x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read()

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.

__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().

The memory or hardware allocated is not specific to a domain.

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.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Link: https://lore.kernel.org/r/20240213184438.16675-16-james.morse@arm.com
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>

3 files changed, 40 insertions, 3 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index e933e1cdb1c9..52fa0e14cb86 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 81f5de916db8..e089d1a1a055 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -137,6 +137,7 @@ 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 e8aeff6673ea..9b503e6ac490 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -269,7 +269,7 @@ 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);
@@ -324,9 +324,17 @@ 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
@@ -340,7 +348,8 @@ 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);
@@ -353,6 +362,8 @@ 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)
@@ -533,7 +544,7 @@ 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;
 
@@ -722,11 +733,27 @@ 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);
 
 		/*
@@ -736,6 +763,8 @@ 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);
 	}
 }