summaryrefslogtreecommitdiff
path: root/arch/s390
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/include/asm/bitops.h5
-rw-r--r--arch/s390/include/asm/css_chars.h4
-rw-r--r--arch/s390/include/asm/kvm_host.h126
-rw-r--r--arch/s390/include/asm/sclp.h1
-rw-r--r--arch/s390/kvm/Kconfig1
-rw-r--r--arch/s390/kvm/diag.c1
-rw-r--r--arch/s390/kvm/interrupt.c288
-rw-r--r--arch/s390/kvm/kvm-s390.c209
-rw-r--r--arch/s390/kvm/kvm-s390.h22
-rw-r--r--arch/s390/kvm/priv.c38
-rw-r--r--arch/s390/kvm/sigp.c18
-rw-r--r--arch/s390/kvm/vsie.c91
-rw-r--r--arch/s390/mm/gmap.c44
13 files changed, 608 insertions, 240 deletions
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 31e400c1a1f3..86e5b2fdee3c 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -261,6 +261,11 @@ static inline void clear_bit_inv(unsigned long nr, volatile unsigned long *ptr)
return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
+static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr)
+{
+ return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
+}
+
static inline void __set_bit_inv(unsigned long nr, volatile unsigned long *ptr)
{
return __set_bit(nr ^ (BITS_PER_LONG - 1), ptr);
diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h
index a478eb61aaf7..fb56fa3283a2 100644
--- a/arch/s390/include/asm/css_chars.h
+++ b/arch/s390/include/asm/css_chars.h
@@ -20,7 +20,9 @@ struct css_general_char {
u32 aif_tdd : 1; /* bit 56 */
u32 : 1;
u32 qebsm : 1; /* bit 58 */
- u32 : 8;
+ u32 : 2;
+ u32 aiv : 1; /* bit 61 */
+ u32 : 5;
u32 aif_osa : 1; /* bit 67 */
u32 : 12;
u32 eadm_rf : 1; /* bit 80 */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index c1b0a9ac1dc8..afb0f08b8021 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -2,7 +2,7 @@
/*
* definition for kernel virtual machines on s390
*
- * Copyright IBM Corp. 2008, 2009
+ * Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
@@ -183,6 +183,7 @@ struct kvm_s390_sie_block {
#define ECA_IB 0x40000000
#define ECA_SIGPI 0x10000000
#define ECA_MVPGI 0x01000000
+#define ECA_AIV 0x00200000
#define ECA_VX 0x00020000
#define ECA_PROTEXCI 0x00002000
#define ECA_SII 0x00000001
@@ -228,7 +229,9 @@ struct kvm_s390_sie_block {
__u8 epdx; /* 0x0069 */
__u8 reserved6a[2]; /* 0x006a */
__u32 todpr; /* 0x006c */
- __u8 reserved70[16]; /* 0x0070 */
+#define GISA_FORMAT1 0x00000001
+ __u32 gd; /* 0x0070 */
+ __u8 reserved74[12]; /* 0x0074 */
__u64 mso; /* 0x0080 */
__u64 msl; /* 0x0088 */
psw_t gpsw; /* 0x0090 */
@@ -317,18 +320,30 @@ struct kvm_vcpu_stat {
u64 deliver_program_int;
u64 deliver_io_int;
u64 exit_wait_state;
+ u64 instruction_epsw;
+ u64 instruction_gs;
+ u64 instruction_io_other;
+ u64 instruction_lpsw;
+ u64 instruction_lpswe;
u64 instruction_pfmf;
+ u64 instruction_ptff;
+ u64 instruction_sck;
+ u64 instruction_sckpf;
u64 instruction_stidp;
u64 instruction_spx;
u64 instruction_stpx;
u64 instruction_stap;
- u64 instruction_storage_key;
+ u64 instruction_iske;
+ u64 instruction_ri;
+ u64 instruction_rrbe;
+ u64 instruction_sske;
u64 instruction_ipte_interlock;
- u64 instruction_stsch;
- u64 instruction_chsc;
u64 instruction_stsi;
u64 instruction_stfl;
+ u64 instruction_tb;
+ u64 instruction_tpi;
u64 instruction_tprot;
+ u64 instruction_tsch;
u64 instruction_sie;
u64 instruction_essa;
u64 instruction_sthyi;
@@ -354,6 +369,7 @@ struct kvm_vcpu_stat {
u64 diagnose_258;
u64 diagnose_308;
u64 diagnose_500;
+ u64 diagnose_other;
};
#define PGM_OPERATION 0x01
@@ -410,35 +426,35 @@ struct kvm_vcpu_stat {
#define PGM_PER 0x80
#define PGM_CRYPTO_OPERATION 0x119
-/* irq types in order of priority */
+/* irq types in ascend order of priorities */
enum irq_types {
- IRQ_PEND_MCHK_EX = 0,
- IRQ_PEND_SVC,
- IRQ_PEND_PROG,
- IRQ_PEND_MCHK_REP,
- IRQ_PEND_EXT_IRQ_KEY,
- IRQ_PEND_EXT_MALFUNC,
- IRQ_PEND_EXT_EMERGENCY,
- IRQ_PEND_EXT_EXTERNAL,
- IRQ_PEND_EXT_CLOCK_COMP,
- IRQ_PEND_EXT_CPU_TIMER,
- IRQ_PEND_EXT_TIMING,
- IRQ_PEND_EXT_SERVICE,
- IRQ_PEND_EXT_HOST,
- IRQ_PEND_PFAULT_INIT,
- IRQ_PEND_PFAULT_DONE,
- IRQ_PEND_VIRTIO,
- IRQ_PEND_IO_ISC_0,
- IRQ_PEND_IO_ISC_1,
- IRQ_PEND_IO_ISC_2,
- IRQ_PEND_IO_ISC_3,
- IRQ_PEND_IO_ISC_4,
- IRQ_PEND_IO_ISC_5,
- IRQ_PEND_IO_ISC_6,
- IRQ_PEND_IO_ISC_7,
- IRQ_PEND_SIGP_STOP,
+ IRQ_PEND_SET_PREFIX = 0,
IRQ_PEND_RESTART,
- IRQ_PEND_SET_PREFIX,
+ IRQ_PEND_SIGP_STOP,
+ IRQ_PEND_IO_ISC_7,
+ IRQ_PEND_IO_ISC_6,
+ IRQ_PEND_IO_ISC_5,
+ IRQ_PEND_IO_ISC_4,
+ IRQ_PEND_IO_ISC_3,
+ IRQ_PEND_IO_ISC_2,
+ IRQ_PEND_IO_ISC_1,
+ IRQ_PEND_IO_ISC_0,
+ IRQ_PEND_VIRTIO,
+ IRQ_PEND_PFAULT_DONE,
+ IRQ_PEND_PFAULT_INIT,
+ IRQ_PEND_EXT_HOST,
+ IRQ_PEND_EXT_SERVICE,
+ IRQ_PEND_EXT_TIMING,
+ IRQ_PEND_EXT_CPU_TIMER,
+ IRQ_PEND_EXT_CLOCK_COMP,
+ IRQ_PEND_EXT_EXTERNAL,
+ IRQ_PEND_EXT_EMERGENCY,
+ IRQ_PEND_EXT_MALFUNC,
+ IRQ_PEND_EXT_IRQ_KEY,
+ IRQ_PEND_MCHK_REP,
+ IRQ_PEND_PROG,
+ IRQ_PEND_SVC,
+ IRQ_PEND_MCHK_EX,
IRQ_PEND_COUNT
};
@@ -516,9 +532,6 @@ struct kvm_s390_irq_payload {
struct kvm_s390_local_interrupt {
spinlock_t lock;
- struct kvm_s390_float_interrupt *float_int;
- struct swait_queue_head *wq;
- atomic_t *cpuflags;
DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
struct kvm_s390_irq_payload irq;
unsigned long pending_irqs;
@@ -707,14 +720,50 @@ struct kvm_s390_crypto_cb {
struct kvm_s390_apcb1 apcb1; /* 0x0080 */
};
+struct kvm_s390_gisa {
+ union {
+ struct { /* common to all formats */
+ u32 next_alert;
+ u8 ipm;
+ u8 reserved01[2];
+ u8 iam;
+ };
+ struct { /* format 0 */
+ u32 next_alert;
+ u8 ipm;
+ u8 reserved01;
+ u8 : 6;
+ u8 g : 1;
+ u8 c : 1;
+ u8 iam;
+ u8 reserved02[4];
+ u32 airq_count;
+ } g0;
+ struct { /* format 1 */
+ u32 next_alert;
+ u8 ipm;
+ u8 simm;
+ u8 nimm;
+ u8 iam;
+ u8 aism[8];
+ u8 : 6;
+ u8 g : 1;
+ u8 c : 1;
+ u8 reserved03[11];
+ u32 airq_count;
+ } g1;
+ };
+};
+
/*
- * sie_page2 has to be allocated as DMA because fac_list and crycb need
- * 31bit addresses in the sie control block.
