feat(amu): enable per-core AMU auxiliary counters

This change makes AMU auxiliary counters configurable on a per-core
basis, controlled by `ENABLE_AMU_AUXILIARY_COUNTERS`.

Auxiliary counters can be described via the `HW_CONFIG` device tree if
the `ENABLE_AMU_FCONF` build option is enabled, or the platform must
otherwise implement the `plat_amu_topology` function.

A new phandle property for `cpu` nodes (`amu`) has been introduced to
the `HW_CONFIG` specification to allow CPUs to describe the view of
their own AMU:

```
cpu0: cpu@0 {
    ...

    amu = <&cpu0_amu>;
};
```

Multiple cores may share an `amu` handle if they implement the
same set of auxiliary counters.

AMU counters are described for one or more AMUs through the use of a new
`amus` node:

```
amus {
    cpu0_amu: amu-0 {
        #address-cells = <1>;
        #size-cells = <0>;

        counter@0 {
            reg = <0>;

            enable-at-el3;
        };

        counter@n {
            reg = <n>;

            ...
        };
    };
};
```

This structure describes the **auxiliary** (group 1) AMU counters.
Architected counters have architecturally-defined behaviour, and as
such do not require DTB entries.

These `counter` nodes support two properties:

- The `reg` property represents the counter register index.
- The presence of the `enable-at-el3` property determines whether
  the firmware should enable the counter prior to exiting EL3.

Change-Id: Ie43aee010518c5725a3b338a4899b0857caf4c28
Signed-off-by: Chris Kay <chris.kay@arm.com>
diff --git a/lib/extensions/amu/aarch32/amu.c b/lib/extensions/amu/aarch32/amu.c
index e92b9f1..57b1158 100644
--- a/lib/extensions/amu/aarch32/amu.c
+++ b/lib/extensions/amu/aarch32/amu.c
@@ -11,6 +11,7 @@
 #include "../amu_private.h"
 #include <arch.h>
 #include <arch_helpers.h>
+#include <common/debug.h>
 #include <lib/el3_runtime/pubsub_events.h>
 #include <lib/extensions/amu.h>
 
@@ -182,6 +183,30 @@
 	assert(amcgcr_cg0nc <= AMU_AMCGCR_CG0NC_MAX);
 
 	/*
+	 * The platform may opt to enable specific auxiliary counters. This can
+	 * be done via the common FCONF getter, or via the platform-implemented
+	 * function.
+	 */
+
+#if ENABLE_AMU_AUXILIARY_COUNTERS
+	const struct amu_topology *topology;
+
+#if ENABLE_AMU_FCONF
+	topology = FCONF_GET_PROPERTY(amu, config, topology);
+#else
+	topology = plat_amu_topology();
+#endif /* ENABLE_AMU_FCONF */
+
+	if (topology != NULL) {
+		unsigned int core_pos = plat_my_core_pos();
+
+		amcntenset1_el0_px = topology->cores[core_pos].enable;
+	} else {
+		ERROR("AMU: failed to generate AMU topology\n");
+	}
+#endif /* ENABLE_AMU_AUXILIARY_COUNTERS */
+
+	/*
 	 * Enable the requested counters.
 	 */
 
@@ -190,6 +215,10 @@
 	amcfgr_ncg = read_amcfgr_ncg();
 	if (amcfgr_ncg > 0U) {
 		write_amcntenset1_px(amcntenset1_px);
+
+#if !ENABLE_AMU_AUXILIARY_COUNTERS
+		VERBOSE("AMU: auxiliary counters detected but support is disabled\n");
+#endif
 	}
 
 	/* Initialize FEAT_AMUv1p1 features if present. */
diff --git a/lib/extensions/amu/aarch64/amu.c b/lib/extensions/amu/aarch64/amu.c
index 58094ae..f712520 100644
--- a/lib/extensions/amu/aarch64/amu.c
+++ b/lib/extensions/amu/aarch64/amu.c
@@ -12,11 +12,17 @@
 #include <arch.h>
 #include <arch_features.h>
 #include <arch_helpers.h>
+#include <common/debug.h>
 #include <lib/el3_runtime/pubsub_events.h>
 #include <lib/extensions/amu.h>
 
 #include <plat/common/platform.h>
 
+#if ENABLE_AMU_FCONF
+#	include <lib/fconf/fconf.h>
+#	include <lib/fconf/fconf_amu_getter.h>
+#endif
+
 struct amu_ctx {
 	uint64_t group0_cnts[AMU_GROUP0_MAX_COUNTERS];
 #if ENABLE_AMU_AUXILIARY_COUNTERS
@@ -227,6 +233,30 @@
 	assert(amcgcr_el0_cg0nc <= AMU_AMCGCR_CG0NC_MAX);
 
