroup.c +8 -6
index 57c2021..32d1624 100644
@@ -283,11 +283,10 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 	return test_bit(CGRP_DEAD, &cgrp->flags);
 }
 
-struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
-	struct kernfs_open_file *of = seq->private;
 	struct cgroup *cgrp = of->kn->parent->priv;
-	struct cftype *cft = seq_cft(seq);
+	struct cftype *cft = of_cft(of);
 
 	/*
 	 * This is open and unprotected implementation of cgroup_css().

@@ -302,7 +301,7 @@ struct cgroup_subsys_state *seq_css(struct seq_file *seq)
 	else
 		return &cgrp->dummy_css;
 }
-EXPORT_SYMBOL_GPL(seq_css);
+EXPORT_SYMBOL_GPL(of_css);
 
 /**
  * cgroup_is_descendant - test ancestry

@@ -1035,8 +1034,8 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 	if (cft->read_u64 || cft->read_s64 || cft->seq_show)
 		mode |= S_IRUGO;
 
-	if (cft->write_u64 || cft->write_s64 || cft->write_string ||
-	    cft->trigger)
+	if (cft->write_u64 || cft->write_s64 || cft->write ||
+	    cft->write_string || cft->trigger)
 		mode |= S_IWUSR;
 
 	return mode;

@@ -2724,6 +2723,9 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	struct cgroup_subsys_state *css;
 	int ret;
 
+	if (cft->write)
+		return cft->write(of, buf, nbytes, off);
+
 	/*
 	 * kernfs guarantees that a file isn't deleted with operations in
 	 * flight, which means that the matching css is and stays alive and
Signature · 1 line
1.9.0
author maintainer
#2 lore raw

PATCH 2/5 cgroup: replace cftype->write_string() with cftype->write()

In reply to Tejun Heo

Convert all cftype->write_string() users to the new cftype->write() which maps directly to kernfs write operation and has full access to kernfs and cgroup contexts. The conversions are mostly mechanical.

* @css and @cft are accessed using of_css() and of_cft() accessors respectively instead of being specified as arguments.

* Should return @nbytes on success instead of 0.

* @buf is not trimmed automatically. Trim if necessary. Note that blkcg doesn't need this as blkg_conf_prep() can already handle whitespaces.

cftype->write_string() has no user left after the conversions and removed.

While at it, remove unnecessary local variable @p in cgroup_subtree_control_write() and stale comment about CGROUP_LOCAL_BUFFER_SIZE in cgroup_freezer.c.

This patch doesn't introduce any visible behavior changes.

Signed-off-by Tejun Heo <[email protected]>
Cc Vivek Goyal <[email protected]>
Cc Jens Axboe <[email protected]>
Cc Li Zefan <[email protected]>
Cc Johannes Weiner <[email protected]>
Cc Michal Hocko <[email protected]>
Cc Aristeu Rozanski <[email protected]>
---
 block/blk-throttle.c      | 32 ++++++++++++++++----------------
 block/cfq-iosched.c       | 28 ++++++++++++++--------------
 include/linux/cgroup.h    | 10 +---------
 kernel/cgroup.c           | 38 +++++++++++++++++++-------------------
 kernel/cgroup_freezer.c   | 20 +++++++++-----------
 kernel/cpuset.c           | 16 +++++++++-------
 mm/hugetlb_cgroup.c       | 17 +++++++++--------
 mm/memcontrol.c           | 46 +++++++++++++++++++++++++---------------------
 net/ipv4/tcp_memcontrol.c | 16 +++++++++-------
 security/device_cgroup.c  | 14 +++++++-------
 10 files changed, 118 insertions(+), 119 deletions(-)
block/blk-throttle.c +16 -16
index 033745c..5e8fd1b 100644
@@ -1346,10 +1346,10 @@ static int tg_print_conf_uint(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
-		       const char *buf, bool is_u64)
+static ssize_t tg_set_conf(struct kernfs_open_file *of,
+			   char *buf, size_t nbytes, loff_t off, bool is_u64)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct throtl_grp *tg;
 	struct throtl_service_queue *sq;

@@ -1368,9 +1368,9 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 		ctx.v = -1;
 
 	if (is_u64)
-		*(u64 *)((void *)tg + cft->private) = ctx.v;
+		*(u64 *)((void *)tg + of_cft(of)->private) = ctx.v;
 	else
-		*(unsigned int *)((void *)tg + cft->private) = ctx.v;
+		*(unsigned int *)((void *)tg + of_cft(of)->private) = ctx.v;
 
 	throtl_log(&tg->service_queue,
 		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",

@@ -1404,19 +1404,19 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 	}
 
 	blkg_conf_finish(&ctx);
-	return 0;
+	return nbytes;
 }
 
-static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
-			   char *buf)
+static ssize_t tg_set_conf_u64(struct kernfs_open_file *of,
+			       char *buf, size_t nbytes, loff_t off)
 {
-	return tg_set_conf(css, cft, buf, true);
+	return tg_set_conf(of, buf, nbytes, off, true);
 }
 
-static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buf)
+static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	return tg_set_conf(css, cft, buf, false);
+	return tg_set_conf(of, buf, nbytes, off, false);
 }
 
 static struct cftype throtl_files[] = {

@@ -1424,25 +1424,25 @@ static struct cftype throtl_files[] = {
 		.name = "throttle.read_bps_device",
 		.private = offsetof(struct throtl_grp, bps[READ]),
 		.seq_show = tg_print_conf_u64,
-		.write_string = tg_set_conf_u64,
+		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
 		.seq_show = tg_print_conf_u64,
-		.write_string = tg_set_conf_u64,
+		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
 		.seq_show = tg_print_conf_uint,
-		.write_string = tg_set_conf_uint,
+		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
 		.seq_show = tg_print_conf_uint,
-		.write_string = tg_set_conf_uint,
+		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.io_service_bytes",
block/cfq-iosched.c +14 -14
index e0985f1..a73020b 100644
@@ -1670,11 +1670,11 @@ static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				    struct cftype *cft, const char *buf,
-				    bool is_leaf_weight)
+static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
+					char *buf, size_t nbytes, loff_t off,
+					bool is_leaf_weight)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct cfq_group *cfqg;
 	int ret;

@@ -1697,19 +1697,19 @@ static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
 	}
 
 	blkg_conf_finish(&ctx);
-	return ret;
+	return ret ?: nbytes;
 }
 
-static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buf)
+static ssize_t cfqg_set_weight_device(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
-	return __cfqg_set_weight_device(css, cft, buf, false);
+	return __cfqg_set_weight_device(of, buf, nbytes, off, false);
 }
 
-static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
-				       struct cftype *cft, char *buf)
+static ssize_t cfqg_set_leaf_weight_device(struct kernfs_open_file *of,
+					   char *buf, size_t nbytes, loff_t off)
 {
-	return __cfqg_set_weight_device(css, cft, buf, true);
+	return __cfqg_set_weight_device(of, buf, nbytes, off, true);
 }
 
 static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,

@@ -1837,7 +1837,7 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "weight_device",
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cfqg_print_leaf_weight_device,
-		.write_string = cfqg_set_leaf_weight_device,
+		.write = cfqg_set_leaf_weight_device,
 	},
 	{
 		.name = "weight",