+ * sie_page2 has to be allocated as DMA because fac_list, crycb and
+ * gisa need 31bit addresses in the sie control block.
*/
struct sie_page2 {
__u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */
struct kvm_s390_crypto_cb crycb; /* 0x0800 */
- u8 reserved900[0x1000 - 0x900]; /* 0x0900 */
+ struct kvm_s390_gisa gisa; /* 0x0900 */
+ u8 reserved920[0x1000 - 0x920]; /* 0x0920 */
};
struct kvm_s390_vsie {
@@ -761,6 +810,7 @@ struct kvm_arch{
struct kvm_s390_migration_state *migration_state;
/* subset of available cpu features enabled by user space */
DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
+ struct kvm_s390_gisa *gisa;
};
#define KVM_HVA_ERR_BAD (-1UL)
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index d3c1a8a2e3ad..3cae9168f63c 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -77,6 +77,7 @@ struct sclp_info {
unsigned char has_ibs : 1;
unsigned char has_skey : 1;
unsigned char has_kss : 1;
+ unsigned char has_gisaf : 1;
unsigned int ibc;
unsigned int mtid;
unsigned int mtid_cp;
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 9a4594e0a1ff..a3dbd459cce9 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -23,6 +23,7 @@ config KVM
select PREEMPT_NOTIFIERS
select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select HAVE_KVM_VCPU_ASYNC_IOCTL
select HAVE_KVM_EVENTFD
select KVM_ASYNC_PF
select KVM_ASYNC_PF_SYNC
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 89aa114a2cba..45634b3d2e0a 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -257,6 +257,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
case 0x500:
return __diag_virtio_hypercall(vcpu);
default:
+ vcpu->stat.diagnose_other++;
return -EOPNOTSUPP;
}
}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 024ad8bcc516..aabf46f5f883 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -36,7 +36,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
{
int c, scn;
- if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+ if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND))
return 0;
BUG_ON(!kvm_s390_use_sca_entries());
@@ -101,18 +101,17 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
/* another external call is pending */
return -EBUSY;
}
- atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
return 0;
}
static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
{
- struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc, expect;
if (!kvm_s390_use_sca_entries())
return;
- atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
@@ -190,8 +189,8 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
static inline int is_ioirq(unsigned long irq_type)
{
- return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
- (irq_type <= IRQ_PEND_IO_ISC_7));
+ return ((irq_type >= IRQ_PEND_IO_ISC_7) &&
+ (irq_type <= IRQ_PEND_IO_ISC_0));
}
static uint64_t isc_to_isc_bits(int isc)
@@ -199,25 +198,59 @@ static uint64_t isc_to_isc_bits(int isc)
return (0x80 >> isc) << 24;
}
+static inline u32 isc_to_int_word(u8 isc)
+{
+ return ((u32)isc << 27) | 0x80000000;
+}
+
static inline u8 int_word_to_isc(u32 int_word)
{
return (int_word & 0x38000000) >> 27;
}
+/*
+ * To use atomic bitmap functions, we have to provide a bitmap address
+ * that is u64 aligned. However, the ipm might be u32 aligned.
+ * Therefore, we logically start the bitmap at the very beginning of the
+ * struct and fixup the bit number.
+ */
+#define IPM_BIT_OFFSET (offsetof(struct kvm_s390_gisa, ipm) * BITS_PER_BYTE)
+
+static inline void kvm_s390_gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline u8 kvm_s390_gisa_get_ipm(struct kvm_s390_gisa *gisa)
+{
+ return READ_ONCE(gisa->ipm);
+}
+
+static inline void kvm_s390_gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
{
return vcpu->kvm->arch.float_int.pending_irqs |
- vcpu->arch.local_int.pending_irqs;
+ vcpu->arch.local_int.pending_irqs |
+ kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7;
}
static inline int isc_to_irq_type(unsigned long isc)
{
- return IRQ_PEND_IO_ISC_0 + isc;
+ return IRQ_PEND_IO_ISC_0 - isc;
}
static inline int irq_type_to_isc(unsigned long irq_type)
{
- return irq_type - IRQ_PEND_IO_ISC_0;
+ return IRQ_PEND_IO_ISC_0 - irq_type;
}
static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
@@ -278,20 +311,20 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
- atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
- set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
+ set_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
- atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
- clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
+ clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
}
static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
{
- atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
- &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IO_INT | CPUSTAT_EXT_INT |
+ CPUSTAT_STOP_INT);
vcpu->arch.sie_block->lctl = 0x0000;
vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
@@ -302,17 +335,12 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
}
}
-static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
-{
- atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
-}
-
static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
{
if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
return;
else if (psw_ioint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_IO_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR6;
}
@@ -322,7 +350,7 @@ static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
return;
if (psw_extint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR0;
}
@@ -340,7 +368,7 @@ static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
if (kvm_s390_is_stop_irq_pending(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
}
/* Set interception request for non-deliverable interrupts */
@@ -897,18 +925,38 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
return rc ? -EFAULT : 0;
}
+static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io)
+{
+ int rc;
+
+ rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID);
+ rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR);
+ rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM);
+ rc |= put_guest_lc(vcpu, io->io_int_word, (u32 *)__LC_IO_INT_WORD);
+ rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ return rc ? -EFAULT : 0;
+}
+
static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
unsigned long irq_type)
{
struct list_head *isc_list;
struct kvm_s390_float_interrupt *fi;
struct kvm_s390_interrupt_info *inti = NULL;
+ struct kvm_s390_io_info io;
+ u32 isc;
int rc = 0;
fi = &vcpu->kvm->arch.float_int;
spin_lock(&fi->lock);
- isc_list = &fi->lists[irq_type_to_isc(irq_type)];
+ isc = irq_type_to_isc(irq_type);
+ isc_list = &fi->lists[isc];
inti = list_first_entry_or_null(isc_list,
struct kvm_s390_interrupt_info,
list);
@@ -936,24 +984,31 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
spin_unlock(&fi->lock);
if (inti) {
