Merge branch 'topic/ppc-kvm' into next

Merge our topic branch shared with KVM. In particular this includes the
rewrite of the idle code into C.

Documentation/powerpc/DAWR-POWER9.txt

@@ -56,3 +56,35 @@ POWER9. Loads and stores to the watchpoint locations will not be
 trapped in GDB. The watchpoint is remembered, so if the guest is
 migrated back to the POWER8 host, it will start working again.
 
+Force enabling the DAWR
+=============================
+Kernels (since ~v5.2) have an option to force enable the DAWR via:
+
+  echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous
+
+This enables the DAWR even on POWER9.
+
+This is a dangerous setting, USE AT YOUR OWN RISK.
+
+Some users may not care about a bad user crashing their box
+(ie. single user/desktop systems) and really want the DAWR.  This
+allows them to force enable DAWR.
+
+This flag can also be used to disable DAWR access. Once this is
+cleared, all DAWR access should be cleared immediately and your
+machine once again safe from crashing.
+
+Userspace may get confused by toggling this. If DAWR is force
+enabled/disabled between getting the number of breakpoints (via
+PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an
+inconsistent view of what's available. Similarly for guests.
+
+For the DAWR to be enabled in a KVM guest, the DAWR needs to be force
+enabled in the host AND the guest. For this reason, this won't work on
+POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the
+dawr_enable_dangerous file will fail if the hypervisor doesn't support
+writing the DAWR.
+
+To double check the DAWR is working, run this kernel selftest:
+  tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
+Any errors/failures/skips mean something is wrong.

arch/powerpc/include/asm/cpuidle.h

@@ -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
@@ -68,16 +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;
-};
 
 #define PNV_IDLE_NAME_LEN    16
 struct pnv_idle_states_t {
@@ -92,10 +83,6 @@ struct pnv_idle_states_t {
 
 extern struct pnv_idle_states_t *pnv_idle_states;
 extern int nr_pnv_idle_states;
-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);

arch/powerpc/include/asm/hw_breakpoint.h

@@ -90,10 +90,18 @@ static inline void hw_breakpoint_disable(void)
 extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs);
 int hw_breakpoint_handler(struct die_args *args);
 
+extern int set_dawr(struct arch_hw_breakpoint *brk);
+extern bool dawr_force_enable;
+static inline bool dawr_enabled(void)
+{
+	return dawr_force_enable;
+}
+
 #else	/* CONFIG_HAVE_HW_BREAKPOINT */
 static inline void hw_breakpoint_disable(void) { }
 static inline void thread_change_pc(struct task_struct *tsk,
 					struct pt_regs *regs) { }
+static inline bool dawr_enabled(void) { return false; }
 #endif	/* CONFIG_HAVE_HW_BREAKPOINT */
 #endif	/* __KERNEL__ */
 #endif	/* _PPC_BOOK3S_64_HW_BREAKPOINT_H */

arch/powerpc/include/asm/opal-api.h

@@ -186,8 +186,8 @@
 #define OPAL_XIVE_FREE_IRQ			140
 #define OPAL_XIVE_SYNC				141
 #define OPAL_XIVE_DUMP				142
-#define OPAL_XIVE_RESERVED3			143
-#define OPAL_XIVE_RESERVED4			144
+#define OPAL_XIVE_GET_QUEUE_STATE		143
+#define OPAL_XIVE_SET_QUEUE_STATE		144
 #define OPAL_SIGNAL_SYSTEM_RESET		145
 #define OPAL_NPU_INIT_CONTEXT			146
 #define OPAL_NPU_DESTROY_CONTEXT		147
@@ -210,7 +210,8 @@
 #define OPAL_PCI_GET_PBCQ_TUNNEL_BAR		164
 #define OPAL_PCI_SET_PBCQ_TUNNEL_BAR		165
 #define	OPAL_NX_COPROC_INIT			167
-#define OPAL_LAST				167
+#define OPAL_XIVE_GET_VP_STATE			170
+#define OPAL_LAST				170
 
