Merge tag 'v4.0-rc1' into perf/core, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/powerpc/perf/core-fsl-emb.c

@@ -330,9 +330,11 @@ static int fsl_emb_pmu_add(struct perf_event *event, int flags)
 	}
 	local64_set(&event->hw.prev_count, val);
 
-	if (!(flags & PERF_EF_START)) {
+	if (unlikely(!(flags & PERF_EF_START))) {
 		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
 		val = 0;
+	} else {
+		event->hw.state &= ~(PERF_HES_STOPPED | PERF_HES_UPTODATE);
 	}
 
 	write_pmc(i, val);
@@ -389,6 +391,7 @@ static void fsl_emb_pmu_del(struct perf_event *event, int flags)
 static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
 {
 	unsigned long flags;
+	unsigned long val;
 	s64 left;
 
 	if (event->hw.idx < 0 || !event->hw.sample_period)
@@ -405,7 +408,10 @@ static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
 
 	event->hw.state = 0;
 	left = local64_read(&event->hw.period_left);
-	write_pmc(event->hw.idx, left);
+	val = 0;
+	if (left < 0x80000000L)
+		val = 0x80000000L - left;
+	write_pmc(event->hw.idx, val);
 
 	perf_event_update_userpage(event);
 	perf_pmu_enable(event->pmu);

arch/powerpc/perf/hv-24x7-catalog.h

@@ -30,4 +30,29 @@ struct hv_24x7_catalog_page_0 {
 	__u8 reserved6[2];
 } __packed;
 
+struct hv_24x7_event_data {
+	__be16 length; /* in bytes, must be a multiple of 16 */
+	__u8 reserved1[2];
+	__u8 domain; /* Chip = 1, Core = 2 */
+	__u8 reserved2[1];
+	__be16 event_group_record_offs; /* in bytes, must be 8 byte aligned */
+	__be16 event_group_record_len; /* in bytes */
+
+	/* in bytes, offset from event_group_record */
+	__be16 event_counter_offs;
+
+	/* verified_state, unverified_state, caveat_state, broken_state, ... */
+	__be32 flags;
+
+	__be16 primary_group_ix;
+	__be16 group_count;
+	__be16 event_name_len;
+	__u8 remainder[];
+	/* __u8 event_name[event_name_len - 2]; */
+	/* __be16 event_description_len; */
+	/* __u8 event_desc[event_description_len - 2]; */
+	/* __be16 detailed_desc_len; */
+	/* __u8 detailed_desc[detailed_desc_len - 2]; */
+} __packed;
+
 #endif

arch/powerpc/perf/hv-24x7-domains.h

@@ -0,0 +1,28 @@
+
+/*
+ * DOMAIN(name, num, index_kind, is_physical)
+ *
+ * @name:	An all caps token, suitable for use in generating an enum
+ *		member and appending to an event name in sysfs.
+ *
+ * @num:	The number corresponding to the domain as given in
+ *		documentation. We assume the catalog domain and the hcall
+ *		domain have the same numbering (so far they do), but this
+ *		may need to be changed in the future.
+ *
+ * @index_kind: A stringifiable token describing the meaning of the index
+ *		within the given domain. Must fit the parsing rules of the
+ *		perf sysfs api.
+ *
+ * @is_physical: True if the domain is physical, false otherwise (if virtual).
+ *
+ * Note: The terms PHYS_CHIP, PHYS_CORE, VCPU correspond to physical chip,
+ *	 physical core and virtual processor in 24x7 Counters specifications.
+ */
+
+DOMAIN(PHYS_CHIP, 0x01, chip, true)
+DOMAIN(PHYS_CORE, 0x02, core, true)
+DOMAIN(VCPU_HOME_CORE, 0x03, vcpu, false)
+DOMAIN(VCPU_HOME_CHIP, 0x04, vcpu, false)
+DOMAIN(VCPU_HOME_NODE, 0x05, vcpu, false)
+DOMAIN(VCPU_REMOTE_NODE, 0x06, vcpu, false)

arch/powerpc/perf/hv-24x7.c

@@ -13,16 +13,66 @@
 #define pr_fmt(fmt) "hv-24x7: " fmt
 
 #include <linux/perf_event.h>
+#include <linux/rbtree.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
+
 #include <asm/firmware.h>
 #include <asm/hvcall.h>
 #include <asm/io.h>
+#include <linux/byteorder/generic.h>
 
 #include "hv-24x7.h"
 #include "hv-24x7-catalog.h"
 #include "hv-common.h"
 
+static const char *event_domain_suffix(unsigned domain)
+{
+	switch (domain) {
+#define DOMAIN(n, v, x, c)		\
+	case HV_PERF_DOMAIN_##n:	\
+		return "__" #n;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+	default:
+		WARN(1, "unknown domain %d\n", domain);
+		return "__UNKNOWN_DOMAIN_SUFFIX";
+	}
+}
+
+static bool domain_is_valid(unsigned domain)
+{
+	switch (domain) {
+#define DOMAIN(n, v, x, c)		\
+	case HV_PERF_DOMAIN_##n:	\
+		/* fall through */
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_physical_domain(unsigned domain)
+{
+	switch (domain) {
+#define DOMAIN(n, v, x, c)		\
+	case HV_PERF_DOMAIN_##n:	\
+		return c;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+	default:
+		return false;
+	}
+}
+
+static bool catalog_entry_domain_is_valid(unsigned domain)
+{
+	return is_physical_domain(domain);
+}
+
 /*
  * TODO: Merging events:
  * - Think of the hcall as an interface to a 4d array of counters:
@@ -44,13 +94,14 @@
 
 /*
  * Example usage:
- *  perf stat -e 'hv_24x7/domain=2,offset=8,starting_index=0,lpar=0xffffffff/'
+ *  perf stat -e 'hv_24x7/domain=2,offset=8,vcpu=0,lpar=0xffffffff/'
  */
 
 /* u3 0-6, one of HV_24X7_PERF_DOMAIN */
 EVENT_DEFINE_RANGE_FORMAT(domain, config, 0, 3);
 /* u16 */
-EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 16, 31);
+EVENT_DEFINE_RANGE_FORMAT(core, config, 16, 31);
+EVENT_DEFINE_RANGE_FORMAT(vcpu, config, 16, 31);
 /* u32, see "data_offset" */
 EVENT_DEFINE_RANGE_FORMAT(offset, config, 32, 63);
 /* u16 */
@@ -63,7 +114,8 @@ EVENT_DEFINE_RANGE(reserved3, config2,  0, 63);
 static struct attribute *format_attrs[] = {
 	&format_attr_domain.attr,
 	&format_attr_offset.attr,
-	&format_attr_starting_index.attr,
+	&format_attr_core.attr,
+	&format_attr_vcpu.attr,
 	&format_attr_lpar.attr,
 	NULL,
 };
@@ -73,8 +125,115 @@ static struct attribute_group format_group = {
 	.attrs = format_attrs,
 };
 
