Skip to contentSkip to conversation

powerpc/64s: Move idle code to powernv C code

RFC PATCH New Nicholas Piggin 1 participant 1 message Jul 31, 2018

Subsystems (2)
lore
Share & tools
lore

Nicholas Piggin

author reviewer
#0 lore raw

RFC PATCH v3 1/1 powerpc/64s: Move idle code to powernv C code

Reimplement Book3S idle code to C, in the powernv platform code. Assembly stubs are used to save and restore the stack frame and non-volatile GPRs before going to idle, but these are small and mostly agnostic to microarchitecture implementation details.

The optimisation where EC=ESL=0 idle modes did not have to save GPRs or mtmsrd L=0 is restored, because it's simple to do.

Idle wakeup no longer uses the ->cpu_restore call to reinit SPRs, but saves and restores them all explicitly. This can easily be extended to tracking the set of system-wide SPRs that do not have to be saved each time.

Moving the HMI, SPR, OPAL, locking, etc. to C is the only real way this stuff will cope with non-trivial new CPU implementation details, firmware changes, etc., without becoming unmaintainable.

Since RFC v1:
- Now tested and working with POWER9 hash and radix.
- KVM support added. This took a bit of work to untangle and might still have some issues, but POWER9 seems to work including hash on radix with dependent threads mode.
- This snowballed a bit because of KVM and other details making it not feasible to leave POWER7/8 code alone. That's only half done at the moment.
- So far this trades about 800 lines of asm for 500 of C. With POWER7/8 support done it might be another hundred or so lines of C.

Since RFC v2:
- Fixed deep state SLB reloading
- Now tested and working with POWER8.
- Accounted for most feedback.

Thanks,
Nick

---
 include/asm/book3s/64/mmu-hash.h |    1 
 include/asm/cpuidle.h            |   21 
 include/asm/paca.h               |   40 -
 include/asm/processor.h          |    9 
 include/asm/reg.h                |    7 
 kernel/asm-offsets.c             |   18 
 kernel/dt_cpu_ftrs.c             |   21 
 kernel/exceptions-64s.S          |   17 
 kernel/idle_book3s.S             |  998 +++------------------------------------
 kernel/setup-common.c            |    4 
 kvm/book3s_hv_rmhandlers.S       |   94 ++-
 mm/slb.c                         |   15 
 platforms/powernv/idle.c         |  839 ++++++++++++++++++++++++++------
 platforms/powernv/subcore.c      |    2 
 xmon/xmon.c                      |   25 
 15 files changed, 902 insertions(+), 1209 deletions(-)
arch/powerpc/include/asm/book3s/64/mmu-hash.h +1 -0
index 50ed64fba4ae..b68a4fe446d6 100644
@@ -487,6 +487,7 @@ extern void hpte_init_native(void);
 
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
+extern void slb_shadow_reload(void);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);
arch/powerpc/include/asm/cpuidle.h +3 -18
index e210a83eb196..9b5c7ec908f2 100644
@@ -27,10 +27,11 @@
  * the THREAD_WINKLE_BITS are set, which indicate which threads have not
  * yet woken from the winkle state.
  */
-#define PNV_CORE_IDLE_LOCK_BIT			0x10000000
+#define NR_PNV_CORE_IDLE_LOCK_BIT		28
+#define PNV_CORE_IDLE_LOCK_BIT			(1ULL << NR_PNV_CORE_IDLE_LOCK_BIT)
 
+#define PNV_CORE_IDLE_WINKLE_COUNT_SHIFT	16
 #define PNV_CORE_IDLE_WINKLE_COUNT		0x00010000
-#define PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT	0x00080000
 #define PNV_CORE_IDLE_WINKLE_COUNT_BITS		0x000F0000
 #define PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT	8
 #define PNV_CORE_IDLE_THREAD_WINKLE_BITS	0x0000FF00
@@ -68,22 +69,6 @@
 #define ERR_DEEP_STATE_ESL_MISMATCH	-2
 