- rc = put_guest_lc(vcpu, inti->io.subchannel_id,
- (u16 *)__LC_SUBCHANNEL_ID);
- rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
- (u16 *)__LC_SUBCHANNEL_NR);
- rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
- (u32 *)__LC_IO_INT_PARM);
- rc |= put_guest_lc(vcpu, inti->io.io_int_word,
- (u32 *)__LC_IO_INT_WORD);
- rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
+ rc = __do_deliver_io(vcpu, &(inti->io));
kfree(inti);
+ goto out;
}
- return rc ? -EFAULT : 0;
+ if (vcpu->kvm->arch.gisa &&
+ kvm_s390_gisa_tac_ipm_gisc(vcpu->kvm->arch.gisa, isc)) {
+ /*
+ * in case an adapter interrupt was not delivered
+ * in SIE context KVM will handle the delivery
+ */
+ VCPU_EVENT(vcpu, 4, "%s isc %u", "deliver: I/O (AI/gisa)", isc);
+ memset(&io, 0, sizeof(io));
+ io.io_int_word = isc_to_int_word(isc);
+ vcpu->stat.deliver_io_int++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_INT_IO(1, 0, 0, 0),
+ ((__u32)io.subchannel_id << 16) |
+ io.subchannel_nr,
+ ((__u64)io.io_int_parm << 32) |
+ io.io_int_word);
+ rc = __do_deliver_io(vcpu, &io);
+ }
+out:
+ return rc;
}
typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
@@ -1155,8 +1210,8 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
while ((irqs = deliverable_irqs(vcpu)) && !rc) {
- /* bits are in the order of interrupt priority */
- irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
+ /* bits are in the reverse order of interrupt priority */
+ irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT);
if (is_ioirq(irq_type)) {
rc = __deliver_io(vcpu, irq_type);
} else {
@@ -1228,7 +1283,7 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
li->irq.ext = irq->u.ext;
set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
@@ -1253,7 +1308,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
return -EBUSY;
*extcall = irq->u.extcall;
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
@@ -1297,7 +1352,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs))
return -EBUSY;
stop->flags = irq->u.stop.flags;
- __set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
return 0;
}
@@ -1329,7 +1384,7 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
@@ -1373,7 +1428,7 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
0, 0);
set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
@@ -1386,7 +1441,7 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
0, 0);
set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
@@ -1416,20 +1471,86 @@ static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm,
return NULL;
}
+static struct kvm_s390_interrupt_info *get_top_io_int(struct kvm *kvm,
+ u64 isc_mask, u32 schid)
+{
+ struct kvm_s390_interrupt_info *inti = NULL;
+ int isc;
+
+ for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
+ if (isc_mask & isc_to_isc_bits(isc))
+ inti = get_io_int(kvm, isc, schid);
+ }
+ return inti;
+}
+
+static int get_top_gisa_isc(struct kvm *kvm, u64 isc_mask, u32 schid)
+{
+ unsigned long active_mask;
+ int isc;
+
+ if (schid)
+ goto out;
+ if (!kvm->arch.gisa)
+ goto out;
+
+ active_mask = (isc_mask & kvm_s390_gisa_get_ipm(kvm->arch.gisa) << 24) << 32;
+ while (active_mask) {
+ isc = __fls(active_mask) ^ (BITS_PER_LONG - 1);
+ if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, isc))
+ return isc;
+ clear_bit_inv(isc, &active_mask);
+ }
+out:
+ return -EINVAL;
+}
+
/*
* Dequeue and return an I/O interrupt matching any of the interruption
* subclasses as designated by the isc mask in cr6 and the schid (if != 0).
+ * Take into account the interrupts pending in the interrupt list and in GISA.
+ *
+ * Note that for a guest that does not enable I/O interrupts
+ * but relies on TPI, a flood of classic interrupts may starve
+ * out adapter interrupts on the same isc. Linux does not do
+ * that, and it is possible to work around the issue by configuring
+ * different iscs for classic and adapter interrupts in the guest,
+ * but we may want to revisit this in the future.
*/
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
u64 isc_mask, u32 schid)
{
- struct kvm_s390_interrupt_info *inti = NULL;
+ struct kvm_s390_interrupt_info *inti, *tmp_inti;
int isc;
- for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
- if (isc_mask & isc_to_isc_bits(isc))
- inti = get_io_int(kvm, isc, schid);
+ inti = get_top_io_int(kvm, isc_mask, schid);
+
+ isc = get_top_gisa_isc(kvm, isc_mask, schid);
+ if (isc < 0)
+ /* no AI in GISA */
+ goto out;
+
+ if (!inti)
+ /* AI in GISA but no classical IO int */
+ goto gisa_out;
+
+ /* both types of interrupts present */
+ if (int_word_to_isc(inti->io.io_int_word) <= isc) {
+ /* classical IO int with higher priority */
+ kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ goto out;
}
+gisa_out:
+ tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (tmp_inti) {
+ tmp_inti->type = KVM_S390_INT_IO(1, 0, 0, 0);
+ tmp_inti->io.io_int_word = isc_to_int_word(isc);
+ if (inti)
+ kvm_s390_reinject_io_int(kvm, inti);
+ inti = tmp_inti;
+ } else
+ kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+out:
return inti;
}
@@ -1517,6 +1638,15 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
struct list_head *list;
int isc;
+ isc = int_word_to_isc(inti->io.io_int_word);
+
+ if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) {
+ VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc);
+ kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ kfree(inti);
+ return 0;
+ }
+
fi = &kvm->arch.float_int;
spin_lock(&fi->lock);
if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) {
@@ -1532,7 +1662,6 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
inti->io.subchannel_id >> 8,
inti->io.subchannel_id >> 1 & 0x3,
inti->io.subchannel_nr);
- isc = int_word_to_isc(inti->io.io_int_word);
list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
list_add_tail(&inti->list, list);
set_bit(isc_to_irq_type(isc), &fi->pending_irqs);
@@ -1546,7 +1675,6 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
static void __floating_irq_kick(struct kvm *kvm, u64 type)
{
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
- struct kvm_s390_local_interrupt *li;
struct kvm_vcpu *dst_vcpu;
int sigcpu, online_vcpus, nr_tries = 0;
@@ -1568,20 +1696,17 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
/* make the VCPU drop out of the SIE, or wake it up if sleeping */
- li = &dst_vcpu->arch.local_int;
- spin_lock(&li->lock);
switch (type) {
case KVM_S390_MCHK:
- atomic_or(CPUSTAT_STOP_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT);
break;
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- atomic_or(CPUSTAT_IO_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
break;
default:
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT);
break;
}
- spin_unlock(&li->lock);
kvm_s390_vcpu_wakeup(dst_vcpu);
}
@@ -1820,6 +1945,7 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
for (i = 0; i < FIRQ_MAX_COUNT; i++)
fi->counters[i] = 0;
spin_unlock(&fi->lock);
+ kvm_s390_gisa_clear(kvm);
};
static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