+static struct attribute_group event_group = {
+	.name = "events",
+	/* .attrs is set in init */
+};
+
+static struct attribute_group event_desc_group = {
+	.name = "event_descs",
+	/* .attrs is set in init */
+};
+
+static struct attribute_group event_long_desc_group = {
+	.name = "event_long_descs",
+	/* .attrs is set in init */
+};
+
 static struct kmem_cache *hv_page_cache;
 
+static char *event_name(struct hv_24x7_event_data *ev, int *len)
+{
+	*len = be16_to_cpu(ev->event_name_len) - 2;
+	return (char *)ev->remainder;
+}
+
+static char *event_desc(struct hv_24x7_event_data *ev, int *len)
+{
+	unsigned nl = be16_to_cpu(ev->event_name_len);
+	__be16 *desc_len = (__be16 *)(ev->remainder + nl - 2);
+	*len = be16_to_cpu(*desc_len) - 2;
+	return (char *)ev->remainder + nl;
+}
+
+static char *event_long_desc(struct hv_24x7_event_data *ev, int *len)
+{
+	unsigned nl = be16_to_cpu(ev->event_name_len);
+	__be16 *desc_len_ = (__be16 *)(ev->remainder + nl - 2);
+	unsigned desc_len = be16_to_cpu(*desc_len_);
+	__be16 *long_desc_len = (__be16 *)(ev->remainder + nl + desc_len - 2);
+	*len = be16_to_cpu(*long_desc_len) - 2;
+	return (char *)ev->remainder + nl + desc_len;
+}
+
+static bool event_fixed_portion_is_within(struct hv_24x7_event_data *ev,
+					  void *end)
+{
+	void *start = ev;
+
+	return (start + offsetof(struct hv_24x7_event_data, remainder)) < end;
+}
+
+/*
+ * Things we don't check:
+ *  - padding for desc, name, and long/detailed desc is required to be '\0'
+ *    bytes.
+ *
+ *  Return NULL if we pass end,
+ *  Otherwise return the address of the byte just following the event.
+ */
+static void *event_end(struct hv_24x7_event_data *ev, void *end)
+{
+	void *start = ev;
+	__be16 *dl_, *ldl_;
+	unsigned dl, ldl;
+	unsigned nl = be16_to_cpu(ev->event_name_len);
+
+	if (nl < 2) {
+		pr_debug("%s: name length too short: %d", __func__, nl);
+		return NULL;
+	}
+
+	if (start + nl > end) {
+		pr_debug("%s: start=%p + nl=%u > end=%p",
+				__func__, start, nl, end);
+		return NULL;
+	}
+
+	dl_ = (__be16 *)(ev->remainder + nl - 2);
+	if (!IS_ALIGNED((uintptr_t)dl_, 2))
+		pr_warn("desc len not aligned %p", dl_);
+	dl = be16_to_cpu(*dl_);
+	if (dl < 2) {
+		pr_debug("%s: desc len too short: %d", __func__, dl);
+		return NULL;
+	}
+
+	if (start + nl + dl > end) {
+		pr_debug("%s: (start=%p + nl=%u + dl=%u)=%p > end=%p",
+				__func__, start, nl, dl, start + nl + dl, end);
+		return NULL;
+	}
+
+	ldl_ = (__be16 *)(ev->remainder + nl + dl - 2);
+	if (!IS_ALIGNED((uintptr_t)ldl_, 2))
+		pr_warn("long desc len not aligned %p", ldl_);
+	ldl = be16_to_cpu(*ldl_);
+	if (ldl < 2) {
+		pr_debug("%s: long desc len too short (ldl=%u)",
+				__func__, ldl);
+		return NULL;
+	}
+
+	if (start + nl + dl + ldl > end) {
+		pr_debug("%s: start=%p + nl=%u + dl=%u + ldl=%u > end=%p",
+				__func__, start, nl, dl, ldl, end);
+		return NULL;
+	}
+
+	return start + nl + dl + ldl;
+}
+
 static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096,
 					      unsigned long version,
 					      unsigned long index)
@@ -97,6 +256,609 @@ static unsigned long h_get_24x7_catalog_page(char page[],
 					version, index);
 }
 
