KVM: PPC: Handle some PAPR hcalls in the kernel

This adds the infrastructure for handling PAPR hcalls in the kernel,
either early in the guest exit path while we are still in real mode,
or later once the MMU has been turned back on and we are in the full
kernel context.  The advantage of handling hcalls in real mode if
possible is that we avoid two partition switches -- and this will
become more important when we support SMT4 guests, since a partition
switch means we have to pull all of the threads in the core out of
the guest.  The disadvantage is that we can only access the kernel
linear mapping, not anything vmalloced or ioremapped, since the MMU
is off.

This also adds code to handle the following hcalls in real mode:

H_ENTER       Add an HPTE to the hashed page table
H_REMOVE      Remove an HPTE from the hashed page table
H_READ        Read HPTEs from the hashed page table
H_PROTECT     Change the protection bits in an HPTE
H_BULK_REMOVE Remove up to 4 HPTEs from the hashed page table
H_SET_DABR    Set the data address breakpoint register

Plus code to handle the following hcalls in the kernel:

H_CEDE        Idle the vcpu until an interrupt or H_PROD hcall arrives
H_PROD        Wake up a ceded vcpu
H_REGISTER_VPA Register a virtual processor area (VPA)

The code that runs in real mode has to be in the base kernel, not in
the module, if KVM is compiled as a module.  The real-mode code can
only access the kernel linear mapping, not vmalloc or ioremap space.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/hvcall.h

@@ -29,6 +29,10 @@
 #define H_LONG_BUSY_ORDER_100_SEC	9905  /* Long busy, hint that 100sec \
 						 is a good time to retry */
 #define H_LONG_BUSY_END_RANGE		9905  /* End of long busy range */
+
+/* Internal value used in book3s_hv kvm support; not returned to guests */
+#define H_TOO_HARD	9999
+
 #define H_HARDWARE	-1	/* Hardware error */
 #define H_FUNCTION	-2	/* Function not supported */
 #define H_PRIVILEGE	-3	/* Caller not privileged */
@@ -100,6 +104,7 @@
 #define H_PAGE_SET_ACTIVE	H_PAGE_STATE_CHANGE
 #define H_AVPN			(1UL<<(63-32))	/* An avpn is provided as a sanity test */
 #define H_ANDCOND		(1UL<<(63-33))
+#define H_LOCAL			(1UL<<(63-35))
 #define H_ICACHE_INVALIDATE	(1UL<<(63-40))	/* icbi, etc.  (ignored for IO pages) */
 #define H_ICACHE_SYNCHRONIZE	(1UL<<(63-41))	/* dcbst, icbi, etc (ignored for IO pages */
 #define H_COALESCE_CAND	(1UL<<(63-42))	/* page is a good candidate for coalescing */

arch/powerpc/include/asm/kvm_host.h

@@ -59,6 +59,10 @@ struct kvm;
 struct kvm_run;
 struct kvm_vcpu;
 
+struct lppaca;
+struct slb_shadow;
+struct dtl;
+
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
 };
@@ -344,7 +348,14 @@ struct kvm_vcpu_arch {
 	u64 dec_expires;
 	unsigned long pending_exceptions;
 	u16 last_cpu;
+	u8 ceded;
+	u8 prodded;
 	u32 last_inst;
+
+	struct lppaca *vpa;
+	struct slb_shadow *slb_shadow;
+	struct dtl *dtl;
+	struct dtl *dtl_end;
 	int trap;
 	struct kvm_vcpu_arch_shared *shared;
 	unsigned long magic_page_pa; /* phys addr to map the magic page to */

arch/powerpc/include/asm/kvm_ppc.h

@@ -118,6 +118,7 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_map_vrma(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
+extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,

arch/powerpc/kernel/asm-offsets.c

@@ -189,6 +189,7 @@ int main(void)
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
 	DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
 	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
+	DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count));
 	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
@@ -459,6 +460,7 @@ int main(void)
 	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
 	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
 	DEFINE(VCPU_LPCR, offsetof(struct kvm_vcpu, arch.lpcr));
+	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
 	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
 	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
 	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));

arch/powerpc/kvm/Makefile

@@ -54,14 +54,17 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
 	book3s_64_mmu_hv.o
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
+	book3s_hv_rm_mmu.o
 
-kvm-book3s_64-objs := \
+kvm-book3s_64-module-objs := \
 	../../../virt/kvm/kvm_main.o \
 	powerpc.o \
 	emulate.o \
 	book3s.o \
 	$(kvm-book3s_64-objs-y)
-kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs)
+
+kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs)
 
 kvm-book3s_32-objs := \
 	$(common-objs-y) \
@@ -83,3 +86,4 @@ obj-$(CONFIG_KVM_E500) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
 