 #ifndef __ASSEMBLY__
-/* Additional SPRs that need to be saved/restored during stop */
-struct stop_sprs {
-	u64 pid;
-	u64 ldbar;
-	u64 fscr;
-	u64 hfscr;
-	u64 mmcr1;
-	u64 mmcr2;
-	u64 mmcra;
-};
-
-extern u32 pnv_fastsleep_workaround_at_entry[];
-extern u32 pnv_fastsleep_workaround_at_exit[];
-
-extern u64 pnv_first_deep_stop_state;
-
 unsigned long pnv_cpu_offline(unsigned int cpu);
 int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags);
 static inline void report_invalid_psscr_val(u64 psscr_val, int err)
arch/powerpc/include/asm/paca.h +23 -17
index 4e9cede5a7e7..d2cee5ebaaa1 100644
@@ -168,7 +168,6 @@ struct paca_struct {
 	u8 irq_happened;		/* irq happened while soft-disabled */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
-	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	u8 pmcregs_in_use;		/* pseries puts this in lppaca */
 #endif
@@ -178,23 +177,30 @@ struct paca_struct {
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	/* Per-core mask tracking idle threads and a lock bit-[L][TTTTTTTT] */
-	u32 *core_idle_state_ptr;
-	u8 thread_idle_state;		/* PNV_THREAD_RUNNING/NAP/SLEEP	*/
-	/* Mask to indicate thread id in core */
-	u8 thread_mask;
-	/* Mask to denote subcore sibling threads */
-	u8 subcore_sibling_mask;
-	/* Flag to request this thread not to stop */
-	atomic_t dont_stop;
-	/* The PSSCR value that the kernel requested before going to stop */
-	u64 requested_psscr;
+	/* PowerNV idle fields */
+	/* PNV_CORE_IDLE_* bits, all siblings work on thread 0 paca */
+	unsigned long idle_state;
+	union {
+		/* P7/P8 specific fields */
+		struct {
+			/* PNV_THREAD_RUNNING/NAP/SLEEP	*/
+			u8 thread_idle_state;
+			/* Mask to indicate thread id in core */
+			u8 thread_mask;
+			/* Mask to denote subcore sibling threads */
+			u8 subcore_sibling_mask;
+		};
 
-	/*
-	 * Save area for additional SPRs that need to be
-	 * saved/restored during cpuidle stop.
-	 */
-	struct stop_sprs stop_sprs;
+		/* P9 specific fields */
+		struct {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+			/* The PSSCR value that the kernel requested before going to stop */
+			u64 requested_psscr;
+			/* Flag to request this thread not to stop */
+			atomic_t dont_stop;
+#endif
+		};
+	};
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
arch/powerpc/include/asm/processor.h +6 -3
index 5debe337ea9d..1d241f4d8612 100644
@@ -507,14 +507,17 @@ static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 }
 #endif
 
+/* asm stubs */
+extern unsigned long isa3_idle_stop_noloss(unsigned long psscr_val);
+extern unsigned long isa3_idle_stop_mayloss(unsigned long psscr_val);
+extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
+
 extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-extern unsigned long power7_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc*/
+
 extern void power7_idle_type(unsigned long type);
-extern unsigned long power9_idle_stop(unsigned long psscr_val);
-extern unsigned long power9_offline_stop(unsigned long psscr_val);
 extern void power9_idle_type(unsigned long stop_psscr_val,
 			      unsigned long stop_psscr_mask);
 
arch/powerpc/include/asm/reg.h +3 -4
index d85d000d05b5..76513a2a2192 100644
@@ -753,10 +753,9 @@
 #define	  SRR1_WAKERESET	0x00100000 /* System reset */
 #define   SRR1_WAKEHDBELL	0x000c0000 /* Hypervisor doorbell on P8 */
 #define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
-#define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
-					  * may not be recoverable */
-#define	  SRR1_WS_DEEPER	0x00020000 /* Some resources not maintained */
-#define	  SRR1_WS_DEEP		0x00010000 /* All resources maintained */
+#define	  SRR1_WS_HVLOSS	0x00030000 /* HV resources not maintained */
+#define	  SRR1_WS_GPRLOSS	0x00020000 /* GPRs not maintained */
+#define	  SRR1_WS_NOLOSS	0x00010000 /* All resources maintained */
 #define   SRR1_PROGTM		0x00200000 /* TM Bad Thing */
 #define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
 #define   SRR1_PROGILL		0x00080000 /* Illegal instruction */
arch/powerpc/kernel/asm-offsets.c +0 -18
index 89cf15566c4e..7834256585f1 100644
@@ -256,7 +256,6 @@ int main(void)
 	OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime);
 	OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime);
 	OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
-	OFFSET(PACA_NAPSTATELOST, paca_struct, nap_state_lost);
 	OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso);
 #else /* CONFIG_PPC64 */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
@@ -761,23 +760,6 @@ int main(void)
 	OFFSET(VCPU_TIMING_LAST_ENTER_TBL, kvm_vcpu, arch.timing_last_enter.tv32.tbl);
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	OFFSET(PACA_CORE_IDLE_STATE_PTR, paca_struct, core_idle_state_ptr);
-	OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state);
-	OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask);
-	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
-	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
-	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
-#define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
-	STOP_SPR(STOP_PID, pid);
-	STOP_SPR(STOP_LDBAR, ldbar);
-	STOP_SPR(STOP_FSCR, fscr);
-	STOP_SPR(STOP_HFSCR, hfscr);
-	STOP_SPR(STOP_MMCR1, mmcr1);
-	STOP_SPR(STOP_MMCR2, mmcr2);
-	STOP_SPR(STOP_MMCRA, mmcra);
-#endif
-
 	DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
 	DEFINE(PPC_DBELL_MSGTYPE, PPC_DBELL_MSGTYPE);
 
