KVM: PPC: Book3S HV: Restructure kvmppc_hv_entry to be a subroutine

We have two paths into and out of the low-level guest entry and exit
code: from a vcpu task via kvmppc_hv_entry_trampoline, and from the
system reset vector for an offline secondary thread on POWER7 via
kvm_start_guest.  Currently both just branch to kvmppc_hv_entry to
enter the guest, and on guest exit, we test the vcpu physical thread
ID to detect which way we came in and thus whether we should return
to the vcpu task or go back to nap mode.

In order to make the code flow clearer, and to keep the code relating
to each flow together, this turns kvmppc_hv_entry into a subroutine
that follows the normal conventions for call and return.  This means
that kvmppc_hv_entry_trampoline() and kvmppc_hv_entry() now establish
normal stack frames, and we use the normal stack slots for saving
return addresses rather than local_paca->kvm_hstate.vmhandler.  Apart
from that this is mostly moving code around unchanged.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -66,8 +66,11 @@ kvmppc_skip_Hinterrupt:
  * LR = return address to continue at after eventually re-enabling MMU
  */
 _GLOBAL(kvmppc_hv_entry_trampoline)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -112(r1)
 	mfmsr	r10
-	LOAD_REG_ADDR(r5, kvmppc_hv_entry)
+	LOAD_REG_ADDR(r5, kvmppc_call_hv_entry)
 	li	r0,MSR_RI
 	andc	r0,r10,r0
 	li	r6,MSR_IR | MSR_DR
@@ -77,11 +80,103 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 	mtsrr1	r6
 	RFI
 
-/******************************************************************************
- *                                                                            *
- *                               Entry code                                   *
- *                                                                            *
- *****************************************************************************/
+kvmppc_call_hv_entry:
+	bl	kvmppc_hv_entry
+
+	/* Back from guest - restore host state and return to caller */
+
+	/* Restore host DABR and DABRX */
+	ld	r5,HSTATE_DABR(r13)
+	li	r6,7
+	mtspr	SPRN_DABR,r5
+	mtspr	SPRN_DABRX,r6
+
+	/* Restore SPRG3 */
+	ld	r3,PACA_SPRG3(r13)
+	mtspr	SPRN_SPRG3,r3
+
+	/*
+	 * Reload DEC.  HDEC interrupts were disabled when
+	 * we reloaded the host's LPCR value.
+	 */
+	ld	r3, HSTATE_DECEXP(r13)
+	mftb	r4
+	subf	r4, r4, r3
+	mtspr	SPRN_DEC, r4
+
+	/* Reload the host's PMU registers */
+	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
+	lbz	r4, LPPACA_PMCINUSE(r3)
+	cmpwi	r4, 0
+	beq	23f			/* skip if not */
+	lwz	r3, HSTATE_PMC(r13)
+	lwz	r4, HSTATE_PMC + 4(r13)
+	lwz	r5, HSTATE_PMC + 8(r13)
+	lwz	r6, HSTATE_PMC + 12(r13)
+	lwz	r8, HSTATE_PMC + 16(r13)
+	lwz	r9, HSTATE_PMC + 20(r13)
+BEGIN_FTR_SECTION
+	lwz	r10, HSTATE_PMC + 24(r13)
+	lwz	r11, HSTATE_PMC + 28(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r4
+	mtspr	SPRN_PMC3, r5
+	mtspr	SPRN_PMC4, r6
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+BEGIN_FTR_SECTION
+	mtspr	SPRN_PMC7, r10
+	mtspr	SPRN_PMC8, r11
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	ld	r3, HSTATE_MMCR(r13)
+	ld	r4, HSTATE_MMCR + 8(r13)
+	ld	r5, HSTATE_MMCR + 16(r13)
+	mtspr	SPRN_MMCR1, r4
+	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_MMCR0, r3
+	isync
+23:
+
+	/*
+	 * For external and machine check interrupts, we need
+	 * to call the Linux handler to process the interrupt.
+	 * We do that by jumping to absolute address 0x500 for
+	 * external interrupts, or the machine_check_fwnmi label
+	 * for machine checks (since firmware might have patched
+	 * the vector area at 0x200).  The [h]rfid at the end of the
+	 * handler will return to the book3s_hv_interrupts.S code.
+	 * For other interrupts we do the rfid to get back
+	 * to the book3s_hv_interrupts.S code here.
+	 */
+	ld	r8, 112+PPC_LR_STKOFF(r1)
+	addi	r1, r1, 112
+	ld	r7, HSTATE_HOST_MSR(r13)
+
+	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+BEGIN_FTR_SECTION
+	beq	11f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+	/* RFI into the highmem handler, or branch to interrupt handler */
+	mfmsr	r6
+	li	r0, MSR_RI
+	andc	r6, r6, r0
+	mtmsrd	r6, 1			/* Clear RI in MSR */
+	mtsrr0	r8
+	mtsrr1	r7
+	beqa	0x500			/* external interrupt (PPC970) */
+	beq	cr1, 13f		/* machine check */
+	RFI
+
+	/* On POWER7, we have external interrupts set to use HSRR0/1 */
+11:	mtspr	SPRN_HSRR0, r8
+	mtspr	SPRN_HSRR1, r7
+	ba	0x500
+
+13:	b	machine_check_fwnmi
+
 
