Merge tag 'kvm-s390-20140422' of git://git.kernel.org/pub/scm/linux/k…

…ernel/git/kvms390/linux into queue

Lazy storage key handling
-------------------------
Linux does not use the ACC and F bits of the storage key. Newer Linux
versions also do not use the storage keys for dirty and reference
tracking. We can optimize the guest handling for those guests for faults
as well as page-in and page-out by simply not caring about the guest
visible storage key. We trap guest storage key instruction to enable
those keys only on demand.

Migration bitmap

Until now s390 never provided a proper dirty bitmap.  Let's provide a
proper migration bitmap for s390. We also change the user dirty tracking
to a fault based mechanism. This makes the host completely independent
from the storage keys. Long term this will allow us to back guest memory
with large pages.

per-VM device attributes
------------------------
To avoid the introduction of new ioctls, let's provide the
attribute semanantic also on the VM-"device".

Userspace controlled CMMA
-------------------------
The CMMA assist is changed from "always on" to "on if requested" via
per-VM device attributes. In addition a callback to reset all usage
states is provided.

Proper guest DAT handling for intercepts
----------------------------------------
While instructions handled by SIE take care of all addressing aspects,
KVM/s390 currently does not care about guest address translation of
intercepts. This worked out fine, because
- the s390 Linux kernel has a 1:1 mapping between kernel virtual<->real
 for all pages up to memory size
- intercepts happen only for a small amount of cases
- all of these intercepts happen to be in the kernel text for current
  distros

Of course we need to be better for other intercepts, kernel modules etc.
We provide the infrastructure and rework all in-kernel intercepts to work
on logical addresses (paging etc) instead of real ones. The code has
been running internally for several months now, so it is time for going
public.

GDB support
-----------
We provide breakpoints, single stepping and watchpoints.

Fixes/Cleanups
--------------
- Improve program check delivery
- Factor out the handling of transactional memory  on program checks
- Use the existing define __LC_PGM_TDB
- Several cleanups in the lowcore structure
- Documentation

NOTES
-----
- All patches touching base s390 are either ACKed or written by the s390
  maintainers
- One base KVM patch "KVM: add kvm_is_error_gpa() helper"
- One patch introduces the notion of VM device attributes

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Conflicts:
	include/uapi/linux/kvm.h

Documentation/virtual/kvm/api.txt

@@ -2314,8 +2314,8 @@ struct kvm_create_device {
 
 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: device ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
+Type: device ioctl, vm ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
@@ -2340,8 +2340,8 @@ struct kvm_device_attr {
 
 4.81 KVM_HAS_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: device ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
+Type: device ioctl, vm ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:

Documentation/virtual/kvm/devices/vm.txt

@@ -0,0 +1,26 @@
+Generic vm interface
+====================================
+
+The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same
+struct kvm_device_attr as other devices, but targets VM-wide settings
+and controls.
+
+The groups and attributes per virtual machine, if any, are architecture
+specific.
+
+1. GROUP: KVM_S390_VM_MEM_CTRL
+Architectures: s390
+
+1.1. ATTRIBUTE: KVM_S390_VM_MEM_CTRL
+Parameters: none
+Returns: -EBUSY if already a vcpus is defined, otherwise 0
+
+Enables CMMA for the virtual machine
+
+1.2. ATTRIBUTE: KVM_S390_VM_CLR_CMMA
+Parameteres: none
+Returns: 0
+
+Clear the CMMA status for all guest pages, so any pages the guest marked
+as unused are again used any may not be reclaimed by the host.

Documentation/virtual/kvm/s390-diag.txt

@@ -78,3 +78,5 @@ DIAGNOSE function code 'X'501 - KVM breakpoint
 
 If the function code specifies 0x501, breakpoint functions may be performed.
 This function code is handled by userspace.
+
+This diagnose function code has no subfunctions and uses no parameters.

arch/s390/include/asm/ctl_reg.h

@@ -57,6 +57,20 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);
 
+union ctlreg0 {
+	unsigned long val;
+	struct {
+#ifdef CONFIG_64BIT
+		unsigned long	   : 32;
+#endif
+		unsigned long	   : 3;
+		unsigned long lap  : 1; /* Low-address-protection control */
+		unsigned long	   : 4;
+		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
+		unsigned long	   : 23;
+	};
+};
+
 #ifdef CONFIG_SMP
 # define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
 # define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)

arch/s390/include/asm/kvm_host.h

@@ -39,9 +39,17 @@ struct sca_entry {
 	__u64	reserved2[2];
 } __attribute__((packed));
 
