by tip-bot2 for Hou Wenlong

[permalink] [raw]

Subject: [tip: x86/cache] x86/resctrl: Add domain online callback for resctrl work

The following commit has been merged into the x86/cache branch of tip:

Commit-ID: 3a7232cdf19e39e7f24c493117b373788b348af2
Gitweb: https://git.kernel.org/tip/3a7232cdf19e39e7f24c493117b373788b348af2
Author: James Morse <[email protected]>
AuthorDate: Fri, 02 Sep 2022 15:48:11
Committer: Borislav Petkov <[email protected]>
CommitterDate: Thu, 22 Sep 2022 15:13:27 +02:00

x86/resctrl: Add domain online callback for resctrl work

Because domains are exposed to user-space via resctrl, the filesystem
must update its state when CPU hotplug callbacks are triggered.

Some of this work is common to any architecture that would support
resctrl, but the work is tied up with the architecture code to
allocate the memory.

Move domain_setup_mon_state(), the monitor subdir creation call and the
mbm/limbo workers into a new resctrl_online_domain() call. These bits
are not specific to the architecture. Grouping them in one function
allows that code to be moved to /fs/ and re-used by another architecture.

Signed-off-by: James Morse <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Jamie Iles <[email protected]>
Reviewed-by: Shaopeng Tan <[email protected]>
Reviewed-by: Reinette Chatre <[email protected]>
Tested-by: Xin Hao <[email protected]>
Tested-by: Shaopeng Tan <[email protected]>
Tested-by: Cristian Marussi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
arch/x86/kernel/cpu/resctrl/core.c | 53 ++------------------
arch/x86/kernel/cpu/resctrl/internal.h | 2 +-
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 65 +++++++++++++++++++++++--
include/linux/resctrl.h | 1 +-
4 files changed, 67 insertions(+), 54 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 2f87177..25f3014 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -443,42 +443,6 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
return 0;
}

-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
-{
- size_t tsize;
-
- if (is_llc_occupancy_enabled()) {
- d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
- if (!d->rmid_busy_llc)
- return -ENOMEM;
- INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
- }
- if (is_mbm_total_enabled()) {
- tsize = sizeof(*d->mbm_total);
- d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
- if (!d->mbm_total) {
- bitmap_free(d->rmid_busy_llc);
- return -ENOMEM;
- }
- }
- if (is_mbm_local_enabled()) {
- tsize = sizeof(*d->mbm_local);
- d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
- if (!d->mbm_local) {
- bitmap_free(d->rmid_busy_llc);
- kfree(d->mbm_total);
- return -ENOMEM;
- }
- }
-
- if (is_mbm_enabled()) {
- INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
- mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
- }
-
- return 0;
-}
-
/*
* domain_add_cpu - Add a cpu to a resource's domain list.
*
@@ -498,6 +462,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
struct list_head *add_pos = NULL;
struct rdt_hw_domain *hw_dom;
struct rdt_domain *d;
+ int err;

d = rdt_find_domain(r, id, &add_pos);
if (IS_ERR(d)) {
@@ -527,21 +492,15 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
return;
}

- if (r->mon_capable && domain_setup_mon_state(r, d)) {
+ list_add_tail(&d->list, add_pos);
+
+ err = resctrl_online_domain(r, d);
+ if (err) {
+ list_del(&d->list);
kfree(hw_dom->ctrl_val);
kfree(hw_dom->mbps_val);
kfree(hw_dom);
- return;
}
-
- list_add_tail(&d->list, add_pos);
-
- /*
- * If resctrl is mounted, add
- * per domain monitor data directories.
- */
- if (static_branch_unlikely(&rdt_mon_enable_key))
- mkdir_mondata_subdir_allrdtgrp(r, d);
}

static void domain_remove_cpu(int cpu, struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 8828b5c..be48a68 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -524,8 +524,6 @@ void mon_event_count(void *info);
int rdtgroup_mondata_show(struct seq_file *m, void *arg);
void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
unsigned int dom_id);
-void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_domain *d);
void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
struct rdt_domain *d, struct rdtgroup *rdtgrp,
int evtid, int first);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index def7c66..030a703 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2565,16 +2565,13 @@ out_destroy:
* Add all subdirectories of mon_data for "ctrl_mon" groups
* and "monitor" groups with given domain id.
*/
-void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_domain *d)
+static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+ struct rdt_domain *d)
{
struct kernfs_node *parent_kn;
struct rdtgroup *prgrp, *crgrp;
struct list_head *head;

- if (!r->mon_capable)
- return;
-
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
parent_kn = prgrp->mon.mon_data_kn;
mkdir_mondata_subdir(parent_kn, d, r, prgrp);
@@ -3236,6 +3233,64 @@ out:
return ret;
}

+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+{
+ size_t tsize;
+
+ if (is_llc_occupancy_enabled()) {
+ d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
+ if (!d->rmid_busy_llc)
+ return -ENOMEM;
+ }
+ if (is_mbm_total_enabled()) {
+ tsize = sizeof(*d->mbm_total);
+ d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+ if (!d->mbm_total) {
+ bitmap_free(d->rmid_busy_llc);
+ return -ENOMEM;
+ }
+ }
+ if (is_mbm_local_enabled()) {
+ tsize = sizeof(*d->mbm_local);
+ d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+ if (!d->mbm_local) {
+ bitmap_free(d->rmid_busy_llc);
+ kfree(d->mbm_total);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+ int err;
+
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ if (!r->mon_capable)
+ return 0;
+
+ err = domain_setup_mon_state(r, d);
+ if (err)
+ return err;
+
+ if (is_mbm_enabled()) {
+ INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+ mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+ }
+
+ if (is_llc_occupancy_enabled())
+ INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
+
+ /* If resctrl is mounted, add per domain monitor data directories. */
+ if (static_branch_unlikely(&rdt_mon_enable_key))
+ mkdir_mondata_subdir_allrdtgrp(r, d);
+
+ return 0;
+}
+
/*
* rdtgroup_init - rdtgroup initialization
*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 8180c53..d512455 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -192,5 +192,6 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
u32 closid, enum resctrl_conf_type type);
+int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);

