Merge tag 'x86_cache_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cache resource control updates from Borislav Petkov:

 - More work by James Morse to disentangle the resctrl filesystem
   generic code from the architectural one with the endgoal of plugging
   ARM's MPAM implementation into it too so that the user interface
   remains the same

 - Properly restore the MSR_MISC_FEATURE_CONTROL value instead of
   blindly overwriting it to 0

* tag 'x86_cache_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
  x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's boot_cpu_data
  x86/resctrl: Rename and change the units of resctrl_cqm_threshold
  x86/resctrl: Move get_corrected_mbm_count() into resctrl_arch_rmid_read()
  x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()
  x86/resctrl: Pass the required parameters into resctrl_arch_rmid_read()
  x86/resctrl: Abstract __rmid_read()
  x86/resctrl: Allow per-rmid arch private storage to be reset
  x86/resctrl: Add per-rmid arch private storage for overflow and chunks
  x86/resctrl: Calculate bandwidth from the previous __mon_event_count() chunks
  x86/resctrl: Allow update_mba_bw() to update controls directly
  x86/resctrl: Remove architecture copy of mbps_val
  x86/resctrl: Switch over to the resctrl mbps_val list
  x86/resctrl: Create mba_sc configuration in the rdt_domain
  x86/resctrl: Abstract and use supports_mba_mbps()
  x86/resctrl: Remove set_mba_sc()s control array re-initialisation
  x86/resctrl: Add domain offline callback for resctrl work
  x86/resctrl: Group struct rdt_hw_domain cleanup
  x86/resctrl: Add domain online callback for resctrl work
  x86/resctrl: Merge mon_capable and mon_enabled
  ...

1 files changed, 180 insertions, 36 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index f276aff521e8..e5a48f05e787 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1030,10 +1030,7 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of,
 static int max_threshold_occ_show(struct kernfs_open_file *of,
 				  struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-
-	seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale);
+	seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
 
 	return 0;
 }
@@ -1055,7 +1052,6 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
 static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 				       char *buf, size_t nbytes, loff_t off)
 {
-	struct rdt_hw_resource *hw_res;
 	unsigned int bytes;
 	int ret;
 
@@ -1063,11 +1059,10 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	if (ret)
 		return ret;
 
-	if (bytes > (boot_cpu_data.x86_cache_size * 1024))
+	if (bytes > resctrl_rmid_realloc_limit)
 		return -EINVAL;
 
-	hw_res = resctrl_to_arch_res(of->kn->parent->priv);
-	resctrl_cqm_threshold = bytes / hw_res->mon_scale;
+	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
 
 	return nbytes;
 }
@@ -1356,11 +1351,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 			      struct seq_file *s, void *v)
 {
 	struct resctrl_schema *schema;
+	enum resctrl_conf_type type;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 	unsigned int size;
 	int ret = 0;
+	u32 closid;
 	bool sep;
 	u32 ctrl;
 
@@ -1386,8 +1383,11 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 		goto out;
 	}
 
+	closid = rdtgrp->closid;
+
 	list_for_each_entry(schema, &resctrl_schema_all, list) {
 		r = schema->res;
+		type = schema->conf_type;
 		sep = false;
 		seq_printf(s, "%*s:", max_name_width, schema->name);
 		list_for_each_entry(d, &r->domains, list) {
@@ -1396,9 +1396,12 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 				size = 0;
 			} else {
-				ctrl = resctrl_arch_get_config(r, d,
-							       rdtgrp->closid,
-							       schema->conf_type);
+				if (is_mba_sc(r))
+					ctrl = d->mbps_val[closid];
+				else
+					ctrl = resctrl_arch_get_config(r, d,
+								       closid,
+								       type);
 				if (r->rid == RDT_RESOURCE_MBA)
 					size = ctrl;
 				else
@@ -1756,7 +1759,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 	if (ret)
 		goto out_destroy;
 
-	/* loop over enabled controls, these are all alloc_enabled */
+	/* loop over enabled controls, these are all alloc_capable */
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
 		fflags =  r->fflags | RF_CTRL_INFO;
@@ -1765,7 +1768,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 			goto out_destroy;
 	}
 
-	for_each_mon_enabled_rdt_resource(r) {
+	for_each_mon_capable_rdt_resource(r) {
 		fflags =  r->fflags | RF_MON_INFO;
 		sprintf(name, "%s_MON", r->name);
 		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
@@ -1889,26 +1892,61 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
 		l3_qos_cfg_update(&hw_res->cdp_enabled);
 }
 
+static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
+{
+	u32 num_closid = resctrl_arch_get_num_closid(r);
+	int cpu = cpumask_any(&d->cpu_mask);
+	int i;
+
+	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
+				   GFP_KERNEL, cpu_to_node(cpu));
+	if (!d->mbps_val)
+		return -ENOMEM;
+
+	for (i = 0; i < num_closid; i++)
+		d->mbps_val[i] = MBA_MAX_MBPS;
+
+	return 0;
+}
+
+static void mba_sc_domain_destroy(struct rdt_resource *r,
+				  struct rdt_domain *d)
+{
+	kfree(d->mbps_val);
+	d->mbps_val = NULL;
+}
+
 /*
- * Enable or disable the MBA software controller
- * which helps user specify bandwidth in MBps.
  * MBA software controller is supported only if
  * MBM is supported and MBA is in linear scale.
  */
+static bool supports_mba_mbps(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+
+	return (is_mbm_local_enabled() &&
+		r->alloc_capable && is_mba_linear());
+}
+
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ */
 static int set_mba_sc(bool mba_sc)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
-	struct rdt_hw_domain *hw_dom;
+	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rdt_domain *d;
+	int i;
 