+union ipte_control {
+	unsigned long val;
+	struct {
+		unsigned long k  : 1;
+		unsigned long kh : 31;
+		unsigned long kg : 32;
+	};
+};
 
 struct sca_block {
-	__u64	ipte_control;
+	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
@@ -85,12 +93,26 @@ struct kvm_s390_sie_block {
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
 #define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
 #define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
-#define ICTL_LPSW 0x00400000
+#define ICTL_PINT	0x20000000
+#define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
 	__u8	icptcode;		/* 0x0050 */
 	__u8	reserved51;		/* 0x0051 */
 	__u16	ihcpu;			/* 0x0052 */
@@ -109,9 +131,21 @@ struct kvm_s390_sie_block {
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
-	__u8	reservedb0[30];		/* 0x00b0 */
-	__u16   iprcc;			/* 0x00ce */
-	__u8	reservedd0[48];		/* 0x00d0 */
+	__u8	reservedb0[28];		/* 0x00b0 */
+	__u16	pgmilc;			/* 0x00cc */
+	__u16	iprcc;			/* 0x00ce */
+	__u32	dxc;			/* 0x00d0 */
+	__u16	mcn;			/* 0x00d4 */
+	__u8	perc;			/* 0x00d6 */
+	__u8	peratmid;		/* 0x00d7 */
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	__u64	tecmc;			/* 0x00e8 */
+	__u8	reservedf0[16];		/* 0x00f0 */
 	__u64	gcr[16];		/* 0x0100 */
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
@@ -146,6 +180,8 @@ struct kvm_vcpu_stat {
 	u32 exit_instruction;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
+	u32 instruction_stctl;
+	u32 instruction_stctg;
 	u32 exit_program_interruption;
 	u32 exit_instr_and_program;
 	u32 deliver_external_call;
@@ -164,6 +200,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_stpx;
 	u32 instruction_stap;
 	u32 instruction_storage_key;
+	u32 instruction_ipte_interlock;
 	u32 instruction_stsch;
 	u32 instruction_chsc;
 	u32 instruction_stsi;
@@ -183,13 +220,58 @@ struct kvm_vcpu_stat {
 	u32 diagnose_9c;
 };
 
-#define PGM_OPERATION            0x01
-#define PGM_PRIVILEGED_OP	 0x02
-#define PGM_EXECUTE              0x03
-#define PGM_PROTECTION           0x04
-#define PGM_ADDRESSING           0x05
-#define PGM_SPECIFICATION        0x06
-#define PGM_DATA                 0x07
+#define PGM_OPERATION			0x01
+#define PGM_PRIVILEGED_OP		0x02
+#define PGM_EXECUTE			0x03
+#define PGM_PROTECTION			0x04
+#define PGM_ADDRESSING			0x05
+#define PGM_SPECIFICATION		0x06
+#define PGM_DATA			0x07
+#define PGM_FIXED_POINT_OVERFLOW	0x08
+#define PGM_FIXED_POINT_DIVIDE		0x09
+#define PGM_DECIMAL_OVERFLOW		0x0a
+#define PGM_DECIMAL_DIVIDE		0x0b
+#define PGM_HFP_EXPONENT_OVERFLOW	0x0c
+#define PGM_HFP_EXPONENT_UNDERFLOW	0x0d
+#define PGM_HFP_SIGNIFICANCE		0x0e
+#define PGM_HFP_DIVIDE			0x0f
+#define PGM_SEGMENT_TRANSLATION		0x10
+#define PGM_PAGE_TRANSLATION		0x11
+#define PGM_TRANSLATION_SPEC		0x12
+#define PGM_SPECIAL_OPERATION		0x13
+#define PGM_OPERAND			0x15
+#define PGM_TRACE_TABEL			0x16
+#define PGM_SPACE_SWITCH		0x1c
+#define PGM_HFP_SQUARE_ROOT		0x1d
+#define PGM_PC_TRANSLATION_SPEC		0x1f
+#define PGM_AFX_TRANSLATION		0x20
+#define PGM_ASX_TRANSLATION		0x21
+#define PGM_LX_TRANSLATION		0x22
+#define PGM_EX_TRANSLATION		0x23
+#define PGM_PRIMARY_AUTHORITY		0x24
+#define PGM_SECONDARY_AUTHORITY		0x25
+#define PGM_LFX_TRANSLATION		0x26
+#define PGM_LSX_TRANSLATION		0x27
+#define PGM_ALET_SPECIFICATION		0x28
+#define PGM_ALEN_TRANSLATION		0x29
+#define PGM_ALE_SEQUENCE		0x2a
+#define PGM_ASTE_VALIDITY		0x2b
+#define PGM_ASTE_SEQUENCE		0x2c
+#define PGM_EXTENDED_AUTHORITY		0x2d
+#define PGM_LSTE_SEQUENCE		0x2e
+#define PGM_ASTE_INSTANCE		0x2f
+#define PGM_STACK_FULL			0x30
+#define PGM_STACK_EMPTY			0x31
+#define PGM_STACK_SPECIFICATION		0x32
+#define PGM_STACK_TYPE			0x33
+#define PGM_STACK_OPERATION		0x34
+#define PGM_ASCE_TYPE			0x38
+#define PGM_REGION_FIRST_TRANS		0x39
+#define PGM_REGION_SECOND_TRANS		0x3a
+#define PGM_REGION_THIRD_TRANS		0x3b
+#define PGM_MONITOR			0x40
+#define PGM_PER				0x80
+#define PGM_CRYPTO_OPERATION		0x119
 
