Merge tag 'x86_cache_updates_for_5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cache resource control updates from Borislav Petkov:
 "Add support for wider Memory Bandwidth Monitoring counters by querying
  their width from CPUID.

  As a prerequsite for that, streamline and unify the CPUID detection of
  the respective resource control attributes.

  By Reinette Chatre"

* tag 'x86_cache_updates_for_5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Support wider MBM counters
  x86/resctrl: Support CPUID enumeration of MBM counter width
  x86/resctrl: Maintain MBM counter width per resource
  x86/resctrl: Query LLC monitoring properties once during boot
  x86/resctrl: Remove unnecessary RMID checks
  x86/cpu: Move resctrl CPUID code to resctrl/
  x86/resctrl: Rename asm/resctrl_sched.h to asm/resctrl.h

9 files changed, 80 insertions, 58 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 547ad7bbf0e0..c36e89930965 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -18,6 +18,7 @@
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
 #include <asm/debugreg.h>
+#include <asm/resctrl.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -597,6 +598,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
 		}
 	}
+
+	resctrl_cpu_detect(c);
 }
 
 static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index bed0cb83fe24..d07809286b95 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -854,30 +854,6 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	}
 }
 
-static void init_cqm(struct cpuinfo_x86 *c)
-{
-	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
-		c->x86_cache_max_rmid  = -1;
-		c->x86_cache_occ_scale = -1;
-		return;
-	}
-
-	/* will be overridden if occupancy monitoring exists */
-	c->x86_cache_max_rmid = cpuid_ebx(0xf);
-
-	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
-	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
-	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
-		u32 eax, ebx, ecx, edx;
-
-		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
-		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
-
-		c->x86_cache_max_rmid  = ecx;
-		c->x86_cache_occ_scale = ebx;
-	}
-}
-
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -945,7 +921,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
-	init_cqm(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
@@ -1377,20 +1352,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 #endif
 }
 
-static void x86_init_cache_qos(struct cpuinfo_x86 *c)
-{
-	/*
-	 * The heavy lifting of max_rmid and cache_occ_scale are handled
-	 * in get_cpu_cap().  Here we just set the max_rmid for the boot_cpu
-	 * in case CQM bits really aren't there in this CPU.
-	 */
-	if (c != &boot_cpu_data) {
-		boot_cpu_data.x86_cache_max_rmid =
-			min(boot_cpu_data.x86_cache_max_rmid,
-			    c->x86_cache_max_rmid);
-	}
-}
-
 /*
  * Validate that ACPI/mptables have the same information about the
  * effective APIC id and update the package map.
@@ -1503,7 +1464,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #endif
 
 	x86_init_rdrand(c);
-	x86_init_cache_qos(c);
 	setup_pku(c);
 
 	/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a19a680542ce..166d7c355896 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -22,6 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cmdline.h>
 #include <asm/traps.h>
+#include <asm/resctrl.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -322,6 +323,11 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		detect_ht_early(c);
 }
 
+static void bsp_init_intel(struct cpuinfo_x86 *c)
+{
+	resctrl_cpu_detect(c);
+}
+
 #ifdef CONFIG_X86_32
 /*
  *	Early probe support logic for ppro memory erratum #50
@@ -961,6 +967,7 @@ static const struct cpu_dev intel_cpu_dev = {
 #endif
 	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
+	.c_bsp_init	= bsp_init_intel,
 	.c_init		= init_intel,
 	.c_x86_vendor	= X86_VENDOR_INTEL,
 };
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index d8cc5223b7ce..12f967c6b603 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/intel-family.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include "internal.h"
 
 /* Mutex to protect rdtgroup access. */
@@ -958,6 +958,36 @@ static __init void rdt_init_res_defs(void)
 
 static enum cpuhp_state rdt_online;
 
+/* Runs once on the BSP during boot. */
+void resctrl_cpu_detect(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		c->x86_cache_mbm_width_offset = -1;
+		return;
+	}
+
+	/* will be overridden if occupancy monitoring exists */
+	c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_cache_max_rmid  = ecx;
+		c->x86_cache_occ_scale = ebx;
+		if (c->x86_vendor == X86_VENDOR_INTEL)
+			c->x86_cache_mbm_width_offset = eax & 0xff;
+		else
+			c->x86_cache_mbm_width_offset = -1;
+	}
+}
+
 static int __init resctrl_late_init(void)
 {
 	struct rdt_resource *r;
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 055c8613b531..934c8fb8a64a 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -495,14 +495,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	return ret;
 }
 
