[PATCH] powerpc/64: system call implement the bulk of the logic in C fix

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/cputime.h | 39 +++++++++++++++++-------------
 arch/powerpc/kernel/syscall_64.c   | 26 ++++++++++++++------
 2 files changed, 41 insertions(+), 24 deletions(-)

diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index c43614cffaac..6639a6847cc0 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h

@@ -44,6 +44,28 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct)
 #ifdef CONFIG_PPC64
 #define get_accounting(tsk)	(&get_paca()->accounting)
 static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+
+/*
+ * account_cpu_user_entry/exit runs "unreconciled", so can't trace,
+ * can't use use get_paca()
+ */
+static notrace inline void account_cpu_user_entry(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = &local_paca->accounting;
+
+	acct->utime += (tb - acct->starttime_user);
+	acct->starttime = tb;
+}
+static notrace inline void account_cpu_user_exit(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = &local_paca->accounting;
+
+	acct->stime += (tb - acct->starttime);
+	acct->starttime_user = tb;
+}
+
 #else
 #define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
 /*

@@ -60,23 +82,6 @@ static inline void arch_vtime_task_switch(struct task_struct *prev)
 }
 #endif
 
-static inline void account_cpu_user_entry(void)
-{
-	unsigned long tb = mftb();
-	struct cpu_accounting_data *acct = get_accounting(current);
-
-	acct->utime += (tb - acct->starttime_user);
-	acct->starttime = tb;
-}
-static inline void account_cpu_user_exit(void)
-{
-	unsigned long tb = mftb();
-	struct cpu_accounting_data *acct = get_accounting(current);
-
-	acct->stime += (tb - acct->starttime);
-	acct->starttime_user = tb;
-}
-
 #endif /* __KERNEL__ */
 #else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 static inline void account_cpu_user_entry(void)

diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 529393a1ff1e..cfe458adde07 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c

@@ -19,7 +19,8 @@ extern void __noreturn tabort_syscall(void);
 
 typedef long (*syscall_fn)(long, long, long, long, long, long);
 
-long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
+/* Has to run notrace because it is entered "unreconciled" */
+notrace long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
 			   unsigned long r0, struct pt_regs *regs)
 {
 	unsigned long ti_flags;

@@ -36,7 +37,7 @@ long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
 #ifdef CONFIG_PPC_SPLPAR
 	if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
 	    firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct lppaca *lp = get_lppaca();
+		struct lppaca *lp = local_paca->lppaca_ptr;
 
 		if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
 			accumulate_stolen_time();

@@ -71,13 +72,22 @@ long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
 		 * We use the return value of do_syscall_trace_enter() as the
 		 * syscall number. If the syscall was rejected for any reason
 		 * do_syscall_trace_enter() returns an invalid syscall number
-		 * and the test below against NR_syscalls will fail.
+		 * 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);
-	}
-
-	if (unlikely(r0 >= NR_syscalls))
+		if (unlikely(r0 >= NR_syscalls))
+			return regs->gpr[3];
+		r3 = regs->gpr[3];
+		r4 = regs->gpr[4];
+		r5 = regs->gpr[5];
+		r6 = regs->gpr[6];
+		r7 = regs->gpr[7];
+		r8 = regs->gpr[8];
+
+	} else if (unlikely(r0 >= NR_syscalls)) {
 		return -ENOSYS;
+	}
 
 	/* May be faster to do array_index_nospec? */
 	barrier_nospec();

@@ -139,8 +149,10 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 		regs->gpr[3] = r3;
 	}
 
-	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE))
+	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
 		do_syscall_trace_leave(regs);
+		ret |= _TIF_RESTOREALL;
+	}
 
 again:
 	local_irq_disable();

-- 
2.23.0