Google Git Google Git
Sign in
linux/linux/kernel/git/dhowells/linux-fs/refs/heads/rxrpc-fixes-2/./drivers/perf/arm-cmn.c
blob: 5378fba916cf53a20657362d7efa4fc229286c1c [file] [edit]
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2016-2020 Arm Limited
// ARM CMN/CI interconnect PMU driver
#include <linux/acpi.h>
#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <linux/debugfs.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/sort.h>
/* Common register stuff */
#define CMN_NODE_INFO 0x0000
#define CMN_NI_NODE_TYPE GENMASK_ULL(15, 0)
#define CMN_NI_NODE_ID GENMASK_ULL(31, 16)
#define CMN_NI_LOGICAL_ID GENMASK_ULL(47, 32)
#define CMN_CHILD_INFO 0x0080
#define CMN_CI_CHILD_COUNT GENMASK_ULL(15, 0)
#define CMN_CI_CHILD_PTR_OFFSET GENMASK_ULL(31, 16)
#define CMN_CHILD_NODE_ADDR GENMASK(29, 0)
#define CMN_CHILD_NODE_ISOLATED BIT(30)
#define CMN_CHILD_NODE_EXTERNAL BIT(31)
/* Some implementations use a mesh larger than the architectural max of 12 */
#define CMN_MAX_DIMENSION 14
#define CMN_MAX_XPS (CMN_MAX_DIMENSION * CMN_MAX_DIMENSION)
#define CMN_MAX_DTMS (CMN_MAX_XPS + (CMN_MAX_DIMENSION - 1) * 4)
/* Currently XPs are the node type we can have most of; others top out at 128 */
#define CMN_MAX_NODES_PER_EVENT CMN_MAX_XPS
/* The CFG node has various info besides the discovery tree */
#define CMN_CFGM_PERIPH_ID_01 0x0008
#define CMN_CFGM_PID0_PART_0 GENMASK_ULL(7, 0)
#define CMN_CFGM_PID1_PART_1 GENMASK_ULL(35, 32)
#define CMN_CFGM_PERIPH_ID_23 0x0010
#define CMN_CFGM_PID2_REVISION GENMASK_ULL(7, 4)
#define CMN_CFGM_INFO_GLOBAL 0x0900
#define CMN_INFO_MULTIPLE_DTM_EN BIT_ULL(63)
#define CMN_S3_R2_MULTIPLE_DTM_EN BIT_ULL(59)
#define CMN_INFO_RSP_VC_NUM GENMASK_ULL(53, 52)
#define CMN_INFO_DAT_VC_NUM GENMASK_ULL(51, 50)
#define CMN_INFO_DEVICE_ISO_ENABLE BIT_ULL(44)
#define CMN_CFGM_INFO_GLOBAL_1 0x0908
#define CMN_S3_R2_RSP_VC_NUM GENMASK_ULL(11, 9)
#define CMN_S3_R2_DAT_VC_NUM GENMASK_ULL(8, 6)
#define CMN_S3_R2_SNP_VC_NUM GENMASK_ULL(5, 3)
#define CMN_S3_R2_REQ_VC_NUM GENMASK_ULL(2, 0)
#define CMN_INFO_SNP_VC_NUM GENMASK_ULL(3, 2)
#define CMN_INFO_REQ_VC_NUM GENMASK_ULL(1, 0)
/* XPs also have some local topology info which has uses too */
#define CMN_MXP__CONNECT_INFO(p) (0x0008 + 8 * (p))
#define CMN__CONNECT_INFO_DEVICE_TYPE GENMASK_ULL(5, 0)
#define CMN_MAX_PORTS 6
#define CI700_CONNECT_INFO_P2_5_OFFSET 0x10
/* PMU registers occupy the 3rd 4KB page of each node's region */
#define CMN_PMU_OFFSET 0x2000
/* ...except when they don't :( */
#define CMN_S3_R1_DTM_OFFSET 0xa000
#define CMN_S3_PMU_OFFSET 0xd900
/* For most nodes, this is all there is */
#define CMN_PMU_EVENT_SEL 0x000
#define CMN__PMU_CBUSY_SNTHROTTLE_SEL GENMASK_ULL(44, 42)
#define CMN__PMU_SN_HOME_SEL GENMASK_ULL(40, 39)
#define CMN__PMU_HBT_LBT_SEL GENMASK_ULL(38, 37)
#define CMN__PMU_CLASS_OCCUP_ID GENMASK_ULL(36, 35)
/* Technically this is 4 bits wide on DNs, but we only use 2 there anyway */
#define CMN__PMU_OCCUP1_ID GENMASK_ULL(34, 32)
/* But then... */
#define CMN__PMU_EVICT_STATE_SEL GENMASK_ULL(54, 52)
#define CMN__PMU_ENHANCED_HBT_LBT_SEL GENMASK_ULL(51, 48)
#define CMN__PMU_SNP_VC_SEL GENMASK_ULL(47, 46)
#define CMN__S3_R2_CBUSY_SNTHROTTLE_SEL GENMASK_ULL(45, 42)
#define CMN__S3_R2_SN_HOME_SEL GENMASK_ULL(41, 40)
#define CMN__S3_R2_HBT_LBT_SEL GENMASK_ULL(39, 38)
#define CMN__S3_R2_CLASS_OCCUP_ID GENMASK_ULL(37, 36)
#define CMN__S3_R2_OCCUP1_ID GENMASK_ULL(35, 32)
/* Some types are designed to coexist with another device in the same node */
#define CMN_CCLA_PMU_EVENT_SEL 0x008
#define CMN_HNP_PMU_EVENT_SEL 0x008
/* DTMs live in the PMU space of XP registers */
#define CMN_DTM_WPn(n) (0x1A0 + (n) * 0x18)
#define CMN_DTM_WPn_CONFIG(n) (CMN_DTM_WPn(n) + 0x00)
#define CMN_DTM_WPn_CONFIG_WP_CHN_NUM GENMASK_ULL(20, 19)
#define CMN_DTM_WPn_CONFIG_WP_DEV_SEL2 GENMASK_ULL(18, 17)
#define CMN_DTM_WPn_CONFIG_WP_COMBINE BIT(9)
#define CMN_DTM_WPn_CONFIG_WP_EXCLUSIVE BIT(8)
#define CMN600_WPn_CONFIG_WP_COMBINE BIT(6)
#define CMN600_WPn_CONFIG_WP_EXCLUSIVE BIT(5)
#define CMN_DTM_WPn_CONFIG_WP_GRP GENMASK_ULL(5, 4)
#define CMN_DTM_WPn_CONFIG_WP_CHN_SEL GENMASK_ULL(3, 1)
#define CMN_DTM_WPn_CONFIG_WP_DEV_SEL BIT(0)
#define CMN_DTM_WPn_VAL(n) (CMN_DTM_WPn(n) + 0x08)
#define CMN_DTM_WPn_MASK(n) (CMN_DTM_WPn(n) + 0x10)
#define CMN_DTM_PMU_CONFIG 0x210
#define CMN__PMEVCNT0_INPUT_SEL GENMASK_ULL(37, 32)
#define CMN__PMEVCNT0_INPUT_SEL_WP 0x00
#define CMN__PMEVCNT0_INPUT_SEL_XP 0x04
#define CMN__PMEVCNT0_INPUT_SEL_DEV 0x10
#define CMN__PMEVCNT0_GLOBAL_NUM GENMASK_ULL(18, 16)
#define CMN__PMEVCNTn_GLOBAL_NUM_SHIFT(n) ((n) * 4)
#define CMN__PMEVCNT_PAIRED(n) BIT(4 + (n))
#define CMN__PMEVCNT23_COMBINED BIT(2)
#define CMN__PMEVCNT01_COMBINED BIT(1)
#define CMN_DTM_PMU_CONFIG_PMU_EN BIT(0)
#define CMN_DTM_PMEVCNT 0x220
#define CMN_DTM_PMEVCNTSR 0x240
#define CMN650_DTM_UNIT_INFO 0x0910
#define CMN_DTM_UNIT_INFO 0x0960
#define CMN_DTM_UNIT_INFO_DTC_DOMAIN GENMASK_ULL(1, 0)
#define CMN_DTM_NUM_COUNTERS 4
/* Want more local counters? Why not replicate the whole DTM! Ugh... */
#define CMN_DTM_OFFSET(n) ((n) * 0x200)
/* The DTC node is where the magic happens */
#define CMN_DT_DTC_CTL 0x0a00
#define CMN_DT_DTC_CTL_DT_EN BIT(0)
#define CMN_DT_DTC_CTL_CG_DISABLE BIT(10)
/* DTC counters are paired in 64-bit registers on a 16-byte stride. Yuck */
#define _CMN_DT_CNT_REG(n) ((((n) / 2) * 4 + (n) % 2) * 4)
#define CMN_DT_PMEVCNT(dtc, n) ((dtc)->pmu_base + _CMN_DT_CNT_REG(n))
#define CMN_DT_PMCCNTR(dtc) ((dtc)->pmu_base + 0x40)
#define CMN_DT_PMEVCNTSR(dtc, n) ((dtc)->pmu_base + 0x50 + _CMN_DT_CNT_REG(n))
#define CMN_DT_PMCCNTRSR(dtc) ((dtc)->pmu_base + 0x90)
#define CMN_DT_PMCR(dtc) ((dtc)->pmu_base + 0x100)
#define CMN_DT_PMCR_PMU_EN BIT(0)
#define CMN_DT_PMCR_CNTR_RST BIT(5)
#define CMN_DT_PMCR_OVFL_INTR_EN BIT(6)
#define CMN_DT_PMOVSR(dtc) ((dtc)->pmu_base + 0x118)
#define CMN_DT_PMOVSR_CLR(dtc) ((dtc)->pmu_base + 0x120)
#define CMN_DT_PMSSR(dtc) ((dtc)->pmu_base + 0x128)
#define CMN_DT_PMSSR_SS_STATUS(n) BIT(n)
#define CMN_DT_PMSRR(dtc) ((dtc)->pmu_base + 0x130)
#define CMN_DT_PMSRR_SS_REQ BIT(0)
#define CMN_DT_NUM_COUNTERS 8
#define CMN_MAX_DTCS 4
/*
* Even in the worst case a DTC counter can't wrap in fewer than 2^42 cycles,
* so throwing away one bit to make overflow handling easy is no big deal.
*/
#define CMN_COUNTER_INIT 0x80000000
/* Similarly for the 40-bit cycle counter */
#define CMN_CC_INIT 0x8000000000ULL
/* Event attributes */
#define CMN_CONFIG_TYPE GENMASK_ULL(15, 0)
#define CMN_CONFIG_EVENTID GENMASK_ULL(26, 16)
#define CMN_CONFIG_FILTER GENMASK_ULL(30, 27)
#define CMN_CONFIG_BYNODEID BIT_ULL(31)
#define CMN_CONFIG_NODEID GENMASK_ULL(47, 32)
#define CMN_CONFIG_FILTER2 GENMASK_ULL(51, 48)
#define CMN_EVENT_TYPE(event) FIELD_GET(CMN_CONFIG_TYPE, (event)->attr.config)
#define CMN_EVENT_EVENTID(event) FIELD_GET(CMN_CONFIG_EVENTID, (event)->attr.config)
#define CMN_EVENT_FILTER(event) FIELD_GET(CMN_CONFIG_FILTER, (event)->attr.config)
#define CMN_EVENT_BYNODEID(event) FIELD_GET(CMN_CONFIG_BYNODEID, (event)->attr.config)
#define CMN_EVENT_NODEID(event) FIELD_GET(CMN_CONFIG_NODEID, (event)->attr.config)
#define CMN_EVENT_FILTER2(event) FIELD_GET(CMN_CONFIG_FILTER2, (event)->attr.config)
#define CMN_CONFIG_WP_COMBINE GENMASK_ULL(30, 27)
#define CMN_CONFIG_WP_DEV_SEL GENMASK_ULL(50, 48)
#define CMN_CONFIG_WP_CHN_SEL GENMASK_ULL(55, 51)
#define CMN_CONFIG_WP_GRP GENMASK_ULL(57, 56)
#define CMN_CONFIG_WP_EXCLUSIVE BIT_ULL(58)
#define CMN_CONFIG1_WP_VAL GENMASK_ULL(63, 0)
#define CMN_CONFIG2_WP_MASK GENMASK_ULL(63, 0)
#define CMN_EVENT_WP_COMBINE(event) FIELD_GET(CMN_CONFIG_WP_COMBINE, (event)->attr.config)
#define CMN_EVENT_WP_DEV_SEL(event) FIELD_GET(CMN_CONFIG_WP_DEV_SEL, (event)->attr.config)
#define CMN_EVENT_WP_CHN_SEL(event) FIELD_GET(CMN_CONFIG_WP_CHN_SEL, (event)->attr.config)
#define CMN_EVENT_WP_GRP(event) FIELD_GET(CMN_CONFIG_WP_GRP, (event)->attr.config)
#define CMN_EVENT_WP_EXCLUSIVE(event) FIELD_GET(CMN_CONFIG_WP_EXCLUSIVE, (event)->attr.config)
#define CMN_EVENT_WP_VAL(event) FIELD_GET(CMN_CONFIG1_WP_VAL, (event)->attr.config1)
#define CMN_EVENT_WP_MASK(event) FIELD_GET(CMN_CONFIG2_WP_MASK, (event)->attr.config2)
/* Made-up event IDs for watchpoint direction */
#define CMN_WP_UP 0
#define CMN_WP_DOWN 2
/* Internal values for encoding event support */
enum cmn_model {
CMN600 = 1,
CMN650 = 2,
CI700 = 4,
CMN700 = 8,
CMNS3R01 = 16,
CMNS3R2 = 32,
/* ...and then we can use bitmap tricks for commonality */
CMN_ANY = -1,
NOT_CMN600 = -2,
CMN_700ON = ~(CMN700 - 1),
CMN_650ON = CMN_700ON | CMN650,
CMNS3 = CMNS3R01 | CMNS3R2,
};
/* Actual part numbers and revision IDs defined by the hardware */
enum cmn_part {
PART_CMN600 = 0x434,
PART_CMN650 = 0x436,
PART_CMN600AE = 0x438,
PART_CMN700 = 0x43c,
PART_CI700 = 0x43a,
PART_CMN_S3 = 0x43e,
/* Synthetic part number, overridden to PART_CMN_S3 during discovery */
PART_GRAVITON5 = 0xa5,
};
/* CMN-600 r0px shouldn't exist in silicon, thankfully */
enum cmn_revision {
REV_CMN600_R1P0,
REV_CMN600_R1P1,
REV_CMN600_R1P2,
REV_CMN600_R1P3,
REV_CMN600_R2P0,
REV_CMN600_R3P0,
REV_CMN600_R3P1,
REV_CMN650_R0P0 = 0,
REV_CMN650_R1P0,
REV_CMN650_R1P1,
REV_CMN650_R2P0,
REV_CMN650_R1P2,
REV_CMN700_R0P0 = 0,
REV_CMN700_R1P0,
REV_CMN700_R2P0,
REV_CMN700_R3P0,
REV_CMNS3_R0P0 = 0,
REV_CMNS3_R0P1,
REV_CMNS3_R1P0,
REV_CMNS3_R2P0,
REV_CMNS3_R2P1,
REV_CMNS3_R2P2,
REV_CMNS3_R2P5,
REV_CI700_R0P0 = 0,
REV_CI700_R1P0,
REV_CI700_R2P0,
};
enum cmn_node_type {
CMN_TYPE_INVALID,
CMN_TYPE_DVM,
CMN_TYPE_CFG,
CMN_TYPE_DTC,
CMN_TYPE_HNI,
CMN_TYPE_HNF,
CMN_TYPE_XP,
CMN_TYPE_SBSX,
CMN_TYPE_MPAM_S,
CMN_TYPE_MPAM_NS,
CMN_TYPE_RNI,
CMN_TYPE_RND = 0xd,
CMN_TYPE_RNSAM = 0xf,
CMN_TYPE_MTSX,
CMN_TYPE_HNP,
CMN_TYPE_CXRA = 0x100,
CMN_TYPE_CXHA,
CMN_TYPE_CXLA,
CMN_TYPE_CCRA,
CMN_TYPE_CCHA,
CMN_TYPE_CCLA,
CMN_TYPE_CCLA_RNI,
CMN_TYPE_HNS = 0x200,
CMN_TYPE_HNS_MPAM_S,
CMN_TYPE_HNS_MPAM_NS,
CMN_TYPE_APB = 0x1000,
/* Not a real node type */
CMN_TYPE_WP = 0x7770
};
enum cmn_filter_select {
SEL_NONE,
SEL_OCCUP1_ID,
SEL_CLASS_OCCUP_ID,
SEL_HBT_LBT_SEL,
SEL_SN_HOME_SEL,
SEL_CBUSY_SNTHROTTLE_SEL,
SEL_SNP_VC_SEL,
SEL_ENHANCED_HBT_LBT_SEL,
SEL_EVICT_STATE_SEL,
SEL_MAX
};
struct arm_cmn_node {
void __iomem *pmu_base;
u16 id, logid;
enum cmn_node_type type;
/* XP properties really, but replicated to children for convenience */
u8 dtm;
s8 dtc;
u8 portid_bits:4;
u8 deviceid_bits:4;
/* DN/HN-F/CXHA */
struct {
u8 val : 4;
u8 count : 4;
} filter[SEL_MAX];
union {
u8 event[4];
__le32 event_sel;
u16 event_w[4];
__le64 event_sel_w;
};
};
struct arm_cmn_dtm {
void __iomem *base;
u32 pmu_config_low;
union {
u8 input_sel[4];
__le32 pmu_config_high;
};
s8 wp_event[4];
};
struct arm_cmn_dtc {
void __iomem *base;
void __iomem *pmu_base;
int irq;
s8 irq_friend;
bool cc_active;
struct perf_event *counters[CMN_DT_NUM_COUNTERS];
struct perf_event *cycles;
};
#define CMN_STATE_DISABLED BIT(0)
#define CMN_STATE_TXN BIT(1)
struct arm_cmn {
struct device *dev;
void __iomem *base;
unsigned int state;
enum cmn_revision rev;
enum cmn_part part;
u8 mesh_x;
u8 mesh_y;
u16 num_xps;
u16 num_dns;
bool multi_dtm;
u8 ports_used;
struct {
unsigned int rsp_vc_num : 2;
unsigned int dat_vc_num : 2;
unsigned int snp_vc_num : 2;
unsigned int req_vc_num : 2;
};
struct arm_cmn_node *xps;
struct arm_cmn_node *dns;
struct arm_cmn_dtm *dtms;
struct arm_cmn_dtc *dtc;
unsigned int num_dtcs;
int cpu;
struct hlist_node cpuhp_node;
struct pmu pmu;
struct dentry *debug;
};
#define to_cmn(p) container_of(p, struct arm_cmn, pmu)
static int arm_cmn_hp_state;
struct arm_cmn_nodeid {
u8 port;
u8 dev;
};
static int arm_cmn_xyidbits(const struct arm_cmn *cmn)
{
return fls((cmn->mesh_x - 1) | (cmn->mesh_y - 1));
}
static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn_node *dn)
{
struct arm_cmn_nodeid nid;
nid.dev = dn->id & ((1U << dn->deviceid_bits) - 1);
nid.port = (dn->id >> dn->deviceid_bits) & ((1U << dn->portid_bits) - 1);
return nid;
}
static struct arm_cmn_node *arm_cmn_node_to_xp(const struct arm_cmn *cmn,
const struct arm_cmn_node *dn)
{
int id = dn->id >> (dn->portid_bits + dn->deviceid_bits);
int bits = arm_cmn_xyidbits(cmn);
int x = id >> bits;
int y = id & ((1U << bits) - 1);
return cmn->xps + cmn->mesh_x * y + x;
}
static struct arm_cmn_node *arm_cmn_node(const struct arm_cmn *cmn,
enum cmn_node_type type)
{
struct arm_cmn_node *dn;
for (dn = cmn->dns; dn->type; dn++)
if (dn->type == type)
return dn;
return NULL;
}
static enum cmn_model arm_cmn_model(const struct arm_cmn *cmn)
{
switch (cmn->part) {
case PART_CMN600:
return CMN600;
case PART_CMN650:
return CMN650;
case PART_CMN700:
return CMN700;
case PART_CI700:
return CI700;
case PART_CMN_S3:
if (cmn->rev >= REV_CMNS3_R2P0)
return CMNS3R2;
return CMNS3R01;
default:
return 0;
};
}
static int arm_cmn_pmu_offset(const struct arm_cmn *cmn, const struct arm_cmn_node *dn)
{
if (cmn->part == PART_CMN_S3) {
if (cmn->rev >= REV_CMNS3_R1P0 && dn->type == CMN_TYPE_XP)
return CMN_S3_R1_DTM_OFFSET;
return CMN_S3_PMU_OFFSET;
}
return CMN_PMU_OFFSET;
}
static u32 arm_cmn_device_connect_info(const struct arm_cmn *cmn,
const struct arm_cmn_node *xp, int port)
{
int offset = CMN_MXP__CONNECT_INFO(port) - arm_cmn_pmu_offset(cmn, xp);
if (port >= 2) {
if (cmn->part == PART_CMN600 || cmn->part == PART_CMN650)
return 0;
/*
* CI-700 may have extra ports, but still has the
* mesh_port_connect_info registers in the way.
