powerpc32: provide VIRT_CPU_ACCOUNTING

This patch provides VIRT_CPU_ACCOUTING to PPC32 architecture.
PPC32 doesn't have the PACA structure, so we use the task_info
structure to store the accounting data.

In order to reuse on PPC32 the PPC64 functions, all u64 data has
been replaced by 'unsigned long' so that it is u32 on PPC32 and
u64 on PPC64

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>

arch/powerpc/Kconfig

@@ -165,6 +165,7 @@ config PPC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_VIRT_CPU_ACCOUNTING
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN

arch/powerpc/include/asm/accounting.h

@@ -0,0 +1,24 @@
+/*
+ * Common time accounting prototypes and such for all ppc machines.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __POWERPC_ACCOUNTING_H
+#define __POWERPC_ACCOUNTING_H
+
+/* Stuff for accurate time accounting */
+struct cpu_accounting_data {
+	unsigned long user_time;	/* accumulated usermode TB ticks */
+	unsigned long system_time;	/* accumulated system TB ticks */
+	unsigned long user_time_scaled;	/* accumulated usermode SPURR ticks */
+	unsigned long starttime;	/* TB value snapshot */
+	unsigned long starttime_user;	/* TB value on exit to usermode */
+	unsigned long startspurr;	/* SPURR value snapshot */
+	unsigned long utime_sspurr;	/* ->user_time when ->startspurr set */
+};
+
+#endif

arch/powerpc/include/asm/cputime.h

@@ -90,11 +90,10 @@ static inline void setup_cputime_one_jiffy(void)
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
 	u64 ct;
-	u64 sec;
+	u64 sec = jif;
 
 	/* have to be a little careful about overflow */
-	ct = jif % HZ;
-	sec = jif / HZ;
+	ct = do_div(sec, HZ);
 	if (ct) {
 		ct *= tb_ticks_per_sec;
 		do_div(ct, HZ);
@@ -230,7 +229,16 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 
 #define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
 
+/*
+ * PPC64 uses PACA which is task independent for storing accounting data while
+ * PPC32 uses struct thread_info, therefore at task switch the accounting data
+ * has to be populated in the new task
+ */
+#ifdef CONFIG_PPC64
 static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+#else
+void arch_vtime_task_switch(struct task_struct *tsk);
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */

arch/powerpc/include/asm/exception-64s.h

@@ -287,7 +287,7 @@ do_kvm_##n:								\
 	std	r0,GPR0(r1);		/* save r0 in stackframe	*/ \
 	std	r10,GPR1(r1);		/* save r1 in stackframe	*/ \
 	beq	4f;			/* if from kernel mode		*/ \
-	ACCOUNT_CPU_USER_ENTRY(r9, r10);				   \
+	ACCOUNT_CPU_USER_ENTRY(r13, r9, r10);				   \
 	SAVE_PPR(area, r9, r10);					   \
 4:	EXCEPTION_PROLOG_COMMON_2(area)					   \
 	EXCEPTION_PROLOG_COMMON_3(n)					   \

arch/powerpc/include/asm/paca.h

@@ -25,6 +25,7 @@
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 #include <asm/kvm_book3s_asm.h>
 #endif
+#include <asm/accounting.h>
 
 register struct paca_struct *local_paca asm("r13");
 
@@ -184,13 +185,7 @@ struct paca_struct {
 #endif
 
 	/* Stuff for accurate time accounting */
-	u64 user_time;			/* accumulated usermode TB ticks */
-	u64 system_time;		/* accumulated system TB ticks */
-	u64 user_time_scaled;		/* accumulated usermode SPURR ticks */
-	u64 starttime;			/* TB value snapshot */
-	u64 starttime_user;		/* TB value on exit to usermode */
-	u64 startspurr;			/* SPURR value snapshot */
-	u64 utime_sspurr;		/* ->user_time when ->startspurr set */
+	struct cpu_accounting_data accounting;
 	u64 stolen_time;		/* TB ticks taken by hypervisor */
 	u64 dtl_ridx;			/* read index in dispatch log */
 	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */

arch/powerpc/include/asm/ppc_asm.h

@@ -24,27 +24,27 @@
  */
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#define ACCOUNT_CPU_USER_ENTRY(ra, rb)
-#define ACCOUNT_CPU_USER_EXIT(ra, rb)
+#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)
+#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)
 #define ACCOUNT_STOLEN_TIME
 #else
-#define ACCOUNT_CPU_USER_ENTRY(ra, rb)					\
+#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)				\
 	MFTB(ra);			/* get timebase */		\
-	ld	rb,PACA_STARTTIME_USER(r13);				\
-	std	ra,PACA_STARTTIME(r13);					\
+	PPC_LL	rb, ACCOUNT_STARTTIME_USER(ptr);			\
+	PPC_STL	ra, ACCOUNT_STARTTIME(ptr);				\
 	subf	rb,rb,ra;		/* subtract start value */	\
-	ld	ra,PACA_USER_TIME(r13);					\
+	PPC_LL	ra, ACCOUNT_USER_TIME(ptr);				\
 	add	ra,ra,rb;		/* add on to user time */	\
-	std	ra,PACA_USER_TIME(r13);					\
+	PPC_STL	ra, ACCOUNT_USER_TIME(ptr);				\
 
