MIPS: Fix idle VS timer enqueue

MIPS re-enables interrupts on its idle routine and performs
a TIF_NEED_RESCHED check afterwards before putting the CPU to sleep.

The IRQs firing between the check and the 'wait' instruction may set the
TIF_NEED_RESCHED flag. In order to deal with this possible race, IRQs
interrupting __r4k_wait() rollback their return address to the
beginning of __r4k_wait() so that TIF_NEED_RESCHED is checked
again before going back to sleep.

However idle IRQs can also queue timers that may require a tick
reprogramming through a new generic idle loop iteration but those timers
would go unnoticed here because __r4k_wait() only checks
TIF_NEED_RESCHED. It doesn't check for pending timers.

Fix this with fast-forwarding idle IRQs return address to the end of the
idle routine instead of the beginning, so that the generic idle loop
handles both TIF_NEED_RESCHED and pending timers.

CONFIG_CPU_MICROMIPS has been removed along with the nop instructions.
There, NOPs are 2 byte in size, so change the code with 3 _ssnop which are
always 4 byte and remove the ifdef. Added ehb to make sure the hazard
is always cleared.

Fixes: c65a548 ("[MIPS] Fix potential latency problem due to non-atomic cpu_wait.")
Signed-off-by: Marco Crivellari <[email protected]>
Signed-off-by: Maciej W. Rozycki <[email protected]>
Acked-by: Frederic Weisbecker <[email protected]>
Signed-off-by: Thomas Bogendoerfer <[email protected]>

Author: DispatchCode

arch/mips/include/asm/idle.h

@@ -6,8 +6,7 @@
 #include <linux/linkage.h>
 
 extern void (*cpu_wait)(void);
-extern void r4k_wait(void);
-extern asmlinkage void __r4k_wait(void);
+extern asmlinkage void r4k_wait(void);
 extern void r4k_wait_irqoff(void);
 
 static inline int using_rollback_handler(void)

arch/mips/kernel/genex.S

@@ -104,42 +104,52 @@ handle_vcei:
 
 	__FINIT
 
-	.align	5	/* 32 byte rollback region */
-LEAF(__r4k_wait)
-	.set	push
-	.set	noreorder
-	/* start of rollback region */
-	LONG_L	t0, TI_FLAGS($28)
-	nop
-	andi	t0, _TIF_NEED_RESCHED
-	bnez	t0, 1f
-	 nop
-	nop
-	nop
-#ifdef CONFIG_CPU_MICROMIPS
-	nop
-	nop
-	nop
-	nop
-#endif
+	/* Align to 32 bytes for the maximum idle interrupt region size. */
+	.align	5
+LEAF(r4k_wait)
+	/* Keep the ISA bit clear for calculations on local labels here. */
+0:	.fill 	0
+	/* Start of idle interrupt region. */
+	local_irq_enable
+	/*
+	 * If an interrupt lands here, before going idle on the next
+	 * instruction, we must *NOT* go idle since the interrupt could
+	 * have set TIF_NEED_RESCHED or caused a timer to need resched.
+	 * Fall through -- see rollback_handler below -- and have the
+	 * idle loop take care of things.
+	 */
+1:	.fill	0
+	/* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up.  */
+	.if		1b - 0b > 32
+	.error	"overlong idle interrupt region"
+	.elseif	1b - 0b > 8
+	.align	4
+	.endif
+2:	.fill	0
+	.equ	r4k_wait_idle_size, 2b - 0b
+	/* End of idle interrupt region; size has to be a power of 2. */
 	.set	MIPS_ISA_ARCH_LEVEL_RAW
+r4k_wait_insn:
 	wait
-	/* end of rollback region (the region size must be power of two) */
-1:
+r4k_wait_exit:
+	.set	mips0
+	local_irq_disable
 	jr	ra
-	 nop
-	.set	pop
-	END(__r4k_wait)
+	END(r4k_wait)
+	.previous
 
 	.macro	BUILD_ROLLBACK_PROLOGUE handler
 	FEXPORT(rollback_\handler)
 	.set	push
 	.set	noat
 	MFC0	k0, CP0_EPC
-	PTR_LA	k1, __r4k_wait
-	ori	k0, 0x1f	/* 32 byte rollback region */
-	xori	k0, 0x1f
+	/* Subtract/add 2 to let the ISA bit propagate through the mask.  */
+	PTR_LA	k1, r4k_wait_insn - 2
+	ori 	k0, r4k_wait_idle_size - 2
+	.set	noreorder
 	bne	k0, k1, \handler
+	PTR_ADDIU 	k0, r4k_wait_exit - r4k_wait_insn + 2
+	.set	reorder
 	MTC0	k0, CP0_EPC
 	.set pop
 	.endm

arch/mips/kernel/idle.c

@@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void)
 	write_c0_conf(cfg | R30XX_CONF_HALT);
 }
 
-void __cpuidle r4k_wait(void)
-{
-	raw_local_irq_enable();
-	__r4k_wait();
-	raw_local_irq_disable();
-}
-
 /*
  * This variant is preferable as it allows testing need_resched and going to
  * sleep depending on the outcome atomically.  Unfortunately the "It is