@@ -1851,7 +1851,7 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "weight_device",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cfqg_print_weight_device,
-		.write_string = cfqg_set_weight_device,
+		.write = cfqg_set_weight_device,
 	},
 	{
 		.name = "weight",

@@ -1863,7 +1863,7 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "leaf_weight_device",
 		.seq_show = cfqg_print_leaf_weight_device,
-		.write_string = cfqg_set_leaf_weight_device,
+		.write = cfqg_set_leaf_weight_device,
 	},
 	{
 		.name = "leaf_weight",
include/linux/cgroup.h +1 -9
index da7a0ca..5f717d7 100644
@@ -455,8 +455,7 @@ struct cftype {
 
 	/*
 	 * The maximum length of string, excluding trailing nul, that can
-	 * be passed to write_string.  If < PAGE_SIZE-1, PAGE_SIZE-1 is
-	 * assumed.
+	 * be passed to write.  If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed.
 	 */
 	size_t max_write_len;
 

@@ -503,13 +502,6 @@ struct cftype {
 			 s64 val);
 
 	/*
-	 * write_string() is passed a nul-terminated kernelspace
-	 * buffer of maximum length determined by max_write_len.
-	 * Returns 0 or -ve error code.
-	 */
-	int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer);
-	/*
 	 * trigger() callback can be used to get some kick from the
 	 * userspace, when the actual string written is not important
 	 * at all. The private field can be used to determine the
kernel/cgroup.c +19 -19
index 32d1624..8939fe4 100644
@@ -1035,7 +1035,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 		mode |= S_IRUGO;
 
 	if (cft->write_u64 || cft->write_s64 || cft->write ||
-	    cft->write_string || cft->trigger)
+	    cft->trigger)
 		mode |= S_IWUSR;
 
 	return mode;

@@ -2352,20 +2352,21 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
 	return attach_task_by_pid(css->cgroup, tgid, true);
 }
 
-static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
-				      struct cftype *cft, char *buffer)
+static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
+					  char *buf, size_t nbytes, loff_t off)
 {
-	struct cgroup_root *root = css->cgroup->root;
+	struct cgroup *cgrp = of_css(of)->cgroup;
+	struct cgroup_root *root = cgrp->root;
 
 	BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
-	if (!cgroup_lock_live_group(css->cgroup))
+	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 	spin_lock(&release_agent_path_lock);
-	strlcpy(root->release_agent_path, buffer,
+	strlcpy(root->release_agent_path, strstrip(buf),
 		sizeof(root->release_agent_path));
 	spin_unlock(&release_agent_path_lock);
 	mutex_unlock(&cgroup_mutex);
-	return 0;
+	return nbytes;
 }
 
 static int cgroup_release_agent_show(struct seq_file *seq, void *v)

@@ -2530,21 +2531,22 @@ out_finish:
 }
 
 /* change the enabled child controllers for a cgroup in the default hierarchy */
-static int cgroup_subtree_control_write(struct cgroup_subsys_state *dummy_css,
-					struct cftype *cft, char *buffer)
+static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
 {
 	unsigned int enable = 0, disable = 0;
-	struct cgroup *cgrp = dummy_css->cgroup, *child;
+	struct cgroup *cgrp = of_css(of)->cgroup, *child;
 	struct cgroup_subsys *ss;
-	char *tok, *p;
+	char *tok;
 	int ssid, ret;
 
 	/*
 	 * Parse input - space separated list of subsystem names prefixed
 	 * with either + or -.
 	 */
-	p = buffer;
-	while ((tok = strsep(&p, " "))) {
+	buf = strstrip(buf);
+	while ((tok = strsep(&buf, " "))) {
 		for_each_subsys(ss, ssid) {
 			if (ss->disabled || strcmp(tok + 1, ss->name))
 				continue;

@@ -2690,7 +2692,7 @@ out_unlock_tree:
 out_unbreak:
 	kernfs_unbreak_active_protection(cgrp->control_kn);
 	cgroup_put(cgrp);
-	return ret;
+	return ret ?: nbytes;
 
 err_undo_css:
 	cgrp->child_subsys_mask &= ~enable;

@@ -2736,9 +2738,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	css = cgroup_css(cgrp, cft->ss);
 	rcu_read_unlock();
 
-	if (cft->write_string) {
-		ret = cft->write_string(css, cft, strstrip(buf));
-	} else if (cft->write_u64) {
+	if (cft->write_u64) {
 		unsigned long long v;
 		ret = kstrtoull(buf, 0, &v);
 		if (!ret)

@@ -3982,7 +3982,7 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cgroup.subtree_control",
 		.flags = CFTYPE_ONLY_ON_DFL,
 		.seq_show = cgroup_subtree_control_show,
-		.write_string = cgroup_subtree_control_write,
+		.write = cgroup_subtree_control_write,
 	},
 	{
 		.name = "cgroup.populated",

@@ -4016,7 +4016,7 @@ static struct cftype cgroup_base_files[] = {
 		.name = "release_agent",
 		.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cgroup_release_agent_show,
-		.write_string = cgroup_release_agent_write,
+		.write = cgroup_release_agent_write,
 		.max_write_len = PATH_MAX - 1,
 	},
 	{ }	/* terminate */
kernel/cgroup_freezer.c +9 -11
index 2bc4a22..d2b4bc7 100644
@@ -71,10 +71,6 @@ bool cgroup_freezing(struct task_struct *task)
 	return ret;
 }
 
-/*
- * cgroups_write_string() limits the size of freezer state strings to
- * CGROUP_LOCAL_BUFFER_SIZE
- */
 static const char *freezer_state_strs(unsigned int state)
 {
 	if (state & CGROUP_FROZEN)

@@ -441,20 +437,22 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 	rcu_read_unlock();
 }
 
-static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			 char *buffer)
+static ssize_t freezer_write(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
 {
 	bool freeze;
 
-	if (strcmp(buffer, freezer_state_strs(0)) == 0)
+	buf = strstrip(buf);
+
+	if (strcmp(buf, freezer_state_strs(0)) == 0)
 		freeze = false;
-	else if (strcmp(buffer, freezer_state_strs(CGROUP_FROZEN)) == 0)
+	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0)
 		freeze = true;
 	else
 		return -EINVAL;
 
-	freezer_change_state(css_freezer(css), freeze);
-	return 0;
+	freezer_change_state(css_freezer(of_css(of)), freeze);
+	return nbytes;
 }
 
 static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css,

@@ -478,7 +476,7 @@ static struct cftype files[] = {
 		.name = "state",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = freezer_read,
-		.write_string = freezer_write,
+		.write = freezer_write,
 	},
 	{
 		.name = "self_freezing",
kernel/cpuset.c +9 -7
index 7c0e8da..97cbb59 100644
@@ -1603,13 +1603,15 @@ out_unlock:
 /*
  * Common handling for a write to a "cpus" or "mems" file.
  */
-static int cpuset_write_resmask(struct cgroup_subsys_state *css,
-				struct cftype *cft, char *buf)
+static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cpuset *cs = css_cs(of_css(of));
 	struct cpuset *trialcs;
 	int retval = -ENODEV;
 
