Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull siginfo updates from Eric Biederman:
 "I have been slowly sorting out siginfo and this is the culmination of
  that work.

  The primary result is in several ways the signal infrastructure has
  been made less error prone. The code has been updated so that manually
  specifying SEND_SIG_FORCED is never necessary. The conversion to the
  new siginfo sending functions is now complete, which makes it
  difficult to send a signal without filling in the proper siginfo
  fields.

  At the tail end of the patchset comes the optimization of decreasing
  the size of struct siginfo in the kernel from 128 bytes to about 48
  bytes on 64bit. The fundamental observation that enables this is by
  definition none of the known ways to use struct siginfo uses the extra
  bytes.

  This comes at the cost of a small user space observable difference.
  For the rare case of siginfo being injected into the kernel only what
  can be copied into kernel_siginfo is delivered to the destination, the
  rest of the bytes are set to 0. For cases where the signal and the
  si_code are known this is safe, because we know those bytes are not
  used. For cases where the signal and si_code combination is unknown
  the bits that won't fit into struct kernel_siginfo are tested to
  verify they are zero, and the send fails if they are not.

  I made an extensive search through userspace code and I could not find
  anything that would break because of the above change. If it turns out
  I did break something it will take just the revert of a single change
  to restore kernel_siginfo to the same size as userspace siginfo.

  Testing did reveal dependencies on preferring the signo passed to
  sigqueueinfo over si->signo, so bit the bullet and added the
  complexity necessary to handle that case.

  Testing also revealed bad things can happen if a negative signal
  number is passed into the system calls. Something no sane application
  will do but something a malicious program or a fuzzer might do. So I
  have fixed the code that performs the bounds checks to ensure negative
  signal numbers are handled"

* 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (80 commits)
  signal: Guard against negative signal numbers in copy_siginfo_from_user32
  signal: Guard against negative signal numbers in copy_siginfo_from_user
  signal: In sigqueueinfo prefer sig not si_signo
  signal: Use a smaller struct siginfo in the kernel
  signal: Distinguish between kernel_siginfo and siginfo
  signal: Introduce copy_siginfo_from_user and use it's return value
  signal: Remove the need for __ARCH_SI_PREABLE_SIZE and SI_PAD_SIZE
  signal: Fail sigqueueinfo if si_signo != sig
  signal/sparc: Move EMT_TAGOVF into the generic siginfo.h
  signal/unicore32: Use force_sig_fault where appropriate
  signal/unicore32: Generate siginfo in ucs32_notify_die
  signal/unicore32: Use send_sig_fault where appropriate
  signal/arc: Use force_sig_fault where appropriate
  signal/arc: Push siginfo generation into unhandled_exception
  signal/ia64: Use force_sig_fault where appropriate
  signal/ia64: Use the force_sig(SIGSEGV,...) in ia64_rt_sigreturn
  signal/ia64: Use the generic force_sigsegv in setup_frame
  signal/arm/kvm: Use send_sig_mceerr
  signal/arm: Use send_sig_fault where appropriate
  signal/arm: Use force_sig_fault where appropriate
  ...

1 files changed, 71 insertions, 105 deletions

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 5bd0a997d81e..8f6dcd88202e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -189,7 +189,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr)
 }
 
 static nokprobe_inline int
-do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
+do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str,
 		  struct pt_regs *regs,	long error_code)
 {
 	if (v8086_mode(regs)) {
@@ -202,10 +202,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 						error_code, trapnr))
 				return 0;
 		}
-		return -1;
-	}
-
-	if (!user_mode(regs)) {
+	} else if (!user_mode(regs)) {
 		if (fixup_exception(regs, trapnr, error_code, 0))
 			return 0;
 
@@ -214,49 +211,6 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 		die(str, regs, error_code);
 	}
 