*/
if (cmn->part == PART_CI700)
offset += CI700_CONNECT_INFO_P2_5_OFFSET;
}
return readl_relaxed(xp->pmu_base + offset);
}
static struct dentry *arm_cmn_debugfs;
#ifdef CONFIG_DEBUG_FS
static const char *arm_cmn_device_type(u8 type)
{
switch(FIELD_GET(CMN__CONNECT_INFO_DEVICE_TYPE, type)) {
case 0x00: return " |";
case 0x01: return " RN-I |";
case 0x02: return " RN-D |";
case 0x04: return " RN-F_B |";
case 0x05: return "RN-F_B_E|";
case 0x06: return " RN-F_A |";
case 0x07: return "RN-F_A_E|";
case 0x08: return " HN-T |";
case 0x09: return " HN-I |";
case 0x0a: return " HN-D |";
case 0x0b: return " HN-P |";
case 0x0c: return " SN-F |";
case 0x0d: return " SBSX |";
case 0x0e: return " HN-F |";
case 0x0f: return " SN-F_E |";
case 0x10: return " SN-F_D |";
case 0x11: return " CXHA |";
case 0x12: return " CXRA |";
case 0x13: return " CXRH |";
case 0x14: return " RN-F_D |";
case 0x15: return "RN-F_D_E|";
case 0x16: return " RN-F_C |";
case 0x17: return "RN-F_C_E|";
case 0x18: return " RN-F_E |";
case 0x19: return "RN-F_E_E|";
case 0x1a: return " HN-S |";
case 0x1b: return " LCN |";
case 0x1c: return " MTSX |";
case 0x1d: return " HN-V |";
case 0x1e: return " CCG |";
case 0x20: return " RN-F_F |";
case 0x21: return "RN-F_F_E|";
case 0x22: return " SN-F_F |";
default: return " ???? |";
}
}
static void arm_cmn_show_logid(struct seq_file *s, const struct arm_cmn_node *xp, int p, int d)
{
struct arm_cmn *cmn = s->private;
struct arm_cmn_node *dn;
u16 id = xp->id | d | (p << xp->deviceid_bits);
for (dn = cmn->dns; dn->type; dn++) {
int pad = dn->logid < 10;
if (dn->type == CMN_TYPE_XP)
continue;
/* Ignore the extra components that will overlap on some ports */
if (dn->type < CMN_TYPE_HNI)
continue;
if (dn->id != id)
continue;
seq_printf(s, " %*c#%-*d |", pad + 1, ' ', 3 - pad, dn->logid);
return;
}
seq_puts(s, " |");
}
static int arm_cmn_map_show(struct seq_file *s, void *data)
{
struct arm_cmn *cmn = s->private;
int x, y, p, pmax = fls(cmn->ports_used);
seq_puts(s, " X");
for (x = 0; x < cmn->mesh_x; x++)
seq_printf(s, " %-2d ", x);
seq_puts(s, "\nY P D+");
y = cmn->mesh_y;
while (y--) {
int xp_base = cmn->mesh_x * y;
struct arm_cmn_node *xp = cmn->xps + xp_base;
u8 port[CMN_MAX_PORTS][CMN_MAX_DIMENSION];
for (x = 0; x < cmn->mesh_x; x++)
seq_puts(s, "--------+");
seq_printf(s, "\n%-2d |", y);
for (x = 0; x < cmn->mesh_x; x++) {
for (p = 0; p < CMN_MAX_PORTS; p++)
port[p][x] = arm_cmn_device_connect_info(cmn, xp + x, p);
seq_printf(s, " XP #%-3d|", xp_base + x);
}
seq_puts(s, "\n |");
for (x = 0; x < cmn->mesh_x; x++) {
s8 dtc = xp[x].dtc;
if (dtc < 0)
seq_puts(s, " DTC ?? |");
else
seq_printf(s, " DTC %d |", dtc);
}
seq_puts(s, "\n |");
for (x = 0; x < cmn->mesh_x; x++)
seq_puts(s, "........|");
for (p = 0; p < pmax; p++) {
seq_printf(s, "\n %d |", p);
for (x = 0; x < cmn->mesh_x; x++)
seq_puts(s, arm_cmn_device_type(port[p][x]));
seq_puts(s, "\n 0|");
for (x = 0; x < cmn->mesh_x; x++)
arm_cmn_show_logid(s, xp + x, p, 0);
seq_puts(s, "\n 1|");
for (x = 0; x < cmn->mesh_x; x++)
arm_cmn_show_logid(s, xp + x, p, 1);
}
seq_puts(s, "\n-----+");
}
for (x = 0; x < cmn->mesh_x; x++)
seq_puts(s, "--------+");
seq_puts(s, "\n");
return 0;
}
DEFINE_SHOW_ATTRIBUTE(arm_cmn_map);
static void arm_cmn_debugfs_init(struct arm_cmn *cmn, int id)
{
const char *name = "map";
if (id > 0)
name = devm_kasprintf(cmn->dev, GFP_KERNEL, "map_%d", id);
if (!name)
return;
cmn->debug = debugfs_create_file(name, 0444, arm_cmn_debugfs, cmn, &arm_cmn_map_fops);
}
#else
static void arm_cmn_debugfs_init(struct arm_cmn *cmn, int id) {}
#endif
enum cmn_filter_type {
FILT_NONE,
FILT_OCCUP1_ID,
FILT_HNF_700,
FILT_HNS,
FILT_HNS_S3R2,
};
#define CMN_FILTER(_sel) [SEL_##_sel] = CMN__PMU_##_sel
#define CMN_FILTER_V2(_sel) [SEL_##_sel] = CMN__S3_R2_##_sel
static const u64 arm_cmn_filters[][SEL_MAX] = {
[FILT_NONE] = {},
/* DVM etc. */
[FILT_OCCUP1_ID] = {
CMN_FILTER(OCCUP1_ID)
},
/* Newer HN-F */
[FILT_HNF_700] = {
CMN_FILTER(OCCUP1_ID),
CMN_FILTER(CLASS_OCCUP_ID),
CMN_FILTER(CBUSY_SNTHROTTLE_SEL)
},
/* HN-S */
[FILT_HNS] = {
CMN_FILTER(OCCUP1_ID),
CMN_FILTER(CLASS_OCCUP_ID),
CMN_FILTER(CBUSY_SNTHROTTLE_SEL),
CMN_FILTER(HBT_LBT_SEL),
CMN_FILTER(SN_HOME_SEL)
},
/* Newer HN-S */
[FILT_HNS_S3R2] = {
CMN_FILTER_V2(OCCUP1_ID),
CMN_FILTER_V2(CLASS_OCCUP_ID),
CMN_FILTER_V2(CBUSY_SNTHROTTLE_SEL),
CMN_FILTER_V2(HBT_LBT_SEL),
CMN_FILTER_V2(SN_HOME_SEL),
CMN_FILTER(SNP_VC_SEL),
CMN_FILTER(ENHANCED_HBT_LBT_SEL),
CMN_FILTER(EVICT_STATE_SEL)
}
};
static enum cmn_filter_type arm_cmn_filter(enum cmn_node_type node,
enum cmn_model model)
{
switch (node) {
default:
return FILT_NONE;
case CMN_TYPE_DVM:
case CMN_TYPE_CXRA:
case CMN_TYPE_CXHA:
case CMN_TYPE_CCRA:
case CMN_TYPE_CCHA:
return FILT_OCCUP1_ID;
case CMN_TYPE_HNF:
if (model < CMN700)
return FILT_OCCUP1_ID;
return FILT_HNF_700;
case CMN_TYPE_HNS:
if (model < CMNS3R2)
return FILT_HNS;
return FILT_HNS_S3R2;
};
}
struct arm_cmn_hw_event {
struct arm_cmn_node *dn;
union {
unsigned long *dtm_idx;
int cc_idx;
};
unsigned long *wp_idx;
s8 dtc_idx[CMN_MAX_DTCS];
u8 num_dns;
u8 dtm_offset;
bool wide_sel;
enum cmn_filter_select filter_sel;
};
static_assert(sizeof(struct arm_cmn_hw_event) <= offsetof(struct hw_perf_event, target));
#define for_each_hw_dn(hw, dn, i) \
for (i = 0, dn = hw->dn; i < hw->num_dns; i++, dn++)
/* @i is the DTC number, @idx is the counter index on that DTC */
#define for_each_hw_dtc_idx(hw, i, idx) \
for (int i = 0, idx; i < CMN_MAX_DTCS; i++) if ((idx = hw->dtc_idx[i]) >= 0)
static struct arm_cmn_hw_event *to_cmn_hw(struct perf_event *event)
{
return (struct arm_cmn_hw_event *)&event->hw;
}
#define BPL2 (BITS_PER_LONG / 2)
static void arm_cmn_set_dtm_idx(struct arm_cmn_hw_event *hw, unsigned int pos, unsigned int val)
{
hw->dtm_idx[pos / BPL2] |= (unsigned long)val << ((pos % BPL2) * 2);
}
static unsigned int arm_cmn_get_dtm_idx(struct arm_cmn_hw_event *hw, unsigned int pos)
{
return (hw->dtm_idx[pos / BPL2] >> ((pos % BPL2) * 2)) & 3;
}
static unsigned long *arm_cmn_alloc_dtm_idx(void)
{
return bitmap_zalloc(CMN_MAX_NODES_PER_EVENT * 2, GFP_KERNEL);
}
static void arm_cmn_set_wp_idx(struct arm_cmn_hw_event *hw, unsigned int pos, bool val)
{
if (val)
set_bit(pos, hw->wp_idx);
}
static unsigned int arm_cmn_get_wp_idx(struct arm_cmn_hw_event *hw, unsigned int pos)
{
return test_bit(pos, hw->wp_idx);
}
static unsigned long *arm_cmn_alloc_wp_idx(void)
{
return bitmap_zalloc(CMN_MAX_XPS, GFP_KERNEL);
}
static void arm_cmn_clear_idx(struct arm_cmn_hw_event *hw)
{
bitmap_zero(hw->dtm_idx, CMN_MAX_NODES_PER_EVENT * 2);
if (hw->wp_idx)
bitmap_zero(hw->wp_idx, CMN_MAX_XPS);
}
struct arm_cmn_filter_attr {
enum cmn_filter_select sel;
u8 val;
};
struct arm_cmn_event_attr {
struct device_attribute attr;
enum cmn_model model;
enum cmn_node_type type;
u16 eventid;
struct arm_cmn_filter_attr filter[2];
};
struct arm_cmn_format_attr {
struct device_attribute attr;
u64 field;
int config;
};
#define _CMN_EVENT_ATTR(_model, _name, _type, _eventid, _fa, _fb, _fc, _fd, ...) \
(&((struct arm_cmn_event_attr[]) {{ \
.attr = __ATTR(_name, 0444, arm_cmn_event_show, NULL), \
.model = _model, \
.type = _type, \
.eventid = _eventid, \
.filter = {{_fa, _fb}, {_fc, _fd}}, \
}})[0].attr.attr)
#define CMN_EVENT_ATTR(_model, _name, _type, _eventid, _filter...) \
_CMN_EVENT_ATTR(_model, _name, _type, _eventid, ##_filter, 0, 0, 0, 0)
static ssize_t arm_cmn_event_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct arm_cmn_event_attr *eattr;
struct arm_cmn_filter_attr *filter;
eattr = container_of(attr, typeof(*eattr), attr);
filter = eattr->filter;
if (eattr->type == CMN_TYPE_DTC)
return sysfs_emit(buf, "type=0x%x\n", eattr->type);
if (eattr->type == CMN_TYPE_WP)
return sysfs_emit(buf,
"type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n",
eattr->type, eattr->eventid);
if (filter[1].sel)
return sysfs_emit(buf, "type=0x%x,eventid=0x%x,filter=0x%x,filter2=0x%x\n",
eattr->type, eattr->eventid, filter[0].val, filter[1].val);
if (filter[0].sel)
return sysfs_emit(buf, "type=0x%x,eventid=0x%x,filter=0x%x\n",
eattr->type, eattr->eventid, filter[0].val);
return sysfs_emit(buf, "type=0x%x,eventid=0x%x\n", eattr->type,
eattr->eventid);
}
static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
struct attribute *attr,
int unused)
{
struct device *dev = kobj_to_dev(kobj);
struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev));
struct arm_cmn_event_attr *eattr;
enum cmn_node_type type;
u16 eventid;
eattr = container_of(attr, typeof(*eattr), attr.attr);
if (!(eattr->model & arm_cmn_model(cmn)))
return 0;
type = eattr->type;
eventid = eattr->eventid;
/* Watchpoints aren't nodes, so avoid confusion */
if (type == CMN_TYPE_WP)
return attr->mode;
/* Hide XP events for unused interfaces/channels */
if (type == CMN_TYPE_XP) {
unsigned int intf = (eventid >> 2) & 7;
unsigned int chan = eventid >> 5;
if ((intf & 4) && !(cmn->ports_used & BIT(intf & 3)))
return 0;
if (chan == 4 && cmn->part == PART_CMN600)
return 0;
if ((chan == 5 && cmn->rsp_vc_num < 2) ||
(chan == 6 && cmn->dat_vc_num < 2) ||
(chan == 7 && cmn->req_vc_num < 2) ||
(chan == 8 && cmn->snp_vc_num < 2))
return 0;
}
/* Revision-specific differences */
if (cmn->part == PART_CMN600) {
if (cmn->rev < REV_CMN600_R1P3) {
if (type == CMN_TYPE_CXRA && eventid > 0x10)
return 0;
}
if (cmn->rev < REV_CMN600_R1P2) {
if (type == CMN_TYPE_HNF && eventid == 0x1b)
return 0;
if (type == CMN_TYPE_CXRA || type == CMN_TYPE_CXHA)
return 0;
}
} else if (cmn->part == PART_CMN650) {
if (cmn->rev < REV_CMN650_R2P0 || cmn->rev == REV_CMN650_R1P2) {
if (type == CMN_TYPE_HNF && eventid > 0x22)
return 0;
if (type == CMN_TYPE_SBSX && eventid == 0x17)
return 0;
if (type == CMN_TYPE_RNI && eventid > 0x10)
return 0;
}
} else if (cmn->part == PART_CMN700) {
if (cmn->rev < REV_CMN700_R2P0) {
if (type == CMN_TYPE_HNF && eventid > 0x2c)
return 0;
if (type == CMN_TYPE_CCHA && eventid > 0x74)
return 0;
if (type == CMN_TYPE_CCLA && eventid > 0x27)
return 0;
}
if (cmn->rev < REV_CMN700_R1P0) {
