Merge tag 'x86_cache_for_v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:
 "A first round of changes towards splitting the arch-specific bits from
  the filesystem bits of resctrl, the ultimate goal being to support
  ARM's equivalent technology MPAM, with the same fs interface (James
  Morse)"

* tag 'x86_cache_for_v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  x86/resctrl: Make resctrl_arch_get_config() return its value
  x86/resctrl: Merge the CDP resources
  x86/resctrl: Expand resctrl_arch_update_domains()'s msr_param range
  x86/resctrl: Remove rdt_cdp_peer_get()
  x86/resctrl: Merge the ctrl_val arrays
  x86/resctrl: Calculate the index from the configuration type
  x86/resctrl: Apply offset correction when config is staged
  x86/resctrl: Make ctrlval arrays the same size
  x86/resctrl: Pass configuration type to resctrl_arch_get_config()
  x86/resctrl: Add a helper to read a closid's configuration
  x86/resctrl: Rename update_domains() to resctrl_arch_update_domains()
  x86/resctrl: Allow different CODE/DATA configurations to be staged
  x86/resctrl: Group staged configuration into a separate struct
  x86/resctrl: Move the schemata names into struct resctrl_schema
  x86/resctrl: Add a helper to read/set the CDP configuration
  x86/resctrl: Swizzle rdt_resource and resctrl_schema in pseudo_lock_region
  x86/resctrl: Pass the schema to resctrl filesystem functions
  x86/resctrl: Add resctrl_arch_get_num_closid()
  x86/resctrl: Store the effective num_closid in the schema
  x86/resctrl: Walk the resctrl schema list instead of an arch list
  ...

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

@@ -174,7 +174,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	struct rdt_resource *r;
 	u32 crmid = 1, nrmid;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
 	/*
 	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
@@ -232,7 +232,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	int cpu;
 	u64 val;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
 	entry->busy = 0;
 	cpu = get_cpu();
@@ -287,6 +287,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 
 static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m;
 	u64 chunks, tval;
 
@@ -318,7 +319,7 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 		return 0;
 	}
 
-	chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width);
+	chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width);
 	m->chunks += chunks;
 	m->prev_msr = tval;
 
@@ -333,7 +334,7 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
  */
 static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m = &rr->d->mbm_local[rmid];
 	u64 tval, cur_bw, chunks;
 
@@ -341,8 +342,8 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
 		return;
 
-	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
-	cur_bw = (get_corrected_mbm_count(rmid, chunks) * r->mon_scale) >> 20;
+	chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width);
+	cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20;
 
 	if (m->delta_comp)
 		m->delta_bw = abs(cur_bw - m->prev_bw);
@@ -421,6 +422,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 {
 	u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
+	struct rdt_hw_resource *hw_r_mba;
+	struct rdt_hw_domain *hw_dom_mba;
 	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
 	struct rdt_domain *dom_mba;
@@ -430,7 +433,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	if (!is_mbm_local_enabled())
 		return;
 
-	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+	hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+	r_mba = &hw_r_mba->r_resctrl;
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
 	pmbm_data = &dom_mbm->mbm_local[rmid];
@@ -440,11 +444,16 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 		pr_warn_once("Failure to get domain for MBA update\n");
 		return;
 	}
+	hw_dom_mba = resctrl_to_arch_dom(dom_mba);
 
 	cur_bw = pmbm_data->prev_bw;
-	user_bw = dom_mba->mbps_val[closid];
+	user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
 	delta_bw = pmbm_data->delta_bw;
-	cur_msr_val = dom_mba->ctrl_val[closid];
+	/*
+	 * resctrl_arch_get_config() chooses the mbps/ctrl value to return
+	 * based on is_mba_sc(). For now, reach into the hw_dom.
+	 */
+	cur_msr_val = hw_dom_mba->ctrl_val[closid];
 
 	/*
 	 * For Ctrl groups read data from child monitor groups.
@@ -479,9 +488,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 		return;
 	}
 
-	cur_msr = r_mba->msr_base + closid;
+	cur_msr = hw_r_mba->msr_base + closid;
 	wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
-	dom_mba->ctrl_val[closid] = new_msr_val;
+	hw_dom_mba->ctrl_val[closid] = new_msr_val;
 
 	/*
 	 * Delta values are updated dynamically package wise for each
@@ -543,7 +552,7 @@ void cqm_handle_limbo(struct work_struct *work)
 
 	mutex_lock(&rdtgroup_mutex);
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
@@ -579,7 +588,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
@@ -676,15 +685,16 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 int rdt_get_mon_l3_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	unsigned int cl_size = boot_cpu_data.x86_cache_size;
 	int ret;
 
