powerpc/perf: Add 24x7 interface headers

24x7 (also called hv_24x7 or H_24X7) is an interface to obtain
performance counters from the hypervisor. These counters do not have a
fixed format/possition and are instead documented in a "24x7 Catalog",
which is provided by the hypervisor (that interface is also documented
paritialy in the included hv-24x7-catalog.h and fully in at
https://raw.githubusercontent.com/jmesmon/catalog-24x7/master/hv-24x7-catalog.h ).

The 24x7 data access is simply a copy operation into a 4 dimentional
array of 64bit counters (from hypervisor to kernel memory). There is no
interupt triggered on overflow, these are completely disjoint from the
typical power pmu.

This method of obtaining performance counters from the hypervisor is
intended to paritialy replace the gpci interface.

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

2 files changed, 142 insertions, 0 deletions

diff --git a/arch/powerpc/perf/hv-24x7-catalog.h b/arch/powerpc/perf/hv-24x7-catalog.h
new file mode 100644
index 000000000000..21b19dd86d9c
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7-catalog.h
@@ -0,0 +1,33 @@
+#ifndef LINUX_POWERPC_PERF_HV_24X7_CATALOG_H_
+#define LINUX_POWERPC_PERF_HV_24X7_CATALOG_H_
+
+#include <linux/types.h>
+
+/* From document "24x7 Event and Group Catalog Formats Proposal" v0.15 */
+
+struct hv_24x7_catalog_page_0 {
+#define HV_24X7_CATALOG_MAGIC 0x32347837 /* "24x7" in ASCII */
+	__be32 magic;
+	__be32 length; /* In 4096 byte pages */
+	__be64 version; /* XXX: arbitrary? what's the meaning/useage/purpose? */
+	__u8 build_time_stamp[16]; /* "YYYYMMDDHHMMSS\0\0" */
+	__u8 reserved2[32];
+	__be16 schema_data_offs; /* in 4096 byte pages */
+	__be16 schema_data_len;  /* in 4096 byte pages */
+	__be16 schema_entry_count;
+	__u8 reserved3[2];
+	__be16 event_data_offs;
+	__be16 event_data_len;
+	__be16 event_entry_count;
+	__u8 reserved4[2];
+	__be16 group_data_offs; /* in 4096 byte pages */
+	__be16 group_data_len;  /* in 4096 byte pages */
+	__be16 group_entry_count;
+	__u8 reserved5[2];
+	__be16 formula_data_offs; /* in 4096 byte pages */
+	__be16 formula_data_len;  /* in 4096 byte pages */
+	__be16 formula_entry_count;
+	__u8 reserved6[2];
+} __packed;
+
+#endif
diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h
new file mode 100644
index 000000000000..720ebce4b435
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7.h
@@ -0,0 +1,109 @@
+#ifndef LINUX_POWERPC_PERF_HV_24X7_H_
+#define LINUX_POWERPC_PERF_HV_24X7_H_
+
+#include <linux/types.h>
+
+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];
+
+	/* bytes to read starting at @data_offset. must be a multiple of 8 */
+	__be16 data_size;
+
+	/*
+	 * byte offset within the perf domain to read from. must be 8 byte
+	 * aligned
+	 */
+	__be32 data_offset;
+
+	/*
+	 * only valid for VIRTUAL_PROCESSOR domains, ignored for others.
+	 * -1 means "current partition only"
+	 *  Enabling via phyp/hmc required for non-"-1" values. 0 forbidden
+	 *  unless requestor is 0.
+	 */
+	__be16 starting_lpar_ix;
+
+	/*
+	 * Ignored when @starting_lpar_ix == -1
+	 * Ignored when @performance_domain is not VIRTUAL_PROCESSOR_*
+	 * -1 means "infinite" or all
+	 */
+	__be16 max_num_lpars;
+
+	/* chip, core, or virtual processor based on @performance_domain */
+	__be16 starting_ix;
+	__be16 max_ix;
+} __packed;
+
+struct hv_24x7_request_buffer {
+	/* 0 - ? */
+	/* 1 - ? */
+#define HV_24X7_IF_VERSION_CURRENT 0x01
+	__u8 interface_version;
+	__u8 num_requests;
+	__u8 reserved[0xE];
+	struct hv_24x7_request requests[];
+} __packed;
+
+struct hv_24x7_result_element {
+	__be16 lpar_ix;
+
+	/*
+	 * represents the core, chip, or virtual processor based on the
+	 * request's @performance_domain
+	 */
+	__be16 domain_ix;
+
+	/* -1 if @performance_domain does not refer to a virtual processor */
+	__be32 lpar_cfg_instance_id;
+
+	/* size = @result_element_data_size of cointaining result. */
+	__u8 element_data[];
+} __packed;
+
+struct hv_24x7_result {
+	__u8 result_ix;
+
+	/*
+	 * 0 = not all result elements fit into the buffer, additional requests
+	 *     required
+	 * 1 = all result elements were returned
+	 */
+	__u8 results_complete;
+	__be16 num_elements_returned;
+
+	/* This is a copy of @data_size from the coresponding hv_24x7_request */
+	__be16 result_element_data_size;
+	__u8 reserved[0x2];
+
+	/* WARNING: only valid for first result element due to variable sizes
+	 *          of result elements */
+	/* struct hv_24x7_result_element[@num_elements_returned] */
+	struct hv_24x7_result_element elements[];
+} __packed;
+
+struct hv_24x7_data_result_buffer {
+	/* See versioning for request buffer */
+	__u8 interface_version;
+
+	__u8 num_results;
+	__u8 reserved[0x1];
+	__u8 failing_request_ix;
+	__be32 detailed_rc;
+	__be64 cec_cfg_instance_id;
+	__be64 catalog_version_num;
+	__u8 reserved2[0x8];
+	/* WARNING: only valid for the first result due to variable sizes of
+	 *	    results */
+	struct hv_24x7_result results[]; /* [@num_results] */
+} __packed;
+
+#endif