summaryrefslogtreecommitdiff
path: root/arch/powerpc/perf
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/perf')
-rw-r--r--arch/powerpc/perf/callchain.c4
-rw-r--r--arch/powerpc/perf/core-book3s.c126
-rw-r--r--arch/powerpc/perf/core-fsl-emb.c16
-rw-r--r--arch/powerpc/perf/hv-24x7-catalog.h25
-rw-r--r--arch/powerpc/perf/hv-24x7-domains.h28
-rw-r--r--arch/powerpc/perf/hv-24x7.c1107
-rw-r--r--arch/powerpc/perf/hv-24x7.h20
-rw-r--r--arch/powerpc/perf/hv-common.c10
-rw-r--r--arch/powerpc/perf/hv-common.h10
-rw-r--r--arch/powerpc/perf/hv-gpci-requests.h261
-rw-r--r--arch/powerpc/perf/hv-gpci.c35
-rw-r--r--arch/powerpc/perf/hv-gpci.h37
-rw-r--r--arch/powerpc/perf/mpc7450-pmu.c5
-rw-r--r--arch/powerpc/perf/power4-pmu.c2
-rw-r--r--arch/powerpc/perf/power5+-pmu.c2
-rw-r--r--arch/powerpc/perf/power5-pmu.c2
-rw-r--r--arch/powerpc/perf/power6-pmu.c2
-rw-r--r--arch/powerpc/perf/power7-pmu.c2
-rw-r--r--arch/powerpc/perf/power8-pmu.c27
-rw-r--r--arch/powerpc/perf/ppc970-pmu.c2
-rw-r--r--arch/powerpc/perf/req-gen/_begin.h13
-rw-r--r--arch/powerpc/perf/req-gen/_clear.h5
-rw-r--r--arch/powerpc/perf/req-gen/_end.h4
-rw-r--r--arch/powerpc/perf/req-gen/_request-begin.h15
-rw-r--r--arch/powerpc/perf/req-gen/_request-end.h8
-rw-r--r--arch/powerpc/perf/req-gen/perf.h155
26 files changed, 1650 insertions, 273 deletions
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e780748b..ead55351b254 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
return 0; /* must be 16-byte aligned */
if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
return 0;
- if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+ if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
return 1;
/*
* sp could decrease when we jump off an interrupt stack
@@ -243,7 +243,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
- for (;;) {
+ while (entry->nr < PERF_MAX_STACK_DEPTH) {
fp = (unsigned long __user *) sp;
if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
return;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index fe52db2eea6a..12b638425bb9 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -36,7 +36,12 @@ struct cpu_hw_events {
struct perf_event *event[MAX_HWEVENTS];
u64 events[MAX_HWEVENTS];
unsigned int flags[MAX_HWEVENTS];
- unsigned long mmcr[3];
+ /*
+ * The order of the MMCR array is:
+ * - 64-bit, MMCR0, MMCR1, MMCRA, MMCR2
+ * - 32-bit, MMCR0, MMCR1, MMCR2
+ */
+ unsigned long mmcr[4];
struct perf_event *limited_counter[MAX_LIMITED_HWCOUNTERS];
u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS];
u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
@@ -54,9 +59,9 @@ struct cpu_hw_events {
struct perf_branch_entry bhrb_entries[BHRB_MAX_ENTRIES];
};
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
-struct power_pmu *ppmu;
+static struct power_pmu *ppmu;
/*
* Normally, to ignore kernel events we set the FCS (freeze counters
@@ -112,14 +117,14 @@ static bool is_ebb_event(struct perf_event *event) { return false; }
static int ebb_event_check(struct perf_event *event) { return 0; }
static void ebb_event_add(struct perf_event *event) { }
static void ebb_switch_out(unsigned long mmcr0) { }
-static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
+static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
{
- return mmcr0;
+ return cpuhw->mmcr[0];
}
static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-void power_pmu_flush_branch_stack(void) {}
+static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
static void pmao_restore_workaround(bool ebb) { }
#endif /* CONFIG_PPC32 */
@@ -334,7 +339,7 @@ static void power_pmu_bhrb_reset(void)
static void power_pmu_bhrb_enable(struct perf_event *event)
{
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
if (!ppmu->bhrb_nr)
return;
@@ -345,17 +350,19 @@ static void power_pmu_bhrb_enable(struct perf_event *event)
cpuhw->bhrb_context = event->ctx;
}
cpuhw->bhrb_users++;
+ perf_sched_cb_inc(event->ctx->pmu);
}
static void power_pmu_bhrb_disable(struct perf_event *event)
{
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
if (!ppmu->bhrb_nr)
return;
cpuhw->bhrb_users--;
WARN_ON_ONCE(cpuhw->bhrb_users < 0);
+ perf_sched_cb_dec(event->ctx->pmu);
if (!cpuhw->disabled && !cpuhw->bhrb_users) {
/* BHRB cannot be turned off when other
@@ -370,9 +377,12 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
/* Called from ctxsw to prevent one process's branch entries to
* mingle with the other process's entries during context switch.
*/
-void power_pmu_flush_branch_stack(void)
+static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
{
- if (ppmu->bhrb_nr)
+ if (!ppmu->bhrb_nr)
+ return;
+
+ if (sched_in)
power_pmu_bhrb_reset();
}
/* Calculate the to address for a branch */
@@ -403,7 +413,7 @@ static __u64 power_pmu_bhrb_to(u64 addr)
}
/* Processing BHRB entries */
-void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
{
u64 val;
u64 addr;
@@ -542,8 +552,10 @@ static void ebb_switch_out(unsigned long mmcr0)
current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK;
}
-static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
+static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
{
+ unsigned long mmcr0 = cpuhw->mmcr[0];
+
if (!ebb)
goto out;
@@ -568,7 +580,15 @@ static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
mtspr(SPRN_SIAR, current->thread.siar);
mtspr(SPRN_SIER, current->thread.sier);
mtspr(SPRN_SDAR, current->thread.sdar);
- mtspr(SPRN_MMCR2, current->thread.mmcr2);
+
+ /*
+ * Merge the kernel & user values of MMCR2. The semantics we implement
+ * are that the user MMCR2 can set bits, ie. cause counters to freeze,
+ * but not clear bits. If a task wants to be able to clear bits, ie.
+ * unfreeze counters, it should not set exclude_xxx in its events and
+ * instead manage the MMCR2 entirely by itself.
+ */
+ mtspr(SPRN_MMCR2, cpuhw->mmcr[3] | current->thread.mmcr2);
out:
return mmcr0;
}
@@ -915,6 +935,14 @@ static int check_excludes(struct perf_event **ctrs, unsigned int cflags[],
int i, n, first;
struct perf_event *event;
+ /*
+ * If the PMU we're on supports per event exclude settings then we
+ * don't need to do any of this logic. NB. This assumes no PMU has both
+ * per event exclude and limited PMCs.
+ */
+ if (ppmu->flags & PPMU_ARCH_207S)
+ return 0;
+
n = n_prev + n_new;
if (n <= 1)
return 0;
@@ -1121,7 +1149,7 @@ static void power_pmu_disable(struct pmu *pmu)
if (!ppmu)
return;
local_irq_save(flags);
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
if (!cpuhw->disabled) {
/*
@@ -1188,7 +1216,7 @@ static void power_pmu_enable(struct pmu *pmu)
return;
local_irq_save(flags);
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
if (!cpuhw->disabled)
goto out;
@@ -1219,28 +1247,31 @@ static void power_pmu_enable(struct pmu *pmu)
}
/*
- * Compute MMCR* values for the new set of events
+ * Clear all MMCR settings and recompute them for the new set of events.
*/
+ memset(cpuhw->mmcr, 0, sizeof(cpuhw->mmcr));
+
if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_events, hwc_index,
- cpuhw->mmcr)) {
+ cpuhw->mmcr, cpuhw->event)) {
/* shouldn't ever get here */
printk(KERN_ERR "oops compute_mmcr failed\n");
goto out;
}
- /*
- * Add in MMCR0 freeze bits corresponding to the
- * attr.exclude_* bits for the first event.
- * We have already checked that all events have the
- * same values for these bits as the first event.
- */
- event = cpuhw->event[0];
- if (event->attr.exclude_user)
- cpuhw->mmcr[0] |= MMCR0_FCP;
- if (event->attr.exclude_kernel)
- cpuhw->mmcr[0] |= freeze_events_kernel;
- if (event->attr.exclude_hv)
- cpuhw->mmcr[0] |= MMCR0_FCHV;
+ if (!(ppmu->flags & PPMU_ARCH_207S)) {
+ /*
+ * Add in MMCR0 freeze bits corresponding to the attr.exclude_*
+ * bits for the first event. We have already checked that all
+ * events have the same value for these bits as the first event.
+ */
+ event = cpuhw->event[0];
+ if (event->attr.exclude_user)
+ cpuhw->mmcr[0] |= MMCR0_FCP;
+ if (event->attr.exclude_kernel)
+ cpuhw->mmcr[0] |= freeze_events_kernel;
+ if (event->attr.exclude_hv)
+ cpuhw->mmcr[0] |= MMCR0_FCHV;
+ }
/*
* Write the new configuration to MMCR* with the freeze
@@ -1252,6 +1283,8 @@ static void power_pmu_enable(struct pmu *pmu)
mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE))
| MMCR0_FC);
+ if (ppmu->flags & PPMU_ARCH_207S)
+ mtspr(SPRN_MMCR2, cpuhw->mmcr[3]);
/*
* Read off any pre-existing events that need to move
@@ -1307,10 +1340,7 @@ static void power_pmu_enable(struct pmu *pmu)
out_enable:
pmao_restore_workaround(ebb);
- if (ppmu->flags & PPMU_ARCH_207S)
- mtspr(SPRN_MMCR2, 0);
-
- mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
+ mmcr0 = ebb_switch_in(ebb, cpuhw);
mb();
if (cpuhw->bhrb_users)
@@ -1378,7 +1408,7 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
* Add the event to the list (if there is room)
* and check whether the total set is still feasible.
*/
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
n0 = cpuhw->n_events;
if (n0 >= ppmu->n_counter)
goto out;
@@ -1444,7 +1474,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags)
power_pmu_read(event);
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
for (i = 0; i < cpuhw->n_events; ++i) {
if (event == cpuhw->event[i]) {
while (++i < cpuhw->n_events) {
@@ -1548,9 +1578,9 @@ static void power_pmu_stop(struct perf_event *event, int ef_flags)
* Set the flag to make pmu::enable() not perform the
* schedulability test, it will be performed at commit time
*/
-void power_pmu_start_txn(struct pmu *pmu)
+static void power_pmu_start_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
perf_pmu_disable(pmu);
cpuhw->group_flag |= PERF_EVENT_TXN;
@@ -1562,9 +1592,9 @@ void power_pmu_start_txn(struct pmu *pmu)
* Clear the flag and pmu::enable() will perform the
* schedulability test.