+static unsigned core_domains[] = {
+	HV_PERF_DOMAIN_PHYS_CORE,
+	HV_PERF_DOMAIN_VCPU_HOME_CORE,
+	HV_PERF_DOMAIN_VCPU_HOME_CHIP,
+	HV_PERF_DOMAIN_VCPU_HOME_NODE,
+	HV_PERF_DOMAIN_VCPU_REMOTE_NODE,
+};
+/* chip event data always yeilds a single event, core yeilds multiple */
+#define MAX_EVENTS_PER_EVENT_DATA ARRAY_SIZE(core_domains)
+
+static char *event_fmt(struct hv_24x7_event_data *event, unsigned domain)
+{
+	const char *sindex;
+	const char *lpar;
+
+	if (is_physical_domain(domain)) {
+		lpar = "0x0";
+		sindex = "core";
+	} else {
+		lpar = "?";
+		sindex = "vcpu";
+	}
+
+	return kasprintf(GFP_KERNEL,
+			"domain=0x%x,offset=0x%x,%s=?,lpar=%s",
+			domain,
+			be16_to_cpu(event->event_counter_offs) +
+				be16_to_cpu(event->event_group_record_offs),
+			sindex,
+			lpar);
+}
+
+/* Avoid trusting fw to NUL terminate strings */
+static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp)
+{
+	return kasprintf(gfp, "%.*s", max_len, maybe_str);
+}
+
+static ssize_t device_show_string(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dev_ext_attribute *d;
+
+	d = container_of(attr, struct dev_ext_attribute, attr);
+	return sprintf(buf, "%s\n", (char *)d->var);
+}
+
+static struct attribute *device_str_attr_create_(char *name, char *str)
+{
+	struct dev_ext_attribute *attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+
+	if (!attr)
+		return NULL;
+
+	attr->var = str;
+	attr->attr.attr.name = name;
+	attr->attr.attr.mode = 0444;
+	attr->attr.show = device_show_string;
+	return &attr->attr.attr;
+}
+
+static struct attribute *device_str_attr_create(char *name, int name_max,
+						int name_nonce,
+						char *str, size_t str_max)
+{
+	char *n;
+	char *s = memdup_to_str(str, str_max, GFP_KERNEL);
+	struct attribute *a;
+
+	if (!s)
+		return NULL;
+
+	if (!name_nonce)
+		n = kasprintf(GFP_KERNEL, "%.*s", name_max, name);
+	else
+		n = kasprintf(GFP_KERNEL, "%.*s__%d", name_max, name,
+					name_nonce);
+	if (!n)
+		goto out_s;
+
+	a = device_str_attr_create_(n, s);
+	if (!a)
+		goto out_n;
+
+	return a;
+out_n:
+	kfree(n);
+out_s:
+	kfree(s);
+	return NULL;
+}
+
+static void device_str_attr_destroy(struct attribute *attr)
+{
+	struct dev_ext_attribute *d;
+
+	d = container_of(attr, struct dev_ext_attribute, attr.attr);
+	kfree(d->var);
+	kfree(d->attr.attr.name);
+	kfree(d);
+}
+
+static struct attribute *event_to_attr(unsigned ix,
+				       struct hv_24x7_event_data *event,
+				       unsigned domain,
+				       int nonce)
+{
+	int event_name_len;
+	char *ev_name, *a_ev_name, *val;
+	const char *ev_suffix;
+	struct attribute *attr;
+
+	if (!domain_is_valid(domain)) {
+		pr_warn("catalog event %u has invalid domain %u\n",
+				ix, domain);
+		return NULL;
+	}
+
+	val = event_fmt(event, domain);
+	if (!val)
+		return NULL;
+
+	ev_suffix = event_domain_suffix(domain);
+	ev_name = event_name(event, &event_name_len);
+	if (!nonce)
+		a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s",
+				(int)event_name_len, ev_name, ev_suffix);
+	else
+		a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s__%d",
+				(int)event_name_len, ev_name, ev_suffix, nonce);
+
+
+	if (!a_ev_name)
+		goto out_val;
+
+	attr = device_str_attr_create_(a_ev_name, val);
+	if (!attr)
+		goto out_name;
+
+	return attr;
+out_name:
+	kfree(a_ev_name);
+out_val:
+	kfree(val);
+	return NULL;
+}
+
+static struct attribute *event_to_desc_attr(struct hv_24x7_event_data *event,
+				int nonce)
+{
+	int nl, dl;
+	char *name = event_name(event, &nl);
+	char *desc = event_desc(event, &dl);
+
+	/* If there isn't a description, don't create the sysfs file */
+	if (!dl)
+		return NULL;
+
+	return device_str_attr_create(name, nl, nonce, desc, dl);
+}
+
+static struct attribute *
+event_to_long_desc_attr(struct hv_24x7_event_data *event, int nonce)
+{
+	int nl, dl;
+	char *name = event_name(event, &nl);
+	char *desc = event_long_desc(event, &dl);
+
+	/* If there isn't a description, don't create the sysfs file */
+	if (!dl)
+		return NULL;
+
+	return device_str_attr_create(name, nl, nonce, desc, dl);
+}
+
+static ssize_t event_data_to_attrs(unsigned ix, struct attribute **attrs,
+		struct hv_24x7_event_data *event, int nonce)
+{
+	unsigned i;
+
+	switch (event->domain) {
+	case HV_PERF_DOMAIN_PHYS_CHIP:
+		*attrs = event_to_attr(ix, event, event->domain, nonce);
+		return 1;
+	case HV_PERF_DOMAIN_PHYS_CORE:
+		for (i = 0; i < ARRAY_SIZE(core_domains); i++) {
+			attrs[i] = event_to_attr(ix, event, core_domains[i],
+						nonce);
+			if (!attrs[i]) {
+				pr_warn("catalog event %u: individual attr %u "
+					"creation failure\n", ix, i);
+				for (; i; i--)
+					device_str_attr_destroy(attrs[i - 1]);
+				return -1;
+			}
+		}
+		return i;
+	default:
+		pr_warn("catalog event %u: domain %u is not allowed in the "
+				"catalog\n", ix, event->domain);
+		return -1;
+	}
+}
+
+static size_t event_to_attr_ct(struct hv_24x7_event_data *event)
+{
+	switch (event->domain) {
+	case HV_PERF_DOMAIN_PHYS_CHIP:
+		return 1;
+	case HV_PERF_DOMAIN_PHYS_CORE:
+		return ARRAY_SIZE(core_domains);
+	default:
+		return 0;
+	}
+}
+
+static unsigned long vmalloc_to_phys(void *v)
+{
+	struct page *p = vmalloc_to_page(v);
+
+	BUG_ON(!p);
+	return page_to_phys(p) + offset_in_page(v);
+}
+
+/* */
+struct event_uniq {
+	struct rb_node node;
+	const char *name;
+	int nl;
+	unsigned ct;
+	unsigned domain;
+};
+
+static int memord(const void *d1, size_t s1, const void *d2, size_t s2)
+{
+	if (s1 < s2)
+		return 1;
+	if (s2 > s1)
+		return -1;
+
+	return memcmp(d1, d2, s1);
+}
+
+static int ev_uniq_ord(const void *v1, size_t s1, unsigned d1, const void *v2,
+					size_t s2, unsigned d2)
+{
+	int r = memord(v1, s1, v2, s2);
+
+	if (r)
+		return r;
+	if (d1 > d2)
+		return 1;
+	if (d2 > d1)
+		return -1;
+	return 0;
+}
+
+static int event_uniq_add(struct rb_root *root, const char *name, int nl,
+				unsigned domain)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct event_uniq *data;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct event_uniq *it;
+		int result;
+
+		it = container_of(*new, struct event_uniq, node);
+		result = ev_uniq_ord(name, nl, domain, it->name, it->nl,
+					it->domain);
+
+		parent = *new;
+		if (result < 0)
+			new = &((*new)->rb_left);
+		else if (result > 0)
+			new = &((*new)->rb_right);
+		else {
+			it->ct++;
+			pr_info("found a duplicate event %.*s, ct=%u\n", nl,
+						name, it->ct);
+			return it->ct;
+		}
+	}
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	*data = (struct event_uniq) {
+		.name = name,
+		.nl = nl,
+		.ct = 0,
+		.domain = domain,
+	};
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+
+	/* data->ct */
+	return 0;
+}
+
+static void event_uniq_destroy(struct rb_root *root)
+{
+	/*
+	 * the strings we point to are in the giant block of memory filled by
+	 * the catalog, and are freed separately.
+	 */
+	struct event_uniq *pos, *n;
+
+	rbtree_postorder_for_each_entry_safe(pos, n, root, node)
+		kfree(pos);
+}
+
+
+/*
+ * ensure the event structure's sizes are self consistent and don't cause us to
+ * read outside of the event
+ *
+ * On success, return the event length in bytes.
+ * Otherwise, return -1 (and print as appropriate).
+ */
+static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event,
+					  size_t event_idx,
+					  size_t event_data_bytes,
+					  size_t event_entry_count,
+					  size_t offset, void *end)
+{
+	ssize_t ev_len;
+	void *ev_end, *calc_ev_end;
+
+	if (offset >= event_data_bytes)
+		return -1;
+
+	if (event_idx >= event_entry_count) {
+		pr_devel("catalog event data has %zu bytes of padding after last event\n",
+				event_data_bytes - offset);
+		return -1;
+	}
+