 #define QUIESCE_HOLD			1 /* Spin all calls at entry */
 #define QUIESCE_REJECT			2 /* Fail all calls with OPAL_BUSY */

arch/powerpc/include/asm/opal.h

@@ -279,6 +279,13 @@ int64_t opal_xive_allocate_irq(uint32_t chip_id);
 int64_t opal_xive_free_irq(uint32_t girq);
 int64_t opal_xive_sync(uint32_t type, uint32_t id);
 int64_t opal_xive_dump(uint32_t type, uint32_t id);
+int64_t opal_xive_get_queue_state(uint64_t vp, uint32_t prio,
+				  __be32 *out_qtoggle,
+				  __be32 *out_qindex);
+int64_t opal_xive_set_queue_state(uint64_t vp, uint32_t prio,
+				  uint32_t qtoggle,
+				  uint32_t qindex);
+int64_t opal_xive_get_vp_state(uint64_t vp, __be64 *out_w01);
 int64_t opal_pci_set_p2p(uint64_t phb_init, uint64_t phb_target,
 			uint64_t desc, uint16_t pe_number);
 

arch/powerpc/include/asm/paca.h

@@ -173,7 +173,6 @@ 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
@@ -183,23 +182,28 @@ 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;
+	/* 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 denote subcore sibling threads */
 			u8 subcore_sibling_mask;
-	/* Flag to request this thread not to stop */
-	atomic_t dont_stop;
+		};
+
+		/* P9 specific fields */
+		struct {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 			/* The PSSCR value that the kernel requested before going to stop */
 			u64 requested_psscr;
-
-	/*
-	 * Save area for additional SPRs that need to be
-	 * saved/restored during cpuidle stop.
-	 */
-	struct stop_sprs stop_sprs;
+			/* 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

@@ -414,14 +414,17 @@ static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 }
 #endif
 
+/* asm stubs */
+extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
+extern unsigned long isa300_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

@@ -168,6 +168,7 @@
 #define PSSCR_ESL		0x00200000 /* Enable State Loss */
 #define PSSCR_SD		0x00400000 /* Status Disable */
 #define PSSCR_PLS	0xf000000000000000 /* Power-saving Level Status */
+#define PSSCR_PLS_SHIFT	60
 #define PSSCR_GUEST_VIS	0xf0000000000003ffUL /* Guest-visible PSSCR fields */
 #define PSSCR_FAKE_SUSPEND	0x00000400 /* Fake-suspend bit (P9 DD2.2) */
 #define PSSCR_FAKE_SUSPEND_LG	10	   /* Fake-suspend bit position */
@@ -758,10 +759,9 @@
 #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/include/asm/xive.h

@@ -109,12 +109,26 @@ extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
 extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
 
 extern void xive_native_sync_source(u32 hw_irq);
+extern void xive_native_sync_queue(u32 hw_irq);
 extern bool is_xive_irq(struct irq_chip *chip);
 extern int xive_native_enable_vp(u32 vp_id, bool single_escalation);
 extern int xive_native_disable_vp(u32 vp_id);
 extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
 extern bool xive_native_has_single_escalation(void);
 
+extern int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
+				      u64 *out_qpage,
+				      u64 *out_qsize,
+				      u64 *out_qeoi_page,
+				      u32 *out_escalate_irq,
+				      u64 *out_qflags);
+
+extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle,
+				       u32 *qindex);
+extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle,
+				       u32 qindex);
+extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state);
+
 #else
 
 static inline bool xive_enabled(void) { return false; }

arch/powerpc/kernel/asm-offsets.c

@@ -271,7 +271,6 @@ 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
@@ -773,23 +772,6 @@ 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/exceptions-64s.S

@@ -121,7 +121,9 @@ EXC_VIRT_NONE(0x4000, 0x100)
 	mfspr	r10,SPRN_SRR1 ;						\
 	rlwinm.	r10,r10,47-31,30,31 ;					\
 	beq-	1f ;							\
-	cmpwi	cr3,r10,2 ;						\
+	cmpwi	cr1,r10,2 ;						\
+	mfspr	r3,SPRN_SRR1 ;						\
+	bltlr	cr1 ;	/* no state loss, return to idle caller */	\
 	BRANCH_TO_C000(r10, system_reset_idle_common) ;			\
 1:									\
 	KVMTEST_PR(n) ;							\
@@ -145,8 +147,11 @@ 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
+	/*
+	 * This must be a direct branch (without linker branch stub) because
+	 * we can not use TOC at this point as r2 may not be restored yet.
+	 */
+	b	idle_return_gpr_loss
 #endif
 