*/
-void power_pmu_cancel_txn(struct pmu *pmu)
+static void power_pmu_cancel_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
cpuhw->group_flag &= ~PERF_EVENT_TXN;
perf_pmu_enable(pmu);
@@ -1575,14 +1605,14 @@ void power_pmu_cancel_txn(struct pmu *pmu)
* Perform the group schedulability test as a whole
* Return 0 if success
*/
-int power_pmu_commit_txn(struct pmu *pmu)
+static int power_pmu_commit_txn(struct pmu *pmu)
{
struct cpu_hw_events *cpuhw;
long i, n;
if (!ppmu)
return -EAGAIN;
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
n = cpuhw->n_events;
if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
return -EAGAIN;
@@ -1807,8 +1837,10 @@ static int power_pmu_event_init(struct perf_event *event)
cpuhw->bhrb_filter = ppmu->bhrb_filter_map(
event->attr.branch_sample_type);
- if(cpuhw->bhrb_filter == -1)
+ if (cpuhw->bhrb_filter == -1) {
+ put_cpu_var(cpu_hw_events);
return -EOPNOTSUPP;
+ }
}
put_cpu_var(cpu_hw_events);
@@ -1863,7 +1895,7 @@ ssize_t power_events_sysfs_show(struct device *dev,
return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
}
-struct pmu power_pmu = {
+static struct pmu power_pmu = {
.pmu_enable = power_pmu_enable,
.pmu_disable = power_pmu_disable,
.event_init = power_pmu_event_init,
@@ -1876,7 +1908,7 @@ struct pmu power_pmu = {
.cancel_txn = power_pmu_cancel_txn,
.commit_txn = power_pmu_commit_txn,
.event_idx = power_pmu_event_idx,
- .flush_branch_stack = power_pmu_flush_branch_stack,
+ .sched_task = power_pmu_sched_task,
};
/*
@@ -1939,7 +1971,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
struct cpu_hw_events *cpuhw;
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
power_pmu_bhrb_read(cpuhw);
data.br_stack = &cpuhw->bhrb_stack;
}
@@ -2012,7 +2044,7 @@ static bool pmc_overflow(unsigned long val)
static void perf_event_interrupt(struct pt_regs *regs)
{
int i, j;
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
struct perf_event *event;
unsigned long val[8];
int found, active;
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index d35ae52c69dc..5d747b4cb8ee 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -210,7 +210,7 @@ static void fsl_emb_pmu_disable(struct pmu *pmu)
unsigned long flags;
local_irq_save(flags);
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
if (!cpuhw->disabled) {
cpuhw->disabled = 1;
@@ -249,7 +249,7 @@ static void fsl_emb_pmu_enable(struct pmu *pmu)
unsigned long flags;
local_irq_save(flags);
- cpuhw = &__get_cpu_var(cpu_hw_events);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
if (!cpuhw->disabled)
goto out;
@@ -330,9 +330,11 @@ static int fsl_emb_pmu_add(struct perf_event *event, int flags)
}
local64_set(&event->hw.prev_count, val);
- if (!(flags & PERF_EF_START)) {
+ if (unlikely(!(flags & PERF_EF_START))) {
event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
val = 0;
+ } else {
+ event->hw.state &= ~(PERF_HES_STOPPED | PERF_HES_UPTODATE);
}
write_pmc(i, val);
@@ -389,6 +391,7 @@ static void fsl_emb_pmu_del(struct perf_event *event, int flags)
static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
{
unsigned long flags;
+ unsigned long val;
s64 left;
if (event->hw.idx < 0 || !event->hw.sample_period)
@@ -405,7 +408,10 @@ static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
event->hw.state = 0;
left = local64_read(&event->hw.period_left);
- write_pmc(event->hw.idx, left);
+ val = 0;
+ if (left < 0x80000000L)
+ val = 0x80000000L - left;
+ write_pmc(event->hw.idx, val);
perf_event_update_userpage(event);
perf_pmu_enable(event->pmu);
@@ -653,7 +659,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
static void perf_event_interrupt(struct pt_regs *regs)
{
int i;
- struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
struct perf_event *event;
unsigned long val;
int found = 0;
diff --git a/arch/powerpc/perf/hv-24x7-catalog.h b/arch/powerpc/perf/hv-24x7-catalog.h
index 21b19dd86d9c..69e2e1faf902 100644
--- a/arch/powerpc/perf/hv-24x7-catalog.h
+++ b/arch/powerpc/perf/hv-24x7-catalog.h
@@ -30,4 +30,29 @@ struct hv_24x7_catalog_page_0 {
__u8 reserved6[2];
} __packed;
+struct hv_24x7_event_data {
+ __be16 length; /* in bytes, must be a multiple of 16 */
+ __u8 reserved1[2];
+ __u8 domain; /* Chip = 1, Core = 2 */
+ __u8 reserved2[1];
+ __be16 event_group_record_offs; /* in bytes, must be 8 byte aligned */
+ __be16 event_group_record_len; /* in bytes */
+
+ /* in bytes, offset from event_group_record */
+ __be16 event_counter_offs;
+
+ /* verified_state, unverified_state, caveat_state, broken_state, ... */
+ __be32 flags;
+
+ __be16 primary_group_ix;
+ __be16 group_count;
+ __be16 event_name_len;
+ __u8 remainder[];
+ /* __u8 event_name[event_name_len - 2]; */
+ /* __be16 event_description_len; */
+ /* __u8 event_desc[event_description_len - 2]; */
+ /* __be16 detailed_desc_len; */
+ /* __u8 detailed_desc[detailed_desc_len - 2]; */
+} __packed;
+
#endif
diff --git a/arch/powerpc/perf/hv-24x7-domains.h b/arch/powerpc/perf/hv-24x7-domains.h
new file mode 100644
index 000000000000..49c1efd50045
--- /dev/null
+++ b/arch/powerpc/perf/hv-24x7-domains.h
@@ -0,0 +1,28 @@
+
+/*
+ * DOMAIN(name, num, index_kind, is_physical)
+ *
+ * @name: An all caps token, suitable for use in generating an enum
+ * member and appending to an event name in sysfs.
+ *
+ * @num: The number corresponding to the domain as given in
+ * documentation. We assume the catalog domain and the hcall
+ * domain have the same numbering (so far they do), but this
+ * may need to be changed in the future.
+ *
+ * @index_kind: A stringifiable token describing the meaning of the index
+ * within the given domain. Must fit the parsing rules of the
+ * perf sysfs api.
+ *
+ * @is_physical: True if the domain is physical, false otherwise (if virtual).
+ *
+ * Note: The terms PHYS_CHIP, PHYS_CORE, VCPU correspond to physical chip,
+ * physical core and virtual processor in 24x7 Counters specifications.
+ */
+
+DOMAIN(PHYS_CHIP, 0x01, chip, true)
+DOMAIN(PHYS_CORE, 0x02, core, true)
+DOMAIN(VCPU_HOME_CORE, 0x03, vcpu, false)
+DOMAIN(VCPU_HOME_CHIP, 0x04, vcpu, false)
+DOMAIN(VCPU_HOME_NODE, 0x05, vcpu, false)
+DOMAIN(VCPU_REMOTE_NODE, 0x06, vcpu, false)
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index e0766b82e165..ec2eb20631d1 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -13,16 +13,66 @@
#define pr_fmt(fmt) "hv-24x7: " fmt
#include <linux/perf_event.h>
+#include <linux/rbtree.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
#include <asm/firmware.h>
#include <asm/hvcall.h>
#include <asm/io.h>
+#include <linux/byteorder/generic.h>
#include "hv-24x7.h"
#include "hv-24x7-catalog.h"
#include "hv-common.h"
+static const char *event_domain_suffix(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ return "__" #n;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ default:
+ WARN(1, "unknown domain %d\n", domain);
+ return "__UNKNOWN_DOMAIN_SUFFIX";
+ }
+}
+
+static bool domain_is_valid(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ /* fall through */
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool is_physical_domain(unsigned domain)
+{
+ switch (domain) {
+#define DOMAIN(n, v, x, c) \
+ case HV_PERF_DOMAIN_##n: \
+ return c;
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+ default:
+ return false;
+ }
+}
+
+static bool catalog_entry_domain_is_valid(unsigned domain)
+{
+ return is_physical_domain(domain);
+}
+
/*
* TODO: Merging events:
* - Think of the hcall as an interface to a 4d array of counters:
@@ -44,13 +94,14 @@
/*
* Example usage:
- * perf stat -e 'hv_24x7/domain=2,offset=8,starting_index=0,lpar=0xffffffff/'
+ * perf stat -e 'hv_24x7/domain=2,offset=8,vcpu=0,lpar=0xffffffff/'
*/
/* u3 0-6, one of HV_24X7_PERF_DOMAIN */
EVENT_DEFINE_RANGE_FORMAT(domain, config, 0, 3);
/* u16 */
-EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 16, 31);
+EVENT_DEFINE_RANGE_FORMAT(core, config, 16, 31);
+EVENT_DEFINE_RANGE_FORMAT(vcpu, config, 16, 31);
/* u32, see "data_offset" */
EVENT_DEFINE_RANGE_FORMAT(offset, config, 32, 63);
/* u16 */
@@ -63,7 +114,8 @@ EVENT_DEFINE_RANGE(reserved3, config2, 0, 63);
static struct attribute *format_attrs[] = {
&format_attr_domain.attr,
&format_attr_offset.attr,
- &format_attr_starting_index.attr,
+ &format_attr_core.attr,
+ &format_attr_vcpu.attr,
&format_attr_lpar.attr,
NULL,
};
@@ -73,86 +125,124 @@ static struct attribute_group format_group = {
.attrs = format_attrs,
};
+static struct attribute_group event_group = {
+ .name = "events",
+ /* .attrs is set in init */
+};
+
+static struct attribute_group event_desc_group = {
+ .name = "event_descs",
+ /* .attrs is set in init */
+};
+
+static struct attribute_group event_long_desc_group = {
+ .name = "event_long_descs",
+ /* .attrs is set in init */
+};
+
static struct kmem_cache *hv_page_cache;
/*
- * read_offset_data - copy data from one buffer to another while treating the
- * source buffer as a small view on the total avaliable
- * source data.
- *
- * @dest: buffer to copy into
- * @dest_len: length of @dest in bytes
- * @requested_offset: the offset within the source data we want. Must be > 0
- * @src: buffer to copy data from
- * @src_len: length of @src in bytes
- * @source_offset: the offset in the sorce data that (src,src_len) refers to.
- * Must be > 0
- *
- * returns the number of bytes copied.
- *
- * The following ascii art shows the various buffer possitioning we need to
- * handle, assigns some arbitrary varibles to points on the buffer, and then
- * shows how we fiddle with those values to get things we care about (copy
- * start in src and copy len)
- *
- * s = @src buffer
- * d = @dest buffer
- * '.' areas in d are written to.
- *
- * u
- * x w v z
- * d |.........|
- * s |----------------------|
- *
- * u
- * x w z v
- * d |........------|
- * s |------------------|
- *
- * x w u,z,v
- * d |........|
- * s |------------------|
- *
- * x,w u,v,z
- * d |..................|
- * s |------------------|
- *
- * x u
- * w v z
- * d |........|
- * s |------------------|
- *
- * x z w v
- * d |------|
- * s |------|
- *
- * x = source_offset
- * w = requested_offset
- * z = source_offset + src_len
- * v = requested_offset + dest_len
+ * request_buffer and result_buffer are not required to be 4k aligned,
+ * but are not allowed to cross any 4k boundary. Aligning them to 4k is
+ * the simplest way to ensure that.
