Merge tag 'x86_cache_for_v5.11' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/tip/tip

Pull x86 cache resource control updates from Borislav Petkov:

 - add logic to correct MBM total and local values fixing errata SKX99
   and BDF102 (Fenghua Yu)

 - cleanups

* tag 'x86_cache_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Clean up unused function parameter in rmdir path
  x86/resctrl: Constify kernfs_ops
  x86/resctrl: Correct MBM total and local values
  Documentation/x86: Rename resctrl_ui.rst and add two errata to the file

Documentation/x86/index.rst

@@ -27,7 +27,7 @@ x86-specific Documentation
    pti
    mds
    microcode
-   resctrl_ui
+   resctrl
    tsx_async_abort
    usb-legacy-support
    i386/index

Documentation/x86/resctrl_ui.rst → Documentation/x86/resctrl.rst

@@ -1209,3 +1209,96 @@ View the llc occupancy snapshot::
 
   # cat /sys/fs/resctrl/p1/mon_data/mon_L3_00/llc_occupancy
   11234000
+
+Intel RDT Errata
+================
+
+Intel MBM Counters May Report System Memory Bandwidth Incorrectly
+-----------------------------------------------------------------
+
+Errata SKX99 for Skylake server and BDF102 for Broadwell server.
+
+Problem: Intel Memory Bandwidth Monitoring (MBM) counters track metrics
+according to the assigned Resource Monitor ID (RMID) for that logical
+core. The IA32_QM_CTR register (MSR 0xC8E), used to report these
+metrics, may report incorrect system bandwidth for certain RMID values.
+
+Implication: Due to the errata, system memory bandwidth may not match
+what is reported.
+
+Workaround: MBM total and local readings are corrected according to the
+following correction factor table:
+
++---------------+---------------+---------------+-----------------+
+|core count	|rmid count	|rmid threshold	|correction factor|
++---------------+---------------+---------------+-----------------+
+|1		|8		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|2		|16		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|3		|24		|15		|0.969650	  |
++---------------+---------------+---------------+-----------------+
+|4		|32		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|6		|48		|31		|0.969650	  |
++---------------+---------------+---------------+-----------------+
+|7		|56		|47		|1.142857	  |
++---------------+---------------+---------------+-----------------+
+|8		|64		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|9		|72		|63		|1.185115	  |
++---------------+---------------+---------------+-----------------+
+|10		|80		|63		|1.066553	  |
++---------------+---------------+---------------+-----------------+
+|11		|88		|79		|1.454545	  |
++---------------+---------------+---------------+-----------------+
+|12		|96		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|13		|104		|95		|1.230769	  |
++---------------+---------------+---------------+-----------------+
+|14		|112		|95		|1.142857	  |
++---------------+---------------+---------------+-----------------+
+|15		|120		|95		|1.066667	  |
++---------------+---------------+---------------+-----------------+
+|16		|128		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|17		|136		|127		|1.254863	  |
++---------------+---------------+---------------+-----------------+
+|18		|144		|127		|1.185255	  |
++---------------+---------------+---------------+-----------------+
+|19		|152		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|20		|160		|127		|1.066667	  |
++---------------+---------------+---------------+-----------------+
+|21		|168		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|22		|176		|159		|1.454334	  |
++---------------+---------------+---------------+-----------------+
+|23		|184		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|24		|192		|127		|0.969744	  |
++---------------+---------------+---------------+-----------------+
+|25		|200		|191		|1.280246	  |
++---------------+---------------+---------------+-----------------+
+|26		|208		|191		|1.230921	  |
++---------------+---------------+---------------+-----------------+
+|27		|216		|0		|1.000000	  |
++---------------+---------------+---------------+-----------------+
+|28		|224		|191		|1.143118	  |
++---------------+---------------+---------------+-----------------+
+
+If rmid > rmid threshold, MBM total and local values should be multiplied
+by the correction factor.
+
+See:
+
+1. Erratum SKX99 in Intel Xeon Processor Scalable Family Specification Update:
+http://web.archive.org/web/20200716124958/https://www.intel.com/content/www/us/en/processors/xeon/scalable/xeon-scalable-spec-update.html
+
+2. Erratum BDF102 in Intel Xeon E5-2600 v4 Processor Product Family Specification Update:
+http://web.archive.org/web/20191125200531/https://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/xeon-e5-v4-spec-update.pdf
+
+3. The errata in Intel Resource Director Technology (Intel RDT) on 2nd Generation Intel Xeon Scalable Processors Reference Manual:
+https://software.intel.com/content/www/us/en/develop/articles/intel-resource-director-technology-rdt-reference-manual.html
+
+for further information.

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

@@ -895,6 +895,10 @@ static __init void __check_quirks_intel(void)
 			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
 		else
 			set_rdt_options("!l3cat");
+		fallthrough;
+	case INTEL_FAM6_BROADWELL_X:
+		intel_rdt_mbm_apply_quirk();
+		break;
 	}
 }
 

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

@@ -264,7 +264,7 @@ void __exit rdtgroup_exit(void);
 struct rftype {
 	char			*name;
 	umode_t			mode;
-	struct kernfs_ops	*kf_ops;
+	const struct kernfs_ops	*kf_ops;
 	unsigned long		flags;
 	unsigned long		fflags;
 
@@ -619,6 +619,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
 				unsigned long delay_ms);
 void mbm_handle_overflow(struct work_struct *work);
+void __init intel_rdt_mbm_apply_quirk(void);
 bool is_mba_sc(struct rdt_resource *r);
 void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm);
 u32 delay_bw_map(unsigned long bw, struct rdt_resource *r);

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

@@ -64,6 +64,69 @@ unsigned int rdt_mon_features;
  */
 unsigned int resctrl_cqm_threshold;
 
