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>

arch/s390/Kconfig

@@ -123,6 +123,7 @@ config S390
 	select GENERIC_ALLOCATOR
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_VULNERABILITIES
+	select GENERIC_ENTRY
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_GETTIMEOFDAY
 	select GENERIC_PTDUMP

arch/s390/Kconfig.debug

@@ -6,10 +6,12 @@ config TRACE_IRQFLAGS_SUPPORT
 config EARLY_PRINTK
 	def_bool y
 
-config DEBUG_USER_ASCE
-	bool "Debug User ASCE"
+config DEBUG_ENTRY
+	bool "Debug low-level entry code"
+	depends on DEBUG_KERNEL
 	help
-	  Check on exit to user space that address space control
-	  elements are setup correctly.
+	  This option enables sanity checks in s390 low-level entry code.
+	  Some of these sanity checks may slow down kernel entries and
+	  exits or otherwise impact performance.
 
 	  If unsure, say N.

arch/s390/configs/debug_defconfig

@@ -833,7 +833,6 @@ CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_FTRACE_STARTUP_TEST=y
 # CONFIG_EVENT_TRACE_STARTUP_TEST is not set
-CONFIG_DEBUG_USER_ASCE=y
 CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y
@@ -857,3 +856,4 @@ CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
+CONFIG_DEBUG_ENTRY=y

arch/s390/configs/defconfig

@@ -781,7 +781,6 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
-CONFIG_DEBUG_USER_ASCE=y
 CONFIG_LKDTM=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y

arch/s390/include/asm/cputime.h

@@ -35,4 +35,6 @@ u64 arch_cpu_idle_time(int cpu);
 
 #define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
 
+void account_idle_time_irq(void);
+
 #endif /* _S390_CPUTIME_H */

arch/s390/include/asm/elf.h

@@ -233,8 +233,7 @@ extern char elf_platform[];
 do {								\
 	set_personality(PER_LINUX |				\
 		(current->personality & (~PER_MASK)));		\
-	current->thread.sys_call_table =			\
-		(unsigned long) &sys_call_table;		\
+	current->thread.sys_call_table = sys_call_table;	\
 } while (0)
 #else /* CONFIG_COMPAT */
 #define SET_PERSONALITY(ex)					\
@@ -245,11 +244,11 @@ do {								\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32) {		\
 		set_thread_flag(TIF_31BIT);			\
 		current->thread.sys_call_table =		\
-			(unsigned long)	&sys_call_table_emu;	\
+			sys_call_table_emu;			\
 	} else {						\
 		clear_thread_flag(TIF_31BIT);			\
 		current->thread.sys_call_table =		\
-			(unsigned long) &sys_call_table;	\
+			sys_call_table;				\
 	}							\
 } while (0)
 #endif /* CONFIG_COMPAT */

arch/s390/include/asm/entry-common.h

@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_S390_ENTRY_COMMON_H
+#define ARCH_S390_ENTRY_COMMON_H
+
+#include <linux/sched.h>
+#include <linux/audit.h>
+#include <linux/tracehook.h>
+#include <linux/processor.h>
+#include <linux/uaccess.h>
+#include <asm/fpu/api.h>
+
+#define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_GUARDED_STORAGE | _TIF_PER_TRAP)
+
+void do_per_trap(struct pt_regs *regs);
+void do_syscall(struct pt_regs *regs);
+
+typedef void (*pgm_check_func)(struct pt_regs *regs);
+
+extern pgm_check_func pgm_check_table[128];
+
+#ifdef CONFIG_DEBUG_ENTRY
+static __always_inline void arch_check_user_regs(struct pt_regs *regs)
+{
+	debug_user_asce(0);
+}
+
+#define arch_check_user_regs arch_check_user_regs
+#endif /* CONFIG_DEBUG_ENTRY */
+
+static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+							unsigned long ti_work)
+{
+	if (ti_work & _TIF_PER_TRAP) {
+		clear_thread_flag(TIF_PER_TRAP);
+		do_per_trap(regs);
+	}
+
+	if (ti_work & _TIF_GUARDED_STORAGE)
+		gs_load_bc_cb(regs);
+}
+
+#define arch_exit_to_user_mode_work arch_exit_to_user_mode_work
+
+static __always_inline void arch_exit_to_user_mode(void)
+{
+	if (test_cpu_flag(CIF_FPU))
+		__load_fpu_regs();
+
+	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+		debug_user_asce(1);
+}
+
+#define arch_exit_to_user_mode arch_exit_to_user_mode
+
+static inline bool on_thread_stack(void)
+{
+	return !(((unsigned long)(current->stack) ^ current_stack_pointer()) & ~(THREAD_SIZE - 1));
+}
+
+#endif

