Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Marcelo Tosatti:
 "Considerable KVM/PPC work, x86 kvmclock vsyscall support,
  IA32_TSC_ADJUST MSR emulation, amongst others."

Fix up trivial conflict in kernel/sched/core.c due to cross-cpu
migration notifier added next to rq migration call-back.

* tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (156 commits)
  KVM: emulator: fix real mode segment checks in address linearization
  VMX: remove unneeded enable_unrestricted_guest check
  KVM: VMX: fix DPL during entry to protected mode
  x86/kexec: crash_vmclear_local_vmcss needs __rcu
  kvm: Fix irqfd resampler list walk
  KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump
  x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary
  KVM: MMU: optimize for set_spte
  KVM: PPC: booke: Get/set guest EPCR register using ONE_REG interface
  KVM: PPC: bookehv: Add EPCR support in mtspr/mfspr emulation
  KVM: PPC: bookehv: Add guest computation mode for irq delivery
  KVM: PPC: Make EPCR a valid field for booke64 and bookehv
  KVM: PPC: booke: Extend MAS2 EPN mask for 64-bit
  KVM: PPC: e500: Mask MAS2 EPN high 32-bits in 32/64 tlbwe emulation
  KVM: PPC: Mask ea's high 32-bits in 32/64 instr emulation
  KVM: PPC: e500: Add emulation helper for getting instruction ea
  KVM: PPC: bookehv64: Add support for interrupt handling
  KVM: PPC: bookehv: Remove GET_VCPU macro from exception handler
  KVM: PPC: booke: Fix get_tb() compile error on 64-bit
  KVM: PPC: e500: Silence bogus GCC warning in tlb code
  ...

1 files changed, 41 insertions, 74 deletions

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 714e2c01a6fe..891eb6d93b8b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -305,51 +305,43 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 					addr, access);
 }
 
-static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
-				    struct kvm_mmu_page *sp, u64 *spte,
-				    pt_element_t gpte)
+static bool
+FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+		     u64 *spte, pt_element_t gpte, bool no_dirty_log)
 {
-	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
-		goto no_present;
-
-	if (!is_present_gpte(gpte))
-		goto no_present;
-
-	if (!(gpte & PT_ACCESSED_MASK))
-		goto no_present;
-
-	return false;
-
-no_present:
-	drop_spte(vcpu->kvm, spte);
-	return true;
-}
-
-static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			      u64 *spte, const void *pte)
-{
-	pt_element_t gpte;
 	unsigned pte_access;
+	gfn_t gfn;
 	pfn_t pfn;
 
-	gpte = *(const pt_element_t *)pte;
-	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
-		return;
+	if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
+		return false;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
+
+	gfn = gpte_to_gfn(gpte);
 	pte_access = sp->role.access & gpte_access(vcpu, gpte);
 	protect_clean_gpte(&pte_access, gpte);
-	pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte));
-	if (mmu_invalid_pfn(pfn))
-		return;
+	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
+			no_dirty_log && (pte_access & ACC_WRITE_MASK));
+	if (is_error_pfn(pfn))
+		return false;
 
 	/*
-	 * we call mmu_set_spte() with host_writable = true because that
-	 * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
+	 * we call mmu_set_spte() with host_writable = true because
+	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
 	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-		     NULL, PT_PAGE_TABLE_LEVEL,
-		     gpte_to_gfn(gpte), pfn, true, true);
+		     NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true);
+
+	return true;
+}
+
+static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+			      u64 *spte, const void *pte)
+{
+	pt_element_t gpte = *(const pt_element_t *)pte;
+
+	FNAME(prefetch_gpte)(vcpu, sp, spte, gpte, false);
 }
 
 static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,
@@ -395,53 +387,34 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	spte = sp->spt + i;
 
 	for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
-		pt_element_t gpte;
-		unsigned pte_access;
-		gfn_t gfn;
-		pfn_t pfn;
-
 		if (spte == sptep)
 			continue;
 
 		if (is_shadow_present_pte(*spte))
 			continue;
 
-		gpte = gptep[i];
-
-		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
-			continue;
-
-		pte_access = sp->role.access & gpte_access(vcpu, gpte);
-		protect_clean_gpte(&pte_access, gpte);
-		gfn = gpte_to_gfn(gpte);
-		pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
-				      pte_access & ACC_WRITE_MASK);
-		if (mmu_invalid_pfn(pfn))
+		if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true))
 			break;
-
-		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-			     NULL, PT_PAGE_TABLE_LEVEL, gfn,
-			     pfn, true, true);
 	}
 }
 
 /*
  * Fetch a shadow pte for a specific level in the paging hierarchy.
+ * If the guest tries to write a write-protected page, we need to
+ * emulate this operation, return 1 to indicate this case.
  */
-static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int user_fault, int write_fault, int hlevel,
-			 int *emulate, pfn_t pfn, bool map_writable,
-			 bool prefault)
+			 pfn_t pfn, bool map_writable, bool prefault)
 {
-	unsigned access = gw->pt_access;
 	struct kvm_mmu_page *sp = NULL;
-	int top_level;
-	unsigned direct_access;
 	struct kvm_shadow_walk_iterator it;
+	unsigned direct_access, access = gw->pt_access;
+	int top_level, emulate = 0;
 
 	if (!is_present_gpte(gw->ptes[gw->level - 1]))
-		return NULL;
+		return 0;
 
 	direct_access = gw->pte_access;
 
@@ -505,17 +478,17 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	clear_sp_write_flooding_count(it.sptep);
 	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access,
-		     user_fault, write_fault, emulate, it.level,
+		     user_fault, write_fault, &emulate, it.level,
 		     gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
-	return it.sptep;
+	return emulate;
 
 out_gpte_changed:
 	if (sp)
 		kvm_mmu_put_page(sp, it.sptep);
 	kvm_release_pfn_clean(pfn);
-	return NULL;
+	return 0;
 }
 
 /*
@@ -538,8 +511,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int write_fault = error_code & PFERR_WRITE_MASK;
 	int user_fault = error_code & PFERR_USER_MASK;
 	struct guest_walker walker;
-	u64 *sptep;
-	int emulate = 0;
 	int r;
 	pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
@@ -594,24 +565,20 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return r;
 
 	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu, mmu_seq))
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
 	kvm_mmu_free_some_pages(vcpu);
 	if (!force_pt_level)
 		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
-	sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
-			     level, &emulate, pfn, map_writable, prefault);
-	(void)sptep;
-	pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__,
-		 sptep, *sptep, emulate);
-
+	r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+			 level, pfn, map_writable, prefault);
 	++vcpu->stat.pf_fixed;
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
-	return emulate;
+	return r;
 
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
@@ -757,7 +724,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 					  sizeof(pt_element_t)))
 			return -EINVAL;
 
-		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
+		if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}