+ */
+#define H24x7_DATA_BUFFER_SIZE 4096
+DEFINE_PER_CPU(char, hv_24x7_reqb[H24x7_DATA_BUFFER_SIZE]) __aligned(4096);
+DEFINE_PER_CPU(char, hv_24x7_resb[H24x7_DATA_BUFFER_SIZE]) __aligned(4096);
+
+static char *event_name(struct hv_24x7_event_data *ev, int *len)
+{
+ *len = be16_to_cpu(ev->event_name_len) - 2;
+ return (char *)ev->remainder;
+}
+
+static char *event_desc(struct hv_24x7_event_data *ev, int *len)
+{
+ unsigned nl = be16_to_cpu(ev->event_name_len);
+ __be16 *desc_len = (__be16 *)(ev->remainder + nl - 2);
+
+ *len = be16_to_cpu(*desc_len) - 2;
+ return (char *)ev->remainder + nl;
+}
+
+static char *event_long_desc(struct hv_24x7_event_data *ev, int *len)
+{
+ unsigned nl = be16_to_cpu(ev->event_name_len);
+ __be16 *desc_len_ = (__be16 *)(ev->remainder + nl - 2);
+ unsigned desc_len = be16_to_cpu(*desc_len_);
+ __be16 *long_desc_len = (__be16 *)(ev->remainder + nl + desc_len - 2);
+
+ *len = be16_to_cpu(*long_desc_len) - 2;
+ return (char *)ev->remainder + nl + desc_len;
+}
+
+static bool event_fixed_portion_is_within(struct hv_24x7_event_data *ev,
+ void *end)
+{
+ void *start = ev;
+
+ return (start + offsetof(struct hv_24x7_event_data, remainder)) < end;
+}
+
+/*
+ * Things we don't check:
+ * - padding for desc, name, and long/detailed desc is required to be '\0'
+ * bytes.
*
- * w_offset_in_s = w - x = requested_offset - source_offset
- * z_offset_in_s = z - x = src_len
- * v_offset_in_s = v - x = request_offset + dest_len - src_len
+ * Return NULL if we pass end,
+ * Otherwise return the address of the byte just following the event.
*/
-static ssize_t read_offset_data(void *dest, size_t dest_len,
- loff_t requested_offset, void *src,
- size_t src_len, loff_t source_offset)
+static void *event_end(struct hv_24x7_event_data *ev, void *end)
{
- size_t w_offset_in_s = requested_offset - source_offset;
- size_t z_offset_in_s = src_len;
- size_t v_offset_in_s = requested_offset + dest_len - src_len;
- size_t u_offset_in_s = min(z_offset_in_s, v_offset_in_s);
- size_t copy_len = u_offset_in_s - w_offset_in_s;
+ void *start = ev;
+ __be16 *dl_, *ldl_;
+ unsigned dl, ldl;
+ unsigned nl = be16_to_cpu(ev->event_name_len);
+
+ if (nl < 2) {
+ pr_debug("%s: name length too short: %d", __func__, nl);
+ return NULL;
+ }
- if (requested_offset < 0 || source_offset < 0)
- return -EINVAL;
+ if (start + nl > end) {
+ pr_debug("%s: start=%p + nl=%u > end=%p",
+ __func__, start, nl, end);
+ return NULL;
+ }
- if (z_offset_in_s <= w_offset_in_s)
- return 0;
+ dl_ = (__be16 *)(ev->remainder + nl - 2);
+ if (!IS_ALIGNED((uintptr_t)dl_, 2))
+ pr_warn("desc len not aligned %p", dl_);
+ dl = be16_to_cpu(*dl_);
+ if (dl < 2) {
+ pr_debug("%s: desc len too short: %d", __func__, dl);
+ return NULL;
+ }
- memcpy(dest, src + w_offset_in_s, copy_len);
- return copy_len;
+ if (start + nl + dl > end) {
+ pr_debug("%s: (start=%p + nl=%u + dl=%u)=%p > end=%p",
+ __func__, start, nl, dl, start + nl + dl, end);
+ return NULL;
+ }
+
+ ldl_ = (__be16 *)(ev->remainder + nl + dl - 2);
+ if (!IS_ALIGNED((uintptr_t)ldl_, 2))
+ pr_warn("long desc len not aligned %p", ldl_);
+ ldl = be16_to_cpu(*ldl_);
+ if (ldl < 2) {
+ pr_debug("%s: long desc len too short (ldl=%u)",
+ __func__, ldl);
+ return NULL;
+ }
+
+ if (start + nl + dl + ldl > end) {
+ pr_debug("%s: start=%p + nl=%u + dl=%u + ldl=%u > end=%p",
+ __func__, start, nl, dl, ldl, end);
+ return NULL;
+ }
+
+ return start + nl + dl + ldl;
}
static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096,
@@ -160,14 +250,12 @@ static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096,
unsigned long index)
{
pr_devel("h_get_24x7_catalog_page(0x%lx, %lu, %lu)",
- phys_4096,
- version,
- index);
+ phys_4096, version, index);
+
WARN_ON(!IS_ALIGNED(phys_4096, 4096));
+
return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE,
- phys_4096,
- version,
- index);
+ phys_4096, version, index);
}
static unsigned long h_get_24x7_catalog_page(char page[],
@@ -177,17 +265,642 @@ static unsigned long h_get_24x7_catalog_page(char page[],
version, index);
}
+static unsigned core_domains[] = {
+ HV_PERF_DOMAIN_PHYS_CORE,
+ HV_PERF_DOMAIN_VCPU_HOME_CORE,
+ HV_PERF_DOMAIN_VCPU_HOME_CHIP,
+ HV_PERF_DOMAIN_VCPU_HOME_NODE,
+ HV_PERF_DOMAIN_VCPU_REMOTE_NODE,
+};
+/* chip event data always yeilds a single event, core yeilds multiple */
+#define MAX_EVENTS_PER_EVENT_DATA ARRAY_SIZE(core_domains)
+
+static char *event_fmt(struct hv_24x7_event_data *event, unsigned domain)
+{
+ const char *sindex;
+ const char *lpar;
+
+ if (is_physical_domain(domain)) {
+ lpar = "0x0";
+ sindex = "core";
+ } else {
+ lpar = "?";
+ sindex = "vcpu";
+ }
+
+ return kasprintf(GFP_KERNEL,
+ "domain=0x%x,offset=0x%x,%s=?,lpar=%s",
+ domain,
+ be16_to_cpu(event->event_counter_offs) +
+ be16_to_cpu(event->event_group_record_offs),
+ sindex,
+ lpar);
+}
+
+/* Avoid trusting fw to NUL terminate strings */
+static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp)
+{
+ return kasprintf(gfp, "%.*s", max_len, maybe_str);
+}
+
+static ssize_t device_show_string(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dev_ext_attribute *d;
+
+ d = container_of(attr, struct dev_ext_attribute, attr);
+
+ return sprintf(buf, "%s\n", (char *)d->var);
+}
+
+static struct attribute *device_str_attr_create_(char *name, char *str)
+{
+ struct dev_ext_attribute *attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+
+ if (!attr)
+ return NULL;
+
+ attr->var = str;
+ attr->attr.attr.name = name;
+ attr->attr.attr.mode = 0444;
+ attr->attr.show = device_show_string;
+
+ return &attr->attr.attr;
+}
+
+static struct attribute *device_str_attr_create(char *name, int name_max,
+ int name_nonce,
+ char *str, size_t str_max)
+{
+ char *n;
+ char *s = memdup_to_str(str, str_max, GFP_KERNEL);
+ struct attribute *a;
+
+ if (!s)
+ return NULL;
+
+ if (!name_nonce)
+ n = kasprintf(GFP_KERNEL, "%.*s", name_max, name);
+ else
+ n = kasprintf(GFP_KERNEL, "%.*s__%d", name_max, name,
+ name_nonce);
+ if (!n)
+ goto out_s;
+
+ a = device_str_attr_create_(n, s);
+ if (!a)
+ goto out_n;
+
+ return a;
+out_n:
+ kfree(n);
+out_s:
+ kfree(s);
+ return NULL;
+}
+
+static void device_str_attr_destroy(struct attribute *attr)
+{
+ struct dev_ext_attribute *d;
+
+ d = container_of(attr, struct dev_ext_attribute, attr.attr);
+ kfree(d->var);
+ kfree(d->attr.attr.name);
+ kfree(d);
+}
+
+static struct attribute *event_to_attr(unsigned ix,
+ struct hv_24x7_event_data *event,
+ unsigned domain,
+ int nonce)
+{
+ int event_name_len;
+ char *ev_name, *a_ev_name, *val;
+ const char *ev_suffix;
+ struct attribute *attr;
+
+ if (!domain_is_valid(domain)) {
+ pr_warn("catalog event %u has invalid domain %u\n",
+ ix, domain);
+ return NULL;
+ }
+
+ val = event_fmt(event, domain);
+ if (!val)
+ return NULL;
+
+ ev_suffix = event_domain_suffix(domain);
+ ev_name = event_name(event, &event_name_len);
+ if (!nonce)
+ a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s",
+ (int)event_name_len, ev_name, ev_suffix);
+ else
+ a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s__%d",
+ (int)event_name_len, ev_name, ev_suffix, nonce);
+
+ if (!a_ev_name)
+ goto out_val;
+
+ attr = device_str_attr_create_(a_ev_name, val);
+ if (!attr)
+ goto out_name;
+
+ return attr;
+out_name:
+ kfree(a_ev_name);
+out_val:
+ kfree(val);
+ return NULL;
+}
+
+static struct attribute *event_to_desc_attr(struct hv_24x7_event_data *event,
+ int nonce)
+{
+ int nl, dl;
+ char *name = event_name(event, &nl);
+ char *desc = event_desc(event, &dl);
+
+ /* If there isn't a description, don't create the sysfs file */
+ if (!dl)
+ return NULL;
+
+ return device_str_attr_create(name, nl, nonce, desc, dl);
+}
+
+static struct attribute *
+event_to_long_desc_attr(struct hv_24x7_event_data *event, int nonce)
+{
+ int nl, dl;
+ char *name = event_name(event, &nl);
+ char *desc = event_long_desc(event, &dl);
+
+ /* If there isn't a description, don't create the sysfs file */
+ if (!dl)
+ return NULL;
+
+ return device_str_attr_create(name, nl, nonce, desc, dl);
+}
+
+static ssize_t event_data_to_attrs(unsigned ix, struct attribute **attrs,
+ struct hv_24x7_event_data *event, int nonce)
+{
+ unsigned i;
+
+ switch (event->domain) {
+ case HV_PERF_DOMAIN_PHYS_CHIP:
+ *attrs = event_to_attr(ix, event, event->domain, nonce);
+ return 1;
+ case HV_PERF_DOMAIN_PHYS_CORE:
+ for (i = 0; i < ARRAY_SIZE(core_domains); i++) {
+ attrs[i] = event_to_attr(ix, event, core_domains[i],
+ nonce);
+ if (!attrs[i]) {
+ pr_warn("catalog event %u: individual attr %u "
+ "creation failure\n", ix, i);
+ for (; i; i--)
+ device_str_attr_destroy(attrs[i - 1]);
+ return -1;
+ }
+ }
+ return i;
+ default:
+ pr_warn("catalog event %u: domain %u is not allowed in the "
+ "catalog\n", ix, event->domain);
+ return -1;
+ }
+}
+
+static size_t event_to_attr_ct(struct hv_24x7_event_data *event)
+{
+ switch (event->domain) {
+ case HV_PERF_DOMAIN_PHYS_CHIP:
+ return 1;
+ case HV_PERF_DOMAIN_PHYS_CORE:
+ return ARRAY_SIZE(core_domains);
+ default:
+ return 0;
+ }
+}
+
+static unsigned long vmalloc_to_phys(void *v)
+{
+ struct page *p = vmalloc_to_page(v);
+
+ BUG_ON(!p);
+ return page_to_phys(p) + offset_in_page(v);
+}
+
+/* */
+struct event_uniq {
+ struct rb_node node;
+ const char *name;
+ int nl;
+ unsigned ct;
+ unsigned domain;
+};
+
+static int memord(const void *d1, size_t s1, const void *d2, size_t s2)
+{
+ if (s1 < s2)
+ return 1;
+ if (s2 > s1)
+ return -1;
+
+ return memcmp(d1, d2, s1);
+}
+
+static int ev_uniq_ord(const void *v1, size_t s1, unsigned d1, const void *v2,
+ size_t s2, unsigned d2)
+{
+ int r = memord(v1, s1, v2, s2);
+
+ if (r)
+ return r;
+ if (d1 > d2)
+ return 1;
+ if (d2 > d1)
+ return -1;
+ return 0;
+}
+
+static int event_uniq_add(struct rb_root *root, const char *name, int nl,
+ unsigned domain)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+ struct event_uniq *data;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct event_uniq *it;
+ int result;
+
+ it = container_of(*new, struct event_uniq, node);
+ result = ev_uniq_ord(name, nl, domain, it->name, it->nl,
+ it->domain);
+
+ parent = *new;
+ if (result < 0)
+ new = &((*new)->rb_left);
+ else if (result > 0)
+ new = &((*new)->rb_right);
+ else {
+ it->ct++;
+ pr_info("found a duplicate event %.*s, ct=%u\n", nl,
+ name, it->ct);
+ return it->ct;
+ }
+ }
+
+ data = kmalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ *data = (struct event_uniq) {
+ .name = name,
+ .nl = nl,
+ .ct = 0,
+ .domain = domain,
+ };
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+
+ /* data->ct */
+ return 0;
+}
+
+static void event_uniq_destroy(struct rb_root *root)
+{
+ /*
+ * the strings we point to are in the giant block of memory filled by
+ * the catalog, and are freed separately.