arch/s390/include/asm/fpu/api.h

@@ -47,6 +47,8 @@
 #include <linux/preempt.h>
 
 void save_fpu_regs(void);
+void load_fpu_regs(void);
+void __load_fpu_regs(void);
 
 static inline int test_fp_ctl(u32 fpc)
 {

arch/s390/include/asm/idle.h

@@ -20,11 +20,13 @@ struct s390_idle_data {
 	unsigned long long clock_idle_exit;
 	unsigned long long timer_idle_enter;
 	unsigned long long timer_idle_exit;
+	unsigned long mt_cycles_enter[8];
 };
 
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
-void psw_idle(struct s390_idle_data *, unsigned long);
+void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
+void psw_idle_exit(void);
 
 #endif /* _S390_IDLE_H */

arch/s390/include/asm/lowcore.h

@@ -81,8 +81,8 @@ struct lowcore {
 	psw_t	return_mcck_psw;		/* 0x02a0 */
 
 	/* CPU accounting and timing values. */
-	__u64	sync_enter_timer;		/* 0x02b0 */
-	__u64	async_enter_timer;		/* 0x02b8 */
+	__u64	sys_enter_timer;		/* 0x02b0 */
+	__u8	pad_0x02b8[0x02c0-0x02b8];	/* 0x02b8 */
 	__u64	mcck_enter_timer;		/* 0x02c0 */
 	__u64	exit_timer;			/* 0x02c8 */
 	__u64	user_timer;			/* 0x02d0 */

arch/s390/include/asm/nmi.h

@@ -99,6 +99,7 @@ int nmi_alloc_per_cpu(struct lowcore *lc);
 void nmi_free_per_cpu(struct lowcore *lc);
 
 void s390_handle_mcck(void);
+void __s390_handle_mcck(void);
 int s390_do_machine_check(struct pt_regs *regs);
 
 #endif /* __ASSEMBLY__ */

arch/s390/include/asm/processor.h

@@ -38,6 +38,11 @@
 #include <asm/runtime_instr.h>
 #include <asm/fpu/types.h>
 #include <asm/fpu/internal.h>
+#include <asm/irqflags.h>
+
+typedef long (*sys_call_ptr_t)(unsigned long, unsigned long,
+			       unsigned long, unsigned long,
+			       unsigned long, unsigned long);
 