@@ -1847,6 +1973,22 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
max_irqs = len / sizeof(struct kvm_s390_irq);
+ if (kvm->arch.gisa &&
+ kvm_s390_gisa_get_ipm(kvm->arch.gisa)) {
+ for (i = 0; i <= MAX_ISC; i++) {
+ if (n == max_irqs) {
+ /* signal userspace to try again */
+ ret = -ENOMEM;
+ goto out_nolock;
+ }
+ if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, i)) {
+ irq = (struct kvm_s390_irq *) &buf[n];
+ irq->type = KVM_S390_INT_IO(1, 0, 0, 0);
+ irq->u.io.io_int_word = isc_to_int_word(i);
+ n++;
+ }
+ }
+ }
fi = &kvm->arch.float_int;
spin_lock(&fi->lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++) {
@@ -1885,6 +2027,7 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
out:
spin_unlock(&fi->lock);
+out_nolock:
if (!ret && n > 0) {
if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
ret = -EFAULT;
@@ -2245,7 +2388,7 @@ static int kvm_s390_inject_airq(struct kvm *kvm,
struct kvm_s390_interrupt s390int = {
.type = KVM_S390_INT_IO(1, 0, 0, 0),
.parm = 0,
- .parm64 = (adapter->isc << 27) | 0x80000000,
+ .parm64 = isc_to_int_word(adapter->isc),
};
int ret = 0;
@@ -2687,3 +2830,28 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
return n;
}
+
+void kvm_s390_gisa_clear(struct kvm *kvm)
+{
+ if (kvm->arch.gisa) {
+ memset(kvm->arch.gisa, 0, sizeof(struct kvm_s390_gisa));
+ kvm->arch.gisa->next_alert = (u32)(u64)kvm->arch.gisa;
+ VM_EVENT(kvm, 3, "gisa 0x%pK cleared", kvm->arch.gisa);
+ }
+}
+
+void kvm_s390_gisa_init(struct kvm *kvm)
+{
+ if (css_general_characteristics.aiv) {
+ kvm->arch.gisa = &kvm->arch.sie_page2->gisa;
+ VM_EVENT(kvm, 3, "gisa 0x%pK initialized", kvm->arch.gisa);
+ kvm_s390_gisa_clear(kvm);
+ }
+}
+
+void kvm_s390_gisa_destroy(struct kvm *kvm)
+{
+ if (!kvm->arch.gisa)
+ return;
+ kvm->arch.gisa = NULL;
+}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1371dff2b90d..ba4c7092335a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2,7 +2,7 @@
/*
* hosting IBM Z kernel virtual machines (s390x)
*
- * Copyright IBM Corp. 2008, 2017
+ * Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
@@ -87,19 +87,31 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+ { "instruction_epsw", VCPU_STAT(instruction_epsw) },
+ { "instruction_gs", VCPU_STAT(instruction_gs) },
+ { "instruction_io_other", VCPU_STAT(instruction_io_other) },
+ { "instruction_lpsw", VCPU_STAT(instruction_lpsw) },
+ { "instruction_lpswe", VCPU_STAT(instruction_lpswe) },
{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
+ { "instruction_ptff", VCPU_STAT(instruction_ptff) },
{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
+ { "instruction_sck", VCPU_STAT(instruction_sck) },
+ { "instruction_sckpf", VCPU_STAT(instruction_sckpf) },
{ "instruction_spx", VCPU_STAT(instruction_spx) },
{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
{ "instruction_stap", VCPU_STAT(instruction_stap) },
- { "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+ { "instruction_iske", VCPU_STAT(instruction_iske) },
+ { "instruction_ri", VCPU_STAT(instruction_ri) },
+ { "instruction_rrbe", VCPU_STAT(instruction_rrbe) },
+ { "instruction_sske", VCPU_STAT(instruction_sske) },
{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
- { "instruction_stsch", VCPU_STAT(instruction_stsch) },
- { "instruction_chsc", VCPU_STAT(instruction_chsc) },
{ "instruction_essa", VCPU_STAT(instruction_essa) },
{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+ { "instruction_tb", VCPU_STAT(instruction_tb) },
+ { "instruction_tpi", VCPU_STAT(instruction_tpi) },
{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
+ { "instruction_tsch", VCPU_STAT(instruction_tsch) },
{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
{ "instruction_sie", VCPU_STAT(instruction_sie) },
{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
@@ -118,12 +130,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
- { "diagnose_10", VCPU_STAT(diagnose_10) },
- { "diagnose_44", VCPU_STAT(diagnose_44) },
- { "diagnose_9c", VCPU_STAT(diagnose_9c) },
- { "diagnose_258", VCPU_STAT(diagnose_258) },
- { "diagnose_308", VCPU_STAT(diagnose_308) },
- { "diagnose_500", VCPU_STAT(diagnose_500) },
+ { "instruction_diag_10", VCPU_STAT(diagnose_10) },
+ { "instruction_diag_44", VCPU_STAT(diagnose_44) },
+ { "instruction_diag_9c", VCPU_STAT(diagnose_9c) },
+ { "instruction_diag_258", VCPU_STAT(diagnose_258) },
+ { "instruction_diag_308", VCPU_STAT(diagnose_308) },
+ { "instruction_diag_500", VCPU_STAT(diagnose_500) },
+ { "instruction_diag_other", VCPU_STAT(diagnose_other) },
{ NULL }
};
@@ -576,7 +589,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
case KVM_CAP_S390_GS:
r = -EINVAL;
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus)) {
+ if (kvm->created_vcpus) {
r = -EBUSY;
} else if (test_facility(133)) {
set_kvm_facility(kvm->arch.model.fac_mask, 133);
@@ -1088,7 +1101,6 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm,
struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_feat data;
- int ret = -EBUSY;
if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data)))
return -EFAULT;
@@ -1098,13 +1110,18 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm,
return -EINVAL;
mutex_lock(&kvm->lock);
- if (!atomic_read(&kvm->online_vcpus)) {
- bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
- KVM_S390_VM_CPU_FEAT_NR_BITS);
- ret = 0;
+ if (kvm->created_vcpus) {
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
}
+ bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
+ KVM_S390_VM_CPU_FEAT_NR_BITS);
mutex_unlock(&kvm->lock);
- return ret;
+ VM_EVENT(kvm, 3, "SET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
+ data.feat[0],
+ data.feat[1],
+ data.feat[2]);
+ return 0;
}
static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
@@ -1206,6 +1223,10 @@ static int kvm_s390_get_processor_feat(struct kvm *kvm,
KVM_S390_VM_CPU_FEAT_NR_BITS);
if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
return -EFAULT;
+ VM_EVENT(kvm, 3, "GET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
+ data.feat[0],
+ data.feat[1],
+ data.feat[2]);
return 0;
}
@@ -1219,6 +1240,10 @@ static int kvm_s390_get_machine_feat(struct kvm *kvm,
KVM_S390_VM_CPU_FEAT_NR_BITS);
if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
return -EFAULT;
+ VM_EVENT(kvm, 3, "GET: host feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
+ data.feat[0],
+ data.feat[1],
+ data.feat[2]);
return 0;
}
@@ -1911,6 +1936,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (!kvm->arch.dbf)
goto out_err;
+ BUILD_BUG_ON(sizeof(struct sie_page2) != 4096);
kvm->arch.sie_page2 =
(struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
if (!kvm->arch.sie_page2)
@@ -1981,6 +2007,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
spin_lock_init(&kvm->arch.start_stop_lock);
kvm_s390_vsie_init(kvm);
+ kvm_s390_gisa_init(kvm);
KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
@@ -2043,6 +2070,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kvm_free_vcpus(kvm);
sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
+ kvm_s390_gisa_destroy(kvm);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_remove(kvm->arch.gmap);
@@ -2314,7 +2342,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
gmap_enable(vcpu->arch.enabled_gmap);
- atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING);
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__start_cpu_timer_accounting(vcpu);
vcpu->cpu = cpu;
@@ -2325,7 +2353,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
vcpu->cpu = -1;
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__stop_cpu_timer_accounting(vcpu);
- atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_RUNNING);
vcpu->arch.enabled_gmap = gmap_get_enabled();
gmap_disable(vcpu->arch.enabled_gmap);
@@ -2422,9 +2450,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
CPUSTAT_STOPPED);
if (test_kvm_facility(vcpu->kvm, 78))
- atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED2);
else if (test_kvm_facility(vcpu->kvm, 8))
- atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED);
kvm_s390_vcpu_setup_model(vcpu);
@@ -2456,12 +2484,17 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
if (test_kvm_facility(vcpu->kvm, 139))
vcpu->arch.sie_block->ecd |= ECD_MEF;
+ if (vcpu->arch.sie_block->gd) {
+ vcpu->arch.sie_block->eca |= ECA_AIV;
+ VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u",
+ vcpu->arch.sie_block->gd & 0x3, vcpu->vcpu_id);
+ }
vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx)
| SDNXC;
vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
if (sclp.has_kss)
- atomic_or(CPUSTAT_KSS, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_KSS);
else
vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
@@ -2508,9 +2541,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->arch.sie_block->icpua = id;
spin_lock_init(&vcpu->arch.local_int.lock);
- vcpu->arch.local_int.float_int = &kvm->arch.float_int;
- vcpu->arch.local_int.wq = &vcpu->wq;
- vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+ vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa;
+ if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
+ vcpu->arch.sie_block->gd |= GISA_FORMAT1;
seqcount_init(&vcpu->arch.cputm_seqcount);
rc = kvm_vcpu_init(vcpu, kvm, id);
@@ -2567,7 +2600,7 @@ static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
* return immediately. */
void exit_sie(struct kvm_vcpu *vcpu)
{
- atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
cpu_relax();
}
@@ -2720,47 +2753,70 @@ static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ vcpu_load(vcpu);
memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ vcpu_load(vcpu);
memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
+ vcpu_load(vcpu);
+
memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
+
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
+ vcpu_load(vcpu);
+
memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
+
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- if (test_fp_ctl(fpu->fpc))
- return -EINVAL;
+ int ret = 0;
+
+ vcpu_load(vcpu);
+
+ if (test_fp_ctl(fpu->fpc)) {
+ ret = -EINVAL;
+ goto out;
+ }
vcpu->run->s.regs.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
(freg_t *) fpu->fprs);
else
memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
- return 0;
+
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
+ vcpu_load(vcpu);
+
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
@@ -2769,6 +2825,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
else
memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = vcpu->run->s.regs.fpc;
+
+ vcpu_put(vcpu);
return 0;
}
@@ -2800,41 +2858,56 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
{
int rc = 0;
+ vcpu_load(vcpu);
+
vcpu->guest_debug = 0;
kvm_s390_clear_bp_data(vcpu);
- if (dbg->control & ~VALID_GUESTDBG_FLAGS)
- return -EINVAL;
- if (!sclp.has_gpere)
- return -EINVAL;
+ if (dbg->control & ~VALID_GUESTDBG_FLAGS) {
+ rc = -EINVAL;
+ goto out;
+ }
+ if (!sclp.has_gpere) {
+ rc = -EINVAL;
+ goto out;
+ }
if (dbg->control & KVM_GUESTDBG_ENABLE) {
vcpu->guest_debug = dbg->control;
/* enforce guest PER */
- atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_P);
if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
rc = kvm_s390_import_bp_data(vcpu, dbg);
} else {
- atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P);
vcpu->arch.guestdbg.last_bp = 0;
}
if (rc) {
vcpu->guest_debug = 0;
kvm_s390_clear_bp_data(vcpu);
- atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P);
}
+out:
+ vcpu_put(vcpu);
return rc;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ int ret;
+
+ vcpu_load(vcpu);
+
/* CHECK_STOP and LOAD are not supported yet */
- return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
- KVM_MP_STATE_OPERATING;
+ ret = is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
+ KVM_MP_STATE_OPERATING;
+
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
@@ -2842,6 +2915,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
{
int rc = 0;
+ vcpu_load(vcpu);
+
/* user space knows about this interface - let it control the state */
vcpu->kvm->arch.user_cpu_state_ctrl = 1;
@@ -2859,12 +2934,13 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
rc = -ENXIO;
}
+ vcpu_put(vcpu);
return rc;
}
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
- return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
+ return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
}
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
@@ -2900,8 +2976,7 @@ retry:
if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
if (!ibs_enabled(vcpu)) {
trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
- atomic_or(CPUSTAT_IBS,
- &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_IBS);
}
goto retry;
}
@@ -2909,8 +2984,7 @@ retry:
if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
if (ibs_enabled(vcpu)) {
trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
- atomic_andnot(CPUSTAT_IBS,
- &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IBS);
}
goto retry;
}
@@ -3390,9 +3464,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (kvm_run->immediate_exit)
return -EINTR;
+ vcpu_load(vcpu);
+
if (guestdbg_exit_pending(vcpu)) {
kvm_s390_prepare_debug_exit(vcpu);
- return 0;
+ rc = 0;
+ goto out;
}
kvm_sigset_activate(vcpu);
@@ -3402,7 +3479,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
} else if (is_vcpu_stopped(vcpu)) {
pr_err_ratelimited("can't run stopped vcpu %d\n",
vcpu->vcpu_id);
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
sync_regs(vcpu, kvm_run);
@@ -3432,6 +3510,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_sigset_deactivate(vcpu);
vcpu->stat.exit_userspace++;
+out:
+ vcpu_put(vcpu);
return rc;
}
@@ -3560,7 +3640,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
__disable_ibs_on_all_vcpus(vcpu->kvm);
}
- atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED);
/*
* Another VCPU might have used IBS while we were offline.
* Let's play safe and flush the VCPU at startup.