 /*
@@ -429,17 +434,17 @@ 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	cr1,r10,2
+	bltlr	cr1	/* 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/hw_breakpoint.c

@@ -29,11 +29,15 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
 
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/hvcall.h>
 #include <linux/uaccess.h>
 
 /*
@@ -174,7 +178,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 	if (!ppc_breakpoint_available())
 		return -ENODEV;
 	length_max = 8; /* DABR */
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
 		if ((attr->bp_addr >> 9) !=
@@ -376,3 +380,59 @@ void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
+
+bool dawr_force_enable;
+EXPORT_SYMBOL_GPL(dawr_force_enable);
+
+static ssize_t dawr_write_file_bool(struct file *file,
+				    const char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct arch_hw_breakpoint null_brk = {0, 0, 0};
+	size_t rc;
+
+	/* Send error to user if they hypervisor won't allow us to write DAWR */
+	if ((!dawr_force_enable) &&
+	    (firmware_has_feature(FW_FEATURE_LPAR)) &&
+	    (set_dawr(&null_brk) != H_SUCCESS))
+		return -1;
+
+	rc = debugfs_write_file_bool(file, user_buf, count, ppos);
+	if (rc)
+		return rc;
+
+	/* If we are clearing, make sure all CPUs have the DAWR cleared */
+	if (!dawr_force_enable)
+		smp_call_function((smp_call_func_t)set_dawr, &null_brk, 0);
+
+	return rc;
+}
+
+static const struct file_operations dawr_enable_fops = {
+	.read =		debugfs_read_file_bool,
+	.write =	dawr_write_file_bool,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int __init dawr_force_setup(void)
+{
+	dawr_force_enable = false;
+
+	if (cpu_has_feature(CPU_FTR_DAWR)) {
+		/* Don't setup sysfs file for user control on P8 */
+		dawr_force_enable = true;
+		return 0;
+	}
+
+	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
+		/* Turn DAWR off by default, but allow admin to turn it on */
+		dawr_force_enable = false;
+		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
+					   powerpc_debugfs_root,
+					   &dawr_force_enable,
+					   &dawr_enable_fops);
+	}
+	return 0;
+}
+arch_initcall(dawr_force_setup);

arch/powerpc/kernel/process.c

@@ -67,6 +67,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/asm-prototypes.h>
 #include <asm/stacktrace.h>
+#include <asm/hw_breakpoint.h>
 
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -784,7 +785,7 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk)
 	return __set_dabr(dabr, dabrx);
 }
 
-static inline int set_dawr(struct arch_hw_breakpoint *brk)
+int set_dawr(struct arch_hw_breakpoint *brk)
 {
 	unsigned long dawr, dawrx, mrd;
 
@@ -816,7 +817,7 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
-	if (cpu_has_feature(CPU_FTR_DAWR))
+	if (dawr_enabled())
 		// Power8 or later
 		set_dawr(brk);
 	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
@@ -830,8 +831,8 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 /* Check if we have DAWR or DABR hardware */
 bool ppc_breakpoint_available(void)
 {
-	if (cpu_has_feature(CPU_FTR_DAWR))
-		return true; /* POWER8 DAWR */
+	if (dawr_enabled())
+		return true; /* POWER8 DAWR or POWER9 forced DAWR */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		return false; /* POWER9 with DAWR disabled */
 	/* DABR: Everything but POWER8 and POWER9 */

arch/powerpc/kernel/ptrace.c

@@ -43,6 +43,7 @@
 #include <asm/tm.h>
 #include <asm/asm-prototypes.h>
 #include <asm/debug.h>
+#include <asm/hw_breakpoint.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -3088,7 +3089,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		dbginfo.sizeof_condition = 0;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
-		if (cpu_has_feature(CPU_FTR_DAWR))
+		if (dawr_enabled())
 			dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
 #else
 		dbginfo.features = 0;

arch/powerpc/kernel/setup-common.c

@@ -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.c

@@ -74,6 +74,7 @@
 #include <asm/opal.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
+#include <asm/hw_breakpoint.h>
 
 #include "book3s.h"
 
