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

Pull KVM updates from Paolo Bonzini:
 "Fixes and features for 3.18.

  Apart from the usual cleanups, here is the summary of new features:

   - s390 moves closer towards host large page support

   - PowerPC has improved support for debugging (both inside the guest
     and via gdbstub) and support for e6500 processors

   - ARM/ARM64 support read-only memory (which is necessary to put
     firmware in emulated NOR flash)

   - x86 has the usual emulator fixes and nested virtualization
     improvements (including improved Windows support on Intel and
     Jailhouse hypervisor support on AMD), adaptive PLE which helps
     overcommitting of huge guests.  Also included are some patches that
     make KVM more friendly to memory hot-unplug, and fixes for rare
     caching bugs.

  Two patches have trivial mm/ parts that were acked by Rik and Andrew.

  Note: I will soon switch to a subkey for signing purposes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (157 commits)
  kvm: do not handle APIC access page if in-kernel irqchip is not in use
  KVM: s390: count vcpu wakeups in stat.halt_wakeup
  KVM: s390/facilities: allow TOD-CLOCK steering facility bit
  KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode
  arm/arm64: KVM: Report correct FSC for unsupported fault types
  arm/arm64: KVM: Fix VTTBR_BADDR_MASK and pgd alloc
  kvm: Fix kvm_get_page_retry_io __gup retval check
  arm/arm64: KVM: Fix set_clear_sgi_pend_reg offset
  kvm: x86: Unpin and remove kvm_arch->apic_access_page
  kvm: vmx: Implement set_apic_access_page_addr
  kvm: x86: Add request bit to reload APIC access page address
  kvm: Add arch specific mmu notifier for page invalidation
  kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static
  kvm: Fix page ageing bugs
  kvm/x86/mmu: Pass gfn and level to rmapp callback.
  x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only
  kvm: x86: use macros to compute bank MSRs
  KVM: x86: Remove debug assertion of non-PAE reserved bits
  kvm: don't take vcpu mutex for obviously invalid vcpu ioctls
  kvm: Faults which trigger IO release the mmap_sem
  ...

5 files changed, 75 insertions, 51 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 773bef7614d8..2175f911a73a 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -13,8 +13,11 @@
 
 #ifndef ASM_KVM_HOST_H
 #define ASM_KVM_HOST_H
+
+#include <linux/types.h>
 #include <linux/hrtimer.h>
 #include <linux/interrupt.h>
+#include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
 #include <asm/debug.h>
@@ -154,7 +157,9 @@ struct kvm_s390_sie_block {
 	__u8	armid;			/* 0x00e3 */
 	__u8	reservede4[4];		/* 0x00e4 */
 	__u64	tecmc;			/* 0x00e8 */
-	__u8	reservedf0[16];		/* 0x00f0 */
+	__u8	reservedf0[12];		/* 0x00f0 */
+#define CRYCB_FORMAT1 0x00000001
+	__u32	crycbd;			/* 0x00fc */
 	__u64	gcr[16];		/* 0x0100 */
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
@@ -187,6 +192,7 @@ struct kvm_vcpu_stat {
 	u32 exit_stop_request;
 	u32 exit_validity;
 	u32 exit_instruction;
+	u32 halt_wakeup;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
 	u32 instruction_stctl;
@@ -407,6 +413,15 @@ struct s390_io_adapter {
 #define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8)
 #define MAX_S390_ADAPTER_MAPS 256
 
+struct kvm_s390_crypto {
+	struct kvm_s390_crypto_cb *crycb;
+	__u32 crycbd;
+};
+
+struct kvm_s390_crypto_cb {
+	__u8    reserved00[128];                /* 0x0000 */
+};
+
 struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
@@ -420,6 +435,7 @@ struct kvm_arch{
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	spinlock_t start_stop_lock;
+	struct kvm_s390_crypto crypto;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)
@@ -431,8 +447,6 @@ static inline bool kvm_is_error_hva(unsigned long addr)
 }
 
 #define ASYNC_PF_PER_VCPU	64
-struct kvm_vcpu;
-struct kvm_async_pf;
 struct kvm_arch_async_pf {
 	unsigned long pfault_token;
 };
@@ -450,4 +464,18 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
+
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_check_processor_compat(void *rtn) {}
+static inline void kvm_arch_exit(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_free_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *slot) {}
+
 #endif
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 9e18a61d3df3..d39a31c3cdf2 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -18,9 +18,9 @@
 unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
 
-unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
+unsigned long *page_table_alloc(struct mm_struct *);
 void page_table_free(struct mm_struct *, unsigned long *);
-void page_table_free_rcu(struct mmu_gather *, unsigned long *);
+void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
 
 void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
 			    bool init_skey);
@@ -145,8 +145,8 @@ static inline void pmd_populate(struct mm_struct *mm,
 /*
  * page table entry allocation/free routines.
  */
-#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))
-#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))
+#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
+#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
 
 #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
 #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5efb2fe186e7..b7054356cc98 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
+#include <linux/radix-tree.h>
 #include <asm/bug.h>
 #include <asm/page.h>
 
@@ -789,82 +790,67 @@ static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 
 /**
  * struct gmap_struct - guest address space
+ * @crst_list: list of all crst tables used in the guest address space
  * @mm: pointer to the parent mm_struct
+ * @guest_to_host: radix tree with guest to host address translation
+ * @host_to_guest: radix tree with pointer to segment table entries
+ * @guest_table_lock: spinlock to protect all entries in the guest page table
  * @table: pointer to the page directory
  * @asce: address space control element for gmap page table
- * @crst_list: list of all crst tables used in the guest address space
  * @pfault_enabled: defines if pfaults are applicable for the guest
  */
 struct gmap {
 	struct list_head list;
+	struct list_head crst_list;
 	struct mm_struct *mm;
+	struct radix_tree_root guest_to_host;
+	struct radix_tree_root host_to_guest;
+	spinlock_t guest_table_lock;
 	unsigned long *table;
 	unsigned long asce;
+	unsigned long asce_end;
 	void *private;
-	struct list_head crst_list;
 	bool pfault_enabled;
 };
 