-#define ACCOUNT_CPU_USER_EXIT(ra, rb)					\
+#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)				\
 	MFTB(ra);			/* get timebase */		\
-	ld	rb,PACA_STARTTIME(r13);					\
-	std	ra,PACA_STARTTIME_USER(r13);				\
+	PPC_LL	rb, ACCOUNT_STARTTIME(ptr);				\
+	PPC_STL	ra, ACCOUNT_STARTTIME_USER(ptr);			\
 	subf	rb,rb,ra;		/* subtract start value */	\
-	ld	ra,PACA_SYSTEM_TIME(r13);				\
+	PPC_LL	ra, ACCOUNT_SYSTEM_TIME(ptr);				\
 	add	ra,ra,rb;		/* add on to system time */	\
-	std	ra,PACA_SYSTEM_TIME(r13)
+	PPC_STL	ra, ACCOUNT_SYSTEM_TIME(ptr)
 
 #ifdef CONFIG_PPC_SPLPAR
 #define ACCOUNT_STOLEN_TIME						\

arch/powerpc/include/asm/reg.h

@@ -1294,6 +1294,7 @@ static inline unsigned long mfvtb (void)
 			asm volatile("mfspr %0, %1" : "=r" (rval) : \
 				"i" (SPRN_TBRU)); rval;})
 #endif
+#define mftb()		mftbl()
 #endif /* !__powerpc64__ */
 
 #define mttbl(v)	asm volatile("mttbl %0":: "r"(v))

arch/powerpc/include/asm/thread_info.h

@@ -33,6 +33,7 @@
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <linux/stringify.h>
+#include <asm/accounting.h>
 
 /*
  * low level task data.
@@ -45,6 +46,9 @@ struct thread_info {
 	unsigned long	local_flags;		/* private flags for thread */
 #ifdef CONFIG_LIVEPATCH
 	unsigned long *livepatch_sp;
+#endif
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC32)
+	struct cpu_accounting_data accounting;
 #endif
 	/* low level flags - has atomic operations done on it */
 	unsigned long	flags ____cacheline_aligned_in_smp;

arch/powerpc/kernel/asm-offsets.c

@@ -240,13 +240,28 @@ int main(void)
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
 	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
 	DEFINE(PACA_DSCR_DEFAULT, offsetof(struct paca_struct, dscr_default));
-	DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
-	DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
-	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
-	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
+	DEFINE(ACCOUNT_STARTTIME,
+	       offsetof(struct paca_struct, accounting.starttime));
+	DEFINE(ACCOUNT_STARTTIME_USER,
+	       offsetof(struct paca_struct, accounting.starttime_user));
+	DEFINE(ACCOUNT_USER_TIME,
+	       offsetof(struct paca_struct, accounting.user_time));
+	DEFINE(ACCOUNT_SYSTEM_TIME,
+	       offsetof(struct paca_struct, accounting.system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 	DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
 	DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
+#else /* CONFIG_PPC64 */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	DEFINE(ACCOUNT_STARTTIME,
+	       offsetof(struct thread_info, accounting.starttime));
+	DEFINE(ACCOUNT_STARTTIME_USER,
+	       offsetof(struct thread_info, accounting.starttime_user));
+	DEFINE(ACCOUNT_USER_TIME,
+	       offsetof(struct thread_info, accounting.user_time));
+	DEFINE(ACCOUNT_SYSTEM_TIME,
+	       offsetof(struct thread_info, accounting.system_time));
+#endif
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */

arch/powerpc/kernel/entry_32.S

@@ -175,6 +175,12 @@ transfer_to_handler:
 	addi	r12,r12,-1
 	stw	r12,4(r11)
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	CURRENT_THREAD_INFO(r9, r1)
+	tophys(r9, r9)
+	ACCOUNT_CPU_USER_ENTRY(r9, r11, r12)
+#endif
+
 	b	3f
 