#endif /* _RESCTRL_H */

2022-09-23 18:50:14

by tip-bot2 for Hou Wenlong

[permalink] [raw]

Subject: [tip: x86/cache] x86/resctrl: Pass the required parameters into resctrl_arch_rmid_read()

The following commit has been merged into the x86/cache branch of tip:

Commit-ID: 8286618aca331bf17323ff3023ca831ac6e4b86f
Gitweb: https://git.kernel.org/tip/8286618aca331bf17323ff3023ca831ac6e4b86f
Author: James Morse <[email protected]>
AuthorDate: Fri, 02 Sep 2022 15:48:24
Committer: Borislav Petkov <[email protected]>
CommitterDate: Fri, 23 Sep 2022 14:21:25 +02:00

x86/resctrl: Pass the required parameters into resctrl_arch_rmid_read()

resctrl_arch_rmid_read() is intended as the function that an
architecture agnostic resctrl filesystem driver can use to
read a value in bytes from a hardware register. Currently the function
returns the MBM values in chunks directly from hardware.

To convert this to bytes, some correction and overflow calculations
are needed. These depend on the resource and domain structures.
Overflow detection requires the old chunks value. None of this
is available to resctrl_arch_rmid_read(). MPAM requires the
resource and domain structures to find the MMIO device that holds
the registers.

Pass the resource and domain to resctrl_arch_rmid_read(). This makes
rmid_dirty() too big. Instead merge it with its only caller, and the
name is kept as a local variable.

Signed-off-by: James Morse <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Jamie Iles <[email protected]>
Reviewed-by: Shaopeng Tan <[email protected]>
Reviewed-by: Reinette Chatre <[email protected]>
Tested-by: Xin Hao <[email protected]>
Tested-by: Shaopeng Tan <[email protected]>
Tested-by: Cristian Marussi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
arch/x86/kernel/cpu/resctrl/monitor.c | 31 ++++++++++++++------------
include/linux/resctrl.h | 18 ++++++++++++++-
2 files changed, 34 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 51ab76f..262141b 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -167,10 +167,14 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
memset(am, 0, sizeof(*am));
}

-int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+ u32 rmid, enum resctrl_event_id eventid, u64 *val)
{
u64 msr_val;

+ if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+ return -EINVAL;
+
/*
* As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
* with a valid event code for supported resource type and the bits
@@ -192,16 +196,6 @@ int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
return 0;
}

-static bool rmid_dirty(struct rmid_entry *entry)
-{
- u64 val = 0;
-
- if (resctrl_arch_rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val))
- return true;
-
- return val >= resctrl_cqm_threshold;
-}
-
/*
* Check the RMIDs that are marked as busy for this domain. If the
* reported LLC occupancy is below the threshold clear the busy bit and
@@ -213,6 +207,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
struct rmid_entry *entry;
struct rdt_resource *r;
u32 crmid = 1, nrmid;
+ bool rmid_dirty;
+ u64 val = 0;

r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;

@@ -228,7 +224,14 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
break;

entry = __rmid_entry(nrmid);
- if (force_free || !rmid_dirty(entry)) {
+
+ if (resctrl_arch_rmid_read(r, d, entry->rmid,
+ QOS_L3_OCCUP_EVENT_ID, &val))
+ rmid_dirty = true;
+ else
+ rmid_dirty = (val >= resctrl_cqm_threshold);
+
+ if (force_free || !rmid_dirty) {
clear_bit(entry->rmid, d->rmid_busy_llc);
if (!--entry->busy) {
rmid_limbo_count--;
@@ -278,7 +281,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
cpu = get_cpu();
list_for_each_entry(d, &r->domains, list) {
if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
- err = resctrl_arch_rmid_read(entry->rmid,
+ err = resctrl_arch_rmid_read(r, d, entry->rmid,
QOS_L3_OCCUP_EVENT_ID,
&val);
if (err || val <= resctrl_cqm_threshold)
@@ -336,7 +339,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
if (rr->first)
resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);

- rr->err = resctrl_arch_rmid_read(rmid, rr->evtid, &tval);
+ rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval);
if (rr->err)
return rr->err;

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index efe60dd..7ccfa0d 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -219,7 +219,23 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
u32 closid, enum resctrl_conf_type type);
int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
-int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *res);
+
+/**
+ * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
+ * for this resource and domain.
+ * @r: resource that the counter should be read from.
+ * @d: domain that the counter should be read from.
+ * @rmid: rmid of the counter to read.
+ * @eventid: eventid to read, e.g. L3 occupancy.
+ * @val: result of the counter read in chunks.
+ *
+ * Call from process context on a CPU that belongs to domain @d.
+ *
+ * Return:
+ * 0 on success, or -EIO, -EINVAL etc on error.
+ */
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+ u32 rmid, enum resctrl_event_id eventid, u64 *val);

/**
* resctrl_arch_reset_rmid() - Reset any private state associated with rmid