arch/powerpc/kernel/dt_cpu_ftrs.c +1 -20
index f432054234a4..d635d78facdc 100644
@@ -71,7 +71,6 @@ static int hv_mode;
 
 static struct {
 	u64	lpcr;
-	u64	lpcr_clear;
 	u64	hfscr;
 	u64	fscr;
 } system_registers;
@@ -80,24 +79,7 @@ static void (*init_pmu_registers)(void);
 
 static void __restore_cpu_cpufeatures(void)
 {
-	u64 lpcr;
-
-	/*
-	 * LPCR is restored by the power on engine already. It can be changed
-	 * after early init e.g., by radix enable, and we have no unified API
-	 * for saving and restoring such SPRs.
-	 *
-	 * This ->restore hook should really be removed from idle and register
-	 * restore moved directly into the idle restore code, because this code
-	 * doesn't know how idle is implemented or what it needs restored here.
-	 *
-	 * The best we can do to accommodate secondary boot and idle restore
-	 * for now is "or" LPCR with existing.
-	 */
-	lpcr = mfspr(SPRN_LPCR);
-	lpcr |= system_registers.lpcr;
-	lpcr &= ~system_registers.lpcr_clear;
-	mtspr(SPRN_LPCR, lpcr);
+	mtspr(SPRN_LPCR, system_registers.lpcr);
 	if (hv_mode) {
 		mtspr(SPRN_LPID, 0);
 		mtspr(SPRN_HFSCR, system_registers.hfscr);
@@ -318,7 +300,6 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f)
 {
 	u64 lpcr;
 
-	system_registers.lpcr_clear |= (LPCR_ISL | LPCR_UPRT | LPCR_HR);
 	lpcr = mfspr(SPRN_LPCR);
 	lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR);
 	mtspr(SPRN_LPCR, lpcr);
arch/powerpc/kernel/exceptions-64s.S +9 -8
index 76a14702cb9c..137f0f446472 100644
@@ -135,8 +135,9 @@ TRAMP_KVM(PACA_EXNMI, 0x100)
 
 #ifdef CONFIG_PPC_P7_NAP
 EXC_COMMON_BEGIN(system_reset_idle_common)
-	mfspr	r12,SPRN_SRR1
-	b	pnv_powersave_wakeup
+	mfspr	r3,SPRN_SRR1
+	bltlr	cr3	/* no state loss, return to idle caller */
+	b	idle_return_gpr_loss
 #endif
 
 /*
@@ -415,17 +416,17 @@ EXC_COMMON_BEGIN(machine_check_idle_common)
 	 * Then decrement MCE nesting after finishing with the stack.
 	 */
 	ld	r3,_MSR(r1)
+	ld	r4,_LINK(r1)
 
 	lhz	r11,PACA_IN_MCE(r13)
 	subi	r11,r11,1
 	sth	r11,PACA_IN_MCE(r13)
 
-	/* Turn off the RI bit because SRR1 is used by idle wakeup code. */
-	/* Recoverability could be improved by reducing the use of SRR1. */
-	li	r11,0
-	mtmsrd	r11,1
-
-	b	pnv_powersave_wakeup_mce
+	mtlr	r4
+	rlwinm	r10,r3,47-31,30,31
+	cmpwi	cr3,r10,2
+	bltlr	cr3	/* no state loss, return to idle caller */
+	b	idle_return_gpr_loss
 #endif
 	/*
 	 * Handle machine check early in real mode. We come here with
arch/powerpc/kernel/idle_book3s.S +90 -908

