Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "Small release overall.

  x86:
   - miscellaneous fixes
   - AVIC support (local APIC virtualization, AMD version)

  s390:
   - polling for interrupts after a VCPU goes to halted state is now
     enabled for s390
   - use hardware provided information about facility bits that do not
     need any hypervisor activity, and other fixes for cpu models and
     facilities
   - improve perf output
   - floating interrupt controller improvements.

  MIPS:
   - miscellaneous fixes

  PPC:
   - bugfixes only

  ARM:
   - 16K page size support
   - generic firmware probing layer for timer and GIC

  Christoffer Dall (KVM-ARM maintainer) says:
    "There are a few changes in this pull request touching things
     outside KVM, but they should all carry the necessary acks and it
     made the merge process much easier to do it this way."

  though actually the irqchip maintainers' acks didn't make it into the
  patches.  Marc Zyngier, who is both irqchip and KVM-ARM maintainer,
  later acked at http://mid.gmane.org/573351D1.4060303@arm.com ('more
  formally and for documentation purposes')"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (82 commits)
  KVM: MTRR: remove MSR 0x2f8
  KVM: x86: make hwapic_isr_update and hwapic_irr_update look the same
  svm: Manage vcpu load/unload when enable AVIC
  svm: Do not intercept CR8 when enable AVIC
  svm: Do not expose x2APIC when enable AVIC
  KVM: x86: Introducing kvm_x86_ops.apicv_post_state_restore
  svm: Add VMEXIT handlers for AVIC
  svm: Add interrupt injection via AVIC
  KVM: x86: Detect and Initialize AVIC support
  svm: Introduce new AVIC VMCB registers
  KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick
  KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking hooks
  KVM: x86: Introducing kvm_x86_ops VM init/destroy hooks
  KVM: x86: Rename kvm_apic_get_reg to kvm_lapic_get_reg
  KVM: x86: Misc LAPIC changes to expose helper functions
  KVM: shrink halt polling even more for invalid wakeups
  KVM: s390: set halt polling to 80 microseconds
  KVM: halt_polling: provide a way to qualify wakeups during poll
  KVM: PPC: Book3S HV: Re-enable XICS fast path for irqfd-generated interrupts
  kvm: Conditionally register IRQ bypass consumer
  ...

75 files changed, 2398 insertions, 850 deletions

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 4d0542c5206b..a4482cce4bae 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -199,8 +199,8 @@ Type: vm ioctl
 Parameters: vcpu id (apic id on x86)
 Returns: vcpu fd on success, -1 on error
 
-This API adds a vcpu to a virtual machine.  The vcpu id is a small integer
-in the range [0, max_vcpus).
+This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
+The vcpu id is an integer in the range [0, max_vcpu_id).
 
 The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
 the KVM_CHECK_EXTENSION ioctl() at run-time.
@@ -212,6 +212,12 @@ cpus max.
 If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
 same as the value returned from KVM_CAP_NR_VCPUS.
 
+The maximum possible value for max_vcpu_id can be retrieved using the
+KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.
+
+If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id
+is the same as the value returned from KVM_CAP_MAX_VCPUS.
+
 On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
 threads in one or more virtual CPU cores.  (This is because the
 hardware requires all the hardware threads in a CPU core to be in the
@@ -3788,6 +3794,14 @@ a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
 Fails if VCPU has already been created, or if the irqchip is already in the
 kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
 
+7.6 KVM_CAP_S390_RI
+
+Architectures: s390
+Parameters: none
+
+Allows use of runtime-instrumentation introduced with zEC12 processor.
+Will return -EINVAL if the machine does not support runtime-instrumentation.
+Will return -EBUSY if a VCPU has already been created.
 
 8. Other capabilities.
 ----------------------
diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
index e3e314cb83e8..6b0e115301c8 100644
--- a/Documentation/virtual/kvm/devices/s390_flic.txt
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -11,6 +11,7 @@ FLIC provides support to
 - add interrupts (KVM_DEV_FLIC_ENQUEUE)
 - inspect currently pending interrupts (KVM_FLIC_GET_ALL_IRQS)
 - purge all pending floating interrupts (KVM_DEV_FLIC_CLEAR_IRQS)
+- purge one pending floating I/O interrupt (KVM_DEV_FLIC_CLEAR_IO_IRQ)
 - enable/disable for the guest transparent async page faults
 - register and modify adapter interrupt sources (KVM_DEV_FLIC_ADAPTER_*)
 
@@ -40,6 +41,11 @@ Groups:
     Simply deletes all elements from the list of currently pending floating
     interrupts.  No interrupts are injected into the guest.
 
