summaryrefslogtreecommitdiff
path: root/arch/s390/kvm/interrupt.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kvm/interrupt.c')
-rw-r--r--arch/s390/kvm/interrupt.c1571
1 files changed, 1169 insertions, 402 deletions
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index a619ddae610d..249cdc822ec5 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,141 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* handling kvm guest interrupts
*
- * Copyright IBM Corp. 2008, 2015
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
+ * Copyright IBM Corp. 2008, 2020
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
+#define pr_fmt(fmt) "kvm-s390: " fmt
+
+#include <linux/cpufeature.h>
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
#include <linux/hrtimer.h>
+#include <linux/export.h>
#include <linux/mmu_context.h>
+#include <linux/nospec.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/bitmap.h>
#include <linux/vmalloc.h>
+#include <asm/access-regs.h>
#include <asm/asm-offsets.h>
#include <asm/dis.h>
#include <linux/uaccess.h>
#include <asm/sclp.h>
#include <asm/isc.h>
#include <asm/gmap.h>
-#include <asm/switch_to.h>
#include <asm/nmi.h>
+#include <asm/airq.h>
+#include <asm/tpi.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
+#include "pci.h"
#define PFAULT_INIT 0x0600
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
+static struct kvm_s390_gib *gib;
+
/* handle external calls via sigp interpretation facility */
static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
{
- int c, scn;
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl;
- 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());
- read_lock(&vcpu->kvm->arch.sca_lock);
- if (vcpu->kvm->arch.use_esca) {
- struct esca_block *sca = vcpu->kvm->arch.sca;
- union esca_sigp_ctrl sigp_ctrl =
- sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
- c = sigp_ctrl.c;
- scn = sigp_ctrl.scn;
- } else {
- struct bsca_block *sca = vcpu->kvm->arch.sca;
- union bsca_sigp_ctrl sigp_ctrl =
- sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
- c = sigp_ctrl.c;
- scn = sigp_ctrl.scn;
- }
- read_unlock(&vcpu->kvm->arch.sca_lock);
if (src_id)
- *src_id = scn;
+ *src_id = sigp_ctrl.scn;
- return c;
+ return sigp_ctrl.c;
}
static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
{
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+ union esca_sigp_ctrl old_val, new_val = {.scn = src_id, .c = 1};
int expect, rc;
BUG_ON(!kvm_s390_use_sca_entries());
- read_lock(&vcpu->kvm->arch.sca_lock);
- if (vcpu->kvm->arch.use_esca) {
- struct esca_block *sca = vcpu->kvm->arch.sca;
- union esca_sigp_ctrl *sigp_ctrl =
- &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
-
- new_val.scn = src_id;
- new_val.c = 1;
- old_val.c = 0;
-
- expect = old_val.value;
- rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
- } else {
- struct bsca_block *sca = vcpu->kvm->arch.sca;
- union bsca_sigp_ctrl *sigp_ctrl =
- &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
- new_val.scn = src_id;
- new_val.c = 1;
- old_val.c = 0;
+ old_val = READ_ONCE(*sigp_ctrl);
+ old_val.c = 0;
- expect = old_val.value;
- rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
- }
- read_unlock(&vcpu->kvm->arch.sca_lock);
+ expect = old_val.value;
+ rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
if (rc != expect) {
/* 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;
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl;
if (!kvm_s390_use_sca_entries())
return;
- atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
- read_lock(&vcpu->kvm->arch.sca_lock);
- if (vcpu->kvm->arch.use_esca) {
- struct esca_block *sca = vcpu->kvm->arch.sca;
- union esca_sigp_ctrl *sigp_ctrl =
- &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union esca_sigp_ctrl old = *sigp_ctrl;
-
- expect = old.value;
- rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
- } else {
- struct bsca_block *sca = vcpu->kvm->arch.sca;
- union bsca_sigp_ctrl *sigp_ctrl =
- &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union bsca_sigp_ctrl old = *sigp_ctrl;
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
- expect = old.value;
- rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
- }
- read_unlock(&vcpu->kvm->arch.sca_lock);
- WARN_ON(rc != expect); /* cannot clear? */
+ WRITE_ONCE(sigp_ctrl->value, 0);
}
int psw_extint_disabled(struct kvm_vcpu *vcpu)
@@ -163,7 +118,7 @@ static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
if (psw_extint_disabled(vcpu) ||
- !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+ !(vcpu->arch.sie_block->gcr[0] & CR0_CLOCK_COMPARATOR_SUBMASK))
return 0;
if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
/* No timer interrupts when single stepping */
@@ -173,15 +128,22 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
static int ckc_irq_pending(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm))
+ const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+ const u64 ckc = vcpu->arch.sie_block->ckc;
+
+ if (vcpu->arch.sie_block->gcr[0] & CR0_CLOCK_COMPARATOR_SIGN) {
+ if ((s64)ckc >= (s64)now)
+ return 0;
+ } else if (ckc >= now) {
return 0;
+ }
return ckc_interrupts_enabled(vcpu);
}
static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
{
return !psw_extint_disabled(vcpu) &&
- (vcpu->arch.sie_block->gcr[0] & 0x400ul);
+ (vcpu->arch.sie_block->gcr[0] & CR0_CPU_TIMER_SUBMASK);
}
static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
@@ -191,15 +153,14 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
return kvm_s390_get_cpu_timer(vcpu) >> 63;
}
-static inline int is_ioirq(unsigned long irq_type)
+static uint64_t isc_to_isc_bits(int isc)
{
- return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
- (irq_type <= IRQ_PEND_IO_ISC_7));
+ return (0x80 >> isc) << 24;
}
-static uint64_t isc_to_isc_bits(int isc)
+static inline u32 isc_to_int_word(u8 isc)
{
- return (0x80 >> isc) << 24;
+ return ((u32)isc << 27) | 0x80000000;
}
static inline u8 int_word_to_isc(u32 int_word)
@@ -207,10 +168,130 @@ 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)
+
+/**
+ * gisa_set_iam - change the GISA interruption alert mask
+ *
+ * @gisa: gisa to operate on
+ * @iam: new IAM value to use
+ *
+ * Change the IAM atomically with the next alert address and the IPM
+ * of the GISA if the GISA is not part of the GIB alert list. All three
+ * fields are located in the first long word of the GISA.
+ *
+ * Returns: 0 on success
+ * -EBUSY in case the gisa is part of the alert list
+ */
+static inline int gisa_set_iam(struct kvm_s390_gisa *gisa, u8 iam)
+{
+ u64 word, _word;
+
+ word = READ_ONCE(gisa->u64.word[0]);
+ do {
+ if ((u64)gisa != word >> 32)
+ return -EBUSY;
+ _word = (word & ~0xffUL) | iam;
+ } while (!try_cmpxchg(&gisa->u64.word[0], &word, _word));
+
+ return 0;
+}
+
+/**
+ * gisa_clear_ipm - clear the GISA interruption pending mask
+ *
+ * @gisa: gisa to operate on
+ *
+ * Clear the IPM atomically with the next alert address and the IAM
+ * of the GISA unconditionally. All three fields are located in the
+ * first long word of the GISA.
+ */
+static inline void gisa_clear_ipm(struct kvm_s390_gisa *gisa)
+{
+ u64 word, _word;
+
+ word = READ_ONCE(gisa->u64.word[0]);
+ do {
+ _word = word & ~(0xffUL << 24);
+ } while (!try_cmpxchg(&gisa->u64.word[0], &word, _word));
+}
+
+/**
+ * gisa_get_ipm_or_restore_iam - return IPM or restore GISA IAM
+ *
+ * @gi: gisa interrupt struct to work on
+ *
+ * Atomically restores the interruption alert mask if none of the
+ * relevant ISCs are pending and return the IPM.
