Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Avi Kivity:
 "Changes include additional instruction emulation, page-crossing MMIO,
  faster dirty logging, preventing the watchdog from killing a stopped
  guest, module autoload, a new MSI ABI, and some minor optimizations
  and fixes.  Outside x86 we have a small s390 and a very large ppc
  update.

  Regarding the new (for kvm) rebaseless workflow, some of the patches
  that were merged before we switch trees had to be rebased, while
  others are true pulls.  In either case the signoffs should be correct
  now."

Fix up trivial conflicts in Documentation/feature-removal-schedule.txt
arch/powerpc/kvm/book3s_segment.S and arch/x86/include/asm/kvm_para.h.

I suspect the kvm_para.h resolution ends up doing the "do I have cpuid"
check effectively twice (it was done differently in two different
commits), but better safe than sorry ;)

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (125 commits)
  KVM: make asm-generic/kvm_para.h have an ifdef __KERNEL__ block
  KVM: s390: onereg for timer related registers
  KVM: s390: epoch difference and TOD programmable field
  KVM: s390: KVM_GET/SET_ONEREG for s390
  KVM: s390: add capability indicating COW support
  KVM: Fix mmu_reload() clash with nested vmx event injection
  KVM: MMU: Don't use RCU for lockless shadow walking
  KVM: VMX: Optimize %ds, %es reload
  KVM: VMX: Fix %ds/%es clobber
  KVM: x86 emulator: convert bsf/bsr instructions to emulate_2op_SrcV_nobyte()
  KVM: VMX: unlike vmcs on fail path
  KVM: PPC: Emulator: clean up SPR reads and writes
  KVM: PPC: Emulator: clean up instruction parsing
  kvm/powerpc: Add new ioctl to retreive server MMU infos
  kvm/book3s: Make kernel emulated H_PUT_TCE available for "PR" KVM
  KVM: PPC: bookehv: Fix r8/r13 storing in level exception handler
  KVM: PPC: Book3S: Enable IRQs during exit handling
  KVM: PPC: Fix PR KVM on POWER7 bare metal
  KVM: PPC: Fix stbux emulation
  KVM: PPC: bookehv: Use lwz/stw instead of PPC_LL/PPC_STL for 32-bit fields
  ...

1 files changed, 108 insertions, 77 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b70bf22a3ff3..a84aafce2a12 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -26,6 +26,7 @@
 #include <asm/hvcall.h>
 #include <asm/asm-offsets.h>
 #include <asm/exception-64s.h>
+#include <asm/kvm_book3s_asm.h>
 
 /*****************************************************************************
  *                                                                           *
@@ -82,6 +83,7 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 
 #define XICS_XIRR		4
 #define XICS_QIRR		0xc
+#define XICS_IPI		2	/* interrupt source # for IPIs */
 
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
@@ -94,26 +96,54 @@ kvm_start_guest:
 	subi	r1,r1,STACK_FRAME_OVERHEAD
 	ld	r2,PACATOC(r13)
 
-	/* were we napping due to cede? */
-	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,0
-	bne	kvm_end_cede
+	li	r0,KVM_HWTHREAD_IN_KVM
+	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 
-	/* get vcpu pointer */
-	ld	r4, HSTATE_KVM_VCPU(r13)
+	/* NV GPR values from power7_idle() will no longer be valid */
+	li	r0,1
+	stb	r0,PACA_NAPSTATELOST(r13)
 
-	/* We got here with an IPI; clear it */
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r0, 0xff
-	li	r6, XICS_QIRR
-	li	r7, XICS_XIRR
-	lwzcix	r8, r5, r7		/* ack the interrupt */
+	/* get vcpu pointer, NULL if we have no vcpu to run */
+	ld	r4,HSTATE_KVM_VCPU(r13)
+	cmpdi	cr1,r4,0
+
+	/* Check the wake reason in SRR1 to see why we got here */
+	mfspr	r3,SPRN_SRR1
+	rlwinm	r3,r3,44-31,0x7		/* extract wake reason field */
+	cmpwi	r3,4			/* was it an external interrupt? */
+	bne	27f
+
+	/*
+	 * External interrupt - for now assume it is an IPI, since we
+	 * should never get any other interrupts sent to offline threads.
+	 * Only do this for secondary threads.
+	 */
+	beq	cr1,25f
+	lwz	r3,VCPU_PTID(r4)
+	cmpwi	r3,0
+	beq	27f
+25:	ld	r5,HSTATE_XICS_PHYS(r13)
+	li	r0,0xff
+	li	r6,XICS_QIRR
+	li	r7,XICS_XIRR
+	lwzcix	r8,r5,r7		/* get and ack the interrupt */
 	sync
-	stbcix	r0, r5, r6		/* clear it */
-	stwcix	r8, r5, r7		/* EOI it */
+	clrldi.	r9,r8,40		/* get interrupt source ID. */
+	beq	27f			/* none there? */
+	cmpwi	r9,XICS_IPI
+	bne	26f
+	stbcix	r0,r5,r6		/* clear IPI */
+26:	stwcix	r8,r5,r7		/* EOI the interrupt */
 
