powerpc/pseries: Add pool idle time at LPAR boot

When there are no options specified for lparstat, it is expected to
give reports since LPAR(Logical Partition) boot.

APP(Available Processor Pool) is an indicator of how many cores in the
shared pool are free to use in Shared Processor LPAR(SPLPAR). APP is
derived using pool_idle_time which is obtained using H_PIC call.

The interval based reports show correct APP value while since boot
report shows very high APP values. This happens because in that case APP
is obtained by dividing pool idle time by LPAR uptime. Since pool idle
time is reported by the PowerVM hypervisor since its boot, it need not
align with LPAR boot.

To fix that export boot pool idle time in lparcfg and powerpc-utils will
use this info to derive APP as below for since boot reports.

APP = (pool idle time - boot pool idle time) / (uptime * timebase)

Results:: Observe APP values.
====================== Shared LPAR ================================
lparstat
System Configuration
type=Shared mode=Uncapped smt=8 lcpu=12 mem=15573440 kB cpus=37 ent=12.00

reboot
stress-ng --cpu=$(nproc) -t 600
sleep 600
So in this case app is expected to close to 37-6=31.

====== 6.9-rc1 and lparstat 1.3.10  =============
%user  %sys %wait    %idle    physc %entc lbusy   app  vcsw phint
----- ----- -----    -----    ----- ----- ----- ----- ----- -----
47.48  0.01  0.00    52.51     0.00  0.00 47.49 69099.72 541547    21

=== With this patch and powerpc-utils patch to do the above equation ===
%user  %sys %wait    %idle    physc %entc lbusy   app  vcsw phint
----- ----- -----    -----    ----- ----- ----- ----- ----- -----
47.48  0.01  0.00    52.51     5.73 47.75 47.49 31.21 541753    21
=====================================================================

Note: physc, purr/idle purr being inaccurate is being handled in a
separate patch in powerpc-utils tree.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240412092047.455483-2-sshegde@linux.ibm.com

diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index f73c4d1c26af9822b12fcb9df19f25892933ab38..679efcf21628427f3b2b62ca677f218ace546a4c 100644 (file)
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -170,20 +170,24 @@ out:
        kfree(buf);
 }
 
-static unsigned h_pic(unsigned long *pool_idle_time,
-                     unsigned long *num_procs)
+static long h_pic(unsigned long *pool_idle_time,
+                 unsigned long *num_procs)
 {
-       unsigned long rc;
-       unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+       long rc;
+       unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = {0};
 
        rc = plpar_hcall(H_PIC, retbuf);
 
-       *pool_idle_time = retbuf[0];
-       *num_procs = retbuf[1];
+       if (pool_idle_time)
+               *pool_idle_time = retbuf[0];
+       if (num_procs)
+               *num_procs = retbuf[1];
 
        return rc;
 }
 
+unsigned long boot_pool_idle_time;
+
 /*
  * parse_ppp_data
  * Parse out the data returned from h_get_ppp and h_pic
@@ -215,9 +219,15 @@ static void parse_ppp_data(struct seq_file *m)
                seq_printf(m, "pool_capacity=%d\n",
                           ppp_data.active_procs_in_pool * 100);
 
-               h_pic(&pool_idle_time, &pool_procs);
-               seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
-               seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+               /* In case h_pic call is not successful, this would result in
+                * APP values being wrong in tools like lparstat.
+                */
+
+               if (h_pic(&pool_idle_time, &pool_procs) == H_SUCCESS) {
+                       seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
+                       seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+                       seq_printf(m, "boot_pool_idle_time=%ld\n", boot_pool_idle_time);
+               }
        }
 
        seq_printf(m, "unallocated_capacity_weight=%d\n",
@@ -792,6 +802,7 @@ static const struct proc_ops lparcfg_proc_ops = {
 static int __init lparcfg_init(void)
 {
        umode_t mode = 0444;
+       long retval;
 
        /* Allow writing if we have FW_FEATURE_SPLPAR */
        if (firmware_has_feature(FW_FEATURE_SPLPAR))
@@ -801,6 +812,16 @@ static int __init lparcfg_init(void)
                printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
                return -EIO;
        }
+
+       /* If this call fails, it would result in APP values
+        * being wrong for since boot reports of lparstat
+        */
+       retval = h_pic(&boot_pool_idle_time, NULL);
+
+       if (retval != H_SUCCESS)
+               pr_debug("H_PIC failed during lparcfg init retval: %ld\n",
+                        retval);
+
        return 0;
 }
 machine_device_initcall(pseries, lparcfg_init);