powerpc/powernv: Switch off MMU before entering nap/sleep/rvwinkle mode

commit 8117ac6a6c2fa0f847ff6a21a1f32c8d2c8501d0 upstream.

Currently, when going idle, we set the flag indicating that we are in
nap mode (paca->kvm_hstate.hwthread_state) and then execute the nap
(or sleep or rvwinkle) instruction, all with the MMU on.  This is bad
for two reasons: (a) the architecture specifies that those instructions
must be executed with the MMU off, and in fact with only the SF, HV, ME
and possibly RI bits set, and (b) this introduces a race, because as
soon as we set the flag, another thread can switch the MMU to a guest
context.  If the race is lost, this thread will typically start looping
on relocation-on ISIs at 0xc...4400.

This fixes it by setting the MSR as required by the architecture before
setting the flag or executing the nap/sleep/rvwinkle instruction.

[ shreyas@linux.vnet.ibm.com: Edited to handle LE ]
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index cb9c1740cee016ccf3f7272f4bbcd9041c4278ab..390e09872b77aac410df84f5bcc15b1534276b04 100644 (file)
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -116,6 +116,7 @@
 
 /* Server variant */
 #define MSR_           (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
+#define MSR_IDLE       (MSR_ME | MSR_SF | MSR_HV)
 #define MSR_KERNEL     (MSR_ | MSR_64BIT)
 #define MSR_USER32     (MSR_ | MSR_PR | MSR_EE)
 #define MSR_USER64     (MSR_USER32 | MSR_64BIT)

diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index e11863f4e595e2a3302e3ead79b439751ca5d402..df930727f73b451c183177eb0d9606d46877998a 100644 (file)
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -84,6 +84,22 @@ _GLOBAL(power7_nap)
        std     r9,_MSR(r1)
        std     r1,PACAR1(r13)
 
+       /*
+        * Go to real mode to do the nap, as required by the architecture.
+        * Also, we need to be in real mode before setting hwthread_state,
+        * because as soon as we do that, another thread can switch
+        * the MMU context to the guest.
+        */
+       LOAD_REG_IMMEDIATE(r5, MSR_IDLE)
+       li      r6, MSR_RI
+       andc    r6, r9, r6
+       LOAD_REG_ADDR(r7, power7_enter_nap_mode)
+       mtmsrd  r6, 1           /* clear RI before setting SRR0/1 */
+       mtspr   SPRN_SRR0, r7
+       mtspr   SPRN_SRR1, r5
+       rfid
+
+power7_enter_nap_mode:
 #ifdef CONFIG_KVM_BOOK3S_64_HV
        /* Tell KVM we're napping */
        li      r4,KVM_HWTHREAD_IN_NAP