+	if (!event_fixed_portion_is_within(event, end)) {
+		pr_warn("event %zu fixed portion is not within range\n",
+				event_idx);
+		return -1;
+	}
+
+	ev_len = be16_to_cpu(event->length);
+
+	if (ev_len % 16)
+		pr_info("event %zu has length %zu not divisible by 16: event=%pK\n",
+				event_idx, ev_len, event);
+
+	ev_end = (__u8 *)event + ev_len;
+	if (ev_end > end) {
+		pr_warn("event %zu has .length=%zu, ends after buffer end: ev_end=%pK > end=%pK, offset=%zu\n",
+				event_idx, ev_len, ev_end, end,
+				offset);
+		return -1;
+	}
+
+	calc_ev_end = event_end(event, end);
+	if (!calc_ev_end) {
+		pr_warn("event %zu has a calculated length which exceeds buffer length %zu: event=%pK end=%pK, offset=%zu\n",
+			event_idx, event_data_bytes, event, end,
+			offset);
+		return -1;
+	}
+
+	if (calc_ev_end > ev_end) {
+		pr_warn("event %zu exceeds it's own length: event=%pK, end=%pK, offset=%zu, calc_ev_end=%pK\n",
+			event_idx, event, ev_end, offset, calc_ev_end);
+		return -1;
+	}
+
+	return ev_len;
+}
+
+#define MAX_4K (SIZE_MAX / 4096)
+
+static void create_events_from_catalog(struct attribute ***events_,
+		struct attribute ***event_descs_,
+		struct attribute ***event_long_descs_)
+{
+	unsigned long hret;
+	size_t catalog_len, catalog_page_len, event_entry_count,
+	       event_data_len, event_data_offs,
+	       event_data_bytes, junk_events, event_idx, event_attr_ct, i,
+	       attr_max, event_idx_last, desc_ct, long_desc_ct;
+	ssize_t ct, ev_len;
+	uint32_t catalog_version_num;
+	struct attribute **events, **event_descs, **event_long_descs;
+	struct hv_24x7_catalog_page_0 *page_0 =
+		kmem_cache_alloc(hv_page_cache, GFP_KERNEL);
+	void *page = page_0;
+	void *event_data, *end;
+	struct hv_24x7_event_data *event;
+	struct rb_root ev_uniq = RB_ROOT;
+
+	if (!page)
+		goto e_out;
+
+	hret = h_get_24x7_catalog_page(page, 0, 0);
+	if (hret)
+		goto e_free;
+
+	catalog_version_num = be64_to_cpu(page_0->version);
+	catalog_page_len = be32_to_cpu(page_0->length);
+
+	if (MAX_4K < catalog_page_len) {
+		pr_err("invalid page count: %zu\n", catalog_page_len);
+		goto e_free;
+	}
+
+	catalog_len = catalog_page_len * 4096;
+
+	event_entry_count = be16_to_cpu(page_0->event_entry_count);
+	event_data_offs   = be16_to_cpu(page_0->event_data_offs);
+	event_data_len    = be16_to_cpu(page_0->event_data_len);
+
+	pr_devel("cv %zu cl %zu eec %zu edo %zu edl %zu\n",
+			(size_t)catalog_version_num, catalog_len,
+			event_entry_count, event_data_offs, event_data_len);
+
+	if ((MAX_4K < event_data_len)
+			|| (MAX_4K < event_data_offs)
+			|| (MAX_4K - event_data_offs < event_data_len)) {
+		pr_err("invalid event data offs %zu and/or len %zu\n",
+				event_data_offs, event_data_len);
+		goto e_free;
+	}
+
+	if ((event_data_offs + event_data_len) > catalog_page_len) {
+		pr_err("event data %zu-%zu does not fit inside catalog 0-%zu\n",
+				event_data_offs,
+				event_data_offs + event_data_len,
+				catalog_page_len);
+		goto e_free;
+	}
+
+	if (SIZE_MAX / MAX_EVENTS_PER_EVENT_DATA - 1 < event_entry_count) {
+		pr_err("event_entry_count %zu is invalid\n",
+				event_entry_count);
+		goto e_free;
+	}
+
+	event_data_bytes = event_data_len * 4096;
+
+	/*
+	 * event data can span several pages, events can cross between these
+	 * pages. Use vmalloc to make this easier.
+	 */
+	event_data = vmalloc(event_data_bytes);
+	if (!event_data) {
+		pr_err("could not allocate event data\n");
+		goto e_free;
+	}
+
+	end = event_data + event_data_bytes;
+
+	/*
+	 * using vmalloc_to_phys() like this only works if PAGE_SIZE is
+	 * divisible by 4096
+	 */
+	BUILD_BUG_ON(PAGE_SIZE % 4096);
+
+	for (i = 0; i < event_data_len; i++) {
+		hret = h_get_24x7_catalog_page_(
+				vmalloc_to_phys(event_data + i * 4096),
+				catalog_version_num,
+				i + event_data_offs);
+		if (hret) {
+			pr_err("failed to get event data in page %zu\n",
+					i + event_data_offs);
+			goto e_event_data;
+		}
+	}
+
+	/*
+	 * scan the catalog to determine the number of attributes we need, and
+	 * verify it at the same time.
+	 */
+	for (junk_events = 0, event = event_data, event_idx = 0, attr_max = 0;
+	     ;
+	     event_idx++, event = (void *)event + ev_len) {
+		size_t offset = (void *)event - (void *)event_data;
+		char *name;
+		int nl;
+
+		ev_len = catalog_event_len_validate(event, event_idx,
+						    event_data_bytes,
+						    event_entry_count,
+						    offset, end);
+		if (ev_len < 0)
+			break;
+
+		name = event_name(event, &nl);
+
+		if (event->event_group_record_len == 0) {
+			pr_devel("invalid event %zu (%.*s): group_record_len == 0, skipping\n",
+					event_idx, nl, name);
+			junk_events++;
+			continue;
+		}
+
+		if (!catalog_entry_domain_is_valid(event->domain)) {
+			pr_info("event %zu (%.*s) has invalid domain %d\n",
+					event_idx, nl, name, event->domain);
+			junk_events++;
+			continue;
+		}
+
+		attr_max += event_to_attr_ct(event);
+	}
+
+	event_idx_last = event_idx;
+	if (event_idx_last != event_entry_count)
+		pr_warn("event buffer ended before listed # of events were parsed (got %zu, wanted %zu, junk %zu)\n",
+				event_idx_last, event_entry_count, junk_events);
+
+	events = kmalloc_array(attr_max + 1, sizeof(*events), GFP_KERNEL);
+	if (!events)
+		goto e_event_data;
+
+	event_descs = kmalloc_array(event_idx + 1, sizeof(*event_descs),
+				GFP_KERNEL);
+	if (!event_descs)
+		goto e_event_attrs;
+
+	event_long_descs = kmalloc_array(event_idx + 1,
+			sizeof(*event_long_descs), GFP_KERNEL);
+	if (!event_long_descs)
+		goto e_event_descs;
+
+	/* Iterate over the catalog filling in the attribute vector */
+	for (junk_events = 0, event_attr_ct = 0, desc_ct = 0, long_desc_ct = 0,
+				event = event_data, event_idx = 0;
+			event_idx < event_idx_last;
+			event_idx++, ev_len = be16_to_cpu(event->length),
+				event = (void *)event + ev_len) {
+		char *name;
+		int nl;
+		int nonce;
+		/*
+		 * these are the only "bad" events that are intermixed and that
+		 * we can ignore without issue. make sure to skip them here
+		 */
+		if (event->event_group_record_len == 0)
+			continue;
+		if (!catalog_entry_domain_is_valid(event->domain))
+			continue;
+
+		name  = event_name(event, &nl);
+		nonce = event_uniq_add(&ev_uniq, name, nl, event->domain);
+		ct    = event_data_to_attrs(event_idx, events + event_attr_ct,
+					    event, nonce);
+		if (ct <= 0) {
+			pr_warn("event %zu (%.*s) creation failure, skipping\n",
+				event_idx, nl, name);
+			junk_events++;
+		} else {
+			event_attr_ct += ct;
+			event_descs[desc_ct] = event_to_desc_attr(event, nonce);
+			if (event_descs[desc_ct])
+				desc_ct++;
+			event_long_descs[long_desc_ct] =
+					event_to_long_desc_attr(event, nonce);
+			if (event_long_descs[long_desc_ct])
+				long_desc_ct++;
+		}
+	}
+
+	pr_info("read %zu catalog entries, created %zu event attrs (%zu failures), %zu descs\n",
+			event_idx, event_attr_ct, junk_events, desc_ct);
+
+	events[event_attr_ct] = NULL;
+	event_descs[desc_ct] = NULL;
+	event_long_descs[long_desc_ct] = NULL;
+
+	event_uniq_destroy(&ev_uniq);
+	vfree(event_data);
+	kmem_cache_free(hv_page_cache, page);
+
+	*events_ = events;
+	*event_descs_ = event_descs;
+	*event_long_descs_ = event_long_descs;
+	return;
+
+e_event_descs:
+	kfree(event_descs);
+e_event_attrs:
+	kfree(events);
+e_event_data:
+	vfree(event_data);
+e_free:
+	kmem_cache_free(hv_page_cache, page);
+e_out:
+	*events_ = NULL;
+	*event_descs_ = NULL;
+	*event_long_descs_ = NULL;
+}
+
 static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 			    struct bin_attribute *bin_attr, char *buf,
 			    loff_t offset, size_t count)
@@ -207,16 +969,13 @@ static struct attribute_group if_group = {
 
