riscv: Enable context tracking

This patch implements and enables context tracking for riscv (which is a
prerequisite for CONFIG_NO_HZ_FULL support)

It adds checking for previous state in the entry that all excepttions and
interrupts goes to and calls context_tracking_user_exit() if it comes from
user space. It also calls context_tracking_user_enter() if it will return
to user space before restore_all.

This patch is tested with the dynticks-testing testcase in
qemu-system-riscv64 virt machine and Unleashed board.
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/dynticks-testing.git

We can see the log here. The tick got mostly stopped during the execution
of the user loop.

                        _-----=> irqs-off
                       / _----=> need-resched
                      | / _---=> hardirq/softirq
                      || / _--=> preempt-depth
                      ||| /     delay
     TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
        | |       |   ||||       |         |
   <idle>-0     [001] d..2   604.183512: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=taskset next_pid=273 next_prio=120
user_loop-273   [001] d.h1   604.184788: hrtimer_expire_entry: hrtimer=000000002eda5fab function=tick_sched_timer now=604176096300
user_loop-273   [001] d.s2   604.184897: workqueue_queue_work: work struct=00000000383402c2 function=vmstat_update workqueue=00000000f36d35d4 req_cpu=1 cpu=1
user_loop-273   [001] dns2   604.185039: tick_stop: success=0 dependency=SCHED
user_loop-273   [001] dn.1   604.185103: tick_stop: success=0 dependency=SCHED
user_loop-273   [001] d..2   604.185154: sched_switch: prev_comm=taskset prev_pid=273 prev_prio=120 prev_state=R+ ==> next_comm=kworker/1:1 next_pid=46 next_prio=120
    <...>-46    [001] ....   604.185194: workqueue_execute_start: work struct 00000000383402c2: function vmstat_update
    <...>-46    [001] d..2   604.185266: sched_switch: prev_comm=kworker/1:1 prev_pid=46 prev_prio=120 prev_state=I ==> next_comm=taskset next_pid=273 next_prio=120
user_loop-273   [001] d.h1   604.188812: hrtimer_expire_entry: hrtimer=000000002eda5fab function=tick_sched_timer now=604180133400
user_loop-273   [001] d..1   604.189050: tick_stop: success=1 dependency=NONE
user_loop-273   [001] d..2   614.251386: sched_switch: prev_comm=user_loop prev_pid=273 prev_prio=120 prev_state=X ==> next_comm=swapper/1 next_pid=0 next_prio=120
   <idle>-0     [001] d..2   614.315391: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=taskset next_pid=276 next_prio=120

Signed-off-by: Greentime Hu <[email protected]>
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: greentime

arch/riscv/Kconfig

@@ -53,6 +53,7 @@ config RISCV
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ASM_MODVERSIONS
+	select HAVE_CONTEXT_TRACKING
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_EBPF_JIT if MMU

arch/riscv/kernel/entry.S

@@ -100,6 +100,16 @@ _save_context:
 #ifdef CONFIG_TRACE_IRQFLAGS
 	call trace_hardirqs_off
 #endif
+
+#ifdef CONFIG_CONTEXT_TRACKING
+	/* If previous state is in user mode, call context_tracking_user_exit. */
+	li   a0, SR_PP
+	and a0, s1, a0
+	bnez a0, skip_context_tracking
+	call context_tracking_user_exit
+skip_context_tracking:
+#endif
+
 	/*
 	 * MSB of cause differentiates between
 	 * interrupts and exceptions
@@ -145,7 +155,7 @@ _save_context:
 	tail do_trap_unknown
 
 handle_syscall:
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
 	/* Recover a0 - a7 for system calls */
 	REG_L a0, PT_A0(sp)
 	REG_L a1, PT_A1(sp)
@@ -227,6 +237,10 @@ resume_userspace:
 	andi s1, s0, _TIF_WORK_MASK
 	bnez s1, work_pending
 
+#ifdef CONFIG_CONTEXT_TRACKING
+	call context_tracking_user_enter
+#endif
+
 	/* Save unwound kernel stack pointer in thread_info */
 	addi s0, sp, PT_SIZE_ON_STACK
 	REG_S s0, TASK_TI_KERNEL_SP(tp)