+ *
+ * Returns: the relevant pending ISCs
+ */
+static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
+{
+ u8 pending_mask, alert_mask;
+ u64 word, _word;
+
+ word = READ_ONCE(gi->origin->u64.word[0]);
+ do {
+ alert_mask = READ_ONCE(gi->alert.mask);
+ pending_mask = (u8)(word >> 24) & alert_mask;
+ if (pending_mask)
+ return pending_mask;
+ _word = (word & ~0xffUL) | alert_mask;
+ } while (!try_cmpxchg(&gi->origin->u64.word[0], &word, _word));
+
+ return 0;
+}
+
+static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline u8 gisa_get_ipm(struct kvm_s390_gisa *gisa)
+{
+ return READ_ONCE(gisa->ipm);
+}
+
+static inline int 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_no_gisa(struct kvm_vcpu *vcpu)
+{
+ unsigned long pending = vcpu->kvm->arch.float_int.pending_irqs |
+ vcpu->arch.local_int.pending_irqs;
+
+ pending &= ~vcpu->kvm->arch.float_int.masked_irqs;
+ return pending;
+}
+
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
{
- return vcpu->kvm->arch.float_int.pending_irqs |
- vcpu->arch.local_int.pending_irqs;
+ struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int;
+ unsigned long pending_mask;
+
+ pending_mask = pending_irqs_no_gisa(vcpu);
+ if (gi->origin)
+ pending_mask |= gisa_get_ipm(gi->origin) << IRQ_PEND_IO_ISC_7;
+ return pending_mask;
+}
+
+static inline int isc_to_irq_type(unsigned long isc)
+{
+ return IRQ_PEND_IO_ISC_0 - isc;
+}
+
+static inline int irq_type_to_isc(unsigned long irq_type)
+{
+ return IRQ_PEND_IO_ISC_0 - irq_type;
}
static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
@@ -220,7 +301,7 @@ static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
for (i = 0; i <= MAX_ISC; i++)
if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i)))
- active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i));
+ active_mask &= ~(1UL << (isc_to_irq_type(i)));
return active_mask;
}
@@ -239,18 +320,26 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
active_mask &= ~IRQ_PEND_IO_MASK;
else
active_mask = disable_iscs(vcpu, active_mask);
- if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul))
+ if (!(vcpu->arch.sie_block->gcr[0] & CR0_EXTERNAL_CALL_SUBMASK))
__clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask);
- if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul))
+ if (!(vcpu->arch.sie_block->gcr[0] & CR0_EMERGENCY_SIGNAL_SUBMASK))
__clear_bit(IRQ_PEND_EXT_EMERGENCY, &active_mask);
- if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+ if (!(vcpu->arch.sie_block->gcr[0] & CR0_CLOCK_COMPARATOR_SUBMASK))
__clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask);
- if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul))
+ if (!(vcpu->arch.sie_block->gcr[0] & CR0_CPU_TIMER_SUBMASK))
__clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask);
- if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
+ if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) {
__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
+ __clear_bit(IRQ_PEND_EXT_SERVICE_EV, &active_mask);
+ }
if (psw_mchk_disabled(vcpu))
active_mask &= ~IRQ_PEND_MCHK_MASK;
+ /* PV guest cpus can have a single interruption injected at a time. */
+ if (kvm_s390_pv_cpu_get_handle(vcpu) &&
+ vcpu->arch.sie_block->iictl != IICTL_CODE_NONE)
+ active_mask &= ~(IRQ_PEND_EXT_II_MASK |
+ IRQ_PEND_IO_MASK |
+ IRQ_PEND_MCHK_MASK);
/*
* Check both floating and local interrupt's cr14 because
* bit IRQ_PEND_MCHK_REP could be set in both cases.
@@ -271,20 +360,20 @@ 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_idx, vcpu->kvm->arch.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_idx, vcpu->kvm->arch.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);
@@ -295,34 +384,29 @@ 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))
+ if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK))
return;
- else if (psw_ioint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_IO_INT);
+ if (psw_ioint_disabled(vcpu))
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR6;
}
static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
{
- if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
+ if (!(pending_irqs_no_gisa(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;
}
static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
{
- if (!(pending_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
+ if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_MCHK_MASK))
return;
if (psw_mchk_disabled(vcpu))
vcpu->arch.sie_block->ictl |= ICTL_LPSW;
@@ -333,7 +417,7 @@ 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 */
@@ -348,18 +432,23 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu)
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- int rc;
+ int rc = 0;
+ vcpu->stat.deliver_cputm++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
0, 0);
-
- rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
- (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_CPU_TIMER;
+ } else {
+ rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
+ (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ }
clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
@@ -367,18 +456,23 @@ static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- int rc;
+ int rc = 0;
+ vcpu->stat.deliver_ckc++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
0, 0);
-
- rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
- (u16 __user *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_CLK_COMP;
+ } else {
+ rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
+ (u16 __user *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ }
clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
@@ -420,11 +514,25 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
union mci mci;
int rc;
+ /*
+ * All other possible payload for a machine check (e.g. the register
+ * contents in the save area) will be handled by the ultravisor, as
+ * the hypervisor does not not have the needed information for
+ * protected guests.
+ */
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_MCHK;
+ vcpu->arch.sie_block->mcic = mchk->mcic;
+ vcpu->arch.sie_block->faddr = mchk->failing_storage_address;
+ vcpu->arch.sie_block->edc = mchk->ext_damage_code;
+ return 0;
+ }
+
mci.val = mchk->mcic;
/* take care of lazy register loading */
- save_fpu_regs();
+ kvm_s390_fpu_store(vcpu->run);
save_access_regs(vcpu->run->s.regs.acrs);
- if (MACHINE_HAS_GS && vcpu->arch.gs_enabled)
+ if (cpu_has_gs() && vcpu->arch.gs_enabled)
save_gs_cb(current->thread.gs_cb);
/* Extended save area */
@@ -477,7 +585,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
rc |= put_guest_lc(vcpu, mci.val, (u64 __user *) __LC_MCCK_CODE);
/* Register-save areas */
- if (MACHINE_HAS_VX) {
+ if (cpu_has_vx()) {
convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
rc |= write_guest_lc(vcpu, __LC_FPREGS_SAVE_AREA, fprs, 128);
} else {
@@ -486,7 +594,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
}
rc |= write_guest_lc(vcpu, __LC_GPREGS_SAVE_AREA,
vcpu->run->s.regs.gprs, 128);
- rc |= put_guest_lc(vcpu, current->thread.fpu.fpc,
+ rc |= put_guest_lc(vcpu, vcpu->run->s.regs.fpc,
(u32 __user *) __LC_FP_CREG_SAVE_AREA);
rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->todpr,
(u32 __user *) __LC_TOD_PROGREG_SAVE_AREA);
@@ -536,7 +644,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
/*
* We indicate floating repressible conditions along with
* other pending conditions. Channel Report Pending and Channel
- * Subsystem damage are the only two and and are indicated by
+ * Subsystem damage are the only two and are indicated by
* bits in mcic and masked in cr14.