+ */
+ struct event_uniq *pos, *n;
+
+ rbtree_postorder_for_each_entry_safe(pos, n, root, node)
+ kfree(pos);
+}
+
+
+/*
+ * ensure the event structure's sizes are self consistent and don't cause us to
+ * read outside of the event
+ *
+ * On success, return the event length in bytes.
+ * Otherwise, return -1 (and print as appropriate).
+ */
+static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event,
+ size_t event_idx,
+ size_t event_data_bytes,
+ size_t event_entry_count,
+ size_t offset, void *end)
+{
+ ssize_t ev_len;
+ void *ev_end, *calc_ev_end;
+
+ if (offset >= event_data_bytes)
+ return -1;
+
+ if (event_idx >= event_entry_count) {
+ pr_devel("catalog event data has %zu bytes of padding after last event\n",
+ event_data_bytes - offset);
+ return -1;
+ }
+
+ if (!event_fixed_portion_is_within(event, end)) {
+ pr_warn("event %zu fixed portion is not within range\n",
+ event_idx);
+ return -1;
+ }
+
+ ev_len = be16_to_cpu(event->length);
+
+ if (ev_len % 16)
+ pr_info("event %zu has length %zu not divisible by 16: event=%pK\n",
+ event_idx, ev_len, event);
+
+ ev_end = (__u8 *)event + ev_len;
+ if (ev_end > end) {
+ pr_warn("event %zu has .length=%zu, ends after buffer end: ev_end=%pK > end=%pK, offset=%zu\n",
+ event_idx, ev_len, ev_end, end,
+ offset);
+ return -1;
+ }
+
+ calc_ev_end = event_end(event, end);
+ if (!calc_ev_end) {
+ pr_warn("event %zu has a calculated length which exceeds buffer length %zu: event=%pK end=%pK, offset=%zu\n",
+ event_idx, event_data_bytes, event, end,
+ offset);
+ return -1;
+ }
+
+ if (calc_ev_end > ev_end) {
+ pr_warn("event %zu exceeds it's own length: event=%pK, end=%pK, offset=%zu, calc_ev_end=%pK\n",
+ event_idx, event, ev_end, offset, calc_ev_end);
+ return -1;
+ }
+
+ return ev_len;
+}
+
+#define MAX_4K (SIZE_MAX / 4096)
+
+static int create_events_from_catalog(struct attribute ***events_,
+ struct attribute ***event_descs_,
+ struct attribute ***event_long_descs_)
+{
+ unsigned long hret;
+ size_t catalog_len, catalog_page_len, event_entry_count,
+ event_data_len, event_data_offs,
+ event_data_bytes, junk_events, event_idx, event_attr_ct, i,
+ attr_max, event_idx_last, desc_ct, long_desc_ct;
+ ssize_t ct, ev_len;
+ uint32_t catalog_version_num;
+ struct attribute **events, **event_descs, **event_long_descs;
+ struct hv_24x7_catalog_page_0 *page_0 =
+ kmem_cache_alloc(hv_page_cache, GFP_KERNEL);
+ void *page = page_0;
+ void *event_data, *end;
+ struct hv_24x7_event_data *event;
+ struct rb_root ev_uniq = RB_ROOT;
+ int ret = 0;
+
+ if (!page) {
+ ret = -ENOMEM;
+ goto e_out;
+ }
+
+ hret = h_get_24x7_catalog_page(page, 0, 0);
+ if (hret) {
+ ret = -EIO;
+ goto e_free;
+ }
+
+ catalog_version_num = be64_to_cpu(page_0->version);
+ catalog_page_len = be32_to_cpu(page_0->length);
+
+ if (MAX_4K < catalog_page_len) {
+ pr_err("invalid page count: %zu\n", catalog_page_len);
+ ret = -EIO;
+ goto e_free;
+ }
+
+ catalog_len = catalog_page_len * 4096;
+
+ event_entry_count = be16_to_cpu(page_0->event_entry_count);
+ event_data_offs = be16_to_cpu(page_0->event_data_offs);
+ event_data_len = be16_to_cpu(page_0->event_data_len);
+
+ pr_devel("cv %zu cl %zu eec %zu edo %zu edl %zu\n",
+ (size_t)catalog_version_num, catalog_len,
+ event_entry_count, event_data_offs, event_data_len);
+
+ if ((MAX_4K < event_data_len)
+ || (MAX_4K < event_data_offs)
+ || (MAX_4K - event_data_offs < event_data_len)) {
+ pr_err("invalid event data offs %zu and/or len %zu\n",
+ event_data_offs, event_data_len);
+ ret = -EIO;
+ goto e_free;
+ }
+
+ if ((event_data_offs + event_data_len) > catalog_page_len) {
+ pr_err("event data %zu-%zu does not fit inside catalog 0-%zu\n",
+ event_data_offs,
+ event_data_offs + event_data_len,
+ catalog_page_len);
+ ret = -EIO;
+ goto e_free;
+ }
+
+ if (SIZE_MAX / MAX_EVENTS_PER_EVENT_DATA - 1 < event_entry_count) {
+ pr_err("event_entry_count %zu is invalid\n",
+ event_entry_count);
+ ret = -EIO;
+ goto e_free;
+ }
+
+ event_data_bytes = event_data_len * 4096;
+
+ /*
+ * event data can span several pages, events can cross between these
+ * pages. Use vmalloc to make this easier.
+ */
+ event_data = vmalloc(event_data_bytes);
+ if (!event_data) {
+ pr_err("could not allocate event data\n");
+ ret = -ENOMEM;
+ goto e_free;
+ }
+
+ end = event_data + event_data_bytes;
+
+ /*
+ * using vmalloc_to_phys() like this only works if PAGE_SIZE is
+ * divisible by 4096
+ */
+ BUILD_BUG_ON(PAGE_SIZE % 4096);
+
+ for (i = 0; i < event_data_len; i++) {
+ hret = h_get_24x7_catalog_page_(
+ vmalloc_to_phys(event_data + i * 4096),
+ catalog_version_num,
+ i + event_data_offs);
+ if (hret) {
+ pr_err("failed to get event data in page %zu\n",
+ i + event_data_offs);
+ ret = -EIO;
+ goto e_event_data;
+ }
+ }
+
+ /*
+ * scan the catalog to determine the number of attributes we need, and
+ * verify it at the same time.
