Audit: push audit success and retcode into arch ptrace.h

The audit system previously expected arches calling to audit_syscall_exit to
supply as arguments if the syscall was a success and what the return code was.
Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things
by converting from negative retcodes to an audit internal magic value stating
success or failure.  This helper was wrong and could indicate that a valid
pointer returned to userspace was a failed syscall.  The fix is to fix the
layering foolishness.  We now pass audit_syscall_exit a struct pt_reg and it
in turns calls back into arch code to collect the return value and to
determine if the syscall was a success or failure.  We also define a generic
is_syscall_success() macro which determines success/failure based on if the
value is < -MAX_ERRNO.  This works for arches like x86 which do not use a
separate mechanism to indicate syscall failure.

We make both the is_syscall_success() and regs_return_value() static inlines
instead of macros.  The reason is because the audit function must take a void*
for the regs.  (uml calls theirs struct uml_pt_regs instead of just struct
pt_regs so audit_syscall_exit can't take a struct pt_regs).  Since the audit
function takes a void* we need to use static inlines to cast it back to the
arch correct structure to dereference it.

The other major change is that on some arches, like ia64, MIPS and ppc, we
change regs_return_value() to give us the negative value on syscall failure.
THE only other user of this macro, kretprobe_example.c, won't notice and it
makes the value signed consistently for the audit functions across all archs.

In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old
audit code as the return value.  But the ptrace_64.h code defined the macro
regs_return_value() as regs[3].  I have no idea which one is correct, but this
patch now uses the regs_return_value() function, so it now uses regs[3].

For powerpc we previously used regs->result but now use the
regs_return_value() function which uses regs->gprs[3].  regs->gprs[3] is
always positive so the regs_return_value(), much like ia64 makes it negative
before calling the audit code when appropriate.

Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion]
Acked-by: Tony Luck <tony.luck@intel.com> [for ia64]
Acked-by: Richard Weinberger <richard@nod.at> [for uml]
Acked-by: David S. Miller <davem@davemloft.net> [for sparc]
Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips]
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]

6 files changed, 22 insertions, 18 deletions

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 3e274564f6b..64ced0b8f8f 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -14,6 +14,7 @@
 #include <asm/segment.h>
 #include <asm/irqflags.h>
 #include <linux/linkage.h>
+#include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -208,12 +209,11 @@ sysexit_from_sys_call:
 	TRACE_IRQS_ON
 	sti
 	movl %eax,%esi		/* second arg, syscall return value */
-	cmpl $0,%eax		/* is it < 0? */
-	setl %al		/* 1 if so, 0 if not */
+	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
+	setbe %al		/* 1 if so, 0 if not */
 	movzbl %al,%edi		/* zero-extend that into %edi */
-	inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
-	call audit_syscall_exit
-	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall return value */
+	call __audit_syscall_exit
+	movq RAX-ARGOFFSET(%rsp),%rax	/* reload syscall return value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
 	cli
 	TRACE_IRQS_OFF
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 22d0e21b4dd..a22facf06f0 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -42,6 +42,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/err.h>
 #include <asm/thread_info.h>
 #include <asm/irqflags.h>
 #include <asm/errno.h>
@@ -466,11 +467,10 @@ sysexit_audit:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_ANY)
 	movl %eax,%edx		/* second arg, syscall return value */
-	cmpl $0,%eax		/* is it < 0? */
-	setl %al		/* 1 if so, 0 if not */
+	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
+	setbe %al		/* 1 if so, 0 if not */
 	movzbl %al,%eax		/* zero-extend that */
-	inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
-	call audit_syscall_exit
+	call __audit_syscall_exit
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a20e1cb9dc8..e51393dd93a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -55,6 +55,7 @@
 #include <asm/paravirt.h>
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
+#include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -563,17 +564,16 @@ auditsys:
 	jmp system_call_fastpath
 
 	/*
-	 * Return fast path for syscall audit.  Call audit_syscall_exit()
+	 * Return fast path for syscall audit.  Call __audit_syscall_exit()
 	 * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
 	 * masked off.
 	 */
 sysret_audit:
 	movq RAX-ARGOFFSET(%rsp),%rsi	/* second arg, syscall return value */
-	cmpq $0,%rsi		/* is it < 0? */
-	setl %al		/* 1 if so, 0 if not */
+	cmpq $-MAX_ERRNO,%rsi	/* is it < -MAX_ERRNO? */
+	setbe %al		/* 1 if so, 0 if not */
 	movzbl %al,%edi		/* zero-extend that into %edi */
-	inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
-	call audit_syscall_exit
+	call __audit_syscall_exit
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
 	jmp sysret_check
 #endif	/* CONFIG_AUDITSYSCALL */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 89a04c7b5bb..8b021875877 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1414,8 +1414,7 @@ void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
-	if (unlikely(current->audit_context))
-		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
+	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_exit(regs, regs->ax);
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 863f8753ab0..af17e1c966d 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -335,9 +335,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	if (info->flags & VM86_SCREEN_BITMAP)
 		mark_screen_rdonly(tsk->mm);
 
-	/*call audit_syscall_exit since we do not exit via the normal paths */
+	/*call __audit_syscall_exit since we do not exit via the normal paths */
 	if (unlikely(current->audit_context))
-		audit_syscall_exit(AUDITSC_RESULT(0), 0);
+		__audit_syscall_exit(1, 0);
 
 	__asm__ __volatile__(
 		"movl %0,%%esp\n\t"
diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h
index 711b1621747..5ef9344a8b2 100644
--- a/arch/x86/um/shared/sysdep/ptrace.h
+++ b/arch/x86/um/shared/sysdep/ptrace.h
@@ -3,3 +3,8 @@
 #else
 #include "ptrace_64.h"
 #endif
+
+static inline long regs_return_value(struct uml_pt_regs *regs)
+{
+	return UPT_SYSCALL_RET(regs);
+}