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, 84 insertions, 5 deletions

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index f8a8b9428ae2..c6d40bcf4a68 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/irq.h>
+#include <linux/entry-common.h>
 #include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/lowcore.h>
@@ -95,19 +96,97 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = CPU_RST,    .name = "RST", .desc = "[CPU] CPU Restart"},
 };
 
-void do_IRQ(struct pt_regs *regs, int irq)
+static void do_IRQ(struct pt_regs *regs, int irq)
 {
-	struct pt_regs *old_regs;
-
-	old_regs = set_irq_regs(regs);
-	irq_enter();
 	if (tod_after_eq(S390_lowcore.int_clock,
 			 S390_lowcore.clock_comparator))
 		/* Serve timer interrupts first. */
 		clock_comparator_work();
 	generic_handle_irq(irq);
+}
+
+static int on_async_stack(void)
+{
+	unsigned long frame = current_frame_address();
+
+	return !!!((S390_lowcore.async_stack - frame) >> (PAGE_SHIFT + THREAD_SIZE_ORDER));
+}
+
+static void do_irq_async(struct pt_regs *regs, int irq)
+{
+	if (on_async_stack())
+		do_IRQ(regs, irq);
+	else
+		CALL_ON_STACK(do_IRQ, S390_lowcore.async_stack, 2, regs, irq);
+}
+
+static int irq_pending(struct pt_regs *regs)
+{
+	int cc;
+
+	asm volatile("tpi 0\n"
+		     "ipm %0" : "=d" (cc) : : "cc");
+	return cc >> 28;
+}
+
+void noinstr do_io_irq(struct pt_regs *regs)
+{
+	irqentry_state_t state = irqentry_enter(regs);
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	int from_idle;
+
+	irq_enter();
+
+	if (user_mode(regs))
+		update_timer_sys();
+
+	from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit;
+	if (from_idle)
+		account_idle_time_irq();
+
+	do {
+		memcpy(&regs->int_code, &S390_lowcore.subchannel_id, 12);
+		if (S390_lowcore.io_int_word & BIT(31))
+			do_irq_async(regs, THIN_INTERRUPT);
+		else
+			do_irq_async(regs, IO_INTERRUPT);
+	} while (MACHINE_IS_LPAR && irq_pending(regs));
+
+	irq_exit();
+	set_irq_regs(old_regs);
+	irqentry_exit(regs, state);
+
+	if (from_idle)
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+}
+
+void noinstr do_ext_irq(struct pt_regs *regs)
+{
+	irqentry_state_t state = irqentry_enter(regs);
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	int from_idle;
+
+	irq_enter();
+
+	if (user_mode(regs))
+		update_timer_sys();
+
+	memcpy(&regs->int_code, &S390_lowcore.ext_cpu_addr, 4);
+	regs->int_parm = S390_lowcore.ext_params;
+	regs->int_parm_long = *(unsigned long *)S390_lowcore.ext_params2;
+
+	from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit;
+	if (from_idle)
+		account_idle_time_irq();
+
+	do_irq_async(regs, EXT_INTERRUPT);
+
 	irq_exit();
 	set_irq_regs(old_regs);
+	irqentry_exit(regs, state);
+
+	if (from_idle)
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)