-	return -1;
-}
-
-static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr,
-				siginfo_t *info)
-{
-	unsigned long siaddr;
-	int sicode;
-
-	switch (trapnr) {
-	default:
-		return SEND_SIG_PRIV;
-
-	case X86_TRAP_DE:
-		sicode = FPE_INTDIV;
-		siaddr = uprobe_get_trap_addr(regs);
-		break;
-	case X86_TRAP_UD:
-		sicode = ILL_ILLOPN;
-		siaddr = uprobe_get_trap_addr(regs);
-		break;
-	case X86_TRAP_AC:
-		sicode = BUS_ADRALN;
-		siaddr = 0;
-		break;
-	}
-
-	info->si_signo = signr;
-	info->si_errno = 0;
-	info->si_code = sicode;
-	info->si_addr = (void __user *)siaddr;
-	return info;
-}
-
-static void
-do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
-	long error_code, siginfo_t *info)
-{
-	struct task_struct *tsk = current;
-
-
-	if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
-		return;
 	/*
 	 * We want error_code and trap_nr set for userspace faults and
 	 * kernelspace faults which result in die(), but not
@@ -269,24 +223,45 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	tsk->thread.error_code = error_code;
 	tsk->thread.trap_nr = trapnr;
 
+	return -1;
+}
+
+static void show_signal(struct task_struct *tsk, int signr,
+			const char *type, const char *desc,
+			struct pt_regs *regs, long error_code)
+{
 	if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
 	    printk_ratelimit()) {
-		pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
-			tsk->comm, tsk->pid, str,
+		pr_info("%s[%d] %s%s ip:%lx sp:%lx error:%lx",
+			tsk->comm, task_pid_nr(tsk), type, desc,
 			regs->ip, regs->sp, error_code);
 		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
+}
+
+static void
+do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
+	long error_code, int sicode, void __user *addr)
+{
+	struct task_struct *tsk = current;
+
+
+	if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
+		return;
+
+	show_signal(tsk, signr, "trap ", str, regs, error_code);
 
-	force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk);
+	if (!sicode)
+		force_sig(signr, tsk);
+	else
+		force_sig_fault(signr, sicode, addr, tsk);
 }
 NOKPROBE_SYMBOL(do_trap);
 
 static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
-			  unsigned long trapnr, int signr)
+	unsigned long trapnr, int signr, int sicode, void __user *addr)
 {
-	siginfo_t info;
-
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 
 	/*
@@ -299,26 +274,26 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
 			NOTIFY_STOP) {
 		cond_local_irq_enable(regs);
-		clear_siginfo(&info);
-		do_trap(trapnr, signr, str, regs, error_code,
-			fill_trap_info(regs, signr, trapnr, &info));
+		do_trap(trapnr, signr, str, regs, error_code, sicode, addr);
 	}
 }
 
-#define DO_ERROR(trapnr, signr, str, name)				\
-dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
-{									\
-	do_error_trap(regs, error_code, str, trapnr, signr);		\
+#define IP ((void __user *)uprobe_get_trap_addr(regs))
+#define DO_ERROR(trapnr, signr, sicode, addr, str, name)		   \
+dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	   \
+{									   \
+	do_error_trap(regs, error_code, str, trapnr, signr, sicode, addr); \
 }
 
-DO_ERROR(X86_TRAP_DE,     SIGFPE,  "divide error",		divide_error)
-DO_ERROR(X86_TRAP_OF,     SIGSEGV, "overflow",			overflow)
-DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
-DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",coprocessor_segment_overrun)
-DO_ERROR(X86_TRAP_TS,     SIGSEGV, "invalid TSS",		invalid_TSS)
-DO_ERROR(X86_TRAP_NP,     SIGBUS,  "segment not present",	segment_not_present)
-DO_ERROR(X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment)
-DO_ERROR(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check)
+DO_ERROR(X86_TRAP_DE,     SIGFPE,  FPE_INTDIV,   IP, "divide error",        divide_error)
+DO_ERROR(X86_TRAP_OF,     SIGSEGV,          0, NULL, "overflow",            overflow)
+DO_ERROR(X86_TRAP_UD,     SIGILL,  ILL_ILLOPN,   IP, "invalid opcode",      invalid_op)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,           0, NULL, "coprocessor segment overrun", coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS,     SIGSEGV,          0, NULL, "invalid TSS",         invalid_TSS)
+DO_ERROR(X86_TRAP_NP,     SIGBUS,           0, NULL, "segment not present", segment_not_present)
+DO_ERROR(X86_TRAP_SS,     SIGBUS,           0, NULL, "stack segment",       stack_segment)
+DO_ERROR(X86_TRAP_AC,     SIGBUS,  BUS_ADRALN, NULL, "alignment check",     alignment_check)
+#undef IP
 