@@ -3586,7 +3666,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
kvm_s390_clear_stop_irq(vcpu);
- atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
__disable_ibs_on_vcpu(vcpu);
for (i = 0; i < online_vcpus; i++) {
@@ -3693,36 +3773,45 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
return r;
}
-long kvm_arch_vcpu_ioctl(struct file *filp,
- unsigned int ioctl, unsigned long arg)
+long kvm_arch_vcpu_async_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
- int idx;
- long r;
switch (ioctl) {
case KVM_S390_IRQ: {
struct kvm_s390_irq s390irq;
- r = -EFAULT;
if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
- break;
- r = kvm_s390_inject_vcpu(vcpu, &s390irq);
- break;
+ return -EFAULT;
+ return kvm_s390_inject_vcpu(vcpu, &s390irq);
}
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
struct kvm_s390_irq s390irq;
- r = -EFAULT;
if (copy_from_user(&s390int, argp, sizeof(s390int)))
- break;
+ return -EFAULT;
if (s390int_to_s390irq(&s390int, &s390irq))
return -EINVAL;
- r = kvm_s390_inject_vcpu(vcpu, &s390irq);
- break;
+ return kvm_s390_inject_vcpu(vcpu, &s390irq);
+ }
}
+ return -ENOIOCTLCMD;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int idx;
+ long r;
+
+ vcpu_load(vcpu);
+
+ switch (ioctl) {
case KVM_S390_STORE_STATUS:
idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvm_s390_vcpu_store_status(vcpu, arg);
@@ -3847,6 +3936,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
default:
r = -ENOTTY;
}
+
+ vcpu_put(vcpu);
return r;
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 5e46ba429bcb..bd31b37b0e6f 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -47,14 +47,29 @@ do { \
d_args); \
} while (0)
+static inline void kvm_s390_set_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+ atomic_or(flags, &vcpu->arch.sie_block->cpuflags);
+}
+
+static inline void kvm_s390_clear_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+ atomic_andnot(flags, &vcpu->arch.sie_block->cpuflags);
+}
+
+static inline bool kvm_s390_test_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+ return (atomic_read(&vcpu->arch.sie_block->cpuflags) & flags) == flags;
+}
+
static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
{
- return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
+ return kvm_s390_test_cpuflags(vcpu, CPUSTAT_STOPPED);
}
static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
{
- return test_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+ return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
}
static inline int kvm_is_ucontrol(struct kvm *kvm)
@@ -367,6 +382,9 @@ int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
void __user *buf, int len);
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu,
__u8 __user *buf, int len);
+void kvm_s390_gisa_init(struct kvm *kvm);
+void kvm_s390_gisa_clear(struct kvm *kvm);
+void kvm_s390_gisa_destroy(struct kvm *kvm);
/* implemented in guestdbg.c */
void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 0714bfa56da0..c4c4e157c036 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -2,7 +2,7 @@
/*
* handling privileged instructions
*
- * Copyright IBM Corp. 2008, 2013
+ * Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
@@ -34,6 +34,8 @@
static int handle_ri(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.instruction_ri++;
+
if (test_kvm_facility(vcpu->kvm, 64)) {
VCPU_EVENT(vcpu, 3, "%s", "ENABLE: RI (lazy)");
vcpu->arch.sie_block->ecb3 |= ECB3_RI;
@@ -53,6 +55,8 @@ int kvm_s390_handle_aa(struct kvm_vcpu *vcpu)
static int handle_gs(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.instruction_gs++;
+
if (test_kvm_facility(vcpu->kvm, 133)) {
VCPU_EVENT(vcpu, 3, "%s", "ENABLE: GS (lazy)");
preempt_disable();
@@ -85,6 +89,8 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
u8 ar;
u64 op2, val;
+ vcpu->stat.instruction_sck++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -203,14 +209,14 @@ int kvm_s390_skey_check_enable(struct kvm_vcpu *vcpu)
trace_kvm_s390_skey_related_inst(vcpu);
if (!(sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)) &&
- !(atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS))
+ !kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS))
return rc;
rc = s390_enable_skey();
VCPU_EVENT(vcpu, 3, "enabling storage keys for guest: %d", rc);
if (!rc) {
- if (atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS)
- atomic_andnot(CPUSTAT_KSS, &sie_block->cpuflags);
+ if (kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS))
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_KSS);
else
sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE |
ICTL_RRBE);
@@ -222,7 +228,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
{
int rc;
- vcpu->stat.instruction_storage_key++;
rc = kvm_s390_skey_check_enable(vcpu);
if (rc)
return rc;
@@ -242,6 +247,8 @@ static int handle_iske(struct kvm_vcpu *vcpu)
int reg1, reg2;
int rc;
+ vcpu->stat.instruction_iske++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -274,6 +281,8 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
int reg1, reg2;
int rc;
+ vcpu->stat.instruction_rrbe++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -312,6 +321,8 @@ static int handle_sske(struct kvm_vcpu *vcpu)
int reg1, reg2;
int rc;
+ vcpu->stat.instruction_sske++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -392,6 +403,8 @@ static int handle_test_block(struct kvm_vcpu *vcpu)
gpa_t addr;
int reg2;
+ vcpu->stat.instruction_tb++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -424,6 +437,8 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
u64 addr;
u8 ar;
+ vcpu->stat.instruction_tpi++;
+
addr = kvm_s390_get_base_disp_s(vcpu, &ar);
if (addr & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -484,6 +499,8 @@ static int handle_tsch(struct kvm_vcpu *vcpu)
struct kvm_s390_interrupt_info *inti = NULL;
const u64 isc_mask = 0xffUL << 24; /* all iscs set */
+ vcpu->stat.instruction_tsch++;
+
/* a valid schid has at least one bit set */
if (vcpu->run->s.regs.gprs[1])
inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask,
@@ -527,6 +544,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
if (vcpu->arch.sie_block->ipa == 0xb235)
return handle_tsch(vcpu);
/* Handle in userspace. */
+ vcpu->stat.instruction_io_other++;
return -EOPNOTSUPP;
} else {
/*
@@ -592,6 +610,8 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
int rc;
u8 ar;
+ vcpu->stat.instruction_lpsw++;
+
if (gpsw->mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -619,6 +639,8 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
int rc;
u8 ar;
+ vcpu->stat.instruction_lpswe++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -828,6 +850,8 @@ static int handle_epsw(struct kvm_vcpu *vcpu)
{
int reg1, reg2;
+ vcpu->stat.instruction_epsw++;
+
kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
/* This basically extracts the mask half of the psw. */
@@ -1332,6 +1356,8 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
{
u32 value;
+ vcpu->stat.instruction_sckpf++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -1347,6 +1373,8 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
static int handle_ptff(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.instruction_ptff++;
+
/* we don't emulate any control instructions yet */
kvm_s390_set_psw_cc(vcpu, 3);
return 0;
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index c1f5cde2c878..683036c1c92a 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -20,22 +20,18 @@
static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
u64 *reg)
{
- struct kvm_s390_local_interrupt *li;
- int cpuflags;
+ const bool stopped = kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED);
int rc;
int ext_call_pending;
- li = &dst_vcpu->arch.local_int;
-
- cpuflags = atomic_read(li->cpuflags);
ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu);
- if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending)
+ if (!stopped && !ext_call_pending)
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
else {
*reg &= 0xffffffff00000000UL;
if (ext_call_pending)
*reg |= SIGP_STATUS_EXT_CALL_PENDING;
- if (cpuflags & CPUSTAT_STOPPED)
+ if (stopped)
*reg |= SIGP_STATUS_STOPPED;
rc = SIGP_CC_STATUS_STORED;
}
@@ -208,11 +204,9 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu,
struct kvm_vcpu *dst_vcpu,
u32 addr, u64 *reg)
{
- int flags;
int rc;
- flags = atomic_read(dst_vcpu->arch.local_int.cpuflags);
- if (!(flags & CPUSTAT_STOPPED)) {
+ if (!kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED)) {
*reg &= 0xffffffff00000000UL;
*reg |= SIGP_STATUS_INCORRECT_STATE;
return SIGP_CC_STATUS_STORED;
@@ -231,7 +225,6 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu,
static int __sigp_sense_running(struct kvm_vcpu *vcpu,
struct kvm_vcpu *dst_vcpu, u64 *reg)
{
- struct kvm_s390_local_interrupt *li;
int rc;
if (!test_kvm_facility(vcpu->kvm, 9)) {
@@ -240,8 +233,7 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu,
return SIGP_CC_STATUS_STORED;
}
- li = &dst_vcpu->arch.local_int;
- if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+ if (kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_RUNNING)) {
/* running */
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
} else {
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 751348348477..ec772700ff96 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -28,13 +28,23 @@ struct vsie_page {
* the same offset as that in struct sie_page!