if (type == CMN_TYPE_HNF && eventid > 0x2b)
return 0;
}
}
if (!arm_cmn_node(cmn, type))
return 0;
return attr->mode;
}
#define CMN_EVENT_DVM(_model, _name, _event, _filter...) \
CMN_EVENT_ATTR(_model, dn_##_name, CMN_TYPE_DVM, _event, ##_filter)
#define CMN_EVENT_DTC(_name) \
CMN_EVENT_ATTR(CMN_ANY, dtc_##_name, CMN_TYPE_DTC, 0)
#define CMN_EVENT_HNF(_model, _name, _event) \
CMN_EVENT_ATTR(_model, hnf_##_name, CMN_TYPE_HNF, _event)
#define CMN_EVENT_HNI(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, hni_##_name, CMN_TYPE_HNI, _event)
#define CMN_EVENT_HNP(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, hnp_##_name, CMN_TYPE_HNP, _event)
#define __CMN_EVENT_XP(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, mxp_##_name, CMN_TYPE_XP, _event)
#define CMN_EVENT_SBSX(_model, _name, _event) \
CMN_EVENT_ATTR(_model, sbsx_##_name, CMN_TYPE_SBSX, _event)
#define CMN_EVENT_RNID(_model, _name, _event) \
CMN_EVENT_ATTR(_model, rnid_##_name, CMN_TYPE_RNI, _event)
#define CMN_EVENT_MTSX(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, mtsx_##_name, CMN_TYPE_MTSX, _event)
#define CMN_EVENT_CXRA(_model, _name, _event) \
CMN_EVENT_ATTR(_model, cxra_##_name, CMN_TYPE_CXRA, _event)
#define CMN_EVENT_CXHA(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, cxha_##_name, CMN_TYPE_CXHA, _event)
#define CMN_EVENT_CCRA(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, ccra_##_name, CMN_TYPE_CCRA, _event)
#define CMN_EVENT_CCHA(_model, _name, _event) \
CMN_EVENT_ATTR(_model, ccha_##_name, CMN_TYPE_CCHA, _event)
#define CMN_EVENT_CCLA(_name, _event) \
CMN_EVENT_ATTR(CMN_ANY, ccla_##_name, CMN_TYPE_CCLA, _event)
#define _CMN_EVENT_HNS(_model, _name, _event, _filter...) \
CMN_EVENT_ATTR(_model, hns_##_name, CMN_TYPE_HNS, _event, ##_filter)
#define CMN_EVENT_DVM_OCC(_model, _name, _event) \
CMN_EVENT_DVM(_model, _name##_all, _event, SEL_OCCUP1_ID, 0), \
CMN_EVENT_DVM(_model, _name##_dvmop, _event, SEL_OCCUP1_ID, 1), \
CMN_EVENT_DVM(_model, _name##_dvmsync, _event, SEL_OCCUP1_ID, 2)
#define CMN_EVENT_HN_OCC(_model, _name, _type, _event) \
CMN_EVENT_ATTR(_model, _name##_all, _type, _event, SEL_OCCUP1_ID, 0), \
CMN_EVENT_ATTR(_model, _name##_read, _type, _event, SEL_OCCUP1_ID, 1), \
CMN_EVENT_ATTR(_model, _name##_write, _type, _event, SEL_OCCUP1_ID, 2), \
CMN_EVENT_ATTR(_model, _name##_atomic, _type, _event, SEL_OCCUP1_ID, 3), \
CMN_EVENT_ATTR(_model, _name##_stash, _type, _event, SEL_OCCUP1_ID, 4)
#define CMN_EVENT_HN_CLS(_model, _name, _type, _event) \
CMN_EVENT_ATTR(_model, _name##_class0, _type, _event, SEL_CLASS_OCCUP_ID, 0), \
CMN_EVENT_ATTR(_model, _name##_class1, _type, _event, SEL_CLASS_OCCUP_ID, 1), \
CMN_EVENT_ATTR(_model, _name##_class2, _type, _event, SEL_CLASS_OCCUP_ID, 2), \
CMN_EVENT_ATTR(_model, _name##_class3, _type, _event, SEL_CLASS_OCCUP_ID, 3)
#define CMN_EVENT_HN_SNT(_model, _name, _type, _event) \
CMN_EVENT_ATTR(_model, _name##_all, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 0), \
CMN_EVENT_ATTR(_model, _name##_group0_read, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 1), \
CMN_EVENT_ATTR(_model, _name##_group0_write, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 2), \
CMN_EVENT_ATTR(_model, _name##_group1_read, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 3), \
CMN_EVENT_ATTR(_model, _name##_group1_write, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 4), \
CMN_EVENT_ATTR(_model, _name##_read, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 5), \
CMN_EVENT_ATTR(_model, _name##_write, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 6), \
CMN_EVENT_ATTR(CMNS3R2, _name##_ccg_read, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 9), \
CMN_EVENT_ATTR(CMNS3R2, _name##_ccg_write, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 10), \
CMN_EVENT_ATTR(CMNS3R2, _name##_lbt_read, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 11), \
CMN_EVENT_ATTR(CMNS3R2, _name##_lbt_write, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 12), \
CMN_EVENT_ATTR(CMNS3R2, _name##_lbt, _type, _event, SEL_CBUSY_SNTHROTTLE_SEL, 13)
#define CMN_EVENT_HNF_OCC(_model, _name, _event) \
CMN_EVENT_HN_OCC(_model, hnf_##_name, CMN_TYPE_HNF, _event)
#define CMN_EVENT_HNF_CLS(_model, _name, _event) \
CMN_EVENT_HN_CLS(_model, hnf_##_name, CMN_TYPE_HNF, _event)
#define CMN_EVENT_HNF_SNT(_model, _name, _event) \
CMN_EVENT_HN_SNT(_model, hnf_##_name, CMN_TYPE_HNF, _event)
#define CMN_EVENT_HNS(_name, _event) \
_CMN_EVENT_HNS(CMN_ANY, _name, _event)
#define CMN_EVENT_HNSR0(_name, _event) \
_CMN_EVENT_HNS(CMN700 | CMNS3R01, _name, _event)
#define _CMN_EVENT_HNS_HBT(_model, _name, _event, _sel) \
_CMN_EVENT_HNS(_model, _name##_all, _event, _sel, 0), \
_CMN_EVENT_HNS(_model, _name##_hbt, _event, _sel, 1), \
_CMN_EVENT_HNS(_model, _name##_lbt, _event, _sel, 2)
#define _CMN_EVENT_HNS_EVICT(_model, _name, _event, _fsel1, f1) \
_CMN_EVENT_HNS(_model, _name##_all, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 0), \
_CMN_EVENT_HNS(_model, _name##_eu, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 1), \
_CMN_EVENT_HNS(_model, _name##_en, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 2), \
_CMN_EVENT_HNS(_model, _name##_su, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 3), \
_CMN_EVENT_HNS(_model, _name##_sn, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 4), \
_CMN_EVENT_HNS(_model, _name##_mu, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 5), \
_CMN_EVENT_HNS(_model, _name##_mn, _event, _fsel1, f1, SEL_EVICT_STATE_SEL, 6)
#define CMN_EVENT_HNS_OCC(_model, _name, _event) \
CMN_EVENT_HN_OCC(_model, hns_##_name, CMN_TYPE_HNS, _event), \
_CMN_EVENT_HNS(_model, _name##_rxsnp, _event, SEL_OCCUP1_ID, 5), \
_CMN_EVENT_HNS(_model, _name##_lbt, _event, SEL_OCCUP1_ID, 6), \
_CMN_EVENT_HNS(_model, _name##_hbt, _event, SEL_OCCUP1_ID, 7), \
_CMN_EVENT_HNS(CMNS3R2, _name##_rnf, _event, SEL_OCCUP1_ID, 8), \
_CMN_EVENT_HNS(CMNS3R2, _name##_rni, _event, SEL_OCCUP1_ID, 9), \
_CMN_EVENT_HNS(CMNS3R2, _name##_ccglcn, _event, SEL_OCCUP1_ID, 10), \
_CMN_EVENT_HNS(CMNS3R2, _name##_ccgrn, _event, SEL_OCCUP1_ID, 11)
#define CMN_EVENT_HNS_CLS( _name, _event) \
CMN_EVENT_HN_CLS(CMN_ANY, hns_##_name, CMN_TYPE_HNS, _event)
#define CMN_EVENT_HNSR0_CLS( _name, _event) \
CMN_EVENT_HN_CLS(CMN700 | CMNS3R01, hns_##_name, CMN_TYPE_HNS, _event)
#define CMN_EVENT_HNS_SNT(_model, _name, _event) \
CMN_EVENT_HN_SNT(_model, hns_##_name, CMN_TYPE_HNS, _event)
#define CMN_EVENT_HNS_SNH(_model, _name, _event) \
_CMN_EVENT_HNS(_model, _name##_all, _event, SEL_SN_HOME_SEL, 0), \
_CMN_EVENT_HNS(_model, _name##_sn, _event, SEL_SN_HOME_SEL, 1), \
_CMN_EVENT_HNS(_model, _name##_home, _event, SEL_SN_HOME_SEL, 2)
#define CMN_EVENT_HNS_VC(_name, _event) \
CMN_EVENT_HNSR0(_name, _event), \
_CMN_EVENT_HNS(CMNS3R2, _name##_vc0, _event, SEL_SNP_VC_SEL, 0), \
_CMN_EVENT_HNS(CMNS3R2, _name##_vc1, _event, SEL_SNP_VC_SEL, 1), \
_CMN_EVENT_HNS(CMNS3R2, _name##_vc2, _event, SEL_SNP_VC_SEL, 2)
#define CMN_EVENT_HNS_ENHBT(_name, _event) \
_CMN_EVENT_HNS_HBT(CMNS3R2, _name, _event, SEL_ENHANCED_HBT_LBT_SEL), \
_CMN_EVENT_HNS(CMNS3R2, _name##_rnf, _event, SEL_ENHANCED_HBT_LBT_SEL, 3), \
_CMN_EVENT_HNS(CMNS3R2, _name##_rni, _event, SEL_ENHANCED_HBT_LBT_SEL, 4), \
_CMN_EVENT_HNS(CMNS3R2, _name##_ccglcn, _event, SEL_ENHANCED_HBT_LBT_SEL, 5), \
_CMN_EVENT_HNS(CMNS3R2, _name##_ccgrn, _event, SEL_ENHANCED_HBT_LBT_SEL, 6)
#define CMN_EVENT_HNS_EVICT(_model, _name, _event) \
_CMN_EVENT_HNS_EVICT(_model, _name##_all, _event, SEL_HBT_LBT_SEL, 0), \
_CMN_EVENT_HNS_EVICT(_model, _name##_hbt, _event, SEL_HBT_LBT_SEL, 1), \
_CMN_EVENT_HNS_EVICT(_model, _name##_lbt, _event, SEL_HBT_LBT_SEL, 2)
#define CMN_EVENT_HNSR0_HBT(_name, _event) \
_CMN_EVENT_HNS_HBT(CMN700 | CMNS3R01, _name, _event, SEL_HBT_LBT_SEL)
#define CMN_EVENT_HNS_R2SNH(_name, _event) \
CMN_EVENT_HNSR0(_name, _event), \
CMN_EVENT_HNS_SNH(CMNS3R2, _name, _event)
#define CMN_EVENT_HNS_R2HBT(_name, _event) \
CMN_EVENT_HNSR0(_name, _event), \
_CMN_EVENT_HNS_HBT(CMNS3R2, _name, _event, SEL_HBT_LBT_SEL)
#define CMN_EVENT_HNS_HBT_ENHBT(_name, _event) \
CMN_EVENT_HNSR0_HBT(_name, _event), \
CMN_EVENT_HNS_ENHBT(_name, _event)
#define CMN_EVENT_HNS_HBT_OCC(_name, _event) \
CMN_EVENT_HNSR0_HBT(_name, _event), \
CMN_EVENT_HNS_OCC(CMNS3R2, _name, _event)
#define CMN_EVENT_HNS_HBT_EVICT(_name, _event) \
CMN_EVENT_HNSR0_HBT(_name, _event), \
CMN_EVENT_HNS_EVICT(CMNS3R2, _name, _event)
#define _CMN_EVENT_XP_MESH(_name, _event) \
__CMN_EVENT_XP(e_##_name, (_event) | (0 << 2)), \
__CMN_EVENT_XP(w_##_name, (_event) | (1 << 2)), \
__CMN_EVENT_XP(n_##_name, (_event) | (2 << 2)), \
__CMN_EVENT_XP(s_##_name, (_event) | (3 << 2))
#define _CMN_EVENT_XP_PORT(_name, _event) \
__CMN_EVENT_XP(p0_##_name, (_event) | (4 << 2)), \
__CMN_EVENT_XP(p1_##_name, (_event) | (5 << 2)), \
__CMN_EVENT_XP(p2_##_name, (_event) | (6 << 2)), \
__CMN_EVENT_XP(p3_##_name, (_event) | (7 << 2))
#define _CMN_EVENT_XP(_name, _event) \
_CMN_EVENT_XP_MESH(_name, _event), \
_CMN_EVENT_XP_PORT(_name, _event)
/* Good thing there are only 3 fundamental XP events... */
#define CMN_EVENT_XP(_name, _event) \
_CMN_EVENT_XP(req_##_name, (_event) | (0 << 5)), \
_CMN_EVENT_XP(rsp_##_name, (_event) | (1 << 5)), \
_CMN_EVENT_XP(snp_##_name, (_event) | (2 << 5)), \
_CMN_EVENT_XP(dat_##_name, (_event) | (3 << 5)), \
_CMN_EVENT_XP(pub_##_name, (_event) | (4 << 5)), \
_CMN_EVENT_XP(rsp2_##_name, (_event) | (5 << 5)), \
_CMN_EVENT_XP(dat2_##_name, (_event) | (6 << 5)), \
_CMN_EVENT_XP(req2_##_name, (_event) | (7 << 5)), \
_CMN_EVENT_XP(snp2_##_name, (_event) | (8 << 5))
#define CMN_EVENT_XP_DAT(_name, _event) \
_CMN_EVENT_XP_PORT(dat_##_name, (_event) | (3 << 5)), \
_CMN_EVENT_XP_PORT(dat2_##_name, (_event) | (6 << 5))
static struct attribute *arm_cmn_event_attrs[] = {
CMN_EVENT_DTC(cycles),
/*
* DVM node events conflict with HN-I events in the equivalent PMU
* slot, but our lazy short-cut of using the DTM counter index for
* the PMU index as well happens to avoid that by construction.