*/
if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) {
@@ -554,6 +662,7 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_MCHK,
mchk.cr14, mchk.mcic);
+ vcpu->stat.deliver_machine_check++;
rc = __write_machine_check(vcpu, &mchk);
}
return rc;
@@ -562,17 +671,21 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- int rc;
+ int rc = 0;
VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
vcpu->stat.deliver_restart_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
- rc = write_guest_lc(vcpu,
- offsetof(struct lowcore, restart_old_psw),
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_RESTART;
+ } else {
+ rc = write_guest_lc(vcpu,
+ offsetof(struct lowcore, restart_old_psw),
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ }
clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
@@ -614,6 +727,12 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
vcpu->stat.deliver_emergency_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
cpu_addr, 0);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_EMERGENCY_SIG;
+ vcpu->arch.sie_block->extcpuaddr = cpu_addr;
+ return 0;
+ }
rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
(u16 *)__LC_EXT_INT_CODE);
@@ -642,6 +761,12 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_INT_EXTERNAL_CALL,
extcall.code, 0);
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_EXTERNAL_CALL;
+ vcpu->arch.sie_block->extcpuaddr = extcall.code;
+ return 0;
+ }
rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
(u16 *)__LC_EXT_INT_CODE);
@@ -653,6 +778,21 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
return rc ? -EFAULT : 0;
}
+static int __deliver_prog_pv(struct kvm_vcpu *vcpu, u16 code)
+{
+ switch (code) {
+ case PGM_SPECIFICATION:
+ vcpu->arch.sie_block->iictl = IICTL_CODE_SPECIFICATION;
+ break;
+ case PGM_OPERAND:
+ vcpu->arch.sie_block->iictl = IICTL_CODE_OPERAND;
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -669,10 +809,14 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
pgm_info.code, ilen);
- vcpu->stat.deliver_program_int++;
+ vcpu->stat.deliver_program++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
+ /* PER is handled by the ultravisor */
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ return __deliver_prog_pv(vcpu, pgm_info.code & ~PGM_PER);
+
switch (pgm_info.code & ~PGM_PER) {
case PGM_AFX_TRANSLATION:
case PGM_ASX_TRANSLATION:
@@ -684,7 +828,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
case PGM_PRIMARY_AUTHORITY:
case PGM_SECONDARY_AUTHORITY:
nullifying = true;
- /* fall through */
+ fallthrough;
case PGM_SPACE_SWITCH:
rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
@@ -758,9 +902,8 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
/* bit 1+2 of the target are the ilc, so we can directly use ilen */
rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
- (u64 *) __LC_LAST_BREAK);
- rc |= put_guest_lc(vcpu, pgm_info.code,
- (u16 *)__LC_PGM_INT_CODE);
+ (u64 *) __LC_PGM_LAST_BREAK);
+ rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_CODE);
rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW,
@@ -768,20 +911,49 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
return rc ? -EFAULT : 0;
}
+#define SCCB_MASK 0xFFFFFFF8
+#define SCCB_EVENT_PENDING 0x3
+
+static int write_sclp(struct kvm_vcpu *vcpu, u32 parm)
+{
+ int rc;
+
+ if (kvm_s390_pv_cpu_get_handle(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_EXT;
+ vcpu->arch.sie_block->eic = EXT_IRQ_SERVICE_SIG;
+ vcpu->arch.sie_block->eiparams = parm;
+ return 0;
+ }
+
+ rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
+ rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
+ rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ rc |= put_guest_lc(vcpu, parm,
+ (u32 *)__LC_EXT_PARAMS);
+
+ return rc ? -EFAULT : 0;
+}
+
static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_ext_info ext;
- int rc = 0;
spin_lock(&fi->lock);
- if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
+ if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs) ||
+ !(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
spin_unlock(&fi->lock);
return 0;
}
ext = fi->srv_signal;
memset(&fi->srv_signal, 0, sizeof(ext));
clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
+ clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs);
+ if (kvm_s390_pv_cpu_is_protected(vcpu))
+ set_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs);
spin_unlock(&fi->lock);
VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
@@ -790,16 +962,31 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
ext.ext_params, 0);
- rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
- rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
- rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
- &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= put_guest_lc(vcpu, ext.ext_params,
- (u32 *)__LC_EXT_PARAMS);
+ return write_sclp(vcpu, ext.ext_params);
+}
- return rc ? -EFAULT : 0;
+static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct kvm_s390_ext_info ext;
+
+ spin_lock(&fi->lock);
+ if (!(test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs))) {
+ spin_unlock(&fi->lock);
+ return 0;
+ }
+ ext = fi->srv_signal;
+ /* only clear the event bits */
+ fi->srv_signal.ext_params &= ~SCCB_EVENT_PENDING;
+ clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs);
+ spin_unlock(&fi->lock);
+
+ VCPU_EVENT(vcpu, 4, "%s", "deliver: sclp parameter event");
+ vcpu->stat.deliver_service_signal++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
+ ext.ext_params, 0);
+
+ return write_sclp(vcpu, ext.ext_params & SCCB_EVENT_PENDING);
}
static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
@@ -858,7 +1045,7 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 4,
"deliver: virtio parm: 0x%x,parm64: 0x%llx",
inti->ext.ext_params, inti->ext.ext_params2);
- vcpu->stat.deliver_virtio_interrupt++;
+ vcpu->stat.deliver_virtio++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
inti->type,
inti->ext.ext_params,
@@ -890,18 +1077,48 @@ 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;
+
+ if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+ vcpu->arch.sie_block->iictl = IICTL_CODE_IO;
+ vcpu->arch.sie_block->subchannel_id = io->subchannel_id;
+ vcpu->arch.sie_block->subchannel_nr = io->subchannel_nr;
+ vcpu->arch.sie_block->io_int_parm = io->io_int_parm;
+ vcpu->arch.sie_block->io_int_word = io->io_int_word;
+ return 0;
+ }
+
+ 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_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int;
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 - IRQ_PEND_IO_ISC_0];
+ 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);
@@ -914,7 +1131,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
inti->io.subchannel_id >> 1 & 0x3,
inti->io.subchannel_nr);
- vcpu->stat.deliver_io_int++;
+ vcpu->stat.deliver_io++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
inti->type,
((__u32)inti->io.subchannel_id << 16) |
@@ -929,50 +1146,38 @@ 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 (gi->origin && gisa_tac_ipm_gisc(gi->origin, 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++;
+ 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);
-
-static const deliver_irq_t deliver_irq_funcs[] = {
- [IRQ_PEND_MCHK_EX] = __deliver_machine_check,
- [IRQ_PEND_MCHK_REP] = __deliver_machine_check,
- [IRQ_PEND_PROG] = __deliver_prog,
- [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal,
- [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call,
- [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc,
- [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer,
- [IRQ_PEND_RESTART] = __deliver_restart,
- [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix,
- [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init,
- [IRQ_PEND_EXT_SERVICE] = __deliver_service,
- [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done,
- [IRQ_PEND_VIRTIO] = __deliver_virtio,
-};
-
/* Check whether an external call is pending (deliverable or not) */
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- if (!sclp.has_sigpif)
+ if (!kvm_s390_use_sca_entries())
return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
return sca_ext_call_pending(vcpu, NULL);
@@ -989,7 +1194,7 @@ int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
/* external call pending and deliverable */
if (kvm_s390_ext_call_pending(vcpu) &&
!psw_extint_disabled(vcpu) &&
- (vcpu->arch.sie_block->gcr[0] & 0x2000ul))
+ (vcpu->arch.sie_block->gcr[0] & CR0_EXTERNAL_CALL_SUBMASK))
return 1;
if (!exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
@@ -1004,20 +1209,26 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
{
- u64 now, cputm, sltime = 0;
+ const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+ const u64 ckc = vcpu->arch.sie_block->ckc;
+ u64 cputm, sltime = 0;
if (ckc_interrupts_enabled(vcpu)) {
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
- /* already expired or overflow? */
- if (!sltime || vcpu->arch.sie_block->ckc <= now)
+ if (vcpu->arch.sie_block->gcr[0] & CR0_CLOCK_COMPARATOR_SIGN) {
+ if ((s64)now < (s64)ckc)
+ sltime = tod_to_ns((s64)ckc - (s64)now);
+ } else if (now < ckc) {
+ sltime = tod_to_ns(ckc - now);
+ }
+ /* already expired */
+ if (!sltime)
return 0;
if (cpu_timer_interrupts_enabled(vcpu)) {
cputm = kvm_s390_get_cpu_timer(vcpu);
/* already expired? */
if (cputm >> 63)
return 0;
- return min(sltime, tod_to_ns(cputm));
+ return min_t(u64, sltime, tod_to_ns(cputm));
}
} else if (cpu_timer_interrupts_enabled(vcpu)) {
sltime = kvm_s390_get_cpu_timer(vcpu);
@@ -1030,6 +1241,7 @@ static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
+ struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int;
u64 sltime;
vcpu->stat.exit_wait_state++;
@@ -1043,6 +1255,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
return -EOPNOTSUPP; /* disabled wait */
}
+ if (gi->origin &&
+ (gisa_get_ipm_or_restore_iam(gi) &
+ vcpu->arch.sie_block->gcr[6] >> 24))
+ return 0;
+
if (!ckc_interrupts_enabled(vcpu) &&
!cpu_timer_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
@@ -1058,10 +1275,12 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL);
VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
no_timer:
- srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- kvm_vcpu_block(vcpu);
+ kvm_vcpu_srcu_read_unlock(vcpu);
+ vcpu->kvm->arch.float_int.last_sleep_cpu = vcpu->vcpu_idx;
+ kvm_vcpu_halt(vcpu);
+ vcpu->valid_wakeup = false;
__unset_cpu_idle(vcpu);
- vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ kvm_vcpu_srcu_read_lock(vcpu);
hrtimer_cancel(&vcpu->arch.ckc_timer);
return 0;
@@ -1069,22 +1288,11 @@ no_timer:
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- /*
- * We cannot move this into the if, as the CPU might be already
- * in kvm_vcpu_block without having the waitqueue set (polling)
- */
vcpu->valid_wakeup = true;
- if (swait_active(&vcpu->wq)) {
- /*
- * The vcpu gave up the cpu voluntarily, mark it as a good
- * yield-candidate.
