Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6:
  security: define round_hint_to_min in !CONFIG_SECURITY
  Security/SELinux: seperate lsm specific mmap_min_addr
  SELinux: call cap_file_mmap in selinux_file_mmap
  Capabilities: move cap_file_mmap to commoncap.c

12 files changed, 137 insertions, 41 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ba3a7cb1eaa0..9a72cc78e6b8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout;
 #define sysctl_legacy_va_layout 0
 #endif
 
-extern unsigned long mmap_min_addr;
-
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -575,19 +573,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 }
 
 /*
- * If a hint addr is less than mmap_min_addr change hint to be as
- * low as possible but still greater than mmap_min_addr
- */
-static inline unsigned long round_hint_to_min(unsigned long hint)
-{
-	hint &= PAGE_MASK;
-	if (((void *)hint != NULL) &&
-	    (hint < mmap_min_addr))
-		return PAGE_ALIGN(mmap_min_addr);
-	return hint;
-}
-
-/*
  * Some inline functions in vmstat.h depend on page_zone()
  */
 #include <linux/vmstat.h>
diff --git a/include/linux/security.h b/include/linux/security.h
index 5eff459b3833..1f16eea2017b 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -28,6 +28,7 @@
 #include <linux/resource.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
+#include <linux/mm.h> /* PAGE_ALIGN */
 #include <linux/msg.h>
 #include <linux/sched.h>
 #include <linux/key.h>
@@ -66,6 +67,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
 extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
 extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
+extern int cap_file_mmap(struct file *file, unsigned long reqprot,
+			 unsigned long prot, unsigned long flags,
+			 unsigned long addr, unsigned long addr_only);
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5);
@@ -92,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb);
 extern int cap_netlink_recv(struct sk_buff *skb, int cap);
 
 extern unsigned long mmap_min_addr;
+extern unsigned long dac_mmap_min_addr;
 /*
  * Values used in the task_security_ops calls
  */
@@ -116,6 +121,21 @@ struct request_sock;
 #define LSM_UNSAFE_PTRACE	2
 #define LSM_UNSAFE_PTRACE_CAP	4
 
+/*
+ * If a hint addr is less than mmap_min_addr change hint to be as
+ * low as possible but still greater than mmap_min_addr
+ */
+static inline unsigned long round_hint_to_min(unsigned long hint)
+{
+	hint &= PAGE_MASK;
+	if (((void *)hint != NULL) &&
+	    (hint < mmap_min_addr))
+		return PAGE_ALIGN(mmap_min_addr);
+	return hint;
+}
+extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp,
+				 void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #ifdef CONFIG_SECURITY
 
 struct security_mnt_opts {
@@ -2197,9 +2217,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot,
 				     unsigned long addr,
 				     unsigned long addr_only)
 {
-	if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO))
-		return -EACCES;
-	return 0;
+	return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only);
 }
 
 static inline int security_file_mprotect(struct vm_area_struct *vma,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 98e02328c67d..58be76017fd0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -49,6 +49,7 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
+#include <linux/security.h>
 #include <linux/slow-work.h>
 #include <linux/perf_counter.h>
 
@@ -1306,10 +1307,10 @@ static struct ctl_table vm_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "mmap_min_addr",
-		.data		= &mmap_min_addr,
-		.maxlen         = sizeof(unsigned long),
+		.data		= &dac_mmap_min_addr,
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= &proc_doulongvec_minmax,
+		.proc_handler	= &mmap_min_addr_handler,
 	},
 #ifdef CONFIG_NUMA
 	{
diff --git a/mm/Kconfig b/mm/Kconfig
index c948d4ca8bde..fe5f674d7a7d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -225,9 +225,9 @@ config DEFAULT_MMAP_MIN_ADDR
 	  For most ia64, ppc64 and x86 users with lots of address space
 	  a value of 65536 is reasonable and should cause no problems.
 	  On arm and other archs it should not be higher than 32768.
-	  Programs which use vm86 functionality would either need additional
-	  permissions from either the LSM or the capabilities module or have
-	  this protection disabled.
+	  Programs which use vm86 functionality or have some need to map
+	  this low address space will need CAP_SYS_RAWIO or disable this
+	  protection by setting the value to 0.
 
 	  This value can be changed after boot using the
 	  /proc/sys/vm/mmap_min_addr tunable.
diff --git a/mm/mmap.c b/mm/mmap.c
index 34579b23ebd5..8101de490c73 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -88,9 +88,6 @@ int sysctl_overcommit_ratio = 50;	/* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 struct percpu_counter vm_committed_as;
 
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-
 /*
  * Check that a process has enough memory to allocate a new virtual
  * mapping. 0 means there is enough memory for the allocation to
diff --git a/mm/nommu.c b/mm/nommu.c
index 53cab10fece4..28754c40be98 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -69,9 +69,6 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 int heap_stack_gap = 0;
 
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-
 atomic_long_t mmap_pages_allocated;
 
 EXPORT_SYMBOL(mem_map);
diff --git a/security/Kconfig b/security/Kconfig
index d23c839038f0..9c60c346a91d 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -113,6 +113,22 @@ config SECURITY_ROOTPLUG
 
 	  If you are unsure how to answer this question, answer N.
 
