// SPDX-License-Identifier: GPL-2.0-only/* * Resource Director Technology(RDT) * - Cache Allocation code. * * Copyright (C) 2016 Intel Corporation * * Authors: *    Fenghua Yu <fenghua.yu@intel.com> *    Tony Luck <tony.luck@intel.com> *    Vikas Shivappa <vikas.shivappa@intel.com> * * More information about RDT be found in the Intel (R) x86 Architecture * Software Developer Manual June 2016, volume 3, section 17.17. */ #define pr_fmt(fmt)	"resctrl: " fmt #include <linux/cpu.h>#include <linux/slab.h>#include <linux/err.h>#include <linux/cpuhotplug.h> #include <asm/cpu_device_id.h>#include <asm/resctrl.h>#include "internal.h" /* * rdt_domain structures are kfree()d when their last CPU goes offline, * and allocated when the first CPU in a new domain comes online. * The rdt_resource's domain list is updated when this happens. Readers of * the domain list must either take cpus_read_lock(), or rely on an RCU * read-side critical section, to avoid observing concurrent modification. * All writers take this mutex: */static DEFINE_MUTEX(domain_list_lock); /* * The cached resctrl_pqr_state is strictly per CPU and can never be * updated from a remote CPU. Functions which modify the state * are called with interrupts disabled and no preemption, which * is sufficient for the protection. */DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state); /* * Used to store the max resource name width and max resource data width * to display the schemata in a tabular format */int max_name_width, max_data_width; /* * Global boolean for rdt_alloc which is true if any * resource allocation is enabled. */bool rdt_alloc_capable; 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 ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains)#define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains) struct rdt_hw_resource rdt_resources_all[] = {	[RDT_RESOURCE_L3] =	{		.r_resctrl = {			.rid			= RDT_RESOURCE_L3,			.name			= "L3",			.ctrl_scope		= RESCTRL_L3_CACHE,			.mon_scope		= RESCTRL_L3_CACHE,			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L3),			.mon_domains		= mon_domain_init(RDT_RESOURCE_L3),			.parse_ctrlval		= parse_cbm,			.format_str		= "%d=%0*x",			.fflags			= RFTYPE_RES_CACHE,		},		.msr_base		= MSR_IA32_L3_CBM_BASE,		.msr_update		= cat_wrmsr,	},	[RDT_RESOURCE_L2] =	{		.r_resctrl = {			.rid			= RDT_RESOURCE_L2,			.name			= "L2",			.ctrl_scope		= RESCTRL_L2_CACHE,			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),			.parse_ctrlval		= parse_cbm,			.format_str		= "%d=%0*x",			.fflags			= RFTYPE_RES_CACHE,		},		.msr_base		= MSR_IA32_L2_CBM_BASE,		.msr_update		= cat_wrmsr,	},	[RDT_RESOURCE_MBA] =	{		.r_resctrl = {			.rid			= RDT_RESOURCE_MBA,			.name			= "MB",			.ctrl_scope		= RESCTRL_L3_CACHE,			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),			.parse_ctrlval		= parse_bw,			.format_str		= "%d=%*u",			.fflags			= RFTYPE_RES_MB,		},	},	[RDT_RESOURCE_SMBA] =	{		.r_resctrl = {			.rid			= RDT_RESOURCE_SMBA,			.name			= "SMBA",			.ctrl_scope		= RESCTRL_L3_CACHE,			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),			.parse_ctrlval		= parse_bw,			.format_str		= "%d=%*u",			.fflags			= RFTYPE_RES_MB,		},	},}; u32 resctrl_arch_system_num_rmid_idx(void){	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; 	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */	return r->num_rmid;} /* * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs * as they do not have CPUID enumeration support for Cache allocation. * The check for Vendor/Family/Model is not enough to guarantee that * the MSRs won't #GP fault because only the following SKUs support * CAT: *	Intel(R) Xeon(R)  CPU E5-2658  v3  @  2.20GHz *	Intel(R) Xeon(R)  CPU E5-2648L v3  @  1.80GHz *	Intel(R) Xeon(R)  CPU E5-2628L v3  @  2.00GHz *	Intel(R) Xeon(R)  CPU E5-2618L v3  @  2.30GHz *	Intel(R) Xeon(R)  CPU E5-2608L v3  @  2.00GHz *	Intel(R) Xeon(R)  CPU E5-2658A v3  @  2.20GHz * * Probe by trying to write the first of the L3 cache mask registers * and checking that the bits stick. Max CLOSids is always 4 and max cbm length * is always 20 on hsw server parts. The minimum cache bitmask length * allowed for HSW server is always 2 bits. Hardcode all of them. */static inline void