-	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
 	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
-	r->mbm_width = MBM_CNTR_WIDTH_BASE;
+	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
-		r->mbm_width += mbm_offset;
+		hw_res->mbm_width += mbm_offset;
 	else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX)
 		pr_warn("Ignoring impossible MBM counter offset\n");
 
@@ -698,7 +708,7 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
 
 	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
-	resctrl_cqm_threshold /= r->mon_scale;
+	resctrl_cqm_threshold /= hw_res->mon_scale;
 
 	ret = dom_data_init(r);
 	if (ret)

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

@@ -250,7 +250,7 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
 	plr->line_size = 0;
 	kfree(plr->kmem);
 	plr->kmem = NULL;
-	plr->r = NULL;
+	plr->s = NULL;
 	if (plr->d)
 		plr->d->plr = NULL;
 	plr->d = NULL;
@@ -294,10 +294,10 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 
 	ci = get_cpu_cacheinfo(plr->cpu);
 
-	plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);
+	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->r->cache_level) {
+		if (ci->info_list[i].level == plr->s->res->cache_level) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
@@ -688,8 +688,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 *   resource, the portion of cache used by it should be made
 	 *   unavailable to all future allocations from both resources.
 	 */
-	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
-	    rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
+	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) ||
+	    resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) {
 		rdt_last_cmd_puts("CDP enabled\n");
 		return -EINVAL;
 	}
@@ -800,7 +800,7 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
 	unsigned long cbm_b;
 
 	if (d->plr) {
-		cbm_len = d->plr->r->cache.cbm_len;
+		cbm_len = d->plr->s->res->cache.cbm_len;
 		cbm_b = d->plr->cbm;
 		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
 			return true;

include/linux/resctrl.h

@@ -2,6 +2,8 @@
 #ifndef _RESCTRL_H
 #define _RESCTRL_H
 
+#include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/pid.h>
 
 #ifdef CONFIG_PROC_CPU_RESCTRL
@@ -13,4 +15,186 @@ int proc_resctrl_show(struct seq_file *m,
 