 static const struct attribute_group *attr_groups[] = {
 	&format_group,
+	&event_group,
+	&event_desc_group,
+	&event_long_desc_group,
 	&if_group,
 	NULL,
 };
 
-static bool is_physical_domain(int domain)
-{
-	return  domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP ||
-		domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
-}
-
 DEFINE_PER_CPU(char, hv_24x7_reqb[4096]) __aligned(4096);
 DEFINE_PER_CPU(char, hv_24x7_resb[4096]) __aligned(4096);
 
@@ -291,9 +1050,17 @@ out:
 static unsigned long event_24x7_request(struct perf_event *event, u64 *res,
 		bool success_expected)
 {
+	u16 idx;
+	unsigned domain = event_get_domain(event);
+
+	if (is_physical_domain(domain))
+		idx = event_get_core(event);
+	else
+		idx = event_get_vcpu(event);
+
 	return single_24x7_request(event_get_domain(event),
 				event_get_offset(event),
-				event_get_starting_index(event),
+				idx,
 				event_get_lpar(event),
 				res,
 				success_expected);
@@ -356,7 +1123,7 @@ static int h_24x7_event_init(struct perf_event *event)
 		return -EIO;
 	}
 
-	/* PHYSICAL domains & other lpars require extra capabilities */
+	/* Physical domains & other lpars require extra capabilities */
 	if (!caps.collect_privileged && (is_physical_domain(domain) ||
 		(event_get_lpar(event) != event_get_lpar_max()))) {
 		pr_devel("hv permisions disallow: is_physical_domain:%d, lpar=0x%llx\n",
@@ -452,6 +1219,10 @@ static int hv_24x7_init(void)
 	/* sampling not supported */
 	h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
+	create_events_from_catalog(&event_group.attrs,
+				   &event_desc_group.attrs,
+				   &event_long_desc_group.attrs);
+
 	r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
 	if (r)
 		return r;

arch/powerpc/perf/hv-24x7.h

@@ -3,14 +3,14 @@
 
 #include <linux/types.h>
 
+enum hv_perf_domains {
+#define DOMAIN(n, v, x, c) HV_PERF_DOMAIN_##n = v,
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+};
+
 struct hv_24x7_request {
 	/* PHYSICAL domains require enabling via phyp/hmc. */
-#define HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP 0x01
-#define HV_24X7_PERF_DOMAIN_PHYSICAL_CORE 0x02
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CORE   0x03
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CHIP   0x04
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_NODE   0x05
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_REMOTE_NODE 0x06
 	__u8 performance_domain;
 	__u8 reserved[0x1];
 

arch/powerpc/perf/hv-common.c

@@ -9,13 +9,13 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
 	unsigned long r;
 	struct p {
 		struct hv_get_perf_counter_info_params params;
-		struct cv_system_performance_capabilities caps;
+		struct hv_gpci_system_performance_capabilities caps;
 	} __packed __aligned(sizeof(uint64_t));
 
 	struct p arg = {
 		.params = {
 			.counter_request = cpu_to_be32(
-					CIR_SYSTEM_PERFORMANCE_CAPABILITIES),
+				HV_GPCI_system_performance_capabilities),
 			.starting_index = cpu_to_be32(-1),
 			.counter_info_version_in = 0,
 		}
@@ -31,9 +31,9 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
 
 	caps->version = arg.params.counter_info_version_out;
 	caps->collect_privileged = !!arg.caps.perf_collect_privileged;
-	caps->ga = !!(arg.caps.capability_mask & CV_CM_GA);
-	caps->expanded = !!(arg.caps.capability_mask & CV_CM_EXPANDED);
-	caps->lab = !!(arg.caps.capability_mask & CV_CM_LAB);
+	caps->ga = !!(arg.caps.capability_mask & HV_GPCI_CM_GA);
+	caps->expanded = !!(arg.caps.capability_mask & HV_GPCI_CM_EXPANDED);
+	caps->lab = !!(arg.caps.capability_mask & HV_GPCI_CM_LAB);
 
 	return r;
 }

arch/powerpc/perf/hv-common.h

@@ -20,6 +20,16 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps);
 PMU_FORMAT_ATTR(name, #attr_var ":" #bit_start "-" #bit_end);		\
 EVENT_DEFINE_RANGE(name, attr_var, bit_start, bit_end)
 
