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, 318 insertions, 54 deletions

diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index ddcd896fa2ff..b479ed77c515 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -20,11 +20,282 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 #include <asm/tlbflush.h>
-#include <asm/kvm_e500.h>
 #include <asm/kvm_ppc.h>
 
+#include "../mm/mmu_decl.h"
 #include "booke.h"
-#include "e500_tlb.h"
+#include "e500.h"
+
+struct id {
+	unsigned long val;
+	struct id **pentry;
+};
+
+#define NUM_TIDS 256
+
+/*
+ * This table provide mappings from:
+ * (guestAS,guestTID,guestPR) --> ID of physical cpu
+ * guestAS	[0..1]
+ * guestTID	[0..255]
+ * guestPR	[0..1]
+ * ID		[1..255]
+ * Each vcpu keeps one vcpu_id_table.
+ */
+struct vcpu_id_table {
+	struct id id[2][NUM_TIDS][2];
+};
+
+/*
+ * This table provide reversed mappings of vcpu_id_table:
+ * ID --> address of vcpu_id_table item.
+ * Each physical core has one pcpu_id_table.
+ */
+struct pcpu_id_table {
+	struct id *entry[NUM_TIDS];
+};
+
+static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
+
+/* This variable keeps last used shadow ID on local core.
+ * The valid range of shadow ID is [1..255] */
+static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
+
+/*
+ * Allocate a free shadow id and setup a valid sid mapping in given entry.
+ * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_setup_one(struct id *entry)
+{
+	unsigned long sid;
+	int ret = -1;
+
+	sid = ++(__get_cpu_var(pcpu_last_used_sid));
+	if (sid < NUM_TIDS) {
+		__get_cpu_var(pcpu_sids).entry[sid] = entry;
+		entry->val = sid;
+		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
+		ret = sid;
+	}
+
+	/*
+	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
+	 * the caller will invalidate everything and start over.
+	 *
+	 * sid > NUM_TIDS indicates a race, which we disable preemption to
+	 * avoid.
+	 */
+	WARN_ON(sid > NUM_TIDS);
+
+	return ret;
+}
+
+/*
+ * Check if given entry contain a valid shadow id mapping.
+ * An ID mapping is considered valid only if
+ * both vcpu and pcpu know this mapping.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_lookup(struct id *entry)
+{
+	if (entry && entry->val != 0 &&
+	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
+	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
+		return entry->val;
+	return -1;
+}
+
+/* Invalidate all id mappings on local core -- call with preempt disabled */
+static inline void local_sid_destroy_all(void)
+{
+	__get_cpu_var(pcpu_last_used_sid) = 0;
+	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
+}
+
+static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
+	return vcpu_e500->idt;
+}
+
+static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->idt);
+	vcpu_e500->idt = NULL;
+}
+
+/* Map guest pid to shadow.
+ * We use PID to keep shadow of current guest non-zero PID,
+ * and use PID1 to keep shadow of guest zero PID.
+ * So that guest tlbe with TID=0 can be accessed at any time */
+static void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	preempt_disable();
+	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu),
+			get_cur_pid(&vcpu_e500->vcpu),
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu), 0,
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	preempt_enable();
+}
+
+/* Invalidate all mappings on vcpu */
+static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/* Invalidate one ID mapping on vcpu */
+static inline void kvmppc_e500_id_table_reset_one(
+			       struct kvmppc_vcpu_e500 *vcpu_e500,
+			       int as, int pid, int pr)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+
+	BUG_ON(as >= 2);
+	BUG_ON(pid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	idt->id[as][pid][pr].val = 0;
+	idt->id[as][pid][pr].pentry = NULL;
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/*
+ * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
+ * This function first lookup if a valid mapping exists,
+ * if not, then creates a new one.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 unsigned int as, unsigned int gid,
+				 unsigned int pr, int avoid_recursion)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	int sid;
+
+	BUG_ON(as >= 2);
+	BUG_ON(gid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	sid = local_sid_lookup(&idt->id[as][gid][pr]);
+
+	while (sid <= 0) {
+		/* No mapping yet */
+		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
+		if (sid <= 0) {
+			_tlbil_all();
+			local_sid_destroy_all();
+		}
+
+		/* Update shadow pid when mappings are changed */
+		if (!avoid_recursion)
+			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+
+	return sid;
+}
+
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+				      struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	return kvmppc_e500_get_sid(to_e500(vcpu), get_tlb_ts(gtlbe),
+				   get_tlb_tid(gtlbe), get_cur_pr(vcpu), 0);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	if (vcpu->arch.pid != pid) {
+		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
+		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+}
+
+/* gtlbe must not be mapped by more than one host tlbe */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+                           struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	unsigned int pr, tid, ts, pid;
+	u32 val, eaddr;
+	unsigned long flags;
+
+	ts = get_tlb_ts(gtlbe);
+	tid = get_tlb_tid(gtlbe);
+
+	preempt_disable();
+
+	/* One guest ID may be mapped to two shadow IDs */
+	for (pr = 0; pr < 2; pr++) {
+		/*
+		 * The shadow PID can have a valid mapping on at most one
+		 * host CPU.  In the common case, it will be valid on this
+		 * CPU, in which case we do a local invalidation of the
+		 * specific address.
+		 *
+		 * If the shadow PID is not valid on the current host CPU,
+		 * we invalidate the entire shadow PID.
+		 */
+		pid = local_sid_lookup(&idt->id[ts][tid][pr]);
+		if (pid <= 0) {
+			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
+			continue;
+		}
+
+		/*
+		 * The guest is invalidating a 4K entry which is in a PID
+		 * that has a valid shadow mapping on this host CPU.  We
+		 * search host TLB to invalidate it's shadow TLB entry,
+		 * similar to __tlbil_va except that we need to look in AS1.
+		 */
+		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
+		eaddr = get_tlb_eaddr(gtlbe);
+
+		local_irq_save(flags);
+
+		mtspr(SPRN_MAS6, val);
+		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
+		val = mfspr(SPRN_MAS1);
+		if (val & MAS1_VALID) {
+			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+			asm volatile("tlbwe");
+		}
+
+		local_irq_restore(flags);
+	}
+
+	preempt_enable();
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kvmppc_e500_id_table_reset_all(vcpu_e500);
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+	/* Recalc shadow pid since MSR changes */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
+}
 
