KVM: PPC: Bookehv: Get vcpu's last instruction for emulation

On book3e, KVM uses load external pid (lwepx) dedicated instruction to read
guest last instruction on the exit path. lwepx exceptions (DTLB_MISS, DSI
and LRAT), generated by loading a guest address, needs to be handled by KVM.
These exceptions are generated in a substituted guest translation context
(EPLC[EGS] = 1) from host context (MSR[GS] = 0).

Currently, KVM hooks only interrupts generated from guest context (MSR[GS] = 1),
doing minimal checks on the fast path to avoid host performance degradation.
lwepx exceptions originate from host state (MSR[GS] = 0) which implies
additional checks in DO_KVM macro (beside the current MSR[GS] = 1) by looking
at the Exception Syndrome Register (ESR[EPID]) and the External PID Load Context
Register (EPLC[EGS]). Doing this on each Data TLB miss exception is obvious
too intrusive for the host.

Read guest last instruction from kvmppc_load_last_inst() by searching for the
physical address and kmap it. This address the TODO for TLB eviction and
execute-but-not-read entries, and allow us to get rid of lwepx until we are
able to handle failures.

A simple stress benchmark shows a 1% sys performance degradation compared with
previous approach (lwepx without failure handling):

time for i in `seq 1 10000`; do /bin/echo > /dev/null; done

real    0m 8.85s
user    0m 4.34s
sys     0m 4.48s

vs

real    0m 8.84s
user    0m 4.36s
sys     0m 4.44s

A solution to use lwepx and to handle its exceptions in KVM would be to temporary
highjack the interrupt vector from host. This imposes additional synchronizations
for cores like FSL e6500 that shares host IVOR registers between hardware threads.
This optimized solution can be later developed on top of this patch.

Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 44 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 50df5e3072cc..97bcde2dc075 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -819,6 +819,28 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 	}
 }
 
+static int kvmppc_resume_inst_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				  enum emulation_result emulated, u32 last_inst)
+{
+	switch (emulated) {
+	case EMULATE_AGAIN:
+		return RESUME_GUEST;
+
+	case EMULATE_FAIL:
+		pr_debug("%s: load instruction from guest address %lx failed\n",
+		       __func__, vcpu->arch.pc);
+		/* For debugging, encode the failing instruction and
+		 * report it to userspace. */
+		run->hw.hardware_exit_reason = ~0ULL << 32;
+		run->hw.hardware_exit_reason |= last_inst;
+		kvmppc_core_queue_program(vcpu, ESR_PIL);
+		return RESUME_HOST;
+
+	default:
+		BUG();
+	}
+}
+
 /**
  * kvmppc_handle_exit
  *
@@ -830,6 +852,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	int r = RESUME_HOST;
 	int s;
 	int idx;
+	u32 last_inst = KVM_INST_FETCH_FAILED;
+	enum emulation_result emulated = EMULATE_DONE;
 
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
@@ -837,6 +861,20 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* restart interrupts if they were meant for the host */
 	kvmppc_restart_interrupt(vcpu, exit_nr);
 
+	/*
+	 * get last instruction before beeing preempted
+	 * TODO: for e6500 check also BOOKE_INTERRUPT_LRAT_ERROR & ESR_DATA
+	 */
+	switch (exit_nr) {
+	case BOOKE_INTERRUPT_DATA_STORAGE:
+	case BOOKE_INTERRUPT_DTLB_MISS:
+	case BOOKE_INTERRUPT_HV_PRIV:
+		emulated = kvmppc_get_last_inst(vcpu, false, &last_inst);
+		break;
+	default:
+		break;
+	}
+
 	local_irq_enable();
 
 	trace_kvm_exit(exit_nr, vcpu);
@@ -845,6 +883,11 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 
+	if (emulated != EMULATE_DONE) {
+		r = kvmppc_resume_inst_load(run, vcpu, emulated, last_inst);
+		goto out;
+	}
+
 	switch (exit_nr) {
 	case BOOKE_INTERRUPT_MACHINE_CHECK:
 		printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
@@ -1134,6 +1177,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		BUG();
 	}
 
+out:
 	/*
 	 * To avoid clobbering exit_reason, only check for signals if we
 	 * aren't already exiting to userspace for some other reason.