+  KVM_DEV_FLIC_CLEAR_IO_IRQ
+    Deletes one (if any) I/O interrupt for a subchannel identified by the
+    subsystem identification word passed via the buffer specified by
+    attr->addr (address) and attr->attr (length).
+
   KVM_DEV_FLIC_APF_ENABLE
     Enables async page faults for the guest. So in case of a major page fault
     the host is allowed to handle this async and continues the guest.
@@ -68,7 +74,7 @@ struct kvm_s390_io_adapter {
 
   KVM_DEV_FLIC_ADAPTER_MODIFY
     Modifies attributes of an existing I/O adapter interrupt source. Takes
-    a kvm_s390_io_adapter_req specifiying the adapter and the operation:
+    a kvm_s390_io_adapter_req specifying the adapter and the operation:
 
 struct kvm_s390_io_adapter_req {
 	__u32 id;
@@ -94,3 +100,9 @@ struct kvm_s390_io_adapter_req {
     KVM_S390_IO_ADAPTER_UNMAP
       release a userspace page for the translated address specified in addr
       from the list of mappings
+
+Note: The KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR device ioctls executed on
+FLIC with an unknown group or attribute gives the error code EINVAL (instead of
+ENXIO, as specified in the API documentation). It is not possible to conclude
+that a FLIC operation is unavailable based on the error code resulting from a
+usage attempt.
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 738d5eee91de..0df6b1fc9655 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -187,6 +187,7 @@ struct kvm_vm_stat {
 struct kvm_vcpu_stat {
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
+	u32 halt_poll_invalid;
 	u32 halt_wakeup;
 	u32 hvc_exit_stat;
 	u64 wfe_exit_stat;
@@ -290,6 +291,7 @@ static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
 static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index f17a8d41822c..f9a65061130b 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -47,6 +47,7 @@
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/pgalloc.h>
+#include <asm/stage2_pgtable.h>
 
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
@@ -106,14 +107,16 @@ static inline void kvm_clean_pte(pte_t *pte)
 	clean_pte_table(pte);
 }
 
-static inline void kvm_set_s2pte_writable(pte_t *pte)
+static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
 {
-	pte_val(*pte) |= L_PTE_S2_RDWR;
+	pte_val(pte) |= L_PTE_S2_RDWR;
+	return pte;
 }
 
-static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
+static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
 {
-	pmd_val(*pmd) |= L_PMD_S2_RDWR;
+	pmd_val(pmd) |= L_PMD_S2_RDWR;
+	return pmd;
 }
 
 static inline void kvm_set_s2pte_readonly(pte_t *pte)
@@ -136,22 +139,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 	return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY;
 }
 
-
-/* Open coded p*d_addr_end that can deal with 64bit addresses */
-#define kvm_pgd_addr_end(addr, end)					\
-({	u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;		\
-	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
-})
-
-#define kvm_pud_addr_end(addr,end)		(end)
-
-#define kvm_pmd_addr_end(addr, end)					\
-({	u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK;		\
-	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
-})
-
-#define kvm_pgd_index(addr)			pgd_index(addr)
-
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
@@ -160,19 +147,11 @@ static inline bool kvm_page_empty(void *ptr)
 
 #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
 #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
-#define kvm_pud_table_empty(kvm, pudp) (0)
-
-#define KVM_PREALLOC_LEVEL	0
+#define kvm_pud_table_empty(kvm, pudp) false
 
-static inline void *kvm_get_hwpgd(struct kvm *kvm)
-{
-	return kvm->arch.pgd;
-}
-
-static inline unsigned int kvm_get_hwpgd_size(void)
-{
-	return PTRS_PER_S2_PGD * sizeof(pgd_t);
-}
+#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
+#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define hyp_pud_table_empty(pudp) false
 
 struct kvm;
 
