s390: convert to generic entry

This patch converts s390 to use the generic entry infrastructure from
kernel/entry/*.

There are a few special things on s390:

- PIF_PER_TRAP is moved to TIF_PER_TRAP as the generic code doesn't
  know about our PIF flags in exit_to_user_mode_loop().

- The old code had several ways to restart syscalls:

  a) PIF_SYSCALL_RESTART, which was only set during execve to force a
     restart after upgrading a process (usually qemu-kvm) to pgste page
     table extensions.

  b) PIF_SYSCALL, which is set by do_signal() to indicate that the
     current syscall should be restarted. This is changed so that
     do_signal() now also uses PIF_SYSCALL_RESTART. Continuing to use
     PIF_SYSCALL doesn't work with the generic code, and changing it
     to PIF_SYSCALL_RESTART makes PIF_SYSCALL and PIF_SYSCALL_RESTART
     more unique.

- On s390 calling sys_sigreturn or sys_rt_sigreturn is implemented by
executing a svc instruction on the process stack which causes a fault.
While handling that fault the fault code sets PIF_SYSCALL to hand over
processing to the syscall code on exit to usermode.

The patch introduces PIF_SYSCALL_RET_SET, which is set if ptrace sets
a return value for a syscall. The s390x ptrace ABI uses r2 both for the
syscall number and return value, so ptrace cannot set the syscall number +
return value at the same time. The flag makes handling that a bit easier.
do_syscall() will just skip executing the syscall if PIF_SYSCALL_RET_SET
is set.

CONFIG_DEBUG_ASCE was removd in favour of the generic CONFIG_DEBUG_ENTRY.
CR1/7/13 will be checked both on kernel entry and exit to contain the
correct asces.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

1 files changed, 12 insertions, 105 deletions

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index a76dd27fb2e8..18b3416fd663 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -7,6 +7,7 @@
  *               Martin Schwidefsky (schwidefsky@de.ibm.com)
  */
 
+#include "asm/ptrace.h"
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
@@ -37,9 +38,6 @@
 #include "compat_ptrace.h"
 #endif
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
 void update_cr_regs(struct task_struct *task)
 {
 	struct pt_regs *regs = task_pt_regs(task);
@@ -140,7 +138,7 @@ void ptrace_disable(struct task_struct *task)
 	memset(&task->thread.per_user, 0, sizeof(task->thread.per_user));
 	memset(&task->thread.per_event, 0, sizeof(task->thread.per_event));
 	clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
-	clear_pt_regs_flag(task_pt_regs(task), PIF_PER_TRAP);
+	clear_tsk_thread_flag(task, TIF_PER_TRAP);
 	task->thread.per_flags = 0;
 }
 
@@ -322,25 +320,6 @@ static inline void __poke_user_per(struct task_struct *child,
 		child->thread.per_user.end = data;
 }
 
-static void fixup_int_code(struct task_struct *child, addr_t data)
-{
-	struct pt_regs *regs = task_pt_regs(child);
-	int ilc = regs->int_code >> 16;
-	u16 insn;
-
-	if (ilc > 6)
-		return;
-
-	if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16),
-			&insn, sizeof(insn), FOLL_FORCE) != sizeof(insn))
-		return;
-
-	/* double check that tracee stopped on svc instruction */
-	if ((insn >> 8) != 0xa)
-		return;
-
-	regs->int_code = 0x20000 | (data & 0xffff);
-}
 /*
  * Write a word to the user area of a process at location addr. This
  * operation does have an additional problem compared to peek_user.
@@ -374,10 +353,12 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		}
 
 		if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
-			addr == offsetof(struct user, regs.gprs[2]))
-			fixup_int_code(child, data);
-		*(addr_t *)((addr_t) &regs->psw + addr) = data;
+			addr == offsetof(struct user, regs.gprs[2])) {
+			struct pt_regs *regs = task_pt_regs(child);
 
+			regs->int_code = 0x20000 | (data & 0xffff);
+		}
+		*(addr_t *)((addr_t) &regs->psw + addr) = data;
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
 		/*
 		 * access registers are stored in the thread structure
@@ -742,10 +723,12 @@ static int __poke_user_compat(struct task_struct *child,
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
 				(__u64)(tmp & PSW32_ADDR_AMODE);
 		} else {
-
 			if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
-				addr == offsetof(struct compat_user, regs.gprs[2]))
-				fixup_int_code(child, data);
+				addr == offsetof(struct compat_user, regs.gprs[2])) {
+				struct pt_regs *regs = task_pt_regs(child);
+
+				regs->int_code = 0x20000 | (data & 0xffff);
+			}
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
 		}
@@ -862,82 +845,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 }
 #endif
 
-asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
-{
-	unsigned long mask = -1UL;
-	long ret = -1;
-
-	if (is_compat_task())
-		mask = 0xffffffff;
-
-	/*
-	 * The sysc_tracesys code in entry.S stored the system
-	 * call number to gprs[2].
-	 */
-	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs)) {
-		/*
-		 * Tracing decided this syscall should not happen. Skip
-		 * the system call and the system call restart handling.
-		 */
-		goto skip;
-	}
-
-#ifdef CONFIG_SECCOMP
-	/* Do the secure computing check after ptrace. */
-	if (unlikely(test_thread_flag(TIF_SECCOMP))) {
-		struct seccomp_data sd;
-
-		if (is_compat_task()) {
-			sd.instruction_pointer = regs->psw.addr & 0x7fffffff;
-			sd.arch = AUDIT_ARCH_S390;
-		} else {
-			sd.instruction_pointer = regs->psw.addr;
-			sd.arch = AUDIT_ARCH_S390X;
-		}
-
-		sd.nr = regs->int_code & 0xffff;
-		sd.args[0] = regs->orig_gpr2 & mask;
-		sd.args[1] = regs->gprs[3] & mask;
-		sd.args[2] = regs->gprs[4] & mask;
-		sd.args[3] = regs->gprs[5] & mask;
-		sd.args[4] = regs->gprs[6] & mask;
-		sd.args[5] = regs->gprs[7] & mask;
-
-		if (__secure_computing(&sd) == -1)
-			goto skip;
-	}
-#endif /* CONFIG_SECCOMP */
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_enter(regs, regs->int_code & 0xffff);
-
-
-	audit_syscall_entry(regs->int_code & 0xffff, regs->orig_gpr2 & mask,
-			    regs->gprs[3] &mask, regs->gprs[4] &mask,
-			    regs->gprs[5] &mask);
-
-	if ((signed long)regs->gprs[2] >= NR_syscalls) {
-		regs->gprs[2] = -ENOSYS;
-		ret = -ENOSYS;
-	}
-	return regs->gprs[2];
-skip:
-	clear_pt_regs_flag(regs, PIF_SYSCALL);
-	return ret;
-}
-
-asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
-{
-	audit_syscall_exit(regs);
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->gprs[2]);
-
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
-		tracehook_report_syscall_exit(regs, 0);
-}
-
 /*
  * user_regset definitions.
  */