+	buf = strstrip(buf);
+
 	/*
 	 * CPU or memory hotunplug may leave @cs w/o any execution
 	 * resources, in which case the hotplug code asynchronously updates

@@ -1633,7 +1635,7 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 		goto out_unlock;
 	}
 
-	switch (cft->private) {
+	switch (of_cft(of)->private) {
 	case FILE_CPULIST:
 		retval = update_cpumask(cs, trialcs, buf);
 		break;

@@ -1648,7 +1650,7 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 	free_trial_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 /*

@@ -1750,7 +1752,7 @@ static struct cftype files[] = {
 	{
 		.name = "cpus",
 		.seq_show = cpuset_common_seq_show,
-		.write_string = cpuset_write_resmask,
+		.write = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * NR_CPUS),
 		.private = FILE_CPULIST,
 	},

@@ -1758,7 +1760,7 @@ static struct cftype files[] = {
 	{
 		.name = "mems",
 		.seq_show = cpuset_common_seq_show,
-		.write_string = cpuset_write_resmask,
+		.write = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * MAX_NUMNODES),
 		.private = FILE_MEMLIST,
 	},
mm/hugetlb_cgroup.c +9 -8
index 595d7fd..faea871 100644
@@ -253,15 +253,16 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 	return res_counter_read_u64(&h_cg->hugepage[idx], name);
 }
 
-static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
-				struct cftype *cft, char *buffer)
+static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
 	int idx, name, ret;
 	unsigned long long val;
-	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	buf = strstrip(buf);
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_LIMIT:

@@ -271,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
 			break;
 		}
 		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);

@@ -280,7 +281,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,

@@ -331,7 +332,7 @@ static void __init __hugetlb_cgroup_file_init(int idx)
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
 	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
 	cft->read_u64 = hugetlb_cgroup_read_u64;
-	cft->write_string = hugetlb_cgroup_write;
+	cft->write = hugetlb_cgroup_write;
 
 	/* Add the usage file */
 	cft = &h->cgroup_files[1];
mm/memcontrol.c +25 -21

135 lines not on this page · raw message

net/ipv4/tcp_memcontrol.c +9 -7
index d4f015a..841fd3f 100644
@@ -102,17 +102,19 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
-static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer)
+static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	unsigned long long val;
 	int ret = 0;
 
-	switch (cft->private) {
+	buf = strstrip(buf);
+
+	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = tcp_update_limit(memcg, val);

@@ -121,7 +123,7 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)

@@ -193,7 +195,7 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.limit_in_bytes",
-		.write_string = tcp_cgroup_write,
+		.write = tcp_cgroup_write,
 		.read_u64 = tcp_cgroup_read,
 		.private = RES_LIMIT,
 	},
security/device_cgroup.c +7 -7
index 8365909..82d6b4f 100644
@@ -651,27 +651,27 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	return rc;
 }
 
-static int devcgroup_access_write(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buffer)
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
 	int retval;
 
 	mutex_lock(&devcgroup_mutex);
-	retval = devcgroup_update_access(css_to_devcgroup(css),
-					 cft->private, buffer);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
 	mutex_unlock(&devcgroup_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 static struct cftype dev_cgroup_files[] = {
 	{
 		.name = "allow",
-		.write_string  = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_ALLOW,
 	},
 	{
 		.name = "deny",
-		.write_string = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_DENY,
 	},
 	{
Signature · 1 line
1.9.0
Acked-by on v1 2/5
#3 lore raw

Re: [PATCH 2/5] cgroup: replace cftype->write_string() with cftype->write()

Quoted 41 lines · Tejun Heo

Convert all cftype->write_string() users to the new cftype->write() which maps directly to kernfs write operation and has full access to kernfs and cgroup contexts. The conversions are mostly mechanical.

* @css and @cft are accessed using of_css() and of_cft() accessors respectively instead of being specified as arguments.

* Should return @nbytes on success instead of 0.

* @buf is not trimmed automatically. Trim if necessary. Note that blkcg doesn't need this as blkg_conf_prep() can already handle whitespaces.

cftype->write_string() has no user left after the conversions and removed.

While at it, remove unnecessary local variable @p in cgroup_subtree_control_write() and stale comment about CGROUP_LOCAL_BUFFER_SIZE in cgroup_freezer.c.

This patch doesn't introduce any visible behavior changes.

Signed-off-by Tejun Heo <[email protected]>
Cc Vivek Goyal <[email protected]>
Cc Jens Axboe <[email protected]>
Cc Li Zefan <[email protected]>
Cc Johannes Weiner <[email protected]>
Cc Michal Hocko <[email protected]>
Cc Aristeu Rozanski <[email protected]>
---
 block/blk-throttle.c      | 32 ++++++++++++++++----------------
 block/cfq-iosched.c       | 28 ++++++++++++++--------------
 include/linux/cgroup.h    | 10 +---------
 kernel/cgroup.c           | 38 +++++++++++++++++++-------------------
 kernel/cgroup_freezer.c   | 20 +++++++++-----------
 kernel/cpuset.c           | 16 +++++++++-------
 mm/hugetlb_cgroup.c       | 17 +++++++++--------
 mm/memcontrol.c           | 46 +++++++++++++++++++++++++---------------------
 net/ipv4/tcp_memcontrol.c | 16 +++++++++-------
 security/device_cgroup.c  | 14 +++++++-------
 10 files changed, 118 insertions(+), 119 deletions(-)

(...)

Quoted 29 lines
security/device_cgroup.c +5 -6
index 8365909..82d6b4f 100644
@@ -651,27 +651,27 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	return rc;
 }
 
-static int devcgroup_access_write(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buffer)
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
 	int retval;
 
 	mutex_lock(&devcgroup_mutex);
-	retval = devcgroup_update_access(css_to_devcgroup(css),
-					 cft->private, buffer);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
 	mutex_unlock(&devcgroup_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 static struct cftype dev_cgroup_files[] = {
 	{
 		.name = "allow",
-		.write_string  = devcgroup_access_write,

security/device_cgroup.c static int devcgroup_update_access(struct dev_cgroup *devcgroup, · line 677

Quoted 10 lines
security/device_cgroup.c +2 -1
+		.write = devcgroup_access_write,
 		.private = DEVCG_ALLOW,
 	},
 	{
 		.name = "deny",
-		.write_string = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_DENY,
 	},
 	{

for the device_cgroup part

Acked-by Aristeu Rozanski <[email protected]>
Signature · 1 line
Aristeu
author maintainer
#4 lore raw

PATCH v2 2/5 cgroup: replace cftype->write_string() with cftype->write()

In reply to Tejun Heo

Convert all cftype->write_string() users to the new cftype->write() which maps directly to kernfs write operation and has full access to kernfs and cgroup contexts. The conversions are mostly mechanical.