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
new file mode 100644
index 000000000000..460d616bb2d6
--- /dev/null
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ *
+ * stage2 page table helpers
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_S2_PGTABLE_H_
+#define __ARM_S2_PGTABLE_H_
+
+#define stage2_pgd_none(pgd)			pgd_none(pgd)
+#define stage2_pgd_clear(pgd)			pgd_clear(pgd)
+#define stage2_pgd_present(pgd)			pgd_present(pgd)
+#define stage2_pgd_populate(pgd, pud)		pgd_populate(NULL, pgd, pud)
+#define stage2_pud_offset(pgd, address)		pud_offset(pgd, address)
+#define stage2_pud_free(pud)			pud_free(NULL, pud)
+
+#define stage2_pud_none(pud)			pud_none(pud)
+#define stage2_pud_clear(pud)			pud_clear(pud)
+#define stage2_pud_present(pud)			pud_present(pud)
+#define stage2_pud_populate(pud, pmd)		pud_populate(NULL, pud, pmd)
+#define stage2_pmd_offset(pud, address)		pmd_offset(pud, address)
+#define stage2_pmd_free(pmd)			pmd_free(NULL, pmd)
+
+#define stage2_pud_huge(pud)			pud_huge(pud)
+
+/* Open coded p*d_addr_end that can deal with 64bit addresses */
+static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK;
+
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+#define stage2_pud_addr_end(addr, end)		(end)
+
+static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary = (addr + PMD_SIZE) & PMD_MASK;
+
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+#define stage2_pgd_index(addr)				pgd_index(addr)
+
+#define stage2_pte_table_empty(ptep)			kvm_page_empty(ptep)
+#define stage2_pmd_table_empty(pmdp)			kvm_page_empty(pmdp)
+#define stage2_pud_table_empty(pudp)			false
+
+#endif	/* __ARM_S2_PGTABLE_H_ */
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9ef013d86cc5..237d5d82f0af 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -444,7 +444,7 @@ static void update_vttbr(struct kvm *kvm)
 	kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;
 
 	/* update vttbr to be used with the new vmid */
-	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
+	pgd_phys = virt_to_phys(kvm->arch.pgd);
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
 	kvm->arch.vttbr = pgd_phys | vmid;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index be302128c5d7..45c43aecb8f2 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -43,11 +43,9 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define S2_PGD_SIZE	(PTRS_PER_S2_PGD * sizeof(pgd_t))
 #define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
 
-#define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
-#define kvm_pud_huge(_x)	pud_huge(_x)
-
 #define KVM_S2PTE_FLAG_IS_IOMAP		(1UL << 0)
 #define KVM_S2_FLAG_LOGGING_ACTIVE	(1UL << 1)
 
@@ -69,14 +67,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
-	/*
-	 * This function also gets called when dealing with HYP page
-	 * tables. As HYP doesn't have an associated struct kvm (and
-	 * the HYP page tables are fairly static), we don't do
-	 * anything there.
-	 */
-	if (kvm)
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
 /*
@@ -115,7 +106,7 @@ static bool kvm_is_device_pfn(unsigned long pfn)
  */
 static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
 {
-	if (!kvm_pmd_huge(*pmd))
+	if (!pmd_thp_or_huge(*pmd))
 		return;
 
 	pmd_clear(pmd);
@@ -155,29 +146,29 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
 {
-	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
-	pgd_clear(pgd);
+	pud_t *pud_table __maybe_unused = stage2_pud_offset(pgd, 0UL);
+	stage2_pgd_clear(pgd);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pud_free(NULL, pud_table);
+	stage2_pud_free(pud_table);
 	put_page(virt_to_page(pgd));
 }
 
-static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
-	pmd_t *pmd_table = pmd_offset(pud, 0);
-	VM_BUG_ON(pud_huge(*pud));
-	pud_clear(pud);
+	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(pud, 0);
+	VM_BUG_ON(stage2_pud_huge(*pud));
+	stage2_pud_clear(pud);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pmd_free(NULL, pmd_table);
+	stage2_pmd_free(pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
-	VM_BUG_ON(kvm_pmd_huge(*pmd));
+	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
 	pte_free_kernel(NULL, pte_table);
@@ -204,7 +195,7 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
  * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
  * the IO subsystem will never hit in the cache.
  */
-static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t start_addr = addr;
@@ -226,21 +217,21 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (kvm_pte_table_empty(kvm, start_pte))
-		clear_pmd_entry(kvm, pmd, start_addr);
+	if (stage2_pte_table_empty(start_pte))
+		clear_stage2_pmd_entry(kvm, pmd, start_addr);
 }
 
-static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t next, start_addr = addr;
 	pmd_t *pmd, *start_pmd;
 
-	start_pmd = pmd = pmd_offset(pud, addr);
+	start_pmd = pmd = stage2_pmd_offset(pud, addr);
 	do {
-		next = kvm_pmd_addr_end(addr, end);
+		next = stage2_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
-			if (kvm_pmd_huge(*pmd)) {
+			if (pmd_thp_or_huge(*pmd)) {
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
@@ -250,57 +241,64 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
 
 				put_page(virt_to_page(pmd));
 			} else {
-				unmap_ptes(kvm, pmd, addr, next);
+				unmap_stage2_ptes(kvm, pmd, addr, next);
 			}
 		}
 	} while (pmd++, addr = next, addr != end);
 
-	if (kvm_pmd_table_empty(kvm, start_pmd))
-		clear_pud_entry(kvm, pud, start_addr);
+	if (stage2_pmd_table_empty(start_pmd))
+		clear_stage2_pud_entry(kv