[PATCH] powerpc/powernv: Fix local TLB flush for boot and MCE on POWER9

[Nicholas Piggin]

There are two cases outside the normal address space management
where a CPU's local TLB is to be flushed:

  1. Host boot; in case something has left stale entries in the
     TLB (e.g., kexec).

  2. Machine check; to clean corrupted TLB entries.

CPU state restore from deep idle states also flushes the TLB.
However this seems to be a side effect of reusing the boot code to set
CPU state, rather than a requirement itself.

The current flushing has a number of problems with ISA v3.0B:

- The current radix mode of the MMU is not taken into account. tlbiel
  is undefined if the R field does not match the current radix mode.

- ISA v3.0B hash must flush the partition and process table caches.

- ISA v3.0B radix must flush partition and process scoped translations,
  partition and process table caches, and also the page walk cache.

Add POWER9 cases to handle these, with radix vs hash determined by the
host MMU mode.

Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---

This is a relatively minimal version which does not churn code too
much or remove flushing from the CPU deep state idle restore path.
Should be suitable for stable after some upstream testing.

Thanks,
Nick

 arch/powerpc/kernel/cpu_setup_power.S | 13 ++++++--
 arch/powerpc/kernel/dt_cpu_ftrs.c     | 13 ++------
 arch/powerpc/kernel/mce_power.c       | 56 ++++++++++++++++++++++++++++++++++-
 3 files changed, 67 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 10cb2896b2ae..610955fe8b81 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -218,13 +218,20 @@ __init_tlb_power8:
 	ptesync
 1:	blr
 
+/*
+ * Flush the TLB in hash mode. Hash must flush with RIC=2 once for process
+ * and one for partition scope to clear process and partition table entries.
+ */
 __init_tlb_power9:
-	li	r6,POWER9_TLB_SETS_HASH
+	li	r6,POWER9_TLB_SETS_HASH - 1
 	mtctr	r6
 	li	r7,0xc00	/* IS field = 0b11 */
+	li	r8,0
 	ptesync
-2:	tlbiel	r7
-	addi	r7,r7,0x1000
+	PPC_TLBIEL(7, 8, 2, 1, 0)
+	PPC_TLBIEL(7, 8, 2, 0, 0)
+2:	addi	r7,r7,0x1000
+	PPC_TLBIEL(7, 8, 0, 0, 0)
 	bdnz	2b
 	ptesync
 1:	blr
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 4c7656dc4e04..b0da3718437d 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -105,24 +105,15 @@ static void cpufeatures_flush_tlb(void)
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
-		num_sets = POWER8_TLB_SETS;
+		__flush_tlb_power8(POWER8_TLB_SETS);
 		break;
 	case PVR_POWER9:
-		num_sets = POWER9_TLB_SETS_HASH;
+		__flush_tlb_power9(POWER9_TLB_SETS_HASH);
 		break;
 	default:
-		num_sets = 1;
 		pr_err("unknown CPU version for boot TLB flush\n");
 		break;
 	}
-
-	asm volatile("ptesync" : : : "memory");
-	rb = TLBIEL_INVAL_SET;
-	for (i = 0; i < num_sets; i++) {
-		asm volatile("tlbiel %0" : : "r" (rb));
-		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
-	}
-	asm volatile("ptesync" : : : "memory");
 }
 
 static void __restore_cpu_cpufeatures(void)
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index d24e689e893f..b76ca198e09c 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -53,6 +53,60 @@ static void flush_tlb_206(unsigned int num_sets, unsigned int action)
 	asm volatile("ptesync" : : : "memory");
 }
 
+static void flush_tlb_300(unsigned int num_sets, unsigned int action)
+{
+	unsigned long rb;
+	unsigned int i;
+	unsigned int r;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		rb = TLBIEL_INVAL_SET;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		rb = TLBIEL_INVAL_SET_LPID;
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	asm volatile("ptesync" : : : "memory");
+
+	if (early_radix_enabled())
+		r = 1;
+	else
+		r = 0;
+
+	/*
+	 * First flush table/PWC caches with set 0, then flush the
+	 * rest of the sets, partition scope. Radix must then do it
+	 * all again with process scope. Hash just has to flush
+	 * process table.
+	 */
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
+			"r"(rb), "r"(0), "i"(2), "i"(0), "r"(r));
+	for (i = 1; i < num_sets; i++) {
+		unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);
+
+		asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
+				"r"(rb+set), "r"(0), "i"(2), "i"(0), "r"(r));
+	}
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
+			"r"(rb), "r"(0), "i"(2), "i"(1), "r"(r));
+	if (early_radix_enabled()) {
+		for (i = 1; i < num_sets; i++) {
+			unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);
+
+			asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
+				"r"(rb+set), "r"(0), "i"(2), "i"(1), "r"(r));
+		}
+	}
+
+	asm volatile("ptesync" : : : "memory");
+}
+
 /*
  * Generic routines to flush TLB on POWER processors. These routines
  * are used as flush_tlb hook in the cpu_spec.
@@ -79,7 +133,7 @@ void __flush_tlb_power9(unsigned int action)
 	else
 		num_sets = POWER9_TLB_SETS_HASH;
 
-	flush_tlb_206(num_sets, action);
+	flush_tlb_300(num_sets, action);
 }
 
 
-- 
2.11.0