x86/intel_rdt: Add framework for better RDT UI diagnostics

Commands are given to the resctrl file system by making/removing
directories, or by writing to files.  When something goes wrong
the user is generally left wondering why they got:

   bash: echo: write error: Invalid argument

Add a new file "last_cmd_status" to the "info" directory that
will give the user some better clues on what went wrong.

Provide functions to clear and update last_cmd_status which
check that we hold the rdtgroup_mutex.

[ tglx: Made last_cmd_status static and folded back the hunk from patch 3
  	which replaces the open coded access to last_cmd_status with the
  	accessor function ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vikas Shivappa <vikas.shivappa@intel.com>
Cc: Boris Petkov <bp@suse.de>
Cc: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/edc4e0e9741eee89bba569f0021b1b2662fd9508.1506382469.git.tony.luck@intel.com

2 files changed, 63 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index ebaddaeef023..9d3148d88ec8 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -126,12 +126,15 @@ 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 */
@@ -408,6 +411,10 @@ 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_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index a869d4a073c5..68103513130b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -24,6 +24,7 @@
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
+#include <linux/seq_buf.h>
 #include <linux/seq_file.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
@@ -51,6 +52,31 @@ static struct kernfs_node *kn_mongrp;
 /* Kernel fs node for "mon_data" directory under root */
 static struct kernfs_node *kn_mondata;
 
+static struct seq_buf last_cmd_status;
+static char last_cmd_status_buf[512];
+
+void rdt_last_cmd_clear(void)
+{
+        lockdep_assert_held(&rdtgroup_mutex);
+        seq_buf_clear(&last_cmd_status);
+}
+
+void rdt_last_cmd_puts(const char *s)
+{
+        lockdep_assert_held(&rdtgroup_mutex);
+        seq_buf_puts(&last_cmd_status, s);
+}
+
+void rdt_last_cmd_printf(const char *fmt, ...)
+{
+        va_list ap;
+
+        va_start(ap, fmt);
+        lockdep_assert_held(&rdtgroup_mutex);
+        seq_buf_vprintf(&last_cmd_status, fmt, ap);
+        va_end(ap);
+}
+
 /*
  * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
  * we can keep a bitmap of free CLOSIDs in a single integer.
@@ -569,6 +595,21 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of,
         return ret;
 }
 
+static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
+                                    struct seq_file *seq, void *v)
+{
+        int len;
+
+        mutex_lock(&rdtgroup_mutex);
+        len = seq_buf_used(&last_cmd_status);
+        if (len)
+                seq_printf(seq, "%.*s", len, last_cmd_status_buf);
+        else
+                seq_puts(seq, "ok\n");
+        mutex_unlock(&rdtgroup_mutex);
+        return 0;
+}
+
 static int rdt_num_closids_show(struct kernfs_open_file *of,
                                 struct seq_file *seq, void *v)
 {
@@ -686,6 +727,13 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
         {
+                .name           = "last_cmd_status",
+                .mode           = 0444,
+                .kf_ops         = &rdtgroup_kf_single_ops,
+                .seq_show       = rdt_last_cmd_status_show,
+                .fflags         = RF_TOP_INFO,
+        },
+        {
                 .name           = "num_closids",
                 .mode           = 0444,
                 .kf_ops         = &rdtgroup_kf_single_ops,
@@ -855,6 +903,10 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
                 return PTR_ERR(kn_info);
         kernfs_get(kn_info);
 
+        ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
+        if (ret)
+                goto out_destroy;
+
         for_each_alloc_enabled_rdt_resource(r) {
                 fflags =  r->fflags | RF_CTRL_INFO;
                 ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags);
@@ -1156,6 +1208,7 @@ out_info:
 out_cdp:
         cdp_disable();
 out:
+        rdt_last_cmd_clear();
         mutex_unlock(&rdtgroup_mutex);
 
         return dentry;
@@ -1902,6 +1955,9 @@ int __init rdtgroup_init(void)
 {
         int ret = 0;
 
+        seq_buf_init(&last_cmd_status, last_cmd_status_buf,
+                     sizeof(last_cmd_status_buf));
+
         ret = rdtgroup_setup_root();
         if (ret)
                 return ret;