*/
struct mcck_volatile_info mcck_info; /* 0x0200 */
- /* the pinned originial scb */
+ /*
+ * The pinned original scb. Be aware that other VCPUs can modify
+ * it while we read from it. Values that are used for conditions or
+ * are reused conditionally, should be accessed via READ_ONCE.
+ */
struct kvm_s390_sie_block *scb_o; /* 0x0218 */
/* the shadow gmap in use by the vsie_page */
struct gmap *gmap; /* 0x0220 */
/* address of the last reported fault to guest2 */
unsigned long fault_addr; /* 0x0228 */
- __u8 reserved[0x0700 - 0x0230]; /* 0x0230 */
+ /* calculated guest addresses of satellite control blocks */
+ gpa_t sca_gpa; /* 0x0230 */
+ gpa_t itdba_gpa; /* 0x0238 */
+ gpa_t gvrd_gpa; /* 0x0240 */
+ gpa_t riccbd_gpa; /* 0x0248 */
+ gpa_t sdnx_gpa; /* 0x0250 */
+ __u8 reserved[0x0700 - 0x0258]; /* 0x0258 */
struct kvm_s390_crypto_cb crycb; /* 0x0700 */
__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */
};
@@ -140,12 +150,13 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
- u32 crycb_addr = scb_o->crycbd & 0x7ffffff8U;
+ const uint32_t crycbd_o = READ_ONCE(scb_o->crycbd);
+ const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
unsigned long *b1, *b2;
u8 ecb3_flags;
scb_s->crycbd = 0;
- if (!(scb_o->crycbd & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
+ if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
return 0;
/* format-1 is supported with message-security-assist extension 3 */
if (!test_kvm_facility(vcpu->kvm, 76))
@@ -183,12 +194,15 @@ static void prepare_ibc(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+ /* READ_ONCE does not work on bitfields - use a temporary variable */
+ const uint32_t __new_ibc = scb_o->ibc;
+ const uint32_t new_ibc = READ_ONCE(__new_ibc) & 0x0fffU;
__u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU;
scb_s->ibc = 0;
/* ibc installed in g2 and requested for g3 */
- if (vcpu->kvm->arch.model.ibc && (scb_o->ibc & 0x0fffU)) {
- scb_s->ibc = scb_o->ibc & 0x0fffU;
+ if (vcpu->kvm->arch.model.ibc && new_ibc) {
+ scb_s->ibc = new_ibc;
/* takte care of the minimum ibc level of the machine */
if (scb_s->ibc < min_ibc)
scb_s->ibc = min_ibc;
@@ -259,6 +273,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+ /* READ_ONCE does not work on bitfields - use a temporary variable */
+ const uint32_t __new_prefix = scb_o->prefix;
+ const uint32_t new_prefix = READ_ONCE(__new_prefix);
+ const bool wants_tx = READ_ONCE(scb_o->ecb) & ECB_TE;
bool had_tx = scb_s->ecb & ECB_TE;
unsigned long new_mso = 0;
int rc;
@@ -306,14 +324,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
scb_s->icpua = scb_o->icpua;
if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM))
- new_mso = scb_o->mso & 0xfffffffffff00000UL;
+ new_mso = READ_ONCE(scb_o->mso) & 0xfffffffffff00000UL;
/* if the hva of the prefix changes, we have to remap the prefix */
- if (scb_s->mso != new_mso || scb_s->prefix != scb_o->prefix)
+ if (scb_s->mso != new_mso || scb_s->prefix != new_prefix)
prefix_unmapped(vsie_page);
/* SIE will do mso/msl validity and exception checks for us */
scb_s->msl = scb_o->msl & 0xfffffffffff00000UL;
scb_s->mso = new_mso;
- scb_s->prefix = scb_o->prefix;
+ scb_s->prefix = new_prefix;
/* We have to definetly flush the tlb if this scb never ran */
if (scb_s->ihcpu != 0xffffU)
@@ -325,11 +343,11 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
/* transactional execution */
- if (test_kvm_facility(vcpu->kvm, 73)) {
+ if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
/* remap the prefix is tx is toggled on */
- if ((scb_o->ecb & ECB_TE) && !had_tx)
+ if (!had_tx)
prefix_unmapped(vsie_page);
- scb_s->ecb |= scb_o->ecb & ECB_TE;
+ scb_s->ecb |= ECB_TE;
}
/* branch prediction */
if (test_kvm_facility(vcpu->kvm, 82))
@@ -473,46 +491,42 @@ static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa)
/* unpin all blocks previously pinned by pin_blocks(), marking them dirty */
static void unpin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
- struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
hpa_t hpa;
- gpa_t gpa;
hpa = (u64) scb_s->scaoh << 32 | scb_s->scaol;
if (hpa) {
- gpa = scb_o->scaol & ~0xfUL;
- if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
- gpa |= (u64) scb_o->scaoh << 32;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->sca_gpa, hpa);
+ vsie_page->sca_gpa = 0;
scb_s->scaol = 0;
scb_s->scaoh = 0;
}
hpa = scb_s->itdba;
if (hpa) {
- gpa = scb_o->itdba & ~0xffUL;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->itdba_gpa, hpa);
+ vsie_page->itdba_gpa = 0;
scb_s->itdba = 0;
}
hpa = scb_s->gvrd;
if (hpa) {
- gpa = scb_o->gvrd & ~0x1ffUL;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->gvrd_gpa, hpa);
+ vsie_page->gvrd_gpa = 0;
scb_s->gvrd = 0;
}
hpa = scb_s->riccbd;
if (hpa) {
- gpa = scb_o->riccbd & ~0x3fUL;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->riccbd_gpa, hpa);
+ vsie_page->riccbd_gpa = 0;
scb_s->riccbd = 0;
}
hpa = scb_s->sdnxo;
if (hpa) {
- gpa = scb_o->sdnxo;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->sdnx_gpa, hpa);
+ vsie_page->sdnx_gpa = 0;
scb_s->sdnxo = 0;
}
}
@@ -539,9 +553,9 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
gpa_t gpa;
int rc = 0;
- gpa = scb_o->scaol & ~0xfUL;
+ gpa = READ_ONCE(scb_o->scaol) & ~0xfUL;
if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
- gpa |= (u64) scb_o->scaoh << 32;
+ gpa |= (u64) READ_ONCE(scb_o->scaoh) << 32;
if (gpa) {
if (!(gpa & ~0x1fffUL))
rc = set_validity_icpt(scb_s, 0x0038U);
@@ -557,11 +571,12 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
}
if (rc)
goto unpin;
+ vsie_page->sca_gpa = gpa;
scb_s->scaoh = (u32)((u64)hpa >> 32);
scb_s->scaol = (u32)(u64)hpa;
}
- gpa = scb_o->itdba & ~0xffUL;
+ gpa = READ_ONCE(scb_o->itdba) & ~0xffUL;
if (gpa && (scb_s->ecb & ECB_TE)) {
if (!(gpa & ~0x1fffU)) {
rc = set_validity_icpt(scb_s, 0x0080U);
@@ -573,10 +588,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
rc = set_validity_icpt(scb_s, 0x0080U);
goto unpin;
}
+ vsie_page->itdba_gpa = gpa;
scb_s->itdba = hpa;
}
- gpa = scb_o->gvrd & ~0x1ffUL;
+ gpa = READ_ONCE(scb_o->gvrd) & ~0x1ffUL;
if (gpa && (scb_s->eca & ECA_VX) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
if (!(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x1310U);
@@ -591,10 +607,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
rc = set_validity_icpt(scb_s, 0x1310U);
goto unpin;
}
+ vsie_page->gvrd_gpa = gpa;
scb_s->gvrd = hpa;
}
- gpa = scb_o->riccbd & ~0x3fUL;
+ gpa = READ_ONCE(scb_o->riccbd) & ~0x3fUL;
if (gpa && (scb_s->ecb3 & ECB3_RI)) {
if (!(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x0043U);
@@ -607,13 +624,14 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
goto unpin;
}
/* Validity 0x0044 will be checked by SIE */
+ vsie_page->riccbd_gpa = gpa;
scb_s->riccbd = hpa;
}
if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
unsigned long sdnxc;
- gpa = scb_o->sdnxo & ~0xfUL;
- sdnxc = scb_o->sdnxo & 0xfUL;
+ gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL;
+ sdnxc = READ_ONCE(scb_o->sdnxo) & 0xfUL;
if (!gpa || !(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x10b0U);
goto unpin;
@@ -634,6 +652,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
rc = set_validity_icpt(scb_s, 0x10b0U);
goto unpin;
}
+ vsie_page->sdnx_gpa = gpa;
scb_s->sdnxo = hpa | sdnxc;
}
return 0;
@@ -778,7 +797,7 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page)
static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
- __u32 fac = vsie_page->scb_o->fac & 0x7ffffff8U;
+ __u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;
if (fac && test_kvm_facility(vcpu->kvm, 7)) {
retry_vsie_icpt(vsie_page);
@@ -904,7 +923,7 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu,
* External calls have to lead to a kick of the vcpu and
* therefore the vsie -> Simulate Wait state.