-	if (!is_mbm_enabled() || !is_mba_linear() ||
-	    mba_sc == is_mba_sc(r))
+	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
 		return -EINVAL;
 
 	r->membw.mba_sc = mba_sc;
+
 	list_for_each_entry(d, &r->domains, list) {
-		hw_dom = resctrl_to_arch_dom(d);
-		setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val);
+		for (i = 0; i < num_closid; i++)
+			d->mbps_val[i] = MBA_MAX_MBPS;
 	}
 
 	return 0;
@@ -2106,7 +2144,7 @@ static int schemata_list_create(void)
 	struct rdt_resource *r;
 	int ret = 0;
 
-	for_each_alloc_enabled_rdt_resource(r) {
+	for_each_alloc_capable_rdt_resource(r) {
 		if (resctrl_arch_get_cdp_enabled(r->rid)) {
 			ret = schemata_list_add(r, CDP_CODE);
 			if (ret)
@@ -2261,7 +2299,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->enable_cdpl2 = true;
 		return 0;
 	case Opt_mba_mbps:
-		if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		if (!supports_mba_mbps())
 			return -EINVAL;
 		ctx->enable_mba_mbps = true;
 		return 0;
@@ -2452,7 +2490,7 @@ static void rdt_kill_sb(struct super_block *sb)
 	set_mba_sc(false);
 
 	/*Put everything back to default values. */
-	for_each_alloc_enabled_rdt_resource(r)
+	for_each_alloc_capable_rdt_resource(r)
 		reset_all_ctrls(r);
 	cdp_disable_all();
 	rmdir_all_sub();
@@ -2499,14 +2537,12 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
  * Remove all subdirectories of mon_data of ctrl_mon groups
  * and monitor groups with given domain id.
  */
-void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id)
+static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+					   unsigned int dom_id)
 {
 	struct rdtgroup *prgrp, *crgrp;
 	char name[32];
 
-	if (!r->mon_enabled)
-		return;
-
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		sprintf(name, "mon_%s_%02d", r->name, dom_id);
 		kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);
@@ -2565,16 +2601,13 @@ 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_enabled)
-		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);
@@ -2642,7 +2675,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
 	 * Create the subdirectories for each domain. Note that all events
 	 * in a domain like L3 are grouped into a resource whose domain is L3
 	 */
-	for_each_mon_enabled_rdt_resource(r) {
+	for_each_mon_capable_rdt_resource(r) {
 		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
 		if (ret)
 			goto out_destroy;
@@ -2786,14 +2819,19 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
 }
 
 /* Initialize MBA resource with default values. */
-static void rdtgroup_init_mba(struct rdt_resource *r)
+static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
 {
 	struct resctrl_staged_config *cfg;
 	struct rdt_domain *d;
 
 	list_for_each_entry(d, &r->domains, list) {
+		if (is_mba_sc(r)) {
+			d->mbps_val[closid] = MBA_MAX_MBPS;
+			continue;
+		}
+
 		cfg = &d->staged_config[CDP_NONE];
-		cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+		cfg->new_ctrl = r->default_ctrl;
 		cfg->have_new_ctrl = true;
 	}
 }
@@ -2808,7 +2846,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
 		if (r->rid == RDT_RESOURCE_MBA) {
-			rdtgroup_init_mba(r);
+			rdtgroup_init_mba(r, rdtgrp->closid);
+			if (is_mba_sc(r))
+				continue;
 		} else {
 			ret = rdtgroup_init_cat(s, rdtgrp->closid);
 			if (ret < 0)
@@ -3236,6 +3276,110 @@ out:
 	return ret;
 }
 
+static void domain_destroy_mon_state(struct rdt_domain *d)
+{
+	bitmap_free(d->rmid_busy_llc);
+	kfree(d->mbm_total);
+	kfree(d->mbm_local);
+}
+
+void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+		mba_sc_domain_destroy(r, d);
+
+	if (!r->mon_capable)
+		return;
+
+	/*
+	 * If resctrl is mounted, remove all the
+	 * per domain monitor data directories.
+	 */
+	if (static_branch_unlikely(&rdt_mon_enable_key))
+		rmdir_mondata_subdir_allrdtgrp(r, d->id);
+
+	if (is_mbm_enabled())
+		cancel_delayed_work(&d->mbm_over);
+	if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
+		/*
+		 * When a package is going down, forcefully
+		 * decrement rmid->ebusy. There is no way to know
+		 * that the L3 was flushed and hence may lead to
+		 * incorrect counts in rare scenarios, but leaving
+		 * the RMID as busy creates RMID leaks if the
+		 * package never comes back.
+		 */
+		__check_limbo(d, true);
+		cancel_delayed_work(&d->cqm_limbo);
+	}
+
+	domain_destroy_mon_state(d);
+}
+
+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 (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+		/* RDT_RESOURCE_MBA is never mon_capable */
+		return mba_sc_domain_allocate(r, d);
+
+	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
  *