powerpc/pseries: Implement CONFIG_PARAVIRT_TIME_ACCOUNTING

CONFIG_VIRT_CPU_ACCOUNTING_GEN under pseries does not provide stolen
time accounting unless CONFIG_PARAVIRT_TIME_ACCOUNTING is enabled.
Implement this using the VPA accumulated wait counters.

Note this will not work on current KVM hosts because KVM does not
implement the VPA dispatch counters (yet). It could be implemented
with the dispatch trace log as it is for VIRT_CPU_ACCOUNTING_NATIVE,
but that is not necessary for the more limited accounting provided
by PARAVIRT_TIME_ACCOUNTING, and it is more expensive, complex, and
has downsides like potential log wrap.

From Shrikanth:

[...] it was tested on Power10 [PowerVM] Shared LPAR. system has two
LPAR. we will call first one LPAR1 and second one as LPAR2. Test was
carried out in SMT=1. Similar observation was seen in SMT=8 as well.

LPAR config header from each LPAR is below. LPAR1 is twice as big as
LPAR2. Since Both are sharing the same underlying hardware, work
stealing will happen when both the LPAR's are contending for the same
resource.

LPAR1:
type=Shared mode=Uncapped smt=Off lcpu=40 cpus=40 ent=20.00
LPAR2:
type=Shared mode=Uncapped smt=Off lcpu=20 cpus=40 ent=10.00

mpstat was used to check for the utilization. stress-ng has been used
as the workload. Few cases are tested. when the both LPAR are idle
there is no steal time. when LPAR1 starts running at 100% which
consumes all of the physical resource, steal time starts to get
accounted. With LPAR1 running at 100% and LPAR2 starts running, steal
time starts increasing. This is as expected. When the LPAR2 Load is
increased further, steal time increases further.

Case 1: 0% LPAR1; 0% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
0.00 0.00 0.05 0.00 0.00 0.00 0.00 0.00 0.00 99.95

Case 2: 100% LPAR1; 0% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
97.68 0.00 0.00 0.00 0.00 0.00 2.32 0.00 0.00 0.00

Case 3: 100% LPAR1; 50% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
86.34 0.00 0.10 0.00 0.00 0.03 13.54 0.00 0.00 0.00

Case 4: 100% LPAR1; 100% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
78.54 0.00 0.07 0.00 0.00 0.02 21.36 0.00 0.00 0.00

Case 5: 50% LPAR1; 100% LPAR2
%usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
49.37 0.00 0.00 0.00 0.00 0.00 1.17 0.00 0.00 49.47

Patch is accounting for the steal time and basic tests are holding
good.

Signed-off-by: Nicholas Piggin <[e-mail]>
Tested-by: Shrikanth Hegde <[e-mail]>
[mpe: Add SPDX tag to new paravirt_api_clock.h]
Signed-off-by: Michael Ellerman <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

Documentation/admin-guide/kernel-parameters.txt

···
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc	[X86,PV_OPS,ARM64] Disable paravirtualized steal time
-			accounting. steal time is computed, but won't
-			influence scheduler behaviour
+	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES] Disable paravirtualized
+			steal time accounting. steal time is computed, but
+			won't influence scheduler behaviour
 
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 

arch/powerpc/include/asm/paravirt.h

···
 	return static_branch_unlikely(&shared_processor);
 }
 
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 pseries_paravirt_steal_clock(int cpu);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pseries_paravirt_steal_clock(cpu);
+}
+#endif
+
 /* If bit 0 is set, the cpu has been ceded, conferred, or preempted */
 static inline u32 yield_count_of(int cpu)
 {

arch/powerpc/include/asm/paravirt_api_clock.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/paravirt.h>

arch/powerpc/platforms/pseries/Kconfig

···
 	select SWIOTLB
 	default y
 
+config PARAVIRT
+	bool
+
 config PARAVIRT_SPINLOCKS
+	bool
+
+config PARAVIRT_TIME_ACCOUNTING
+	select PARAVIRT
 	bool
 
 config PPC_SPLPAR
 	bool "Support for shared-processor logical partitions"
 	depends on PPC_PSERIES
 	select PARAVIRT_SPINLOCKS if PPC_QUEUED_SPINLOCKS
+	select PARAVIRT_TIME_ACCOUNTING if VIRT_CPU_ACCOUNTING_GEN
 	default y
 	help
 	  Enabling this option will make the kernel run more efficiently

arch/powerpc/platforms/pseries/lpar.c

···
 }
 
 machine_device_initcall(pseries, vcpudispatch_stats_procfs_init);
+
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+u64 pseries_paravirt_steal_clock(int cpu)
+{
+	struct lppaca *lppaca = &lppaca_of(cpu);
+
+	return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+		be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+}
+#endif
+
 #endif /* CONFIG_PPC_SPLPAR */
 
 void vpa_init(int cpu)

arch/powerpc/platforms/pseries/setup.c

···
 DEFINE_STATIC_KEY_FALSE(shared_processor);
 EXPORT_SYMBOL(shared_processor);
 
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+#endif
+
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
 unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K);
···
 		if (lppaca_shared_proc(get_lppaca())) {
 			static_branch_enable(&shared_processor);
 			pv_spinlocks_init();
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+			static_key_slow_inc(&paravirt_steal_enabled);
+			if (steal_acc)
+				static_key_slow_inc(&paravirt_steal_rq_enabled);
+#endif
 		}
 
 		ppc_md.power_save = pseries_lpar_idle;