*/
- atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
/*
* We have to adjust the g3 epoch by the g2 epoch. The epoch will
* automatically be adjusted on tod clock changes via kvm_sync_clock.
@@ -926,7 +945,7 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu,
*/
static void unregister_shadow_scb(struct kvm_vcpu *vcpu)
{
- atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
WRITE_ONCE(vcpu->arch.vsie_block, NULL);
}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 05d459b638f5..2c55a2b9d6c6 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -815,27 +815,17 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
* @ptl: pointer to the spinlock pointer
*
* Returns a pointer to the locked pte for a guest address, or NULL
- *
- * Note: Can also be called for shadow gmaps.
*/
static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr,
spinlock_t **ptl)
{
unsigned long *table;
- if (gmap_is_shadow(gmap))
- spin_lock(&gmap->guest_table_lock);
+ BUG_ON(gmap_is_shadow(gmap));
/* Walk the gmap page table, lock and get pte pointer */
table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */
- if (!table || *table & _SEGMENT_ENTRY_INVALID) {
- if (gmap_is_shadow(gmap))
- spin_unlock(&gmap->guest_table_lock);
+ if (!table || *table & _SEGMENT_ENTRY_INVALID)
return NULL;
- }
- if (gmap_is_shadow(gmap)) {
- *ptl = &gmap->guest_table_lock;
- return pte_offset_map((pmd_t *) table, gaddr);
- }
return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl);
}
@@ -889,8 +879,6 @@ static void gmap_pte_op_end(spinlock_t *ptl)
* -EFAULT if gaddr is invalid (or mapping for shadows is missing).
*
* Called with sg->mm->mmap_sem in read.
- *
- * Note: Can also be called for shadow gmaps.
*/
static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
unsigned long len, int prot, unsigned long bits)
@@ -900,6 +888,7 @@ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
pte_t *ptep;
int rc;
+ BUG_ON(gmap_is_shadow(gmap));
while (len) {
rc = -EAGAIN;
ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
@@ -960,7 +949,8 @@ EXPORT_SYMBOL_GPL(gmap_mprotect_notify);
* @val: pointer to the unsigned long value to return
*
* Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT
- * if reading using the virtual address failed.
+ * if reading using the virtual address failed. -EINVAL if called on a gmap
+ * shadow.
*
* Called with gmap->mm->mmap_sem in read.
*/
@@ -971,6 +961,9 @@ int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val)
pte_t *ptep, pte;
int rc;
+ if (gmap_is_shadow(gmap))
+ return -EINVAL;
+
while (1) {
rc = -EAGAIN;
ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
@@ -1028,18 +1021,17 @@ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr,
}
/**
- * gmap_protect_rmap - modify access rights to memory and create an rmap
+ * gmap_protect_rmap - restrict access rights to memory (RO) and create an rmap
* @sg: pointer to the shadow guest address space structure
* @raddr: rmap address in the shadow gmap
* @paddr: address in the parent guest address space
* @len: length of the memory area to protect
- * @prot: indicates access rights: none, read-only or read-write
*
* Returns 0 if successfully protected and the rmap was created, -ENOMEM
* if out of memory and -EFAULT if paddr is invalid.
*/
static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
- unsigned long paddr, unsigned long len, int prot)
+ unsigned long paddr, unsigned long len)
{
struct gmap *parent;
struct gmap_rmap *rmap;
@@ -1067,7 +1059,7 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
ptep = gmap_pte_op_walk(parent, paddr, &ptl);
if (ptep) {
spin_lock(&sg->guest_table_lock);
- rc = ptep_force_prot(parent->mm, paddr, ptep, prot,
+ rc = ptep_force_prot(parent->mm, paddr, ptep, PROT_READ,
PGSTE_VSIE_BIT);
if (!rc)
gmap_insert_rmap(sg, vmaddr, rmap);
@@ -1077,7 +1069,7 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
radix_tree_preload_end();
if (rc) {
kfree(rmap);
- rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
+ rc = gmap_pte_op_fixup(parent, paddr, vmaddr, PROT_READ);
if (rc)
return rc;
continue;
@@ -1616,7 +1608,7 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
origin = r2t & _REGION_ENTRY_ORIGIN;
offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
- rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 4);
@@ -1699,7 +1691,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
origin = r3t & _REGION_ENTRY_ORIGIN;
offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
- rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 3);
@@ -1783,7 +1775,7 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
origin = sgt & _REGION_ENTRY_ORIGIN;
offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
- rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 2);
@@ -1902,7 +1894,7 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
/* Make pgt read-only in parent gmap page table (not the pgste) */
raddr = (saddr & _SEGMENT_MASK) | _SHADOW_RMAP_SEGMENT;
origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK;
- rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 1);
@@ -2005,7 +1997,7 @@ EXPORT_SYMBOL_GPL(gmap_shadow_page);
* Called with sg->parent->shadow_lock.
*/
static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
- unsigned long gaddr, pte_t *pte)
+ unsigned long gaddr)
{
struct gmap_rmap *rmap, *rnext, *head;
unsigned long start, end, bits, raddr;
@@ -2090,7 +2082,7 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
spin_lock(&gmap->shadow_lock);
list_for_each_entry_safe(sg, next,
&gmap->children, list)
- gmap_shadow_notify(sg, vmaddr, gaddr, pte);
+ gmap_shadow_notify(sg, vmaddr, gaddr);
spin_unlock(&gmap->shadow_lock);
}
if (bits & PGSTE_IN_BIT)