*/
CMN_EVENT_DVM(CMN600, rxreq_dvmop, 0x01),
CMN_EVENT_DVM(CMN600, rxreq_dvmsync, 0x02),
CMN_EVENT_DVM(CMN600, rxreq_dvmop_vmid_filtered, 0x03),
CMN_EVENT_DVM(CMN600, rxreq_retried, 0x04),
CMN_EVENT_DVM_OCC(CMN600, rxreq_trk_occupancy, 0x05),
CMN_EVENT_DVM(NOT_CMN600, dvmop_tlbi, 0x01),
CMN_EVENT_DVM(NOT_CMN600, dvmop_bpi, 0x02),
CMN_EVENT_DVM(NOT_CMN600, dvmop_pici, 0x03),
CMN_EVENT_DVM(NOT_CMN600, dvmop_vici, 0x04),
CMN_EVENT_DVM(NOT_CMN600, dvmsync, 0x05),
CMN_EVENT_DVM(NOT_CMN600, vmid_filtered, 0x06),
CMN_EVENT_DVM(NOT_CMN600, rndop_filtered, 0x07),
CMN_EVENT_DVM(NOT_CMN600, retry, 0x08),
CMN_EVENT_DVM(NOT_CMN600, txsnp_flitv, 0x09),
CMN_EVENT_DVM(NOT_CMN600, txsnp_stall, 0x0a),
CMN_EVENT_DVM(NOT_CMN600, trkfull, 0x0b),
CMN_EVENT_DVM_OCC(NOT_CMN600, trk_occupancy, 0x0c),
CMN_EVENT_DVM_OCC(CMN_700ON, trk_occupancy_cxha, 0x0d),
CMN_EVENT_DVM_OCC(CMN_700ON, trk_occupancy_pdn, 0x0e),
CMN_EVENT_DVM(CMN_700ON, trk_alloc, 0x0f),
CMN_EVENT_DVM(CMN_700ON, trk_cxha_alloc, 0x10),
CMN_EVENT_DVM(CMN_700ON, trk_pdn_alloc, 0x11),
CMN_EVENT_DVM(CMN_700ON, txsnp_stall_limit, 0x12),
CMN_EVENT_DVM(CMN_700ON, rxsnp_stall_starv, 0x13),
CMN_EVENT_DVM(CMN_700ON, txsnp_sync_stall_op, 0x14),
CMN_EVENT_HNF(CMN_ANY, cache_miss, 0x01),
CMN_EVENT_HNF(CMN_ANY, slc_sf_cache_access, 0x02),
CMN_EVENT_HNF(CMN_ANY, cache_fill, 0x03),
CMN_EVENT_HNF(CMN_ANY, pocq_retry, 0x04),
CMN_EVENT_HNF(CMN_ANY, pocq_reqs_recvd, 0x05),
CMN_EVENT_HNF(CMN_ANY, sf_hit, 0x06),
CMN_EVENT_HNF(CMN_ANY, sf_evictions, 0x07),
CMN_EVENT_HNF(CMN_ANY, dir_snoops_sent, 0x08),
CMN_EVENT_HNF(CMN_ANY, brd_snoops_sent, 0x09),
CMN_EVENT_HNF(CMN_ANY, slc_eviction, 0x0a),
CMN_EVENT_HNF(CMN_ANY, slc_fill_invalid_way, 0x0b),
CMN_EVENT_HNF(CMN_ANY, mc_retries, 0x0c),
CMN_EVENT_HNF(CMN_ANY, mc_reqs, 0x0d),
CMN_EVENT_HNF(CMN_ANY, qos_hh_retry, 0x0e),
CMN_EVENT_HNF_OCC(CMN_ANY, qos_pocq_occupancy, 0x0f),
CMN_EVENT_HNF(CMN_ANY, pocq_addrhaz, 0x10),
CMN_EVENT_HNF(CMN_ANY, pocq_atomic_addrhaz, 0x11),
CMN_EVENT_HNF(CMN_ANY, ld_st_swp_adq_full, 0x12),
CMN_EVENT_HNF(CMN_ANY, cmp_adq_full, 0x13),
CMN_EVENT_HNF(CMN_ANY, txdat_stall, 0x14),
CMN_EVENT_HNF(CMN_ANY, txrsp_stall, 0x15),
CMN_EVENT_HNF(CMN_ANY, seq_full, 0x16),
CMN_EVENT_HNF(CMN_ANY, seq_hit, 0x17),
CMN_EVENT_HNF(CMN_ANY, snp_sent, 0x18),
CMN_EVENT_HNF(CMN_ANY, sfbi_dir_snp_sent, 0x19),
CMN_EVENT_HNF(CMN_ANY, sfbi_brd_snp_sent, 0x1a),
CMN_EVENT_HNF(CMN_ANY, snp_sent_untrk, 0x1b),
CMN_EVENT_HNF(CMN_ANY, intv_dirty, 0x1c),
CMN_EVENT_HNF(CMN_ANY, stash_snp_sent, 0x1d),
CMN_EVENT_HNF(CMN_ANY, stash_data_pull, 0x1e),
CMN_EVENT_HNF(CMN_ANY, snp_fwded, 0x1f),
CMN_EVENT_HNF(NOT_CMN600, atomic_fwd, 0x20),
CMN_EVENT_HNF(NOT_CMN600, mpam_hardlim, 0x21),
CMN_EVENT_HNF(NOT_CMN600, mpam_softlim, 0x22),
CMN_EVENT_HNF(CMN_650ON, snp_sent_cluster, 0x23),
CMN_EVENT_HNF(CMN_650ON, sf_imprecise_evict, 0x24),
CMN_EVENT_HNF(CMN_650ON, sf_evict_shared_line, 0x25),
CMN_EVENT_HNF_CLS(CMN700, pocq_class_occup, 0x26),
CMN_EVENT_HNF_CLS(CMN700, pocq_class_retry, 0x27),
CMN_EVENT_HNF_CLS(CMN700, class_mc_reqs, 0x28),
CMN_EVENT_HNF_CLS(CMN700, class_cgnt_cmin, 0x29),
CMN_EVENT_HNF_SNT(CMN700, sn_throttle, 0x2a),
CMN_EVENT_HNF_SNT(CMN700, sn_throttle_min, 0x2b),
CMN_EVENT_HNF(CMN700, sf_precise_to_imprecise, 0x2c),
CMN_EVENT_HNF(CMN700, snp_intv_cln, 0x2d),
CMN_EVENT_HNF(CMN700, nc_excl, 0x2e),
CMN_EVENT_HNF(CMN700, excl_mon_ovfl, 0x2f),
CMN_EVENT_HNI(rrt_rd_occ_cnt_ovfl, 0x20),
CMN_EVENT_HNI(rrt_wr_occ_cnt_ovfl, 0x21),
CMN_EVENT_HNI(rdt_rd_occ_cnt_ovfl, 0x22),
CMN_EVENT_HNI(rdt_wr_occ_cnt_ovfl, 0x23),
CMN_EVENT_HNI(wdb_occ_cnt_ovfl, 0x24),
CMN_EVENT_HNI(rrt_rd_alloc, 0x25),
CMN_EVENT_HNI(rrt_wr_alloc, 0x26),
CMN_EVENT_HNI(rdt_rd_alloc, 0x27),
CMN_EVENT_HNI(rdt_wr_alloc, 0x28),
CMN_EVENT_HNI(wdb_alloc, 0x29),
CMN_EVENT_HNI(txrsp_retryack, 0x2a),
CMN_EVENT_HNI(arvalid_no_arready, 0x2b),
CMN_EVENT_HNI(arready_no_arvalid, 0x2c),
CMN_EVENT_HNI(awvalid_no_awready, 0x2d),
CMN_EVENT_HNI(awready_no_awvalid, 0x2e),
CMN_EVENT_HNI(wvalid_no_wready, 0x2f),
CMN_EVENT_HNI(txdat_stall, 0x30),
CMN_EVENT_HNI(nonpcie_serialization, 0x31),
CMN_EVENT_HNI(pcie_serialization, 0x32),
/*
* HN-P events squat on top of the HN-I similarly to DVM events, except
* for being crammed into the same physical node as well. And of course
* where would the fun be if the same events were in the same order...
*/
CMN_EVENT_HNP(rrt_wr_occ_cnt_ovfl, 0x01),
CMN_EVENT_HNP(rdt_wr_occ_cnt_ovfl, 0x02),
CMN_EVENT_HNP(wdb_occ_cnt_ovfl, 0x03),
CMN_EVENT_HNP(rrt_wr_alloc, 0x04),
CMN_EVENT_HNP(rdt_wr_alloc, 0x05),
CMN_EVENT_HNP(wdb_alloc, 0x06),
CMN_EVENT_HNP(awvalid_no_awready, 0x07),
CMN_EVENT_HNP(awready_no_awvalid, 0x08),
CMN_EVENT_HNP(wvalid_no_wready, 0x09),
CMN_EVENT_HNP(rrt_rd_occ_cnt_ovfl, 0x11),
CMN_EVENT_HNP(rdt_rd_occ_cnt_ovfl, 0x12),
CMN_EVENT_HNP(rrt_rd_alloc, 0x13),
CMN_EVENT_HNP(rdt_rd_alloc, 0x14),
CMN_EVENT_HNP(arvalid_no_arready, 0x15),
CMN_EVENT_HNP(arready_no_arvalid, 0x16),
CMN_EVENT_XP(txflit_valid, 0x01),
CMN_EVENT_XP(txflit_stall, 0x02),
CMN_EVENT_XP_DAT(partial_dat_flit, 0x03),
/* We treat watchpoints as a special made-up class of XP events */
CMN_EVENT_ATTR(CMN_ANY, watchpoint_up, CMN_TYPE_WP, CMN_WP_UP),
CMN_EVENT_ATTR(CMN_ANY, watchpoint_down, CMN_TYPE_WP, CMN_WP_DOWN),
CMN_EVENT_SBSX(CMN_ANY, rd_req, 0x01),
CMN_EVENT_SBSX(CMN_ANY, wr_req, 0x02),
CMN_EVENT_SBSX(CMN_ANY, cmo_req, 0x03),
CMN_EVENT_SBSX(CMN_ANY, txrsp_retryack, 0x04),
CMN_EVENT_SBSX(CMN_ANY, txdat_flitv, 0x05),
CMN_EVENT_SBSX(CMN_ANY, txrsp_flitv, 0x06),
CMN_EVENT_SBSX(CMN_ANY, rd_req_trkr_occ_cnt_ovfl, 0x11),
CMN_EVENT_SBSX(CMN_ANY, wr_req_trkr_occ_cnt_ovfl, 0x12),
CMN_EVENT_SBSX(CMN_ANY, cmo_req_trkr_occ_cnt_ovfl, 0x13),
CMN_EVENT_SBSX(CMN_ANY, wdb_occ_cnt_ovfl, 0x14),
CMN_EVENT_SBSX(CMN_ANY, rd_axi_trkr_occ_cnt_ovfl, 0x15),
CMN_EVENT_SBSX(CMN_ANY, cmo_axi_trkr_occ_cnt_ovfl, 0x16),
CMN_EVENT_SBSX(NOT_CMN600, rdb_occ_cnt_ovfl, 0x17),
CMN_EVENT_SBSX(CMN_ANY, arvalid_no_arready, 0x21),
CMN_EVENT_SBSX(CMN_ANY, awvalid_no_awready, 0x22),
CMN_EVENT_SBSX(CMN_ANY, wvalid_no_wready, 0x23),
CMN_EVENT_SBSX(CMN_ANY, txdat_stall, 0x24),
CMN_EVENT_SBSX(CMN_ANY, txrsp_stall, 0x25),
CMN_EVENT_RNID(CMN_ANY, s0_rdata_beats, 0x01),
CMN_EVENT_RNID(CMN_ANY, s1_rdata_beats, 0x02),
CMN_EVENT_RNID(CMN_ANY, s2_rdata_beats, 0x03),
CMN_EVENT_RNID(CMN_ANY, rxdat_flits, 0x04),
CMN_EVENT_RNID(CMN_ANY, txdat_flits, 0x05),
CMN_EVENT_RNID(CMN_ANY, txreq_flits_total, 0x06),
CMN_EVENT_RNID(CMN_ANY, txreq_flits_retried, 0x07),
CMN_EVENT_RNID(CMN_ANY, rrt_occ_ovfl, 0x08),
CMN_EVENT_RNID(CMN_ANY, wrt_occ_ovfl, 0x09),
CMN_EVENT_RNID(CMN_ANY, txreq_flits_replayed, 0x0a),
CMN_EVENT_RNID(CMN_ANY, wrcancel_sent, 0x0b),
CMN_EVENT_RNID(CMN_ANY, s0_wdata_beats, 0x0c),
CMN_EVENT_RNID(CMN_ANY, s1_wdata_beats, 0x0d),
CMN_EVENT_RNID(CMN_ANY, s2_wdata_beats, 0x0e),
CMN_EVENT_RNID(CMN_ANY, rrt_alloc, 0x0f),
CMN_EVENT_RNID(CMN_ANY, wrt_alloc, 0x10),
CMN_EVENT_RNID(CMN600, rdb_unord, 0x11),
CMN_EVENT_RNID(CMN600, rdb_replay, 0x12),
CMN_EVENT_RNID(CMN600, rdb_hybrid, 0x13),
CMN_EVENT_RNID(CMN600, rdb_ord, 0x14),
CMN_EVENT_RNID(NOT_CMN600, padb_occ_ovfl, 0x11),
CMN_EVENT_RNID(NOT_CMN600, rpdb_occ_ovfl, 0x12),
CMN_EVENT_RNID(NOT_CMN600, rrt_occup_ovfl_slice1, 0x13),
CMN_EVENT_RNID(NOT_CMN600, rrt_occup_ovfl_slice2, 0x14),
CMN_EVENT_RNID(NOT_CMN600, rrt_occup_ovfl_slice3, 0x15),
CMN_EVENT_RNID(NOT_CMN600, wrt_throttled, 0x16),
CMN_EVENT_RNID(CMN700, ldb_full, 0x17),
CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice0, 0x18),
CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice1, 0x19),
CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice2, 0x1a),
CMN_EVENT_RNID(CMN700, rrt_rd_req_occup_ovfl_slice3, 0x1b),
CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice0, 0x1c),
CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice1, 0x1d),
CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice2, 0x1e),
CMN_EVENT_RNID(CMN700, rrt_burst_occup_ovfl_slice3, 0x1f),
CMN_EVENT_RNID(CMN700, rrt_burst_alloc, 0x20),
CMN_EVENT_RNID(CMN700, awid_hash, 0x21),
CMN_EVENT_RNID(CMN700, atomic_alloc, 0x22),
CMN_EVENT_RNID(CMN700, atomic_occ_ovfl, 0x23),
CMN_EVENT_MTSX(tc_lookup, 0x01),
CMN_EVENT_MTSX(tc_fill, 0x02),
CMN_EVENT_MTSX(tc_miss, 0x03),
CMN_EVENT_MTSX(tdb_forward, 0x04),
CMN_EVENT_MTSX(tcq_hazard, 0x05),
CMN_EVENT_MTSX(tcq_rd_alloc, 0x06),
CMN_EVENT_MTSX(tcq_wr_alloc, 0x07),
CMN_EVENT_MTSX(tcq_cmo_alloc, 0x08),
CMN_EVENT_MTSX(axi_rd_req, 0x09),
CMN_EVENT_MTSX(axi_wr_req, 0x0a),
CMN_EVENT_MTSX(tcq_occ_cnt_ovfl, 0x0b),
CMN_EVENT_MTSX(tdb_occ_cnt_ovfl, 0x0c),
CMN_EVENT_CXRA(CMN_ANY, rht_occ, 0x01),
CMN_EVENT_CXRA(CMN_ANY, sht_occ, 0x02),
CMN_EVENT_CXRA(CMN_ANY, rdb_occ, 0x03),
CMN_EVENT_CXRA(CMN_ANY, wdb_occ, 0x04),
CMN_EVENT_CXRA(CMN_ANY, ssb_occ, 0x05),
CMN_EVENT_CXRA(CMN_ANY, snp_bcasts, 0x06),
CMN_EVENT_CXRA(CMN_ANY, req_chains, 0x07),
CMN_EVENT_CXRA(CMN_ANY, req_chain_avglen, 0x08),
CMN_EVENT_CXRA(CMN_ANY, chirsp_stalls, 0x09),
CMN_EVENT_CXRA(CMN_ANY, chidat_stalls, 0x0a),
CMN_EVENT_CXRA(CMN_ANY, cxreq_pcrd_stalls_link0, 0x0b),
CMN_EVENT_CXRA(CMN_ANY, cxreq_pcrd_stalls_link1, 0x0c),
CMN_EVENT_CXRA(CMN_ANY, cxreq_pcrd_stalls_link2, 0x0d),
CMN_EVENT_CXRA(CMN_ANY, cxdat_pcrd_stalls_link0, 0x0e),
CMN_EVENT_CXRA(CMN_ANY, cxdat_pcrd_stalls_link1, 0x0f),
CMN_EVENT_CXRA(CMN_ANY, cxdat_pcrd_stalls_link2, 0x10),
CMN_EVENT_CXRA(CMN_ANY, external_chirsp_stalls, 0x11),
CMN_EVENT_CXRA(CMN_ANY, external_chidat_stalls, 0x12),
CMN_EVENT_CXRA(NOT_CMN600, cxmisc_pcrd_stalls_link0, 0x13),
CMN_EVENT_CXRA(NOT_CMN600, cxmisc_pcrd_stalls_link1, 0x14),
CMN_EVENT_CXRA(NOT_CMN600, cxmisc_pcrd_stalls_link2, 0x15),
CMN_EVENT_CXHA(rddatbyp, 0x21),
CMN_EVENT_CXHA(chirsp_up_stall, 0x22),
CMN_EVENT_CXHA(chidat_up_stall, 0x23),
CMN_EVENT_CXHA(snppcrd_link0_stall, 0x24),
CMN_EVENT_CXHA(snppcrd_link1_stall, 0x25),
CMN_EVENT_CXHA(snppcrd_link2_stall, 0x26),
CMN_EVENT_CXHA(reqtrk_occ, 0x27),
CMN_EVENT_CXHA(rdb_occ, 0x28),
CMN_EVENT_CXHA(rdbyp_occ, 0x29),
CMN_EVENT_CXHA(wdb_occ, 0x2a),
CMN_EVENT_CXHA(snptrk_occ, 0x2b),
CMN_EVENT_CXHA(sdb_occ, 0x2c),
CMN_EVENT_CXHA(snphaz_occ, 0x2d),
CMN_EVENT_CCRA(rht_occ, 0x41),
CMN_EVENT_CCRA(sht_occ, 0x42),
CMN_EVENT_CCRA(rdb_occ, 0x43),
CMN_EVENT_CCRA(wdb_occ, 0x44),
CMN_EVENT_CCRA(ssb_occ, 0x45),
CMN_EVENT_CCRA(snp_bcasts, 0x46),
CMN_EVENT_CCRA(req_chains, 0x47),
CMN_EVENT_CCRA(req_chain_avglen, 0x48),
CMN_EVENT_CCRA(chirsp_stalls, 0x49),
CMN_EVENT_CCRA(chidat_stalls, 0x4a),
CMN_EVENT_CCRA(cxreq_pcrd_stalls_link0, 0x4b),
CMN_EVENT_CCRA(cxreq_pcrd_stalls_link1, 0x4c),
CMN_EVENT_CCRA(cxreq_pcrd_stalls_link2, 0x4d),
CMN_EVENT_CCRA(cxdat_pcrd_stalls_link0, 0x4e),
CMN_EVENT_CCRA(cxdat_pcrd_stalls_link1, 0x4f),
CMN_EVENT_CCRA(cxdat_pcrd_stalls_link2, 0x50),
CMN_EVENT_CCRA(external_chirsp_stalls, 0x51),
CMN_EVENT_CCRA(external_chidat_stalls, 0x52),
CMN_EVENT_CCRA(cxmisc_pcrd_stalls_link0, 0x53),
CMN_EVENT_CCRA(cxmisc_pcrd_stalls_link1, 0x54),
CMN_EVENT_CCRA(cxmisc_pcrd_stalls_link2, 0x55),
CMN_EVENT_CCRA(rht_alloc, 0x56),