- */
- vcpu->preempted = true;
- swake_up(&vcpu->wq);
- vcpu->stat.halt_wakeup++;
- }
+ kvm_vcpu_wake_up(vcpu);
+
/*
- * The VCPU might not be sleeping but is executing the VSIE. Let's
+ * The VCPU might not be sleeping but rather executing VSIE. Let's
* kick it, so it leaves the SIE to process the request.
*/
kvm_s390_vsie_kick(vcpu);
@@ -1124,8 +1332,8 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- deliver_irq_t func;
int rc = 0;
+ bool delivered = false;
unsigned long irq_type;
unsigned long irqs;
@@ -1142,19 +1350,76 @@ 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);
- if (is_ioirq(irq_type)) {
+ /* bits are in the reverse order of interrupt priority */
+ irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT);
+ switch (irq_type) {
+ case IRQ_PEND_IO_ISC_0:
+ case IRQ_PEND_IO_ISC_1:
+ case IRQ_PEND_IO_ISC_2:
+ case IRQ_PEND_IO_ISC_3:
+ case IRQ_PEND_IO_ISC_4:
+ case IRQ_PEND_IO_ISC_5:
+ case IRQ_PEND_IO_ISC_6:
+ case IRQ_PEND_IO_ISC_7:
rc = __deliver_io(vcpu, irq_type);
- } else {
- func = deliver_irq_funcs[irq_type];
- if (!func) {
- WARN_ON_ONCE(func == NULL);
- clear_bit(irq_type, &li->pending_irqs);
- continue;
- }
- rc = func(vcpu);
+ break;
+ case IRQ_PEND_MCHK_EX:
+ case IRQ_PEND_MCHK_REP:
+ rc = __deliver_machine_check(vcpu);
+ break;
+ case IRQ_PEND_PROG:
+ rc = __deliver_prog(vcpu);
+ break;
+ case IRQ_PEND_EXT_EMERGENCY:
+ rc = __deliver_emergency_signal(vcpu);
+ break;
+ case IRQ_PEND_EXT_EXTERNAL:
+ rc = __deliver_external_call(vcpu);
+ break;
+ case IRQ_PEND_EXT_CLOCK_COMP:
+ rc = __deliver_ckc(vcpu);
+ break;
+ case IRQ_PEND_EXT_CPU_TIMER:
+ rc = __deliver_cpu_timer(vcpu);
+ break;
+ case IRQ_PEND_RESTART:
+ rc = __deliver_restart(vcpu);
+ break;
+ case IRQ_PEND_SET_PREFIX:
+ rc = __deliver_set_prefix(vcpu);
+ break;
+ case IRQ_PEND_PFAULT_INIT:
+ rc = __deliver_pfault_init(vcpu);
+ break;
+ case IRQ_PEND_EXT_SERVICE:
+ rc = __deliver_service(vcpu);
+ break;
+ case IRQ_PEND_EXT_SERVICE_EV:
+ rc = __deliver_service_ev(vcpu);
+ break;
+ case IRQ_PEND_PFAULT_DONE:
+ rc = __deliver_pfault_done(vcpu);
+ break;
+ case IRQ_PEND_VIRTIO:
+ rc = __deliver_virtio(vcpu);
+ break;
+ default:
+ WARN_ONCE(1, "Unknown pending irq type %ld", irq_type);
+ clear_bit(irq_type, &li->pending_irqs);
}
+ delivered |= !rc;
+ }
+
+ /*
+ * We delivered at least one interrupt and modified the PC. Force a
+ * singlestep event now.
+ */
+ if (delivered && guestdbg_sstep_enabled(vcpu)) {
+ struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch;
+
+ debug_exit->addr = vcpu->arch.sie_block->gpsw.addr;
+ debug_exit->type = KVM_SINGLESTEP;
+ vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
}
set_intercept_indicators(vcpu);
@@ -1166,6 +1431,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ vcpu->stat.inject_program++;
VCPU_EVENT(vcpu, 3, "inject: program irq code 0x%x", irq->u.pgm.code);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
irq->u.pgm.code, 0);
@@ -1207,6 +1473,7 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ vcpu->stat.inject_pfault_init++;
VCPU_EVENT(vcpu, 4, "inject: pfault init parameter block at 0x%llx",
irq->u.ext.ext_params2);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
@@ -1215,7 +1482,7 @@ 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;
}
@@ -1225,6 +1492,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
uint16_t src_id = irq->u.extcall.code;
+ vcpu->stat.inject_external_call++;
VCPU_EVENT(vcpu, 4, "inject: external call source-cpu:%u",
src_id);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
@@ -1234,13 +1502,13 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
return -EINVAL;
- if (sclp.has_sigpif)
+ if (kvm_s390_use_sca_entries() && !kvm_s390_pv_cpu_get_handle(vcpu))
return sca_inject_ext_call(vcpu, src_id);
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;
}
@@ -1249,6 +1517,7 @@ static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
+ vcpu->stat.inject_set_prefix++;
VCPU_EVENT(vcpu, 3, "inject: set prefix to %x",
irq->u.prefix.address);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
@@ -1269,6 +1538,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
struct kvm_s390_stop_info *stop = &li->irq.stop;
int rc = 0;
+ vcpu->stat.inject_stop_signal++;
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0);
if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
@@ -1284,15 +1554,15 @@ 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;
}
-static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
- struct kvm_s390_irq *irq)
+static int __inject_sigp_restart(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ vcpu->stat.inject_restart++;
VCPU_EVENT(vcpu, 3, "%s", "inject: restart int");
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
@@ -1305,6 +1575,7 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ vcpu->stat.inject_emergency_signal++;
VCPU_EVENT(vcpu, 4, "inject: emergency from cpu %u",
irq->u.emerg.code);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
@@ -1316,7 +1587,7 @@ 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;
}
@@ -1325,6 +1596,7 @@ static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
+ vcpu->stat.inject_mchk++;
VCPU_EVENT(vcpu, 3, "inject: machine check mcic 0x%llx",
irq->u.mchk.mcic);
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
@@ -1355,12 +1627,13 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ vcpu->stat.inject_ckc++;
VCPU_EVENT(vcpu, 3, "%s", "inject: clock comparator external");
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
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;
}
@@ -1368,12 +1641,13 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ vcpu->stat.inject_cputm++;
VCPU_EVENT(vcpu, 3, "%s", "inject: cpu timer external");
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
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;
}
@@ -1395,7 +1669,7 @@ static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm,
list_del_init(&iter->list);
fi->counters[FIRQ_CNTR_IO] -= 1;
if (list_empty(isc_list))
- clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
+ clear_bit(isc_to_irq_type(isc), &fi->pending_irqs);
spin_unlock(&fi->lock);
return iter;
}
@@ -1403,33 +1677,104 @@ 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)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ unsigned long active_mask;
+ int isc;
+
+ if (schid)
+ goto out;
+ if (!gi->origin)
+ goto out;
+
+ active_mask = (isc_mask & gisa_get_ipm(gi->origin) << 24) << 32;
+ while (active_mask) {
+ isc = __fls(active_mask) ^ (BITS_PER_LONG - 1);
+ if (gisa_tac_ipm_gisc(gi->origin, 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_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ 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 */
+ gisa_set_ipm_gisc(gi->origin, isc);
+ goto out;
}
+gisa_out:
+ tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT);
+ 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
+ gisa_set_ipm_gisc(gi->origin, isc);
+out:
return inti;
}
-#define SCCB_MASK 0xFFFFFFF8
-#define SCCB_EVENT_PENDING 0x3
-
static int __inject_service(struct kvm *kvm,
struct kvm_s390_interrupt_info *inti)
{
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ kvm->stat.inject_service_signal++;
spin_lock(&fi->lock);
fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING;
+
+ /* We always allow events, track them separately from the sccb ints */
+ if (fi->srv_signal.ext_params & SCCB_EVENT_PENDING)
+ set_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs);
+
/*
* Early versions of the QEMU s390 bios will inject several
* service interrupts after another without handling a
@@ -1453,6 +1798,7 @@ static int __inject_virtio(struct kvm *kvm,
{
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ kvm->stat.inject_virtio++;
spin_lock(&fi->lock);
if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) {
spin_unlock(&fi->lock);
@@ -1470,6 +1816,7 @@ static int __inject_pfault_done(struct kvm *kvm,
{
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ kvm->stat.inject_pfault_done++;
spin_lock(&fi->lock);
if (fi->counters[FIRQ_CNTR_PFAULT] >=
(ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) {
@@ -1489,6 +1836,7 @@ static int __inject_float_mchk(struct kvm *kvm,
{
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
+ kvm->stat.inject_float_mchk++;
spin_lock(&fi->lock);
fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS);
fi->mchk.mcic |= inti->mchk.mcic;
@@ -1500,10 +1848,27 @@ static int __inject_float_mchk(struct kvm *kvm,
static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_s390_float_interrupt *fi;
struct list_head *list;
int isc;
+ kvm->stat.inject_io++;
+ isc = int_word_to_isc(inti->io.io_int_word);
+
+ /*
+ * We do not use the lock checking variant as this is just a
+ * performance optimization and we do not hold the lock here.