+config LSM_MMAP_MIN_ADDR
+	int "Low address space for LSM to from user allocation"
+	depends on SECURITY && SECURITY_SELINUX
+	default 65535
+	help
+	  This is the portion of low virtual memory which should be protected
+	  from userspace allocation.  Keeping a user from writing to low pages
+	  can help reduce the impact of kernel NULL pointer bugs.
+
+	  For most ia64, ppc64 and x86 users with lots of address space
+	  a value of 65536 is reasonable and should cause no problems.
+	  On arm and other archs it should not be higher than 32768.
+	  Programs which use vm86 functionality or have some need to map
+	  this low address space will need the permission specific to the
+	  systems running LSM.
+
 source security/selinux/Kconfig
 source security/smack/Kconfig
 source security/tomoyo/Kconfig
diff --git a/security/Makefile b/security/Makefile
index c67557cdaa85..b56e7f9ecbc2 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -8,7 +8,7 @@ subdir-$(CONFIG_SECURITY_SMACK)		+= smack
 subdir-$(CONFIG_SECURITY_TOMOYO)        += tomoyo
 
 # always enable default capabilities
-obj-y		+= commoncap.o
+obj-y		+= commoncap.o min_addr.o
 
 # Object file lists
 obj-$(CONFIG_SECURITY)			+= security.o capability.o
diff --git a/security/capability.c b/security/capability.c
index 21b6cead6a8e..88f752e8152c 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -330,15 +330,6 @@ static int cap_file_ioctl(struct file *file, unsigned int command,
 	return 0;
 }
 
-static int cap_file_mmap(struct file *file, unsigned long reqprot,
-			 unsigned long prot, unsigned long flags,
-			 unsigned long addr, unsigned long addr_only)
-{
-	if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO))
-		return -EACCES;
-	return 0;
-}
-
 static int cap_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			     unsigned long prot)
 {
diff --git a/security/commoncap.c b/security/commoncap.c
index 48b7e0228fa3..e3097c0a1311 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -984,3 +984,33 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages)
 		cap_sys_admin = 1;
 	return __vm_enough_memory(mm, pages, cap_sys_admin);
 }
+
+/*
+ * cap_file_mmap - check if able to map given addr
+ * @file: unused
+ * @reqprot: unused
+ * @prot: unused
+ * @flags: unused
+ * @addr: address attempting to be mapped
+ * @addr_only: unused
+ *
+ * If the process is attempting to map memory below mmap_min_addr they need
+ * CAP_SYS_RAWIO.  The other parameters to this function are unused by the
+ * capability security module.  Returns 0 if this mapping should be allowed
+ * -EPERM if not.
+ */
+int cap_file_mmap(struct file *file, unsigned long reqprot,
+		  unsigned long prot, unsigned long flags,
+		  unsigned long addr, unsigned long addr_only)
+{
+	int ret = 0;
+
+	if (addr < dac_mmap_min_addr) {
+		ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO,
+				  SECURITY_CAP_AUDIT);
+		/* set PF_SUPERPRIV if it turns out we allow the low mmap */
+		if (ret == 0)
+			current->flags |= PF_SUPERPRIV;
+	}
+	return ret;
+}
diff --git a/security/min_addr.c b/security/min_addr.c
new file mode 100644
index 000000000000..14cc7b3b8d03
--- /dev/null
+++ b/security/min_addr.c
@@ -0,0 +1,49 @@
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/security.h>
+#include <linux/sysctl.h>
+
+/* amount of vm to protect from userspace access by both DAC and the LSM*/
+unsigned long mmap_min_addr;
+/* amount of vm to protect from userspace using CAP_SYS_RAWIO (DAC) */
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+/* amount of vm to protect from userspace using the LSM = CONFIG_LSM_MMAP_MIN_ADDR */
+
+/*
+ * Update mmap_min_addr = max(dac_mmap_min_addr, CONFIG_LSM_MMAP_MIN_ADDR)
+ */
+static void update_mmap_min_addr(void)
+{
+#ifdef CONFIG_LSM_MMAP_MIN_ADDR
+	if (dac_mmap_min_addr > CONFIG_LSM_MMAP_MIN_ADDR)
+		mmap_min_addr = dac_mmap_min_addr;
+	else
+		mmap_min_addr = CONFIG_LSM_MMAP_MIN_ADDR;
+#else
+	mmap_min_addr = dac_mmap_min_addr;
+#endif
+}
+
+/*
+ * sysctl handler which just sets dac_mmap_min_addr = the new value and then
+ * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly
+ */
+int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp,
+			  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+
+	update_mmap_min_addr();
+
+	return ret;
+}
+
+int __init init_mmap_min_addr(void)
+{
+	update_mmap_min_addr();
+
+	return 0;
+}
+pure_initcall(init_mmap_min_addr);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 1e8cfc4c2ed6..8d8b69c5664e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3030,9 +3030,21 @@ static int selinux_file_mmap(struct file *file, unsigned long reqprot,
 	int rc = 0;
 	u32 sid = current_sid();
 
-	if (addr < mmap_min_addr)
+	/*
+	 * notice that we are intentionally putting the SELinux check before
+	 * the secondary cap_file_mmap check.  This is such a likely attempt
+	 * at bad behaviour/exploit that we always want to get the AVC, even
+	 * if DAC would have also denied the operation.
+	 */
+	if (addr < CONFIG_LSM_MMAP_MIN_ADDR) {
 		rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT,
 				  MEMPROTECT__MMAP_ZERO, NULL);
+		if (rc)
+			return rc;
+	}
+
+	/* do DAC check on address space usage */
+	rc = cap_file_mmap(file, reqprot, prot, flags, addr, addr_only);
 	if (rc || addr_only)
 		return rc;