CMN_EVENT_CCRA(sht_alloc, 0x57),
CMN_EVENT_CCRA(rdb_alloc, 0x58),
CMN_EVENT_CCRA(wdb_alloc, 0x59),
CMN_EVENT_CCRA(ssb_alloc, 0x5a),
CMN_EVENT_CCHA(CMN_ANY, rddatbyp, 0x61),
CMN_EVENT_CCHA(CMN_ANY, chirsp_up_stall, 0x62),
CMN_EVENT_CCHA(CMN_ANY, chidat_up_stall, 0x63),
CMN_EVENT_CCHA(CMN_ANY, snppcrd_link0_stall, 0x64),
CMN_EVENT_CCHA(CMN_ANY, snppcrd_link1_stall, 0x65),
CMN_EVENT_CCHA(CMN_ANY, snppcrd_link2_stall, 0x66),
CMN_EVENT_CCHA(CMN_ANY, reqtrk_occ, 0x67),
CMN_EVENT_CCHA(CMN_ANY, rdb_occ, 0x68),
CMN_EVENT_CCHA(CMN_ANY, rdbyp_occ, 0x69),
CMN_EVENT_CCHA(CMN_ANY, wdb_occ, 0x6a),
CMN_EVENT_CCHA(CMN_ANY, snptrk_occ, 0x6b),
CMN_EVENT_CCHA(CMN_ANY, sdb_occ, 0x6c),
CMN_EVENT_CCHA(CMN_ANY, snphaz_occ, 0x6d),
CMN_EVENT_CCHA(CMN_ANY, reqtrk_alloc, 0x6e),
CMN_EVENT_CCHA(CMN_ANY, rdb_alloc, 0x6f),
CMN_EVENT_CCHA(CMN_ANY, rdbyp_alloc, 0x70),
CMN_EVENT_CCHA(CMN_ANY, wdb_alloc, 0x71),
CMN_EVENT_CCHA(CMN_ANY, snptrk_alloc, 0x72),
CMN_EVENT_CCHA(CMN_ANY, db_alloc, 0x73),
CMN_EVENT_CCHA(CMN_ANY, snphaz_alloc, 0x74),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_req_occ, 0x75),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_req_alloc, 0x76),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_req_occ, 0x77),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_req_alloc, 0x78),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_req_occ, 0x79),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_req_alloc, 0x7a),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_reg_req_occ, 0x7b),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_reg_req_alloc, 0x7c),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_rsvd_req_occ, 0x7d),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_rsvd_req_alloc, 0x7e),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_dat_occ, 0x7f),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_dat_alloc, 0x80),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_dat_occ, 0x81),
CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_dat_alloc, 0x82),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_dat_occ, 0x83),
CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_dat_alloc, 0x84),
CMN_EVENT_CCHA(CMNS3, chirsp1_up_stall, 0x85),
CMN_EVENT_CCLA(rx_cxs, 0x21),
CMN_EVENT_CCLA(tx_cxs, 0x22),
CMN_EVENT_CCLA(rx_cxs_avg_size, 0x23),
CMN_EVENT_CCLA(tx_cxs_avg_size, 0x24),
CMN_EVENT_CCLA(tx_cxs_lcrd_backpressure, 0x25),
CMN_EVENT_CCLA(link_crdbuf_occ, 0x26),
CMN_EVENT_CCLA(link_crdbuf_alloc, 0x27),
CMN_EVENT_CCLA(pfwd_rcvr_cxs, 0x28),
CMN_EVENT_CCLA(pfwd_sndr_num_flits, 0x29),
CMN_EVENT_CCLA(pfwd_sndr_stalls_static_crd, 0x2a),
CMN_EVENT_CCLA(pfwd_sndr_stalls_dynmaic_crd, 0x2b),
CMN_EVENT_HNS_HBT_ENHBT(cache_miss, 0x01),
CMN_EVENT_HNS_HBT_ENHBT(slc_sf_cache_access, 0x02),
CMN_EVENT_HNS_HBT_ENHBT(cache_fill, 0x03),
CMN_EVENT_HNS_HBT_OCC(pocq_retry, 0x04),
CMN_EVENT_HNS_HBT_OCC(pocq_reqs_recvd, 0x05),
CMN_EVENT_HNS_HBT_ENHBT(sf_hit, 0x06),
CMN_EVENT_HNS_HBT_EVICT(sf_evictions, 0x07),
CMN_EVENT_HNS_VC(dir_snoops_sent, 0x08),
CMN_EVENT_HNS_VC(brd_snoops_sent, 0x09),
CMN_EVENT_HNS_HBT_EVICT(slc_eviction, 0x0a),
CMN_EVENT_HNS_HBT_ENHBT(slc_fill_invalid_way, 0x0b),
CMN_EVENT_HNS_R2SNH(mc_retries_local, 0x0c),
CMN_EVENT_HNS_SNH(CMN_ANY, mc_reqs_local, 0x0d),
CMN_EVENT_HNS(qos_hh_retry, 0x0e),
CMN_EVENT_HNS_OCC(CMN_ANY, qos_pocq_occupancy, 0x0f),
CMN_EVENT_HNS_HBT_ENHBT(pocq_addrhaz, 0x10),
CMN_EVENT_HNS_HBT_ENHBT(pocq_atomic_addrhaz, 0x11),
CMN_EVENT_HNSR0(ld_st_swp_adq_full, 0x12),
CMN_EVENT_HNSR0(cmp_adq_full, 0x13),
CMN_EVENT_HNS(txdat_stall, 0x14),
CMN_EVENT_HNS(txrsp_stall, 0x15),
CMN_EVENT_HNSR0(seq_full, 0x16),
CMN_EVENT_HNS(seq_hit, 0x17),
CMN_EVENT_HNS_VC(snp_sent, 0x18),
CMN_EVENT_HNS_VC(sfbi_dir_snp_sent, 0x19),
CMN_EVENT_HNS_VC(sfbi_brd_snp_sent, 0x1a),
CMN_EVENT_HNS(intv_dirty, 0x1c),
CMN_EVENT_HNSR0(stash_snp_sent, 0x1d),
CMN_EVENT_HNSR0(stash_data_pull, 0x1e),
CMN_EVENT_HNS_VC(snp_fwded, 0x1f),
CMN_EVENT_HNSR0(atomic_fwd, 0x20),
CMN_EVENT_HNS(mpam_hardlim, 0x21),
CMN_EVENT_HNS(mpam_softlim, 0x22),
CMN_EVENT_HNS_VC(snp_sent_cluster, 0x23),
CMN_EVENT_HNS_R2HBT(sf_imprecise_evict, 0x24),
CMN_EVENT_HNS(sf_evict_shared_line, 0x25),
CMN_EVENT_HNS_CLS(pocq_class_occup, 0x26),
CMN_EVENT_HNS_CLS(pocq_class_retry, 0x27),
CMN_EVENT_HNS_CLS(class_mc_reqs_local, 0x28),
CMN_EVENT_HNSR0_CLS(class_cgnt_cmin, 0x29),
CMN_EVENT_HNS_SNT(CMN_ANY, sn_throttle, 0x2a),
CMN_EVENT_HNS_SNT(CMN_ANY, sn_throttle_min, 0x2b),
CMN_EVENT_HNS(sf_precise_to_imprecise, 0x2c),
CMN_EVENT_HNS(snp_intv_cln, 0x2d),
CMN_EVENT_HNS(nc_excl, 0x2e),
CMN_EVENT_HNSR0(excl_mon_ovfl, 0x2f),
CMN_EVENT_HNS(snp_req_recvd, 0x30),
CMN_EVENT_HNS(snp_req_byp_pocq, 0x31),
CMN_EVENT_HNS(dir_ccgha_snp_sent, 0x32),
CMN_EVENT_HNS(brd_ccgha_snp_sent, 0x33),
CMN_EVENT_HNSR0(ccgha_snp_stall, 0x34),
CMN_EVENT_HNS(lbt_req_hardlim, 0x35),
CMN_EVENT_HNS(hbt_req_hardlim, 0x36),
CMN_EVENT_HNS(sf_reupdate, 0x37),
CMN_EVENT_HNS_R2HBT(excl_sf_imprecise, 0x38),
CMN_EVENT_HNS(snp_pocq_addrhaz, 0x39),
CMN_EVENT_HNS_R2SNH(mc_retries_remote, 0x3a),
CMN_EVENT_HNS_SNH(CMN_ANY, mc_reqs_remote, 0x3b),
CMN_EVENT_HNS_CLS(class_mc_reqs_remote, 0x3c),
CMN_EVENT_HNS_ENHBT(readonce_hazard_detected, 0x3d),
CMN_EVENT_HNS_ENHBT(readonce_fwd_data_completed, 0x3e),
CMN_EVENT_HNS_SNT(CMNS3R2, cbusy00, 0x40),
CMN_EVENT_HNS_SNT(CMNS3R2, cbusy01, 0x41),
CMN_EVENT_HNS_SNT(CMNS3R2, cbusy10, 0x42),
CMN_EVENT_HNS_SNT(CMNS3R2, cbusy11, 0x43),
CMN_EVENT_HNS_ENHBT(ro_rnsd_new_alloc_hint, 0x44),
NULL
};
static const struct attribute_group arm_cmn_event_attrs_group = {
.name = "events",
.attrs = arm_cmn_event_attrs,
.is_visible = arm_cmn_event_attr_is_visible,
};
static ssize_t arm_cmn_format_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct arm_cmn_format_attr *fmt = container_of(attr, typeof(*fmt), attr);
if (!fmt->config)
return sysfs_emit(buf, "config:%*pbl\n", 64, &fmt->field);
return sysfs_emit(buf, "config%d:%*pbl\n", fmt->config, 64, &fmt->field);
}
#define _CMN_FORMAT_ATTR(_name, _cfg, _fld) \
(&((struct arm_cmn_format_attr[]) {{ \
.attr = __ATTR(_name, 0444, arm_cmn_format_show, NULL), \
.config = _cfg, \
.field = _fld, \
}})[0].attr.attr)
#define CMN_FORMAT_ATTR(_name, _fld) _CMN_FORMAT_ATTR(_name, 0, _fld)
static struct attribute *arm_cmn_format_attrs[] = {
CMN_FORMAT_ATTR(type, CMN_CONFIG_TYPE),
CMN_FORMAT_ATTR(eventid, CMN_CONFIG_EVENTID),
CMN_FORMAT_ATTR(filter, CMN_CONFIG_FILTER),
CMN_FORMAT_ATTR(bynodeid, CMN_CONFIG_BYNODEID),
CMN_FORMAT_ATTR(nodeid, CMN_CONFIG_NODEID),
CMN_FORMAT_ATTR(filter2, CMN_CONFIG_FILTER2),
CMN_FORMAT_ATTR(wp_dev_sel, CMN_CONFIG_WP_DEV_SEL),
CMN_FORMAT_ATTR(wp_chn_sel, CMN_CONFIG_WP_CHN_SEL),
CMN_FORMAT_ATTR(wp_grp, CMN_CONFIG_WP_GRP),
CMN_FORMAT_ATTR(wp_exclusive, CMN_CONFIG_WP_EXCLUSIVE),
CMN_FORMAT_ATTR(wp_combine, CMN_CONFIG_WP_COMBINE),
_CMN_FORMAT_ATTR(wp_val, 1, CMN_CONFIG1_WP_VAL),
_CMN_FORMAT_ATTR(wp_mask, 2, CMN_CONFIG2_WP_MASK),
/* Old name for UAPI compatibility */
CMN_FORMAT_ATTR(occupid, CMN_CONFIG_FILTER),
NULL
};
static const struct attribute_group arm_cmn_format_attrs_group = {
.name = "format",
.attrs = arm_cmn_format_attrs,
};
static ssize_t arm_cmn_cpumask_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev));
return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(cmn->cpu)));
}
static struct device_attribute arm_cmn_cpumask_attr =
__ATTR(cpumask, 0444, arm_cmn_cpumask_show, NULL);
static ssize_t arm_cmn_identifier_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev));
return sysfs_emit(buf, "%03x%02x\n", cmn->part, cmn->rev);
}
static struct device_attribute arm_cmn_identifier_attr =
__ATTR(identifier, 0444, arm_cmn_identifier_show, NULL);
static struct attribute *arm_cmn_other_attrs[] = {
&arm_cmn_cpumask_attr.attr,
&arm_cmn_identifier_attr.attr,
NULL,
};
static const struct attribute_group arm_cmn_other_attrs_group = {
.attrs = arm_cmn_other_attrs,
};
static const struct attribute_group *arm_cmn_attr_groups[] = {
&arm_cmn_event_attrs_group,
&arm_cmn_format_attrs_group,
&arm_cmn_other_attrs_group,
NULL
};
static int arm_cmn_find_free_wp_idx(struct arm_cmn_dtm *dtm,
struct perf_event *event)
{
int wp_idx = CMN_EVENT_EVENTID(event);
if (dtm->wp_event[wp_idx] >= 0)
if (dtm->wp_event[++wp_idx] >= 0)
return -ENOSPC;
return wp_idx;
}
static int arm_cmn_get_assigned_wp_idx(struct perf_event *event,
struct arm_cmn_hw_event *hw,
unsigned int pos)
{
return CMN_EVENT_EVENTID(event) + arm_cmn_get_wp_idx(hw, pos);
}
static void arm_cmn_claim_wp_idx(struct arm_cmn_dtm *dtm,
struct perf_event *event,
unsigned int dtc, int wp_idx,
unsigned int pos)
{
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
dtm->wp_event[wp_idx] = hw->dtc_idx[dtc];
arm_cmn_set_wp_idx(hw, pos, wp_idx - CMN_EVENT_EVENTID(event));
}
static u32 arm_cmn_wp_config(struct perf_event *event, int wp_idx)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
u32 config;
u32 dev = CMN_EVENT_WP_DEV_SEL(event);
u32 chn = CMN_EVENT_WP_CHN_SEL(event);
u32 grp = CMN_EVENT_WP_GRP(event);
u32 exc = CMN_EVENT_WP_EXCLUSIVE(event);
u32 combine = CMN_EVENT_WP_COMBINE(event);
bool is_cmn600 = cmn->part == PART_CMN600;
/* CMN-600 supports only primary and secondary matching groups */
if (is_cmn600)
grp &= 1;
config = FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_DEV_SEL, dev) |
FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_CHN_SEL, chn) |
FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_GRP, grp);
if (!cmn->multi_dtm)
config |= FIELD_PREP(CMN_DTM_WPn_CONFIG_WP_DEV_SEL2, dev >> 1);
if (exc)
config |= is_cmn600 ? CMN600_WPn_CONFIG_WP_EXCLUSIVE :
CMN_DTM_WPn_CONFIG_WP_EXCLUSIVE;
/* wp_combine is available only on WP0 and WP2 */
if (combine && !(wp_idx & 0x1))
config |= is_cmn600 ? CMN600_WPn_CONFIG_WP_COMBINE :
CMN_DTM_WPn_CONFIG_WP_COMBINE;
return config;
}
static void arm_cmn_set_state(struct arm_cmn *cmn, u32 state)
{
if (!cmn->state)
writel_relaxed(0, CMN_DT_PMCR(&cmn->dtc[0]));
cmn->state |= state;
}
static void arm_cmn_clear_state(struct arm_cmn *cmn, u32 state)
{
cmn->state &= ~state;
if (!cmn->state)
writel_relaxed(CMN_DT_PMCR_PMU_EN | CMN_DT_PMCR_OVFL_INTR_EN,
CMN_DT_PMCR(&cmn->dtc[0]));
}
static void arm_cmn_pmu_enable(struct pmu *pmu)
{
arm_cmn_clear_state(to_cmn(pmu), CMN_STATE_DISABLED);
}
static void arm_cmn_pmu_disable(struct pmu *pmu)
{
arm_cmn_set_state(to_cmn(pmu), CMN_STATE_DISABLED);
}
static u64 arm_cmn_read_dtm(struct arm_cmn *cmn, struct arm_cmn_hw_event *hw,
bool snapshot)
{
struct arm_cmn_dtm *dtm = NULL;
struct arm_cmn_node *dn;
unsigned int i, offset, dtm_idx;
u64 reg, count = 0;
offset = snapshot ? CMN_DTM_PMEVCNTSR : CMN_DTM_PMEVCNT;
for_each_hw_dn(hw, dn, i) {
if (dtm != &cmn->dtms[dn->dtm]) {
dtm = &cmn->dtms[dn->dtm] + hw->dtm_offset;
reg = readq_relaxed(dtm->base + offset);
}
dtm_idx = arm_cmn_get_dtm_idx(hw, i);
count += (u16)(reg >> (dtm_idx * 16));
}
return count;
}
static u64 arm_cmn_read_cc(struct arm_cmn_dtc *dtc)
{
void __iomem *pmccntr = CMN_DT_PMCCNTR(dtc);
