aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDan Rosenberg <drosenberg@vsecurity.com>2011-01-12 16:59:41 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2011-01-13 08:03:08 -0800
commit455cd5ab305c90ffc422dd2e0fb634730942b257 (patch)
treec20e6c3f8e58967991ce9002abe03d31897b171c
parent351f8f8e6499ae4fff40f5e3a8fe16d9e1903646 (diff)
kptr_restrict for hiding kernel pointers from unprivileged users
Add the %pK printk format specifier and the /proc/sys/kernel/kptr_restrict sysctl. The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". [akpm@linux-foundation.org: check for IRQ context when !kptr_restrict, save an indent level, s/WARN/WARN_ONCE/] [akpm@linux-foundation.org: coding-style fixup] [randy.dunlap@oracle.com: fix kernel/sysctl.c warning] Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: James Morris <jmorris@namei.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Thomas Graf <tgraf@infradead.org> Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Kees Cook <kees.cook@canonical.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David S. Miller <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Eric Paris <eparis@parisplace.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--Documentation/sysctl/kernel.txt14
-rw-r--r--include/linux/printk.h1
-rw-r--r--kernel/sysctl.c10
-rw-r--r--lib/vsprintf.c22
4 files changed, 47 insertions, 0 deletions
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 574067194f3..11d5ceda5bb 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -34,6 +34,7 @@ show up in /proc/sys/kernel:
- hotplug
- java-appletviewer [ binfmt_java, obsolete ]
- java-interpreter [ binfmt_java, obsolete ]
+- kptr_restrict
- kstack_depth_to_print [ X86 only ]
- l2cr [ PPC only ]
- modprobe ==> Documentation/debugging-modules.txt
@@ -261,6 +262,19 @@ This flag controls the L2 cache of G3 processor boards. If
==============================================================
+kptr_restrict:
+
+This toggle indicates whether restrictions are placed on
+exposing kernel addresses via /proc and other interfaces. When
+kptr_restrict is set to (0), there are no restrictions. When
+kptr_restrict is set to (1), the default, kernel pointers
+printed using the %pK format specifier will be replaced with 0's
+unless the user has CAP_SYSLOG. When kptr_restrict is set to
+(2), kernel pointers printed using %pK will be replaced with 0's
+regardless of privileges.
+
+==============================================================
+
kstack_depth_to_print: (X86 only)
Controls the number of words to print when dumping the raw
diff --git a/include/linux/printk.h b/include/linux/printk.h
index b772ca5fbdf..9adfba6ec28 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -83,6 +83,7 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
extern int printk_delay_msec;
extern int dmesg_restrict;
+extern int kptr_restrict;
/*
* Print a one-time message (analogous to WARN_ONCE() et al):
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ae5cbb1e3ce..c6811ee2092 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/signal.h>
+#include <linux/printk.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/ctype.h>
@@ -710,6 +711,15 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
+ {
+ .procname = "kptr_restrict",
+ .data = &kptr_restrict,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
#endif
{
.procname = "ngroups_max",
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index c150d3dafff..6ff38524ec1 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -936,6 +936,8 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
return string(buf, end, uuid, spec);
}
+int kptr_restrict = 1;
+
/*
* Show a '%p' thing. A kernel extension is that the '%p' is followed
* by an extra set of alphanumeric characters that are extended format
@@ -979,6 +981,7 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
* Implements a "recursive vsnprintf".
* Do not use this feature without some mechanism to verify the
* correctness of the format string and va_list arguments.
+ * - 'K' For a kernel pointer that should be hidden from unprivileged users
*
* Note: The difference between 'S' and 'F' is that on ia64 and ppc64
* function pointers are really function descriptors, which contain a
@@ -1035,6 +1038,25 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
return buf + vsnprintf(buf, end - buf,
((struct va_format *)ptr)->fmt,
*(((struct va_format *)ptr)->va));
+ case 'K':
+ /*
+ * %pK cannot be used in IRQ context because its test
+ * for CAP_SYSLOG would be meaningless.
+ */
+ if (in_irq() || in_serving_softirq() || in_nmi()) {
+ if (spec.field_width == -1)
+ spec.field_width = 2 * sizeof(void *);
+ return string(buf, end, "pK-error", spec);
+ } else if ((kptr_restrict == 0) ||
+ (kptr_restrict == 1 &&
+ has_capability_noaudit(current, CAP_SYSLOG)))
+ break;
+
+ if (spec.field_width == -1) {
+ spec.field_width = 2 * sizeof(void *);
+ spec.flags |= ZEROPAD;
+ }
+ return number(buf, end, 0, spec);
}
spec.flags |= SMALL;
if (spec.field_width == -1) {