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
@@ -398,6 +404,13 @@ BEGIN_FTR_SECTION
 	lwarx	r7,0,r1
 END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1			/* to clear the reservation */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	andi.	r4,r8,MSR_PR
+	beq	3f
+	CURRENT_THREAD_INFO(r4, r1)
+	ACCOUNT_CPU_USER_EXIT(r4, r5, r7)
+3:
+#endif
 	lwz	r4,_LINK(r1)
 	lwz	r5,_CCR(r1)
 	mtlr	r4
@@ -769,6 +782,10 @@ restore_user:
 	andis.	r10,r0,DBCR0_IDM@h
 	bnel-	load_dbcr0
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	CURRENT_THREAD_INFO(r9, r1)
+	ACCOUNT_CPU_USER_EXIT(r9, r10, r11)
+#endif
 
 	b	restore
 

arch/powerpc/kernel/entry_64.S

@@ -72,7 +72,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
 	beq	2f			/* if from kernel mode */
-	ACCOUNT_CPU_USER_ENTRY(r10, r11)
+	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
 2:	std	r2,GPR2(r1)
 	std	r3,GPR3(r1)
 	mfcr	r2
@@ -246,7 +246,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	ld	r4,_LINK(r1)
 
 	beq-	1f
-	ACCOUNT_CPU_USER_EXIT(r11, r12)
+	ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
 
 BEGIN_FTR_SECTION
 	HMT_MEDIUM_LOW
@@ -859,7 +859,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 BEGIN_FTR_SECTION
 	mtspr	SPRN_PPR,r2	/* Restore PPR */
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	ACCOUNT_CPU_USER_EXIT(r2, r4)
+	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
 1:
 	mtspr	SPRN_SRR1,r3

arch/powerpc/kernel/exceptions-64e.S

@@ -386,7 +386,7 @@ exc_##n##_common:							    \
 	std	r10,_NIP(r1);		/* save SRR0 to stackframe */	    \
 	std	r11,_MSR(r1);		/* save SRR1 to stackframe */	    \
 	beq	2f;			/* if from kernel mode */	    \
-	ACCOUNT_CPU_USER_ENTRY(r10,r11);/* accounting (uses cr0+eq) */	    \
+	ACCOUNT_CPU_USER_ENTRY(r13,r10,r11);/* accounting (uses cr0+eq) */  \
 2:	ld	r3,excf+EX_R10(r13);	/* get back r10 */		    \
 	ld	r4,excf+EX_R11(r13);	/* get back r11 */		    \
 	mfspr	r5,scratch;		/* get back r13 */		    \
@@ -1059,7 +1059,7 @@ fast_exception_return:
 	andi.	r6,r10,MSR_PR
 	REST_2GPRS(6, r1)
 	beq	1f
-	ACCOUNT_CPU_USER_EXIT(r10, r11)
+	ACCOUNT_CPU_USER_EXIT(r13, r10, r11)
 	ld	r0,GPR13(r1)
 
 1:	stdcx.	r0,0,r1		/* to clear the reservation */

arch/powerpc/kernel/time.c

@@ -167,7 +167,15 @@ DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 cputime_t cputime_one_jiffy;
 
+#ifdef CONFIG_PPC_SPLPAR
 void (*dtl_consumer)(struct dtl_entry *, u64);
+#endif
+
+#ifdef CONFIG_PPC64
+#define get_accounting(tsk)	(&get_paca()->accounting)
+#else
+#define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
+#endif
 
 static void calc_cputime_factors(void)
 {
@@ -187,7 +195,7 @@ static void calc_cputime_factors(void)
  * Read the SPURR on systems that have it, otherwise the PURR,
  * or if that doesn't exist return the timebase value passed in.
  */
-static u64 read_spurr(u64 tb)
+static unsigned long read_spurr(unsigned long tb)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		return mfspr(SPRN_SPURR);
@@ -250,8 +258,8 @@ static u64 scan_dispatch_log(u64 stop_tb)
 void accumulate_stolen_time(void)
 {
 	u64 sst, ust;
-
 	u8 save_soft_enabled = local_paca->soft_enabled;
+	struct cpu_accounting_data *acct = &local_paca->accounting;
 
 	/* We are called early in the exception entry, before
 	 * soft/hard_enabled are sync'ed to the expected state
@@ -261,10 +269,10 @@ void accumulate_stolen_time(void)
 	 */
 	local_paca->soft_enabled = 0;
 
-	sst = scan_dispatch_log(local_paca->starttime_user);
-	ust = scan_dispatch_log(local_paca->starttime);
-	local_paca->system_time -= sst;
-	local_paca->user_time -= ust;
+	sst = scan_dispatch_log(acct->starttime_user);
+	ust = scan_dispatch_log(acct->starttime);
+	acct->system_time -= sst;
+	acct->user_time -= ust;
 	local_paca->stolen_time += ust + sst;
 
 	local_paca->soft_enabled = save_soft_enabled;
@@ -276,7 +284,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
 