+#define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
+
+/*
+ * The correction factor table is documented in Documentation/x86/resctrl.rst.
+ * If rmid > rmid threshold, MBM total and local values should be multiplied
+ * by the correction factor.
+ *
+ * The original table is modified for better code:
+ *
+ * 1. The threshold 0 is changed to rmid count - 1 so don't do correction
+ *    for the case.
+ * 2. MBM total and local correction table indexed by core counter which is
+ *    equal to (x86_cache_max_rmid + 1) / 8 - 1 and is from 0 up to 27.
+ * 3. The correction factor is normalized to 2^20 (1048576) so it's faster
+ *    to calculate corrected value by shifting:
+ *    corrected_value = (original_value * correction_factor) >> 20
+ */
+static const struct mbm_correction_factor_table {
+	u32 rmidthreshold;
+	u64 cf;
+} mbm_cf_table[] __initdata = {
+	{7,	CF(1.000000)},
+	{15,	CF(1.000000)},
+	{15,	CF(0.969650)},
+	{31,	CF(1.000000)},
+	{31,	CF(1.066667)},
+	{31,	CF(0.969650)},
+	{47,	CF(1.142857)},
+	{63,	CF(1.000000)},
+	{63,	CF(1.185115)},
+	{63,	CF(1.066553)},
+	{79,	CF(1.454545)},
+	{95,	CF(1.000000)},
+	{95,	CF(1.230769)},
+	{95,	CF(1.142857)},
+	{95,	CF(1.066667)},
+	{127,	CF(1.000000)},
+	{127,	CF(1.254863)},
+	{127,	CF(1.185255)},
+	{151,	CF(1.000000)},
+	{127,	CF(1.066667)},
+	{167,	CF(1.000000)},
+	{159,	CF(1.454334)},
+	{183,	CF(1.000000)},
+	{127,	CF(0.969744)},
+	{191,	CF(1.280246)},
+	{191,	CF(1.230921)},
+	{215,	CF(1.000000)},
+	{191,	CF(1.143118)},
+};
+
+static u32 mbm_cf_rmidthreshold __read_mostly = UINT_MAX;
+static u64 mbm_cf __read_mostly;
+
+static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
+{
+	/* Correct MBM value. */
+	if (rmid > mbm_cf_rmidthreshold)
+		val = (val * mbm_cf) >> 20;
+
+	return val;
+}
+
 static inline struct rmid_entry *__rmid_entry(u32 rmid)
 {
 	struct rmid_entry *entry;
@@ -260,7 +323,8 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 	m->chunks += chunks;
 	m->prev_msr = tval;
 
-	rr->val += m->chunks;
+	rr->val += get_corrected_mbm_count(rmid, m->chunks);
+
 	return 0;
 }
 
@@ -279,7 +343,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 		return;
 
 	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
-	cur_bw = (chunks * r->mon_scale) >> 20;
+	cur_bw = (get_corrected_mbm_count(rmid, chunks) * r->mon_scale) >> 20;
 
 	if (m->delta_comp)
 		m->delta_bw = abs(cur_bw - m->prev_bw);
@@ -642,3 +706,17 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 
 	return 0;
 }
+
+void __init intel_rdt_mbm_apply_quirk(void)
+{
+	int cf_index;
+
+	cf_index = (boot_cpu_data.x86_cache_max_rmid + 1) / 8 - 1;
+	if (cf_index >= ARRAY_SIZE(mbm_cf_table)) {
+		pr_info("No MBM correction factor available\n");
+		return;
+	}
+
+	mbm_cf_rmidthreshold = mbm_cf_table[cf_index].rmidthreshold;
+	mbm_cf = mbm_cf_table[cf_index].cf;
+}

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

@@ -240,13 +240,13 @@ static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
 	return -EINVAL;
 }
 
-static struct kernfs_ops rdtgroup_kf_single_ops = {
+static const struct kernfs_ops rdtgroup_kf_single_ops = {
 	.atomic_write_len	= PAGE_SIZE,
 	.write			= rdtgroup_file_write,
 	.seq_show		= rdtgroup_seqfile_show,
 };
 
-static struct kernfs_ops kf_mondata_ops = {
+static const struct kernfs_ops kf_mondata_ops = {
 	.atomic_write_len	= PAGE_SIZE,
 	.seq_show		= rdtgroup_mondata_show,
 };
@@ -3023,8 +3023,7 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	return -EPERM;
 }
 
-static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
-			      cpumask_var_t tmpmask)
+static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 {
 	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
 	int cpu;
@@ -3056,8 +3055,7 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	return 0;
 }
 
-static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
-				struct rdtgroup *rdtgrp)
+static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
 {
 	rdtgrp->flags = RDT_DELETED;
 	list_del(&rdtgrp->rdtgroup_list);
@@ -3066,8 +3064,7 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
 	return 0;
 }
 
-static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
-			       cpumask_var_t tmpmask)
+static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 {
 	int cpu;
 
@@ -3094,7 +3091,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	closid_free(rdtgrp->closid);
 	free_rmid(rdtgrp->mon.rmid);
 
-	rdtgroup_ctrl_remove(kn, rdtgrp);
+	rdtgroup_ctrl_remove(rdtgrp);
 
 	/*
 	 * Free all the child monitor group rmids.
@@ -3131,13 +3128,13 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	    rdtgrp != &rdtgroup_default) {
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
+			ret = rdtgroup_ctrl_remove(rdtgrp);
 		} else {
-			ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
+			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
 		}
 	} else if (rdtgrp->type == RDTMON_GROUP &&
 		 is_mon_groups(parent_kn, kn->name)) {
-		ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
+		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
 	} else {
 		ret = -EPERM;
 	}