+obj-y += $(kvm-book3s_64-builtin-objs-y)

arch/powerpc/kvm/book3s_hv.c

@@ -124,6 +124,158 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 	       vcpu->arch.last_inst);
 }
 
+struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
+{
+	int r;
+	struct kvm_vcpu *v, *ret = NULL;
+
+	mutex_lock(&kvm->lock);
+	kvm_for_each_vcpu(r, v, kvm) {
+		if (v->vcpu_id == id) {
+			ret = v;
+			break;
+		}
+	}
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
+static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
+{
+	vpa->shared_proc = 1;
+	vpa->yield_count = 1;
+}
+
+static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
+				       unsigned long flags,
+				       unsigned long vcpuid, unsigned long vpa)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long pg_index, ra, len;
+	unsigned long pg_offset;
+	void *va;
+	struct kvm_vcpu *tvcpu;
+
+	tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
+	if (!tvcpu)
+		return H_PARAMETER;
+
+	flags >>= 63 - 18;
+	flags &= 7;
+	if (flags == 0 || flags == 4)
+		return H_PARAMETER;
+	if (flags < 4) {
+		if (vpa & 0x7f)
+			return H_PARAMETER;
+		/* registering new area; convert logical addr to real */
+		pg_index = vpa >> kvm->arch.ram_porder;
+		pg_offset = vpa & (kvm->arch.ram_psize - 1);
+		if (pg_index >= kvm->arch.ram_npages)
+			return H_PARAMETER;
+		if (kvm->arch.ram_pginfo[pg_index].pfn == 0)
+			return H_PARAMETER;
+		ra = kvm->arch.ram_pginfo[pg_index].pfn << PAGE_SHIFT;
+		ra |= pg_offset;
+		va = __va(ra);
+		if (flags <= 1)
+			len = *(unsigned short *)(va + 4);
+		else
+			len = *(unsigned int *)(va + 4);
+		if (pg_offset + len > kvm->arch.ram_psize)
+			return H_PARAMETER;
+		switch (flags) {
+		case 1:		/* register VPA */
+			if (len < 640)
+				return H_PARAMETER;
+			tvcpu->arch.vpa = va;
+			init_vpa(vcpu, va);
+			break;
+		case 2:		/* register DTL */
+			if (len < 48)
+				return H_PARAMETER;
+			if (!tvcpu->arch.vpa)
+				return H_RESOURCE;
+			len -= len % 48;
+			tvcpu->arch.dtl = va;
+			tvcpu->arch.dtl_end = va + len;
+			break;
+		case 3:		/* register SLB shadow buffer */
+			if (len < 8)
+				return H_PARAMETER;
+			if (!tvcpu->arch.vpa)
+				return H_RESOURCE;
+			tvcpu->arch.slb_shadow = va;
+			len = (len - 16) / 16;
+			tvcpu->arch.slb_shadow = va;
+			break;
+		}
+	} else {
+		switch (flags) {
+		case 5:		/* unregister VPA */
+			if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
+				return H_RESOURCE;
+			tvcpu->arch.vpa = NULL;
+			break;
+		case 6:		/* unregister DTL */
+			tvcpu->arch.dtl = NULL;
+			break;
+		case 7:		/* unregister SLB shadow buffer */
+			tvcpu->arch.slb_shadow = NULL;
+			break;
+		}
+	}
+	return H_SUCCESS;
+}
+
+int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
+{
+	unsigned long req = kvmppc_get_gpr(vcpu, 3);
+	unsigned long target, ret = H_SUCCESS;
+	struct kvm_vcpu *tvcpu;
+
+	switch (req) {
+	case H_CEDE:
+		vcpu->arch.shregs.msr |= MSR_EE;
+		vcpu->arch.ceded = 1;
+		smp_mb();
+		if (!vcpu->arch.prodded)
+			kvmppc_vcpu_block(vcpu);
+		else
+			vcpu->arch.prodded = 0;
+		smp_mb();
+		vcpu->arch.ceded = 0;
+		break;
+	case H_PROD:
+		target = kvmppc_get_gpr(vcpu, 4);
+		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+		if (!tvcpu) {
+			ret = H_PARAMETER;
+			break;
+		}
+		tvcpu->arch.prodded = 1;
+		smp_mb();
+		if (vcpu->arch.ceded) {
+			if (waitqueue_active(&vcpu->wq)) {
+				wake_up_interruptible(&vcpu->wq);
+				vcpu->stat.halt_wakeup++;
+			}
+		}
+		break;
+	case H_CONFER:
+		break;
+	case H_REGISTER_VPA:
+		ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
+					kvmppc_get_gpr(vcpu, 5),
+					kvmppc_get_gpr(vcpu, 6));
+		break;
+	default:
+		return RESUME_HOST;
+	}
+	kvmppc_set_gpr(vcpu, 3, ret);
+	vcpu->arch.hcall_needed = 0;
+	return RESUME_GUEST;
+}
+
 static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			      struct task_struct *tsk)
 {
@@ -318,7 +470,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 
 extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 
-int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+static int kvmppc_run_vcpu(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	u64 now;
 
@@ -370,6 +522,22 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	return -EBUSY;
 }
 
+int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	do {
+		r = kvmppc_run_vcpu(run, vcpu);
+
+		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
+		    !(vcpu->arch.shregs.msr & MSR_PR)) {
+			r = kvmppc_pseries_do_hcall(vcpu);
+			kvmppc_core_deliver_interrupts(vcpu);
+		}
+	} while (r == RESUME_GUEST);
+	return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem)
 {

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -166,6 +166,14 @@ kvmppc_hv_entry:
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
 
+	/* Increment yield count if they have a VPA */
+	ld	r3, VCPU_VPA(r4)
+	cmpdi	r3, 0
+	beq	25f
+	lwz	r5, LPPACA_YIELDCOUNT(r3)
+	addi	r5, r5, 1
+	stw	r5, LPPACA_YIELDCOUNT(r3)
+25:
 	/* Load up DAR and DSISR */
 	ld	r5, VCPU_DAR(r4)
 	lwz	r6, VCPU_DSISR(r4)
@@ -401,6 +409,10 @@ kvmppc_interrupt:
 	cmpwi	r3,0
 	bge	ignore_hdec
 2:
+	/* See if this is something we can handle in real mode */
+	cmpwi	r12,BOOK3S_INTERRUPT_SYSCALL
+	beq	hcall_try_real_mode
+hcall_real_cont:
 
 	/* Check for mediated interrupts (could be done earlier really ...) */
 	cmpwi	r12,BOOK3S_INTERRUPT_EXTERNAL
@@ -579,13 +591,28 @@ hdec_soon:
 	std	r5, VCPU_SPRG2(r9)
 	std	r6, VCPU_SPRG3(r9)
 
-	/* Save PMU registers */
+	/* Increment yield count if they have a VPA */
+	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
+	cmpdi	r8, 0
+	beq	25f
+	lwz	r3, LPPACA_YIELDCOUNT(r8)
+	addi	r3, r3, 1
+	stw	r3, LPPACA_YIELDCOUNT(r8)
+25:
+	/* Save PMU registers if requested */
+	/* r8 and cr0.eq are live here */
 	li	r3, 1
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
 	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
 	isync
-	mfspr	r5, SPRN_MMCR1
+	beq	21f			/* if no VPA, save PMU stuff anyway */
+	lbz	r7, LPPACA_PMCINUSE(r8)
+	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
+	bne	21f
+	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
+	b	22f
+21:	mfspr	r5, SPRN_MMCR1
 	mfspr	r6, SPRN_MMCRA
 	std	r4, VCPU_MMCR(r9)
 	std	r5, VCPU_MMCR + 8(r9)
@@ -676,6 +703,125 @@ hdec_soon:
 	mfspr	r7,SPRN_HDSISR
 	b	7b
 