@@ -3374,7 +3375,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	mtspr(SPRN_PURR, vcpu->arch.purr);
 	mtspr(SPRN_SPURR, vcpu->arch.spurr);
 
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		mtspr(SPRN_DAWR, vcpu->arch.dawr);
 		mtspr(SPRN_DAWRX, vcpu->arch.dawrx);
 	}

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -35,6 +35,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
+#include <asm/cpuidle.h>
 
 /* Sign-extend HDEC if not on POWER9 */
 #define EXTEND_HDEC(reg)			\
@@ -45,6 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 /* Values in HSTATE_NAPPING(r13) */
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
+#define NAPPING_UNSPLIT	3
 
 /* Stack frame offsets for kvmppc_hv_entry */
 #define SFS			208
@@ -290,17 +292,19 @@ kvm_novcpu_exit:
 	b	kvmhv_switch_to_host
 
 /*
- * We come in here when wakened from nap mode.
- * Relocation is off and most register values are lost.
- * r13 points to the PACA.
+ * We come in here when wakened from Linux offline idle code.
+ * Relocation is off
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
  */
-	.globl	kvm_start_guest
-kvm_start_guest:
-	/* Set runlatch bit the minute you wake up from nap */
-	mfspr	r0, SPRN_CTRLF
-	ori 	r0, r0, 1
-	mtspr	SPRN_CTRLT, r0
+_GLOBAL(idle_kvm_start_guest)
+	ld	r4,PACAEMERGSP(r13)
+	mfcr	r5
+	mflr	r0
+	std	r1,0(r4)
+	std	r5,8(r4)
+	std	r0,16(r4)
+	subi	r1,r4,STACK_FRAME_OVERHEAD
+	SAVE_NVGPRS(r1)
 
 	/*
 	 * Could avoid this and pass it through in r3. For now,
@@ -308,27 +312,23 @@ kvm_start_guest:
 	 */
 	mtspr	SPRN_SRR1,r3
 
-	ld	r2,PACATOC(r13)
-
 	li	r0,0
 	stb	r0,PACA_FTRACE_ENABLED(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 
-	/* NV GPR values from power7_idle() will no longer be valid */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/* were we napping due to cede? */
+	/* kvm cede / napping does not come through here */
 	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,NAPPING_CEDE
-	beq	kvm_end_cede
-	cmpwi	r0,NAPPING_NOVCPU
-	beq	kvm_novcpu_wakeup
+	twnei	r0,0
+
+	b	1f
+
+kvm_unsplit_wakeup:
+	li	r0, 0
+	stb	r0, HSTATE_NAPPING(r13)
 
-	ld	r1,PACAEMERGSP(r13)
-	subi	r1,r1,STACK_FRAME_OVERHEAD
+1:
 
 	/*
 	 * We weren't napping due to cede, so this must be a secondary
@@ -437,19 +437,25 @@ kvm_no_guest:
 	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r3, 0
 	bne	54f
-/*
- * We jump to pnv_wakeup_loss, which will return to the caller
- * of power7_nap in the powernv cpu offline loop.  The value we
- * put in r3 becomes the return value for power7_nap. pnv_wakeup_loss
- * requires SRR1 in r12.
+
+	/*
+	 * Jump to idle_return_gpr_loss, which returns to the
+	 * idle_kvm_start_guest caller.
 	 */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
-	li	r3, 0
-	mfspr	r12,SPRN_SRR1
-	b	pnv_wakeup_loss
+	/* set up r3 for return */
+	mfspr	r3,SPRN_SRR1
+	REST_NVGPRS(r1)
+	addi	r1, r1, STACK_FRAME_OVERHEAD
+	ld	r0, 16(r1)
+	ld	r5, 8(r1)
+	ld	r1, 0(r1)
+	mtlr	r0
+	mtcr	r5
+	blr
 
