KVM: PPC: Book3S HV: Translate kvmhv_commence_exit to C

This replaces the assembler code for kvmhv_commence_exit() with C code
in book3s_hv_builtin.c.  It also moves the IPI sending code that was
in book3s_hv_rm_xics.c into a new kvmhv_rm_send_ipi() function so it
can be used by kvmhv_commence_exit() as well as icp_rm_set_vcpu_irq().
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NAlexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -438,6 +438,8 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 
 extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
 
+extern void kvmhv_rm_send_ipi(int cpu);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -22,6 +22,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 #include <asm/archrandom.h>
+#include <asm/xics.h>
 
 #define KVM_CMA_CHUNK_ORDER	18
 
@@ -184,3 +185,65 @@ long kvmppc_h_random(struct kvm_vcpu *vcpu)
 
 	return H_HARDWARE;
 }
+
+static inline void rm_writeb(unsigned long paddr, u8 val)
+{
+	__asm__ __volatile__("stbcix %0,0,%1"
+		: : "r" (val), "r" (paddr) : "memory");
+}
+
+/*
+ * Send an interrupt to another CPU.
+ * This can only be called in real mode.
+ * The caller needs to include any barrier needed to order writes
+ * to memory vs. the IPI/message.
+ */
+void kvmhv_rm_send_ipi(int cpu)
+{
+	unsigned long xics_phys;
+
+	/* Poke the target */
+	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+}
+
+/*
+ * The following functions are called from the assembly code
+ * in book3s_hv_rmhandlers.S.
+ */
+static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
+{
+	int cpu = vc->pcpu;
+
+	/* Order setting of exit map vs. msgsnd/IPI */
+	smp_mb();
+	for (; active; active >>= 1, ++cpu)
+		if (active & 1)
+			kvmhv_rm_send_ipi(cpu);
+}
+
+void kvmhv_commence_exit(int trap)
+{
+	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
+	int ptid = local_paca->kvm_hstate.ptid;
+	int me, ee;
+
+	/* Set our bit in the threads-exiting-guest map in the 0xff00
+	   bits of vcore->entry_exit_map */
+	me = 0x100 << ptid;
+	do {
+		ee = vc->entry_exit_map;
+	} while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);
+
+	/* Are we the first here? */
+	if ((ee >> 8) != 0)
+		return;
+
+	/*
+	 * Trigger the other threads in this vcore to exit the guest.
+	 * If this is a hypervisor decrementer interrupt then they
+	 * will be already on their way out of the guest.
+	 */
+	if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
+		kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
+}

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -26,12 +26,6 @@
 static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 			    u32 new_irq);
 
-static inline void rm_writeb(unsigned long paddr, u8 val)
-{
-	__asm__ __volatile__("sync; stbcix %0,0,%1"
-		: : "r" (val), "r" (paddr) : "memory");
-}
-
 /* -- ICS routines -- */
 static void ics_rm_check_resend(struct kvmppc_xics *xics,
 				struct kvmppc_ics *ics, struct kvmppc_icp *icp)
@@ -60,7 +54,6 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 				struct kvm_vcpu *this_vcpu)
 {
 	struct kvmppc_icp *this_icp = this_vcpu->arch.icp;
-	unsigned long xics_phys;
 	int cpu;
 
 	/* Mark the target VCPU as having an interrupt pending */
@@ -83,9 +76,8 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 	/* In SMT cpu will always point to thread 0, we adjust it */
 	cpu += vcpu->arch.ptid;
 
-	/* Not too hard, then poke the target */
-	xics_phys = paca[cpu].kvm_hstate.xics_phys;
-	rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+	smp_mb();
+	kvmhv_rm_send_ipi(cpu);
 }
 
 static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -264,7 +264,11 @@ kvm_novcpu_exit:
 	addi	r3, r4, VCPU_TB_RMEXIT
 	bl	kvmhv_accumulate_time
 #endif
-13:	bl	kvmhv_commence_exit
+13:	mr	r3, r12
+	stw	r12, 112-4(r1)
+	bl	kvmhv_commence_exit
+	nop
+	lwz	r12, 112-4(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -1161,6 +1165,9 @@ mc_cont:
 
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
+	nop
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	lwz	r12, VCPU_TRAP(r9)
 
 	/* Save guest CTRL register, set runlatch to 1 */
 	mfspr	r6,SPRN_CTRLF
@@ -1614,63 +1621,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtlr	r0
 	blr
 
-kvmhv_commence_exit:		/* r12 = trap, r13 = paca, doesn't trash r9 */
-	mflr	r0
-	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -PPC_MIN_STKFRM(r1)
-
-	/* Set our bit in the threads-exiting-guest map in the 0xff00
-	   bits of vcore->entry_exit_map */
-	ld	r5, HSTATE_KVM_VCORE(r13)
-	lbz	r4, HSTATE_PTID(r13)
-	li	r7, 0x100
-	sld	r7, r7, r4
-	addi	r6, r5, VCORE_ENTRY_EXIT
-41:	lwarx	r3, 0, r6
-	or	r0, r3, r7
-	stwcx.	r0, 0, r6
-	bne	41b
-	isync		/* order stwcx. vs. reading napping_threads */
-
-	/*
-	 * At this point we have an interrupt that we have to pass
-	 * up to the kernel or qemu; we can't handle it in real mode.
-	 * Thus we have to do a partition switch, so we have to
-	 * collect the other threads, if we are the first thread
-	 * to take an interrupt.  To do this, we send a message or
-	 * IPI to all the threads that have their bit set in the entry
-	 * map in vcore->entry_exit_map (other than ourselves).
-	 * However, we don't need to bother if this is an HDEC
-	 * interrupt, since the other threads will already be on their
-	 * way here in that case.
-	 */
-	cmpwi	r3,0x100	/* Are we the first here? */
-	bge	43f
-	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
-	beq	43f
-
-	srwi	r0,r7,8
-	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
-	beq	43f
-	/* Order entry/exit update vs. IPIs */
-	sync
-	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
-	subf	r6,r4,r13
-42:	andi.	r0,r3,1
-	beq	44f
-	ld	r8,HSTATE_XICS_PHYS(r6)	/* get thread's XICS reg addr */
-	li	r0,IPI_PRIORITY
-	li	r7,XICS_MFRR
-	stbcix	r0,r7,r8		/* trigger the IPI */
-44:	srdi.	r3,r3,1
-	addi	r6,r6,PACA_SIZE
-	bne	42b
-
-43:	ld	r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1)
-	addi	r1, r1, PPC_MIN_STKFRM
-	mtlr	r0
-	blr
-
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
  * If it is an HPTE not found fault that is due to the guest accessing