powerpc/mm: Fixup tlbie vs store ordering issue on POWER9

On POWER9, under some circumstances, a broadcast TLB invalidation
might complete before all previous stores have drained, potentially
allowing stale stores from becoming visible after the invalidation.
This works around it by doubling up those TLB invalidations which was
verified by HW to be sufficient to close the risk window.

This will be documented in a yet-to-be-published errata.

Fixes: 1a472c9dba ("powerpc/mm/radix: Add tlbflush routines")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Enable the feature in the DT CPU features code for all Power9,
      rename the feature to CPU_FTR_P9_TLBIE_BUG per benh.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/mm/tlb-radix.c

@@ -151,6 +151,17 @@ static inline void __tlbie_va(unsigned long va, unsigned long pid,
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void fixup_tlbie(void)
+{
+	unsigned long pid = 0;
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+	}
+}
+
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
@@ -200,6 +211,7 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	default:
 		__tlbie_pid(pid, RIC_FLUSH_ALL);
 	}
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -253,6 +265,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 
 	asm volatile("ptesync": : :"memory");
 	__tlbie_va(va, pid, ap, ric);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -264,6 +277,7 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	if (also_pwc)
 		__tlbie_pid(pid, RIC_FLUSH_PWC);
 	__tlbie_va_range(start, end, pid, page_size, psize);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -498,6 +512,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
 						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+			fixup_tlbie();
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
 		}
 	}