 struct kvm_s390_interrupt_info {
 	struct list_head list;
@@ -229,6 +311,45 @@ struct kvm_s390_float_interrupt {
 	unsigned int irq_count;
 };
 
+struct kvm_hw_wp_info_arch {
+	unsigned long addr;
+	unsigned long phys_addr;
+	int len;
+	char *old_data;
+};
+
+struct kvm_hw_bp_info_arch {
+	unsigned long addr;
+	int len;
+};
+
+/*
+ * Only the upper 16 bits of kvm_guest_debug->control are arch specific.
+ * Further KVM_GUESTDBG flags which an be used from userspace can be found in
+ * arch/s390/include/uapi/asm/kvm.h
+ */
+#define KVM_GUESTDBG_EXIT_PENDING 0x10000000
+
+#define guestdbg_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)
+#define guestdbg_sstep_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+#define guestdbg_hw_bp_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+#define guestdbg_exit_pending(vcpu) (guestdbg_enabled(vcpu) && \
+		(vcpu->guest_debug & KVM_GUESTDBG_EXIT_PENDING))
+
+struct kvm_guestdbg_info_arch {
+	unsigned long cr0;
+	unsigned long cr9;
+	unsigned long cr10;
+	unsigned long cr11;
+	struct kvm_hw_bp_info_arch *hw_bp_info;
+	struct kvm_hw_wp_info_arch *hw_wp_info;
+	int nr_hw_bp;
+	int nr_hw_wp;
+	unsigned long last_bp;
+};
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
@@ -238,11 +359,13 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
+	struct kvm_s390_pgm_info pgm;
 	union  {
 		struct cpuid	cpu_id;
 		u64		stidp_data;
 	};
 	struct gmap *gmap;
+	struct kvm_guestdbg_info_arch guestdbg;
 #define KVM_S390_PFAULT_TOKEN_INVALID	(-1UL)
 	unsigned long pfault_token;
 	unsigned long pfault_select;
@@ -285,7 +408,9 @@ struct kvm_arch{
 	struct gmap *gmap;
 	int css_support;
 	int use_irqchip;
+	int use_cmma;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
+	wait_queue_head_t ipte_wq;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)

arch/s390/include/asm/lowcore.h

@@ -56,13 +56,14 @@ struct _lowcore {
 	__u16	pgm_code;			/* 0x008e */
 	__u32	trans_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u32	per_address;			/* 0x0098 */
 	__u32	monitor_code;			/* 0x009c */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00b8-0x00a4];	/* 0x00a4 */
 	__u16	subchannel_id;			/* 0x00b8 */
 	__u16	subchannel_nr;			/* 0x00ba */
@@ -196,12 +197,13 @@ struct _lowcore {
 	__u16	pgm_code;			/* 0x008e */
 	__u32	data_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u64	per_address;			/* 0x0098 */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00a8-0x00a4];	/* 0x00a4 */
 	__u64	trans_exc_code;			/* 0x00a8 */
 	__u64	monitor_code;			/* 0x00b0 */

arch/s390/include/asm/mmu.h

@@ -16,6 +16,8 @@ typedef struct {
 	unsigned long vdso_base;
 	/* The mmu context has extended page tables. */
 	unsigned int has_pgste:1;
+	/* The mmu context uses storage keys. */
+	unsigned int use_skey:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						      \

arch/s390/include/asm/mmu_context.h

@@ -23,6 +23,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
 	mm->context.has_pgste = 0;
+	mm->context.use_skey = 0;
 	mm->context.asce_limit = STACK_TOP_MAX;
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;

arch/s390/include/asm/pgalloc.h

@@ -22,7 +22,8 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
 
-void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
+			    bool init_skey);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq);