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 # v4.14
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 v4.14]
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 80 insertions, 13 deletions

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 09b9263e3cc6..a4b6efbf667b 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -104,8 +104,30 @@ 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)
+static inline void fixup_tlbie_vpn(unsigned long vpn, int psize,
+				   int apsize, int ssize)
 {
+	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)) {
 		/* Need the extra ptesync to ensure we don't reorder tlbie*/
 		asm volatile("ptesync": : :"memory");
@@ -190,7 +212,7 @@ 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);
+		fixup_tlbie_vpn(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -759,7 +781,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		/*
 		 * Just do one more with the last used values.
 		 */
-		fixup_tlbie(vpn, psize, psize, ssize);
+		fixup_tlbie_vpn(vpn, psize, psize, ssize);
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
 
 		if (lock_tlbie)
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 5081e03b5e40..41e782f126d6 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -39,14 +39,18 @@ 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)
+
+static inline void fixup_tlbie_va(unsigned long va, unsigned long pid,
+				  unsigned long ap)
 {
-	unsigned long pid = 0;
-	unsigned long va = ((1UL << 52) - 1);
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, 0, ap, RIC_FLUSH_TLB);
+	}
 
 	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		asm volatile("ptesync": : :"memory");
-		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+		__tlbie_va(va, pid, ap, RIC_FLUSH_TLB);
 	}
 }
 
@@ -95,23 +99,64 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
-static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
+static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix 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");
-	fixup_tlbie();
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void fixup_tlbie_pid(unsigned long pid)
+{
+	/*
+	 * We can use any address for the invalidation, pick one which is
+	 * probably unused as an optimisation.
+	 */
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_pid(0, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+	}
+}
+
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
+{
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid(pid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid(pid);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid(pid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid(pid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid(pid);
+	}
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
 static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 			      unsigned long ap, unsigned long ric)
 {
@@ -135,7 +180,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 {
 	asm volatile("ptesync": : :"memory");
 	__tlbie_va(va, pid, ap, ric);
-	fixup_tlbie();
+	fixup_tlbie_va(va, pid, ap);
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }