powerpc/mm: Fixup tlbie vs mtpidr/mtlpidr ordering issue on POWER9

commit 047e6575aec71d75b765c22111820c4776cd1c43 upstream.

On POWER9, under some circumstances, a broadcast TLB invalidation will
fail to invalidate the ERAT cache on some threads when there are
parallel mtpidr/mtlpidr happening on other threads of the same core.
This can cause stores to continue to go to a page after it's unmapped.

The workaround is to force an ERAT flush using PID=0 or LPID=0 tlbie
flush. This additional TLB flush will cause the ERAT cache
invalidation. Since we are using PID=0 or LPID=0, we don't get
filtered out by the TLB snoop filtering logic.

We need to still follow this up with another tlbie to take care of
store vs tlbie ordering issue explained in commit:
a5d4b5891c2f ("powerpc/mm: Fixup tlbie vs store ordering issue on
POWER9"). The presence of ERAT cache implies we can still get new
stores and they may miss store queue marking flush.

Cc: stable@vger.kernel.org
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190924035254.24612-3-aneesh.kumar@linux.ibm.com
[sandipan: Backported to v4.19]
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 32 insertions, 10 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 7c68d834c94a..02ab86be9ded 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -434,6 +434,37 @@ static inline int is_mmio_hpte(unsigned long v, unsigned long r)
 		(HPTE_R_KEY_HI | HPTE_R_KEY_LO));
 }
 
+static inline void fixup_tlbie_lpid(unsigned long rb_value, unsigned long lpid)
+{
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		/* Radix flush for a hash guest */
+
+		unsigned long rb,rs,prs,r,ric;
+
+		rb = PPC_BIT(52); /* IS = 2 */
+		rs = 0;  /* lpid = 0 */
+		prs = 0; /* partition scoped */
+		r = 1;   /* radix format */
+		ric = 0; /* RIC_FLSUH_TLB */
+
+		/*
+		 * Need the extra ptesync to make sure we don't
+		 * re-order the tlbie
+		 */
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+			     : : "r"(rb), "i"(r), "i"(prs),
+			       "i"(ric), "r"(rs) : "memory");
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+			     "r" (rb_value), "r" (lpid));
+	}
+}
+
 static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 		      long npages, int global, bool need_sync)
 {
@@ -452,16 +483,7 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
 		}
 
-		if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
-			/*
-			 * Need the extra ptesync to make sure we don't
-			 * re-order the tlbie
-			 */
-			asm volatile("ptesync": : :"memory");
-			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
-				     "r" (rbvalues[0]), "r" (kvm->arch.lpid));
-		}
-
+		fixup_tlbie_lpid(rbvalues[i - 1], kvm->arch.lpid);
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 	} else {
 		if (need_sync)