Merge branch 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

torvalds · torvalds · commit 3643b7e05b16 · 2017-11-13T19:05:19.000-08:00
Pull x86 cache resource updates from Thomas Gleixner:
 "This update provides updates to RDT:

  - A diagnostic framework for the Resource Director Technology (RDT)
    user interface (sysfs). The failure modes of the user interface are
    hard to diagnose from the error codes. An extra last command status
    file provides now sensible textual information about the failure so
    its simpler to use.

  - A few minor cleanups and updates in the RDT code"

* 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/intel_rdt: Fix a silent failure when writing zero value schemata
  x86/intel_rdt: Fix potential deadlock during resctrl mount
  x86/intel_rdt: Fix potential deadlock during resctrl unmount
  x86/intel_rdt: Initialize bitmask of shareable resource if CDP enabled
  x86/intel_rdt: Remove redundant assignment
  x86/intel_rdt/cqm: Make integer rmid_limbo_count static
  x86/intel_rdt: Add documentation for "info/last_cmd_status"
  x86/intel_rdt: Add diagnostics when making directories
  x86/intel_rdt: Add diagnostics when writing the cpus file
  x86/intel_rdt: Add diagnostics when writing the tasks file
  x86/intel_rdt: Add diagnostics when writing the schemata file
  x86/intel_rdt: Add framework for better RDT UI diagnostics
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
@@ -87,6 +87,17 @@ with the following files:
 			bytes) at which a previously used LLC_occupancy
 			counter can be considered for re-use.
 
+Finally, in the top level of the "info" directory there is a file
+named "last_cmd_status". This is reset with every "command" issued
+via the file system (making new directories or writing to any of the
+control files). If the command was successful, it will read as "ok".
+If the command failed, it will provide more information that can be
+conveyed in the error returns from file operations. E.g.
+
+	# echo L3:0=f7 > schemata
+	bash: echo: write error: Invalid argument
+	# cat info/last_cmd_status
+	mask f7 has non-consecutive 1-bits
 
 Resource alloc and monitor groups
 ---------------------------------
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
@@ -267,6 +267,7 @@ static void rdt_get_cdp_l3_config(int type)
 	r->num_closid = r_l3->num_closid / 2;
 	r->cache.cbm_len = r_l3->cache.cbm_len;
 	r->default_ctrl = r_l3->default_ctrl;
+	r->cache.shareable_bits = r_l3->cache.shareable_bits;
 	r->data_width = (r->cache.cbm_len + 3) / 4;
 	r->alloc_capable = true;
 	/*
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
@@ -127,12 +127,15 @@ struct rdtgroup {
 #define RFTYPE_BASE			BIT(1)
 #define RF_CTRLSHIFT			4
 #define RF_MONSHIFT			5
+#define RF_TOPSHIFT			6
 #define RFTYPE_CTRL			BIT(RF_CTRLSHIFT)
 #define RFTYPE_MON			BIT(RF_MONSHIFT)
+#define RFTYPE_TOP			BIT(RF_TOPSHIFT)
 #define RFTYPE_RES_CACHE		BIT(8)
 #define RFTYPE_RES_MB			BIT(9)
 #define RF_CTRL_INFO			(RFTYPE_INFO | RFTYPE_CTRL)
 #define RF_MON_INFO			(RFTYPE_INFO | RFTYPE_MON)
+#define RF_TOP_INFO			(RFTYPE_INFO | RFTYPE_TOP)
 #define RF_CTRL_BASE			(RFTYPE_BASE | RFTYPE_CTRL)
 
 /* List of all resource groups */
@@ -409,6 +412,10 @@ union cpuid_0x10_x_edx {
 	unsigned int full;
 };
 
+void rdt_last_cmd_clear(void);
+void rdt_last_cmd_puts(const char *s);
+void rdt_last_cmd_printf(const char *fmt, ...);
+
 void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -42,15 +42,22 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	/*
 	 * Only linear delay values is supported for current Intel SKUs.
 	 */
-	if (!r->membw.delay_linear)
+	if (!r->membw.delay_linear) {
+		rdt_last_cmd_puts("No support for non-linear MB domains\n");
 		return false;
+	}
 
 	ret = kstrtoul(buf, 10, &bw);
-	if (ret)
+	if (ret) {
+		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
 		return false;
+	}
 
-	if (bw < r->membw.min_bw || bw > r->default_ctrl)
+	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
+				    r->membw.min_bw, r->default_ctrl);
 		return false;
+	}
 
 	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
 	return true;
@@ -60,8 +67,10 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
 
-	if (d->have_new_ctrl)
+	if (d->have_new_ctrl) {
+		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
 		return -EINVAL;
+	}
 
 	if (!bw_validate(buf, &data, r))
 		return -EINVAL;
@@ -84,20 +93,29 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	int ret;
 
 	ret = kstrtoul(buf, 16, &val);
-	if (ret)
+	if (ret) {
+		rdt_last_cmd_printf("non-hex character in mask %s\n", buf);
 		return false;
+	}
 
-	if (val == 0 || val > r->default_ctrl)
+	if (val == 0 || val > r->default_ctrl) {
+		rdt_last_cmd_puts("mask out of range\n");
 		return false;
+	}
 
 	first_bit = find_first_bit(&val, cbm_len);
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
-	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)
+	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
+		rdt_last_cmd_printf("mask %lx has non-consecutive 1-bits\n", val);
 		return false;
+	}
 
-	if ((zero_bit - first_bit) < r->cache.min_cbm_bits)
+	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
+		rdt_last_cmd_printf("Need at least %d bits in mask\n",
+				    r->cache.min_cbm_bits);
 		return false;
+	}
 
 	*data = val;
 	return true;
@@ -111,8 +129,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
 
-	if (d->have_new_ctrl)
+	if (d->have_new_ctrl) {
+		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
 		return -EINVAL;
+	}
 
 	if(!cbm_validate(buf, &data, r))
 		return -EINVAL;
@@ -139,8 +159,10 @@ static int parse_line(char *line, struct rdt_resource *r)
 		return 0;
 	dom = strsep(&line, ";");
 	id = strsep(&dom, "=");
-	if (!dom || kstrtoul(id, 10, &dom_id))
+	if (!dom || kstrtoul(id, 10, &dom_id)) {
+		rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
 		return -EINVAL;
+	}
 	dom = strim(dom);
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
@@ -196,6 +218,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
 		if (!strcmp(resname, r->name) && closid < r->num_closid)
 			return parse_line(tok, r);
 	}
+	rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
 	return -EINVAL;
 }
 
@@ -218,6 +241,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		rdtgroup_kn_unlock(of->kn);
 		return -ENOENT;
 	}
+	rdt_last_cmd_clear();
 
 	closid = rdtgrp->closid;
 
@@ -229,6 +253,12 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	while ((tok = strsep(&buf, "\n")) != NULL) {
 		resname = strim(strsep(&tok, ":"));
 		if (!tok) {
+			rdt_last_cmd_puts("Missing ':'\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		if (tok[0] == '\0') {
+			rdt_last_cmd_printf("Missing '%s' value\n", resname);
 			ret = -EINVAL;
 			goto out;
 		}
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -51,7 +51,7 @@ static LIST_HEAD(rmid_free_lru);
  *     may have a occupancy value > intel_cqm_threshold. User can change
  *     the threshold occupancy value.
  */
-unsigned int rmid_limbo_count;
+static unsigned int rmid_limbo_count;
 
 /**
  * @rmid_entry - The entry in the limbo and free lists.
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