+ */
+ for (junk_events = 0, event = event_data, event_idx = 0, attr_max = 0;
+ ;
+ event_idx++, event = (void *)event + ev_len) {
+ size_t offset = (void *)event - (void *)event_data;
+ char *name;
+ int nl;
+
+ ev_len = catalog_event_len_validate(event, event_idx,
+ event_data_bytes,
+ event_entry_count,
+ offset, end);
+ if (ev_len < 0)
+ break;
+
+ name = event_name(event, &nl);
+
+ if (event->event_group_record_len == 0) {
+ pr_devel("invalid event %zu (%.*s): group_record_len == 0, skipping\n",
+ event_idx, nl, name);
+ junk_events++;
+ continue;
+ }
+
+ if (!catalog_entry_domain_is_valid(event->domain)) {
+ pr_info("event %zu (%.*s) has invalid domain %d\n",
+ event_idx, nl, name, event->domain);
+ junk_events++;
+ continue;
+ }
+
+ attr_max += event_to_attr_ct(event);
+ }
+
+ event_idx_last = event_idx;
+ if (event_idx_last != event_entry_count)
+ pr_warn("event buffer ended before listed # of events were parsed (got %zu, wanted %zu, junk %zu)\n",
+ event_idx_last, event_entry_count, junk_events);
+
+ events = kmalloc_array(attr_max + 1, sizeof(*events), GFP_KERNEL);
+ if (!events) {
+ ret = -ENOMEM;
+ goto e_event_data;
+ }
+
+ event_descs = kmalloc_array(event_idx + 1, sizeof(*event_descs),
+ GFP_KERNEL);
+ if (!event_descs) {
+ ret = -ENOMEM;
+ goto e_event_attrs;
+ }
+
+ event_long_descs = kmalloc_array(event_idx + 1,
+ sizeof(*event_long_descs), GFP_KERNEL);
+ if (!event_long_descs) {
+ ret = -ENOMEM;
+ goto e_event_descs;
+ }
+
+ /* Iterate over the catalog filling in the attribute vector */
+ for (junk_events = 0, event_attr_ct = 0, desc_ct = 0, long_desc_ct = 0,
+ event = event_data, event_idx = 0;
+ event_idx < event_idx_last;
+ event_idx++, ev_len = be16_to_cpu(event->length),
+ event = (void *)event + ev_len) {
+ char *name;
+ int nl;
+ int nonce;
+ /*
+ * these are the only "bad" events that are intermixed and that
+ * we can ignore without issue. make sure to skip them here
+ */
+ if (event->event_group_record_len == 0)
+ continue;
+ if (!catalog_entry_domain_is_valid(event->domain))
+ continue;
+
+ name = event_name(event, &nl);
+ nonce = event_uniq_add(&ev_uniq, name, nl, event->domain);
+ ct = event_data_to_attrs(event_idx, events + event_attr_ct,
+ event, nonce);
+ if (ct <= 0) {
+ pr_warn("event %zu (%.*s) creation failure, skipping\n",
+ event_idx, nl, name);
+ junk_events++;
+ } else {
+ event_attr_ct += ct;
+ event_descs[desc_ct] = event_to_desc_attr(event, nonce);
+ if (event_descs[desc_ct])
+ desc_ct++;
+ event_long_descs[long_desc_ct] =
+ event_to_long_desc_attr(event, nonce);
+ if (event_long_descs[long_desc_ct])
+ long_desc_ct++;
+ }
+ }
+
+ pr_info("read %zu catalog entries, created %zu event attrs (%zu failures), %zu descs\n",
+ event_idx, event_attr_ct, junk_events, desc_ct);
+
+ events[event_attr_ct] = NULL;
+ event_descs[desc_ct] = NULL;
+ event_long_descs[long_desc_ct] = NULL;
+
+ event_uniq_destroy(&ev_uniq);
+ vfree(event_data);
+ kmem_cache_free(hv_page_cache, page);
+
+ *events_ = events;
+ *event_descs_ = event_descs;
+ *event_long_descs_ = event_long_descs;
+ return 0;
+
+e_event_descs:
+ kfree(event_descs);
+e_event_attrs:
+ kfree(events);
+e_event_data:
+ vfree(event_data);
+e_free:
+ kmem_cache_free(hv_page_cache, page);
+e_out:
+ *events_ = NULL;
+ *event_descs_ = NULL;
+ *event_long_descs_ = NULL;
+ return ret;
+}
+
static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
struct bin_attribute *bin_attr, char *buf,
loff_t offset, size_t count)
{
unsigned long hret;
ssize_t ret = 0;
- size_t catalog_len = 0, catalog_page_len = 0, page_count = 0;
+ size_t catalog_len = 0, catalog_page_len = 0;
loff_t page_offset = 0;
+ loff_t offset_in_page;
+ size_t copy_len;
uint64_t catalog_version_num = 0;
void *page = kmem_cache_alloc(hv_page_cache, GFP_USER);
struct hv_24x7_catalog_page_0 *page_0 = page;
+
if (!page)
return -ENOMEM;
@@ -202,7 +915,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
catalog_len = catalog_page_len * 4096;
page_offset = offset / 4096;
- page_count = count / 4096;
+ offset_in_page = offset % 4096;
if (page_offset >= catalog_page_len)
goto e_free;
@@ -216,18 +929,23 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
}
}
- ret = read_offset_data(buf, count, offset,
- page, 4096, page_offset * 4096);
+ copy_len = 4096 - offset_in_page;
+ if (copy_len > count)
+ copy_len = count;
+
+ memcpy(buf, page+offset_in_page, copy_len);
+ ret = copy_len;
+
e_free:
if (hret)
pr_err("h_get_24x7_catalog_page(ver=%lld, page=%lld) failed:"
" rc=%ld\n",
catalog_version_num, page_offset, hret);
- kfree(page);
+ kmem_cache_free(hv_page_cache, page);
- pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n",
- offset, page_offset, count, page_count, catalog_len,
- catalog_page_len, ret);
+ pr_devel("catalog_read: offset=%lld(%lld) count=%zu "
+ "catalog_len=%zu(%zu) => %zd\n", offset, page_offset,
+ count, catalog_len, catalog_page_len, ret);
return ret;
}
@@ -250,7 +968,7 @@ static ssize_t _name##_show(struct device *dev, \
} \
ret = sprintf(buf, _fmt, _expr); \
e_free: \
- kfree(page); \
+ kmem_cache_free(hv_page_cache, page); \
return ret; \
} \
static DEVICE_ATTR_RO(_name)
@@ -280,82 +998,141 @@ static struct attribute_group if_group = {
static const struct attribute_group *attr_groups[] = {
&format_group,
+ &event_group,
+ &event_desc_group,
+ &event_long_desc_group,
&if_group,
NULL,
};
-static bool is_physical_domain(int domain)
+static void log_24x7_hcall(struct hv_24x7_request_buffer *request_buffer,
+ struct hv_24x7_data_result_buffer *result_buffer,
+ unsigned long ret)
{
- return domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP ||
- domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
+ struct hv_24x7_request *req;
+
+ req = &request_buffer->requests[0];
+ pr_notice_ratelimited("hcall failed: [%d %#x %#x %d] => "
+ "ret 0x%lx (%ld) detail=0x%x failing ix=%x\n",
+ req->performance_domain, req->data_offset,
+ req->starting_ix, req->starting_lpar_ix, ret, ret,
+ result_buffer->detailed_rc,
+ result_buffer->failing_request_ix);
}
-static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
- u16 lpar, u64 *res,
- bool success_expected)
+/*
+ * Start the process for a new H_GET_24x7_DATA hcall.
+ */
+static void init_24x7_request(struct hv_24x7_request_buffer *request_buffer,
+ struct hv_24x7_data_result_buffer *result_buffer)
+{
+
+ memset(request_buffer, 0, 4096);
+ memset(result_buffer, 0, 4096);
+
+ request_buffer->interface_version = HV_24X7_IF_VERSION_CURRENT;
+ /* memset above set request_buffer->num_requests to 0 */
+}
+
+/*
+ * Commit (i.e perform) the H_GET_24x7_DATA hcall using the data collected
+ * by 'init_24x7_request()' and 'add_event_to_24x7_request()'.
+ */
+static int make_24x7_request(struct hv_24x7_request_buffer *request_buffer,
+ struct hv_24x7_data_result_buffer *result_buffer)
{
unsigned long ret;
/*
- * request_buffer and result_buffer are not required to be 4k aligned,
- * but are not allowed to cross any 4k boundary. Aligning them to 4k is
- * the simplest way to ensure that.
+ * NOTE: Due to variable number of array elements in request and
+ * result buffer(s), sizeof() is not reliable. Use the actual
+ * allocated buffer size, H24x7_DATA_BUFFER_SIZE.
*/
- struct reqb {
- struct hv_24x7_request_buffer buf;
- struct hv_24x7_request req;
- } __packed __aligned(4096) request_buffer = {
- .buf = {
- .interface_version = HV_24X7_IF_VERSION_CURRENT,
- .num_requests = 1,
- },
- .req = {
- .performance_domain = domain,
- .data_size = cpu_to_be16(8),
- .data_offset = cpu_to_be32(offset),
- .starting_lpar_ix = cpu_to_be16(lpar),
- .max_num_lpars = cpu_to_be16(1),
- .starting_ix = cpu_to_be16(ix),
- .max_ix = cpu_to_be16(1),
- }
- };
+ ret = plpar_hcall_norets(H_GET_24X7_DATA,
+ virt_to_phys(request_buffer), H24x7_DATA_BUFFER_SIZE,
+ virt_to_phys(result_buffer), H24x7_DATA_BUFFER_SIZE);
- struct resb {
- struct hv_24x7_data_result_buffer buf;
- struct hv_24x7_result res;
- struct hv_24x7_result_element elem;
- __be64 result;
- } __packed __aligned(4096) result_buffer = {};
+ if (ret)
+ log_24x7_hcall(request_buffer, result_buffer, ret);
- ret = plpar_hcall_norets(H_GET_24X7_DATA,
- virt_to_phys(&request_buffer), sizeof(request_buffer),
- virt_to_phys(&result_buffer), sizeof(result_buffer));
+ return ret;
+}
- if (ret) {
- if (success_expected)
- pr_err_ratelimited("hcall failed: %d %#x %#x %d => 0x%lx (%ld) detail=0x%x failing ix=%x\n",
- domain, offset, ix, lpar,
- ret, ret,
- result_buffer.buf.detailed_rc,
- result_buffer.buf.failing_request_ix);
- return ret;
+/*
+ * Add the given @event to the next slot in the 24x7 request_buffer.
+ *
+ * Note that H_GET_24X7_DATA hcall allows reading several counters'
+ * values in a single HCALL. We expect the caller to add events to the
+ * request buffer one by one, make the HCALL and process the results.
+ */
+static int add_event_to_24x7_request(struct perf_event *event,
+ struct hv_24x7_request_buffer *request_buffer)
+{
+ u16 idx;
+ int i;
+ struct hv_24x7_request *req;
+
+ if (request_buffer->num_requests > 254) {
+ pr_devel("Too many requests for 24x7 HCALL %d\n",
+ request_buffer->num_requests);
+ return -EINVAL;
}
- *res = be64_to_cpu(result_buffer.result);
- return ret;
+ if (is_physical_domain(event_get_domain(event)))
+ idx = event_get_core(event);
+ else
+ idx = event_get_vcpu(event);
+
+ i = request_buffer->num_requests++;
+ req = &request_buffer->requests[i];
+
+ req->performance_domain = event_get_domain(event);
+ req->data_size = cpu_to_be16(8);
+ req->data_offset = cpu_to_be32(event_get_offset(event));
+ req->starting_lpar_ix = cpu_to_be16(event_get_lpar(event)),
+ req->max_num_lpars = cpu_to_be16(1);
+ req->starting_ix = cpu_to_be16(idx);
+ req->max_ix = cpu_to_be16(1);
+
+ return 0;
}
-static unsigned long event_24x7_request(struct perf_event *event, u64 *res,
- bool success_expected)
+static unsigned long single_24x7_request(struct perf_event *event, u64 *count)
{
- return single_24x7_request(event_get_domain(event),
- event_get_offset(event),
- event_get_starting_index(event),
- event_get_lpar(event),
- res,
- success_expected);
+ unsigned long ret;
+ struct hv_24x7_request_buffer *request_buffer;
+ struct hv_24x7_data_result_buffer *result_buffer;
+ struct hv_24x7_result *resb;
+
+ BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
+ BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
+
