powerpc: Revert "Use the POWER8 Micro Partition Prefetch Engine in KVM HV on POWER8"

This reverts commit 9678cdaae939 ("Use the POWER8 Micro Partition
Prefetch Engine in KVM HV on POWER8") because the original commit had
multiple, partly self-cancelling bugs, that could cause occasional
memory corruption.

In fact the logmpp instruction was incorrectly using register r0 as the
source of the buffer address and operation code, and depending on what
was in r0, it would either do nothing or corrupt the 64k page pointed to
by r0.

The logmpp instruction encoding and the operation code definitions could
be corrected, but then there is the problem that there is no clearly
defined way to know when the hardware has finished writing to the
buffer.

The original commit attempted to work around this by aborting the
write-out before starting the prefetch, but this is ineffective in the
case where the virtual core is now executing on a different physical
core from the one where the write-out was initiated.

These problems plus advice from the hardware designers not to use the
function (since the measured performance improvement from using the
feature was actually mostly negative), mean that reverting the code is
the best option.

Fixes: 9678cdaae939 ("Use the POWER8 Micro Partition Prefetch Engine in KVM HV on POWER8")
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 1 insertions, 54 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 228049786888..9c26c5a96ea2 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -36,7 +36,6 @@
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
-#include <asm/cache.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -75,12 +74,6 @@
 
 static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 
-#if defined(CONFIG_PPC_64K_PAGES)
-#define MPP_BUFFER_ORDER	0
-#elif defined(CONFIG_PPC_4K_PAGES)
-#define MPP_BUFFER_ORDER	3
-#endif
-
 static int dynamic_mt_modes = 6;
 module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)");
@@ -1455,13 +1448,6 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	vcore->kvm = kvm;
 	INIT_LIST_HEAD(&vcore->preempt_list);
 
-	vcore->mpp_buffer_is_valid = false;
-
-	if (cpu_has_feature(CPU_FTR_ARCH_207S))
-		vcore->mpp_buffer = (void *)__get_free_pages(
-			GFP_KERNEL|__GFP_ZERO,
-			MPP_BUFFER_ORDER);
-
 	return vcore;
 }
 
@@ -1894,33 +1880,6 @@ static int on_primary_thread(void)
 	return 1;
 }
 
-static void kvmppc_start_saving_l2_cache(struct kvmppc_vcore *vc)
-{
-	phys_addr_t phy_addr, mpp_addr;
-
-	phy_addr = (phys_addr_t)virt_to_phys(vc->mpp_buffer);
-	mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK;
-
-	mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_ABORT);
-	logmpp(mpp_addr | PPC_LOGMPP_LOG_L2);
-
-	vc->mpp_buffer_is_valid = true;
-}
-
-static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
-{
-	phys_addr_t phy_addr, mpp_addr;
-
-	phy_addr = virt_to_phys(vc->mpp_buffer);
-	mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK;
-
-	/* We must abort any in-progress save operations to ensure
-	 * the table is valid so that prefetch engine knows when to
-	 * stop prefetching. */
-	logmpp(mpp_addr | PPC_LOGMPP_LOG_ABORT);
-	mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
-}
-
 /*
  * A list of virtual cores for each physical CPU.
  * These are vcores that could run but their runner VCPU tasks are
@@ -2471,14 +2430,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
 
-	if (vc->mpp_buffer_is_valid)
-		kvmppc_start_restoring_l2_cache(vc);
-
 	__kvmppc_vcore_entry();
 
-	if (vc->mpp_buffer)
-		kvmppc_start_saving_l2_cache(vc);
-
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
 	spin_lock(&vc->lock);
@@ -3073,14 +3026,8 @@ static void kvmppc_free_vcores(struct kvm *kvm)
 {
 	long int i;
 
-	for (i = 0; i < KVM_MAX_VCORES; ++i) {
-		if (kvm->arch.vcores[i] && kvm->arch.vcores[i]->mpp_buffer) {
-			struct kvmppc_vcore *vc = kvm->arch.vcores[i];
-			free_pages((unsigned long)vc->mpp_buffer,
-				   MPP_BUFFER_ORDER);
-		}
+	for (i = 0; i < KVM_MAX_VCORES; ++i)
 		kfree(kvm->arch.vcores[i]);
-	}
 	kvm->arch.online_vcores = 0;
 }