Merge branch 'exit-cleanups-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull exit cleanups from Eric Biederman:
 "In preparation of doing something about PTRACE_EVENT_EXIT I have
  started cleaning up various pieces of code related to do_exit. Most of
  that code I did not manage to get tested and reviewed before the merge
  window opened but a handful of very useful cleanups are ready to be
  merged.

  The first change is simply the removal of the bdflush system call. The
  code has now been disabled long enough that even the oldest userspace
  working userspace setups anyone can find to test are fine with the
  bdflush system call being removed.

  Changing m68k fsp040_die to use force_sigsegv(SIGSEGV) instead of
  calling do_exit directly is interesting only in that it is nearly the
  most difficult of the incorrect uses of do_exit to remove.

  The change to the seccomp code to simply send a signal instead of
  calling do_coredump directly is a very nice little cleanup made
  possible by realizing the existing signal sending helpers were missing
  a little bit of functionality that is easy to provide"

* 'exit-cleanups-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  signal/seccomp: Dump core when there is only one live thread
  signal/seccomp: Refactor seccomp signal and coredump generation
  signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die
  exit/bdflush: Remove the deprecated bdflush system call

3 files changed, 33 insertions, 40 deletions

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 6469eca8078c..4d8f44a17727 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -922,30 +922,6 @@ void get_seccomp_filter(struct task_struct *tsk)
 	refcount_inc(&orig->users);
 }
 
-static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason)
-{
-	clear_siginfo(info);
-	info->si_signo = SIGSYS;
-	info->si_code = SYS_SECCOMP;
-	info->si_call_addr = (void __user *)KSTK_EIP(current);
-	info->si_errno = reason;
-	info->si_arch = syscall_get_arch(current);
-	info->si_syscall = syscall;
-}
-
-/**
- * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
- * @syscall: syscall number to send to userland
- * @reason: filter-supplied reason code to send to userland (via si_errno)
- *
- * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
- */
-static void seccomp_send_sigsys(int syscall, int reason)
-{
-	struct kernel_siginfo info;
-	seccomp_init_siginfo(&info, syscall, reason);
-	force_sig_info(&info);
-}
 #endif	/* CONFIG_SECCOMP_FILTER */
 
 /* For use with seccomp_actions_logged */
@@ -1218,7 +1194,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		/* Show the handler the original registers. */
 		syscall_rollback(current, current_pt_regs());
 		/* Let the filter pass back 16 bits of data. */
-		seccomp_send_sigsys(this_syscall, data);
+		force_sig_seccomp(this_syscall, data, false);
 		goto skip;
 
 	case SECCOMP_RET_TRACE:
@@ -1288,19 +1264,15 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		seccomp_log(this_syscall, SIGSYS, action, true);
 		/* Dump core only if this is the last remaining thread. */
 		if (action != SECCOMP_RET_KILL_THREAD ||
-		    get_nr_threads(current) == 1) {
-			kernel_siginfo_t info;
-
+		    (atomic_read(&current->signal->live) == 1)) {
 			/* Show the original registers in the dump. */
 			syscall_rollback(current, current_pt_regs());
-			/* Trigger a manual coredump since do_exit skips it. */
-			seccomp_init_siginfo(&info, this_syscall, data);
-			do_coredump(&info);
-		}
-		if (action == SECCOMP_RET_KILL_THREAD)
+			/* Trigger a coredump with SIGSYS */
+			force_sig_seccomp(this_syscall, data, true);
+		} else {
 			do_exit(SIGSYS);
-		else
-			do_group_exit(SIGSYS);
+		}
+		return -1; /* skip the syscall go directly to signal handling */
 	}
 
 	unreachable();
diff --git a/kernel/signal.c b/kernel/signal.c
index 65a54118ac9e..cf7e2505ae31 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -54,6 +54,7 @@
 #include <asm/unistd.h>
 #include <asm/siginfo.h>
 #include <asm/cacheflush.h>
+#include <asm/syscall.h>	/* for syscall_get_* */
 
 /*
  * SLAB caches for signal bits.
@@ -1322,7 +1323,7 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
  * that is why we also clear SIGNAL_UNKILLABLE.
  */
 static int
-force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t)
+force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl)
 {
 	unsigned long int flags;
 	int ret, blocked, ignored;
@@ -1333,7 +1334,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t)
 	action = &t->sighand->action[sig-1];
 	ignored = action->sa.sa_handler == SIG_IGN;
 	blocked = sigismember(&t->blocked, sig);
-	if (blocked || ignored) {
+	if (blocked || ignored || sigdfl) {
 		action->sa.sa_handler = SIG_DFL;
 		if (blocked) {
 			sigdelset(&t->blocked, sig);
@@ -1354,7 +1355,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t)
 
 int force_sig_info(struct kernel_siginfo *info)
 {
-	return force_sig_info_to_task(info, current);
+	return force_sig_info_to_task(info, current, false);
 }
 
 /*
@@ -1696,7 +1697,7 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr
 	info.si_flags = flags;
 	info.si_isr = isr;
 #endif
-	return force_sig_info_to_task(&info, t);
+	return force_sig_info_to_task(&info, t, false);
 }
 
 int force_sig_fault(int sig, int code, void __user *addr
@@ -1798,6 +1799,27 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
 	return force_sig_info(&info);
 }
 
+/**
+ * force_sig_seccomp - signals the task to allow in-process syscall emulation
+ * @syscall: syscall number to send to userland
+ * @reason: filter-supplied reason code to send to userland (via si_errno)
+ *
+ * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
+ */
+int force_sig_seccomp(int syscall, int reason, bool force_coredump)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGSYS;
+	info.si_code = SYS_SECCOMP;
+	info.si_call_addr = (void __user *)KSTK_EIP(current);
+	info.si_errno = reason;
+	info.si_arch = syscall_get_arch(current);
+	info.si_syscall = syscall;
+	return force_sig_info_to_task(&info, current, force_coredump);
+}
+
 /* For the crazy architectures that include trap information in
  * the errno field, instead of an actual errno value.
  */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 30971b1dd4a9..cb6f98f5c97a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -416,7 +416,6 @@ COND_SYSCALL(epoll_wait);
 COND_SYSCALL(recv);
 COND_SYSCALL_COMPAT(recv);
 COND_SYSCALL(send);
-COND_SYSCALL(bdflush);
 COND_SYSCALL(uselib);
 
 /* optional: time32 */