* @css and @cft are accessed using of_css() and of_cft() accessors respectively instead of being specified as arguments.

* Should return @nbytes on success instead of 0.

* @buf is not trimmed automatically. Trim if necessary. Note that blkcg and netprio don't need this as the parsers already handle whitespaces.

cftype->write_string() has no user left after the conversions and removed.

While at it, remove unnecessary local variable @p in cgroup_subtree_control_write() and stale comment about CGROUP_LOCAL_BUFFER_SIZE in cgroup_freezer.c.

This patch doesn't introduce any visible behavior changes.

v2: netprio was missing from conversion. Converted.

Signed-off-by Tejun Heo <[email protected]>
Cc Vivek Goyal <[email protected]>
Cc Jens Axboe <axboe-tSWWG44O7X1aa/[email protected]>
Cc Li Zefan <[email protected]>
Cc Johannes Weiner <[email protected]>
Cc Michal Hocko <[email protected]>
Cc Aristeu Rozanski <[email protected]>
Cc Neil Horman <[email protected]>
Cc "David S. Miller" <davem-fT/PcQaiUtIeIZ0/[email protected]>
---
 block/blk-throttle.c      | 32 ++++++++++++++++----------------
 block/cfq-iosched.c       | 28 ++++++++++++++--------------
 include/linux/cgroup.h    | 10 +---------
 kernel/cgroup.c           | 38 +++++++++++++++++++-------------------
 kernel/cgroup_freezer.c   | 20 +++++++++-----------
 kernel/cpuset.c           | 16 +++++++++-------
 mm/hugetlb_cgroup.c       | 17 +++++++++--------
 mm/memcontrol.c           | 46 +++++++++++++++++++++++++---------------------
 net/core/netprio_cgroup.c | 12 ++++++------
 net/ipv4/tcp_memcontrol.c | 16 +++++++++-------
 security/device_cgroup.c  | 14 +++++++-------
 11 files changed, 124 insertions(+), 125 deletions(-)
block/blk-throttle.c +16 -16
index 033745c..5e8fd1b 100644
@@ -1346,10 +1346,10 @@ static int tg_print_conf_uint(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
-		       const char *buf, bool is_u64)
+static ssize_t tg_set_conf(struct kernfs_open_file *of,
+			   char *buf, size_t nbytes, loff_t off, bool is_u64)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct throtl_grp *tg;
 	struct throtl_service_queue *sq;

@@ -1368,9 +1368,9 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 		ctx.v = -1;
 
 	if (is_u64)
-		*(u64 *)((void *)tg + cft->private) = ctx.v;
+		*(u64 *)((void *)tg + of_cft(of)->private) = ctx.v;
 	else
-		*(unsigned int *)((void *)tg + cft->private) = ctx.v;
+		*(unsigned int *)((void *)tg + of_cft(of)->private) = ctx.v;
 
 	throtl_log(&tg->service_queue,
 		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",

@@ -1404,19 +1404,19 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 	}
 
 	blkg_conf_finish(&ctx);
-	return 0;
+	return nbytes;
 }
 
-static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
-			   char *buf)
+static ssize_t tg_set_conf_u64(struct kernfs_open_file *of,
+			       char *buf, size_t nbytes, loff_t off)
 {
-	return tg_set_conf(css, cft, buf, true);
+	return tg_set_conf(of, buf, nbytes, off, true);
 }
 
-static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buf)
+static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	return tg_set_conf(css, cft, buf, false);
+	return tg_set_conf(of, buf, nbytes, off, false);
 }
 
 static struct cftype throtl_files[] = {

@@ -1424,25 +1424,25 @@ static struct cftype throtl_files[] = {
 		.name = "throttle.read_bps_device",
 		.private = offsetof(struct throtl_grp, bps[READ]),
 		.seq_show = tg_print_conf_u64,
-		.write_string = tg_set_conf_u64,
+		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
 		.seq_show = tg_print_conf_u64,
-		.write_string = tg_set_conf_u64,
+		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
 		.seq_show = tg_print_conf_uint,
-		.write_string = tg_set_conf_uint,
+		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
 		.seq_show = tg_print_conf_uint,
-		.write_string = tg_set_conf_uint,
+		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.io_service_bytes",
block/cfq-iosched.c +14 -14
index e0985f1..a73020b 100644
@@ -1670,11 +1670,11 @@ static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				    struct cftype *cft, const char *buf,
-				    bool is_leaf_weight)
+static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
+					char *buf, size_t nbytes, loff_t off,
+					bool is_leaf_weight)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct cfq_group *cfqg;
 	int ret;

@@ -1697,19 +1697,19 @@ static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
 	}
 
 	blkg_conf_finish(&ctx);
-	return ret;
+	return ret ?: nbytes;
 }
 
-static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buf)
+static ssize_t cfqg_set_weight_device(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
-	return __cfqg_set_weight_device(css, cft, buf, false);
+	return __cfqg_set_weight_device(of, buf, nbytes, off, false);
 }
 
-static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
-				       struct cftype *cft, char *buf)
+static ssize_t cfqg_set_leaf_weight_device(struct kernfs_open_file *of,
+					   char *buf, size_t nbytes, loff_t off)
 {
-	return __cfqg_set_weight_device(css, cft, buf, true);
+	return __cfqg_set_weight_device(of, buf, nbytes, off, true);
 }
 
 static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,

@@ -1837,7 +1837,7 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "weight_device",
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cfqg_print_leaf_weight_device,
-		.write_string = cfqg_set_leaf_weight_device,
+		.write = cfqg_set_leaf_weight_device,
 	},
 	{
 		.name = "weight",

@@ -1851,7 +1851,7 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "weight_device",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cfqg_print_weight_device,
-		.write_string = cfqg_set_weight_device,
+		.write = cfqg_set_weight_device,
 	},
 	{
 		.name = "weight",

@@ -1863,7 +1863,7 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "leaf_weight_device",
 		.seq_show = cfqg_print_leaf_weight_device,
-		.write_string = cfqg_set_leaf_weight_device,
+		.write = cfqg_set_leaf_weight_device,
 	},
 	{
 		.name = "leaf_weight",
include/linux/cgroup.h +1 -9
index da7a0ca..5f717d7 100644
@@ -455,8 +455,7 @@ struct cftype {
 
 	/*
 	 * The maximum length of string, excluding trailing nul, that can
-	 * be passed to write_string.  If < PAGE_SIZE-1, PAGE_SIZE-1 is
-	 * assumed.
+	 * be passed to write.  If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed.
 	 */
 	size_t max_write_len;
 

@@ -503,13 +502,6 @@ struct cftype {
 			 s64 val);
 