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
@@ -137,7 +232,7 @@ kvm_start_guest:
 	cmpdi	r4,0
 	/* if we have no vcpu to run, go back to sleep */
 	beq	kvm_no_guest
-	b	kvmppc_hv_entry
+	b	30f
 
 27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
 	b	kvm_no_guest
@@ -147,6 +242,57 @@ kvm_start_guest:
 	stw	r8,HSTATE_SAVED_XIRR(r13)
 	b	kvm_no_guest
 
+30:	bl	kvmppc_hv_entry
+
+	/* Back from the guest, go back to nap */
+	/* Clear our vcpu pointer so we don't come back in early */
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+	lwsync
+	/* Clear any pending IPI - we're an offline thread */
+	ld	r5, HSTATE_XICS_PHYS(r13)
+	li	r7, XICS_XIRR
+	lwzcix	r3, r5, r7		/* ack any pending interrupt */
+	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
+	beq	37f
+	sync
+	li	r0, 0xff
+	li	r6, XICS_MFRR
+	stbcix	r0, r5, r6		/* clear the IPI */
+	stwcix	r3, r5, r7		/* EOI it */
+37:	sync
+
+	/* increment the nap count and then go to nap mode */
+	ld	r4, HSTATE_KVM_VCORE(r13)
+	addi	r4, r4, VCORE_NAP_COUNT
+	lwsync				/* make previous updates visible */
+51:	lwarx	r3, 0, r4
+	addi	r3, r3, 1
+	stwcx.	r3, 0, r4
+	bne	51b
+
+kvm_no_guest:
+	li	r0, KVM_HWTHREAD_IN_NAP
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	li	r3, LPCR_PECE0
+	mfspr	r4, SPRN_LPCR
+	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
+	mtspr	SPRN_LPCR, r4
+	isync
+	std	r0, HSTATE_SCRATCH0(r13)
+	ptesync
+	ld	r0, HSTATE_SCRATCH0(r13)
+1:	cmpd	r0, r0
+	bne	1b
+	nap
+	b	.
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
 
@@ -159,7 +305,8 @@ kvmppc_hv_entry:
 	 * all other volatile GPRS = free
 	 */
 	mflr	r0
-	std	r0, HSTATE_VMHANDLER(r13)
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -112(r1)
 
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -1198,103 +1345,30 @@ BEGIN_FTR_SECTION
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 22:
+	ld	r0, 112+PPC_LR_STKOFF(r1)
+	addi	r1, r1, 112
+	mtlr	r0
+	blr
+secondary_too_late:
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	HMT_LOW
+13:	lbz	r3,VCORE_IN_GUEST(r5)
+	cmpwi	r3,0
+	bne	13b
+	HMT_MEDIUM
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+	ld	r11,PACA_SLBSHADOWPTR(r13)
 