1,037 lines not on this page · raw message

arch/powerpc/kernel/setup-common.c +2 -2
index 40b44bb53a4e..e089da156ef3 100644
@@ -401,8 +401,8 @@ void __init check_for_initrd(void)
 
 #ifdef CONFIG_SMP
 
-int threads_per_core, threads_per_subcore, threads_shift;
-cpumask_t threads_core_mask;
+int threads_per_core, threads_per_subcore, threads_shift __read_mostly;
+cpumask_t threads_core_mask __read_mostly;
 EXPORT_SYMBOL_GPL(threads_per_core);
 EXPORT_SYMBOL_GPL(threads_per_subcore);
 EXPORT_SYMBOL_GPL(threads_shift);
arch/powerpc/kvm/book3s_hv_rmhandlers.S +56 -38

169 lines not on this page · raw message

arch/powerpc/mm/slb.c +15 -0
index cb796724a6fc..1518beec3161 100644
@@ -90,6 +90,21 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
 		     : "memory" );
 }
 
+void slb_shadow_reload(void)
+{
+	struct slb_shadow *p = get_slb_shadow();
+	enum slb_index index;
+
+	for (index = 0; index < SLB_NUM_BOLTED; index++) {
+		if (be64_to_cpu(p->save_area[index].esid) & SLB_ESID_V) {
+			asm volatile("slbmte  %0,%1" :
+			     : "r" (be64_to_cpu(p->save_area[index].vsid)),
+			       "r" (be64_to_cpu(p->save_area[index].esid)));
+		}
+	}
+	isync();
+}
+
 static void __slb_flush_and_rebolt(void)
 {
 	/* If you change this make sure you change SLB_NUM_BOLTED
arch/powerpc/platforms/powernv/idle.c +681 -158

1,019 lines not on this page · raw message

arch/powerpc/platforms/powernv/subcore.c +1 -1
index 45563004feda..1d7a9fd30dd1 100644
@@ -183,7 +183,7 @@ static void unsplit_core(void)
 	cpu = smp_processor_id();
 	if (cpu_thread_in_core(cpu) != 0) {
 		while (mfspr(SPRN_HID0) & mask)
-			power7_idle_insn(PNV_THREAD_NAP);
+			power7_idle_type(PNV_THREAD_NAP);
 
 		per_cpu(split_state, cpu).step = SYNC_STEP_UNSPLIT;
 		return;
arch/powerpc/xmon/xmon.c +11 -14
index fdc43d5ccb42..4fcae8e8e741 100644
@@ -2417,7 +2417,6 @@ static void dump_one_paca(int cpu)
 	DUMP(p, irq_happened, "%#-*x");
 	DUMP(p, io_sync, "%#-*x");
 	DUMP(p, irq_work_pending, "%#-*x");
-	DUMP(p, nap_state_lost, "%#-*x");
 	DUMP(p, sprg_vdso, "%#-*llx");
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -2425,19 +2424,17 @@ static void dump_one_paca(int cpu)
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	DUMP(p, core_idle_state_ptr, "%-*px");
-	DUMP(p, thread_idle_state, "%#-*x");
-	DUMP(p, thread_mask, "%#-*x");
-	DUMP(p, subcore_sibling_mask, "%#-*x");
-	DUMP(p, requested_psscr, "%#-*llx");
-	DUMP(p, stop_sprs.pid, "%#-*llx");
-	DUMP(p, stop_sprs.ldbar, "%#-*llx");
-	DUMP(p, stop_sprs.fscr, "%#-*llx");
-	DUMP(p, stop_sprs.hfscr, "%#-*llx");
-	DUMP(p, stop_sprs.mmcr1, "%#-*llx");
-	DUMP(p, stop_sprs.mmcr2, "%#-*llx");
-	DUMP(p, stop_sprs.mmcra, "%#-*llx");
-	DUMP(p, dont_stop.counter, "%#-*x");
+	DUMP(p, idle_state, "%#-*lx");
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		DUMP(p, thread_idle_state, "%#-*x");
+		DUMP(p, thread_mask, "%#-*x");
+		DUMP(p, subcore_sibling_mask, "%#-*x");
+	} else {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		DUMP(p, requested_psscr, "%#-*llx");
+		DUMP(p, dont_stop.counter, "%#-*x");
+#endif
+	}
 #endif
 
 	DUMP(p, accounting.utime, "%#-*lx");