+ request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+ result_buffer = (void *)get_cpu_var(hv_24x7_resb);
+
+ init_24x7_request(request_buffer, result_buffer);
+
+ ret = add_event_to_24x7_request(event, request_buffer);
+ if (ret)
+ goto out;
+
+ ret = make_24x7_request(request_buffer, result_buffer);
+ if (ret) {
+ log_24x7_hcall(request_buffer, result_buffer, ret);
+ goto out;
+ }
+
+ /* process result from hcall */
+ resb = &result_buffer->results[0];
+ *count = be64_to_cpu(resb->elements[0].element_data[0]);
+
+out:
+ put_cpu_var(hv_24x7_reqb);
+ put_cpu_var(hv_24x7_resb);
+ return ret;
}
+
static int h_24x7_event_init(struct perf_event *event)
{
struct hv_perf_caps caps;
@@ -387,8 +1164,7 @@ static int h_24x7_event_init(struct perf_event *event)
event->attr.exclude_hv ||
event->attr.exclude_idle ||
event->attr.exclude_host ||
- event->attr.exclude_guest ||
- is_sampling_event(event)) /* no sampling */
+ event->attr.exclude_guest)
return -EINVAL;
/* no branch sampling */
@@ -414,17 +1190,17 @@ static int h_24x7_event_init(struct perf_event *event)
return -EIO;
}
- /* PHYSICAL domains & other lpars require extra capabilities */
+ /* Physical domains & other lpars require extra capabilities */
if (!caps.collect_privileged && (is_physical_domain(domain) ||
(event_get_lpar(event) != event_get_lpar_max()))) {
- pr_devel("hv permisions disallow: is_physical_domain:%d, lpar=0x%llx\n",
+ pr_devel("hv permissions disallow: is_physical_domain:%d, lpar=0x%llx\n",
is_physical_domain(domain),
event_get_lpar(event));
return -EACCES;
}
/* see if the event complains */
- if (event_24x7_request(event, &ct, false)) {
+ if (single_24x7_request(event, &ct)) {
pr_devel("test hcall failed\n");
return -EIO;
}
@@ -436,7 +1212,7 @@ static u64 h_24x7_get_value(struct perf_event *event)
{
unsigned long ret;
u64 ct;
- ret = event_24x7_request(event, &ct, true);
+ ret = single_24x7_request(event, &ct);
if (ret)
/* We checked this in event init, shouldn't fail here... */
return 0;
@@ -444,15 +1220,22 @@ static u64 h_24x7_get_value(struct perf_event *event)
return ct;
}
-static void h_24x7_event_update(struct perf_event *event)
+static void update_event_count(struct perf_event *event, u64 now)
{
s64 prev;
- u64 now;
- now = h_24x7_get_value(event);
+
prev = local64_xchg(&event->hw.prev_count, now);
local64_add(now - prev, &event->count);
}
+static void h_24x7_event_read(struct perf_event *event)
+{
+ u64 now;
+
+ now = h_24x7_get_value(event);
+ update_event_count(event, now);
+}
+
static void h_24x7_event_start(struct perf_event *event, int flags)
{
if (flags & PERF_EF_RELOAD)
@@ -461,7 +1244,7 @@ static void h_24x7_event_start(struct perf_event *event, int flags)
static void h_24x7_event_stop(struct perf_event *event, int flags)
{
- h_24x7_event_update(event);
+ h_24x7_event_read(event);
}
static int h_24x7_event_add(struct perf_event *event, int flags)
@@ -472,11 +1255,6 @@ static int h_24x7_event_add(struct perf_event *event, int flags)
return 0;
}
-static int h_24x7_event_idx(struct perf_event *event)
-{
- return 0;
-}
-
static struct pmu h_24x7_pmu = {
.task_ctx_nr = perf_invalid_context,
@@ -487,8 +1265,7 @@ static struct pmu h_24x7_pmu = {
.del = h_24x7_event_stop,
.start = h_24x7_event_start,
.stop = h_24x7_event_stop,
- .read = h_24x7_event_update,
- .event_idx = h_24x7_event_idx,
+ .read = h_24x7_event_read,
};
static int hv_24x7_init(void)
@@ -513,6 +1290,16 @@ static int hv_24x7_init(void)
if (!hv_page_cache)
return -ENOMEM;
+ /* sampling not supported */
+ h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
+ r = create_events_from_catalog(&event_group.attrs,
+ &event_desc_group.attrs,
+ &event_long_desc_group.attrs);
+
+ if (r)
+ return r;
+
r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
if (r)
return r;
diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h
index 720ebce4b435..0f9fa21a29f2 100644
--- a/arch/powerpc/perf/hv-24x7.h
+++ b/arch/powerpc/perf/hv-24x7.h
@@ -3,14 +3,14 @@
#include <linux/types.h>
+enum hv_perf_domains {
+#define DOMAIN(n, v, x, c) HV_PERF_DOMAIN_##n = v,
+#include "hv-24x7-domains.h"
+#undef DOMAIN
+};
+
struct hv_24x7_request {
/* PHYSICAL domains require enabling via phyp/hmc. */
-#define HV_24X7_PERF_DOMAIN_PHYSICAL_CHIP 0x01
-#define HV_24X7_PERF_DOMAIN_PHYSICAL_CORE 0x02
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CORE 0x03
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_CHIP 0x04
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_HOME_NODE 0x05
-#define HV_24X7_PERF_DOMAIN_VIRTUAL_PROCESSOR_REMOTE_NODE 0x06
__u8 performance_domain;
__u8 reserved[0x1];
@@ -50,7 +50,7 @@ struct hv_24x7_request_buffer {
__u8 interface_version;
__u8 num_requests;
__u8 reserved[0xE];
- struct hv_24x7_request requests[];
+ struct hv_24x7_request requests[1];
} __packed;
struct hv_24x7_result_element {
@@ -66,7 +66,7 @@ struct hv_24x7_result_element {
__be32 lpar_cfg_instance_id;
/* size = @result_element_data_size of cointaining result. */
- __u8 element_data[];
+ __u64 element_data[1];
} __packed;
struct hv_24x7_result {
@@ -87,7 +87,7 @@ struct hv_24x7_result {
/* 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[];
+ struct hv_24x7_result_element elements[1];
} __packed;
struct hv_24x7_data_result_buffer {
@@ -103,7 +103,7 @@ struct hv_24x7_data_result_buffer {
__u8 reserved2[0x8];
/* WARNING: only valid for the first result due to variable sizes of
* results */
- struct hv_24x7_result results[]; /* [@num_results] */
+ struct hv_24x7_result results[1]; /* [@num_results] */
} __packed;
#endif
diff --git a/arch/powerpc/perf/hv-common.c b/arch/powerpc/perf/hv-common.c
index 47e02b366f58..7dce8f109967 100644
--- a/arch/powerpc/perf/hv-common.c
+++ b/arch/powerpc/perf/hv-common.c
@@ -9,13 +9,13 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
unsigned long r;
struct p {
struct hv_get_perf_counter_info_params params;
- struct cv_system_performance_capabilities caps;
+ struct hv_gpci_system_performance_capabilities caps;
} __packed __aligned(sizeof(uint64_t));
struct p arg = {
.params = {
.counter_request = cpu_to_be32(
- CIR_SYSTEM_PERFORMANCE_CAPABILITIES),
+ HV_GPCI_system_performance_capabilities),
.starting_index = cpu_to_be32(-1),
.counter_info_version_in = 0,
}
@@ -31,9 +31,9 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps)
caps->version = arg.params.counter_info_version_out;
caps->collect_privileged = !!arg.caps.perf_collect_privileged;
- caps->ga = !!(arg.caps.capability_mask & CV_CM_GA);
- caps->expanded = !!(arg.caps.capability_mask & CV_CM_EXPANDED);
- caps->lab = !!(arg.caps.capability_mask & CV_CM_LAB);
+ caps->ga = !!(arg.caps.capability_mask & HV_GPCI_CM_GA);
+ caps->expanded = !!(arg.caps.capability_mask & HV_GPCI_CM_EXPANDED);
+ caps->lab = !!(arg.caps.capability_mask & HV_GPCI_CM_LAB);
return r;
}
diff --git a/arch/powerpc/perf/hv-common.h b/arch/powerpc/perf/hv-common.h
index 5d79cecbd73d..349aaba4d2d1 100644
--- a/arch/powerpc/perf/hv-common.h
+++ b/arch/powerpc/perf/hv-common.h
@@ -20,6 +20,16 @@ unsigned long hv_perf_caps_get(struct hv_perf_caps *caps);
PMU_FORMAT_ATTR(name, #attr_var ":" #bit_start "-" #bit_end); \
EVENT_DEFINE_RANGE(name, attr_var, bit_start, bit_end)
+/*
+ * The EVENT_DEFINE_RANGE_FORMAT() macro above includes helper functions
+ * for the fields (eg: event_get_starting_index()). For some fields we
+ * need the bit-range definition, but no the helper functions. Define a
+ * lite version of the above macro without the helpers and silence
+ * compiler warnings unused static functions.
+ */
+#define EVENT_DEFINE_RANGE_FORMAT_LITE(name, attr_var, bit_start, bit_end) \
+PMU_FORMAT_ATTR(name, #attr_var ":" #bit_start "-" #bit_end);
+
#define EVENT_DEFINE_RANGE(name, attr_var, bit_start, bit_end) \
static u64 event_get_##name##_max(void) \
{ \
diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h
new file mode 100644
index 000000000000..acd17648cd18
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci-requests.h
@@ -0,0 +1,261 @@
+
+#include "req-gen/_begin.h"
+
+/*
+ * Based on the document "getPerfCountInfo v1.07"
+ */
+
+/*
+ * #define REQUEST_NAME counter_request_name
+ * #define REQUEST_NUM r_num
+ * #define REQUEST_IDX_KIND starting_index_kind
+ * #include I(REQUEST_BEGIN)
+ * REQUEST(
+ * __field(...)
+ * __field(...)
+ * __array(...)
+ * __count(...)
+ * )
+ * #include I(REQUEST_END)
+ *
+ * - starting_index_kind is one of the following, depending on the event:
+ *
+ * hw_chip_id: hardware chip id or -1 for current hw chip
+ * partition_id
+ * sibling_part_id,
+ * phys_processor_idx:
+ * 0xffffffffffffffff: or -1, which means it is irrelavant for the event
+ *
+ * __count(offset, bytes, name):
+ * a counter that should be exposed via perf
+ * __field(offset, bytes, name)
+ * a normal field
+ * __array(offset, bytes, name)
+ * an array of bytes
+ *
+ *
+ * @bytes for __count, and __field _must_ be a numeral token
+ * in decimal, not an expression and not in hex.
+ *
+ *
+ * TODO:
+ * - expose secondary index (if any counter ever uses it, only 0xA0
+ * appears to use it right now, and it doesn't have any counters)
+ * - embed versioning info
+ * - include counter descriptions
+ */
+#define REQUEST_NAME dispatch_timebase_by_processor
+#define REQUEST_NUM 0x10
+#define REQUEST_IDX_KIND "phys_processor_idx=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0, 8, processor_time_in_timebase_cycles)
+ __field(0x8, 4, hw_processor_id)
+ __field(0xC, 2, owning_part_id)
+ __field(0xE, 1, processor_state)
+ __field(0xF, 1, version)
+ __field(0x10, 4, hw_chip_id)
+ __field(0x14, 4, phys_module_id)
+ __field(0x18, 4, primary_affinity_domain_idx)
+ __field(0x1C, 4, secondary_affinity_domain_idx)
+ __field(0x20, 4, processor_version)
+ __field(0x24, 2, logical_processor_idx)
+ __field(0x26, 2, reserved)
+ __field(0x28, 4, processor_id_register)
+ __field(0x2C, 4, phys_processor_idx)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME entitled_capped_uncapped_donated_idle_timebase_by_partition
+#define REQUEST_NUM 0x20
+#define REQUEST_IDX_KIND "sibling_part_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 8, partition_id)
+ __count(0x8, 8, entitled_cycles)
+ __count(0x10, 8, consumed_capped_cycles)
+ __count(0x18, 8, consumed_uncapped_cycles)
+ __count(0x20, 8, cycles_donated)
+ __count(0x28, 8, purr_idle_cycles)
+)
+#include I(REQUEST_END)
+
+/*
+ * Not available for counter_info_version >= 0x8, use
+ * run_instruction_cycles_by_partition(0x100) instead.