+/*
+ * The EVENT_DEFINE_RANGE_FORMAT() macro above includes helper functions
+ * for the fields (eg: event_get_starting_index()). For some fields we
+ * need the bit-range definition, but no the helper functions. Define a
+ * lite version of the above macro without the helpers and silence
+ * compiler warnings unused static functions.
+ */
+#define EVENT_DEFINE_RANGE_FORMAT_LITE(name, attr_var, bit_start, bit_end) \
+PMU_FORMAT_ATTR(name, #attr_var ":" #bit_start "-" #bit_end);
+
 #define EVENT_DEFINE_RANGE(name, attr_var, bit_start, bit_end)	\
 static u64 event_get_##name##_max(void)					\
 {									\

arch/powerpc/perf/hv-gpci-requests.h

@@ -0,0 +1,261 @@
+
+#include "req-gen/_begin.h"
+
+/*
+ * Based on the document "getPerfCountInfo v1.07"
+ */
+
+/*
+ * #define REQUEST_NAME counter_request_name
+ * #define REQUEST_NUM r_num
+ * #define REQUEST_IDX_KIND starting_index_kind
+ * #include I(REQUEST_BEGIN)
+ * REQUEST(
+ *	__field(...)
+ *	__field(...)
+ *	__array(...)
+ *	__count(...)
+ * )
+ * #include I(REQUEST_END)
+ *
+ * - starting_index_kind is one of the following, depending on the event:
+ *
+ *   hw_chip_id: hardware chip id or -1 for current hw chip
+ *   partition_id
+ *   sibling_part_id,
+ *   phys_processor_idx:
+ *   0xffffffffffffffff: or -1, which means it is irrelavant for the event
+ *
+ * __count(offset, bytes, name):
+ *	a counter that should be exposed via perf
+ * __field(offset, bytes, name)
+ *	a normal field
+ * __array(offset, bytes, name)
+ *	an array of bytes
+ *
+ *
+ *	@bytes for __count, and __field _must_ be a numeral token
+ *	in decimal, not an expression and not in hex.
+ *
+ *
+ * TODO:
+ *	- expose secondary index (if any counter ever uses it, only 0xA0
+ *	  appears to use it right now, and it doesn't have any counters)
+ *	- embed versioning info
+ *	- include counter descriptions
+ */
+#define REQUEST_NAME dispatch_timebase_by_processor
+#define REQUEST_NUM 0x10
+#define REQUEST_IDX_KIND "phys_processor_idx=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0,	8,	processor_time_in_timebase_cycles)
+	__field(0x8,	4,	hw_processor_id)
+	__field(0xC,	2,	owning_part_id)
+	__field(0xE,	1,	processor_state)
+	__field(0xF,	1,	version)
+	__field(0x10,	4,	hw_chip_id)
+	__field(0x14,	4,	phys_module_id)
+	__field(0x18,	4,	primary_affinity_domain_idx)
+	__field(0x1C,	4,	secondary_affinity_domain_idx)
+	__field(0x20,	4,	processor_version)
+	__field(0x24,	2,	logical_processor_idx)
+	__field(0x26,	2,	reserved)
+	__field(0x28,	4,	processor_id_register)
+	__field(0x2C,	4,	phys_processor_idx)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME entitled_capped_uncapped_donated_idle_timebase_by_partition
+#define REQUEST_NUM 0x20
+#define REQUEST_IDX_KIND "sibling_part_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	8,	partition_id)
+	__count(0x8,	8,	entitled_cycles)
+	__count(0x10,	8,	consumed_capped_cycles)
+	__count(0x18,	8,	consumed_uncapped_cycles)
+	__count(0x20,	8,	cycles_donated)
+	__count(0x28,	8,	purr_idle_cycles)
+)
+#include I(REQUEST_END)
+
+/*
+ * Not available for counter_info_version >= 0x8, use
+ * run_instruction_cycles_by_partition(0x100) instead.
+ */
+#define REQUEST_NAME run_instructions_run_cycles_by_partition
+#define REQUEST_NUM 0x30
+#define REQUEST_IDX_KIND "sibling_part_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	8,	partition_id)
+	__count(0x8,	8,	instructions_completed)
+	__count(0x10,	8,	cycles)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_performance_capabilities
+#define REQUEST_NUM 0x40
+#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	1,	perf_collect_privileged)
+	__field(0x1,	1,	capability_mask)
+	__array(0x2,	0xE,	reserved)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_abc_links
+#define REQUEST_NUM 0x50
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	4,	hw_chip_id)
+	__array(0x4,	0xC,	reserved1)
+	__count(0x10,	8,	total_link_cycles)
+	__count(0x18,	8,	idle_cycles_for_a_link)
+	__count(0x20,	8,	idle_cycles_for_b_link)
+	__count(0x28,	8,	idle_cycles_for_c_link)
+	__array(0x30,	0x20,	reserved2)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_wxyz_links
+#define REQUEST_NUM 0x60
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	4,	hw_chip_id)
+	__array(0x4,	0xC,	reserved1)
+	__count(0x10,	8,	total_link_cycles)
+	__count(0x18,	8,	idle_cycles_for_w_link)
+	__count(0x20,	8,	idle_cycles_for_x_link)
+	__count(0x28,	8,	idle_cycles_for_y_link)
+	__count(0x30,	8,	idle_cycles_for_z_link)
+	__array(0x38,	0x28,	reserved2)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_gx_links
+#define REQUEST_NUM 0x70
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	4,	hw_chip_id)
+	__array(0x4,	0xC,	reserved1)
+	__count(0x10,	8,	gx0_in_address_cycles)
+	__count(0x18,	8,	gx0_in_data_cycles)
+	__count(0x20,	8,	gx0_in_retries)
+	__count(0x28,	8,	gx0_in_bus_cycles)
+	__count(0x30,	8,	gx0_in_cycles_total)
+	__count(0x38,	8,	gx0_out_address_cycles)
+	__count(0x40,	8,	gx0_out_data_cycles)
+	__count(0x48,	8,	gx0_out_retries)
+	__count(0x50,	8,	gx0_out_bus_cycles)
+	__count(0x58,	8,	gx0_out_cycles_total)
+	__count(0x60,	8,	gx1_in_address_cycles)
+	__count(0x68,	8,	gx1_in_data_cycles)
+	__count(0x70,	8,	gx1_in_retries)
+	__count(0x78,	8,	gx1_in_bus_cycles)
+	__count(0x80,	8,	gx1_in_cycles_total)
+	__count(0x88,	8,	gx1_out_address_cycles)
+	__count(0x90,	8,	gx1_out_data_cycles)
+	__count(0x98,	8,	gx1_out_retries)
+	__count(0xA0,	8,	gx1_out_bus_cycles)
+	__count(0xA8,	8,	gx1_out_cycles_total)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_mc_links
+#define REQUEST_NUM 0x80
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	4,	hw_chip_id)
+	__array(0x4,	0xC,	reserved1)
+	__count(0x10,	8,	mc0_frames)
+	__count(0x18,	8,	mc0_reads)
+	__count(0x20,	8,	mc0_write)
+	__count(0x28,	8,	mc0_total_cycles)
+	__count(0x30,	8,	mc1_frames)
+	__count(0x38,	8,	mc1_reads)
+	__count(0x40,	8,	mc1_writes)
+	__count(0x48,	8,	mc1_total_cycles)
+)
+#include I(REQUEST_END)
+
+/* Processor_config (0x90) skipped, no counters */
+/* Current_processor_frequency (0x91) skipped, no counters */
+
+#define REQUEST_NAME processor_core_utilization
+#define REQUEST_NUM 0x94
+#define REQUEST_IDX_KIND "phys_processor_idx=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	4,	phys_processor_idx)
+	__field(0x4,	4,	hw_processor_id)
+	__count(0x8,	8,	cycles_across_any_thread)
+	__count(0x10,	8,	timebase_at_collection)
+	__count(0x18,	8,	purr_cycles)
+	__count(0x20,	8,	sum_of_cycles_across_all_threads)
+	__count(0x28,	8,	instructions_completed)
+)
+#include I(REQUEST_END)
+
+/* Processor_core_power_mode (0x95) skipped, no counters */
+/* Affinity_domain_information_by_virtual_processor (0xA0) skipped,
+ *	no counters */
+/* Affinity_domain_information_by_domain (0xB0) skipped, no counters */
+/* Affinity_domain_information_by_partition (0xB1) skipped, no counters */
+/* Physical_memory_info (0xC0) skipped, no counters */
+/* Processor_bus_topology (0xD0) skipped, no counters */
+
+#define REQUEST_NAME partition_hypervisor_queuing_times
+#define REQUEST_NUM 0xE0
+#define REQUEST_IDX_KIND "partition_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	2, partition_id)
+	__array(0x2,	6, reserved1)
+	__count(0x8,	8, time_waiting_for_entitlement)
+	__count(0x10,	8, times_waited_for_entitlement)
+	__count(0x18,	8, time_waiting_for_phys_processor)
+	__count(0x20,	8, times_waited_for_phys_processor)
+	__count(0x28,	8, dispatches_on_home_core)
+	__count(0x30,	8, dispatches_on_home_primary_affinity_domain)
+	__count(0x38,	8, dispatches_on_home_secondary_affinity_domain)
+	__count(0x40,	8, dispatches_off_home_secondary_affinity_domain)
+	__count(0x48,	8, dispatches_on_dedicated_processor_donating_cycles)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_hypervisor_times
+#define REQUEST_NUM 0xF0
+#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0,	8,	time_spent_to_dispatch_virtual_processors)
+	__count(0x8,	8,	time_spent_processing_virtual_processor_timers)
+	__count(0x10,	8,	time_spent_managing_partitions_over_entitlement)
+	__count(0x18,	8,	time_spent_on_system_management)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_tlbie_count_and_time
+#define REQUEST_NUM 0xF4
+#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0,	8,	tlbie_instructions_issued)
+	/*
+	 * FIXME: The spec says the offset here is 0x10, which I suspect
+	 *	  is wrong.
+	 */
+	__count(0x8,	8,	time_spent_issuing_tlbies)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME partition_instruction_count_and_time
+#define REQUEST_NUM 0x100
+#define REQUEST_IDX_KIND "partition_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0,	2,	partition_id)
+	__array(0x2,	0x6,	reserved1)
+	__count(0x8,	8,	instructions_performed)
+	__count(0x10,	8,	time_collected)
+)
+#include I(REQUEST_END)
+
+/* set_mmcrh (0x80001000) skipped, no counters */
+/* retrieve_hpmcx (0x80002000) skipped, no counters */
+
+#include "req-gen/_end.h"