 #endif
 
+/**
+ * enum resctrl_conf_type - The type of configuration.
+ * @CDP_NONE:	No prioritisation, both code and data are controlled or monitored.
+ * @CDP_CODE:	Configuration applies to instruction fetches.
+ * @CDP_DATA:	Configuration applies to reads and writes.
+ */
+enum resctrl_conf_type {
+	CDP_NONE,
+	CDP_CODE,
+	CDP_DATA,
+};
+
+#define CDP_NUM_TYPES	(CDP_DATA + 1)
+
+/**
+ * struct resctrl_staged_config - parsed configuration to be applied
+ * @new_ctrl:		new ctrl value to be loaded
+ * @have_new_ctrl:	whether the user provided new_ctrl is valid
+ */
+struct resctrl_staged_config {
+	u32			new_ctrl;
+	bool			have_new_ctrl;
+};
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @list:		all instances of this resource
+ * @id:			unique id for this instance
+ * @cpu_mask:		which CPUs share this resource
+ * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
+ * @mbm_total:		saved state for MBM total bandwidth
+ * @mbm_local:		saved state for MBM local bandwidth
+ * @mbm_over:		worker to periodically read MBM h/w counters
+ * @cqm_limbo:		worker to periodically read CQM h/w counters
+ * @mbm_work_cpu:	worker CPU for MBM h/w counters
+ * @cqm_work_cpu:	worker CPU for CQM h/w counters
+ * @plr:		pseudo-locked region (if any) associated with domain
+ * @staged_config:	parsed configuration to be applied
+ */
+struct rdt_domain {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+	unsigned long			*rmid_busy_llc;
+	struct mbm_state		*mbm_total;
+	struct mbm_state		*mbm_local;
+	struct delayed_work		mbm_over;
+	struct delayed_work		cqm_limbo;
+	int				mbm_work_cpu;
+	int				cqm_work_cpu;
+	struct pseudo_lock_region	*plr;
+	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+};
+
+/**
+ * struct resctrl_cache - Cache allocation related data
+ * @cbm_len:		Length of the cache bit mask
+ * @min_cbm_bits:	Minimum number of consecutive bits to be set
+ * @shareable_bits:	Bitmask of shareable resource with other
+ *			executing entities
+ * @arch_has_sparse_bitmaps:	True if a bitmap like f00f is valid.
+ * @arch_has_empty_bitmaps:	True if the '0' bitmap is valid.
+ * @arch_has_per_cpu_cfg:	True if QOS_CFG register for this cache
+ *				level has CPU scope.
+ */
+struct resctrl_cache {
+	unsigned int	cbm_len;
+	unsigned int	min_cbm_bits;
+	unsigned int	shareable_bits;
+	bool		arch_has_sparse_bitmaps;
+	bool		arch_has_empty_bitmaps;
+	bool		arch_has_per_cpu_cfg;
+};
+
+/**
+ * enum membw_throttle_mode - System's memory bandwidth throttling mode
+ * @THREAD_THROTTLE_UNDEFINED:	Not relevant to the system
+ * @THREAD_THROTTLE_MAX:	Memory bandwidth is throttled at the core
+ *				always using smallest bandwidth percentage
+ *				assigned to threads, aka "max throttling"
+ * @THREAD_THROTTLE_PER_THREAD:	Memory bandwidth is throttled at the thread
+ */
+enum membw_throttle_mode {
+	THREAD_THROTTLE_UNDEFINED = 0,
+	THREAD_THROTTLE_MAX,
+	THREAD_THROTTLE_PER_THREAD,
+};
+
+/**
+ * struct resctrl_membw - Memory bandwidth allocation related data
+ * @min_bw:		Minimum memory bandwidth percentage user can request
+ * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @delay_linear:	True if memory B/W delay is in linear scale
+ * @arch_needs_linear:	True if we can't configure non-linear resources
+ * @throttle_mode:	Bandwidth throttling mode when threads request
+ *			different memory bandwidths
+ * @mba_sc:		True if MBA software controller(mba_sc) is enabled
+ * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
+ */
+struct resctrl_membw {
+	u32				min_bw;
+	u32				bw_gran;
+	u32				delay_linear;
+	bool				arch_needs_linear;
+	enum membw_throttle_mode	throttle_mode;
+	bool				mba_sc;
+	u32				*mb_map;
+};
+
+struct rdt_parse_data;
+struct resctrl_schema;
+
+/**
+ * struct rdt_resource - attributes of a resctrl resource
+ * @rid:		The index of the resource
+ * @alloc_enabled:	Is allocation enabled on this machine
+ * @mon_enabled:	Is monitoring enabled for this feature
+ * @alloc_capable:	Is allocation available on this machine
+ * @mon_capable:	Is monitor feature available on this machine
+ * @num_rmid:		Number of RMIDs available
+ * @cache_level:	Which cache level defines scope of this resource
+ * @cache:		Cache allocation related data
+ * @membw:		If the component has bandwidth controls, their properties.
+ * @domains:		All domains for this resource
+ * @name:		Name to use in "schemata" file.
+ * @data_width:		Character width of data when displaying
+ * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
+ * @format_str:		Per resource format string to show domain value
+ * @parse_ctrlval:	Per resource function pointer to parse control values
+ * @evt_list:		List of monitoring events
+ * @fflags:		flags to choose base and info files
+ * @cdp_capable:	Is the CDP feature available on this resource
+ */
+struct rdt_resource {
+	int			rid;
+	bool			alloc_enabled;
+	bool			mon_enabled;
+	bool			alloc_capable;
+	bool			mon_capable;
+	int			num_rmid;
+	int			cache_level;
+	struct resctrl_cache	cache;
+	struct resctrl_membw	membw;
+	struct list_head	domains;
+	char			*name;
+	int			data_width;
+	u32			default_ctrl;
+	const char		*format_str;
+	int			(*parse_ctrlval)(struct rdt_parse_data *data,
+						 struct resctrl_schema *s,
+						 struct rdt_domain *d);
+	struct list_head	evt_list;
+	unsigned long		fflags;
+	bool			cdp_capable;
+};
+
+/**
+ * struct resctrl_schema - configuration abilities of a resource presented to
+ *			   user-space
+ * @list:	Member of resctrl_schema_all.
+ * @name:	The name to use in the "schemata" file.
+ * @conf_type:	Whether this schema is specific to code/data.
+ * @res:	The resource structure exported by the architecture to describe
+ *		the hardware that is configured by this schema.
+ * @num_closid:	The number of closid that can be used with this schema. When
+ *		features like CDP are enabled, this will be lower than the
+ *		hardware supports for the resource.
+ */
+struct resctrl_schema {
+	struct list_head		list;
+	char				name[8];
+	enum resctrl_conf_type		conf_type;
+	struct rdt_resource		*res;
+	u32				num_closid;
+};
+
+/* The number of closid supported by this resource regardless of CDP */
+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);
+
 #endif /* _RESCTRL_H */