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, 33 insertions, 61 deletions

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index d0e638ef3af6..7d9571f4ae3d 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -303,9 +303,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	die_kernel_fault(msg, addr, esr, regs);
 }
 
-static void __do_user_fault(struct siginfo *info, unsigned int esr)
+static void set_thread_esr(unsigned long address, unsigned int esr)
 {
-	current->thread.fault_address = (unsigned long)info->si_addr;
+	current->thread.fault_address = address;
 
 	/*
 	 * If the faulting address is in the kernel, we must sanitize the ESR.
@@ -358,7 +358,6 @@ static void __do_user_fault(struct siginfo *info, unsigned int esr)
 	}
 
 	current->thread.fault_code = esr;
-	arm64_force_sig_info(info, esr_to_fault_info(esr)->name, current);
 }
 
 static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
@@ -369,14 +368,10 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 	 */
 	if (user_mode(regs)) {
 		const struct fault_info *inf = esr_to_fault_info(esr);
-		struct siginfo si;
 
-		clear_siginfo(&si);
-		si.si_signo	= inf->sig;
-		si.si_code	= inf->code;
-		si.si_addr	= (void __user *)addr;
-
-		__do_user_fault(&si, esr);
+		set_thread_esr(addr, esr);
+		arm64_force_sig_fault(inf->sig, inf->code, (void __user *)addr,
+				      inf->name);
 	} else {
 		__do_kernel_fault(addr, esr, regs);
 	}
@@ -430,9 +425,9 @@ static bool is_el0_instruction_abort(unsigned int esr)
 static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 				   struct pt_regs *regs)
 {
+	const struct fault_info *inf;
 	struct task_struct *tsk;
 	struct mm_struct *mm;
-	struct siginfo si;
 	vm_fault_t fault, major = 0;
 	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -568,37 +563,35 @@ retry:
 		return 0;
 	}
 
-	clear_siginfo(&si);
-	si.si_addr = (void __user *)addr;
-
+	inf = esr_to_fault_info(esr);
+	set_thread_esr(addr, esr);
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to successfully fix up
 		 * this page fault.
 		 */
-		si.si_signo	= SIGBUS;
-		si.si_code	= BUS_ADRERR;
-	} else if (fault & VM_FAULT_HWPOISON_LARGE) {
-		unsigned int hindex = VM_FAULT_GET_HINDEX(fault);
-
-		si.si_signo	= SIGBUS;
-		si.si_code	= BUS_MCEERR_AR;
-		si.si_addr_lsb	= hstate_index_to_shift(hindex);
-	} else if (fault & VM_FAULT_HWPOISON) {
-		si.si_signo	= SIGBUS;
-		si.si_code	= BUS_MCEERR_AR;
-		si.si_addr_lsb	= PAGE_SHIFT;
+		arm64_force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)addr,
+				      inf->name);
+	} else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) {
+		unsigned int lsb;
+
+		lsb = PAGE_SHIFT;
+		if (fault & VM_FAULT_HWPOISON_LARGE)
+			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+
+		arm64_force_sig_mceerr(BUS_MCEERR_AR, (void __user *)addr, lsb,
+				       inf->name);
 	} else {
 		/*
 		 * Something tried to access memory that isn't in our memory
 		 * map.
 		 */
-		si.si_signo	= SIGSEGV;
-		si.si_code	= fault == VM_FAULT_BADACCESS ?
-				  SEGV_ACCERR : SEGV_MAPERR;
+		arm64_force_sig_fault(SIGSEGV,
+				      fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR,
+				      (void __user *)addr,
+				      inf->name);
 	}
 
-	__do_user_fault(&si, esr);
 	return 0;
 
 no_context:
@@ -631,8 +624,8 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 
 static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
-	struct siginfo info;
 	const struct fault_info *inf;
+	void __user *siaddr;
 
 	inf = esr_to_fault_info(esr);
 
@@ -651,15 +644,11 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 			nmi_exit();
 	}
 
-	clear_siginfo(&info);
-	info.si_signo = inf->sig;
-	info.si_errno = 0;
-	info.si_code  = inf->code;
 	if (esr & ESR_ELx_FnV)
-		info.si_addr = NULL;
+		siaddr = NULL;
 	else
-		info.si_addr  = (void __user *)addr;
-	arm64_notify_die(inf->name, regs, &info, esr);
+		siaddr  = (void __user *)addr;
+	arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
 
 	return 0;
 }
@@ -740,7 +729,6 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 					 struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_fault_info(esr);
-	struct siginfo info;
 
 	if (!inf->fn(addr, esr, regs))
 		return;
@@ -751,12 +739,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 		show_pte(addr);
 	}
 
-	clear_siginfo(&info);
-	info.si_signo = inf->sig;
-	info.si_errno = 0;
-	info.si_code  = inf->code;
-	info.si_addr  = (void __user *)addr;
-	arm64_notify_die(inf->name, regs, &info, esr);
+	arm64_notify_die(inf->name, regs,
+			 inf->sig, inf->code, (void __user *)addr, esr);
 }
 
 asmlinkage void __exception do_el0_irq_bp_hardening(void)
@@ -786,20 +770,14 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 					   unsigned int esr,
 					   struct pt_regs *regs)
 {
-	struct siginfo info;
-
 	if (user_mode(regs)) {
 		if (instruction_pointer(regs) > TASK_SIZE)
 			arm64_apply_bp_hardening();
 		local_daif_restore(DAIF_PROCCTX);
 	}
 
-	clear_siginfo(&info);
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code  = BUS_ADRALN;
-	info.si_addr  = (void __user *)addr;
-	arm64_notify_die("SP/PC alignment exception", regs, &info, esr);
+	arm64_notify_die("SP/PC alignment exception", regs,
+			 SIGBUS, BUS_ADRALN, (void __user *)addr, esr);
 }
 
 int __init early_brk64(unsigned long addr, unsigned int esr,
@@ -853,14 +831,8 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 	if (!inf->fn(addr, esr, regs)) {
 		rv = 1;
 	} else {
-		struct siginfo info;
-
-		clear_siginfo(&info);
-		info.si_signo = inf->sig;
-		info.si_errno = 0;
-		info.si_code  = inf->code;
-		info.si_addr  = (void __user *)addr;
-		arm64_notify_die(inf->name, regs, &info, esr);
+		arm64_notify_die(inf->name, regs,
+				 inf->sig, inf->code, (void __user *)addr, esr);
 		rv = 0;
 	}