 	/*
-	 * write_string() is passed a nul-terminated kernelspace
-	 * buffer of maximum length determined by max_write_len.
-	 * Returns 0 or -ve error code.
-	 */
-	int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer);
-	/*
 	 * trigger() callback can be used to get some kick from the
 	 * userspace, when the actual string written is not important
 	 * at all. The private field can be used to determine the
kernel/cgroup.c +19 -19
index f8fc556..39d7f65 100644
@@ -1035,7 +1035,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 		mode |= S_IRUGO;
 
 	if (cft->write_u64 || cft->write_s64 || cft->write ||
-	    cft->write_string || cft->trigger)
+	    cft->trigger)
 		mode |= S_IWUSR;
 
 	return mode;

@@ -2352,20 +2352,21 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
 	return attach_task_by_pid(css->cgroup, tgid, true);
 }
 
-static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
-				      struct cftype *cft, char *buffer)
+static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
+					  char *buf, size_t nbytes, loff_t off)
 {
-	struct cgroup_root *root = css->cgroup->root;
+	struct cgroup *cgrp = of_css(of)->cgroup;
+	struct cgroup_root *root = cgrp->root;
 
 	BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
-	if (!cgroup_lock_live_group(css->cgroup))
+	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 	spin_lock(&release_agent_path_lock);
-	strlcpy(root->release_agent_path, buffer,
+	strlcpy(root->release_agent_path, strstrip(buf),
 		sizeof(root->release_agent_path));
 	spin_unlock(&release_agent_path_lock);
 	mutex_unlock(&cgroup_mutex);
-	return 0;
+	return nbytes;
 }
 
 static int cgroup_release_agent_show(struct seq_file *seq, void *v)

@@ -2530,21 +2531,22 @@ out_finish:
 }
 
 /* change the enabled child controllers for a cgroup in the default hierarchy */
-static int cgroup_subtree_control_write(struct cgroup_subsys_state *dummy_css,
-					struct cftype *cft, char *buffer)
+static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
 {
 	unsigned int enable = 0, disable = 0;
-	struct cgroup *cgrp = dummy_css->cgroup, *child;
+	struct cgroup *cgrp = of_css(of)->cgroup, *child;
 	struct cgroup_subsys *ss;
-	char *tok, *p;
+	char *tok;
 	int ssid, ret;
 
 	/*
 	 * Parse input - space separated list of subsystem names prefixed
 	 * with either + or -.
 	 */
-	p = buffer;
-	while ((tok = strsep(&p, " "))) {
+	buf = strstrip(buf);
+	while ((tok = strsep(&buf, " "))) {
 		if (tok[0] =='\0')
 			continue;
 		for_each_subsys(ss, ssid) {

@@ -2692,7 +2694,7 @@ out_unlock_tree:
 out_unbreak:
 	kernfs_unbreak_active_protection(cgrp->control_kn);
 	cgroup_put(cgrp);
-	return ret;
+	return ret ?: nbytes;
 
 err_undo_css:
 	cgrp->child_subsys_mask &= ~enable;

@@ -2738,9 +2740,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	css = cgroup_css(cgrp, cft->ss);
 	rcu_read_unlock();
 
-	if (cft->write_string) {
-		ret = cft->write_string(css, cft, strstrip(buf));
-	} else if (cft->write_u64) {
+	if (cft->write_u64) {
 		unsigned long long v;
 		ret = kstrtoull(buf, 0, &v);
 		if (!ret)

@@ -3984,7 +3984,7 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cgroup.subtree_control",
 		.flags = CFTYPE_ONLY_ON_DFL,
 		.seq_show = cgroup_subtree_control_show,
-		.write_string = cgroup_subtree_control_write,
+		.write = cgroup_subtree_control_write,
 	},
 	{
 		.name = "cgroup.populated",

@@ -4018,7 +4018,7 @@ static struct cftype cgroup_base_files[] = {
 		.name = "release_agent",
 		.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cgroup_release_agent_show,
-		.write_string = cgroup_release_agent_write,
+		.write = cgroup_release_agent_write,
 		.max_write_len = PATH_MAX - 1,
 	},
 	{ }	/* terminate */
kernel/cgroup_freezer.c +9 -11
index 2bc4a22..d2b4bc7 100644
@@ -71,10 +71,6 @@ bool cgroup_freezing(struct task_struct *task)
 	return ret;
 }
 
-/*
- * cgroups_write_string() limits the size of freezer state strings to
- * CGROUP_LOCAL_BUFFER_SIZE
- */
 static const char *freezer_state_strs(unsigned int state)
 {
 	if (state & CGROUP_FROZEN)

@@ -441,20 +437,22 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 	rcu_read_unlock();
 }
 
-static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			 char *buffer)
+static ssize_t freezer_write(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
 {
 	bool freeze;
 
-	if (strcmp(buffer, freezer_state_strs(0)) == 0)
+	buf = strstrip(buf);
+
+	if (strcmp(buf, freezer_state_strs(0)) == 0)
 		freeze = false;
-	else if (strcmp(buffer, freezer_state_strs(CGROUP_FROZEN)) == 0)
+	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0)
 		freeze = true;
 	else
 		return -EINVAL;
 
-	freezer_change_state(css_freezer(css), freeze);
-	return 0;
+	freezer_change_state(css_freezer(of_css(of)), freeze);
+	return nbytes;
 }
 
 static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css,

@@ -478,7 +476,7 @@ static struct cftype files[] = {
 		.name = "state",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = freezer_read,
-		.write_string = freezer_write,
+		.write = freezer_write,
 	},
 	{
 		.name = "self_freezing",
kernel/cpuset.c +9 -7
index 7c0e8da..97cbb59 100644
@@ -1603,13 +1603,15 @@ out_unlock:
 /*
  * Common handling for a write to a "cpus" or "mems" file.
  */
-static int cpuset_write_resmask(struct cgroup_subsys_state *css,
-				struct cftype *cft, char *buf)
+static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cpuset *cs = css_cs(of_css(of));
 	struct cpuset *trialcs;
 	int retval = -ENODEV;
 
+	buf = strstrip(buf);
+
 	/*
 	 * CPU or memory hotunplug may leave @cs w/o any execution
 	 * resources, in which case the hotplug code asynchronously updates

@@ -1633,7 +1635,7 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 		goto out_unlock;
 	}
 
-	switch (cft->private) {
+	switch (of_cft(of)->private) {
 	case FILE_CPULIST:
 		retval = update_cpumask(cs, trialcs, buf);
 		break;

@@ -1648,7 +1650,7 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 	free_trial_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 /*

@@ -1750,7 +1752,7 @@ static struct cftype files[] = {
 	{
 		.name = "cpus",
 		.seq_show = cpuset_common_seq_show,
-		.write_string = cpuset_write_resmask,
+		.write = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * NR_CPUS),
 		.private = FILE_CPULIST,
 	},