+/*
+ * Try to handle an hcall in real mode.
+ * Returns to the guest if we handle it, or continues on up to
+ * the kernel if we can't (i.e. if we don't have a handler for
+ * it, or if the handler returns H_TOO_HARD).
+ */
+	.globl	hcall_try_real_mode
+hcall_try_real_mode:
+	ld	r3,VCPU_GPR(r3)(r9)
+	andi.	r0,r11,MSR_PR
+	bne	hcall_real_cont
+	clrrdi	r3,r3,2
+	cmpldi	r3,hcall_real_table_end - hcall_real_table
+	bge	hcall_real_cont
+	LOAD_REG_ADDR(r4, hcall_real_table)
+	lwzx	r3,r3,r4
+	cmpwi	r3,0
+	beq	hcall_real_cont
+	add	r3,r3,r4
+	mtctr	r3
+	mr	r3,r9		/* get vcpu pointer */
+	ld	r4,VCPU_GPR(r4)(r9)
+	bctrl
+	cmpdi	r3,H_TOO_HARD
+	beq	hcall_real_fallback
+	ld	r4,HSTATE_KVM_VCPU(r13)
+	std	r3,VCPU_GPR(r3)(r4)
+	ld	r10,VCPU_PC(r4)
+	ld	r11,VCPU_MSR(r4)
+	b	fast_guest_return
+
+	/* We've attempted a real mode hcall, but it's punted it back
+	 * to userspace.  We need to restore some clobbered volatiles
+	 * before resuming the pass-it-to-qemu path */
+hcall_real_fallback:
+	li	r12,BOOK3S_INTERRUPT_SYSCALL
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	ld	r11, VCPU_MSR(r9)
+
+	b	hcall_real_cont
+
+	.globl	hcall_real_table
+hcall_real_table:
+	.long	0		/* 0 - unused */
+	.long	.kvmppc_h_remove - hcall_real_table
+	.long	.kvmppc_h_enter - hcall_real_table
+	.long	.kvmppc_h_read - hcall_real_table
+	.long	0		/* 0x10 - H_CLEAR_MOD */
+	.long	0		/* 0x14 - H_CLEAR_REF */
+	.long	.kvmppc_h_protect - hcall_real_table
+	.long	0		/* 0x1c - H_GET_TCE */
+	.long	0		/* 0x20 - H_SET_TCE */
+	.long	0		/* 0x24 - H_SET_SPRG0 */
+	.long	.kvmppc_h_set_dabr - hcall_real_table
+	.long	0		/* 0x2c */
+	.long	0		/* 0x30 */
+	.long	0		/* 0x34 */
+	.long	0		/* 0x38 */
+	.long	0		/* 0x3c */
+	.long	0		/* 0x40 */
+	.long	0		/* 0x44 */
+	.long	0		/* 0x48 */
+	.long	0		/* 0x4c */
+	.long	0		/* 0x50 */
+	.long	0		/* 0x54 */
+	.long	0		/* 0x58 */
+	.long	0		/* 0x5c */
+	.long	0		/* 0x60 */
+	.long	0		/* 0x64 */
+	.long	0		/* 0x68 */
+	.long	0		/* 0x6c */
+	.long	0		/* 0x70 */
+	.long	0		/* 0x74 */
+	.long	0		/* 0x78 */
+	.long	0		/* 0x7c */
+	.long	0		/* 0x80 */
+	.long	0		/* 0x84 */
+	.long	0		/* 0x88 */
+	.long	0		/* 0x8c */
+	.long	0		/* 0x90 */
+	.long	0		/* 0x94 */
+	.long	0		/* 0x98 */
+	.long	0		/* 0x9c */
+	.long	0		/* 0xa0 */
+	.long	0		/* 0xa4 */
+	.long	0		/* 0xa8 */
+	.long	0		/* 0xac */
+	.long	0		/* 0xb0 */
+	.long	0		/* 0xb4 */
+	.long	0		/* 0xb8 */
+	.long	0		/* 0xbc */
+	.long	0		/* 0xc0 */
+	.long	0		/* 0xc4 */
+	.long	0		/* 0xc8 */
+	.long	0		/* 0xcc */
+	.long	0		/* 0xd0 */
+	.long	0		/* 0xd4 */
+	.long	0		/* 0xd8 */
+	.long	0		/* 0xdc */
+	.long	0		/* 0xe0 */
+	.long	0		/* 0xe4 */
+	.long	0		/* 0xe8 */
+	.long	0		/* 0xec */
+	.long	0		/* 0xf0 */
+	.long	0		/* 0xf4 */
+	.long	0		/* 0xf8 */
+	.long	0		/* 0xfc */
+	.long	0		/* 0x100 */
+	.long	0		/* 0x104 */
+	.long	0		/* 0x108 */
+	.long	0		/* 0x10c */
+	.long	0		/* 0x110 */
+	.long	0		/* 0x114 */
+	.long	0		/* 0x118 */
+	.long	0		/* 0x11c */
+	.long	0		/* 0x120 */
+	.long	.kvmppc_h_bulk_remove - hcall_real_table
+hcall_real_table_end:
+
 ignore_hdec:
 	mr	r4,r9
 	b	fast_guest_return
@@ -688,10 +834,16 @@ bounce_ext_interrupt:
 	LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME);
 	b	fast_guest_return
 
+_GLOBAL(kvmppc_h_set_dabr)
+	std	r4,VCPU_DABR(r3)
+	mtspr	SPRN_DABR,r4
+	li	r3,0
+	blr
+
 /*
  * Save away FP, VMX and VSX registers.
  * r3 = vcpu pointer
-*/
+ */
 _GLOBAL(kvmppc_save_fp)
 	mfmsr	r9
 	ori	r8,r9,MSR_FP

arch/powerpc/kvm/powerpc.c

@@ -42,7 +42,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 	return !(v->arch.shared->msr & MSR_WE) ||
 	       !!(v->arch.pending_exceptions);
 #else
-	return 1;
+	return !(v->arch.ceded) || !!(v->arch.pending_exceptions);
 #endif
 }