 	/*
+	 * The platform may opt to enable specific auxiliary counters. This can
+	 * be done via the common FCONF getter, or via the platform-implemented
+	 * function.
+	 */
+
+#if ENABLE_AMU_AUXILIARY_COUNTERS
+	const struct amu_topology *topology;
+
+#if ENABLE_AMU_FCONF
+	topology = FCONF_GET_PROPERTY(amu, config, topology);
+#else
+	topology = plat_amu_topology();
+#endif /* ENABLE_AMU_FCONF */
+
+	if (topology != NULL) {
+		unsigned int core_pos = plat_my_core_pos();
+
+		amcntenset1_el0_px = topology->cores[core_pos].enable;
+	} else {
+		ERROR("AMU: failed to generate AMU topology\n");
+	}
+#endif /* ENABLE_AMU_AUXILIARY_COUNTERS */
+
+	/*
 	 * Enable the requested counters.
 	 */
 
@@ -235,6 +265,10 @@
 	amcfgr_el0_ncg = read_amcfgr_el0_ncg();
 	if (amcfgr_el0_ncg > 0U) {
 		write_amcntenset1_el0_px(amcntenset1_el0_px);
+
+#if !ENABLE_AMU_AUXILIARY_COUNTERS
+		VERBOSE("AMU: auxiliary counters detected but support is disabled\n");
+#endif
 	}
 
 	/* Initialize FEAT_AMUv1p1 features if present. */
diff --git a/lib/extensions/amu/amu.mk b/lib/extensions/amu/amu.mk
index b4e04dd..0d203cb 100644
--- a/lib/extensions/amu/amu.mk
+++ b/lib/extensions/amu/amu.mk
@@ -4,5 +4,21 @@
 # SPDX-License-Identifier: BSD-3-Clause
 #
 