 	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
 		stolen = scan_dispatch_log(stop_tb);
-		get_paca()->system_time -= stolen;
+		get_paca()->accounting.system_time -= stolen;
 	}
 
 	stolen += get_paca()->stolen_time;
@@ -296,27 +304,29 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
-static u64 vtime_delta(struct task_struct *tsk,
-			u64 *sys_scaled, u64 *stolen)
+static unsigned long vtime_delta(struct task_struct *tsk,
+				 unsigned long *sys_scaled,
+				 unsigned long *stolen)
 {
-	u64 now, nowscaled, deltascaled;
-	u64 udelta, delta, user_scaled;
+	unsigned long now, nowscaled, deltascaled;
+	unsigned long udelta, delta, user_scaled;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = mftb();
 	nowscaled = read_spurr(now);
-	get_paca()->system_time += now - get_paca()->starttime;
-	get_paca()->starttime = now;
-	deltascaled = nowscaled - get_paca()->startspurr;
-	get_paca()->startspurr = nowscaled;
+	acct->system_time += now - acct->starttime;
+	acct->starttime = now;
+	deltascaled = nowscaled - acct->startspurr;
+	acct->startspurr = nowscaled;
 
 	*stolen = calculate_stolen_time(now);
 
-	delta = get_paca()->system_time;
-	get_paca()->system_time = 0;
-	udelta = get_paca()->user_time - get_paca()->utime_sspurr;
-	get_paca()->utime_sspurr = get_paca()->user_time;
+	delta = acct->system_time;
+	acct->system_time = 0;
+	udelta = acct->user_time - acct->utime_sspurr;
+	acct->utime_sspurr = acct->user_time;
 
 	/*
 	 * Because we don't read the SPURR on every kernel entry/exit,
@@ -338,14 +348,14 @@ static u64 vtime_delta(struct task_struct *tsk,
 			*sys_scaled = deltascaled;
 		}
 	}
-	get_paca()->user_time_scaled += user_scaled;
+	acct->user_time_scaled += user_scaled;
 
 	return delta;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	u64 delta, sys_scaled, stolen;
+	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
 	account_system_time(tsk, 0, delta, sys_scaled);
@@ -356,7 +366,7 @@ EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	u64 delta, sys_scaled, stolen;
+	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
 	account_idle_time(delta + stolen);
@@ -374,15 +384,32 @@ void vtime_account_idle(struct task_struct *tsk)
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	utime = get_paca()->user_time;
-	utimescaled = get_paca()->user_time_scaled;
-	get_paca()->user_time = 0;
-	get_paca()->user_time_scaled = 0;
-	get_paca()->utime_sspurr = 0;
+	utime = acct->user_time;
+	utimescaled = acct->user_time_scaled;
+	acct->user_time = 0;
+	acct->user_time_scaled = 0;
+	acct->utime_sspurr = 0;
 	account_user_time(tsk, utime, utimescaled);
 }
 
+#ifdef CONFIG_PPC32
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void arch_vtime_task_switch(struct task_struct *prev)
+{
+	struct cpu_accounting_data *acct = get_accounting(current);
+
+	acct->starttime = get_accounting(prev)->starttime;
+	acct->system_time = 0;
+	acct->user_time = 0;
+}
+#endif /* CONFIG_PPC32 */
+
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #define calc_cputime_factors()
 #endif

arch/powerpc/platforms/Kconfig.cputype

@@ -1,7 +1,6 @@
 config PPC64
 	bool "64-bit kernel"
 	default n
-	select HAVE_VIRT_CPU_ACCOUNTING
 	select ZLIB_DEFLATE
 	help
 	  This option selects whether a 32-bit or a 64-bit kernel

arch/powerpc/xmon/xmon.c

@@ -2213,13 +2213,13 @@ static void dump_one_paca(int cpu)
 	DUMP(p, subcore_sibling_mask, "x");
 #endif
 
-	DUMP(p, user_time, "llx");
-	DUMP(p, system_time, "llx");
-	DUMP(p, user_time_scaled, "llx");
-	DUMP(p, starttime, "llx");
-	DUMP(p, starttime_user, "llx");
-	DUMP(p, startspurr, "llx");
-	DUMP(p, utime_sspurr, "llx");
+	DUMP(p, accounting.user_time, "llx");
+	DUMP(p, accounting.system_time, "llx");
+	DUMP(p, accounting.user_time_scaled, "llx");
+	DUMP(p, accounting.starttime, "llx");
+	DUMP(p, accounting.starttime_user, "llx");
+	DUMP(p, accounting.startspurr, "llx");
+	DUMP(p, accounting.utime_sspurr, "llx");
 	DUMP(p, stolen_time, "llx");
 #undef DUMP