From 0415b00d175e0d8945e6785aad21b5f157976ce0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 24 Mar 2011 18:50:09 +0100 Subject: percpu: Always align percpu output section to PAGE_SIZE Percpu allocator honors alignment request upto PAGE_SIZE and both the percpu addresses in the percpu address space and the translated kernel addresses should be aligned accordingly. The calculation of the former depends on the alignment of percpu output section in the kernel image. The linker script macros PERCPU_VADDR() and PERCPU() are used to define this output section and the latter takes @align parameter. Several architectures are using @align smaller than PAGE_SIZE breaking percpu memory alignment. This patch removes @align parameter from PERCPU(), renames it to PERCPU_SECTION() and makes it always align to PAGE_SIZE. While at it, add PCPU_SETUP_BUG_ON() checks such that alignment problems are reliably detected and remove percpu alignment comment recently added in workqueue.c as the condition would trigger BUG way before reaching there. For um, this patch raises the alignment of percpu area. As the area is in .init, there shouldn't be any noticeable difference. This problem was discovered by David Howells while debugging boot failure on mn10300. Signed-off-by: Tejun Heo Acked-by: Mike Frysinger Cc: uclinux-dist-devel@blackfin.uclinux.org Cc: David Howells Cc: Jeff Dike Cc: user-mode-linux-devel@lists.sourceforge.net --- kernel/workqueue.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 04ef830690e..d30a502e8c6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2860,9 +2860,7 @@ static int alloc_cwqs(struct workqueue_struct *wq) } } - /* just in case, make sure it's actually aligned - * - this is affected by PERCPU() alignment in vmlinux.lds.S - */ + /* just in case, make sure it's actually aligned */ BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); return wq->cpu_wq.v ? 0 : -ENOMEM; } -- cgit v1.2.3-70-g09d2 From 17f60a7da150fdd0cfb9756f86a262daa72c835f Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 1 Apr 2011 17:07:50 -0400 Subject: capabilites: allow the application of capability limits to usermode helpers There is no way to limit the capabilities of usermodehelpers. This problem reared its head recently when someone complained that any user with cap_net_admin was able to load arbitrary kernel modules, even though the user didn't have cap_sys_module. The reason is because the actual load is done by a usermode helper and those always have the full cap set. This patch addes new sysctls which allow us to bound the permissions of usermode helpers. /proc/sys/kernel/usermodehelper/bset /proc/sys/kernel/usermodehelper/inheritable You must have CAP_SYS_MODULE and CAP_SETPCAP to change these (changes are &= ONLY). When the kernel launches a usermodehelper it will do so with these as the bset and pI. -v2: make globals static create spinlock to protect globals -v3: require both CAP_SETPCAP and CAP_SYS_MODULE -v4: fix the typo s/CAP_SET_PCAP/CAP_SETPCAP/ because I didn't commit Signed-off-by: Eric Paris No-objection-from: Serge E. Hallyn Acked-by: David Howells Acked-by: Serge E. Hallyn Acked-by: Andrew G. Morgan Signed-off-by: James Morris --- include/linux/kmod.h | 3 ++ kernel/kmod.c | 100 +++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sysctl.c | 6 ++++ 3 files changed, 109 insertions(+) (limited to 'kernel') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 6efd7a78de6..79bb98d7185 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -24,6 +24,7 @@ #include #include #include +#include #define KMOD_PATH_LEN 256 @@ -109,6 +110,8 @@ call_usermodehelper(char *path, char **argv, char **envp, enum umh_wait wait) NULL, NULL, NULL); } +extern struct ctl_table usermodehelper_table[]; + extern void usermodehelper_init(void); extern int usermodehelper_disable(void); diff --git a/kernel/kmod.c b/kernel/kmod.c index 9cd0591c96a..06fdea2819b 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -43,6 +44,13 @@ extern int max_threads; static struct workqueue_struct *khelper_wq; +#define CAP_BSET (void *)1 +#define CAP_PI (void *)2 + +static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; +static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; +static DEFINE_SPINLOCK(umh_sysctl_lock); + #ifdef CONFIG_MODULES /* @@ -132,6 +140,7 @@ EXPORT_SYMBOL(__request_module); static int ____call_usermodehelper(void *data) { struct subprocess_info *sub_info = data; + struct cred *new; int retval; spin_lock_irq(¤t->sighand->siglock); @@ -153,6 +162,19 @@ static int ____call_usermodehelper(void *data) goto fail; } + retval = -ENOMEM; + new = prepare_kernel_cred(current); + if (!new) + goto fail; + + spin_lock(&umh_sysctl_lock); + new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); + new->cap_inheritable = cap_intersect(usermodehelper_inheritable, + new->cap_inheritable); + spin_unlock(&umh_sysctl_lock); + + commit_creds(new); + retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); @@ -418,6 +440,84 @@ unlock: } EXPORT_SYMBOL(call_usermodehelper_exec); +static int proc_cap_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + unsigned long cap_array[_KERNEL_CAPABILITY_U32S]; + kernel_cap_t new_cap; + int err, i; + + if (write && (!capable(CAP_SETPCAP) || + !capable(CAP_SYS_MODULE))) + return -EPERM; + + /* + * convert from the global kernel_cap_t to the ulong array to print to + * userspace if this is a read. + */ + spin_lock(&umh_sysctl_lock); + for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) { + if (table->data == CAP_BSET) + cap_array[i] = usermodehelper_bset.cap[i]; + else if (table->data == CAP_PI) + cap_array[i] = usermodehelper_inheritable.cap[i]; + else + BUG(); + } + spin_unlock(&umh_sysctl_lock); + + t = *table; + t.data = &cap_array; + + /* + * actually read or write and array of ulongs from userspace. Remember + * these are least significant 32 bits first + */ + err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + + /* + * convert from the sysctl array of ulongs to the kernel_cap_t + * internal representation + */ + for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) + new_cap.cap[i] = cap_array[i]; + + /* + * Drop everything not in the new_cap (but don't add things) + */ + spin_lock(&umh_sysctl_lock); + if (write) { + if (table->data == CAP_BSET) + usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap); + if (table->data == CAP_PI) + usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap); + } + spin_unlock(&umh_sysctl_lock); + + return 0; +} + +struct ctl_table usermodehelper_table[] = { + { + .procname = "bset", + .data = CAP_BSET, + .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .mode = 0600, + .proc_handler = proc_cap_handler, + }, + { + .procname = "inheritable", + .data = CAP_PI, + .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .mode = 0600, + .proc_handler = proc_cap_handler, + }, + { } +}; + void __init usermodehelper_init(void) { khelper_wq = create_singlethread_workqueue("khelper"); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c0bb32414b1..965134bed6c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include @@ -615,6 +616,11 @@ static struct ctl_table kern_table[] = { .mode = 0555, .child = random_table, }, + { + .procname = "usermodehelper", + .mode = 0555, + .child = usermodehelper_table, + }, { .procname = "overflowuid", .data = &overflowuid, -- cgit v1.2.3-70-g09d2 From ffa8e59df047d57e812a04f7d6baf6a25c652c0c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 1 Apr 2011 17:08:34 -0400 Subject: capabilities: do not drop CAP_SETPCAP from the initial task In olden' days of yore CAP_SETPCAP had special meaning for the init task. We actually have code to make sure that CAP_SETPCAP wasn't in pE of things using the init_cred. But CAP_SETPCAP isn't so special any more and we don't have a reason to special case dropping it for init or kthreads.... Signed-off-by: Eric Paris Acked-by: Andrew G. Morgan Signed-off-by: James Morris --- include/linux/capability.h | 6 ++++-- kernel/capability.c | 2 -- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/capability.h b/include/linux/capability.h index 16ee8b49a20..11d562863e4 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -412,7 +412,6 @@ extern const kernel_cap_t __cap_init_eff_set; # define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }}) # define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }}) -# define CAP_INIT_EFF_SET ((kernel_cap_t){{ ~CAP_TO_MASK(CAP_SETPCAP), ~0 }}) # define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \ | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \ CAP_FS_MASK_B1 } }) @@ -423,10 +422,10 @@ extern const kernel_cap_t __cap_init_eff_set; #endif /* _KERNEL_CAPABILITY_U32S != 2 */ #define CAP_INIT_INH_SET CAP_EMPTY_SET +#define CAP_INIT_EFF_SET CAP_FULL_SET # define cap_clear(c) do { (c) = __cap_empty_set; } while (0) # define cap_set_full(c) do { (c) = __cap_full_set; } while (0) -# define cap_set_init_eff(c) do { (c) = __cap_init_eff_set; } while (0) #define cap_raise(c, flag) ((c).cap[CAP_TO_INDEX(flag)] |= CAP_TO_MASK(flag)) #define cap_lower(c, flag) ((c).cap[CAP_TO_INDEX(flag)] &= ~CAP_TO_MASK(flag)) @@ -547,6 +546,9 @@ extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool task_ns_capable(struct task_struct *t, int cap); +extern const kernel_cap_t __cap_empty_set; +extern const kernel_cap_t __cap_full_set; + /** * nsown_capable - Check superior capability to one's own user_ns * @cap: The capability in question diff --git a/kernel/capability.c b/kernel/capability.c index bf0c734d0c1..2a374d512ea 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -23,11 +23,9 @@ const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; const kernel_cap_t __cap_full_set = CAP_FULL_SET; -const kernel_cap_t __cap_init_eff_set = CAP_INIT_EFF_SET; EXPORT_SYMBOL(__cap_empty_set); EXPORT_SYMBOL(__cap_full_set); -EXPORT_SYMBOL(__cap_init_eff_set); int file_caps_enabled = 1; -- cgit v1.2.3-70-g09d2 From 5163b583a036b103c3cec7171d6731c125773ed6 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 1 Apr 2011 17:08:39 -0400 Subject: capabilities: delete unused cap_set_full unused code. Clean it up. Signed-off-by: Eric Paris Acked-by: David Howells Acked-by: Andrew G. Morgan Signed-off-by: James Morris --- include/linux/capability.h | 2 -- kernel/capability.c | 2 -- 2 files changed, 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/capability.h b/include/linux/capability.h index 11d562863e4..8d0da30dad2 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -425,7 +425,6 @@ extern const kernel_cap_t __cap_init_eff_set; #define CAP_INIT_EFF_SET CAP_FULL_SET # define cap_clear(c) do { (c) = __cap_empty_set; } while (0) -# define cap_set_full(c) do { (c) = __cap_full_set; } while (0) #define cap_raise(c, flag) ((c).cap[CAP_TO_INDEX(flag)] |= CAP_TO_MASK(flag)) #define cap_lower(c, flag) ((c).cap[CAP_TO_INDEX(flag)] &= ~CAP_TO_MASK(flag)) @@ -547,7 +546,6 @@ extern bool ns_capable(struct user_namespace *ns, int cap); extern bool task_ns_capable(struct task_struct *t, int cap); extern const kernel_cap_t __cap_empty_set; -extern const kernel_cap_t __cap_full_set; /** * nsown_capable - Check superior capability to one's own user_ns diff --git a/kernel/capability.c b/kernel/capability.c index 2a374d512ea..14ea4210a53 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -22,10 +22,8 @@ */ const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; -const kernel_cap_t __cap_full_set = CAP_FULL_SET; EXPORT_SYMBOL(__cap_empty_set); -EXPORT_SYMBOL(__cap_full_set); int file_caps_enabled = 1; -- cgit v1.2.3-70-g09d2 From a3232d2fa2e3cbab3e76d91cdae5890fee8a4034 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 1 Apr 2011 17:08:45 -0400 Subject: capabilities: delete all CAP_INIT macros The CAP_INIT macros of INH, BSET, and EFF made sense at one point in time, but now days they aren't helping. Just open code the logic in the init_cred. Signed-off-by: Eric Paris Acked-by: David Howells Signed-off-by: James Morris --- include/linux/capability.h | 3 --- include/linux/init_task.h | 7 ------- kernel/cred.c | 6 +++--- 3 files changed, 3 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/include/linux/capability.h b/include/linux/capability.h index 8d0da30dad2..04fed72809d 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -421,9 +421,6 @@ extern const kernel_cap_t __cap_init_eff_set; #endif /* _KERNEL_CAPABILITY_U32S != 2 */ -#define CAP_INIT_INH_SET CAP_EMPTY_SET -#define CAP_INIT_EFF_SET CAP_FULL_SET - # define cap_clear(c) do { (c) = __cap_empty_set; } while (0) #define cap_raise(c, flag) ((c).cap[CAP_TO_INDEX(flag)] |= CAP_TO_MASK(flag)) diff --git a/include/linux/init_task.h b/include/linux/init_task.h index caa151fbebb..1f277204de3 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -83,13 +83,6 @@ extern struct group_info init_groups; #define INIT_IDS #endif -/* - * Because of the reduced scope of CAP_SETPCAP when filesystem - * capabilities are in effect, it is safe to allow CAP_SETPCAP to - * be available in the default configuration. - */ -# define CAP_INIT_BSET CAP_FULL_SET - #ifdef CONFIG_RCU_BOOST #define INIT_TASK_RCU_BOOST() \ .rcu_boost_mutex = NULL, diff --git a/kernel/cred.c b/kernel/cred.c index 5557b55048d..b982f0863ae 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -49,10 +49,10 @@ struct cred init_cred = { .magic = CRED_MAGIC, #endif .securebits = SECUREBITS_DEFAULT, - .cap_inheritable = CAP_INIT_INH_SET, + .cap_inheritable = CAP_EMPTY_SET, .cap_permitted = CAP_FULL_SET, - .cap_effective = CAP_INIT_EFF_SET, - .cap_bset = CAP_INIT_BSET, + .cap_effective = CAP_FULL_SET, + .cap_bset = CAP_FULL_SET, .user = INIT_USER, .group_info = &init_groups, #ifdef CONFIG_KEYS -- cgit v1.2.3-70-g09d2