- Add a tracepoint to read out LLC occupancy of resource monitor IDs with the

goal of freeing them sooner rather than later
 
 - Other code improvements and cleanups
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmZCW64ACgkQEsHwGGHe
 VUq7Dw//ZM+4OX3l0P6NTv4WJ9UDn3IltRm+D61J6hYw19iETlGGAel5T6DI1LPT
 GYAoOazd9ouNjwU0YhOn6Se3SVWKxLLOGH+/RIJtqwiCwTy2nGfSPHw3pnTxwtK4
 pRttm6fPQWIUuQyDrzmbJGP+va4YDtVtDyBkxNlk8pQTvF7X0QCcu6GjNW9r6+Md
 92J2AwzeoDAeIc16vKHru4S3wBCqdP7xZ9GqBb8wrNxBy8taSN4wE9cuwDjev5Yw
 ANGeREv3odWvYQ7p0fQVY2j25ddjGNE4qEEJ1iAIJDh9bIHURAF3s1aSPqcMyHyF
 eB8NNf7ZjQhycmBX9ci6CHYOKc3i25nWiMoaC1iWZKQEviTt3OCEeKr20mjAfKOz
 wlUs55iGrHkbS10kB91Z6lOMDNiIu+x4kuiF5y1W73SDfkY+pYv8zLQL9rhNpYnd
 BEcOF+YaJuhi4Y7GUDb0fWdIUZcfGItSJyNbR8jaznJKcP2pjznSUKqM/AphZyuU
 bVsVsYkYQiE2vl4xYdmyHnxsfnpuMTVNuPpIonyp1mIa77iDVeiwYabkau+pz8L9
 Rv1jhUmYVfawxKiRc6tOQAsxOtAiqrm2GBpZlisw8KtfzZaPC9h7U7bXC4up1TtH
 nZVt+qV/8M9nc3Trocb+d8djbrv+Uqh4EHPTBbFEfW6qsMFsXhk=
 =8EKr
 -----END PGP SIGNATURE-----

Merge tag 'x86_cache_for_v6.10_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:

 - Add a tracepoint to read out LLC occupancy of resource monitor IDs
   with the goal of freeing them sooner rather than later

 - Other code improvements and cleanups

* tag 'x86_cache_for_v6.10_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Add tracepoint for llc_occupancy tracking
  x86/resctrl: Rename pseudo_lock_event.h to trace.h
  x86/resctrl: Simplify call convention for MSR update functions
  x86/resctrl: Pass domain to target CPU

Documentation/arch/x86/resctrl.rst

@@ -446,6 +446,12 @@ during mkdir.
 max_threshold_occupancy is a user configurable value to determine the
 occupancy at which an RMID can be freed.
 
+The mon_llc_occupancy_limbo tracepoint gives the precise occupancy in bytes
+for a subset of RMID that are not immediately available for allocation.
+This can't be relied on to produce output every second, it may be necessary
+to attempt to create an empty monitor group to force an update. Output may
+only be produced if creation of a control or monitor group fails.
+
 Schemata files - general concepts
 ---------------------------------
 Each line in the file describes one resource. The line starts with

arch/x86/kernel/cpu/resctrl/core.c

@@ -56,14 +56,9 @@ int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
-		struct rdt_resource *r);
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
-	      struct rdt_resource *r);
+static void mba_wrmsr_intel(struct msr_param *m);
+static void cat_wrmsr(struct msr_param *m);
+static void mba_wrmsr_amd(struct msr_param *m);
 
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
 
@@ -309,12 +304,11 @@ static void rdt_get_cdp_l2_config(void)
 	rdt_get_cdp_config(RDT_RESOURCE_L2);
 }
 
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void mba_wrmsr_amd(struct msr_param *m)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
 	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
 	for (i = m->low; i < m->high; i++)
 		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -334,25 +328,22 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 	return r->default_ctrl;
 }
 
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
-		struct rdt_resource *r)
+static void mba_wrmsr_intel(struct msr_param *m)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
 	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
 	/*  Write the delay values for mba. */
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r));
+		wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
 }
 
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void cat_wrmsr(struct msr_param *m)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
 	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
 	for (i = m->low; i < m->high; i++)
 		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -362,6 +353,8 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
 {
 	struct rdt_domain *d;
 
+	lockdep_assert_cpus_held();
+
 	list_for_each_entry(d, &r->domains, list) {
 		/* Find the domain that contains this CPU */
 		if (cpumask_test_cpu(cpu, &d->cpu_mask))
@@ -378,19 +371,11 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
 
 void rdt_ctrl_update(void *arg)
 {
+	struct rdt_hw_resource *hw_res;
 	struct msr_param *m = arg;
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
-	struct rdt_resource *r = m->res;
-	int cpu = smp_processor_id();
-	struct rdt_domain *d;
 
-	d = get_domain_from_cpu(cpu, r);
-	if (d) {
-		hw_res->msr_update(d, m, r);
-		return;
-	}
-	pr_warn_once("cpu %d not found in any domain for resource %s\n",
-		     cpu, r->name);
+	hw_res = resctrl_to_arch_res(m->res);
+	hw_res->msr_update(m);
 }
 
 /*
@@ -463,9 +448,11 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 	hw_dom->ctrl_val = dc;
 	setup_default_ctrlval(r, dc);
 
+	m.res = r;
+	m.dom = d;
 	m.low = 0;
 	m.high = hw_res->num_closid;
-	hw_res->msr_update(d, &m, r);
+	hw_res->msr_update(&m);
 	return 0;
 }
 