u64 val = readq_relaxed(pmccntr);
writeq_relaxed(CMN_CC_INIT, pmccntr);
return (val - CMN_CC_INIT) & ((CMN_CC_INIT << 1) - 1);
}
static u32 arm_cmn_read_counter(struct arm_cmn_dtc *dtc, int idx)
{
void __iomem *pmevcnt = CMN_DT_PMEVCNT(dtc, idx);
u32 val = readl_relaxed(pmevcnt);
writel_relaxed(CMN_COUNTER_INIT, pmevcnt);
return val - CMN_COUNTER_INIT;
}
static void arm_cmn_init_counter(struct perf_event *event)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
u64 count;
for_each_hw_dtc_idx(hw, i, idx) {
writel_relaxed(CMN_COUNTER_INIT, CMN_DT_PMEVCNT(&cmn->dtc[i], idx));
cmn->dtc[i].counters[idx] = event;
}
count = arm_cmn_read_dtm(cmn, hw, false);
local64_set(&event->hw.prev_count, count);
}
static void arm_cmn_event_read(struct perf_event *event)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
u64 delta, new, prev;
unsigned long flags;
if (CMN_EVENT_TYPE(event) == CMN_TYPE_DTC) {
delta = arm_cmn_read_cc(cmn->dtc + hw->cc_idx);
local64_add(delta, &event->count);
return;
}
new = arm_cmn_read_dtm(cmn, hw, false);
prev = local64_xchg(&event->hw.prev_count, new);
delta = new - prev;
local_irq_save(flags);
for_each_hw_dtc_idx(hw, i, idx) {
new = arm_cmn_read_counter(cmn->dtc + i, idx);
delta += new << 16;
}
local_irq_restore(flags);
local64_add(delta, &event->count);
}
static int arm_cmn_set_event_sel_hi(struct arm_cmn_node *dn,
enum cmn_filter_select fsel, u8 val)
{
if (!dn->filter[fsel].count) {
const u64 *filter = arm_cmn_filters[dn->filter[SEL_NONE].val];
u64 reg = 0;
dn->filter[fsel].val = val;
for (int i = SEL_OCCUP1_ID; i < SEL_MAX; i++) {
if (filter[i])
reg |= field_prep(filter[i], dn->filter[i].val);
}
writel_relaxed(reg >> 32, dn->pmu_base + CMN_PMU_EVENT_SEL + 4);
} else if (dn->filter[fsel].val != val) {
return -EBUSY;
}
dn->filter[fsel].count++;
return 0;
}
static void arm_cmn_set_event_sel_lo(struct arm_cmn_node *dn, int dtm_idx,
int eventid, bool wide_sel)
{
if (wide_sel) {
dn->event_w[dtm_idx] = eventid;
writeq_relaxed(le64_to_cpu(dn->event_sel_w), dn->pmu_base + CMN_PMU_EVENT_SEL);
} else {
dn->event[dtm_idx] = eventid;
writel_relaxed(le32_to_cpu(dn->event_sel), dn->pmu_base + CMN_PMU_EVENT_SEL);
}
}
static void arm_cmn_event_start(struct perf_event *event, int flags)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
struct arm_cmn_node *dn;
enum cmn_node_type type = CMN_EVENT_TYPE(event);
int i;
if (type == CMN_TYPE_DTC) {
struct arm_cmn_dtc *dtc = cmn->dtc + hw->cc_idx;
writel_relaxed(CMN_DT_DTC_CTL_DT_EN | CMN_DT_DTC_CTL_CG_DISABLE,
dtc->base + CMN_DT_DTC_CTL);
writeq_relaxed(CMN_CC_INIT, CMN_DT_PMCCNTR(dtc));
dtc->cc_active = true;
} else if (type == CMN_TYPE_WP) {
u64 val = CMN_EVENT_WP_VAL(event);
u64 mask = CMN_EVENT_WP_MASK(event);
for_each_hw_dn(hw, dn, i) {
void __iomem *base = dn->pmu_base + CMN_DTM_OFFSET(hw->dtm_offset);
int wp_idx = arm_cmn_get_assigned_wp_idx(event, hw, i);
writeq_relaxed(val, base + CMN_DTM_WPn_VAL(wp_idx));
writeq_relaxed(mask, base + CMN_DTM_WPn_MASK(wp_idx));
}
} else for_each_hw_dn(hw, dn, i) {
int dtm_idx = arm_cmn_get_dtm_idx(hw, i);
arm_cmn_set_event_sel_lo(dn, dtm_idx, CMN_EVENT_EVENTID(event),
hw->wide_sel);
}
}
static void arm_cmn_event_stop(struct perf_event *event, int flags)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
struct arm_cmn_node *dn;
enum cmn_node_type type = CMN_EVENT_TYPE(event);
int i;
if (type == CMN_TYPE_DTC) {
struct arm_cmn_dtc *dtc = cmn->dtc + hw->cc_idx;
dtc->cc_active = false;
writel_relaxed(CMN_DT_DTC_CTL_DT_EN, dtc->base + CMN_DT_DTC_CTL);
} else if (type == CMN_TYPE_WP) {
for_each_hw_dn(hw, dn, i) {
void __iomem *base = dn->pmu_base + CMN_DTM_OFFSET(hw->dtm_offset);
int wp_idx = arm_cmn_get_assigned_wp_idx(event, hw, i);
writeq_relaxed(0, base + CMN_DTM_WPn_MASK(wp_idx));
writeq_relaxed(~0ULL, base + CMN_DTM_WPn_VAL(wp_idx));
}
} else for_each_hw_dn(hw, dn, i) {
int dtm_idx = arm_cmn_get_dtm_idx(hw, i);
arm_cmn_set_event_sel_lo(dn, dtm_idx, 0, hw->wide_sel);
}
arm_cmn_event_read(event);
}
struct arm_cmn_val {
u8 dtm_count[CMN_MAX_DTMS];
u8 filter[CMN_MAX_DTMS][SEL_MAX];
u8 wp[CMN_MAX_DTMS][4];
u8 wp_combine[CMN_MAX_DTMS][2];
int dtc_count[CMN_MAX_DTCS];
bool cycles;
};
static int arm_cmn_val_find_free_wp_config(struct perf_event *event,
struct arm_cmn_val *val, int dtm)
{
int wp_idx = CMN_EVENT_EVENTID(event);
if (val->wp[dtm][wp_idx])
if (val->wp[dtm][++wp_idx])
return -ENOSPC;
return wp_idx;
}
static void arm_cmn_val_add_event(struct arm_cmn *cmn, struct arm_cmn_val *val,
struct perf_event *event)
{
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
struct arm_cmn_node *dn;
enum cmn_node_type type;
int i;
if (is_software_event(event))
return;
type = CMN_EVENT_TYPE(event);
if (type == CMN_TYPE_DTC) {
val->cycles = true;
return;
}
for_each_hw_dtc_idx(hw, dtc, idx)
val->dtc_count[dtc]++;
for_each_hw_dn(hw, dn, i) {
int wp_idx, dtm = dn->dtm, sel = hw->filter_sel;
val->dtm_count[dtm]++;
if (sel == SEL_EVICT_STATE_SEL) {
val->filter[dtm][sel] = CMN_EVENT_FILTER2(event) + 1;
sel = SEL_HBT_LBT_SEL;
}
if (sel)
val->filter[dtm][sel] = CMN_EVENT_FILTER(event) + 1;
if (type != CMN_TYPE_WP)
continue;
wp_idx = arm_cmn_val_find_free_wp_config(event, val, dtm);
val->wp[dtm][wp_idx] = 1;
val->wp_combine[dtm][wp_idx >> 1] += !!CMN_EVENT_WP_COMBINE(event);
}
}
static int arm_cmn_validate_group(struct arm_cmn *cmn, struct perf_event *event)
{
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
struct arm_cmn_node *dn;
struct perf_event *sibling, *leader = event->group_leader;
enum cmn_node_type type;
struct arm_cmn_val *val;
int i, ret = -EINVAL;
if (leader == event)
return 0;
if (event->pmu != leader->pmu && !is_software_event(leader))
return -EINVAL;
val = kzalloc_obj(*val);
if (!val)
return -ENOMEM;
arm_cmn_val_add_event(cmn, val, leader);
for_each_sibling_event(sibling, leader)
arm_cmn_val_add_event(cmn, val, sibling);
type = CMN_EVENT_TYPE(event);
if (type == CMN_TYPE_DTC) {
ret = val->cycles ? -EINVAL : 0;
goto done;
}
for_each_hw_dtc_idx(hw, dtc, idx)
if (val->dtc_count[dtc] == CMN_DT_NUM_COUNTERS)
goto done;
for_each_hw_dn(hw, dn, i) {
int wp_idx, dtm = dn->dtm, sel = hw->filter_sel;
if (val->dtm_count[dtm] == CMN_DTM_NUM_COUNTERS)
goto done;
if (sel == SEL_EVICT_STATE_SEL) {
if (val->filter[dtm][sel] &&
val->filter[dtm][sel] != CMN_EVENT_FILTER2(event) + 1)
goto done;
sel = SEL_HBT_LBT_SEL;
}
if (sel && val->filter[dtm][sel] &&
val->filter[dtm][sel] != CMN_EVENT_FILTER(event) + 1)
goto done;
if (type != CMN_TYPE_WP)
continue;
wp_idx = arm_cmn_val_find_free_wp_config(event, val, dtm);
if (wp_idx < 0)
goto done;
if (wp_idx & 1 &&
val->wp_combine[dtm][wp_idx >> 1] != !!CMN_EVENT_WP_COMBINE(event))
goto done;
}
ret = 0;
done:
kfree(val);
return ret;
}
static enum cmn_filter_select arm_cmn_event_filter(const struct arm_cmn *cmn,
enum cmn_node_type type,
unsigned int eventid)
{
struct arm_cmn_event_attr *e;
enum cmn_model model = arm_cmn_model(cmn);
for (int i = 0; i < ARRAY_SIZE(arm_cmn_event_attrs) - 1; i++) {
e = container_of(arm_cmn_event_attrs[i], typeof(*e), attr.attr);
if (e->model & model && e->type == type && e->eventid == eventid)
return e->filter[1].sel ?: e->filter[0].sel;
}
return SEL_NONE;
}
static void arm_cmn_event_destroy(struct perf_event *event)
{
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
bitmap_free(hw->dtm_idx);
bitmap_free(hw->wp_idx);
}
static int arm_cmn_event_init(struct perf_event *event)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
struct arm_cmn_node *dn;
enum cmn_node_type type;
bool bynodeid;
u16 nodeid, eventid;
if (event->attr.type != event->pmu->type)
return -ENOENT;
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
event->cpu = cmn->cpu;
if (event->cpu < 0)
return -EINVAL;
type = CMN_EVENT_TYPE(event);
/* DTC events (i.e. cycles) already have everything they need */
if (type == CMN_TYPE_DTC)
return arm_cmn_validate_group(cmn, event);
event->destroy = arm_cmn_event_destroy;
hw->dtm_idx = arm_cmn_alloc_dtm_idx();
if (!hw->dtm_idx)
return -ENOMEM;
eventid = CMN_EVENT_EVENTID(event);
/* For watchpoints we need the actual XP node here */
if (type == CMN_TYPE_WP) {
type = CMN_TYPE_XP;
/* ...and we need a "real" direction */
if (eventid != CMN_WP_UP && eventid != CMN_WP_DOWN)
return -EINVAL;
/* ...but the DTM may depend on which port we're watching */
if (cmn->multi_dtm)
hw->dtm_offset = CMN_EVENT_WP_DEV_SEL(event) / 2;
hw->wp_idx = arm_cmn_alloc_wp_idx();
if (!hw->wp_idx)
return -ENOMEM;
} else if (type == CMN_TYPE_XP &&
(cmn->part == PART_CMN700 || cmn->part == PART_CMN_S3)) {
hw->wide_sel = true;
} else if (type == CMN_TYPE_RND) {
/* Secretly permit this as an alias for "rnid" events */
type = CMN_TYPE_RNI;
}
/* This is sufficiently annoying to recalculate, so cache it */
hw->filter_sel = arm_cmn_event_filter(cmn, type, eventid);
bynodeid = CMN_EVENT_BYNODEID(event);
nodeid = CMN_EVENT_NODEID(event);
hw->dn = arm_cmn_node(cmn, type);
if (!hw->dn)
return -EINVAL;
memset(hw->dtc_idx, -1, sizeof(hw->dtc_idx));
for (dn = hw->dn; dn->type == type; dn++) {
if (bynodeid && dn->id != nodeid) {
hw->dn++;
continue;
}
hw->num_dns++;
if (dn->dtc < 0)
memset(hw->dtc_idx, 0, cmn->num_dtcs);
else
hw->dtc_idx[dn->dtc] = 0;
if (bynodeid)
break;
}
if (!hw->num_dns) {
dev_dbg(cmn->dev, "invalid node 0x%x type 0x%x\n", nodeid, type);
return -EINVAL;
}
return arm_cmn_validate_group(cmn, event);
}
static void arm_cmn_event_clear(struct arm_cmn *cmn, struct perf_event *event,
int i)
{
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
enum cmn_node_type type = CMN_EVENT_TYPE(event);
while (i--) {
struct arm_cmn_dtm *dtm = &cmn->dtms[hw->dn[i].dtm] + hw->dtm_offset;
unsigned int dtm_idx = arm_cmn_get_dtm_idx(hw, i);
if (type == CMN_TYPE_WP) {
int wp_idx = arm_cmn_get_assigned_wp_idx(event, hw, i);
dtm->wp_event[wp_idx] = -1;
}
if (hw->filter_sel)
hw->dn[i].filter[hw->filter_sel].count--;
if (hw->filter_sel == SEL_EVICT_STATE_SEL)
hw->dn[i].filter[SEL_HBT_LBT_SEL].count--;
dtm->pmu_config_low &= ~CMN__PMEVCNT_PAIRED(dtm_idx);
writel_relaxed(dtm->pmu_config_low, dtm->base + CMN_DTM_PMU_CONFIG);
}
arm_cmn_clear_idx(hw);
for_each_hw_dtc_idx(hw, j, idx)
cmn->dtc[j].counters[idx] = NULL;
}
static int arm_cmn_set_event_filter(struct arm_cmn_node *dn, struct perf_event *event)
{
enum cmn_filter_select fsel = to_cmn_hw(event)->filter_sel;
bool evict_state = fsel == SEL_EVICT_STATE_SEL;
int ret = 0;
if (evict_state) {
ret = arm_cmn_set_event_sel_hi(dn, fsel, CMN_EVENT_FILTER2(event));
if (ret)
return ret;
fsel = SEL_HBT_LBT_SEL;
}
if (fsel)
ret = arm_cmn_set_event_sel_hi(dn, fsel, CMN_EVENT_FILTER(event));
if (ret && evict_state)
dn->filter[SEL_EVICT_STATE_SEL].count--;
return ret;
}
static int arm_cmn_event_add(struct perf_event *event, int flags)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
struct arm_cmn_node *dn;
enum cmn_node_type type = CMN_EVENT_TYPE(event);
unsigned int input_sel, i = 0;
if (type == CMN_TYPE_DTC) {
while (cmn->dtc[i].cycles)