+ * This is ok as the code will pick interrupts from both "lists"
+ * for delivery.
+ */
+ if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) {
+ VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc);
+ gisa_set_ipm_gisc(gi->origin, 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) {
@@ -1519,10 +1884,9 @@ 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(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
+ set_bit(isc_to_irq_type(isc), &fi->pending_irqs);
spin_unlock(&fi->lock);
return 0;
}
@@ -1532,8 +1896,6 @@ 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;
@@ -1541,34 +1903,31 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
if (!online_vcpus)
return;
- /* find idle VCPUs first, then round robin */
- sigcpu = find_first_bit(fi->idle_mask, online_vcpus);
- if (sigcpu == online_vcpus) {
- do {
- sigcpu = fi->next_rr_cpu;
- fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus;
- /* avoid endless loops if all vcpus are stopped */
- if (nr_tries++ >= online_vcpus)
- return;
- } while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu)));
+ for (sigcpu = kvm->arch.float_int.last_sleep_cpu; ; sigcpu++) {
+ sigcpu %= online_vcpus;
+ dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
+ if (!is_vcpu_stopped(dst_vcpu))
+ break;
+ /* avoid endless loops if all vcpus are stopped */
+ if (nr_tries++ >= online_vcpus)
+ return;
}
- 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);
+ if (!(type & KVM_S390_INT_IO_AI_MASK &&
+ kvm->arch.gisa_int.origin) ||
+ kvm_s390_pv_cpu_get_handle(dst_vcpu))
+ 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);
}
@@ -1609,7 +1968,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
struct kvm_s390_interrupt_info *inti;
int rc;
- inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT);
if (!inti)
return -ENOMEM;
@@ -1688,6 +2047,16 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
case KVM_S390_MCHK:
irq->u.mchk.mcic = s390int->parm64;
break;
+ case KVM_S390_INT_PFAULT_INIT:
+ irq->u.ext.ext_params = s390int->parm;
+ irq->u.ext.ext_params2 = s390int->parm64;
+ break;
+ case KVM_S390_RESTART:
+ case KVM_S390_INT_CLOCK_COMP:
+ case KVM_S390_INT_CPU_TIMER:
+ break;
+ default:
+ return -EINVAL;
}
return 0;
}
@@ -1699,6 +2068,13 @@ int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu)
return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
}
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+ return test_bit(IRQ_PEND_RESTART, &li->pending_irqs);
+}
+
void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1724,7 +2100,7 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
rc = __inject_sigp_stop(vcpu, irq);
break;
case KVM_S390_RESTART:
- rc = __inject_sigp_restart(vcpu, irq);
+ rc = __inject_sigp_restart(vcpu);
break;
case KVM_S390_INT_CLOCK_COMP:
rc = __inject_ckc(vcpu);
@@ -1798,6 +2174,10 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
int i;
+ mutex_lock(&kvm->lock);
+ if (!kvm_s390_pv_is_protected(kvm))
+ fi->masked_irqs = 0;
+ mutex_unlock(&kvm->lock);
spin_lock(&fi->lock);
fi->pending_irqs = 0;
memset(&fi->srv_signal, 0, sizeof(fi->srv_signal));
@@ -1807,10 +2187,12 @@ 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)
{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_s390_interrupt_info *inti;
struct kvm_s390_float_interrupt *fi;
struct kvm_s390_irq *buf;
@@ -1834,6 +2216,21 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
max_irqs = len / sizeof(struct kvm_s390_irq);
+ if (gi->origin && gisa_get_ipm(gi->origin)) {
+ for (i = 0; i <= MAX_ISC; i++) {
+ if (n == max_irqs) {
+ /* signal userspace to try again */
+ ret = -ENOMEM;
+ goto out_nolock;
+ }
+ if (gisa_tac_ipm_gisc(gi->origin, 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++) {
@@ -1847,7 +2244,8 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
n++;
}
}
- if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) {
+ if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs) ||
+ test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs)) {
if (n == max_irqs) {
/* signal userspace to try again */
ret = -ENOMEM;
@@ -1872,6 +2270,7 @@ 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;
@@ -1890,7 +2289,7 @@ static int flic_ais_mode_get_all(struct kvm *kvm, struct kvm_device_attr *attr)
return -EINVAL;
if (!test_kvm_facility(kvm, 72))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
mutex_lock(&fi->ais_lock);
ais.simm = fi->simm;
@@ -1975,7 +2374,7 @@ static int enqueue_floating_irq(struct kvm_device *dev,
return -EINVAL;
while (len >= sizeof(struct kvm_s390_irq)) {
- inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT);
if (!inti)
return -ENOMEM;
@@ -2000,6 +2399,7 @@ static struct s390_io_adapter *get_io_adapter(struct kvm *kvm, unsigned int id)
{
if (id >= MAX_S390_IO_ADAPTERS)
return NULL;
+ id = array_index_nospec(id, MAX_S390_IO_ADAPTERS);
return kvm->arch.adapters[id];
}
@@ -2013,17 +2413,19 @@ static int register_io_adapter(struct kvm_device *dev,
(void __user *)attr->addr, sizeof(adapter_info)))
return -EFAULT;
- if ((adapter_info.id >= MAX_S390_IO_ADAPTERS) ||
- (dev->kvm->arch.adapters[adapter_info.id] != NULL))
+ if (adapter_info.id >= MAX_S390_IO_ADAPTERS)
+ return -EINVAL;
+
+ adapter_info.id = array_index_nospec(adapter_info.id,
+ MAX_S390_IO_ADAPTERS);
+
+ if (dev->kvm->arch.adapters[adapter_info.id] != NULL)
return -EINVAL;
- adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
+ adapter = kzalloc(sizeof(*adapter), GFP_KERNEL_ACCOUNT);
if (!adapter)
return -ENOMEM;
- INIT_LIST_HEAD(&adapter->maps);
- init_rwsem(&adapter->maps_lock);
- atomic_set(&adapter->nr_maps, 0);
adapter->id = adapter_info.id;
adapter->isc = adapter_info.isc;
adapter->maskable = adapter_info.maskable;
@@ -2048,87 +2450,12 @@ int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked)
return ret;
}
-static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
-{
- struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
- struct s390_map_info *map;
- int ret;
-
- if (!adapter || !addr)
- return -EINVAL;
-
- map = kzalloc(sizeof(*map), GFP_KERNEL);
- if (!map) {
- ret = -ENOMEM;
- goto out;
- }
- INIT_LIST_HEAD(&map->list);
- map->guest_addr = addr;
- map->addr = gmap_translate(kvm->arch.gmap, addr);
- if (map->addr == -EFAULT) {
- ret = -EFAULT;
- goto out;
- }
- ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
- if (ret < 0)
- goto out;
- BUG_ON(ret != 1);
- down_write(&adapter->maps_lock);
- if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) {
- list_add_tail(&map->list, &adapter->maps);
- ret = 0;
- } else {
- put_page(map->page);
- ret = -EINVAL;
- }