-	/* NV GPR values from power7_idle() will no longer be valid */
-	stb	r0, PACA_NAPSTATELOST(r13)
+27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
+
+	/* if we have no vcpu to run, go back to sleep */
+	beq	cr1,kvm_no_guest
+
+	/* were we napping due to cede? */
+	lbz	r0,HSTATE_NAPPING(r13)
+	cmpwi	r0,0
+	bne	kvm_end_cede
 
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
@@ -129,24 +159,15 @@ kvmppc_hv_entry:
 	mflr	r0
 	std	r0, HSTATE_VMHANDLER(r13)
 
-	ld	r14, VCPU_GPR(r14)(r4)
-	ld	r15, VCPU_GPR(r15)(r4)
-	ld	r16, VCPU_GPR(r16)(r4)
-	ld	r17, VCPU_GPR(r17)(r4)
-	ld	r18, VCPU_GPR(r18)(r4)
-	ld	r19, VCPU_GPR(r19)(r4)
-	ld	r20, VCPU_GPR(r20)(r4)
-	ld	r21, VCPU_GPR(r21)(r4)
-	ld	r22, VCPU_GPR(r22)(r4)
-	ld	r23, VCPU_GPR(r23)(r4)
-	ld	r24, VCPU_GPR(r24)(r4)
-	ld	r25, VCPU_GPR(r25)(r4)
-	ld	r26, VCPU_GPR(r26)(r4)
-	ld	r27, VCPU_GPR(r27)(r4)
-	ld	r28, VCPU_GPR(r28)(r4)
-	ld	r29, VCPU_GPR(r29)(r4)
-	ld	r30, VCPU_GPR(r30)(r4)
-	ld	r31, VCPU_GPR(r31)(r4)
+	/* Set partition DABR */
+	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
+	li	r5,3
+	ld	r6,VCPU_DABR(r4)
+	mtspr	SPRN_DABRX,r5
+	mtspr	SPRN_DABR,r6
+BEGIN_FTR_SECTION
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 	/* Load guest PMU registers */
 	/* R4 is live here (vcpu pointer) */
@@ -185,6 +206,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	/* Load up FP, VMX and VSX registers */
 	bl	kvmppc_load_fp
 
+	ld	r14, VCPU_GPR(r14)(r4)
+	ld	r15, VCPU_GPR(r15)(r4)
+	ld	r16, VCPU_GPR(r16)(r4)
+	ld	r17, VCPU_GPR(r17)(r4)
+	ld	r18, VCPU_GPR(r18)(r4)
+	ld	r19, VCPU_GPR(r19)(r4)
+	ld	r20, VCPU_GPR(r20)(r4)
+	ld	r21, VCPU_GPR(r21)(r4)
+	ld	r22, VCPU_GPR(r22)(r4)
+	ld	r23, VCPU_GPR(r23)(r4)
+	ld	r24, VCPU_GPR(r24)(r4)
+	ld	r25, VCPU_GPR(r25)(r4)
+	ld	r26, VCPU_GPR(r26)(r4)
+	ld	r27, VCPU_GPR(r27)(r4)
+	ld	r28, VCPU_GPR(r28)(r4)
+	ld	r29, VCPU_GPR(r29)(r4)
+	ld	r30, VCPU_GPR(r30)(r4)
+	ld	r31, VCPU_GPR(r31)(r4)
+
 BEGIN_FTR_SECTION
 	/* Switch DSCR to guest value */
 	ld	r5, VCPU_DSCR(r4)
@@ -226,12 +266,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mtspr	SPRN_DAR, r5
 	mtspr	SPRN_DSISR, r6
 