if (++i == cmn->num_dtcs)
return -ENOSPC;
cmn->dtc[i].cycles = event;
hw->cc_idx = i;
if (flags & PERF_EF_START)
arm_cmn_event_start(event, 0);
return 0;
}
/* Grab the global counters first... */
for_each_hw_dtc_idx(hw, j, idx) {
if (cmn->part == PART_CMN600 && j > 0) {
idx = hw->dtc_idx[0];
} else {
idx = 0;
while (cmn->dtc[j].counters[idx])
if (++idx == CMN_DT_NUM_COUNTERS)
return -ENOSPC;
}
hw->dtc_idx[j] = idx;
}
/* ...then the local counters to feed them */
for_each_hw_dn(hw, dn, i) {
struct arm_cmn_dtm *dtm = &cmn->dtms[dn->dtm] + hw->dtm_offset;
unsigned int dtm_idx, shift, d = max_t(int, dn->dtc, 0);
u64 reg;
dtm_idx = 0;
while (dtm->pmu_config_low & CMN__PMEVCNT_PAIRED(dtm_idx))
if (++dtm_idx == CMN_DTM_NUM_COUNTERS)
goto free_dtms;
if (type == CMN_TYPE_XP) {
input_sel = CMN__PMEVCNT0_INPUT_SEL_XP + dtm_idx;
} else if (type == CMN_TYPE_WP) {
int tmp, wp_idx;
u32 cfg;
wp_idx = arm_cmn_find_free_wp_idx(dtm, event);
if (wp_idx < 0)
goto free_dtms;
cfg = arm_cmn_wp_config(event, wp_idx);
tmp = dtm->wp_event[wp_idx ^ 1];
if (tmp >= 0 && CMN_EVENT_WP_COMBINE(event) !=
CMN_EVENT_WP_COMBINE(cmn->dtc[d].counters[tmp]))
goto free_dtms;
input_sel = CMN__PMEVCNT0_INPUT_SEL_WP + wp_idx;
arm_cmn_claim_wp_idx(dtm, event, d, wp_idx, i);
writel_relaxed(cfg, dtm->base + CMN_DTM_WPn_CONFIG(wp_idx));
} else {
struct arm_cmn_nodeid nid = arm_cmn_nid(dn);
if (cmn->multi_dtm)
nid.port %= 2;
input_sel = CMN__PMEVCNT0_INPUT_SEL_DEV + dtm_idx +
(nid.port << 4) + (nid.dev << 2);
if (arm_cmn_set_event_filter(dn, event))
goto free_dtms;
}
arm_cmn_set_dtm_idx(hw, i, dtm_idx);
dtm->input_sel[dtm_idx] = input_sel;
shift = CMN__PMEVCNTn_GLOBAL_NUM_SHIFT(dtm_idx);
dtm->pmu_config_low &= ~(CMN__PMEVCNT0_GLOBAL_NUM << shift);
dtm->pmu_config_low |= FIELD_PREP(CMN__PMEVCNT0_GLOBAL_NUM, hw->dtc_idx[d]) << shift;
dtm->pmu_config_low |= CMN__PMEVCNT_PAIRED(dtm_idx);
reg = (u64)le32_to_cpu(dtm->pmu_config_high) << 32 | dtm->pmu_config_low;
writeq_relaxed(reg, dtm->base + CMN_DTM_PMU_CONFIG);
}
/* Go go go! */
arm_cmn_init_counter(event);
if (flags & PERF_EF_START)
arm_cmn_event_start(event, 0);
return 0;
free_dtms:
arm_cmn_event_clear(cmn, event, i);
return -ENOSPC;
}
static void arm_cmn_event_del(struct perf_event *event, int flags)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
enum cmn_node_type type = CMN_EVENT_TYPE(event);
arm_cmn_event_stop(event, PERF_EF_UPDATE);
if (type == CMN_TYPE_DTC)
cmn->dtc[hw->cc_idx].cycles = NULL;
else
arm_cmn_event_clear(cmn, event, hw->num_dns);
}
/*
* We stop the PMU for both add and read, to avoid skew across DTM counters.
* In theory we could use snapshots to read without stopping, but then it
* becomes a lot trickier to deal with overlow and racing against interrupts,
* plus it seems they don't work properly on some hardware anyway :(
*/
static void arm_cmn_start_txn(struct pmu *pmu, unsigned int flags)
{
arm_cmn_set_state(to_cmn(pmu), CMN_STATE_TXN);
}
static void arm_cmn_end_txn(struct pmu *pmu)
{
arm_cmn_clear_state(to_cmn(pmu), CMN_STATE_TXN);
}
static int arm_cmn_commit_txn(struct pmu *pmu)
{
arm_cmn_end_txn(pmu);
return 0;
}
static void arm_cmn_migrate(struct arm_cmn *cmn, unsigned int cpu)
{
unsigned int i;
perf_pmu_migrate_context(&cmn->pmu, cmn->cpu, cpu);
for (i = 0; i < cmn->num_dtcs; i++)
irq_set_affinity(cmn->dtc[i].irq, cpumask_of(cpu));
cmn->cpu = cpu;
}
static int arm_cmn_pmu_online_cpu(unsigned int cpu, struct hlist_node *cpuhp_node)
{
struct arm_cmn *cmn;
int node;
cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
node = dev_to_node(cmn->dev);
if (cpu_to_node(cmn->cpu) != node && cpu_to_node(cpu) == node)
arm_cmn_migrate(cmn, cpu);
return 0;
}
static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_node)
{
struct arm_cmn *cmn;
unsigned int target;
int node;
cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
if (cpu != cmn->cpu)
return 0;
node = dev_to_node(cmn->dev);
target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
if (target >= nr_cpu_ids)
target = cpumask_any_but(cpu_online_mask, cpu);
if (target < nr_cpu_ids)
arm_cmn_migrate(cmn, target);
return 0;
}
static irqreturn_t arm_cmn_handle_irq(int irq, void *dev_id)
{
struct arm_cmn_dtc *dtc = dev_id;
irqreturn_t ret = IRQ_NONE;
for (;;) {
u32 status = readl_relaxed(CMN_DT_PMOVSR(dtc));
u64 delta;
int i;
for (i = 0; i < CMN_DT_NUM_COUNTERS; i++) {
if (status & (1U << i)) {
ret = IRQ_HANDLED;
if (WARN_ON(!dtc->counters[i]))
continue;
delta = (u64)arm_cmn_read_counter(dtc, i) << 16;
local64_add(delta, &dtc->counters[i]->count);
}
}
if (status & (1U << CMN_DT_NUM_COUNTERS)) {
ret = IRQ_HANDLED;
if (dtc->cc_active && !WARN_ON(!dtc->cycles)) {
delta = arm_cmn_read_cc(dtc);
local64_add(delta, &dtc->cycles->count);
}
}
writel_relaxed(status, CMN_DT_PMOVSR_CLR(dtc));
if (!dtc->irq_friend)
return ret;
dtc += dtc->irq_friend;
}
}
/* We can reasonably accommodate DTCs of the same CMN sharing IRQs */
static int arm_cmn_init_irqs(struct arm_cmn *cmn)
{
int i, j, irq, err;
for (i = 0; i < cmn->num_dtcs; i++) {
irq = cmn->dtc[i].irq;
for (j = i; j--; ) {
if (cmn->dtc[j].irq == irq) {
cmn->dtc[j].irq_friend = i - j;
goto next;
}
}
err = devm_request_irq(cmn->dev, irq, arm_cmn_handle_irq,
IRQF_NOBALANCING | IRQF_NO_THREAD,
dev_name(cmn->dev), &cmn->dtc[i]);
if (err)
return err;
err = irq_set_affinity(irq, cpumask_of(cmn->cpu));
if (err)
return err;
next:
; /* isn't C great? */
}
return 0;
}
static void arm_cmn_init_dtm(struct arm_cmn_dtm *dtm, struct arm_cmn_node *xp, int idx)
{
int i;
dtm->base = xp->pmu_base + CMN_DTM_OFFSET(idx);
dtm->pmu_config_low = CMN_DTM_PMU_CONFIG_PMU_EN;
writeq_relaxed(dtm->pmu_config_low, dtm->base + CMN_DTM_PMU_CONFIG);
for (i = 0; i < 4; i++) {
dtm->wp_event[i] = -1;
writeq_relaxed(0, dtm->base + CMN_DTM_WPn_MASK(i));
writeq_relaxed(~0ULL, dtm->base + CMN_DTM_WPn_VAL(i));
}
}
static int arm_cmn_init_dtc(struct arm_cmn *cmn, struct arm_cmn_node *dn, int idx)
{
struct arm_cmn_dtc *dtc = cmn->dtc + idx;
const struct resource *cfg;
resource_size_t base, size;
dtc->pmu_base = dn->pmu_base;
dtc->base = dtc->pmu_base - arm_cmn_pmu_offset(cmn, dn);
dtc->irq = platform_get_irq(to_platform_device(cmn->dev), idx);
if (dtc->irq < 0)
return dtc->irq;
cfg = platform_get_resource(to_platform_device(cmn->dev), IORESOURCE_MEM, 0);
base = dtc->base - cmn->base + cfg->start;
size = cmn->part == PART_CMN600 ? SZ_16K : SZ_64K;
if (!devm_request_mem_region(cmn->dev, base, size, dev_name(cmn->dev)))
return dev_err_probe(cmn->dev, -EBUSY,
"Failed to request DTC region 0x%pa\n", &base);
writel_relaxed(CMN_DT_DTC_CTL_DT_EN, dtc->base + CMN_DT_DTC_CTL);
writel_relaxed(CMN_DT_PMCR_PMU_EN | CMN_DT_PMCR_OVFL_INTR_EN, CMN_DT_PMCR(dtc));
writeq_relaxed(0, CMN_DT_PMCCNTR(dtc));
writel_relaxed(0x1ff, CMN_DT_PMOVSR_CLR(dtc));
return 0;
}
static int arm_cmn_node_cmp(const void *a, const void *b)
{
const struct arm_cmn_node *dna = a, *dnb = b;
int cmp;
cmp = dna->type - dnb->type;
if (!cmp)
cmp = dna->logid - dnb->logid;
return cmp;
}
static int arm_cmn_init_dtcs(struct arm_cmn *cmn)
{
struct arm_cmn_node *dn, *xp;
int dtc_idx = 0;
cmn->dtc = devm_kcalloc(cmn->dev, cmn->num_dtcs, sizeof(cmn->dtc[0]), GFP_KERNEL);
if (!cmn->dtc)
return -ENOMEM;
sort(cmn->dns, cmn->num_dns, sizeof(cmn->dns[0]), arm_cmn_node_cmp, NULL);
cmn->xps = arm_cmn_node(cmn, CMN_TYPE_XP);
for (dn = cmn->dns; dn->type; dn++) {
if (dn->type == CMN_TYPE_XP)
continue;
xp = arm_cmn_node_to_xp(cmn, dn);
dn->dtc = xp->dtc;
dn->dtm = xp->dtm;
if (cmn->multi_dtm)
dn->dtm += arm_cmn_nid(dn).port / 2;
if (dn->type == CMN_TYPE_DTC) {
int err = arm_cmn_init_dtc(cmn, dn, dtc_idx++);
if (err)
return err;
}
/* To the PMU, RN-Ds don't add anything over RN-Is, so smoosh them together */
if (dn->type == CMN_TYPE_RND)
dn->type = CMN_TYPE_RNI;
/* We split the RN-I off already, so let the CCLA part match CCLA events */
if (dn->type == CMN_TYPE_CCLA_RNI)
dn->type = CMN_TYPE_CCLA;
}
arm_cmn_set_state(cmn, CMN_STATE_DISABLED);
return 0;
}
static unsigned int arm_cmn_dtc_domain(struct arm_cmn *cmn, void __iomem *xp_region)
{
int offset = CMN_DTM_UNIT_INFO;
if (cmn->part == PART_CMN650 || cmn->part == PART_CI700)
offset = CMN650_DTM_UNIT_INFO;
return FIELD_GET(CMN_DTM_UNIT_INFO_DTC_DOMAIN, readl_relaxed(xp_region + offset));
}
static unsigned int arm_cmn_graviton5_dtc_domain(u16 xp_id)
{
unsigned int x = (xp_id >> 7) & 0xf;
unsigned int y = (xp_id >> 3) & 0xf;
/*
* The unit info register reads as zero; derive the DTC domain from
* the XP's mesh coordinates over the 10x14 mesh.
*/
return (x / 5) + (y / 7) * 2;
}
static void arm_cmn_init_node_info(struct arm_cmn *cmn, u32 offset, struct arm_cmn_node *node)
{
int level;
u64 reg = readq_relaxed(cmn->base + offset + CMN_NODE_INFO);
node->type = FIELD_GET(CMN_NI_NODE_TYPE, reg);
node->id = FIELD_GET(CMN_NI_NODE_ID, reg);
node->logid = FIELD_GET(CMN_NI_LOGICAL_ID, reg);
node->pmu_base = cmn->base + offset + arm_cmn_pmu_offset(cmn, node);
if (node->type == CMN_TYPE_CFG)
level = 0;
else if (node->type == CMN_TYPE_XP)
level = 1;
else
level = 2;
dev_dbg(cmn->dev, "node%*c%#06hx%*ctype:%-#6x id:%-4hd off:%#x\n",
(level * 2) + 1, ' ', node->id, 5 - (level * 2), ' ',
node->type, node->logid, offset);
}
static enum cmn_node_type arm_cmn_subtype(enum cmn_node_type type)
{
switch (type) {
case CMN_TYPE_HNP:
return CMN_TYPE_HNI;
case CMN_TYPE_CCLA_RNI:
return CMN_TYPE_RNI;
default:
return CMN_TYPE_INVALID;
}
}
static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
{
void __iomem *cfg_region, __iomem *xp_region;
struct arm_cmn_node cfg, *dn;
struct arm_cmn_dtm *dtm;
enum cmn_model model;
enum cmn_part part;
u16 child_count, child_poff;
u64 reg;
int i, j;
size_t sz;
bool graviton5_workaround = false;
arm_cmn_init_node_info(cmn, rgn_offset, &cfg);
if (cfg.type != CMN_TYPE_CFG)
return -ENODEV;
cfg_region = cmn->base + rgn_offset;
reg = readq_relaxed(cfg_region + CMN_CFGM_PERIPH_ID_01);
part = FIELD_GET(CMN_CFGM_PID0_PART_0, reg);
part |= FIELD_GET(CMN_CFGM_PID1_PART_1, reg) << 8;
/* Graviton5 has a customised CMN-S3 which needs some fixups */
if (cmn->part == PART_GRAVITON5) {
cmn->part = PART_CMN_S3;
graviton5_workaround = true;
}
/* 600AE is close enough that it's not really worth more complexity */
if (part == PART_CMN600AE)
part = PART_CMN600;
if (cmn->part && cmn->part != part)
dev_warn(cmn->dev,
"Firmware binding mismatch: expected part number 0x%x, found 0x%x\n",
cmn->part, part);
cmn->part = part;
reg = readl_relaxed(cfg_region + CMN_CFGM_PERIPH_ID_23);
cmn->rev = FIELD_GET(CMN_CFGM_PID2_REVISION, reg);
model = arm_cmn_model(cmn);
if (!model)
dev_warn(cmn->dev, "Unknown part number: 0x%x\n", part);
/*
* With the device isolation feature, if firmware has neglected to enable
* an XP port then we risk locking up if we try to access anything behind
* it; however prior to CMN S3 r2p0 we also have no way to tell from
* Non-Secure whether any given port is disabled or not, so in that case
* the only way to win is not to play...