- up_write(&adapter->maps_lock);
-out:
- if (ret)
- kfree(map);
- return ret;
-}
-
-static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
-{
- struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
- struct s390_map_info *map, *tmp;
- int found = 0;
-
- if (!adapter || !addr)
- return -EINVAL;
-
- down_write(&adapter->maps_lock);
- list_for_each_entry_safe(map, tmp, &adapter->maps, list) {
- if (map->guest_addr == addr) {
- found = 1;
- atomic_dec(&adapter->nr_maps);
- list_del(&map->list);
- put_page(map->page);
- kfree(map);
- break;
- }
- }
- up_write(&adapter->maps_lock);
-
- return found ? 0 : -EINVAL;
-}
-
void kvm_s390_destroy_adapters(struct kvm *kvm)
{
int i;
- struct s390_map_info *map, *tmp;
- for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) {
- if (!kvm->arch.adapters[i])
- continue;
- list_for_each_entry_safe(map, tmp,
- &kvm->arch.adapters[i]->maps, list) {
- list_del(&map->list);
- put_page(map->page);
- kfree(map);
- }
+ for (i = 0; i < MAX_S390_IO_ADAPTERS; i++)
kfree(kvm->arch.adapters[i]);
- }
}
static int modify_io_adapter(struct kvm_device *dev,
@@ -2150,11 +2477,14 @@ static int modify_io_adapter(struct kvm_device *dev,
if (ret > 0)
ret = 0;
break;
+ /*
+ * The following operations are no longer needed and therefore no-ops.
+ * The gpa to hva translation is done when an IRQ route is set up. The
+ * set_irq code uses get_user_pages_remote() to do the actual write.
+ */
case KVM_S390_IO_ADAPTER_MAP:
- ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr);
- break;
case KVM_S390_IO_ADAPTER_UNMAP:
- ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr);
+ ret = 0;
break;
default:
ret = -EINVAL;
@@ -2175,6 +2505,8 @@ static int clear_io_irq(struct kvm *kvm, struct kvm_device_attr *attr)
return -EINVAL;
if (copy_from_user(&schid, (void __user *) attr->addr, sizeof(schid)))
return -EFAULT;
+ if (!schid)
+ return -EINVAL;
kfree(kvm_s390_get_io_int(kvm, isc_mask, schid));
/*
* If userspace is conforming to the architecture, we can have at most
@@ -2191,7 +2523,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr)
int ret = 0;
if (!test_kvm_facility(kvm, 72))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
return -EFAULT;
@@ -2230,7 +2562,7 @@ 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;
@@ -2271,7 +2603,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr)
struct kvm_s390_ais_all ais;
if (!test_kvm_facility(kvm, 72))
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais)))
return -EFAULT;
@@ -2287,7 +2619,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr)
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
int r = 0;
- unsigned int i;
+ unsigned long i;
struct kvm_vcpu *vcpu;
switch (attr->group) {
@@ -2298,9 +2630,13 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
kvm_s390_clear_float_irqs(dev->kvm);
break;
case KVM_DEV_FLIC_APF_ENABLE:
+ if (kvm_is_ucontrol(dev->kvm))
+ return -EINVAL;
dev->kvm->arch.gmap->pfault_enabled = 1;
break;
case KVM_DEV_FLIC_APF_DISABLE_WAIT:
+ if (kvm_is_ucontrol(dev->kvm))
+ return -EINVAL;
dev->kvm->arch.gmap->pfault_enabled = 0;
/*
* Make sure no async faults are in transition when
@@ -2391,19 +2727,22 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
}
-static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter,
- u64 addr)
+static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
{
- struct s390_map_info *map;
+ struct mm_struct *mm = kvm->mm;
+ struct page *page = NULL;
+ int locked = 1;
- if (!adapter)
- return NULL;
-
- list_for_each_entry(map, &adapter->maps, list) {
- if (map->guest_addr == addr)
- return map;
+ if (mmget_not_zero(mm)) {
+ mmap_read_lock(mm);
+ get_user_pages_remote(mm, uaddr, 1, FOLL_WRITE,
+ &page, &locked);
+ if (locked)
+ mmap_read_unlock(mm);
+ mmput(mm);
}
- return NULL;
+
+ return page;
}
static int adapter_indicators_set(struct kvm *kvm,
@@ -2412,30 +2751,35 @@ static int adapter_indicators_set(struct kvm *kvm,
{
unsigned long bit;
int summary_set, idx;
- struct s390_map_info *info;
+ struct page *ind_page, *summary_page;
void *map;
- info = get_map_info(adapter, adapter_int->ind_addr);
- if (!info)
+ ind_page = get_map_page(kvm, adapter_int->ind_addr);
+ if (!ind_page)
return -1;
- map = page_address(info->page);
- bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap);
- set_bit(bit, map);
- idx = srcu_read_lock(&kvm->srcu);
- mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
- set_page_dirty_lock(info->page);
- info = get_map_info(adapter, adapter_int->summary_addr);
- if (!info) {
- srcu_read_unlock(&kvm->srcu, idx);
+ summary_page = get_map_page(kvm, adapter_int->summary_addr);
+ if (!summary_page) {
+ put_page(ind_page);
return -1;
}
- map = page_address(info->page);
- bit = get_ind_bit(info->addr, adapter_int->summary_offset,
- adapter->swap);
+
+ idx = srcu_read_lock(&kvm->srcu);
+ map = page_address(ind_page);
+ bit = get_ind_bit(adapter_int->ind_addr,
+ adapter_int->ind_offset, adapter->swap);
+ set_bit(bit, map);
+ mark_page_dirty(kvm, adapter_int->ind_addr >> PAGE_SHIFT);
+ set_page_dirty_lock(ind_page);
+ map = page_address(summary_page);
+ bit = get_ind_bit(adapter_int->summary_addr,
+ adapter_int->summary_offset, adapter->swap);
summary_set = test_and_set_bit(bit, map);
- mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
- set_page_dirty_lock(info->page);
+ mark_page_dirty(kvm, adapter_int->summary_addr >> PAGE_SHIFT);
+ set_page_dirty_lock(summary_page);
srcu_read_unlock(&kvm->srcu, idx);
+
+ put_page(ind_page);
+ put_page(summary_page);
return summary_set ? 0 : 1;
}
@@ -2457,9 +2801,7 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
adapter = get_io_adapter(kvm, e->adapter.adapter_id);
if (!adapter)
return -1;
- down_read(&adapter->maps_lock);
ret = adapter_indicators_set(kvm, adapter, &e->adapter);
- up_read(&adapter->maps_lock);
if ((ret > 0) && !adapter->masked) {
ret = kvm_s390_inject_airq(kvm, adapter);
if (ret == 0)
@@ -2479,14 +2821,15 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
struct kvm_s390_mchk_info *mchk;
union mci mci;
__u64 cr14 = 0; /* upper bits are not used */
+ int rc;
mci.val = mcck_info->mcic;
if (mci.sr)
- cr14 |= MCCK_CR14_RECOVERY_SUB_MASK;
+ cr14 |= CR14_RECOVERY_SUBMASK;
if (mci.dg)
- cr14 |= MCCK_CR14_DEGRAD_SUB_MASK;
+ cr14 |= CR14_DEGRADATION_SUBMASK;
if (mci.w)
- cr14 |= MCCK_CR14_WARN_SUB_MASK;
+ cr14 |= CR14_WARNING_SUBMASK;
mchk = mci.ck ? &inti.mchk : &irq.u.mchk;
mchk->cr14 = cr14;
@@ -2496,35 +2839,45 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
if (mci.ck) {
/* Inject the floating machine check */
inti.type = KVM_S390_MCHK;