+include lib/fconf/fconf.mk
+
 AMU_SOURCES	:=	lib/extensions/amu/${ARCH}/amu.c \
 			lib/extensions/amu/${ARCH}/amu_helpers.S
+
+ifneq (${ENABLE_AMU_AUXILIARY_COUNTERS},0)
+        ifeq (${ENABLE_AMU},0)
+                $(error AMU auxiliary counter support (`ENABLE_AMU_AUXILIARY_COUNTERS`) requires AMU support (`ENABLE_AMU`))
+        endif
+endif
+
+ifneq (${ENABLE_AMU_FCONF},0)
+        ifeq (${ENABLE_AMU_AUXILIARY_COUNTERS},0)
+                $(error AMU FCONF support (`ENABLE_AMU_FCONF`) is not necessary when auxiliary counter support (`ENABLE_AMU_AUXILIARY_COUNTERS`) is disabled)
+        endif
+
+        AMU_SOURCES	+=	${FCONF_AMU_SOURCES}
+endif
diff --git a/lib/extensions/amu/amu_fconf.c b/lib/extensions/amu/amu_fconf.c
new file mode 100644
index 0000000..c7fb803
--- /dev/null
+++ b/lib/extensions/amu/amu_fconf.c
@@ -0,0 +1,200 @@
+/*
+ * Copyright (c) 2021, Arm Limited. All rights reserved.
+ *
+ * SPDX-License-Identifier: BSD-3-Clause
+ */
+
+#include <stddef.h>
+#include <stdint.h>
+
+#include "amu_private.h"
+#include <common/debug.h>
+#include <common/fdt_wrappers.h>
+#include <lib/extensions/amu.h>
+#include <lib/fconf/fconf.h>
+#include <libfdt.h>
+
+#include <plat/common/platform.h>
+
+static bool amu_topology_populated_ ; /* Whether the topology is valid */
+static struct amu_fconf_topology amu_topology_; /* Populated topology cache */
+
+const struct amu_fconf_topology *amu_topology(void)
+{
+	if (!amu_topology_populated_) {
+		return NULL;
+	}
+
+	return &amu_topology_;
+}
+
+/*
+ * Populate the core-specific AMU structure with information retrieved from a
+ * device tree.
+ *
+ * Returns `0` on success, or a negative integer representing an error code.
+ */
+static int amu_fconf_populate_cpu_amu(const void *fdt, int parent,
+				      struct amu_fconf_core *amu)
+{
+	int ret = 0;
+	int node = 0;
+
+	fdt_for_each_subnode(node, fdt, parent) {
+		const char *name;
+		const char *value;
+		int len;
+
+		uintptr_t idx = 0U;
+
+		name = fdt_get_name(fdt, node, &len);
+		if (strncmp(name, "counter@", 8) != 0) {
+			continue;
+		}
+
+		ret = fdt_get_reg_props_by_index(fdt, node, 0, &idx, NULL);
+		if (ret < 0) {
+			break;
+		}
+
+		value = fdt_getprop(fdt, node, "enable-at-el3", &len);
+		if ((value == NULL) && (len != -FDT_ERR_NOTFOUND)) {
+			break;
+		}
+
+		if (len != -FDT_ERR_NOTFOUND) {
+			amu->enable |= (1 << idx);
+		}
+	}
+
+	if ((node < 0) && (node != -FDT_ERR_NOTFOUND)) {
+		return node;
+	}
+
+	return ret;
+}
+
+/*
+ * Within a `cpu` node, attempt to dereference the `amu` property, and populate
+ * the AMU information for the core.
+ *
+ * Returns `0` on success, or a negative integer representing an error code.
+ */
+static int amu_fconf_populate_cpu(const void *fdt, int node, uintptr_t mpidr)
+{
+	int ret;
+	int idx;
+
+	uint32_t amu_phandle;
+	struct amu_fconf_core *amu;
+
+	ret = fdt_read_uint32(fdt, node, "amu", &amu_phandle);
+	if (ret < 0) {
+		if (ret == -FDT_ERR_NOTFOUND) {
+			ret = 0;
+		}
+
+		return ret;
+	}
+
+	node = fdt_node_offset_by_phandle(fdt, amu_phandle);
+	if (node < 0) {
+		return node;
+	}
+
+	idx = plat_core_pos_by_mpidr(mpidr);
+	amu = &amu_topology_.cores[idx];
+
+	return amu_fconf_populate_cpu_amu(fdt, node, amu);
+}
+
+/*
+ * For every CPU node (`/cpus/cpu@n`) in an FDT, executes a callback passing a
+ * pointer to the FDT and the offset of the CPU node. If the return value of the
+ * callback is negative, it is treated as an error and the loop is aborted. In
+ * this situation, the value of the callback is returned from the function.
+ *
+ * Returns `0` on success, or a negative integer representing an error code.
+ */
+static int amu_fconf_foreach_cpu(const void *fdt,
+				 int (*callback)(const void *, int, uintptr_t))
+{
+	int ret = 0;
+	int parent, node = 0;
+
+	parent = fdt_path_offset(fdt, "/cpus");
+	if (parent < 0) {
+		if (parent == -FDT_ERR_NOTFOUND) {
+			parent = 0;
+		}
+
+		return parent;
+	}
+
+	fdt_for_each_subnode(node, fdt, parent) {
+		const char *name;
+		int len;
+
+		uintptr_t mpidr = 0U;
+
+		name = fdt_get_name(fdt, node, &len);
+		if (strncmp(name, "cpu@", 4) != 0) {
+			continue;
+		}
+
+		ret = fdt_get_reg_props_by_index(fdt, node, 0, &mpidr, NULL);
+		if (ret < 0) {
+			break;
+		}
+
+		ret = callback(fdt, node, mpidr);
+		if (ret < 0) {
+			break;
+		}
+	}
+
+	if ((node < 0) && (node != -FDT_ERR_NOTFOUND)) {
+		return node;
+	}
+
+	return ret;
+}
+
+/*
+ * Populates the global `amu_topology` structure based on what's described by
+ * the hardware configuration device tree blob.
+ *
+ * The device tree is expected to provide an `amu` property for each `cpu` node,
+ * like so:
+ *
+ *     cpu@0 {
+ *         amu = <&cpu0_amu>;
+ *     };
+ *
+ *     amus {
+ *         cpu0_amu: amu-0 {
+ *             counters {
+ *                 #address-cells = <2>;
+ *                 #size-cells = <0>;
+ *
+ *                 counter@x,y {
+ *                     reg = <x y>; // Group x, counter y
+ *                 };
+ *             };
+ *         };
+ *     };
+ */
+static int amu_fconf_populate(uintptr_t config)
+{
+	int ret = amu_fconf_foreach_cpu(
+		(const void *)config, amu_fconf_populate_cpu);
+	if (ret < 0) {
+		ERROR("AMU-FCONF: Failed to configure AMU: %d\n", ret);
+	} else {
+		amu_topology_populated_ = true;
+	}
+
+	return ret;
+}
+
+FCONF_REGISTER_POPULATOR(HW_CONFIG, amu, amu_fconf_populate);
diff --git a/lib/fconf/fconf.mk b/lib/fconf/fconf.mk
index bc6f608..18bcb35 100644
--- a/lib/fconf/fconf.mk
+++ b/lib/fconf/fconf.mk
@@ -11,3 +11,6 @@
 
