x86/uv: Implement UV BAU runtime enable and disable control via /proc/sgi_uv/

This patch enables the BAU to be turned on or off dynamically.

  echo "on"  > /proc/sgi_uv/ptc_statistics
  echo "off" > /proc/sgi_uv/ptc_statistics

The system may be booted with or without the nobau option.

Whether the system currently has the BAU off can be seen in
the /proc file -- normally with the baustats script.
Each cpu will have a 1 in the bauoff field if the BAU was turned
off, so baustats will give a count of cpus that have it off.

Signed-off-by: Cliff Wickman <cpw@sgi.com>
Link: http://lkml.kernel.org/r/20120622131330.GB31884@sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 6149b47..847c00b 100644 (file)
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -520,6 +520,7 @@ struct ptc_stats {
        unsigned long   s_uv2_wars;             /* uv2 workaround, perm. busy */
        unsigned long   s_uv2_wars_hw;          /* uv2 workaround, hiwater */
        unsigned long   s_uv2_war_waits;        /* uv2 workaround, long waits */
+       unsigned long   s_enters;               /* entries to the driver */
        /* destination statistics */
        unsigned long   d_alltlb;               /* times all tlb's on this
                                                   cpu were flushed */
@@ -586,6 +587,7 @@ struct bau_control {
        int                     timeout_tries;
        int                     ipi_attempts;
        int                     conseccompletes;
+       short                   nobau;
        int                     baudisabled;
        int                     set_bau_off;
        short                   cpu;

diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 0c48d43..1492170 100644 (file)
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -38,6 +38,7 @@ static int timeout_base_ns[] = {
 
 static int timeout_us;
 static int nobau;
+static int nobau_perm;
 static int baudisabled;
 static spinlock_t disable_lock;
 static cycles_t congested_cycles;
@@ -120,6 +121,40 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats);
 static DEFINE_PER_CPU(struct bau_control, bau_control);
 static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
 
+static void
+set_bau_on(void)
+{
+       int cpu;
+       struct bau_control *bcp;
+
+       if (nobau_perm) {
+               pr_info("BAU not initialized; cannot be turned on\n");
+               return;
+       }
+       nobau = 0;
+       for_each_present_cpu(cpu) {
+               bcp = &per_cpu(bau_control, cpu);
+               bcp->nobau = 0;
+       }
+       pr_info("BAU turned on\n");
+       return;
+}
+
+static void
+set_bau_off(void)
+{
+       int cpu;
+       struct bau_control *bcp;
+
+       nobau = 1;
+       for_each_present_cpu(cpu) {
+               bcp = &per_cpu(bau_control, cpu);
+               bcp->nobau = 1;
+       }
+       pr_info("BAU turned off\n");
+       return;
+}
+
 /*
  * Determine the first node on a uvhub. 'Nodes' are used for kernel
  * memory allocation.
@@ -1079,12 +1114,12 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
        struct ptc_stats *stat;
        struct bau_control *bcp;
 
-       /* kernel was booted 'nobau' */
-       if (nobau)
-               return cpumask;
-
        bcp = &per_cpu(bau_control, cpu);
        stat = bcp->statp;
+       stat->s_enters++;
+
+       if (bcp->nobau)
+               return cpumask;
 
        /* bau was disabled due to slow response */
        if (bcp->baudisabled) {
@@ -1338,29 +1373,32 @@ static inline unsigned long long usec_2_cycles(unsigned long microsec)
 static int ptc_seq_show(struct seq_file *file, void *data)
 {
        struct ptc_stats *stat;
+       struct bau_control *bcp;
        int cpu;
 
        cpu = *(loff_t *)data;
        if (!cpu) {
                seq_printf(file,
-                       "# cpu sent stime self locals remotes ncpus localhub ");
+               "# cpu bauoff sent stime self locals remotes ncpus localhub ");
                seq_printf(file,
                        "remotehub numuvhubs numuvhubs16 numuvhubs8 ");
                seq_printf(file,
                    "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok ");
                seq_printf(file,
-                       "resetp resett giveup sto bz throt swack recv rtime ");
+                       "resetp resett giveup sto bz throt enters swack recv rtime ");
                seq_printf(file,
                        "all one mult none retry canc nocan reset rcan ");
                seq_printf(file,
                        "disable enable wars warshw warwaits\n");
        }
        if (cpu < num_possible_cpus() && cpu_online(cpu)) {
-               stat = &per_cpu(ptcstats, cpu);
+               bcp = &per_cpu(bau_control, cpu);
+               stat = bcp->statp;
                /* source side statistics */
                seq_printf(file,
-                       "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
-                          cpu, stat->s_requestor, cycles_2_us(stat->s_time),
+                          "cpu %d %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
+                          cpu, bcp->nobau, stat->s_requestor,
+                          cycles_2_us(stat->s_time),
                           stat->s_ntargself, stat->s_ntarglocals,
                           stat->s_ntargremotes, stat->s_ntargcpu,
                           stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub,
@@ -1369,11 +1407,11 @@ static int ptc_seq_show(struct seq_file *file, void *data)
                           stat->s_ntarguvhub8, stat->s_ntarguvhub4,
                           stat->s_ntarguvhub2, stat->s_ntarguvhub1,
                           stat->s_dtimeout, stat->s_strongnacks);
-               seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld ",
+               seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld %ld ",
                           stat->s_retry_messages, stat->s_retriesok,
                           stat->s_resets_plug, stat->s_resets_timeout,
                           stat->s_giveup, stat->s_stimeout,
-                          stat->s_busy, stat->s_throttles);
+                          stat->s_busy, stat->s_throttles, stat->s_enters);
 
                /* destination side statistics */
                seq_printf(file,
@@ -1438,6 +1476,14 @@ static ssize_t ptc_proc_write(struct file *file, const char __user *user,
                return -EFAULT;
        optstr[count - 1] = '\0';
 
+       if (!strcmp(optstr, "on")) {
+               set_bau_on();
+               return count;
+       } else if (!strcmp(optstr, "off")) {
+               set_bau_off();
+               return count;
+       }
+
        if (strict_strtol(optstr, 10, &input_arg) < 0) {
                printk(KERN_DEBUG "%s is invalid\n", optstr);
                return -EINVAL;
@@ -1836,6 +1882,8 @@ static void __init init_per_cpu_tunables(void)
        for_each_present_cpu(cpu) {
                bcp = &per_cpu(bau_control, cpu);
                bcp->baudisabled                = 0;
+               if (nobau)
+                       bcp->nobau              = 1;
                bcp->statp                      = &per_cpu(ptcstats, cpu);
                /* time interval to catch a hardware stay-busy bug */
                bcp->timeout_interval           = usec_2_cycles(2*timeout_us);
@@ -2069,9 +2117,6 @@ static int __init uv_bau_init(void)
        if (!is_uv_system())
                return 0;
 
-       if (nobau)
-               return 0;
-
        for_each_possible_cpu(cur_cpu) {
                mask = &per_cpu(uv_flush_tlb_mask, cur_cpu);
                zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu));
@@ -2091,7 +2136,8 @@ static int __init uv_bau_init(void)
        enable_timeouts();
 
        if (init_per_cpu(nuvhubs, uv_base_pnode)) {
-               nobau = 1;
+               set_bau_off();
+               nobau_perm = 1;
                return 0;
        }