-	/* Set partition DABR */
-	li	r5,3
-	ld	r6,VCPU_DABR(r4)
-	mtspr	SPRN_DABRX,r5
-	mtspr	SPRN_DABR,r6
-
 BEGIN_FTR_SECTION
 	/* Restore AMR and UAMOR, set AMOR to all 1s */
 	ld	r5,VCPU_AMR(r4)
@@ -925,12 +959,6 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_AMR,r6
 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
-
 	/* Switch DSCR back to host value */
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
@@ -969,6 +997,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	std	r5, VCPU_SPRG2(r9)
 	std	r6, VCPU_SPRG3(r9)
 
+	/* save FP state */
+	mr	r3, r9
+	bl	.kvmppc_save_fp
+
 	/* Increment yield count if they have a VPA */
 	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
 	cmpdi	r8, 0
@@ -983,6 +1015,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
 	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	mfspr	r6, SPRN_MMCRA
+BEGIN_FTR_SECTION
+	/* On P7, clear MMCRA in order to disable SDAR updates */
+	li	r7, 0
+	mtspr	SPRN_MMCRA, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	isync
 	beq	21f			/* if no VPA, save PMU stuff anyway */
 	lbz	r7, LPPACA_PMCINUSE(r8)
@@ -991,7 +1029,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	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)
 	std	r6, VCPU_MMCR + 16(r9)
@@ -1016,17 +1053,20 @@ BEGIN_FTR_SECTION
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 22:
-	/* save FP state */
-	mr	r3, r9
-	bl	.kvmppc_save_fp
 
 	/* Secondary threads go off to take a nap on POWER7 */
 BEGIN_FTR_SECTION
-	lwz	r0,VCPU_PTID(r3)
+	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
+
 	/*
 	 * Reload DEC.  HDEC interrupts were disabled when
 	 * we reloaded the host's LPCR value.
@@ -1363,7 +1403,12 @@ bounce_ext_interrupt:
 
 _GLOBAL(kvmppc_h_set_dabr)
 	std	r4,VCPU_DABR(r3)
-	mtspr	SPRN_DABR,r4
+	/* Work around P7 bug where DABR can get corrupted on mtspr */
+1:	mtspr	SPRN_DABR,r4
+	mfspr	r5, SPRN_DABR
+	cmpd	r4, r5
+	bne	1b
+	isync
 	li	r3,0
 	blr
 
@@ -1445,8 +1490,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	 * Take a nap until a decrementer or external interrupt occurs,
 	 * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
 	 */
-	li	r0,0x80
-	stb	r0,PACAPROCSTART(r13)
+	li	r0,1
+	stb	r0,HSTATE_HWTHREAD_REQ(r13)
 	mfspr	r5,SPRN_LPCR
 	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR,r5
@@ -1463,26 +1508,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 kvm_end_cede:
 	/* Woken by external or decrementer interrupt */
 	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
 
-	/* If we're a secondary thread and we got here by an IPI, ack it */
-	ld	r4,HSTATE_KVM_VCPU(r13)
-	lwz	r3,VCPU_PTID(r4)
-	cmpwi	r3,0
-	beq	27f
-	mfspr	r3,SPRN_SRR1
-	rlwinm	r3,r3,44-31,0x7		/* extract wake reason field */
-	cmpwi	r3,4			/* was it an external interrupt? */
-	bne	27f
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r0,0xff
-	li	r6,XICS_QIRR
-	li	r7,XICS_XIRR
-	lwzcix	r8,r5,r7		/* ack the interrupt */
-	sync
-	stbcix	r0,r5,r6		/* clear it */
-	stwcix	r8,r5,r7		/* EOI it */
-27:
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
@@ -1580,12 +1606,17 @@ secondary_nap:
 	stwcx.	r3, 0, r4
 	bne	51b
 
+kvm_no_guest:
+	li	r0, KVM_HWTHREAD_IN_NAP
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
 	isync
-	li	r0, 0
 	std	r0, HSTATE_SCRATCH0(r13)
 	ptesync
 	ld	r0, HSTATE_SCRATCH0(r13)
@@ -1599,8 +1630,8 @@ secondary_nap:
  * r3 = vcpu pointer
  */
 _GLOBAL(kvmppc_save_fp)
-	mfmsr	r9
-	ori	r8,r9,MSR_FP
+	mfmsr	r5
+	ori	r8,r5,MSR_FP
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	oris	r8,r8,MSR_VEC@h
@@ -1649,7 +1680,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	mfspr	r6,SPRN_VRSAVE
 	stw	r6,VCPU_VRSAVE(r3)
-	mtmsrd	r9
+	mtmsrd	r5
 	isync
 	blr