From patchwork series 423582

https://patchwork.ozlabs.org//project/linuxppc-dev/list/?series=423582

Author: Fox Snowpatch

arch/powerpc/Kconfig

@@ -204,6 +204,7 @@ config PPC
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP		if PCI
 	select GENERIC_PTDUMP
+        select GENERIC_ENTRY
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_TIME_NS

arch/powerpc/include/asm/hw_irq.h

@@ -216,6 +216,11 @@ static inline bool arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
+/*common entry*/
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
+{
+	return arch_irqs_disabled();
+}
 static inline void set_pmi_irq_pending(void)
 {
 	/*

arch/powerpc/include/asm/processor.h

@@ -394,6 +394,12 @@ int validate_sp(unsigned long sp, struct task_struct *p);
 int validate_sp_size(unsigned long sp, struct task_struct *p,
 		     unsigned long nbytes);
 
+/*for common entry*/
+static __always_inline bool on_thread_stack(void)
+{
+	return validate_sp(current_stack_pointer, current);
+}
+
 /*
  * Prefetch macros.
  */

arch/powerpc/include/asm/syscall.h

@@ -119,4 +119,9 @@ static inline int syscall_get_arch(struct task_struct *task)
 	else
 		return AUDIT_ARCH_PPC64;
 }
+
+static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
+{
+	return false;
+}
 #endif	/* _ASM_SYSCALL_H */

arch/powerpc/include/asm/thread_info.h

@@ -58,6 +58,7 @@ struct thread_info {
 	unsigned int	cpu;
 #endif
 	unsigned long	local_flags;		/* private flags for thread */
+	unsigned long	syscall_work;
 #ifdef CONFIG_LIVEPATCH_64
 	unsigned long *livepatch_sp;
 #endif

arch/powerpc/kernel/interrupt.c

@@ -294,11 +294,6 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 		regs->gpr[3] = r3;
 	}
 
-	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
-		do_syscall_trace_leave(regs);
-		ret |= _TIF_RESTOREALL;
-	}
-
 	local_irq_disable();
 	ret = interrupt_exit_user_prepare_main(ret, regs);
 

arch/powerpc/kernel/ptrace/ptrace.c

@@ -21,9 +21,6 @@
 #include <asm/switch_to.h>
 #include <asm/debug.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
 #include "ptrace-decl.h"
 