 void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
 {
@@ -36,17 +307,20 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	kvmppc_e500_tlb_load(vcpu, cpu);
+	kvmppc_booke_vcpu_load(vcpu, cpu);
+
+	/* Shadow PID may be expired on local core */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_e500_tlb_put(vcpu);
-
 #ifdef CONFIG_SPE
 	if (vcpu->arch.shadow_msr & MSR_SPE)
 		kvmppc_vcpu_disable_spe(vcpu);
 #endif
+
+	kvmppc_booke_vcpu_put(vcpu);
 }
 
 int kvmppc_core_check_processor_compat(void)
@@ -61,6 +335,23 @@ int kvmppc_core_check_processor_compat(void)
 	return r;
 }
 
+static void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	struct kvm_book3e_206_tlb_entry *tlbe;
+
+	/* Insert large initial mapping for guest. */
+	tlbe = get_entry(vcpu_e500, 1, 0);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
+	tlbe->mas2 = 0;
+	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
+
+	/* 4K map for serial output. Used by kernel wrapper. */
+	tlbe = get_entry(vcpu_e500, 1, 1);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
 int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -76,32 +367,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
-int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
-                               struct kvm_translation *tr)
-{
-	int index;
-	gva_t eaddr;
-	u8 pid;
-	u8 as;
-
-	eaddr = tr->linear_address;
-	pid = (tr->linear_address >> 32) & 0xff;
-	as = (tr->linear_address >> 40) & 0x1;
-
-	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
-	if (index < 0) {
-		tr->valid = 0;
-		return 0;
-	}
-
-	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
-	/* XXX what does "writeable" and "usermode" even mean? */
-	tr->valid = 1;
-
-	return 0;
-}
-
 void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -115,19 +380,6 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
 	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
 
-	sregs->u.e.mas0 = vcpu->arch.shared->mas0;
-	sregs->u.e.mas1 = vcpu->arch.shared->mas1;
-	sregs->u.e.mas2 = vcpu->arch.shared->mas2;
-	sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
-	sregs->u.e.mas4 = vcpu->arch.shared->mas4;
-	sregs->u.e.mas6 = vcpu->arch.shared->mas6;
-
-	sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
-	sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
-	sregs->u.e.tlbcfg[1] = vcpu_e500->tlb1cfg;
-	sregs->u.e.tlbcfg[2] = 0;
-	sregs->u.e.tlbcfg[3] = 0;
-
 	sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
 	sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
 	sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
@@ -135,11 +387,13 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
 
 	kvmppc_get_sregs_ivor(vcpu, sregs);
+	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
 }
 
 int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int ret;
 
 	if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
 		vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
@@ -147,14 +401,9 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
 	}
 
-	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
-		vcpu->arch.shared->mas0 = sregs->u.e.mas0;
-		vcpu->arch.shared->mas1 = sregs->u.e.mas1;
-		vcpu->arch.shared->mas2 = sregs->u.e.mas2;
-		vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
-		vcpu->arch.shared->mas4 = sregs->u.e.mas4;
-		vcpu->arch.shared->mas6 = sregs->u.e.mas6;
-	}
+	ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+	if (ret < 0)
+		return ret;
 
 	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
 		return 0;
@@ -193,9 +442,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+		goto uninit_vcpu;
+
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
-		goto uninit_vcpu;
+		goto uninit_id;
 
 	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (!vcpu->arch.shared)
@@ -205,6 +457,8 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_id:
+	kvmppc_e500_id_table_free(vcpu_e500);
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_vcpu:
@@ -218,11 +472,21 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
 	free_page((unsigned long)vcpu->arch.shared);
-	kvm_vcpu_uninit(vcpu);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvmppc_e500_id_table_free(vcpu_e500);
+	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+}
+
 static int __init kvmppc_e500_init(void)
 {
 	int r, i;