powerpc/64s: Improve local TLB flush for boot and MCE on POWER9

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

  1. Booting the kernel, in case something has left stale entries in
     the TLB (e.g., kexec).

  2. Machine check, to clean corrupted TLB entries.

One other place where the TLB is flushed, is waking from deep idle
states. The flush is a side-effect of calling ->cpu_restore with the
intention of re-setting various SPRs. The flush itself is unnecessary
because in the first case, the TLB should not acquire new corrupted
TLB entries as part of sleep/wake (though they may be lost).

This type of TLB flush is coded inflexibly, several times for each CPU
type, and they have a number of problems with ISA v3.0B:

- The current radix mode of the MMU is not taken into account, it is
  always done as a hash flushn For IS=2 (LPID-matching flush from host)
  and IS=3 with HV=0 (guest kernel flush), tlbie(l) 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 as
  well.

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

So consolidate the flushing code and implement it in C and inline asm
under the mm/ directory with the rest of the flush code. Add ISA v3.0B
cases for radix and hash, and use the radix flush in radix environment.

Provide a way for IS=2 (LPID flush) to specify the radix mode of the
partition. Have KVM pass in the radix mode of the guest.

Take out the flushes from early cputable/dt_cpu_ftrs detection hooks,
and move it later in the boot process after, the MMU registers are set
up and before relocation is first turned on.

The TLB flush is no longer called when restoring from deep idle states.
This was not be done as a separate step because booting secondaries
uses the same cpu_restore as idle restore, which needs the TLB flush.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 177 insertions, 0 deletions

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 640cf566e986..a0675e91ad7d 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -47,6 +47,103 @@
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
+static inline void tlbiel_hash_set_isa206(unsigned int set, unsigned int is)
+{
+	unsigned long rb;
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+
+	asm volatile("tlbiel %0" : : "r" (rb));
+}
+
+/*
+ * tlbiel instruction for hash, set invalidation
+ * i.e., r=1 and is=01 or is=10 or is=11
+ */
+static inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is,
+					unsigned int pid,
+					unsigned int ric, unsigned int prs)
+{
+	unsigned long rb;
+	unsigned long rs;
+	unsigned int r = 0; /* hash format */
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : "memory");
+}
+
+
+static void tlbiel_all_isa206(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	for (set = 0; set < num_sets; set++)
+		tlbiel_hash_set_isa206(set, is);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and any caching of partition table
+	 * entries. Then flush the remaining sets of the TLB. Hash mode uses
+	 * partition scoped TLB translations.
+	 */
+	tlbiel_hash_set_isa300(0, is, 0, 2, 0);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+
+	/*
+	 * Now invalidate the process table cache.
+	 *
+	 * From ISA v3.0B p. 1078:
+	 *     The following forms are invalid.
+	 *      * PRS=1, R=0, and RIC!=2 (The only process-scoped
+	 *        HPT caching is of the Process Table.)
+	 */
+	tlbiel_hash_set_isa300(0, is, 0, 2, 1);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+void hash__tlbiel_all(unsigned int action)
+{
+	unsigned int is;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		is = 3;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		is = 2;
+		break;
+	default:
+		BUG();
+	}
+
+	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
+		tlbiel_all_isa300(POWER9_TLB_SETS_HASH, is);
+	else if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
+		tlbiel_all_isa206(POWER8_TLB_SETS, is);
+	else if (early_cpu_has_feature(CPU_FTR_ARCH_206))
+		tlbiel_all_isa206(POWER7_TLB_SETS, is);
+	else
+		WARN(1, "%s called on pre-POWER7 CPU\n", __func__);
+
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
 static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 						int apsize, int ssize)
 {
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 0c802ded6f21..69fa01e02b63 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1051,6 +1051,10 @@ void __init hash__early_init_mmu(void)
 	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206)
+			&& cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 #ifdef CONFIG_SMP
@@ -1070,6 +1074,10 @@ void hash__early_init_mmu_secondary(void)
 	}
 	/* Initialize SLB */
 	slb_initialize();
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206)
+			&& cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index cfbbee941a76..27ccab28665b 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -579,6 +579,9 @@ void __init radix__early_init_mmu(void)
 
 	radix_init_iamr();
 	radix_init_pgtable();
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 void radix__early_init_mmu_secondary(void)
@@ -600,6 +603,9 @@ void radix__early_init_mmu_secondary(void)
 		radix_init_amor();
 	}
 	radix_init_iamr();
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 void radix__mmu_cleanup_all(void)
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 884f4b705b57..fbaa429471a1 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -23,6 +23,72 @@
 #define RIC_FLUSH_PWC 1
 #define RIC_FLUSH_ALL 2
 
+/*
+ * tlbiel instruction for radix, set invalidation
+ * i.e., r=1 and is=01 or is=10 or is=11
+ */
+static inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is,
+					unsigned int pid,
+					unsigned int ric, unsigned int prs)
+{
+	unsigned long rb;
+	unsigned long rs;
+	unsigned int r = 1; /* radix format */
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : "memory");
+}
+
+static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and the entire Page Walk Cache
+	 * and partition table entries. Then flush the remaining sets of the
+	 * TLB.
+	 */
+	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
+
+	/* Do the same for process scoped entries. */
+	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+void radix__tlbiel_all(unsigned int action)
+{
+	unsigned int is;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		is = 3;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		is = 2;
+		break;
+	default:
+		BUG();
+	}
+
+	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
+		tlbiel_all_isa300(POWER9_TLB_SETS_RADIX, is);
+	else
+		WARN(1, "%s called on pre-POWER9 CPU\n", __func__);
+
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
 static inline void __tlbiel_pid(unsigned long pid, int set,
 				unsigned long ric)
 {