arch/powerpc/perf/hv-gpci.c

@@ -31,7 +31,18 @@
 /* u32 */
 EVENT_DEFINE_RANGE_FORMAT(request, config, 0, 31);
 /* u32 */
+/*
+ * Note that starting_index, phys_processor_idx, sibling_part_id,
+ * hw_chip_id, partition_id all refer to the same bit range. They
+ * are basically aliases for the starting_index. The specific alias
+ * used depends on the event. See REQUEST_IDX_KIND in hv-gpci-requests.h
+ */
 EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(phys_processor_idx, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(sibling_part_id, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(hw_chip_id, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(partition_id, config, 32, 63);
+
 /* u16 */
 EVENT_DEFINE_RANGE_FORMAT(secondary_index, config1, 0, 15);
 /* u8 */
@@ -44,6 +55,10 @@ EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
 static struct attribute *format_attrs[] = {
 	&format_attr_request.attr,
 	&format_attr_starting_index.attr,
+	&format_attr_phys_processor_idx.attr,
+	&format_attr_sibling_part_id.attr,
+	&format_attr_hw_chip_id.attr,
+	&format_attr_partition_id.attr,
 	&format_attr_secondary_index.attr,
 	&format_attr_counter_info_version.attr,
 
@@ -57,6 +72,11 @@ static struct attribute_group format_group = {
 	.attrs = format_attrs,
 };
 
+static struct attribute_group event_group = {
+	.name  = "events",
+	.attrs = hv_gpci_event_attrs,
+};
+
 #define HV_CAPS_ATTR(_name, _format)				\
 static ssize_t _name##_show(struct device *dev,			\
 			    struct device_attribute *attr,	\
@@ -102,6 +122,7 @@ static struct attribute_group interface_group = {
 
 static const struct attribute_group *attr_groups[] = {
 	&format_group,
+	&event_group,
 	&interface_group,
 	NULL,
 };
@@ -265,6 +286,8 @@ static int hv_gpci_init(void)
 	unsigned long hret;
 	struct hv_perf_caps caps;
 
+	hv_gpci_assert_offsets_correct();
+
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		pr_debug("not a virtualized system, not enabling\n");
 		return -ENODEV;

arch/powerpc/perf/hv-gpci.h

@@ -42,32 +42,19 @@ struct hv_get_perf_counter_info_params {
  */
 #define COUNTER_INFO_VERSION_CURRENT 0x8
 
-/*
- * These determine the counter_value[] layout and the meaning of starting_index
- * and secondary_index.
- *
- * Unless otherwise noted, @secondary_index is unused and ignored.
- */
-enum counter_info_requests {
-
-	/* GENERAL */
-
-	/* @starting_index: must be -1 (to refer to the current partition)
-	 */
-	CIR_SYSTEM_PERFORMANCE_CAPABILITIES = 0X40,
+/* capability mask masks. */
+enum {
+	HV_GPCI_CM_GA = (1 << 7),
+	HV_GPCI_CM_EXPANDED = (1 << 6),
+	HV_GPCI_CM_LAB = (1 << 5)
 };
 
-struct cv_system_performance_capabilities {
-	/* If != 0, allowed to collect data from other partitions */
-	__u8 perf_collect_privileged;
-
-	/* These following are only valid if counter_info_version >= 0x3 */
-#define CV_CM_GA       (1 << 7)
-#define CV_CM_EXPANDED (1 << 6)
-#define CV_CM_LAB      (1 << 5)
-	/* remaining bits are reserved */
-	__u8 capability_mask;
-	__u8 reserved[0xE];
-} __packed;
+#define REQUEST_FILE "../hv-gpci-requests.h"
+#define NAME_LOWER hv_gpci
+#define NAME_UPPER HV_GPCI
+#include "req-gen/perf.h"
+#undef REQUEST_FILE
+#undef NAME_LOWER
+#undef NAME_UPPER
 
 #endif

arch/powerpc/perf/req-gen/_begin.h

@@ -0,0 +1,13 @@
+/* Include paths to be used in interface defining headers */
+#ifndef POWERPC_PERF_REQ_GEN_H_
+#define POWERPC_PERF_REQ_GEN_H_
+
+#define CAT2_STR_(t, s) __stringify(t/s)
+#define CAT2_STR(t, s) CAT2_STR_(t, s)
+#define I(...) __VA_ARGS__
+
+#endif
+
+#define REQ_GEN_PREFIX req-gen
+#define REQUEST_BEGIN CAT2_STR(REQ_GEN_PREFIX, _request-begin.h)
+#define REQUEST_END   CAT2_STR(REQ_GEN_PREFIX, _request-end.h)

arch/powerpc/perf/req-gen/_clear.h

@@ -0,0 +1,5 @@
+
+#undef __field_
+#undef __count_
+#undef __array_
+#undef REQUEST_

arch/powerpc/perf/req-gen/_end.h

@@ -0,0 +1,4 @@
+
+#undef REQ_GEN_PREFIX
+#undef REQUEST_BEGIN
+#undef REQUEST_END

arch/powerpc/perf/req-gen/_request-begin.h

@@ -0,0 +1,15 @@
+
+#define REQUEST(r_contents) \
+	REQUEST_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, I(r_contents))
+
+#define __field(f_offset, f_bytes, f_name) \
+	__field_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+		 f_offset, f_bytes, f_name)
+
+#define __array(f_offset, f_bytes, f_name) \
+	__array_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+		 f_offset, f_bytes, f_name)
+
+#define __count(f_offset, f_bytes, f_name) \
+	__count_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+		 f_offset, f_bytes, f_name)

arch/powerpc/perf/req-gen/_request-end.h

@@ -0,0 +1,8 @@
+#undef REQUEST
+#undef __field
+#undef __array
+#undef __count
+
+#undef REQUEST_NAME
+#undef REQUEST_NUM
+#undef REQUEST_IDX_KIND

arch/powerpc/perf/req-gen/perf.h

@@ -0,0 +1,155 @@
+#ifndef LINUX_POWERPC_PERF_REQ_GEN_PERF_H_
+#define LINUX_POWERPC_PERF_REQ_GEN_PERF_H_
+
+#include <linux/perf_event.h>
+
+#ifndef REQUEST_FILE
+#error "REQUEST_FILE must be defined before including"
+#endif
+
+#ifndef NAME_LOWER
+#error "NAME_LOWER must be defined before including"
+#endif
+
+#ifndef NAME_UPPER
+#error "NAME_UPPER must be defined before including"
+#endif
+
+#define BE_TYPE_b1 __u8
+#define BE_TYPE_b2 __be16
+#define BE_TYPE_b4 __be32
+#define BE_TYPE_b8 __be64
+
+#define BYTES_TO_BE_TYPE(bytes) \
+		BE_TYPE_b##bytes
+
+#define CAT2_(a, b) a ## b
+#define CAT2(a, b) CAT2_(a, b)
+#define CAT3_(a, b, c) a ## b ## c
+#define CAT3(a, b, c) CAT3_(a, b, c)
+
+/*
+ * enumerate the request values as
+ * <NAME_UPPER>_<request name> = <request value>
+ */
+#define REQUEST_VALUE__(name_upper, r_name) name_upper ## _ ## r_name
+#define REQUEST_VALUE_(name_upper, r_name) REQUEST_VALUE__(name_upper, r_name)
+#define REQUEST_VALUE(r_name) REQUEST_VALUE_(NAME_UPPER, r_name)
+
+#include "_clear.h"
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+	REQUEST_VALUE(r_name) = r_value,
+enum CAT2(NAME_LOWER, _requests) {
+#include REQUEST_FILE
+};
+
+/*
+ * For each request:
+ * struct <NAME_LOWER>_<request name> {
+ *	r_fields
+ * };
+ */
+#include "_clear.h"
+#define STRUCT_NAME__(name_lower, r_name) name_lower ## _ ## r_name
+#define STRUCT_NAME_(name_lower, r_name) STRUCT_NAME__(name_lower, r_name)
+#define STRUCT_NAME(r_name) STRUCT_NAME_(NAME_LOWER, r_name)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields)	\
+struct STRUCT_NAME(r_name) {				\
+	r_fields					\
+};
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name) \
+	BYTES_TO_BE_TYPE(f_bytes) f_name;
+#define __count_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name) \
+	__field_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_bytes, a_name) \
+	__u8 a_name[a_bytes];
+
+#include REQUEST_FILE
+
+/*
+ * Generate a check of the field offsets
+ * <NAME_LOWER>_assert_offsets_correct()
+ */
+#include "_clear.h"
+#define REQUEST_(r_name, r_value, index, r_fields)			\
+r_fields
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name) \
+	BUILD_BUG_ON(offsetof(struct STRUCT_NAME(r_name), f_name) != f_offset);
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+	__field_(r_name, r_value, r_idx_1, c_offset, c_size, c_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name) \
+	__field_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+
+static inline void CAT2(NAME_LOWER, _assert_offsets_correct)(void)
+{
+#include REQUEST_FILE
+}
+
+/*
+ * Generate event attributes:
+ * PMU_EVENT_ATTR_STRING(<request name>_<field name>,
+ *	<NAME_LOWER>_event_attr_<request name>_<field name>,
+ *		"request=<request value>"
+ *		"starting_index=<starting index type>"
+ *		"counter_info_version=CURRENT_COUNTER_INFO_VERSION"
+ *		"length=<f_size>"
+ *		"offset=<f_offset>")
+ *
+ *	TODO: counter_info_version may need to vary, we should interperate the
+ *	value to some extent
+ */
+#define EVENT_ATTR_NAME__(name, r_name, c_name) \
+	name ## _event_attr_ ## r_name ## _ ## c_name
+#define EVENT_ATTR_NAME_(name, r_name, c_name) \
+	EVENT_ATTR_NAME__(name, r_name, c_name)
+#define EVENT_ATTR_NAME(r_name, c_name) \
+	EVENT_ATTR_NAME_(NAME_LOWER, r_name, c_name)
+
+#include "_clear.h"
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name)	\
+PMU_EVENT_ATTR_STRING(							\
+		CAT3(r_name, _, c_name),				\
+		EVENT_ATTR_NAME(r_name, c_name),			\
+		"request=" __stringify(r_value) ","			\
+		r_idx_1 ","						\
+		"counter_info_version="					\
+			__stringify(COUNTER_INFO_VERSION_CURRENT) ","	\
+		"length=" #c_size ","					\
+		"offset=" #c_offset)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields)			\
+	r_fields
+
+#include REQUEST_FILE
+
+/*
+ * Define event attribute array
+ * static struct attribute *hv_gpci_event_attrs[] = {
+ *	&<NAME_LOWER>_event_attr_<request name>_<field name>.attr,
+ * };
+ */
+#include "_clear.h"
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name)
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name)	\
+	&EVENT_ATTR_NAME(r_name, c_name).attr.attr,
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields)			\
+	r_fields
+
+static __maybe_unused struct attribute *hv_gpci_event_attrs[] = {
+#include REQUEST_FILE
+	NULL
+};
+
+/* cleanup */
+#include "_clear.h"
+#undef EVENT_ATTR_NAME
+#undef EVENT_ATTR_NAME_
+#undef BIT_NAME
+#undef BIT_NAME_
+#undef STRUCT_NAME
+#undef REQUEST_VALUE
+#undef REQUEST_VALUE_
+
+#endif