Merge tag 'x86_cache_for_v6.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:
 "Add support on AMD for assigning QoS bandwidth counters to resources
  (RMIDs) with the ability for those resources to be tracked by the
  counters as long as they're assigned to them.

  Previously, due to hw limitations, bandwidth counts from untracked
  resources would get lost when those resources are not tracked.

  Refactor the code and user interfaces to be able to also support
  other, similar features on ARM, for example"

* tag 'x86_cache_for_v6.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits)
  fs/resctrl: Fix counter auto-assignment on mkdir with mbm_event enabled
  MAINTAINERS: resctrl: Add myself as reviewer
  x86/resctrl: Configure mbm_event mode if supported
  fs/resctrl: Introduce the interface to switch between monitor modes
  fs/resctrl: Disable BMEC event configuration when mbm_event mode is enabled
  fs/resctrl: Introduce the interface to modify assignments in a group
  fs/resctrl: Introduce mbm_L3_assignments to list assignments in a group
  fs/resctrl: Auto assign counters on mkdir and clean up on group removal
  fs/resctrl: Introduce mbm_assign_on_mkdir to enable assignments on mkdir
  fs/resctrl: Provide interface to update the event configurations
  fs/resctrl: Add event configuration directory under info/L3_MON/
  fs/resctrl: Support counter read/reset with mbm_event assignment mode
  x86/resctrl: Implement resctrl_arch_reset_cntr() and resctrl_arch_cntr_read()
  x86/resctrl: Refactor resctrl_arch_rmid_read()
  fs/resctrl: Introduce counter ID read, reset calls in mbm_event mode
  fs/resctrl: Pass struct rdtgroup instead of individual members
  fs/resctrl: Add the functionality to unassign MBM events
  fs/resctrl: Add the functionality to assign MBM events
  x86,fs/resctrl: Implement resctrl_arch_config_cntr() to assign a counter with ABMC
  fs/resctrl: Introduce event configuration field in struct mon_evt
  ...

1 files changed, 206 insertions, 42 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c261558276cd..c8945610d455 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -31,11 +31,6 @@
  */
 bool rdt_mon_capable;
 
-/*
- * Global to indicate which monitoring events are enabled.
- */
-unsigned int rdt_mon_features;
-
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
 static int snc_nodes_per_l3_cache = 1;
@@ -135,7 +130,7 @@ static int logical_rmid_to_physical_rmid(int cpu, int lrmid)
 	if (snc_nodes_per_l3_cache == 1)
 		return lrmid;
 
-	return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+	return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->mon.num_rmid;
 }
 
 static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
@@ -166,18 +161,14 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
-	switch (eventid) {
-	case QOS_L3_OCCUP_EVENT_ID:
-		return NULL;
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &hw_dom->arch_mbm_total[rmid];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &hw_dom->arch_mbm_local[rmid];
-	default:
-		/* Never expect to get here */
-		WARN_ON_ONCE(1);
+	struct arch_mbm_state *state;
+
+	if (!resctrl_is_mbm_event(eventid))
 		return NULL;
-	}
+
+	state = hw_dom->arch_mbm_states[MBM_STATE_IDX(eventid)];
+
+	return state ? &state[rmid] : NULL;
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
@@ -206,14 +197,16 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
-
-	if (resctrl_arch_is_mbm_total_enabled())
-		memset(hw_dom->arch_mbm_total, 0,
-		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
-
-	if (resctrl_arch_is_mbm_local_enabled())
-		memset(hw_dom->arch_mbm_local, 0,
-		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
+	enum resctrl_event_id eventid;
+	int idx;
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		memset(hw_dom->arch_mbm_states[idx], 0,
+		       sizeof(*hw_dom->arch_mbm_states[0]) * r->mon.num_rmid);
+	}
 }
 
 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@@ -224,15 +217,33 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
+static u64 get_corrected_val(struct rdt_resource *r, struct rdt_mon_domain *d,
+			     u32 rmid, enum resctrl_event_id eventid, u64 msr_val)
+{
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	struct arch_mbm_state *am;
+	u64 chunks;
+
+	am = get_arch_mbm_state(hw_dom, rmid, eventid);
+	if (am) {
+		am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
+						 hw_res->mbm_width);
+		chunks = get_corrected_mbm_count(rmid, am->chunks);
+		am->prev_msr = msr_val;
+	} else {
+		chunks = msr_val;
+	}
+
+	return chunks * hw_res->mon_scale;
+}
+
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	int cpu = cpumask_any(&d->hdr.cpu_mask);
-	struct arch_mbm_state *am;
-	u64 msr_val, chunks;
+	u64 msr_val;
 	u32 prmid;
 	int ret;
 
@@ -243,17 +254,76 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 	if (ret)
 		return ret;
 