+ */
+#define REQUEST_NAME run_instructions_run_cycles_by_partition
+#define REQUEST_NUM 0x30
+#define REQUEST_IDX_KIND "sibling_part_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 8, partition_id)
+ __count(0x8, 8, instructions_completed)
+ __count(0x10, 8, cycles)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_performance_capabilities
+#define REQUEST_NUM 0x40
+#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 1, perf_collect_privileged)
+ __field(0x1, 1, capability_mask)
+ __array(0x2, 0xE, reserved)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_abc_links
+#define REQUEST_NUM 0x50
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, total_link_cycles)
+ __count(0x18, 8, idle_cycles_for_a_link)
+ __count(0x20, 8, idle_cycles_for_b_link)
+ __count(0x28, 8, idle_cycles_for_c_link)
+ __array(0x30, 0x20, reserved2)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_wxyz_links
+#define REQUEST_NUM 0x60
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, total_link_cycles)
+ __count(0x18, 8, idle_cycles_for_w_link)
+ __count(0x20, 8, idle_cycles_for_x_link)
+ __count(0x28, 8, idle_cycles_for_y_link)
+ __count(0x30, 8, idle_cycles_for_z_link)
+ __array(0x38, 0x28, reserved2)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_gx_links
+#define REQUEST_NUM 0x70
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, gx0_in_address_cycles)
+ __count(0x18, 8, gx0_in_data_cycles)
+ __count(0x20, 8, gx0_in_retries)
+ __count(0x28, 8, gx0_in_bus_cycles)
+ __count(0x30, 8, gx0_in_cycles_total)
+ __count(0x38, 8, gx0_out_address_cycles)
+ __count(0x40, 8, gx0_out_data_cycles)
+ __count(0x48, 8, gx0_out_retries)
+ __count(0x50, 8, gx0_out_bus_cycles)
+ __count(0x58, 8, gx0_out_cycles_total)
+ __count(0x60, 8, gx1_in_address_cycles)
+ __count(0x68, 8, gx1_in_data_cycles)
+ __count(0x70, 8, gx1_in_retries)
+ __count(0x78, 8, gx1_in_bus_cycles)
+ __count(0x80, 8, gx1_in_cycles_total)
+ __count(0x88, 8, gx1_out_address_cycles)
+ __count(0x90, 8, gx1_out_data_cycles)
+ __count(0x98, 8, gx1_out_retries)
+ __count(0xA0, 8, gx1_out_bus_cycles)
+ __count(0xA8, 8, gx1_out_cycles_total)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME processor_bus_utilization_mc_links
+#define REQUEST_NUM 0x80
+#define REQUEST_IDX_KIND "hw_chip_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, hw_chip_id)
+ __array(0x4, 0xC, reserved1)
+ __count(0x10, 8, mc0_frames)
+ __count(0x18, 8, mc0_reads)
+ __count(0x20, 8, mc0_write)
+ __count(0x28, 8, mc0_total_cycles)
+ __count(0x30, 8, mc1_frames)
+ __count(0x38, 8, mc1_reads)
+ __count(0x40, 8, mc1_writes)
+ __count(0x48, 8, mc1_total_cycles)
+)
+#include I(REQUEST_END)
+
+/* Processor_config (0x90) skipped, no counters */
+/* Current_processor_frequency (0x91) skipped, no counters */
+
+#define REQUEST_NAME processor_core_utilization
+#define REQUEST_NUM 0x94
+#define REQUEST_IDX_KIND "phys_processor_idx=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 4, phys_processor_idx)
+ __field(0x4, 4, hw_processor_id)
+ __count(0x8, 8, cycles_across_any_thread)
+ __count(0x10, 8, timebase_at_collection)
+ __count(0x18, 8, purr_cycles)
+ __count(0x20, 8, sum_of_cycles_across_all_threads)
+ __count(0x28, 8, instructions_completed)
+)
+#include I(REQUEST_END)
+
+/* Processor_core_power_mode (0x95) skipped, no counters */
+/* Affinity_domain_information_by_virtual_processor (0xA0) skipped,
+ * no counters */
+/* Affinity_domain_information_by_domain (0xB0) skipped, no counters */
+/* Affinity_domain_information_by_partition (0xB1) skipped, no counters */
+/* Physical_memory_info (0xC0) skipped, no counters */
+/* Processor_bus_topology (0xD0) skipped, no counters */
+
+#define REQUEST_NAME partition_hypervisor_queuing_times
+#define REQUEST_NUM 0xE0
+#define REQUEST_IDX_KIND "partition_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 2, partition_id)
+ __array(0x2, 6, reserved1)
+ __count(0x8, 8, time_waiting_for_entitlement)
+ __count(0x10, 8, times_waited_for_entitlement)
+ __count(0x18, 8, time_waiting_for_phys_processor)
+ __count(0x20, 8, times_waited_for_phys_processor)
+ __count(0x28, 8, dispatches_on_home_core)
+ __count(0x30, 8, dispatches_on_home_primary_affinity_domain)
+ __count(0x38, 8, dispatches_on_home_secondary_affinity_domain)
+ __count(0x40, 8, dispatches_off_home_secondary_affinity_domain)
+ __count(0x48, 8, dispatches_on_dedicated_processor_donating_cycles)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_hypervisor_times
+#define REQUEST_NUM 0xF0
+#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors)
+ __count(0x8, 8, time_spent_processing_virtual_processor_timers)
+ __count(0x10, 8, time_spent_managing_partitions_over_entitlement)
+ __count(0x18, 8, time_spent_on_system_management)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME system_tlbie_count_and_time
+#define REQUEST_NUM 0xF4
+#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#include I(REQUEST_BEGIN)
+REQUEST(__count(0, 8, tlbie_instructions_issued)
+ /*
+ * FIXME: The spec says the offset here is 0x10, which I suspect
+ * is wrong.
+ */
+ __count(0x8, 8, time_spent_issuing_tlbies)
+)
+#include I(REQUEST_END)
+
+#define REQUEST_NAME partition_instruction_count_and_time
+#define REQUEST_NUM 0x100
+#define REQUEST_IDX_KIND "partition_id=?"
+#include I(REQUEST_BEGIN)
+REQUEST(__field(0, 2, partition_id)
+ __array(0x2, 0x6, reserved1)
+ __count(0x8, 8, instructions_performed)
+ __count(0x10, 8, time_collected)
+)
+#include I(REQUEST_END)
+
+/* set_mmcrh (0x80001000) skipped, no counters */
+/* retrieve_hpmcx (0x80002000) skipped, no counters */
+
+#include "req-gen/_end.h"
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index c9d399a2df82..856fe6e03c2a 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -31,7 +31,18 @@
/* u32 */
EVENT_DEFINE_RANGE_FORMAT(request, config, 0, 31);
/* u32 */
+/*
+ * Note that starting_index, phys_processor_idx, sibling_part_id,
+ * hw_chip_id, partition_id all refer to the same bit range. They
+ * are basically aliases for the starting_index. The specific alias
+ * used depends on the event. See REQUEST_IDX_KIND in hv-gpci-requests.h
+ */
EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(phys_processor_idx, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(sibling_part_id, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(hw_chip_id, config, 32, 63);
+EVENT_DEFINE_RANGE_FORMAT_LITE(partition_id, config, 32, 63);
+
/* u16 */
EVENT_DEFINE_RANGE_FORMAT(secondary_index, config1, 0, 15);
/* u8 */
@@ -44,6 +55,10 @@ EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
static struct attribute *format_attrs[] = {
&format_attr_request.attr,
&format_attr_starting_index.attr,
+ &format_attr_phys_processor_idx.attr,
+ &format_attr_sibling_part_id.attr,
+ &format_attr_hw_chip_id.attr,
+ &format_attr_partition_id.attr,
&format_attr_secondary_index.attr,
&format_attr_counter_info_version.attr,
@@ -57,6 +72,11 @@ static struct attribute_group format_group = {
.attrs = format_attrs,
};
+static struct attribute_group event_group = {
+ .name = "events",
+ .attrs = hv_gpci_event_attrs,
+};
+
#define HV_CAPS_ATTR(_name, _format) \
static ssize_t _name##_show(struct device *dev, \
struct device_attribute *attr, \
@@ -102,6 +122,7 @@ static struct attribute_group interface_group = {
static const struct attribute_group *attr_groups[] = {
&format_group,
+ &event_group,
&interface_group,
NULL,
};
@@ -210,8 +231,7 @@ static int h_gpci_event_init(struct perf_event *event)
event->attr.exclude_hv ||
event->attr.exclude_idle ||
event->attr.exclude_host ||
- event->attr.exclude_guest ||
- is_sampling_event(event)) /* no sampling */
+ event->attr.exclude_guest)
return -EINVAL;
/* no branch sampling */
@@ -247,11 +267,6 @@ static int h_gpci_event_init(struct perf_event *event)
return 0;
}
-static int h_gpci_event_idx(struct perf_event *event)
-{
- return 0;
-}
-
static struct pmu h_gpci_pmu = {
.task_ctx_nr = perf_invalid_context,
@@ -263,7 +278,6 @@ static struct pmu h_gpci_pmu = {
.start = h_gpci_event_start,
.stop = h_gpci_event_stop,
.read = h_gpci_event_update,
- .event_idx = h_gpci_event_idx,
};
static int hv_gpci_init(void)
@@ -272,6 +286,8 @@ static int hv_gpci_init(void)
unsigned long hret;
struct hv_perf_caps caps;
+ hv_gpci_assert_offsets_correct();
+
if (!firmware_has_feature(FW_FEATURE_LPAR)) {
pr_debug("not a virtualized system, not enabling\n");
return -ENODEV;
@@ -284,6 +300,9 @@ static int hv_gpci_init(void)
return -ENODEV;
}
+ /* sampling not supported */
+ h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
if (r)
return r;
diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h
index b25f460c9cce..86ede8275961 100644
--- a/arch/powerpc/perf/hv-gpci.h
+++ b/arch/powerpc/perf/hv-gpci.h
@@ -42,32 +42,19 @@ struct hv_get_perf_counter_info_params {
*/
#define COUNTER_INFO_VERSION_CURRENT 0x8
-/*
- * These determine the counter_value[] layout and the meaning of starting_index
- * and secondary_index.
- *
- * Unless otherwise noted, @secondary_index is unused and ignored.
- */
-enum counter_info_requests {
-
- /* GENERAL */
-
- /* @starting_index: must be -1 (to refer to the current partition)
- */
- CIR_SYSTEM_PERFORMANCE_CAPABILITIES = 0X40,
+/* capability mask masks. */
+enum {
+ HV_GPCI_CM_GA = (1 << 7),
+ HV_GPCI_CM_EXPANDED = (1 << 6),
+ HV_GPCI_CM_LAB = (1 << 5)
};
-struct cv_system_performance_capabilities {
- /* If != 0, allowed to collect data from other partitions */
- __u8 perf_collect_privileged;
-
- /* These following are only valid if counter_info_version >= 0x3 */
-#define CV_CM_GA (1 << 7)
-#define CV_CM_EXPANDED (1 << 6)
-#define CV_CM_LAB (1 << 5)
- /* remaining bits are reserved */
- __u8 capability_mask;
- __u8 reserved[0xE];
-} __packed;
+#define REQUEST_FILE "../hv-gpci-requests.h"
+#define NAME_LOWER hv_gpci
+#define NAME_UPPER HV_GPCI
+#include "req-gen/perf.h"
+#undef REQUEST_FILE
+#undef NAME_LOWER
+#undef NAME_UPPER
#endif
diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c
index fe21b515ca44..d115c5635bf3 100644
--- a/arch/powerpc/perf/mpc7450-pmu.c
+++ b/arch/powerpc/perf/mpc7450-pmu.c
@@ -260,8 +260,9 @@ static const u32 pmcsel_mask[N_COUNTER] = {
/*
* Compute MMCR0/1/2 values for a set of events.