 static inline void set_cpu_flag(int flag)
 {
@@ -101,31 +106,32 @@ extern void __bpon(void);
  */
 struct thread_struct {
 	unsigned int  acrs[NUM_ACRS];
-        unsigned long ksp;              /* kernel stack pointer             */
-	unsigned long user_timer;	/* task cputime in user space */
-	unsigned long guest_timer;	/* task cputime in kvm guest */
-	unsigned long system_timer;	/* task cputime in kernel space */
-	unsigned long hardirq_timer;	/* task cputime in hardirq context */
-	unsigned long softirq_timer;	/* task cputime in softirq context */
-	unsigned long sys_call_table;	/* system call table address */
-	unsigned long gmap_addr;	/* address of last gmap fault. */
-	unsigned int gmap_write_flag;	/* gmap fault write indication */
-	unsigned int gmap_int_code;	/* int code of last gmap fault */
-	unsigned int gmap_pfault;	/* signal of a pending guest pfault */
+	unsigned long ksp;			/* kernel stack pointer */
+	unsigned long user_timer;		/* task cputime in user space */
+	unsigned long guest_timer;		/* task cputime in kvm guest */
+	unsigned long system_timer;		/* task cputime in kernel space */
+	unsigned long hardirq_timer;		/* task cputime in hardirq context */
+	unsigned long softirq_timer;		/* task cputime in softirq context */
+	const sys_call_ptr_t *sys_call_table;	/* system call table address */
+	unsigned long gmap_addr;		/* address of last gmap fault. */
+	unsigned int gmap_write_flag;		/* gmap fault write indication */
+	unsigned int gmap_int_code;		/* int code of last gmap fault */
+	unsigned int gmap_pfault;		/* signal of a pending guest pfault */
+
 	/* Per-thread information related to debugging */
-	struct per_regs per_user;	/* User specified PER registers */
-	struct per_event per_event;	/* Cause of the last PER trap */
-	unsigned long per_flags;	/* Flags to control debug behavior */
-	unsigned int system_call;	/* system call number in signal */
-	unsigned long last_break;	/* last breaking-event-address. */
-        /* pfault_wait is used to block the process on a pfault event */
+	struct per_regs per_user;		/* User specified PER registers */
+	struct per_event per_event;		/* Cause of the last PER trap */
+	unsigned long per_flags;		/* Flags to control debug behavior */
+	unsigned int system_call;		/* system call number in signal */
+	unsigned long last_break;		/* last breaking-event-address. */
+	/* pfault_wait is used to block the process on a pfault event */
 	unsigned long pfault_wait;
 	struct list_head list;
 	/* cpu runtime instrumentation */
 	struct runtime_instr_cb *ri_cb;
-	struct gs_cb *gs_cb;		/* Current guarded storage cb */
-	struct gs_cb *gs_bc_cb;		/* Broadcast guarded storage cb */
-	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
+	struct gs_cb *gs_cb;			/* Current guarded storage cb */
+	struct gs_cb *gs_bc_cb;			/* Broadcast guarded storage cb */
+	unsigned char trap_tdb[256];		/* Transaction abort diagnose block */
 	/*
 	 * Warning: 'fpu' is dynamically-sized. It *MUST* be at
 	 * the end.
@@ -184,6 +190,7 @@ static inline void release_thread(struct task_struct *tsk) { }
 
 /* Free guarded storage control block */
 void guarded_storage_release(struct task_struct *tsk);
+void gs_load_bc_cb(struct pt_regs *regs);
 
 unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk) ((struct pt_regs *) \
@@ -324,6 +331,11 @@ extern void memcpy_absolute(void *, void *, size_t);
 extern int s390_isolate_bp(void);
 extern int s390_isolate_bp_guest(void);
 
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
+{
+	return arch_irqs_disabled_flags(regs->psw.mask);
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_S390_PROCESSOR_H */

arch/s390/include/asm/ptrace.h

@@ -11,13 +11,13 @@
 #include <uapi/asm/ptrace.h>
 
 #define PIF_SYSCALL		0	/* inside a system call */
-#define PIF_PER_TRAP		1	/* deliver sigtrap on return to user */
-#define PIF_SYSCALL_RESTART	2	/* restart the current system call */
+#define PIF_SYSCALL_RESTART	1	/* restart the current system call */
+#define PIF_SYSCALL_RET_SET	2	/* return value was set via ptrace */
 #define PIF_GUEST_FAULT		3	/* indicates program check in sie64a */
 
 #define _PIF_SYSCALL		BIT(PIF_SYSCALL)
-#define _PIF_PER_TRAP		BIT(PIF_PER_TRAP)
 #define _PIF_SYSCALL_RESTART	BIT(PIF_SYSCALL_RESTART)
+#define _PIF_SYSCALL_RET_SET	BIT(PIF_SYSCALL_RET_SET)
 #define _PIF_GUEST_FAULT	BIT(PIF_GUEST_FAULT)
 
 #ifndef __ASSEMBLY__
@@ -68,6 +68,9 @@ enum {
 	&(*(struct psw_bits *)(&(__psw)));	\
 }))
 