- WARN_ON_ONCE(__inject_vm(vcpu->kvm, &inti));
+ rc = __inject_vm(vcpu->kvm, &inti);
} else {
/* Inject the machine check to specified vcpu */
irq.type = KVM_S390_MCHK;
- WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
+ rc = kvm_s390_inject_vcpu(vcpu, &irq);
}
+ WARN_ON_ONCE(rc);
}
int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
- int ret;
+ u64 uaddr_s, uaddr_i;
+ int idx;
switch (ue->type) {
+ /* we store the userspace addresses instead of the guest addresses */
case KVM_IRQ_ROUTING_S390_ADAPTER:
+ if (kvm_is_ucontrol(kvm))
+ return -EINVAL;
e->set = set_adapter_int;
- e->adapter.summary_addr = ue->u.adapter.summary_addr;
- e->adapter.ind_addr = ue->u.adapter.ind_addr;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr);
+ uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i))
+ return -EFAULT;
+ e->adapter.summary_addr = uaddr_s;
+ e->adapter.ind_addr = uaddr_i;
e->adapter.summary_offset = ue->u.adapter.summary_offset;
e->adapter.ind_offset = ue->u.adapter.ind_offset;
e->adapter.adapter_id = ue->u.adapter.adapter_id;
- ret = 0;
- break;
+ return 0;
default:
- ret = -EINVAL;
+ return -EINVAL;
}
-
- return ret;
}
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
@@ -2618,7 +2971,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li,
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
{
int scn;
- unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+ DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
unsigned long pending_irqs;
struct kvm_s390_irq irq;
@@ -2670,3 +3023,417 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
return n;
}
+
+static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
+{
+ int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ struct kvm_vcpu *vcpu;
+ u8 vcpu_isc_mask;
+
+ for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
+ vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+ if (psw_ioint_disabled(vcpu))
+ continue;
+ vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+ if (deliverable_mask & vcpu_isc_mask) {
+ /* lately kicked but not yet running */
+ if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
+ return;
+ kvm_s390_vcpu_wakeup(vcpu);
+ return;
+ }
+ }
+}
+
+static enum hrtimer_restart gisa_vcpu_kicker(struct hrtimer *timer)
+{
+ struct kvm_s390_gisa_interrupt *gi =
+ container_of(timer, struct kvm_s390_gisa_interrupt, timer);
+ struct kvm *kvm =
+ container_of(gi->origin, struct sie_page2, gisa)->kvm;
+ u8 pending_mask;
+
+ pending_mask = gisa_get_ipm_or_restore_iam(gi);
+ if (pending_mask) {
+ __airqs_kick_single_vcpu(kvm, pending_mask);
+ hrtimer_forward_now(timer, ns_to_ktime(gi->expires));
+ return HRTIMER_RESTART;
+ }
+
+ return HRTIMER_NORESTART;
+}
+
+#define NULL_GISA_ADDR 0x00000000UL
+#define NONE_GISA_ADDR 0x00000001UL
+#define GISA_ADDR_MASK 0xfffff000UL
+
+static void process_gib_alert_list(void)
+{
+ struct kvm_s390_gisa_interrupt *gi;
+ u32 final, gisa_phys, origin = 0UL;
+ struct kvm_s390_gisa *gisa;
+ struct kvm *kvm;
+
+ do {
+ /*
+ * If the NONE_GISA_ADDR is still stored in the alert list
+ * origin, we will leave the outer loop. No further GISA has
+ * been added to the alert list by millicode while processing
+ * the current alert list.
+ */
+ final = (origin & NONE_GISA_ADDR);
+ /*
+ * Cut off the alert list and store the NONE_GISA_ADDR in the
+ * alert list origin to avoid further GAL interruptions.
+ * A new alert list can be build up by millicode in parallel
+ * for guests not in the yet cut-off alert list. When in the
+ * final loop, store the NULL_GISA_ADDR instead. This will re-
+ * enable GAL interruptions on the host again.
+ */
+ origin = xchg(&gib->alert_list_origin,
+ (!final) ? NONE_GISA_ADDR : NULL_GISA_ADDR);
+ /*
+ * Loop through the just cut-off alert list and start the
+ * gisa timers to kick idle vcpus to consume the pending
+ * interruptions asap.
+ */
+ while (origin & GISA_ADDR_MASK) {
+ gisa_phys = origin;
+ gisa = phys_to_virt(gisa_phys);
+ origin = gisa->next_alert;
+ gisa->next_alert = gisa_phys;
+ kvm = container_of(gisa, struct sie_page2, gisa)->kvm;
+ gi = &kvm->arch.gisa_int;
+ if (hrtimer_active(&gi->timer))
+ hrtimer_cancel(&gi->timer);
+ hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL);
+ }
+ } while (!final);
+
+}
+
+void kvm_s390_gisa_clear(struct kvm *kvm)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!gi->origin)
+ return;
+ gisa_clear_ipm(gi->origin);
+ VM_EVENT(kvm, 3, "gisa 0x%p cleared", gi->origin);
+}
+
+void kvm_s390_gisa_init(struct kvm *kvm)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!css_general_characteristics.aiv)
+ return;
+ gi->origin = &kvm->arch.sie_page2->gisa;
+ gi->alert.mask = 0;
+ spin_lock_init(&gi->alert.ref_lock);
+ gi->expires = 50 * 1000; /* 50 usec */
+ hrtimer_setup(&gi->timer, gisa_vcpu_kicker, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ memset(gi->origin, 0, sizeof(struct kvm_s390_gisa));
+ gi->origin->next_alert = (u32)virt_to_phys(gi->origin);
+ VM_EVENT(kvm, 3, "gisa 0x%p initialized", gi->origin);
+}
+
+void kvm_s390_gisa_enable(struct kvm *kvm)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+ u32 gisa_desc;
+
+ if (gi->origin)
+ return;
+ kvm_s390_gisa_init(kvm);
+ gisa_desc = kvm_s390_get_gisa_desc(kvm);
+ if (!gisa_desc)
+ return;
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ mutex_lock(&vcpu->mutex);
+ vcpu->arch.sie_block->gd = gisa_desc;
+ 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);
+ mutex_unlock(&vcpu->mutex);
+ }
+}
+
+void kvm_s390_gisa_destroy(struct kvm *kvm)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ struct kvm_s390_gisa *gisa = gi->origin;
+
+ if (!gi->origin)
+ return;
+ WARN(gi->alert.mask != 0x00,
+ "unexpected non zero alert.mask 0x%02x",
+ gi->alert.mask);
+ gi->alert.mask = 0x00;
+ if (gisa_set_iam(gi->origin, gi->alert.mask))
+ process_gib_alert_list();
+ hrtimer_cancel(&gi->timer);
+ gi->origin = NULL;
+ VM_EVENT(kvm, 3, "gisa 0x%p destroyed", gisa);
+}
+
+void kvm_s390_gisa_disable(struct kvm *kvm)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+
+ if (!gi->origin)
+ return;
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ mutex_lock(&vcpu->mutex);
+ vcpu->arch.sie_block->eca &= ~ECA_AIV;
+ vcpu->arch.sie_block->gd = 0U;
+ mutex_unlock(&vcpu->mutex);
+ VCPU_EVENT(vcpu, 3, "AIV disabled for cpu %03u", vcpu->vcpu_id);
+ }
+ kvm_s390_gisa_destroy(kvm);
+}
+
+/**
+ * kvm_s390_gisc_register - register a guest ISC
+ *
+ * @kvm: the kernel vm to work with
+ * @gisc: the guest interruption sub class to register
+ *
+ * The function extends the vm specific alert mask to use.