@@ -1758,7 +1760,7 @@ static struct cftype files[] = {
 	{
 		.name = "mems",
 		.seq_show = cpuset_common_seq_show,
-		.write_string = cpuset_write_resmask,
+		.write = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * MAX_NUMNODES),
 		.private = FILE_MEMLIST,
 	},
mm/hugetlb_cgroup.c +9 -8
index 595d7fd..faea871 100644
@@ -253,15 +253,16 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 	return res_counter_read_u64(&h_cg->hugepage[idx], name);
 }
 
-static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
-				struct cftype *cft, char *buffer)
+static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
 	int idx, name, ret;
 	unsigned long long val;
-	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	buf = strstrip(buf);
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_LIMIT:

@@ -271,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
 			break;
 		}
 		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);

@@ -280,7 +281,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,

@@ -331,7 +332,7 @@ static void __init __hugetlb_cgroup_file_init(int idx)
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
 	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
 	cft->read_u64 = hugetlb_cgroup_read_u64;
-	cft->write_string = hugetlb_cgroup_write;
+	cft->write = hugetlb_cgroup_write;
 
 	/* Add the usage file */
 	cft = &h->cgroup_files[1];
mm/memcontrol.c +25 -21

135 lines not on this page · raw message

net/core/netprio_cgroup.c +6 -6
index 3825f66..b990cef 100644
@@ -185,15 +185,15 @@ static int read_priomap(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
-			 char *buffer)
+static ssize_t write_priomap(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
 {
 	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
 	u32 prio;
 	int ret;
 
-	if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+	if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
 		return -EINVAL;
 
 	dev = dev_get_by_name(&init_net, devname);

@@ -202,11 +202,11 @@ static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	rtnl_lock();
 
-	ret = netprio_set_prio(css, dev, prio);
+	ret = netprio_set_prio(of_css(of), dev, prio);
 
 	rtnl_unlock();
 	dev_put(dev);
-	return ret;
+	return ret ?: nbytes;
 }
 
 static int update_netprio(const void *v, struct file *file, unsigned n)

@@ -239,7 +239,7 @@ static struct cftype ss_files[] = {
 	{
 		.name = "ifpriomap",
 		.seq_show = read_priomap,
-		.write_string = write_priomap,
+		.write = write_priomap,
 	},
 	{ }	/* terminate */
 };
net/ipv4/tcp_memcontrol.c +9 -7
index d4f015a..841fd3f 100644
@@ -102,17 +102,19 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
-static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer)
+static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	unsigned long long val;
 	int ret = 0;
 
-	switch (cft->private) {
+	buf = strstrip(buf);
+
+	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = tcp_update_limit(memcg, val);

@@ -121,7 +123,7 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)

@@ -193,7 +195,7 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.limit_in_bytes",
-		.write_string = tcp_cgroup_write,
+		.write = tcp_cgroup_write,
 		.read_u64 = tcp_cgroup_read,
 		.private = RES_LIMIT,
 	},
security/device_cgroup.c +7 -7
index 8365909..82d6b4f 100644
@@ -651,27 +651,27 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	return rc;
 }
 
-static int devcgroup_access_write(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buffer)
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
 	int retval;
 
 	mutex_lock(&devcgroup_mutex);
-	retval = devcgroup_update_access(css_to_devcgroup(css),
-					 cft->private, buffer);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
 	mutex_unlock(&devcgroup_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 static struct cftype dev_cgroup_files[] = {
 	{
 		.name = "allow",
-		.write_string  = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_ALLOW,
 	},
 	{
 		.name = "deny",
-		.write_string = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_DENY,
 	},
 	{
Signature · 1 line
1.9.0
#5 lore raw

Re: [PATCH 2/5] cgroup: replace cftype->write_string() with cftype->write()

In reply to Tejun Heo
Quoted 29 lines · Tejun Heo

Convert all cftype->write_string() users to the new cftype->write() which maps directly to kernfs write operation and has full access to kernfs and cgroup contexts. The conversions are mostly mechanical.

* @css and @cft are accessed using of_css() and of_cft() accessors respectively instead of being specified as arguments.

* Should return @nbytes on success instead of 0.

* @buf is not trimmed automatically. Trim if necessary. Note that blkcg doesn't need this as blkg_conf_prep() can already handle whitespaces.

cftype->write_string() has no user left after the conversions and removed.

While at it, remove unnecessary local variable @p in cgroup_subtree_control_write() and stale comment about CGROUP_LOCAL_BUFFER_SIZE in cgroup_freezer.c.

This patch doesn't introduce any visible behavior changes.

Signed-off-by Tejun Heo <[email protected]>
Cc Vivek Goyal <[email protected]>
Cc Jens Axboe <axboe-tSWWG44O7X1aa/[email protected]>
Cc Li Zefan <[email protected]>
Cc Johannes Weiner <[email protected]>
Cc Michal Hocko <[email protected]>
Cc Aristeu Rozanski <[email protected]>
Quoted 3 lines
---
 block/blk-throttle.c      | 32 ++++++++++++++++----------------
 block/cfq-iosched.c       | 28 ++++++++++++++--------------

Ack to blk-throttle.c and cfq-iosched.c changes.

thanks
Vivek

author maintainer
#6 lore raw

PATCH 3/5 cgroup: replace cftype->trigger() with cftype->write()

In reply to Tejun Heo

cftype->trigger() is pointless. It's trivial to ignore the input buffer from a regular ->write() operation. Convert all ->trigger() users to ->write() and remove ->trigger().

This patch doesn't introduce any visible behavior changes.

Signed-off-by Tejun Heo <[email protected]>
Cc Johannes Weiner <[email protected]>
Cc Michal Hocko <[email protected]>
---
 include/linux/cgroup.h    |  8 --------
 kernel/cgroup.c           |  5 +----
 mm/hugetlb_cgroup.c       | 16 ++++++++--------
 mm/memcontrol.c           | 34 ++++++++++++++++++----------------
 net/ipv4/tcp_memcontrol.c | 15 ++++++++-------
 5 files changed, 35 insertions(+), 43 deletions(-)
include/linux/cgroup.h +0 -8
index 5f717d7..f8cfadb 100644
@@ -502,14 +502,6 @@ struct cftype {
 			 s64 val);
 
 	/*
-	 * trigger() callback can be used to get some kick from the
-	 * userspace, when the actual string written is not important
-	 * at all. The private field can be used to determine the
-	 * kick type for multiplexing.
-	 */
-	int (*trigger)(struct cgroup_subsys_state *css, unsigned int event);
-
-	/*
 	 * write() is the generic write callback which maps directly to
 	 * kernfs write operation and overrides all other operations.
 	 * Maximum write size is determined by ->max_write_len.  Use
kernel/cgroup.c +1 -4
index 8939fe4..4b340c3 100644
@@ -1034,8 +1034,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 	if (cft->read_u64 || cft->read_s64 || cft->seq_show)
 		mode |= S_IRUGO;
 
-	if (cft->write_u64 || cft->write_s64 || cft->write ||
-	    cft->trigger)
+	if (cft->write_u64 || cft->write_s64 || cft->write)
 		mode |= S_IWUSR;
 
 	return mode;