 FCONF_DYN_SOURCES	:=	lib/fconf/fconf_dyn_cfg_getter.c
 FCONF_DYN_SOURCES	+=	${FDT_WRAPPERS_SOURCES}
+
+FCONF_AMU_SOURCES	:=	lib/fconf/fconf_amu_getter.c
+FCONF_AMU_SOURCES	+=	${FDT_WRAPPERS_SOURCES}
diff --git a/lib/fconf/fconf_amu_getter.c b/lib/fconf/fconf_amu_getter.c
new file mode 100644
index 0000000..eff309c
--- /dev/null
+++ b/lib/fconf/fconf_amu_getter.c
@@ -0,0 +1,142 @@
+/*
+ * Copyright (c) 2021, Arm Limited. All rights reserved.
+ *
+ * SPDX-License-Identifier: BSD-3-Clause
+ */
+
+#include <stddef.h>
+#include <stdint.h>
+
+#include <common/debug.h>
+#include <common/fdt_wrappers.h>
+#include <lib/fconf/fconf.h>
+#include <lib/fconf/fconf_amu_getter.h>
+#include <libfdt.h>
+
+#include <plat/common/platform.h>
+
+struct fconf_amu_config fconf_amu_config;
+static struct amu_topology fconf_amu_topology_;
+
+/*
+ * Populate the core-specific AMU structure with information retrieved from a
+ * device tree.
+ *
+ * Returns `0` on success, or a negative integer representing an error code.
+ */
+static int fconf_populate_amu_cpu_amu(const void *fdt, int parent,
+				      struct amu_core *amu)
+{
+	int ret = 0;
+	int node = 0;
+
+	fdt_for_each_subnode(node, fdt, parent) {
+		const char *name;
+		const char *value;
+		int len;
+
+		uintptr_t idx = 0U;
+
+		name = fdt_get_name(fdt, node, &len);
+		if (strncmp(name, "counter@", 8) != 0) {
+			continue;
+		}
+
+		ret = fdt_get_reg_props_by_index(fdt, node, 0, &idx, NULL);
+		if (ret < 0) {
+			break;
+		}
+
+		value = fdt_getprop(fdt, node, "enable-at-el3", &len);
+		if ((value == NULL) && (len != -FDT_ERR_NOTFOUND)) {
+			break;
+		}
+
+		if (len != -FDT_ERR_NOTFOUND) {
+			amu->enable |= (1 << idx);
+		}
+	}
+
+	if ((node < 0) && (node != -FDT_ERR_NOTFOUND)) {
+		return node;
+	}
+
+	return ret;
+}
+
+/*
+ * Within a `cpu` node, attempt to dereference the `amu` property, and populate
+ * the AMU information for the core.
+ *
+ * Returns `0` on success, or a negative integer representing an error code.
+ */
+static int fconf_populate_amu_cpu(const void *fdt, int node, uintptr_t mpidr)
+{
+	int ret;
+	int idx;
+
+	uint32_t amu_phandle;
+	struct amu_core *amu;
+
+	ret = fdt_read_uint32(fdt, node, "amu", &amu_phandle);
+	if (ret < 0) {
+		if (ret == -FDT_ERR_NOTFOUND) {
+			ret = 0;
+		}
+
+		return ret;
+	}
+
+	node = fdt_node_offset_by_phandle(fdt, amu_phandle);
+	if (node < 0) {
+		return node;
+	}
+
+	idx = plat_core_pos_by_mpidr(mpidr);
+	if (idx < 0) {
+		return -FDT_ERR_BADVALUE;
+	}
+
+	amu = &fconf_amu_topology_.cores[idx];
+
+	return fconf_populate_amu_cpu_amu(fdt, node, amu);
+}
+
+/*
+ * Populates the global `amu_topology` structure based on what's described by
+ * the hardware configuration device tree blob.
+ *
+ * The device tree is expected to provide an `amu` property for each `cpu` node,
+ * like so:
+ *
+ *     cpu@0 {
+ *         amu = <&cpu0_amu>;
+ *     };
+ *
+ *     amus {
+ *         cpu0_amu: amu-0 {
+ *             counters {
+ *                 #address-cells = <2>;
+ *                 #size-cells = <0>;
+ *
+ *                 counter@x,y {
+ *                     reg = <x y>; // Group x, counter y
+ *                 };
+ *             };
+ *         };
+ *     };
+ */
+static int fconf_populate_amu(uintptr_t config)
+{
+	int ret = fdtw_for_each_cpu(
+		(const void *)config, fconf_populate_amu_cpu);
+	if (ret == 0) {
+		fconf_amu_config.topology = &fconf_amu_topology_;
+	} else {
+		ERROR("FCONF: failed to parse AMU information: %d\n", ret);
+	}
+
+	return ret;
+}
+
+FCONF_REGISTER_POPULATOR(HW_CONFIG, amu, fconf_populate_amu);