arm64: Delay cpu feature capability checks

At the moment we run through the arm64_features capability list for
each CPU and set the capability if one of the CPU supports it. This
could be problematic in a heterogeneous system with differing capabilities.
Delay the CPU feature checks until all the enabled CPUs are up(i.e,
smp_cpus_done(), so that we can make better decisions based on the
overall system capability. Once we decide and advertise the capabilities
the alternatives can be applied. From this state, we cannot roll back
a feature to disabled based on the values from a new hotplugged CPU,
due to the runtime patching and other reasons. So, for all new CPUs,
we need to make sure that they have the established system capabilities.
Failing which, we bring the CPU down, preventing it from turning online.
Once the capabilities are decided, any new CPU booting up goes through
verification to ensure that it has all the enabled capabilities and also
invokes the respective enable() method on the CPU.

The CPU errata checks are not delayed and is still executed per-CPU
to detect the respective capabilities. If we ever come across a non-errata
capability that needs to be checked on each-CPU, we could introduce them via
a new capability table(or introduce a flag), which can be processed per CPU.

The next patch will make the feature checks use the system wide
safe value of a feature register.

NOTE: The enable() methods associated with the capability is scheduled
on all the CPUs (which is the only use case at the moment). If we need
a different type of 'enable()' which only needs to be run once on any CPU,
we should be able to handle that when needed.

Signed-off-by: Suzuki K. Poulose <suzuki.poulose@arm.com>
Tested-by: Dave Martin <Dave.Martin@arm.com>
[catalin.marinas@arm.com: static variable and coding style fixes]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

6 files changed, 111 insertions, 9 deletions

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 12d883a067c4..1603ae84ea45 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -70,7 +70,7 @@ struct arm64_cpu_capabilities {
         const char *desc;
         u16 capability;
         bool (*matches)(const struct arm64_cpu_capabilities *);
-        void (*enable)(void);
+        void (*enable)(void *);         /* Called on all active CPUs */
         union {
                 struct {        /* To be used for erratum handling only */
                         u32 midr_model;
@@ -140,7 +140,14 @@ void __init setup_cpu_features(void);
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
                             const char *info);
 void check_local_cpu_errata(void);
-void check_local_cpu_features(void);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void verify_local_cpu_capabilities(void);
+#else
+static inline void verify_local_cpu_capabilities(void)
+{
+}
+#endif
 
 u64 read_system_reg(u32 id);
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 98f32355dc97..4acb7ca94fcd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #endif
 
-void cpu_enable_pan(void);
+void cpu_enable_pan(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 78c4cb7af20e..e002cadf84bf 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
+#include <asm/cpu_ops.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 
@@ -645,19 +646,101 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 }
 
 /*
- * Run through the enabled capabilities and enable() it on the CPUs
+ * Run through the enabled capabilities and enable() it on all active
+ * CPUs
  */
 void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
         int i;
 
+        for (i = 0; caps[i].desc; i++)
+                if (caps[i].enable && cpus_have_cap(caps[i].capability))
+                        on_each_cpu(caps[i].enable, NULL, true);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Flag to indicate if we have computed the system wide
+ * capabilities based on the boot time active CPUs. This
+ * will be used to determine if a new booting CPU should
+ * go through the verification process to make sure that it
+ * supports the system capabilities, without using a hotplug
+ * notifier.
+ */
+static bool sys_caps_initialised;
+
+static inline void set_sys_caps_initialised(void)
+{
+        sys_caps_initialised = true;
+}
+
+/*
+ * Park the CPU which doesn't have the capability as advertised
+ * by the system.
+ */
+static void fail_incapable_cpu(char *cap_type,
+                                 const struct arm64_cpu_capabilities *cap)
+{
+        int cpu = smp_processor_id();
+
+        pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc);
+        /* Mark this CPU absent */
+        set_cpu_present(cpu, 0);
+
+        /* Check if we can park ourselves */
+        if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
+                cpu_ops[cpu]->cpu_die(cpu);
+        asm(
+        "1:     wfe\n"
+        "       wfi\n"
+        "       b       1b");
+}
+
+/*
+ * Run through the enabled system capabilities and enable() it on this CPU.
+ * The capabilities were decided based on the available CPUs at the boot time.
+ * Any new CPU should match the system wide status of the capability. If the
+ * new CPU doesn't have a capability which the system now has enabled, we
+ * cannot do anything to fix it up and could cause unexpected failures. So
+ * we park the CPU.
+ */
+void verify_local_cpu_capabilities(void)
+{
+        int i;
+        const struct arm64_cpu_capabilities *caps;
+
+        /*
+         * If we haven't computed the system capabilities, there is nothing
+         * to verify.
+         */
+        if (!sys_caps_initialised)
+                return;
+
+        caps = arm64_features;
         for (i = 0; caps[i].desc; i++) {
-                if (cpus_have_cap(caps[i].capability) && caps[i].enable)
-                        caps[i].enable();
+                if (!cpus_have_cap(caps[i].capability))
+                        continue;
+                /*
+                 * If the new CPU misses an advertised feature, we cannot proceed
+                 * further, park the cpu.
+                 */
+                if (!caps[i].matches(&caps[i]))
+                        fail_incapable_cpu("arm64_features", &caps[i]);
+                if (caps[i].enable)
+                        caps[i].enable(NULL);
         }
 }
 
-void check_local_cpu_features(void)
+#else   /* !CONFIG_HOTPLUG_CPU */
+
+static inline void set_sys_caps_initialised(void)
+{
+}
+
+#endif  /* CONFIG_HOTPLUG_CPU */
+
+static void setup_feature_capabilities(void)
 {
         update_cpu_capabilities(arm64_features, "detected feature:");
         enable_cpu_capabilities(arm64_features);
@@ -670,6 +753,12 @@ void __init setup_cpu_features(void)
         u32 cwg;
         int cls;
 
+        /* Set the CPU feature capabilies */
+        setup_feature_capabilities();
+
+        /* Advertise that we have computed the system capabilities */
+        set_sys_caps_initialised();
+
         /*
          * Check for sane CTR_EL0.CWG value.
          */
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index f25869ea2646..789fbea92b79 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -229,7 +229,6 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
         cpuinfo_detect_icache_policy(info);
 
         check_local_cpu_errata();
-        check_local_cpu_features();
 }
 
 void cpuinfo_store_cpu(void)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d1d00499f0cf..2bbdc0e4fd14 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -156,6 +156,13 @@ asmlinkage void secondary_start_kernel(void)
         preempt_disable();
         trace_hardirqs_off();
 
+        /*
+         * If the system has established the capabilities, make sure
+         * this CPU ticks all of those. If it doesn't, the CPU will
+         * fail to come online.
+         */
+        verify_local_cpu_capabilities();
+
         if (cpu_ops[cpu]->cpu_postboot)
                 cpu_ops[cpu]->cpu_postboot();
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index aba9ead1384c..066d5aea16c6 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -555,7 +555,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 }
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void)
+void cpu_enable_pan(void *__unused)
 {
         config_sctlr_el1(SCTLR_EL1_SPAN, 0);
 }