cache_alloc_hsw_probe(void){	struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3];	struct rdt_resource *r  = &hw_res->r_resctrl;	u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0; 	if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm))		return; 	rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0); 	/* If all the bits were set in MSR, return success */	if (l3_cbm_0 != max_cbm)		return; 	hw_res->num_closid = 4;	r->default_ctrl = max_cbm;	r->cache.cbm_len = 20;	r->cache.shareable_bits = 0xc0000;	r->cache.min_cbm_bits = 2;	r->cache.arch_has_sparse_bitmasks = false;	r->alloc_capable = true; 	rdt_alloc_capable = true;} bool is_mba_sc(struct rdt_resource *r){	if (!r)		return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc; 	/*	 * The software controller support is only applicable to MBA resource.	 * Make sure to check for resource type.	 */	if (r->rid != RDT_RESOURCE_MBA)		return false; 	return r->membw.mba_sc;} /* * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values * exposed to user interface and the h/w understandable delay values. * * The non-linear delay values have the granularity of power of two * and also the h/w does not guarantee a curve for configured delay * values vs. actual b/w enforced. * Hence we need a mapping that is pre calibrated so the user can * express the memory b/w as a percentage value. */static inline bool rdt_get_mb_table(struct rdt_resource *r){	/*	 * There are no Intel SKUs as of now to support non-linear delay.	 */	pr_info("MBA b/w map not implemented for cpu:%d, model:%d",		boot_cpu_data.x86, boot_cpu_data.x86_model); 	return false;} static __init bool __get_mem_config_intel(struct rdt_resource *r){	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);	union cpuid_0x10_3_eax eax;	union cpuid_0x10_x_edx edx;	u32 ebx, ecx, max_delay; 	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);	hw_res->num_closid = edx.split.cos_max + 1;	max_delay = eax.split.max_delay + 1;	r->default_ctrl = MAX_MBA_BW;	r->membw.arch_needs_linear = true;	if (ecx & MBA_IS_LINEAR) {		r->membw.delay_linear = true;		r->membw.min_bw = MAX_MBA_BW - max_delay;		r->membw.bw_gran = MAX_MBA_BW - max_delay;	} else {		if (!rdt_get_mb_table(r))			return false;		r->membw.arch_needs_linear = false;	}	r->data_width = 3; 	if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA))		r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;	else		r->membw.throttle_mode = THREAD_THROTTLE_MAX;	thread_throttle_mode_init(); 	r->alloc_capable = true; 	return true;} static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r){	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);	u32 eax, ebx, ecx, edx, subleaf; 	/*	 * Query CPUID_Fn80000020_EDX_x01 for MBA and	 * CPUID_Fn80000020_EDX_x02 for SMBA	 */	subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 :  1; 	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);	hw_res->num_closid = edx + 1;	r->default_ctrl = 1 << eax; 	/* AMD does not use delay */	r->membw.delay_linear = false;	r->membw.arch_needs_linear = false; 	/*	 * AMD does not use memory delay throttle model to control	 * the allocation like Intel does.	 */	r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED;	r->membw.min_bw = 0;	r->membw.bw_gran = 1;	/* Max value is 2048, Data width should be 4 in decimal */	r->data_width = 4; 	r->alloc_capable = true; 	return true;} static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r){	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);	union cpuid_0x10_1_eax eax;	union cpuid_0x10_x_ecx ecx;	union cpuid_0x10_x_edx edx;	u32 ebx; 	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full);	hw_res->num_closid = edx.split.cos_max + 1;	r->cache.cbm_len = eax.split.cbm_len + 1;	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;	r->cache.shareable_bits = ebx & r->default_ctrl;	r->data_width = (r->cache.cbm_len + 3) / 4;	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)		r->cache.arch_has_sparse_bitmasks = ecx.split.noncont;	r->alloc_capable = true;} static void rdt_get_cdp_config(int level){	/*	 * By default, CDP is disabled. CDP can be enabled by mount parameter	 * "cdp" during resctrl file system mount time.	 */	rdt_resources_all[level].cdp_enabled = false;	rdt_resources_all[level].r_resctrl.cdp_capable = true;} static void rdt_get_cdp_l3_config(void){	rdt_get_cdp_config(RDT_RESOURCE_L3);} static void rdt_get_cdp_l2_config(void){	rdt_get_cdp_config(RDT_RESOURCE_L2);} static void mba_wrmsr_amd(struct msr_param *m){	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);	unsigned int i; 	for (i = m->low; i < m->high; i++)		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);} /* * Map the memory b/w percentage value to delay values * that can be written to QOS_MSRs. * There are currently no SKUs which support non linear delay values. */static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r){	if (r->membw.delay_linear)		return MAX_MBA_BW - bw; 	pr_warn_once("Non Linear delay-bw map not supported but queried\n");	return r->default_ctrl;} static void mba_wrmsr_intel(struct msr_param *m){	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);	unsigned int i; 	/*  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], m->res));} static void cat_wrmsr(struct msr_param *m){	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);	unsigned int i; 	for (i = m->low; i < m->high; i++)		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);} struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r){	struct rdt_ctrl_domain *d; 	lockdep_assert_cpus_held(); 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {		/* Find the domain that contains this CPU */		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))			return d;	} 	return NULL;} struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r){	struct rdt_mon_domain *d; 	lockdep_assert_cpus_held(); 	list_for_each_entry(d, &r->mon_domains, hdr.list) {		/* Find the domain that contains this CPU */		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))			return d;	} 	return NULL;} u32 resctrl_arch_get_num_closid(struct rdt_resource *r){	return resctrl_to_arch_res(r)->num_closid;} void rdt_ctrl_update(void *arg){	struct rdt_hw_resource *hw_res;	struct msr_param *m = arg; 	hw_res = resctrl_to_arch_res(m->res);	hw_res->msr_update(m);} /* * rdt_find_domain - Search for a domain id in a resource domain list. * * Search the domain list to find the domain id. If the domain id is * found, return the domain. NULL otherwise.  If the domain id is not * found (and NULL returned) then the first domain with id bigger than * the input id can be returned to the caller via @pos. */struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,				       struct list_head **pos){	struct rdt_domain_hdr *d;	struct list_head *l; 	list_for_each(l, h) {		d = list_entry(l, struct rdt_domain_hdr, list);		/* When id is found, return its domain. */		if (id == d->id)			return d;		/* Stop searching when finding id's position in sorted list. */		if (id < d->id)			break;	} 	if (pos)		*pos = l; 	return NULL;} static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc){	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);	int i; 	/*	 * Initialize the Control MSRs to having no control.	 * For Cache Allocation: Set all bits in cbm	 * For Memory Allocation: Set b/w requested to 100%	 */	for (i = 0; i < hw_res->num_closid; i++, dc++)		*dc = r->default_ctrl;} static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom){	kfree(hw_dom->ctrl_val);	kfree(hw_dom);} static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom){	kfree(hw_dom->arch_mbm_total);	kfree(hw_dom->arch_mbm_local);	kfree(hw_dom);} static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *d){	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);	struct msr_param m;	u32 *dc; 	dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val),			   GFP_KERNEL);	if (!dc)		return -ENOMEM; 	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(&m);	return 0;} /** * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters * @num_rmid:	The size of the MBM counter array * @hw_dom:	The domain that owns the allocated arrays */static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom){	size_t tsize; 	if (is_mbm_total_enabled()) {		tsize = sizeof(*hw_dom->arch_mbm_total);		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);		if (!hw_dom->arch_mbm_total)			return -ENOMEM;	}

Lines 1–500 of 1137. Load more