ptrace: Don't allow accessing an undumpable mm

It is the reasonable expectation that if an executable file is not
readable there will be no way for a user without special privileges to
read the file.  This is enforced in ptrace_attach but if ptrace
is already attached before exec there is no enforcement for read-only
executables.

As the only way to read such an mm is through access_process_vm
spin a variant called ptrace_access_vm that will fail if the
target process is not being ptraced by the current process, or
the current process did not have sufficient privileges when ptracing
began to read the target processes mm.

In the ptrace implementations replace access_process_vm by
ptrace_access_vm.  There remain several ptrace sites that still use
access_process_vm as they are reading the target executables
instructions (for kernel consumption) or register stacks.  As such it
does not appear necessary to add a permission check to those calls.

This bug has always existed in Linux.

Fixes: v1.0
Cc: stable@vger.kernel.org
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

arch/alpha/kernel/ptrace.c

@@ -283,7 +283,7 @@ long arch_ptrace(struct task_struct *child, long request,
 	/* When I and D space are separate, these will need to be fixed.  */
 	case PTRACE_PEEKTEXT: /* read word at location addr. */
 	case PTRACE_PEEKDATA:
-		copied = access_process_vm(child, addr, &tmp, sizeof(tmp),
+		copied = ptrace_access_vm(child, addr, &tmp, sizeof(tmp),
 				FOLL_FORCE);
 		ret = -EIO;
 		if (copied != sizeof(tmp))

arch/blackfin/kernel/ptrace.c

@@ -270,7 +270,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			switch (bfin_mem_access_type(addr, to_copy)) {
 			case BFIN_MEM_ACCESS_CORE:
 			case BFIN_MEM_ACCESS_CORE_ONLY:
-				copied = access_process_vm(child, addr, &tmp,
+				copied = ptrace_access_vm(child, addr, &tmp,
 							   to_copy, FOLL_FORCE);
 				if (copied)
 					break;
@@ -323,7 +323,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			switch (bfin_mem_access_type(addr, to_copy)) {
 			case BFIN_MEM_ACCESS_CORE:
 			case BFIN_MEM_ACCESS_CORE_ONLY:
-				copied = access_process_vm(child, addr, &data,
+				copied = ptrace_access_vm(child, addr, &data,
 				                           to_copy,
 							   FOLL_FORCE | FOLL_WRITE);
 				break;

arch/cris/arch-v32/kernel/ptrace.c

@@ -147,7 +147,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				/* The trampoline page is globally mapped, no page table to traverse.*/
 				tmp = *(unsigned long*)addr;
 			} else {
-				copied = access_process_vm(child, addr, &tmp, sizeof(tmp), FOLL_FORCE);
+				copied = ptrace_access_vm(child, addr, &tmp, sizeof(tmp), FOLL_FORCE);
 
 				if (copied != sizeof(tmp))
 					break;

arch/ia64/kernel/ptrace.c

@@ -1159,7 +1159,7 @@ arch_ptrace (struct task_struct *child, long request,
 	case PTRACE_PEEKTEXT:
 	case PTRACE_PEEKDATA:
 		/* read word at location addr */
-		if (access_process_vm(child, addr, &data, sizeof(data),
+		if (ptrace_access_vm(child, addr, &data, sizeof(data),
 				FOLL_FORCE)
 		    != sizeof(data))
 			return -EIO;

arch/mips/kernel/ptrace32.c

@@ -69,7 +69,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		if (get_user(addrOthers, (u32 __user * __user *) (unsigned long) addr) != 0)
 			break;
 
-		copied = access_process_vm(child, (u64)addrOthers, &tmp,
+		copied = ptrace_access_vm(child, (u64)addrOthers, &tmp,
 				sizeof(tmp), FOLL_FORCE);
 		if (copied != sizeof(tmp))
 			break;
@@ -178,7 +178,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		if (get_user(addrOthers, (u32 __user * __user *) (unsigned long) addr) != 0)
 			break;
 		ret = 0;
-		if (access_process_vm(child, (u64)addrOthers, &data,
+		if (ptrace_access_vm(child, (u64)addrOthers, &data,
 					sizeof(data),
 					FOLL_FORCE | FOLL_WRITE) == sizeof(data))
 			break;

arch/powerpc/kernel/ptrace32.c

@@ -73,7 +73,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		if (get_user(addrOthers, (u32 __user * __user *)addr) != 0)
 			break;
 
