Re: [PATCH v6 15/24] x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read()

From: Moger, Babu
Date: Thu Oct 05 2023 - 17:46:23 EST

Hi James,

On 9/14/2023 12:21 PM, James Morse wrote:
Depending on the number of monitors available, Arm's MPAM may need to
allocate a monitor prior to reading the counter value. Allocating a
contended resource may involve sleeping.

add_rmid_to_limbo() calls resctrl_arch_rmid_read() for multiple domains,
the allocation should be valid for all domains.

__check_limbo() and mon_event_count() each make multiple calls to
resctrl_arch_rmid_read(), to avoid extra work on contended systems,
the allocation should be valid for multiple invocations of
resctrl_arch_rmid_read().

Add arch hooks for this allocation, which need calling before
resctrl_arch_rmid_read(). The allocated monitor is passed to
resctrl_arch_rmid_read(), then freed again afterwards. The helper
can be called on any CPU, and can sleep.

Reviewed-by: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>
Tested-by: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>
Tested-By: Peter Newman <peternewman@xxxxxxxxxx>
Signed-off-by: James Morse <james.morse@xxxxxxx>
---
Changes since v3:
* Expanded comment.
* Removed stray header include.
* Reworded commit message.
* Made ctx a void * instead of an int.

Changes since v4:
* Used IS_ERR() in more places.

Changes since v5:
* Pass the error back from mon_event_read() as -EINVAL/Unavailable.
* Add some ratelimited warnings when failing to allocate a mon context
---
arch/x86/include/asm/resctrl.h | 11 ++++++++
arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 7 +++++
arch/x86/kernel/cpu/resctrl/internal.h | 1 +
arch/x86/kernel/cpu/resctrl/monitor.c | 34 +++++++++++++++++++++--
include/linux/resctrl.h | 5 +++-
5 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 1d274dbabc44..29c4cc343787 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -136,6 +136,17 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
return rmid;
}
+/* x86 can always read an rmid, nothing needs allocating */
+struct rdt_resource;
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+{
+ might_sleep();
+ return NULL;
+};
+
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
+ void *ctx) { };
+
void resctrl_cpu_detect(struct cpuinfo_x86 *c);
#else
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index bd263b9a0abd..ce4821ea111b 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -546,6 +546,11 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
rr->d = d;
rr->val = 0;
rr->first = first;
+ rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+ if (IS_ERR(rr->arch_mon_ctx)) {
+ rr->err = -EINVAL;
+ return;
+ }
cpu = cpumask_any_housekeeping(&d->cpu_mask);
@@ -559,6 +564,8 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
else
smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
+
+ resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
}
int rdtgroup_mondata_show(struct seq_file *m, void *arg)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 37bb3de37a4a..66d9ebb5e03a 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -136,6 +136,7 @@ struct rmid_read {
bool first;
int err;
u64 val;
+ void *arch_mon_ctx;
};
extern bool rdt_alloc_capable;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 05d949ec94f1..28a2c8765faf 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -270,7 +270,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
u32 unused, u32 rmid, enum resctrl_event_id eventid,
- u64 *val)
+ u64 *val, void *ignored)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
@@ -325,9 +325,17 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
u32 idx_limit = resctrl_arch_system_num_rmid_idx();
struct rmid_entry *entry;
u32 idx, cur_idx = 1;
+ void *arch_mon_ctx;
bool rmid_dirty;
u64 val = 0;
+ arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
+ if (IS_ERR(arch_mon_ctx)) {
+ pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+ PTR_ERR(arch_mon_ctx));
+ return;
+ }
+
/*
* Skip RMID 0 and start from RMID 1 and check all the RMIDs that
* are marked as busy for occupancy < threshold. If the occupancy
@@ -341,7 +349,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
entry = __rmid_entry(idx);
if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
- QOS_L3_OCCUP_EVENT_ID, &val)) {
+ QOS_L3_OCCUP_EVENT_ID, &val,
+ arch_mon_ctx)) {
rmid_dirty = true;
} else {
rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
@@ -354,6 +363,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
}
cur_idx = idx + 1;
}
+
+ resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
}
bool has_busy_rmid(struct rdt_domain *d)
@@ -532,7 +543,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
}
rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid,
- &tval);
+ &tval, rr->arch_mon_ctx);
if (rr->err)
return rr->err;
@@ -743,11 +754,27 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
if (is_mbm_total_enabled()) {
rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
rr.val = 0;
+ rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+ if (IS_ERR(rr.arch_mon_ctx)) {
+ pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+ PTR_ERR(rr.arch_mon_ctx));
+ return;
+ }
+
__mon_event_count(closid, rmid, &rr);
+
+ resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
}
if (is_mbm_local_enabled()) {
rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
rr.val = 0;
+ rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+ if (IS_ERR(rr.arch_mon_ctx)) {
+ pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+ PTR_ERR(rr.arch_mon_ctx));
+ return;
+ }
+
__mon_event_count(closid, rmid, &rr);
/*
@@ -757,6 +784,7 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
*/
if (is_mba_sc(NULL))
mbm_bw_count(closid, rmid, &rr);
+ resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);

Space before the last line would be cleaner.

if (is_mba_sc(NULL))
mbm_bw_count(closid, rmid, &rr);
+
+ resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);


}
}
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index f7311102e94c..5e4b4df9610b 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -235,6 +235,9 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
* @rmid: rmid of the counter to read.
* @eventid: eventid to read, e.g. L3 occupancy.
* @val: result of the counter read in bytes.
+ * @arch_mon_ctx: An architecture specific value from
+ * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies
+ * the hardware monitor allocated for this read request.
*
* Some architectures need to sleep when first programming some of the counters.
* (specifically: arm64's MPAM cache occupancy counters can return 'not ready'
@@ -248,7 +251,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
*/
int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
u32 closid, u32 rmid, enum resctrl_event_id eventid,
- u64 *val);
+ u64 *val, void *arch_mon_ctx);

Just wondering.. Have you thought about passing rmid_read structure to this function?

Because most of the information is already inside the rmid_read structure. We can avoid passing 7 parameters.

Thanks

Babu

/**
* resctrl_arch_rmid_read_context_check() - warn about invalid contexts