+#define PGM_INT_CODE_MASK	0x7f
+#define PGM_INT_CODE_PER	0x80
+
 /*
  * The pt_regs struct defines the way the registers are stored on
  * the stack during a system call.

arch/s390/include/asm/syscall.h

@@ -14,8 +14,8 @@
 #include <linux/err.h>
 #include <asm/ptrace.h>
 
-extern const unsigned long sys_call_table[];
-extern const unsigned long sys_call_table_emu[];
+extern const sys_call_ptr_t sys_call_table[];
+extern const sys_call_ptr_t sys_call_table_emu[];
 
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
@@ -56,6 +56,7 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
+	set_pt_regs_flag(regs, PIF_SYSCALL_RET_SET);
 	regs->gprs[2] = error ? error : val;
 }
 
@@ -97,4 +98,10 @@ static inline int syscall_get_arch(struct task_struct *task)
 #endif
 	return AUDIT_ARCH_S390X;
 }
+
+static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
+{
+	return false;
+}
+
 #endif	/* _ASM_SYSCALL_H */

arch/s390/include/asm/thread_info.h

@@ -36,6 +36,7 @@
  */
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
+	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
 };
 
 /*
@@ -68,6 +69,7 @@ void arch_setup_new_exec(void);
 #define TIF_NOTIFY_SIGNAL	7	/* signal notifications exist */
 #define TIF_ISOLATE_BP		8	/* Run process with isolated BP */
 #define TIF_ISOLATE_BP_GUEST	9	/* Run KVM guests with isolated BP */
+#define TIF_PER_TRAP		10	/* Need to handle PER trap on exit to usermode */
 
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
@@ -91,6 +93,7 @@ void arch_setup_new_exec(void);
 #define _TIF_PATCH_PENDING	BIT(TIF_PATCH_PENDING)
 #define _TIF_ISOLATE_BP		BIT(TIF_ISOLATE_BP)
 #define _TIF_ISOLATE_BP_GUEST	BIT(TIF_ISOLATE_BP_GUEST)
+#define _TIF_PER_TRAP		BIT(TIF_PER_TRAP)
 
 #define _TIF_31BIT		BIT(TIF_31BIT)
 #define _TIF_SINGLE_STEP	BIT(TIF_SINGLE_STEP)

arch/s390/include/asm/uaccess.h

@@ -18,7 +18,7 @@
 #include <asm/extable.h>
 #include <asm/facility.h>
 
-void debug_user_asce(void);
+void debug_user_asce(int exit);
 
 static inline int __range_ok(unsigned long addr, unsigned long size)
 {

arch/s390/include/asm/vtime.h

@@ -4,4 +4,18 @@
 
 #define __ARCH_HAS_VTIME_TASK_SWITCH
 
+static inline void update_timer_sys(void)
+{
+	S390_lowcore.system_timer += S390_lowcore.last_update_timer - S390_lowcore.exit_timer;
+	S390_lowcore.user_timer += S390_lowcore.exit_timer - S390_lowcore.sys_enter_timer;
+	S390_lowcore.last_update_timer = S390_lowcore.sys_enter_timer;
+}
+
+static inline void update_timer_mcck(void)
+{
+	S390_lowcore.system_timer += S390_lowcore.last_update_timer - S390_lowcore.exit_timer;
+	S390_lowcore.user_timer += S390_lowcore.exit_timer - S390_lowcore.mcck_enter_timer;
+	S390_lowcore.last_update_timer = S390_lowcore.mcck_enter_timer;
+}
+
 #endif /* _S390_VTIME_H */

arch/s390/include/uapi/asm/ptrace.h

@@ -179,8 +179,9 @@
 #define ACR_SIZE	4
 
 
-#define PTRACE_OLDSETOPTIONS	     21
-
+#define PTRACE_OLDSETOPTIONS		21
+#define PTRACE_SYSEMU			31
+#define PTRACE_SYSEMU_SINGLESTEP	32
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
 #include <linux/types.h>