*/
-static int mpc7450_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[],
+ unsigned long mmcr[],
+ struct perf_event *pevents[])
{
u8 event_index[N_CLASSES][N_COUNTER];
int n_classevent[N_CLASSES];
diff --git a/arch/powerpc/perf/power4-pmu.c b/arch/powerpc/perf/power4-pmu.c
index 9103a1de864d..ce6072fa481b 100644
--- a/arch/powerpc/perf/power4-pmu.c
+++ b/arch/powerpc/perf/power4-pmu.c
@@ -356,7 +356,7 @@ static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[])
}
static int p4_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
{
unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
unsigned int pmc, unit, byte, psel, lower;
diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index b03b6dc0172d..0526dac66007 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -452,7 +452,7 @@ static int power5p_marked_instr_event(u64 event)
}
static int power5p_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = 0;
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index 1e8ce423c3af..4dc99f9f7962 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -383,7 +383,7 @@ static int power5_marked_instr_event(u64 event)
}
static int power5_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 31128e086fed..9c9d646b68a1 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -175,7 +175,7 @@ static int power6_marked_instr_event(u64 event)
* Assign PMC numbers and compute MMCR1 value for a set of events
*/
static int p6_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 56c67bca2f75..5b62f2389290 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -245,7 +245,7 @@ static int power7_marked_instr_event(u64 event)
}
static int power7_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
{
unsigned long mmcr1 = 0;
unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 639cd9156585..396351db601b 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -15,6 +15,7 @@
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <asm/firmware.h>
+#include <asm/cputable.h>
/*
@@ -266,6 +267,11 @@
#define MMCRA_SDAR_MODE_TLB (1ull << 42)
#define MMCRA_IFM_SHIFT 30
+/* Bits in MMCR2 for POWER8 */
+#define MMCR2_FCS(pmc) (1ull << (63 - (((pmc) - 1) * 9)))
+#define MMCR2_FCP(pmc) (1ull << (62 - (((pmc) - 1) * 9)))
+#define MMCR2_FCH(pmc) (1ull << (57 - (((pmc) - 1) * 9)))
+
static inline bool event_is_fab_match(u64 event)
{
@@ -393,9 +399,10 @@ static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long
}
static int power8_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[],
+ struct perf_event *pevents[])
{
- unsigned long mmcra, mmcr1, unit, combine, psel, cache, val;
+ unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val;
unsigned int pmc, pmc_inuse;
int i;
@@ -410,7 +417,7 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
/* In continous sampling mode, update SDAR on TLB miss */
mmcra = MMCRA_SDAR_MODE_TLB;
- mmcr1 = 0;
+ mmcr1 = mmcr2 = 0;
/* Second pass: assign PMCs, set all MMCR1 fields */
for (i = 0; i < n_ev; ++i) {
@@ -472,6 +479,19 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
mmcra |= val << MMCRA_IFM_SHIFT;
}
+ if (pevents[i]->attr.exclude_user)
+ mmcr2 |= MMCR2_FCP(pmc);
+
+ if (pevents[i]->attr.exclude_hv)
+ mmcr2 |= MMCR2_FCH(pmc);
+
+ if (pevents[i]->attr.exclude_kernel) {
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ mmcr2 |= MMCR2_FCH(pmc);
+ else
+ mmcr2 |= MMCR2_FCS(pmc);
+ }
+
hwc[i] = pmc - 1;
}
@@ -491,6 +511,7 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
+ mmcr[3] = mmcr2;
return 0;
}
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 20139ceeacf6..8b6a8a36fa38 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -257,7 +257,7 @@ static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
}
static int p970_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
+ unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[])
{
unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
unsigned int pmc, unit, byte, psel;
diff --git a/arch/powerpc/perf/req-gen/_begin.h b/arch/powerpc/perf/req-gen/_begin.h
new file mode 100644
index 000000000000..acfb17a55c16
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_begin.h
@@ -0,0 +1,13 @@
+/* Include paths to be used in interface defining headers */
+#ifndef POWERPC_PERF_REQ_GEN_H_
+#define POWERPC_PERF_REQ_GEN_H_
+
+#define CAT2_STR_(t, s) __stringify(t/s)
+#define CAT2_STR(t, s) CAT2_STR_(t, s)
+#define I(...) __VA_ARGS__
+
+#endif
+
+#define REQ_GEN_PREFIX req-gen
+#define REQUEST_BEGIN CAT2_STR(REQ_GEN_PREFIX, _request-begin.h)
+#define REQUEST_END CAT2_STR(REQ_GEN_PREFIX, _request-end.h)
diff --git a/arch/powerpc/perf/req-gen/_clear.h b/arch/powerpc/perf/req-gen/_clear.h
new file mode 100644
index 000000000000..422974f89573
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_clear.h
@@ -0,0 +1,5 @@
+
+#undef __field_
+#undef __count_
+#undef __array_
+#undef REQUEST_
diff --git a/arch/powerpc/perf/req-gen/_end.h b/arch/powerpc/perf/req-gen/_end.h
new file mode 100644
index 000000000000..8a406980b6bf
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_end.h
@@ -0,0 +1,4 @@
+
+#undef REQ_GEN_PREFIX
+#undef REQUEST_BEGIN
+#undef REQUEST_END
diff --git a/arch/powerpc/perf/req-gen/_request-begin.h b/arch/powerpc/perf/req-gen/_request-begin.h
new file mode 100644
index 000000000000..f6d98642cf1d
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_request-begin.h
@@ -0,0 +1,15 @@
+
+#define REQUEST(r_contents) \
+ REQUEST_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, I(r_contents))
+
+#define __field(f_offset, f_bytes, f_name) \
+ __field_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+ f_offset, f_bytes, f_name)
+
+#define __array(f_offset, f_bytes, f_name) \
+ __array_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+ f_offset, f_bytes, f_name)
+
+#define __count(f_offset, f_bytes, f_name) \
+ __count_(REQUEST_NAME, REQUEST_NUM, REQUEST_IDX_KIND, \
+ f_offset, f_bytes, f_name)
diff --git a/arch/powerpc/perf/req-gen/_request-end.h b/arch/powerpc/perf/req-gen/_request-end.h
new file mode 100644
index 000000000000..5573be6c3588
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/_request-end.h
@@ -0,0 +1,8 @@
+#undef REQUEST
+#undef __field
+#undef __array
+#undef __count
+
+#undef REQUEST_NAME
+#undef REQUEST_NUM
+#undef REQUEST_IDX_KIND
diff --git a/arch/powerpc/perf/req-gen/perf.h b/arch/powerpc/perf/req-gen/perf.h
new file mode 100644
index 000000000000..1b122469323d
--- /dev/null
+++ b/arch/powerpc/perf/req-gen/perf.h
@@ -0,0 +1,155 @@
+#ifndef LINUX_POWERPC_PERF_REQ_GEN_PERF_H_
+#define LINUX_POWERPC_PERF_REQ_GEN_PERF_H_
+
+#include <linux/perf_event.h>
+
+#ifndef REQUEST_FILE
+#error "REQUEST_FILE must be defined before including"
+#endif
+
+#ifndef NAME_LOWER
+#error "NAME_LOWER must be defined before including"
+#endif
+
+#ifndef NAME_UPPER
+#error "NAME_UPPER must be defined before including"
+#endif
+
+#define BE_TYPE_b1 __u8
+#define BE_TYPE_b2 __be16
+#define BE_TYPE_b4 __be32
+#define BE_TYPE_b8 __be64
+
+#define BYTES_TO_BE_TYPE(bytes) \
+ BE_TYPE_b##bytes
+
+#define CAT2_(a, b) a ## b
+#define CAT2(a, b) CAT2_(a, b)
+#define CAT3_(a, b, c) a ## b ## c
+#define CAT3(a, b, c) CAT3_(a, b, c)
+
+/*
+ * enumerate the request values as
+ * <NAME_UPPER>_<request name> = <request value>
+ */
+#define REQUEST_VALUE__(name_upper, r_name) name_upper ## _ ## r_name
+#define REQUEST_VALUE_(name_upper, r_name) REQUEST_VALUE__(name_upper, r_name)
+#define REQUEST_VALUE(r_name) REQUEST_VALUE_(NAME_UPPER, r_name)
+
+#include "_clear.h"
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+ REQUEST_VALUE(r_name) = r_value,
+enum CAT2(NAME_LOWER, _requests) {
+#include REQUEST_FILE
+};
+
+/*
+ * For each request:
+ * struct <NAME_LOWER>_<request name> {
+ * r_fields
+ * };
+ */
+#include "_clear.h"
+#define STRUCT_NAME__(name_lower, r_name) name_lower ## _ ## r_name
+#define STRUCT_NAME_(name_lower, r_name) STRUCT_NAME__(name_lower, r_name)
+#define STRUCT_NAME(r_name) STRUCT_NAME_(NAME_LOWER, r_name)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+struct STRUCT_NAME(r_name) { \
+ r_fields \
+};
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name) \
+ BYTES_TO_BE_TYPE(f_bytes) f_name;
+#define __count_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name) \
+ __field_(r_name, r_value, r_idx_1, f_offset, f_bytes, f_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_bytes, a_name) \
+ __u8 a_name[a_bytes];
+
+#include REQUEST_FILE
+
+/*
+ * Generate a check of the field offsets
+ * <NAME_LOWER>_assert_offsets_correct()
+ */
+#include "_clear.h"
+#define REQUEST_(r_name, r_value, index, r_fields) \
+r_fields
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name) \
+ BUILD_BUG_ON(offsetof(struct STRUCT_NAME(r_name), f_name) != f_offset);
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+ __field_(r_name, r_value, r_idx_1, c_offset, c_size, c_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name) \
+ __field_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+
+static inline void CAT2(NAME_LOWER, _assert_offsets_correct)(void)
+{
+#include REQUEST_FILE
+}
+
+/*
+ * Generate event attributes:
+ * PMU_EVENT_ATTR_STRING(<request name>_<field name>,
+ * <NAME_LOWER>_event_attr_<request name>_<field name>,
+ * "request=<request value>"
+ * "starting_index=<starting index type>"
+ * "counter_info_version=CURRENT_COUNTER_INFO_VERSION"
+ * "length=<f_size>"
+ * "offset=<f_offset>")
+ *
+ * TODO: counter_info_version may need to vary, we should interperate the
+ * value to some extent
+ */
+#define EVENT_ATTR_NAME__(name, r_name, c_name) \
+ name ## _event_attr_ ## r_name ## _ ## c_name
+#define EVENT_ATTR_NAME_(name, r_name, c_name) \
+ EVENT_ATTR_NAME__(name, r_name, c_name)
+#define EVENT_ATTR_NAME(r_name, c_name) \
+ EVENT_ATTR_NAME_(NAME_LOWER, r_name, c_name)
+
+#include "_clear.h"
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name)
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+PMU_EVENT_ATTR_STRING( \
+ CAT3(r_name, _, c_name), \
+ EVENT_ATTR_NAME(r_name, c_name), \
+ "request=" __stringify(r_value) "," \
+ r_idx_1 "," \
+ "counter_info_version=" \
+ __stringify(COUNTER_INFO_VERSION_CURRENT) "," \
+ "length=" #c_size "," \
+ "offset=" #c_offset)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+ r_fields
+
+#include REQUEST_FILE
+
+/*
+ * Define event attribute array
+ * static struct attribute *hv_gpci_event_attrs[] = {
+ * &<NAME_LOWER>_event_attr_<request name>_<field name>.attr,
+ * };
+ */
+#include "_clear.h"
+#define __field_(r_name, r_value, r_idx_1, f_offset, f_size, f_name)
+#define __count_(r_name, r_value, r_idx_1, c_offset, c_size, c_name) \
+ &EVENT_ATTR_NAME(r_name, c_name).attr.attr,
+#define __array_(r_name, r_value, r_idx_1, a_offset, a_size, a_name)
+#define REQUEST_(r_name, r_value, r_idx_1, r_fields) \
+ r_fields
+
+static __maybe_unused struct attribute *hv_gpci_event_attrs[] = {
+#include REQUEST_FILE
+ NULL
+};
+
+/* cleanup */
+#include "_clear.h"
+#undef EVENT_ATTR_NAME
+#undef EVENT_ATTR_NAME_
+#undef BIT_NAME
+#undef BIT_NAME_
+#undef STRUCT_NAME
+#undef REQUEST_VALUE
+#undef REQUEST_VALUE_
+
+#endif