@@ -2748,8 +2747,6 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 		ret = kstrtoll(buf, 0, &v);
 		if (!ret)
 			ret = cft->write_s64(css, cft, v);
-	} else if (cft->trigger) {
-		ret = cft->trigger(css, (unsigned int)cft->private);
 	} else {
 		ret = -EINVAL;
 	}
mm/hugetlb_cgroup.c +8 -8
index faea871..8597daa 100644
@@ -284,14 +284,14 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
-static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,
-				unsigned int event)
+static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
 	int idx, name, ret = 0;
-	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(event);
-	name = MEMFILE_ATTR(event);
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_MAX_USAGE:

@@ -304,7 +304,7 @@ static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static char *mem_fmt(char *buf, int size, unsigned long hsize)

@@ -344,14 +344,14 @@ static void __init __hugetlb_cgroup_file_init(int idx)
 	cft = &h->cgroup_files[2];
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
 	cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
-	cft->trigger = hugetlb_cgroup_reset;
+	cft->write = hugetlb_cgroup_reset;
 	cft->read_u64 = hugetlb_cgroup_read_u64;
 
 	/* Add the failcntfile */
 	cft = &h->cgroup_files[3];
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
 	cft->private  = MEMFILE_PRIVATE(idx, RES_FAILCNT);
-	cft->trigger  = hugetlb_cgroup_reset;
+	cft->write = hugetlb_cgroup_reset;
 	cft->read_u64 = hugetlb_cgroup_read_u64;
 
 	/* NULL terminate the last cft */
mm/memcontrol.c +18 -16
index 0258419..0845097 100644
@@ -4885,14 +4885,15 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 	return 0;
 }
 
-static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css,
-					unsigned int event)
+static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 
 	if (mem_cgroup_is_root(memcg))
 		return -EINVAL;
-	return mem_cgroup_force_empty(memcg);
+	return mem_cgroup_force_empty(memcg) ?: nbytes;
 }
 
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,

@@ -5218,14 +5219,15 @@ out:
 	*memsw_limit = min_memsw_limit;
 }
 
-static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
+static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
+				size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	int name;
 	enum res_type type;
 
-	type = MEMFILE_TYPE(event);
-	name = MEMFILE_ATTR(event);
+	type = MEMFILE_TYPE(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_MAX_USAGE:

@@ -5250,7 +5252,7 @@ static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 		break;
 	}
 
-	return 0;
+	return nbytes;
 }
 
 static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,

@@ -6103,7 +6105,7 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{

@@ -6121,7 +6123,7 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "failcnt",
 		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{

@@ -6130,7 +6132,7 @@ static struct cftype mem_cgroup_files[] = {
 	},
 	{
 		.name = "force_empty",
-		.trigger = mem_cgroup_force_empty_write,
+		.write = mem_cgroup_force_empty_write,
 	},
 	{
 		.name = "use_hierarchy",

@@ -6184,13 +6186,13 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "kmem.failcnt",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "kmem.max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 #ifdef CONFIG_SLABINFO

@@ -6213,7 +6215,7 @@ static struct cftype memsw_cgroup_files[] = {
 	{
 		.name = "memsw.max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{

@@ -6225,7 +6227,7 @@ static struct cftype memsw_cgroup_files[] = {
 	{
 		.name = "memsw.failcnt",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{ },	/* terminate */
net/ipv4/tcp_memcontrol.c +8 -7
index 841fd3f..f7a2ec3 100644
@@ -170,17 +170,18 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 	return val;
 }
 
-static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
+static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg;
 	struct cg_proto *cg_proto;
 
-	memcg = mem_cgroup_from_css(css);
+	memcg = mem_cgroup_from_css(of_css(of));
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
-		return 0;
+		return nbytes;
 
-	switch (event) {
+	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
 		res_counter_reset_max(&cg_proto->memory_allocated);
 		break;

@@ -189,7 +190,7 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 		break;
 	}
 
-	return 0;
+	return nbytes;
 }
 
 static struct cftype tcp_files[] = {

@@ -207,13 +208,13 @@ static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.failcnt",
 		.private = RES_FAILCNT,
-		.trigger = tcp_cgroup_reset,
+		.write = tcp_cgroup_reset,
 		.read_u64 = tcp_cgroup_read,
 	},
 	{
 		.name = "kmem.tcp.max_usage_in_bytes",
 		.private = RES_MAX_USAGE,
-		.trigger = tcp_cgroup_reset,
+		.write = tcp_cgroup_reset,
 		.read_u64 = tcp_cgroup_read,
 	},
 	{ }	/* terminate */
Signature · 1 line
1.9.0
author maintainer
#7 lore raw

PATCH 4/5 cgroup: convert "tasks" and "cgroup.procs" handle to use cftype->write()

In reply to Tejun Heo

cgroup_tasks_write() and cgroup_procs_write() are currently using cftype->write_u64(). This patch converts them to use cftype->write() instead. This allows access to the associated kernfs_open_file which will be necessary to implement the planned kernfs active protection manipulation for these files.

This shifts buffer parsing to attach_task_by_pid() and makes it return @nbytes on success. Let's rename it to __cgroup_procs_write() to clearly indicate that this is a write handler implementation.

This patch doesn't introduce any visible behavior changes.

Signed-off-by Tejun Heo <[email protected]>
---
 kernel/cgroup.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)
kernel/cgroup.c +16 -10
index 4b340c3..06ad484 100644
@@ -2232,12 +2232,18 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
  * function to attach either it or all tasks in its threadgroup. Will lock
  * cgroup_mutex and threadgroup.
  */
-static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
+static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
+				    size_t nbytes, loff_t off, bool threadgroup)
 {
 	struct task_struct *tsk;
 	const struct cred *cred = current_cred(), *tcred;
+	struct cgroup *cgrp = of_css(of)->cgroup;
+	pid_t pid;
 	int ret;
 
+	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
+		return -EINVAL;
+
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 

@@ -2305,7 +2311,7 @@ retry_find_task:
 	put_task_struct(tsk);
 out_unlock_cgroup:
 	mutex_unlock(&cgroup_mutex);
-	return ret;
+	return ret ?: nbytes;
 }
 
 /**

@@ -2339,16 +2345,16 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 
-static int cgroup_tasks_write(struct cgroup_subsys_state *css,
-			      struct cftype *cft, u64 pid)
+static ssize_t cgroup_tasks_write(struct kernfs_open_file *of,
+				  char *buf, size_t nbytes, loff_t off)
 {
-	return attach_task_by_pid(css->cgroup, pid, false);
+	return __cgroup_procs_write(of, buf, nbytes, off, false);
 }
 
-static int cgroup_procs_write(struct cgroup_subsys_state *css,
-			      struct cftype *cft, u64 tgid)
+static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
+				  char *buf, size_t nbytes, loff_t off)
 {
-	return attach_task_by_pid(css->cgroup, tgid, true);
+	return __cgroup_procs_write(of, buf, nbytes, off, true);
 }
 
 static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,

@@ -3951,7 +3957,7 @@ static struct cftype cgroup_base_files[] = {
 		.seq_stop = cgroup_pidlist_stop,
 		.seq_show = cgroup_pidlist_show,
 		.private = CGROUP_FILE_PROCS,
-		.write_u64 = cgroup_procs_write,
+		.write = cgroup_procs_write,
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	{

