From 555724a831b4a146e7bdf16ecc989cda032b076d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 12 May 2014 13:56:27 -0400 Subject: kernfs, sysfs, cgroup: restrict extra perm check on open to sysfs The kernfs open method - kernfs_fop_open() - inherited extra permission checks from sysfs. While the vfs layer allows ignoring the read/write permissions checks if the issuer has CAP_DAC_OVERRIDE, sysfs explicitly denied open regardless of the cap if the file doesn't have any of the UGO perms of the requested access or doesn't implement the requested operation. It can be debated whether this was a good idea or not but the behavior is too subtle and dangerous to change at this point. After cgroup got converted to kernfs, this extra perm check also got applied to cgroup breaking libcgroup which opens write-only files with O_RDWR as root. This patch gates the extra open permission check with a new flag KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK and enables it for sysfs. For sysfs, nothing changes. For cgroup, root now can perform any operation regardless of the permissions as it was before kernfs conversion. Note that kernfs still fails unimplemented operations with -EINVAL. While at it, add comments explaining KERNFS_ROOT flags. Signed-off-by: Tejun Heo Reported-by: Andrey Wagin Tested-by: Andrey Wagin Cc: Li Zefan References: http://lkml.kernel.org/g/CANaxB-xUm3rJ-Cbp72q-rQJO5mZe1qK6qXsQM=vh0U8upJ44+A@mail.gmail.com Fixes: 2bd59d48ebfb ("cgroup: convert to kernfs") Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index b0122dc6f96a..ca1be5c9136c 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -50,7 +50,24 @@ enum kernfs_node_flag { /* @flags for kernfs_create_root() */ enum kernfs_root_flag { - KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, + /* + * kernfs_nodes are created in the deactivated state and invisible. + * They require explicit kernfs_activate() to become visible. This + * can be used to make related nodes become visible atomically + * after all nodes are created successfully. + */ + KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, + + /* + * For regular flies, if the opener has CAP_DAC_OVERRIDE, open(2) + * succeeds regardless of the RW permissions. sysfs had an extra + * layer of enforcement where open(2) fails with -EACCES regardless + * of CAP_DAC_OVERRIDE if the permission doesn't have the + * respective read or write access at all (none of S_IRUGO or + * S_IWUGO) or the respective operation isn't implemented. The + * following flag enables that behavior. + */ + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, }; /* type-specific structures for kernfs_node union members */ -- cgit v1.2.3 From 5024ae29cd285ce9e736776414da645d3a91828c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 7 May 2014 21:31:17 -0400 Subject: cgroup: introduce task_css_is_root() Determining the css of a task usually requires RCU read lock as that's the only thing which keeps the returned css accessible till its reference is acquired; however, testing whether a task belongs to the root can be performed without dereferencing the returned css by comparing the returned pointer against the root one in init_css_set[] which never changes. Implement task_css_is_root() which can be invoked in any context. This will be used by the scheduled cgroup_freezer change. v2: cgroup no longer supports modular controllers. No need to export init_css_set. Pointed out by Li. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 15 +++++++++++++++ kernel/cgroup.c | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c2515851c1aa..d60904b9e505 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -473,6 +473,7 @@ struct cftype { }; extern struct cgroup_root cgrp_dfl_root; +extern struct css_set init_css_set; static inline bool cgroup_on_dfl(const struct cgroup *cgrp) { @@ -700,6 +701,20 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, return task_css_check(task, subsys_id, false); } +/** + * task_css_is_root - test whether a task belongs to the root css + * @task: the target task + * @subsys_id: the target subsystem ID + * + * Test whether @task belongs to the root css on the specified subsystem. + * May be invoked in any context. + */ +static inline bool task_css_is_root(struct task_struct *task, int subsys_id) +{ + return task_css_check(task, subsys_id, true) == + init_css_set.subsys[subsys_id]; +} + static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 11a03d67635a..3f1ca934a237 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -348,7 +348,7 @@ struct cgrp_cset_link { * reference-counted, to improve performance when child cgroups * haven't been created. */ -static struct css_set init_css_set = { +struct css_set init_css_set = { .refcount = ATOMIC_INIT(1), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .tasks = LIST_HEAD_INIT(init_css_set.tasks), -- cgit v1.2.3 From 4c358e15553ed88bf2ddae422624624e1dd663d1 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 15 May 2014 14:44:30 +1000 Subject: of: fix CONFIG_OF=n prototype of of_node_full_name() Make the CONFIG_OF=n prototpe of of_node_full_name() mateh the CONFIG_OF=y version. Fixes compile warnings like this: sound/soc/soc-core.c: In function 'soc_check_aux_dev': sound/soc/soc-core.c:1667:3: warning: passing argument 1 of 'of_node_full_name' discards 'const' qualifier from pointer target type [enabled by default] codecname = of_node_full_name(aux_dev->codec_of_node); when CONFIG_OF is not defined. Signed-off-by: Stephen Rothwell Signed-off-by: Grant Likely --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 3bad8d106e0e..e6f0988c1c68 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -349,7 +349,7 @@ int of_device_is_stdout_path(struct device_node *dn); #else /* CONFIG_OF */ -static inline const char* of_node_full_name(struct device_node *np) +static inline const char* of_node_full_name(const struct device_node *np) { return ""; } -- cgit v1.2.3