 /**
- * struct gmap_rmap - reverse mapping for segment table entries
- * @gmap: pointer to the gmap_struct
- * @entry: pointer to a segment table entry
- * @vmaddr: virtual address in the guest address space
- */
-struct gmap_rmap {
-	struct list_head list;
-	struct gmap *gmap;
-	unsigned long *entry;
-	unsigned long vmaddr;
-};
-
-/**
- * struct gmap_pgtable - gmap information attached to a page table
- * @vmaddr: address of the 1MB segment in the process virtual memory
- * @mapper: list of segment table entries mapping a page table
- */
-struct gmap_pgtable {
-	unsigned long vmaddr;
-	struct list_head mapper;
-};
-
-/**
  * struct gmap_notifier - notify function block for page invalidation
  * @notifier_call: address of callback function
  */
 struct gmap_notifier {
 	struct list_head list;
-	void (*notifier_call)(struct gmap *gmap, unsigned long address);
+	void (*notifier_call)(struct gmap *gmap, unsigned long gaddr);
 };
 
-struct gmap *gmap_alloc(struct mm_struct *mm);
+struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit);
 void gmap_free(struct gmap *gmap);
 void gmap_enable(struct gmap *gmap);
 void gmap_disable(struct gmap *gmap);
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
 		     unsigned long to, unsigned long len);
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
-unsigned long __gmap_translate(unsigned long address, struct gmap *);
-unsigned long gmap_translate(unsigned long address, struct gmap *);
-unsigned long __gmap_fault(unsigned long address, struct gmap *);
-unsigned long gmap_fault(unsigned long address, struct gmap *);
-void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
-void __gmap_zap(unsigned long address, struct gmap *);
+unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
+unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
+int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
+int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
+void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
+void __gmap_zap(struct gmap *, unsigned long gaddr);
 bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *);
 
 
 void gmap_register_ipte_notifier(struct gmap_notifier *);
 void gmap_unregister_ipte_notifier(struct gmap_notifier *);
 int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
-void gmap_do_ipte_notify(struct mm_struct *, pte_t *);
+void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *);
 
 static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
+					unsigned long addr,
 					pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
 	if (pgste_val(pgste) & PGSTE_IN_BIT) {
 		pgste_val(pgste) &= ~PGSTE_IN_BIT;
-		gmap_do_ipte_notify(mm, ptep);
+		gmap_do_ipte_notify(mm, addr, ptep);
 	}
 #endif
 	return pgste;
@@ -1110,7 +1096,7 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
 	pgste_val(pgste) &= ~PGSTE_UC_BIT;
 	pte = *ptep;
 	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
-		pgste = pgste_ipte_notify(mm, ptep, pgste);
+		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
 		__ptep_ipte(addr, ptep);
 		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
 			pte_val(pte) |= _PAGE_PROTECT;
@@ -1132,7 +1118,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
+		pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
 	}
 
 	oldpte = pte = *ptep;
@@ -1179,7 +1165,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, ptep, pgste);
+		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
@@ -1203,7 +1189,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste_ipte_notify(mm, ptep, pgste);
+		pgste_ipte_notify(mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
@@ -1240,7 +1226,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
+		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
@@ -1274,7 +1260,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 
 	if (!full && mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, ptep, pgste);
+		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
@@ -1299,7 +1285,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
 	if (pte_write(pte)) {
 		if (mm_has_pgste(mm)) {
 			pgste = pgste_get_lock(ptep);
-			pgste = pgste_ipte_notify(mm, ptep, pgste);
+			pgste = pgste_ipte_notify(mm, address, ptep, pgste);
 		}
 
 		ptep_flush_lazy(mm, address, ptep);
@@ -1325,7 +1311,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 		return 0;
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
+		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
 	}
 
 	ptep_flush_direct(vma->vm_mm, address, ptep);
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index a25f09fbaf36..572c59949004 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -105,7 +105,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				unsigned long address)
 {
-	page_table_free_rcu(tlb, (unsigned long *) pte);
+	page_table_free_rcu(tlb, (unsigned long *) pte, address);
 }
 
 /*
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 0fc26430a1e5..48eda3ab4944 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -111,12 +111,22 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_GPRS   (1UL << 1)
 #define KVM_SYNC_ACRS   (1UL << 2)
 #define KVM_SYNC_CRS    (1UL << 3)
+#define KVM_SYNC_ARCH0  (1UL << 4)
+#define KVM_SYNC_PFAULT (1UL << 5)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
 	__u64 gprs[16];	/* general purpose registers */
 	__u32 acrs[16];	/* access registers */
 	__u64 crs[16];	/* control registers */
+	__u64 todpr;	/* tod programmable register [ARCH0] */
+	__u64 cputm;	/* cpu timer [ARCH0] */
+	__u64 ckc;	/* clock comparator [ARCH0] */
+	__u64 pp;	/* program parameter [ARCH0] */
+	__u64 gbea;	/* guest breaking-event address [ARCH0] */
+	__u64 pft;	/* pfault token [PFAULT] */
+	__u64 pfs;	/* pfault select [PFAULT] */
+	__u64 pfc;	/* pfault compare [PFAULT] */
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)