@@ -4000,7 +4006,7 @@ static struct cftype cgroup_base_files[] = {
 		.seq_stop = cgroup_pidlist_stop,
 		.seq_show = cgroup_pidlist_show,
 		.private = CGROUP_FILE_TASKS,
-		.write_u64 = cgroup_tasks_write,
+		.write = cgroup_tasks_write,
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	{
Signature · 1 line
1.9.0
author maintainer
#8 lore raw

PATCH 5/5 cgroup: remove cgroup->control_kn

In reply to Tejun Heo

Now that cgroup_subtree_control_write() has access to the associated kernfs_open_file and thus the kernfs_node, there's no need to cache it in cgroup->control_kn on creation. Remove cgroup->control_kn and use @of->kn directly.

Signed-off-by Tejun Heo <[email protected]>
---
 include/linux/cgroup.h | 1 -
 kernel/cgroup.c        | 8 +++-----
 2 files changed, 3 insertions(+), 6 deletions(-)
include/linux/cgroup.h +0 -1
index f8cfadb..037fa80 100644
@@ -179,7 +179,6 @@ struct cgroup {
 
 	struct cgroup *parent;		/* my parent */
 	struct kernfs_node *kn;		/* cgroup kernfs entry */
-	struct kernfs_node *control_kn;	/* kn for "cgroup.subtree_control" */
 	struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */
 
 	/*
kernel/cgroup.c +3 -5
index 06ad484..eeb4b62 100644
@@ -2578,7 +2578,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	 * active_ref protection.
 	 */
 	cgroup_get(cgrp);
-	kernfs_break_active_protection(cgrp->control_kn);
+	kernfs_break_active_protection(of->kn);
 
 	mutex_lock(&cgroup_tree_mutex);
 

@@ -2695,7 +2695,7 @@ out_unlock:
 out_unlock_tree:
 	mutex_unlock(&cgroup_tree_mutex);
 out_unbreak:
-	kernfs_unbreak_active_protection(cgrp->control_kn);
+	kernfs_unbreak_active_protection(of->kn);
 	cgroup_put(cgrp);
 	return ret ?: nbytes;
 

@@ -2885,9 +2885,7 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
 		return ret;
 	}
 
-	if (cft->seq_show == cgroup_subtree_control_show)
-		cgrp->control_kn = kn;
-	else if (cft->seq_show == cgroup_populated_show)
+	if (cft->seq_show == cgroup_populated_show)
 		cgrp->populated_kn = kn;
 	return 0;
 }
Signature · 1 line
1.9.0
author maintainer
#9 lore raw
In reply to Tejun Heo
Quoted 8 lines · Tejun Heo

This patchset is on top of

cgroup/for-3.16 12d3089c192c ("kernel/cpuset.c: convert printk to pr_foo()")
+ [1] [PATCHSET cgroup/for-3.16] cgroup: post unified hierarchy fixes and updates

and available on the following git branch.

git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-post-unified-updates

Refreshed without content change on top of

b9a63d0116e8 ("Merge branch 'for-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu into for-3.16")
+ [1] [PATCHSET v2 cgroup/for-3.16] cgroup: post unified hierarchy fixes and updates

and available on the following git branch.

git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-post-unified-updates-v2

Signature · 3 lines
tejun

[1] http://lkml.kernel.org/g/1399663975-315-1-git-send-email-tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org
Acked-by on v1 1/1
#10 lore raw
In reply to Tejun Heo
Quoted 41 lines · Tejun Heo

Hello,

This patchset implements a new cftype operation ->write() and replace ->write_string() and ->trigger() with it. ->write() is similar to ->write_string() but maps directly to the kernfs write operation and has access to all available context information including the associated kernfs_open_file, which will make things like implementing kernfs active protection manipulation easier.

->write_string() becomes redundant and ->trigger() has always been spurious. This patch replaces all users of the two methods to ->write() and remove them.

This patchset contains the following five patches.

0001-cgroup-implement-cftype-write.patch 0002-cgroup-replace-cftype-write_string-with-cftype-write.patch 0003-cgroup-replace-cftype-trigger-with-cftype-write.patch 0004-cgroup-convert-tasks-and-cgroup.procs-handle-to-use-.patch 0005-cgroup-remove-cgroup-control_kn.patch

0001 implements cftype->write().

0002-0003 replace cftype->write_string() and ->trigger() with it.

0004 convert "tasks" and "cgroup.procs" handler too.

0005 removes cgroup->control_kn as the kernfs_node is now directly accessible from kernfs_open_file.

This patchset is on top of

cgroup/for-3.16 12d3089c192c ("kernel/cpuset.c: convert printk to pr_foo()")
+ [1] [PATCHSET cgroup/for-3.16] cgroup: post unified hierarchy fixes and updates

and available on the following git branch.

git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git review-post-unified-updates

diffstat follows.

Quoted 12 lines
 block/blk-throttle.c      |   32 ++++++++---------
 block/cfq-iosched.c       |   28 +++++++--------
 include/linux/cgroup.h    |   40 +++++++++++----------
 kernel/cgroup.c           |   85 +++++++++++++++++++++++-----------------------
 kernel/cgroup_freezer.c   |   20 ++++------
 kernel/cpuset.c           |   16 ++++----
 mm/hugetlb_cgroup.c       |   33 +++++++++--------
 mm/memcontrol.c           |   80 +++++++++++++++++++++++--------------------
 net/ipv4/tcp_memcontrol.c |   31 +++++++++-------
 security/device_cgroup.c  |   14 +++----
 10 files changed, 197 insertions(+), 182 deletions(-)
Acked-by Li Zefan <[email protected]>
author maintainer Applied
#11 lore raw
In reply to Tejun Heo
Quoted 13 lines · Tejun Heo

Hello,

This patchset implements a new cftype operation ->write() and replace ->write_string() and ->trigger() with it. ->write() is similar to ->write_string() but maps directly to the kernfs write operation and has access to all available context information including the associated kernfs_open_file, which will make things like implementing kernfs active protection manipulation easier.

->write_string() becomes redundant and ->trigger() has always been spurious. This patch replaces all users of the two methods to ->write() and remove them.

Quoted 7 lines

This patchset contains the following five patches.

0001-cgroup-implement-cftype-write.patch 0002-cgroup-replace-cftype-write_string-with-cftype-write.patch 0003-cgroup-replace-cftype-trigger-with-cftype-write.patch 0004-cgroup-convert-tasks-and-cgroup.procs-handle-to-use-.patch 0005-cgroup-remove-cgroup-control_kn.patch

Applied to cgroup/for-3.16.

Thanks.

Signature · 1 line
tejun