cpu/hotplug: Prevent state corruption on error rollback

KAGA-KOKO · KAGA-KOKO · commit 69fa6eb7d6a6 · 2018-09-06T15:21:38.000+02:00
When a teardown callback fails, the CPU hotplug code brings the CPU back to the previous state. The previous state becomes the new target state. The rollback happens in undo_cpu_down() which increments the state unconditionally even if the state is already the same as the target. As a consequence the next CPU hotplug operation will start at the wrong state. This is easily to observe when __cpu_disable() fails. Prevent the unconditional undo by checking the state vs. target before incrementing state and fix up the consequently wrong conditional in the unplug code which handles the failure of the final CPU take down on the control CPU side. Fixes: 4dddfb5 ("smp/hotplug: Rewrite AP state machine core") Reported-by: Neeraj Upadhyay <neeraju@codeaurora.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Geert Uytterhoeven <geert+renesas@glider.be> Tested-by: Sudeep Holla <sudeep.holla@arm.com> Tested-by: Neeraj Upadhyay <neeraju@codeaurora.org> Cc: josh@joshtriplett.org Cc: peterz@infradead.org Cc: jiangshanlai@gmail.com Cc: dzickus@redhat.com Cc: brendan.jackman@arm.com Cc: malat@debian.org Cc: sramana@codeaurora.org Cc: linux-arm-msm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1809051419580.1416@nanos.tec.linutronix.de ----
diff --git a/kernel/cpu.c b/kernel/cpu.c
@@ -916,7 +916,8 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
 		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
 		if (ret) {
 			st->target = prev_state;
-			undo_cpu_down(cpu, st);
+			if (st->state < prev_state)
+				undo_cpu_down(cpu, st);
 			break;
 		}
 	}
@@ -969,7 +970,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	 * to do the further cleanups.
 	 */
 	ret = cpuhp_down_callbacks(cpu, st, target);
-	if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
+	if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) {
 		cpuhp_reset_state(st, prev_state);
 		__cpuhp_kick_ap(st);
 	}

Original file line number	Diff line number	Diff line change
`@@ -916,7 +916,8 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,`
`916`	`916`	`ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);`
`917`	`917`	`if (ret) {`
`918`	`918`	`st->target = prev_state;`
`919`		`- undo_cpu_down(cpu, st);`
	`919`	`+ if (st->state < prev_state)`
	`920`	`+ undo_cpu_down(cpu, st);`
`920`	`921`	`break;`
`921`	`922`	`}`
`922`	`923`	`}`
`@@ -969,7 +970,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,`
`969`	`970`	`* to do the further cleanups.`
`970`	`971`	`*/`
`971`	`972`	`ret = cpuhp_down_callbacks(cpu, st, target);`
`972`		`- if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {`
	`973`	`+ if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) {`
`973`	`974`	`cpuhp_reset_state(st, prev_state);`
`974`	`975`	`__cpuhp_kick_ap(st);`
`975`	`976`	`}`