-	/* Secondary threads go off to take a nap on POWER7 */
-BEGIN_FTR_SECTION
-	lwz	r0,VCPU_PTID(r9)
-	cmpwi	r0,0
-	bne	secondary_nap
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* Restore host DABR and DABRX */
-	ld	r5,HSTATE_DABR(r13)
-	li	r6,7
-	mtspr	SPRN_DABR,r5
-	mtspr	SPRN_DABRX,r6
-
-	/* Restore SPRG3 */
-	ld	r3,PACA_SPRG3(r13)
-	mtspr	SPRN_SPRG3,r3
-
-	/*
-	 * Reload DEC.  HDEC interrupts were disabled when
-	 * we reloaded the host's LPCR value.
-	 */
-	ld	r3, HSTATE_DECEXP(r13)
-	mftb	r4
-	subf	r4, r4, r3
-	mtspr	SPRN_DEC, r4
-
-	/* Reload the host's PMU registers */
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r4, LPPACA_PMCINUSE(r3)
-	cmpwi	r4, 0
-	beq	23f			/* skip if not */
-	lwz	r3, HSTATE_PMC(r13)
-	lwz	r4, HSTATE_PMC + 4(r13)
-	lwz	r5, HSTATE_PMC + 8(r13)
-	lwz	r6, HSTATE_PMC + 12(r13)
-	lwz	r8, HSTATE_PMC + 16(r13)
-	lwz	r9, HSTATE_PMC + 20(r13)
-BEGIN_FTR_SECTION
-	lwz	r10, HSTATE_PMC + 24(r13)
-	lwz	r11, HSTATE_PMC + 28(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r4
-	mtspr	SPRN_PMC3, r5
-	mtspr	SPRN_PMC4, r6
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-BEGIN_FTR_SECTION
-	mtspr	SPRN_PMC7, r10
-	mtspr	SPRN_PMC8, r11
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	ld	r3, HSTATE_MMCR(r13)
-	ld	r4, HSTATE_MMCR + 8(r13)
-	ld	r5, HSTATE_MMCR + 16(r13)
-	mtspr	SPRN_MMCR1, r4
-	mtspr	SPRN_MMCRA, r5
-	mtspr	SPRN_MMCR0, r3
-	isync
-23:
-	/*
-	 * For external and machine check interrupts, we need
-	 * to call the Linux handler to process the interrupt.
-	 * We do that by jumping to absolute address 0x500 for
-	 * external interrupts, or the machine_check_fwnmi label
-	 * for machine checks (since firmware might have patched
-	 * the vector area at 0x200).  The [h]rfid at the end of the
-	 * handler will return to the book3s_hv_interrupts.S code.
-	 * For other interrupts we do the rfid to get back
-	 * to the book3s_hv_interrupts.S code here.
-	 */
-	ld	r8, HSTATE_VMHANDLER(r13)
-	ld	r7, HSTATE_HOST_MSR(r13)
-
-	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-BEGIN_FTR_SECTION
-	beq	11f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* RFI into the highmem handler, or branch to interrupt handler */
-	mfmsr	r6
-	li	r0, MSR_RI
-	andc	r6, r6, r0
-	mtmsrd	r6, 1			/* Clear RI in MSR */
-	mtsrr0	r8
-	mtsrr1	r7
-	beqa	0x500			/* external interrupt (PPC970) */
-	beq	cr1, 13f		/* machine check */
-	RFI
-
-	/* On POWER7, we have external interrupts set to use HSRR0/1 */
-11:	mtspr	SPRN_HSRR0, r8
-	mtspr	SPRN_HSRR1, r7
-	ba	0x500
-
-13:	b	machine_check_fwnmi
+	.rept	SLB_NUM_BOLTED
+	ld	r5,SLBSHADOW_SAVEAREA(r11)
+	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r11,r11,16
+	.endr
+	b	22b
 
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
@@ -1741,68 +1815,6 @@ machine_check_realmode:
 	rotldi	r11, r11, 63
 	b	fast_interrupt_c_return
 
-secondary_too_late:
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	HMT_LOW
-13:	lbz	r3,VCORE_IN_GUEST(r5)
-	cmpwi	r3,0
-	bne	13b
-	HMT_MEDIUM
-	ld	r11,PACA_SLBSHADOWPTR(r13)
-
-	.rept	SLB_NUM_BOLTED
-	ld	r5,SLBSHADOW_SAVEAREA(r11)
-	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
-	andis.	r7,r5,SLB_ESID_V@h
-	beq	1f
-	slbmte	r6,r5
-1:	addi	r11,r11,16
-	.endr
-
-secondary_nap:
-	/* Clear our vcpu pointer so we don't come back in early */
-	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
-	lwsync
-	/* Clear any pending IPI - assume we're a secondary thread */
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r7, XICS_XIRR
-	lwzcix	r3, r5, r7		/* ack any pending interrupt */
-	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
-	beq	37f
-	sync
-	li	r0, 0xff
-	li	r6, XICS_MFRR
-	stbcix	r0, r5, r6		/* clear the IPI */
-	stwcix	r3, r5, r7		/* EOI it */
-37:	sync
-
-	/* increment the nap count and then go to nap mode */
-	ld	r4, HSTATE_KVM_VCORE(r13)
-	addi	r4, r4, VCORE_NAP_COUNT
-	lwsync				/* make previous updates visible */
-51:	lwarx	r3, 0, r4
-	addi	r3, r3, 1
-	stwcx.	r3, 0, r4
-	bne	51b
-
-kvm_no_guest:
-	li	r0, KVM_HWTHREAD_IN_NAP
-	stb	r0, HSTATE_HWTHREAD_STATE(r13)
-
-	li	r3, LPCR_PECE0
-	mfspr	r4, SPRN_LPCR
-	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
-	mtspr	SPRN_LPCR, r4
-	isync
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
-	nap
-	b	.
-
 /*
  * Save away FP, VMX and VSX registers.
  * r3 = vcpu pointer