*/
reg = readq_relaxed(cfg_region + CMN_CFGM_INFO_GLOBAL);
if (reg & CMN_INFO_DEVICE_ISO_ENABLE && model == CMNS3R01) {
dev_err(cmn->dev, "Device isolation enabled, not continuing due to risk of lockup\n");
return -ENODEV;
}
if (model < CMNS3R2) {
cmn->multi_dtm = reg & CMN_INFO_MULTIPLE_DTM_EN;
cmn->rsp_vc_num = FIELD_GET(CMN_INFO_RSP_VC_NUM, reg);
cmn->dat_vc_num = FIELD_GET(CMN_INFO_DAT_VC_NUM, reg);
} else {
cmn->multi_dtm = reg & CMN_S3_R2_MULTIPLE_DTM_EN;
}
reg = readq_relaxed(cfg_region + CMN_CFGM_INFO_GLOBAL_1);
if (model < CMNS3R2) {
cmn->snp_vc_num = FIELD_GET(CMN_INFO_SNP_VC_NUM, reg);
cmn->req_vc_num = FIELD_GET(CMN_INFO_REQ_VC_NUM, reg);
} else {
cmn->rsp_vc_num = FIELD_GET(CMN_S3_R2_RSP_VC_NUM, reg);
cmn->dat_vc_num = FIELD_GET(CMN_S3_R2_DAT_VC_NUM, reg);
cmn->snp_vc_num = FIELD_GET(CMN_S3_R2_SNP_VC_NUM, reg);
cmn->req_vc_num = FIELD_GET(CMN_S3_R2_REQ_VC_NUM, reg);
}
reg = readq_relaxed(cfg_region + CMN_CHILD_INFO);
child_count = FIELD_GET(CMN_CI_CHILD_COUNT, reg);
child_poff = FIELD_GET(CMN_CI_CHILD_PTR_OFFSET, reg);
cmn->num_xps = child_count;
cmn->num_dns = cmn->num_xps;
/* Pass 1: visit the XPs, enumerate their children */
cfg_region += child_poff;
for (i = 0; i < cmn->num_xps; i++) {
reg = readq_relaxed(cfg_region + i * 8);
xp_region = cmn->base + (reg & CMN_CHILD_NODE_ADDR);
reg = readq_relaxed(xp_region + CMN_CHILD_INFO);
cmn->num_dns += FIELD_GET(CMN_CI_CHILD_COUNT, reg);
}
/*
* Some nodes effectively have two separate types, which we'll handle
* by creating one of each internally. For a (very) safe initial upper
* bound, account for double the number of non-XP nodes.
*/
dn = devm_kcalloc(cmn->dev, cmn->num_dns * 2 - cmn->num_xps,
sizeof(*dn), GFP_KERNEL);
if (!dn)
return -ENOMEM;
/* Initial safe upper bound on DTMs for any possible mesh layout */
i = cmn->num_xps;
if (cmn->multi_dtm)
i += cmn->num_xps + 1;
dtm = devm_kcalloc(cmn->dev, i, sizeof(*dtm), GFP_KERNEL);
if (!dtm)
return -ENOMEM;
/* Pass 2: now we can actually populate the nodes */
cmn->dns = dn;
cmn->dtms = dtm;
for (i = 0; i < cmn->num_xps; i++) {
struct arm_cmn_node *xp = dn++;
unsigned int xp_ports = 0;
reg = readq_relaxed(cfg_region + i * 8);
xp_region = cmn->base + (reg & CMN_CHILD_NODE_ADDR);
arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, xp);
/*
* Thanks to the order in which XP logical IDs seem to be
* assigned, we can handily infer the mesh X dimension by
* looking out for the XP at (0,1) without needing to know
* the exact node ID format, which we can later derive.
*/
if (xp->id == (1 << 3))
cmn->mesh_x = xp->logid;
if (cmn->part == PART_CMN600)
xp->dtc = -1;
else if (graviton5_workaround)
xp->dtc = arm_cmn_graviton5_dtc_domain(xp->id);
else
xp->dtc = arm_cmn_dtc_domain(cmn, xp_region);
xp->dtm = dtm - cmn->dtms;
arm_cmn_init_dtm(dtm++, xp, 0);
/*
* Keeping track of connected ports will let us filter out
* unnecessary XP events easily, and also infer the per-XP
* part of the node ID format.
*/
for (int p = 0; p < CMN_MAX_PORTS; p++)
if (arm_cmn_device_connect_info(cmn, xp, p))
xp_ports |= BIT(p);
if (cmn->num_xps == 1) {
xp->portid_bits = 3;
xp->deviceid_bits = 2;
} else if (xp_ports > 0x3) {
xp->portid_bits = 2;
xp->deviceid_bits = 1;
} else {
xp->portid_bits = 1;
xp->deviceid_bits = 2;
}
if (cmn->multi_dtm && (xp_ports > 0x3))
arm_cmn_init_dtm(dtm++, xp, 1);
if (cmn->multi_dtm && (xp_ports > 0xf))
arm_cmn_init_dtm(dtm++, xp, 2);
cmn->ports_used |= xp_ports;
reg = readq_relaxed(xp_region + CMN_CHILD_INFO);
child_count = FIELD_GET(CMN_CI_CHILD_COUNT, reg);
child_poff = FIELD_GET(CMN_CI_CHILD_PTR_OFFSET, reg);
for (j = 0; j < child_count; j++) {
reg = readq_relaxed(xp_region + child_poff + j * 8);
/*
* Don't even try to touch anything external, since in general
* we haven't a clue how to power up arbitrary CHI requesters,
* and none of them have standard PMU events anyway. Isolated
* nodes effectively just do not exist at all from our PoV.
*/
if (reg & (CMN_CHILD_NODE_EXTERNAL | CMN_CHILD_NODE_ISOLATED)) {
dev_dbg(cmn->dev, "ignoring external/isolated node %llx\n", reg);
continue;
}
/*
* AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus
* child count larger than the number of valid child pointers.
* A child offset of 0 can only occur on CMN-600; otherwise it
* would imply the root node being its own grandchild, which
* we can safely dismiss in general.
*/
if (reg == 0 && cmn->part != PART_CMN600) {
dev_dbg(cmn->dev, "bogus child pointer?\n");
continue;
}
arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn);
dn->portid_bits = xp->portid_bits;
dn->deviceid_bits = xp->deviceid_bits;
/*
* Logical IDs are assigned from 0 per node type, so as
* soon as we see one bigger than expected, we can assume
* there are more than we can cope with.
*/
if (dn->logid > CMN_MAX_NODES_PER_EVENT) {
dev_err(cmn->dev, "Node ID invalid for supported CMN versions: %d\n", dn->logid);
return -ENODEV;
}
/*
* We can utilise the "wasted" filter array slot to store
* the index for referencing the filter encodings later.
*/
dn->filter[SEL_NONE].val = arm_cmn_filter(dn->type, model);
switch (dn->type) {
case CMN_TYPE_DTC:
if (graviton5_workaround) {
/* Node info logical ID is zeroed; use the XP's */
dn->logid = xp->logid;
}
cmn->num_dtcs++;
dn++;
break;
/* These guys have PMU events */
case CMN_TYPE_DVM:
case CMN_TYPE_HNI:
case CMN_TYPE_HNF:
case CMN_TYPE_SBSX:
case CMN_TYPE_RNI:
case CMN_TYPE_RND:
case CMN_TYPE_MTSX:
case CMN_TYPE_CXRA:
case CMN_TYPE_CXHA:
case CMN_TYPE_CCRA:
case CMN_TYPE_CCHA:
case CMN_TYPE_HNS:
dn++;
break;
case CMN_TYPE_CCLA:
dn->pmu_base += CMN_CCLA_PMU_EVENT_SEL;
dn++;
break;
/* Nothing to see here */
case CMN_TYPE_MPAM_S:
case CMN_TYPE_MPAM_NS:
case CMN_TYPE_RNSAM:
case CMN_TYPE_CXLA:
case CMN_TYPE_HNS_MPAM_S:
case CMN_TYPE_HNS_MPAM_NS:
case CMN_TYPE_APB:
break;
/*
* Split "optimised" combination nodes into separate
* types for the different event sets. Offsetting the
* base address lets us handle the second pmu_event_sel
* register via the normal mechanism later.
*/
case CMN_TYPE_HNP:
case CMN_TYPE_CCLA_RNI:
dn[1] = dn[0];
dn[0].pmu_base += CMN_CCLA_PMU_EVENT_SEL;
dn[1].type = arm_cmn_subtype(dn->type);
dn += 2;
break;
/* Something has gone horribly wrong */
default:
dev_err(cmn->dev, "Device node type invalid for supported CMN versions: 0x%x\n", dn->type);
return -ENODEV;
}
}
}
/* Correct for any nodes we added or skipped */
cmn->num_dns = dn - cmn->dns;
/* Cheeky +1 to help terminate pointer-based iteration later */
sz = (void *)(dn + 1) - (void *)cmn->dns;
dn = devm_krealloc(cmn->dev, cmn->dns, sz, GFP_KERNEL);
if (dn)
cmn->dns = dn;
sz = (void *)dtm - (void *)cmn->dtms;
dtm = devm_krealloc(cmn->dev, cmn->dtms, sz, GFP_KERNEL);
if (dtm)
cmn->dtms = dtm;
/*
* If mesh_x wasn't set during discovery then we never saw
* an XP at (0,1), thus we must have an Nx1 configuration.
*/
if (!cmn->mesh_x)
cmn->mesh_x = cmn->num_xps;
cmn->mesh_y = cmn->num_xps / cmn->mesh_x;
if (max(cmn->mesh_x, cmn->mesh_y) > CMN_MAX_DIMENSION) {
dev_err(cmn->dev, "Mesh size invalid for supported CMN versions: %dx%d\n", cmn->mesh_x, cmn->mesh_y);
return -ENODEV;
}
/* 1x1 config plays havoc with XP event encodings */
if (cmn->num_xps == 1)
dev_warn(cmn->dev, "1x1 config not fully supported, translate XP events manually\n");
dev_dbg(cmn->dev, "periph_id part 0x%03x revision %d\n", cmn->part, cmn->rev);
reg = cmn->ports_used;
dev_dbg(cmn->dev, "mesh %dx%d, ID width %d, ports %6pbl%s\n",
cmn->mesh_x, cmn->mesh_y, arm_cmn_xyidbits(cmn), &reg,
cmn->multi_dtm ? ", multi-DTM" : "");
return 0;
}
static int arm_cmn_get_root(struct arm_cmn *cmn, const struct resource *cfg)
{
const struct device_node *np = cmn->dev->of_node;
const struct resource *root;
u32 rootnode;
if (cmn->part != PART_CMN600)
return 0;
if (np)
return of_property_read_u32(np, "arm,root-node", &rootnode) ?: rootnode;
root = platform_get_resource(to_platform_device(cmn->dev), IORESOURCE_MEM, 1);
return root ? root->start - cfg->start : -EINVAL;
}
static int arm_cmn_probe(struct platform_device *pdev)
{
struct arm_cmn *cmn;
const struct resource *cfg;
const char *name;
static atomic_t id;
int err, rootnode, this_id;
cmn = devm_kzalloc(&pdev->dev, sizeof(*cmn), GFP_KERNEL);
if (!cmn)
return -ENOMEM;
cmn->dev = &pdev->dev;
cmn->part = (unsigned long)device_get_match_data(cmn->dev);
cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
platform_set_drvdata(pdev, cmn);
cfg = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!cfg)
return -EINVAL;
/* Map the whole region now, claim the DTCs once we've found them */
cmn->base = devm_ioremap(cmn->dev, cfg->start, resource_size(cfg));
if (!cmn->base)
return -ENOMEM;
rootnode = arm_cmn_get_root(cmn, cfg);
if (rootnode < 0)
return rootnode;
err = arm_cmn_discover(cmn, rootnode);
if (err)
return err;
err = arm_cmn_init_dtcs(cmn);
if (err)
return err;
err = arm_cmn_init_irqs(cmn);
if (err)
return err;
cmn->pmu = (struct pmu) {
.module = THIS_MODULE,
.parent = cmn->dev,
.attr_groups = arm_cmn_attr_groups,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
.task_ctx_nr = perf_invalid_context,
.pmu_enable = arm_cmn_pmu_enable,
.pmu_disable = arm_cmn_pmu_disable,
.event_init = arm_cmn_event_init,
.add = arm_cmn_event_add,
.del = arm_cmn_event_del,
.start = arm_cmn_event_start,
.stop = arm_cmn_event_stop,
.read = arm_cmn_event_read,
.start_txn = arm_cmn_start_txn,
.commit_txn = arm_cmn_commit_txn,
.cancel_txn = arm_cmn_end_txn,
};
this_id = atomic_fetch_inc(&id);
name = devm_kasprintf(cmn->dev, GFP_KERNEL, "arm_cmn_%d", this_id);
if (!name)
return -ENOMEM;
err = cpuhp_state_add_instance(arm_cmn_hp_state, &cmn->cpuhp_node);
if (err)
return err;
err = perf_pmu_register(&cmn->pmu, name, -1);
if (err)
cpuhp_state_remove_instance_nocalls(arm_cmn_hp_state, &cmn->cpuhp_node);
else
arm_cmn_debugfs_init(cmn, this_id);
return err;
}
static void arm_cmn_remove(struct platform_device *pdev)
{
struct arm_cmn *cmn = platform_get_drvdata(pdev);
writel_relaxed(0, cmn->dtc[0].base + CMN_DT_DTC_CTL);
perf_pmu_unregister(&cmn->pmu);
cpuhp_state_remove_instance_nocalls(arm_cmn_hp_state, &cmn->cpuhp_node);
debugfs_remove(cmn->debug);
}
#ifdef CONFIG_OF
static const struct of_device_id arm_cmn_of_match[] = {
{ .compatible = "arm,cmn-600", .data = (void *)PART_CMN600 },
{ .compatible = "arm,cmn-650" },
{ .compatible = "arm,cmn-700" },
{ .compatible = "arm,cmn-s3" },
{ .compatible = "arm,ci-700" },
{}
};
MODULE_DEVICE_TABLE(of, arm_cmn_of_match);
#endif
#ifdef CONFIG_ACPI
static const struct acpi_device_id arm_cmn_acpi_match[] = {
{ "ARMHC600", PART_CMN600 },
{ "ARMHC650" },
{ "ARMHC700" },
{ "ARMHC003" },
{ "AMZN0070", PART_GRAVITON5 },
{}
};
MODULE_DEVICE_TABLE(acpi, arm_cmn_acpi_match);
#endif
static struct platform_driver arm_cmn_driver = {
.driver = {
.name = "arm-cmn",
.of_match_table = of_match_ptr(arm_cmn_of_match),
.acpi_match_table = ACPI_PTR(arm_cmn_acpi_match),
.suppress_bind_attrs = true,
},
.probe = arm_cmn_probe,
.remove = arm_cmn_remove,
};
static int __init arm_cmn_init(void)
{
int ret;
ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
"perf/arm/cmn:online",
arm_cmn_pmu_online_cpu,
arm_cmn_pmu_offline_cpu);
if (ret < 0)
return ret;
arm_cmn_hp_state = ret;
arm_cmn_debugfs = debugfs_create_dir("arm-cmn", NULL);
ret = platform_driver_register(&arm_cmn_driver);
if (ret) {
cpuhp_remove_multi_state(arm_cmn_hp_state);
debugfs_remove(arm_cmn_debugfs);
}
return ret;
}
static void __exit arm_cmn_exit(void)
{
platform_driver_unregister(&arm_cmn_driver);
cpuhp_remove_multi_state(arm_cmn_hp_state);
debugfs_remove(arm_cmn_debugfs);
}
module_init(arm_cmn_init);
module_exit(arm_cmn_exit);
MODULE_AUTHOR("Robin Murphy <robin.murphy@arm.com>");
MODULE_DESCRIPTION("Arm CMN/CI interconnect PMU driver");
MODULE_LICENSE("GPL v2");