[PATCH v11 11/13] x86/resctrl: Add interface to write mbm_total_bytes_config

From: Babu Moger
Date: Mon Jan 09 2023 - 11:45:19 EST


The event configuration for mbm_total_bytes can be changed by the user by
writing to the file /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config.

The event configuration settings are domain specific and affect all the
CPUs in the domain.

Following are the types of events supported:

==== ===========================================================
Bits Description
==== ===========================================================
6 Dirty Victims from the QOS domain to all types of memory
5 Reads to slow memory in the non-local NUMA domain
4 Reads to slow memory in the local NUMA domain
3 Non-temporal writes to non-local NUMA domain
2 Non-temporal writes to local NUMA domain
1 Reads to memory in the non-local NUMA domain
0 Reads to memory in the local NUMA domain
==== ===========================================================

For example:
To change the mbm_total_bytes to count only reads on domain 0, the bits
0, 1, 4 and 5 needs to be set, which is 110011b (in hex 0x33). Run the
command.
$echo 0=0x33 > /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config

To change the mbm_total_bytes to count all the slow memory reads on
domain 1, the bits 4 and 5 needs to be set which is 110000b (in hex 0x30).
Run the command.
$echo 1=0x30 > /sys/fs/resctrl/info/L3_MON/mbm_total_bytes_config

Signed-off-by: Babu Moger <babu.moger@xxxxxxx>
---
arch/x86/kernel/cpu/resctrl/monitor.c | 17 ++++
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 124 ++++++++++++++++++++++++-
include/linux/resctrl.h | 11 +++
3 files changed, 151 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 7c8a3a745041..c50c43656bdb 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -176,6 +176,23 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
memset(am, 0, sizeof(*am));
}

+/*
+ * Assumes that hardware counters are also reset and thus that there is
+ * no need to record initial non-zero counts.
+ */
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+{
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+
+ if (is_mbm_total_enabled())
+ memset(hw_dom->arch_mbm_total, 0,
+ sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
+
+ if (is_mbm_local_enabled())
+ memset(hw_dom->arch_mbm_local, 0,
+ sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
+}
+
static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
{
u64 shift = 64 - width, chunks;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 43e2a866e8e0..21fdb4a48a11 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1515,6 +1515,127 @@ static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
return 0;
}

+static void mon_event_config_write(void *info)
+{
+ struct mon_config_info *mon_info = info;
+ unsigned int index;
+
+ index = mon_event_config_index_get(mon_info->evtid);
+ if (index == INVALID_CONFIG_INDEX) {
+ pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+ return;
+ }
+ wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
+}
+
+static int mbm_config_write_domain(struct rdt_resource *r,
+ struct rdt_domain *d, u32 evtid, u32 val)
+{
+ struct mon_config_info mon_info = {0};
+ int ret = 0;
+
+ /* mon_config cannot be more than the supported set of events */
+ if (val > MAX_EVT_CONFIG_BITS) {
+ rdt_last_cmd_puts("Invalid event configuration\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Read the current config value first. If both are the same then
+ * no need to write it again.
+ */
+ mon_info.evtid = evtid;
+ mondata_config_read(d, &mon_info);
+ if (mon_info.mon_config == val)
+ goto out;
+
+ mon_info.mon_config = val;
+
+ /*
+ * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
+ * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
+ * are scoped at the domain level. Writing any of these MSRs
+ * on one CPU is observed by all the CPUs in the domain.
+ */
+ smp_call_function_any(&d->cpu_mask, mon_event_config_write,
+ &mon_info, 1);
+
+ /*
+ * When an Event Configuration is changed, the bandwidth counters
+ * for all RMIDs and Events will be cleared by the hardware. The
+ * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
+ * every RMID on the next read to any event for every RMID.
+ * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
+ * cleared while it is tracked by the hardware. Clear the
+ * mbm_local and mbm_total counts for all the RMIDs.
+ */
+ resctrl_arch_reset_rmid_all(r, d);
+
+out:
+ return ret;
+}
+
+static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
+{
+ char *dom_str = NULL, *id_str;
+ unsigned long dom_id, val;
+ struct rdt_domain *d;
+ int ret = 0;
+
+next:
+ if (!tok || tok[0] == '\0')
+ return 0;
+
+ /* Start processing the strings for each domain */
+ dom_str = strim(strsep(&tok, ";"));
+ id_str = strsep(&dom_str, "=");
+
+ if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
+ rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
+ return -EINVAL;
+ }
+
+ if (!dom_str || kstrtoul(dom_str, 16, &val)) {
+ rdt_last_cmd_puts("Non-numeric event configuration value\n");
+ return -EINVAL;
+ }
+
+ list_for_each_entry(d, &r->domains, list) {
+ if (d->id == dom_id) {
+ ret = mbm_config_write_domain(r, d, evtid, val);
+ if (ret)
+ return -EINVAL;
+ goto next;
+ }
+ }
+
+ return -EINVAL;
+}
+
+static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ struct rdt_resource *r = of->kn->parent->priv;
+ int ret;
+
+ /* Valid input requires a trailing newline */
+ if (nbytes == 0 || buf[nbytes - 1] != '\n')
+ return -EINVAL;
+
+ mutex_lock(&rdtgroup_mutex);
+
+ rdt_last_cmd_clear();
+
+ buf[nbytes - 1] = '\0';
+
+ ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+ mutex_unlock(&rdtgroup_mutex);
+
+ return ret ?: nbytes;
+}
+
/* rdtgroup information files for one cache resource. */
static struct rftype res_common_files[] = {
{
@@ -1615,9 +1736,10 @@ static struct rftype res_common_files[] = {
},
{
.name = "mbm_total_bytes_config",
- .mode = 0444,
+ .mode = 0644,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = mbm_total_bytes_config_show,
+ .write = mbm_total_bytes_config_write,
},
{
.name = "mbm_local_bytes_config",
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 0cee154abc9f..8334eeacfec5 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -250,6 +250,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
u32 rmid, enum resctrl_event_id eventid);

+/**
+ * resctrl_arch_reset_rmid_all() - Reset all private state associated with
+ * all rmids and eventids.
+ * @r: The resctrl resource.
+ * @d: The domain for which all architectural counter state will
+ * be cleared.
+ *
+ * This can be called from any CPU.
+ */
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d);
+
extern unsigned int resctrl_rmid_realloc_threshold;
extern unsigned int resctrl_rmid_realloc_limit;

--
2.34.1