-void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
-		    struct rdtgroup *rdtgrp, int evtid, int first)
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    int evtid, int first)
 {
 	/*
 	 * setup the parameters to send to the IPI to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
+	rr->r = r;
 	rr->d = d;
 	rr->val = 0;
 	rr->first = first;
@@ -539,7 +541,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		goto out;
 	}
 
-	mon_event_read(&rr, d, rdtgrp, evtid, false);
+	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
 	if (rr.val & RMID_VAL_ERROR)
 		seq_puts(m, "Error\n");
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3dd13f3a8b23..f20a47d120b1 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -31,7 +31,7 @@
 
 #define CQM_LIMBOCHECK_INTERVAL	1000
 
-#define MBM_CNTR_WIDTH			24
+#define MBM_CNTR_WIDTH_BASE		24
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
@@ -40,6 +40,12 @@
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
+/*
+ * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for
+ * data to be returned. The counter width is discovered from the hardware
+ * as an offset from MBM_CNTR_WIDTH_BASE.
+ */
+#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
 
 struct rdt_fs_context {
@@ -87,6 +93,7 @@ union mon_data_bits {
 
 struct rmid_read {
 	struct rdtgroup		*rgrp;
+	struct rdt_resource	*r;
 	struct rdt_domain	*d;
 	int			evtid;
 	bool			first;
@@ -460,6 +467,7 @@ struct rdt_resource {
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
+	unsigned int		mbm_width;
 	unsigned long		fflags;
 };
 
@@ -587,8 +595,9 @@ void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    unsigned int dom_id);
 void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    struct rdt_domain *d);
-void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
-		    struct rdtgroup *rdtgrp, int evtid, int first);
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    int evtid, int first);
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
 				unsigned long delay_ms);
 void mbm_handle_overflow(struct work_struct *work);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 773124b0e18a..837d7d012b7b 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -214,9 +214,9 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr)
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 {
-	u64 shift = 64 - MBM_CNTR_WIDTH, chunks;
+	u64 shift = 64 - width, chunks;
 
 	chunks = (cur_msr << shift) - (prev_msr << shift);
 	return chunks >>= shift;
@@ -256,7 +256,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 		return 0;
 	}
 
-	chunks = mbm_overflow_count(m->prev_msr, tval);
+	chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width);
 	m->chunks += chunks;
 	m->prev_msr = tval;
 
@@ -278,7 +278,7 @@ 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);
+	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
 	m->chunks_bw += chunks;
 	m->chunks = m->chunks_bw;
 	cur_bw = (chunks * r->mon_scale) >> 20;
@@ -433,11 +433,12 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	}
 }
 
-static void mbm_update(struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
 	rr.first = false;
+	rr.r = r;
 	rr.d = d;
 
 	/*
@@ -510,6 +511,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
 	struct list_head *head;
+	struct rdt_resource *r;
 	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
@@ -517,16 +519,18 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
-	d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]);
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	d = get_domain_from_cpu(cpu, r);
 	if (!d)
 		goto out_unlock;
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(d, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp->mon.rmid);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(d, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp->mon.rmid);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);
@@ -614,11 +618,18 @@ 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;
 	unsigned int cl_size = boot_cpu_data.x86_cache_size;
 	int ret;
 
 	r->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;
+
+	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
+		r->mbm_width += mbm_offset;
+	else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX)
+		pr_warn("Ignoring impossible MBM counter offset\n");
 
 	/*
 	 * A reasonable upper limit on the max threshold is the number
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index d7623e1b927d..4bd28b388a1a 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -24,7 +24,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include <asm/perf_event.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 5a359d9fcc05..d7cb5ab0d1f0 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -29,7 +29,7 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
@@ -2472,7 +2472,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 			goto out_destroy;
 
 		if (is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, d, prgrp, mevt->evtid, true);
+			mon_event_read(&rr, r, d, prgrp, mevt->evtid, true);
 	}
 	kernfs_activate(kn);
 	return 0;