 53:	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
@@ -534,6 +540,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	lbz	r0, KVM_SPLIT_DO_NAP(r3)
 	cmpwi	r0, 0
 	beq	57f
+	li	r3, NAPPING_UNSPLIT
+	stb	r3, HSTATE_NAPPING(r13)
 	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
 	mfspr	r5, SPRN_LPCR
 	rlwimi	r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
@@ -822,18 +830,21 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_IAMR, r5
 	mtspr	SPRN_PSPB, r6
 	mtspr	SPRN_FSCR, r7
-	ld	r5, VCPU_DAWR(r4)
-	ld	r6, VCPU_DAWRX(r4)
-	ld	r7, VCPU_CIABR(r4)
-	ld	r8, VCPU_TAR(r4)
 	/*
 	 * Handle broken DAWR case by not writing it. This means we
 	 * can still store the DAWR register for migration.
 	 */
-BEGIN_FTR_SECTION
+	LOAD_REG_ADDR(r5, dawr_force_enable)
+	lbz	r5, 0(r5)
+	cmpdi	r5, 0
+	beq	1f
+	ld	r5, VCPU_DAWR(r4)
+	ld	r6, VCPU_DAWRX(r4)
 	mtspr	SPRN_DAWR, r5
 	mtspr	SPRN_DAWRX, r6
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
+1:
+	ld	r7, VCPU_CIABR(r4)
+	ld	r8, VCPU_TAR(r4)
 	mtspr	SPRN_CIABR, r7
 	mtspr	SPRN_TAR, r8
 	ld	r5, VCPU_IC(r4)
@@ -2513,11 +2524,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	blr
 
 2:
-BEGIN_FTR_SECTION
-	/* POWER9 with disabled DAWR */
+	LOAD_REG_ADDR(r11, dawr_force_enable)
+	lbz	r11, 0(r11)
+	cmpdi	r11, 0
 	li	r3, H_HARDWARE
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
+	beqlr
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
 	rlwimi	r5, r4, 2, DAWRX_WT
@@ -2654,6 +2665,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	lis	r3, LPCR_PECEDP@h	/* Do wake on privileged doorbell */
 
+	/* Go back to host stack */
+	ld	r1, HSTATE_HOST_R1(r13)
+
 	/*
 	 * Take a nap until a decrementer or external or doobell interrupt
 	 * occurs, with PECE1 and PECE0 set in LPCR.
@@ -2682,26 +2696,42 @@ BEGIN_FTR_SECTION
 	 *		requested level = 0 (just stop dispatching)
 	 */
 	lis	r3, (PSSCR_EC | PSSCR_ESL)@h
-	mtspr	SPRN_PSSCR, r3
 	/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
 	li	r4, LPCR_PECE_HVEE@higher
 	sldi	r4, r4, 32
 	or	r5, r5, r4
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+	li	r3, PNV_THREAD_NAP
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r5
 	isync
-	li	r0, 0
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
+
 BEGIN_FTR_SECTION
-	nap
+	bl	isa300_idle_stop_mayloss
 FTR_SECTION_ELSE
-	PPC_STOP
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
-	b	.
+	bl	isa206_idle_insn_mayloss
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+
+	mfspr	r0, SPRN_CTRLF
+	ori	r0, r0, 1
+	mtspr	SPRN_CTRLT, r0
+
+	mtspr	SPRN_SRR1, r3
+
+	li	r0, 0
+	stb	r0, PACA_FTRACE_ENABLED(r13)
+
+	li	r0, KVM_HWTHREAD_IN_KVM
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+
+	lbz	r0, HSTATE_NAPPING(r13)
+	cmpwi	r0, NAPPING_CEDE
+	beq	kvm_end_cede
+	cmpwi	r0, NAPPING_NOVCPU
+	beq	kvm_novcpu_wakeup
+	cmpwi	r0, NAPPING_UNSPLIT
+	beq	kvm_unsplit_wakeup
+	twi	31,0,0 /* Nap state must not be zero */
 
 33:	mr	r4, r3
 	li	r3, 0
@@ -2709,12 +2739,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	b	34f
 
 kvm_end_cede:
+	/* Woken by external or decrementer interrupt */
+
 	/* get vcpu pointer */
 	ld	r4, HSTATE_KVM_VCPU(r13)
 