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -272,22 +272,6 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
-			 struct resctrl_staged_config *cfg, u32 idx,
-			 cpumask_var_t cpu_mask)
-{
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
-
-	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
-		cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
-		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
-
-		return true;
-	}
-
-	return false;
-}
-
 int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
@@ -302,9 +286,10 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
 	hw_dom->ctrl_val[idx] = cfg_val;
 
 	msr_param.res = r;
+	msr_param.dom = d;
 	msr_param.low = idx;
 	msr_param.high = idx + 1;
-	hw_res->msr_update(d, &msr_param, r);
+	hw_res->msr_update(&msr_param);
 
 	return 0;
 }
@@ -315,48 +300,39 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	struct rdt_hw_domain *hw_dom;
 	struct msr_param msr_param;
 	enum resctrl_conf_type t;
-	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
 	u32 idx;
 
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	msr_param.res = NULL;
 	list_for_each_entry(d, &r->domains, list) {
 		hw_dom = resctrl_to_arch_dom(d);
+		msr_param.res = NULL;
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
 				continue;
 
 			idx = get_config_index(closid, t);
-			if (!apply_config(hw_dom, cfg, idx, cpu_mask))
+			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
 				continue;
+			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 			if (!msr_param.res) {
 				msr_param.low = idx;
 				msr_param.high = msr_param.low + 1;
 				msr_param.res = r;
+				msr_param.dom = d;
 			} else {
 				msr_param.low = min(msr_param.low, idx);
 				msr_param.high = max(msr_param.high, idx + 1);
 			}
 		}
+		if (msr_param.res)
+			smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	if (cpumask_empty(cpu_mask))
-		goto done;
-
-	/* Update resource control msr on all the CPUs. */
-	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-done:
-	free_cpumask_var(cpu_mask);
-
 	return 0;
 }
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -379,11 +379,13 @@ static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
 /**
  * struct msr_param - set a range of MSRs from a domain
  * @res:       The resource to use
+ * @dom:       The domain to update
  * @low:       Beginning index from base MSR
  * @high:      End index
  */
 struct msr_param {
 	struct rdt_resource	*res;
+	struct rdt_domain	*dom;
 	u32			low;
 	u32			high;
 };
@@ -443,8 +445,7 @@ struct rdt_hw_resource {
 	struct rdt_resource	r_resctrl;
 	u32			num_closid;
 	unsigned int		msr_base;
-	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
-				 struct rdt_resource *r);
+	void			(*msr_update)(struct msr_param *m);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
 	unsigned int		mbm_cfg_mask;

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -24,6 +24,7 @@
 #include <asm/resctrl.h>
 
 #include "internal.h"
+#include "trace.h"
 
 /**
  * struct rmid_entry - dirty tracking for all RMID.
@@ -354,6 +355,16 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 			rmid_dirty = true;
 		} else {
 			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+
+			/*
+			 * x86's CLOSID and RMID are independent numbers, so the entry's
+			 * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
+			 * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
+			 * used to select the configuration. It is thus necessary to track both
+			 * CLOSID and RMID because there may be dependencies between them
+			 * on some architectures.
+			 */
+			trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->id, val);
 		}
 
 		if (force_free || !rmid_dirty) {

arch/x86/kernel/cpu/resctrl/pseudo_lock.c

@@ -31,7 +31,7 @@
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
-#include "pseudo_lock_event.h"
+#include "trace.h"
 
 /*
  * The bits needed to disable hardware prefetching varies based on the

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -2813,16 +2813,12 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_domain *hw_dom;
 	struct msr_param msr_param;
-	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
 	int i;
 
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	msr_param.res = r;
 	msr_param.low = 0;
 	msr_param.high = hw_res->num_closid;
@@ -2834,17 +2830,13 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	 */
 	list_for_each_entry(d, &r->domains, list) {
 		hw_dom = resctrl_to_arch_dom(d);
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 
 		for (i = 0; i < hw_res->num_closid; i++)
 			hw_dom->ctrl_val[i] = r->default_ctrl;
+		msr_param.dom = d;
+		smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	/* Update CBM on all the CPUs in cpu_mask */
-	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-	free_cpumask_var(cpu_mask);
-
 	return 0;
 }
 

arch/x86/kernel/cpu/resctrl/trace.h

@@ -2,8 +2,8 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM resctrl
 
-#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_PSEUDO_LOCK_H
+#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RESCTRL_H
 
 #include <linux/tracepoint.h>
 
@@ -35,9 +35,25 @@ TRACE_EVENT(pseudo_lock_l3,
 	    TP_printk("hits=%llu miss=%llu",
 		      __entry->l3_hits, __entry->l3_miss));
 
-#endif /* _TRACE_PSEUDO_LOCK_H */
+TRACE_EVENT(mon_llc_occupancy_limbo,
+	    TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
+	    TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
+	    TP_STRUCT__entry(__field(u32, ctrl_hw_id)
+			     __field(u32, mon_hw_id)
+			     __field(int, domain_id)
+			     __field(u64, llc_occupancy_bytes)),
+	    TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
+			   __entry->mon_hw_id = mon_hw_id;
+			   __entry->domain_id = domain_id;
+			   __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
+	    TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
+		      __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
+		      __entry->llc_occupancy_bytes)
+	   );
+
+#endif /* _TRACE_RESCTRL_H */
 
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE pseudo_lock_event
+#define TRACE_INCLUDE_FILE trace
 #include <trace/define_trace.h>