+ * The effective IAM mask in the GISA is updated as well
+ * in case the GISA is not part of the GIB alert list.
+ * It will be updated latest when the IAM gets restored
+ * by gisa_get_ipm_or_restore_iam().
+ *
+ * Returns: the nonspecific ISC (NISC) the gib alert mechanism
+ * has registered with the channel subsystem.
+ * -ENODEV in case the vm uses no GISA
+ * -ERANGE in case the guest ISC is invalid
+ */
+int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+
+ if (!gi->origin)
+ return -ENODEV;
+ if (gisc > MAX_ISC)
+ return -ERANGE;
+
+ spin_lock(&gi->alert.ref_lock);
+ gi->alert.ref_count[gisc]++;
+ if (gi->alert.ref_count[gisc] == 1) {
+ gi->alert.mask |= 0x80 >> gisc;
+ gisa_set_iam(gi->origin, gi->alert.mask);
+ }
+ spin_unlock(&gi->alert.ref_lock);
+
+ return gib->nisc;
+}
+EXPORT_SYMBOL_GPL(kvm_s390_gisc_register);
+
+/**
+ * kvm_s390_gisc_unregister - unregister a guest ISC
+ *
+ * @kvm: the kernel vm to work with
+ * @gisc: the guest interruption sub class to register
+ *
+ * The function reduces the vm specific alert mask to use.
+ * The effective IAM mask in the GISA is updated as well
+ * in case the GISA is not part of the GIB alert list.
+ * It will be updated latest when the IAM gets restored
+ * by gisa_get_ipm_or_restore_iam().
+ *
+ * Returns: the nonspecific ISC (NISC) the gib alert mechanism
+ * has registered with the channel subsystem.
+ * -ENODEV in case the vm uses no GISA
+ * -ERANGE in case the guest ISC is invalid
+ * -EINVAL in case the guest ISC is not registered
+ */
+int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc)
+{
+ struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
+ int rc = 0;
+
+ if (!gi->origin)
+ return -ENODEV;
+ if (gisc > MAX_ISC)
+ return -ERANGE;
+
+ spin_lock(&gi->alert.ref_lock);
+ if (gi->alert.ref_count[gisc] == 0) {
+ rc = -EINVAL;
+ goto out;
+ }
+ gi->alert.ref_count[gisc]--;
+ if (gi->alert.ref_count[gisc] == 0) {
+ gi->alert.mask &= ~(0x80 >> gisc);
+ gisa_set_iam(gi->origin, gi->alert.mask);
+ }
+out:
+ spin_unlock(&gi->alert.ref_lock);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister);
+
+static void aen_host_forward(unsigned long si)
+{
+ struct kvm_s390_gisa_interrupt *gi;
+ struct zpci_gaite *gaite;
+ struct kvm *kvm;
+
+ gaite = (struct zpci_gaite *)aift->gait +
+ (si * sizeof(struct zpci_gaite));
+ if (gaite->count == 0)
+ return;
+ if (gaite->aisb != 0)
+ set_bit_inv(gaite->aisbo, phys_to_virt(gaite->aisb));
+
+ kvm = kvm_s390_pci_si_to_kvm(aift, si);
+ if (!kvm)
+ return;
+ gi = &kvm->arch.gisa_int;
+
+ if (!(gi->origin->g1.simm & AIS_MODE_MASK(gaite->gisc)) ||
+ !(gi->origin->g1.nimm & AIS_MODE_MASK(gaite->gisc))) {
+ gisa_set_ipm_gisc(gi->origin, gaite->gisc);
+ if (hrtimer_active(&gi->timer))
+ hrtimer_cancel(&gi->timer);
+ hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL);
+ kvm->stat.aen_forward++;
+ }
+}
+
+static void aen_process_gait(u8 isc)
+{
+ bool found = false, first = true;
+ union zpci_sic_iib iib = {{0}};
+ unsigned long si, flags;
+
+ spin_lock_irqsave(&aift->gait_lock, flags);
+
+ if (!aift->gait) {
+ spin_unlock_irqrestore(&aift->gait_lock, flags);
+ return;
+ }
+
+ for (si = 0;;) {
+ /* Scan adapter summary indicator bit vector */
+ si = airq_iv_scan(aift->sbv, si, airq_iv_end(aift->sbv));
+ if (si == -1UL) {
+ if (first || found) {
+ /* Re-enable interrupts. */
+ zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, isc,
+ &iib);
+ first = found = false;
+ } else {
+ /* Interrupts on and all bits processed */
+ break;
+ }
+ found = false;
+ si = 0;
+ /* Scan again after re-enabling interrupts */
+ continue;
+ }
+ found = true;
+ aen_host_forward(si);
+ }
+
+ spin_unlock_irqrestore(&aift->gait_lock, flags);
+}
+
+static void gib_alert_irq_handler(struct airq_struct *airq,
+ struct tpi_info *tpi_info)
+{
+ struct tpi_adapter_info *info = (struct tpi_adapter_info *)tpi_info;
+
+ inc_irq_stat(IRQIO_GAL);
+
+ if ((info->forward || info->error) &&
+ IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
+ aen_process_gait(info->isc);
+ if (info->aism != 0)
+ process_gib_alert_list();
+ } else {
+ process_gib_alert_list();
+ }
+}
+
+static struct airq_struct gib_alert_irq = {
+ .handler = gib_alert_irq_handler,
+};
+
+void kvm_s390_gib_destroy(void)
+{
+ if (!gib)
+ return;
+ if (kvm_s390_pci_interp_allowed() && aift) {
+ mutex_lock(&aift->aift_lock);
+ kvm_s390_pci_aen_exit();
+ mutex_unlock(&aift->aift_lock);
+ }
+ chsc_sgib(0);
+ unregister_adapter_interrupt(&gib_alert_irq);
+ free_page((unsigned long)gib);
+ gib = NULL;
+}
+
+int __init kvm_s390_gib_init(u8 nisc)
+{
+ u32 gib_origin;
+ int rc = 0;
+
+ if (!css_general_characteristics.aiv) {
+ KVM_EVENT(3, "%s", "gib not initialized, no AIV facility");
+ goto out;
+ }
+
+ gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL_ACCOUNT | GFP_DMA);
+ if (!gib) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ gib_alert_irq.isc = nisc;
+ if (register_adapter_interrupt(&gib_alert_irq)) {
+ pr_err("Registering the GIB alert interruption handler failed\n");
+ rc = -EIO;
+ goto out_free_gib;
+ }
+ /* adapter interrupts used for AP (applicable here) don't use the LSI */
+ *gib_alert_irq.lsi_ptr = 0xff;
+
+ gib->nisc = nisc;
+ gib_origin = virt_to_phys(gib);
+ if (chsc_sgib(gib_origin)) {
+ pr_err("Associating the GIB with the AIV facility failed\n");
+ free_page((unsigned long)gib);
+ gib = NULL;
+ rc = -EIO;
+ goto out_unreg_gal;
+ }
+
+ if (kvm_s390_pci_interp_allowed()) {
+ if (kvm_s390_pci_aen_init(nisc)) {
+ pr_err("Initializing AEN for PCI failed\n");
+ rc = -EIO;
+ goto out_unreg_gal;
+ }
+ }
+
+ KVM_EVENT(3, "gib 0x%p (nisc=%d) initialized", gib, gib->nisc);
+ goto out;
+
+out_unreg_gal:
+ unregister_adapter_interrupt(&gib_alert_irq);
+out_free_gib:
+ free_page((unsigned long)gib);
+ gib = NULL;
+out:
+ return rc;
+}
generated by cgit (git 2.34.1) at 2025-12-25 01:14:27 +0000