-		copied = access_process_vm(child, (u64)addrOthers, &tmp,
+		copied = ptrace_access_vm(child, (u64)addrOthers, &tmp,
 				sizeof(tmp), FOLL_FORCE);
 		if (copied != sizeof(tmp))
 			break;
@@ -178,7 +178,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		if (get_user(addrOthers, (u32 __user * __user *)addr) != 0)
 			break;
 		ret = 0;
-		if (access_process_vm(child, (u64)addrOthers, &tmp,
+		if (ptrace_access_vm(child, (u64)addrOthers, &tmp,
 					sizeof(tmp),
 					FOLL_FORCE | FOLL_WRITE) == sizeof(tmp))
 			break;

include/linux/mm.h

@@ -1270,6 +1270,8 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *
 		unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
+extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long addr, void *buf, int len, unsigned int gup_flags);
 
 long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,

include/linux/ptrace.h

@@ -8,6 +8,9 @@
 #include <linux/pid_namespace.h>	/* For task_active_pid_ns.  */
 #include <uapi/linux/ptrace.h>
 
+extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
+			    void *buf, int len, unsigned int gup_flags);
+
 /*
  * Ptrace flags
  *

kernel/ptrace.c

@@ -27,6 +27,35 @@
 #include <linux/cn_proc.h>
 #include <linux/compat.h>
 
+/*
+ * Access another process' address space via ptrace.
+ * Source/target buffer must be kernel space,
+ * Do not walk the page table directly, use get_user_pages
+ */
+int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
+		     void *buf, int len, unsigned int gup_flags)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return 0;
+
+	if (!tsk->ptrace ||
+	    (current != tsk->parent) ||
+	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
+	     !ptracer_capable(tsk, mm->user_ns))) {
+		mmput(mm);
+		return 0;
+	}
+
+	ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
+	mmput(mm);
+
+	return ret;
+}
+
 
 /*
  * ptrace a task: make the debugger its new parent and
@@ -535,7 +564,8 @@ int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst
 		int this_len, retval;
 
 		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
-		retval = access_process_vm(tsk, src, buf, this_len, FOLL_FORCE);
+		retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE);
+
 		if (!retval) {
 			if (copied)
 				break;
@@ -562,7 +592,7 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
 		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
 		if (copy_from_user(buf, src, this_len))
 			return -EFAULT;
-		retval = access_process_vm(tsk, dst, buf, this_len,
+		retval = ptrace_access_vm(tsk, dst, buf, this_len,
 				FOLL_FORCE | FOLL_WRITE);
 		if (!retval) {
 			if (copied)
@@ -1126,7 +1156,7 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
 	unsigned long tmp;
 	int copied;
 
-	copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE);
+	copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE);
 	if (copied != sizeof(tmp))
 		return -EIO;
 	return put_user(tmp, (unsigned long __user *)data);
@@ -1137,7 +1167,7 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
 {
 	int copied;
 
-	copied = access_process_vm(tsk, addr, &data, sizeof(data),
+	copied = ptrace_access_vm(tsk, addr, &data, sizeof(data),
 			FOLL_FORCE | FOLL_WRITE);
 	return (copied == sizeof(data)) ? 0 : -EIO;
 }
@@ -1155,7 +1185,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 	switch (request) {
 	case PTRACE_PEEKTEXT:
 	case PTRACE_PEEKDATA:
-		ret = access_process_vm(child, addr, &word, sizeof(word),
+		ret = ptrace_access_vm(child, addr, &word, sizeof(word),
 				FOLL_FORCE);
 		if (ret != sizeof(word))
 			ret = -EIO;
@@ -1165,7 +1195,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 
 	case PTRACE_POKETEXT:
 	case PTRACE_POKEDATA:
-		ret = access_process_vm(child, addr, &data, sizeof(data),
+		ret = ptrace_access_vm(child, addr, &data, sizeof(data),
 				FOLL_FORCE | FOLL_WRITE);
 		ret = (ret != sizeof(data) ? -EIO : 0);
 		break;

mm/memory.c

@@ -3868,7 +3868,7 @@ EXPORT_SYMBOL_GPL(generic_access_phys);
  * Access another process' address space as given in mm.  If non-NULL, use the
  * given task for page fault accounting.
  */
-static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
+int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, unsigned int gup_flags)
 {
 	struct vm_area_struct *vma;

mm/nommu.c

@@ -1808,7 +1808,7 @@ void filemap_map_pages(struct fault_env *fe,
 }
 EXPORT_SYMBOL(filemap_map_pages);
 
-static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
+int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, unsigned int gup_flags)
 {
 	struct vm_area_struct *vma;