 /*
@@ -195,144 +192,6 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-#ifdef CONFIG_SECCOMP
-static int do_seccomp(struct pt_regs *regs)
-{
-	if (!test_thread_flag(TIF_SECCOMP))
-		return 0;
-
-	/*
-	 * The ABI we present to seccomp tracers is that r3 contains
-	 * the syscall return value and orig_gpr3 contains the first
-	 * syscall parameter. This is different to the ptrace ABI where
-	 * both r3 and orig_gpr3 contain the first syscall parameter.
-	 */
-	regs->gpr[3] = -ENOSYS;
-
-	/*
-	 * We use the __ version here because we have already checked
-	 * TIF_SECCOMP. If this fails, there is nothing left to do, we
-	 * have already loaded -ENOSYS into r3, or seccomp has put
-	 * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
-	 */
-	if (__secure_computing(NULL))
-		return -1;
-
-	/*
-	 * The syscall was allowed by seccomp, restore the register
-	 * state to what audit expects.
-	 * Note that we use orig_gpr3, which means a seccomp tracer can
-	 * modify the first syscall parameter (in orig_gpr3) and also
-	 * allow the syscall to proceed.
-	 */
-	regs->gpr[3] = regs->orig_gpr3;
-
-	return 0;
-}
-#else
-static inline int do_seccomp(struct pt_regs *regs) { return 0; }
-#endif /* CONFIG_SECCOMP */
-
-/**
- * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
- * @regs: the pt_regs of the task to trace (current)
- *
- * Performs various types of tracing on syscall entry. This includes seccomp,
- * ptrace, syscall tracepoints and audit.
- *
- * The pt_regs are potentially visible to userspace via ptrace, so their
- * contents is ABI.
- *
- * One or more of the tracers may modify the contents of pt_regs, in particular
- * to modify arguments or even the syscall number itself.
- *
- * It's also possible that a tracer can choose to reject the system call. In
- * that case this function will return an illegal syscall number, and will put
- * an appropriate return value in regs->r3.
- *
- * Return: the (possibly changed) syscall number.
- */
-long do_syscall_trace_enter(struct pt_regs *regs)
-{
-	u32 flags;
-
-	flags = read_thread_flags() & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
-
-	if (flags) {
-		int rc = ptrace_report_syscall_entry(regs);
-
-		if (unlikely(flags & _TIF_SYSCALL_EMU)) {
-			/*
-			 * A nonzero return code from
-			 * ptrace_report_syscall_entry() tells us to prevent
-			 * the syscall execution, but we are not going to
-			 * execute it anyway.
-			 *
-			 * Returning -1 will skip the syscall execution. We want
-			 * to avoid clobbering any registers, so we don't goto
-			 * the skip label below.
-			 */
-			return -1;
-		}
-
-		if (rc) {
-			/*
-			 * The tracer decided to abort the syscall. Note that
-			 * the tracer may also just change regs->gpr[0] to an
-			 * invalid syscall number, that is handled below on the
-			 * exit path.
-			 */
-			goto skip;
-		}
-	}
-
-	/* Run seccomp after ptrace; allow it to set gpr[3]. */
-	if (do_seccomp(regs))
-		return -1;
-
-	/* Avoid trace and audit when syscall is invalid. */
-	if (regs->gpr[0] >= NR_syscalls)
-		goto skip;
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_enter(regs, regs->gpr[0]);
-
-	if (!is_32bit_task())
-		audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
-				    regs->gpr[5], regs->gpr[6]);
-	else
-		audit_syscall_entry(regs->gpr[0],
-				    regs->gpr[3] & 0xffffffff,
-				    regs->gpr[4] & 0xffffffff,
-				    regs->gpr[5] & 0xffffffff,
-				    regs->gpr[6] & 0xffffffff);
-
-	/* Return the possibly modified but valid syscall number */
-	return regs->gpr[0];
-
-skip:
-	/*
-	 * If we are aborting explicitly, or if the syscall number is
-	 * now invalid, set the return value to -ENOSYS.
-	 */
-	regs->gpr[3] = -ENOSYS;
-	return -1;
-}
-
-void do_syscall_trace_leave(struct pt_regs *regs)
-{
-	int step;
-
-	audit_syscall_exit(regs);
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->result);
-
-	step = test_thread_flag(TIF_SINGLESTEP);
-	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
-		ptrace_report_syscall_exit(regs, step);
-}
-
 void __init pt_regs_check(void);
 
 /*

arch/powerpc/kernel/syscall.c

@@ -3,6 +3,7 @@
 #include <linux/compat.h>
 #include <linux/context_tracking.h>
 #include <linux/randomize_kstack.h>
+#include <linux/entry-common.h>
 
 #include <asm/interrupt.h>
 #include <asm/kup.h>
@@ -131,7 +132,7 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
 		 * and the test against NR_syscalls will fail and the return
 		 * value to be used is in regs->gpr[3].
 		 */
-		r0 = do_syscall_trace_enter(regs);
+		syscall_enter_from_user_mode(regs, r0);
 		if (unlikely(r0 >= NR_syscalls))
 			return regs->gpr[3];
 
@@ -185,5 +186,8 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
 	 */
 	choose_random_kstack_offset(mftb());
 
+	/*common entry*/
+	syscall_exit_to_user_mode(regs);
+
 	return ret;
 }

arch/powerpc/mm/fault.c

@@ -23,6 +23,7 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/entry-common.h>
 #include <linux/highmem.h>
 #include <linux/extable.h>
 #include <linux/kprobes.h>
@@ -578,15 +579,19 @@ NOKPROBE_SYMBOL(___do_page_fault);
 static __always_inline void __do_page_fault(struct pt_regs *regs)
 {
 	long err;
+	irqentry_state_t state = irqentry_enter(regs);
 
 	err = ___do_page_fault(regs, regs->dar, regs->dsisr);
 	if (unlikely(err))
 		bad_page_fault(regs, err);
+	irqentry_exit(regs, state);
 }
 
 DEFINE_INTERRUPT_HANDLER(do_page_fault)
 {
+	irqentry_state_t state = irqentry_enter(regs);
 	__do_page_fault(regs);
+	irqentry_exit(regs, state);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64