+	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+
+	return 0;
+}
+
+static int __cntr_id_read(u32 cntr_id, u64 *val)
+{
+	u64 msr_val;
+
+	/*
+	 * QM_EVTSEL Register definition:
+	 * =======================================================
+	 * Bits    Mnemonic        Description
+	 * =======================================================
+	 * 63:44   --              Reserved
+	 * 43:32   RMID            RMID or counter ID in ABMC mode
+	 *                         when reading an MBM event
+	 * 31      ExtendedEvtID   Extended Event Identifier
+	 * 30:8    --              Reserved
+	 * 7:0     EvtID           Event Identifier
+	 * =======================================================
+	 * The contents of a specific counter can be read by setting the
+	 * following fields in QM_EVTSEL.ExtendedEvtID(=1) and
+	 * QM_EVTSEL.EvtID = L3CacheABMC (=1) and setting QM_EVTSEL.RMID
+	 * to the desired counter ID. Reading the QM_CTR then returns the
+	 * contents of the specified counter. The RMID_VAL_ERROR bit is set
+	 * if the counter configuration is invalid, or if an invalid counter
+	 * ID is set in the QM_EVTSEL.RMID field.  The RMID_VAL_UNAVAIL bit
+	 * is set if the counter data is unavailable.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, ABMC_EXTENDED_EVT_ID | ABMC_EVT_ID, cntr_id);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+	return 0;
+}
+
+void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+			     u32 unused, u32 rmid, int cntr_id,
+			     enum resctrl_event_id eventid)
+{
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct arch_mbm_state *am;
+
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
-		am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
-						 hw_res->mbm_width);
-		chunks = get_corrected_mbm_count(rmid, am->chunks);
-		am->prev_msr = msr_val;
-	} else {
-		chunks = msr_val;
+		memset(am, 0, sizeof(*am));
+
+		/* Record any initial, non-zero count value. */
+		__cntr_id_read(cntr_id, &am->prev_msr);
 	}
+}
+
+int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+			   u32 unused, u32 rmid, int cntr_id,
+			   enum resctrl_event_id eventid, u64 *val)
+{
+	u64 msr_val;
+	int ret;
+
+	ret = __cntr_id_read(cntr_id, &msr_val);
+	if (ret)
+		return ret;
 
-	*val = chunks * hw_res->mon_scale;
+	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
 
 	return 0;
 }
@@ -346,12 +416,13 @@ int __init 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 threshold;
+	u32 eax, ebx, ecx, edx;
 
 	snc_nodes_per_l3_cache = snc_get_config();
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
 	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
-	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
+	r->mon.num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
@@ -366,7 +437,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 *
 	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
 	 */
-	threshold = resctrl_rmid_realloc_limit / r->num_rmid;
+	threshold = resctrl_rmid_realloc_limit / r->mon.num_rmid;
 
 	/*
 	 * Because num_rmid may not be a power of two, round the value
@@ -375,12 +446,17 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 */
 	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
-	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
-		u32 eax, ebx, ecx, edx;
-
+	if (rdt_cpu_has(X86_FEATURE_BMEC) || rdt_cpu_has(X86_FEATURE_ABMC)) {
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
-		r->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
+		r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
+	}
+
+	if (rdt_cpu_has(X86_FEATURE_ABMC)) {
+		r->mon.mbm_cntr_assignable = true;
+		cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx);
+		r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1;
+		hw_res->mbm_cntr_assign_enabled = true;
 	}
 
 	r->mon_capable = true;
@@ -401,3 +477,91 @@ void __init intel_rdt_mbm_apply_quirk(void)
 	mbm_cf_rmidthreshold = mbm_cf_table[cf_index].rmidthreshold;
 	mbm_cf = mbm_cf_table[cf_index].cf;
 }
+
+static void resctrl_abmc_set_one_amd(void *arg)
+{
+	bool *enable = arg;
+
+	if (*enable)
+		msr_set_bit(MSR_IA32_L3_QOS_EXT_CFG, ABMC_ENABLE_BIT);
+	else
+		msr_clear_bit(MSR_IA32_L3_QOS_EXT_CFG, ABMC_ENABLE_BIT);
+}
+
+/*
+ * ABMC enable/disable requires update of L3_QOS_EXT_CFG MSR on all the CPUs
+ * associated with all monitor domains.
+ */
+static void _resctrl_abmc_enable(struct rdt_resource *r, bool enable)
+{
+	struct rdt_mon_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
+		on_each_cpu_mask(&d->hdr.cpu_mask, resctrl_abmc_set_one_amd,
+				 &enable, 1);
+		resctrl_arch_reset_rmid_all(r, d);
+	}
+}
+
+int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+
+	if (r->mon.mbm_cntr_assignable &&
+	    hw_res->mbm_cntr_assign_enabled != enable) {
+		_resctrl_abmc_enable(r, enable);
+		hw_res->mbm_cntr_assign_enabled = enable;
+	}
+
+	return 0;
+}
+
+bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r)
+{
+	return resctrl_to_arch_res(r)->mbm_cntr_assign_enabled;
+}
+
+static void resctrl_abmc_config_one_amd(void *info)
+{
+	union l3_qos_abmc_cfg *abmc_cfg = info;
+
+	wrmsrl(MSR_IA32_L3_QOS_ABMC_CFG, abmc_cfg->full);
+}
+
+/*
+ * Send an IPI to the domain to assign the counter to RMID, event pair.
+ */
+void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+			      enum resctrl_event_id evtid, u32 rmid, u32 closid,
+			      u32 cntr_id, bool assign)
+{
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	union l3_qos_abmc_cfg abmc_cfg = { 0 };
+	struct arch_mbm_state *am;
+
+	abmc_cfg.split.cfg_en = 1;
+	abmc_cfg.split.cntr_en = assign ? 1 : 0;
+	abmc_cfg.split.cntr_id = cntr_id;
+	abmc_cfg.split.bw_src = rmid;
+	if (assign)
+		abmc_cfg.split.bw_type = resctrl_get_mon_evt_cfg(evtid);
+
+	smp_call_function_any(&d->hdr.cpu_mask, resctrl_abmc_config_one_amd, &abmc_cfg, 1);
+
+	/*
+	 * The hardware counter is reset (because cfg_en == 1) so there is no
+	 * need to record initial non-zero counts.
+	 */
+	am = get_arch_mbm_state(hw_dom, rmid, evtid);
+	if (am)
+		memset(am, 0, sizeof(*am));
+}
+
+void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+
+	resctrl_abmc_set_one_amd(&hw_res->mbm_cntr_assign_enabled);
+}