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

commit a5d4b5891c2f1f865a2def1eb0030f534e77ff86 upstream.

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.

Cc: stable@vger.kernel.org # v4.14
Fixes: 1a472c9dba6b ("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>
Link: https://lore.kernel.org/r/20180323045627.16800-3-aneesh.kumar@linux.vnet.ibm.com/
[sandipan: Backported to v4.14]
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 46 insertions, 12 deletions

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 640cf566e986..96797bff5937 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -104,6 +104,15 @@ static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 	return va;
 }
 
+static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		/* Need the extra ptesync to ensure we don't reorder tlbie*/
+		asm volatile("ptesync": : :"memory");
+		___tlbie(vpn, psize, apsize, ssize);
+	}
+}
+
 static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long rb;
@@ -181,6 +190,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
 		asm volatile("ptesync": : :"memory");
 	} else {
 		__tlbie(vpn, psize, apsize, ssize);
+		fixup_tlbie(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -674,7 +684,7 @@ static void native_hpte_clear(void)
  */
 static void native_flush_hash_range(unsigned long number, int local)
 {
-	unsigned long vpn;
+	unsigned long vpn = 0;
 	unsigned long hash, index, hidx, shift, slot;
 	struct hash_pte *hptep;
 	unsigned long hpte_v;
@@ -746,6 +756,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 				__tlbie(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
+		/*
+		 * Just do one more with the last used values.
+		 */
+		fixup_tlbie(vpn, psize, psize, ssize);
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
 
 		if (lock_tlbie)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 12f95b1f7d07..48ed34d52ffd 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -491,6 +491,7 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
 	}
+	/* do we need fixup here ?*/
 	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 4b295cfd5f7e..1a4912c5e5a2 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -23,6 +23,33 @@
 #define RIC_FLUSH_PWC 1
 #define RIC_FLUSH_ALL 2
 
+static inline void __tlbie_va(unsigned long va, unsigned long pid,
+			      unsigned long ap, unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = pid << PPC_BITLSHIFT(31);
+	prs = 1; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	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);
+	}
+}
+
 static inline void __tlbiel_pid(unsigned long pid, int set,
 				unsigned long ric)
 {
@@ -80,6 +107,7 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	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");
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
@@ -105,19 +133,10 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
 			     unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,prs,r;
-
-	rb = va & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = pid << PPC_BITLSHIFT(31);
-	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
-
 	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");
+	__tlbie_va(va, pid, ap, ric);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
 /*