summaryrefslogtreecommitdiffstats
path: root/arch/powerpc
diff options
context:
space:
mode:
authorPaul Mackerras <paulus@ozlabs.org>2016-10-21 20:03:05 +1100
committerMichael Ellerman <mpe@ellerman.id.au>2016-10-24 19:29:36 +1100
commit56c46222af0d09149fadec2a3ce9d4889de01cc6 (patch)
treeeaf5e055eaea82bbb34a947e6c072bca764c9a37 /arch/powerpc
parenta05b82d5149dfeef05254a11c3636a89a854520a (diff)
downloadlinux-56c46222af0d09149fadec2a3ce9d4889de01cc6.tar.bz2
powerpc/64: Re-fix race condition between going idle and entering guest
Commit 8117ac6a6c2f ("powerpc/powernv: Switch off MMU before entering nap/sleep/rvwinkle mode", 2014-12-10) fixed a race condition where one thread entering a KVM guest could switch the MMU context to the guest while another thread was still in host kernel context with the MMU on. That commit moved the point where a thread entering a power-saving mode set its kvm_hstate.hwthread_state field in its PACA to KVM_HWTHREAD_IN_IDLE from a point where the MMU was on to after the MMU had been switched off. That commit also added a comment explaining that we have to switch to real mode before setting hwthread_state to avoid this race. Nevertheless, commit 4eae2c9ae54a ("powerpc/powernv: Make pnv_powersave_common more generic", 2016-07-08) subsequently moved the setting of hwthread_state back to a point where the MMU is on, thus reintroducing the race, despite the comment saying that this should not be done being included in full in the context lines of the patch that did it. This fixes the race again and adds a bigger and shoutier comment explaining the potential race condition. Fixes: 4eae2c9ae54a ("powerpc/powernv: Make pnv_powersave_common more generic") Cc: stable@vger.kernel.org # v4.8+ Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: Shreyas B. Prabhu <shreyasbp@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/kernel/idle_book3s.S32
1 files changed, 26 insertions, 6 deletions
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index bd739fed26e3..0d8712a835d2 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -163,12 +163,6 @@ _GLOBAL(pnv_powersave_common)
std r9,_MSR(r1)
std r1,PACAR1(r13)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- /* Tell KVM we're entering idle */
- li r4,KVM_HWTHREAD_IN_IDLE
- stb r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-
/*
* 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,
@@ -185,6 +179,26 @@ _GLOBAL(pnv_powersave_common)
.globl pnv_enter_arch207_idle_mode
pnv_enter_arch207_idle_mode:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /* Tell KVM we're entering idle */
+ li r4,KVM_HWTHREAD_IN_IDLE
+ /******************************************************/
+ /* N O T E W E L L ! ! ! N O T E W E L L */
+ /* The following store to HSTATE_HWTHREAD_STATE(r13) */
+ /* MUST occur in real mode, i.e. with the MMU off, */
+ /* and the MMU must stay off until we clear this flag */
+ /* and test HSTATE_HWTHREAD_REQ(r13) in the system */
+ /* reset interrupt vector in exceptions-64s.S. */
+ /* The reason is that another thread can switch the */
+ /* MMU to a guest context whenever this flag is set */
+ /* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on, */
+ /* that would potentially cause this thread to start */
+ /* executing instructions from guest memory in */
+ /* hypervisor mode, leading to a host crash or data */
+ /* corruption, or worse. */
+ /******************************************************/
+ stb r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
stb r3,PACA_THREAD_IDLE_STATE(r13)
cmpwi cr3,r3,PNV_THREAD_SLEEP
bge cr3,2f
@@ -250,6 +264,12 @@ enter_winkle:
* r3 - requested stop state
*/
power_enter_stop:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /* Tell KVM we're entering idle */
+ li r4,KVM_HWTHREAD_IN_IDLE
+ /* DO THIS IN REAL MODE! See comment above. */
+ stb r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
/*
* Check if the requested state is a deep idle state.
*/