 #ifdef CONFIG_VMAP_STACK
 __visible void __noreturn handle_stack_overflow(const char *message,
@@ -459,7 +434,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
 	const struct mpx_bndcsr *bndcsr;
-	siginfo_t *info;
 
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
@@ -497,8 +471,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 			goto exit_trap;
 		break; /* Success, it was handled */
 	case 1: /* Bound violation. */
-		info = mpx_generate_siginfo(regs);
-		if (IS_ERR(info)) {
+	{
+		struct task_struct *tsk = current;
+		struct mpx_fault_info mpx;
+
+		if (mpx_fault_info(&mpx, regs)) {
 			/*
 			 * We failed to decode the MPX instruction.  Act as if
 			 * the exception was not caused by MPX.
@@ -507,14 +484,20 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 		}
 		/*
 		 * Success, we decoded the instruction and retrieved
-		 * an 'info' containing the address being accessed
+		 * an 'mpx' containing the address being accessed
 		 * which caused the exception.  This information
 		 * allows and application to possibly handle the
 		 * #BR exception itself.
 		 */
-		do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
-		kfree(info);
+		if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs,
+				       error_code))
+			break;
+
+		show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code);
+
+		force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper);
 		break;
+	}
 	case 0: /* No exception caused by Intel MPX operations. */
 		goto exit_trap;
 	default:
@@ -531,12 +514,13 @@ exit_trap:
 	 * up here if the kernel has MPX turned off at compile
 	 * time..
 	 */
-	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
+	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL);
 }
 
 dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {
+	const char *desc = "general protection fault";
 	struct task_struct *tsk;
 
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
@@ -570,25 +554,18 @@ do_general_protection(struct pt_regs *regs, long error_code)
 		    kprobe_fault_handler(regs, X86_TRAP_GP))
 			return;
 
-		if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+		if (notify_die(DIE_GPF, desc, regs, error_code,
 			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
-			die("general protection fault", regs, error_code);
+			die(desc, regs, error_code);
 		return;
 	}
 
 	tsk->thread.error_code = error_code;
 	tsk->thread.trap_nr = X86_TRAP_GP;
 
-	if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
-			printk_ratelimit()) {
-		pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
-			tsk->comm, task_pid_nr(tsk),
-			regs->ip, regs->sp, error_code);
-		print_vma_addr(KERN_CONT " in ", regs->ip);
-		pr_cont("\n");
-	}
+	show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
 
-	force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
+	force_sig(SIGSEGV, tsk);
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
@@ -631,7 +608,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 		goto exit;
 
 	cond_local_irq_enable(regs);
-	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
+	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, 0, NULL);
 	cond_local_irq_disable(regs);
 
 exit:
@@ -845,7 +822,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
 	struct task_struct *task = current;
 	struct fpu *fpu = &task->thread.fpu;
-	siginfo_t info;
+	int si_code;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
 
@@ -871,18 +848,14 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 	task->thread.trap_nr	= trapnr;
 	task->thread.error_code = error_code;
-	clear_siginfo(&info);
-	info.si_signo		= SIGFPE;
-	info.si_errno		= 0;
-	info.si_addr		= (void __user *)uprobe_get_trap_addr(regs);
-
-	info.si_code = fpu__exception_code(fpu, trapnr);
 
+	si_code = fpu__exception_code(fpu, trapnr);
 	/* Retry when we get spurious exceptions: */
-	if (!info.si_code)
+	if (!si_code)
 		return;
 
-	force_sig_info(SIGFPE, &info, task);
+	force_sig_fault(SIGFPE, si_code,
+			(void __user *)uprobe_get_trap_addr(regs), task);
 }
 
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
@@ -942,20 +915,13 @@ NOKPROBE_SYMBOL(do_device_not_available);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
-	siginfo_t info;
-
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	local_irq_enable();
 
-	clear_siginfo(&info);
-	info.si_signo = SIGILL;
-	info.si_errno = 0;
-	info.si_code = ILL_BADSTK;
-	info.si_addr = NULL;
 	if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
 			X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
 		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
-			&info);
+			ILL_BADSTK, (void __user *)NULL);
 	}
 }
 #endif