-	/* Woken by external or decrementer interrupt */
-	ld	r1, HSTATE_HOST_R1(r13)
-
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	addi	r3, r4, VCPU_TB_RMINTR
 	bl	kvmhv_accumulate_time

arch/powerpc/platforms/powernv/opal-call.c

@@ -262,6 +262,9 @@ OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
 OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
 OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
 OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
+OPAL_CALL(opal_xive_get_queue_state,		OPAL_XIVE_GET_QUEUE_STATE);
+OPAL_CALL(opal_xive_set_queue_state,		OPAL_XIVE_SET_QUEUE_STATE);
+OPAL_CALL(opal_xive_get_vp_state,		OPAL_XIVE_GET_VP_STATE);
 OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
 OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
 OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);

arch/powerpc/platforms/powernv/subcore.c

@@ -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/sysdev/xive/native.c

@@ -437,6 +437,12 @@ void xive_native_sync_source(u32 hw_irq)
 }
 EXPORT_SYMBOL_GPL(xive_native_sync_source);
 
+void xive_native_sync_queue(u32 hw_irq)
+{
+	opal_xive_sync(XIVE_SYNC_QUEUE, hw_irq);
+}
+EXPORT_SYMBOL_GPL(xive_native_sync_queue);
+
 static const struct xive_ops xive_native_ops = {
 	.populate_irq_data	= xive_native_populate_irq_data,
 	.configure_irq		= xive_native_configure_irq,
@@ -711,3 +717,96 @@ bool xive_native_has_single_escalation(void)
 	return xive_has_single_esc;
 }
 EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
+
+int xive_native_get_queue_info(u32 vp_id, u32 prio,
+			       u64 *out_qpage,
+			       u64 *out_qsize,
+			       u64 *out_qeoi_page,
+			       u32 *out_escalate_irq,
+			       u64 *out_qflags)
+{
+	__be64 qpage;
+	__be64 qsize;
+	__be64 qeoi_page;
+	__be32 escalate_irq;
+	__be64 qflags;
+	s64 rc;
+
+	rc = opal_xive_get_queue_info(vp_id, prio, &qpage, &qsize,
+				      &qeoi_page, &escalate_irq, &qflags);
+	if (rc) {
+		pr_err("OPAL failed to get queue info for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	if (out_qpage)
+		*out_qpage = be64_to_cpu(qpage);
+	if (out_qsize)
+		*out_qsize = be32_to_cpu(qsize);
+	if (out_qeoi_page)
+		*out_qeoi_page = be64_to_cpu(qeoi_page);
+	if (out_escalate_irq)
+		*out_escalate_irq = be32_to_cpu(escalate_irq);
+	if (out_qflags)
+		*out_qflags = be64_to_cpu(qflags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_info);
+
+int xive_native_get_queue_state(u32 vp_id, u32 prio, u32 *qtoggle, u32 *qindex)
+{
+	__be32 opal_qtoggle;
+	__be32 opal_qindex;
+	s64 rc;
+
+	rc = opal_xive_get_queue_state(vp_id, prio, &opal_qtoggle,
+				       &opal_qindex);
+	if (rc) {
+		pr_err("OPAL failed to get queue state for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	if (qtoggle)
+		*qtoggle = be32_to_cpu(opal_qtoggle);
+	if (qindex)
+		*qindex = be32_to_cpu(opal_qindex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_state);
+
+int xive_native_set_queue_state(u32 vp_id, u32 prio, u32 qtoggle, u32 qindex)
+{
+	s64 rc;
+
+	rc = opal_xive_set_queue_state(vp_id, prio, qtoggle, qindex);
+	if (rc) {
+		pr_err("OPAL failed to set queue state for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_set_queue_state);
+
+int xive_native_get_vp_state(u32 vp_id, u64 *out_state)
+{
+	__be64 state;
+	s64 rc;
+
+	rc = opal_xive_get_vp_state(vp_id, &state);
+	if (rc) {
+		pr_err("OPAL failed to get vp state for VCPU %d : %lld\n",
+		       vp_id, rc);
+		return -EIO;
+	}
+
+	if (out_state)
+		*out_state = be64_to_cpu(state);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_state);

arch/powerpc/xmon/xmon.c

@@ -2431,7 +2431,6 @@ 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
@@ -2439,20 +2438,17 @@ static void dump_one_paca(int cpu)
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	DUMP(p, core_idle_state_ptr, "%-*px");
+	DUMP(p, idle_state, "%#-*lx");
+	if (!early_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, 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");
 #endif
+	}
+#endif
 
 	DUMP(p, accounting.utime, "%#-*lx");
 	DUMP(p, accounting.stime, "%#-*lx");