arch/s390/kernel/Makefile

@@ -34,7 +34,7 @@ CFLAGS_dumpstack.o	+= -fno-optimize-sibling-calls
 CFLAGS_unwind_bc.o	+= -fno-optimize-sibling-calls
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
-obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
+obj-y	+= processor.o syscall.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o
 obj-y	+= sysinfo.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o

arch/s390/kernel/asm-offsets.c

@@ -26,26 +26,14 @@ int main(void)
 	BLANK();
 	/* thread struct offsets */
 	OFFSET(__THREAD_ksp, thread_struct, ksp);
-	OFFSET(__THREAD_sysc_table,  thread_struct, sys_call_table);
-	OFFSET(__THREAD_last_break, thread_struct, last_break);
-	OFFSET(__THREAD_FPU_fpc, thread_struct, fpu.fpc);
-	OFFSET(__THREAD_FPU_regs, thread_struct, fpu.regs);
-	OFFSET(__THREAD_per_cause, thread_struct, per_event.cause);
-	OFFSET(__THREAD_per_address, thread_struct, per_event.address);
-	OFFSET(__THREAD_per_paid, thread_struct, per_event.paid);
-	OFFSET(__THREAD_trap_tdb, thread_struct, trap_tdb);
 	BLANK();
 	/* thread info offsets */
 	OFFSET(__TI_flags, task_struct, thread_info.flags);
 	BLANK();
 	/* pt_regs offsets */
-	OFFSET(__PT_ARGS, pt_regs, args);
 	OFFSET(__PT_PSW, pt_regs, psw);
 	OFFSET(__PT_GPRS, pt_regs, gprs);
 	OFFSET(__PT_ORIG_GPR2, pt_regs, orig_gpr2);
-	OFFSET(__PT_INT_CODE, pt_regs, int_code);
-	OFFSET(__PT_INT_PARM, pt_regs, int_parm);
-	OFFSET(__PT_INT_PARM_LONG, pt_regs, int_parm_long);
 	OFFSET(__PT_FLAGS, pt_regs, flags);
 	OFFSET(__PT_CR1, pt_regs, cr1);
 	DEFINE(__PT_SIZE, sizeof(struct pt_regs));
@@ -64,6 +52,7 @@ int main(void)
 	OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit);
 	OFFSET(__TIMER_IDLE_ENTER, s390_idle_data, timer_idle_enter);
 	OFFSET(__TIMER_IDLE_EXIT, s390_idle_data, timer_idle_exit);
+	OFFSET(__MT_CYCLES_ENTER, s390_idle_data, mt_cycles_enter);
 	BLANK();
 	/* hardware defined lowcore locations 0x000 - 0x1ff */
 	OFFSET(__LC_EXT_PARAMS, lowcore, ext_params);
@@ -115,13 +104,9 @@ int main(void)
 	OFFSET(__LC_CPU_FLAGS, lowcore, cpu_flags);
 	OFFSET(__LC_RETURN_PSW, lowcore, return_psw);
 	OFFSET(__LC_RETURN_MCCK_PSW, lowcore, return_mcck_psw);
-	OFFSET(__LC_SYNC_ENTER_TIMER, lowcore, sync_enter_timer);
-	OFFSET(__LC_ASYNC_ENTER_TIMER, lowcore, async_enter_timer);
+	OFFSET(__LC_SYS_ENTER_TIMER, lowcore, sys_enter_timer);
 	OFFSET(__LC_MCCK_ENTER_TIMER, lowcore, mcck_enter_timer);
 	OFFSET(__LC_EXIT_TIMER, lowcore, exit_timer);
-	OFFSET(__LC_USER_TIMER, lowcore, user_timer);
-	OFFSET(__LC_SYSTEM_TIMER, lowcore, system_timer);
-	OFFSET(__LC_STEAL_TIMER, lowcore, steal_timer);
 	OFFSET(__LC_LAST_UPDATE_TIMER, lowcore, last_update_timer);
 	OFFSET(__LC_LAST_UPDATE_CLOCK, lowcore, last_update_clock);
 	OFFSET(__LC_INT_CLOCK, lowcore, int_clock);